Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more KVM updates from Paolo Bonzini:
 "PPC:
   - Improvements and bugfixes for secure VM support, giving reduced
     startup time and memory hotplug support.

   - Locking fixes in nested KVM code

   - Increase number of guests supported by HV KVM to 4094

   - Preliminary POWER10 support

  ARM:
   - Split the VHE and nVHE hypervisor code bases, build the EL2 code
     separately, allowing for the VHE code to now be built with
     instrumentation

   - Level-based TLB invalidation support

   - Restructure of the vcpu register storage to accomodate the NV code

   - Pointer Authentication available for guests on nVHE hosts

   - Simplification of the system register table parsing

   - MMU cleanups and fixes

   - A number of post-32bit cleanups and other fixes

  MIPS:
   - compilation fixes

  x86:
   - bugfixes

   - support for the SERIALIZE instruction"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (70 commits)
  KVM: MIPS/VZ: Fix build error caused by 'kvm_run' cleanup
  x86/kvm/hyper-v: Synic default SCONTROL MSR needs to be enabled
  MIPS: KVM: Convert a fallthrough comment to fallthrough
  MIPS: VZ: Only include loongson_regs.h for CPU_LOONGSON64
  x86: Expose SERIALIZE for supported cpuid
  KVM: x86: Don't attempt to load PDPTRs when 64-bit mode is enabled
  KVM: arm64: Move S1PTW S2 fault logic out of io_mem_abort()
  KVM: arm64: Don't skip cache maintenance for read-only memslots
  KVM: arm64: Handle data and instruction external aborts the same way
  KVM: arm64: Rename kvm_vcpu_dabt_isextabt()
  KVM: arm: Add trace name for ARM_NISV
  KVM: arm64: Ensure that all nVHE hyp code is in .hyp.text
  KVM: arm64: Substitute RANDOMIZE_BASE for HARDEN_EL2_VECTORS
  KVM: arm64: Make nVHE ASLR conditional on RANDOMIZE_BASE
  KVM: PPC: Book3S HV: Rework secure mem slot dropping
  KVM: PPC: Book3S HV: Move kvmppc_svm_page_out up
  KVM: PPC: Book3S HV: Migrate hot plugged memory
  KVM: PPC: Book3S HV: In H_SVM_INIT_DONE, migrate remaining normal-GFNs to secure-GFNs
  KVM: PPC: Book3S HV: Track the state GFNs associated with secure VMs
  KVM: PPC: Book3S HV: Disable page merging in H_SVM_INIT_START
  ...

Documentation/powerpc/ultravisor.rst

@@ -895,6 +895,7 @@ Return values
     One of the following values:
 
 	* H_SUCCESS	 on success.
+        * H_STATE        if the VM is not in a position to switch to secure.
 
 Description
 ~~~~~~~~~~~
@@ -933,6 +934,8 @@ Return values
 	* H_UNSUPPORTED		if called from the wrong context (e.g.
 				from an SVM or before an H_SVM_INIT_START
 				hypercall).
+	* H_STATE		if the hypervisor could not successfully
+                                transition the VM to Secure VM.
 
 Description
 ~~~~~~~~~~~

arch/arm64/Kconfig

@@ -1182,22 +1182,6 @@ config HARDEN_BRANCH_PREDICTOR
 
 	  If unsure, say Y.
 
-config HARDEN_EL2_VECTORS
-	bool "Harden EL2 vector mapping against system register leak" if EXPERT
-	default y
-	help
-	  Speculation attacks against some high-performance processors can
-	  be used to leak privileged information such as the vector base
-	  register, resulting in a potential defeat of the EL2 layout
-	  randomization.
-
-	  This config option will map the vectors to a fixed location,
-	  independent of the EL2 code mapping, so that revealing VBAR_EL2
-	  to an attacker does not give away any extra information. This
-	  only gets enabled on affected CPUs.
-
-	  If unsure, say Y.
-
 config ARM64_SSBD
 	bool "Speculative Store Bypass Disable" if EXPERT
 	default y
@@ -1520,7 +1504,6 @@ menu "ARMv8.3 architectural features"
 config ARM64_PTR_AUTH
 	bool "Enable support for pointer authentication"
 	default y
-	depends on !KVM || ARM64_VHE
 	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
 	# Modern compilers insert a .note.gnu.property section note for PAC
 	# which is only understood by binutils starting with version 2.33.1.
@@ -1547,8 +1530,7 @@ config ARM64_PTR_AUTH
 
 	  The feature is detected at runtime. If the feature is not present in
 	  hardware it will not be advertised to userspace/KVM guest nor will it
-	  be enabled. However, KVM guest also require VHE mode and hence
-	  CONFIG_ARM64_VHE=y option to use this feature.
+	  be enabled.
 
 	  If the feature is present on the boot CPU but not on a late CPU, then
 	  the late CPU will be parked. Also, if the boot CPU does not have

arch/arm64/include/asm/kvm_asm.h

@@ -42,33 +42,81 @@
 
 #include <linux/mm.h>
 
-/* Translate a kernel address of @sym into its equivalent linear mapping */
-#define kvm_ksym_ref(sym)						\
+/*
+ * Translate name of a symbol defined in nVHE hyp to the name seen
+ * by kernel proper. All nVHE symbols are prefixed by the build system
+ * to avoid clashes with the VHE variants.
+ */
+#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
+
+#define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym)		\
+	DECLARE_KVM_VHE_SYM(sym);		\
+	DECLARE_KVM_NVHE_SYM(sym)
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ *   to has_vhe(). has_vhe() is implemented as a *final* capability,
+ *   while this is used early at boot time, when the capabilities are
+ *   not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ *   pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym)	(is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \
+					   : CHOOSE_NVHE_SYM(sym))
+#else
+/* The nVHE hypervisor shouldn't even try to access anything */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_HYP_SYM(sym)	__nvhe_undefined_symbol
+#endif
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr)						\
 	({								\
-		void *val = &sym;					\
+		void *val = (ptr);					\
 		if (!is_kernel_in_hyp_mode())				\
-			val = lm_alias(&sym);				\
+			val = lm_alias((ptr));				\
 		val;							\
 	 })
+#define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
 
 struct kvm;
 struct kvm_vcpu;
+struct kvm_s2_mmu;
 
