openwrt/package/kernel/mac80211/patches/300-mac80211-add-an-intermediate-software-queue-implemen.patch

From: Felix Fietkau <nbd@openwrt.org>
Date: Tue, 18 Nov 2014 23:58:51 +0100
Subject: [PATCH] mac80211: add an intermediate software queue implementation

This allows drivers to request per-vif and per-sta-tid queues from which
they can pull frames. This makes it easier to keep the hardware queues
short, and to improve fairness between clients and vifs.

The task of scheduling packet transmission is left up to the driver -
queueing is controlled by mac80211. Drivers can only dequeue packets by
calling ieee80211_tx_dequeue. This makes it possible to add active queue
management later without changing drivers using this code.

This can also be used as a starting point to implement A-MSDU
aggregation in a way that does not add artificially induced latency.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
---

--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -84,6 +84,39 @@
  *
  */
 
+/**
+ * DOC: mac80211 software tx queueing
+ *
+ * mac80211 provides an optional intermediate queueing implementation designed
+ * to allow the driver to keep hardware queues short and provide some fairness
+ * between different stations/interfaces.
+ * In this model, the driver pulls data frames from the mac80211 queue instead
+ * of letting mac80211 push them via drv_tx().
+ * Other frames (e.g. control or management) are still pushed using drv_tx().
+ *
+ * Drivers indicate that they use this model by implementing the .wake_tx_queue
+ * driver operation.
+ *
+ * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with a
+ * single per-vif queue for multicast data frames.
+ *
+ * The driver is expected to initialize its private per-queue data for stations
+ * and interfaces in the .add_interface and .sta_add ops.
+ *
+ * The driver can't access the queue directly. To dequeue a frame, it calls
+ * ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a queue, it
+ * calls the .wake_tx_queue driver op.
+ *
+ * For AP powersave TIM handling, the driver only needs to indicate if it has
+ * buffered packets in the driver specific data structures by calling
+ * ieee80211_sta_set_buffered(). For frames buffered in the ieee80211_txq
+ * struct, mac80211 sets the appropriate TIM PVB bits and calls
+ * .release_buffered_frames().
+ * In that callback the driver is therefore expected to release its own
+ * buffered frames and afterwards also frames from the ieee80211_txq (obtained
+ * via the usual ieee80211_tx_dequeue).
+ */
+
 struct device;
 
 /**
@@ -1246,6 +1279,7 @@ enum ieee80211_vif_flags {
  *	monitor interface (if that is requested.)
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *).
+ * @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
  */
 struct ieee80211_vif {
 	enum nl80211_iftype type;
@@ -1257,6 +1291,8 @@ struct ieee80211_vif {
 	u8 cab_queue;
 	u8 hw_queue[IEEE80211_NUM_ACS];
 
+	struct ieee80211_txq *txq;
+
 	struct ieee80211_chanctx_conf __rcu *chanctx_conf;
 
 	u32 driver_flags;
@@ -1501,6 +1537,7 @@ struct ieee80211_sta_rates {
  * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only
  *	valid if the STA is a TDLS peer in the first place.
  * @mfp: indicates whether the STA uses management frame protection or not.
+ * @txq: per-TID data TX queues (if driver uses the TXQ abstraction)
  */
 struct ieee80211_sta {
 	u32 supp_rates[IEEE80211_NUM_BANDS];
@@ -1519,6 +1556,8 @@ struct ieee80211_sta {
 	bool tdls_initiator;
 	bool mfp;
 
+	struct ieee80211_txq *txq[IEEE80211_NUM_TIDS];
+
 	/* must be last */
 	u8 drv_priv[0] __aligned(sizeof(void *));
 };
@@ -1547,6 +1586,27 @@ struct ieee80211_tx_control {
 };
 
