Re: [PATCH 04/15] x86/virt/tdx: Enable the Extensions right after basic TDX Module init

[Xu Yilun]

On Thu, May 28, 2026 at 09:32:08PM +0000, Edgecombe, Rick P wrote:
> On Fri, 2026-05-22 at 11:41 +0800, Xu Yilun wrote:
> > The detailed initialization flow for TDX Module Extensions has been
> > fully implemented.
> > 
> 
> I'm not sure what this means exactly. Why "detailed". Is that important?

It's not important. I should re-phrase, The entire initialization flow...

> 
> >  Enable the flow after basic TDX Module
> > initialization.
> > 
> > Theoretically, the Extensions doesn't need to be enabled right after
> > basic TDX initialization. It could be enabled right before the first
> > Extension SEAMCALL is issued. That would save or postpone memory usage.
> > But it isn't worth the complexity, the needs for the Extensions are vast
> > but the savings are little for a typical TDX capable system (about
> > 0.001% of memory). So the Linux decision is to just enable it along with
> > the basic TDX.
> 
> The Linux decision is whatever this patch turns out to be after community
> review. So for the patch log we just need to justify why it's a good idea, not
> not make an argument to defer to authority.

Understood. I'll re-phrase this paragraph according to all the comments,
especially the last sentence.

> 
> > 
> > Note that the Extensions initialization flow will still not start if no
> > add-on features require Extensions. The enabling of add-on features will
> > be in later patches. Until then, the system hasn't consumed extra memory.
> 
> Hmm, this patch reads like we are finally doing the initialization up until this
> point. Then it turns out we don't actually light up the new code yet... 
> 
> A lot of this diff is adding __init to the function added in the earlier
> patches. Do we need to do this? Why not add them as __init in the original
> patches?
> 
> 
> I think we maybe want to say instead that we are setting up to enable extensions
> at TDX module init time, and do the explanation of why. Then without the __init
> stuff, the patch is just about the init time decision. Which seems about right
> sized.

Yes. Since the patch doesn't actually light up anything new, I think it
could just be the first patch of Extensions so add __init at the first
place.