Re: AMD Athlon bogus performance value causing RCU stalls?

[Thomas Gleixner]

On Wed, 26 Sep 2018, Rob Prowel wrote:
> On 09/23/18 17:19, Thomas Gleixner wrote:
> > > 
> > > Other than RTFM, or please build a bunch of kernels from source on your
> > > slow
> > > machine, using differing config options to help track down the cause of
> > > this...any thoughts about a solution?
> > 
> > Yes. This was decoded recently as an issue on 32bit due to a calculation
> > which is based on 'unsigned long' but requires to be 64bit wide.
> > 
> > It's in the 4.18.8 stable kernel, which should be available from your
> > fedora repo anytime soon.
> 
> OK.  Followup on AMD performance counter problem in 4.18.7
> 
> The Dell machine I was experiencing the problem on had a lot of ACPI
> issues.  One of the invalid ACPI entries was for a system timer.
> dmesg suggests that the broken timer was used in calculating the
> Athlon performance value.  So no, 32/64 bit math was not the issue.

Uff.

> ACPI=off in the kernel boot line fixed the issue completely. Machine
> still functions well as a file/web/postgresql dev server so it's all
> good.

Thanks for letting me know. I was about to dust of that old X2 I have
somewhere.

Thanks,

	tglx