 /**
+ * struct ieee80211_txq - Software intermediate tx queue
+ *
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @sta: station table entry, %NULL for per-vif queue
+ * @tid: the TID for this queue (unused for per-vif queue)
+ * @ac: the AC for this queue
+ *
+ * The driver can obtain packets from this queue by calling
+ * ieee80211_tx_dequeue().
+ */
+struct ieee80211_txq {
+	struct ieee80211_vif *vif;
+	struct ieee80211_sta *sta;
+	u8 tid;
+	u8 ac;
+
+	/* must be last */
+	u8 drv_priv[0] __aligned(sizeof(void *));
+};
+
+/**
  * enum ieee80211_hw_flags - hardware flags
  *
  * These flags are used to indicate hardware capabilities to
@@ -1770,6 +1830,8 @@ enum ieee80211_hw_flags {
  *	within &struct ieee80211_sta.
  * @chanctx_data_size: size (in bytes) of the drv_priv data area
  *	within &struct ieee80211_chanctx_conf.
+ * @txq_data_size: size (in bytes) of the drv_priv data area
+ *	within @struct ieee80211_txq.
  *
  * @max_rates: maximum number of alternate rate retry stages the hw
  *	can handle.
@@ -1818,6 +1880,9 @@ enum ieee80211_hw_flags {
  * @n_cipher_schemes: a size of an array of cipher schemes definitions.
  * @cipher_schemes: a pointer to an array of cipher scheme definitions
  *	supported by HW.
+ *
+ * @txq_ac_max_pending: maximum number of frames per AC pending in all txq
+ *	entries for a vif.
  */
 struct ieee80211_hw {
 	struct ieee80211_conf conf;
@@ -1830,6 +1895,7 @@ struct ieee80211_hw {
 	int vif_data_size;
 	int sta_data_size;
 	int chanctx_data_size;
+	int txq_data_size;
 	u16 queues;
 	u16 max_listen_interval;
 	s8 max_signal;
@@ -1846,6 +1912,7 @@ struct ieee80211_hw {
 	u8 uapsd_max_sp_len;
 	u8 n_cipher_schemes;
 	const struct ieee80211_cipher_scheme *cipher_schemes;
+	int txq_ac_max_pending;
 };
 
 /**
@@ -3007,6 +3074,8 @@ enum ieee80211_reconfig_type {
  *	response template is provided, together with the location of the
  *	switch-timing IE within the template. The skb can only be used within
  *	the function call.
+ *
+ * @wake_tx_queue: Called when new packets have been added to the queue.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -3238,6 +3307,9 @@ struct ieee80211_ops {
 	void (*tdls_recv_channel_switch)(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_tdls_ch_sw_params *params);
+
+	void (*wake_tx_queue)(struct ieee80211_hw *hw,
+			      struct ieee80211_txq *txq);
 };
 
 /**
@@ -5249,4 +5321,15 @@ void ieee80211_unreserve_tid(struct ieee
  */
 size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
 			  const u8 *ids, int n_ids, size_t offset);
+
+/**
+ * ieee80211_tx_dequeue - dequeue a packet from a software tx queue
+ *
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @txq: pointer obtained from station or virtual interface
+ *
+ * Returns the skb if successful, %NULL if no frame was available.
+ */
+struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
+				     struct ieee80211_txq *txq);
 #endif /* MAC80211_H */
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1367,4 +1367,16 @@ drv_tdls_recv_channel_switch(struct ieee
 	trace_drv_return_void(local);
 }
 
+static inline void drv_wake_tx_queue(struct ieee80211_local *local,
+				     struct txq_info *txq)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
+
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_wake_tx_queue(local, sdata, txq);
+	local->ops->wake_tx_queue(&local->hw, &txq->txq);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -809,6 +809,19 @@ struct mac80211_qos_map {
 	struct rcu_head rcu_head;
 };
 
+enum txq_info_flags {
+	IEEE80211_TXQ_STOP,
+	IEEE80211_TXQ_AMPDU,
+};
+
+struct txq_info {
+	struct sk_buff_head queue;
+	unsigned long flags;
+
+	/* keep last! */
+	struct ieee80211_txq txq;
+};
+
 struct ieee80211_sub_if_data {
 	struct list_head list;
 
@@ -853,6 +866,7 @@ struct ieee80211_sub_if_data {
 	bool control_port_no_encrypt;
 	int encrypt_headroom;
 
+	atomic_t txqs_len[IEEE80211_NUM_ACS];
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
 	struct mac80211_qos_map __rcu *qos_map;
 
@@ -1453,6 +1467,10 @@ static inline struct ieee80211_local *hw
 	return container_of(hw, struct ieee80211_local, hw);
 }
 
+static inline struct txq_info *to_txq_info(struct ieee80211_txq *txq)
+{
+	return container_of(txq, struct txq_info, txq);
+}
 
 static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr)
 {
@@ -1905,6 +1923,9 @@ static inline bool ieee80211_can_run_wor
 	return true;
 }
 
