From: Jason Gunthorpe <jgg@nvidia.com>
To: Zhi Wang <zhiw@nvidia.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"nouveau@lists.freedesktop.org" <nouveau@lists.freedesktop.org>,
"alex.williamson@redhat.com" <alex.williamson@redhat.com>,
"kevin.tian@intel.com" <kevin.tian@intel.com>,
"airlied@gmail.com" <airlied@gmail.com>,
"daniel@ffwll.ch" <daniel@ffwll.ch>,
Andy Currid <ACurrid@nvidia.com>, Neo Jia <cjia@nvidia.com>,
Surath Mitra <smitra@nvidia.com>,
Ankit Agrawal <ankita@nvidia.com>,
Aniket Agashe <aniketa@nvidia.com>,
Kirti Wankhede <kwankhede@nvidia.com>,
"Tarun Gupta (SW-GPU)" <targupta@nvidia.com>,
"zhiwang@kernel.org" <zhiwang@kernel.org>
Subject: Re: [RFC 18/29] nvkm/vgpu: introduce pci_driver.sriov_configure() in nvkm
Date: Tue, 15 Oct 2024 09:27:58 -0300 [thread overview]
Message-ID: <20241015122758.GJ3394334@nvidia.com> (raw)
In-Reply-To: <d46ff67d-92f2-4e84-b1a7-1576b422b6a6@nvidia.com>
On Mon, Oct 14, 2024 at 08:32:03AM +0000, Zhi Wang wrote:
> Turning on the SRIOV feature is just a part of the process enabling a
> vGPU. The VF is not instantly usable before a vGPU type is chosen via
> another userspace interface (e.g. fwctl).
That's OK, that has become pretty normal now that VFs are just empty
handles when they are created until they are properly profiled.
> Besides, admin has to enable the vGPU support by some means (e.g. a
> kernel parameter is just one candidate) and GSP firmware needs to be
> configured accordingly when being loaded.
Definitely not a kernel parameter..
> As this is related to user space interface, I am leaning towards putting
> some restriction/checks for the pre-condition in the
> driver.sriov_configure(), so admin would know there is something wrong
> in his configuration as early as possible, instead of he failed to
> creating vGPUs again and again, then he found he forgot to enable the
> vGPU support.
Well, as I've said, this is poor, you shouldn't have a FW SRIOV enable
bit at all, or at least it shouldn't be user configurable.
If the PCI function supports SRIOV then it should work to turn it on.
Jason
next prev parent reply other threads:[~2024-10-15 12:28 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-22 12:49 [RFC 00/29] Introduce NVIDIA GPU Virtualization (vGPU) Support Zhi Wang
2024-09-22 12:49 ` [RFC 01/29] nvkm/vgpu: introduce NVIDIA vGPU support prelude Zhi Wang
2024-09-26 9:20 ` Greg KH
2024-10-14 9:59 ` Zhi Wang
2024-10-14 11:36 ` Greg KH
2024-09-22 12:49 ` [RFC 02/29] nvkm/vgpu: attach to nvkm as a nvkm client Zhi Wang
2024-09-26 9:21 ` Greg KH
2024-10-14 10:16 ` Zhi Wang
2024-10-14 11:33 ` Greg KH
2024-09-22 12:49 ` [RFC 03/29] nvkm/vgpu: reserve a larger GSP heap when NVIDIA vGPU is enabled Zhi Wang
2024-09-22 12:49 ` [RFC 04/29] nvkm/vgpu: set the VF partition count " Zhi Wang
2024-09-26 22:51 ` Jason Gunthorpe
2024-10-13 18:54 ` Zhi Wang
2024-10-15 12:20 ` Jason Gunthorpe
2024-10-15 15:19 ` Zhi Wang
2024-10-15 16:35 ` Jason Gunthorpe
2024-09-22 12:49 ` [RFC 05/29] nvkm/vgpu: populate GSP_VF_INFO " Zhi Wang
2024-09-26 22:52 ` Jason Gunthorpe
2024-09-22 12:49 ` [RFC 06/29] nvkm/vgpu: set RMSetSriovMode " Zhi Wang
2024-09-26 22:53 ` Jason Gunthorpe
2024-10-14 7:38 ` Zhi Wang
2024-10-15 3:49 ` Christoph Hellwig
2024-10-15 12:23 ` Jason Gunthorpe
2024-09-22 12:49 ` [RFC 07/29] nvkm/gsp: add a notify handler for GSP event GPUACCT_PERFMON_UTIL_SAMPLES Zhi Wang
2024-09-22 12:49 ` [RFC 08/29] nvkm/vgpu: get the size VMMU segment from GSP firmware Zhi Wang
2024-09-22 12:49 ` [RFC 09/29] nvkm/vgpu: introduce the reserved channel allocator Zhi Wang
2024-09-22 12:49 ` [RFC 10/29] nvkm/vgpu: introduce interfaces for NVIDIA vGPU VFIO module Zhi Wang
