net/mlx5: Cancel recovery work in remove flow

If there is pending delayed work for health recovery it must be canceled
if the device is being unloaded.

Fixes: 05ac2c0b7438 ("net/mlx5: Fix race between PCI error handlers and health work")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 23c12f1..0b49739 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1196,6 +1196,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 {
        int err = 0;
 
+       mlx5_drain_health_wq(dev);
+
        mutex_lock(&dev->intf_state_mutex);
        if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
                dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
@@ -1358,10 +1360,9 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
        mlx5_enter_error_state(dev);
        mlx5_unload_one(dev, priv, false);
-       /* In case of kernel call save the pci state and drain health wq */
+       /* In case of kernel call save the pci state */
        if (state) {
                pci_save_state(pdev);
-               mlx5_drain_health_wq(dev);
                mlx5_pci_disable_device(dev);
        }