Re: [PATCH 01/15] x86/virt/tdx: Read global metadata for TDX Module Extensions

[Edgecombe, Rick P]

On Thu, 2026-05-28 at 12:25 +0800, Xu Yilun wrote:
> > > 
> > > If I read the TDX module base spec correctly, the amount of memory for
> > > extensions and EXT_REQUIRED field depends on the enabled features, which
> > > is
> > > determined by TDH.SYS.CONFIG/TDH.SYS.UPDATE ?
> 
> Yes.
> 
> > 
> > This is my read too. Looks like we need a separate step after
> > config_tdx_module() to readout config-dependatant metadata.
> 
> 
> The timing for when metadata becomes valid is now variable, e.g., the
> TDX QUOTING metadata is only valid after TDH.QUOTE.INIT [1].
> 
> Based on recent discussion, I think we should introduce runtime metadata
> reading interfaces for specific metadata sets as needed, rather than
> another catch-all step right after config_tdx_module(). See [2] for the
> proposed approach for Extensions metadata.
> 
> [1]:
> https://lore.kernel.org/all/20260522034128.3144354-7-yilun.xu@xxxxxxxxxxxxxxx/
> [2]: https://lore.kernel.org/all/ahXAL41ZmIDHmgfu@yilunxu-OptiPlex-7050/

Yea It is going to get confusing as to which metadata is populated at which
step. And if anything updates it.

I'm not sure we need to have all the metadata stored permanently. Some of the
metadata is needed for KVM and someday TSM. But a lot of it is onetime internal
use. There is some handiness in referring to a global var, but also those
reference add confusion as to when it got populated.

We only use ext_required, max_quote_size and memory_pool_required_pages each
once. So why not just read them to the stack and leave them out of struct
tdx_sys_info? Making it so there is not confusion of when it was read. And also
saving a global var that is never used again is a bit wrong.

How about for struct tdx_sys_info_ext read it to the stack in init_tdx_ext() and
pass it into init_tdx_ext_features(). For max_quote_size read it where it is
already read, but not into the global struct.

Do you see a problem?