Merge branch kvm-arm64/pkvm/fixed-features into kvmarm-master/next

* kvm-arm64/pkvm/fixed-features: (22 commits)
  : .
  : Add the pKVM fixed feature that allows a bunch of exceptions
  : to either be forbidden or be easily handled at EL2.
  : .
  KVM: arm64: pkvm: Give priority to standard traps over pvm handling
  KVM: arm64: pkvm: Pass vpcu instead of kvm to kvm_get_exit_handler_array()
  KVM: arm64: pkvm: Move kvm_handle_pvm_restricted around
  KVM: arm64: pkvm: Consolidate include files
  KVM: arm64: pkvm: Preserve pending SError on exit from AArch32
  KVM: arm64: pkvm: Handle GICv3 traps as required
  KVM: arm64: pkvm: Drop sysregs that should never be routed to the host
  KVM: arm64: pkvm: Drop AArch32-specific registers
  KVM: arm64: pkvm: Make the ERR/ERX*_EL1 registers RAZ/WI
  KVM: arm64: pkvm: Use a single function to expose all id-regs
  KVM: arm64: Fix early exit ptrauth handling
  KVM: arm64: Handle protected guests at 32 bits
  KVM: arm64: Trap access to pVM restricted features
  KVM: arm64: Move sanitized copies of CPU features
  KVM: arm64: Initialize trap registers for protected VMs
  KVM: arm64: Add handlers for protected VM System Registers
  KVM: arm64: Simplify masking out MTE in feature id reg
  KVM: arm64: Add missing field descriptor for MDCR_EL2
  KVM: arm64: Pass struct kvm to per-EC handlers
  KVM: arm64: Move early handlers to per-EC handlers
  ...
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_arm.h

@@ -295,6 +295,7 @@
 #define MDCR_EL2_HPMFZO		(UL(1) << 29)
 #define MDCR_EL2_MTPME		(UL(1) << 28)
 #define MDCR_EL2_TDCC		(UL(1) << 27)
+#define MDCR_EL2_HLP		(UL(1) << 26)
 #define MDCR_EL2_HCCD		(UL(1) << 23)
 #define MDCR_EL2_TTRF		(UL(1) << 19)
 #define MDCR_EL2_HPMD		(UL(1) << 17)

arch/arm64/include/asm/kvm_asm.h

@@ -74,6 +74,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
 };
 
 #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]

arch/arm64/include/asm/kvm_host.h

@@ -781,6 +781,8 @@ static inline bool kvm_vm_is_protected(struct kvm *kvm)
 	return false;
 }
 
+void kvm_init_protected_traps(struct kvm_vcpu *vcpu);
+
 int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
 bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 

arch/arm64/include/asm/kvm_hyp.h

@@ -115,7 +115,12 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
 #endif
 
+extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val);
 extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val);
 extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val);
 
 #endif /* __ARM64_KVM_HYP_H__ */

arch/arm64/kvm/arm.c

@@ -622,6 +622,14 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 
 	ret = kvm_arm_pmu_v3_enable(vcpu);
 
+	/*
+	 * Initialize traps for protected VMs.
+	 * NOTE: Move to run in EL2 directly, rather than via a hypercall, once
+	 * the code is in place for first run initialization at EL2.
+	 */
+	if (kvm_vm_is_protected(kvm))
+		kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);
+
 	return ret;
 }
 
@@ -1819,8 +1827,13 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits)
 	void *addr = phys_to_virt(hyp_mem_base);
 	int ret;
 
+	kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+	kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
+	kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1);
+	kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1);
 	kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1);
 
 	ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP);
 	if (ret)

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_FAULT_H__
+#define __ARM64_KVM_HYP_FAULT_H__
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg_par();
+	if (!__kvm_at("s1e1r", far))
+		tmp = read_sysreg_par();
+	else
+		tmp = SYS_PAR_EL1_F; /* back to the guest */
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & SYS_PAR_EL1_F))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = PAR_TO_HPFAR(tmp);
+	return true;
+}
+
+static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+{
+	u64 hpfar, far;
+
+	far = read_sysreg_el2(SYS_FAR);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	fault->far_el2 = far;
+	fault->hpfar_el2 = hpfar;
+	return true;
+}
+
+#endif