-extern char __kvm_hyp_init[];
-extern char __kvm_hyp_init_end[];
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
+#define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
-extern char __kvm_hyp_vector[];
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+extern atomic_t arm64_el2_vector_last_slot;
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs	CHOOSE_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);
 
-extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
-
-extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __kvm_enable_ssbs(void);
 
@@ -143,7 +191,6 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 .macro get_vcpu_ptr vcpu, ctxt
 	get_host_ctxt \ctxt, \vcpu
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
-	kern_hyp_va	\vcpu
 .endm
 
 #endif

arch/arm64/include/asm/kvm_coproc.h

@@ -19,14 +19,6 @@ struct kvm_sys_reg_table {
 	size_t num;
 };
 
-struct kvm_sys_reg_target_table {
-	struct kvm_sys_reg_table table64;
-	struct kvm_sys_reg_table table32;
-};
-
-void kvm_register_target_sys_reg_table(unsigned int target,
-				       struct kvm_sys_reg_target_table *table);
-
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
 int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
 int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);

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;
 }
 
 /*
@@ -259,14 +238,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
-static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
+static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
 }
 
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
 	if (esr & ESR_ELx_CV)
 		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
@@ -291,64 +270,64 @@ static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
 
 static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_xVC_IMM_MASK;
 }
 
 static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_ISV);
 }
 
 static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+	return kvm_vcpu_get_esr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
 }
 
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SSE);
 }
 
 static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SF);
 }
 
 static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
-	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
+	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
 static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
 		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM);
 }
 
 static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
-	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
+	return 1 << ((kvm_vcpu_get_esr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
 }
 
 /* This one is not specific to Data Abort */
 static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL);
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_IL);
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
 {
-	return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+	return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 }
 
 static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
@@ -358,15 +337,15 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
 	case FSC_SEA:
@@ -387,7 +366,7 @@ static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
@@ -516,14 +495,14 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
  * Skip an instruction which has been emulated at hyp while most guest sysregs
  * are live.
  */
-static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+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;
 
@@ -159,6 +174,16 @@ 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 */
@@ -210,7 +235,15 @@ 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];
@@ -243,6 +276,9 @@ 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;
@@ -327,7 +363,7 @@ struct kvm_vcpu_arch {
 	struct vcpu_reset_state	reset_state;
 
 	/* True when deferrable sysregs are loaded on the physical CPU,
-	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+	 * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
 	bool sysregs_loaded_on_cpu;
 
 	/* Guest PV state */
@@ -378,15 +414,20 @@ struct kvm_vcpu_arch {
 #define vcpu_has_ptrauth(vcpu)		false
 #endif
 
-#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);
@@ -442,6 +483,18 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 
 u64 __kvm_call_hyp(void *hypfn, ...);
 
+#define kvm_call_hyp_nvhe(f, ...)					\
+	do {								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	} while(0)
+
+#define kvm_call_hyp_nvhe_ret(f, ...)					\
+	({								\
+		DECLARE_KVM_NVHE_SYM(f);				\
+		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+	})
+
 /*
  * 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
@@ -453,7 +506,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			f(__VA_ARGS__);					\
 			isb();						\
 		} else {						\
-			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
 		}							\
 	} while(0)
 
@@ -465,8 +518,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			ret = f(__VA_ARGS__);				\
 			isb();						\
 		} else {						\
-			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
-					     ##__VA_ARGS__);		\
+			ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__);	\
 		}							\
 									\
 		ret;							\
@@ -518,7 +570,7 @@ 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)
@@ -619,8 +671,8 @@ static inline int kvm_arm_have_ssbd(void)
 	}
 }
 
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
 int kvm_set_ipa_limit(void);
 

arch/arm64/include/asm/kvm_hyp.h

@@ -12,8 +12,6 @@
 #include <asm/alternative.h>
 #include <asm/sysreg.h>
 
-#define __hyp_text __section(.hyp.text) notrace __noscs
-
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
@@ -63,17 +61,20 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
+#endif
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+#else
 void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+#endif
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
@@ -81,11 +82,17 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
+#ifndef __KVM_NVHE_HYPERVISOR__
 void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
 void deactivate_traps_vhe_put(void);
+#endif
 
 u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt);
+#ifdef __KVM_NVHE_HYPERVISOR__
 void __noreturn __hyp_do_panic(unsigned long, ...);
+#endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
 

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/kvm_ptrauth.h

@@ -61,44 +61,36 @@
 
 /*
  * Both ptrauth_switch_to_guest and ptrauth_switch_to_host macros will
- * check for the presence of one of the cpufeature flag
- * ARM64_HAS_ADDRESS_AUTH_ARCH or ARM64_HAS_ADDRESS_AUTH_IMP_DEF and
+ * check for the presence ARM64_HAS_ADDRESS_AUTH, which is defined as
+ * (ARM64_HAS_ADDRESS_AUTH_ARCH || ARM64_HAS_ADDRESS_AUTH_IMP_DEF) and
  * then proceed ahead with the save/restore of Pointer Authentication
- * key registers.
+ * key registers if enabled for the guest.
  */
 .macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	1000f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	1001f
-alternative_else_nop_endif
-1000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 1001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
-1001:
+.L__skip_switch\@:
 .endm
 
 .macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3
-alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH
-	b	2000f
-alternative_else_nop_endif
-alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF
-	b	2001f
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
 alternative_else_nop_endif
-2000:
-	ldr	\reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)]
+	mrs	\reg1, hcr_el2
 	and	\reg1, \reg1, #(HCR_API | HCR_APK)
-	cbz	\reg1, 2001f
+	cbz	\reg1, .L__skip_switch\@
 	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_save_state	\reg1, \reg2, \reg3
 	add	\reg1, \h_ctxt, #CPU_APIAKEYLO_EL1
 	ptrauth_restore_state	\reg1, \reg2, \reg3
 	isb
-2001:
+.L__skip_switch\@:
 .endm
 
 #else /* !CONFIG_ARM64_PTR_AUTH */

arch/arm64/include/asm/mmu.h

@@ -45,13 +45,6 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
-     defined(CONFIG_HARDEN_EL2_VECTORS))
-
-extern char __bp_harden_hyp_vecs[];
-extern atomic_t arm64_el2_vector_last_slot;
-#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
-
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 

arch/arm64/include/asm/virt.h

@@ -85,10 +85,17 @@ static inline bool is_kernel_in_hyp_mode(void)
 
 static __always_inline bool has_vhe(void)
 {
-	if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN))
+	/*
+	 * The following macros are defined for code specic to VHE/nVHE.
+	 * If has_vhe() is inlined into those compilation units, it can
+	 * be determined statically. Otherwise fall back to caps.
+	 */
+	if (__is_defined(__KVM_VHE_HYPERVISOR__))
 		return true;
-
-	return false;
+	else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
 }
 
