From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH 2/2] virtio: let virtio use DMA API when guest RAM is protected Date: Sat, 22 Feb 2020 14:07:58 -0500 Message-ID: <20200222140408-mutt-send-email-mst@kernel.org> References: <20200220160606.53156-1-pasic@linux.ibm.com> <20200220160606.53156-3-pasic@linux.ibm.com> <20200220161309.GB12709@lst.de> <20200221153340.4cdcde81.pasic@linux.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20200221153340.4cdcde81.pasic@linux.ibm.com> Sender: linux-kernel-owner@vger.kernel.org To: Halil Pasic Cc: Christoph Hellwig , Jason Wang , Marek Szyprowski , Robin Murphy , linux-s390@vger.kernel.org, virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, Christian Borntraeger , Janosch Frank , Viktor Mihajlovski , Cornelia Huck , Ram Pai , Thiago Jung Bauermann , David Gibson , "Lendacky, Thomas" , Michael Mueller List-Id: virtualization@lists.linuxfoundation.org On Fri, Feb 21, 2020 at 03:33:40PM +0100, Halil Pasic wrote: > AFAIU you have a positive attitude towards the idea, that > !F_VIRTIO_PLATFORM implies 'no DMA API is used by virtio' > should be scrapped. > > I would like to accomplish that without adverse effects to virtio-ccw > (because caring for virtio-ccw is a part of job description). > > Regards, > Halil It is possible, in theory. IIRC the main challenge is that DMA API has overhead of indirect function calls even when all it does it return back the PA without changes. So that will lead to a measureable performance degradation. That might be fixable, possibly using some kind of logic along the lines of if (iova is pa) return pa else indirect call and for unmapping, we might need an API that says "unmap is a nop, safe to skip" so we don't maintain the dma address until unmap. -- MST