From: Avi Kivity <avi@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org
Subject: Re: [PATCH 2/3] KVM: VMX: Short circuit STI; HLT while an interrupt is pending
Date: Sun, 20 Feb 2011 11:04:55 +0200 [thread overview]
Message-ID: <4D60D937.5020808@redhat.com> (raw)
In-Reply-To: <20110217161634.GA10918@amt.cnet>
On 02/17/2011 06:16 PM, Marcelo Tosatti wrote:
> On Thu, Feb 17, 2011 at 11:12:43AM +0200, Avi Kivity wrote:
> > >> >> index ee1cd1a..541da0e 100644
> > >> >> --- a/arch/x86/kvm/vmx.c
> > >> >> +++ b/arch/x86/kvm/vmx.c
> > >> >> @@ -3437,6 +3437,15 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
> > >> >> static int handle_halt(struct kvm_vcpu *vcpu)
> > >> >> {
> > >> >> skip_emulated_instruction(vcpu);
> > >> >> + /*
> > >> >> + * Short-circuit an STI; HLT sequence while an interrupt is pending:
> > >> >> + * instead of halting, re-entering the guest, and exiting immediately
> > >> >> + * on an interrupt window exit, go directly to the last step.
> > >> >> + */
> > >> >> + if ((to_vmx(vcpu)->cpu_based_vm_exec_control
> > >> >> + & CPU_BASED_VIRTUAL_INTR_PENDING)
> > >> >> + && (kvm_get_rflags(vcpu)& X86_EFLAGS_IF))
> > >> >> + return handle_interrupt_window(vcpu);
> > >> >> return kvm_emulate_halt(vcpu);
> > >> >> }
> > >> >
> > >> >Why does the normal vcpu entry path fails to inject the interrupt? Because after halt,
> > >> >KVM_REQ_EVENT is not set?
> > >>
> > >> Yes. Also, we want to clear CPU_BASED_VIRTUAL_INTR_PENDING.
> > >
> > >Is there a reason why it cannot be handled in the main loop?
> >
> > Don't follow. What are you suggesting?
>
> That vcpu main loop (inject_pending_events etc) should be able to inject
> the interrupt and clear interrupt exiting, instead of a short circuit
> in specific exit handlers, as an improvement on top of the current
> patchset.
Yes, it makes sense to make move virtual interrupt pending logic into
x86.c. On the other hand, it may conflict with using the hardware
interrupt queue on svm (which we don't make use of yet).
> Any numbers, BTW?
Not yet.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2011-02-20 9:05 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-14 14:42 [PATCH 0/3] Optimize STI; HLT while an interrupt is pending Avi Kivity
2011-02-14 14:42 ` [PATCH 1/3] KVM: VMX: Cache CPU_BASED_VM_EXEC_CONTROL VMCS field Avi Kivity
2011-02-14 14:42 ` [PATCH 2/3] KVM: VMX: Short circuit STI; HLT while an interrupt is pending Avi Kivity
2011-02-15 20:36 ` Marcelo Tosatti
2011-02-16 9:01 ` Avi Kivity
2011-02-16 16:51 ` Marcelo Tosatti
2011-02-17 9:12 ` Avi Kivity
2011-02-17 16:16 ` Marcelo Tosatti
2011-02-20 9:04 ` Avi Kivity [this message]
2011-02-14 14:42 ` [PATCH 3/3] KVM: SVM: " 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=4D60D937.5020808@redhat.com \
--to=avi@redhat.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