6 files changed, 39 insertions, 11 deletions
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 232b439cbaf3..ff8f4511df71 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
@@ -130,6 +131,7 @@
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 7f3c87f7a0ce..c31be7eda9df 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -107,7 +107,7 @@
 	isb					// Make sure SRE is now set
 	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
 	tbz	x0, #0, .Lskip_gicv3_\@		// and check that it sticks
-	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICH_HCR_EL2 to defaults
 .Lskip_gicv3_\@:
 .endm
 
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 7fd836bea7eb..3995652daf81 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -192,4 +192,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
 extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
 
+extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
+					unsigned long flags);
+#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap
+
 #endif	/* __ASM_IO_H */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d62405ce3e6d..f71358271b71 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -40,13 +40,26 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
 
 void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
 
+#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.hcr_el2 & HCR_RW);
 }
+#else
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED,
+			       &kvm->arch.flags));
+
+	return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+}
+#endif
 
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
@@ -72,15 +85,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 |= HCR_TVM;
 	}
 
-	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+	if (vcpu_el1_is_32bit(vcpu))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
-
-	/*
-	 * TID3: trap feature register accesses that we virtualise.
-	 * For now this is conditional, since no AArch32 feature regs
-	 * are currently virtualised.
-	 */
-	if (!vcpu_el1_is_32bit(vcpu))
+	else
+		/*
+		 * TID3: trap feature register accesses that we virtualise.
+		 * For now this is conditional, since no AArch32 feature regs
+		 * are currently virtualised.
+		 */
 		vcpu->arch.hcr_el2 |= HCR_TID3;
 
 	if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e3b25dc6c367..94a27a7520f4 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -127,6 +127,16 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_MTE_ENABLED			1
 	/* At least one vCPU has ran in the VM */
 #define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
+	/*
+	 * The following two bits are used to indicate the guest's EL1
+	 * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
+	 * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
+	 * Otherwise, the guest's EL1 register width has not yet been
+	 * determined yet.
+	 */
+#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED		3
+#define KVM_ARCH_FLAG_EL1_32BIT				4
+
 	unsigned long flags;
 
 	/*
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 94e147e5456c..dff2b483ea50 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -535,7 +535,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				 PMD_TYPE_TABLE)
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_SECT)
-#define pmd_leaf(pmd)		pmd_sect(pmd)
+#define pmd_leaf(pmd)		(pmd_present(pmd) && !pmd_table(pmd))
 #define pmd_bad(pmd)		(!pmd_table(pmd))
 
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
@@ -625,7 +625,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!pud_table(pud))
 #define pud_present(pud)	pte_present(pud_pte(pud))
-#define pud_leaf(pud)		pud_sect(pud)
+#define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
 
 static inline void set_pud(pud_t *pudp, pud_t pud)