[PATCH v2 2/2] KVM: arm64: Delay the execution of the polling on the GICR_VPENDBASER.Dirty bit

[Shenming Lu <lushenming@huawei.com>]

In order to further reduce the impact of the wait delay of the
VPT analysis, we can delay the execution of the polling on the
GICR_VPENDBASER.Dirty bit (call it from kvm_vgic_flush_hwstate()
corresponding to vPE resident), let the GIC and the CPU work in
parallel on the entry path.

Signed-off-by: Shenming Lu <lushenming@huawei.com>
---
 arch/arm64/kvm/vgic/vgic-v4.c      | 16 ++++++++++++++++
 arch/arm64/kvm/vgic/vgic.c         |  3 +++
 drivers/irqchip/irq-gic-v3-its.c   | 16 ++++++++++++----
 drivers/irqchip/irq-gic-v4.c       | 11 +++++++++++
 include/kvm/arm_vgic.h             |  3 +++
 include/linux/irqchip/arm-gic-v4.h |  4 ++++
 6 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index b5fa73c9fd35..b0da74809187 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -353,6 +353,22 @@ 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->vpe_ready)
+		return;
+
+	its_commit_vpe(vpe);
+
+	vpe->vpe_ready = true;
+}
+
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
 				     struct kvm_kernel_irq_routing_entry *irq_entry)
 {
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index c3643b7f101b..1c597c9885fa 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/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)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 22f427135c6b..f30aba14933e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/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)
@@ -3855,6 +3853,8 @@ static void its_vpe_deschedule(struct its_vpe *vpe)
 
 	vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
 	vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+
+	vpe->vpe_ready = false;
 }
 
 static void its_vpe_invall(struct its_vpe *vpe)
@@ -3891,6 +3891,10 @@ 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 +4056,6 @@ 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,
@@ -4091,6 +4093,8 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
 					    GICR_VPENDBASER_PendingLast);
 		vpe->pending_last = true;
 	}
+
+	vpe->vpe_ready = false;
 }
 
 static void its_vpe_4_1_invall(struct its_vpe *vpe)
@@ -4128,6 +4132,10 @@ 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;
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 0c18714ae13e..6cea71a4e68b 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -258,6 +258,17 @@ 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,
+	};
+
+	WARN_ON(preemptible());
+
+	return its_send_vpe_cmd(vpe, &info);
+}
+
 int its_invall_vpe(struct its_vpe *vpe)
 {
 	struct its_cmd_info info = {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index a8d8fdcd3723..f2170df6cf7c 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -401,7 +401,10 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
+void vgic_v4_commit(struct kvm_vcpu *vcpu);
+
 int vgic_v4_load(struct kvm_vcpu *vcpu);
+
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 6976b8331b60..936d88e482a9 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -75,6 +75,8 @@ struct its_vpe {
 	u16			vpe_id;
 	/* Pending VLPIs on schedule out? */
 	bool			pending_last;
+	/* VPT parse complete */
+	bool			vpe_ready;
 };
 
 /*
@@ -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);
-- 
2.23.0