+void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
+			     struct sta_info *sta,
+			     struct txq_info *txq, int tid);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -969,6 +969,13 @@ static void ieee80211_do_stop(struct iee
 	}
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
+	if (sdata->vif.txq) {
+		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
+
+		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
+	}
+
 	if (local->open_count == 0)
 		ieee80211_clear_tx_pending(local);
 
@@ -1674,6 +1681,7 @@ int ieee80211_if_add(struct ieee80211_lo
 {
 	struct net_device *ndev = NULL;
 	struct ieee80211_sub_if_data *sdata = NULL;
+	struct txq_info *txqi;
 	int ret, i;
 	int txqs = 1;
 
@@ -1693,10 +1701,18 @@ int ieee80211_if_add(struct ieee80211_lo
 		ieee80211_assign_perm_addr(local, wdev->address, type);
 		memcpy(sdata->vif.addr, wdev->address, ETH_ALEN);
 	} else {
+		int size = ALIGN(sizeof(*sdata) + local->hw.vif_data_size,
+				 sizeof(void *));
+		int txq_size = 0;
+
+		if (local->ops->wake_tx_queue)
+			txq_size += sizeof(struct txq_info) +
+				    local->hw.txq_data_size;
+
 		if (local->hw.queues >= IEEE80211_NUM_ACS)
 			txqs = IEEE80211_NUM_ACS;
 
-		ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size,
+		ndev = alloc_netdev_mqs(size + txq_size,
 					name, NET_NAME_UNKNOWN,
 					ieee80211_if_setup, txqs, 1);
 		if (!ndev)
@@ -1731,6 +1747,11 @@ int ieee80211_if_add(struct ieee80211_lo
 		memcpy(sdata->vif.addr, ndev->dev_addr, ETH_ALEN);
 		memcpy(sdata->name, ndev->name, IFNAMSIZ);
 
+		if (txq_size) {
+			txqi = netdev_priv(ndev) + size;
+			ieee80211_init_tx_queue(sdata, NULL, txqi, 0);
+		}
+
 		sdata->dev = ndev;
 	}
 
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1019,6 +1019,9 @@ int ieee80211_register_hw(struct ieee802
 
 	local->dynamic_ps_forced_timeout = -1;
 
+	if (!local->hw.txq_ac_max_pending)
+		local->hw.txq_ac_max_pending = 64;
+
 	result = ieee80211_wep_init(local);
 	if (result < 0)
 		wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n",
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -118,6 +118,16 @@ static void __cleanup_single_sta(struct 
 		atomic_dec(&ps->num_sta_ps);
 	}
 
+	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]);
+			int n = skb_queue_len(&txqi->queue);
+
+			ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+			atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]);
+		}
+	}
+
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]);
 		ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]);
@@ -234,6 +244,8 @@ void sta_info_free(struct ieee80211_loca
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
 	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
@@ -285,11 +297,12 @@ struct sta_info *sta_info_alloc(struct i
 				const u8 *addr, gfp_t gfp)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_hw *hw = &local->hw;
 	struct sta_info *sta;
 	struct timespec uptime;
 	int i;
 
-	sta = kzalloc(sizeof(*sta) + local->hw.sta_data_size, gfp);
+	sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
 	if (!sta)
 		return NULL;
 
@@ -321,11 +334,25 @@ struct sta_info *sta_info_alloc(struct i
 	for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++)
 		ewma_init(&sta->chain_signal_avg[i], 1024, 8);
 
-	if (sta_prepare_rate_control(local, sta, gfp)) {
-		kfree(sta);
-		return NULL;
+	if (local->ops->wake_tx_queue) {
+		void *txq_data;
+		int size = sizeof(struct txq_info) +
+			   ALIGN(hw->txq_data_size, sizeof(void *));
+
+		txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp);
+		if (!txq_data)
+			goto free;
+
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txq = txq_data + i * size;
+
+			ieee80211_init_tx_queue(sdata, sta, txq, i);
+		}
 	}
 
