Re: [PATCH][2.6.7-mm1] perfctr ppc32 update

[Benjamin Herrenschmidt]

On Tue, 2004-06-22 at 15:09, Mikael Pettersson wrote:
> Benjamin Herrenschmidt writes:
>  > Hrm... your code will not work with externally clocked timebases
>  > (like the G5) and I'm not sure you get the core freq. right with
>  > CPU that can do clock slewing or machines that can switch the
>  > core/bus ratio (laptops).
> 
> Do you mean the PLL_CFG code that's been in -mm for the last couple
> of weeks, or just the recently posted update? The update replaced
> in-kernel /proc/cpuinfo parsing (gross) with OF queries taken straight
> from the pmac code in arch/ppc/platform/.
> 
> I'm ignoring 970/G5 until IBM releases the damn documentation.

Well, the G5 can have it's own tb but can also be externally clocked and
that's how Apple does. I'm not sure about all G4 models.

>  > We should rather define an arch API to return those infos...
> 
> No argument there.
-- 
Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/