[PATCH v5 21/21] net/txgbe: fix temperature track for AML NIC

[Zaiyu Wang]

Previously, temperature tracking for the amlite NIC was handled by
firmware together with the hardware setup. However, the firmware-based
PHY configuration has proven to be unstable.

Re-add the temperature tracking function directly in the driver and
invoke it periodically to ensure the PHY remains calibrated. According
to the hardware recommendation, the tracking sequence should be run at
least every 100 ms to keep temperature drift within 5 °C. Considering
the software and hardware overhead, a 2-second interval is used as a
practical trade-off that still meets stability requirements while
minimizing performance impact.

The periodic tracking is implemented using a timer in the driver, and
the sequence itself is the same as the one originally performed during
link setup.

Fixes: fb6eb170dfa2 ("net/txgbe: add basic link configuration for Amber-Lite")
Cc: stable at dpdk.org

Signed-off-by: Zaiyu Wang <zaiyuwang at trustnetic.com>
---
 drivers/net/txgbe/txgbe_ethdev.c | 44 +++++++++++++++++++++++++++++++-
 drivers/net/txgbe/txgbe_ethdev.h |  1 +
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/drivers/net/txgbe/txgbe_ethdev.c b/drivers/net/txgbe/txgbe_ethdev.c
index 96532a015e..155d8f08ba 100644
--- a/drivers/net/txgbe/txgbe_ethdev.c
+++ b/drivers/net/txgbe/txgbe_ethdev.c
@@ -2011,8 +2011,10 @@ txgbe_dev_start(struct rte_eth_dev *dev)
 	txgbe_filter_restore(dev);
 
 	hw->bp_event_interval = 100 * 1000;
-	if (hw->mac.type == txgbe_mac_aml || hw->mac.type == txgbe_mac_aml40)
+	if (hw->mac.type == txgbe_mac_aml || hw->mac.type == txgbe_mac_aml40) {
 		rte_eal_alarm_set(hw->bp_event_interval, txgbe_dev_e56_check_bp_event, dev);
+		rte_eal_alarm_set(1000 * 1000 * 2, txgbe_dev_check_aml_temp_event, dev);
+	}
 
 	if (tm_conf->root && !tm_conf->committed)
 		PMD_DRV_LOG(WARNING,
@@ -2060,6 +2062,7 @@ txgbe_dev_stop(struct rte_eth_dev *dev)
 
 	if (hw->mac.type == txgbe_mac_aml || hw->mac.type == txgbe_mac_aml40) {
 		rte_eal_alarm_cancel(txgbe_dev_e56_check_bp_event, dev);
+		rte_eal_alarm_cancel(txgbe_dev_check_aml_temp_event, dev);
 		rte_eal_alarm_cancel(txgbe_dev_setup_link_alarm_handler_aml, hw);
 	}
 
@@ -2932,6 +2935,45 @@ txgbe_dev_supported_ptypes_get(struct rte_eth_dev *dev, size_t *no_of_elements)
 	return NULL;
 }
 
+void txgbe_dev_check_aml_temp_event(void *param)
+{
+	struct rte_eth_dev *dev = (struct rte_eth_dev *)param;
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+	uint32_t link_speed = 0, val = 0;
+	s32 status = 0;
+	int temp;
+
+	if (hw == NULL)
+		return;
+
+	status = txgbe_e56_get_temp(hw, &temp);
+	if (status)
+		temp = DEFAULT_TEMP;
+
+	if (!(temp - hw->temperature > 4 ||
+		hw->temperature - temp > 4))
+		goto out;
+
+	hw->temperature = temp;
+	val = rd32(hw, TXGBE_PORT);
+	if (val & TXGBE_AMLITE_LED_LINK_40G)
+		link_speed = TXGBE_LINK_SPEED_40GB_FULL;
+	else if (val & TXGBE_AMLITE_LED_LINK_25G)
+		link_speed = TXGBE_LINK_SPEED_25GB_FULL;
+	else
+		link_speed = TXGBE_LINK_SPEED_10GB_FULL;
+
+	rte_spinlock_lock(&hw->phy_lock);
+	if (hw->mac.type == txgbe_mac_aml)
+		txgbe_temp_track_seq(hw, link_speed);
+	else if (hw->mac.type == txgbe_mac_aml40)
+		txgbe_temp_track_seq_40g(hw, link_speed);
+	rte_spinlock_unlock(&hw->phy_lock);
+
+out:
+	rte_eal_alarm_set(1000 * 1000 * 2, txgbe_dev_check_aml_temp_event, dev);
+}
+
 void txgbe_dev_e56_check_bp_event(void *param)
 {
 	struct rte_eth_dev *dev = (struct rte_eth_dev *)param;
diff --git a/drivers/net/txgbe/txgbe_ethdev.h b/drivers/net/txgbe/txgbe_ethdev.h
index 309db3bfe9..c32c61d8bf 100644
--- a/drivers/net/txgbe/txgbe_ethdev.h
+++ b/drivers/net/txgbe/txgbe_ethdev.h
@@ -747,5 +747,6 @@ void txgbe_vlan_hw_strip_bitmap_set(struct rte_eth_dev *dev,
 		uint16_t queue, bool on);
 void txgbe_config_vlan_strip_on_all_queues(struct rte_eth_dev *dev,
 						  int mask);
+void txgbe_dev_check_aml_temp_event(void *param);
 void txgbe_dev_e56_check_bp_event(void *param);
 #endif /* _TXGBE_ETHDEV_H_ */
-- 
2.21.0.windows.1