Re: [RFC PATCH V3 0/5] Hi:

[Jason Wang]

On 2019/1/8 äå6:12, Jason Wang wrote:
> On 2019/1/7 äå10:47, Michael S. Tsirkin wrote:
> > On Mon, Jan 07, 2019 at 02:58:08PM +0800, Jason Wang wrote:
> > > On 2019/1/5 äå5:41, Michael S. Tsirkin wrote:
> > > > On Sat, Dec 29, 2018 at 08:46:51PM +0800, Jason Wang wrote:
> > > > > This series tries to access virtqueue metadata through kernel virtual
> > > > > address instead of copy_user() friends since they had too much
> > > > > overheads like checks, spec barriers or even hardware feature
> > > > > toggling.
> > > > I think it's a reasonable approach.
> > > > However I need to look at whether and which mmu notifiers are 
> > > > invoked before
> > > > writeback. Do you know?
> > >
> > > I don't know but just looking at the MMU notifier ops definition, 
> > > there's no
> > > such callback if my understanding is correct.
> > >
> > > Thanks
> > In that case how are you making sure used ring updates are written back?
> > If they aren't guest will crash ...
>
>
> I think this is the writeback issue you mentioned early. I don't do a 
> followup on the pointer but it looks to me some work is ongoing to fix 
> the issue.
>
> I can investigate it more, but it's not something new, consider the 
> case of VFIO.
>
> Thanks


Ok, after some investigation. The GUP + dirty pages issue is not easy to 
be fixed so it may still take a while.

An idea is switch back to copy_user() friends if we find the metadata 
page is not anonymous.

Does this sound good to you?

Thanks