Re: [PATCH QEMU v25 09/17] vfio: Add load state functions to SaveVMHandlers

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Alex Williamson (alex.williamson@redhat.com) wrote:
> On Sun, 21 Jun 2020 01:51:18 +0530
> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> 
> > Sequence  during _RESUMING device state:
> > While data for this device is available, repeat below steps:
> > a. read data_offset from where user application should write data.
> > b. write data of data_size to migration region from data_offset.
> > c. write data_size which indicates vendor driver that data is written in
> >    staging buffer.
> > 
> > For user, data is opaque. User should write data in the same order as
> > received.
> > 
> > Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> > Reviewed-by: Neo Jia <cjia@nvidia.com>
> > Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> > ---
> >  hw/vfio/migration.c  | 177 +++++++++++++++++++++++++++++++++++++++++++++++++++
> >  hw/vfio/trace-events |   3 +
> >  2 files changed, 180 insertions(+)
> > 
> > diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> > index ef1150c1ff02..faacea5327cb 100644
> > --- a/hw/vfio/migration.c
> > +++ b/hw/vfio/migration.c
> > @@ -302,6 +302,33 @@ static int vfio_save_device_config_state(QEMUFile *f, void *opaque)
> >      return qemu_file_get_error(f);
> >  }
> >  
> > +static int vfio_load_device_config_state(QEMUFile *f, void *opaque)
> > +{
> > +    VFIODevice *vbasedev = opaque;
> > +    uint64_t data;
> > +
> > +    if (vbasedev->ops && vbasedev->ops->vfio_load_config) {
> > +        int ret;
> > +
> > +        ret = vbasedev->ops->vfio_load_config(vbasedev, f);
> > +        if (ret) {
> > +            error_report("%s: Failed to load device config space",
> > +                         vbasedev->name);
> > +            return ret;
> > +        }
> > +    }
> > +
> > +    data = qemu_get_be64(f);
> > +    if (data != VFIO_MIG_FLAG_END_OF_STATE) {
> > +        error_report("%s: Failed loading device config space, "
> > +                     "end flag incorrect 0x%"PRIx64, vbasedev->name, data);
> > +        return -EINVAL;
> > +    }
> > +
> > +    trace_vfio_load_device_config_state(vbasedev->name);
> > +    return qemu_file_get_error(f);
> > +}
> > +
> >  /* ---------------------------------------------------------------------- */
> >  
> >  static int vfio_save_setup(QEMUFile *f, void *opaque)
> > @@ -472,12 +499,162 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
> >      return ret;
> >  }
> >  
> > +static int vfio_load_setup(QEMUFile *f, void *opaque)
> > +{
> > +    VFIODevice *vbasedev = opaque;
> > +    VFIOMigration *migration = vbasedev->migration;
> > +    int ret = 0;
> > +
> > +    if (migration->region.mmaps) {
> > +        ret = vfio_region_mmap(&migration->region);
> > +        if (ret) {
> > +            error_report("%s: Failed to mmap VFIO migration region %d: %s",
> > +                         vbasedev->name, migration->region.nr,
> > +                         strerror(-ret));
> > +            return ret;
> 
> 
> Not fatal.
> 
> 
> > +        }
> > +    }
> > +
> > +    ret = vfio_migration_set_state(vbasedev, ~VFIO_DEVICE_STATE_MASK,
> > +                                   VFIO_DEVICE_STATE_RESUMING);
> > +    if (ret) {
> > +        error_report("%s: Failed to set state RESUMING", vbasedev->name);
> > +    }
> > +    return ret;
> > +}
> > +
> > +static int vfio_load_cleanup(void *opaque)
> > +{
> > +    vfio_save_cleanup(opaque);
> > +    return 0;
> > +}
> > +
> > +static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
> > +{
> > +    VFIODevice *vbasedev = opaque;
> > +    VFIOMigration *migration = vbasedev->migration;
> > +    int ret = 0;
> > +    uint64_t data, data_size;
> > +
> > +    data = qemu_get_be64(f);
> > +    while (data != VFIO_MIG_FLAG_END_OF_STATE) {
> > +
> > +        trace_vfio_load_state(vbasedev->name, data);
> > +
> > +        switch (data) {
> > +        case VFIO_MIG_FLAG_DEV_CONFIG_STATE:
> > +        {
> > +            ret = vfio_load_device_config_state(f, opaque);
> > +            if (ret) {
> > +                return ret;
> > +            }
> > +            break;
> > +        }
> > +        case VFIO_MIG_FLAG_DEV_SETUP_STATE:
> > +        {
> > +            data = qemu_get_be64(f);
> > +            if (data == VFIO_MIG_FLAG_END_OF_STATE) {
> > +                return ret;
> > +            } else {
> > +                error_report("%s: SETUP STATE: EOS not found 0x%"PRIx64,
> > +                             vbasedev->name, data);
> > +                return -EINVAL;
> 
> This is essentially just a compatibility failure, right?  For instance
> some future version of QEMU might include additional data between these
> markers that we don't understand and therefore we fail the migration.

