From: Alex Williamson <alex.williamson@redhat.com>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>,
"intel-gvt-dev@lists.freedesktop.org"
<intel-gvt-dev@lists.freedesktop.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>
Subject: Re: [PATCH v3 0/2] VFIO mdev aggregated resources handling
Date: Tue, 7 Jul 2020 19:06:34 -0600 [thread overview]
Message-ID: <20200707190634.4d9055fe@x1.home> (raw)
In-Reply-To: <MWHPR11MB1645CC388BF45FD2E6309C3C8C660@MWHPR11MB1645.namprd11.prod.outlook.com>
On Tue, 7 Jul 2020 23:28:39 +0000
"Tian, Kevin" <kevin.tian@intel.com> wrote:
> Hi, Alex,
>
> Gentle ping... Please let us know whether this version looks good.
I figured this is entangled with the versioning scheme. There are
unanswered questions about how something that assumes a device of a
given type is software compatible to another device of the same type
handles aggregation and how the type class would indicate compatibility
with an aggregated instance. Thanks,
Alex
> > From: Zhenyu Wang <zhenyuw@linux.intel.com>
> > Sent: Wednesday, April 8, 2020 1:58 PM
> >
> > Hi,
> >
> > This is a refresh on previous series:
> > https://patchwork.kernel.org/cover/11208279/
> > and https://patchwork.freedesktop.org/series/70425/
> >
> > Current mdev device create interface depends on fixed mdev type, which
> > get uuid from user to create instance of mdev device. If user wants to
> > use customized number of resource for mdev device, then only can
> > create new mdev type for that which may not be flexible. This
> > requirement comes not only from to be able to allocate flexible
> > resources for KVMGT, but also from Intel scalable IO virtualization
> > which would use vfio/mdev to be able to allocate arbitrary resources
> > on mdev instance. More info on [1] [2] [3].
> >
> > As we agreed that for current opaque mdev device type, we'd still
> > explore management interface based on mdev sysfs definition. And this
> > one tries to follow Alex's previous suggestion to create generic
> > parameters under 'mdev' directory for each device, so vendor driver
> > could provide support like as other defined mdev sysfs entries.
> >
> > For mdev type with aggregation support, files as "aggregated_instances"
> > and "max_aggregation" should be created under 'mdev' directory. E.g
> >
> > /sys/devices/pci0000:00/0000:00:02.0/<UUID>/mdev/
> > |-- aggregated_instances
> > |-- max_aggregation
> >
> > "aggregated_instances" is used to set or return current number of
> > instances for aggregation, which can not be larger than "max_aggregation".
> >
> > The first patch is to update the document for new mdev parameter directory.
> > The second one is to add aggregation support in GVT driver.
> >
> > References:
> > [1] https://software.intel.com/en-us/download/intel-virtualization-
> > technology-for-directed-io-architecture-specification
> > [2] https://software.intel.com/en-us/download/intel-scalable-io-
> > virtualization-technical-specification
> > [3] https://schd.ws/hosted_files/lc32018/00/LC3-SIOV-final.pdf
> >
> > Changelog:
> > v3:
> > - add more description for sysfs entries
> > - rebase GVT support
> > - rename accounting function
> >
> > Zhenyu Wang (2):
> > Documentation/driver-api/vfio-mediated-device.rst: update for
> > aggregation support
> > drm/i915/gvt: mdev aggregation type
> >
> > .../driver-api/vfio-mediated-device.rst | 22 +++
> > drivers/gpu/drm/i915/gvt/aperture_gm.c | 44 +++--
> > drivers/gpu/drm/i915/gvt/gtt.c | 9 +-
> > drivers/gpu/drm/i915/gvt/gvt.c | 7 +-
> > drivers/gpu/drm/i915/gvt/gvt.h | 42 +++--
> > drivers/gpu/drm/i915/gvt/kvmgt.c | 115 +++++++++++-
> > drivers/gpu/drm/i915/gvt/vgpu.c | 172 ++++++++++++------
> > 7 files changed, 317 insertions(+), 94 deletions(-)
> >
> > --
> > 2.25.1
>
next prev parent reply other threads:[~2020-07-08 1:07 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-26 5:41 [PATCH v2 0/2] VFIO mdev aggregated resources handling Zhenyu Wang
2020-03-26 5:41 ` [PATCH v2 1/2] Documentation/driver-api/vfio-mediated-device.rst: update for aggregation support Zhenyu Wang
2020-03-26 8:17 ` Tian, Kevin
2020-03-26 8:21 ` Zhenyu Wang
2020-03-27 6:16 ` Tian, Kevin
2020-03-27 6:21 ` Zhenyu Wang
2020-03-26 5:41 ` [PATCH v2 2/2] drm/i915/gvt: mdev aggregation type Zhenyu Wang
2020-03-27 7:48 ` Tian, Kevin
2020-03-27 8:12 ` Zhenyu Wang
2020-03-27 8:44 ` Tian, Kevin
2020-03-27 8:58 ` Zhenyu Wang
2020-03-27 9:31 ` Tian, Kevin
2020-04-08 5:58 ` [PATCH v3 0/2] VFIO mdev aggregated resources handling Zhenyu Wang
2020-07-07 23:28 ` Tian, Kevin
2020-07-08 1:06 ` Alex Williamson [this message]
2020-07-08 1:54 ` Zhenyu Wang
2020-07-08 3:38 ` Yan Zhao
2020-07-08 3:40 ` Yan Zhao
2020-07-08 4:17 ` Alex Williamson
2020-07-08 6:31 ` Tian, Kevin
2020-07-08 9:54 ` Zhenyu Wang
2020-07-08 18:48 ` Alex Williamson
2020-07-09 2:53 ` Tian, Kevin
2020-07-09 7:23 ` Yan Zhao
2020-07-09 20:22 ` Alex Williamson
2020-07-10 1:58 ` Yan Zhao
2020-07-10 15:00 ` Alex Williamson
2020-07-09 17:28 ` Alex Williamson
2020-07-10 2:09 ` Tian, Kevin
2020-07-10 6:29 ` Yan Zhao
2020-07-10 15:12 ` Alex Williamson
2020-07-13 0:59 ` Yan Zhao
2020-04-08 5:58 ` [PATCH v3 1/2] Documentation/driver-api/vfio-mediated-device.rst: update for aggregation support Zhenyu Wang
2020-04-08 5:58 ` [PATCH v3 2/2] drm/i915/gvt: mdev aggregation type Zhenyu Wang
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=20200707190634.4d9055fe@x1.home \
--to=alex.williamson@redhat.com \
--cc=intel-gvt-dev@lists.freedesktop.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=zhenyuw@linux.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;
as well as URLs for NNTP newsgroup(s).