Re: [PATCH v3 00/16] TDX: Enable Dynamic PAMT

[Edgecombe, Rick P]

On Mon, 2025-09-29 at 09:58 -0700, Rick Edgecombe wrote:
> It might serve a purpose of proving that scalability is possible. I was thinking
> if we had line of sight to improving it we could go with the "simple" solution
> and wait until there is a problem. Is it reasonable?

We discussed this offline and the conclusion was to just keep a global
reader/writer lock as the backpocket solution. So DPAMT seamcalls take the
global reader, and if they get a BUSY code, they take the global lock as write
and retry. Similar to what KVM does on a per-VM scope, but globally and reduced
by the refcount.

But until there is a measured issue, just keep the simpler global exclusive lock
with the refcount to start. So unless anyone new chimes in, we can call this
closed.