Re: [PATCH v27 09/17] vfio: Add load state functions to SaveVMHandlers

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

On Thu, 22 Oct 2020 16:41:59 +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  | 192 +++++++++++++++++++++++++++++++++++++++++++++++++++
>  hw/vfio/trace-events |   3 +
>  2 files changed, 195 insertions(+)
> 
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 5506cef15d88..46d05d230e2a 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -257,6 +257,77 @@ static int vfio_save_buffer(QEMUFile *f, VFIODevice *vbasedev, uint64_t *size)
>      return ret;
>  }
>  
> +static int vfio_load_buffer(QEMUFile *f, VFIODevice *vbasedev,
> +                            uint64_t data_size)
> +{
> +    VFIORegion *region = &vbasedev->migration->region;
> +    uint64_t data_offset = 0, size, report_size;
> +    int ret;
> +
> +    do {
> +        ret = vfio_mig_read(vbasedev, &data_offset, sizeof(data_offset),
> +                      region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_offset));
> +        if (ret < 0) {
> +            return ret;
> +        }
> +
> +        if (data_offset + data_size > region->size) {
> +            /*
> +             * If data_size is greater than the data section of migration region
> +             * then iterate the write buffer operation. This case can occur if
> +             * size of migration region at destination is smaller than size of
> +             * migration region at source.
> +             */
> +            report_size = size = region->size - data_offset;
> +            data_size -= size;
> +        } else {
> +            report_size = size = data_size;
> +            data_size = 0;
> +        }
> +
> +        trace_vfio_load_state_device_data(vbasedev->name, data_offset, size);
> +
> +        while (size) {
> +            void *buf;
> +            uint64_t sec_size;
> +            bool buf_alloc = false;
> +
> +            buf = get_data_section_size(region, data_offset, size, &sec_size);
> +
> +            if (!buf) {
> +                buf = g_try_malloc(sec_size);
> +                if (!buf) {
> +                    error_report("%s: Error allocating buffer ", __func__);
> +                    return -ENOMEM;
> +                }
> +                buf_alloc = true;
> +            }
> +
> +            qemu_get_buffer(f, buf, sec_size);
> +
> +            if (buf_alloc) {
> +                ret = vfio_mig_write(vbasedev, buf, sec_size,
> +                        region->fd_offset + data_offset);
> +                g_free(buf);
> +
> +                if (ret < 0) {
> +                    return ret;
> +                }
> +            }
> +            size -= sec_size;
> +            data_offset += sec_size;
> +        }
> +
> +        ret = vfio_mig_write(vbasedev, &report_size, sizeof(report_size),
> +                        region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_size));
> +        if (ret < 0) {
> +            return ret;
> +        }
> +    } while (data_size);
> +
> +    return 0;
> +}
> +
>  static int vfio_update_pending(VFIODevice *vbasedev)
>  {
>      VFIOMigration *migration = vbasedev->migration;
> @@ -293,6 +364,33 @@ 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)
> @@ -477,12 +575,106 @@ 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);


Checking, are we in the right thread context not to require locking the
iothread as we did in vfio_save_setup()?


> +        if (ret) {
> +            error_report("%s: Failed to mmap VFIO migration region %d: %s",
> +                         vbasedev->name, migration->region.nr,
> +                         strerror(-ret));
> +            error_report("%s: Falling back to slow path", vbasedev->name);
> +        }
> +    }
> +
> +    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);
> +        if (migration->region.mmaps) {
> +            vfio_region_unmap(&migration->region);
> +        }
> +    }
> +    return ret;
> +}
> +
> +static int vfio_load_cleanup(void *opaque)
> +{
> +    vfio_save_cleanup(opaque);


The tracing in there is going to be rather confusing.  Thanks,

Alex


> +    return 0;
> +}
> +
> +static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
> +{
> +    VFIODevice *vbasedev = opaque;
> +    int ret = 0;
> +    uint64_t data;
> +
> +    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;
> +            }
> +            break;
> +        }
> +        case VFIO_MIG_FLAG_DEV_DATA_STATE:
> +        {
> +            uint64_t data_size = qemu_get_be64(f);
> +
> +            if (data_size) {
> +                ret = vfio_load_buffer(f, vbasedev, data_size);
> +                if (ret < 0) {
> +                    return ret;
> +                }
> +            }
> +            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 9f5712dab1ea..4804cc266d44 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -159,3 +159,6 @@ 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