Re: [PATCH][2.5] flush_tlb_all is not preempt safe.

[Zwane Mwaikambo]

On Fri, 14 Feb 2003, Zwane Mwaikambo wrote:

> Hi,
> 	Considering that smp_call_function isn't allowed to hold a lock 
> reference and within smp_call_function we lock and unlock call_lock thus 
> triggering a preempt point. Therefore we can't guarantee that we'll be on 
> the same processor when we hit do_flush_tlb_all_local.
> 
> void flush_tlb_all(void)
> {
> 	preempt_disable();
> 	smp_call_function (flush_tlb_all_ipi,0,1,1);
> 
> 	do_flush_tlb_all_local();
> 	preempt_enable();
> }

Of course i had to go and paste the code i was working on. The original 
isn't wrapped in preempt_disable/enable.

	Zwane (who really needs to get to bed now)
-- 
function.linuxpower.ca