mac80211: fix station destruction in AP/mesh modes

Unfortunately, commit b22cfcfcae5b, intended to speed up roaming
by avoiding the synchronize_rcu() broke AP/mesh modes as it moved
some code into that work item that will still call into the driver
at a time where it's no longer expected to handle this: after the
AP or mesh has been stopped.

To fix this problem remove the per-station work struct, maintain a
station cleanup list instead and flush this list when stations are
flushed. To keep this patch smaller for stable, do this when the
stations are flushed (sta_info_flush()). This unfortunately brings
back the original roaming delay; I'll fix that again in a separate
patch.

Also, Ben reported that the original commit could sometimes (with
many interfaces) cause long delays when an interface is set down,
due to blocking on flush_workqueue(). Since we now maintain the
cleanup list, this particular change of the original patch can be
reverted.

Cc: stable@vger.kernel.org [3.7]
Reported-by: Ben Greear <greearb@candelatech.com>
Tested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

net/mac80211/ieee80211_i.h

@@ -773,6 +773,10 @@ struct ieee80211_sub_if_data {
 		u32 mntr_flags;
 	} u;
 
+	spinlock_t cleanup_stations_lock;
+	struct list_head cleanup_stations;
+	struct work_struct cleanup_stations_wk;
+
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct {
 		struct dentry *dir;

net/mac80211/iface.c

@@ -868,20 +868,11 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 		cancel_work_sync(&sdata->work);
 		/*
 		 * When we get here, the interface is marked down.
-		 * Call rcu_barrier() to wait both for the RX path
+		 * Call synchronize_rcu() to wait for the RX path
 		 * should it be using the interface and enqueuing
-		 * frames at this very time on another CPU, and
-		 * for the sta free call_rcu callbacks.
+		 * frames at this very time on another CPU.
 		 */
-		rcu_barrier();
-
-		/*
-		 * free_sta_rcu() enqueues a work for the actual
-		 * sta cleanup, so we need to flush it while
-		 * sdata is still valid.
-		 */
-		flush_workqueue(local->workqueue);
-
+		synchronize_rcu();
 		skb_queue_purge(&sdata->skb_queue);
 
 		/*
@@ -1501,6 +1492,15 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 	mutex_unlock(&local->iflist_mtx);
 }
 
+static void ieee80211_cleanup_sdata_stas_wk(struct work_struct *wk)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	sdata = container_of(wk, struct ieee80211_sub_if_data, cleanup_stations_wk);
+
+	ieee80211_cleanup_sdata_stas(sdata);
+}
+
 int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		     struct wireless_dev **new_wdev, enum nl80211_iftype type,
 		     struct vif_params *params)
@@ -1576,6 +1576,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 	INIT_LIST_HEAD(&sdata->key_list);
 
+	spin_lock_init(&sdata->cleanup_stations_lock);
+	INIT_LIST_HEAD(&sdata->cleanup_stations);
+	INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk);
+
 	for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
 		struct ieee80211_supported_band *sband;
 		sband = local->hw.wiphy->bands[i];

net/mac80211/sta_info.c

@@ -91,9 +91,8 @@ static int sta_info_hash_del(struct ieee80211_local *local,
 	return -ENOENT;
 }
 
-static void free_sta_work(struct work_struct *wk)
+static void cleanup_single_sta(struct sta_info *sta)
 {
-	struct sta_info *sta = container_of(wk, struct sta_info, free_sta_wk);
 	int ac, i;
 	struct tid_ampdu_tx *tid_tx;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
@@ -153,11 +152,35 @@ static void free_sta_work(struct work_struct *wk)
 	sta_info_free(local, sta);
 }
 
+void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata)
+{
+	struct sta_info *sta;
+
+	spin_lock_bh(&sdata->cleanup_stations_lock);
+	while (!list_empty(&sdata->cleanup_stations)) {
+		sta = list_first_entry(&sdata->cleanup_stations,
+				       struct sta_info, list);
+		list_del(&sta->list);
+		spin_unlock_bh(&sdata->cleanup_stations_lock);
+
+		cleanup_single_sta(sta);
+
+		spin_lock_bh(&sdata->cleanup_stations_lock);
+	}
+
+	spin_unlock_bh(&sdata->cleanup_stations_lock);
+}
+
 static void free_sta_rcu(struct rcu_head *h)
 {
 	struct sta_info *sta = container_of(h, struct sta_info, rcu_head);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
 
-	ieee80211_queue_work(&sta->local->hw, &sta->free_sta_wk);
+	spin_lock(&sdata->cleanup_stations_lock);
+	list_add_tail(&sta->list, &sdata->cleanup_stations);
+	spin_unlock(&sdata->cleanup_stations_lock);
+
+	ieee80211_queue_work(&sdata->local->hw, &sdata->cleanup_stations_wk);
 }
 
 /* protected by RCU */
@@ -310,7 +333,6 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 
 	spin_lock_init(&sta->lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
-	INIT_WORK(&sta->free_sta_wk, free_sta_work);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
 
@@ -891,6 +913,20 @@ int sta_info_flush(struct ieee80211_local *local,
 	}
 	mutex_unlock(&local->sta_mtx);
 
+	rcu_barrier();
+
+	if (sdata) {
+		ieee80211_cleanup_sdata_stas(sdata);
+		cancel_work_sync(&sdata->cleanup_stations_wk);
+	} else {
+		mutex_lock(&local->iflist_mtx);
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			ieee80211_cleanup_sdata_stas(sdata);
+			cancel_work_sync(&sdata->cleanup_stations_wk);
+		}
+		mutex_unlock(&local->iflist_mtx);
+	}
+
 	return ret;
 }
 

net/mac80211/sta_info.h

@@ -299,7 +299,6 @@ struct sta_info {
 	spinlock_t lock;
 
 	struct work_struct drv_unblock_wk;
-	struct work_struct free_sta_wk;
 
 	u16 listen_interval;
 
@@ -563,4 +562,6 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta);
 void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta);
 void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta);
 
+void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata);
+
 #endif /* STA_INFO_H */