wifi: rtw89: add function to wait for completion of TX skbs

Allocate a per-skb completion to track those skbs we are interested in
and wait for them to complete transmission with TX status.

Normally, the completion object is freed by wait side, but it could be
timeout result that complete side should free the object instead. Add a
owner field with RCU to determine which side should free the object.
Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230411124832.14965-3-pkshih@realtek.com

drivers/net/wireless/realtek/rtw89/core.c

@@ -867,6 +867,37 @@ void rtw89_core_tx_kick_off(struct rtw89_dev *rtwdev, u8 qsel)
 	rtw89_hci_tx_kick_off(rtwdev, ch_dma);
 }
 
+int rtw89_core_tx_kick_off_and_wait(struct rtw89_dev *rtwdev, struct sk_buff *skb,
+				    int qsel, unsigned int timeout)
+{
+	struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb);
+	struct rtw89_tx_wait_info *wait;
+	unsigned long time_left;
+	int ret = 0;
+
+	wait = kzalloc(sizeof(*wait), GFP_KERNEL);
+	if (!wait) {
+		rtw89_core_tx_kick_off(rtwdev, qsel);
+		return 0;
+	}
+
+	init_completion(&wait->completion);
+	rcu_assign_pointer(skb_data->wait, wait);
+
+	rtw89_core_tx_kick_off(rtwdev, qsel);
+	time_left = wait_for_completion_timeout(&wait->completion,
+						msecs_to_jiffies(timeout));
+	if (time_left == 0)
+		ret = -ETIMEDOUT;
+	else if (!wait->tx_done)
+		ret = -EAGAIN;
+
+	rcu_assign_pointer(skb_data->wait, NULL);
+	kfree_rcu(wait, rcu_head);
+
+	return ret;
+}
+
 int rtw89_h2c_tx(struct rtw89_dev *rtwdev,
 		 struct sk_buff *skb, bool fwdl)
 {

drivers/net/wireless/realtek/rtw89/core.h

@@ -2623,6 +2623,17 @@ struct rtw89_phy_rate_pattern {
 	bool enable;
 };
 
+struct rtw89_tx_wait_info {
+	struct rcu_head rcu_head;
+	struct completion completion;
+	bool tx_done;
+};
+
+struct rtw89_tx_skb_data {
+	struct rtw89_tx_wait_info __rcu *wait;
+	u8 hci_priv[];
+};
+
 #define RTW89_P2P_MAX_NOA_NUM 2
 
 struct rtw89_vif {
@@ -4179,6 +4190,14 @@ static inline void rtw89_hci_clear(struct rtw89_dev *rtwdev, struct pci_dev *pde
 		rtwdev->hci.ops->clear(rtwdev, pdev);
 }
 
+static inline
+struct rtw89_tx_skb_data *RTW89_TX_SKB_CB(struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	return (struct rtw89_tx_skb_data *)info->status.status_driver_data;
+}
+
 static inline u8 rtw89_read8(struct rtw89_dev *rtwdev, u32 addr)
 {
 	return rtwdev->hci.ops->read8(rtwdev, addr);
@@ -4822,11 +4841,32 @@ static inline struct sk_buff *rtw89_alloc_skb_for_rx(struct rtw89_dev *rtwdev,
 	return dev_alloc_skb(length);
 }
 
+static inline void rtw89_core_tx_wait_complete(struct rtw89_dev *rtwdev,
+					       struct rtw89_tx_skb_data *skb_data,
+					       bool tx_done)
+{
+	struct rtw89_tx_wait_info *wait;
+
+	rcu_read_lock();
+
+	wait = rcu_dereference(skb_data->wait);
+	if (!wait)
+		goto out;
+
+	wait->tx_done = tx_done;
+	complete(&wait->completion);
+
+out:
+	rcu_read_unlock();
+}
+
 int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta, struct sk_buff *skb, int *qsel);
 int rtw89_h2c_tx(struct rtw89_dev *rtwdev,
 		 struct sk_buff *skb, bool fwdl);
 void rtw89_core_tx_kick_off(struct rtw89_dev *rtwdev, u8 qsel);
+int rtw89_core_tx_kick_off_and_wait(struct rtw89_dev *rtwdev, struct sk_buff *skb,
+				    int qsel, unsigned int timeout);
 void rtw89_core_fill_txdesc(struct rtw89_dev *rtwdev,
 			    struct rtw89_tx_desc_info *desc_info,
 			    void *txdesc);

drivers/net/wireless/realtek/rtw89/pci.c

@@ -364,8 +364,11 @@ static void rtw89_pci_tx_status(struct rtw89_dev *rtwdev,
 				struct rtw89_pci_tx_ring *tx_ring,
 				struct sk_buff *skb, u8 tx_status)
 {
+	struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb);
 	struct ieee80211_tx_info *info;
 
+	rtw89_core_tx_wait_complete(rtwdev, skb_data, tx_status == RTW89_TX_DONE);
+
 	info = IEEE80211_SKB_CB(skb);
 	ieee80211_tx_info_clear_status(info);
 
@@ -1203,6 +1206,7 @@ static int rtw89_pci_txwd_submit(struct rtw89_dev *rtwdev,
 	struct pci_dev *pdev = rtwpci->pdev;
 	struct sk_buff *skb = tx_req->skb;
 	struct rtw89_pci_tx_data *tx_data = RTW89_PCI_TX_SKB_CB(skb);
+	struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb);
 	bool en_wd_info = desc_info->en_wd_info;
 	u32 txwd_len;
 	u32 txwp_len;
@@ -1218,6 +1222,7 @@ static int rtw89_pci_txwd_submit(struct rtw89_dev *rtwdev,
 	}
 
 	tx_data->dma = dma;
+	rcu_assign_pointer(skb_data->wait, NULL);
 
 	txwp_len = sizeof(*txwp_info);
 	txwd_len = chip->txwd_body_size;

drivers/net/wireless/realtek/rtw89/pci.h

@@ -1004,9 +1004,9 @@ rtw89_pci_rxbd_increase(struct rtw89_pci_rx_ring *rx_ring, u32 cnt)
 
 static inline struct rtw89_pci_tx_data *RTW89_PCI_TX_SKB_CB(struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct rtw89_tx_skb_data *data = RTW89_TX_SKB_CB(skb);
 
-	return (struct rtw89_pci_tx_data *)info->status.status_driver_data;
+	return (struct rtw89_pci_tx_data *)data->hci_priv;
 }
 
 static inline struct rtw89_pci_tx_bd_32 *