wifi: ath10k: Serialize wake_tx_queue ops

Serialize the ath10k implementation of the wake_tx_queue ops.
ath10k_mac_op_wake_tx_queue() must not run concurrent since it's using
ieee80211_txq_schedule_start().

The intend of this patch is to sort out an issue discovered in the discussion
referred to by the Link tag.

I can't test it with real hardware and thus just implemented the per-ac queue
lock Felix suggested. One obvious alternative to the per-ac lock would be to
bring back the txqs_lock commit bb2edb73 ("ath10k: migrate to mac80211 txq
scheduling") dropped.

Fixes: bb2edb73 ("ath10k: migrate to mac80211 txq scheduling")
Reported-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/519b5bb9-8899-ae7c-4eff-f3116cdfdb56@nbd.name
CC: <stable@vger.kernel.org>
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20230323165527.156414-1-alexander@wetzel-home.de

drivers/net/wireless/ath/ath10k/core.c

@@ -3643,6 +3643,9 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 	mutex_init(&ar->dump_mutex);
 	spin_lock_init(&ar->data_lock);
 
+	for (int ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+		spin_lock_init(&ar->queue_lock[ac]);
+
 	INIT_LIST_HEAD(&ar->peers);
 	init_waitqueue_head(&ar->peer_mapping_wq);
 	init_waitqueue_head(&ar->htt.empty_tx_wq);

drivers/net/wireless/ath/ath10k/core.h

@@ -1170,6 +1170,9 @@ struct ath10k {
 	/* protects shared structure data */
 	spinlock_t data_lock;
 
+	/* serialize wake_tx_queue calls per ac */
+	spinlock_t queue_lock[IEEE80211_NUM_ACS];
+
 	struct list_head arvifs;
 	struct list_head peers;
 	struct ath10k_peer *peer_map[ATH10K_MAX_NUM_PEER_IDS];

drivers/net/wireless/ath/ath10k/mac.c

@@ -4732,13 +4732,14 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 {
 	struct ath10k *ar = hw->priv;
 	int ret;
-	u8 ac;
+	u8 ac = txq->ac;
 
 	ath10k_htt_tx_txq_update(hw, txq);
 	if (ar->htt.tx_q_state.mode != HTT_TX_MODE_SWITCH_PUSH)
 		return;
 
-	ac = txq->ac;
+	spin_lock_bh(&ar->queue_lock[ac]);
+
 	ieee80211_txq_schedule_start(hw, ac);
 	txq = ieee80211_next_txq(hw, ac);
 	if (!txq)
@@ -4753,6 +4754,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 	ath10k_htt_tx_txq_update(hw, txq);
 out:
 	ieee80211_txq_schedule_end(hw, ac);
+	spin_unlock_bh(&ar->queue_lock[ac]);
 }
 
 /* Must not be called with conf_mutex held as workers can use that also. */