Re: [PATCH v9 QEMU 07/15] vfio: Add migration region initialization and finalize function

[Alex Williamson <alex.williamson@redhat.com>]

On Tue, 12 Nov 2019 22:35:16 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> - Migration functions are implemented for VFIO_DEVICE_TYPE_PCI device in this
>   patch series.
> - VFIO device supports migration or not is decided based of migration region
>   query. If migration region query is successful and migration region
>   initialization is successful then migration is supported else migration is
>   blocked.
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
>  hw/vfio/Makefile.objs         |   2 +-
>  hw/vfio/migration.c           | 137 ++++++++++++++++++++++++++++++++++++++++++
>  hw/vfio/trace-events          |   3 +
>  include/hw/vfio/vfio-common.h |  10 +++
>  4 files changed, 151 insertions(+), 1 deletion(-)
>  create mode 100644 hw/vfio/migration.c
> 
> diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
> index abad8b818c9b..36033d1437c5 100644
> --- a/hw/vfio/Makefile.objs
> +++ b/hw/vfio/Makefile.objs
> @@ -1,4 +1,4 @@
> -obj-y += common.o spapr.o
> +obj-y += common.o spapr.o migration.o
>  obj-$(CONFIG_VFIO_PCI) += pci.o pci-quirks.o display.o
>  obj-$(CONFIG_VFIO_CCW) += ccw.o
>  obj-$(CONFIG_VFIO_PLATFORM) += platform.o
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> new file mode 100644
> index 000000000000..c17bd1b0b934
> --- /dev/null
> +++ b/hw/vfio/migration.c
> @@ -0,0 +1,137 @@
> +/*
> + * Migration support for VFIO devices
> + *
> + * Copyright NVIDIA, Inc. 2019
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2. See
> + * the COPYING file in the top-level directory.
> + */
> +
> +#include "qemu/osdep.h"
> +#include <linux/vfio.h>
> +
> +#include "hw/vfio/vfio-common.h"
> +#include "cpu.h"
> +#include "migration/migration.h"
> +#include "migration/qemu-file.h"
> +#include "migration/register.h"
> +#include "migration/blocker.h"
> +#include "migration/misc.h"
> +#include "qapi/error.h"
> +#include "exec/ramlist.h"
> +#include "exec/ram_addr.h"
> +#include "pci.h"
> +#include "trace.h"
> +
> +static void vfio_migration_region_exit(VFIODevice *vbasedev)
> +{
> +    VFIOMigration *migration = vbasedev->migration;
> +
> +    if (!migration) {
> +        return;
> +    }
> +
> +    if (migration->region.size) {
> +        vfio_region_exit(&migration->region);
> +        vfio_region_finalize(&migration->region);
> +    }
> +}
> +
> +static int vfio_migration_region_init(VFIODevice *vbasedev, int index)
> +{
> +    VFIOMigration *migration = vbasedev->migration;
> +    Object *obj = NULL;
> +    int ret = -EINVAL;
> +
> +    if (!vbasedev->ops || !vbasedev->ops->vfio_get_object) {

Is it possible not to have vbasedev->ops?

> +        return ret;
> +    }
> +
> +    obj = vbasedev->ops->vfio_get_object(vbasedev);
> +    if (!obj) {
> +        return ret;
> +    }
> +
> +    ret = vfio_region_setup(obj, vbasedev, &migration->region, index,
> +                            "migration");
> +    if (ret) {
> +        error_report("%s: Failed to setup VFIO migration region %d: %s",
> +                     vbasedev->name, index, strerror(-ret));
> +        goto err;
> +    }
> +
> +    if (!migration->region.size) {
> +        ret = -EINVAL;
> +        error_report("%s: Invalid region size of VFIO migration region %d: %s",
> +                     vbasedev->name, index, strerror(-ret));
> +        goto err;
> +    }
> +
> +    return 0;
> +
> +err:
> +    vfio_migration_region_exit(vbasedev);
> +    return ret;
> +}
> +
> +static int vfio_migration_init(VFIODevice *vbasedev,
> +                               struct vfio_region_info *info)
> +{
> +    int ret;
> +
> +    vbasedev->migration = g_new0(VFIOMigration, 1);
> +
> +    ret = vfio_migration_region_init(vbasedev, info->index);
> +    if (ret) {
> +        error_report("%s: Failed to initialise migration region",
> +                     vbasedev->name);
> +        g_free(vbasedev->migration);

Note that vbasedev->migration is not NULL, so calling
vfio_migration_region_exit() at this point will be a use-after-free
error.