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

@@ -8,6 +8,7 @@
 #define __ARM64_KVM_HYP_SWITCH_H__
 
 #include <hyp/adjust_pc.h>
+#include <hyp/fault.h>
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
@@ -133,78 +134,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
-	u64 par, tmp;
-
-	/*
-	 * Resolve the IPA the hard way using the guest VA.
-	 *
-	 * Stage-1 translation already validated the memory access
-	 * rights. As such, we can use the EL1 translation regime, and
-	 * don't have to distinguish between EL0 and EL1 access.
-	 *
-	 * We do need to save/restore PAR_EL1 though, as we haven't
-	 * saved the guest context yet, and we may return early...
-	 */
-	par = read_sysreg_par();
-	if (!__kvm_at("s1e1r", far))
-		tmp = read_sysreg_par();
-	else
-		tmp = SYS_PAR_EL1_F; /* back to the guest */
-	write_sysreg(par, par_el1);
-
-	if (unlikely(tmp & SYS_PAR_EL1_F))
-		return false; /* Translation failed, back to guest */
-
-	/* Convert PAR to HPFAR format */
-	*hpfar = PAR_TO_HPFAR(tmp);
-	return true;
-}
-
-static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
-{
-	u64 hpfar, far;
-
-	far = read_sysreg_el2(SYS_FAR);
-
-	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
-	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
-	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
-		hpfar = read_sysreg(hpfar_el2);
-	}
-
-	fault->far_el2 = far;
-	fault->hpfar_el2 = hpfar;
-	return true;
-}
-
 static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 {
-	u8 ec;
-	u64 esr;
-
-	esr = vcpu->arch.fault.esr_el2;
-	ec = ESR_ELx_EC(esr);
-
-	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
-		return true;
-
-	return __get_fault_info(esr, &vcpu->arch.fault);
+	return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
 }
 
 static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu)
@@ -225,8 +157,13 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+/*
+ * We trap the first access to the FP/SIMD to save the host context and
+ * restore the guest context lazily.
+ * If FP/SIMD is not implemented, handle the trap and inject an undefined
+ * instruction exception to the guest. Similarly for trapped SVE accesses.
+ */
+static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest, sve_host;
 	u8 esr_ec;
@@ -244,9 +181,6 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	}
 
 	esr_ec = kvm_vcpu_trap_get_class(vcpu);
-	if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
-	    esr_ec != ESR_ELx_EC_SVE)
-		return false;
 
 	/* Don't handle SVE traps for non-SVE vcpus here: */
 	if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD)
@@ -348,14 +282,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 
 static inline bool esr_is_ptrauth_trap(u32 esr)
 {
-	u32 ec = ESR_ELx_EC(esr);
-
-	if (ec == ESR_ELx_EC_PAC)
-		return true;
-
-	if (ec != ESR_ELx_EC_SYS64)
-		return false;
-
 	switch (esr_sys64_to_sysreg(esr)) {
 	case SYS_APIAKEYLO_EL1:
 	case SYS_APIAKEYHI_EL1:
@@ -384,13 +310,12 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
 
 DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 
-static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm_cpu_context *ctxt;
 	u64 val;
 
-	if (!vcpu_has_ptrauth(vcpu) ||
-	    !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+	if (!vcpu_has_ptrauth(vcpu))
 		return false;
 
 	ctxt = this_cpu_ptr(&kvm_hyp_ctxt);
@@ -409,6 +334,90 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
+		return true;
+
+	if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+		return kvm_hyp_handle_ptrauth(vcpu, exit_code);
+
+	return false;
+}
+
+static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
+		return true;
+
+	return false;
+}
+
+static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	return false;
+}
+
+static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+		bool valid;
+
+		valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+			kvm_vcpu_dabt_isvalid(vcpu) &&
+			!kvm_vcpu_abt_issea(vcpu) &&
+			!kvm_vcpu_abt_iss1tw(vcpu);
+
+		if (valid) {
+			int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+			if (ret == 1)
+				return true;
+
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
+		}
+	}
+
+	return false;
+}
+
+typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
+
+/*
+ * Allow the hypervisor to handle the exit with an exit handler if it has one.
+ *
+ * Returns true if the hypervisor handled the exit, and control should go back
+ * to the guest, or false if it hasn't.
+ */
+static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
+	exit_handler_fn fn;
+
+	fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
+
+	if (fn)
+		return fn(vcpu, exit_code);
+
+	return false;
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -443,59 +452,9 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
-	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
-	    handle_tx2_tvm(vcpu))
+	/* Check if there's an exit handler and allow it to handle the exit. */
+	if (kvm_hyp_handle_exit(vcpu, exit_code))
 		goto guest;
-
-	/*
-	 * We trap the first access to the FP/SIMD to save the host context
-	 * and restore the guest context lazily.
-	 * If FP/SIMD is not implemented, handle the trap and inject an
-	 * undefined instruction exception to the guest.
-	 * Similarly for trapped SVE accesses.
-	 */
-	if (__hyp_handle_fpsimd(vcpu))
-		goto guest;
-
-	if (__hyp_handle_ptrauth(vcpu))
-		goto guest;
-
-	if (!__populate_fault_info(vcpu))
-		goto guest;
-
-	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
-		bool valid;
-
-		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
-			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
-			kvm_vcpu_dabt_isvalid(vcpu) &&
-			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_abt_iss1tw(vcpu);
-
-		if (valid) {
-			int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
-			if (ret == 1)
-				goto guest;
-
-			/* Promote an illegal access to an SError.*/
-			if (ret == -1)
-				*exit_code = ARM_EXCEPTION_EL1_SERROR;
-
-			goto exit;
-		}
-	}
-
-	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
-		int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
-		if (ret == 1)
-			goto guest;
-	}
-
 exit:
 	/* Return to the host kernel and handle the exit */
 	return false;

