[v5,14/15] vfio: Document dual stage control

Commit Message

Yi Liu July 12, 2020, 11:21 a.m. UTC

From: Eric Auger <[e-mail]>

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 <[e-mail]>
CC: Jacob Pan <[e-mail]>
Cc: Alex Williamson <[e-mail]>
Cc: Eric Auger <[e-mail]>
Cc: Jean-Philippe Brucker <[e-mail]>
Cc: Joerg Roedel <[e-mail]>
Cc: Lu Baolu <[e-mail]>
Reviewed-by: Stefan Hajnoczi <[e-mail]>
Signed-off-by: Eric Auger <[e-mail]>
Signed-off-by: Liu Yi L <[e-mail]>
---
v3 -> v4:
*) add review-by from Stefan Hajnoczi

v2 -> v3:
*) address comments from Stefan Hajnoczi

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 | 67 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

Comments

Eric Auger July 18, 2020, 1:39 p.m. UTC | #1

Hi Yi,

On 7/12/20 1:21 PM, Liu Yi L wrote:
> From: Eric Auger <[e-mail]>
> 
> The VFIO API was enhanced to support nested stage control: a bunch of
> new iotcls and usage guideline.
ioctls
> 
> Let's document the process to follow to set up nested mode.
> 
> Cc: Kevin Tian <[e-mail]>
> CC: Jacob Pan <[e-mail]>
> Cc: Alex Williamson <[e-mail]>
> Cc: Eric Auger <[e-mail]>
> Cc: Jean-Philippe Brucker <[e-mail]>
> Cc: Joerg Roedel <[e-mail]>
> Cc: Lu Baolu <[e-mail]>
> Reviewed-by: Stefan Hajnoczi <[e-mail]>
> Signed-off-by: Eric Auger <[e-mail]>
> Signed-off-by: Liu Yi L <[e-mail]>
> ---
> v3 -> v4:
> *) add review-by from Stefan Hajnoczi
> 
> v2 -> v3:
> *) address comments from Stefan Hajnoczi
> 
> 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 | 67 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 67 insertions(+)
> 
> diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst
> index f1a4d3c..0672c45 100644
> --- a/Documentation/driver-api/vfio.rst
> +++ b/Documentation/driver-api/vfio.rst
> @@ -239,6 +239,73 @@ 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 as configuration structures and page table
> +formats are compatible between the virtual IOMMU and the physical IOMMU.
> +
> +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.
the guest OS, here and below?
> +GVA->GPA page tables are available when PASID (Process Address Space 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

> +defined by the Virtual Command Support in VT-d 3.0 spec, guest software
> +running on VT-d should allocate PASID from host kernel.
because VTD 3.0 requires the unicity of the PASID, system wide, instead
of the above repetition.

 To allocate PASID
> +from host, user space should check the IOMMU_NESTING_FEAT_SYSWIDE_PASID
> +bit of the nesting info reported from host kernel. VFIO reports the nesting
> +info by VFIO_IOMMU_GET_INFO. User space could allocate PASID from host by:
if SYSWIDE_PASID requirement is exposed, the userspace *must* allocate ...
> +
> +    req.flags = VFIO_IOMMU_ALLOC_PASID;
> +    ioctl(container, VFIO_IOMMU_PASID_REQUEST, &req);
> +
> +With first stage/level page table bound to host, it allows to combine the
> +guest stage 1 translation along with the hypervisor stage 2 translation to
> +get final address.
> +
> +When the guest invalidates stage 1 related caches, invalidations must be
> +forwarded to the host through
> +
> +    nesting_op->flags = VFIO_IOMMU_NESTING_OP_CACHE_INVLD;
> +    memcpy(&nesting_op->data, &inv_data, sizeof(inv_data));
> +    ioctl(container->fd, VFIO_IOMMU_NESTING_OP, nesting_op);
> +
> +Those invalidations can happen at various granularity levels, page, context,
> +...
> +
>  VFIO User API
>  -------------------------------------------------------------------------------
I see you dropped the unrecoverable error reporting part of the original
contribution. By the way don't you need any error handling for either of
the use cases on vtd?
>  
> 
Thanks

Eric

Yi Liu July 25, 2020, 8:54 a.m. UTC | #2

Hi Eric,

> From: Auger Eric <[e-mail]>
> Sent: Saturday, July 18, 2020 9:40 PM
> 
> Hi Yi,
> 
> On 7/12/20 1:21 PM, Liu Yi L wrote:
> > From: Eric Auger <[e-mail]>
> >
> > The VFIO API was enhanced to support nested stage control: a bunch of
> > new iotcls and usage guideline.
> ioctls

got it.

