vfio: Add an option to get migration data size

Add an option to get migration data size by introducing a new migration
feature named VFIO_DEVICE_FEATURE_MIG_DATA_SIZE.

Upon VFIO_DEVICE_FEATURE_GET the estimated data length that will be
required to complete STOP_COPY is returned.

This option may better enable user space to consider before moving to
STOP_COPY whether it can meet the downtime SLA based on the returned
data.

The patch also includes the implementation for mlx5 and hisi for this
new option to make it feature complete for the existing drivers in this
area.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Longfang Liu <liulongfang@huawei.com>
Link: https://lore.kernel.org/r/20221106174630.25909-2-yishaih@nvidia.comSigned-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c

@@ -957,6 +957,14 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 	return res;
 }
 
+static int
+hisi_acc_vfio_pci_get_data_size(struct vfio_device *vdev,
+				unsigned long *stop_copy_length)
+{
+	*stop_copy_length = sizeof(struct acc_vf_data);
+	return 0;
+}
+
 static int
 hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state *curr_state)
@@ -1213,6 +1221,7 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
 	.migration_set_state = hisi_acc_vfio_pci_set_device_state,
 	.migration_get_state = hisi_acc_vfio_pci_get_device_state,
+	.migration_get_data_size = hisi_acc_vfio_pci_get_data_size,
 };
 
 static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)

drivers/vfio/pci/mlx5/main.c

@@ -512,6 +512,23 @@ mlx5vf_pci_set_device_state(struct vfio_device *vdev,
 	return res;
 }
 
+static int mlx5vf_pci_get_data_size(struct vfio_device *vdev,
+				    unsigned long *stop_copy_length)
+{
+	struct mlx5vf_pci_core_device *mvdev = container_of(
+		vdev, struct mlx5vf_pci_core_device, core_device.vdev);
+	size_t state_size;
+	int ret;
+
+	mutex_lock(&mvdev->state_mutex);
+	ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
+						    &state_size);
+	if (!ret)
+		*stop_copy_length = state_size;
+	mlx5vf_state_mutex_unlock(mvdev);
+	return ret;
+}
+
 static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
 				       enum vfio_device_mig_state *curr_state)
 {
@@ -577,6 +594,7 @@ static void mlx5vf_pci_close_device(struct vfio_device *core_vdev)
 static const struct vfio_migration_ops mlx5vf_pci_mig_ops = {
 	.migration_set_state = mlx5vf_pci_set_device_state,
 	.migration_get_state = mlx5vf_pci_get_device_state,
+	.migration_get_data_size = mlx5vf_pci_get_data_size,
 };
 
 static const struct vfio_log_ops mlx5vf_pci_log_ops = {

drivers/vfio/pci/vfio_pci_core.c

@@ -2127,7 +2127,8 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 
 	if (vdev->vdev.mig_ops) {
 		if (!(vdev->vdev.mig_ops->migration_get_state &&
-		      vdev->vdev.mig_ops->migration_set_state) ||
+		      vdev->vdev.mig_ops->migration_set_state &&
+		      vdev->vdev.mig_ops->migration_get_data_size) ||
 		    !(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY))
 			return -EINVAL;
 	}

drivers/vfio/vfio_main.c

@@ -1242,6 +1242,34 @@ vfio_ioctl_device_feature_mig_device_state(struct vfio_device *device,
 	return 0;
 }
 
+static int
+vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device,
+					      u32 flags, void __user *arg,
+					      size_t argsz)
+{
+	struct vfio_device_feature_mig_data_size data_size = {};
+	unsigned long stop_copy_length;
+	int ret;
+
+	if (!device->mig_ops)
+		return -ENOTTY;
+
+	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
+				 sizeof(data_size));
+	if (ret != 1)
+		return ret;
+
+	ret = device->mig_ops->migration_get_data_size(device, &stop_copy_length);
+	if (ret)
+		return ret;
+
+	data_size.stop_copy_length = stop_copy_length;
+	if (copy_to_user(arg, &data_size, sizeof(data_size)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
 					       u32 flags, void __user *arg,
 					       size_t argsz)
@@ -1469,6 +1497,10 @@ static int vfio_ioctl_device_feature(struct vfio_device *device,
 		return vfio_ioctl_device_feature_logging_report(
 			device, feature.flags, arg->data,
 			feature.argsz - minsz);
+	case VFIO_DEVICE_FEATURE_MIG_DATA_SIZE:
+		return vfio_ioctl_device_feature_migration_data_size(
+			device, feature.flags, arg->data,
+			feature.argsz - minsz);
 	default:
 		if (unlikely(!device->ops->device_feature))
 			return -EINVAL;

include/linux/vfio.h

@@ -107,6 +107,9 @@ struct vfio_device_ops {
  * @migration_get_state: Optional callback to get the migration state for
  *         devices that support migration. It's mandatory for
  *         VFIO_DEVICE_FEATURE_MIGRATION migration support.
+ * @migration_get_data_size: Optional callback to get the estimated data
+ *          length that will be required to complete stop copy. It's mandatory for
+ *          VFIO_DEVICE_FEATURE_MIGRATION migration support.
  */
 struct vfio_migration_ops {
 	struct file *(*migration_set_state)(
@@ -114,6 +117,8 @@ struct vfio_migration_ops {
 		enum vfio_device_mig_state new_state);
 	int (*migration_get_state)(struct vfio_device *device,
 				   enum vfio_device_mig_state *curr_state);
+	int (*migration_get_data_size)(struct vfio_device *device,
+				       unsigned long *stop_copy_length);
 };
 
 /**

include/uapi/linux/vfio.h

@@ -1128,6 +1128,19 @@ struct vfio_device_feature_dma_logging_report {
 
 #define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
 
+/*
+ * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will
+ * be required to complete stop copy.
+ *
+ * Note: Can be called on each device state.
+ */
+
+struct vfio_device_feature_mig_data_size {
+	__aligned_u64 stop_copy_length;
+};
+
+#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**