1 files changed, 570 insertions, 0 deletions

diff --git a/package/kernel/mac80211/patches/300-mac80211-add-an-intermediate-software-queue-implemen.patch b/package/kernel/mac80211/patches/300-mac80211-add-an-intermediate-software-queue-implemen.patch
new file mode 100644
index 0000000000..dbf9737f6d
--- /dev/null
+++ b/package/kernel/mac80211/patches/300-mac80211-add-an-intermediate-software-queue-implemen.patch
@@ -0,0 +1,570 @@
+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
+@@ -1257,6 +1257,8 @@ 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;
+@@ -1519,6 +1521,8 @@ 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 +1551,27 @@ 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, may be NULL for per-vif queue
++ * @tid: the TID for this queue (unset 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 +1795,8 @@ 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 +1845,9 @@ 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 +1860,7 @@ 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 +1877,7 @@ 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 +3039,8 @@ 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 +3272,9 @@ 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 +5286,17 @@ 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 .add_tx_queue() call
++ *
++ * Returns the sjb if successful, ERR_PTR(-EAGAIN) 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 +1367,21 @@ 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;
++
++	if (txq->txq.sta)
++		trace_drv_wake_sta_tx_queue(local, sdata, txq->txq.sta,
++					    txq->txq.tid);
++	else
++		trace_drv_wake_vif_tx_queue(local, sdata);
++
++	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 +809,13 @@ struct mac80211_qos_map {
+ 	struct rcu_head rcu_head;
+ };
+ 
++struct txq_info {
++	struct sk_buff_head queue;
++
++	/* keep last! */
++	struct ieee80211_txq txq;
++};
++
+ struct ieee80211_sub_if_data {
+ 	struct list_head list;
+ 
+@@ -853,6 +860,7 @@ 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;
+ 
+@@ -1905,6 +1913,12 @@ 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_flush_tx_queue(struct ieee80211_local *local,
++			      struct ieee80211_txq *txq);
++
+ 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 +969,9 @@ static void ieee80211_do_stop(struct iee
+ 	}
+ 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+ 
++	if (sdata->vif.txq)
++		ieee80211_flush_tx_queue(local, sdata->vif.txq);
++
+ 	if (local->open_count == 0)
+ 		ieee80211_clear_tx_pending(local);
+ 
+@@ -1773,6 +1776,15 @@ int ieee80211_if_add(struct ieee80211_lo
+ 	ieee80211_setup_sdata(sdata, type);
+ 
+ 	if (ndev) {
++		struct txq_info *txqi = NULL;
++
++		if (local->ops->wake_tx_queue) {
++			txqi = kzalloc(sizeof(*txqi) +
++				      local->hw.txq_data_size, GFP_KERNEL);
++			if (txqi)
++				ieee80211_init_tx_queue(sdata, NULL, txqi, 0);
++		}
++
+ 		if (params) {
+ 			ndev->ieee80211_ptr->use_4addr = params->use_4addr;
+ 			if (type == NL80211_IFTYPE_STATION)
+@@ -1785,6 +1797,7 @@ int ieee80211_if_add(struct ieee80211_lo
+ 
+ 		ret = register_netdevice(ndev);
+ 		if (ret) {
++			kfree(txqi);
+ 			free_netdev(ndev);
+ 			return ret;
+ 		}
+@@ -1802,6 +1815,7 @@ int ieee80211_if_add(struct ieee80211_lo
+ 
+ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
+ {
++	struct txq_info *txqi;
+ 	ASSERT_RTNL();
+ 
+ 	mutex_lock(&sdata->local->iflist_mtx);
+@@ -1810,6 +1824,11 @@ void ieee80211_if_remove(struct ieee8021
+ 
+ 	synchronize_rcu();
+ 
++	if (sdata->vif.txq) {
++		txqi = container_of(sdata->vif.txq, struct txq_info, txq);
++		kfree(txqi);
++	}
++
+ 	if (sdata->dev) {
+ 		unregister_netdevice(sdata->dev);
+ 	} else {
+@@ -1833,6 +1852,7 @@ void ieee80211_sdata_stop(struct ieee802
+ void ieee80211_remove_interfaces(struct ieee80211_local *local)
+ {
+ 	struct ieee80211_sub_if_data *sdata, *tmp;
++	struct txq_info *txqi;
+ 	LIST_HEAD(unreg_list);
+ 	LIST_HEAD(wdev_list);
+ 
+@@ -1851,6 +1871,12 @@ void ieee80211_remove_interfaces(struct 
+ 	list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
