Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-SDR: Lhh95kBgihuL6f2raskgvQMBxI8HWcLUyeuhAhjOFnaiaMxAioQj/FDRQ/1hfB4RAfu+kMTUCw
 3GcvjilqfUKQ==
IronPort-SDR: cQP4sYRLvkF/zHOBchRoulg3qa0HJQBogVgvkCjQ22xPO+xxNdCKSa5LQu4iHrJQJvJBPqOgGU
 7QFs2h7WIU9g==
From:   "Tian, Kevin" <kevin.tian@intel.com>
To:     Alex Williamson <alex.williamson@redhat.com>,
        Jason Gunthorpe <jgg@nvidia.com>
CC:     Jean-Philippe Brucker <jean-philippe@linaro.org>,
        "Jiang, Dave" <dave.jiang@intel.com>,
        "Raj, Ashok" <ashok.raj@intel.com>,
        "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
        Jonathan Corbet <corbet@lwn.net>,
        Robin Murphy <robin.murphy@arm.com>,
        LKML <linux-kernel@vger.kernel.org>,
        "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>,
        David Gibson <david@gibson.dropbear.id.au>,
        Kirti Wankhede <kwankhede@nvidia.com>,
        "David Woodhouse" <dwmw2@infradead.org>,
        Jason Wang <jasowang@redhat.com>
Subject: RE: [RFC] /dev/ioasid uAPI proposal
Thread-Topic: [RFC] /dev/ioasid uAPI proposal
Thread-Index: AddSzQ970oLnVHLeQca/ysPD8zMJZwBL2ymAAKTbxpAAKSt7gAAHpf9wAB1YcAAAAm5sgAAA1YgAAADonIAAAEmcgAABzCaAAAHbfwAAAYTsAAAEeLUAAAiRJwAAAHcmwA==
Date:   Thu, 3 Jun 2021 03:22:27 +0000
Message-ID: <MWHPR11MB1886DC8ECF5D56FE485D13D58C3C9@MWHPR11MB1886.namprd11.prod.outlook.com>
References: <20210601162225.259923bc.alex.williamson@redhat.com>
        <MWHPR11MB1886E8454A58661DC2CDBA678C3D9@MWHPR11MB1886.namprd11.prod.outlook.com>
        <20210602160140.GV1002214@nvidia.com>
        <20210602111117.026d4a26.alex.williamson@redhat.com>
        <20210602173510.GE1002214@nvidia.com>
        <20210602120111.5e5bcf93.alex.williamson@redhat.com>
        <20210602180925.GH1002214@nvidia.com>
        <20210602130053.615db578.alex.williamson@redhat.com>
        <20210602195404.GI1002214@nvidia.com>
        <20210602143734.72fb4fa4.alex.williamson@redhat.com>
        <20210602224536.GJ1002214@nvidia.com>
 <20210602205054.3505c9c3.alex.williamson@redhat.com>
In-Reply-To: <20210602205054.3505c9c3.alex.williamson@redhat.com>
Accept-Language: en-US
Content-Language: en-US
dlp-version: 11.5.1.3
dlp-product: dlpe-windows
dlp-reaction: no-action
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 746f4b84-b5ae-44b4-6453-08d9263ed0ca
X-MS-Exchange-CrossTenant-originalarrivaltime: 03 Jun 2021 03:22:28.0559
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: rwdqsGeOicFqvCnqQ4qPdmqbL2nf3L64N6Hd4C4XC4PPwIXSHkeJosVgGEas+pVXf12Gkxk+fHV5UTdoySmkJA==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR11MB0030
X-OriginatorOrg: intel.com
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

> From: Alex Williamson <alex.williamson@redhat.com>
> Sent: Thursday, June 3, 2021 10:51 AM
>=20
> On Wed, 2 Jun 2021 19:45:36 -0300
> Jason Gunthorpe <jgg@nvidia.com> wrote:
>=20
> > On Wed, Jun 02, 2021 at 02:37:34PM -0600, Alex Williamson wrote:
> >
> > > Right.  I don't follow where you're jumping to relaying DMA_PTE_SNP
> > > from the guest page table... what page table?
> >
> > I see my confusion now, the phrasing in your earlier remark led me
> > think this was about allowing the no-snoop performance enhancement in
> > some restricted way.
> >
> > It is really about blocking no-snoop 100% of the time and then
> > disabling the dangerous wbinvd when the block is successful.
> >
> > Didn't closely read the kvm code :\
> >
> > If it was about allowing the optimization then I'd expect the guest to
> > enable no-snoopable regions via it's vIOMMU and realize them to the
> > hypervisor and plumb the whole thing through. Hence my remark about
> > the guest page tables..
> >
> > So really the test is just 'were we able to block it' ?
>=20
> Yup.  Do we really still consider that there's some performance benefit
> to be had by enabling a device to use no-snoop?  This seems largely a
> legacy thing.

Yes, there is indeed performance benefit for device to use no-snoop,
e.g. 8K display and some imaging processing path, etc. The problem is
that the IOMMU for such devices is typically a different one from the
default IOMMU for most devices. This special IOMMU may not have
the ability of enforcing snoop on no-snoop PCI traffic then this fact
must be understood by KVM to do proper mtrr/pat/wbinvd virtualization=20
for such devices to work correctly.

>=20
> > > This support existed before mdev, IIRC we needed it for direct
> > > assignment of NVIDIA GPUs.
> >
> > Probably because they ignored the disable no-snoop bits in the control
> > block, or reset them in some insane way to "fix" broken bioses and
> > kept using it even though by all rights qemu would have tried hard to
> > turn it off via the config space. Processing no-snoop without a
> > working wbinvd would be fatal. Yeesh
> >
> > But Ok, back the /dev/ioasid. This answers a few lingering questions I
> > had..
> >
> > 1) Mixing IOMMU_CAP_CACHE_COHERENCY
> and !IOMMU_CAP_CACHE_COHERENCY
> >    domains.
> >
> >    This doesn't actually matter. If you mix them together then kvm
> >    will turn on wbinvd anyhow, so we don't need to use the DMA_PTE_SNP
> >    anywhere in this VM.
> >
> >    This if two IOMMU's are joined together into a single /dev/ioasid
> >    then we can just make them both pretend to be
> >    !IOMMU_CAP_CACHE_COHERENCY and both not set IOMMU_CACHE.
>=20
> Yes and no.  Yes, if any domain is !IOMMU_CAP_CACHE_COHERENCY then
> we
> need to emulate wbinvd, but no we'll use IOMMU_CACHE any time it's
> available based on the per domain support available.  That gives us the
> most consistent behavior, ie. we don't have VMs emulating wbinvd
> because they used to have a device attached where the domain required
> it and we can't atomically remap with new flags to perform the same as
> a VM that never had that device attached in the first place.
>=20
> > 2) How to fit this part of kvm in some new /dev/ioasid world
> >
> >    What we want to do here is iterate over every ioasid associated
> >    with the group fd that is passed into kvm.
>=20
> Yeah, we need some better names, binding a device to an ioasid (fd) but
> then attaching a device to an allocated ioasid (non-fd)... I assume
> you're talking about the latter ioasid.
>=20
> >    Today the group fd has a single container which specifies the
> >    single ioasid so this is being done trivially.
> >
> >    To reorg we want to get the ioasid from the device not the
> >    group (see my note to David about the groups vs device rational)
> >
> >    This is just iterating over each vfio_device in the group and
> >    querying the ioasid it is using.
>=20
> The IOMMU API group interfaces is largely iommu_group_for_each_dev()
> anyway, we still need to account for all the RIDs and aliases of a
> group.
>=20
> >    Or perhaps more directly: an op attaching the vfio_device to the
> >    kvm and having some simple helper
> >          '(un)register ioasid with kvm (kvm, ioasid)'
> >    that the vfio_device driver can call that just sorts this out.
>=20
> We could almost eliminate the device notion altogether here, use an
> ioasidfd_for_each_ioasid() but we really want a way to trigger on each
> change to the composition of the device set for the ioasid, which is
> why we currently do it on addition or removal of a group, where the
> group has a consistent set of IOMMU properties.  Register a notifier
> callback via the ioasidfd?  Thanks,
>=20

When discussing I/O page fault support in another thread, the consensus
is that an device handle will be registered (by user) or allocated (return
to user) in /dev/ioasid when binding the device to ioasid fd. From this=20
angle we can register {ioasid_fd, device_handle} to KVM and then call=20
something like ioasidfd_device_is_coherent() to get the property.=20
Anyway the coherency is a per-device property which is not changed=20
by how many I/O page tables are attached to it.

Thanks
Kevin