arch/arm64/kvm/hyp/include/nvhe/fixed_config.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#ifndef __ARM64_KVM_FIXED_CONFIG_H__
+#define __ARM64_KVM_FIXED_CONFIG_H__
+
+#include <asm/sysreg.h>
+
+/*
+ * This file contains definitions for features to be allowed or restricted for
+ * guest virtual machines, depending on the mode KVM is running in and on the
+ * type of guest that is running.
+ *
+ * The ALLOW masks represent a bitmask of feature fields that are allowed
+ * without any restrictions as long as they are supported by the system.
+ *
+ * The RESTRICT_UNSIGNED masks, if present, represent unsigned fields for
+ * features that are restricted to support at most the specified feature.
+ *
+ * If a feature field is not present in either, than it is not supported.
+ *
+ * The approach taken for protected VMs is to allow features that are:
+ * - Needed by common Linux distributions (e.g., floating point)
+ * - Trivial to support, e.g., supporting the feature does not introduce or
+ * require tracking of additional state in KVM
+ * - Cannot be trapped or prevent the guest from using anyway
+ */
+
+/*
+ * Allow for protected VMs:
+ * - Floating-point and Advanced SIMD
+ * - Data Independent Timing
+ */
+#define PVM_ID_AA64PFR0_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64PFR0_FP) | \
+	ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD) | \
+	ARM64_FEATURE_MASK(ID_AA64PFR0_DIT) \
+	)
+
+/*
+ * Restrict to the following *unsigned* features for protected VMs:
+ * - AArch64 guests only (no support for AArch32 guests):
+ *	AArch32 adds complexity in trap handling, emulation, condition codes,
+ *	etc...
+ * - RAS (v1)
+ *	Supported by KVM
+ */
+#define PVM_ID_AA64PFR0_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL2), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL3), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), ID_AA64PFR0_RAS_V1) \
+	)
+
+/*
+ * Allow for protected VMs:
+ * - Branch Target Identification
+ * - Speculative Store Bypassing
+ */
+#define PVM_ID_AA64PFR1_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64PFR1_BT) | \
+	ARM64_FEATURE_MASK(ID_AA64PFR1_SSBS) \
+	)
+
+/*
+ * Allow for protected VMs:
+ * - Mixed-endian
+ * - Distinction between Secure and Non-secure Memory
+ * - Mixed-endian at EL0 only
+ * - Non-context synchronizing exception entry and exit
+ */
+#define PVM_ID_AA64MMFR0_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR0_SNSMEM) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL0) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR0_EXS) \
+	)
+
+/*
+ * Restrict to the following *unsigned* features for protected VMs:
+ * - 40-bit IPA
+ * - 16-bit ASID
+ */
+#define PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_PARANGE), ID_AA64MMFR0_PARANGE_40) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_ASID), ID_AA64MMFR0_ASID_16) \
+	)
+
+/*
+ * Allow for protected VMs:
+ * - Hardware translation table updates to Access flag and Dirty state
+ * - Number of VMID bits from CPU
+ * - Hierarchical Permission Disables
+ * - Privileged Access Never
+ * - SError interrupt exceptions from speculative reads
+ * - Enhanced Translation Synchronization
+ */
+#define PVM_ID_AA64MMFR1_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_HADBS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_VMIDBITS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_HPD) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_PAN) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_SPECSEI) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_ETS) \
+	)
+
+/*
+ * Allow for protected VMs:
+ * - Common not Private translations
+ * - User Access Override
+ * - IESB bit in the SCTLR_ELx registers
+ * - Unaligned single-copy atomicity and atomic functions
+ * - ESR_ELx.EC value on an exception by read access to feature ID space
+ * - TTL field in address operations.
+ * - Break-before-make sequences when changing translation block size
+ * - E0PDx mechanism
+ */
+#define PVM_ID_AA64MMFR2_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_CNP) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_UAO) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_IESB) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_AT) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_IDS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_TTL) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_BBM) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR2_E0PD) \
+	)
+
+/*
+ * No support for Scalable Vectors for protected VMs:
+ *	Requires additional support from KVM, e.g., context-switching and
+ *	trapping at EL2
+ */
+#define PVM_ID_AA64ZFR0_ALLOW (0ULL)
+
+/*
+ * No support for debug, including breakpoints, and watchpoints for protected
+ * VMs:
+ *	The Arm architecture mandates support for at least the Armv8 debug
+ *	architecture, which would include at least 2 hardware breakpoints and
+ *	watchpoints. Providing that support to protected guests adds
+ *	considerable state and complexity. Therefore, the reserved value of 0 is
+ *	used for debug-related fields.
+ */
+#define PVM_ID_AA64DFR0_ALLOW (0ULL)
+#define PVM_ID_AA64DFR1_ALLOW (0ULL)
+
+/*
+ * No support for implementation defined features.
+ */
+#define PVM_ID_AA64AFR0_ALLOW (0ULL)
+#define PVM_ID_AA64AFR1_ALLOW (0ULL)
+
+/*
+ * No restrictions on instructions implemented in AArch64.
+ */
+#define PVM_ID_AA64ISAR0_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_AES) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA1) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA2) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_CRC32) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_RDM) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA3) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_SM3) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_SM4) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_DP) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_FHM) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_TS) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_TLB) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR0_RNDR) \
+	)
+
+#define PVM_ID_AA64ISAR1_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_DPB) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_API) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_JSCVT) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_FCMA) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_LRCPC) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_FRINTTS) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_SB) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_SPECRES) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_BF16) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_DGH) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR1_I8MM) \
+	)
+
+u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id);
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
+int kvm_check_pvm_sysreg_table(void);
+
+#endif /* __ARM64_KVM_FIXED_CONFIG_H__ */

