Re: [PATCH v2 7/9] x86/svm: VMEntry/Exit logic for MSR_SPEC_CTRL

2022-01-31 Thread Andrew Cooper
On 31/01/2022 12:55, Jan Beulich wrote: > On 28.01.2022 14:29, Andrew Cooper wrote: >> --- a/xen/arch/x86/hvm/svm/entry.S >> +++ b/xen/arch/x86/hvm/svm/entry.S >> @@ -55,11 +55,12 @@ __UNLIKELY_END(nsvm_hap) >> mov %rsp, %rdi >> call svm_vmenter_helper >> >> -mov

Re: [PATCH v2 7/9] x86/svm: VMEntry/Exit logic for MSR_SPEC_CTRL

2022-01-31 Thread Jan Beulich
On 28.01.2022 14:29, Andrew Cooper wrote: > --- a/xen/arch/x86/hvm/svm/entry.S > +++ b/xen/arch/x86/hvm/svm/entry.S > @@ -55,11 +55,12 @@ __UNLIKELY_END(nsvm_hap) > mov %rsp, %rdi > call svm_vmenter_helper > > -mov VCPU_arch_msrs(%rbx), %rax > -mov

Re: [PATCH v2 7/9] x86/svm: VMEntry/Exit logic for MSR_SPEC_CTRL

2022-01-31 Thread Andrew Cooper
On 31/01/2022 10:33, Jan Beulich wrote: > On 28.01.2022 14:29, Andrew Cooper wrote: >> Hardware maintains both host and guest versions of MSR_SPEC_CTRL, but guests >> run with the logical OR of both values. Therefore, in principle we want to >> clear Xen's value before entering the guest.

Re: [PATCH v2 7/9] x86/svm: VMEntry/Exit logic for MSR_SPEC_CTRL

2022-01-31 Thread Jan Beulich
On 28.01.2022 14:29, Andrew Cooper wrote: > Hardware maintains both host and guest versions of MSR_SPEC_CTRL, but guests > run with the logical OR of both values. Therefore, in principle we want to > clear Xen's value before entering the guest. However, for migration > compatibility, and for

[PATCH v2 7/9] x86/svm: VMEntry/Exit logic for MSR_SPEC_CTRL

2022-01-28 Thread Andrew Cooper
Hardware maintains both host and guest versions of MSR_SPEC_CTRL, but guests run with the logical OR of both values. Therefore, in principle we want to clear Xen's value before entering the guest. However, for migration compatibility, and for performance reasons with SEV-SNP guests, we want the