KVM: arm64: Delay the polling of the GICR_VPENDBASER.Dirty bit

In order to reduce the impact of the VPT parsing happening on the GIC,
we can split the vcpu reseidency in two phases:

- programming GICR_VPENDBASER: this still happens in vcpu_load()
- checking for the VPT parsing to be complete: this can happen
  on vcpu entry (in kvm_vgic_flush_hwstate())

This allows the GIC and the CPU to work in parallel, rewmoving some
of the entry overhead.

Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Shenming Lu <lushenming@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20201128141857.983-3-lushenming@huawei.com

arch/arm64/kvm/vgic/vgic-v4.c

@@ -353,6 +353,18 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	return err;
 }
 
+void vgic_v4_commit(struct kvm_vcpu *vcpu)
+{
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+
+	/*
+	 * No need to wait for the vPE to be ready across a shallow guest
+	 * exit, as only a vcpu_put will invalidate it.
+	 */
+	if (!vpe->ready)
+		its_commit_vpe(vpe);
+}
+
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
 				     struct kvm_kernel_irq_routing_entry *irq_entry)
 {

arch/arm64/kvm/vgic/vgic.c

@@ -915,6 +915,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 	if (can_access_vgic_from_kernel())
 		vgic_restore_state(vcpu);
+
+	if (vgic_supports_direct_msis(vcpu->kvm))
+		vgic_v4_commit(vcpu);
 }
 
 void kvm_vgic_load(struct kvm_vcpu *vcpu)

drivers/irqchip/irq-gic-v3-its.c

@@ -3842,8 +3842,6 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -3891,6 +3889,10 @@ static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_deschedule(vpe);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_invall(vpe);
 		return 0;
@@ -4052,8 +4054,6 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe,
 	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
 
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
@@ -4128,6 +4128,10 @@ static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_4_1_deschedule(vpe, info);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_4_1_invall(vpe);
 		return 0;

drivers/irqchip/irq-gic-v4.c

@@ -232,6 +232,8 @@ int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 	if (!ret)
 		vpe->resident = false;
 
+	vpe->ready = false;
+
 	return ret;
 }
 
@@ -258,6 +260,23 @@ int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
 	return ret;
 }
 
+int its_commit_vpe(struct its_vpe *vpe)
+{
+	struct its_cmd_info info = {
+		.cmd_type = COMMIT_VPE,
+	};
+	int ret;
+
+	WARN_ON(preemptible());
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->ready = true;
+
+	return ret;
+}
+
+
 int its_invall_vpe(struct its_vpe *vpe)
 {
 	struct its_cmd_info info = {

include/kvm/arm_vgic.h

@@ -402,6 +402,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
+void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */

include/linux/irqchip/arm-gic-v4.h

@@ -39,6 +39,8 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
+	/* VPT parse complete */
+	bool			ready;
 	union {
 		/* GICv4.0 implementations */
 		struct {
@@ -104,6 +106,7 @@ enum its_vcpu_info_cmd_type {
 	PROP_UPDATE_AND_INV_VLPI,
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
+	COMMIT_VPE,
 	INVALL_VPE,
 	PROP_UPDATE_VSGI,
 };
@@ -129,6 +132,7 @@ int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
 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_commit_vpe(struct its_vpe *vpe);
 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);