From 9999e48639b3cecb08ffb37358bcba3b48161b29 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:17 +0000
Subject: [PATCH] add ax88772_rst

---
 kernel/drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 1273 ++++++++++++++++++++++++++++++++++++++++-----------------
 1 files changed, 883 insertions(+), 390 deletions(-)

diff --git a/kernel/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/kernel/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 5190402..9d36228 100644
--- a/kernel/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/kernel/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Xilinx Axi Ethernet device driver
  *
@@ -6,6 +7,7 @@
  * Copyright (c) 2008-2009 Secret Lab Technologies Ltd.
  * Copyright (c) 2010 - 2011 Michal Simek <monstr@monstr.eu>
  * Copyright (c) 2010 - 2011 PetaLogix
+ * Copyright (c) 2019 SED Systems, a division of Calian Ltd.
  * Copyright (c) 2010 - 2012 Xilinx, Inc. All rights reserved.
  *
  * This is a driver for the Xilinx Axi Ethernet which is used in the Virtex6
@@ -20,6 +22,7 @@
  *  - Add support for extended VLAN support.
  */
 
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/etherdevice.h>
 #include <linux/module.h>
@@ -37,16 +40,19 @@
 
 #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		128
+#define RX_BD_NUM_DEFAULT		1024
+#define TX_BD_NUM_MIN			(MAX_SKB_FRAGS + 1)
+#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"
 #define DRIVER_DESCRIPTION	"Xilinx Axi Ethernet driver"
 #define DRIVER_VERSION		"1.00a"
 
-#define AXIENET_REGS_N		32
+#define AXIENET_REGS_N		40
 
 /* Match table for of_platform binding */
 static const struct of_device_id axienet_of_match[] = {
@@ -124,7 +130,7 @@
  */
 static inline u32 axienet_dma_in32(struct axienet_local *lp, off_t reg)
 {
-	return in_be32(lp->dma_regs + reg);
+	return ioread32(lp->dma_regs + reg);
 }
 
 /**
@@ -139,7 +145,35 @@
 static inline void axienet_dma_out32(struct axienet_local *lp,
 				     off_t reg, u32 value)
 {
-	out_be32((lp->dma_regs + reg), value);
+	iowrite32(value, lp->dma_regs + reg);
+}
+
+static void axienet_dma_out_addr(struct axienet_local *lp, off_t reg,
+				 dma_addr_t addr)
+{
+	axienet_dma_out32(lp, reg, lower_32_bits(addr));
+
+	if (lp->features & XAE_FEATURE_DMA_64BIT)
+		axienet_dma_out32(lp, reg + 4, upper_32_bits(addr));
+}
+
+static void desc_set_phys_addr(struct axienet_local *lp, dma_addr_t addr,
+			       struct axidma_bd *desc)
+{
+	desc->phys = lower_32_bits(addr);
+	if (lp->features & XAE_FEATURE_DMA_64BIT)
+		desc->phys_msb = upper_32_bits(addr);
+}
+
+static dma_addr_t desc_get_phys_addr(struct axienet_local *lp,
+				     struct axidma_bd *desc)
+{
+	dma_addr_t ret = desc->phys;
+
+	if (lp->features & XAE_FEATURE_DMA_64BIT)
+		ret |= ((dma_addr_t)desc->phys_msb << 16) << 16;
+
+	return ret;
 }
 
 /**
@@ -155,25 +189,41 @@
 	int i;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	for (i = 0; i < 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((struct sk_buff *)
-			      (lp->rx_bd_v[i].sw_id_offset));
+	/* If we end up here, tx_bd_v must have been DMA allocated. */
+	dma_free_coherent(ndev->dev.parent,
+			  sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
+			  lp->tx_bd_v,
+			  lp->tx_bd_p);
+
+	if (!lp->rx_bd_v)
+		return;
+
+	for (i = 0; i < lp->rx_bd_num; i++) {
+		dma_addr_t phys;
+
+		/* A NULL skb means this descriptor has not been initialised
+		 * at all.
+		 */
+		if (!lp->rx_bd_v[i].skb)
+			break;
+
+		dev_kfree_skb(lp->rx_bd_v[i].skb);
+
+		/* For each descriptor, we programmed cntrl with the (non-zero)
+		 * descriptor size, after it had been successfully allocated.
+		 * So a non-zero value in there means we need to unmap it.
+		 */
+		if (lp->rx_bd_v[i].cntrl) {
+			phys = desc_get_phys_addr(lp, &lp->rx_bd_v[i]);
+			dma_unmap_single(ndev->dev.parent, phys,
+					 lp->max_frm_size, DMA_FROM_DEVICE);
+		}
 	}
 
-	if (lp->rx_bd_v) {
-		dma_free_coherent(ndev->dev.parent,
-				  sizeof(*lp->rx_bd_v) * 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,
-				  lp->tx_bd_v,
-				  lp->tx_bd_p);
-	}
+	dma_free_coherent(ndev->dev.parent,
+			  sizeof(*lp->rx_bd_v) * lp->rx_bd_num,
+			  lp->rx_bd_v,
+			  lp->rx_bd_p);
 }
 
 /**
@@ -199,38 +249,50 @@
 	lp->rx_bd_ci = 0;
 
 	/* Allocate the Tx and Rx buffer descriptors. */
-	lp->tx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
-					  &lp->tx_bd_p, GFP_KERNEL);
+	lp->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
+					 &lp->tx_bd_p, GFP_KERNEL);
 	if (!lp->tx_bd_v)
-		goto out;
+		return -ENOMEM;
 
-	lp->rx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->rx_bd_v) * RX_BD_NUM,
-					  &lp->rx_bd_p, GFP_KERNEL);
+	lp->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 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++) {
-		lp->tx_bd_v[i].next = lp->tx_bd_p +
-				      sizeof(*lp->tx_bd_v) *
-				      ((i + 1) % TX_BD_NUM);
+	for (i = 0; i < lp->tx_bd_num; i++) {
+		dma_addr_t addr = lp->tx_bd_p +
+				  sizeof(*lp->tx_bd_v) *
+				  ((i + 1) % lp->tx_bd_num);
+
+		lp->tx_bd_v[i].next = lower_32_bits(addr);
+		if (lp->features & XAE_FEATURE_DMA_64BIT)
+			lp->tx_bd_v[i].next_msb = upper_32_bits(addr);
 	}
 
-	for (i = 0; i < RX_BD_NUM; i++) {
-		lp->rx_bd_v[i].next = lp->rx_bd_p +
-				      sizeof(*lp->rx_bd_v) *
-				      ((i + 1) % RX_BD_NUM);
+	for (i = 0; i < lp->rx_bd_num; i++) {
+		dma_addr_t addr;
+
+		addr = lp->rx_bd_p + sizeof(*lp->rx_bd_v) *
+			((i + 1) % lp->rx_bd_num);
+		lp->rx_bd_v[i].next = lower_32_bits(addr);
+		if (lp->features & XAE_FEATURE_DMA_64BIT)
+			lp->rx_bd_v[i].next_msb = upper_32_bits(addr);
 
 		skb = netdev_alloc_skb_ip_align(ndev, lp->max_frm_size);
 		if (!skb)
 			goto out;
 
-		lp->rx_bd_v[i].sw_id_offset = (u32) skb;
-		lp->rx_bd_v[i].phys = dma_map_single(ndev->dev.parent,
-						     skb->data,
-						     lp->max_frm_size,
-						     DMA_FROM_DEVICE);
+		lp->rx_bd_v[i].skb = skb;
+		addr = dma_map_single(ndev->dev.parent, skb->data,
+				      lp->max_frm_size, DMA_FROM_DEVICE);
+		if (dma_mapping_error(ndev->dev.parent, addr)) {
+			netdev_err(ndev, "DMA mapping error\n");
+			goto out;
+		}
+		desc_set_phys_addr(lp, addr, &lp->rx_bd_v[i]);
+
 		lp->rx_bd_v[i].cntrl = lp->max_frm_size;
 	}
 
@@ -263,31 +325,21 @@
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
 	 * halted state. This will make the Rx side ready for reception.
 	 */
-	axienet_dma_out32(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
+	axienet_dma_out_addr(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
 	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)));
+	axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
+			     (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
 	 * tail pointer register that the Tx channel will start transmitting.
 	 */
-	axienet_dma_out32(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
+	axienet_dma_out_addr(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
-
-	/* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */
-	ret = read_poll_timeout(axienet_ior, value,
-				value & XAE_INT_PHYRSTCMPLT_MASK,
-				DELAY_OF_ONE_MILLISEC, 50000, false, lp,
-				XAE_IS_OFFSET);
-	if (ret) {
-		dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__);
-		return ret;
-	}
 
 	return 0;
 out:
@@ -443,24 +495,39 @@
 	lp->options |= options;
 }
 
-static void __axienet_device_reset(struct axienet_local *lp, off_t offset)
+static int __axienet_device_reset(struct axienet_local *lp)
 {
-	u32 timeout;
+	u32 value;
+	int ret;
+
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
 	 * commands/transfers will be flushed or completed during this
 	 * reset process.
+	 * Note that even though both TX and RX have their own reset register,
+	 * they both reset the entire DMA core, so only one needs to be used.
 	 */
-	axienet_dma_out32(lp, offset, XAXIDMA_CR_RESET_MASK);
-	timeout = DELAY_OF_ONE_MILLISEC;
-	while (axienet_dma_in32(lp, offset) & XAXIDMA_CR_RESET_MASK) {
-		udelay(1);
-		if (--timeout == 0) {
-			netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
-				   __func__);
-			break;
-		}
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, XAXIDMA_CR_RESET_MASK);
+	ret = read_poll_timeout(axienet_dma_in32, value,
+				!(value & XAXIDMA_CR_RESET_MASK),
+				DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+				XAXIDMA_TX_CR_OFFSET);
+	if (ret) {
+		dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__);
+		return ret;
 	}
+
+	/* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */
+	ret = read_poll_timeout(axienet_ior, value,
+				value & XAE_INT_PHYRSTCMPLT_MASK,
+				DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+				XAE_IS_OFFSET);
+	if (ret) {
+		dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__);
+		return ret;
+	}
+
+	return 0;
 }
 
 /**
@@ -473,14 +540,17 @@
  * areconnected to Axi Ethernet reset lines, this in turn resets the Axi
  * Ethernet core. No separate hardware reset is done for the Axi Ethernet
  * core.
+ * Returns 0 on success or a negative error number otherwise.
  */
-static void axienet_device_reset(struct net_device *ndev)
+static int axienet_device_reset(struct net_device *ndev)
 {
 	u32 axienet_status;
 	struct axienet_local *lp = netdev_priv(ndev);
+	int ret;
 
-	__axienet_device_reset(lp, XAXIDMA_TX_CR_OFFSET);
-	__axienet_device_reset(lp, XAXIDMA_RX_CR_OFFSET);
+	ret = __axienet_device_reset(lp);
+	if (ret)
+		return ret;
 
 	lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE;
 	lp->options |= XAE_OPTION_VLAN;
@@ -495,9 +565,11 @@
 			lp->options |= XAE_OPTION_JUMBO;
 	}
 
-	if (axienet_dma_bd_init(ndev)) {
+	ret = axienet_dma_bd_init(ndev);
+	if (ret) {
 		netdev_err(ndev, "%s: descriptor allocation failed\n",
 			   __func__);
+		return ret;
 	}
 
 	axienet_status = axienet_ior(lp, XAE_RCW1_OFFSET);
@@ -507,6 +579,8 @@
 	axienet_status = axienet_ior(lp, XAE_IP_OFFSET);
 	if (axienet_status & XAE_INT_RXRJECT_MASK)
 		axienet_iow(lp, XAE_IS_OFFSET, XAE_INT_RXRJECT_MASK);
+	axienet_iow(lp, XAE_IE_OFFSET, lp->eth_irq > 0 ?
+		    XAE_INT_RECV_ERROR_MASK : 0);
 
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
@@ -520,115 +594,70 @@
 	axienet_setoptions(ndev, lp->options);
 
 	netif_trans_update(ndev);
+
+	return 0;
 }
 
 /**
- * axienet_adjust_link - Adjust the PHY link speed/duplex.
+ * axienet_free_tx_chain - Clean up a series of linked TX descriptors.
  * @ndev:	Pointer to the net_device structure
+ * @first_bd:	Index of first descriptor to clean up
+ * @nr_bds:	Number of descriptors to clean up, can be -1 if unknown.
+ * @sizep:	Pointer to a u32 filled with the total sum of all bytes
+ * 		in all cleaned-up descriptors. Ignored if NULL.
  *
- * This function is called to change the speed and duplex setting after
- * auto negotiation is done by the PHY. This is the function that gets
- * registered with the PHY interface through the "of_phy_connect" call.
+ * Would either be called after a successful transmit operation, or after
+ * there was an error when setting up the chain.
+ * Returns the number of descriptors handled.
  */
-static void axienet_adjust_link(struct net_device *ndev)
+static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
+				 int nr_bds, u32 *sizep)
 {
-	u32 emmc_reg;
-	u32 link_state;
-	u32 setspeed = 1;
-	struct axienet_local *lp = netdev_priv(ndev);
-	struct phy_device *phy = ndev->phydev;
-
-	link_state = phy->speed | (phy->duplex << 1) | phy->link;
-	if (lp->last_link != link_state) {
-		if ((phy->speed == SPEED_10) || (phy->speed == SPEED_100)) {
-			if (lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX)
-				setspeed = 0;
-		} else {
-			if ((phy->speed == SPEED_1000) &&
-			    (lp->phy_mode == PHY_INTERFACE_MODE_MII))
-				setspeed = 0;
-		}
-
-		if (setspeed == 1) {
-			emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
-			emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK;
-
-			switch (phy->speed) {
-			case SPEED_1000:
-				emmc_reg |= XAE_EMMC_LINKSPD_1000;
-				break;
-			case SPEED_100:
-				emmc_reg |= XAE_EMMC_LINKSPD_100;
-				break;
-			case SPEED_10:
-				emmc_reg |= XAE_EMMC_LINKSPD_10;
-				break;
-			default:
-				dev_err(&ndev->dev, "Speed other than 10, 100 "
-					"or 1Gbps is not supported\n");
-				break;
-			}
-
-			axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg);
-			lp->last_link = link_state;
-			phy_print_status(phy);
-		} else {
-			netdev_err(ndev,
-				   "Error setting Axi Ethernet mac speed\n");
-		}
-	}
-}
-
-/**
- * axienet_start_xmit_done - Invoked once a transmit is completed by the
- * Axi DMA Tx channel.
- * @ndev:	Pointer to the net_device structure
- *
- * This function is invoked from the Axi DMA Tx isr to notify the completion
- * of transmit operation. It clears fields in the corresponding Tx BDs and
- * unmaps the corresponding buffer so that CPU can regain ownership of the
- * buffer. It finally invokes "netif_wake_queue" to restart transmission if
- * required.
- */
-static void axienet_start_xmit_done(struct net_device *ndev)
-{
-	u32 size = 0;
-	u32 packets = 0;
 	struct axienet_local *lp = netdev_priv(ndev);
 	struct axidma_bd *cur_p;
-	unsigned int status = 0;
+	int max_bds = nr_bds;
+	unsigned int status;
+	dma_addr_t phys;
+	int i;
 
