On April 11, 2025 9:32:32 PM PDT, Xin Li <xin@xxxxxxxxx> wrote: >On 4/11/2025 2:12 PM, Jim Mattson wrote: >> Surely, any CPU that has WRMSRNS also supports "Virtualize >> IA32_SPEC_CTRL," right? Shouldn't we be using that feature rather than >> swapping host and guest values with some form of WRMSR? > >Good question, the simple answer is that they are irrelevant. Also, *in this specific case* IA32_SPEC_CTRL is architecturally nonserializing, i.e. WRMSR executes as WRMSRNS anyway.