Index: ath_hal/ah.c
===================================================================
--- ath_hal/ah.c	(revision 312609)
+++ ath_hal/ah.c	(working copy)
@@ -1415,6 +1415,8 @@
 
 /*
  * Get CCA setting.
+ *
+ * XXX TODO: this may not actually be the same on all chips! Grr!
  */
 int
 ath_hal_getcca(struct ath_hal *ah)
Index: if_ath_tx.c
===================================================================
--- if_ath_tx.c	(revision 312609)
+++ if_ath_tx.c	(working copy)
@@ -3129,7 +3129,21 @@
 		ATH_TID_INSERT_TAIL(atid, bf, bf_list);
 		/* XXX sched? */
 	} else if (ath_tx_ampdu_running(sc, an, tid)) {
-		/* AMPDU running, attempt direct dispatch if possible */
+		/*
+		 * AMPDU running, queue single-frame if the hardware queue
+		 * isn't busy.
+		 *
+		 * If the hardware queue is busy, sending an aggregate frame
+		 * then just hold off so we can queue more aggregate frames.
+		 *
+		 * Otherwise we may end up with single frames leaking through
+		 * because we are dispatching them too quickly.
+		 *
+		 * TODO: maybe we should treat this as two policies - minimise
+		 * latency, or maximise throughput.  Then for BE/BK we can
+		 * maximise throughput, and VO/VI (if AMPDU is enabled!)
+		 * minimise latency.
+		 */
 
 		/*
 		 * Always queue the frame to the tail of the list.
@@ -3138,18 +3152,19 @@
 
 		/*
 		 * If the hardware queue isn't busy, direct dispatch
-		 * the head frame in the list.  Don't schedule the
-		 * TID - let it build some more frames first?
+		 * the head frame in the list.
 		 *
-		 * When running A-MPDU, always just check the hardware
-		 * queue depth against the aggregate frame limit.
-		 * We don't want to burst a large number of single frames
-		 * out to the hardware; we want to aggressively hold back.
+		 * Note: if we're say, configured to do ADDBA but not A-MPDU
+		 * then maybe we want to still queue two non-aggregate frames
+		 * to the hardware.  Again with the per-TID policy
+		 * configuration..)
 		 *
 		 * Otherwise, schedule the TID.
 		 */
 		/* XXX TXQ locking */
-		if (txq->axq_depth + txq->fifo.axq_depth < sc->sc_hwq_limit_aggr) {
+		//if (txq->axq_depth + txq->fifo.axq_depth < sc->sc_hwq_limit_aggr) {
+		if (txq->axq_depth + txq->fifo.axq_depth == 0) {
+
 			bf = ATH_TID_FIRST(atid);
 			ATH_TID_REMOVE(atid, bf, bf_list);