diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index 264d92da3240..370bd6c5e6cb 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -222,7 +222,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (used_lrs) {
+	if (used_lrs || cpu_if->its_vpe.its_vm) {
 		int i;
 		u32 elrsr;
 
@@ -247,7 +247,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	int i;
 
-	if (used_lrs) {
+	if (used_lrs || cpu_if->its_vpe.its_vm) {
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 
 		for (i = 0; i < used_lrs; i++)
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index abd9c7352677..3af69f2a3866 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -867,15 +867,21 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * either observe the new interrupt before or after doing this check,
 	 * and introducing additional synchronization mechanism doesn't change
 	 * this.
+	 *
+	 * Note that we still need to go through the whole thing if anything
+	 * can be directly injected (GICv4).
 	 */
-	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) &&
+	    !vgic_supports_direct_msis(vcpu->kvm))
 		return;
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
-	raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
-	vgic_flush_lr_state(vcpu);
-	raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+	if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
+		raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
+		vgic_flush_lr_state(vcpu);
+		raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+	}
 
 	if (can_access_vgic_from_kernel())
 		vgic_restore_state(vcpu);