Re: [PATCH 0/6] Add RMPOPT support.

[Dave Hansen]

On 2/17/26 12:09, Ashish Kalra wrote:
> RMPOPT is a new instruction designed to minimize the performance
> overhead of RMP checks for the hypervisor and non-SNP guests. 

This needs a little theory of operation for the new instruction. It
seems like it will enable optimizations all by itself. You just call it,
and it figures out when the CPU can optimize things. The CPU also
figures out when the optimization must be flipped off.

That's not awful.

To be honest, though, I think this is misdesigned. Shouldn't the CPU
*boot* in a state where it is optimized? Why should software have to
tell it that coming out of reset, there is no SEV-SNP memory?