Use this story to track the mlx VF multifd migration's support status in RHEL 9

The mlx multifd VF migration's not enabled actually.

Test steps:

• check the VF's attribute

  # /usr/libexec/qemu-kvm --device vfio-pci,? | grep -i migration  <-- The multifd-related attribute like migration-multifd-transfer  doesn't exist
  enable-migration=<OnOffAuto> - on/off/auto (default: "auto")
  migration-events=<bool> -  (default: false)
  x-migration-max-queued-buffers=<uint64> -  (default: 18446744073709551615)  
  

• start a VM with a migratable mlx VF
  check the global migration info

  (qemu) info migrate <-- The multifd-related option like send-switchover-start  doesn't exist
  globals:
  store-global-state: on
  only-migratable: off
  send-configuration: on
  send-section-footer: on
  clear-bitmap-shift: 18
  

• migrate the VM with multifd

   virsh migrate --live --parallel --parallel-connections $connection $VM --desturi qemu+ssh://$ip_address/system 

• check the migration details when the above mlx VF multifd migration starts：

  (qemu) info migrate_capabilities"
  xbzrle: off
  rdma-pin-all: off
  auto-converge: off
  zero-blocks: off
  events: on
  postcopy-ram: off
  x-colo: off
  release-ram: off
  return-path: on
  pause-before-switchover: on
  multifd: on
  dirty-bitmaps: off
  postcopy-blocktime: off
  late-block-activate: off
  x-ignore-shared: off
  validate-uuid: off
  background-snapshot: off
  zero-copy-send: off
  postcopy-preempt: off
  switchover-ack: on
  dirty-limit: off
  mapped-ram: off
  
  
  (qemu)  info migrate_parameters
  announce-initial: 50 ms
  announce-max: 550 ms
  announce-rounds: 5
  announce-step: 100 ms
  throttle-trigger-threshold: 50
  cpu-throttle-initial: 20
  cpu-throttle-increment: 10
  cpu-throttle-tailslow: off
  max-cpu-throttle: 99
  tls-creds: ''
  tls-hostname: ''
  max-bandwidth: 9223372036853727232 bytes/second
  avail-switchover-bandwidth: 0 bytes/second
  downtime-limit: 300 ms
  x-checkpoint-delay: 20000 ms
  multifd-channels: 4
  multifd-compression: none
  zero-page-detection: multifd
  xbzrle-cache-size: 67108864 bytes
  max-postcopy-bandwidth: 0
  tls-authz: ''
  x-vcpu-dirty-limit-period: 1000 ms
  vcpu-dirty-limit: 1 MB/s
  mode: normal
  direct-io: off
  
  
  (qemu) info migrate
  globals:
  store-global-state: on
  only-migratable: off
  send-configuration: on
  send-section-footer: on
  clear-bitmap-shift: 18
  Migration status: active
  total time: 958 ms
  expected downtime: 300 ms
  setup: 46 ms
  transferred ram: 107506 kbytes
  throughput: 872.75 mbps
  remaining ram: 6522924 kbytes
  total ram: 8405552 kbytes
  duplicate: 444373 pages
  normal: 25643 pages
  normal bytes: 102572 kbytes
  dirty sync count: 1
  page size: 4 kbytes
  multifd bytes: 107397 kbytes
  pages-per-second: 26566
  precopy ram: 0 kbytes
  vfio device transferred: 108 kbytes
  

• check the migration details when the above mlx VF multifd migration is nearly completed.

  (qemu) info migrate_capabilities"
  xbzrle: off
  rdma-pin-all: off
  auto-converge: off
  zero-blocks: off
  events: on
  postcopy-ram: off
  x-colo: off
  release-ram: off
  return-path: off
  pause-before-switchover: off
  multifd: off  <-- the multifd will be set back to off
  dirty-bitmaps: off
  postcopy-blocktime: off
  late-block-activate: off
  x-ignore-shared: off
  validate-uuid: off
  background-snapshot: off
  zero-copy-send: off
  postcopy-preempt: off
  switchover-ack: off
  dirty-limit: off
  mapped-ram: off
  
  (qemu)  info migrate_parameters
  announce-initial: 50 ms
  announce-max: 550 ms
  announce-rounds: 5
  announce-step: 100 ms
  throttle-trigger-threshold: 50
  cpu-throttle-initial: 20
  cpu-throttle-increment: 10
  cpu-throttle-tailslow: off
  max-cpu-throttle: 99
  tls-creds: ''
  tls-hostname: ''
  max-bandwidth: 134217728 bytes/second
  avail-switchover-bandwidth: 0 bytes/second
  downtime-limit: 300 ms
  x-checkpoint-delay: 20000 ms
  multifd-channels: 2  <-- the multifd-channels will be set back to default value
  multifd-compression: none
  zero-page-detection: multifd
  xbzrle-cache-size: 67108864 bytes
  max-postcopy-bandwidth: 0
  tls-authz: ''
  x-vcpu-dirty-limit-period: 1000 ms
  vcpu-dirty-limit: 1 MB/s
  mode: normal
  direct-io: off
  
  
  (qemu) info migrate
  globals:
  store-global-state: on
  only-migratable: off
  send-configuration: on
  send-section-footer: on
  clear-bitmap-shift: 18
  Migration status: completed
  total time: 0 ms
  

Actual result:
The mlx VF multifd migration is not enabled actually