vfio/migration: Add P2P support for VFIO migration

VFIO migration uAPI defines an optional intermediate P2P quiescent
state. While in the P2P quiescent state, P2P DMA transactions cannot be
initiated by the device, but the device can respond to incoming ones.
Additionally, all outstanding P2P transactions are guaranteed to have
been completed by the time the device enters this state.

The purpose of this state is to support migration of multiple devices
that might do P2P transactions between themselves.

Add support for P2P migration by transitioning all the devices to the
P2P quiescent state before stopping or starting the devices. Use the new
VMChangeStateHandler prepare_cb to achieve that behavior.

This will allow migration of multiple VFIO devices if all of them
support P2P migration.

Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Tested-by: YangHang Liu <yanghliu@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 43 insertions, 3 deletions

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 48f9c23cbe..71855468fe 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -71,8 +71,12 @@ static const char *mig_state_to_str(enum vfio_device_mig_state state)
         return "STOP_COPY";
     case VFIO_DEVICE_STATE_RESUMING:
         return "RESUMING";
+    case VFIO_DEVICE_STATE_RUNNING_P2P:
+        return "RUNNING_P2P";
     case VFIO_DEVICE_STATE_PRE_COPY:
         return "PRE_COPY";
+    case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+        return "PRE_COPY_P2P";
     default:
         return "UNKNOWN STATE";
     }
@@ -652,6 +656,39 @@ static const SaveVMHandlers savevm_vfio_handlers = {
 
 /* ---------------------------------------------------------------------- */
 
+static void vfio_vmstate_change_prepare(void *opaque, bool running,
+                                        RunState state)
+{
+    VFIODevice *vbasedev = opaque;
+    VFIOMigration *migration = vbasedev->migration;
+    enum vfio_device_mig_state new_state;
+    int ret;
+
+    new_state = migration->device_state == VFIO_DEVICE_STATE_PRE_COPY ?
+                    VFIO_DEVICE_STATE_PRE_COPY_P2P :
+                    VFIO_DEVICE_STATE_RUNNING_P2P;
+
+    /*
+     * If setting the device in new_state fails, the device should be reset.
+     * To do so, use ERROR state as a recover state.
+     */
+    ret = vfio_migration_set_state(vbasedev, new_state,
+                                   VFIO_DEVICE_STATE_ERROR);
+    if (ret) {
+        /*
+         * Migration should be aborted in this case, but vm_state_notify()
+         * currently does not support reporting failures.
+         */
+        if (migrate_get_current()->to_dst_file) {
+            qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
+        }
+    }
+
+    trace_vfio_vmstate_change_prepare(vbasedev->name, running,
+                                      RunState_str(state),
+                                      mig_state_to_str(new_state));
+}
+
 static void vfio_vmstate_change(void *opaque, bool running, RunState state)
 {
     VFIODevice *vbasedev = opaque;
@@ -758,6 +795,7 @@ static int vfio_migration_init(VFIODevice *vbasedev)
     char id[256] = "";
     g_autofree char *path = NULL, *oid = NULL;
     uint64_t mig_flags = 0;
+    VMChangeStateHandler *prepare_cb;
 
     if (!vbasedev->ops->vfio_get_object) {
         return -EINVAL;
@@ -798,9 +836,11 @@ static int vfio_migration_init(VFIODevice *vbasedev)
     register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1, &savevm_vfio_handlers,
                          vbasedev);
 
-    migration->vm_state = qdev_add_vm_change_state_handler(vbasedev->dev,
-                                                           vfio_vmstate_change,
-                                                           vbasedev);
+    prepare_cb = migration->mig_flags & VFIO_MIGRATION_P2P ?
+                     vfio_vmstate_change_prepare :
+                     NULL;
+    migration->vm_state = qdev_add_vm_change_state_handler_full(
+        vbasedev->dev, vfio_vmstate_change, prepare_cb, vbasedev);
     migration->migration_state.notify = vfio_migration_state_notifier;
     add_migration_state_change_notifier(&migration->migration_state);