Re: [PATCH] Re: AMD Mobile Semprons (3500+, 3600+,...) break with nohz and highres enabled

[Thomas Gleixner <tglx@linutronix.de>]

On Thu, 17 Jul 2008, Richard wrote:
> > north-bridge: nvidia c51mv
> > south-bridge: nvidia mcp51m
> > 
> > Also both are MSI laptops:
> >   - MSI-M670, modell MS-1632
> >   - MSI S430x
> > (This could also be a chipset or even an MSI specific BIOS bug?
> > Richard could you compare with your HW, pls if still possible).
> > 
> > Some more info:
> >   - things break entering C2 or deeper
> >   - noapictimer workaround helps to come a bit further, but results in sever
> >     other errors, disk(dma error), keyboad, mouse etc., also see:

Hmm, I don't see how the apic timer is related to that, but it might
be a problem with the hpet.

Does "noapictimer nohz=off" work ?

> >     https://bugzilla.novell.com/show_bug.cgi?id=396220#c13
> >   - "nohz=off" works (tested on 2.6.25.4-8-pae and 2.6.22.17-0.1-default
> > SUSE kernels)
> >   - processor.max_cstate=1 works

Why does it work with 2.6.24 on kubuntu 8.04 ? 

How does a 2.6.24/25/26 vanilla kernel behave on those systems ?

> > 00:09.0 RAM memory: nVidia Corporation MCP51 Host Bridge (rev a2)
> 
> Here is a dump from lspci.... looks completely different :-P and here i was
> blaming ATI :-)
> 
> 00:00.0 Host bridge: ATI Technologies Inc RS690 Host Bridge

Oh, that's a different beast, but it might be also a problem with the
timer interrupt routing.

Thanks,

	tglx