Re: [RFC PATCH] powerpc/32: Switch VDSO to C implementation.

[Christophe Leroy]

Le 26/10/2019 Ã 17:53, Thomas Gleixner a ÃcritÂ:
> On Tue, 22 Oct 2019, Christophe Leroy wrote:
> > Le 22/10/2019 Ã 11:01, Christophe Leroy a ÃcritÂ:
> > > Le 21/10/2019 Ã 23:29, Thomas Gleixner a ÃcritÂ:
> > > > On Mon, 21 Oct 2019, Christophe Leroy wrote:
> > > >
> > > > > This is a tentative to switch powerpc/32 vdso to generic C
> > > > > implementation.
> > > > > It will likely not work on 64 bits or even build properly at the moment.
> > > > >
> > > > > powerpc is a bit special for VDSO as well as system calls in the
> > > > > way that it requires setting CR SO bit which cannot be done in C.
> > > > > Therefore, entry/exit and fallback needs to be performed in ASM.
> > > > >
> > > > > To allow that, C fallbacks just return -1 and the ASM entry point
> > > > > performs the system call when the C function returns -1.
> > > > >
> > > > > The performance is rather disappoiting. That's most likely all
> > > > > calculation in the C implementation are based on 64 bits math and
> > > > > converted to 32 bits at the very end. I guess C implementation should
> > > > > use 32 bits math like the assembly VDSO does as of today.
> > > >
> > > > > gettimeofday:ÂÂÂ vdso: 750 nsec/call
> > > > >
> > > > > gettimeofday:ÂÂÂ vdso: 1533 nsec/call
> > >
> > > Small improvement (3%) with the proposed change:
> > >
> > > gettimeofday:ÂÂÂ vdso: 1485 nsec/call
> >
> > By inlining do_hres() I get the following:
> >
> > gettimeofday:    vdso: 1072 nsec/call
>
> What's the effect for clock_gettime()?
>
> gettimeofday() is suboptimal vs. the PPC ASM variant due to an extra
> division, but clock_gettime() should be 1:1 comparable.

Original PPC asm:
clock-gettime-realtime:    vdso: 928 nsec/call

My original RFC:
clock-gettime-realtime:    vdso: 1570 nsec/call

With your suggested vdso_calc_delta():
clock-gettime-realtime:    vdso: 1512 nsec/call

With your vdso_calc_delta() and inlined do_hres():
clock-gettime-realtime:    vdso: 1302 nsec/call

Christophe