Re: [PATCH 1/4] KVM: MMU: Concurrent guest walkers

[Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>]

Avi Kivity wrote:
> Avi Kivity wrote:
>> From: Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>>
>> Do not hold kvm->lock mutex across the entire pagefault code,
>> only acquire it in places where it is necessary, such as mmu
>> hash list, active list, rmap and parent pte handling.
>>
>> Allow concurrent guest walkers by switching walk_addr() to use
>> mmap_sem in read-mode.
>>
>> And get rid of the lockless __gfn_to_page.
>>
>> [avi: move kvm_mmu_pte_write() locking inside the function]
>> [avi: add locking for real mode]
>>
>>   
>
> Something's wrong here, since with this patch applied I get soft 
> lockups running FC6 x86_64.  Wierd since apic accesses are per-vcpu 
> and so the locking (even if wrong) should not matter.
>

This goes away if lockstats are disabled, so it is probably an artifact.

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


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2005.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/