linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Marc Zyngier <maz@kernel.org>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
	Andrew Jones <drjones@redhat.com>,
	kvm@vger.kernel.org, Eric Auger <eric.auger@redhat.com>,
	Heinrich Schuchardt <xypron.glpk@gmx.de>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Christoffer Dall <christoffer.dall@arm.com>,
	Steven Price <steven.price@arm.com>,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	Julien Grall <julien.grall@arm.com>,
	Alexander Graf <graf@amazon.com>,
	linux-arm-kernel@lists.infradead.org,
	Zenghui Yu <yuzenghui@huawei.com>,
	James Morse <james.morse@arm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Will Deacon <will@kernel.org>,
	kvmarm@lists.cs.columbia.edu,
	Julien Thierry <julien.thierry.kdev@gmail.com>
Subject: [PATCH 22/22] KVM: arm64: Opportunistically turn off WFI trapping when using direct LPI injection
Date: Wed, 20 Nov 2019 16:42:36 +0000	[thread overview]
Message-ID: <20191120164236.29359-23-maz@kernel.org> (raw)
In-Reply-To: <20191120164236.29359-1-maz@kernel.org>

Just like we do for WFE trapping, it can be useful to turn off
WFI trapping when the physical CPU is not oversubscribed (that
is, the vcpu is the only runnable process on this CPU) *and*
that we're using direct injection of interrupts.

The conditions are reevaluated on each vcpu_load(), ensuring that
we don't switch to this mode on a busy system.

On a GICv4 system, this has the effect of reducing the generation
of doorbell interrupts to zero when the right conditions are
met, which is a huge improvement over the current situation
(where the doorbells are screaming if the CPU ever hits a
blocking WFI).

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Link: https://lore.kernel.org/r/20191107160412.30301-3-maz@kernel.org
---
 arch/arm/include/asm/kvm_emulate.h   | 4 ++--
 arch/arm64/include/asm/kvm_emulate.h | 9 +++++++--
 virt/kvm/arm/arm.c                   | 4 ++--
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 40002416efec..023c01cad2b1 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr &= ~HCR_TWE;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr |= HCR_TWE;
 }
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 6e92f6c7b1e4..5a542d801f07 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -87,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr_el2;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count))
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 |= HCR_TWE;
+	vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
 static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index bd2afcf9a13f..dac96e355f69 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -386,9 +386,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_vcpu_pmu_restore_guest(vcpu);
 
 	if (single_task_running())
-		vcpu_clear_wfe_traps(vcpu);
+		vcpu_clear_wfx_traps(vcpu);
 	else
-		vcpu_set_wfe_traps(vcpu);
+		vcpu_set_wfx_traps(vcpu);
 
 	vcpu_ptrauth_setup_lazy(vcpu);
 }
-- 
2.20.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2019-11-20 16:50 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-20 16:42 [GIT PULL] KVM/arm updates for 5.5 Marc Zyngier
2019-11-20 16:42 ` [PATCH 01/22] KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace Marc Zyngier
2019-11-20 16:42 ` [PATCH 02/22] KVM: arm/arm64: Allow user injection of external data aborts Marc Zyngier
2019-11-20 16:42 ` [PATCH 03/22] KVM: arm64: Document PV-time interface Marc Zyngier
2019-11-20 16:42 ` [PATCH 04/22] KVM: arm/arm64: Factor out hypercall handling from PSCI code Marc Zyngier
2019-11-20 16:42 ` [PATCH 05/22] KVM: arm64: Implement PV_TIME_FEATURES call Marc Zyngier
2019-11-20 16:42 ` [PATCH 06/22] KVM: Implement kvm_put_guest() Marc Zyngier
2019-11-20 16:42 ` [PATCH 07/22] KVM: arm64: Support stolen time reporting via shared structure Marc Zyngier
2019-11-20 16:42 ` [PATCH 08/22] KVM: Allow kvm_device_ops to be const Marc Zyngier
2019-11-20 16:42 ` [PATCH 09/22] KVM: arm64: Provide VCPU attributes for stolen time Marc Zyngier
2019-11-20 16:42 ` [PATCH 10/22] arm/arm64: Provide a wrapper for SMCCC 1.1 calls Marc Zyngier
2019-11-20 16:42 ` [PATCH 11/22] arm/arm64: Make use of the SMCCC 1.1 wrapper Marc Zyngier
2019-11-20 16:42 ` [PATCH 12/22] arm64: Retrieve stolen time as paravirtualized guest Marc Zyngier
2019-11-20 16:42 ` [PATCH 13/22] KVM: arm64: Select TASK_DELAY_ACCT+TASKSTATS rather than SCHEDSTATS Marc Zyngier
2019-11-20 16:42 ` [PATCH 14/22] KVM: arm/arm64: Show halt poll counters in debugfs Marc Zyngier
2019-11-20 16:42 ` [PATCH 15/22] KVM: arm64: Don't set HCR_EL2.TVM when S2FWB is supported Marc Zyngier
2019-11-20 16:42 ` [PATCH 16/22] KVM: arm64: vgic-v4: Move the GICv4 residency flow to be driven by vcpu_load/put Marc Zyngier
2019-11-20 16:42 ` [PATCH 17/22] KVM: arm/arm64: vgic: Remove the declaration of kvm_send_userspace_msi() Marc Zyngier
2019-11-20 16:42 ` [PATCH 18/22] KVM: arm/arm64: vgic: Fix some comments typo Marc Zyngier
2019-11-20 16:42 ` [PATCH 19/22] KVM: arm/arm64: vgic: Don't rely on the wrong pending table Marc Zyngier
2019-11-20 16:42 ` [PATCH 20/22] KVM: arm/arm64: Let the timer expire in hardirq context on RT Marc Zyngier
2019-11-20 16:42 ` [PATCH 21/22] KVM: vgic-v4: Track the number of VLPIs per vcpu Marc Zyngier
2019-11-20 16:42 ` Marc Zyngier [this message]
2019-11-21  8:58 ` [GIT PULL] KVM/arm updates for 5.5 Paolo Bonzini
2019-11-21  9:06   ` Marc Zyngier

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=20191120164236.29359-23-maz@kernel.org \
    --to=maz@kernel.org \
    --cc=bigeasy@linutronix.de \
    --cc=borntraeger@de.ibm.com \
    --cc=christoffer.dall@arm.com \
    --cc=drjones@redhat.com \
    --cc=eric.auger@redhat.com \
    --cc=graf@amazon.com \
    --cc=james.morse@arm.com \
    --cc=julien.grall@arm.com \
    --cc=julien.thierry.kdev@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=mark.rutland@arm.com \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=steven.price@arm.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=xypron.glpk@gmx.de \
    --cc=yuzenghui@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).