diff mbox series

[net-next,v2,2/2] net: phy: dp83tg720: Add randomized polling intervals for unstable link detection

Message ID 20250205091151.2165678-3-o.rempel@pengutronix.de (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series Use PHYlib for reset randomization and adjustable polling | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 7 of 7 maintainers
netdev/build_clang success Errors and warnings before: 1 this patch: 1
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 81 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-02-05--12-00 (tests: 868)

Commit Message

Oleksij Rempel Feb. 5, 2025, 9:11 a.m. UTC
Address the limitations of the DP83TG720 PHY, which cannot reliably detect or
report a stable link state. To handle this, the PHY must be periodically reset
when the link is down. However, synchronized reset intervals between the PHY
and its link partner can result in a deadlock, preventing the link from
re-establishing.

This change introduces a randomized polling interval when the link is down to
desynchronize resets between link partners.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
---
 drivers/net/phy/dp83tg720.c | 78 +++++++++++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)
diff mbox series

Patch

diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c
index 050f4537d140..0599807de5c7 100644
--- a/drivers/net/phy/dp83tg720.c
+++ b/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_phy_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 milliseconds) until the next update event for the PHY state
+ * machine.
+ */
+static unsigned int dp83tg720_phy_get_next_update_time(struct phy_device *phydev)
+{
+	unsigned int jiffy_ms = jiffies_to_msecs(1); /* Jiffy granularity in ms */
+	unsigned int next_time_ms;
+
+	if (phydev->link) {
+		/* When the link is up, use a fixed 1000ms interval */
+		next_time_ms = DP83TG720S_POLL_ACTIVE_LINK;
+	} else {
+		unsigned int min_jiffies, max_jiffies, rand_jiffies;
+		/* When the link is down, randomize interval between
+		 * configured min/max
+		 */
+
+		/* Convert min and max to jiffies */
+		min_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MIN);
+		max_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MAX);
+
+		/* Randomize in the jiffie range and convert back to ms */
+		rand_jiffies = min_jiffies +
+			get_random_u32_below(max_jiffies - min_jiffies + 1);
+		next_time_ms = jiffies_to_msecs(rand_jiffies);
+	}
+
+	/* Ensure the polling time is at least one jiffy */
+	return max(next_time_ms, jiffy_ms);
+}
+
 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_phy_get_next_update_time,
 
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,