Re: early x86 unseeded randomness

From: Thomas Gleixner
Date: Tue Aug 15 2017 - 09:48:42 EST


On Tue, 15 Aug 2017, Borislav Petkov wrote:
> On Tue, Aug 15, 2017 at 12:47:36PM +0200, Thomas Gleixner wrote:
> > 8<-------------------
> >
> > --- a/arch/x86/kernel/tsc.c
> > +++ b/arch/x86/kernel/tsc.c
> > @@ -1360,3 +1360,19 @@ unsigned long calibrate_delay_is_known(v
> > return 0;
> > }
> > #endif
> > +
> > +u64 __init tsc_early_random(void)
> > +{
> > + u64 uninitialized_var(res);
> > + int i;
> > +
> > + if (!boot_cpu_has(X86_FEATURE_TSC))
> > + return res;
> > +
> > + res ^= rdtsc();
> > + for (i = 0; i < BITS_PER_LONG; i++) {
> > + res ^= ((rdtsc() & 0x04) >> 2) << i;
> > + udelay(2);
> > + }
> > + return res;
> > +}
>
> Something like this is exactly what I was aiming at with my dumb patch.
> We could use this for early boot randomness on x86.
>
> Should I turn it into proper patches or you want to?

Go ahead. What you actually want to do is to replace boot_cpu_has() with a
real cpuid() check because boot_cpu_has() is not initialized on real early
boot.

Thanks,

tglx