From: Marcelo Tosatti <mtosatti@redhat.com>
To: Gleb Natapov <gleb@redhat.com>
Cc: "Zhang, Yang Z" <yang.z.zhang@intel.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"Shan, Haitao" <haitao.shan@intel.com>,
"Zhang, Xiantao" <xiantao.zhang@intel.com>,
"Nakajima, Jun" <jun.nakajima@intel.com>,
"Anvin, H Peter" <h.peter.anvin@intel.com>
Subject: Re: [PATCH 2/2] x86, apicv: Add Posted Interrupt supporting
Date: Thu, 31 Jan 2013 11:44:43 -0200 [thread overview]
Message-ID: <20130131134443.GA4419@amt.cnet> (raw)
In-Reply-To: <20130131133837.GB23213@redhat.com>
On Thu, Jan 31, 2013 at 03:38:37PM +0200, Gleb Natapov wrote:
> On Thu, Jan 31, 2013 at 11:32:45AM -0200, Marcelo Tosatti wrote:
> > On Thu, Jan 31, 2013 at 11:43:48AM +0200, Gleb Natapov wrote:
> > > On Wed, Jan 30, 2013 at 09:03:11PM -0200, Marcelo Tosatti wrote:
> > > > Posted interrupt patch:
> > > > 2) Must move IN_GUEST_MODE assignment after local_irq_disable, in
> > > > vcpu_enter_guest function. Otherwise:
> > > >
> > > > cpu0 vcpu1<->cpu1
> > > >
> > > > vcpu->mode = IN_GUEST_MODE
> > > >
> > > > if IN_GUEST_MODE == true
> > > > send IPI
> > > > local_irq_disable
> > > >
> > > > PIR not transferred to VIRR, misses interrupt.
> > > >
> > > cpu0 will set KVM_REQ_EVENT, so vmentry will be aborted after
> > > local_irq_disable() by ->requests check.
> >
> > Yes, but you don't want KVM_REQ_EVENT+kick. It defeats the purpose
> > of posted interrupts. You want
> >
> > if vcpu in guest mode
> > send posted interrupt IPI
> > else
> > KVM_REQ_EVENT+kick
> >
> I am thinking:
>
> set KVM_REQ_EVENT
> if pi is enabled
> send posted interrupt IPI
> else
> kick
KVM_REQ_EVENT must be after sending posted interrupt IPI. Otherwise on
the vcpu entry side
test_and_clear(KVM_REQ_EVENT) {
No bits set in PIR
}
What about item 4 below?
> > > > 3) Must check outstanding PIR notification bit unconditionally on
> > > > every VM-entry, because:
> > > >
> > > > 1. local_irq_disable
> > > > 2. vcpu->mode = IN_GUEST_MODE
> > > > 3. vmenter
> > > > 4. vmexit
> > > > 5. vcpu->mode = OUTSIDE_GUEST_MODE
> > > >
> > > > If PIR-IPI-interrupt is sent between an event which triggers VM-exit
> > > > (for example, an external interrupt due to a device), and step 5
> > > > (assignment of vcpu->mode), the PIR->VIRR transfer before vmentry must
> > > > be made.
> > > Not sure I understand, but I think KVM_REQ_EVENT will cover that too.
> >
> > See above.
> >
> > > >
> > > > 4) Today, an interrupt notification is cached on IRR until its delivered - further
> > > > interrupt injection is not generating further interrupt notification
> > > > bits. With PIR, behaviour changes: Its possible to have one bit in PIR and another
> > > > on IRR APIC page (if timing is right). Is this harmless? Why?
> > > >
> > > >
> > >
> > > --
> > > Gleb.
>
> --
> Gleb.
next prev parent reply other threads:[~2013-01-31 13:44 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-13 7:29 [PATCH 0/2] KVM: Add posted interrupt supporting Yang Zhang
2012-12-13 7:29 ` [PATCH 1/2] x86: Enable ack interrupt on vmexit Yang Zhang
2012-12-13 7:51 ` Gleb Natapov
2012-12-13 7:54 ` Zhang, Yang Z
2012-12-13 7:58 ` Gleb Natapov
2012-12-13 8:03 ` Zhang, Yang Z
2012-12-13 8:05 ` Gleb Natapov
2012-12-13 8:19 ` Zhang, Yang Z
2012-12-13 8:22 ` Gleb Natapov
2012-12-13 8:23 ` Zhang, Yang Z
2012-12-16 13:26 ` Zhang, Yang Z
2012-12-18 9:11 ` Gleb Natapov
2012-12-13 7:29 ` [PATCH 2/2] x86, apicv: Add Posted Interrupt supporting Yang Zhang
2013-01-22 22:59 ` Marcelo Tosatti
2013-01-23 5:09 ` Zhang, Yang Z
2013-01-24 23:43 ` Marcelo Tosatti
2013-01-25 0:40 ` Zhang, Yang Z
2013-01-30 23:03 ` Marcelo Tosatti
2013-01-30 23:57 ` Marcelo Tosatti
2013-01-31 7:35 ` Gleb Natapov
2013-01-31 9:43 ` Gleb Natapov
2013-01-31 13:32 ` Marcelo Tosatti
2013-01-31 13:38 ` Gleb Natapov
2013-01-31 13:44 ` Marcelo Tosatti [this message]
2013-01-31 13:55 ` Gleb Natapov
2013-02-04 0:57 ` Marcelo Tosatti
2013-02-04 9:10 ` Zhang, Yang Z
2013-02-04 9:55 ` Gleb Natapov
2013-02-04 14:43 ` Marcelo Tosatti
2013-02-04 17:13 ` Gleb Natapov
2013-02-04 19:59 ` Marcelo Tosatti
2013-02-04 20:47 ` Marcelo Tosatti
2013-02-05 5:57 ` Zhang, Yang Z
2013-02-05 8:00 ` Gleb Natapov
2013-02-05 10:35 ` Zhang, Yang Z
2013-02-05 10:54 ` Gleb Natapov
2013-02-05 10:58 ` Zhang, Yang Z
2013-02-05 11:16 ` Gleb Natapov
2013-02-05 13:26 ` Zhang, Yang Z
2013-02-05 13:29 ` Gleb Natapov
2013-02-05 13:40 ` Zhang, Yang Z
2013-02-05 13:43 ` Gleb Natapov
2013-02-07 1:23 ` Marcelo Tosatti
2013-02-05 7:32 ` Gleb Natapov
2013-02-06 22:49 ` Marcelo Tosatti
2013-02-07 0:24 ` Marcelo Tosatti
2013-02-07 13:52 ` Gleb Natapov
2013-02-08 2:07 ` Marcelo Tosatti
2013-02-08 12:18 ` Gleb Natapov
2013-02-07 14:01 ` Gleb Natapov
2013-02-07 21:49 ` Marcelo Tosatti
2013-02-08 12:28 ` Gleb Natapov
2013-02-08 13:46 ` Marcelo Tosatti
2013-01-31 9:37 ` Gleb Natapov
2013-02-04 9:11 ` Zhang, Yang Z
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=20130131134443.GA4419@amt.cnet \
--to=mtosatti@redhat.com \
--cc=gleb@redhat.com \
--cc=h.peter.anvin@intel.com \
--cc=haitao.shan@intel.com \
--cc=jun.nakajima@intel.com \
--cc=kvm@vger.kernel.org \
--cc=xiantao.zhang@intel.com \
--cc=yang.z.zhang@intel.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