diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index c01910d53f9e..117ba6db023d 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -87,6 +87,11 @@ static struct irq_domain *gic_domain;
 static const struct irq_domain_ops *vpe_domain_ops;
 static const struct irq_domain_ops *sgi_domain_ops;
 
+static bool has_v4_1(void)
+{
+	return !!sgi_domain_ops;
+}
+
 int its_alloc_vcpu_irqs(struct its_vm *vm)
 {
 	int vpe_base_irq, i;
@@ -139,18 +144,50 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 	return irq_set_vcpu_affinity(vpe->irq, info);
 }
 
-int its_schedule_vpe(struct its_vpe *vpe, bool on)
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 {
-	struct its_cmd_info info;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+	struct its_cmd_info info = { };
 	int ret;
 
 	WARN_ON(preemptible());
 
-	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
+	info.cmd_type = DESCHEDULE_VPE;
+	if (has_v4_1()) {
+		/* GICv4.1 can directly deal with doorbells */
+		info.req_db = db;
+	} else {
+		/* Undo the nested disable_irq() calls... */
+		while (db && irqd_irq_disabled(&desc->irq_data))
+			enable_irq(vpe->irq);
+	}
 
 	ret = its_send_vpe_cmd(vpe, &info);
 	if (!ret)
-		vpe->resident = on;
+		vpe->resident = false;
+
+	return ret;
+}
+
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
+{
+	struct its_cmd_info info = { };
+	int ret;
+
+	WARN_ON(preemptible());
+
+	info.cmd_type = SCHEDULE_VPE;
+	if (has_v4_1()) {
+		info.g0en = g0en;
+		info.g1en = g1en;
+	} else {
+		/* Disabled the doorbell, as we're about to enter the guest */
+		disable_irq_nosync(vpe->irq);
+	}
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = true;
 
 	return ret;
 }
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 9d53f545a3d5..63457908c9c4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -70,6 +70,7 @@ struct vgic_global {
 
 	/* Hardware has GICv4? */
 	bool			has_gicv4;
+	bool			has_gicv4_1;
 
 	/* GIC system register CPU interface */
 	struct static_key_false gicv3_cpuif;
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 1b34100e3536..34ed4b5754dd 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -125,7 +125,8 @@ struct its_cmd_info {
 
 int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
-int its_schedule_vpe(struct its_vpe *vpe, bool on);
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index f45635a6f0ec..1bc09b523486 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -595,7 +595,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	/* GICv4 support? */
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
-		kvm_info("GICv4 support %sabled\n",
+		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
+		kvm_info("GICv4%s support %sabled\n",
+			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
 			 gicv4_enable ? "en" : "dis");
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 46f875589c47..1eb0f8c76219 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -67,10 +67,10 @@
  * it. And if we've migrated our vcpu from one CPU to another, we must
  * tell the ITS (so that the messages reach the right redistributor).
  * This is done in two steps: first issue a irq_set_affinity() on the
- * irq corresponding to the vcpu, then call its_schedule_vpe(). You
- * must be in a non-preemptible context. On exit, another call to
- * its_schedule_vpe() tells the redistributor that we're done with the
- * vcpu.
+ * irq corresponding to the vcpu, then call its_make_vpe_resident().
+ * You must be in a non-preemptible context. On exit, a call to
+ * its_make_vpe_non_resident() tells the redistributor that we're done
+ * with the vcpu.
  *
  * Finally, the doorbell handling: Each vcpu is allocated an interrupt
  * which will fire each time a VLPI is made pending whilst the vcpu is
@@ -86,7 +86,8 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	struct kvm_vcpu *vcpu = info;
 
 	/* We got the message, no need to fire again */
-	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+	if (!kvm_vgic_global_state.has_gicv4_1 &&
+	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
@@ -199,19 +200,11 @@ void vgic_v4_teardown(struct kvm *kvm)
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
-	struct irq_desc *desc = irq_to_desc(vpe->irq);
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	/*
-	 * If blocking, a doorbell is required. Undo the nested
-	 * disable_irq() calls...
-	 */
-	while (need_db && irqd_irq_disabled(&desc->irq_data))
-		enable_irq(vpe->irq);
-
-	return its_schedule_vpe(vpe, false);
+	return its_make_vpe_non_resident(vpe, need_db);
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -232,18 +225,19 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	/* Disabled the doorbell, as we're about to enter the guest */
-	disable_irq_nosync(vpe->irq);
-
-	err = its_schedule_vpe(vpe, true);
+	err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled);
 	if (err)
 		return err;
 
 	/*
 	 * Now that the VPE is resident, let's get rid of a potential
-	 * doorbell interrupt that would still be pending.
+	 * doorbell interrupt that would still be pending. This is a
+	 * GICv4.0 only "feature"...
 	 */
-	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+	if (!kvm_vgic_global_state.has_gicv4_1)
+		err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+
+	return err;
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,