net: hibmcge: fix multiple phy_stop() issue

After detecting the np_link_fail exception,
the driver attempts to fix the exception by
using phy_stop() and phy_start() in the scheduled task.

However, hbg_fix_np_link_fail() and .ndo_stop()
may be concurrently executed. As a result,
phy_stop() is executed twice, and the following Calltrace occurs:

 hibmcge 0000:84:00.2 enp132s0f2: Link is Down
 hibmcge 0000:84:00.2: failed to link between MAC and PHY, try to fix...
 ------------[ cut here ]------------
 called from state HALTED
 WARNING: CPU: 71 PID: 23391 at drivers/net/phy/phy.c:1503 phy_stop...
 ...
 pc : phy_stop+0x138/0x180
 lr : phy_stop+0x138/0x180
 sp : ffff8000c76bbd40
 x29: ffff8000c76bbd40 x28: 0000000000000000 x27: 0000000000000000
 x26: ffff2020047358c0 x25: ffff202004735940 x24: ffff20200000e405
 x23: ffff2020060e5178 x22: ffff2020060e4000 x21: ffff2020060e49c0
 x20: ffff2020060e5170 x19: ffff20202538e000 x18: 0000000000000020
 x17: 0000000000000000 x16: ffffcede02e28f40 x15: ffffffffffffffff
 x14: 0000000000000000 x13: 205d313933333254 x12: 5b5d393430303233
 x11: ffffcede04555958 x10: ffffcede04495918 x9 : ffffcede0274fee0
 x8 : 00000000000bffe8 x7 : c0000000ffff7fff x6 : 0000000000000001
 x5 : 00000000002bffa8 x4 : 0000000000000000 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff20202e429480
 Call trace:
  phy_stop+0x138/0x180
  hbg_fix_np_link_fail+0x4c/0x90 [hibmcge]
  hbg_service_task+0xfc/0x148 [hibmcge]
  process_one_work+0x180/0x398
  worker_thread+0x210/0x328
  kthread+0xe0/0xf0
  ret_from_fork+0x10/0x20
 ---[ end trace 0000000000000000 ]---

This patch adds the rtnl_lock to hbg_fix_np_link_fail()
to ensure that other operations are not performed concurrently.
In addition, np_link_fail exception can be fixed
only when the PHY is link.

Fixes: e0306637e85d ("net: hibmcge: Add support for mac link exception handling feature")
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250410021327.590362-8-shaojijie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index f29a937ad0879f9ceac8363c2e075d1d00c8c39b..42b0083c9193f23ae04d536484c61a66c274f0a3 100644 (file)
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2024 Hisilicon Limited.
 
 #include <linux/phy.h>
+#include <linux/rtnetlink.h>
 #include "hbg_common.h"
 #include "hbg_hw.h"
 #include "hbg_mdio.h"
@@ -133,12 +134,17 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
 {
        struct device *dev = &priv->pdev->dev;
 
+       rtnl_lock();
+
        if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
                dev_err(dev, "failed to fix the MAC link status\n");
                priv->stats.np_link_fail_cnt = 0;
-               return;
+               goto unlock;
        }
 
+       if (!priv->mac.phydev->link)
+               goto unlock;
+
        priv->stats.np_link_fail_cnt++;
        dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
 
@@ -147,6 +153,9 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
         */
        hbg_phy_stop(priv);
        hbg_phy_start(priv);
+
+unlock:
+       rtnl_unlock();
 }
 
 static void hbg_phy_adjust_link(struct net_device *netdev)