On Tue, Jul 20, 2021 at 04:09:27PM +0300, Max Gurtovoy wrote:
> 
> On 7/20/2021 3:57 PM, Stefan Hajnoczi wrote:
> > On Tue, Jul 20, 2021 at 03:27:00PM +0300, Max Gurtovoy wrote:
> > > On 7/20/2021 6:02 AM, Jason Wang wrote:
> > > > 在 2021/7/19 下午8:43, Stefan Hajnoczi 写道:
> > > > > On Fri, Jul 16, 2021 at 10:03:17AM +0800, Jason Wang wrote:
> > > > > > 在 2021/7/15 下午6:01, Stefan Hajnoczi 写道:
> > > > > > > On Thu, Jul 15, 2021 at 09:35:13AM +0800, Jason Wang wrote:
> > > > > > > > 在 2021/7/14 下午11:07, Stefan Hajnoczi 写道:
> > > > > > > > > On Wed, Jul 14, 2021 at 06:29:28PM +0800, Jason Wang wrote:
> > > > > > > > > > 在 2021/7/14 下午5:53, Stefan Hajnoczi 写道:
> > > > > > > > > > > On Tue, Jul 13, 2021 at 08:16:35PM +0800, Jason Wang wrote:
> > > > > > > > > > > > 在 2021/7/13 下午6:00, Stefan Hajnoczi 写道:
> > > > > > > > > > > > > On Tue, Jul 13, 2021 at 11:27:03AM +0800, Jason Wang wrote:
> > > > > > > > > > > > > > 在 2021/7/12 下午5:57, Stefan Hajnoczi 写道:
> > > > > > > > > > > > > > > On Mon, Jul 12, 2021 at 12:00:39PM +0800, Jason Wang wrote:
> > > > > > > > > > > > > > > > 在 2021/7/11 上午4:36, Michael S. Tsirkin 写道:
> > > > > > > > > > > > > > > > > On Fri, Jul 09, 2021
> > > > > > > > > > > > > > > > > at 07:23:33PM +0200,
> > > > > > > > > > > > > > > > > Eugenio Perez Martin
> > > > > > > > > > > > > > > > > wrote:
> > > > > > > > > That's
> > > > > > > > > basically the difference between the vhost/vDPA's
> > > > > > > > > selective passthrough
> > > > > > > > > approach and VFIO's full passthrough approach.
> > > > > > > > We can't do VFIO full pasthrough for migration anyway,
> > > > > > > > some kind of mdev is
> > > > > > > > required but it's duplicated with the current vp_vdpa driver.
> > > > > > > I'm not sure that's true. Generic VFIO PCI migration can probably be
> > > > > > > achieved without mdev:
> > > > > > > 1. Define a migration PCI Capability that indicates support for
> > > > > > >       VFIO_REGION_TYPE_MIGRATION. This allows the PCI device
> > > > > > > to implement
> > > > > > >       the migration interface in hardware instead of an mdev driver.
> > > > > > So I think it still depend on the driver to implement migrate
> > > > > > state which is
> > > > > > vendor specific.
> > > > > The current VFIO migration interface depends on a device-specific
> > > > > software mdev driver but here I'm showing that the physical device can
> > > > > implement the migration interface so that no device-specific driver code
> > > > > is needed.
> > > > 
> > > > This is not what I read from the patch:
> > > > 
> > > >   * device_state: (read/write)
> > > >   *      - The user application writes to this field to inform the vendor
> > > > driver
> > > >   *        about the device state to be transitioned to.
> > > >   *      - The vendor driver should take the necessary actions to change
> > > > the
> > > >   *        device state. After successful transition to a given state, the
> > > >   *        vendor driver should return success on write(device_state,
> > > > state)
> > > >   *        system call. If the device state transition fails, the vendor
> > > > driver
> > > >   *        should return an appropriate -errno for the fault condition.
> > > > 
> > > > Vendor driver need to mediate between the uAPI and the actual device.
> > > We're building an infrastructure for VFIO PCI devices in the last few
> > > months.
> > > 
> > > It should be merged hopefully to kernel 5.15.
> > Do you have links to patch series or a brief description of the VFIO API
> > features that are on the roadmap?
> 
> we devided it to few patchsets .
> 
> The entire series can be found at:
> 
> https://github.com/jgunthorpe/linux/commits/mlx5_vfio_pci
> 
> We'll first add support for mlx5 devices suspend/resume (ConnectX-6 and
> above).
> 
> The driver is ready in the series above.

I looked briefly and it seems to implement the existing
VFIO_REGION_TYPE_MIGRATION API for mlx5 devices? I thought
"infrastructure for VFIO PCI devices" meant you were adding new
VFIO/mdev migration APIs.

Stefan