net: axienet: Make RX/TX ring sizes configurable

Add support for setting the RX and TX ring sizes for this driver using
ethtool. Also increase the default RX ring size as the previous default
was far too low for good performance in some configurations.

Signed-off-by: Robert Hancock <hancock@sedsystems.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 65 insertions, 25 deletions

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index bdc6e8047959..2c2d626c12a7 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -39,9 +39,11 @@
 
 #include "xilinx_axienet.h"
 
-/* Descriptors defines for Tx and Rx DMA - 2^n for the best performance */
-#define TX_BD_NUM		64
-#define RX_BD_NUM		128
+/* Descriptors defines for Tx and Rx DMA */
+#define TX_BD_NUM_DEFAULT		64
+#define RX_BD_NUM_DEFAULT		1024
+#define TX_BD_NUM_MAX			4096
+#define RX_BD_NUM_MAX			4096
 
 /* Must be shorter than length of ethtool_drvinfo.driver field to fit */
 #define DRIVER_NAME		"xaxienet"
@@ -157,7 +159,7 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 	int i;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		dma_unmap_single(ndev->dev.parent, lp->rx_bd_v[i].phys,
 				 lp->max_frm_size, DMA_FROM_DEVICE);
 		dev_kfree_skb(lp->rx_bd_v[i].skb);
@@ -165,13 +167,13 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 
 	if (lp->rx_bd_v) {
 		dma_free_coherent(ndev->dev.parent,
-				  sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+				  sizeof(*lp->rx_bd_v) * lp->rx_bd_num,
 				  lp->rx_bd_v,
 				  lp->rx_bd_p);
 	}
 	if (lp->tx_bd_v) {
 		dma_free_coherent(ndev->dev.parent,
-				  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+				  sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
 				  lp->tx_bd_v,
 				  lp->tx_bd_p);
 	}
@@ -201,27 +203,27 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 
 	/* Allocate the Tx and Rx buffer descriptors. */
 	lp->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
-					 sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+					 sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
 					 &lp->tx_bd_p, GFP_KERNEL);
 	if (!lp->tx_bd_v)
 		goto out;
 
 	lp->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
-					 sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+					 sizeof(*lp->rx_bd_v) * lp->rx_bd_num,
 					 &lp->rx_bd_p, GFP_KERNEL);
 	if (!lp->rx_bd_v)
 		goto out;
 
-	for (i = 0; i < TX_BD_NUM; i++) {
+	for (i = 0; i < lp->tx_bd_num; i++) {
 		lp->tx_bd_v[i].next = lp->tx_bd_p +
 				      sizeof(*lp->tx_bd_v) *
-				      ((i + 1) % TX_BD_NUM);
+				      ((i + 1) % lp->tx_bd_num);
 	}
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		lp->rx_bd_v[i].next = lp->rx_bd_p +
 				      sizeof(*lp->rx_bd_v) *
-				      ((i + 1) % RX_BD_NUM);
+				      ((i + 1) % lp->rx_bd_num);
 
 		skb = netdev_alloc_skb_ip_align(ndev, lp->max_frm_size);
 		if (!skb)
@@ -269,7 +271,7 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
-			  (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+			  (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -610,8 +612,8 @@ static void axienet_start_xmit_done(struct net_device *ndev)
 		size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 		packets++;
 
-		++lp->tx_bd_ci;
-		lp->tx_bd_ci %= TX_BD_NUM;
+		if (++lp->tx_bd_ci >= lp->tx_bd_num)
+			lp->tx_bd_ci = 0;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
 		status = cur_p->status;
 	}
@@ -638,7 +640,7 @@ static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
 					    int num_frag)
 {
 	struct axidma_bd *cur_p;
-	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % TX_BD_NUM];
+	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
 	if (cur_p->status & XAXIDMA_BD_STS_ALL_MASK)
 		return NETDEV_TX_BUSY;
 	return 0;
@@ -698,8 +700,8 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 				     skb_headlen(skb), DMA_TO_DEVICE);
 
 	for (ii = 0; ii < num_frag; ii++) {
-		++lp->tx_bd_tail;
-		lp->tx_bd_tail %= TX_BD_NUM;
+		if (++lp->tx_bd_tail >= lp->tx_bd_num)
+			lp->tx_bd_tail = 0;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 		frag = &skb_shinfo(skb)->frags[ii];
 		cur_p->phys = dma_map_single(ndev->dev.parent,
@@ -715,8 +717,8 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	/* Start the transfer */
 	axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
-	++lp->tx_bd_tail;
-	lp->tx_bd_tail %= TX_BD_NUM;
+	if (++lp->tx_bd_tail >= lp->tx_bd_num)
+		lp->tx_bd_tail = 0;
 
 	return NETDEV_TX_OK;
 }
@@ -790,8 +792,8 @@ static void axienet_recv(struct net_device *ndev)
 		cur_p->status = 0;
 		cur_p->skb = new_skb;
 
