From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeremy Fitzhardinge Subject: Re: pv_ops & gntdev? Date: Wed, 25 Feb 2009 14:30:32 -0800 Message-ID: <49A5C688.8080705@goop.org> References: <49A44030.2070709@redhat.com> <49A4640E.1000807@goop.org> <49A470DD.2000008@redhat.com> <49A517F6.30005@redhat.com> <49A58506.2020407@goop.org> <49A59453.1090502@redhat.com> <49A5A5A2.10001@goop.org> <49A5C335.3010306@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <49A5C335.3010306@redhat.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Gerd Hoffmann Cc: Xen Development Mailing List List-Id: xen-devel@lists.xenproject.org Gerd Hoffmann wrote: > Jeremy Fitzhardinge wrote: > >> Gerd Hoffmann wrote: >> >>> Also: 2.6.18 gntdev does some funky interaction with the balloon driver. >>> What is the point in doing so? >>> >>> >> Oh, the alloc_empty_pages_and_pagevec() stuff? It allocates some pages, >> just for their pfn slots, and then returns the underlying memory back to >> Xen. It uses the pfns to slot granted pages into. >> > > Yep, gives pfn slot for the grant map. And a struct page too. > > /me wonderes whenever that is required or whenever I could just map the > grants without asking the balloon driver for some slots ... > I think they could be special ptes now, and not need any struct page. J