 #endif /* __ASSEMBLY__ */

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/cpu_errata.c

@@ -632,7 +632,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(midr, &range) && has_dic;
 }
 
-#if defined(CONFIG_HARDEN_EL2_VECTORS)
+#ifdef CONFIG_RANDOMIZE_BASE
 
 static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
@@ -891,7 +891,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = check_branch_predictor,
 	},
-#ifdef CONFIG_HARDEN_EL2_VECTORS
+#ifdef CONFIG_RANDOMIZE_BASE
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,

arch/arm64/kernel/image-vars.h

@@ -51,4 +51,58 @@ __efistub__ctype		= _ctype;
 
 #endif
 
+#ifdef CONFIG_KVM
+
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, to
+ * separate it from the kernel proper. The following symbols are legally
+ * accessed by it, therefore provide aliases to make them linkable.
+ * Do not include symbols which may not be safely accessed under hypervisor
+ * memory mappings.
+ */
+
+#define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
+
+/* Alternative callbacks for init-time patching of nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
+KVM_NVHE_ALIAS(kvm_patch_vector_branch);
+KVM_NVHE_ALIAS(kvm_update_va_mask);
+
+/* Global kernel state accessed by nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
+KVM_NVHE_ALIAS(kvm_host_data);
+KVM_NVHE_ALIAS(kvm_vgic_global_state);
+
+/* Kernel constant needed to compute idmap addresses. */
+KVM_NVHE_ALIAS(kimage_voffset);
+
+/* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(__hyp_panic_string);
+KVM_NVHE_ALIAS(panic);
+
+/* Vectors installed by hyp-init on reset HVC. */
+KVM_NVHE_ALIAS(__hyp_stub_vectors);
+
+/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
+KVM_NVHE_ALIAS(idmap_t0sz);
+
+/* Kernel symbol used by icache_is_vpipt(). */
+KVM_NVHE_ALIAS(__icache_flags);
+
+/* Kernel symbols needed for cpus_have_final/const_caps checks. */
+KVM_NVHE_ALIAS(arm64_const_caps_ready);
+KVM_NVHE_ALIAS(cpu_hwcap_keys);
+KVM_NVHE_ALIAS(cpu_hwcaps);
+
+/* Static keys which are set if a vGIC trap should be handled in hyp. */
+KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
+KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
+
+/* Static key checked in pmr_sync(). */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+KVM_NVHE_ALIAS(gic_pmr_sync);
+#endif
+
+#endif /* CONFIG_KVM */
+
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */

arch/arm64/kvm/Kconfig

@@ -58,7 +58,7 @@ config KVM_ARM_PMU
 	  virtual machines.
 
 config KVM_INDIRECT_VECTORS
-	def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS
+	def_bool HARDEN_BRANCH_PREDICTOR || RANDOMIZE_BASE
 
 endif # KVM
 

arch/arm64/kvm/Makefile

@@ -13,8 +13,8 @@ obj-$(CONFIG_KVM) += hyp/
 kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
-	 inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
-	 guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
+	 inject_fault.o regmap.o va_layout.o hyp.o handle_exit.o \
+	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
 	 aarch32.o arch_timer.o \
 	 vgic/vgic.o vgic/vgic-init.o \

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]);
@@ -281,6 +265,8 @@ 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;
@@ -336,16 +322,18 @@ 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;
 	}
 
@@ -353,7 +341,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
-	kvm_vcpu_load_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_load_sysregs_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
@@ -371,7 +360,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvm_arch_vcpu_put_fp(vcpu);
-	kvm_vcpu_put_sysregs(vcpu);
+	if (has_vhe())
+		kvm_vcpu_put_sysregs_vhe(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
@@ -468,7 +458,6 @@ static bool need_new_vmid_gen(struct kvm_vmid *vmid)
 
 /**
  * update_vmid - Update the vmid with a valid VMID for the current generation
- * @kvm: The guest that struct vmid belongs to
  * @vmid: The stage-2 VMID information struct
  */
 static void update_vmid(struct kvm_vmid *vmid)
@@ -680,7 +669,7 @@ 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 +718,13 @@ 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();
@@ -750,11 +739,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		trace_kvm_entry(*vcpu_pc(vcpu));
 		guest_enter_irqoff();
 
-		if (has_vhe()) {
-			ret = kvm_vcpu_run_vhe(vcpu);
-		} else {
-			ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
-		}
+		ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -784,7 +769,7 @@ 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);
 
@@ -1287,7 +1272,7 @@ static void cpu_init_hyp_mode(void)
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
 	tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
-		     (unsigned long)kvm_ksym_ref(kvm_host_data));
+		     (unsigned long)kvm_ksym_ref(&kvm_host_data));
 
 	pgd_ptr = kvm_mmu_get_httbr();
 	hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
@@ -1308,7 +1293,7 @@ static void cpu_init_hyp_mode(void)
 	 */
 	if (this_cpu_has_cap(ARM64_SSBS) &&
 	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
-		kvm_call_hyp(__kvm_enable_ssbs);
+		kvm_call_hyp_nvhe(__kvm_enable_ssbs);
 	}
 }
 

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/handle_exit.c

@@ -89,7 +89,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
@@ -119,13 +119,13 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int ret = 0;
 
 	run->exit_reason = KVM_EXIT_DEBUG;
-	run->debug.arch.hsr = hsr;
+	run->debug.arch.hsr = esr;
 
-	switch (ESR_ELx_EC(hsr)) {
+	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
 		/* fall through */
@@ -135,8 +135,8 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 	case ESR_ELx_EC_BRK64:
 		break;
 	default:
-		kvm_err("%s: un-handled case hsr: %#08x\n",
-			__func__, (unsigned int) hsr);
+		kvm_err("%s: un-handled case esr: %#08x\n",
+			__func__, (unsigned int) esr);
 		ret = -1;
 		break;
 	}
@@ -146,10 +146,10 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 
 static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
 
-	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
-		      hsr, esr_get_class_string(hsr));
+	kvm_pr_unimpl("Unknown exception class: esr: %#08x -- %s\n",
+		      esr, esr_get_class_string(esr));
 
