Re: [Qemu-devel] [PATCH 3/9] vfio: unplug failover primary device before migration

[Cornelia Huck]

On Fri,  2 Aug 2019 17:05:59 +0200
Jens Freimann <address@hidden> wrote:

> As usual block all vfio-pci devices from being migrated, but make an
> exception for failover primary devices. This is achieved by setting
> unmigratable to 0 but also add a migration blocker for all vfio-pci
> devices except failover primary devices. These will be unplugged before
> migration happens by the migration handler of the corresponding
> virtio-net standby device.
> 
> Signed-off-by: Jens Freimann <address@hidden>
> ---
>  hw/vfio/pci.c | 24 +++++++++++++++++++++++-
>  hw/vfio/pci.h |  1 +
>  2 files changed, 24 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index d6ae9bd4ac..398d26669b 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -35,6 +35,9 @@
>  #include "pci.h"
>  #include "trace.h"
>  #include "qapi/error.h"
> +#include "migration/blocker.h"
> +#include "qemu/option.h"
> +#include "qemu/option_int.h"
>  
>  #define TYPE_VFIO_PCI "vfio-pci"
>  #define PCI_VFIO(obj)    OBJECT_CHECK(VFIOPCIDevice, obj, TYPE_VFIO_PCI)
> @@ -2693,6 +2696,12 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice 
> *vdev)
>      vdev->req_enabled = false;
>  }
>  
> +static int has_standby_arg(void *opaque, const char *name,
> +                           const char *value, Error **errp)
> +{
> +    return strcmp(name, "standby") == 0;
> +}
> +
>  static void vfio_realize(PCIDevice *pdev, Error **errp)
>  {
>      VFIOPCIDevice *vdev = PCI_VFIO(pdev);
> @@ -2706,6 +2715,19 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
>      int i, ret;
>      bool is_mdev;
>  
> +    if (qemu_opt_foreach(pdev->qdev.opts, has_standby_arg,
> +                         (void *) pdev->qdev.opts, &err) == 0) {
> +        error_setg(&vdev->migration_blocker,
> +                "VFIO device doesn't support migration");
> +        ret = migrate_add_blocker(vdev->migration_blocker, &err);
> +        if (err) {
> +            error_propagate(errp, err);
> +            error_free(vdev->migration_blocker);
> +        }
> +    } else {
> +        pdev->qdev.allow_unplug_during_migration = true;

I think you add this only in the next patch?

> +    }
> +
>      if (!vdev->vbasedev.sysfsdev) {
>          if (!(~vdev->host.domain || ~vdev->host.bus ||
>                ~vdev->host.slot || ~vdev->host.function)) {
> @@ -3148,7 +3170,7 @@ static Property vfio_pci_dev_properties[] = {
>  
>  static const VMStateDescription vfio_pci_vmstate = {
>      .name = "vfio-pci",
> -    .unmigratable = 1,
> +    .unmigratable = 0,
>  };
>  
>  static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
> index 27d58fc55b..0f6f8cb395 100644
> --- a/hw/vfio/pci.h
> +++ b/hw/vfio/pci.h
> @@ -169,6 +169,7 @@ typedef struct VFIOPCIDevice {
>      bool no_vfio_ioeventfd;
>      bool enable_ramfb;
>      VFIODisplay *dpy;
> +    Error *migration_blocker;
>  } VFIOPCIDevice;
>  
>  uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);

This patch interacts with support for vfio migration (last posted in
<address@hidden>, I've not seen
a later version yet.)

With that, we'd have three cases to consider:
1) device is a failover primary
2) device has a migration region
3) none of the above

Can 1) and 2) happen simultaneously? If yes, what should take
precedence?