diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c73b4ce1abce..7c347ab3a555 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -71,8 +71,10 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
-	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_vmcr_aprs,
-	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
+	__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_init_shadow,
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_shadow,
 };
@@ -213,6 +215,8 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_gic_config(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
 
 extern u64 __kvm_get_mdcr_el2(void);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 328ce108d0f1..c8d51e2db879 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -61,8 +61,8 @@ void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if);
-void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if);
-void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if);
+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__
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b65a2d3dcc23..6ed7ef7785fe 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -398,14 +398,15 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 	 * doorbells to be signalled, should an interrupt become pending.
 	 */
 	preempt_disable();
-	kvm_vgic_put(vcpu, true);
+	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
 	preempt_enable();
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
-	kvm_vgic_load(vcpu);
+	vgic_v4_load(vcpu);
 	preempt_enable();
 }
 
@@ -459,7 +460,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	if (has_vhe())
 		kvm_vcpu_put_sysregs_vhe(vcpu);
 	kvm_timer_vcpu_put(vcpu);
-	kvm_vgic_put(vcpu, false);
+	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
 
 	vcpu->cpu = -1;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index d9d9fa27fd8e..46ea55349cba 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -360,6 +360,16 @@ static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
 }
 
+static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
+{
+	cpu_reg(host_ctxt, 1) = __vgic_v3_read_vmcr();
+}
+
+static void handle___vgic_v3_write_vmcr(struct kvm_cpu_context *host_ctxt)
+{
+	__vgic_v3_write_vmcr(cpu_reg(host_ctxt, 1));
+}
+
 static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
 {
 	__vgic_v3_init_lrs();
@@ -370,18 +380,18 @@ static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
 }
 
-static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
 
-	__vgic_v3_save_vmcr_aprs(kern_hyp_va(cpu_if));
+	__vgic_v3_save_aprs(kern_hyp_va(cpu_if));
 }
 
-static void handle___vgic_v3_restore_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
 
-	__vgic_v3_restore_vmcr_aprs(kern_hyp_va(cpu_if));
+	__vgic_v3_restore_aprs(kern_hyp_va(cpu_if));
 }
 
 static void handle___pkvm_init(struct kvm_cpu_context *host_ctxt)
@@ -478,8 +488,10 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
-	HANDLE_FUNC(__vgic_v3_save_vmcr_aprs),
-	HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs),
+	HANDLE_FUNC(__vgic_v3_read_vmcr),
+	HANDLE_FUNC(__vgic_v3_write_vmcr),
+	HANDLE_FUNC(__vgic_v3_save_aprs),
+	HANDLE_FUNC(__vgic_v3_restore_aprs),
 	HANDLE_FUNC(__pkvm_init_shadow),
 	HANDLE_FUNC(__pkvm_teardown_shadow),
 };
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 4c8ebcd31bb7..20db2f281cf2 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -330,7 +330,7 @@ void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(0, ICH_HCR_EL2);
 }
 
-static void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -363,7 +363,7 @@ static void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -455,35 +455,16 @@ u64 __vgic_v3_get_gic_config(void)
 	return val;
 }
 
-static u64 __vgic_v3_read_vmcr(void)
+u64 __vgic_v3_read_vmcr(void)
 {
 	return read_gicreg(ICH_VMCR_EL2);
 }
 
-static void __vgic_v3_write_vmcr(u32 vmcr)
+void __vgic_v3_write_vmcr(u32 vmcr)
 {
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
-void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
-{
-	__vgic_v3_save_aprs(cpu_if);
-	if (cpu_if->vgic_sre)
-		cpu_if->vgic_vmcr = __vgic_v3_read_vmcr();
-}
-
-void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
-{
-	/*
-	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
-	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
-	 * VMCR_EL2 save/restore in the world switch.
-	 */
-	if (cpu_if->vgic_sre)
-		__vgic_v3_write_vmcr(cpu_if->vgic_vmcr);
-	__vgic_v3_restore_aprs(cpu_if);
-}
-
 static int __vgic_v3_bpr_min(void)
 {
 	/* See Pseudocode for VPriorityGroup */
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index 4e8bb90bd96f..645648349c99 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -470,10 +470,17 @@ void vgic_v2_load(struct kvm_vcpu *vcpu)
 		       kvm_vgic_global_state.vctrl_base + GICH_APR);
 }
 
-void vgic_v2_put(struct kvm_vcpu *vcpu, bool blocking)
+void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 
 	cpu_if->vgic_vmcr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VMCR);
+}
+
+void vgic_v2_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+
+	vgic_v2_vmcr_sync(vcpu);
 	cpu_if->vgic_apr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_APR);
 }
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 9fc83f9e8283..78cf674c1230 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -707,7 +707,15 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
+	/*
+	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
+	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
+	 * VMCR_EL2 save/restore in the world switch.
+	 */
+	if (likely(cpu_if->vgic_sre))
+		kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr);
+
+	kvm_call_hyp(__vgic_v3_restore_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(cpu_if);
@@ -715,13 +723,23 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 	WARN_ON(vgic_v4_load(vcpu));
 }
 
-void vgic_v3_put(struct kvm_vcpu *vcpu, bool blocking)
+void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	WARN_ON(vgic_v4_put(vcpu, blocking));
+	if (likely(cpu_if->vgic_sre))
+		cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr);
+}
 
-	kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
+void vgic_v3_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	WARN_ON(vgic_v4_put(vcpu, false));
+
+	vgic_v3_vmcr_sync(vcpu);
+
+	kvm_call_hyp(__vgic_v3_save_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_deactivate_traps(cpu_if);
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 0bf570eb4622..5dad4996cfb2 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -931,15 +931,26 @@ void kvm_vgic_load(struct kvm_vcpu *vcpu)
 		vgic_v3_load(vcpu);
 }
 
-void kvm_vgic_put(struct kvm_vcpu *vcpu, bool blocking)
+void kvm_vgic_put(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!vgic_initialized(vcpu->kvm)))
 		return;
 
 	if (kvm_vgic_global_state.type == VGIC_V2)
-		vgic_v2_put(vcpu, blocking);
+		vgic_v2_put(vcpu);
 	else
-		vgic_v3_put(vcpu, blocking);
+		vgic_v3_put(vcpu);
+}
+
+void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+		return;
+
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_vmcr_sync(vcpu);
+	else
+		vgic_v3_vmcr_sync(vcpu);
 }
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 947985b3b03e..3fd6c86a7ef3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -196,7 +196,8 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 
 void vgic_v2_init_lrs(void);
 void vgic_v2_load(struct kvm_vcpu *vcpu);
-void vgic_v2_put(struct kvm_vcpu *vcpu, bool blocking);
+void vgic_v2_put(struct kvm_vcpu *vcpu);
+void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu);
 
 void vgic_v2_save_state(struct kvm_vcpu *vcpu);
 void vgic_v2_restore_state(struct kvm_vcpu *vcpu);
@@ -226,7 +227,8 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
 bool vgic_v3_check_base(struct kvm *kvm);
 
 void vgic_v3_load(struct kvm_vcpu *vcpu);
-void vgic_v3_put(struct kvm_vcpu *vcpu, bool blocking);
+void vgic_v3_put(struct kvm_vcpu *vcpu);
+void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu);
 
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 65e09c3924be..bb30a6803d9f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -380,7 +380,8 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid);
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 
 void kvm_vgic_load(struct kvm_vcpu *vcpu);
-void kvm_vgic_put(struct kvm_vcpu *vcpu, bool blocking);
+void kvm_vgic_put(struct kvm_vcpu *vcpu);
+void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu);
 
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	((k)->arch.vgic.initialized)