mlxsw: core: Fix use-after-free when flashing firmware during init

When the switch driver (e.g., mlxsw_spectrum) determines it needs to
flash a new firmware version it resets the ASIC after the flashing
process. The bus driver (e.g., mlxsw_pci) then registers itself again
with mlxsw_core which means (among other things) that the device
registers itself again with the hwmon subsystem again.

Since the device was registered with the hwmon subsystem using
devm_hwmon_device_register_with_groups(), then the old hwmon device
(registered before the flashing) was never unregistered and was
referencing stale data, resulting in a use-after free.

Fix by removing reliance on device managed APIs in mlxsw_hwmon_init().

Fixes: c86d62cc ("mlxsw: spectrum: Reset FW after flash")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/core.c

@@ -1055,6 +1055,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_driver_init:
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
+	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
 	if (!reload)
 		devlink_unregister(devlink);
@@ -1088,6 +1089,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
+	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 	if (!reload)
 		devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);

drivers/net/ethernet/mellanox/mlxsw/core.h

@@ -359,6 +359,10 @@ static inline int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
+static inline void mlxsw_hwmon_fini(struct mlxsw_hwmon *mlxsw_hwmon)
+{
+}
+
 #endif
 
 struct mlxsw_thermal;

drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c

@@ -303,8 +303,7 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	struct device *hwmon_dev;
 	int err;
 
-	mlxsw_hwmon = devm_kzalloc(mlxsw_bus_info->dev, sizeof(*mlxsw_hwmon),
-				   GFP_KERNEL);
+	mlxsw_hwmon = kzalloc(sizeof(*mlxsw_hwmon), GFP_KERNEL);
 	if (!mlxsw_hwmon)
 		return -ENOMEM;
 	mlxsw_hwmon->core = mlxsw_core;
@@ -321,10 +320,9 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_hwmon->groups[0] = &mlxsw_hwmon->group;
 	mlxsw_hwmon->group.attrs = mlxsw_hwmon->attrs;
 
-	hwmon_dev = devm_hwmon_device_register_with_groups(mlxsw_bus_info->dev,
-							   "mlxsw",
-							   mlxsw_hwmon,
-							   mlxsw_hwmon->groups);
+	hwmon_dev = hwmon_device_register_with_groups(mlxsw_bus_info->dev,
+						      "mlxsw", mlxsw_hwmon,
+						      mlxsw_hwmon->groups);
 	if (IS_ERR(hwmon_dev)) {
 		err = PTR_ERR(hwmon_dev);
 		goto err_hwmon_register;
@@ -337,5 +335,12 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 err_hwmon_register:
 err_fans_init:
 err_temp_init:
+	kfree(mlxsw_hwmon);
 	return err;
 }
+
+void mlxsw_hwmon_fini(struct mlxsw_hwmon *mlxsw_hwmon)
+{
+	hwmon_device_unregister(mlxsw_hwmon->hwmon_dev);
+	kfree(mlxsw_hwmon);
+}