Or any other screwup in data layout;  we've found having a canary at the
end of state is quite useful for when we screwup for one reason or
another.

Dave

> Thanks,
> 
> Alex
> 
> > +            }
> > +            break;
> > +        }
> > +        case VFIO_MIG_FLAG_DEV_DATA_STATE:
> > +        {
> > +            VFIORegion *region = &migration->region;
> > +            uint64_t data_offset = 0, size;
> > +
> > +            data_size = size = qemu_get_be64(f);
> > +            if (data_size == 0) {
> > +                break;
> > +            }
> > +
> > +            ret = pread(vbasedev->fd, &data_offset, sizeof(data_offset),
> > +                        region->fd_offset +
> > +                        offsetof(struct vfio_device_migration_info,
> > +                        data_offset));
> > +            if (ret != sizeof(data_offset)) {
> > +                error_report("%s:Failed to get migration buffer data offset %d",
> > +                             vbasedev->name, ret);
> > +                return -EINVAL;
> > +            }
> > +
> > +            trace_vfio_load_state_device_data(vbasedev->name, data_offset,
> > +                                              data_size);
> > +
> > +            while (size) {
> > +                void *buf = NULL;
> > +                uint64_t sec_size;
> > +                bool buffer_mmaped;
> > +
> > +                buf = get_data_section_size(region, data_offset, size,
> > +                                            &sec_size);
> > +
> > +                buffer_mmaped = (buf != NULL);
> > +
> > +                if (!buffer_mmaped) {
> > +                    buf = g_try_malloc(sec_size);
> > +                    if (!buf) {
> > +                        error_report("%s: Error allocating buffer ", __func__);
> > +                        return -ENOMEM;
> > +                    }
> > +                }
> > +
> > +                qemu_get_buffer(f, buf, sec_size);
> > +
> > +                if (!buffer_mmaped) {
> > +                    ret = pwrite(vbasedev->fd, buf, sec_size,
> > +                                 region->fd_offset + data_offset);
> > +                    g_free(buf);
> > +
> > +                    if (ret != sec_size) {
> > +                        error_report("%s: Failed to set migration buffer %d",
> > +                                vbasedev->name, ret);
> > +                        return -EINVAL;
> > +                    }
> > +                }
> > +                size -= sec_size;
> > +                data_offset += sec_size;
> > +            }
> > +
> > +            ret = pwrite(vbasedev->fd, &data_size, sizeof(data_size),
> > +                         region->fd_offset +
> > +                       offsetof(struct vfio_device_migration_info, data_size));
> > +            if (ret != sizeof(data_size)) {
> > +                error_report("%s: Failed to set migration buffer data size %d",
> > +                             vbasedev->name, ret);
> > +                return -EINVAL;
> > +            }
> > +            break;
> > +        }
> > +
> > +        default:
> > +            error_report("%s: Unknown tag 0x%"PRIx64, vbasedev->name, data);
> > +            return -EINVAL;
> > +        }
> > +
> > +        data = qemu_get_be64(f);
> > +        ret = qemu_file_get_error(f);
> > +        if (ret) {
> > +            return ret;
> > +        }
> > +    }
> > +
> > +    return ret;
> > +}
> > +
> >  static SaveVMHandlers savevm_vfio_handlers = {
> >      .save_setup = vfio_save_setup,
> >      .save_cleanup = vfio_save_cleanup,
> >      .save_live_pending = vfio_save_pending,
> >      .save_live_iterate = vfio_save_iterate,
> >      .save_live_complete_precopy = vfio_save_complete_precopy,
> > +    .load_setup = vfio_load_setup,
> > +    .load_cleanup = vfio_load_cleanup,
> > +    .load_state = vfio_load_state,
> >  };
> >  
> >  /* ---------------------------------------------------------------------- */
> > diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> > index 9a1c5e17d97f..4a4bd3ba9a2a 100644
> > --- a/hw/vfio/trace-events
> > +++ b/hw/vfio/trace-events
> > @@ -157,3 +157,6 @@ vfio_save_device_config_state(const char *name) " (%s)"
> >  vfio_save_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
> >  vfio_save_iterate(const char *name, int data_size) " (%s) data_size %d"
> >  vfio_save_complete_precopy(const char *name) " (%s)"
> > +vfio_load_device_config_state(const char *name) " (%s)"
> > +vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
> > +vfio_load_state_device_data(const char *name, uint64_t data_offset, uint64_t data_size) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK