NVIDIA GPU driver infrastructure
 help / color / mirror / Atom feed
From: Zhi Wang <zhiw@nvidia.com>
To: Alexandre Courbot <acourbot@nvidia.com>
Cc: <dakr@kernel.org>, <airlied@gmail.com>, <simona@ffwll.ch>,
	<ojeda@kernel.org>, <alex.gaynor@gmail.com>,
	<boqun.feng@gmail.com>, <gary@garyguo.net>,
	<bjorn3_gh@protonmail.com>, <lossin@kernel.org>,
	<a.hindborg@kernel.org>, <aliceryhl@google.com>,
	<tmgross@umich.edu>, <jhubbard@nvidia.com>,
	<ecourtney@nvidia.com>, <joelagnelf@nvidia.com>,
	<apopple@nvidia.com>, <cjia@nvidia.com>, <smitra@nvidia.com>,
	<kjaju@nvidia.com>, <alkumar@nvidia.com>, <ankita@nvidia.com>,
	<aniketa@nvidia.com>, <kwankhede@nvidia.com>,
	<targupta@nvidia.com>, <nova-gpu@lists.linux.dev>,
	<linux-kernel@vger.kernel.org>, <zhiwang@kernel.org>
Subject: Re: [PATCH] gpu: nova-core: reserve a larger GSP WPR2 heap when vGPU is enabled
Date: Wed, 17 Jun 2026 11:07:19 +0300	[thread overview]
Message-ID: <20260617110719.7736f80c@inno-dell> (raw)
In-Reply-To: <DJAJGC4LLOK3.YAX75103O00O@nvidia.com>

On Tue, 16 Jun 2026 23:20:41 +0900
"Alexandre Courbot" <acourbot@nvidia.com> wrote:

> On Thu Jun 4, 2026 at 8:43 PM JST, Zhi Wang wrote:

snip

> 
> `total_vfs` is only meaningful if `vgpu_requested` is true. So these
> two parameters would be better modeled using an `Option`, or maybe
> even better a dedicated parameter type for vGPU settings? Something
> like (please pick a better name if any):
> 
>     enum VgpuRequest {
>         Disabled,
>         Requested {
>             total_vfs: u16,
>         }
>     }
> 

Make sense. Let me try. 

> > +    ) -> Result<Self> {

snip

> > diff --git a/drivers/gpu/nova-core/gsp/fw.rs
> > b/drivers/gpu/nova-core/gsp/fw.rs index 14424a2c2d83..2f3cbc5d5114
> > 100644 --- a/drivers/gpu/nova-core/gsp/fw.rs
> > +++ b/drivers/gpu/nova-core/gsp/fw.rs
> > @@ -101,6 +101,18 @@ pub(in crate::gsp) fn
> > advance_cpu_write_ptr(qs: &Coherent<GspMem>, count: u32) {
> > pub(crate) const GSP_MSG_QUEUE_ELEMENT_SIZE_MAX: usize =
> > num::u32_as_usize(bindings::GSP_MSG_QUEUE_ELEMENT_SIZE_MAX); 
> > +const GSP_FW_HEAP_SIZE_VGPU_1VM: u64 = 174 * u64::SZ_1M;
> > +const GSP_FW_HEAP_SIZE_VGPU_DEFAULT: u64 = 581 * u64::SZ_1M;
> > +const GSP_FW_HEAP_SIZE_VGPU_48VMS: u64 = 1370 * u64::SZ_1M;  
> 
> Do we have a source of truth for these values? I can see definitions
> for `GSP_FW_HEAP_SIZE_VGPU_DEFAULT` and `GSP_FW_HEAP_SIZE_VGPU_48VMS`
> in OpenRM (meaning we could generate bindings for them), but cannot
> find a reference for `GSP_FW_HEAP_SIZE_VGPU_1VM`...

I see. Let me remove this one and we can add this when OpenRM has it.

Z.


  parent reply	other threads:[~2026-06-17  8:07 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-04 11:43 [PATCH 0/9] gpu: nova-core: boot GSP with vGPU enabled on Zhi Wang
2026-06-04 11:43 ` [PATCH 1/9] rust: pci: expose sriov_get_totalvfs() helper Zhi Wang
2026-06-05 14:08   ` Alexandre Courbot
2026-06-17  7:51     ` Zhi Wang
2026-06-04 11:43 ` [PATCH 2/9] gpu: nova-core: factor out common FSP message header Zhi Wang
2026-06-05 13:21   ` Alexandre Courbot
2026-06-04 11:43 ` [PATCH 3/9] gpu: nova-core: return FSP response buffer to caller Zhi Wang
2026-06-05 13:25   ` Alexandre Courbot
2026-06-05 16:04     ` Zhi Wang
2026-06-09  6:07       ` Alexandre Courbot
2026-06-17  7:52         ` Zhi Wang
2026-06-04 11:43 ` [PATCH 4/9] gpu: nova-core: read vGPU mode from FSP via PRC protocol Zhi Wang
2026-06-16  8:35   ` Alexandre Courbot
2026-06-17  8:01     ` Zhi Wang
2026-06-04 11:43 ` [PATCH 5/9] gpu: nova-core: add FSP and PRC protocol documentation Zhi Wang
2026-06-16  8:17   ` Alexandre Courbot
2026-06-17  7:51     ` Zhi Wang
2026-06-17 13:21       ` Alexandre Courbot
2026-06-04 11:43 ` [PATCH 6/9] gpu: nova-core: consolidate GSP boot parameters into GspBootContext Zhi Wang
2026-06-16 14:13   ` Alexandre Courbot
2026-06-17 13:22     ` Alexandre Courbot
2026-06-04 11:43 ` [PATCH 7/9] gpu: nova-core: add vGPU preludes Zhi Wang
2026-06-17  3:08   ` Alexandre Courbot
2026-06-04 11:43 ` [PATCH 8/9] gpu: nova-core: set RMSetSriovMode when NVIDIA vGPU is enabled Zhi Wang
2026-06-17  3:13   ` Alexandre Courbot
2026-06-04 11:43 ` [PATCH] gpu: nova-core: reserve a larger GSP WPR2 heap when " Zhi Wang
2026-06-16 14:20   ` Alexandre Courbot
2026-06-17  3:09     ` Alexandre Courbot
2026-06-17  8:07     ` Zhi Wang [this message]
2026-06-17 12:02       ` Alexandre Courbot

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=20260617110719.7736f80c@inno-dell \
    --to=zhiw@nvidia.com \
    --cc=a.hindborg@kernel.org \
    --cc=acourbot@nvidia.com \
    --cc=airlied@gmail.com \
    --cc=alex.gaynor@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=alkumar@nvidia.com \
    --cc=aniketa@nvidia.com \
    --cc=ankita@nvidia.com \
    --cc=apopple@nvidia.com \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun.feng@gmail.com \
    --cc=cjia@nvidia.com \
    --cc=dakr@kernel.org \
    --cc=ecourtney@nvidia.com \
    --cc=gary@garyguo.net \
    --cc=jhubbard@nvidia.com \
    --cc=joelagnelf@nvidia.com \
    --cc=kjaju@nvidia.com \
    --cc=kwankhede@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lossin@kernel.org \
    --cc=nova-gpu@lists.linux.dev \
    --cc=ojeda@kernel.org \
    --cc=simona@ffwll.ch \
    --cc=smitra@nvidia.com \
    --cc=targupta@nvidia.com \
    --cc=tmgross@umich.edu \
    --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