All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoffer Dall <christoffer.dall@linaro.org>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>,
	kvmarm@lists.cs.columbia.edu,
	linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org
Subject: [PULL 19/27] KVM: arm/arm64: GICv4: Use the doorbell interrupt as an unblocking source
Date: Mon, 13 Nov 2017 10:17:44 +0100	[thread overview]
Message-ID: <20171113091752.10663-20-christoffer.dall@linaro.org> (raw)
In-Reply-To: <20171113091752.10663-1-christoffer.dall@linaro.org>

From: Marc Zyngier <marc.zyngier@arm.com>

The doorbell interrupt is only useful if the vcpu is blocked on WFI.
In all other cases, recieving a doorbell interrupt is just a waste
of cycles.

So let's only enable the doorbell if a vcpu is getting blocked,
and disable it when it is unblocked. This is very similar to
what we're doing for the background timer.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h      |  3 +++
 virt/kvm/arm/arm.c          |  2 ++
 virt/kvm/arm/vgic/vgic-v4.c | 18 ++++++++++++++++++
 3 files changed, 23 insertions(+)

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2f750c770bf2..8c896540a72c 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -381,4 +381,7 @@ 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 kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
+void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 34a15c0c65ab..01e575b9f78b 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -315,11 +315,13 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
 	kvm_timer_schedule(vcpu);
+	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
 	kvm_timer_unschedule(vcpu);
+	kvm_vgic_v4_disable_doorbell(vcpu);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 796e00c77903..1375a53054b9 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -233,3 +233,21 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 	mutex_unlock(&its->its_lock);
 	return ret;
 }
+
+void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vgic_supports_direct_msis(vcpu->kvm)) {
+		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+		if (irq)
+			enable_irq(irq);
+	}
+}
+
+void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vgic_supports_direct_msis(vcpu->kvm)) {
+		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+		if (irq)
+			disable_irq(irq);
+	}
+}
-- 
2.14.2

WARNING: multiple messages have this Message-ID (diff)
From: christoffer.dall@linaro.org (Christoffer Dall)
To: linux-arm-kernel@lists.infradead.org
Subject: [PULL 19/27] KVM: arm/arm64: GICv4: Use the doorbell interrupt as an unblocking source
Date: Mon, 13 Nov 2017 10:17:44 +0100	[thread overview]
Message-ID: <20171113091752.10663-20-christoffer.dall@linaro.org> (raw)
In-Reply-To: <20171113091752.10663-1-christoffer.dall@linaro.org>

From: Marc Zyngier <marc.zyngier@arm.com>

The doorbell interrupt is only useful if the vcpu is blocked on WFI.
In all other cases, recieving a doorbell interrupt is just a waste
of cycles.

So let's only enable the doorbell if a vcpu is getting blocked,
and disable it when it is unblocked. This is very similar to
what we're doing for the background timer.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h      |  3 +++
 virt/kvm/arm/arm.c          |  2 ++
 virt/kvm/arm/vgic/vgic-v4.c | 18 ++++++++++++++++++
 3 files changed, 23 insertions(+)

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2f750c770bf2..8c896540a72c 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -381,4 +381,7 @@ 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 kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
+void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 34a15c0c65ab..01e575b9f78b 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -315,11 +315,13 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
 	kvm_timer_schedule(vcpu);
+	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
 	kvm_timer_unschedule(vcpu);
+	kvm_vgic_v4_disable_doorbell(vcpu);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index 796e00c77903..1375a53054b9 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -233,3 +233,21 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 	mutex_unlock(&its->its_lock);
 	return ret;
 }
+
+void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vgic_supports_direct_msis(vcpu->kvm)) {
+		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+		if (irq)
+			enable_irq(irq);
+	}
+}
+
+void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vgic_supports_direct_msis(vcpu->kvm)) {
+		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+		if (irq)
+			disable_irq(irq);
+	}
+}
-- 
2.14.2

  parent reply	other threads:[~2017-11-13  9:17 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-13  9:17 [PULL 00/27] KVM/ARM GICv4 Support for v4.15 Christoffer Dall
2017-11-13  9:17 ` Christoffer Dall
2017-11-13  9:17 ` [PULL 01/27] KVM: arm/arm64: register irq bypass consumer on ARM/ARM64 Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 02/27] KVM: arm/arm64: vgic: restructure kvm_vgic_(un)map_phys_irq Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 03/27] KVM: arm: Select ARM_GIC_V3 and ARM_GIC_V3_ITS Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 04/27] KVM: arm/arm64: vgic: Move kvm_vgic_destroy call around Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 05/27] KVM: arm/arm64: vITS: Add MSI translation helpers Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 06/27] KVM: arm/arm64: vITS: Add a helper to update the affinity of an LPI Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 07/27] KVM: arm/arm64: GICv4: Add property field and per-VM predicate Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 08/27] KVM: arm/arm64: GICv4: Add init/teardown of the per-VM vPE irq domain Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 09/27] KVM: arm/arm64: GICv4: Wire mapping/unmapping of VLPIs in VFIO irq bypass Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 10/27] KVM: arm/arm64: GICv4: Handle INT command applied to a VLPI Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 11/27] KVM: arm/arm64: GICv4: Unmap VLPI when freeing an LPI Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 12/27] KVM: arm/arm64: GICv4: Propagate affinity changes to the physical ITS Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 13/27] KVM: arm/arm64: GICv4: Handle CLEAR applied to a VLPI Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 14/27] KVM: arm/arm64: GICv4: Handle MOVALL applied to a vPE Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 15/27] KVM: arm/arm64: GICv4: Propagate property updates to VLPIs Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 16/27] KVM: arm/arm64: GICv4: Handle INVALL applied to a vPE Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 17/27] KVM: arm/arm64: GICv4: Use pending_last as a scheduling hint Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 18/27] KVM: arm/arm64: GICv4: Add doorbell interrupt handling Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` Christoffer Dall [this message]
2017-11-13  9:17   ` [PULL 19/27] KVM: arm/arm64: GICv4: Use the doorbell interrupt as an unblocking source Christoffer Dall
2017-11-13  9:17 ` [PULL 20/27] KVM: arm/arm64: GICv4: Hook vPE scheduling into vgic flush/sync Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 21/27] KVM: arm/arm64: GICv4: Enable virtual cpuif if VLPIs can be delivered Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 22/27] KVM: arm/arm64: GICv4: Prevent a VM using GICv4 from being saved Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 23/27] KVM: arm/arm64: GICv4: Prevent userspace from changing doorbell affinity Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 24/27] KVM: arm/arm64: GICv4: Enable VLPI support Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 25/27] KVM: arm/arm64: GICv4: Theory of operations Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 26/27] KVM: arm/arm64: Fix GICv4 ITS initialization issues Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-13  9:17 ` [PULL 27/27] KVM: arm/arm64: Don't queue VLPIs on INV/INVALL Christoffer Dall
2017-11-13  9:17   ` Christoffer Dall
2017-11-17 12:23 ` [PULL 00/27] KVM/ARM GICv4 Support for v4.15 Paolo Bonzini
2017-11-17 12:23   ` Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171113091752.10663-20-christoffer.dall@linaro.org \
    --to=christoffer.dall@linaro.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=marc.zyngier@arm.com \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.