mac80211: Move reorder-sensitive TX handlers to after TXQ dequeue

The TXQ intermediate queues can cause packet reordering when more than
one flow is active to a single station. Since some of the wifi-specific
packet handling (notably sequence number and encryption handling) is
sensitive to re-ordering, things break if they are applied before the
TXQ.

This splits up the TX handlers and fast_xmit logic into two parts: An
early part and a late part. The former is applied before TXQ enqueue,
and the latter after dequeue. The non-TXQ path just applies both parts
at once.

Because fragments shouldn't be split up or reordered, the fragmentation
handler is run after dequeue. Any fragments are then kept in the TXQ and
on subsequent dequeues they take precedence over dequeueing from the FQ
structure.

This approach avoids having to scatter special cases all over the place
for when TXQ is enabled, at the cost of making the fast_xmit and TX
handler code slightly more complex.
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
[fix a few code-style nits, make ieee80211_xmit_fast_finish void,
 remove a useless txq->sta check]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

include/net/mac80211.h

@@ -715,6 +715,7 @@ enum mac80211_tx_info_flags {
  *	frame (PS-Poll or uAPSD).
  * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information
  * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame
+ * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path
  *
  * These flags are used in tx_info->control.flags.
  */
@@ -723,6 +724,7 @@ enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTRL_PS_RESPONSE		= BIT(1),
 	IEEE80211_TX_CTRL_RATE_INJECT		= BIT(2),
 	IEEE80211_TX_CTRL_AMSDU			= BIT(3),
+	IEEE80211_TX_CTRL_FAST_XMIT		= BIT(4),
 };
 
 /*

net/mac80211/ieee80211_i.h

@@ -815,12 +815,14 @@ enum txq_info_flags {
  * @def_flow: used as a fallback flow when a packet destined to @tin hashes to
  *	a fq_flow which is already owned by a different tin
  * @def_cvars: codel vars for @def_flow
+ * @frags: used to keep fragments created after dequeue
  */
 struct txq_info {
 	struct fq_tin tin;
 	struct fq_flow def_flow;
 	struct codel_vars def_cvars;
 	struct codel_stats cstats;
+	struct sk_buff_head frags;
 	unsigned long flags;
 
 	/* keep last! */
@@ -1498,6 +1500,13 @@ static inline struct txq_info *to_txq_info(struct ieee80211_txq *txq)
 	return container_of(txq, struct txq_info, txq);
 }
 
+static inline bool txq_has_queue(struct ieee80211_txq *txq)
+{
+	struct txq_info *txqi = to_txq_info(txq);
+
+	return !(skb_queue_empty(&txqi->frags) && !txqi->tin.backlog_packets);
+}
+
 static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr)
 {
 	return ether_addr_equal(raddr, addr) ||

net/mac80211/rx.c

@@ -1323,9 +1323,7 @@ static void sta_ps_start(struct sta_info *sta)
 		return;
 
 	for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
-		struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
-
-		if (txqi->tin.backlog_packets)
+		if (txq_has_queue(sta->sta.txq[tid]))
 			set_bit(tid, &sta->txq_buffered_tids);
 		else
 			clear_bit(tid, &sta->txq_buffered_tids);

net/mac80211/sta_info.c

@@ -1212,12 +1212,10 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	if (sta->sta.txq[0]) {
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
-			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
-
-			if (!txqi->tin.backlog_packets)
+			if (!txq_has_queue(sta->sta.txq[i]))
 				continue;
 
-			drv_wake_tx_queue(local, txqi);
+			drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i]));
 		}
 	}
 
@@ -1649,9 +1647,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 			return;
 
 		for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
-			struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
-
-			if (!(tids & BIT(tid)) || txqi->tin.backlog_packets)
+			if (!(tids & BIT(tid)) || txq_has_queue(sta->sta.txq[tid]))
 				continue;
 
 			sta_info_recalc_tim(sta);

net/mac80211/util.c

@@ -3441,11 +3441,18 @@ void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
 			     unsigned long *byte_cnt)
 {
 	struct txq_info *txqi = to_txq_info(txq);
+	u32 frag_cnt = 0, frag_bytes = 0;
+	struct sk_buff *skb;
+
+	skb_queue_walk(&txqi->frags, skb) {
+		frag_cnt++;
+		frag_bytes += skb->len;
+	}
 
 	if (frame_cnt)
-		*frame_cnt = txqi->tin.backlog_packets;
+		*frame_cnt = txqi->tin.backlog_packets + frag_cnt;
 
 	if (byte_cnt)
-		*byte_cnt = txqi->tin.backlog_bytes;
+		*byte_cnt = txqi->tin.backlog_bytes + frag_bytes;
 }
 EXPORT_SYMBOL(ieee80211_txq_get_depth);