+	if (sta_prepare_rate_control(local, sta, gfp))
+		goto free_txq;
+
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		/*
 		 * timer_to_tid must be initialized with identity mapping
@@ -346,7 +373,7 @@ struct sta_info *sta_info_alloc(struct i
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
 		struct ieee80211_supported_band *sband =
-			local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)];
+			hw->wiphy->bands[ieee80211_get_sdata_band(sdata)];
 		u8 smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >>
 				IEEE80211_HT_CAP_SM_PS_SHIFT;
 		/*
@@ -371,6 +398,13 @@ struct sta_info *sta_info_alloc(struct i
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
 
 	return sta;
+
+free_txq:
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
+free:
+	kfree(sta);
+	return NULL;
 }
 
 static int sta_info_insert_check(struct sta_info *sta)
@@ -640,6 +674,8 @@ static void __sta_info_recalc_tim(struct
 
 		indicate_tim |=
 			sta->driver_buffered_tids & tids;
+		indicate_tim |=
+			sta->txq_buffered_tids & tids;
 	}
 
  done:
@@ -1071,7 +1107,7 @@ void ieee80211_sta_ps_deliver_wakeup(str
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff_head pending;
-	int filtered = 0, buffered = 0, ac;
+	int filtered = 0, buffered = 0, ac, i;
 	unsigned long flags;
 	struct ps_data *ps;
 
@@ -1090,10 +1126,22 @@ void ieee80211_sta_ps_deliver_wakeup(str
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
 	sta->driver_buffered_tids = 0;
+	sta->txq_buffered_tids = 0;
 
 	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
 		drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->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 (!skb_queue_len(&txqi->queue))
+				continue;
+
+			drv_wake_tx_queue(local, txqi);
+		}
+	}
+
 	skb_queue_head_init(&pending);
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
@@ -1275,8 +1323,10 @@ ieee80211_sta_ps_deliver_response(struct
 		/* if we already have frames from software, then we can't also
 		 * release from hardware queues
 		 */
-		if (skb_queue_empty(&frames))
+		if (skb_queue_empty(&frames)) {
 			driver_release_tids |= sta->driver_buffered_tids & tids;
+			driver_release_tids |= sta->txq_buffered_tids & tids;
+		}
 
 		if (driver_release_tids) {
 			/* If the driver has data on more than one TID then
@@ -1447,6 +1497,9 @@ ieee80211_sta_ps_deliver_response(struct
 
 		sta_info_recalc_tim(sta);
 	} else {
+		unsigned long tids = sta->txq_buffered_tids & driver_release_tids;
+		int tid;
+
 		/*
 		 * We need to release a frame that is buffered somewhere in the
 		 * driver ... it'll have to handle that.
@@ -1466,8 +1519,22 @@ ieee80211_sta_ps_deliver_response(struct
 		 * that the TID(s) became empty before returning here from the
 		 * release function.
 		 * Either way, however, when the driver tells us that the TID(s)
-		 * became empty we'll do the TIM recalculation.
+		 * became empty or we find that a txq became empty, we'll do the
+		 * TIM recalculation.
 		 */
+
+		if (!sta->sta.txq[0])
+			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)) || skb_queue_len(&txqi->queue))
+				continue;
+
+			sta_info_recalc_tim(sta);
+			break;
+		}
 	}
 }
 
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -274,6 +274,7 @@ struct sta_ampdu_mlme {
  *	entered power saving state, these are also delivered to
  *	the station when it leaves powersave or polls for frames
  * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on
+ * @txq_buffered_tids: bitmap of TIDs that mac80211 has txq data buffered on
  * @rx_packets: Number of MSDUs received from this STA
  * @rx_bytes: Number of bytes received from this STA
  * @last_rx: time (in jiffies) when last frame was received from this STA
@@ -368,6 +369,7 @@ struct sta_info {
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
+	unsigned long txq_buffered_tids;
 
 	/* Updated from RX path only, no locking requirements */
 	unsigned long rx_packets;
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2312,6 +2312,37 @@ TRACE_EVENT(drv_tdls_recv_channel_switch
 	)
 );
 
+TRACE_EVENT(drv_wake_tx_queue,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct txq_info *txq),
+
+	TP_ARGS(local, sdata, txq),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(u8, ac)
+		__field(u8, tid)
+	),
+
+	TP_fast_assign(
+		struct ieee80211_sta *sta = txq->txq.sta;
+
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->ac = txq->txq.ac;
+		__entry->tid = txq->txq.tid;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " ac:%d tid:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->ac, __entry->tid
+	)
+);
+
 #ifdef CPTCFG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM mac80211_msg
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -776,12 +776,22 @@ ieee80211_tx_h_rate_ctrl(struct ieee8021
 	return TX_CONTINUE;
 }
 
