vdpa/mlx5: Add mkey leak detection

Track allocated mrs in a list and show warning when leaks are detected
on device free or reset.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-9-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 1a0d27b..50aac8f 100644 (file)
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -37,6 +37,7 @@ struct mlx5_vdpa_mr {
        bool user_mr;
 
        refcount_t refcount;
+       struct list_head mr_list;
 };
 
 struct mlx5_vdpa_resources {
@@ -95,6 +96,7 @@ struct mlx5_vdpa_dev {
        u32 generation;
 
        struct mlx5_vdpa_mr *mr[MLX5_VDPA_NUM_AS];
+       struct list_head mr_list_head;
        /* serialize mr access */
        struct mutex mr_mtx;
        struct mlx5_control_vq cvq;

diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index c7dc891..4758914 100644 (file)
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -508,6 +508,8 @@ static void _mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_
 
        vhost_iotlb_free(mr->iotlb);
 
+       list_del(&mr->mr_list);
+
        kfree(mr);
 }
 
@@ -560,12 +562,31 @@ void mlx5_vdpa_update_mr(struct mlx5_vdpa_dev *mvdev,
        mutex_unlock(&mvdev->mr_mtx);
 }
 
+static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev)
+{
+       struct mlx5_vdpa_mr *mr;
+
+       mutex_lock(&mvdev->mr_mtx);
+
+       list_for_each_entry(mr, &mvdev->mr_list_head, mr_list) {
+
+               mlx5_vdpa_warn(mvdev, "mkey still alive after resource delete: "
+                                     "mr: %p, mkey: 0x%x, refcount: %u\n",
+                                      mr, mr->mkey, refcount_read(&mr->refcount));
+       }
+
+       mutex_unlock(&mvdev->mr_mtx);
+
+}
+
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
        for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
                mlx5_vdpa_update_mr(mvdev, NULL, i);
 
        prune_iotlb(mvdev->cvq.iotlb);
+
+       mlx5_vdpa_show_mr_leaks(mvdev);
 }
 
 static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
@@ -592,6 +613,8 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
        if (err)
                goto err_iotlb;
 
+       list_add_tail(&mr->mr_list, &mvdev->mr_list_head);
+
        return 0;
 
 err_iotlb:

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 133cbb6..778821b 100644 (file)
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -3722,6 +3722,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
        if (err)
                goto err_mpfs;
 
+       INIT_LIST_HEAD(&mvdev->mr_list_head);
+
        if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
                err = mlx5_vdpa_create_dma_mr(mvdev);
                if (err)