[PATCH v3 3/4] wifi: rtw88: usb: Support RX aggregation

[Bitterblue Smith <rtl8821cerfe2@xxxxxxxxx>]

The chips can be configured to aggregate several frames into a single
USB transfer. Modify rtw_usb_rx_handler() to support this case.

RX aggregation improves the RX speed on certain ARM systems, like the
NanoPi NEO Core2.

Currently none of the chips are configured to aggregate frames.

Tested with RTL8811CU and RTL8723DU.

Reviewed-by: Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>
Tested-by: Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@xxxxxxxxx>
---
v3:
 - Don't initialise next_skb.
 - Add Tested-by and Reviewed-by: Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>

v2:
 - Simplify the code and make it more readable.
 - Rebase on top of latest rtw-next.
---
 drivers/net/wireless/realtek/rtw88/usb.c | 61 ++++++++++++++++--------
 1 file changed, 40 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 10f1d724370e..4c7ba5c76a57 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -546,11 +546,12 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 	struct rtw_usb *rtwusb = container_of(work, struct rtw_usb, rx_work);
 	struct rtw_dev *rtwdev = rtwusb->rtwdev;
 	const struct rtw_chip_info *chip = rtwdev->chip;
-	struct rtw_rx_pkt_stat pkt_stat;
+	u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
 	struct ieee80211_rx_status rx_status;
+	u32 pkt_offset, next_pkt, urb_len;
+	struct rtw_rx_pkt_stat pkt_stat;
+	struct sk_buff *next_skb;
 	struct sk_buff *skb;
-	u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
-	u32 pkt_offset;
 	u8 *rx_desc;
 	int limit;
 
@@ -559,31 +560,48 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 		if (!skb)
 			break;
 
-		rx_desc = skb->data;
-		chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat,
-					 &rx_status);
-		pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
-			     pkt_stat.shift;
-
-		if (pkt_stat.is_c2h) {
-			skb_put(skb, pkt_stat.pkt_len + pkt_offset);
-			rtw_fw_c2h_cmd_rx_irqsafe(rtwdev, pkt_offset, skb);
-			continue;
-		}
-
 		if (skb_queue_len(&rtwusb->rx_queue) >= RTW_USB_MAX_RXQ_LEN) {
 			dev_dbg_ratelimited(rtwdev->dev, "failed to get rx_queue, overflow\n");
 			dev_kfree_skb_any(skb);
 			continue;
 		}
 
-		skb_put(skb, pkt_stat.pkt_len);
-		skb_reserve(skb, pkt_offset);
+		urb_len = skb->len;
+
+		do {
+			rx_desc = skb->data;
+			chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat,
+						 &rx_status);
+			pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
+				     pkt_stat.shift;
+
+			next_pkt = round_up(pkt_stat.pkt_len + pkt_offset, 8);
+
+			if (urb_len >= next_pkt + pkt_desc_sz)
+				next_skb = skb_clone(skb, GFP_KERNEL);
+			else
+				next_skb = NULL;
+
+			if (pkt_stat.is_c2h) {
+				skb_trim(skb, pkt_stat.pkt_len + pkt_offset);
+				rtw_fw_c2h_cmd_rx_irqsafe(rtwdev, pkt_offset, skb);
+			} else {
+				skb_pull(skb, pkt_offset);
+				skb_trim(skb, pkt_stat.pkt_len);
+				rtw_update_rx_freq_for_invalid(rtwdev, skb,
+							       &rx_status,
+							       &pkt_stat);
+				rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
+				memcpy(skb->cb, &rx_status, sizeof(rx_status));
+				ieee80211_rx_irqsafe(rtwdev->hw, skb);
+			}
+
+			skb = next_skb;
+			if (skb)
+				skb_pull(skb, next_pkt);
 
-		rtw_update_rx_freq_for_invalid(rtwdev, skb, &rx_status, &pkt_stat);
-		rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
-		memcpy(skb->cb, &rx_status, sizeof(rx_status));
-		ieee80211_rx_irqsafe(rtwdev->hw, skb);
+			urb_len -= next_pkt;
+		} while (skb);
 	}
 }
 
@@ -627,6 +645,7 @@ static void rtw_usb_read_port_complete(struct urb *urb)
 			if (skb)
 				dev_kfree_skb_any(skb);
 		} else {
+			skb_put(skb, urb->actual_length);
 			skb_queue_tail(&rtwusb->rx_queue, skb);
 			queue_work(rtwusb->rxwq, &rtwusb->rx_work);
 		}
-- 
2.45.2