mlxsw: core: Add an infrastructure to track transceiver overheat counter

Initialize an array that stores per-module overheat state and a counter
indicating how many times the module was in overheat state.

Export a function to query the counter according to module number.
Will be used later on by the switch driver (i.e., mlxsw_spectrum) to expose
module's overheat counter as part of ethtool statistics.

Initialize mlxsw_env after driver initialization to be able to query
number of modules from MGPIR register.
Signed-off-by: NAmit Cohen <amcohen@nvidia.com>
Signed-off-by: NIdo Schimmel <idosch@nvidia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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

@@ -26,6 +26,7 @@
 #include <trace/events/devlink.h>
 
 #include "core.h"
+#include "core_env.h"
 #include "item.h"
 #include "cmd.h"
 #include "port.h"
@@ -87,6 +88,8 @@ struct mlxsw_core {
 	struct {
 		struct devlink_health_reporter *fw_fatal;
 	} health;
+	struct mlxsw_env *env;
+	bool is_initialized; /* Denotes if core was already initialized. */
 	unsigned long driver_priv[];
 	/* driver_priv has to be always the last item */
 };
@@ -1943,6 +1946,11 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
+	err = mlxsw_env_init(mlxsw_core, &mlxsw_core->env);
+	if (err)
+		goto err_env_init;
+
+	mlxsw_core->is_initialized = true;
 	devlink_params_publish(devlink);
 
 	if (!reload)
@@ -1950,6 +1958,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 
 	return 0;
 
+err_env_init:
+	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
@@ -2026,6 +2036,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	}
 
 	devlink_params_unpublish(devlink);
+	mlxsw_core->is_initialized = false;
+	mlxsw_env_fini(mlxsw_core->env);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 	if (mlxsw_core->driver->fini)
@@ -2829,6 +2841,16 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_port_devlink_port_get);
 
+struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->env;
+}
+
+bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->is_initialized;
+}
+
 int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module)
 {
 	enum mlxsw_reg_pmtm_module_type module_type;

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

@@ -221,6 +221,8 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
 struct devlink_port *
 mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
 				 u8 local_port);
+struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core);
+bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core);
 int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module);
 
 int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);

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

@@ -10,6 +10,18 @@
 #include "item.h"
 #include "reg.h"
 
+struct mlxsw_env_module_info {
+	u64 module_overheat_counter;
+	bool is_overheat;
+};
+
+struct mlxsw_env {
+	struct mlxsw_core *core;
+	u8 module_count;
+	spinlock_t module_info_lock; /* Protects 'module_info'. */
+	struct mlxsw_env_module_info module_info[];
+};
+
 static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
 					  bool *qsfp, bool *cmis)
 {
@@ -293,3 +305,57 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 EXPORT_SYMBOL(mlxsw_env_get_module_eeprom);
+
+int
+mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
+				      u64 *p_counter)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	/* Prevent switch driver from accessing uninitialized data. */
+	if (!mlxsw_core_is_initialized(mlxsw_core)) {
+		*p_counter = 0;
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	spin_lock_bh(&mlxsw_env->module_info_lock);
+	*p_counter = mlxsw_env->module_info[module].module_overheat_counter;
+	spin_unlock_bh(&mlxsw_env->module_info_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get);
+
+int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
+{
+	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+	struct mlxsw_env *env;
+	u8 module_count;
+	int err;
+
+	mlxsw_reg_mgpir_pack(mgpir_pl);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgpir_unpack(mgpir_pl, NULL, NULL, NULL, &module_count);
+
+	env = kzalloc(struct_size(env, module_info, module_count), GFP_KERNEL);
+	if (!env)
+		return -ENOMEM;
+
+	spin_lock_init(&env->module_info_lock);
+	env->core = mlxsw_core;
+	env->module_count = module_count;
+	*p_env = env;
+
+	return 0;
+}
+
+void mlxsw_env_fini(struct mlxsw_env *env)
+{
+	kfree(env);
+}

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

@@ -14,4 +14,10 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev,
 				struct mlxsw_core *mlxsw_core, int module,
 				struct ethtool_eeprom *ee, u8 *data);
 
+int
+mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
+				      u64 *p_counter);
+int mlxsw_env_init(struct mlxsw_core *core, struct mlxsw_env **p_env);
+void mlxsw_env_fini(struct mlxsw_env *env);
+
 #endif