+static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid)
+{
+	u16 *seq = &sta->tid_seq[tid];
+	__le16 ret = cpu_to_le16(*seq);
+
+	/* Increase the sequence number. */
+	*seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ;
+
+	return ret;
+}
+
 static ieee80211_tx_result debug_noinline
 ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
-	u16 *seq;
 	u8 *qc;
 	int tid;
 
@@ -832,13 +842,10 @@ ieee80211_tx_h_sequence(struct ieee80211
 
 	qc = ieee80211_get_qos_ctl(hdr);
 	tid = *qc & IEEE80211_QOS_CTL_TID_MASK;
-	seq = &tx->sta->tid_seq[tid];
 	tx->sta->tx_msdu[tid]++;
 
-	hdr->seq_ctrl = cpu_to_le16(*seq);
-
-	/* Increase the sequence number. */
-	*seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ;
+	if (!tx->sta->sta.txq[0])
+		hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid);
 
 	return TX_CONTINUE;
 }
@@ -1067,7 +1074,7 @@ static bool ieee80211_tx_prep_agg(struct
 		 * nothing -- this aggregation session is being started
 		 * but that might still fail with the driver
 		 */
-	} else {
+	} else if (!tx->sta->sta.txq[tid]) {
 		spin_lock(&tx->sta->lock);
 		/*
 		 * Need to re-check now, because we may get here
@@ -1201,13 +1208,102 @@ ieee80211_tx_prepare(struct ieee80211_su
 	return TX_CONTINUE;
 }
 
+static void ieee80211_drv_tx(struct ieee80211_local *local,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *pubsta,
+			     struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_control control = {
+		.sta = pubsta,
+	};
+	struct ieee80211_txq *txq = NULL;
+	struct txq_info *txqi;
+	u8 ac;
+
+	if (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)
+		goto tx_normal;
+
+	if (!ieee80211_is_data(hdr->frame_control))
+		goto tx_normal;
+
+	if (pubsta) {
+		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+
+		txq = pubsta->txq[tid];
+	} else if (vif) {
+		txq = vif->txq;
+	}
+
+	if (!txq)
+		goto tx_normal;
+
+	ac = txq->ac;
+	txqi = to_txq_info(txq);
+	atomic_inc(&sdata->txqs_len[ac]);
+	if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending)
+		netif_stop_subqueue(sdata->dev, ac);
+
+	skb_queue_tail(&txqi->queue, skb);
+	drv_wake_tx_queue(local, txqi);
+
+	return;
+
+tx_normal:
+	drv_tx(local, &control, skb);
+}
+
+struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
+				     struct ieee80211_txq *txq)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
+	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
+	struct ieee80211_hdr *hdr;
+	struct sk_buff *skb = NULL;
+	u8 ac = txq->ac;
+
+	spin_lock_bh(&txqi->queue.lock);
+
+	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
+		goto out;
+
+	skb = __skb_dequeue(&txqi->queue);
+	if (!skb)
+		goto out;
+
+	atomic_dec(&sdata->txqs_len[ac]);
+	if (__netif_subqueue_stopped(sdata->dev, ac))
+		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
+
+	hdr = (struct ieee80211_hdr *)skb->data;
+	if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) {
+		struct sta_info *sta = container_of(txq->sta, struct sta_info,
+						    sta);
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+		hdr->seq_ctrl = ieee80211_tx_next_seq(sta, txq->tid);
+		if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
+			info->flags |= IEEE80211_TX_CTL_AMPDU;
+		else
+			info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+	}
+
+out:
+	spin_unlock_bh(&txqi->queue.lock);
+
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_tx_dequeue);
+
 static bool ieee80211_tx_frags(struct ieee80211_local *local,
 			       struct ieee80211_vif *vif,
 			       struct ieee80211_sta *sta,
 			       struct sk_buff_head *skbs,
 			       bool txpending)
 {
-	struct ieee80211_tx_control control;
 	struct sk_buff *skb, *tmp;
 	unsigned long flags;
 
@@ -1265,10 +1361,9 @@ static bool ieee80211_tx_frags(struct ie
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
 		info->control.vif = vif;
-		control.sta = sta;
 
 		__skb_unlink(skb, skbs);
-		drv_tx(local, &control, skb);
+		ieee80211_drv_tx(local, vif, sta, skb);
 	}
 
 	return true;
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -308,6 +308,11 @@ void ieee80211_propagate_queue_wake(stru
 		for (ac = 0; ac < n_acs; ac++) {
 			int ac_queue = sdata->vif.hw_queue[ac];
 
