net/mlx5e: kTLS, Fix protection domain in use syndrome when devlink reload

There are DEK objects cached in DEK pool after kTLS is used, and they
are freed only in mlx5e_ktls_cleanup().

mlx5e_destroy_mdev_resources() is called in mlx5e_suspend() to
free mdev resources, including protection domain (PD). However, PD is
still referenced by the cached DEK objects in this case, because
profile->cleanup() (and therefore mlx5e_ktls_cleanup()) is called
after mlx5e_suspend() during devlink reload. So the following FW
syndrome is generated:

 mlx5_cmd_out_err:803:(pid 12948): DEALLOC_PD(0x801) op_mod(0x0) failed,
    status bad resource state(0x9), syndrome (0xef0c8a), err(-22)

To avoid this syndrome, move DEK pool destruction to
mlx5e_ktls_cleanup_tx(), which is called by profile->cleanup_tx(). And
move pool creation to mlx5e_ktls_init_tx() for symmetry.

Fixes: f741db1 ("net/mlx5e: kTLS, Improve connection rate by using fast update encryption key")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Author: Jianbo Liu

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c

@@ -188,7 +188,6 @@ static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls,
 
 int mlx5e_ktls_init(struct mlx5e_priv *priv)
 {
-	struct mlx5_crypto_dek_pool *dek_pool;
 	struct mlx5e_tls *tls;
 
 	if (!mlx5e_is_ktls_device(priv->mdev))
@@ -199,12 +198,6 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv)
 		return -ENOMEM;
 	tls->mdev = priv->mdev;
 
-	dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY);
-	if (IS_ERR(dek_pool)) {
-		kfree(tls);
-		return PTR_ERR(dek_pool);
-	}
-	tls->dek_pool = dek_pool;
 	priv->tls = tls;
 
 	mlx5e_tls_debugfs_init(tls, priv->dfs_root);
@@ -222,7 +215,6 @@ void mlx5e_ktls_cleanup(struct mlx5e_priv *priv)
 	debugfs_remove_recursive(tls->debugfs.dfs);
 	tls->debugfs.dfs = NULL;
 
-	mlx5_crypto_dek_pool_destroy(tls->dek_pool);
 	kfree(priv->tls);
 	priv->tls = NULL;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c

@@ -908,28 +908,51 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls,
 
 int mlx5e_ktls_init_tx(struct mlx5e_priv *priv)
 {
+	struct mlx5_crypto_dek_pool *dek_pool;
 	struct mlx5e_tls *tls = priv->tls;
+	int err;
+
+	if (!mlx5e_is_ktls_device(priv->mdev))
+		return 0;
+
+	/* DEK pool could be used by either or both of TX and RX. But we have to
+	 * put the creation here to avoid syndrome when doing devlink reload.
+	 */
+	dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY);
+	if (IS_ERR(dek_pool))
+		return PTR_ERR(dek_pool);
+	tls->dek_pool = dek_pool;
 
 	if (!mlx5e_is_ktls_tx(priv->mdev))
 		return 0;
 
 	priv->tls->tx_pool = mlx5e_tls_tx_pool_init(priv->mdev, &priv->tls->sw_stats);
-	if (!priv->tls->tx_pool)
-		return -ENOMEM;
+	if (!priv->tls->tx_pool) {
+		err = -ENOMEM;
+		goto err_tx_pool_init;
+	}
 
 	mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs);
 
 	return 0;
+
+err_tx_pool_init:
+	mlx5_crypto_dek_pool_destroy(dek_pool);
+	return err;
 }
 
 void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv)
 {
 	if (!mlx5e_is_ktls_tx(priv->mdev))
-		return;
+		goto dek_pool_destroy;
 
 	debugfs_remove_recursive(priv->tls->debugfs.dfs_tx);
 	priv->tls->debugfs.dfs_tx = NULL;
 
 	mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool);
 	priv->tls->tx_pool = NULL;
+
+dek_pool_destroy:
+	if (mlx5e_is_ktls_device(priv->mdev))
+		mlx5_crypto_dek_pool_destroy(priv->tls->dek_pool);
 }