Re: [PATCH v26 17/17] qapi: Add VFIO devices migration stats in Migration stats

[Alex Williamson]

On Wed, 23 Sep 2020 04:54:19 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> Added amount of bytes transferred to the target VM by all VFIO devices
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> ---
> 
> Note: Comments from v25 for this patch are not addressed yet.
> https://www.mail-archive.com/qemu-devel@nongnu.org/msg715620.html
> 
> Alex, need more pointer on documentation part raised Markus Armbruster.

I'm not sure what you're asking of me here.  Are we being asked to
justify that a vfio device has state that needs to be migrated and the
ability to dirty pages?
 
> 
>  hw/vfio/common.c            | 20 ++++++++++++++++++++
>  hw/vfio/migration.c         | 10 ++++++++++
>  include/qemu/vfio-helpers.h |  3 +++
>  migration/migration.c       | 14 ++++++++++++++
>  monitor/hmp-cmds.c          |  6 ++++++
>  qapi/migration.json         | 17 +++++++++++++++++
>  6 files changed, 70 insertions(+)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 7eeaa368187a..286cdaac8674 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -39,6 +39,7 @@
>  #include "trace.h"
>  #include "qapi/error.h"
>  #include "migration/migration.h"
> +#include "qemu/vfio-helpers.h"
>  
>  VFIOGroupList vfio_group_list =
>      QLIST_HEAD_INITIALIZER(vfio_group_list);
> @@ -292,6 +293,25 @@ const MemoryRegionOps vfio_region_ops = {
>   * Device state interfaces
>   */
>  
> +bool vfio_mig_active(void)
> +{
> +    VFIOGroup *group;
> +    VFIODevice *vbasedev;
> +
> +    if (QLIST_EMPTY(&vfio_group_list)) {
> +        return false;
> +    }
> +
> +    QLIST_FOREACH(group, &vfio_group_list, next) {
> +        QLIST_FOREACH(vbasedev, &group->device_list, next) {
> +            if (vbasedev->migration_blocker) {
> +                return false;
> +            }
> +        }
> +    }
> +    return true;
> +}
> +
>  static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container)
>  {
>      VFIOGroup *group;
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 822b68b4e015..c4226fa8b183 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -28,6 +28,7 @@
>  #include "pci.h"
>  #include "trace.h"
>  #include "hw/hw.h"
> +#include "qemu/vfio-helpers.h"
>  
>  /*
>   * Flags used as delimiter:
> @@ -40,6 +41,8 @@
>  #define VFIO_MIG_FLAG_DEV_SETUP_STATE   (0xffffffffef100003ULL)
>  #define VFIO_MIG_FLAG_DEV_DATA_STATE    (0xffffffffef100004ULL)
>  
> +static int64_t bytes_transferred;
> +
>  static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
>                                    off_t off, bool iswrite)
>  {
> @@ -289,6 +292,7 @@ static int vfio_save_buffer(QEMUFile *f, VFIODevice 
> *vbasedev, uint64_t *size)
>          *size = data_size;
>      }
>  
> +    bytes_transferred += data_size;
>      return ret;
>  }
>  
> @@ -770,6 +774,7 @@ static void vfio_migration_state_notifier(Notifier 
> *notifier, void *data)
>          }
>  
>          vfio_set_dirty_page_tracking(vbasedev, false);
> +        bytes_transferred = 0;
>      }
>  }
>  
> @@ -820,6 +825,11 @@ static int vfio_migration_init(VFIODevice *vbasedev,
>  
>  /* ---------------------------------------------------------------------- */
>  
> +int64_t vfio_mig_bytes_transferred(void)
> +{
> +    return bytes_transferred;
> +}
> +
>  int vfio_migration_probe(VFIODevice *vbasedev, Error **errp)
>  {
>      VFIOContainer *container = vbasedev->group->container;
> diff --git a/include/qemu/vfio-helpers.h b/include/qemu/vfio-helpers.h
> index 1f057c2b9e40..26a7df0767b1 100644
> --- a/include/qemu/vfio-helpers.h
> +++ b/include/qemu/vfio-helpers.h
> @@ -29,4 +29,7 @@ void qemu_vfio_pci_unmap_bar(QEMUVFIOState *s, int index, 
> void *bar,
>  int qemu_vfio_pci_init_irq(QEMUVFIOState *s, EventNotifier *e,
