1 files changed, 348 insertions, 24 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 3713c45cfa1e..6dd4ae2f45f4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -5,6 +5,7 @@
 #include <linux/err.h>
 #include <linux/ethtool.h>
 #include <linux/sfp.h>
+#include <linux/mutex.h>
 
 #include "core.h"
 #include "core_env.h"
@@ -14,12 +15,15 @@
 struct mlxsw_env_module_info {
 	u64 module_overheat_counter;
 	bool is_overheat;
+	int num_ports_mapped;
+	int num_ports_up;
+	enum ethtool_module_power_mode_policy power_mode_policy;
 };
 
 struct mlxsw_env {
 	struct mlxsw_core *core;
 	u8 module_count;
-	spinlock_t module_info_lock; /* Protects 'module_info'. */
+	struct mutex module_info_lock; /* Protects 'module_info'. */
 	struct mlxsw_env_module_info module_info[];
 };
 
@@ -389,6 +393,205 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module,
 }
 EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page);
 
+static int mlxsw_env_module_reset(struct mlxsw_core *mlxsw_core, u8 module)
+{
+	char pmaos_pl[MLXSW_REG_PMAOS_LEN];
+
+	mlxsw_reg_pmaos_pack(pmaos_pl, module);
+	mlxsw_reg_pmaos_rst_set(pmaos_pl, true);
+
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
+}
+
+int mlxsw_env_reset_module(struct net_device *netdev,
+			   struct mlxsw_core *mlxsw_core, u8 module, u32 *flags)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	u32 req = *flags;
+	int err;
+
+	if (!(req & ETH_RESET_PHY) &&
+	    !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT)))
+		return 0;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	if (mlxsw_env->module_info[module].num_ports_up) {
+		netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (mlxsw_env->module_info[module].num_ports_mapped > 1 &&
+	    !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) {
+		netdev_err(netdev, "Cannot reset module without \"phy-shared\" flag when shared by multiple ports\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = mlxsw_env_module_reset(mlxsw_core, module);
+	if (err) {
+		netdev_err(netdev, "Failed to reset module\n");
+		goto out;
+	}
+
+	*flags &= ~(ETH_RESET_PHY | (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT));
+
+out:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_reset_module);
+
+int
+mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				struct ethtool_module_power_mode_params *params,
+				struct netlink_ext_ack *extack)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	char mcion_pl[MLXSW_REG_MCION_LEN];
+	u32 status_bits;
+	int err;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	params->policy = mlxsw_env->module_info[module].power_mode_policy;
+
+	mlxsw_reg_mcion_pack(mcion_pl, module);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcion), mcion_pl);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to retrieve module's power mode");
+		goto out;
+	}
+
+	status_bits = mlxsw_reg_mcion_module_status_bits_get(mcion_pl);
+	if (!(status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK))
+		goto out;
+
+	if (status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK)
+		params->mode = ETHTOOL_MODULE_POWER_MODE_LOW;
+	else
+		params->mode = ETHTOOL_MODULE_POWER_MODE_HIGH;
+
+out:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_power_mode);
+
+static int mlxsw_env_module_enable_set(struct mlxsw_core *mlxsw_core,
+				       u8 module, bool enable)
+{
+	enum mlxsw_reg_pmaos_admin_status admin_status;
+	char pmaos_pl[MLXSW_REG_PMAOS_LEN];
+
+	mlxsw_reg_pmaos_pack(pmaos_pl, module);
+	admin_status = enable ? MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED :
+				MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED;
+	mlxsw_reg_pmaos_admin_status_set(pmaos_pl, admin_status);
+	mlxsw_reg_pmaos_ase_set(pmaos_pl, true);
+
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
+}
+
+static int mlxsw_env_module_low_power_set(struct mlxsw_core *mlxsw_core,
+					  u8 module, bool low_power)
+{
+	u16 eeprom_override_mask, eeprom_override;
+	char pmmp_pl[MLXSW_REG_PMMP_LEN];
+
+	mlxsw_reg_pmmp_pack(pmmp_pl, module);
+	mlxsw_reg_pmmp_sticky_set(pmmp_pl, true);
+	/* Mask all the bits except low power mode. */
+	eeprom_override_mask = ~MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK;
+	mlxsw_reg_pmmp_eeprom_override_mask_set(pmmp_pl, eeprom_override_mask);
+	eeprom_override = low_power ? MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK :
+				      0;
+	mlxsw_reg_pmmp_eeprom_override_set(pmmp_pl, eeprom_override);
+
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmmp), pmmp_pl);
+}
+
+static int __mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core,
+					     u8 module, bool low_power,
+					     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = mlxsw_env_module_enable_set(mlxsw_core, module, false);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to disable module");
+		return err;
+	}
+
+	err = mlxsw_env_module_low_power_set(mlxsw_core, module, low_power);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set module's power mode");
+		goto err_module_low_power_set;
+	}
+
+	err = mlxsw_env_module_enable_set(mlxsw_core, module, true);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to enable module");
+		goto err_module_enable_set;
+	}
+
+	return 0;
+
+err_module_enable_set:
+	mlxsw_env_module_low_power_set(mlxsw_core, module, !low_power);
+err_module_low_power_set:
+	mlxsw_env_module_enable_set(mlxsw_core, module, true);
+	return err;
+}
+
+int
+mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				enum ethtool_module_power_mode_policy policy,
+				struct netlink_ext_ack *extack)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	bool low_power;
+	int err = 0;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	if (policy != ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH &&
+	    policy != ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported power mode policy");
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	if (mlxsw_env->module_info[module].power_mode_policy == policy)
+		goto out;
+
+	/* If any ports are up, we are already in high power mode. */
+	if (mlxsw_env->module_info[module].num_ports_up)
+		goto out_set_policy;
+
+	low_power = policy == ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO;
+	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, low_power,
+						extack);
+	if (err)
+		goto out;
+
+out_set_policy:
+	mlxsw_env->module_info[module].power_mode_policy = policy;
+out:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_set_module_power_mode);
+
 static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core,
 					    u8 module,
 					    bool *p_has_temp_sensor)
@@ -482,22 +685,32 @@ static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
-static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg,
-				      char *mtwe_pl, void *priv)
+struct mlxsw_env_module_temp_warn_event {
+	struct mlxsw_env *mlxsw_env;
+	char mtwe_pl[MLXSW_REG_MTWE_LEN];
+	struct work_struct work;
+};
+
+static void mlxsw_env_mtwe_event_work(struct work_struct *work)
 {
-	struct mlxsw_env *mlxsw_env = priv;
+	struct mlxsw_env_module_temp_warn_event *event;
+	struct mlxsw_env *mlxsw_env;
 	int i, sensor_warning;
 	bool is_overheat;
 
