Re: [PATCH 24/27] x86/fpu: Add a fastpath to __fpu__restore_sig()

[Thomas Gleixner]

On Mon, 8 Apr 2019, Sebastian Andrzej Siewior wrote:

> On 2019-04-08 19:05:56 [+0200], Thomas Gleixner wrote:
> > > diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
> > > index a5b086ec426a5..f20e1d1fffa29 100644
> > > --- a/arch/x86/kernel/fpu/signal.c
> > > +++ b/arch/x86/kernel/fpu/signal.c
> > > @@ -242,10 +242,10 @@ sanitize_restored_xstate(union fpregs_state *state,
> > >  /*
> > >   * Restore the extended state if present. Otherwise, restore the FP/SSE state.
> > >   */
> > > -static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
> > > +static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
> > >  {
> > >  	if (use_xsave()) {
> > > -		if ((unsigned long)buf % 64 || fx_only) {
> > > +		if (fx_only) {
> > 
> > This change is weird and not mentioned in the changelog....
> 
> if you scroll up there is this:
> |          * to loaded again on return to userland (overriding last_cpu avoids the
> |          * optimisation).
> |          */
> |         set_thread_flag(TIF_NEED_FPU_LOAD);
> |         __fpu_invalidate_fpregs_state(fpu);
> | 
> |         if ((unsigned long)buf_fx % 64)
> |                 fx_only = 1;
> â
> |                 ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
> |                 pagefault_enable();
> 
> 
> so I just removed that part because it was already done earlier.
> Is it still weird and should be mentioned in the changelog?

Bah. Staring at this for too long. All good ...