Received-SPF: pass (google.com: domain of linux-kernel+bounces-19353-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Precedence: bulk
MIME-Version: 1.0
References: <20240103075343.549293-1-ppandit@redhat.com>
In-Reply-To: <20240103075343.549293-1-ppandit@redhat.com>
From: Prasad Pandit <ppandit@redhat.com>
Date: Mon, 8 Jan 2024 16:15:45 +0530
Message-ID: <CAE8KmOwPKDM5xcd1kFhefeJsqYZndP09n9AxaRbypTsHm8mkgw@mail.gmail.com>
Subject: Re: [PATCH] KVM: x86: make KVM_REQ_NMI request iff NMI pending for vcpu
To: Sean Christopherson <seanjc@google.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, 
	Prasad Pandit <pjp@fedoraproject.org>
Content-Type: text/plain; charset="UTF-8"

On Wed, 3 Jan 2024 at 13:24, Prasad Pandit <ppandit@redhat.com> wrote:
> kvm_vcpu_ioctl_x86_set_vcpu_events() routine makes 'KVM_REQ_NMI'
> request for a vcpu even when its 'events->nmi.pending' is zero.
> Ex:
>     qemu_thread_start
>      kvm_vcpu_thread_fn
>       qemu_wait_io_event
>        qemu_wait_io_event_common
>         process_queued_cpu_work
>          do_kvm_cpu_synchronize_post_init/_reset
>           kvm_arch_put_registers
>            kvm_put_vcpu_events (cpu, level=[2|3])
>
> This leads vCPU threads in QEMU to constantly acquire & release the
> global mutex lock, delaying the guest boot due to lock contention.
> Add check to make KVM_REQ_NMI request only if vcpu has NMI pending.
>
> Fixes: bdedff263132 ("KVM: x86: Route pending NMIs from userspace through process_nmi()")
> Signed-off-by: Prasad Pandit <pjp@fedoraproject.org>
> ---
>  arch/x86/kvm/x86.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 1a3aaa7dafae..468870450b8b 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5405,7 +5405,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
>         if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
>                 vcpu->arch.nmi_pending = 0;
>                 atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
> -               kvm_make_request(KVM_REQ_NMI, vcpu);
> +               if (events->nmi.pending)
> +                       kvm_make_request(KVM_REQ_NMI, vcpu);
>         }
>         static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
> --
> 2.43.0

Ping...!
---
  - Prasad