Re: [Patch] tsc-disable_A5

[john stultz]

On Fri, 2002-06-14 at 14:53, Mikael Pettersson wrote:
> Unless my memory is failing me, I believe the simplest approach
> is to (1) don't set CONFIG_X86_TSC, and (2) pass "notsc" as a
> kernel boot parameter.

Correct, and this patch basically does both of the above. 

The problem is that CONFIG_X86_TSC is enabled on PPro and above cpus.
The machines which are having this problem are multi-node P3 or P4
systems. Each cpu has a working TSC, its just that because they are not
synced they should not be used. 

So the patch adds a CONFIG_DISABLE_TSC which is then checked where
earlier just CONFIG_X86_TSC was used. Additionally, if
CONFIG_DISABLE_TSC is set, the flag set by "notsc" is also set.

The usage of CONFIG_X86_TSC took me a bit to get my head around
initially, so your clarification is helpful.

Thanks
-john