From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH v4 0/6] virtio core DMA API conversion Date: Tue, 10 Nov 2015 14:43:09 +0200 Message-ID: <20151110142633-mutt-send-email-mst__7520.62551114268$1447159415$gmane$org@redhat.com> References: <20151109133624-mutt-send-email-mst@redhat.com> <1447109937.31884.42.camel@kernel.crashing.org> <1447121076.31884.61.camel@kernel.crashing.org> <1447133316.31884.67.camel@kernel.crashing.org> <1447151874.31884.82.camel@kernel.crashing.org> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: Content-Disposition: inline In-Reply-To: <1447151874.31884.82.camel@kernel.crashing.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Benjamin Herrenschmidt Cc: Joerg Roedel , KVM , linux-s390 , Sebastian Ott , "linux-kernel@vger.kernel.org" , Andy Lutomirski , Christian Borntraeger , Christoph Hellwig , Andy Lutomirski , sparclinux@vger.kernel.org, Paolo Bonzini , Linux Virtualization , David Woodhouse , "David S. Miller" , Martin Schwidefsky List-Id: virtualization@lists.linuxfoundation.org On Tue, Nov 10, 2015 at 09:37:54PM +1100, Benjamin Herrenschmidt wrote: > On Mon, 2015-11-09 at 21:35 -0800, Andy Lutomirski wrote: > > = > > We could do it the other way around: on powerpc, if a PCI device is in > > that range and doesn't have the "bypass" property at all, then it's > > assumed to bypass the IOMMU.=A0=A0This means that everything that > > currently works continues working.=A0=A0If someone builds a physical > > virtio device or uses another system in PCIe target mode speaking > > virtio, then it won't work until they upgrade their firmware to set > > bypass=3D0.=A0=A0Meanwhile everyone using hypothetical new QEMU also ge= ts > > bypass=3D0 and no ambiguity. > > > > vfio will presumably notice the bypass and correctly refuse to map any > > current virtio devices. > > = > > Would that work? > = > That would be extremely strange from a platform perspective. Any device > in that vendor/device range would bypass the iommu unless some new > property "actually-works-like-a-real-pci-device" happens to exist in > the device-tree, which we would then need to define somewhere and > handle accross at least 3 different platforms who get their device-tree = > from widly different places. Then we are back to virtio driver telling DMA core whether it wants a 1:1 mapping in the iommu? If that's acceptable to others, I don't think that's too bad. > Also if tomorrow I create a PCI device that implements virtio-net and > put it in a machine running IBM proprietary firmware (or Apple's or > Sun's), it won't have that property... > = > This is not hypothetical. People are using virtio to do point-to-point > communication between machines via PCIe today. > = > Cheers, > Ben. But not virtio-pci I think - that's broken for that usecase since we use weaker barriers than required for real IO, as these have measureable overhead. We could have a feature "is a real PCI device", that's completely reasonable. -- = MST