xref: /linux/drivers/net/ethernet/cadence/macb_main.c (revision 546b928da0427b0d6c663cbb992bd7bfa9ac7971)

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Cadence MACB/GEM Ethernet Controller driver
 *
 * Copyright (C) 2004-2006 Atmel Corporation
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/circ_buf.h>
#include <linux/clk-provider.h>
#include <linux/clk.h>
#include <linux/crc32.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/etherdevice.h>
#include <linux/firmware/xlnx-zynqmp.h>
#include <linux/inetdevice.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/ip.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/netdevice.h>
#include <linux/of.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/phy/phy.h>
#include <linux/phylink.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/ptp_classify.h>
#include <linux/reset.h>
#include <linux/slab.h>
#include <linux/tcp.h>
#include <linux/types.h>
#include <linux/udp.h>
#include <linux/gcd.h>
#include <net/pkt_sched.h>
#include "macb.h"

/* This structure is only used for MACB on SiFive FU540 devices */
struct sifive_fu540_macb_mgmt {
	void __iomem *reg;
	unsigned long rate;
	struct clk_hw hw;
};

#define MACB_RX_BUFFER_SIZE	128
#define RX_BUFFER_MULTIPLE	64  /* bytes */
#define RX_BUFFER_MAX		(0xFF * RX_BUFFER_MULTIPLE) /* 16320 bytes */

#define DEFAULT_RX_RING_SIZE	512 /* must be power of 2 */
#define MIN_RX_RING_SIZE	64
#define MAX_RX_RING_SIZE	8192

#define DEFAULT_TX_RING_SIZE	512 /* must be power of 2 */
#define MIN_TX_RING_SIZE	64
#define MAX_TX_RING_SIZE	4096

/* level of occupied TX descriptors under which we wake up TX process */
#define MACB_TX_WAKEUP_THRESH(bp)	(3 * (bp)->tx_ring_size / 4)

#define MACB_RX_INT_FLAGS	(MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR))
#define MACB_TX_ERR_FLAGS	(MACB_BIT(ISR_TUND)			\
					| MACB_BIT(ISR_RLE)		\
					| MACB_BIT(TXERR))
#define MACB_TX_INT_FLAGS	(MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP)	\
					| MACB_BIT(TXUBR))

#define MACB_INT_MISC_FLAGS	(MACB_TX_ERR_FLAGS | MACB_BIT(RXUBR) | \
				 MACB_BIT(ISR_ROVR) | MACB_BIT(HRESP) | \
				 GEM_BIT(WOL) | MACB_BIT(WOL))

/* Max length of transmit frame must be a multiple of 8 bytes */
#define MACB_TX_LEN_ALIGN	8
#define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a
 * false amba_error in TX path from the DMA assuming there is not enough
 * space in the SRAM (16KB) even when there is.
 */
#define GEM_MAX_TX_LEN		(unsigned int)(0x3FC0)

#define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
#define MACB_NETIF_LSO		NETIF_F_TSO

#define MACB_WOL_ENABLED		BIT(0)

#define HS_SPEED_10000M			4
#define MACB_SERDES_RATE_10G		1

/* Graceful stop timeouts in us. We should allow up to
 * 1 frame time (10 Mbits/s, full-duplex, ignoring collisions)
 */
#define MACB_HALT_TIMEOUT	14000
#define MACB_PM_TIMEOUT  100 /* ms */

#define MACB_MDIO_TIMEOUT	1000000 /* in usecs */

/* DMA buffer descriptor might be different size
 * depends on hardware configuration:
 *
 * 1. dma address width 32 bits:
 *    word 1: 32 bit address of Data Buffer
 *    word 2: control
 *
 * 2. dma address width 64 bits:
 *    word 1: 32 bit address of Data Buffer
 *    word 2: control
 *    word 3: upper 32 bit address of Data Buffer
 *    word 4: unused
 *
 * 3. dma address width 32 bits with hardware timestamping:
 *    word 1: 32 bit address of Data Buffer
 *    word 2: control
 *    word 3: timestamp word 1
 *    word 4: timestamp word 2
 *
 * 4. dma address width 64 bits with hardware timestamping:
 *    word 1: 32 bit address of Data Buffer
 *    word 2: control
 *    word 3: upper 32 bit address of Data Buffer
 *    word 4: unused
 *    word 5: timestamp word 1
 *    word 6: timestamp word 2
 */
static unsigned int macb_dma_desc_get_size(struct macb *bp)
{
	unsigned int desc_size = sizeof(struct macb_dma_desc);

	if (macb_dma64(bp))
		desc_size += sizeof(struct macb_dma_desc_64);
	if (macb_dma_ptp(bp))
		desc_size += sizeof(struct macb_dma_desc_ptp);

	return desc_size;
}

static unsigned int macb_adj_dma_desc_idx(struct macb *bp, unsigned int desc_idx)
{
	return desc_idx * (1 + macb_dma64(bp) + macb_dma_ptp(bp));
}

static struct macb_dma_desc_64 *macb_64b_desc(struct macb *bp, struct macb_dma_desc *desc)
{
	return (struct macb_dma_desc_64 *)((void *)desc
		+ sizeof(struct macb_dma_desc));
}

/* Ring buffer accessors */
static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
{
	return index & (bp->tx_ring_size - 1);
}

static struct macb_dma_desc *macb_tx_desc(struct macb_queue *queue,
					  unsigned int index)
{
	index = macb_tx_ring_wrap(queue->bp, index);
	index = macb_adj_dma_desc_idx(queue->bp, index);
	return &queue->tx_ring[index];
}

static struct macb_tx_skb *macb_tx_skb(struct macb_queue *queue,
				       unsigned int index)
{
	return &queue->tx_skb[macb_tx_ring_wrap(queue->bp, index)];
}

static dma_addr_t macb_tx_dma(struct macb_queue *queue, unsigned int index)
{
	dma_addr_t offset;

	offset = macb_tx_ring_wrap(queue->bp, index) *
			macb_dma_desc_get_size(queue->bp);

	return queue->tx_ring_dma + offset;
}

static unsigned int macb_rx_ring_wrap(struct macb *bp, unsigned int index)
{
	return index & (bp->rx_ring_size - 1);
}

static struct macb_dma_desc *macb_rx_desc(struct macb_queue *queue, unsigned int index)
{
	index = macb_rx_ring_wrap(queue->bp, index);
	index = macb_adj_dma_desc_idx(queue->bp, index);
	return &queue->rx_ring[index];
}

static void *macb_rx_buffer(struct macb_queue *queue, unsigned int index)
{
	return queue->rx_buffers + queue->bp->rx_buffer_size *
	       macb_rx_ring_wrap(queue->bp, index);
}

/* I/O accessors */
static u32 hw_readl_native(struct macb *bp, int offset)
{
	return __raw_readl(bp->regs + offset);
}

static void hw_writel_native(struct macb *bp, int offset, u32 value)
{
	__raw_writel(value, bp->regs + offset);
}

static u32 hw_readl(struct macb *bp, int offset)
{
	return readl_relaxed(bp->regs + offset);
}

static void hw_writel(struct macb *bp, int offset, u32 value)
{
	writel_relaxed(value, bp->regs + offset);
}

/* Find the CPU endianness by using the loopback bit of NCR register. When the
 * CPU is in big endian we need to program swapped mode for management
 * descriptor access.
 */
static bool hw_is_native_io(void __iomem *addr)
{
	u32 value = MACB_BIT(LLB);

