Re: [Xen-devel] [PATCH v8 13/17] x86/boot: Calculate the most appropriate BTI mitigation to use

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

On 16/01/18 14:25, Boris Ostrovsky wrote:
> On 01/16/2018 09:13 AM, Andrew Cooper wrote:
>> On 16/01/18 14:10, Boris Ostrovsky wrote:
>>> On 01/12/2018 01:01 PM, Andrew Cooper wrote:
>>>>  
>>>> +    if ( boot_cpu_has(X86_FEATURE_IBRSB) )
>>>> +    {
>>>> +        /*
>>>> +         * Even if we've chosen to not have IBRS set in Xen context, we 
>>>> still
>>>> +         * need the IBRS entry/exit logic to virtualise IBRS support for
>>>> +         * guests.
>>>> +         */
>>>> +        if ( ibrs )
>>>> +            setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_SET);
>>>> +        else
>>>> +            setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_CLEAR);
>>>> +    }
>>>>
>>> Are you going to add support for Intel's "Enhanced IBRS" (I think that's
>>> what they call the "always on" mode")?
>> I'm not going to touch IBRS_ATT mode until I've got an SDP to develop
>> against.
>>
>> Given how many times the IBRS_ATT spec has changed already, I have
>> little confidence that it will remain unchanged right to the eventual
>> hardware arrives.
> I don't know if you are aware of it (I learned about this doc on Sunday) but
>
> https://software.intel.com/sites/default/files/managed/c5/63/336996-Speculative-Execution-Side-Channel-Mitigations.pdf
>
> (Not part of the SDM but still, an official specification. For a change.)

Wow - the published 1.0 has far more than the prerelease versions.

Still, ARCH_CAPS is only going to appear in new hardware, which is still
probably years away.  There are more important things to worry about at
the moment.

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel