From mboxrd@z Thu Jan 1 00:00:00 1970 From: Kenneth-Lee-2012@foxmail.com (Kenneth Lee) Date: Sat, 26 May 2018 10:24:45 +0800 Subject: [PATCH v2 03/40] iommu/sva: Manage process address spaces In-Reply-To: <20180525093959.000040a7@huawei.com> References: <20180511190641.23008-1-jean-philippe.brucker@arm.com> <20180511190641.23008-4-jean-philippe.brucker@arm.com> <20180516163117.622693ea@jacob-builder> <20180522094334.71f0e36b@jacob-builder> <20180524115039.GA10260@apalos> <19e82a74-429a-3f86-119e-32b12082d0ff@arm.com> <20180525063311.GA11605@apalos> <20180525093959.000040a7@huawei.com> Message-ID: <20180526022445.GA6069@kllp05>+42CE4B8EA5F87363 To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Fri, May 25, 2018 at 09:39:59AM +0100, Jonathan Cameron wrote: > Date: Fri, 25 May 2018 09:39:59 +0100 > From: Jonathan Cameron > To: Ilias Apalodimas > CC: Jean-Philippe Brucker , > "xieyisheng1 at huawei.com" , "kvm at vger.kernel.org" > , "linux-pci at vger.kernel.org" > , "xuzaibo at huawei.com" , > Will Deacon , "okaya at codeaurora.org" > , "linux-mm at kvack.org" , > "yi.l.liu at intel.com" , "ashok.raj at intel.com" > , "tn at semihalf.com" , > "joro at 8bytes.org" , "robdclark at gmail.com" > , "bharatku at xilinx.com" , > "linux-acpi at vger.kernel.org" , > "liudongdong3 at huawei.com" , "rfranz at cavium.com" > , "devicetree at vger.kernel.org" > , "kevin.tian at intel.com" > , Jacob Pan , > "alex.williamson at redhat.com" , > "rgummal at xilinx.com" , "thunder.leizhen at huawei.com" > , "linux-arm-kernel at lists.infradead.org" > , "shunyong.yang at hxt-semitech.com" > , "dwmw2 at infradead.org" > , "liubo95 at huawei.com" , > "jcrouse at codeaurora.org" , > "iommu at lists.linux-foundation.org" , > Robin Murphy , "christian.koenig at amd.com" > , "nwatters at codeaurora.org" > , "baolu.lu at linux.intel.com" > , liguozhu at hisilicon.com, > kenneth-lee-2012 at foxmail.com > Subject: Re: [PATCH v2 03/40] iommu/sva: Manage process address spaces > Message-ID: <20180525093959.000040a7@huawei.com> > > +CC Kenneth Lee > > On Fri, 25 May 2018 09:33:11 +0300 > Ilias Apalodimas wrote: > > > On Thu, May 24, 2018 at 04:04:39PM +0100, Jean-Philippe Brucker wrote: > > > On 24/05/18 12:50, Ilias Apalodimas wrote: > > > >> Interesting, I hadn't thought about this use-case before. At first I > > > >> thought you were talking about mdev devices assigned to VMs, but I think > > > >> you're referring to mdevs assigned to userspace drivers instead? Out of > > > >> curiosity, is it only theoretical or does someone actually need this? > > > > > > > > There has been some non upstreamed efforts to have mdev and produce userspace > > > > drivers. Huawei is using it on what they call "wrapdrive" for crypto devices and > > > > we did a proof of concept for ethernet interfaces. At the time we choose not to > > > > involve the IOMMU for the reason you mentioned, but having it there would be > > > > good. > > > > > > I'm guessing there were good reasons to do it that way but I wonder, is > > > it not simpler to just have the kernel driver create a /dev/foo, with a > > > standard ioctl/mmap/poll interface? Here VFIO adds a layer of > > > indirection, and since the mediating driver has to implement these > > > operations already, what is gained? > > The best reason i can come up with is "common code". You already have one API > > doing that for you so we replicate it in a /dev file? > > The mdev approach still needs extentions to support what we tried to do (i.e > > mdev bus might need yo have access on iommu_ops), but as far as i undestand it's > > a possible case. Hi, Jean, Please allow me to share my understanding here: https://zhuanlan.zhihu.com/p/35489035 The reason we do not use the /dev/foo scheme is that the devices to be shared are programmable accelerators. We cannot fix up the kernel driver for them. > > > > > > Thanks, > > > Jean > > -- -Kenneth Lee (Hisilicon)