Merge branch 'mlxsw-Expose-transceiver-overheat-counter'

Ido Schimmel says:

====================
mlxsw: Expose transceiver overheat counter

Amit says:

An overheated transceiver can be the root cause of various network
problems such as link flapping. Counting the number of times a
transceiver's temperature was higher than its configured threshold can
therefore help in debugging such issues.

This patch set exposes a transceiver overheat counter via ethtool. This
is achieved by configuring the Spectrum ASIC to generate events whenever
a transceiver is overheated. The temperature thresholds are queried from
the transceiver (if available) and set to the default otherwise.

Example:

...
transceiver_overheat: 2

Patch set overview:

Patches #1-#3 add required device registers
Patches #4-#5 add required infrastructure in mlxsw to configure and
count overheat events
Patches #6-#9 gradually add support for the transceiver overheat counter
Patch #10 exposes the transceiver overheat counter via ethtool
====================

Signed-off-by: David S. Miller <[email protected]>

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 */
 };
@@ -133,6 +136,11 @@ bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_res_query_enabled);
 
+bool mlxsw_core_temp_warn_enabled(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver->temp_warn_enabled;
+}
+
 bool
 mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev,
 					  const struct mlxsw_fw_rev *req_rev)
@@ -1943,13 +1951,20 @@ __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)
 		devlink_reload_enable(devlink);
 
 	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 +2041,8 @@ 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 +2846,16 @@ 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

@@ -32,6 +32,8 @@ void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
 bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core);
 
+bool mlxsw_core_temp_warn_enabled(const struct mlxsw_core *mlxsw_core);
+
 bool
 mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev,
 					  const struct mlxsw_fw_rev *req_rev);
@@ -221,6 +223,8 @@ 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);
@@ -371,6 +375,7 @@ struct mlxsw_driver {
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
 	bool fw_fatal_enabled;
+	bool temp_warn_enabled;
 };
 
 int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,