Re: Re: [patch 0/3]Enable CMCI (Corrected Machine Check Error Interrupt) for Intel CPUs

[Keir Fraser <keir.fraser@eu.citrix.com>]

On 24/12/2008 14:51, "Jiang, Yunhong" <yunhong.jiang@intel.com> wrote:

>>> Yes, that's what I mean of "do similar thing in the
>> cmci_cpu_down()". We
>>> placed it in stop_machine_run() because it has rendezvous
>> all CPU already :$
>> 
>> Yeah, on_each_cpu() rendezvous is pretty cheap. May as well
>> have cleaner
>> partitioned code than avoid an extra rendezvous.
> 
> I'd have a bit clarification here. Simply harirqs disabled in the
> on_each_cpu() is not enough. What we need is, firstly make sure every CPU has
> irq disabled, then every CPU begin update the CMCI status. If this is what you
> mean, we will take a patch for it later.

Every CPU will have IRQs disabled on entry to the on_each_cpu() IPI
function. I couldn't mean much else -- for example, it's not even valid for
the caller of on_each_cpu() to enter it with IRQs disabled.

 -- Keir