arch/arm64/kvm/hyp/include/nvhe/trap_handler.h

@@ -15,4 +15,6 @@
 #define DECLARE_REG(type, name, ctxt, reg)	\
 				type name = (type)cpu_reg(ctxt, (reg))
 
+void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -14,7 +14,7 @@ lib-objs := $(addprefix ../../../lib/, $(lib-objs))
 
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
 	 hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o page_alloc.o \
-	 cache.o setup.o mm.o mem_protect.o
+	 cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o
 obj-y += $(lib-objs)

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -4,7 +4,7 @@
  * Author: Andrew Scull <ascull@google.com>
  */
 
-#include <hyp/switch.h>
+#include <hyp/adjust_pc.h>
 
 #include <asm/pgtable-types.h>
 #include <asm/kvm_asm.h>
@@ -160,6 +160,14 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
 {
 	cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
 }
+
+static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+
+	__pkvm_vcpu_init_traps(kern_hyp_va(vcpu));
+}
+
 typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 #define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x
@@ -187,6 +195,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__vgic_v3_write_vmcr),
 	HANDLE_FUNC(__vgic_v3_save_aprs),
 	HANDLE_FUNC(__vgic_v3_restore_aprs),
+	HANDLE_FUNC(__pkvm_vcpu_init_traps),
 };
 
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)

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

@@ -11,7 +11,7 @@
 #include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
-#include <hyp/switch.h>
+#include <hyp/fault.h>
 
 #include <nvhe/gfp.h>
 #include <nvhe/memory.h>
@@ -25,12 +25,6 @@ struct host_kvm host_kvm;
 
 static struct hyp_pool host_s2_pool;
 
-/*
- * Copies of the host's CPU features registers holding sanitized values.
- */
-u64 id_aa64mmfr0_el1_sys_val;
-u64 id_aa64mmfr1_el1_sys_val;
-
 const u8 pkvm_hyp_id = 1;
 
 static void *host_s2_zalloc_pages_exact(size_t size)

