From mboxrd@z Thu Jan 1 00:00:00 1970 From: Anthony Liguori Subject: Re: [PATCH] Handle vma regions with no backing page (v2) Date: Wed, 30 Apr 2008 10:37:24 -0500 Message-ID: <48189234.6050502@codemonkey.ws> References: <1209496160-20482-1-git-send-email-aliguori@us.ibm.com> <48179E8D.4070407@qumranet.com> <200804291757.25327.hollisb@us.ibm.com> <4817AB73.20703@us.ibm.com> <20080430070039.GA12501@duo.random> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Carsten Otte , Hollis Blanchard , kvm-devel@lists.sourceforge.net, Avi Kivity , Ben-Ami Yassour , "Zhang, Xiantao" To: Andrea Arcangeli Return-path: In-Reply-To: <20080430070039.GA12501@duo.random> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces@lists.sourceforge.net Errors-To: kvm-devel-bounces@lists.sourceforge.net List-Id: kvm.vger.kernel.org Andrea Arcangeli wrote: > On Tue, Apr 29, 2008 at 06:12:51PM -0500, Anthony Liguori wrote: > >> IIUC PPC correctly, all IO pages have corresponding struct pages. This >> means that get_user_pages() would succeed and you can reference count them? >> In this case, we would never take the VM_PFNMAP path. >> > > get_user_pages only works on vmas where only pfn with struct page can > be mapped, but if a struct page exists it doesn't mean get_user_pages > will succeed. All mmio regions should be marked VM_IO as reading on > them affects hardware somehow and that prevents get_user_pages to work > on them regardless if a struct page exists. > Ah, thanks for the clarification. Regards, Anthony Liguori ------------------------------------------------------------------------- This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone