[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190806134030.GD11627@ziepe.ca>
Date: Tue, 6 Aug 2019 10:40:30 -0300
From: Jason Gunthorpe <jgg@...pe.ca>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: Jason Wang <jasowang@...hat.com>, kvm@...r.kernel.org,
virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH V2 7/9] vhost: do not use RCU to synchronize MMU notifier
with worker
On Tue, Aug 06, 2019 at 09:36:58AM -0400, Michael S. Tsirkin wrote:
> On Tue, Aug 06, 2019 at 08:53:17AM -0300, Jason Gunthorpe wrote:
> > On Sun, Aug 04, 2019 at 04:07:17AM -0400, Michael S. Tsirkin wrote:
> > > > > > Also, why can't this just permanently GUP the pages? In fact, where
> > > > > > does it put_page them anyhow? Worrying that 7f466 adds a get_user page
> > > > > > but does not add a put_page??
> > > >
> > > > You didn't answer this.. Why not just use GUP?
> > > >
> > > > Jason
> > >
> > > Sorry I misunderstood the question. Permanent GUP breaks lots of
> > > functionality we need such as THP and numa balancing.
> >
> > Really? It doesn't look like that many pages are involved..
> >
> > Jason
>
> Yea. But they just might happen to be heavily accessed ones....
Maybe you can solve the numa balance problem some other way and use
normal GUP..
Jason
Powered by blists - more mailing lists