[PATCH net-next V2 12/13] net/mlx5e: Disable data direct on data direct device unbind

[Tariq Toukan <tariqt@nvidia.com>]

From: Dragos Tatulea <dtatulea@nvidia.com>

To prevent invalid accesses after the data direct device is unbound,
stop the netdev and drop the providers using the unbound DMA device. To
prevent further use disable the private flag.

Also release the providers during suspend because the notifier
is disabled at that point and a data direct device unbind would
go unnoticed. This would result in dangling references to the
unbound DMA device.

FW reset, devlink reload and health recovery are not affected: they
unregister the netdev, which releases the memory providers and dmabuf
bindings.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/data_direct.c |  4 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 67 ++++++++++++++++++-
 2 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c b/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
index 7db94b8a5b79..246a03f44afd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
@@ -198,9 +198,11 @@ static void mlx5_data_direct_bind(struct mlx5_data_direct_registration *reg,
 static void
 mlx5_data_direct_do_unbind(struct mlx5_data_direct_registration *reg)
 {
+	struct mlx5_data_direct_dev *dev = reg->dd.dev;
+
 	WRITE_ONCE(reg->dd.dev, NULL);
 	blocking_notifier_call_chain(&reg->users, MLX5_DATA_DIRECT_UNBIND,
-				     NULL);
+				     dev);
 }
 
 int mlx5_data_direct_init(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ebd41f24330d..63d91ef0dda8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -6170,9 +6170,53 @@ static int mlx5e_data_direct_event(struct notifier_block *nb,
 {
 	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv,
 					       data_direct_nb);
+	struct mlx5_data_direct_dev *dd_dev = data;
+	struct net_device *netdev = priv->netdev;
+	struct mlx5e_params new_params;
+	bool enabled, reopen;
+	int err;
+
+	if (action != MLX5_DATA_DIRECT_UNBIND)
+		return NOTIFY_DONE;
+
+	rtnl_lock();
+	netdev_lock(netdev);
+
+	mutex_lock(&priv->state_lock);
+	enabled = MLX5E_GET_PFLAG(&priv->channels.params,
+				  MLX5E_PFLAG_DATA_DIRECT);
+	mutex_unlock(&priv->state_lock);
+	if (!enabled)
+		goto out;
+
+	reopen = netif_running(netdev);
+	netif_close(netdev);
+
+	err = netdev_unbind_dma_dev(netdev, dd_dev->device);
+	if (WARN_ON_ONCE(err)) {
+		netdev_err(netdev, "Failed to unbind dma device, won't reopen netdev, err=%d\n",
+			   err);
+		goto out;
+	}
+
+	mutex_lock(&priv->state_lock);
+	new_params = priv->channels.params;
+	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_DATA_DIRECT, false);
+	mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, false);
+	mutex_unlock(&priv->state_lock);
+
+	netdev_info(netdev, "data_direct device unbound, disabled data_direct\n");
 
-	if (action == MLX5_DATA_DIRECT_UNBIND)
-		mlx5_core_dbg(priv->mdev, "data direct device unbound\n");
+	if (reopen) {
+		err = netif_open(netdev, NULL);
+		if (err)
+			netdev_err(netdev, "Failed to reopen after data_direct unbind, err=%d\n",
+				   err);
+	}
+
+out:
+	netdev_unlock(netdev);
+	rtnl_unlock();
 
 	return NOTIFY_OK;
 }
@@ -6407,6 +6451,24 @@ static int mlx5e_nic_enable(struct mlx5e_priv *priv)
 	return err;
 }
 
+static void mlx5e_data_direct_unbind_dev(struct mlx5e_priv *priv)
+{
+	struct mlx5_data_direct_dev *dd_dev;
+	bool enabled;
+
+	dd_dev = mlx5_data_direct_get_dev(priv->mdev->data_direct);
+	if (!dd_dev)
+		return;
+
+	mutex_lock(&priv->state_lock);
+	enabled = MLX5E_GET_PFLAG(&priv->channels.params,
+				  MLX5E_PFLAG_DATA_DIRECT);
+	mutex_unlock(&priv->state_lock);
+	if (enabled)
+		WARN_ON_ONCE(netdev_unbind_dma_dev(priv->netdev,
+						   dd_dev->device));
+}
+
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -6424,6 +6486,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_close_trap(priv->en_trap);
 		priv->en_trap = NULL;
 	}
+	mlx5e_data_direct_unbind_dev(priv);
 	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
-- 
2.44.0