Re: [git-pull -tip] x86: Addition of cpufeatures to friendly access miscellaneous MSRs

["H. Peter Anvin" <hpa@zytor.com>]

Jaswinder Singh Rajput wrote:
> 
> The basic point of these patchset is to friendly access miscellaneous
> MSRs in kernel and userspace.
> 
> Some of these patches are using hardware cpufeature and others are
> software.
> 
> In kernel some of these MSRs are frequently used and doing checking
> before accessing these MSR in various places.
> 
> So I think it will be right approach to check in one place and set
> related cpufeature and in other places we only need to check cpufeature
> and then access MSR.
> 
> This patchset is only adding cpufeature. I will release accessing
> cpufeatures in upcoming series.
> 

For those that have in-kernel users, this is fine (and valid), but this 
is the wrong order in which to do things, since you patchset doesn't 
verify where those happen.  Rather, it's better to follow each 
cpufeature with its users rather than a batch of producers followed by a 
set of consumers.

Note: I do *not* consider debugfs only consumers to be valid in this 
context.

	-hpa