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -200,10 +200,10 @@ static exit_handle_fn arm_exit_handlers[] = {
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	u8 hsr_ec = ESR_ELx_EC(hsr);
+	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u8 esr_ec = ESR_ELx_EC(esr);
 
-	return arm_exit_handlers[hsr_ec];
+	return arm_exit_handlers[esr_ec];
 }
 
 /*
@@ -242,15 +242,15 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 	struct kvm_run *run = vcpu->run;
 
 	if (ARM_SERROR_PENDING(exception_index)) {
-		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+		u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
 
 		/*
 		 * HVC/SMC already have an adjusted PC, which we need
 		 * to correct in order to return to after having
 		 * injected the SError.
 		 */
-		if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 ||
-		    hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) {
+		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 ||
+		    esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) {
 			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
 			*vcpu_pc(vcpu) -= adj;
 		}
@@ -307,5 +307,5 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
-		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }

arch/arm64/kvm/hyp/Makefile

@@ -3,18 +3,12 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
-		$(DISABLE_STACKLEAK_PLUGIN)
-
-obj-$(CONFIG_KVM) += hyp.o
-
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
+incdir := $(srctree)/$(src)/include
+subdir-asflags-y := -I$(incdir)
+subdir-ccflags-y := -I$(incdir)				\
+		    -fno-stack-protector		\
+		    -DDISABLE_BRANCH_PROFILING		\
+		    $(DISABLE_STACKLEAK_PLUGIN)
+
+obj-$(CONFIG_KVM) += vhe/ nvhe/
+obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o

arch/arm64/kvm/hyp/aarch32.c

@@ -44,14 +44,14 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;
 	int cond;
 
 	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+	if (kvm_vcpu_get_esr(vcpu) >> 30)
 		return true;
 
 	/* Is condition field valid? */
@@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
  */
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  * kvm_skip_instr - skip a trapped instruction and proceed to the next
  * @vcpu: The vcpu pointer
  */
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;

arch/arm64/kvm/hyp/entry.S

@@ -16,12 +16,10 @@
 #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
-	.pushsection	.hyp.text, "ax"
 
 /*
  * We treat x18 as callee-saved as the host may use it as a platform

arch/arm64/kvm/hyp/fpsimd.S

@@ -9,7 +9,6 @@
 #include <asm/fpsimdmacros.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1

arch/arm64/kvm/hyp/hyp-entry.S

@@ -16,7 +16,6 @@
 #include <asm/mmu.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 .macro do_el2_call
 	/*
@@ -40,6 +39,7 @@ el1_sync:				// Guest trapped into EL2
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
 	cbnz	x1, el1_hvc_guest	// called HVC
 
@@ -74,6 +74,7 @@ el1_sync:				// Guest trapped into EL2
 
 	eret
 	sb
+#endif /* __KVM_NVHE_HYPERVISOR__ */
 
 el1_hvc_guest:
 	/*
@@ -180,6 +181,7 @@ el2_error:
 	eret
 	sb
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
@@ -189,6 +191,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	eret
 	sb
 SYM_FUNC_END(__hyp_do_panic)
+#endif
 
 SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
@@ -318,20 +321,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs)
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
-
-	.popsection
-
-SYM_CODE_START(__smccc_workaround_1_smc)
-	esb
-	sub	sp, sp, #(8 * 4)
-	stp	x2, x3, [sp, #(8 * 0)]
-	stp	x0, x1, [sp, #(8 * 2)]
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
-	smc	#0
-	ldp	x2, x3, [sp, #(8 * 0)]
-	ldp	x0, x1, [sp, #(8 * 2)]
-	add	sp, sp, #(8 * 4)
-1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
-	.org 1b
-SYM_CODE_END(__smccc_workaround_1_smc)
 #endif

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

@@ -4,6 +4,9 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__
+#define __ARM64_KVM_HYP_DEBUG_SR_H__
+
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
@@ -85,53 +88,8 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
-{
-	u64 reg;
-
-	/* Clear pmscr in case of early return */
-	*pmscr_el1 = 0;
-
-	/* SPE present on this CPU? */
-	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
-						  ID_AA64DFR0_PMSVER_SHIFT))
-		return;
-
-	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(SYS_PMBIDR_EL1);
-	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
-		return;
-
-	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
-	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
-		return;
-
-	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
-	write_sysreg_s(0, SYS_PMSCR_EL1);
-	isb();
-
-	/* Now drain all buffered data to memory */
-	psb_csync();
-	dsb(nsh);
-}
-
-static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
-{
-	if (!pmscr_el1)
-		return;
-
-	/* The host page table is installed, but not yet synchronised */
-	isb();
-
-	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
-}
-
-static void __hyp_text __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;
@@ -145,12 +103,11 @@ static void __hyp_text __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 void __hyp_text __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;
@@ -165,23 +122,16 @@ static void __hyp_text __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);
 }
 
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	/*
-	 * Non-VHE: Disable and flush SPE data generation
-	 * VHE: The vcpu can run, but it can't hide.
-	 */
-	if (!has_vhe())
-		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -190,20 +140,17 @@ void __hyp_text __debug_switch_to_guest(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);
 }
 
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	if (!has_vhe())
-		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -212,13 +159,10 @@ void __hyp_text __debug_switch_to_host(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;
 }
 
