Merge branch 'use-phylib-for-reset-randomization-and-adjustable-polling'

Oleksij Rempel says:

====================
Use PHYlib for reset randomization and adjustable polling

This patch set tackles a DP83TG720 reset lock issue and improves PHY
polling. Rather than adding a separate polling worker to randomize PHY
resets, I chose to extend the PHYlib framework - which already handles
most of the needed functionality - with adjustable polling. This
approach not only addresses the DP83TG720-specific problem (where
synchronized resets can lock the link) but also lays the groundwork for
optimizing PHY stats polling across all PHY drivers. With generic PHY
stats coming in, we can adjust the polling interval based on hardware
characteristics, such as using longer intervals for PHYs with stable HW
counters or shorter ones for high-speed links prone to counter
overflows.

Patch version changes are tracked in separate patches.
====================

Link: https://patch.msgid.link/20250210082358.200751-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

drivers/net/phy/dp83tg720.c

@@ -4,12 +4,31 @@
  */
 #include <linux/bitfield.h>
 #include <linux/ethtool_netlink.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/phy.h>
+#include <linux/random.h>
 
 #include "open_alliance_helpers.h"
 
+/*
+ * DP83TG720S_POLL_ACTIVE_LINK - Polling interval in milliseconds when the link
+ *				 is active.
+ * DP83TG720S_POLL_NO_LINK_MIN - Minimum polling interval in milliseconds when
+ *				 the link is down.
+ * DP83TG720S_POLL_NO_LINK_MAX - Maximum polling interval in milliseconds when
+ *				 the link is down.
+ *
+ * These values are not documented or officially recommended by the vendor but
+ * were determined through empirical testing. They achieve a good balance in
+ * minimizing the number of reset retries while ensuring reliable link recovery
+ * within a reasonable timeframe.
+ */
+#define DP83TG720S_POLL_ACTIVE_LINK		1000
+#define DP83TG720S_POLL_NO_LINK_MIN		100
+#define DP83TG720S_POLL_NO_LINK_MAX		1000
+
 #define DP83TG720S_PHY_ID			0x2000a284
 
 /* MDIO_MMD_VEND2 registers */
@@ -371,6 +390,13 @@ static int dp83tg720_read_status(struct phy_device *phydev)
 		if (ret)
 			return ret;
 
+		/* Sleep 600ms for PHY stabilization post-reset.
+		 * Empirically chosen value (not documented).
+		 * Helps reduce reset bounces with link partners having similar
+		 * issues.
+		 */
+		msleep(600);
+
 		/* After HW reset we need to restore master/slave configuration.
 		 * genphy_c45_pma_baset1_read_master_slave() call will be done
 		 * by the dp83tg720_config_aneg() function.
@@ -498,6 +524,57 @@ static int dp83tg720_probe(struct phy_device *phydev)
 	return 0;
 }
 
+/**
+ * dp83tg720_get_next_update_time - Determine the next update time for PHY
+ *                                  state
+ * @phydev: Pointer to the phy_device structure
+ *
+ * This function addresses a limitation of the DP83TG720 PHY, which cannot
+ * reliably detect or report a stable link state. To recover from such
+ * scenarios, the PHY must be periodically reset when the link is down. However,
+ * if the link partner also runs Linux with the same driver, synchronized reset
+ * intervals can lead to a deadlock where the link never establishes due to
+ * simultaneous resets on both sides.
+ *
+ * To avoid this, the function implements randomized polling intervals when the
+ * link is down. It ensures that reset intervals are desynchronized by
+ * introducing a random delay between a configured minimum and maximum range.
+ * When the link is up, a fixed polling interval is used to minimize overhead.
+ *
+ * This mechanism guarantees that the link will reestablish within 10 seconds
+ * in the worst-case scenario.
+ *
+ * Return: Time (in jiffies) until the next update event for the PHY state
+ * machine.
+ */
+static unsigned int dp83tg720_get_next_update_time(struct phy_device *phydev)
+{
+	unsigned int next_time_jiffies;
+
+	if (phydev->link) {
+		/* When the link is up, use a fixed 1000ms interval
+		 * (in jiffies)
+		 */
+		next_time_jiffies =
+			msecs_to_jiffies(DP83TG720S_POLL_ACTIVE_LINK);
+	} else {
+		unsigned int min_jiffies, max_jiffies, rand_jiffies;
+
+		/* When the link is down, randomize interval between min/max
+		 * (in jiffies)
+		 */
+		min_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MIN);
+		max_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MAX);
+
+		rand_jiffies = min_jiffies +
+			get_random_u32_below(max_jiffies - min_jiffies + 1);
+		next_time_jiffies = rand_jiffies;
+	}
+
+	/* Ensure the polling time is at least one jiffy */
+	return max(next_time_jiffies, 1U);
+}
+
 static struct phy_driver dp83tg720_driver[] = {
 {
 	PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID),
@@ -516,6 +593,7 @@ static struct phy_driver dp83tg720_driver[] = {
 	.get_link_stats	= dp83tg720_get_link_stats,
 	.get_phy_stats	= dp83tg720_get_phy_stats,
 	.update_stats	= dp83tg720_update_stats,
+	.get_next_update_time = dp83tg720_get_next_update_time,
 
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,

drivers/net/phy/phy.c

@@ -1501,6 +1501,24 @@ void phy_free_interrupt(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_free_interrupt);
 
+/**
+ * phy_get_next_update_time - Determine the next PHY update time
+ * @phydev: Pointer to the phy_device structure
+ *
+ * This function queries the PHY driver to get the time for the next polling
+ * event. If the driver does not implement the callback, a default value is
+ * used.
+ *
+ * Return: The time for the next polling event in jiffies
+ */
+static unsigned int phy_get_next_update_time(struct phy_device *phydev)
+{
+	if (phydev->drv && phydev->drv->get_next_update_time)
+		return phydev->drv->get_next_update_time(phydev);
+
+	return PHY_STATE_TIME;
+}
+
 enum phy_state_work {
 	PHY_STATE_WORK_NONE,
 	PHY_STATE_WORK_ANEG,
@@ -1580,7 +1598,8 @@ static enum phy_state_work _phy_state_machine(struct phy_device *phydev)
 	 * called from phy_disconnect() synchronously.
 	 */
 	if (phy_polling_mode(phydev) && phy_is_started(phydev))
-		phy_queue_state_machine(phydev, PHY_STATE_TIME);
+		phy_queue_state_machine(phydev,
+					phy_get_next_update_time(phydev));
 
 	return state_work;
 }

include/linux/phy.h

@@ -1270,6 +1270,19 @@ struct phy_driver {
 	 */
 	int (*led_polarity_set)(struct phy_device *dev, int index,
 				unsigned long modes);
+
+	/**
+	 * @get_next_update_time: Get the time until the next update event
+	 * @dev: PHY device
+	 *
+	 * Callback to determine the time (in jiffies) until the next
+	 * update event for the PHY state  machine. Allows PHY drivers to
+	 * dynamically adjust polling intervals based on link state or other
+	 * conditions.
+	 *
+	 * Returns the time in jiffies until the next update event.
+	 */
+	unsigned int (*get_next_update_time)(struct phy_device *dev);
 };
 #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d),		\
 				      struct phy_driver, mdiodrv)