-	cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
-	status = cur_p->status;
-	while (status & XAXIDMA_BD_STS_COMPLETE_MASK) {
-		dma_unmap_single(ndev->dev.parent, cur_p->phys,
-				(cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
-				DMA_TO_DEVICE);
-		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
-		/*cur_p->phys = 0;*/
+	if (max_bds == -1)
+		max_bds = lp->tx_bd_num;
+
+	for (i = 0; i < max_bds; i++) {
+		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
+		status = cur_p->status;
+
+		/* If no number is given, clean up *all* descriptors that have
+		 * been completed by the MAC.
+		 */
+		if (nr_bds == -1 && !(status & XAXIDMA_BD_STS_COMPLETE_MASK))
+			break;
+
+		/* Ensure we see complete descriptor update */
+		dma_rmb();
+		phys = desc_get_phys_addr(lp, cur_p);
+		dma_unmap_single(ndev->dev.parent, phys,
+				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
+				 DMA_TO_DEVICE);
+
+		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
+			dev_consume_skb_irq(cur_p->skb);
+
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
 		cur_p->app4 = 0;
+		cur_p->skb = NULL;
+		/* ensure our transmit path and device don't prematurely see status cleared */
+		wmb();
+		cur_p->cntrl = 0;
 		cur_p->status = 0;
 
-		size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
-		packets++;
-
-		++lp->tx_bd_ci;
-		lp->tx_bd_ci %= TX_BD_NUM;
-		cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
-		status = cur_p->status;
+		if (sizep)
+			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
-	ndev->stats.tx_packets += packets;
-	ndev->stats.tx_bytes += size;
-
-	/* Matches barrier in axienet_start_xmit */
-	smp_mb();
-
-	netif_wake_queue(ndev);
+	return i;
 }
 
 /**
@@ -648,10 +677,46 @@
 					    int num_frag)
 {
 	struct axidma_bd *cur_p;
-	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % TX_BD_NUM];
-	if (cur_p->status & XAXIDMA_BD_STS_ALL_MASK)
+
+	/* Ensure we see all descriptor updates from device or TX IRQ path */
+	rmb();
+	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
+	if (cur_p->cntrl)
 		return NETDEV_TX_BUSY;
 	return 0;
+}
+
+/**
+ * axienet_start_xmit_done - Invoked once a transmit is completed by the
+ * Axi DMA Tx channel.
+ * @ndev:	Pointer to the net_device structure
+ *
+ * This function is invoked from the Axi DMA Tx isr to notify the completion
+ * of transmit operation. It clears fields in the corresponding Tx BDs and
+ * unmaps the corresponding buffer so that CPU can regain ownership of the
+ * buffer. It finally invokes "netif_wake_queue" to restart transmission if
+ * required.
+ */
+static void axienet_start_xmit_done(struct net_device *ndev)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+	u32 packets = 0;
+	u32 size = 0;
+
+	packets = axienet_free_tx_chain(ndev, lp->tx_bd_ci, -1, &size);
+
+	lp->tx_bd_ci += packets;
+	if (lp->tx_bd_ci >= lp->tx_bd_num)
+		lp->tx_bd_ci -= lp->tx_bd_num;
+
+	ndev->stats.tx_packets += packets;
+	ndev->stats.tx_bytes += size;
+
+	/* Matches barrier in axienet_start_xmit */
+	smp_mb();
+
+	if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+		netif_wake_queue(ndev);
 }
 
 /**
@@ -675,27 +740,23 @@
 	u32 csum_start_off;
 	u32 csum_index_off;
 	skb_frag_t *frag;
-	dma_addr_t tail_p;
+	dma_addr_t tail_p, phys;
 	struct axienet_local *lp = netdev_priv(ndev);
 	struct axidma_bd *cur_p;
+	u32 orig_tail_ptr = lp->tx_bd_tail;
 
 	num_frag = skb_shinfo(skb)->nr_frags;
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
 	if (axienet_check_tx_bd_space(lp, num_frag + 1)) {
-		if (netif_queue_stopped(ndev))
-			return NETDEV_TX_BUSY;
-
+		/* Should not happen as last start_xmit call should have
+		 * checked for sufficient space and queue should only be
+		 * woken when sufficient space is available.
+		 */
 		netif_stop_queue(ndev);
-
-		/* Matches barrier in axienet_start_xmit_done */
-		smp_mb();
-
-		/* Space might have just been freed - check again */
-		if (axienet_check_tx_bd_space(lp, num_frag + 1))
-			return NETDEV_TX_BUSY;
-
-		netif_wake_queue(ndev);
+		if (net_ratelimit())
+			netdev_warn(ndev, "TX ring unexpectedly full\n");
+		return NETDEV_TX_BUSY;
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -713,30 +774,60 @@
 		cur_p->app0 |= 2; /* Tx Full Checksum Offload Enabled */
 	}
 
+	phys = dma_map_single(ndev->dev.parent, skb->data,
+			      skb_headlen(skb), DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(ndev->dev.parent, phys))) {
+		if (net_ratelimit())
+			netdev_err(ndev, "TX DMA mapping error\n");
+		ndev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+	desc_set_phys_addr(lp, phys, cur_p);
 	cur_p->cntrl = skb_headlen(skb) | XAXIDMA_BD_CTRL_TXSOF_MASK;
-	cur_p->phys = dma_map_single(ndev->dev.parent, skb->data,
-				     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,
-					     skb_frag_address(frag),
-					     skb_frag_size(frag),
-					     DMA_TO_DEVICE);
+		phys = dma_map_single(ndev->dev.parent,
+				      skb_frag_address(frag),
+				      skb_frag_size(frag),
+				      DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(ndev->dev.parent, phys))) {
+			if (net_ratelimit())
+				netdev_err(ndev, "TX DMA mapping error\n");
+			ndev->stats.tx_dropped++;
+			axienet_free_tx_chain(ndev, orig_tail_ptr, ii + 1,
+					      NULL);
+			lp->tx_bd_tail = orig_tail_ptr;
+
+			return NETDEV_TX_OK;
+		}
+		desc_set_phys_addr(lp, phys, cur_p);
 		cur_p->cntrl = skb_frag_size(frag);
 	}
 
 	cur_p->cntrl |= XAXIDMA_BD_CTRL_TXEOF_MASK;
-	cur_p->app4 = (unsigned long)skb;
+	cur_p->skb = skb;
 
 	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;
+	axienet_dma_out_addr(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
+	if (++lp->tx_bd_tail >= lp->tx_bd_num)
+		lp->tx_bd_tail = 0;
+
+	/* Stop queue if next transmit may not have space */
+	if (axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
+		netif_stop_queue(ndev);
+
+		/* Matches barrier in axienet_start_xmit_done */
+		smp_mb();
+
+		/* Space might have just been freed - check again */
+		if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+			netif_wake_queue(ndev);
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -764,52 +855,78 @@
 	cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 
 	while ((cur_p->status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
-		tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
-		skb = (struct sk_buff *) (cur_p->sw_id_offset);
-		length = cur_p->app4 & 0x0000FFFF;
+		dma_addr_t phys;
 
