kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoffer Dall <cdall@linaro.org>
To: Andrew Jones <drjones@redhat.com>
Cc: marc.zyngier@arm.com, pbonzini@redhat.com,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org
Subject: Re: [PATCH v4 07/11] KVM: arm/arm64: optimize VCPU RUN
Date: Thu, 1 Jun 2017 12:35:22 +0200	[thread overview]
Message-ID: <20170601103522.GG20919@cbox> (raw)
In-Reply-To: <20170516022035.7674-8-drjones@redhat.com>

On Tue, May 16, 2017 at 04:20:31AM +0200, Andrew Jones wrote:
> We can make a small optimization by not checking the state of
> the power_off field on each run. This is done by treating
> power_off like pause, only checking it when we get the EXIT
> VCPU request. When a VCPU powers off another VCPU the EXIT
> request is already made, so we just need to make sure the
> request is also made on self power off. kvm_vcpu_kick() isn't
> necessary for these cases, as the VCPU would just be kicking
> itself, but we add it anyway as a self kick doesn't cost much,
> and it makes the code more future-proof.
> 
> Signed-off-by: Andrew Jones <drjones@redhat.com>

Reviewed-by: Christoffer Dall <cdall@linaro.org>

> ---
>  virt/kvm/arm/arm.c  | 19 +++++++++++--------
>  virt/kvm/arm/psci.c |  2 ++
>  2 files changed, 13 insertions(+), 8 deletions(-)
> 
> diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
> index 21a4db90073f..9379b1d75ad3 100644
> --- a/virt/kvm/arm/arm.c
> +++ b/virt/kvm/arm/arm.c
> @@ -368,6 +368,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>  	kvm_timer_vcpu_put(vcpu);
>  }
>  
> +static void vcpu_power_off(struct kvm_vcpu *vcpu)
> +{
> +	vcpu->arch.power_off = true;
> +	kvm_make_request(KVM_REQ_VCPU_EXIT, vcpu);
> +	kvm_vcpu_kick(vcpu);
> +}
> +
>  int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
>  				    struct kvm_mp_state *mp_state)
>  {
> @@ -387,7 +394,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
>  		vcpu->arch.power_off = false;
>  		break;
>  	case KVM_MP_STATE_STOPPED:
> -		vcpu->arch.power_off = true;
> +		vcpu_power_off(vcpu);
>  		break;
>  	default:
>  		return -EINVAL;
> @@ -557,7 +564,7 @@ static void vcpu_sleep(struct kvm_vcpu *vcpu)
>  	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
>  				       (!vcpu->arch.pause)));
>  
> -	if (vcpu->arch.pause) {
> +	if (vcpu->arch.power_off || vcpu->arch.pause) {
>  		/* Awaken to handle a signal, request we sleep again later. */
>  		kvm_make_request(KVM_REQ_VCPU_EXIT, vcpu);
>  	}
> @@ -623,9 +630,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
>  
>  		check_vcpu_requests(vcpu);
>  
> -		if (vcpu->arch.power_off)
> -			vcpu_sleep(vcpu);
> -
>  		/*
>  		 * Preparing the interrupts to be injected also
>  		 * involves poking the GIC, which must be done in a
> @@ -662,8 +666,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
>  		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
>  
>  		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
> -		    kvm_request_pending(vcpu) ||
> -		    vcpu->arch.power_off) {
> +		    kvm_request_pending(vcpu)) {
>  			vcpu->mode = OUTSIDE_GUEST_MODE;
>  			local_irq_enable();
>  			kvm_pmu_sync_hwstate(vcpu);
> @@ -896,7 +899,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
>  	 * Handle the "start in power-off" case.
>  	 */
>  	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
> -		vcpu->arch.power_off = true;
> +		vcpu_power_off(vcpu);
>  	else
>  		vcpu->arch.power_off = false;
>  
> diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
> index f189d0ad30d5..4a436685c552 100644
> --- a/virt/kvm/arm/psci.c
> +++ b/virt/kvm/arm/psci.c
> @@ -65,6 +65,8 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
>  static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
>  {
>  	vcpu->arch.power_off = true;
> +	kvm_make_request(KVM_REQ_VCPU_EXIT, vcpu);
> +	kvm_vcpu_kick(vcpu);
>  }
>  
>  static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
> -- 
> 2.9.3
> 

  reply	other threads:[~2017-06-01 10:35 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-16  2:20 [PATCH v4 00/11] KVM: arm/arm64: race fixes and vcpu requests Andrew Jones
2017-05-16  2:20 ` [PATCH v4 01/11] KVM: improve arch vcpu request defining Andrew Jones
2017-06-01 10:34   ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 02/11] KVM: add kvm_request_pending Andrew Jones
2017-06-01 10:35   ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 03/11] KVM: Add documentation for VCPU requests Andrew Jones
2017-05-26  7:31   ` Christoffer Dall
2017-05-26  9:43     ` Andrew Jones
2017-05-16  2:20 ` [PATCH v4 04/11] KVM: arm/arm64: properly use vcpu requests Andrew Jones
2017-05-16  2:20 ` [PATCH v4 05/11] KVM: arm/arm64: replace pause checks with vcpu request checks Andrew Jones
2017-06-01 10:35   ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 06/11] KVM: arm/arm64: use vcpu requests for power_off Andrew Jones
2017-06-01 10:35   ` Christoffer Dall
2017-06-01 10:35   ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 07/11] KVM: arm/arm64: optimize VCPU RUN Andrew Jones
2017-06-01 10:35   ` Christoffer Dall [this message]
2017-05-16  2:20 ` [PATCH v4 08/11] KVM: arm/arm64: change exit request to sleep request Andrew Jones
2017-06-01 10:35   ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 09/11] KVM: arm/arm64: use vcpu requests for irq injection Andrew Jones
2017-06-01 10:35   ` Christoffer Dall
2017-06-01 10:59     ` Andrew Jones
2017-06-01 13:27       ` Christoffer Dall
2017-06-01 13:38         ` Andrew Jones
2017-06-01 13:53           ` Christoffer Dall
2017-05-16  2:20 ` [PATCH v4 10/11] KVM: arm/arm64: PMU: remove request-less vcpu kick Andrew Jones
2017-05-16  2:20 ` [PATCH v4 11/11] KVM: arm/arm64: timer: " Andrew Jones
2017-06-01 10:34   ` Christoffer Dall
2017-06-01 11:09     ` Andrew Jones
2017-06-01 12:37       ` Paolo Bonzini
2017-06-01 13:23         ` Christoffer Dall

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=20170601103522.GG20919@cbox \
    --to=cdall@linaro.org \
    --cc=drjones@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=marc.zyngier@arm.com \
    --cc=pbonzini@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 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).