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.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

3 files changed, 29 insertions, 1 deletions

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 39eeca18a0f7..0c0c0c7f0521 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -958,6 +958,14 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 }
 
 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)
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 457138b92f13..6e9cf2aacc52 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/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 = {
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 9be2d5be5d95..189d4930c276 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/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;
 	}