rtw88: pci: Use DMA sync instead of remapping in RX ISR

Since each skb in RX ring is reused instead of new allocation, we can
treat the DMA in a more efficient way by DMA synchronization.
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

drivers/net/wireless/realtek/rtw88/pci.c

@@ -206,6 +206,23 @@ static int rtw_pci_reset_rx_desc(struct rtw_dev *rtwdev, struct sk_buff *skb,
 	return 0;
 }
 
+static void rtw_pci_sync_rx_desc_device(struct rtw_dev *rtwdev, dma_addr_t dma,
+					struct rtw_pci_rx_ring *rx_ring,
+					u32 idx, u32 desc_sz)
+{
+	struct device *dev = rtwdev->dev;
+	struct rtw_pci_rx_buffer_desc *buf_desc;
+	int buf_sz = RTK_PCI_RX_BUF_SIZE;
+
+	dma_sync_single_for_device(dev, dma, buf_sz, DMA_FROM_DEVICE);
+
+	buf_desc = (struct rtw_pci_rx_buffer_desc *)(rx_ring->r.head +
+						     idx * desc_sz);
+	memset(buf_desc, 0, sizeof(*buf_desc));
+	buf_desc->buf_size = cpu_to_le16(RTK_PCI_RX_BUF_SIZE);
+	buf_desc->dma = cpu_to_le32(dma);
+}
+
 static int rtw_pci_init_rx_ring(struct rtw_dev *rtwdev,
 				struct rtw_pci_rx_ring *rx_ring,
 				u8 desc_size, u32 len)
@@ -784,8 +801,8 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
 		rtw_pci_dma_check(rtwdev, ring, cur_rp);
 		skb = ring->buf[cur_rp];
 		dma = *((dma_addr_t *)skb->cb);
-		pci_unmap_single(rtwpci->pdev, dma, RTK_PCI_RX_BUF_SIZE,
-				 PCI_DMA_FROMDEVICE);
+		dma_sync_single_for_cpu(rtwdev->dev, dma, RTK_PCI_RX_BUF_SIZE,
+					DMA_FROM_DEVICE);
 		rx_desc = skb->data;
 		chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat, &rx_status);
 
@@ -820,7 +837,8 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
 
 next_rp:
 		/* new skb delivered to mac80211, re-enable original skb DMA */
-		rtw_pci_reset_rx_desc(rtwdev, skb, ring, cur_rp, buf_desc_sz);
+		rtw_pci_sync_rx_desc_device(rtwdev, dma, ring, cur_rp,
+					    buf_desc_sz);
 
 		/* host read next element in ring */
 		if (++cur_rp >= ring->r.len)