-		dma_unmap_single(ndev->dev.parent, cur_p->phys,
-				 lp->max_frm_size,
-				 DMA_FROM_DEVICE);
+		/* Ensure we see complete descriptor update */
+		dma_rmb();
 
-		skb_put(skb, length);
-		skb->protocol = eth_type_trans(skb, ndev);
-		/*skb_checksum_none_assert(skb);*/
-		skb->ip_summed = CHECKSUM_NONE;
+		skb = cur_p->skb;
+		cur_p->skb = NULL;
 
-		/* if we're doing Rx csum offload, set it up */
-		if (lp->features & XAE_FEATURE_FULL_RX_CSUM) {
-			csumstatus = (cur_p->app2 &
-				      XAE_FULL_CSUM_STATUS_MASK) >> 3;
-			if ((csumstatus == XAE_IP_TCP_CSUM_VALIDATED) ||
-			    (csumstatus == XAE_IP_UDP_CSUM_VALIDATED)) {
-				skb->ip_summed = CHECKSUM_UNNECESSARY;
+		/* skb could be NULL if a previous pass already received the
+		 * packet for this slot in the ring, but failed to refill it
+		 * with a newly allocated buffer. In this case, don't try to
+		 * receive it again.
+		 */
+		if (likely(skb)) {
+			length = cur_p->app4 & 0x0000FFFF;
+
+			phys = desc_get_phys_addr(lp, cur_p);
+			dma_unmap_single(ndev->dev.parent, phys, lp->max_frm_size,
+					 DMA_FROM_DEVICE);
+
+			skb_put(skb, length);
+			skb->protocol = eth_type_trans(skb, ndev);
+			/*skb_checksum_none_assert(skb);*/
+			skb->ip_summed = CHECKSUM_NONE;
+
+			/* if we're doing Rx csum offload, set it up */
+			if (lp->features & XAE_FEATURE_FULL_RX_CSUM) {
+				csumstatus = (cur_p->app2 &
+					      XAE_FULL_CSUM_STATUS_MASK) >> 3;
+				if (csumstatus == XAE_IP_TCP_CSUM_VALIDATED ||
+				    csumstatus == XAE_IP_UDP_CSUM_VALIDATED) {
+					skb->ip_summed = CHECKSUM_UNNECESSARY;
+				}
+			} else if ((lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) != 0 &&
+				   skb->protocol == htons(ETH_P_IP) &&
+				   skb->len > 64) {
+				skb->csum = be32_to_cpu(cur_p->app3 & 0xFFFF);
+				skb->ip_summed = CHECKSUM_COMPLETE;
 			}
-		} else if ((lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) != 0 &&
-			   skb->protocol == htons(ETH_P_IP) &&
-			   skb->len > 64) {
-			skb->csum = be32_to_cpu(cur_p->app3 & 0xFFFF);
-			skb->ip_summed = CHECKSUM_COMPLETE;
+
+			netif_rx(skb);
+
+			size += length;
+			packets++;
 		}
-
-		netif_rx(skb);
-
-		size += length;
-		packets++;
 
 		new_skb = netdev_alloc_skb_ip_align(ndev, lp->max_frm_size);
 		if (!new_skb)
-			return;
+			break;
 
-		cur_p->phys = dma_map_single(ndev->dev.parent, new_skb->data,
-					     lp->max_frm_size,
-					     DMA_FROM_DEVICE);
+		phys = dma_map_single(ndev->dev.parent, new_skb->data,
+				      lp->max_frm_size,
+				      DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(ndev->dev.parent, phys))) {
+			if (net_ratelimit())
+				netdev_err(ndev, "RX DMA mapping error\n");
+			dev_kfree_skb(new_skb);
+			break;
+		}
+		desc_set_phys_addr(lp, phys, cur_p);
+
 		cur_p->cntrl = lp->max_frm_size;
 		cur_p->status = 0;
-		cur_p->sw_id_offset = (u32) new_skb;
+		cur_p->skb = new_skb;
 
-		++lp->rx_bd_ci;
-		lp->rx_bd_ci %= RX_BD_NUM;
+		/* Only update tail_p to mark this slot as usable after it has
+		 * been successfully refilled.
+		 */
+		tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
+
+		if (++lp->rx_bd_ci >= lp->rx_bd_num)
+			lp->rx_bd_ci = 0;
 		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 	}
 
@@ -817,7 +934,7 @@
 	ndev->stats.rx_bytes += size;
 
 	if (tail_p)
-		axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
+		axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
 }
 
 /**
@@ -825,7 +942,7 @@
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * Return: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED if device generated a TX interrupt, IRQ_NONE otherwise.
  *
  * This is the Axi DMA Tx done Isr. It invokes "axienet_start_xmit_done"
  * to complete the BD processing.
@@ -844,10 +961,11 @@
 		goto out;
 	}
 	if (!(status & XAXIDMA_IRQ_ALL_MASK))
-		dev_err(&ndev->dev, "No interrupts asserted in Tx path\n");
+		return IRQ_NONE;
 	if (status & XAXIDMA_IRQ_ERROR_MASK) {
 		dev_err(&ndev->dev, "DMA Tx error 0x%x\n", status);
-		dev_err(&ndev->dev, "Current BD is at: 0x%x\n",
+		dev_err(&ndev->dev, "Current BD is at: 0x%x%08x\n",
+			(lp->tx_bd_v[lp->tx_bd_ci]).phys_msb,
 			(lp->tx_bd_v[lp->tx_bd_ci]).phys);
 
 		cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
@@ -862,7 +980,7 @@
 		/* Write to the Rx channel control register */
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
 
-		tasklet_schedule(&lp->dma_err_tasklet);
+		schedule_work(&lp->dma_err_task);
 		axienet_dma_out32(lp, XAXIDMA_TX_SR_OFFSET, status);
 	}
 out:
@@ -874,7 +992,7 @@
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * Return: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED if device generated a RX interrupt, IRQ_NONE otherwise.
  *
  * This is the Axi DMA Rx Isr. It invokes "axienet_recv" to complete the BD
  * processing.
@@ -893,10 +1011,11 @@
 		goto out;
 	}
 	if (!(status & XAXIDMA_IRQ_ALL_MASK))
-		dev_err(&ndev->dev, "No interrupts asserted in Rx path\n");
+		return IRQ_NONE;
 	if (status & XAXIDMA_IRQ_ERROR_MASK) {
 		dev_err(&ndev->dev, "DMA Rx error 0x%x\n", status);
-		dev_err(&ndev->dev, "Current BD is at: 0x%x\n",
+		dev_err(&ndev->dev, "Current BD is at: 0x%x%08x\n",
+			(lp->rx_bd_v[lp->rx_bd_ci]).phys_msb,
 			(lp->rx_bd_v[lp->rx_bd_ci]).phys);
 
 		cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
@@ -911,14 +1030,43 @@
 		/* write to the Rx channel control register */
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
 
-		tasklet_schedule(&lp->dma_err_tasklet);
+		schedule_work(&lp->dma_err_task);
 		axienet_dma_out32(lp, XAXIDMA_RX_SR_OFFSET, status);
 	}
 out:
 	return IRQ_HANDLED;
 }
 
