From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934239AbcKKQWQ (ORCPT ); Fri, 11 Nov 2016 11:22:16 -0500 Received: from 8bytes.org ([81.169.241.247]:40672 "EHLO theia.8bytes.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932532AbcKKQWO (ORCPT ); Fri, 11 Nov 2016 11:22:14 -0500 Date: Fri, 11 Nov 2016 17:22:11 +0100 From: Joerg Roedel To: Auger Eric Cc: drjones@redhat.com, jason@lakedaemon.net, kvm@vger.kernel.org, marc.zyngier@arm.com, punit.agrawal@arm.com, will.deacon@arm.com, linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, diana.craciun@nxp.com, alex.williamson@redhat.com, pranav.sawargaonkar@gmail.com, linux-arm-kernel@lists.infradead.org, tglx@linutronix.de, robin.murphy@arm.com, christoffer.dall@linaro.org, eric.auger.pro@gmail.com Subject: Re: [RFC v2 8/8] iommu/arm-smmu: implement add_reserved_regions callback Message-ID: <20161111162211.GU2078@8bytes.org> References: <1478258646-3117-1-git-send-email-eric.auger@redhat.com> <1478258646-3117-9-git-send-email-eric.auger@redhat.com> <20161110154606.GH2078@8bytes.org> <04ed9694-707d-260b-70c6-f367d292ceca@redhat.com> <20161110161331.GJ2078@8bytes.org> <20161111114223.GP2078@8bytes.org> <79da09b8-ac1e-cebf-5393-7d67f002b3e3@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <79da09b8-ac1e-cebf-5393-7d67f002b3e3@redhat.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Eric, On Fri, Nov 11, 2016 at 04:47:01PM +0100, Auger Eric wrote: > Effectively in passthrough use case, the userspace defines the address > space layout and maps guest RAM PA=IOVA to PAs (using > VFIO_IOMMU_MAP_DMA). But this address space does not comprise the MSI > IOVAs. Userspace does not care about MSI IOMMU mapping. So the MSI IOVA > region must be allocated by either the VFIO driver or the IOMMU driver I > think. Who else could initialize the IOVA allocator domain? So I think we need a way to tell userspace about the reserved regions (per iommu-group) so that userspace knows where it can not map anything, and VFIO can enforce that. But the right struct here is not an iova-allocator rb-tree, a ordered linked list should be sufficient. Joerg From mboxrd@z Thu Jan 1 00:00:00 1970 From: joro@8bytes.org (Joerg Roedel) Date: Fri, 11 Nov 2016 17:22:11 +0100 Subject: [RFC v2 8/8] iommu/arm-smmu: implement add_reserved_regions callback In-Reply-To: <79da09b8-ac1e-cebf-5393-7d67f002b3e3@redhat.com> References: <1478258646-3117-1-git-send-email-eric.auger@redhat.com> <1478258646-3117-9-git-send-email-eric.auger@redhat.com> <20161110154606.GH2078@8bytes.org> <04ed9694-707d-260b-70c6-f367d292ceca@redhat.com> <20161110161331.GJ2078@8bytes.org> <20161111114223.GP2078@8bytes.org> <79da09b8-ac1e-cebf-5393-7d67f002b3e3@redhat.com> Message-ID: <20161111162211.GU2078@8bytes.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi Eric, On Fri, Nov 11, 2016 at 04:47:01PM +0100, Auger Eric wrote: > Effectively in passthrough use case, the userspace defines the address > space layout and maps guest RAM PA=IOVA to PAs (using > VFIO_IOMMU_MAP_DMA). But this address space does not comprise the MSI > IOVAs. Userspace does not care about MSI IOMMU mapping. So the MSI IOVA > region must be allocated by either the VFIO driver or the IOMMU driver I > think. Who else could initialize the IOVA allocator domain? So I think we need a way to tell userspace about the reserved regions (per iommu-group) so that userspace knows where it can not map anything, and VFIO can enforce that. But the right struct here is not an iova-allocator rb-tree, a ordered linked list should be sufficient. Joerg