From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Return-Path: Date: Fri, 3 Mar 2017 09:05:51 -0800 From: "Raj, Ashok" To: David Woodhouse Subject: Re: [RFC PATCH 22/30] iommu: Bind/unbind tasks to/from devices Message-ID: <20170303170550.rj7awy4jjfiw6qgd@araj-mobl1> References: <20170227195441.5170-1-jean-philippe.brucker@arm.com> <20170227195441.5170-23-jean-philippe.brucker@arm.com> <1488534044.6234.14.camel@infradead.org> MIME-Version: 1.0 In-Reply-To: <1488534044.6234.14.camel@infradead.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Shanker Donthineni , kvm@vger.kernel.org, Jean-Philippe Brucker , Catalin Marinas , Sinan Kaya , Will Deacon , Harv Abdulhamid , iommu@lists.linux-foundation.org, linux-pci@vger.kernel.org, Bjorn Helgaas , ashok.raj@intel.com, linux-arm-kernel@lists.infradead.org, Nate Watterson Content-Type: text/plain; charset="us-ascii" Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+bjorn=helgaas.com@lists.infradead.org List-ID: Hi David, Good to hear back from you! On Fri, Mar 03, 2017 at 09:40:44AM +0000, David Woodhouse wrote: > > Intel slightly deviates from the "one PASID per process" vision too, > because it currently has a PASID allocator idr per IOMMU. That wants > making system-wide. And probably not Intel-specific. Intel version is getting the system wide pasid. We are actively working on it and should be out shortly. > > Some other comments... > > We also have SVM_FLAG_SUPERVISOR_MODE, which gives access to kernel > address space. Yes, people use it. There are some gaps with the current implementation, esp related to vmalloc. We have something internally, these will also be posted soon after some testing. Cheers, Ashok _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Raj, Ashok" Subject: Re: [RFC PATCH 22/30] iommu: Bind/unbind tasks to/from devices Date: Fri, 3 Mar 2017 09:05:51 -0800 Message-ID: <20170303170550.rj7awy4jjfiw6qgd@araj-mobl1> References: <20170227195441.5170-1-jean-philippe.brucker@arm.com> <20170227195441.5170-23-jean-philippe.brucker@arm.com> <1488534044.6234.14.camel@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Shanker Donthineni , kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Catalin Marinas , Sinan Kaya , Will Deacon , Harv Abdulhamid , iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, linux-pci-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Bjorn Helgaas , linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, Nate Watterson To: David Woodhouse Return-path: Content-Disposition: inline In-Reply-To: <1488534044.6234.14.camel-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org List-Id: kvm.vger.kernel.org Hi David, Good to hear back from you! On Fri, Mar 03, 2017 at 09:40:44AM +0000, David Woodhouse wrote: > > Intel slightly deviates from the "one PASID per process" vision too, > because it currently has a PASID allocator idr per IOMMU. That wants > making system-wide. And probably not Intel-specific. Intel version is getting the system wide pasid. We are actively working on it and should be out shortly. > > Some other comments... > > We also have SVM_FLAG_SUPERVISOR_MODE, which gives access to kernel > address space. Yes, people use it. There are some gaps with the current implementation, esp related to vmalloc. We have something internally, these will also be posted soon after some testing. Cheers, Ashok From mboxrd@z Thu Jan 1 00:00:00 1970 From: ashok.raj@intel.com (Raj, Ashok) Date: Fri, 3 Mar 2017 09:05:51 -0800 Subject: [RFC PATCH 22/30] iommu: Bind/unbind tasks to/from devices In-Reply-To: <1488534044.6234.14.camel@infradead.org> References: <20170227195441.5170-1-jean-philippe.brucker@arm.com> <20170227195441.5170-23-jean-philippe.brucker@arm.com> <1488534044.6234.14.camel@infradead.org> Message-ID: <20170303170550.rj7awy4jjfiw6qgd@araj-mobl1> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi David, Good to hear back from you! On Fri, Mar 03, 2017 at 09:40:44AM +0000, David Woodhouse wrote: > > Intel slightly deviates from the "one PASID per process" vision too, > because it currently has a PASID allocator idr per IOMMU. That wants > making system-wide. And probably not Intel-specific. Intel version is getting the system wide pasid. We are actively working on it and should be out shortly. > > Some other comments... > > We also have SVM_FLAG_SUPERVISOR_MODE, which gives access to kernel > address space. Yes, people use it. There are some gaps with the current implementation, esp related to vmalloc. We have something internally, these will also be posted soon after some testing. Cheers, Ashok