All of lore.kernel.org
 help / color / mirror / Atom feed
From: Vitaly Kuznetsov <vkuznets@redhat.com>
To: Wanpeng Li <kernellwp@gmail.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>
Subject: Re: [PATCH 3/3] KVM: LAPIC: Optimize PMI delivering overhead
Date: Fri, 08 Oct 2021 12:52:46 +0200	[thread overview]
Message-ID: <87ily73i0x.fsf@vitty.brq.redhat.com> (raw)
In-Reply-To: <1633687054-18865-3-git-send-email-wanpengli@tencent.com>

Wanpeng Li <kernellwp@gmail.com> writes:

> From: Wanpeng Li <wanpengli@tencent.com>
>
> The overhead of kvm_vcpu_kick() is huge since expensive rcu/memory
> barrier etc operations in rcuwait_wake_up(). It is worse when local 
> delivery since the vCPU is scheduled and we still suffer from this. 
> We can observe 12us+ for kvm_vcpu_kick() in kvm_pmu_deliver_pmi() 
> path by ftrace before the patch and 6us+ after the optimization. 
>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
>  arch/x86/kvm/lapic.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index 76fb00921203..ec6997187c6d 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -1120,7 +1120,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
>  	case APIC_DM_NMI:
>  		result = 1;
>  		kvm_inject_nmi(vcpu);
> -		kvm_vcpu_kick(vcpu);
> +		if (vcpu != kvm_get_running_vcpu())
> +			kvm_vcpu_kick(vcpu);

Out of curiosity,

can this be converted into a generic optimization for kvm_vcpu_kick()
instead? I.e. if kvm_vcpu_kick() is called for the currently running
vCPU, there's almost nothing to do, especially when we already have a
request pending, right? (I didn't put too much though to it)

>  		break;
>  
>  	case APIC_DM_INIT:

-- 
Vitaly


  reply	other threads:[~2021-10-08 10:52 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-08  9:57 [PATCH 1/3] KVM: emulate: #GP when emulating rdpmc if CR0.PE is 1 Wanpeng Li
2021-10-08  9:57 ` [PATCH 2/3] KVM: vPMU: Fill get_msr MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0 Wanpeng Li
2021-10-08 11:02   ` Like Xu
2021-10-08 11:17     ` Wanpeng Li
2021-10-08  9:57 ` [PATCH 3/3] KVM: LAPIC: Optimize PMI delivering overhead Wanpeng Li
2021-10-08 10:52   ` Vitaly Kuznetsov [this message]
2021-10-08 11:06     ` Wanpeng Li
2021-10-08 15:59       ` Sean Christopherson
2021-10-09  9:14         ` Wanpeng Li
2021-10-08 15:20 ` [PATCH 1/3] KVM: emulate: #GP when emulating rdpmc if CR0.PE is 1 Sean Christopherson
2021-10-09  9:09   ` Wanpeng Li

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=87ily73i0x.fsf@vitty.brq.redhat.com \
    --to=vkuznets@redhat.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kernellwp@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=seanjc@google.com \
    --cc=wanpengli@tencent.com \
    --subject='Re: [PATCH 3/3] KVM: LAPIC: Optimize PMI delivering overhead' \
    /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

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.