-static void axienet_dma_err_handler(unsigned long data);
+/**
+ * axienet_eth_irq - Ethernet core Isr.
+ * @irq:	irq number
+ * @_ndev:	net_device pointer
+ *
+ * Return: IRQ_HANDLED if device generated a core interrupt, IRQ_NONE otherwise.
+ *
+ * Handle miscellaneous conditions indicated by Ethernet core IRQ.
+ */
+static irqreturn_t axienet_eth_irq(int irq, void *_ndev)
+{
+	struct net_device *ndev = _ndev;
+	struct axienet_local *lp = netdev_priv(ndev);
+	unsigned int pending;
+
+	pending = axienet_ior(lp, XAE_IP_OFFSET);
+	if (!pending)
+		return IRQ_NONE;
+
+	if (pending & XAE_INT_RXFIFOOVR_MASK)
+		ndev->stats.rx_missed_errors++;
+
+	if (pending & XAE_INT_RXRJECT_MASK)
+		ndev->stats.rx_frame_errors++;
+
+	axienet_iow(lp, XAE_IS_OFFSET, pending);
+	return IRQ_HANDLED;
+}
+
+static void axienet_dma_err_handler(struct work_struct *work);
 
 /**
  * axienet_open - Driver open routine.
@@ -927,68 +1075,73 @@
  * Return: 0, on success.
  *	    non-zero error value on failure
  *
- * This is the driver open routine. It calls phy_start to start the PHY device.
+ * This is the driver open routine. It calls phylink_start to start the
+ * PHY device.
  * It also allocates interrupt service routines, enables the interrupt lines
  * and ISR handling. Axi Ethernet core is reset through Axi DMA core. Buffer
  * descriptors are initialized.
  */
 static int axienet_open(struct net_device *ndev)
 {
-	int ret, mdio_mcreg;
+	int ret;
 	struct axienet_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = NULL;
 
 	dev_dbg(&ndev->dev, "axienet_open()\n");
 
-	mdio_mcreg = axienet_ior(lp, XAE_MDIO_MC_OFFSET);
-	ret = axienet_mdio_wait_until_ready(lp);
-	if (ret < 0)
-		return ret;
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
-	 * including the MDIO. If MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards.
+	 * including the MDIO. MDIO must be disabled before resetting
+	 * and re-enabled afterwards.
+	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET,
-		    (mdio_mcreg & (~XAE_MDIO_MC_MDIOEN_MASK)));
-	axienet_device_reset(ndev);
-	/* Enable the MDIO */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, mdio_mcreg);
-	ret = axienet_mdio_wait_until_ready(lp);
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
+	ret = axienet_device_reset(ndev);
+	if (ret == 0)
+		ret = axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
 	if (ret < 0)
 		return ret;
 
-	if (lp->phy_node) {
-		phydev = of_phy_connect(lp->ndev, lp->phy_node,
-					axienet_adjust_link, 0, lp->phy_mode);
-
-		if (!phydev)
-			dev_err(lp->dev, "of_phy_connect() failed\n");
-		else
-			phy_start(phydev);
+	ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
+	if (ret) {
+		dev_err(lp->dev, "phylink_of_phy_connect() failed: %d\n", ret);
+		return ret;
 	}
 
-	/* Enable tasklets for Axi DMA error handling */
-	tasklet_init(&lp->dma_err_tasklet, axienet_dma_err_handler,
-		     (unsigned long) lp);
+	phylink_start(lp->phylink);
+
+	/* Enable worker thread for Axi DMA error handling */
+	INIT_WORK(&lp->dma_err_task, axienet_dma_err_handler);
 
 	/* Enable interrupts for Axi DMA Tx */
-	ret = request_irq(lp->tx_irq, axienet_tx_irq, 0, ndev->name, ndev);
+	ret = request_irq(lp->tx_irq, axienet_tx_irq, IRQF_SHARED,
+			  ndev->name, ndev);
 	if (ret)
 		goto err_tx_irq;
 	/* Enable interrupts for Axi DMA Rx */
-	ret = request_irq(lp->rx_irq, axienet_rx_irq, 0, ndev->name, ndev);
+	ret = request_irq(lp->rx_irq, axienet_rx_irq, IRQF_SHARED,
+			  ndev->name, ndev);
 	if (ret)
 		goto err_rx_irq;
+	/* Enable interrupts for Axi Ethernet core (if defined) */
+	if (lp->eth_irq > 0) {
+		ret = request_irq(lp->eth_irq, axienet_eth_irq, IRQF_SHARED,
+				  ndev->name, ndev);
+		if (ret)
+			goto err_eth_irq;
+	}
 
 	return 0;
 
+err_eth_irq:
+	free_irq(lp->rx_irq, ndev);
 err_rx_irq:
 	free_irq(lp->tx_irq, ndev);
 err_tx_irq:
-	if (phydev)
-		phy_disconnect(phydev);
-	tasklet_kill(&lp->dma_err_tasklet);
+	phylink_stop(lp->phylink);
+	phylink_disconnect_phy(lp->phylink);
+	cancel_work_sync(&lp->dma_err_task);
 	dev_err(lp->dev, "request_irq() failed\n");
 	return ret;
 }
@@ -999,33 +1152,60 @@
  *
  * Return: 0, on success.
  *
- * This is the driver stop routine. It calls phy_disconnect to stop the PHY
+ * This is the driver stop routine. It calls phylink_disconnect to stop the PHY
  * device. It also removes the interrupt handlers and disables the interrupts.
  * The Axi DMA Tx/Rx BDs are released.
  */
 static int axienet_stop(struct net_device *ndev)
 {
-	u32 cr;
+	u32 cr, sr;
+	int count;
 	struct axienet_local *lp = netdev_priv(ndev);
 
 	dev_dbg(&ndev->dev, "axienet_close()\n");
 
-	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
-	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
-			  cr & (~XAXIDMA_CR_RUNSTOP_MASK));
-	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
-	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
-			  cr & (~XAXIDMA_CR_RUNSTOP_MASK));
+	phylink_stop(lp->phylink);
+	phylink_disconnect_phy(lp->phylink);
+
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 
-	tasklet_kill(&lp->dma_err_tasklet);
+	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
 
+	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+
+	axienet_iow(lp, XAE_IE_OFFSET, 0);
+
+	/* Give DMAs a chance to halt gracefully */
+	sr = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	for (count = 0; !(sr & XAXIDMA_SR_HALT_MASK) && count < 5; ++count) {
+		msleep(20);
+		sr = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	}
+
+	sr = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	for (count = 0; !(sr & XAXIDMA_SR_HALT_MASK) && count < 5; ++count) {
+		msleep(20);
+		sr = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	}
+
+	/* Do a reset to ensure DMA is really stopped */
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
+	__axienet_device_reset(lp);
+	axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
+
+	cancel_work_sync(&lp->dma_err_task);
+
+	if (lp->eth_irq > 0)
+		free_irq(lp->eth_irq, ndev);
 	free_irq(lp->tx_irq, ndev);
 	free_irq(lp->rx_irq, ndev);
-
-	if (ndev->phydev)
-		phy_disconnect(ndev->phydev);
 
 	axienet_dma_bd_release(ndev);
 	return 0;
@@ -1078,6 +1258,16 @@
 }
 #endif
 
+static int axienet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	return phylink_mii_ioctl(lp->phylink, rq, cmd);
+}
+
 static const struct net_device_ops axienet_netdev_ops = {
 	.ndo_open = axienet_open,
 	.ndo_stop = axienet_stop,
@@ -1085,6 +1275,7 @@
 	.ndo_change_mtu	= axienet_change_mtu,
 	.ndo_set_mac_address = netdev_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
+	.ndo_do_ioctl = axienet_ioctl,
 	.ndo_set_rx_mode = axienet_set_multicast_list,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = axienet_poll_controller,
@@ -1165,15 +1356,54 @@
 	data[20] = axienet_ior(lp, XAE_MDIO_MCR_OFFSET);
 	data[21] = axienet_ior(lp, XAE_MDIO_MWD_OFFSET);
 	data[22] = axienet_ior(lp, XAE_MDIO_MRD_OFFSET);
-	data[23] = axienet_ior(lp, XAE_MDIO_MIS_OFFSET);
-	data[24] = axienet_ior(lp, XAE_MDIO_MIP_OFFSET);
-	data[25] = axienet_ior(lp, XAE_MDIO_MIE_OFFSET);
-	data[26] = axienet_ior(lp, XAE_MDIO_MIC_OFFSET);
 	data[27] = axienet_ior(lp, XAE_UAW0_OFFSET);
 	data[28] = axienet_ior(lp, XAE_UAW1_OFFSET);
 	data[29] = axienet_ior(lp, XAE_FMI_OFFSET);
 	data[30] = axienet_ior(lp, XAE_AF0_OFFSET);
 	data[31] = axienet_ior(lp, XAE_AF1_OFFSET);
+	data[32] = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+	data[33] = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	data[34] = axienet_dma_in32(lp, XAXIDMA_TX_CDESC_OFFSET);
+	data[35] = axienet_dma_in32(lp, XAXIDMA_TX_TDESC_OFFSET);
+	data[36] = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+	data[37] = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	data[38] = axienet_dma_in32(lp, XAXIDMA_RX_CDESC_OFFSET);
+	data[39] = axienet_dma_in32(lp, XAXIDMA_RX_TDESC_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->tx_pending < TX_BD_NUM_MIN ||
+	    ering->tx_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;
 }
 
 /**
@@ -1189,12 +1419,9 @@
 axienet_ethtools_get_pauseparam(struct net_device *ndev,
 				struct ethtool_pauseparam *epauseparm)
 {
-	u32 regval;
 	struct axienet_local *lp = netdev_priv(ndev);
-	epauseparm->autoneg  = 0;
-	regval = axienet_ior(lp, XAE_FCC_OFFSET);
-	epauseparm->tx_pause = regval & XAE_FCC_FCTX_MASK;
-	epauseparm->rx_pause = regval & XAE_FCC_FCRX_MASK;
+
+	phylink_ethtool_get_pauseparam(lp->phylink, epauseparm);
 }
 
 /**
@@ -1213,27 +1440,9 @@
 axienet_ethtools_set_pauseparam(struct net_device *ndev,
 				struct ethtool_pauseparam *epauseparm)
 {
-	u32 regval = 0;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	if (netif_running(ndev)) {
-		netdev_err(ndev,
-			   "Please stop netif before applying configuration\n");
-		return -EFAULT;
-	}
-
-	regval = axienet_ior(lp, XAE_FCC_OFFSET);
-	if (epauseparm->tx_pause)
-		regval |= XAE_FCC_FCTX_MASK;
-	else
-		regval &= ~XAE_FCC_FCTX_MASK;
-	if (epauseparm->rx_pause)
-		regval |= XAE_FCC_FCRX_MASK;
-	else
-		regval &= ~XAE_FCC_FCRX_MASK;
-	axienet_iow(lp, XAE_FCC_OFFSET, regval);
-
-	return 0;
+	return phylink_ethtool_set_pauseparam(lp->phylink, epauseparm);
 }
 
 /**
@@ -1283,27 +1492,6 @@
 		return -EFAULT;
 	}
 
-	if ((ecoalesce->rx_coalesce_usecs) ||
-	    (ecoalesce->rx_coalesce_usecs_irq) ||
-	    (ecoalesce->rx_max_coalesced_frames_irq) ||
-	    (ecoalesce->tx_coalesce_usecs) ||
-	    (ecoalesce->tx_coalesce_usecs_irq) ||
-	    (ecoalesce->tx_max_coalesced_frames_irq) ||
-	    (ecoalesce->stats_block_coalesce_usecs) ||
-	    (ecoalesce->use_adaptive_rx_coalesce) ||
-	    (ecoalesce->use_adaptive_tx_coalesce) ||
-	    (ecoalesce->pkt_rate_low) ||
-	    (ecoalesce->rx_coalesce_usecs_low) ||
-	    (ecoalesce->rx_max_coalesced_frames_low) ||
-	    (ecoalesce->tx_coalesce_usecs_low) ||
-	    (ecoalesce->tx_max_coalesced_frames_low) ||
-	    (ecoalesce->pkt_rate_high) ||
-	    (ecoalesce->rx_coalesce_usecs_high) ||
-	    (ecoalesce->rx_max_coalesced_frames_high) ||
-	    (ecoalesce->tx_coalesce_usecs_high) ||
-	    (ecoalesce->tx_max_coalesced_frames_high) ||
-	    (ecoalesce->rate_sample_interval))
-		return -EOPNOTSUPP;
 	if (ecoalesce->rx_max_coalesced_frames)
 		lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames;
 	if (ecoalesce->tx_max_coalesced_frames)
@@ -1312,63 +1500,241 @@
 	return 0;
 }
 
