All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: "Tian, Kevin" <kevin.tian@intel.com>,
	Gerd Hoffmann <kraxel@redhat.com>,
	"Song, Jike" <jike.song@intel.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"White, Michael L" <michael.l.white@intel.com>,
	"Dong, Eddie" <eddie.dong@intel.com>,
	"intel-gfx@lists.freedesktop.org"
	<intel-gfx@lists.freedesktop.org>,
	"Li, Susie" <susie.li@intel.com>,
	"Cowperthwaite, David J" <david.j.cowperthwaite@intel.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Haron, Sandra" <sandra.haron@intel.com>
Subject: Re: [ANNOUNCE][RFC] KVMGT - the implementation of Intel GVT-g(full GPU virtualization) for KVM
Date: Wed, 10 Dec 2014 17:59:05 +0100	[thread overview]
Message-ID: <54887BD9.7030903@redhat.com> (raw)
In-Reply-To: <AADFC41AFE54684AB9EE6CBC0274A5D12611365D@SHSMSX101.ccr.corp.intel.com>



On 09/12/2014 03:49, Tian, Kevin wrote:
> - Now we have XenGT/KVMGT separately maintained, and KVMGT lags
> behind XenGT regarding to features and qualities. Likely you'll continue
> see stale code (like Xen inst decoder) for some time. In the future we
> plan to maintain a single kernel repo for both, so KVMGT can share
> same quality as XenGT once KVM in-kernel dm framework is stable.
> 
> - Regarding to Qemu hacks, KVMGT really doesn't have any different 
> requirements as what have been discussed for GPU pass-through, e.g. 
> about ISA bridge. Our implementation is based on an old Qemu repo, 
> and honestly speaking not cleanly developed, because we know we
> can leverage from GPU pass-through support once it's in Qemu. At 
> that time we'll leverage the same logic with minimal changes to 
> hook KVMGT mgmt. APIs (e.g. create/destroy a vGPU instance). So
> we can ignore this area for now. :-)

Could the virtual device model introduce new registers in order to avoid
poking at the ISA bridge?  I'm not sure that you "can leverage from GPU
pass-through support once it's in Qemu", since the Xen IGD passthrough
support is being added to a separate machine that is specific to Xen IGD
passthrough; no ISA bridge hacking will probably be allowed on the "-M
pc" and "-M q35" machine types.

Paolo
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: "Tian, Kevin" <kevin.tian@intel.com>,
	Gerd Hoffmann <kraxel@redhat.com>,
	"Song, Jike" <jike.song@intel.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"White, Michael L" <michael.l.white@intel.com>,
	"Dong, Eddie" <eddie.dong@intel.com>,
	"intel-gfx@lists.freedesktop.org"
	<intel-gfx@lists.freedesktop.org>,
	"Li, Susie" <susie.li@intel.com>,
	"Cowperthwaite, David J" <david.j.cowperthwaite@intel.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Haron, Sandra" <sandra.haron@intel.com>
Subject: Re: [Intel-gfx] [ANNOUNCE][RFC] KVMGT - the implementation of Intel GVT-g(full GPU virtualization) for KVM
Date: Wed, 10 Dec 2014 17:59:05 +0100	[thread overview]
Message-ID: <54887BD9.7030903@redhat.com> (raw)
In-Reply-To: <AADFC41AFE54684AB9EE6CBC0274A5D12611365D@SHSMSX101.ccr.corp.intel.com>



On 09/12/2014 03:49, Tian, Kevin wrote:
> - Now we have XenGT/KVMGT separately maintained, and KVMGT lags
> behind XenGT regarding to features and qualities. Likely you'll continue
> see stale code (like Xen inst decoder) for some time. In the future we
> plan to maintain a single kernel repo for both, so KVMGT can share
> same quality as XenGT once KVM in-kernel dm framework is stable.
> 
> - Regarding to Qemu hacks, KVMGT really doesn't have any different 
> requirements as what have been discussed for GPU pass-through, e.g. 
> about ISA bridge. Our implementation is based on an old Qemu repo, 
> and honestly speaking not cleanly developed, because we know we
> can leverage from GPU pass-through support once it's in Qemu. At 
> that time we'll leverage the same logic with minimal changes to 
> hook KVMGT mgmt. APIs (e.g. create/destroy a vGPU instance). So
> we can ignore this area for now. :-)

Could the virtual device model introduce new registers in order to avoid
poking at the ISA bridge?  I'm not sure that you "can leverage from GPU
pass-through support once it's in Qemu", since the Xen IGD passthrough
support is being added to a separate machine that is specific to Xen IGD
passthrough; no ISA bridge hacking will probably be allowed on the "-M
pc" and "-M q35" machine types.

Paolo

  reply	other threads:[~2014-12-10 16:59 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-12-04  2:24 [ANNOUNCE][RFC] KVMGT - the implementation of Intel GVT-g(full GPU virtualization) for KVM Jike Song
2014-12-04  2:24 ` Jike Song
2014-12-04 19:56 ` Igor Gnatenko
2014-12-05  8:50 ` Gerd Hoffmann
2014-12-05  8:50   ` Gerd Hoffmann
2014-12-05 13:03   ` Paolo Bonzini
2014-12-05 13:03     ` Paolo Bonzini
2014-12-06  4:30     ` Jike Song
2014-12-06  4:30       ` Jike Song
2014-12-09  2:49     ` Tian, Kevin
2014-12-09  2:49       ` [Intel-gfx] " Tian, Kevin
2014-12-10 16:59       ` Paolo Bonzini [this message]
2014-12-10 16:59         ` Paolo Bonzini
2014-12-11  0:33         ` Tian, Kevin
2014-12-11  0:33           ` [Intel-gfx] " Tian, Kevin
2014-12-11  1:38           ` Paolo Bonzini
2014-12-11  1:38             ` Paolo Bonzini
2014-12-05 13:54   ` Daniel Vetter
2014-12-05 13:54     ` [Intel-gfx] " Daniel Vetter
2014-12-06  4:32     ` Jike Song
2014-12-06  4:32       ` [Intel-gfx] " Jike Song
2014-12-06  4:17   ` Jike Song
2014-12-06  4:17     ` Jike Song
2014-12-08  9:55     ` Gerd Hoffmann
2014-12-08  9:55       ` Gerd Hoffmann
2014-12-08 10:20       ` Daniel Vetter
2014-12-08 10:20         ` [Intel-gfx] " Daniel Vetter
2014-12-09  2:51         ` Tian, Kevin
2014-12-09  2:51           ` [Intel-gfx] " Tian, Kevin
2014-12-09  9:54 ` Jan Kiszka
2014-12-10  6:31   ` Jike Song
2014-12-10  6:31     ` Jike Song
2014-12-10  6:34   ` Jike Song
2014-12-10  6:34     ` [Intel-gfx] " Jike Song
2014-12-10  7:28     ` Tian, Kevin
2014-12-10  7:28       ` [Intel-gfx] " Tian, Kevin
2015-10-27  9:36 ` Jike Song
2015-10-27  9:36   ` Jike Song
2016-01-27  6:32   ` [ANNOUNCE] 2015-Q4 release of KVMGT (Was Re: KVMGT - the implementation of ...) Jike Song
2016-01-27  6:32     ` Jike Song
2016-04-16  6:31     ` [ANNOUNCE] 2016-Q1 " Jike Song
2016-04-16  6:31       ` Jike Song
2016-07-20  4:52       ` [ANNOUNCE] 2016-Q2 " Jike Song
2016-07-20  4:52         ` Jike Song
2016-11-06 15:23         ` [ANNOUNCE] 2016-Q3 " Jike Song
2016-11-06 15:23           ` Jike Song

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=54887BD9.7030903@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=david.j.cowperthwaite@intel.com \
    --cc=eddie.dong@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jike.song@intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kraxel@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=michael.l.white@intel.com \
    --cc=sandra.haron@intel.com \
    --cc=susie.li@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.