vdpa/mlx5: implement .reset_map driver op

Since commit 6f5312f ("vdpa/mlx5: Add support for running with
virtio_vdpa"), mlx5_vdpa starts with preallocate 1:1 DMA MR at device
creation time. This 1:1 DMA MR will be implicitly destroyed while the
first .set_map call is invoked, in which case callers like vhost-vdpa
will start to set up custom mappings. When the .reset callback is
invoked, the custom mappings will be cleared and the 1:1 DMA MR will be
re-created.

In order to reduce excessive memory mapping cost in live migration, it
is desirable to decouple the vhost-vdpa IOTLB abstraction from the
virtio device life cycle, i.e. mappings can be kept around intact across
virtio device reset. Leverage the .reset_map callback, which is meant to
destroy the regular MR (including cvq mapping) on the given ASID and
recreate the initial DMA mapping. That way, the device .reset op runs
free from having to maintain and clean up memory mappings by itself.

Additionally, implement .compat_reset to cater for older userspace,
which may wish to see mapping to be cleared during reset.

Co-developed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Message-Id: <1697880319-4937-7-git-send-email-si-wei.liu@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>

Author: siwliu-kernel

drivers/vdpa/mlx5/core/mlx5_vdpa.h

@@ -127,6 +127,7 @@ int mlx5_vdpa_update_cvq_iotlb(struct mlx5_vdpa_dev *mvdev,
 				struct vhost_iotlb *iotlb,
 				unsigned int asid);
 int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev);
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                                         \
 	dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__,     \

drivers/vdpa/mlx5/core/mr.c

@@ -645,3 +645,20 @@ int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev)
 
 	return mlx5_vdpa_update_cvq_iotlb(mvdev, NULL, 0);
 }
+
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+	if (asid >= MLX5_VDPA_NUM_AS)
+		return -EINVAL;
+
+	mlx5_vdpa_destroy_mr(mvdev, mvdev->mr[asid]);
+
+	if (asid == 0 && MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+		if (mlx5_vdpa_create_dma_mr(mvdev))
+			mlx5_vdpa_warn(mvdev, "create DMA MR failed\n");
+	} else {
+		mlx5_vdpa_update_cvq_iotlb(mvdev, NULL, asid);
+	}
+
+	return 0;
+}

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -2876,7 +2876,7 @@ static void init_group_to_asid_map(struct mlx5_vdpa_dev *mvdev)
 		mvdev->group2asid[i] = 0;
 }
 
-static int mlx5_vdpa_reset(struct vdpa_device *vdev)
+static int mlx5_vdpa_compat_reset(struct vdpa_device *vdev, u32 flags)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
@@ -2888,7 +2888,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	unregister_link_notifier(ndev);
 	teardown_driver(ndev);
 	clear_vqs_ready(ndev);
-	mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
+	if (flags & VDPA_RESET_F_CLEAN_MAP)
+		mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
 	ndev->mvdev.status = 0;
 	ndev->mvdev.suspended = false;
 	ndev->cur_num_vqs = 0;
@@ -2899,7 +2900,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	init_group_to_asid_map(mvdev);
 	++mvdev->generation;
 
-	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+	if ((flags & VDPA_RESET_F_CLEAN_MAP) &&
+	    MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
 		if (mlx5_vdpa_create_dma_mr(mvdev))
 			mlx5_vdpa_warn(mvdev, "create MR failed\n");
 	}
@@ -2908,6 +2910,11 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	return 0;
 }
 
+static int mlx5_vdpa_reset(struct vdpa_device *vdev)
+{
+	return mlx5_vdpa_compat_reset(vdev, 0);
+}
+
 static size_t mlx5_vdpa_get_config_size(struct vdpa_device *vdev)
 {
 	return sizeof(struct virtio_net_config);
@@ -2987,6 +2994,18 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
 	return err;
 }
 
+static int mlx5_vdpa_reset_map(struct vdpa_device *vdev, unsigned int asid)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	int err;
+
+	down_write(&ndev->reslock);
+	err = mlx5_vdpa_reset_mr(mvdev, asid);
+	up_write(&ndev->reslock);
+	return err;
+}
+
 static struct device *mlx5_get_vq_dma_dev(struct vdpa_device *vdev, u16 idx)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -3250,11 +3269,13 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_status = mlx5_vdpa_get_status,
 	.set_status = mlx5_vdpa_set_status,
 	.reset = mlx5_vdpa_reset,
+	.compat_reset = mlx5_vdpa_compat_reset,
 	.get_config_size = mlx5_vdpa_get_config_size,
 	.get_config = mlx5_vdpa_get_config,
 	.set_config = mlx5_vdpa_set_config,
 	.get_generation = mlx5_vdpa_get_generation,
 	.set_map = mlx5_vdpa_set_map,
+	.reset_map = mlx5_vdpa_reset_map,
 	.set_group_asid = mlx5_set_group_asid,
 	.get_vq_dma_dev = mlx5_get_vq_dma_dev,
 	.free = mlx5_vdpa_free,