-		++lp->rx_bd_ci;
-		lp->rx_bd_ci %= RX_BD_NUM;
+		if (++lp->rx_bd_ci >= lp->rx_bd_num)
+			lp->rx_bd_ci = 0;
 		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 	}
 
@@ -1179,6 +1181,40 @@ static void axienet_ethtools_get_regs(struct net_device *ndev,
 	data[31] = axienet_ior(lp, XAE_AF1_OFFSET);
 }
 
+static void axienet_ethtools_get_ringparam(struct net_device *ndev,
+					   struct ethtool_ringparam *ering)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	ering->rx_max_pending = RX_BD_NUM_MAX;
+	ering->rx_mini_max_pending = 0;
+	ering->rx_jumbo_max_pending = 0;
+	ering->tx_max_pending = TX_BD_NUM_MAX;
+	ering->rx_pending = lp->rx_bd_num;
+	ering->rx_mini_pending = 0;
+	ering->rx_jumbo_pending = 0;
+	ering->tx_pending = lp->tx_bd_num;
+}
+
+static int axienet_ethtools_set_ringparam(struct net_device *ndev,
+					  struct ethtool_ringparam *ering)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	if (ering->rx_pending > RX_BD_NUM_MAX ||
+	    ering->rx_mini_pending ||
+	    ering->rx_jumbo_pending ||
+	    ering->rx_pending > TX_BD_NUM_MAX)
+		return -EINVAL;
+
+	if (netif_running(ndev))
+		return -EBUSY;
+
+	lp->rx_bd_num = ering->rx_pending;
+	lp->tx_bd_num = ering->tx_pending;
+	return 0;
+}
+
 /**
  * axienet_ethtools_get_pauseparam - Get the pause parameter setting for
  *				     Tx and Rx paths.
@@ -1320,6 +1356,8 @@ static const struct ethtool_ops axienet_ethtool_ops = {
 	.get_regs_len   = axienet_ethtools_get_regs_len,
 	.get_regs       = axienet_ethtools_get_regs,
 	.get_link       = ethtool_op_get_link,
+	.get_ringparam	= axienet_ethtools_get_ringparam,
+	.set_ringparam	= axienet_ethtools_set_ringparam,
 	.get_pauseparam = axienet_ethtools_get_pauseparam,
 	.set_pauseparam = axienet_ethtools_set_pauseparam,
 	.get_coalesce   = axienet_ethtools_get_coalesce,
@@ -1357,7 +1395,7 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_mdio_enable(lp);
 	mutex_unlock(&lp->mii_bus->mdio_lock);
 
-	for (i = 0; i < TX_BD_NUM; i++) {
+	for (i = 0; i < lp->tx_bd_num; i++) {
 		cur_p = &lp->tx_bd_v[i];
 		if (cur_p->phys)
 			dma_unmap_single(ndev->dev.parent, cur_p->phys,
@@ -1377,7 +1415,7 @@ static void axienet_dma_err_handler(unsigned long data)
 		cur_p->skb = NULL;
 	}
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		cur_p = &lp->rx_bd_v[i];
 		cur_p->status = 0;
 		cur_p->app0 = 0;
@@ -1425,7 +1463,7 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
-			  (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+			  (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -1497,6 +1535,8 @@ static int axienet_probe(struct platform_device *pdev)
 	lp->ndev = ndev;
 	lp->dev = &pdev->dev;
 	lp->options = XAE_OPTION_DEFAULTS;
+	lp->rx_bd_num = RX_BD_NUM_DEFAULT;
+	lp->tx_bd_num = TX_BD_NUM_DEFAULT;
 	/* Map device registers */
 	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	lp->regs_start = ethres->start;