+			if (local->ops->wake_tx_queue &&
+			    (atomic_read(&sdata->txqs_len[ac]) >
+			     local->hw.txq_ac_max_pending))
+				continue;
+
 			if (ac_queue == queue ||
 			    (sdata->vif.cab_queue == queue &&
 			     local->queue_stop_reasons[ac_queue] == 0 &&
@@ -3307,3 +3312,20 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u
 
 	return buf;
 }
+
+void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
+			     struct sta_info *sta,
+			     struct txq_info *txqi, int tid)
+{
+	skb_queue_head_init(&txqi->queue);
+	txqi->txq.vif = &sdata->vif;
+
+	if (sta) {
+		txqi->txq.sta = &sta->sta;
+		sta->sta.txq[tid] = &txqi->txq;
+		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
+	} else {
+		sdata->vif.txq = &txqi->txq;
+		txqi->txq.ac = IEEE80211_AC_BE;
+	}
+}
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1176,6 +1176,7 @@ static void sta_ps_start(struct sta_info
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct ps_data *ps;
+	int tid;
 
 	if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
@@ -1189,6 +1190,18 @@ static void sta_ps_start(struct sta_info
 		drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta);
 	ps_dbg(sdata, "STA %pM aid %d enters power save mode\n",
 	       sta->sta.addr, sta->sta.aid);
+
+	if (!sta->sta.txq[0])
+		return;
+
+	for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
+		struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+
+		if (!skb_queue_len(&txqi->queue))
+			set_bit(tid, &sta->txq_buffered_tids);
+		else
+			clear_bit(tid, &sta->txq_buffered_tids);
+	}
 }
 
 static void sta_ps_end(struct sta_info *sta)
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -188,6 +188,43 @@ ieee80211_wake_queue_agg(struct ieee8021
 	__release(agg_queue);
 }
 
+static void
+ieee80211_agg_stop_txq(struct sta_info *sta, int tid)
+{
+	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct txq_info *txqi;
+
+	if (!txq)
+		return;
+
+	txqi = to_txq_info(txq);
+
+	/* Lock here to protect against further seqno updates on dequeue */
+	spin_lock_bh(&txqi->queue.lock);
+	set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+	spin_unlock_bh(&txqi->queue.lock);
+}
+
+static void
+ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable)
+{
+	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct txq_info *txqi;
+
+	if (!txq)
+		return;
+
+	txqi = to_txq_info(txq);
+
+	if (enable)
+		set_bit(IEEE80211_TXQ_AMPDU, &txqi->flags);
+	else
+		clear_bit(IEEE80211_TXQ_AMPDU, &txqi->flags);
+
+	clear_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+	drv_wake_tx_queue(sta->sdata->local, txqi);
+}
+
 /*
  * splice packets from the STA's pending to the local pending,
  * requires a call to ieee80211_agg_splice_finish later
@@ -247,6 +284,7 @@ static void ieee80211_remove_tid_tx(stru
 	ieee80211_assign_tid_tx(sta, tid, NULL);
 
 	ieee80211_agg_splice_finish(sta->sdata, tid);
+	ieee80211_agg_start_txq(sta, tid, false);
 
 	kfree_rcu(tid_tx, rcu_head);
 }
@@ -418,6 +456,8 @@ void ieee80211_tx_ba_session_handle_star
 	 */
 	clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state);
 
+	ieee80211_agg_stop_txq(sta, tid);
+
 	/*
 	 * Make sure no packets are being processed. This ensures that
 	 * we have a valid starting sequence number and that in-flight
@@ -440,6 +480,8 @@ void ieee80211_tx_ba_session_handle_star
 		ieee80211_agg_splice_finish(sdata, tid);
 		spin_unlock_bh(&sta->lock);
 
+		ieee80211_agg_start_txq(sta, tid, false);
+
 		kfree_rcu(tid_tx, rcu_head);
 		return;
 	}
@@ -666,6 +708,8 @@ static void ieee80211_agg_tx_operational
 	ieee80211_agg_splice_finish(sta->sdata, tid);
 
 	spin_unlock_bh(&sta->lock);
+
+	ieee80211_agg_start_txq(sta, tid, true);
 }
 
 void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid)