RE: [PATCH v2 14/15] vfio: Document dual stage control

From: Liu, Yi L
Date: Tue Jun 23 2020 - 02:44:02 EST


> From: Stefan Hajnoczi <stefanha@xxxxxxxxx>
> Sent: Monday, June 22, 2020 8:51 PM
>
> On Wed, Jun 17, 2020 at 06:27:27AM +0000, Liu, Yi L wrote:
> > > From: Stefan Hajnoczi <stefanha@xxxxxxxxx>
> > > Sent: Monday, June 15, 2020 5:41 PM
> > > On Thu, Jun 11, 2020 at 05:15:33AM -0700, Liu Yi L wrote:
> > >
> > > > From: Eric Auger <eric.auger@xxxxxxxxxx>
> > > >
> > > > The VFIO API was enhanced to support nested stage control: a bunch of
> > > > new iotcls and usage guideline.
> > > >
> > > > Let's document the process to follow to set up nested mode.
> > > >
> > > > Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
> > > > CC: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> > > > Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
> > > > Cc: Eric Auger <eric.auger@xxxxxxxxxx>
> > > > Cc: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
> > > > Cc: Joerg Roedel <joro@xxxxxxxxxx>
> > > > Cc: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> > > > Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
> > > > Signed-off-by: Liu Yi L <yi.l.liu@xxxxxxxxx>
> > > > ---
> > > > v1 -> v2:
> > > > *) new in v2, compared with Eric's original version, pasid table bind
> > > > and fault reporting is removed as this series doesn't cover them.
> > > > Original version from Eric.
> > > > https://lkml.org/lkml/2020/3/20/700
> > > >
> > > > Documentation/driver-api/vfio.rst | 64
> > > > +++++++++++++++++++++++++++++++++++++++
> > > > 1 file changed, 64 insertions(+)
> > > >
> > > > diff --git a/Documentation/driver-api/vfio.rst
> > > > b/Documentation/driver-api/vfio.rst
> > > > index f1a4d3c..06224bd 100644
> > > > --- a/Documentation/driver-api/vfio.rst
> > > > +++ b/Documentation/driver-api/vfio.rst
> > > > @@ -239,6 +239,70 @@ group and can access them as follows::
> > > > /* Gratuitous device reset and go... */
> > > > ioctl(device, VFIO_DEVICE_RESET);
> > > >
> > > > +IOMMU Dual Stage Control
> > > > +------------------------
> > > > +
> > > > +Some IOMMUs support 2 stages/levels of translation. Stage corresponds
> > > > +to the ARM terminology while level corresponds to Intel's VTD terminology.
> > > > +In the following text we use either without distinction.
> > > > +
> > > > +This is useful when the guest is exposed with a virtual IOMMU and
> > > > +some devices are assigned to the guest through VFIO. Then the guest
> > > > +OS can use stage 1 (GIOVA -> GPA or GVA->GPA), while the hypervisor
> > > > +uses stage 2 for VM isolation (GPA -> HPA).
> > > > +
> > > > +Under dual stage translation, the guest gets ownership of the stage 1
> > > > +page tables and also owns stage 1 configuration structures. The
> > > > +hypervisor owns the root configuration structure (for security
> > > > +reason), including stage 2 configuration. This works as long
> > > > +configuration structures and page table
> > >
> > > s/as long configuration/as long as configuration/
> >
> > got it.
> >
> > >
> > > > +format are compatible between the virtual IOMMU and the physical IOMMU.
> > >
> > > s/format/formats/
> >
> > I see.
> >
> > > > +
> > > > +Assuming the HW supports it, this nested mode is selected by choosing
> > > > +the VFIO_TYPE1_NESTING_IOMMU type through:
> > > > +
> > > > + ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_NESTING_IOMMU);
> > > > +
> > > > +This forces the hypervisor to use the stage 2, leaving stage 1
> > > > +available for guest usage. The guest stage 1 format depends on IOMMU
> > > > +vendor, and it is the same with the nesting configuration method.
> > > > +User space should check the format and configuration method after
> > > > +setting nesting type by
> > > > +using:
> > > > +
> > > > + ioctl(container->fd, VFIO_IOMMU_GET_INFO, &nesting_info);
> > > > +
> > > > +Details can be found in Documentation/userspace-api/iommu.rst. For
> > > > +Intel VT-d, each stage 1 page table is bound to host by:
> > > > +
> > > > + nesting_op->flags = VFIO_IOMMU_NESTING_OP_BIND_PGTBL;
> > > > + memcpy(&nesting_op->data, &bind_data, sizeof(bind_data));
> > > > + ioctl(container->fd, VFIO_IOMMU_NESTING_OP, nesting_op);
> > > > +
> > > > +As mentioned above, guest OS may use stage 1 for GIOVA->GPA or GVA->GPA.
> > > > +GVA->GPA page tables are available when PASID (Process Address Space
> > > > +GVA->ID)
> > > > +is exposed to guest. e.g. guest with PASID-capable devices assigned.
> > > > +For such page table binding, the bind_data should include PASID info,
> > > > +which is allocated by guest itself or by host. This depends on
> > > > +hardware vendor e.g. Intel VT-d requires to allocate PASID from host.
> > > > +This requirement is available by VFIO_IOMMU_GET_INFO. User space
> > > > +could allocate PASID from host by:
> > > > +
> > > > + req.flags = VFIO_IOMMU_ALLOC_PASID;
> > > > + ioctl(container, VFIO_IOMMU_PASID_REQUEST, &req);
> > >
> > > It is not clear how the userspace application determines whether PASIDs must be
> > > allocated from the host via VFIO_IOMMU_PASID_REQUEST or if the guest itself
> can
> > > allocate PASIDs. The text mentions VFIO_IOMMU_GET_INFO but what exactly
> > > should the userspace application check?
> >
> > For VT-d, spec 3.0 introduced Virtual Cmd interface for PASID allocation,
> > guest request PASID from host if it detects the interface. Application
> > should check the IOMMU_NESTING_FEAT_SYSWIDE_PASID setting in the below
> > info reported by VFIO_IOMMU_GET_INFO. And virtual VT-d should not report
> > SVA related capabilities to guest if SYSWIDE_PASID is not supported by
> > kernel.
> >
> > +struct iommu_nesting_info {
> > + __u32 size;
> > + __u32 format;
> > + __u32 features;
> > +#define IOMMU_NESTING_FEAT_SYSWIDE_PASID (1 << 0)
> > +#define IOMMU_NESTING_FEAT_BIND_PGTBL (1 << 1)
> > +#define IOMMU_NESTING_FEAT_CACHE_INVLD (1 << 2)
> > + __u32 flags;
> > + __u8 data[];
> > +};
> > https://lore.kernel.org/linux-iommu/1591877734-66527-3-git-send-email-
> yi.l.liu@xxxxxxxxx/
>
> I see. Is it possible to add this information into this patch or at
> least a reference so readers know where to find out exactly how to do
> this?

oh, yes. this would help a lot. will add it.

Regards,
Yi Liu
> Stefan