Re: [kvm-devel] [PATCH 6/13] KVM: memory slot management

[Anthony Liguori <aliguori@us.ibm.com>]

Avi Kivity wrote:
>>> 2. The next mmu implementation, which caches guest translations.
>>>
>>> The potential problem above now becomes acute.  The guest will have 
>>> kernel mappings for every page, and after a short while they'll all be 
>>> faulted in and locked.  This defeats the swap integration which is IMO a 
>>> very strong point.
>>>
>>> We can work around that by periodically forcing out translations (some 
>>> kind of clock algorithm) at some rate so the host vm can have a go at 
>>> them.  That can turn out to be expensive as we'll need to interrupt all 
>>> running vcpus to flush (real) tlb entries.
>>>     
>>>       
>> Don't understand. Can't one CPU cause a TLB entry to be flushed on all
>> CPUs?
>>
>>   
>>     
>
> It's not about tlb entries.  The shadow page tables collaples a GV -> HV 
> -> HP  double translation into a GV -> HP page table.  When the Linux vm 
> goes around evicting pages, it invalidates those mappings.
>
> There are two solutions possible: lock pages which participate in these 
> translations (and their number can be large) or modify the Linux vm to 
> consult a reverse mapping and remove the translations (in which case TLB 
> entries need to be removed).
>   

If you locked pages that have active shadow mappings, you could then use 
a secondary mechanism to invalidate existing mappings when necessary.

You could even base this on a user-configurable heuristic (give this VM 
1G of memory, with 512MB of dedicated memory for instance).

I seem to recall some discussion about having a memory pressure 
notification mechanism.  If such a thing existed, this could be used to 
reduce the guests actual memory foot print.  I'm woefully ignorant 
though of any recent developments in this area...

Regards,

Anthony Liguori