+ 		list_del(&sdata->list);
+ 
++		if (sdata->vif.txq) {
++			txqi = container_of(sdata->vif.txq, struct txq_info,
++					   txq);
++			kfree(txqi);
++		}
++
+ 		if (sdata->dev)
+ 			unregister_netdevice_queue(sdata->dev, &unreg_list);
+ 		else
+--- 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 +118,11 @@ static void __cleanup_single_sta(struct 
+ 		atomic_dec(&ps->num_sta_ps);
+ 	}
+ 
++	if (sta->txq) {
++		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
++			ieee80211_flush_tx_queue(local, sta->sta.txq[i]);
++	}
++
+ 	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 +239,7 @@ void sta_info_free(struct ieee80211_loca
+ 
+ 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
+ 
++	kfree(sta->txq);
+ 	kfree(rcu_dereference_raw(sta->sta.rates));
+ 	kfree(sta);
+ }
+@@ -285,11 +291,12 @@ 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 +328,23 @@ 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) {
++		int size = sizeof(struct txq_info) +
++			   ALIGN(hw->txq_data_size, sizeof(void *));
++
++		sta->txq = kcalloc(IEEE80211_NUM_TIDS, size, gfp);
++		if (!sta->txq)
++			goto free;
++
++		for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
++			struct txq_info *txq = sta->txq + 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 +365,7 @@ 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 +390,12 @@ struct sta_info *sta_info_alloc(struct i
+ 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
+ 
+ 	return sta;
++
++free_txq:
++	kfree(sta->txq);
++free:
++	kfree(sta);
++	return NULL;
+ }
+ 
+ static int sta_info_insert_check(struct sta_info *sta)
+--- a/net/mac80211/sta_info.h
++++ b/net/mac80211/sta_info.h
+@@ -368,6 +368,7 @@ 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;
++	struct txq_info *txq;
+ 
+ 	/* Updated from RX path only, no locking requirements */
+ 	unsigned long rx_packets;
+--- a/net/mac80211/trace.h
++++ b/net/mac80211/trace.h
+@@ -2312,6 +2312,40 @@ TRACE_EVENT(drv_tdls_recv_channel_switch
+ 	)
+ );
+ 
++DEFINE_EVENT(local_sdata_evt, drv_wake_vif_tx_queue,
++	TP_PROTO(struct ieee80211_local *local,
++		 struct ieee80211_sub_if_data *sdata),
++	TP_ARGS(local, sdata)
++);
++
++TRACE_EVENT(drv_wake_sta_tx_queue,
++	TP_PROTO(struct ieee80211_local *local,
++		 struct ieee80211_sub_if_data *sdata,
++		 struct ieee80211_sta *sta,
++		 u8 tid),
++
++	TP_ARGS(local, sdata, sta, tid),
++
++	TP_STRUCT__entry(
++		LOCAL_ENTRY
++		VIF_ENTRY
++		STA_ENTRY
++		__field(u8, tid)
++	),
++
++	TP_fast_assign(
++		LOCAL_ASSIGN;
++		VIF_ASSIGN;
++		STA_ASSIGN;
++		__entry->tid = tid;
++	),
++
++	TP_printk(
++		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " tid: 0x%x",
++		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __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
+@@ -1201,13 +1201,76 @@ 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_control control = {
++		.sta = pubsta
++	};
++	struct ieee80211_txq *txq = NULL;
++	struct txq_info *txqi;
++	u8 ac;
++
++	if (ieee80211_is_mgmt(hdr->frame_control) ||
++	    ieee80211_is_ctl(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 = container_of(txq, struct 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 sk_buff *skb;
++	u8 ac = txq->ac;
++
++	skb = skb_dequeue(&txqi->queue);
++	if (!skb)
++		return ERR_PTR(-EAGAIN);
++
++	atomic_dec(&sdata->txqs_len[ac]);
++	if (__netif_subqueue_stopped(sdata->dev, ac))
++		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
++
++	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 +1328,9 @@ 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 +3312,36 @@ 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;
++	}
++}
++
++void ieee80211_flush_tx_queue(struct ieee80211_local *local,
++			      struct ieee80211_txq *txq)
++{
++	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
++	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
++	struct sk_buff *skb;
++	int n = 0;
++
++	while ((skb = skb_dequeue(&txqi->queue)) != NULL) {
++		n++;
++		ieee80211_free_txskb(&local->hw, skb);
++	}
++
++	atomic_sub(n, &sdata->txqs_len[txq->ac]);
++}