> >
> > Let's document the process to follow to set up nested mode.
> >
> > Cc: Kevin Tian <[e-mail]>
> > CC: Jacob Pan <[e-mail]>
> > Cc: Alex Williamson <[e-mail]>
> > Cc: Eric Auger <[e-mail]>
> > Cc: Jean-Philippe Brucker <[e-mail]>
> > Cc: Joerg Roedel <[e-mail]>
> > Cc: Lu Baolu <[e-mail]>
> > Reviewed-by: Stefan Hajnoczi <[e-mail]>
> > Signed-off-by: Eric Auger <[e-mail]>
> > Signed-off-by: Liu Yi L <[e-mail]>
> > ---
> > v3 -> v4:
> > *) add review-by from Stefan Hajnoczi
> >
> > v2 -> v3:
> > *) address comments from Stefan Hajnoczi
> >
> > 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 | 67
> +++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 67 insertions(+)
> >
> > diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst
> > index f1a4d3c..0672c45 100644
> > --- a/Documentation/driver-api/vfio.rst
> > +++ b/Documentation/driver-api/vfio.rst
> > @@ -239,6 +239,73 @@ 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 as configuration structures and page table
> > +formats are compatible between the virtual IOMMU and the physical IOMMU.
> > +
> > +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.
> the guest OS, here and below?

got it.

> > +GVA->GPA page tables are available when PASID (Process Address Space 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
> 
> > +defined by the Virtual Command Support in VT-d 3.0 spec, guest software
> > +running on VT-d should allocate PASID from host kernel.
> because VTD 3.0 requires the unicity of the PASID, system wide, instead
> of the above repetition.

I see. perhaps better to say Intel platform. :-) will refine it.

> 
>  To allocate PASID
> > +from host, user space should check the IOMMU_NESTING_FEAT_SYSWIDE_PASID
> > +bit of the nesting info reported from host kernel. VFIO reports the nesting
> > +info by VFIO_IOMMU_GET_INFO. User space could allocate PASID from host by:
> if SYSWIDE_PASID requirement is exposed, the userspace *must* allocate ...

got it.

> > +
> > +    req.flags = VFIO_IOMMU_ALLOC_PASID;
> > +    ioctl(container, VFIO_IOMMU_PASID_REQUEST, &req);
> > +
> > +With first stage/level page table bound to host, it allows to combine the
> > +guest stage 1 translation along with the hypervisor stage 2 translation to
> > +get final address.
> > +
> > +When the guest invalidates stage 1 related caches, invalidations must be
> > +forwarded to the host through
> > +
> > +    nesting_op->flags = VFIO_IOMMU_NESTING_OP_CACHE_INVLD;
> > +    memcpy(&nesting_op->data, &inv_data, sizeof(inv_data));
> > +    ioctl(container->fd, VFIO_IOMMU_NESTING_OP, nesting_op);
> > +
> > +Those invalidations can happen at various granularity levels, page, context,
> > +...
> > +
> >  VFIO User API
> >  -------------------------------------------------------------------------------
> I see you dropped the unrecoverable error reporting part of the original
> contribution. By the way don't you need any error handling for either of
> the use cases on vtd?

yes, I dropped the error reporting part, the reason is the series doesn’t
include the error reporting support. guess adding it when the error
reporting is sent out.

Regards,
Yi Liu

> >
> >
> Thanks
> 
> Eric

Patch

diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst
index f1a4d3c..0672c45 100644
--- a/Documentation/driver-api/vfio.rst
+++ b/Documentation/driver-api/vfio.rst
@@ -239,6 +239,73 @@  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 as configuration structures and page table
+formats are compatible between the virtual IOMMU and the physical IOMMU.
+
+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 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
+defined by the Virtual Command Support in VT-d 3.0 spec, guest software
+running on VT-d should allocate PASID from host kernel. To allocate PASID
+from host, user space should check the IOMMU_NESTING_FEAT_SYSWIDE_PASID
+bit of the nesting info reported from host kernel. VFIO reports the nesting
+info 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);
+
+With first stage/level page table bound to host, it allows to combine the
+guest stage 1 translation along with the hypervisor stage 2 translation to
+get final address.
+
+When the guest invalidates stage 1 related caches, invalidations must be
+forwarded to the host through
+
+    nesting_op->flags = VFIO_IOMMU_NESTING_OP_CACHE_INVLD;
+    memcpy(&nesting_op->data, &inv_data, sizeof(inv_data));
+    ioctl(container->fd, VFIO_IOMMU_NESTING_OP, nesting_op);
+
+Those invalidations can happen at various granularity levels, page, context,
+...
+
 VFIO User API
 -------------------------------------------------------------------------------