+	event = container_of(work, struct mlxsw_env_module_temp_warn_event,
+			     work);
+	mlxsw_env = event->mlxsw_env;
+
 	for (i = 0; i < mlxsw_env->module_count; i++) {
 		/* 64-127 of sensor_index are mapped to the port modules
 		 * sequentially (module 0 is mapped to sensor_index 64,
 		 * module 1 to sensor_index 65 and so on)
 		 */
 		sensor_warning =
-			mlxsw_reg_mtwe_sensor_warning_get(mtwe_pl,
+			mlxsw_reg_mtwe_sensor_warning_get(event->mtwe_pl,
 							  i + MLXSW_REG_MTMP_MODULE_INDEX_MIN);
-		spin_lock(&mlxsw_env->module_info_lock);
+		mutex_lock(&mlxsw_env->module_info_lock);
 		is_overheat =
 			mlxsw_env->module_info[i].is_overheat;
 
@@ -507,13 +720,13 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg,
 			 * warning OR current state in "no warning" and MTWE
 			 * does not report warning.
 			 */
-			spin_unlock(&mlxsw_env->module_info_lock);
+			mutex_unlock(&mlxsw_env->module_info_lock);
 			continue;
 		} else if (is_overheat && !sensor_warning) {
 			/* MTWE reports "no warning", turn is_overheat off.
 			 */
 			mlxsw_env->module_info[i].is_overheat = false;
-			spin_unlock(&mlxsw_env->module_info_lock);
+			mutex_unlock(&mlxsw_env->module_info_lock);
 		} else {
 			/* Current state is "no warning" and MTWE reports
 			 * "warning", increase the counter and turn is_overheat
@@ -521,13 +734,32 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg,
 			 */
 			mlxsw_env->module_info[i].is_overheat = true;
 			mlxsw_env->module_info[i].module_overheat_counter++;
-			spin_unlock(&mlxsw_env->module_info_lock);
+			mutex_unlock(&mlxsw_env->module_info_lock);
 		}
 	}
+
+	kfree(event);
+}
+
+static void
+mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl,
+			     void *priv)
+{
+	struct mlxsw_env_module_temp_warn_event *event;
+	struct mlxsw_env *mlxsw_env = priv;
+
+	event = kmalloc(sizeof(*event), GFP_ATOMIC);
+	if (!event)
+		return;
+
+	event->mlxsw_env = mlxsw_env;
+	memcpy(event->mtwe_pl, mtwe_pl, MLXSW_REG_MTWE_LEN);
+	INIT_WORK(&event->work, mlxsw_env_mtwe_event_work);
+	mlxsw_core_schedule_work(&event->work);
 }
 
 static const struct mlxsw_listener mlxsw_env_temp_warn_listener =
-	MLXSW_EVENTL(mlxsw_env_mtwe_event_func, MTWE, MTWE);
+	MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE);
 
 static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core)
 {
@@ -568,9 +800,9 @@ static void mlxsw_env_pmpe_event_work(struct work_struct *work)
 			     work);
 	mlxsw_env = event->mlxsw_env;
 
