Re: [PATCH 5/6] kvm, x86: use ro page and don't copy shared page

[Avi Kivity]

On 07/17/2010 07:31 AM, Gleb Natapov wrote:
> > > Currently pages allocated for guest memory are required to be RW, so after your series
> > > behaviour will remain exactly the same as before.
> > >        
> > Except KSM pages.
> >
> >      
> KSM page will be COWed by __get_user_pages_fast(addr, 1, 1, page) in
> get_user_page_and_protection() just like it COWed now, no?
>    

Well, we don't want to COW it on write faults.

The optimal behaviour is:

- write faults: COW and instantiate a writeable spte
- read faults: instantiate a readable spte; if likely(page is 
writeable), make it a writeable spte; if likely(page is dirty) make it a 
dirty spte
- speculative spte instantiations: if likely(page is present) 
instantiate a pte; if accessed, mark it accessed, if writeable, mark it 
writeable; if dirty, mark it dirty

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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/