-u32 __hyp_text __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
+#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__
+#define __ARM64_KVM_HYP_SYSREG_SR_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
+}
+
+static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt_sys_reg(ctxt, TPIDR_EL0)	= read_sysreg(tpidr_el0);
+	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
+}
+
+static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt_sys_reg(ctxt, CSSELR_EL1)	= read_sysreg(csselr_el1);
+	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
+	ctxt_sys_reg(ctxt, CPACR_EL1)	= read_sysreg_el1(SYS_CPACR);
+	ctxt_sys_reg(ctxt, TTBR0_EL1)	= read_sysreg_el1(SYS_TTBR0);
+	ctxt_sys_reg(ctxt, TTBR1_EL1)	= read_sysreg_el1(SYS_TTBR1);
+	ctxt_sys_reg(ctxt, TCR_EL1)	= read_sysreg_el1(SYS_TCR);
+	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
+	ctxt_sys_reg(ctxt, AFSR0_EL1)	= read_sysreg_el1(SYS_AFSR0);
+	ctxt_sys_reg(ctxt, AFSR1_EL1)	= read_sysreg_el1(SYS_AFSR1);
+	ctxt_sys_reg(ctxt, FAR_EL1)	= read_sysreg_el1(SYS_FAR);
+	ctxt_sys_reg(ctxt, MAIR_EL1)	= read_sysreg_el1(SYS_MAIR);
+	ctxt_sys_reg(ctxt, VBAR_EL1)	= read_sysreg_el1(SYS_VBAR);
+	ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt_sys_reg(ctxt, AMAIR_EL1)	= read_sysreg_el1(SYS_AMAIR);
+	ctxt_sys_reg(ctxt, CNTKCTL_EL1)	= read_sysreg_el1(SYS_CNTKCTL);
+	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
+	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+
+	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
+	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
+	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
+}
+
+static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
+	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
+}
+
+static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1),  mdscr_el1);
+}
+
+static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0),	tpidr_el0);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
+}
+
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1),	csselr_el1);
+
+	if (has_vhe() ||
+	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
+	} else	if (!ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for guest registers, hence the context
+		 * test. We're coming from the host, so SCTLR.M is already
+		 * set. Pairs with nVHE's __activate_traps().
+		 */
+		write_sysreg_el1((ctxt_sys_reg(ctxt, TCR_EL1) |
+				  TCR_EPD1_MASK | TCR_EPD0_MASK),
+				 SYS_TCR);
+		isb();
+	}
+
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1),	SYS_CPACR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1),	SYS_AFSR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1),	SYS_AFSR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL1),	SYS_FAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL1),	SYS_MAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL1),	SYS_VBAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1),	SYS_AMAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
+	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
+
+	if (!has_vhe() &&
+	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
+	    ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for host registers, hence the context
+		 * test. Pairs with nVHE's __deactivate_traps().
+		 */
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * deconfigured and disabled. We can now restore the host's
+		 * S1 configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
+	}
+
+	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
+}
+
+static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+{
+	u64 pstate = ctxt->regs.pstate;
+	u64 mode = pstate & PSR_AA32_MODE_MASK;
+
+	/*
+	 * Safety check to ensure we're setting the CPU up to enter the guest
+	 * in a less privileged mode.
+	 *
+	 * If we are attempting a return to EL2 or higher in AArch64 state,
+	 * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that
+	 * we'll take an illegal exception state exception immediately after
+	 * the ERET to the guest.  Attempts to return to AArch32 Hyp will
+	 * result in an illegal exception return because EL2's execution state
+	 * is determined by SCR_EL3.RW.
+	 */
+	if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
+		pstate = PSR_MODE_EL2h | PSR_IL_BIT;
+
+	write_sysreg_el2(ctxt->regs.pc,			SYS_ELR);
+	write_sysreg_el2(pstate,			SYS_SPSR);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		write_sysreg_s(ctxt_sys_reg(ctxt, DISR_EL1), SYS_VDISR_EL2);
+}
+
+static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	vcpu->arch.ctxt.spsr_abt = read_sysreg(spsr_abt);
+	vcpu->arch.ctxt.spsr_und = read_sysreg(spsr_und);
+	vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
+	vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
+
+	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
+	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
+
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
+		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
+}
+
+static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	write_sysreg(vcpu->arch.ctxt.spsr_abt, spsr_abt);
+	write_sysreg(vcpu->arch.ctxt.spsr_und, spsr_und);
+	write_sysreg(vcpu->arch.ctxt.spsr_irq, spsr_irq);
+	write_sysreg(vcpu->arch.ctxt.spsr_fiq, spsr_fiq);
+
+	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
+
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
+		write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2);
+}
+
+#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */

arch/arm64/kvm/hyp/nvhe/Makefile

+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_NVHE_HYPERVISOR__
+ccflags-y := -D__KVM_NVHE_HYPERVISOR__
+
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o
+
+obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
+extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
+
+$(obj)/%.hyp.tmp.o: $(src)/%.c FORCE
+	$(call if_changed_rule,cc_o_c)
+$(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
+	$(call if_changed_rule,as_o_S)
+$(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
+	$(call if_changed,hypcopy)
+
+# Disable reordering functions by GCC (enabled at -O2).
+# This pass puts functions into '.text.*' sections to aid the linker
+# in optimizing ELF layout. See HYPCOPY comment below for more info.
+ccflags-y += $(call cc-option,-fno-reorder-functions)
+
+# The HYPCOPY command uses `objcopy` to prefix all ELF symbol names
+# and relevant ELF section names to avoid clashes with VHE code/data.
+#
+# Hyp code is assumed to be in the '.text' section of the input object
+# files (with the exception of specialized sections such as
+# '.hyp.idmap.text'). This assumption may be broken by a compiler that
+# divides code into sections like '.text.unlikely' so as to optimize
+# ELF layout. HYPCOPY checks that no such sections exist in the input
+# using `objdump`, otherwise they would be linked together with other
+# kernel code and not memory-mapped correctly at runtime.
+quiet_cmd_hypcopy = HYPCOPY $@
+      cmd_hypcopy =							\
+	if $(OBJDUMP) -h $< | grep -F '.text.'; then			\
+		echo "$@: function reordering not supported in nVHE hyp code" >&2; \
+		/bin/false;						\
+	fi;								\
+	$(OBJCOPY) --prefix-symbols=__kvm_nvhe_				\
+		   --rename-section=.text=.hyp.text			\
+		   $< $@
+
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+
+# KVM nVHE code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
+
+# Skip objtool checking for this directory because nVHE code is compiled with
+# non-standard build rules.
+OBJECT_FILES_NON_STANDARD := y

arch/arm64/kvm/hyp/nvhe/debug-sr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static void __debug_save_spe(u64 *pmscr_el1)
+{
+	u64 reg;
+
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
+	/* SPE present on this CPU? */
+	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
+						  ID_AA64DFR0_PMSVER_SHIFT))
+		return;
+
+	/* Yes; is it owned by EL3? */
+	reg = read_sysreg_s(SYS_PMBIDR_EL1);
+	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
+		return;
+
+	/* No; is the host actually using the thing? */
+	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
+		return;
+
+	/* Yes; save the control register and disable data generation */
+	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+	write_sysreg_s(0, SYS_PMSCR_EL1);
+	isb();
+
+	/* Now drain all buffered data to memory */
+	psb_csync();
+	dsb(nsh);
+}
+
+static void __debug_restore_spe(u64 pmscr_el1)
+{
+	if (!pmscr_el1)
+		return;
+
+	/* The host page table is installed, but not yet synchronised */
+	isb();
+
+	/* Re-enable data generation */
+	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	/* Disable and flush SPE data generation */
+	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}

arch/arm64/kvm/hyp-init.S → arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -105,6 +105,11 @@ alternative_else_nop_endif
 	 */
 	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
 CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	mov_q	x5, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB)
+	orr	x4, x4, x5
+alternative_else_nop_endif
 	msr	sctlr_el2, x4
 	isb
 

