From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joerg Roedel Subject: Re: Summary of LPC guest MSI discussion in Santa Fe Date: Mon, 14 Nov 2016 16:19:24 +0100 Message-ID: <20161114151923.GX2078@8bytes.org> References: <20161109233847.GT17771@arm.com> <20161109165957.62c1eb61@t450s.home> <83b6440a-31eb-c1b4-642c-a4c311f37ef2@redhat.com> <20161109175517.174e7803@t450s.home> <20161110020130.GA19108@arm.com> <20161110104601.0939ba9a@t450s.home> <20161111111944.GO2078@8bytes.org> <20161111085056.4cf8989d@t450s.home> <20161111090543.57623f2d@t450s.home> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20161111090543.57623f2d@t450s.home> Sender: kvm-owner@vger.kernel.org To: Alex Williamson Cc: linux-arm-kernel@lists.infradead.org, drjones@redhat.com, jason@lakedaemon.net, kvm@vger.kernel.org, marc.zyngier@arm.com, benh@kernel.crashing.org, punit.agrawal@arm.com, Will Deacon , linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, pranav.sawargaonkar@gmail.com, arnd@arndb.de, dwmw@amazon.co.uk, jcm@redhat.com, tglx@linutronix.de, Christoffer Dall , eric.auger.pro@gmail.com List-Id: iommu@lists.linux-foundation.org On Fri, Nov 11, 2016 at 09:05:43AM -0700, Alex Williamson wrote: > On Fri, 11 Nov 2016 08:50:56 -0700 > Alex Williamson wrote: > > > > It's really just a happenstance that we don't map RAM over the x86 MSI > > range though. That property really can't be guaranteed once we mix > > architectures, such as running an aarch64 VM on x86 host via TCG. > > AIUI, the MSI range is actually handled differently than other DMA > > ranges, so a iommu_map() overlapping a range that the iommu cannot map > > should fail just like an attempt to map beyond the address width of the > > iommu. > > (clarification, this is x86 specific, the MSI controller - interrupt > remapper - is embedded in the iommu AIUI, so the iommu is actually not > able to provide DMA translation for this range. Right, on x86 the MSI range can be covered by page-tables, but those are ignored by the IOMMU hardware. But what I am trying to say is, that checking for these ranges happens already on a higher level (in the dma-api implementations by marking these regions as allocted) so that there is no need to check for them again in the iommu_map/unmap path. Joerg