From mboxrd@z Thu Jan 1 00:00:00 1970 From: Anthony Liguori Subject: Re: [PATCH 1/5] Support more than 3.5GB with virtio (v3) Date: Fri, 09 May 2008 13:37:02 -0500 Message-ID: <482499CE.5030100@us.ibm.com> References: <1210183780-19024-1-git-send-email-aliguori@us.ibm.com> <48246C92.8040900@qumranet.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: kvm-devel@lists.sourceforge.net, Marcelo Tosatti To: Avi Kivity Return-path: In-Reply-To: <48246C92.8040900@qumranet.com> 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 Avi Kivity wrote: > Anthony Liguori wrote: >> We're pretty sloppy in virtio right now about phys_ram_base >> assumptions. This >> patch is an incremental step between what we have today and a full >> blown DMA >> API. I backported the DMA API but the performance impact was not >> acceptable >> to me. There's only a slight performance impact with this particular >> patch. >> >> Since we're no longer assuming guest physical memory is contiguous, >> we need >> a more complex way to validate the memory regions than just checking >> if it's >> within ram_size. >> > > Applied patches 1-2. Since patch 4 is under contention on qemu-devel, > and 3 and 5 depend on it, I'd like to get the can_receive semantic > change accepted first. I'll send it upstream, but I think it's much less of a divergence than the current virtio_net_poll hacks. 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