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+#include <hyp/sysreg-sr.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+	__activate_traps_common(vcpu);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
+	if (!update_fp_enabled(vcpu)) {
+		val |= CPTR_EL2_TFP;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1),	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1),	SYS_TCR);
+	}
+}
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 mdcr_el2;
+
+	___deactivate_traps(vcpu);
+
+	mdcr_el2 = read_sysreg(mdcr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
+	__deactivate_traps_common();
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
+	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static void __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+/* Save VGICv3 state on non-VHE systems */
+static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/* Restore VGICv3 state on non_VEH systems */
+static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+		__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
+	}
+}
+
+/**
+ * Disable host events, enable guest events
+ */
+static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
+/* Switch to the guest for legacy non-VHE systems */
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool pmu_switch_needed;
+	u64 exit_code;
+
+	/*
+	 * 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 | GIC_PRIO_PSR_I_SET);
+		pmr_sync();
+	}
+
+	vcpu = kern_hyp_va(vcpu);
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+
+	__sysreg_save_state_nvhe(host_ctxt);
+
+	/*
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->arch.hw_mmu));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	__sysreg_save_state_nvhe(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+	__timer_disable_traps(vcpu);
+	__hyp_vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__sysreg_restore_state_nvhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	/*
+	 * This must come after restoring the host sysregs, since a non-VHE
+	 * system may enable SPE here and make use of the TTBRs.
+	 */
+	__debug_switch_to_host(vcpu);
+
+	if (pmu_switch_needed)
+		__pmu_switch_to_host(host_ctxt);
+
+	/* Returning to host will clear PSR.I, remask PMR if needed */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQOFF);
+
+	return exit_code;
+}
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+	struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu;
+	unsigned long str_va;
+
+	if (read_sysreg(vttbr_el2)) {
+		__timer_disable_traps(vcpu);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state_nvhe(host_ctxt);
+	}
+
+	/*
+	 * Force the panic string to be loaded from the literal pool,
+	 * making sure it is a kernel address and not a PC-relative
+	 * reference.
+	 */
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
+
+	__hyp_do_panic(str_va,
+		       spsr, elr,
+		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
+		       read_sysreg(hpfar_el2), par, vcpu);
+	unreachable();
+}

arch/arm64/kvm/hyp/nvhe/sysreg-sr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * Non-VHE: Both host and guest must save everything.
+ */
+
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_el1_state(ctxt);
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_user_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_user_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+
+void __kvm_enable_ssbs(void)
+{
+	u64 tmp;
+
+	asm volatile(
+	"mrs	%0, sctlr_el2\n"
+	"orr	%0, %0, %1\n"
+	"msr	sctlr_el2, %0"
+	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}

arch/arm64/kvm/hyp/timer-sr.c → arch/arm64/kvm/hyp/nvhe/timer-sr.c

@@ -10,7 +10,7 @@
 
 #include <asm/kvm_hyp.h>
 
-void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
+void __kvm_timer_set_cntvoff(u64 cntvoff)
 {
 	write_sysreg(cntvoff, cntvoff_el2);
 }
@@ -19,7 +19,7 @@ void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
+void __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
@@ -33,7 +33,7 @@ void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
  * Should only be called on non-VHE systems.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
+void __timer_enable_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/tlbflush.h>
+
+struct tlb_inv_context {
+	u64		tcr;
+};
+
+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;
+
+		/*
+		 * For CPUs that are affected by ARM 1319367, we need to
+		 * avoid a host Stage-1 walk while we have the guest's
+		 * VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the S1 MMU is enabled, so we can
+		 * simply set the EPD bits to avoid any further TLB fill.
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		isb();
+	}
+
+	__load_guest_stage2(mmu);
+}
+
+static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
+{
+	write_sysreg(0, vttbr_el2);
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+		/* Ensure write of the host VMID */
+		isb();
+		/* Restore the host's TCR_EL1 */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+	}
+}
+
+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 */
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	__tlbi_level(ipas2e1is, ipa, level);
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(ish);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+
+	/*
+	 * If the host is running at EL1 and we have a VPIPT I-cache,
+	 * then we must perform I-cache maintenance at EL2 in order for
+	 * it to have an effect on the guest. Since the guest cannot hit
+	 * I-cache lines allocated with a different VMID, we don't need
+	 * to worry about junk out of guest reset (we nuke the I-cache on
+	 * VMID rollover), but we do need to be careful when remapping
+	 * executable pages for the same guest. This can happen when KSM
+	 * takes a CoW fault on an executable page, copies the page into
+	 * a page that was previously mapped in the guest and then needs
+	 * to invalidate the guest view of the I-cache for that page
+	 * from EL1. To solve this, we invalidate the entire I-cache when
+	 * unmapping a page from a guest if we have a VPIPT I-cache but
+	 * the host is running at EL1. As above, we could do better if
+	 * we had the VA.
+	 *
+	 * The moral of this story is: if you have a VPIPT I-cache, then
+	 * you should be running with VHE enabled.
+	 */
+	if (icache_is_vpipt())
+		__flush_icache_all();
+
+	__tlb_switch_to_host(&cxt);
+}
+
+void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	__tlbi(vmalls12e1is);
+	dsb(ish);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
+
+void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+{
+	struct tlb_inv_context cxt;
+
+	/* Switch to requested VMID */
+	mmu = kern_hyp_va(mmu);
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
+
+void __kvm_flush_vm_context(void)
+{
+	dsb(ishst);
+	__tlbi(alle1is);
+
+	/*
+	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
+	 * is necessary across a VMID rollover.
+	 *
+	 * VPIPT caches constrain lookup and maintenance to the active VMID,
+	 * so we need to invalidate lines with a stale VMID to avoid an ABA
+	 * race after multiple rollovers.
+	 *
+	 */
+	if (icache_is_vpipt())
+		asm volatile("ic ialluis");
+
+	dsb(ish);
+}

arch/arm64/kvm/hyp/smccc_wa.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015-2018 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/linkage.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+	/*
+	 * This is not executed directly and is instead copied into the vectors
+	 * by install_bp_hardening_cb().
+	 */
+	.data
+	.pushsection	.rodata
+	.global		__smccc_workaround_1_smc
+SYM_DATA_START(__smccc_workaround_1_smc)
+	esb
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_DATA_END(__smccc_workaround_1_smc)

arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c

@@ -13,7 +13,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+static bool __is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
@@ -32,7 +32,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
  *  0: Not a GICV access
  * -1: Illegal GICV access successfully performed
  */
-int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 	struct vgic_dist *vgic = &kvm->arch.vgic;

arch/arm64/kvm/hyp/vhe/Makefile

+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_VHE_HYPERVISOR__
+ccflags-y := -D__KVM_VHE_HYPERVISOR__
+
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+	 ../fpsimd.o ../hyp-entry.o

arch/arm64/kvm/hyp/vhe/debug-sr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	__debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu);
+
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~CPACR_EL1_ZEN;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+
+	val |= CPTR_EL2_TAM;
+
+	if (update_fp_enabled(vcpu)) {
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_EL1_ZEN;
+	} else {
+		val &= ~CPACR_EL1_FPEN;
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
+}
+NOKPROBE_SYMBOL(__activate_traps);
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	extern char vectors[];	/* kernel exception vectors */
+
+	___deactivate_traps(vcpu);
+
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL2/EL0 translation regime used by
+	 * the host.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+
+	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
+	write_sysreg(vectors, vbar_el1);
+}
+NOKPROBE_SYMBOL(__deactivate_traps);
+
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+{
+	__activate_traps_common(vcpu);
+}
+
+void deactivate_traps_vhe_put(void)
+{
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+		    MDCR_EL2_TPMS;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+
+	__deactivate_traps_common();
+}
+
+/* Switch to the guest for VHE systems running in EL2 */
+static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	u64 exit_code;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	sysreg_save_host_state_vhe(host_ctxt);
+
+	/*
+	 * ARM erratum 1165522 requires us to configure both stage 1 and
+	 * stage 2 translation for the guest context before we clear
+	 * HCR_EL2.TGE.
+	 *
+	 * We have already configured the guest's stage 1 translation in
+	 * kvm_vcpu_load_sysregs_vhe above.  We must now call __activate_vm
+	 * before __activate_traps, because __activate_vm configures
+	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
+	 * (among other things).
+	 */
+	__activate_vm(vcpu->arch.hw_mmu);
+	__activate_traps(vcpu);
+
+	sysreg_restore_guest_state_vhe(guest_ctxt);
+	__debug_switch_to_guest(vcpu);
+
+	__set_guest_arch_workaround_state(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	__set_host_arch_workaround_state(vcpu);
+
+	sysreg_save_guest_state_vhe(guest_ctxt);
+
+	__deactivate_traps(vcpu);
+
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+		__fpsimd_save_fpexc32(vcpu);
+
+	__debug_switch_to_host(vcpu);
+
+	return exit_code;
+}
+NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
+
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	local_daif_mask();
+
+	/*
+	 * 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.
+	 *
+	 * 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.
+	 */
+	pmr_sync();
+
+	ret = __kvm_vcpu_run_vhe(vcpu);
+
+	/*
+	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
+	 * and the GIC PMR if the host is using IRQ priorities.
+	 */
+	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+	/*
+	 * 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();
+
+	return ret;
+}
+
+static void __hyp_call_panic(u64 spsr, u64 elr, u64 par,
+			     struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_vcpu *vcpu;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+
+	__deactivate_traps(vcpu);
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	panic(__hyp_panic_string,
+	      spsr, elr,
+	      read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
+	      read_sysreg(hpfar_el2), par, vcpu);
+}
+NOKPROBE_SYMBOL(__hyp_call_panic);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+	u64 spsr = read_sysreg_el2(SYS_SPSR);
+	u64 elr = read_sysreg_el2(SYS_ELR);
+	u64 par = read_sysreg(par_el1);
+
+	__hyp_call_panic(spsr, elr, par, host_ctxt);
+	unreachable();
+}

arch/arm64/kvm/hyp/vhe/sysreg-sr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
+ * tpidr_el0 and tpidrro_el0 only need to be switched when going
+ * to host userspace or a different VCPU.  EL1 registers only need to be
+ * switched when potentially going to run a different VCPU.  The latter two
+ * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
+ */
+
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
+
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
+
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
+
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
+
+/**
+ * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Load system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_load() function
+ * and loading system register state early avoids having to load them on
+ * every entry to the VM.
+ */
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__sysreg_save_user_state(host_ctxt);
+
+	/*
+	 * Load guest EL1 and user state
+	 *
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_user_state(guest_ctxt);
+	__sysreg_restore_el1_state(guest_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = true;
+
+	activate_traps_vhe_load(vcpu);
+}
+
+/**
+ * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Save guest system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_put() function
+ * and deferring saving system register state until we're no longer running the
+ * VCPU avoids having to save them on every exit from the VM.
+ */
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	deactivate_traps_vhe_put();
+
+	__sysreg_save_el1_state(guest_ctxt);
+	__sysreg_save_user_state(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+
+	/* Restore host user state */
+	__sysreg_restore_user_state(host_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = false;
+}

arch/arm64/kvm/hyp/vhe/timer-sr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+
+void __kvm_timer_set_cntvoff(u64 cntvoff)
+{
+	write_sysreg(cntvoff, cntvoff_el2);
+}

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

@@ -16,8 +16,8 @@ struct tlb_inv_context {
 	u64		sctlr;
 };
 
-static void __hyp_text __tlb_switch_to_guest_vhe(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;
 
@@ -53,48 +53,14 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 	 * 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 __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
-						  struct tlb_inv_context *cxt)
-{
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		u64 val;
-
-		/*
-		 * For CPUs that are affected by ARM 1319367, we need to
-		 * avoid a host Stage-1 walk while we have the guest's
-		 * VMID set in the VTTBR in order to invalidate TLBs.
-		 * We're guaranteed that the S1 MMU is enabled, so we can
-		 * simply set the EPD bits to avoid any further TLB fill.
-		 */
-		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
-		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
-		write_sysreg_el1(val, SYS_TCR);
-		isb();
-	}
-
-	/* __load_guest_stage2() includes an ISB for the workaround. */
-	__load_guest_stage2(kvm);
-	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
-}
-
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
-					     struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_guest_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_guest_nvhe(kvm, cxt);
-}
-
-static void __hyp_text __tlb_switch_to_host_vhe(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
@@ -113,37 +79,15 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 	local_irq_restore(cxt->flags);
 }
 