> +        return ret;
> +    }
> +
> +    return 0;
> +}
> +
> +/* ---------------------------------------------------------------------- */
> +
> +int vfio_migration_probe(VFIODevice *vbasedev, Error **errp)
> +{
> +    struct vfio_region_info *info;
> +    Error *local_err = NULL;
> +    int ret;
> +
> +    ret = vfio_get_dev_region_info(vbasedev, VFIO_REGION_TYPE_MIGRATION,
> +                                   VFIO_REGION_SUBTYPE_MIGRATION, &info);
> +    if (ret) {
> +        goto add_blocker;
> +    }
> +
> +    ret = vfio_migration_init(vbasedev, info);
> +    if (ret) {
> +        goto add_blocker;
> +    }
> +
> +    trace_vfio_migration_probe(vbasedev->name, info->index);
> +    return 0;
> +
> +add_blocker:
> +    error_setg(&vbasedev->migration_blocker,
> +               "VFIO device doesn't support migration");
> +    ret = migrate_add_blocker(vbasedev->migration_blocker, &local_err);
> +    if (local_err) {
> +        error_propagate(errp, local_err);
> +        error_free(vbasedev->migration_blocker);
> +    }

This won't get along well with the failover code that's in QEMU master.

> +    return ret;
> +}
> +
> +void vfio_migration_finalize(VFIODevice *vbasedev)
> +{
> +    if (vbasedev->migration_blocker) {
> +        migrate_del_blocker(vbasedev->migration_blocker);
> +        error_free(vbasedev->migration_blocker);
> +    }
> +
> +    vfio_migration_region_exit(vbasedev);
> +    g_free(vbasedev->migration);

This will do bad things if vfio_migration_init() failed as indicated
above.

> +}
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 8cdc27946cb8..191a726a1312 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -143,3 +143,6 @@ vfio_display_edid_link_up(void) ""
>  vfio_display_edid_link_down(void) ""
>  vfio_display_edid_update(uint32_t prefx, uint32_t prefy) "%ux%u"
>  vfio_display_edid_write_error(void) ""
> +
> +# migration.c
> +vfio_migration_probe(char *name, uint32_t index) " (%s) Region %d"
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index d69a7f3ae31e..927511897a44 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -57,6 +57,11 @@ typedef struct VFIORegion {
>      uint8_t nr; /* cache the region number for debug */
>  } VFIORegion;
>  
> +typedef struct VFIOMigration {
> +    VFIORegion region;
> +    uint64_t pending_bytes;

pending_bytes is not used here, let's add it when it's needed.

> +} VFIOMigration;
> +
>  typedef struct VFIOAddressSpace {
>      AddressSpace *as;
>      QLIST_HEAD(, VFIOContainer) containers;
> @@ -113,6 +118,8 @@ typedef struct VFIODevice {
>      unsigned int num_irqs;
>      unsigned int num_regions;
>      unsigned int flags;
> +    VFIOMigration *migration;
> +    Error *migration_blocker;

See:

f045a0104c8c ("vfio: unplug failover primary device before migration")

Edit: I see once I got to the last patch how you managed this.

>  } VFIODevice;
>  
>  struct VFIODeviceOps {
> @@ -204,4 +211,7 @@ int vfio_spapr_create_window(VFIOContainer *container,
>  int vfio_spapr_remove_window(VFIOContainer *container,
>                               hwaddr offset_within_address_space);
>  
> +int vfio_migration_probe(VFIODevice *vbasedev, Error **errp);
> +void vfio_migration_finalize(VFIODevice *vbasedev);
> +
>  #endif /* HW_VFIO_VFIO_COMMON_H */