From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jacob Pan Subject: Re: [PATCH 00/10] iommu/vt-d: Add scalable mode support Date: Wed, 18 Jul 2018 17:47:02 -0700 Message-ID: <20180718174702.31e1c1d6@jacob-builder> References: <1531723793-14607-1-git-send-email-baolu.lu@linux.intel.com> <07fe2e3f-4f4a-58db-ee2a-2620183d93b2@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <07fe2e3f-4f4a-58db-ee2a-2620183d93b2-5wv7dgnIgG8@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 To: Jean-Philippe Brucker Cc: ashok.raj-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, sanjay.k.kumar-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, jacob.jun.pan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, David Woodhouse , yi.y.sun-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org List-Id: iommu@lists.linux-foundation.org On Mon, 16 Jul 2018 11:51:57 +0100 Jean-Philippe Brucker wrote: > Hi, > > On 16/07/18 07:49, Lu Baolu wrote: > > Intel vt-d rev3.0 [1] introduces a new translation mode called > > 'scalable mode', which enables PASID-granular translations for > > first level, second level, nested and pass-through modes. The > > vt-d scalable mode is the key ingredient to enable Scalable I/O > > Virtualization (Scalable IOV) [2] [3], which allows sharing a > > device in minimal possible granularity (ADI - Assignable Device > > Interface). It also includes all the capabilities required to > > enable Shared Virtual Addressing (SVA). As a result, previous > > Extended Context (ECS) mode is deprecated (no production ever > > implements ECS). > > > > Each scalable mode pasid table entry is 64 bytes in length, with > > fields point to the first level page table and the second level > > page table. The PGTT (Pasid Granular Translation Type) field is > > used by hardware to determine the translation type. > > Looks promising! Since the 2nd level page tables are in the PASID > entry, the hypervisor traps guest accesses to the PASID tables > instead of passing through the whole PASID directory? Are you still > planning to use the VFIO BIND_PASID_TABLE interface in this mode, or > a slightly different one for individual PASIDs? > Since we deprecated ECS mode, there is no need for VT-d to bind guest pasid table in scalable mode. We are planning on adding another flag for bind guest pasid and guest CR3, Perhaps call it VFIO_IOMMU_BIND_GUEST_SVA. > Thanks, > Jean > _______________________________________________ > iommu mailing list > iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org > https://lists.linuxfoundation.org/mailman/listinfo/iommu [Jacob Pan]