All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mingwei Zhang <mizhang@google.com>
To: Jim Mattson <jmattson@google.com>
Cc: kvm@vger.kernel.org, Sean Christopherson <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Like Xu <likexu@tencent.com>,
	Roman Kagan <rkagan@amazon.de>, Kan Liang <kan.liang@intel.com>,
	Dapeng1 Mi <dapeng1.mi@intel.com>
Subject: Re: [PATCH 2/2] KVM: x86: Mask LVTPC when handling a PMI
Date: Sat, 2 Sep 2023 19:06:46 +0000	[thread overview]
Message-ID: <ZPOHxsdYhWdMRoyT@google.com> (raw)
In-Reply-To: <20230901185646.2823254-2-jmattson@google.com>

On Fri, Sep 01, 2023, Jim Mattson wrote:
> Per the SDM, "When the local APIC handles a performance-monitoring
> counters interrupt, it automatically sets the mask flag in the LVT
> performance counter register."
> 
> Add this behavior to KVM's local APIC emulation, to reduce the
> incidence of "dazed and confused" spurious NMI warnings in Linux
> guests (at least, those that use a PMI handler with "late_ack").
> 
> Fixes: 23930f9521c9 ("KVM: x86: Enable NMI Watchdog via in-kernel PIT source")
> Signed-off-by: Jim Mattson <jmattson@google.com>
Tested-by: Mingwei Zhang <mizhang@google.com>

I see consistent number of PMIs and NMIs when running perf on an idle
VM.
> ---
>  arch/x86/kvm/lapic.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index a983a16163b1..1a79ec54ae1e 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -2743,6 +2743,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
>  		vector = reg & APIC_VECTOR_MASK;
>  		mode = reg & APIC_MODE_MASK;
>  		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
> +		if (lvt_type == APIC_LVTPC)
> +			kvm_lapic_set_reg(apic, lvt_type, reg | APIC_LVT_MASKED);
>  		return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
>  					NULL);
>  	}
> -- 
> 2.42.0.283.g2d96d420d3-goog
> 

  reply	other threads:[~2023-09-02 19:06 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-01 18:56 [PATCH 1/2] KVM: x86: Synthesize at most one PMI per VM-exit Jim Mattson
2023-09-01 18:56 ` [PATCH 2/2] KVM: x86: Mask LVTPC when handling a PMI Jim Mattson
2023-09-02 19:06   ` Mingwei Zhang [this message]
2023-09-06  8:59   ` Mi, Dapeng1
2023-09-22 18:22   ` Sean Christopherson
2023-09-25 17:52     ` Jim Mattson
2023-09-25 18:00       ` Sean Christopherson
2023-09-02 19:05 ` [PATCH 1/2] KVM: x86: Synthesize at most one PMI per VM-exit Mingwei Zhang
2023-09-06  9:17 ` Mi, Dapeng
2023-09-06 20:54   ` Mingwei Zhang
2023-09-07  6:29     ` Mi, Dapeng
2023-09-14 11:57 ` Like Xu
2023-09-14 14:27   ` Sean Christopherson
2023-09-22 18:46 ` Sean Christopherson
2023-09-22 19:04   ` Jim Mattson
2023-09-22 19:21     ` Sean Christopherson
2023-09-22 20:25       ` Mingwei Zhang
2023-09-22 20:34         ` Sean Christopherson
2023-09-22 20:49           ` Mingwei Zhang
2023-09-22 21:02             ` Mingwei Zhang
2023-09-22 22:44               ` Sean Christopherson
2023-09-25  6:00                 ` Mingwei Zhang
2023-09-25 19:54               ` Mingwei Zhang
2023-09-22 21:06             ` Sean Christopherson
2023-09-22 22:42               ` Mingwei Zhang
2023-09-22 23:00                 ` Sean Christopherson
2023-09-25  6:09                   ` Mingwei Zhang
2023-09-25 16:22                     ` Mingwei Zhang
2023-09-25 17:06                       ` Sean Christopherson
2023-09-25  7:06                 ` Like Xu
2023-09-25  7:33       ` Like Xu
  -- strict thread matches above, loose matches on Subject: below --
2023-09-25 17:34 [PATCH 0/2] Fix the duplicate PMI injections in vPMU Mingwei Zhang
2023-09-25 17:34 ` [PATCH 2/2] KVM: x86: Mask LVTPC when handling a PMI Mingwei Zhang
2023-09-25 17:52   ` Sean Christopherson
2023-09-25 19:34     ` Mingwei Zhang

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=ZPOHxsdYhWdMRoyT@google.com \
    --to=mizhang@google.com \
    --cc=dapeng1.mi@intel.com \
    --cc=jmattson@google.com \
    --cc=kan.liang@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=likexu@tencent.com \
    --cc=pbonzini@redhat.com \
    --cc=rkagan@amazon.de \
    --cc=seanjc@google.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.