Re: [PATCH v2] x86/SVM: restrict hardware SSBD update upon guest VIRT_SPEC_CTRL write

2023-03-02 Thread Jan Beulich
On 01.03.2023 21:55, Andrew Cooper wrote: > On 15/12/2022 8:20 am, Jan Beulich wrote: >> core_set_legacy_ssbd() counts the number of times SSBD is being enabled >> via LS_CFG on a core. This assumes that calls there only occur if the >> state actually changes. While svm_ctxt_switch_{to,from}() conf

Re: [PATCH v2] x86/SVM: restrict hardware SSBD update upon guest VIRT_SPEC_CTRL write

2023-03-01 Thread Andrew Cooper
On 15/12/2022 8:20 am, Jan Beulich wrote: > core_set_legacy_ssbd() counts the number of times SSBD is being enabled > via LS_CFG on a core. This assumes that calls there only occur if the > state actually changes. While svm_ctxt_switch_{to,from}() conform to > this, guest_wrmsr() doesn't: It also c

[PATCH v2] x86/SVM: restrict hardware SSBD update upon guest VIRT_SPEC_CTRL write

2022-12-15 Thread Jan Beulich
core_set_legacy_ssbd() counts the number of times SSBD is being enabled via LS_CFG on a core. This assumes that calls there only occur if the state actually changes. While svm_ctxt_switch_{to,from}() conform to this, guest_wrmsr() doesn't: It also calls the function when the bit doesn't actually ch