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <nvhe/fixed_config.h>
+#include <nvhe/trap_handler.h>
+
+/*
+ * Set trap register values based on features in ID_AA64PFR0.
+ */
+static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1);
+	u64 hcr_set = HCR_RW;
+	u64 hcr_clear = 0;
+	u64 cptr_set = 0;
+
+	/* Protected KVM does not support AArch32 guests. */
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0),
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+
+	/*
+	 * Linux guests assume support for floating-point and Advanced SIMD. Do
+	 * not change the trapping behavior for these from the KVM default.
+	 */
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+				PVM_ID_AA64PFR0_ALLOW));
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+				PVM_ID_AA64PFR0_ALLOW));
+
+	/* Trap RAS unless all current versions are supported */
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), feature_ids) <
+	    ID_AA64PFR0_RAS_V1P1) {
+		hcr_set |= HCR_TERR | HCR_TEA;
+		hcr_clear |= HCR_FIEN;
+	}
+
+	/* Trap AMU */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_AMU), feature_ids)) {
+		hcr_clear |= HCR_AMVOFFEN;
+		cptr_set |= CPTR_EL2_TAM;
+	}
+
+	/* Trap SVE */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_SVE), feature_ids))
+		cptr_set |= CPTR_EL2_TZ;
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+	vcpu->arch.hcr_el2 &= ~hcr_clear;
+	vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64PFR1.
+ */
+static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1);
+	u64 hcr_set = 0;
+	u64 hcr_clear = 0;
+
+	/* Memory Tagging: Trap and Treat as Untagged if not supported. */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), feature_ids)) {
+		hcr_set |= HCR_TID5;
+		hcr_clear |= HCR_DCT | HCR_ATA;
+	}
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+	vcpu->arch.hcr_el2 &= ~hcr_clear;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64DFR0.
+ */
+static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1);
+	u64 mdcr_set = 0;
+	u64 mdcr_clear = 0;
+	u64 cptr_set = 0;
+
+	/* Trap/constrain PMU */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMUVER), feature_ids)) {
+		mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
+		mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME |
+			      MDCR_EL2_HPMN_MASK;
+	}
+
+	/* Trap Debug */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), feature_ids))
+		mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE;
+
+	/* Trap OS Double Lock */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DOUBLELOCK), feature_ids))
+		mdcr_set |= MDCR_EL2_TDOSA;
+
+	/* Trap SPE */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMSVER), feature_ids)) {
+		mdcr_set |= MDCR_EL2_TPMS;
+		mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+	}
+
+	/* Trap Trace Filter */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACE_FILT), feature_ids))
+		mdcr_set |= MDCR_EL2_TTRF;
+
+	/* Trap Trace */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACEVER), feature_ids))
+		cptr_set |= CPTR_EL2_TTA;
+
+	vcpu->arch.mdcr_el2 |= mdcr_set;
+	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
+	vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR0.
+ */
+static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1);
+	u64 mdcr_set = 0;
+
+	/* Trap Debug Communications Channel registers */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_FGT), feature_ids))
+		mdcr_set |= MDCR_EL2_TDCC;
+
+	vcpu->arch.mdcr_el2 |= mdcr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR1.
+ */
+static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1);
+	u64 hcr_set = 0;
+
+	/* Trap LOR */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_LOR), feature_ids))
+		hcr_set |= HCR_TLOR;
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+}
+
+/*
+ * Set baseline trap register values.
+ */
+static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
+{
+	const u64 hcr_trap_feat_regs = HCR_TID3;
+	const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1;
+
+	/*
+	 * Always trap:
+	 * - Feature id registers: to control features exposed to guests
+	 * - Implementation-defined features
+	 */
+	vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef;
+
+	/* Clear res0 and set res1 bits to trap potential new features. */
+	vcpu->arch.hcr_el2 &= ~(HCR_RES0);
+	vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0);
+	vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
+	vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
+}
+
+/*
+ * Initialize trap register values for protected VMs.
+ */
+void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
+{
+	pvm_init_trap_regs(vcpu);
+	pvm_init_traps_aa64pfr0(vcpu);
+	pvm_init_traps_aa64pfr1(vcpu);
+	pvm_init_traps_aa64dfr0(vcpu);
+	pvm_init_traps_aa64mmfr0(vcpu);
+	pvm_init_traps_aa64mmfr1(vcpu);
+}

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

@@ -10,6 +10,7 @@
 #include <asm/kvm_pgtable.h>
 
 #include <nvhe/early_alloc.h>
+#include <nvhe/fixed_config.h>
 #include <nvhe/gfp.h>
 #include <nvhe/memory.h>
 #include <nvhe/mem_protect.h>
@@ -260,6 +261,8 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 	void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
 	int ret;
 
+	BUG_ON(kvm_check_pvm_sysreg_table());
+
 	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
 		return -EINVAL;
 

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

@@ -27,6 +27,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 
+#include <nvhe/fixed_config.h>
 #include <nvhe/mem_protect.h>
 
 /* Non-VHE specific context */
@@ -158,6 +159,101 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 		write_sysreg(pmu->events_host, pmcntenset_el0);
 }
 