2024-09-22 12:49 ` [RFC 11/29] nvkm/vgpu: introduce GSP RM client alloc and free for vGPU Zhi Wang
2024-09-22 12:49 ` [RFC 12/29] nvkm/vgpu: introduce GSP RM control interface " Zhi Wang
2024-09-22 12:49 ` [RFC 13/29] nvkm: move chid.h to nvkm/engine Zhi Wang
2024-09-22 12:49 ` [RFC 14/29] nvkm/vgpu: introduce channel allocation for vGPU Zhi Wang
2024-09-22 12:49 ` [RFC 15/29] nvkm/vgpu: introduce FB memory " Zhi Wang
2024-09-22 12:49 ` [RFC 16/29] nvkm/vgpu: introduce BAR1 map routines for vGPUs Zhi Wang
2024-09-22 12:49 ` [RFC 17/29] nvkm/vgpu: introduce engine bitmap for vGPU Zhi Wang
2024-09-22 12:49 ` [RFC 18/29] nvkm/vgpu: introduce pci_driver.sriov_configure() in nvkm Zhi Wang
2024-09-26 22:56 ` Jason Gunthorpe
2024-10-14 8:32 ` Zhi Wang
2024-10-15 12:27 ` Jason Gunthorpe [this message]
2024-10-15 15:14 ` Zhi Wang
2024-10-14 8:36 ` Zhi Wang
2024-09-22 12:49 ` [RFC 19/29] vfio/vgpu_mgr: introdcue vGPU lifecycle management prelude Zhi Wang
2024-09-22 12:49 ` [RFC 20/29] vfio/vgpu_mgr: allocate GSP RM client for NVIDIA vGPU manager Zhi Wang
2024-09-22 12:49 ` [RFC 21/29] vfio/vgpu_mgr: introduce vGPU type uploading Zhi Wang
2024-09-22 12:49 ` [RFC 22/29] vfio/vgpu_mgr: allocate vGPU FB memory when creating vGPUs Zhi Wang
2024-09-22 12:49 ` [RFC 23/29] vfio/vgpu_mgr: allocate vGPU channels " Zhi Wang
2024-09-22 12:49 ` [RFC 24/29] vfio/vgpu_mgr: allocate mgmt heap " Zhi Wang
2024-09-22 12:49 ` [RFC 25/29] vfio/vgpu_mgr: map mgmt heap when creating a vGPU Zhi Wang
2024-09-22 12:49 ` [RFC 26/29] vfio/vgpu_mgr: allocate GSP RM client when creating vGPUs Zhi Wang
2024-09-22 12:49 ` [RFC 27/29] vfio/vgpu_mgr: bootload the new vGPU Zhi Wang
2024-09-25 0:31 ` Dave Airlie
2024-09-22 12:49 ` [RFC 28/29] vfio/vgpu_mgr: introduce vGPU host RPC channel Zhi Wang
2024-09-22 12:49 ` [RFC 29/29] vfio/vgpu_mgr: introduce NVIDIA vGPU VFIO variant driver Zhi Wang
2024-09-22 13:11 ` [RFC 00/29] Introduce NVIDIA GPU Virtualization (vGPU) Support Zhi Wang
2024-09-23 8:38 ` Danilo Krummrich
2024-09-24 19:49 ` Zhi Wang
2024-09-23 6:22 ` Tian, Kevin
2024-09-23 15:02 ` Jason Gunthorpe
2024-09-26 6:43 ` Tian, Kevin
2024-09-26 12:55 ` Jason Gunthorpe
2024-09-26 22:57 ` Jason Gunthorpe
2024-09-27 0:13 ` Tian, Kevin
2024-09-23 8:49 ` Danilo Krummrich
2024-09-23 15:01 ` Jason Gunthorpe
2024-09-23 22:50 ` Danilo Krummrich
2024-09-24 16:41 ` Jason Gunthorpe
2024-09-24 19:56 ` Danilo Krummrich
2024-09-24 22:52 ` Dave Airlie
2024-09-24 23:47 ` Jason Gunthorpe
2024-09-25 0:18 ` Dave Airlie
2024-09-25 1:29 ` Jason Gunthorpe
2024-09-25 0:53 ` Jason Gunthorpe
2024-09-25 1:08 ` Dave Airlie
2024-09-25 15:28 ` Jason Gunthorpe
2024-09-25 10:55 ` Danilo Krummrich
2024-09-26 9:14 ` Greg KH
2024-09-26 12:42 ` Jason Gunthorpe
2024-09-26 12:54 ` Greg KH
2024-09-26 13:07 ` Danilo Krummrich
2024-09-26 14:40 ` Jason Gunthorpe
2024-09-26 18:07 ` Andy Ritger
2024-09-26 22:23 ` Danilo Krummrich
2024-09-26 22:42 ` Danilo Krummrich
2024-09-27 12:51 ` Jason Gunthorpe
2024-09-27 14:22 ` Danilo Krummrich
2024-09-27 15:27 ` Jason Gunthorpe
2024-09-30 15:59 ` Danilo Krummrich
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=20241015122758.GJ3394334@nvidia.com \
--to=jgg@nvidia.com \
--cc=ACurrid@nvidia.com \
--cc=airlied@gmail.com \
--cc=alex.williamson@redhat.com \
--cc=aniketa@nvidia.com \
--cc=ankita@nvidia.com \
--cc=cjia@nvidia.com \
--cc=daniel@ffwll.ch \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=kwankhede@nvidia.com \
--cc=nouveau@lists.freedesktop.org \
--cc=smitra@nvidia.com \
--cc=targupta@nvidia.com \
--cc=zhiw@nvidia.com \
--cc=zhiwang@kernel.org \
/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