Re: [PATCH v2 1/2] x86/msr: Carry on after a non-"safe" MSR access fails without !panic_on_oops

[Ingo Molnar <mingo@kernel.org>]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Mon, Sep 21, 2015 at 1:46 AM, Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Linus, what's your preference?
> 
> So quite frankly, is there any reason we don't just implement
> native_read_msr() as just
> 
>    unsigned long long native_read_msr(unsigned int msr)
>    {
>       int err;
>       unsigned long long val;
> 
>       val = native_read_msr_safe(msr, &err);
>       WARN_ON_ONCE(err);
>       return val;
>    }
> 
> Note: no inline, no nothing. Just put it in arch/x86/lib/msr.c, and be
> done with it. I don't see the downside.

Absolutely!

> How many msr reads are <i>so</i> critical that the function call overhead would 
> matter? Get rid of the inline version of the _safe() thing too, and put that 
> thing there too.

Only a very low number of them is performance critical (because even 
hw-accelerated MSR accesses are generally slow so we try to avoid MSR accesses in 
fast paths as much as possible, via shadowing, etc.) - and in the few cases where 
we have to access an MSR in a fast path we can do those separately.

I'm only worried about the 'default' APIs, i.e. rdmsr() that is used throughout 
arch/x86/ over a hundred times, not about performance critical code paths that get 
enough testing and enough attention in general.

Thanks,

	Ingo