From: Jan Kiszka <jan.kiszka@siemens.com>
To: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Joerg Roedel <joerg.roedel@amd.com>
Subject: Re: [PATCH 1/2] KVM: Fix race between nmi injection and enabling nmi window
Date: Thu, 03 Feb 2011 16:11:49 +0100 [thread overview]
Message-ID: <4D4AC5B5.5050504@siemens.com> (raw)
In-Reply-To: <1296745369-12066-2-git-send-email-avi@redhat.com>
On 2011-02-03 16:02, Avi Kivity wrote:
> The interrupt injection logic looks something like
>
> if an nmi is pending, and nmi injection allowed
> inject nmi
> if an nmi is pending
> request exit on nmi window
>
> the problem is that "nmi is pending" can be set asynchronously by
> the PIT; if it happens to fire between the two if statements, we
> will request an nmi window even though nmi injection is allowed. On
> SVM, this has disasterous results, since it causes eflags.TF to be
> set in random guest code.
Good point. Fortunately never seen on production machines so far here
(we have very moderate NMI rates).
>
> The fix is simple; make nmi_pending asynchronous using the standard
You mean synchronous, no?
> vcpu->requests mechanism; this ensures the code above is completely
> synchronous wrt nmi_pending.
>
> Signed-off-by: Avi Kivity <avi@redhat.com>
> ---
> arch/x86/kvm/x86.c | 4 +++-
> include/linux/kvm_host.h | 1 +
> 2 files changed, 4 insertions(+), 1 deletions(-)
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index a7f65aa..abe76c0 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -360,8 +360,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
>
> void kvm_inject_nmi(struct kvm_vcpu *vcpu)
> {
> + kvm_make_request(KVM_REQ_NMI, vcpu);
> kvm_make_request(KVM_REQ_EVENT, vcpu);
> - vcpu->arch.nmi_pending = 1;
> }
> EXPORT_SYMBOL_GPL(kvm_inject_nmi);
>
> @@ -5182,6 +5182,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
> r = 1;
> goto out;
> }
> + if (kvm_check_request(KVM_REQ_NMI, vcpu))
> + vcpu->arch.nmi_pending = true;
> }
>
> r = kvm_mmu_reload(vcpu);
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index c8dee22..7581090 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -43,6 +43,7 @@
> #define KVM_REQ_DEACTIVATE_FPU 10
> #define KVM_REQ_EVENT 11
> #define KVM_REQ_APF_HALT 12
> +#define KVM_REQ_NMI 13
>
> #define KVM_USERSPACE_IRQ_SOURCE_ID 0
>
Looks good.
Jan
--
Siemens AG, Corporate Technology, CT T DE IT 1
Corporate Competence Center Embedded Linux
next prev parent reply other threads:[~2011-02-03 15:12 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-03 15:02 [PATCH 0/2] SVM NMI fixes Avi Kivity
2011-02-03 15:02 ` [PATCH 1/2] KVM: Fix race between nmi injection and enabling nmi window Avi Kivity
2011-02-03 15:11 ` Jan Kiszka [this message]
2011-02-03 15:15 ` Avi Kivity
2011-02-03 15:02 ` [PATCH 2/2] KVM: SVM: check for progress after IRET interception Avi Kivity
2011-02-03 15:07 ` Avi Kivity
2011-02-03 15:21 ` Jan Kiszka
2011-02-03 15:30 ` Avi Kivity
2011-02-03 15:55 ` Jan Kiszka
2011-02-03 15:58 ` Avi Kivity
2011-02-03 16:14 ` Jan Kiszka
2011-02-03 16:20 ` Avi Kivity
2011-02-03 16:30 ` Jan Kiszka
2011-02-08 13:49 ` Marcelo Tosatti
2011-02-08 14:05 ` Avi Kivity
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=4D4AC5B5.5050504@siemens.com \
--to=jan.kiszka@siemens.com \
--cc=avi@redhat.com \
--cc=joerg.roedel@amd.com \
--cc=kvm@vger.kernel.org \
--cc=mtosatti@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