From: Marcelo Tosatti <mtosatti@redhat.com>
To: Avi Kivity <avi@redhat.com>
Cc: kvm@vger.kernel.org, quintela@redhat.com
Subject: Re: [patch 1/3] KVM: x86: add ioctls to get/set PIO state
Date: Thu, 4 Feb 2010 19:36:43 -0200 [thread overview]
Message-ID: <20100204213643.GC2766@amt.cnet> (raw)
In-Reply-To: <4B6B1D1F.1080701@redhat.com>
On Thu, Feb 04, 2010 at 09:16:47PM +0200, Avi Kivity wrote:
> On 01/28/2010 09:03 PM, Marcelo Tosatti wrote:
> >A vcpu can be stopped after handling IO in userspace,
> >but before returning to kernel to finish processing.
> >
>
> Is this strictly needed? If we teach qemu to migrate before
> executing the pio request, I think we'll be all right? should work
> at least for IN/INS, not sure about OUT/OUTS.
It would be nice (instead of more state to keep track of between
kernel/user) but the drawbacks i see are:
You'd have to add a limitation so that any IN which was processed
by device emulation has to re-entry kernel to complete it (so it
complicates vcpu stop in userspace).
And for OUTS larger than page size (== arch->pio_data size) you need to
know the current position to continue it on the destination (or roll
back the entire effect of the instruction in device emulation, and RIP).
next prev parent reply other threads:[~2010-02-04 21:37 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-28 19:03 [patch 0/3] save/restore in-progress PIO Marcelo Tosatti
2010-01-28 19:03 ` [patch 1/3] KVM: x86: add ioctls to get/set PIO state Marcelo Tosatti
2010-02-04 19:16 ` Avi Kivity
2010-02-04 21:36 ` Marcelo Tosatti [this message]
2010-02-04 21:46 ` Avi Kivity
2010-02-04 22:12 ` Marcelo Tosatti
2010-02-04 22:45 ` Marcelo Tosatti
2010-02-08 22:41 ` Marcelo Tosatti
2010-02-09 6:38 ` Avi Kivity
2010-02-09 18:23 ` Marcelo Tosatti
2010-02-09 20:58 ` qemu-kvm: do not allow vcpu stop with in progress PIO Marcelo Tosatti
2010-02-10 7:02 ` Avi Kivity
2010-02-10 16:25 ` Marcelo Tosatti
2010-02-10 16:40 ` Avi Kivity
2010-02-10 16:52 ` Alexander Graf
2010-02-10 17:01 ` Avi Kivity
2010-02-10 17:03 ` Alexander Graf
2010-02-10 17:08 ` Avi Kivity
2010-02-10 17:07 ` Gleb Natapov
2010-02-10 17:08 ` Avi Kivity
2010-02-13 18:10 ` KVM: add doc note about PIO/MMIO completion API Marcelo Tosatti
2010-02-14 8:17 ` Avi Kivity
2010-02-17 9:22 ` Avi Kivity
2010-02-18 13:24 ` qemu-kvm: do not allow vcpu stop with in progress PIO Avi Kivity
2010-01-28 19:03 ` [patch 2/3] uqmaster: save/restore pio state Marcelo Tosatti
2010-01-28 19:03 ` [patch 3/3] uqmaster: save/restore PIO page Marcelo Tosatti
2010-01-28 20:24 ` Anthony Liguori
2010-01-28 21:10 ` Marcelo Tosatti
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=20100204213643.GC2766@amt.cnet \
--to=mtosatti@redhat.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=quintela@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