Re: [PATCH 10/11] x86/fpu: prepare copy_fpstate_to_sigframe for TIF_LOAD_FPU

[Sebastian Andrzej Siewior]

On 2018-10-15 17:24:31 [+0200], Borislav Petkov wrote:
> On Fri, Oct 12, 2018 at 12:40:19PM -0700, Dave Hansen wrote:
> > > +	__fpregs_changes_end();
> > 
> > Do we really need the __fpregs_changes_*() abstraction for this single
> > call site?
> 
> Yap, I'm staring at those in patch 2, there's no documentation there what
> they're supposed to do, only the commit message of patch 11 says:
> 
> "The __fpregs_changes_{begin|end}() section ensures that the register
> remain unchanged. Otherwise a context switch or a BH could save the
> registers to its FPU context and processor's FPU register would remain
> random."
> 
> So I'd say we should drop that abstraction, use preempt_* and put that
> text above the single usage site.

There are more than one caller and this function disables preemption and
BH in the end. Therefore I would like to keep it. But as suggested in
the previous patch I will think about renaming it.

> Thx.

Sebastian