Re: [PATCH v6 1/2] x86/msr: Add write msr notrace

[Wanpeng Li]

2016-10-29 0:47 GMT+08:00 Borislav Petkov <bp@xxxxxxxxx>:
[...]
>>
>>  /* Can be uninlined because referenced by paravirt */
>> -notrace static inline void native_write_msr(unsigned int msr,
>> +notrace static inline void __native_write_msr_notrace(unsigned int msr,
>>                                           unsigned low, unsigned high)
>                                             ^^^^^^^
> Align arguments on an opening brace.

Other functions like native_write_msr() and native_write_msr_safe()
etc are also not aligned, so your suggestion maybe result in
inconsistent.

>
> Also, please fix that in a patch ontop of this one:
>
> WARNING: storage class should be at the beginning of the declaration
> #43: FILE: arch/x86/include/asm/msr.h:118:
> +notrace static inline void __native_write_msr_notrace(unsigned int msr,
>
> WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
> #54: FILE: arch/x86/include/asm/msr.h:129:
> +                                           unsigned low, unsigned high)
>
> And because we know what those are, you can convert them directly to u32.

Ditto.

>
> IOW, the end result should be something like this:
>
> static inline void notrace
> __native_write_msr_notrace(unsigned int msr, u32 low, u32 high)
>
> And yes, I suggested using the "_notrace" suffix for the name but then
> it would look funny if we end up using it in code.
>
> So maybe we should make that lower-level helper simply:
>
> static inline void notrace
> __native_write_msr(unsigned int msr, u32 low, u32 high)
>
> to denote that it does purely the WRMSR operation and nothing else.
>
> Yap, that looks the cleanest to me.

Agreed.

Regards,
Wanpeng Li