[PATCH] wifi: cfg80211: avoid holding rtnl_mutex across all cfg80211_leave() calls

[Ömer Mete Kaya]

reg_check_chans_work() holds rtnl_mutex for the entire duration of
iterating over all registered devices and calling cfg80211_leave() on
each invalid wdev. cfg80211_leave() can be slow (disconnect, stop AP,
leave mesh), causing rtnl_mutex starvation when many wireless interfaces
are present. This results in tasks waiting for rtnl_mutex for longer
than hung_task_timeout_secs:

  INFO: task hung in inet_rtm_newaddr
  INFO: task hung in inet6_rtm_newaddr
  INFO: task hung in nsim_destroy
  INFO: task hung in tun_chr_close
  INFO: task hung in switchdev_deferred_process_work

Fix by taking a snapshot of cfg80211_rdev_list under RCU, holding a
device reference (get_device/put_device) to prevent freeing, then
acquiring rtnl per-device so other rtnl waiters get a chance to run
between devices. After acquiring rtnl, wiphy.registered is checked to
skip any device that was unregistered in the meantime.

Fixes: f7e60032c661 ("wifi: cfg80211: fix locking in regulatory disconnect")
Reported-by: syzbot+adeb8550754921fece20@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=adeb8550754921fece20
Reported-by: syzbot+101224300649c3eb8af4@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=101224300649c3eb8af4
Reported-by: syzbot+8141dcbd23a8f857798a@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=8141dcbd23a8f857798a
Reported-by: syzbot+b0ae8f1abf7d891e0426@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=b0ae8f1abf7d891e0426
Reported-by: syzbot+d6bbe0f5705cb8a5aa2b@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://syzkaller.appspot.com/bug?extid=d6bbe0f5705cb8a5aa2b
Signed-off-by: Ömer Mete Kaya <omermetekaya0@xxxxxxxxx>
---
 net/wireless/reg.c | 44 +++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 39 insertions(+), 5 deletions(-)

diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index a8336baf85dc..7a3f1e470e14 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2463,15 +2463,49 @@ static void reg_leave_invalid_chans(struct wiphy *wiphy)
 
 static void reg_check_chans_work(struct work_struct *work)
 {
-	struct cfg80211_registered_device *rdev;
+	struct cfg80211_registered_device *rdev, **snap;
+	int i, n = 0;
 
 	pr_debug("Verifying active interfaces after reg change\n");
-	rtnl_lock();
 
-	for_each_rdev(rdev)
-		reg_leave_invalid_chans(&rdev->wiphy);
+	/*
+	 * Snapshot rdev pointers under RCU with a device reference so they
+	 * cannot be freed between per-device rtnl acquisitions. Using a
+	 * per-device rtnl_lock() instead of holding it across all devices
+	 * avoids starving other rtnl waiters when cfg80211_leave() is slow.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list)
+		n++;
+	rcu_read_unlock();
 
-	rtnl_unlock();
+	if (!n)
+		return;
+
+	snap = kmalloc_array(n, sizeof(*snap), GFP_KERNEL);
+	if (!snap)
+		return;
+
+	i = 0;
+	rcu_read_lock();
+	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
+		if (i >= n)
+			break;
+		get_device(&rdev->wiphy.dev);
+		snap[i++] = rdev;
+	}
+	rcu_read_unlock();
+	n = i;
+
+	for (i = 0; i < n; i++) {
+		rtnl_lock();
+		if (snap[i]->wiphy.registered)
+			reg_leave_invalid_chans(&snap[i]->wiphy);
+		rtnl_unlock();
+		put_device(&snap[i]->wiphy.dev);
+	}
+
+	kfree(snap);
 }
 
 void reg_check_channels(void)
-- 
2.55.0