mac80211: add an intermediate software queueing implementation

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

git-svn-id: svn://svn.openwrt.org/openwrt/trunk@43325 3c298f89-4303-0410-b956-a3cf2f4a3e73

1 files changed, 498 insertions, 0 deletions

diff --git a/package/kernel/mac80211/patches/321-mac80211-add-an-intermediate-software-queue-implemen.patch b/package/kernel/mac80211/patches/321-mac80211-add-an-intermediate-software-queue-implemen.patch
new file mode 100644
index 0000000000..ce5d4dcc3e
--- /dev/null
+++ b/package/kernel/mac80211/patches/321-mac80211-add-an-intermediate-software-queue-implemen.patch
@@ -0,0 +1,498 @@
+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
+@@ -1192,6 +1192,8 @@ 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;
+@@ -1448,6 +1450,8 @@ struct ieee80211_sta {
+ 	bool tdls;
+ 	bool tdls_initiator;
+ 
++	struct ieee80211_txq *txq[IEEE80211_NUM_TIDS];
++
+ 	/* must be last */
+ 	u8 drv_priv[0] __aligned(sizeof(void *));
+ };
+@@ -1476,6 +1480,27 @@ 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
+@@ -1698,6 +1723,8 @@ 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.
+@@ -1746,6 +1773,9 @@ 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;
+@@ -1758,6 +1788,7 @@ 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;
+@@ -1774,6 +1805,7 @@ struct ieee80211_hw {
+ 	u8 uapsd_max_sp_len;
+ 	u8 n_cipher_schemes;
+ 	const struct ieee80211_cipher_scheme *cipher_schemes;
++	int txq_ac_max_pending;
+ };
+ 
+ /**
+@@ -2881,6 +2913,8 @@ enum ieee80211_reconfig_type {
+  *
+  * @get_txpower: get current maximum tx power (in dBm) based on configuration
+  *	and hardware limits.
++ *
++ * @wake_tx_queue: Called when new packets have been added to the queue.
+  */
+ struct ieee80211_ops {
+ 	void (*tx)(struct ieee80211_hw *hw,
+@@ -3095,6 +3129,9 @@ struct ieee80211_ops {
+ 	u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
+ 	int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ 			   int *dbm);
++
++	void (*wake_tx_queue)(struct ieee80211_hw *hw,
++			      struct ieee80211_txq *txq);
+ };
+ 
+ /**
+@@ -5038,4 +5075,17 @@ void ieee80211_tdls_oper_request(struct 
+  */
+ 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 0 if successful, -EAGAIN if no frame was available.
++ */
++int ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq,
++			 struct sk_buff **skb);
++
++
+ #endif /* MAC80211_H */
+--- a/net/mac80211/driver-ops.h
++++ b/net/mac80211/driver-ops.h
+@@ -1311,4 +1311,21 @@ static inline int drv_get_txpower(struct
+ 	return ret;
+ }
+ 
++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
+@@ -793,6 +793,13 @@ 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;
+ 
+@@ -837,6 +844,8 @@ struct ieee80211_sub_if_data {
+ 	bool control_port_no_encrypt;
+ 	int encrypt_headroom;
+ 
++	struct txq_info *txq;
++	atomic_t txq_len[IEEE80211_NUM_ACS];
+ 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
+ 	struct mac80211_qos_map __rcu *qos_map;
+ 
+@@ -1868,6 +1877,11 @@ void ieee80211_add_pending_skbs(struct i
+ 				struct sk_buff_head *skbs);
+ void ieee80211_flush_queues(struct ieee80211_local *local,
+ 			    struct ieee80211_sub_if_data *sdata);
++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,
+--- a/net/mac80211/iface.c
++++ b/net/mac80211/iface.c
+@@ -967,6 +967,9 @@ 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 +1776,13 @@ int ieee80211_if_add(struct ieee80211_lo
+ 	/* setup type-dependent data */
+ 	ieee80211_setup_sdata(sdata, type);
+ 
++	if (local->ops->wake_tx_queue) {
++		sdata->txq = kzalloc(sizeof(*sdata->txq) +
++				     local->hw.txq_data_size, GFP_KERNEL);
++		if (sdata->txq)
++			ieee80211_init_tx_queue(sdata, NULL, sdata->txq, 0);
++	}
++
+ 	if (ndev) {
+ 		if (params) {
+ 			ndev->ieee80211_ptr->use_4addr = params->use_4addr;
+--- a/net/mac80211/main.c
++++ b/net/mac80211/main.c
+@@ -1004,6 +1004,9 @@ 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
+@@ -119,6 +119,11 @@ static void __cleanup_single_sta(struct 
+ 		sta_info_recalc_tim(sta);
+ 	}
+ 
++	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]);
+@@ -241,6 +246,8 @@ void sta_info_free(struct ieee80211_loca
+ 		kfree(sta->tx_lat);
+ 	}
+ 
++	kfree(sta->txq);
++
+ 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
+ 
+ 	kfree(rcu_dereference_raw(sta->sta.rates));
+@@ -294,12 +301,13 @@ 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;
+ 	struct ieee80211_tx_latency_bin_ranges *tx_latency;
+ 	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;
+ 
+@@ -357,6 +365,20 @@ 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 (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;
+ 
+@@ -380,7 +402,7 @@ 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;
+ 		/*
+--- a/net/mac80211/sta_info.h
++++ b/net/mac80211/sta_info.h
+@@ -371,6 +371,7 @@ 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;
++	void *txq;
+ 
+ 	/* Updated from RX path only, no locking requirements */
+ 	unsigned long rx_packets;
+--- a/net/mac80211/trace.h
++++ b/net/mac80211/trace.h
+@@ -2201,6 +2201,40 @@ TRACE_EVENT(drv_get_txpower,
+ 	)
+ );
+ 
++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
+--- a/net/mac80211/tx.c
++++ b/net/mac80211/tx.c
+@@ -1198,13 +1198,75 @@ 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 *pubtxq = NULL;
++	struct txq_info *txq;
++	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;
++		pubtxq = pubsta->txq[tid];
++	} else {
++		pubtxq = vif->txq;
++	}
++
++	if (!pubtxq)
++		goto tx_normal;
++
++	ac = pubtxq->ac;
++	txq = container_of(pubtxq, struct txq_info, txq);
++	atomic_inc(&sdata->txq_len[ac]);
++	if (atomic_read(&sdata->txq_len[ac]) >= local->hw.txq_ac_max_pending)
++		netif_stop_subqueue(sdata->dev, ac);
++
++	skb_queue_tail(&txq->queue, skb);
++	drv_wake_tx_queue(local, txq);
++
++	return;
++
++tx_normal:
++	drv_tx(local, &control, skb);
++}
++
++int ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *pubtxq,
++			 struct sk_buff **dest)
++{
++	struct ieee80211_local *local = hw_to_local(hw);
++	struct ieee80211_sub_if_data *sdata = vif_to_sdata(pubtxq->vif);
++	struct txq_info *txq = container_of(pubtxq, struct txq_info, txq);
++	u8 ac = pubtxq->ac;
++
++	*dest = skb_dequeue(&txq->queue);
++	if (!*dest)
++		return -EAGAIN;
++
++	atomic_dec(&sdata->txq_len[ac]);
++	if (__netif_subqueue_stopped(sdata->dev, ac))
++		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
++
++	return 0;
++}
++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;
+ 
+@@ -1262,10 +1324,9 @@ 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->txq_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 &&
+@@ -3182,3 +3187,33 @@ 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 *txq, int tid)
++{
++	skb_queue_head_init(&txq->queue);
++	txq->txq.vif = &sdata->vif;
++
++	if (sta) {
++		txq->txq.sta = &sta->sta;
++		sta->sta.txq[tid] = &txq->txq;
++		txq->txq.ac = ieee802_1d_to_ac[tid & 7];
++	} else {
++		sdata->vif.txq = &txq->txq;
++		txq->txq.ac = IEEE80211_AC_BE;
++	}
++}
++
++void ieee80211_flush_tx_queue(struct ieee80211_local *local,
++			      struct ieee80211_txq *pubtxq)
++{
++	struct txq_info *txq = container_of(pubtxq, struct txq_info, txq);
++	struct ieee80211_sub_if_data *sdata = vif_to_sdata(pubtxq->vif);
++	struct sk_buff *skb;
++
++	while ((skb = skb_dequeue(&txq->queue)) != NULL) {
++		atomic_dec(&sdata->txq_len[pubtxq->ac]);
++		ieee80211_free_txskb(&local->hw, skb);
++	}
++}