+static int
+axienet_ethtools_get_link_ksettings(struct net_device *ndev,
+				    struct ethtool_link_ksettings *cmd)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	return phylink_ethtool_ksettings_get(lp->phylink, cmd);
+}
+
+static int
+axienet_ethtools_set_link_ksettings(struct net_device *ndev,
+				    const struct ethtool_link_ksettings *cmd)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	return phylink_ethtool_ksettings_set(lp->phylink, cmd);
+}
+
 static const struct ethtool_ops axienet_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES,
 	.get_drvinfo    = axienet_ethtools_get_drvinfo,
 	.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,
 	.set_coalesce   = axienet_ethtools_set_coalesce,
-	.get_link_ksettings = phy_ethtool_get_link_ksettings,
-	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_link_ksettings = axienet_ethtools_get_link_ksettings,
+	.set_link_ksettings = axienet_ethtools_set_link_ksettings,
+};
+
+static void axienet_validate(struct phylink_config *config,
+			     unsigned long *supported,
+			     struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+	/* Only support the mode we are configured for */
+	if (state->interface != PHY_INTERFACE_MODE_NA &&
+	    state->interface != lp->phy_mode) {
+		netdev_warn(ndev, "Cannot use PHY mode %s, supported: %s\n",
+			    phy_modes(state->interface),
+			    phy_modes(lp->phy_mode));
+		bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+		return;
+	}
+
+	phylink_set(mask, Autoneg);
+	phylink_set_port_modes(mask);
+
+	phylink_set(mask, Asym_Pause);
+	phylink_set(mask, Pause);
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_NA:
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_GMII:
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		phylink_set(mask, 1000baseX_Full);
+		phylink_set(mask, 1000baseT_Full);
+		if (state->interface == PHY_INTERFACE_MODE_1000BASEX)
+			break;
+		fallthrough;
+	case PHY_INTERFACE_MODE_MII:
+		phylink_set(mask, 100baseT_Full);
+		phylink_set(mask, 10baseT_Full);
+	default:
+		break;
+	}
+
+	bitmap_and(supported, supported, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static void axienet_mac_pcs_get_state(struct phylink_config *config,
+				      struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+		phylink_mii_c22_pcs_get_state(lp->pcs_phy, state);
+		break;
+	default:
+		break;
+	}
+}
+
+static void axienet_mac_an_restart(struct phylink_config *config)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	phylink_mii_c22_pcs_an_restart(lp->pcs_phy);
+}
+
+static void axienet_mac_config(struct phylink_config *config, unsigned int mode,
+			       const struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	int ret;
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
+		ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode,
+						 state->interface,
+						 state->advertising);
+		if (ret < 0)
+			netdev_warn(ndev, "Failed to configure PCS: %d\n",
+				    ret);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void axienet_mac_link_down(struct phylink_config *config,
+				  unsigned int mode,
+				  phy_interface_t interface)
+{
+	/* nothing meaningful to do */
+}
+
+static void axienet_mac_link_up(struct phylink_config *config,
+				struct phy_device *phy,
+				unsigned int mode, phy_interface_t interface,
+				int speed, int duplex,
+				bool tx_pause, bool rx_pause)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	u32 emmc_reg, fcc_reg;
+
+	emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
+	emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK;
+
+	switch (speed) {
+	case SPEED_1000:
+		emmc_reg |= XAE_EMMC_LINKSPD_1000;
+		break;
+	case SPEED_100:
+		emmc_reg |= XAE_EMMC_LINKSPD_100;
+		break;
+	case SPEED_10:
+		emmc_reg |= XAE_EMMC_LINKSPD_10;
+		break;
+	default:
+		dev_err(&ndev->dev,
+			"Speed other than 10, 100 or 1Gbps is not supported\n");
+		break;
+	}
+
+	axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg);
+
+	fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET);
+	if (tx_pause)
+		fcc_reg |= XAE_FCC_FCTX_MASK;
+	else
+		fcc_reg &= ~XAE_FCC_FCTX_MASK;
+	if (rx_pause)
+		fcc_reg |= XAE_FCC_FCRX_MASK;
+	else
+		fcc_reg &= ~XAE_FCC_FCRX_MASK;
+	axienet_iow(lp, XAE_FCC_OFFSET, fcc_reg);
+}
+
+static const struct phylink_mac_ops axienet_phylink_ops = {
+	.validate = axienet_validate,
+	.mac_pcs_get_state = axienet_mac_pcs_get_state,
+	.mac_an_restart = axienet_mac_an_restart,
+	.mac_config = axienet_mac_config,
+	.mac_link_down = axienet_mac_link_down,
+	.mac_link_up = axienet_mac_link_up,
 };
 
 /**
- * axienet_dma_err_handler - Tasklet handler for Axi DMA Error
- * @data:	Data passed
+ * axienet_dma_err_handler - Work queue task for Axi DMA Error
+ * @work:	pointer to work_struct
  *
  * Resets the Axi DMA and Axi Ethernet devices, and reconfigures the
  * Tx/Rx BDs.
  */
-static void axienet_dma_err_handler(unsigned long data)
+static void axienet_dma_err_handler(struct work_struct *work)
 {
 	u32 axienet_status;
 	u32 cr, i;
-	int mdio_mcreg;
-	struct axienet_local *lp = (struct axienet_local *) data;
+	struct axienet_local *lp = container_of(work, struct axienet_local,
+						dma_err_task);
 	struct net_device *ndev = lp->ndev;
 	struct axidma_bd *cur_p;
 
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
-	mdio_mcreg = axienet_ior(lp, XAE_MDIO_MC_OFFSET);
-	axienet_mdio_wait_until_ready(lp);
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
-	 * including the MDIO. So if MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards.
+	 * including the MDIO. MDIO must be disabled before resetting
+	 * and re-enabled afterwards.
+	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, (mdio_mcreg &
-		    ~XAE_MDIO_MC_MDIOEN_MASK));
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
+	__axienet_device_reset(lp);
+	axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
 
-	__axienet_device_reset(lp, XAXIDMA_TX_CR_OFFSET);
-	__axienet_device_reset(lp, XAXIDMA_RX_CR_OFFSET);
-
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, mdio_mcreg);
-	axienet_mdio_wait_until_ready(lp);
-
-	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,
+		if (cur_p->cntrl) {
+			dma_addr_t addr = desc_get_phys_addr(lp, cur_p);
+
+			dma_unmap_single(ndev->dev.parent, addr,
 					 (cur_p->cntrl &
 					  XAXIDMA_BD_CTRL_LENGTH_MASK),
 					 DMA_TO_DEVICE);
-		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *) cur_p->app4);
+		}
+		if (cur_p->skb)
+			dev_kfree_skb_irq(cur_p->skb);
 		cur_p->phys = 0;
+		cur_p->phys_msb = 0;
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
 		cur_p->app0 = 0;
@@ -1376,10 +1742,10 @@
 		cur_p->app2 = 0;
 		cur_p->app3 = 0;
 		cur_p->app4 = 0;
-		cur_p->sw_id_offset = 0;
+		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;
@@ -1422,18 +1788,18 @@
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
 	 * halted state. This will make the Rx side ready for reception.
 	 */
-	axienet_dma_out32(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
+	axienet_dma_out_addr(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
 	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)));
+	axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
+			     (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
 	 * tail pointer register that the Tx channel will start transmitting
 	 */
-	axienet_dma_out32(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
+	axienet_dma_out_addr(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
@@ -1445,6 +1811,8 @@
 	axienet_status = axienet_ior(lp, XAE_IP_OFFSET);
 	if (axienet_status & XAE_INT_RXRJECT_MASK)
 		axienet_iow(lp, XAE_IS_OFFSET, XAE_INT_RXRJECT_MASK);
+	axienet_iow(lp, XAE_IE_OFFSET, lp->eth_irq > 0 ?
+		    XAE_INT_RECV_ERROR_MASK : 0);
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
 	/* Sync default options with HW but leave receiver and
@@ -1476,7 +1844,8 @@
 	struct axienet_local *lp;
 	struct net_device *ndev;
 	const void *mac_addr;
-	struct resource *ethres, dmares;
+	struct resource *ethres;
+	int addr_width = 32;
 	u32 value;
 
 	ndev = alloc_etherdev(sizeof(*lp));
@@ -1499,14 +1868,29 @@
 	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;
+
+	lp->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(lp->clk)) {
+		ret = PTR_ERR(lp->clk);
+		goto free_netdev;
+	}
+	ret = clk_prepare_enable(lp->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to enable clock: %d\n", ret);
+		goto free_netdev;
+	}
+
 	/* Map device registers */
 	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	lp->regs = devm_ioremap_resource(&pdev->dev, ethres);
 	if (IS_ERR(lp->regs)) {
 		dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n");
 		ret = PTR_ERR(lp->regs);
-		goto free_netdev;
+		goto cleanup_clk;
 	}
+	lp->regs_start = ethres->start;
 
 	/* Setup checksum offload, but default to off if not specified */
 	lp->features = 0;
@@ -1579,70 +1963,156 @@
 			break;
 		default:
 			ret = -EINVAL;
-			goto free_netdev;
+			goto cleanup_clk;
 		}
 	} else {
-		lp->phy_mode = of_get_phy_mode(pdev->dev.of_node);
-		if ((int)lp->phy_mode < 0) {
-			ret = -EINVAL;
-			goto free_netdev;
-		}
+		ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode);
+		if (ret)
+			goto cleanup_clk;
 	}
 