+/**
+ * Handler for protected VM MSR, MRS or System instruction execution in AArch64.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/*
+	 * Make sure we handle the exit for workarounds and ptrauth
+	 * before the pKVM handling, as the latter could decide to
+	 * UNDEF.
+	 */
+	return (kvm_hyp_handle_sysreg(vcpu, exit_code) ||
+		kvm_handle_pvm_sysreg(vcpu, exit_code));
+}
+
+/**
+ * Handler for protected floating-point and Advanced SIMD accesses.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/* Linux guests assume support for floating-point and Advanced SIMD. */
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+				PVM_ID_AA64PFR0_ALLOW));
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+				PVM_ID_AA64PFR0_ALLOW));
+
+	return kvm_hyp_handle_fpsimd(vcpu, exit_code);
+}
+
+static const exit_handler_fn hyp_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
+	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn pvm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_SYS64]		= kvm_handle_pvm_sys64,
+	[ESR_ELx_EC_SVE]		= kvm_handle_pvm_restricted,
+	[ESR_ELx_EC_FP_ASIMD]		= kvm_handle_pvm_fpsimd,
+	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
+	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(kvm_vm_is_protected(kern_hyp_va(vcpu->kvm))))
+		return pvm_exit_handlers;
+
+	return hyp_exit_handlers;
+}
+
+/*
+ * Some guests (e.g., protected VMs) are not be allowed to run in AArch32.
+ * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a
+ * guest from dropping to AArch32 EL0 if implemented by the CPU. If the
+ * hypervisor spots a guest in such a state ensure it is handled, and don't
+ * trust the host to spot or fix it.  The check below is based on the one in
+ * kvm_arch_vcpu_ioctl_run().
+ *
+ * Returns false if the guest ran in AArch32 when it shouldn't have, and
+ * thus should exit to the host, or true if a the guest run loop can continue.
+ */
+static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+
+	if (kvm_vm_is_protected(kvm) && vcpu_mode_is_32bit(vcpu)) {
+		/*
+		 * As we have caught the guest red-handed, decide that it isn't
+		 * fit for purpose anymore by making the vcpu invalid. The VMM
+		 * can try and fix it by re-initializing the vcpu with
+		 * KVM_ARM_VCPU_INIT, however, this is likely not possible for
+		 * protected VMs.
+		 */
+		vcpu->arch.target = -1;
+		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
+		*exit_code |= ARM_EXCEPTION_IL;
+		return false;
+	}
+
+	return true;
+}
+
 /* Switch to the guest for legacy non-VHE systems */
 int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
@@ -220,6 +316,9 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
+		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
+			break;
+
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#include <hyp/adjust_pc.h>
+
+#include <nvhe/fixed_config.h>
+
+#include "../../sys_regs.h"
+
+/*
+ * Copies of the host's CPU features registers holding sanitized values at hyp.
+ */
+u64 id_aa64pfr0_el1_sys_val;
+u64 id_aa64pfr1_el1_sys_val;
+u64 id_aa64isar0_el1_sys_val;
+u64 id_aa64isar1_el1_sys_val;
+u64 id_aa64mmfr0_el1_sys_val;
+u64 id_aa64mmfr1_el1_sys_val;
+u64 id_aa64mmfr2_el1_sys_val;
+
+/*
+ * Inject an unknown/undefined exception to an AArch64 guest while most of its
+ * sysregs are live.
+ */
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+
+	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 |
+			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
+			     KVM_ARM64_PENDING_EXCEPTION);
+
+	__kvm_adjust_pc(vcpu);
+
+	write_sysreg_el1(esr, SYS_ESR);
+	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
+	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+	write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+}
+
+/*
+ * Returns the restricted features values of the feature register based on the
+ * limitations in restrict_fields.
+ * A feature id field value of 0b0000 does not impose any restrictions.
+ * Note: Use only for unsigned feature field values.
+ */
+static u64 get_restricted_features_unsigned(u64 sys_reg_val,
+					    u64 restrict_fields)
+{
+	u64 value = 0UL;
+	u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+
+	/*
+	 * According to the Arm Architecture Reference Manual, feature fields
+	 * use increasing values to indicate increases in functionality.
+	 * Iterate over the restricted feature fields and calculate the minimum
+	 * unsigned value between the one supported by the system, and what the
+	 * value is being restricted to.
+	 */
+	while (sys_reg_val && restrict_fields) {
+		value |= min(sys_reg_val & mask, restrict_fields & mask);
+		sys_reg_val &= ~mask;
+		restrict_fields &= ~mask;
+		mask <<= ARM64_FEATURE_FIELD_BITS;
+	}
+
+	return value;
+}
+
+/*
+ * Functions that return the value of feature id registers for protected VMs
+ * based on allowed features, system features, and KVM support.
+ */
+
+static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+	u64 set_mask = 0;
+	u64 allow_mask = PVM_ID_AA64PFR0_ALLOW;
+
+	if (!vcpu_has_sve(vcpu))
+		allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE);
+
+	set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val,
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED);
+
+	/* Spectre and Meltdown mitigation in KVM */
+	set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2),
+			       (u64)kvm->arch.pfr0_csv2);
+	set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3),
+			       (u64)kvm->arch.pfr0_csv3);
+
+	return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask;
+}
+
+static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+	u64 allow_mask = PVM_ID_AA64PFR1_ALLOW;
+
+	if (!kvm_has_mte(kvm))
+		allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
+
+	return id_aa64pfr1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for Scalable Vectors, therefore, hyp has no sanitized
+	 * copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for debug, including breakpoints, and watchpoints,
+	 * therefore, pKVM has no sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for debug, therefore, hyp has no sanitized copy of the
+	 * feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for implementation defined features, therefore, hyp has no
+	 * sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for implementation defined features, therefore, hyp has no
+	 * sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW;
+}
+
+static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu)
+{
+	u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW;
+
+	if (!vcpu_has_ptrauth(vcpu))
+		allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_API) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI));
+
+	return id_aa64isar1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu)
+{
+	u64 set_mask;
+
+	set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val,
+		PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED);
+
+	return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW;
+}
+
+static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW;
+}
+
+/* Read a sanitized cpufeature ID register by its encoding */
+u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
+{
+	switch (id) {
+	case SYS_ID_AA64PFR0_EL1:
+		return get_pvm_id_aa64pfr0(vcpu);
+	case SYS_ID_AA64PFR1_EL1:
+		return get_pvm_id_aa64pfr1(vcpu);
+	case SYS_ID_AA64ZFR0_EL1:
+		return get_pvm_id_aa64zfr0(vcpu);
+	case SYS_ID_AA64DFR0_EL1:
+		return get_pvm_id_aa64dfr0(vcpu);
+	case SYS_ID_AA64DFR1_EL1:
+		return get_pvm_id_aa64dfr1(vcpu);
+	case SYS_ID_AA64AFR0_EL1:
+		return get_pvm_id_aa64afr0(vcpu);
+	case SYS_ID_AA64AFR1_EL1:
+		return get_pvm_id_aa64afr1(vcpu);
+	case SYS_ID_AA64ISAR0_EL1:
+		return get_pvm_id_aa64isar0(vcpu);
+	case SYS_ID_AA64ISAR1_EL1:
+		return get_pvm_id_aa64isar1(vcpu);
+	case SYS_ID_AA64MMFR0_EL1:
+		return get_pvm_id_aa64mmfr0(vcpu);
+	case SYS_ID_AA64MMFR1_EL1:
+		return get_pvm_id_aa64mmfr1(vcpu);
+	case SYS_ID_AA64MMFR2_EL1:
+		return get_pvm_id_aa64mmfr2(vcpu);
+	default:
+		/*
+		 * Should never happen because all cases are covered in
+		 * pvm_sys_reg_descs[].
+		 */
+		WARN_ON(1);
+		break;
+	}
+
+	return 0;
+}
+
+static u64 read_id_reg(const struct kvm_vcpu *vcpu,
+		       struct sys_reg_desc const *r)
+{
+	return pvm_read_id_reg(vcpu, reg_to_encoding(r));
+}
+
+/* Handler to RAZ/WI sysregs */
+static bool pvm_access_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	if (!p->is_write)
+		p->regval = 0;
+
+	return true;
+}
+
+/*
+ * Accessor for AArch32 feature id registers.
+ *
+ * The value of these registers is "unknown" according to the spec if AArch32
+ * isn't supported.
+ */
+static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu,
+				  struct sys_reg_params *p,
+				  const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		inject_undef64(vcpu);
+		return false;
+	}
+
+	/*
+	 * No support for AArch32 guests, therefore, pKVM has no sanitized copy
+	 * of AArch32 feature id registers.
+	 */
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+		     PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_ELx_64BIT_ONLY);
+
+	return pvm_access_raz_wi(vcpu, p, r);
+}
+
+/*
+ * Accessor for AArch64 feature id registers.
+ *
+ * If access is allowed, set the regval to the protected VM's view of the
+ * register and return true.
+ * Otherwise, inject an undefined exception and return false.
+ */
+static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu,
+				  struct sys_reg_params *p,
+				  const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		inject_undef64(vcpu);
+		return false;
+	}
+
+	p->regval = read_id_reg(vcpu, r);
+	return true;
+}
+
+static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
+			     struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	/* pVMs only support GICv3. 'nuf said. */
+	if (!p->is_write)
+		p->regval = ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE;
+
+	return true;
+}
+
+/* Mark the specified system register as an AArch32 feature id register. */
+#define AARCH32(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch32 }
+
+/* Mark the specified system register as an AArch64 feature id register. */
+#define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }
+
+/* Mark the specified system register as Read-As-Zero/Write-Ignored */
+#define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }
+
+/* Mark the specified system register as not being handled in hyp. */