>                             int irq_type, Error **errp);
>  
> +bool vfio_mig_active(void);
> +int64_t vfio_mig_bytes_transferred(void);
> +
>  #endif
> diff --git a/migration/migration.c b/migration/migration.c
> index 58a5452471f9..b204bb1f6cd9 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -56,6 +56,7 @@
>  #include "net/announce.h"
>  #include "qemu/queue.h"
>  #include "multifd.h"
> +#include "qemu/vfio-helpers.h"
>  
>  #define MAX_THROTTLE  (32 << 20)      /* Migration transfer speed throttling 
> */
>  
> @@ -996,6 +997,17 @@ static void populate_disk_info(MigrationInfo *info)
>      }
>  }
>  
> +static void populate_vfio_info(MigrationInfo *info)
> +{
> +#ifdef CONFIG_LINUX
> +    if (vfio_mig_active()) {
> +        info->has_vfio = true;
> +        info->vfio = g_malloc0(sizeof(*info->vfio));
> +        info->vfio->transferred = vfio_mig_bytes_transferred();
> +    }
> +#endif
> +}
> +
>  static void fill_source_migration_info(MigrationInfo *info)
>  {
>      MigrationState *s = migrate_get_current();
> @@ -1020,6 +1032,7 @@ static void fill_source_migration_info(MigrationInfo 
> *info)
>          populate_time_info(info, s);
>          populate_ram_info(info, s);
>          populate_disk_info(info);
> +        populate_vfio_info(info);
>          break;
>      case MIGRATION_STATUS_COLO:
>          info->has_status = true;
> @@ -1028,6 +1041,7 @@ static void fill_source_migration_info(MigrationInfo 
> *info)
>      case MIGRATION_STATUS_COMPLETED:
>          populate_time_info(info, s);
>          populate_ram_info(info, s);
> +        populate_vfio_info(info);
>          break;
>      case MIGRATION_STATUS_FAILED:
>          info->has_status = true;
> diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
> index 7711726fd222..40d60d6a6651 100644
> --- a/monitor/hmp-cmds.c
> +++ b/monitor/hmp-cmds.c
> @@ -355,6 +355,12 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
>          }
>          monitor_printf(mon, "]\n");
>      }
> +
> +    if (info->has_vfio) {
> +        monitor_printf(mon, "vfio device transferred: %" PRIu64 " kbytes\n",
> +                       info->vfio->transferred >> 10);
> +    }
> +
>      qapi_free_MigrationInfo(info);
>  }
>  
> diff --git a/qapi/migration.json b/qapi/migration.json
> index 675f70bb6734..3535977123d3 100644
> --- a/qapi/migration.json
> +++ b/qapi/migration.json
> @@ -147,6 +147,18 @@
>              'active', 'postcopy-active', 'postcopy-paused',
>              'postcopy-recover', 'completed', 'failed', 'colo',
>              'pre-switchover', 'device', 'wait-unplug' ] }
> +##
> +# @VfioStats:
> +#
> +# Detailed VFIO devices migration statistics
> +#
> +# @transferred: amount of bytes transferred to the target VM by VFIO devices
> +#
> +# Since: 5.1
> +#
> +##
> +{ 'struct': 'VfioStats',
> +  'data': {'transferred': 'int' } }
>  
>  ##
>  # @MigrationInfo:
> @@ -208,11 +220,16 @@
>  #
>  # @socket-address: Only used for tcp, to know what the real port is (Since 
> 4.0)
>  #
> +# @vfio: @VfioStats containing detailed VFIO devices migration statistics,
> +#        only returned if VFIO device is present, migration is supported by 
> all
> +#         VFIO devices and status is 'active' or 'completed' (since 5.1)

This could be clarified a little:

...only returned if all VFIO devices attached to a VM support migration
and migration status is 'active' or 'completed' (since 5.2)

Is that accurate?  Thanks,

Alex

> +#
>  # Since: 0.14.0
>  ##
>  { 'struct': 'MigrationInfo',
>    'data': {'*status': 'MigrationStatus', '*ram': 'MigrationStats',
>             '*disk': 'MigrationStats',
> +           '*vfio': 'VfioStats',
>             '*xbzrle-cache': 'XBZRLECacheStats',
>             '*total-time': 'int',
>             '*expected-downtime': 'int',