mlxsw: core: Add validation of hardware device types for MGPIR register

When reading the number of gearboxes from the hardware, the driver does
not validate the returned 'device type' field. The driver can therefore
wrongly assume that the queried devices are gearboxes.

On Spectrum-3 systems that support different types of devices, this can
prevent the driver from loading, as it will try to query the
temperature sensors from devices which it assumes are gearboxes and in
fact are not.

For example:
[  218.129230] mlxsw_minimal 2-0048: Reg cmd access status failed (status=7(bad parameter))
[  218.138282] mlxsw_minimal 2-0048: Reg cmd access failed (reg_id=900a(mtmp),type=write)
[  218.147131] mlxsw_minimal 2-0048: Failed to setup temp sensor number 256
[  218.534480] mlxsw_minimal 2-0048: Fail to register core bus
[  218.540714] mlxsw_minimal: probe of 2-0048 failed with error -5

Fix this by validating the 'device type' field.

Fixes: 2e265a8b6c094 ("mlxsw: core: Extend hwmon interface with inter-connect temperature attributes")
Fixes: f14f4e621b1b4 ("mlxsw: core: Extend thermal core with per inter-connect device thermal zones")
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 9bf8da5..3fe878d 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -573,6 +573,7 @@ static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon)
 
 static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon)
 {
+       enum mlxsw_reg_mgpir_device_type device_type;
        int index, max_index, sensor_index;
        char mgpir_pl[MLXSW_REG_MGPIR_LEN];
        char mtmp_pl[MLXSW_REG_MTMP_LEN];
@@ -584,8 +585,9 @@ static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon)
        if (err)
                return err;
 
-       mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, NULL, NULL, NULL);
-       if (!gbox_num)
+       mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, &device_type, NULL, NULL);
+       if (device_type != MLXSW_REG_MGPIR_DEVICE_TYPE_GEARBOX_DIE ||
+           !gbox_num)
                return 0;
 
        index = mlxsw_hwmon->module_sensor_max;

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index c721b17..ce0a683 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -895,8 +895,10 @@ static int
 mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core,
                             struct mlxsw_thermal *thermal)
 {
+       enum mlxsw_reg_mgpir_device_type device_type;
        struct mlxsw_thermal_module *gearbox_tz;
        char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+       u8 gbox_num;
        int i;
        int err;
 
@@ -908,11 +910,13 @@ mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core,
        if (err)
                return err;
 
-       mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL,
+       mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, &device_type, NULL,
                               NULL);
-       if (!thermal->tz_gearbox_num)
+       if (device_type != MLXSW_REG_MGPIR_DEVICE_TYPE_GEARBOX_DIE ||
+           !gbox_num)
                return 0;
 
+       thermal->tz_gearbox_num = gbox_num;
        thermal->tz_gearbox_arr = kcalloc(thermal->tz_gearbox_num,
                                          sizeof(*thermal->tz_gearbox_arr),
                                          GFP_KERNEL);