Re: [PATCH 7/7] nova-core: mm: Add data structures for page table management

[John Hubbard <jhubbard@nvidia.com>]

On 10/21/25 11:26 AM, Joel Fernandes wrote:
> On 10/20/2025 4:59 PM, John Hubbard wrote:
>> On 10/20/25 11:55 AM, Joel Fernandes wrote:
>> ...
> Yes, there's different format versions.
> 
> This patch supports all Turing and later GPUs because all GPUs including Hopper+
> are backward compatible with version 1. However they wont be able to use the
> version 2 and 3 features with only this patch.
> 
> I kind of intentionally did this for a first cut. But yes, I could split it into
> versions. The 3 MMU structures (PTE, PDE and Dual PDE) are versioned. Version 2
> is Turing and later. Hopper+ is when Version 3 got introduced and it is also

Ah, then we shouldn't even do version 1. We should take full advantage of
the fact that Nova's earliest GPU is Turing.

> backward compatible with Version 2.
> 
> We could eventually support versions 2 and 3 (instead of just version 1 as I am
> doing), however my working MMU translation prototype is based on version 1 (I
> did not have to configure anything in the MMU to switch versions, this was default).
> 
> There are a couple of options:
> 
> 1. For starters, support only version 1. Drawback is, when/if we want to use
> version 2 and 3 features, it may require some rework.
> 
> 2. Have the following hierarchy:
> mm/types.rs - all common structures (stuff that is generic like Pfn).
> mm/types/ver1.rs - Version 1 specific types.
> mm/types/ver2.rs - Version 2 specific types.
> mm/types/ver3.rs - Version 3 specific types.

Maybe a file/directory structure that more directly indicates page table
formats. "mm/types" could be quite a few things.

> The advantage of this is it keeps the structs namespaced. So it'd be
> nova_core::mm:types::ver2::Pte or nova_core::mm:types::ver3::Pte. And the
> nova-core MMU code can pick the correct version.
> 
> 3. Keep the single file types.rs and just suffix the structs with version
> numbers. This is attractive because there are only 3 types that have version
> flavors (pte, pde and dual pde). So instead of Pte, we would have PteVersion1,
> PteVersion2 etc, and a helper abstraction can pick the correct struct.
> 
> 4. Any of the options 1-3, but dropping version 1 since Turing+ supports version
> 2 and later. I do have to figure out how to configure the MMU to use a specific

Right, I see you already noticed that we can start with Turing. Good.

> version (which is reasonable).
> 
> 5. Your options here.
> 
> Btw, I used Nouveau as a reference as well, so likely Nouveau doesn't support
> version 2 and 3 features. Not that that matters (we should support newer
> features in nova-core), but just thought I'd mention it.
> 
> Other thoughts?

Two things:

1) Danilo is working on writing down locking requirements for Nova page
tables, based on earlier experience with Nouveau page table locking
problems, which were apparently very serious.

2) Maybe it would be good to start with versions 2 and 3, so that we
can see how to do >1 version?

thanks,
-- 
John Hubbard