Blamed commit converted the untracked dev_hold()/dev_put() calls
in the watchdog code to use the tracked dev_hold_track()/dev_put_track()
(which were later renamed/interfaced to netdev_hold() and netdev_put()).

By introducing dev->watchdog_dev_tracker to store the
reference tracking information without adding synchronization
between netdev_watchdog_up() and dev_watchdog(), it enabled the
race condition where this pointer could be overwritten or freed
concurrently, leading to the list corruption crash syzbot reported:

list_del corruption, ffff888114a18c00->next is NULL
 kernel BUG at lib/list_debug.c:52 !
Oops: invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 1 UID: 0 PID: 91 Comm: kworker/u8:5 Not tainted syzkaller #0 PREEMPT(lazy)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/09/2026
Workqueue: events_unbound linkwatch_event
 RIP: 0010:__list_del_entry_valid_or_report.cold+0x22/0x2a lib/list_debug.c:52
Call Trace:
 <TASK>
  __list_del_entry_valid include/linux/list.h:132 [inline]
  __list_del_entry include/linux/list.h:246 [inline]
  list_move_tail include/linux/list.h:341 [inline]
  ref_tracker_free+0x1a7/0x6c0 lib/ref_tracker.c:329
  netdev_tracker_free include/linux/netdevice.h:4491 [inline]
  netdev_put include/linux/netdevice.h:4508 [inline]
  netdev_put include/linux/netdevice.h:4504 [inline]
  netdev_watchdog_down net/sched/sch_generic.c:600 [inline]
  dev_deactivate_many+0x28c/0xfe0 net/sched/sch_generic.c:1363
  dev_deactivate+0x109/0x1d0 net/sched/sch_generic.c:1397
  linkwatch_do_dev net/core/link_watch.c:184 [inline]
  linkwatch_do_dev+0xd3/0x120 net/core/link_watch.c:166
  __linkwatch_run_queue+0x3a5/0x810 net/core/link_watch.c:240
  linkwatch_event+0x8f/0xc0 net/core/link_watch.c:314
  process_one_work+0xa0e/0x1980 kernel/workqueue.c:3314
  process_scheduled_works kernel/workqueue.c:3397 [inline]
  worker_thread+0x5ef/0xe50 kernel/workqueue.c:3478
  kthread+0x370/0x450 kernel/kthread.c:436
  ret_from_fork+0x69a/0xc80 arch/x86/kernel/process.c:158
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245

This patch has three coordinated parts:

1) Zero tracker on free:
   Modify netdev_tracker_free() to poison the tracker pointer after freeing.
   This helps detect and avoid double frees.

2) Remove netdev_watchdog_up() call from netif_carrier_on():
   This ensures netdev_watchdog_up() is only called from process/BH context
   (via linkwatch workqueue dev_activate()), allowing us to use
   spin_lock_bh() for synchronization.

3) Synchronize watchdog up and watchdog timer:
   Protect netdev_watchdog_up with tx_global_lock.
   Only allocate a new tracker in netdev_watchdog_up() if one is
   not already present.
   In dev_watchdog(), keep the lock held while calling netdev_put()
   to avoid races with concurrent netdev_watchdog_up().
   In dev_watchdog(), ensure we don't release the tracker if the
   timer was rescheduled either by dev_watchdog() itself or concurrently
   by netdev_watchdog_up().

Fixes: f12bf6f3f942 ("net: watchdog: add net device refcount tracker")
Reported-by: syzbot+381d82bbf0253710b35d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6a26b751.c25708ab.1b19ef.0013.GAE@google.com/T/#u (local)
Tested-by: syzbot+3479efbc2821cb2a79f2@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/linux/netdevice.h |  7 ++++++-
 net/sched/sch_generic.c   | 26 +++++++++++++++-----------
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0e1e581efc5ac264259b2f0fdfe41c50a6f47239..fb9f7cee1d29de5367ea902d352296f952525c57 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h

@@ -4488,7 +4488,12 @@ static inline void netdev_tracker_free(struct net_device *dev,
 				       netdevice_tracker *tracker)
 {
 #ifdef CONFIG_NET_DEV_REFCNT_TRACKER
-	ref_tracker_free(&dev->refcnt_tracker, tracker);
+	if (!tracker) {
+		ref_tracker_free(&dev->refcnt_tracker, NULL);
+	} else if (!IS_ERR(*tracker)) {
+		ref_tracker_free(&dev->refcnt_tracker, tracker);
+		*tracker = ERR_PTR(-EEXIST);
+	}
 #endif
 }
 

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a93321db8fd75d30c61e146c290bbc139c37c913..6ca7cec17b3164a481e72368376315d9b9d289cd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c

@@ -568,16 +568,18 @@ static void dev_watchdog(struct timer_list *t)
 				dev->netdev_ops->ndo_tx_timeout(dev, i);
 				netif_unfreeze_queues(dev);
 			}
-			if (!mod_timer(&dev->watchdog_timer,
-				       round_jiffies(oldest_start +
-						     dev->watchdog_timeo)))
-				release = false;
+			mod_timer(&dev->watchdog_timer,
+				  round_jiffies(oldest_start +
+						dev->watchdog_timeo));
+			release = false;
 		}
 	}
-	spin_unlock(&dev->tx_global_lock);
-
+	if (timer_pending(&dev->watchdog_timer))
+		release = false;
 	if (release)
 		netdev_put(dev, &dev->watchdog_dev_tracker);
+
+	spin_unlock(&dev->tx_global_lock);
 }
 
 void netdev_watchdog_up(struct net_device *dev)

@@ -586,10 +588,14 @@ void netdev_watchdog_up(struct net_device *dev)
 		return;
 	if (dev->watchdog_timeo <= 0)
 		dev->watchdog_timeo = 5*HZ;
+	spin_lock_bh(&dev->tx_global_lock);
 	if (!mod_timer(&dev->watchdog_timer,
-		       round_jiffies(jiffies + dev->watchdog_timeo)))
-		netdev_hold(dev, &dev->watchdog_dev_tracker,
-			    GFP_ATOMIC);
+		       round_jiffies(jiffies + dev->watchdog_timeo))) {
+		if (IS_ERR_OR_NULL(dev->watchdog_dev_tracker))
+			netdev_hold(dev, &dev->watchdog_dev_tracker,
+				    GFP_ATOMIC);
+	}
+	spin_unlock_bh(&dev->tx_global_lock);
 }
 EXPORT_SYMBOL_GPL(netdev_watchdog_up);
 

@@ -614,8 +620,6 @@ void netif_carrier_on(struct net_device *dev)
 			return;
 		atomic_inc(&dev->carrier_up_count);
 		linkwatch_fire_event(dev);
-		if (netif_running(dev))
-			netdev_watchdog_up(dev);
 	}
 }
 EXPORT_SYMBOL(netif_carrier_on);

-- 
2.54.0.1032.g2f8565e1d1-goog