Re: [PATCH 2/4] x86/cpufeatures: Add AMD feature bits for Prediction Command

[Tom Lendacky <thomas.lendacky@amd.com>]

On 1/21/2018 6:22 AM, David Woodhouse wrote:
> 
>> On Sat, Jan 20, 2018 at 12:03:31PM +0000, David Woodhouse wrote:
>>> AMD doesn't implement the Speculation Control MSR that Intel does, but
>>> the Prediction Control MSR does exist and is advertised by a separate
>>> CPUID bit. Add support for that.
>>>
>>> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
>>> ---
>>>  arch/x86/include/asm/cpufeatures.h | 1 +
>>>  arch/x86/kernel/cpu/scattered.c    | 1 +
>>>  2 files changed, 2 insertions(+)
>>>
>>> diff --git a/arch/x86/include/asm/cpufeatures.h
>>> b/arch/x86/include/asm/cpufeatures.h
>>> index adebdaa..624d978 100644
>>> --- a/arch/x86/include/asm/cpufeatures.h
>>> +++ b/arch/x86/include/asm/cpufeatures.h
>>> @@ -207,6 +207,7 @@
>>>  #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* AMD Retpoline
>>> mitigation for Spectre variant 2 */
>>>  #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory
>>> Number */
>>>
>>> +#define X86_FEATURE_AMD_PRED_CMD	( 7*32+17) /* Prediction Command MSR
>>> (AMD) */

You should use the existing 0x80000008 EBX entry for this.

>>
>> Right, so this bit I've seen being called differently. Tom, can you
>> clarify pls?
> 
> Yeah, that's fat-fingered in a cut/paste in refactoring. Fixed in what I
> posted this morning. I would like to see public docs with it though...
> Tom?

I'm looking to see if we have our specification posted on a public link.
But, in the meantime, AMD will advertise all three features (IBRS, IBPB
and STIBP) in separate CPUID bits:

IBPB:  0x80000008 EBX[12]
IBRS:  0x80000008 EBX[14]
STIBP: 0x80000008 EBX[15]

And we will follow the Intel specification should we set the bits in
CPUID 0x7.

For example, IBPB support would be indicated by CPUID:
   0x80000008 EBX[12] || 0x7 EDX[26]

Thanks,
Tom

>