[PATCH ath-next v5 5/9] wifi: ath11k: schedule TXQs from the driver

[Julius Bairaktaris]

The wake_tx_queue handler serves only the txq mac80211 passes it, so
there is no deficit round robin between stations. Run the round in the
driver: walk the access category's active txqs with
ieee80211_next_txq() and drain each through the TCL ring check until the
airtime queue limit binds or the queue empties. A full ring ends the
round, since all txqs of a round share it. Each round holds a
per-category lock, as in ath10k, because mac80211 forbids concurrent
rounds on one category and the next patch also starts rounds from tx
completion. The design was proposed for ath11k in [1].

Link: https://lore.kernel.org/all/20230501130725.7171-1-quic_tamizhr@quicinc.com/ [1]

Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.9.0.1-02146-QCAHKSWPL_SILICONZ-1

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Julius Bairaktaris <julius at bairaktaris.de>
---
 drivers/net/wireless/ath/ath11k/core.h |  5 +++
 drivers/net/wireless/ath/ath11k/mac.c  | 44 +++++++++++++++++++++++---
 2 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index a0d725923ef24..40895d276de5f 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -709,6 +709,11 @@ struct ath11k {
 	 */
 	spinlock_t data_lock;
 
+	/* serialises one scheduling round per access category against the
+	 * other contexts that drive it
+	 */
+	spinlock_t txq_lock[IEEE80211_NUM_ACS];
+
 	struct list_head arvifs;
 	/* should never be NULL; needed for regular htt rx */
 	struct ieee80211_channel *rx_channel;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index eca16a151d068..226e1417ffe74 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -10078,13 +10078,12 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw,
 	return ret;
 }
 
-static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
-					struct ieee80211_txq *txq)
+static int ath11k_mac_tx_push_txq(struct ath11k *ar, struct ieee80211_txq *txq)
 {
 	struct ieee80211_tx_control control = {
 		.sta = txq->sta,
 	};
-	struct ath11k *ar = hw->priv;
+	struct ieee80211_hw *hw = ar->hw;
 	struct dp_tx_ring *tx_ring;
 	struct hal_srng *tcl_ring;
 	struct sk_buff *skb;
@@ -10097,6 +10096,10 @@ static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 	tx_ring = &ar->ab->dp.tx_ring[ring_id];
 	tcl_ring = &ar->ab->hal.srng_list[tx_ring->tcl_data_ring.ring_id];
 
+	/* ieee80211_tx_dequeue() applies the airtime queue limit, so a
+	 * selection ends where that limit binds or the queue empties. A full
+	 * TCL ring ends the whole round.
+	 */
 	while (1) {
 		if (unlikely(test_bit(ATH11K_FLAG_CRASH_FLUSH,
 				      &ar->ab->dev_flags)))
@@ -10110,7 +10113,7 @@ static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 
 		if (num_free == 0) {
 			spin_unlock_bh(&tx_ring->wake_tx_lock);
-			break;
+			return -ENOSPC;
 		}
 
 		skb = ieee80211_tx_dequeue(hw, txq);
@@ -10123,6 +10126,34 @@ static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 
 		spin_unlock_bh(&tx_ring->wake_tx_lock);
 	}
+
+	return 0;
+}
+
+static void ath11k_mac_schedule_txq(struct ath11k *ar, u8 ac)
+{
+	struct ieee80211_hw *hw = ar->hw;
+	struct ieee80211_txq *txq;
+
+	spin_lock_bh(&ar->txq_lock[ac]);
+
+	ieee80211_txq_schedule_start(hw, ac);
+	while ((txq = ieee80211_next_txq(hw, ac))) {
+		int ret = ath11k_mac_tx_push_txq(ar, txq);
+
+		ieee80211_return_txq(hw, txq, false);
+		if (unlikely(ret))
+			break;
+	}
+	ieee80211_txq_schedule_end(hw, ac);
+
+	spin_unlock_bh(&ar->txq_lock[ac]);
+}
+
+static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
+					struct ieee80211_txq *txq)
+{
+	ath11k_mac_schedule_txq(hw->priv, txq->ac);
 }
 
 static const struct ieee80211_ops ath11k_ops = {
@@ -10817,7 +10848,7 @@ int ath11k_mac_allocate(struct ath11k_base *ab)
 	struct ath11k *ar;
 	struct ath11k_pdev *pdev;
 	int ret;
-	int i;
+	int i, j;
 
 	if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))
 		return 0;
@@ -10851,6 +10882,9 @@ int ath11k_mac_allocate(struct ath11k_base *ab)
 
 		pdev->ar = ar;
 		spin_lock_init(&ar->data_lock);
+
+		for (j = 0; j < IEEE80211_NUM_ACS; j++)
+			spin_lock_init(&ar->txq_lock[j]);
 		INIT_LIST_HEAD(&ar->arvifs);
 		INIT_LIST_HEAD(&ar->ppdu_stats_info);
 		mutex_init(&ar->conf_mutex);
-- 
2.53.0