diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index b736a452c2ca79d624055ebd5ba64555a28f89c1..661bd0344254d9968281e882ada51e3f91ae6e83 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -378,6 +378,8 @@ static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 
+#define kvm_arm_vcpu_loaded(vcpu)	(false)
+
 static inline int kvm_arm_config_vm(struct kvm *kvm, unsigned long type)
 {
 	if (type)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bb51607b190509cf73746139a1c21149bb92d4e0..62b6d044767489e9401fdccd378bdbacba6be030 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -584,6 +584,8 @@ void kvm_set_ipa_limit(void);
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 
+#define kvm_arm_vcpu_loaded(vcpu)	((vcpu)->arch.sysregs_loaded_on_cpu)
+
 int kvm_arm_config_vm(struct kvm *kvm, unsigned long type);
 
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index 18d6d5124397893dd978ab88a6fc7f4c3596fbdd..92c9ad6c0182ee1bfeaa9dfb1a4b2bfc9513b6cd 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -44,6 +44,26 @@ static const u8 return_offsets[8][2] = {
 	[7] = { 4, 4 },		/* FIQ, unused */
 };
 
+static bool pre_fault_synchronize(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	if (kvm_arm_vcpu_loaded(vcpu)) {
+		kvm_arch_vcpu_put(vcpu);
+		return true;
+	}
+
+	preempt_enable();
+	return false;
+}
+
+static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded)
+{
+	if (loaded) {
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+		preempt_enable();
+	}
+}
+
 /*
  * When an exception is taken, most CPSR fields are left unchanged in the
  * handler. However, some are explicitly overridden (e.g. M[4:0]).
@@ -166,7 +186,10 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 void kvm_inject_undef32(struct kvm_vcpu *vcpu)
 {
+	bool loaded = pre_fault_synchronize(vcpu);
+
 	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
+	post_fault_synchronize(vcpu, loaded);
 }
 
 /*
@@ -179,6 +202,9 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 	u32 vect_offset;
 	u32 *far, *fsr;
 	bool is_lpae;
+	bool loaded;
+
+	loaded = pre_fault_synchronize(vcpu);
 
 	if (is_pabt) {
 		vect_offset = 12;
@@ -202,6 +228,8 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
 		*fsr = DFSR_FSC_EXTABT_nLPAE;
 	}
+
+	post_fault_synchronize(vcpu, loaded);
 }
 
 void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr)