Re: [kvm-devel] KVM Test result, kernel 873c05f.., userspace d102d75..

[Avi K. <av...@qu...>]

Marcelo Tosatti wrote:
> On Thu, Apr 24, 2008 at 04:44:27PM +0300, Avi Kivity wrote:
>   
>> Chris Lalancette wrote:
>>     
>>> Avi Kivity wrote:
>>>  
>>>       
>>>> Ok.  __pit_timer_fn() is called from an interrupt, which then calls 
>>>> smp_call_function_single(), which calls spin_lock().  If we've already 
>>>> taken the lock, we hang.
>>>>
>>>>    
>>>>         
>>> Ah.  Just adding a "me too"; I didn't get a chance to debug it yesterday, 
>>> but I
>>> was seeing similar problems.  If I disabled in-kernel pit with 
>>> -no-kvm-pit, all
>>> was well.
>>>  
>>>       
>> How to fix it, though?  the only idea that comes to mind is to affine 
>> the hrtimer with vcpu0 (like the local apic timers) which would mean we 
>> only need to unwait the waitqueue, and never need to send the IPI.  
>> Would slightly improve performance as well.
>>     
>
> Yes, agree. 
>
> For now I think just revert
>   

I committed this, so this should be fixed for now.  I'm not sure hrtimer 
migration would work 100% reliably (suppose it fired just after a vcpu 
migration) so I think a queue_work is better.


-- 
error compiling committee.c: too many arguments to function