net/mlx5: Always drain health in shutdown callback

There is no point in recovery during device shutdown. if health
work started need to wait for it to avoid races and NULL pointer
access.

Hence, drain health WQ on shutdown callback.

Fixes: 1958fc2f ("net/mlx5: SF, Add auxiliary device driver")
Fixes: d2aa060d ("net/mlx5: Cancel health poll before sending panic teardown command")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/20240730061638.1831002-2-tariqt@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -2142,7 +2142,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	/* Panic tear down fw command will stop the PCI bus communication
 	 * with the HCA, so the health poll is no longer needed.
 	 */
-	mlx5_drain_health_wq(dev);
 	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_fast_teardown_hca(dev);
@@ -2177,6 +2176,7 @@ static void shutdown(struct pci_dev *pdev)
 
 	mlx5_core_info(dev, "Shutdown was called\n");
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+	mlx5_drain_health_wq(dev);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev, false);

drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c

@@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 	struct mlx5_core_dev *mdev = sf_dev->mdev;
 
 	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_drain_health_wq(mdev);
 	mlx5_unload_one(mdev, false);
 }