cfg80211: fix management registrations deadlock

Lockdep reports that we may deadlock because we take the RTNL on
the work struct, but flush it under RTNL. Clearly, it's correct.
In practice, this can happen when doing rfkill on an active device.

Fix this by moving the work struct to the wiphy (registered dev)
layer, and iterate over all the wdevs inside there. This then
means we need to track which one of them has work to do, so we
don't update to the driver for all wdevs all the time.

Also fix a locking bug I noticed while working on this - the
registrations list is iterated as if it was an RCU list, but it
isn't handle that way - and we need to lock now for the update
flag anyway, so remove the RCU.

Fixes: 6cd536fe62ef ("cfg80211: change internal management frame registration API")
Reported-by: Markus Theil <markus.theil@tu-ilmenau.de>
Reported-and-tested-by: Kenneth R. Crudup <kenny@panix.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20200604120420.b1dc540a7e26.I55dcca56bb5bdc5d7ad66a36a0b42afd7034d8be@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

1 files changed, 21 insertions, 5 deletions

diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 189334314cba..a6c61a2e6569 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -440,9 +440,15 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
 
 	ASSERT_RTNL();
 
+	spin_lock_bh(&wdev->mgmt_registrations_lock);
+	if (!wdev->mgmt_registrations_need_update) {
+		spin_unlock_bh(&wdev->mgmt_registrations_lock);
+		return;
+	}
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(tmp, &rdev->wiphy.wdev_list, list) {
-		list_for_each_entry_rcu(reg, &tmp->mgmt_registrations, list) {
+		list_for_each_entry(reg, &tmp->mgmt_registrations, list) {
 			u32 mask = BIT(le16_to_cpu(reg->frame_type) >> 4);
 			u32 mcast_mask = 0;
 
@@ -460,16 +466,23 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
 	}
 	rcu_read_unlock();
 
+	wdev->mgmt_registrations_need_update = 0;
+	spin_unlock_bh(&wdev->mgmt_registrations_lock);
+
 	rdev_update_mgmt_frame_registrations(rdev, wdev, &upd);
 }
 
 void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk)
 {
-	struct wireless_dev *wdev = container_of(wk, struct wireless_dev,
-						 mgmt_registrations_update_wk);
+	struct cfg80211_registered_device *rdev;
+	struct wireless_dev *wdev;
+
+	rdev = container_of(wk, struct cfg80211_registered_device,
+			    mgmt_registrations_update_wk);
 
 	rtnl_lock();
-	cfg80211_mgmt_registrations_update(wdev);
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list)
+		cfg80211_mgmt_registrations_update(wdev);
 	rtnl_unlock();
 }
 
@@ -557,6 +570,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
 		nreg->multicast_rx = multicast_rx;
 		list_add(&nreg->list, &wdev->mgmt_registrations);
 	}
+	wdev->mgmt_registrations_need_update = 1;
 	spin_unlock_bh(&wdev->mgmt_registrations_lock);
 
 	cfg80211_mgmt_registrations_update(wdev);
@@ -585,7 +599,8 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
 		list_del(&reg->list);
 		kfree(reg);
 
-		schedule_work(&wdev->mgmt_registrations_update_wk);
+		wdev->mgmt_registrations_need_update = 1;
+		schedule_work(&rdev->mgmt_registrations_update_wk);
 	}
 
 	spin_unlock_bh(&wdev->mgmt_registrations_lock);
@@ -608,6 +623,7 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev)
 		list_del(&reg->list);
 		kfree(reg);
 	}
+	wdev->mgmt_registrations_need_update = 1;
 	spin_unlock_bh(&wdev->mgmt_registrations_lock);
 
 	cfg80211_mgmt_registrations_update(wdev);