net: lantiq: configure the burst length in ethernet drivers

Configure the burst length in Ethernet drivers. This improves
Ethernet performance by 58%. According to the vendor BSP,
8W burst length is supported by ar9 and newer SoCs.

The NAT benchmark results on xRX200 (Down/Up):
* 2W: 330 Mb/s
* 4W: 432 Mb/s    372 Mb/s
* 8W: 520 Mb/s    389 Mb/s

Tested on xRX200 and xRX330.
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/lantiq_etop.c

@@ -96,6 +96,9 @@ struct ltq_etop_priv {
 	struct ltq_etop_chan ch[MAX_DMA_CHAN];
 	int tx_free[MAX_DMA_CHAN >> 1];
 
+	int tx_burst_len;
+	int rx_burst_len;
+
 	spinlock_t lock;
 };
 
@@ -259,7 +262,7 @@ ltq_etop_hw_init(struct net_device *dev)
 	/* enable crc generation */
 	ltq_etop_w32(PPE32_CGEN, LQ_PPE32_ENET_MAC_CFG);
 
-	ltq_dma_init_port(DMA_PORT_ETOP);
+	ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len);
 
 	for (i = 0; i < MAX_DMA_CHAN; i++) {
 		int irq = LTQ_DMA_CH0_INT + i;
@@ -472,8 +475,8 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	/* dma needs to start on a 16 byte aligned address */
-	byte_offset = CPHYSADDR(skb->data) % 16;
+	/* dma needs to start on a burst length value aligned address */
+	byte_offset = CPHYSADDR(skb->data) % (priv->tx_burst_len * 4);
 	ch->skb[ch->dma.desc] = skb;
 
 	netif_trans_update(dev);
@@ -667,6 +670,18 @@ ltq_etop_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->lock);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
+	err = device_property_read_u32(&pdev->dev, "lantiq,tx-burst-length", &priv->tx_burst_len);
+	if (err < 0) {
+		dev_err(&pdev->dev, "unable to read tx-burst-length property\n");
+		return err;
+	}
+
+	err = device_property_read_u32(&pdev->dev, "lantiq,rx-burst-length", &priv->rx_burst_len);
+	if (err < 0) {
+		dev_err(&pdev->dev, "unable to read rx-burst-length property\n");
+		return err;
+	}
+
 	for (i = 0; i < MAX_DMA_CHAN; i++) {
 		if (IS_TX(i))
 			netif_napi_add(dev, &priv->ch[i].napi,

drivers/net/ethernet/lantiq_xrx200.c

@@ -71,6 +71,9 @@ struct xrx200_priv {
 	struct net_device *net_dev;
 	struct device *dev;
 
+	int tx_burst_len;
+	int rx_burst_len;
+
 	__iomem void *pmac_reg;
 };
 
@@ -316,8 +319,8 @@ static netdev_tx_t xrx200_start_xmit(struct sk_buff *skb,
 	if (unlikely(dma_mapping_error(priv->dev, mapping)))
 		goto err_drop;
 
-	/* dma needs to start on a 16 byte aligned address */
-	byte_offset = mapping % 16;
+	/* dma needs to start on a burst length value aligned address */
+	byte_offset = mapping % (priv->tx_burst_len * 4);
 
 	desc->addr = mapping - byte_offset;
 	/* Make sure the address is written before we give it to HW */
@@ -369,7 +372,7 @@ static int xrx200_dma_init(struct xrx200_priv *priv)
 	int ret = 0;
 	int i;
 
-	ltq_dma_init_port(DMA_PORT_ETOP);
+	ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len);
 
 	ch_rx->dma.nr = XRX200_DMA_RX;
 	ch_rx->dma.dev = priv->dev;
@@ -478,6 +481,18 @@ static int xrx200_probe(struct platform_device *pdev)
 	if (err)
 		eth_hw_addr_random(net_dev);
 
+	err = device_property_read_u32(dev, "lantiq,tx-burst-length", &priv->tx_burst_len);
+	if (err < 0) {
+		dev_err(dev, "unable to read tx-burst-length property\n");
+		return err;
+	}
+
+	err = device_property_read_u32(dev, "lantiq,rx-burst-length", &priv->rx_burst_len);
+	if (err < 0) {
+		dev_err(dev, "unable to read rx-burst-length property\n");
+		return err;
+	}
+
 	/* bring up the dma engine and IP core */
 	err = xrx200_dma_init(priv);
 	if (err)