-static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
-						 struct tlb_inv_context *cxt)
-{
-	write_sysreg(0, vttbr_el2);
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/* Ensure write of the host VMID */
-		isb();
-		/* Restore the host's TCR_EL1 */
-		write_sysreg_el1(cxt->tcr, SYS_TCR);
-	}
-}
-
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
-					    struct tlb_inv_context *cxt)
-{
-	if (has_vhe())
-		__tlb_switch_to_host_vhe(kvm, cxt);
-	else
-		__tlb_switch_to_host_nvhe(kvm, cxt);
-}
-
-void __hyp_text __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);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -151,7 +95,7 @@ void __hyp_text __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,
@@ -164,64 +108,40 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (!has_vhe() && icache_is_vpipt())
-		__flush_icache_all();
-
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __hyp_text __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);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __hyp_text __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);
+	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(kvm, &cxt);
+	__tlb_switch_to_host(&cxt);
 }
 
-void __hyp_text __kvm_flush_vm_context(void)
+void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);

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/mmio.c

@@ -146,12 +146,6 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 		return -ENOSYS;
 	}
 
-	/* Page table accesses IO mem: tell guest to fix its TTBR */
-	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
-	}
-
 	/*
 	 * Prepare MMIO operation. First decode the syndrome data we get
 	 * from the CPU. Then try if some in-kernel emulation feels

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

@@ -42,6 +42,11 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
+static bool system_has_full_ptr_auth(void)
+{
+	return system_supports_address_auth() && system_supports_generic_auth();
+}
+
 /**
  * kvm_arch_vm_ioctl_check_extension
  *
@@ -80,8 +85,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		r = has_vhe() && system_supports_address_auth() &&
-				 system_supports_generic_auth();
+		r = system_has_full_ptr_auth();
 		break;
 	default:
 		r = 0;
@@ -205,19 +209,14 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 {
-	/* Support ptrauth only if the system supports these capabilities. */
-	if (!has_vhe())
-		return -EINVAL;
-
-	if (!system_supports_address_auth() ||
-	    !system_supports_generic_auth())
-		return -EINVAL;
 	/*
 	 * For now make sure that both address/generic pointer authentication
-	 * features are requested by the userspace together.
+	 * features are requested by the userspace together and the system
+	 * supports these capabilities.
 	 */
 	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
+	    !system_has_full_ptr_auth())
 		return -EINVAL;
 
 	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
@@ -292,7 +291,7 @@ 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_generic_v8.c

-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Based on arch/arm/kvm/coproc_a15.c:
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Authors: Rusty Russell <rusty@rustcorp.au>
- *          Christoffer Dall <c.dall@virtualopensystems.com>
- */
-#include <linux/kvm_host.h>
-#include <asm/cputype.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
-#include <asm/sysreg.h>
-#include <linux/init.h>
-
-#include "sys_regs.h"
-
-static bool access_actlr(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *r)
-{
-	if (p->is_write)
-		return ignore_write(vcpu, p);
-
-	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
-
-	if (p->is_aarch32) {
-		if (r->Op2 & 2)
-			p->regval = upper_32_bits(p->regval);
-		else
-			p->regval = lower_32_bits(p->regval);
-	}
-
-	return true;
-}
-
-static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
-{
-	__vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
-}
-
-/*
- * Implementation specific sys-reg registers.
- * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
- */
-static const struct sys_reg_desc genericv8_sys_regs[] = {
-	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
-};
-
-static const struct sys_reg_desc genericv8_cp15_regs[] = {
-	/* ACTLR */
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
-	  access_actlr },
-	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b011),
-	  access_actlr },
-};
-
-static struct kvm_sys_reg_target_table genericv8_target_table = {
-	.table64 = {
-		.table = genericv8_sys_regs,
-		.num = ARRAY_SIZE(genericv8_sys_regs),
-	},
-	.table32 = {
-		.table = genericv8_cp15_regs,
-		.num = ARRAY_SIZE(genericv8_cp15_regs),
-	},
-};
-
-static int __init sys_reg_genericv8_init(void)
-{
-	unsigned int i;
-
-	for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++)
-		BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
-			       &genericv8_sys_regs[i]) >= 0);
-
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
-					  &genericv8_target_table);
-	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_GENERIC_V8,
-					  &genericv8_target_table);
-
-	return 0;
-}
-late_initcall(sys_reg_genericv8_init);

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);
 	),
 

arch/arm64/kvm/va_layout.c

@@ -48,7 +48,7 @@ __init void kvm_compute_layout(void)
 	va_mask = GENMASK_ULL(tag_lsb - 1, 0);
 	tag_val = hyp_va_msb;
 
-	if (tag_lsb != (vabits_actual - 1)) {
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) {
 		/* We have some free bits to insert a random tag. */
 		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 	}

arch/arm64/kvm/vgic/vgic-irqfd.c

@@ -100,19 +100,33 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 
 /**
  * kvm_arch_set_irq_inatomic: fast-path for irqfd injection
- *
- * Currently only direct MSI injection is supported.
  */
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
 {
-	if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) {
+	if (!level)
+		return -EWOULDBLOCK;
+
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_MSI: {
 		struct kvm_msi msi;
 
+		if (!vgic_has_its(kvm))
+			break;
+
 		kvm_populate_msi(e, &msi);
-		if (!vgic_its_inject_cached_translation(kvm, &msi))
-			return 0;
+		return vgic_its_inject_cached_translation(kvm, &msi);
+	}
+
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		/*
+		 * Injecting SPIs is always possible in atomic context
+		 * as long as the damn vgic is initialized.
+		 */
+		if (unlikely(!vgic_initialized(kvm)))
+			break;
+		return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status);
 	}
 
 	return -EWOULDBLOCK;

arch/arm64/kvm/vgic/vgic-its.c

@@ -757,9 +757,8 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 
 	db = (u64)msi->address_hi << 32 | msi->address_lo;
 	irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data);
-
 	if (!irq)
-		return -1;
+		return -EWOULDBLOCK;
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;