+#define HOST_HANDLED(REG) { SYS_DESC(REG), .access = NULL }
+
+/*
+ * Architected system registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * NOTE: Anything not explicitly listed here is *restricted by default*, i.e.,
+ * it will lead to injecting an exception into the guest.
+ */
+static const struct sys_reg_desc pvm_sys_reg_descs[] = {
+	/* Cache maintenance by set/way operations are restricted. */
+
+	/* Debug and Trace Registers are restricted. */
+
+	/* AArch64 mappings of the AArch32 ID registers */
+	/* CRm=1 */
+	AARCH32(SYS_ID_PFR0_EL1),
+	AARCH32(SYS_ID_PFR1_EL1),
+	AARCH32(SYS_ID_DFR0_EL1),
+	AARCH32(SYS_ID_AFR0_EL1),
+	AARCH32(SYS_ID_MMFR0_EL1),
+	AARCH32(SYS_ID_MMFR1_EL1),
+	AARCH32(SYS_ID_MMFR2_EL1),
+	AARCH32(SYS_ID_MMFR3_EL1),
+
+	/* CRm=2 */
+	AARCH32(SYS_ID_ISAR0_EL1),
+	AARCH32(SYS_ID_ISAR1_EL1),
+	AARCH32(SYS_ID_ISAR2_EL1),
+	AARCH32(SYS_ID_ISAR3_EL1),
+	AARCH32(SYS_ID_ISAR4_EL1),
+	AARCH32(SYS_ID_ISAR5_EL1),
+	AARCH32(SYS_ID_MMFR4_EL1),
+	AARCH32(SYS_ID_ISAR6_EL1),
+
+	/* CRm=3 */
+	AARCH32(SYS_MVFR0_EL1),
+	AARCH32(SYS_MVFR1_EL1),
+	AARCH32(SYS_MVFR2_EL1),
+	AARCH32(SYS_ID_PFR2_EL1),
+	AARCH32(SYS_ID_DFR1_EL1),
+	AARCH32(SYS_ID_MMFR5_EL1),
+
+	/* AArch64 ID registers */
+	/* CRm=4 */
+	AARCH64(SYS_ID_AA64PFR0_EL1),
+	AARCH64(SYS_ID_AA64PFR1_EL1),
+	AARCH64(SYS_ID_AA64ZFR0_EL1),
+	AARCH64(SYS_ID_AA64DFR0_EL1),
+	AARCH64(SYS_ID_AA64DFR1_EL1),
+	AARCH64(SYS_ID_AA64AFR0_EL1),
+	AARCH64(SYS_ID_AA64AFR1_EL1),
+	AARCH64(SYS_ID_AA64ISAR0_EL1),
+	AARCH64(SYS_ID_AA64ISAR1_EL1),
+	AARCH64(SYS_ID_AA64MMFR0_EL1),
+	AARCH64(SYS_ID_AA64MMFR1_EL1),
+	AARCH64(SYS_ID_AA64MMFR2_EL1),
+
+	/* Scalable Vector Registers are restricted. */
+
+	RAZ_WI(SYS_ERRIDR_EL1),
+	RAZ_WI(SYS_ERRSELR_EL1),
+	RAZ_WI(SYS_ERXFR_EL1),
+	RAZ_WI(SYS_ERXCTLR_EL1),
+	RAZ_WI(SYS_ERXSTATUS_EL1),
+	RAZ_WI(SYS_ERXADDR_EL1),
+	RAZ_WI(SYS_ERXMISC0_EL1),
+	RAZ_WI(SYS_ERXMISC1_EL1),
+
+	/* Performance Monitoring Registers are restricted. */
+
+	/* Limited Ordering Regions Registers are restricted. */
+
+	HOST_HANDLED(SYS_ICC_SGI1R_EL1),
+	HOST_HANDLED(SYS_ICC_ASGI1R_EL1),
+	HOST_HANDLED(SYS_ICC_SGI0R_EL1),
+	{ SYS_DESC(SYS_ICC_SRE_EL1), .access = pvm_gic_read_sre, },
+
+	HOST_HANDLED(SYS_CCSIDR_EL1),
+	HOST_HANDLED(SYS_CLIDR_EL1),
+	HOST_HANDLED(SYS_CSSELR_EL1),
+	HOST_HANDLED(SYS_CTR_EL0),
+
+	/* Performance Monitoring Registers are restricted. */
+
+	/* Activity Monitoring Registers are restricted. */
+
+	HOST_HANDLED(SYS_CNTP_TVAL_EL0),
+	HOST_HANDLED(SYS_CNTP_CTL_EL0),
+	HOST_HANDLED(SYS_CNTP_CVAL_EL0),
+
+	/* Performance Monitoring Registers are restricted. */
+};
+
+/*
+ * Checks that the sysreg table is unique and in-order.
+ *
+ * Returns 0 if the table is consistent, or 1 otherwise.
+ */
+int kvm_check_pvm_sysreg_table(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_descs); i++) {
+		if (cmp_sys_reg(&pvm_sys_reg_descs[i-1], &pvm_sys_reg_descs[i]) >= 0)
+			return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Handler for protected VM MSR, MRS or System instruction execution.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't, to be handled by the host.
+ */
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	const struct sys_reg_desc *r;
+	struct sys_reg_params params;
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
+	int Rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	params = esr_sys64_to_params(esr);
+	params.regval = vcpu_get_reg(vcpu, Rt);
+
+	r = find_reg(&params, pvm_sys_reg_descs, ARRAY_SIZE(pvm_sys_reg_descs));
+
+	/* Undefined (RESTRICTED). */
+	if (r == NULL) {
+		inject_undef64(vcpu);
+		return true;
+	}
+
+	/* Handled by the host (HOST_HANDLED) */
+	if (r->access == NULL)
+		return false;
+
+	/* Handled by hyp: skip instruction if instructed to do so. */
+	if (r->access(vcpu, &params, r))
+		__kvm_skip_instr(vcpu);
+
+	if (!params.is_write)
+		vcpu_set_reg(vcpu, Rt, params.regval);
+
+	return true;
+}
+
+/**
+ * Handler for protected VM restricted exceptions.
+ *
+ * Inject an undefined exception into the guest and return true to indicate that
+ * the hypervisor has handled the exit, and control should go back to the guest.
+ */
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	inject_undef64(vcpu);
+	return true;
+}

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

@@ -96,6 +96,22 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
 	__deactivate_traps_common(vcpu);
 }
 
+static const exit_handler_fn hyp_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
+	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+{
+	return hyp_exit_handlers;
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/sys_regs.c

@@ -1087,14 +1087,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		}
 		break;
 	case SYS_ID_AA64PFR1_EL1:
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
-		if (kvm_has_mte(vcpu->kvm)) {
-			u64 pfr, mte;
-
-			pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
-			mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT);
-			val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), mte);
-		}
+		if (!kvm_has_mte(vcpu->kvm))
+			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
 		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))