On Wed, 2010-04-07 at 09:50 -0700, David Daney wrote:
[...]
> > +static inline unsigned long long mips_cyc2ns(u64 cyc, u64 mult, u64 shift)
> > +{
> > +#ifdef CONFIG_32BIT
> > + /*
> > + * To balance the overhead of 128bit-arithematic and the precision
> > + * lost, we choose a smaller shift to avoid the quick overflow as the
> > + * X86& ARM does. please refer to arch/x86/kernel/tsc.c and
> > + * arch/arm/plat-orion/time.c
> > + */
> > + return (cyc * mult)>> shift;
>
> Have you tested that on a 32-bit kernel? I think it may overflow for
> many cases.
>
Yes, I have done some basic testing ;)
Since a c0 count with 400MHz clock frequency will overflow after about
more than 1 hour with the scaling factor 10, I think it is enough for
the generic debugging, such as Ftrace, If it is not enough, perhaps we
can choose a smaller scaling factor, such as 8.
The core idea here is to get a smaller mult to let (cyc * mult) not
overflow that quickly but also not get a 'bad' precision, of course, we
can try to implement the 128bit arithmatic in 32bit system, but that may
increase the overhead(not tested it yet, perhaps will be worse than the
original getnstimeofday()).
Regards,
Wu Zhangjin