-	spin_lock_bh(&mlxsw_env->module_info_lock);
+	mutex_lock(&mlxsw_env->module_info_lock);
 	mlxsw_env->module_info[event->module].is_overheat = false;
-	spin_unlock_bh(&mlxsw_env->module_info_lock);
+	mutex_unlock(&mlxsw_env->module_info_lock);
 
 	err = mlxsw_env_module_has_temp_sensor(mlxsw_env->core, event->module,
 					       &has_temp_sensor);
@@ -652,8 +884,10 @@ mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core,
 	for (i = 0; i < module_count; i++) {
 		char pmaos_pl[MLXSW_REG_PMAOS_LEN];
 
-		mlxsw_reg_pmaos_pack(pmaos_pl, i,
-				     MLXSW_REG_PMAOS_E_GENERATE_EVENT);
+		mlxsw_reg_pmaos_pack(pmaos_pl, i);
+		mlxsw_reg_pmaos_e_set(pmaos_pl,
+				      MLXSW_REG_PMAOS_E_GENERATE_EVENT);
+		mlxsw_reg_pmaos_ee_set(pmaos_pl, true);
 		err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
 		if (err)
 			return err;
@@ -667,29 +901,110 @@ mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
 {
 	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);
+	mutex_lock(&mlxsw_env->module_info_lock);
 	*p_counter = mlxsw_env->module_info[module].module_overheat_counter;
-	spin_unlock_bh(&mlxsw_env->module_info_lock);
+	mutex_unlock(&mlxsw_env->module_info_lock);
 
 	return 0;
 }
 EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get);
 
+void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+	mlxsw_env->module_info[module].num_ports_mapped++;
+	mutex_unlock(&mlxsw_env->module_info_lock);
+}
+EXPORT_SYMBOL(mlxsw_env_module_port_map);
+
+void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+	mlxsw_env->module_info[module].num_ports_mapped--;
+	mutex_unlock(&mlxsw_env->module_info_lock);
+}
+EXPORT_SYMBOL(mlxsw_env_module_port_unmap);
+
+int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	int err = 0;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	if (mlxsw_env->module_info[module].power_mode_policy !=
+	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
+		goto out_inc;
+
+	if (mlxsw_env->module_info[module].num_ports_up != 0)
+		goto out_inc;
+
+	/* Transition to high power mode following first port using the module
+	 * being put administratively up.
+	 */
+	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, false,
+						NULL);
+	if (err)
+		goto out_unlock;
+
+out_inc:
+	mlxsw_env->module_info[module].num_ports_up++;
+out_unlock:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_module_port_up);
+
+void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	mlxsw_env->module_info[module].num_ports_up--;
+
+	if (mlxsw_env->module_info[module].power_mode_policy !=
+	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
+		goto out_unlock;
+
+	if (mlxsw_env->module_info[module].num_ports_up != 0)
+		goto out_unlock;
+
+	/* Transition to low power mode following last port using the module
+	 * being put administratively down.
+	 */
+	__mlxsw_env_set_module_power_mode(mlxsw_core, module, true, NULL);
+
+out_unlock:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+}
+EXPORT_SYMBOL(mlxsw_env_module_port_down);
+
 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;
+	int i, err;
 
 	mlxsw_reg_mgpir_pack(mgpir_pl);
 	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl);
@@ -702,7 +1017,14 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
 	if (!env)
 		return -ENOMEM;
 
-	spin_lock_init(&env->module_info_lock);
+	/* Firmware defaults to high power mode policy where modules are
+	 * transitioned to high power mode following plug-in.
+	 */
+	for (i = 0; i < module_count; i++)
+		env->module_info[i].power_mode_policy =
+			ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH;
+
+	mutex_init(&env->module_info_lock);
 	env->core = mlxsw_core;
 	env->module_count = module_count;
 	*p_env = env;
@@ -732,6 +1054,7 @@ err_oper_state_event_enable:
 err_module_plug_event_register:
 	mlxsw_env_temp_warn_event_unregister(env);
 err_temp_warn_event_register:
+	mutex_destroy(&env->module_info_lock);
 	kfree(env);
 	return err;
 }
@@ -742,5 +1065,6 @@ void mlxsw_env_fini(struct mlxsw_env *env)
 	/* Make sure there is no more event work scheduled. */
 	mlxsw_core_flush_owq();
 	mlxsw_env_temp_warn_event_unregister(env);
+	mutex_destroy(&env->module_info_lock);
 	kfree(env);
 }