Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-16 Thread Andrew Cooper
On 16/06/2023 1:12 pm, Jan Beulich wrote: > On 15.06.2023 20:17, Andrew Cooper wrote: >> On 15/06/2023 1:13 pm, Jan Beulich wrote: >>> On 15.06.2023 12:41, Andrew Cooper wrote: On 15/06/2023 9:30 am, Jan Beulich wrote: > On 14.06.2023 20:12, Andrew Cooper wrote: >> On 13/06/2023 10:59

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-16 Thread Jan Beulich
On 15.06.2023 20:17, Andrew Cooper wrote: > On 15/06/2023 1:13 pm, Jan Beulich wrote: >> On 15.06.2023 12:41, Andrew Cooper wrote: >>> On 15/06/2023 9:30 am, Jan Beulich wrote: On 14.06.2023 20:12, Andrew Cooper wrote: > On 13/06/2023 10:59 am, Jan Beulich wrote: >> On 12.06.2023 18:13

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-15 Thread Andrew Cooper
On 15/06/2023 1:13 pm, Jan Beulich wrote: > On 15.06.2023 12:41, Andrew Cooper wrote: >> On 15/06/2023 9:30 am, Jan Beulich wrote: >>> On 14.06.2023 20:12, Andrew Cooper wrote: On 13/06/2023 10:59 am, Jan Beulich wrote: > On 12.06.2023 18:13, Andrew Cooper wrote: >> The RSBA bit, "RSB

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-15 Thread Jan Beulich
On 15.06.2023 12:41, Andrew Cooper wrote: > On 15/06/2023 9:30 am, Jan Beulich wrote: >> On 14.06.2023 20:12, Andrew Cooper wrote: >>> On 13/06/2023 10:59 am, Jan Beulich wrote: On 12.06.2023 18:13, Andrew Cooper wrote: > The RSBA bit, "RSB Alternative", means that the RSB may use alternat

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-15 Thread Andrew Cooper
On 15/06/2023 9:30 am, Jan Beulich wrote: > On 14.06.2023 20:12, Andrew Cooper wrote: >> On 13/06/2023 10:59 am, Jan Beulich wrote: >>> On 12.06.2023 18:13, Andrew Cooper wrote: The RSBA bit, "RSB Alternative", means that the RSB may use alternative predictors when empty. From a practica

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-15 Thread Jan Beulich
On 14.06.2023 20:12, Andrew Cooper wrote: > On 13/06/2023 10:59 am, Jan Beulich wrote: >> On 12.06.2023 18:13, Andrew Cooper wrote: >>> The RSBA bit, "RSB Alternative", means that the RSB may use alternative >>> predictors when empty. From a practical point of view, this mean "Retpoline >>> not sa

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-14 Thread Andrew Cooper
On 13/06/2023 10:59 am, Jan Beulich wrote: > On 12.06.2023 18:13, Andrew Cooper wrote: >> The RSBA bit, "RSB Alternative", means that the RSB may use alternative >> predictors when empty. From a practical point of view, this mean "Retpoline >> not safe". >> >> Enhanced IBRS (officially IBRS_ALL in

Re: [PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-13 Thread Jan Beulich
On 12.06.2023 18:13, Andrew Cooper wrote: > The RSBA bit, "RSB Alternative", means that the RSB may use alternative > predictors when empty. From a practical point of view, this mean "Retpoline > not safe". > > Enhanced IBRS (officially IBRS_ALL in Intel's docs, previously IBRS_ATT) is a > statem

[PATCH v3 4/4] x86/cpu-policy: Derive RSBA/RRSBA for guest policies

2023-06-12 Thread Andrew Cooper
The RSBA bit, "RSB Alternative", means that the RSB may use alternative predictors when empty. From a practical point of view, this mean "Retpoline not safe". Enhanced IBRS (officially IBRS_ALL in Intel's docs, previously IBRS_ATT) is a statement that IBRS is implemented in hardware (as opposed t