diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index decd30c1e290..62a5f0889583 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -330,6 +330,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -1109,6 +1110,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1128,6 +1131,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	}
 
 	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	spin_unlock(&sta->ps_lock);
 
 	/* This station just woke up and isn't aware of our SMPS state */
 	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d77ff7090630..d3a6d8208f2f 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -267,6 +267,7 @@ struct ieee80211_tx_latency_stat {
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -356,10 +357,8 @@ struct sta_info {
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 97a02d3f7d87..4080c615636f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -478,6 +478,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -492,6 +506,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,