diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 1375a53054b9584d80d3f49763662be1ccdd3151..c9cec01008c2e1f5e672a10c022237e0e6c21256 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -131,6 +131,45 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
+int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+	if (!vgic_supports_direct_msis(vcpu->kvm))
+		return 0;
+
+	return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false);
+}
+
+int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+	int err;
+
+	if (!vgic_supports_direct_msis(vcpu->kvm))
+		return 0;
+
+	/*
+	 * Before making the VPE resident, make sure the redistributor
+	 * corresponding to our current CPU expects us here. See the
+	 * doc in drivers/irqchip/irq-gic-v4.c to understand how this
+	 * turns into a VMOVP command at the ITS level.
+	 */
+	err = irq_set_affinity(irq, cpumask_of(smp_processor_id()));
+	if (err)
+		return err;
+
+	err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true);
+	if (err)
+		return err;
+
+	/*
+	 * Now that the VPE is resident, let's get rid of a potential
+	 * doorbell interrupt that would still be pending.
+	 */
+	err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false);
+
+	return err;
+}
+
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
 				     struct kvm_kernel_irq_routing_entry *irq_entry)
 {
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index d29e9121536643aabcfc8a7fd80b7ef4656bae2e..b168a328a9e0748052d506e63df613517a7f7e17 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -718,6 +718,8 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
+	WARN_ON(vgic_v4_sync_hwstate(vcpu));
+
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -730,6 +732,8 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(vgic_v4_flush_hwstate(vcpu));
+
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index bf03a9648fbb019cb0549e7d32e5c44dbb049e85..efbcf8f96f9c1a1bec87ce874103027c10de47ac 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -244,5 +244,7 @@ struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
+int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu);
+int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu);
 
 #endif