Messages in this thread | | | Date | Fri, 2 Nov 2018 16:44:16 +0100 | From | Sebastian Andrzej Siewior <> | Subject | Re: [PATCH 10/11] x86/fpu: prepare copy_fpstate_to_sigframe for TIF_LOAD_FPU |
| |
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
| |