 	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
 	np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
-	if (!np) {
-		dev_err(&pdev->dev, "could not find DMA node\n");
-		ret = -ENODEV;
-		goto free_netdev;
-	}
-	ret = of_address_to_resource(np, 0, &dmares);
-	if (ret) {
-		dev_err(&pdev->dev, "unable to get DMA resource\n");
+	if (np) {
+		struct resource dmares;
+
+		ret = of_address_to_resource(np, 0, &dmares);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"unable to get DMA resource\n");
+			of_node_put(np);
+			goto cleanup_clk;
+		}
+		lp->dma_regs = devm_ioremap_resource(&pdev->dev,
+						     &dmares);
+		lp->rx_irq = irq_of_parse_and_map(np, 1);
+		lp->tx_irq = irq_of_parse_and_map(np, 0);
 		of_node_put(np);
-		goto free_netdev;
+		lp->eth_irq = platform_get_irq_optional(pdev, 0);
+	} else {
+		/* Check for these resources directly on the Ethernet node. */
+		struct resource *res = platform_get_resource(pdev,
+							     IORESOURCE_MEM, 1);
+		lp->dma_regs = devm_ioremap_resource(&pdev->dev, res);
+		lp->rx_irq = platform_get_irq(pdev, 1);
+		lp->tx_irq = platform_get_irq(pdev, 0);
+		lp->eth_irq = platform_get_irq_optional(pdev, 2);
 	}
-	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
 	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
 		ret = PTR_ERR(lp->dma_regs);
-		of_node_put(np);
-		goto free_netdev;
+		goto cleanup_clk;
 	}
-	lp->rx_irq = irq_of_parse_and_map(np, 1);
-	lp->tx_irq = irq_of_parse_and_map(np, 0);
-	of_node_put(np);
 	if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
 		dev_err(&pdev->dev, "could not determine irqs\n");
 		ret = -ENOMEM;
-		goto free_netdev;
+		goto cleanup_clk;
 	}
+
+	/* Reset core now that clocks are enabled, prior to accessing MDIO */
+	ret = __axienet_device_reset(lp);
+	if (ret)
+		goto cleanup_clk;
+
+	/* Autodetect the need for 64-bit DMA pointers.
+	 * When the IP is configured for a bus width bigger than 32 bits,
+	 * writing the MSB registers is mandatory, even if they are all 0.
+	 * We can detect this case by writing all 1's to one such register
+	 * and see if that sticks: when the IP is configured for 32 bits
+	 * only, those registers are RES0.
+	 * Those MSB registers were introduced in IP v7.1, which we check first.
+	 */
+	if ((axienet_ior(lp, XAE_ID_OFFSET) >> 24) >= 0x9) {
+		void __iomem *desc = lp->dma_regs + XAXIDMA_TX_CDESC_OFFSET + 4;
+
+		iowrite32(0x0, desc);
+		if (ioread32(desc) == 0) {	/* sanity check */
+			iowrite32(0xffffffff, desc);
+			if (ioread32(desc) > 0) {
+				lp->features |= XAE_FEATURE_DMA_64BIT;
+				addr_width = 64;
+				dev_info(&pdev->dev,
+					 "autodetected 64-bit DMA range\n");
+			}
+			iowrite32(0x0, desc);
+		}
+	}
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
+	if (ret) {
+		dev_err(&pdev->dev, "No suitable DMA available\n");
+		goto cleanup_clk;
+	}
+
+	/* Check for Ethernet core IRQ (optional) */
+	if (lp->eth_irq <= 0)
+		dev_info(&pdev->dev, "Ethernet core IRQ not defined\n");
 
 	/* Retrieve the MAC address */
 	mac_addr = of_get_mac_address(pdev->dev.of_node);
-	if (!mac_addr) {
-		dev_err(&pdev->dev, "could not find MAC address\n");
-		goto free_netdev;
+	if (IS_ERR(mac_addr)) {
+		dev_warn(&pdev->dev, "could not find MAC address property: %ld\n",
+			 PTR_ERR(mac_addr));
+		mac_addr = NULL;
 	}
 	axienet_set_mac_address(ndev, mac_addr);
 
 	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 
-	lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
-	if (lp->phy_node) {
-		ret = axienet_mdio_setup(lp, pdev->dev.of_node);
-		if (ret)
-			dev_warn(&pdev->dev, "error registering MDIO bus\n");
+	ret = axienet_mdio_setup(lp);
+	if (ret)
+		dev_warn(&pdev->dev,
+			 "error registering MDIO bus: %d\n", ret);
+
+	if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII ||
+	    lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) {
+		lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+		if (!lp->phy_node) {
+			dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n");
+			ret = -EINVAL;
+			goto cleanup_mdio;
+		}
+		lp->pcs_phy = of_mdio_find_device(lp->phy_node);
+		if (!lp->pcs_phy) {
+			ret = -EPROBE_DEFER;
+			goto cleanup_mdio;
+		}
+		lp->phylink_config.pcs_poll = true;
+	}
+
+	lp->phylink_config.dev = &ndev->dev;
+	lp->phylink_config.type = PHYLINK_NETDEV;
+
+	lp->phylink = phylink_create(&lp->phylink_config, pdev->dev.fwnode,
+				     lp->phy_mode,
+				     &axienet_phylink_ops);
+	if (IS_ERR(lp->phylink)) {
+		ret = PTR_ERR(lp->phylink);
+		dev_err(&pdev->dev, "phylink_create error (%i)\n", ret);
+		goto cleanup_mdio;
 	}
 
 	ret = register_netdev(lp->ndev);
 	if (ret) {
 		dev_err(lp->dev, "register_netdev() error (%i)\n", ret);
-		goto free_netdev;
+		goto cleanup_phylink;
 	}
 
 	return 0;
+
+cleanup_phylink:
+	phylink_destroy(lp->phylink);
+
+cleanup_mdio:
+	if (lp->pcs_phy)
+		put_device(&lp->pcs_phy->dev);
+	if (lp->mii_bus)
+		axienet_mdio_teardown(lp);
+	of_node_put(lp->phy_node);
+
+cleanup_clk:
+	clk_disable_unprepare(lp->clk);
 
 free_netdev:
 	free_netdev(ndev);
@@ -1655,8 +2125,17 @@
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	axienet_mdio_teardown(lp);
 	unregister_netdev(ndev);
+
+	if (lp->phylink)
+		phylink_destroy(lp->phylink);
+
+	if (lp->pcs_phy)
+		put_device(&lp->pcs_phy->dev);
+
+	axienet_mdio_teardown(lp);
+
+	clk_disable_unprepare(lp->clk);
 
 	of_node_put(lp->phy_node);
 	lp->phy_node = NULL;
@@ -1666,9 +2145,23 @@
 	return 0;
 }
 
+static void axienet_shutdown(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+
+	rtnl_lock();
+	netif_device_detach(ndev);
+
+	if (netif_running(ndev))
+		dev_close(ndev);
+
+	rtnl_unlock();
+}
+
 static struct platform_driver axienet_driver = {
 	.probe = axienet_probe,
 	.remove = axienet_remove,
+	.shutdown = axienet_shutdown,
 	.driver = {
 		 .name = "xilinx_axienet",
 		 .of_match_table = axienet_of_match,

--
Gitblit v1.6.2