Re: [PATCH] x86: Prefer MWAIT over HALT on AMD processors

[Wyes Karny]

On 4/5/2022 7:35 PM, Borislav Petkov wrote:
> On Tue, Apr 05, 2022 at 06:30:21PM +0530, Wyes Karny wrote:
>> From: Lewis Caroll <lewis.carroll@xxxxxxx>
>>
>> Currently in the absence of the cpuidle driver (eg: when global
>> C-States are disabled in the BIOS or when cpuidle is driver is not
>> compiled in),
> 
> When does that ever happen?
> 
> Sounds like a very very niche situation to me...
Certain customers prefer to turn off C-States from the BIOS in
low-latency environments.

> 
>> Here we enable MWAIT instruction as the default idle call for AMD
>> Zen processors which support MWAIT. We retain the existing behaviour
>> for older processors which depend on HALT.
> 
> Please use passive voice in your commit message: no "we" or "I", etc,
> and describe your changes in imperative mood.
> 
> Also, pls read section "2) Describe your changes" in
> Documentation/process/submitting-patches.rst for more details.
> 
> Also, see section "Changelog" in
> Documentation/process/maintainer-tip.rst
> 
> Bottom line is: personal pronouns are ambiguous in text, especially with
> so many parties/companies/etc developing the kernel so let's avoid them
> please.

Sure. I'll update this. Thanks.
> 
>>  static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
>>  {
>> -	if (c->x86_vendor != X86_VENDOR_INTEL)
>> +	if (!early_mwait_supported(c))
> 
> Isn't it enough to simply do here:
> 
> 	if (cpu_has(c, X86_FEATURE_ZEN))
> 		return 1;
> 
>         if (c->x86_vendor != X86_VENDOR_INTEL)
>                 return 0;
> 
> 	...
> 
> 

If x86_FEATURE_ZEN is set and X86_FEATURE_MWAIT is not set or has X86_BUG_MONITOR
then it won't return correct value.

--
Thanks,
Wyes