	__raw_writel(value, addr + MACB_NCR);
	value = __raw_readl(addr + MACB_NCR);

	/* Write 0 back to disable everything */
	__raw_writel(0, addr + MACB_NCR);

	return value == MACB_BIT(LLB);
}

static bool hw_is_gem(void __iomem *addr, bool native_io)
{
	u32 id;

	if (native_io)
		id = __raw_readl(addr + MACB_MID);
	else
		id = readl_relaxed(addr + MACB_MID);

	return MACB_BFEXT(IDNUM, id) >= 0x2;
}

static void macb_set_hwaddr(struct macb *bp)
{
	u32 bottom;
	u16 top;

	bottom = get_unaligned_le32(bp->netdev->dev_addr);
	macb_or_gem_writel(bp, SA1B, bottom);
	top = get_unaligned_le16(bp->netdev->dev_addr + 4);
	macb_or_gem_writel(bp, SA1T, top);

	if (gem_has_ptp(bp)) {
		gem_writel(bp, RXPTPUNI, bottom);
		gem_writel(bp, TXPTPUNI, bottom);
	}

	/* Clear unused address register sets */
	macb_or_gem_writel(bp, SA2B, 0);
	macb_or_gem_writel(bp, SA2T, 0);
	macb_or_gem_writel(bp, SA3B, 0);
	macb_or_gem_writel(bp, SA3T, 0);
	macb_or_gem_writel(bp, SA4B, 0);
	macb_or_gem_writel(bp, SA4T, 0);
}

static void macb_get_hwaddr(struct macb *bp)
{
	u32 bottom;
	u16 top;
	u8 addr[6];
	int i;

	/* Check all 4 address register for valid address */
	for (i = 0; i < 4; i++) {
		bottom = macb_or_gem_readl(bp, SA1B + i * 8);
		top = macb_or_gem_readl(bp, SA1T + i * 8);

		addr[0] = bottom & 0xff;
		addr[1] = (bottom >> 8) & 0xff;
		addr[2] = (bottom >> 16) & 0xff;
		addr[3] = (bottom >> 24) & 0xff;
		addr[4] = top & 0xff;
		addr[5] = (top >> 8) & 0xff;

		if (is_valid_ether_addr(addr)) {
			eth_hw_addr_set(bp->netdev, addr);
			return;
		}
	}

	dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
	eth_hw_addr_random(bp->netdev);
}

static int macb_mdio_wait_for_idle(struct macb *bp)
{
	u32 val;

	return readx_poll_timeout(MACB_READ_NSR, bp, val, val & MACB_BIT(IDLE),
				  1, MACB_MDIO_TIMEOUT);
}

static int macb_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum)
{
	struct macb *bp = bus->priv;
	int status;

	status = pm_runtime_resume_and_get(&bp->pdev->dev);
	if (status < 0)
		goto mdio_pm_exit;

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_read_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF)
			      | MACB_BF(RW, MACB_MAN_C22_READ)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, regnum)
			      | MACB_BF(CODE, MACB_MAN_C22_CODE)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_read_exit;

	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));

mdio_read_exit:
	pm_runtime_put_autosuspend(&bp->pdev->dev);
mdio_pm_exit:
	return status;
}

static int macb_mdio_read_c45(struct mii_bus *bus, int mii_id, int devad,
			      int regnum)
{
	struct macb *bp = bus->priv;
	int status;

	status = pm_runtime_get_sync(&bp->pdev->dev);
	if (status < 0) {
		pm_runtime_put_noidle(&bp->pdev->dev);
		goto mdio_pm_exit;
	}

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_read_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
			      | MACB_BF(RW, MACB_MAN_C45_ADDR)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, devad & 0x1F)
			      | MACB_BF(DATA, regnum & 0xFFFF)
			      | MACB_BF(CODE, MACB_MAN_C45_CODE)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_read_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
			      | MACB_BF(RW, MACB_MAN_C45_READ)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, devad & 0x1F)
			      | MACB_BF(CODE, MACB_MAN_C45_CODE)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_read_exit;

	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));

mdio_read_exit:
	pm_runtime_put_autosuspend(&bp->pdev->dev);
mdio_pm_exit:
	return status;
}

static int macb_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum,
			       u16 value)
{
	struct macb *bp = bus->priv;
	int status;

	status = pm_runtime_resume_and_get(&bp->pdev->dev);
	if (status < 0)
		goto mdio_pm_exit;

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_write_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF)
			      | MACB_BF(RW, MACB_MAN_C22_WRITE)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, regnum)
			      | MACB_BF(CODE, MACB_MAN_C22_CODE)
			      | MACB_BF(DATA, value)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_write_exit;

mdio_write_exit:
	pm_runtime_put_autosuspend(&bp->pdev->dev);
mdio_pm_exit:
	return status;
}

static int macb_mdio_write_c45(struct mii_bus *bus, int mii_id,
			       int devad, int regnum,
			       u16 value)
{
	struct macb *bp = bus->priv;
	int status;

	status = pm_runtime_get_sync(&bp->pdev->dev);
	if (status < 0) {
		pm_runtime_put_noidle(&bp->pdev->dev);
		goto mdio_pm_exit;
	}

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_write_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
			      | MACB_BF(RW, MACB_MAN_C45_ADDR)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, devad & 0x1F)
			      | MACB_BF(DATA, regnum & 0xFFFF)
			      | MACB_BF(CODE, MACB_MAN_C45_CODE)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_write_exit;

	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF)
			      | MACB_BF(RW, MACB_MAN_C45_WRITE)
			      | MACB_BF(PHYA, mii_id)
			      | MACB_BF(REGA, devad & 0x1F)
			      | MACB_BF(CODE, MACB_MAN_C45_CODE)
			      | MACB_BF(DATA, value)));

	status = macb_mdio_wait_for_idle(bp);
	if (status < 0)
		goto mdio_write_exit;

mdio_write_exit:
	pm_runtime_put_autosuspend(&bp->pdev->dev);
mdio_pm_exit:
	return status;
}

static void macb_init_buffers(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int q;

	/* Single register for all queues' high 32 bits. */
	if (macb_dma64(bp)) {
		macb_writel(bp, RBQPH,
			    upper_32_bits(bp->queues[0].rx_ring_dma));
		macb_writel(bp, TBQPH,
			    upper_32_bits(bp->queues[0].tx_ring_dma));
	}

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		queue_writel(queue, RBQP, lower_32_bits(queue->rx_ring_dma));
		queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
	}
}

/**
 * macb_set_tx_clk() - Set a clock to a new frequency
 * @bp:		pointer to struct macb
 * @speed:	New frequency in Hz
 */
static void macb_set_tx_clk(struct macb *bp, int speed)
{
	long ferr, rate, rate_rounded;

	if (!bp->tx_clk || (bp->caps & MACB_CAPS_CLK_HW_CHG))
		return;

	/* In case of MII the PHY is the clock master */
	if (bp->phy_interface == PHY_INTERFACE_MODE_MII)
		return;

	rate = rgmii_clock(speed);
	if (rate < 0)
		return;

	rate_rounded = clk_round_rate(bp->tx_clk, rate);
	if (rate_rounded < 0)
		return;

	/* RGMII allows 50 ppm frequency error. Test and warn if this limit
	 * is not satisfied.
	 */
	ferr = abs(rate_rounded - rate);
	ferr = DIV_ROUND_UP(ferr, rate / 100000);
	if (ferr > 5)
		netdev_warn(bp->netdev,
			    "unable to generate target frequency: %ld Hz\n",
			    rate);

	if (clk_set_rate(bp->tx_clk, rate_rounded))
		netdev_err(bp->netdev, "adjusting tx_clk failed.\n");
}

static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
				 phy_interface_t interface, int speed,
				 int duplex)
{
	struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs);
	u32 config;

	config = gem_readl(bp, USX_CONTROL);
	config = GEM_BFINS(SERDES_RATE, MACB_SERDES_RATE_10G, config);
	config = GEM_BFINS(USX_CTRL_SPEED, HS_SPEED_10000M, config);
	config &= ~(GEM_BIT(TX_SCR_BYPASS) | GEM_BIT(RX_SCR_BYPASS));
	config |= GEM_BIT(TX_EN);
	gem_writel(bp, USX_CONTROL, config);
}

static void macb_usx_pcs_get_state(struct phylink_pcs *pcs,
				   unsigned int neg_mode,
				   struct phylink_link_state *state)
{
	struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs);
	u32 val;

	state->speed = SPEED_10000;
	state->duplex = 1;
	state->an_complete = 1;

	val = gem_readl(bp, USX_STATUS);
	state->link = !!(val & GEM_BIT(USX_BLOCK_LOCK));
	val = gem_readl(bp, NCFGR);
	if (val & GEM_BIT(PAE))
		state->pause = MLO_PAUSE_RX;
}

static int macb_usx_pcs_config(struct phylink_pcs *pcs,
			       unsigned int neg_mode,
			       phy_interface_t interface,
			       const unsigned long *advertising,
			       bool permit_pause_to_mac)
{
	struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs);

	gem_writel(bp, USX_CONTROL, gem_readl(bp, USX_CONTROL) |
		   GEM_BIT(SIGNAL_OK));

	return 0;
}

static unsigned int macb_pcs_inband_caps(struct phylink_pcs *pcs,
					 phy_interface_t interface)
{
	return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE;
}

static void macb_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
			       struct phylink_link_state *state)
{
	struct macb *bp = container_of(pcs, struct macb, phylink_sgmii_pcs);
	u16 bmsr, lpa;

	bmsr = gem_readl(bp, PCSSTS);
	lpa = gem_readl(bp, PCSANLPBASE);
	phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa);
}

static void macb_pcs_an_restart(struct phylink_pcs *pcs)
{
	/* Not supported */
}

static int macb_pcs_config(struct phylink_pcs *pcs,
			   unsigned int neg_mode,
			   phy_interface_t interface,
			   const unsigned long *advertising,
			   bool permit_pause_to_mac)
{
	struct macb *bp = container_of(pcs, struct macb, phylink_sgmii_pcs);
	u32 old, new;

	old = gem_readl(bp, PCSANADV);
	new = phylink_mii_c22_pcs_encode_advertisement(interface, advertising);
	if (new != -EINVAL && old != new)
		gem_writel(bp, PCSANADV, new);

	/* Disable AN if it's not to be used, enable otherwise.
	 * Must be written after PCSSEL is set in NCFGR which is done in
	 * macb_mac_config(), otherwise writes will not take effect.
	 */
	old = gem_readl(bp, PCSCNTRL);
	if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED)
		new = old | BMCR_ANENABLE;
	else
		new = old & ~BMCR_ANENABLE;
	if (old != new)
		gem_writel(bp, PCSCNTRL, new);

	return 0;
}

static const struct phylink_pcs_ops macb_phylink_usx_pcs_ops = {
	.pcs_get_state = macb_usx_pcs_get_state,
	.pcs_config = macb_usx_pcs_config,
	.pcs_link_up = macb_usx_pcs_link_up,
};

static const struct phylink_pcs_ops macb_phylink_pcs_ops = {
	.pcs_inband_caps = macb_pcs_inband_caps,
	.pcs_get_state = macb_pcs_get_state,
	.pcs_an_restart = macb_pcs_an_restart,
	.pcs_config = macb_pcs_config,
};

static bool macb_tx_lpi_set(struct macb *bp, bool enable)
{
	u32 old, ncr;

	lockdep_assert_held(&bp->lock);

	ncr = macb_readl(bp, NCR);
	old = ncr;
	if (enable)
		ncr |= GEM_BIT(TXLPIEN);
	else
		ncr &= ~GEM_BIT(TXLPIEN);
	if (old != ncr)
		macb_writel(bp, NCR, ncr);

	return old != ncr;
}

static bool macb_tx_all_queues_idle(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int q;

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		if (READ_ONCE(queue->tx_head) != READ_ONCE(queue->tx_tail))
			return false;
	}
	return true;
}

static void macb_tx_lpi_work_fn(struct work_struct *work)
{
	struct macb *bp = container_of(work, struct macb, tx_lpi_work.work);
	unsigned long flags;

	spin_lock_irqsave(&bp->lock, flags);
	if (bp->eee_active && macb_tx_all_queues_idle(bp))
		macb_tx_lpi_set(bp, true);
	spin_unlock_irqrestore(&bp->lock, flags);
}

static void macb_tx_lpi_schedule(struct macb *bp)
{
	if (bp->eee_active)
		mod_delayed_work(system_wq, &bp->tx_lpi_work,
				 usecs_to_jiffies(bp->tx_lpi_timer));
}

/* Wake from LPI before transmitting. The MAC must deassert TXLPIEN
 * and wait for the PHY to exit LPI before any frame can be sent.
 * IEEE 802.3az Tw_sys is ~17us for 1000BASE-T, ~30us for 100BASE-TX;
 * we use a conservative 50us.
 */
static void macb_tx_lpi_wake(struct macb *bp)
{
	lockdep_assert_held(&bp->lock);

	if (!bp->eee_active)
		return;

	if (!macb_tx_lpi_set(bp, false))
		return;

	cancel_delayed_work(&bp->tx_lpi_work);
	udelay(50);
}

static void macb_mac_disable_tx_lpi(struct phylink_config *config)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);
	unsigned long flags;

	cancel_delayed_work_sync(&bp->tx_lpi_work);

	spin_lock_irqsave(&bp->lock, flags);
	bp->eee_active = false;
	macb_tx_lpi_set(bp, false);
	spin_unlock_irqrestore(&bp->lock, flags);
}

static int macb_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
				  bool tx_clk_stop)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);
	unsigned long flags;

	spin_lock_irqsave(&bp->lock, flags);
	bp->tx_lpi_timer = timer;
	bp->eee_active = true;
	spin_unlock_irqrestore(&bp->lock, flags);

	/* Defer initial LPI entry by 1 second after link-up per
	 * IEEE 802.3az section 22.7a.
	 */
	mod_delayed_work(system_wq, &bp->tx_lpi_work, msecs_to_jiffies(1000));

	return 0;
}

static void macb_mac_config(struct phylink_config *config, unsigned int mode,
			    const struct phylink_link_state *state)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);
	unsigned long flags;
	u32 old_ctrl, ctrl;
	u32 old_ncr, ncr;

	spin_lock_irqsave(&bp->lock, flags);

	old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
	old_ncr = ncr = macb_or_gem_readl(bp, NCR);

	if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
		if (state->interface == PHY_INTERFACE_MODE_RMII)
			ctrl |= MACB_BIT(RM9200_RMII);
	} else if (macb_is_gem(bp)) {
		ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
		ncr &= ~GEM_BIT(ENABLE_HS_MAC);

		if (state->interface == PHY_INTERFACE_MODE_SGMII) {
			ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
		} else if (state->interface == PHY_INTERFACE_MODE_10GBASER) {
			ctrl |= GEM_BIT(PCSSEL);
			ncr |= GEM_BIT(ENABLE_HS_MAC);
		} else if (bp->caps & MACB_CAPS_MIIONRGMII &&
			   bp->phy_interface == PHY_INTERFACE_MODE_MII) {
			ncr |= MACB_BIT(MIIONRGMII);
		}
	}

	/* Apply the new configuration, if any */
	if (old_ctrl ^ ctrl)
		macb_or_gem_writel(bp, NCFGR, ctrl);

	if (old_ncr ^ ncr)
		macb_or_gem_writel(bp, NCR, ncr);

	spin_unlock_irqrestore(&bp->lock, flags);
}

static void macb_mac_link_down(struct phylink_config *config, unsigned int mode,
			       phy_interface_t interface)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned int q;
	u32 ctrl;

	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
			queue_writel(queue, IDR,
				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));

	/* Disable Rx and Tx */
	ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE));
	macb_writel(bp, NCR, ctrl);

	netif_tx_stop_all_queues(netdev);
}

/* Use juggling algorithm to left rotate tx ring and tx skb array */
static void gem_shuffle_tx_one_ring(struct macb_queue *queue)
{
	unsigned int head, tail, count, ring_size, desc_size;
	struct macb_tx_skb tx_skb, *skb_curr, *skb_next;
	struct macb_dma_desc *desc_curr, *desc_next;
	unsigned int i, cycles, shift, curr, next;
	struct macb *bp = queue->bp;
	unsigned char desc[24];
	unsigned long flags;

	desc_size = macb_dma_desc_get_size(bp);

	if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc)))
		return;

	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
	head = queue->tx_head;
	tail = queue->tx_tail;
	ring_size = bp->tx_ring_size;
	count = CIRC_CNT(head, tail, ring_size);

	if (!(tail % ring_size))
		goto unlock;

	if (!count) {
		queue->tx_head = 0;
		queue->tx_tail = 0;
		goto unlock;
	}

	shift = tail % ring_size;
	cycles = gcd(ring_size, shift);

	for (i = 0; i < cycles; i++) {
		memcpy(&desc, macb_tx_desc(queue, i), desc_size);
		memcpy(&tx_skb, macb_tx_skb(queue, i),
		       sizeof(struct macb_tx_skb));

		curr = i;
		next = (curr + shift) % ring_size;

		while (next != i) {
			desc_curr = macb_tx_desc(queue, curr);
			desc_next = macb_tx_desc(queue, next);

			memcpy(desc_curr, desc_next, desc_size);

			if (next == ring_size - 1)
				desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
			if (curr == ring_size - 1)
				desc_curr->ctrl |= MACB_BIT(TX_WRAP);

			skb_curr = macb_tx_skb(queue, curr);
			skb_next = macb_tx_skb(queue, next);
			memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb));

			curr = next;
			next = (curr + shift) % ring_size;
		}

		desc_curr = macb_tx_desc(queue, curr);
		memcpy(desc_curr, &desc, desc_size);
		if (i == ring_size - 1)
			desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
		if (curr == ring_size - 1)
			desc_curr->ctrl |= MACB_BIT(TX_WRAP);
		memcpy(macb_tx_skb(queue, curr), &tx_skb,
		       sizeof(struct macb_tx_skb));
	}

	queue->tx_head = count;
	queue->tx_tail = 0;

	/* Make descriptor updates visible to hardware */
	wmb();

unlock:
	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
}

/* Rotate the queue so that the tail is at index 0 */
static void gem_shuffle_tx_rings(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int q;

	for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++)
		gem_shuffle_tx_one_ring(queue);
}

static void macb_mac_link_up(struct phylink_config *config,
			     struct phy_device *phydev,
			     unsigned int mode, phy_interface_t interface,
			     int speed, int duplex,
			     bool tx_pause, bool rx_pause)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned long flags;
	unsigned int q;
	u32 ctrl;

	spin_lock_irqsave(&bp->lock, flags);

	ctrl = macb_or_gem_readl(bp, NCFGR);

	ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD));

	if (speed == SPEED_100)
		ctrl |= MACB_BIT(SPD);

	if (duplex)
		ctrl |= MACB_BIT(FD);

	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
		ctrl &= ~MACB_BIT(PAE);
		if (macb_is_gem(bp)) {
			ctrl &= ~GEM_BIT(GBE);

			if (speed == SPEED_1000)
				ctrl |= GEM_BIT(GBE);
		}

		if (rx_pause)
			ctrl |= MACB_BIT(PAE);

		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
			queue_writel(queue, IER,
				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
		}
	}

	macb_or_gem_writel(bp, NCFGR, ctrl);

	if (bp->phy_interface == PHY_INTERFACE_MODE_10GBASER)
		gem_writel(bp, HS_MAC_CONFIG, GEM_BFINS(HS_MAC_SPEED, HS_SPEED_10000M,
							gem_readl(bp, HS_MAC_CONFIG)));

	spin_unlock_irqrestore(&bp->lock, flags);

	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
		macb_set_tx_clk(bp, speed);
		gem_shuffle_tx_rings(bp);
	}

	/* Enable Rx and Tx; Enable PTP unicast */
	ctrl = macb_readl(bp, NCR);
	if (gem_has_ptp(bp))
		ctrl |= MACB_BIT(PTPUNI);

	macb_writel(bp, NCR, ctrl | MACB_BIT(RE) | MACB_BIT(TE));

	netif_tx_wake_all_queues(netdev);
}

static struct phylink_pcs *macb_mac_select_pcs(struct phylink_config *config,
					       phy_interface_t interface)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);

	if (interface == PHY_INTERFACE_MODE_10GBASER)
		return &bp->phylink_usx_pcs;
	else if (interface == PHY_INTERFACE_MODE_SGMII)
		return &bp->phylink_sgmii_pcs;
	else
		return NULL;
}

static const struct phylink_mac_ops macb_phylink_ops = {
	.mac_select_pcs = macb_mac_select_pcs,
	.mac_config = macb_mac_config,
	.mac_link_down = macb_mac_link_down,
	.mac_link_up = macb_mac_link_up,
	.mac_disable_tx_lpi = macb_mac_disable_tx_lpi,
	.mac_enable_tx_lpi = macb_mac_enable_tx_lpi,
};

static bool macb_phy_handle_exists(struct device_node *dn)
{
	dn = of_parse_phandle(dn, "phy-handle", 0);
	of_node_put(dn);
	return dn != NULL;
}

static int macb_phylink_connect(struct macb *bp)
{
	struct device_node *dn = bp->pdev->dev.of_node;
	struct net_device *netdev = bp->netdev;
	struct phy_device *phydev;
	int ret;

	if (dn)
		ret = phylink_of_phy_connect(bp->phylink, dn, 0);

	if (!dn || (ret && !macb_phy_handle_exists(dn))) {
		phydev = phy_find_first(bp->mii_bus);
		if (!phydev) {
			netdev_err(netdev, "no PHY found\n");
			return -ENXIO;
		}

		/* attach the mac to the phy */
		ret = phylink_connect_phy(bp->phylink, phydev);
	}

	if (ret) {
		netdev_err(netdev, "Could not attach PHY (%d)\n", ret);
		return ret;
	}

	phylink_start(bp->phylink);

	return 0;
}

static void macb_get_pcs_fixed_state(struct phylink_config *config,
				     struct phylink_link_state *state)
{
	struct net_device *netdev = to_net_dev(config->dev);
	struct macb *bp = netdev_priv(netdev);

	state->link = (macb_readl(bp, NSR) & MACB_BIT(NSR_LINK)) != 0;
}

/* based on au1000_eth. c*/
static int macb_mii_probe(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);

	bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops;
	bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops;

	bp->phylink_config.dev = &netdev->dev;
	bp->phylink_config.type = PHYLINK_NETDEV;
	bp->phylink_config.mac_managed_pm = true;

	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) {
		bp->phylink_config.poll_fixed_state = true;
		bp->phylink_config.get_fixed_state = macb_get_pcs_fixed_state;
		/* The PCSAUTONEG bit in PCSCNTRL is on out of reset. Setting
		 * default_an_inband to true tells phylink to turn it off only
		 * if necessary (e.g. a fixed link or a PHY that doesn't support
		 * inband).
		 */
		bp->phylink_config.default_an_inband = true;
	}

	bp->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
		MAC_10 | MAC_100;

	__set_bit(PHY_INTERFACE_MODE_MII,
		  bp->phylink_config.supported_interfaces);
	__set_bit(PHY_INTERFACE_MODE_RMII,
		  bp->phylink_config.supported_interfaces);

	/* Determine what modes are supported */
	if (macb_is_gem(bp) && (bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE)) {
		bp->phylink_config.mac_capabilities |= MAC_1000FD;
		if (!(bp->caps & MACB_CAPS_NO_GIGABIT_HALF))
			bp->phylink_config.mac_capabilities |= MAC_1000HD;

		__set_bit(PHY_INTERFACE_MODE_GMII,
			  bp->phylink_config.supported_interfaces);
		phy_interface_set_rgmii(bp->phylink_config.supported_interfaces);

		if (bp->caps & MACB_CAPS_PCS)
			__set_bit(PHY_INTERFACE_MODE_SGMII,
				  bp->phylink_config.supported_interfaces);

		if (bp->caps & MACB_CAPS_HIGH_SPEED) {
			__set_bit(PHY_INTERFACE_MODE_10GBASER,
				  bp->phylink_config.supported_interfaces);
			bp->phylink_config.mac_capabilities |= MAC_10000FD;
		}
	}

	/* Configure EEE LPI if supported */
	if (bp->caps & MACB_CAPS_EEE) {
		__set_bit(PHY_INTERFACE_MODE_MII,
			  bp->phylink_config.lpi_interfaces);
		__set_bit(PHY_INTERFACE_MODE_GMII,
			  bp->phylink_config.lpi_interfaces);
		phy_interface_set_rgmii(bp->phylink_config.lpi_interfaces);
		bp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD;
		bp->phylink_config.lpi_timer_default = 250000;
		bp->phylink_config.eee_enabled_default = true;
	}

	bp->phylink = phylink_create(&bp->phylink_config, bp->pdev->dev.fwnode,
				     bp->phy_interface, &macb_phylink_ops);
	if (IS_ERR(bp->phylink)) {
		netdev_err(netdev, "Could not create a phylink instance (%ld)\n",
			   PTR_ERR(bp->phylink));
		return PTR_ERR(bp->phylink);
	}

	return 0;
}

static int macb_mdiobus_register(struct macb *bp, struct device_node *mdio_np)
{
	struct device_node *child, *np = bp->pdev->dev.of_node;

	/* If we have a child named mdio, probe it instead of looking for PHYs
	 * directly under the MAC node
	 */
	if (mdio_np)
		return of_mdiobus_register(bp->mii_bus, mdio_np);

	/* Only create the PHY from the device tree if at least one PHY is
	 * described. Otherwise scan the entire MDIO bus. We do this to support
	 * old device tree that did not follow the best practices and did not
	 * describe their network PHYs.
	 */
	for_each_available_child_of_node(np, child)
		if (of_mdiobus_child_is_phy(child)) {
			/* The loop increments the child refcount,
			 * decrement it before returning.
			 */
			of_node_put(child);

			return of_mdiobus_register(bp->mii_bus, np);
		}

	return mdiobus_register(bp->mii_bus);
}

static int macb_mii_init(struct macb *bp)
{
	struct device_node *mdio_np, *np = bp->pdev->dev.of_node;
	int err = -ENXIO;

	/* With fixed-link, we don't need to register the MDIO bus,
	 * except if we have a child named "mdio" in the device tree.
	 * In that case, some devices may be attached to the MACB's MDIO bus.
	 */
	mdio_np = of_get_child_by_name(np, "mdio");
	if (!mdio_np && of_phy_is_fixed_link(np))
		return macb_mii_probe(bp->netdev);

	/* Enable management port */
	macb_writel(bp, NCR, MACB_BIT(MPE));

	bp->mii_bus = mdiobus_alloc();
	if (!bp->mii_bus) {
		err = -ENOMEM;
		goto err_out;
	}

	bp->mii_bus->name = "MACB_mii_bus";
	bp->mii_bus->read = &macb_mdio_read_c22;
	bp->mii_bus->write = &macb_mdio_write_c22;
	bp->mii_bus->read_c45 = &macb_mdio_read_c45;
	bp->mii_bus->write_c45 = &macb_mdio_write_c45;
	snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
		 bp->pdev->name, bp->pdev->id);
	bp->mii_bus->priv = bp;
	bp->mii_bus->parent = &bp->pdev->dev;

	dev_set_drvdata(&bp->netdev->dev, bp->mii_bus);

	err = macb_mdiobus_register(bp, mdio_np);
	if (err)
		goto err_out_free_mdiobus;

	err = macb_mii_probe(bp->netdev);
	if (err)
		goto err_out_unregister_bus;

	of_node_put(mdio_np);

	return 0;

err_out_unregister_bus:
	mdiobus_unregister(bp->mii_bus);
err_out_free_mdiobus:
	mdiobus_free(bp->mii_bus);
err_out:
	of_node_put(mdio_np);

	return err;
}

static void macb_update_stats(struct macb *bp)
{
	u64 *p = &bp->hw_stats.macb.rx_pause_frames;
	u64 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
	int offset = MACB_PFR;

	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);

	for (; p < end; p++, offset += 4)
		*p += bp->macb_reg_readl(bp, offset);
}

static int macb_halt_tx(struct macb *bp)
{
	u32 status;

	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));

	/* Poll TSR until TGO is cleared or timeout. */
	return read_poll_timeout_atomic(macb_readl, status,
					!(status & MACB_BIT(TGO)),
					250, MACB_HALT_TIMEOUT, false,
					bp, TSR);
}

static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
{
	if (tx_skb->mapping) {
		if (tx_skb->mapped_as_page)
			dma_unmap_page(&bp->pdev->dev, tx_skb->mapping,
				       tx_skb->size, DMA_TO_DEVICE);
		else
			dma_unmap_single(&bp->pdev->dev, tx_skb->mapping,
					 tx_skb->size, DMA_TO_DEVICE);
		tx_skb->mapping = 0;
	}

	if (tx_skb->skb) {
		dev_consume_skb_any(tx_skb->skb);
		tx_skb->skb = NULL;
	}
}

static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_t addr)
{
	if (macb_dma64(bp)) {
		struct macb_dma_desc_64 *desc_64;

		desc_64 = macb_64b_desc(bp, desc);
		desc_64->addrh = upper_32_bits(addr);
		/* The low bits of RX address contain the RX_USED bit, clearing
		 * of which allows packet RX. Make sure the high bits are also
		 * visible to HW at that point.
		 */
		dma_wmb();
	}

	desc->addr = lower_32_bits(addr);
}

static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc)
{
	dma_addr_t addr = 0;

	if (macb_dma64(bp)) {
		struct macb_dma_desc_64 *desc_64;

		desc_64 = macb_64b_desc(bp, desc);
		addr = ((u64)(desc_64->addrh) << 32);
	}
	addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
	if (macb_dma_ptp(bp))
		addr &= ~GEM_BIT(DMA_RXVALID);
	return addr;
}

static void macb_tx_error_task(struct work_struct *work)
{
	struct macb_queue *queue = container_of(work, struct macb_queue,
						tx_error_task);
	unsigned int q = queue - queue->bp->queues;
	struct macb *bp = queue->bp;
	struct macb_tx_skb *tx_skb;
	struct macb_dma_desc *desc;
	bool halt_timeout = false;
	struct sk_buff *skb;
	unsigned long flags;
	unsigned int tail;
	u32 packets = 0;
	u32 bytes = 0;

	netdev_vdbg(bp->netdev, "%s: q = %u, t = %u, h = %u\n",
		    __func__, q, queue->tx_tail, queue->tx_head);

	/* Prevent the queue NAPI TX poll from running, as it calls
	 * macb_tx_complete(), which in turn may call netif_wake_subqueue().
	 * As explained below, we have to halt the transmission before updating
	 * TBQP registers so we call netif_tx_stop_all_queues() to notify the
	 * network engine about the macb/gem being halted.
	 */
	napi_disable(&queue->napi_tx);
	spin_lock_irqsave(&bp->lock, flags);

	/* Make sure nobody is trying to queue up new packets */
	netif_tx_stop_all_queues(bp->netdev);

	/* Stop transmission now
	 * (in case we have just queued new packets)
	 * macb/gem must be halted to write TBQP register
	 */
	if (macb_halt_tx(bp)) {
		netdev_err(bp->netdev, "BUG: halt tx timed out\n");
		macb_writel(bp, NCR, macb_readl(bp, NCR) & (~MACB_BIT(TE)));
		halt_timeout = true;
	}

	/* Treat frames in TX queue including the ones that caused the error.
	 * Free transmit buffers in upper layer.
	 */
	for (tail = queue->tx_tail; tail != queue->tx_head; tail++) {
		u32	ctrl;

		desc = macb_tx_desc(queue, tail);
		ctrl = desc->ctrl;
		tx_skb = macb_tx_skb(queue, tail);
		skb = tx_skb->skb;

		if (ctrl & MACB_BIT(TX_USED)) {
			/* skb is set for the last buffer of the frame */
			while (!skb) {
				macb_tx_unmap(bp, tx_skb, 0);
				tail++;
				tx_skb = macb_tx_skb(queue, tail);
				skb = tx_skb->skb;
			}

			/* ctrl still refers to the first buffer descriptor
			 * since it's the only one written back by the hardware
			 */
			if (!(ctrl & MACB_BIT(TX_BUF_EXHAUSTED))) {
				netdev_vdbg(bp->netdev, "txerr skb %u (data %p) TX complete\n",
					    macb_tx_ring_wrap(bp, tail),
					    skb->data);
				bp->netdev->stats.tx_packets++;
				queue->stats.tx_packets++;
				packets++;
				bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len;
				queue->stats.tx_bytes += skb->len - tx_skb->fcs_len;
				bytes += skb->len;
			}
		} else {
			/* "Buffers exhausted mid-frame" errors may only happen
			 * if the driver is buggy, so complain loudly about
			 * those. Statistics are updated by hardware.
			 */
			if (ctrl & MACB_BIT(TX_BUF_EXHAUSTED))
				netdev_err(bp->netdev,
					   "BUG: TX buffers exhausted mid-frame\n");

			desc->ctrl = ctrl | MACB_BIT(TX_USED);
		}

		macb_tx_unmap(bp, tx_skb, 0);
	}

	netdev_tx_completed_queue(netdev_get_tx_queue(bp->netdev, q),
				  packets, bytes);

	/* Set end of TX queue */
	desc = macb_tx_desc(queue, 0);
	macb_set_addr(bp, desc, 0);
	desc->ctrl = MACB_BIT(TX_USED);

	/* Make descriptor updates visible to hardware */
	wmb();

	/* Reinitialize the TX desc queue */
	queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
	/* Make TX ring reflect state of hardware */
	queue->tx_head = 0;
	queue->tx_tail = 0;

	/* Housework before enabling TX IRQ */
	macb_writel(bp, TSR, macb_readl(bp, TSR));
	queue_writel(queue, IER, MACB_TX_INT_FLAGS);

	if (halt_timeout)
		macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TE));

	/* Now we are ready to start transmission again */
	netif_tx_start_all_queues(bp->netdev);
	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));

	spin_unlock_irqrestore(&bp->lock, flags);
	napi_enable(&queue->napi_tx);
}

static bool ptp_one_step_sync(struct sk_buff *skb)
{
	struct ptp_header *hdr;
	unsigned int ptp_class;
	u8 msgtype;

	/* No need to parse packet if PTP TS is not involved */
	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
		goto not_oss;

	/* Identify and return whether PTP one step sync is being processed */
	ptp_class = ptp_classify_raw(skb);
	if (ptp_class == PTP_CLASS_NONE)
		goto not_oss;

	hdr = ptp_parse_header(skb, ptp_class);
	if (!hdr)
		goto not_oss;

	if (hdr->flag_field[0] & PTP_FLAG_TWOSTEP)
		goto not_oss;

	msgtype = ptp_get_msgtype(hdr, ptp_class);
	if (msgtype == PTP_MSGTYPE_SYNC)
		return true;

not_oss:
	return false;
}

static int macb_tx_complete(struct macb_queue *queue, int budget)
{
	struct macb *bp = queue->bp;
	unsigned int q = queue - bp->queues;
	unsigned long flags;
	unsigned int tail;
	unsigned int head;
	int packets = 0;
	u32 bytes = 0;

	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
	head = queue->tx_head;
	for (tail = queue->tx_tail; tail != head && packets < budget; tail++) {
		struct macb_tx_skb	*tx_skb;
		struct sk_buff		*skb;
		struct macb_dma_desc	*desc;
		u32			ctrl;

		desc = macb_tx_desc(queue, tail);

		/* Make hw descriptor updates visible to CPU */
		rmb();

		ctrl = desc->ctrl;

		/* TX_USED bit is only set by hardware on the very first buffer
		 * descriptor of the transmitted frame.
		 */
		if (!(ctrl & MACB_BIT(TX_USED)))
			break;

		/* Process all buffers of the current transmitted frame */
		for (;; tail++) {
			tx_skb = macb_tx_skb(queue, tail);
			skb = tx_skb->skb;

			/* First, update TX stats if needed */
			if (skb) {
				if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
				    !ptp_one_step_sync(skb))
					gem_ptp_do_txstamp(bp, skb, desc);

				netdev_vdbg(bp->netdev, "skb %u (data %p) TX complete\n",
					    macb_tx_ring_wrap(bp, tail),
					    skb->data);
				bp->netdev->stats.tx_packets++;
				queue->stats.tx_packets++;
				bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len;
				queue->stats.tx_bytes += skb->len - tx_skb->fcs_len;
				packets++;
				bytes += skb->len;
			}

			/* Now we can safely release resources */
			macb_tx_unmap(bp, tx_skb, budget);

			/* skb is set only for the last buffer of the frame.
			 * WARNING: at this point skb has been freed by
			 * macb_tx_unmap().
			 */
			if (skb)
				break;
		}
	}

	netdev_tx_completed_queue(netdev_get_tx_queue(bp->netdev, q),
				  packets, bytes);

	queue->tx_tail = tail;
	if (__netif_subqueue_stopped(bp->netdev, q) &&
	    CIRC_CNT(queue->tx_head, queue->tx_tail,
		     bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp))
		netif_wake_subqueue(bp->netdev, q);
	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);

	if (packets)
		macb_tx_lpi_schedule(bp);

	return packets;
}

static void gem_rx_refill(struct macb_queue *queue)
{
	struct macb *bp = queue->bp;
	struct macb_dma_desc *desc;
	struct sk_buff *skb;
	unsigned int entry;
	dma_addr_t paddr;

	while (CIRC_SPACE(queue->rx_prepared_head, queue->rx_tail,
			bp->rx_ring_size) > 0) {
		entry = macb_rx_ring_wrap(bp, queue->rx_prepared_head);

		/* Make hw descriptor updates visible to CPU */
		rmb();

		desc = macb_rx_desc(queue, entry);

		if (!queue->rx_skbuff[entry]) {
			/* allocate sk_buff for this free entry in ring */
			skb = netdev_alloc_skb(bp->netdev, bp->rx_buffer_size);
			if (unlikely(!skb)) {
				netdev_err(bp->netdev,
					   "Unable to allocate sk_buff\n");
				break;
			}

			/* now fill corresponding descriptor entry */
			paddr = dma_map_single(&bp->pdev->dev, skb->data,
					       bp->rx_buffer_size,
					       DMA_FROM_DEVICE);
			if (dma_mapping_error(&bp->pdev->dev, paddr)) {
				dev_kfree_skb(skb);
				break;
			}

			queue->rx_skbuff[entry] = skb;

			if (entry == bp->rx_ring_size - 1)
				paddr |= MACB_BIT(RX_WRAP);
			desc->ctrl = 0;
			/* Setting addr clears RX_USED and allows reception,
			 * make sure ctrl is cleared first to avoid a race.
			 */
			dma_wmb();
			macb_set_addr(bp, desc, paddr);

			/* Properly align Ethernet header.
			 *
			 * Hardware can add dummy bytes if asked using the RBOF
			 * field inside the NCFGR register. That feature isn't
			 * available if hardware is RSC capable.
			 *
			 * We cannot fallback to doing the 2-byte shift before
			 * DMA mapping because the address field does not allow
			 * setting the low 2/3 bits.
			 * It is 3 bits if HW_DMA_CAP_PTP, else 2 bits.
			 */
			if (!(bp->caps & MACB_CAPS_RSC))
				skb_reserve(skb, NET_IP_ALIGN);
		} else {
			desc->ctrl = 0;
			dma_wmb();
			desc->addr &= ~MACB_BIT(RX_USED);
		}
		queue->rx_prepared_head++;
	}

	/* Make descriptor updates visible to hardware */
	wmb();

	netdev_vdbg(bp->netdev, "rx ring: queue: %p, prepared head %d, tail %d\n",
		    queue, queue->rx_prepared_head, queue->rx_tail);
}

/* Mark DMA descriptors from begin up to and not including end as unused */
static void discard_partial_frame(struct macb_queue *queue, unsigned int begin,
				  unsigned int end)
{
	unsigned int frag;

	for (frag = begin; frag != end; frag++) {
		struct macb_dma_desc *desc = macb_rx_desc(queue, frag);

		desc->addr &= ~MACB_BIT(RX_USED);
	}

	/* Make descriptor updates visible to hardware */
	wmb();

	/* When this happens, the hardware stats registers for
	 * whatever caused this is updated, so we don't have to record
	 * anything.
	 */
}

static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
		  int budget)
{
	struct macb *bp = queue->bp;
	struct macb_dma_desc *desc;
	struct sk_buff *skb;
	unsigned int entry;
	unsigned int len;
	int count = 0;

	while (count < budget) {
		u32 ctrl;
		dma_addr_t addr;
		bool rxused;

		entry = macb_rx_ring_wrap(bp, queue->rx_tail);
		desc = macb_rx_desc(queue, entry);

		/* Make hw descriptor updates visible to CPU */
		rmb();

		rxused = (desc->addr & MACB_BIT(RX_USED)) ? true : false;
		addr = macb_get_addr(bp, desc);

		if (!rxused)
			break;

		/* Ensure ctrl is at least as up-to-date as rxused */
		dma_rmb();

		ctrl = desc->ctrl;

		queue->rx_tail++;
		count++;

		if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) {
			netdev_err(bp->netdev,
				   "not whole frame pointed by descriptor\n");
			bp->netdev->stats.rx_dropped++;
			queue->stats.rx_dropped++;
			break;
		}
		skb = queue->rx_skbuff[entry];
		if (unlikely(!skb)) {
			netdev_err(bp->netdev,
				   "inconsistent Rx descriptor chain\n");
			bp->netdev->stats.rx_dropped++;
			queue->stats.rx_dropped++;
			break;
		}
		/* now everything is ready for receiving packet */
		queue->rx_skbuff[entry] = NULL;
		len = ctrl & bp->rx_frm_len_mask;

		netdev_vdbg(bp->netdev, "%s %u (len %u)\n",
			    __func__, entry, len);

		skb_put(skb, len);
		dma_unmap_single(&bp->pdev->dev, addr,
				 bp->rx_buffer_size, DMA_FROM_DEVICE);

		skb->protocol = eth_type_trans(skb, bp->netdev);
		skb_checksum_none_assert(skb);
		if (bp->netdev->features & NETIF_F_RXCSUM &&
		    !(bp->netdev->flags & IFF_PROMISC) &&
		    GEM_BFEXT(RX_CSUM, ctrl) & GEM_RX_CSUM_CHECKED_MASK)
			skb->ip_summed = CHECKSUM_UNNECESSARY;

		bp->netdev->stats.rx_packets++;
		queue->stats.rx_packets++;
		bp->netdev->stats.rx_bytes += skb->len;
		queue->stats.rx_bytes += skb->len;

		gem_ptp_do_rxstamp(bp, skb, desc);

#if defined(DEBUG) && defined(VERBOSE_DEBUG)
		netdev_vdbg(bp->netdev, "received skb of length %u, csum: %08x\n",
			    skb->len, skb->csum);
		print_hex_dump(KERN_DEBUG, " mac: ", DUMP_PREFIX_ADDRESS, 16, 1,
			       skb_mac_header(skb), 16, true);
		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_ADDRESS, 16, 1,
			       skb->data, 32, true);
#endif

		napi_gro_receive(napi, skb);
	}

	gem_rx_refill(queue);

	return count;
}

static int macb_rx_frame(struct macb_queue *queue, struct napi_struct *napi,
			 unsigned int first_frag, unsigned int last_frag)
{
	struct macb *bp = queue->bp;
	struct macb_dma_desc *desc;
	unsigned int offset;
	struct sk_buff *skb;
	unsigned int frag;
	unsigned int len;

	desc = macb_rx_desc(queue, last_frag);
	len = desc->ctrl & bp->rx_frm_len_mask;

	netdev_vdbg(bp->netdev, "%s frags %u - %u (len %u)\n",
		    __func__,
		    macb_rx_ring_wrap(bp, first_frag),
		    macb_rx_ring_wrap(bp, last_frag), len);

	/* The ethernet header starts NET_IP_ALIGN bytes into the
	 * first buffer. Since the header is 14 bytes, this makes the
	 * payload word-aligned.
	 *
	 * Instead of calling skb_reserve(NET_IP_ALIGN), we just copy
	 * the two padding bytes into the skb so that we avoid hitting
	 * the slowpath in memcpy(), and pull them off afterwards.
	 */
	skb = netdev_alloc_skb(bp->netdev, len + NET_IP_ALIGN);
	if (!skb) {
		bp->netdev->stats.rx_dropped++;
		for (frag = first_frag; ; frag++) {
			desc = macb_rx_desc(queue, frag);
			desc->addr &= ~MACB_BIT(RX_USED);
			if (frag == last_frag)
				break;
		}

		/* Make descriptor updates visible to hardware */
		wmb();

		return 1;
	}

	offset = 0;
	len += NET_IP_ALIGN;
	skb_checksum_none_assert(skb);
	skb_put(skb, len);

	for (frag = first_frag; ; frag++) {
		unsigned int frag_len = bp->rx_buffer_size;

		if (offset + frag_len > len) {
			if (unlikely(frag != last_frag)) {
				dev_kfree_skb_any(skb);
				return -1;
			}
			frag_len = len - offset;
		}
		skb_copy_to_linear_data_offset(skb, offset,
					       macb_rx_buffer(queue, frag),
					       frag_len);
		offset += bp->rx_buffer_size;
		desc = macb_rx_desc(queue, frag);
		desc->addr &= ~MACB_BIT(RX_USED);

		if (frag == last_frag)
			break;
	}

	/* Make descriptor updates visible to hardware */
	wmb();

	__skb_pull(skb, NET_IP_ALIGN);
	skb->protocol = eth_type_trans(skb, bp->netdev);

	bp->netdev->stats.rx_packets++;
	bp->netdev->stats.rx_bytes += skb->len;
	netdev_vdbg(bp->netdev, "received skb of length %u, csum: %08x\n",
		    skb->len, skb->csum);
	napi_gro_receive(napi, skb);

	return 0;
}

static inline void macb_init_rx_ring(struct macb_queue *queue)
{
	struct macb_dma_desc *desc = NULL;
	struct macb *bp = queue->bp;
	dma_addr_t addr;
	int i;

	addr = queue->rx_buffers_dma;
	for (i = 0; i < bp->rx_ring_size; i++) {
		desc = macb_rx_desc(queue, i);
		macb_set_addr(bp, desc, addr);
		desc->ctrl = 0;
		addr += bp->rx_buffer_size;
	}
	desc->addr |= MACB_BIT(RX_WRAP);
	queue->rx_tail = 0;
}

static int macb_rx(struct macb_queue *queue, struct napi_struct *napi,
		   int budget)
{
	struct macb *bp = queue->bp;
	bool reset_rx_queue = false;
	int first_frag = -1;
	unsigned int tail;
	int received = 0;

	for (tail = queue->rx_tail; budget > 0; tail++) {
		struct macb_dma_desc *desc = macb_rx_desc(queue, tail);
		u32 ctrl;

		/* Make hw descriptor updates visible to CPU */
		rmb();

		if (!(desc->addr & MACB_BIT(RX_USED)))
			break;

		/* Ensure ctrl is at least as up-to-date as addr */
		dma_rmb();

		ctrl = desc->ctrl;

		if (ctrl & MACB_BIT(RX_SOF)) {
			if (first_frag != -1)
				discard_partial_frame(queue, first_frag, tail);
			first_frag = tail;
		}

		if (ctrl & MACB_BIT(RX_EOF)) {
			int dropped;

			if (unlikely(first_frag == -1)) {
				reset_rx_queue = true;
				continue;
			}

			dropped = macb_rx_frame(queue, napi, first_frag, tail);
			first_frag = -1;
			if (unlikely(dropped < 0)) {
				reset_rx_queue = true;
				continue;
			}
			if (!dropped) {
				received++;
				budget--;
			}
		}
	}

	if (unlikely(reset_rx_queue)) {
		unsigned long flags;
		u32 ctrl;

		netdev_err(bp->netdev, "RX queue corruption: reset it\n");

		spin_lock_irqsave(&bp->lock, flags);

		ctrl = macb_readl(bp, NCR);
		macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE));

		macb_init_rx_ring(queue);
		queue_writel(queue, RBQP, queue->rx_ring_dma);

		macb_writel(bp, NCR, ctrl | MACB_BIT(RE));

		spin_unlock_irqrestore(&bp->lock, flags);
		return received;
	}

	if (first_frag != -1)
		queue->rx_tail = first_frag;
	else
		queue->rx_tail = tail;

	return received;
}

static bool macb_rx_pending(struct macb_queue *queue)
{
	struct macb *bp = queue->bp;
	struct macb_dma_desc *desc;
	unsigned int entry;

	entry = macb_rx_ring_wrap(bp, queue->rx_tail);
	desc = macb_rx_desc(queue, entry);

	/* Make hw descriptor updates visible to CPU */
	rmb();

	return (desc->addr & MACB_BIT(RX_USED)) != 0;
}

static int macb_rx_poll(struct napi_struct *napi, int budget)
{
	struct macb_queue *queue = container_of(napi, struct macb_queue, napi_rx);
	struct macb *bp = queue->bp;
	int work_done;

	work_done = bp->macbgem_ops.mog_rx(queue, napi, budget);

	netdev_vdbg(bp->netdev, "RX poll: queue = %u, work_done = %d, budget = %d\n",
		    (unsigned int)(queue - bp->queues), work_done, budget);

	if (work_done < budget && napi_complete_done(napi, work_done)) {
		queue_writel(queue, IER, bp->rx_intr_mask);

		/* Packet completions only seem to propagate to raise
		 * interrupts when interrupts are enabled at the time, so if
		 * packets were received while interrupts were disabled,
		 * they will not cause another interrupt to be generated when
		 * interrupts are re-enabled.
		 * Check for this case here to avoid losing a wakeup. This can
		 * potentially race with the interrupt handler doing the same
		 * actions if an interrupt is raised just after enabling them,
		 * but this should be harmless.
		 */
		if (macb_rx_pending(queue)) {
			queue_writel(queue, IDR, bp->rx_intr_mask);
			macb_queue_isr_clear(bp, queue, MACB_BIT(RCOMP));
			netdev_vdbg(bp->netdev, "poll: packets pending, reschedule\n");
			napi_schedule(napi);
		}
	}

	/* TODO: Handle errors */

	return work_done;
}

static void macb_tx_restart(struct macb_queue *queue)
{
	struct macb *bp = queue->bp;
	unsigned int head_idx, tbqp;
	unsigned long flags;

	spin_lock_irqsave(&queue->tx_ptr_lock, flags);

	if (queue->tx_head == queue->tx_tail)
		goto out_tx_ptr_unlock;

	tbqp = queue_readl(queue, TBQP) / macb_dma_desc_get_size(bp);
	tbqp = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, tbqp));
	head_idx = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, queue->tx_head));

	if (tbqp == head_idx)
		goto out_tx_ptr_unlock;

	spin_lock(&bp->lock);
	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
	spin_unlock(&bp->lock);

out_tx_ptr_unlock:
	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
}

static bool macb_tx_complete_pending(struct macb_queue *queue)
{
	bool retval = false;
	unsigned long flags;

	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
	if (queue->tx_head != queue->tx_tail) {
		/* Make hw descriptor updates visible to CPU */
		rmb();

		if (macb_tx_desc(queue, queue->tx_tail)->ctrl & MACB_BIT(TX_USED))
			retval = true;
	}
	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
	return retval;
}

static int macb_tx_poll(struct napi_struct *napi, int budget)
{
	struct macb_queue *queue = container_of(napi, struct macb_queue, napi_tx);
	struct macb *bp = queue->bp;
	int work_done;

	work_done = macb_tx_complete(queue, budget);

	rmb(); // ensure txubr_pending is up to date
	if (queue->txubr_pending) {
		queue->txubr_pending = false;
		netdev_vdbg(bp->netdev, "poll: tx restart\n");
		macb_tx_restart(queue);
	}

	netdev_vdbg(bp->netdev, "TX poll: queue = %u, work_done = %d, budget = %d\n",
		    (unsigned int)(queue - bp->queues), work_done, budget);

	if (work_done < budget && napi_complete_done(napi, work_done)) {
		queue_writel(queue, IER, MACB_BIT(TCOMP));

		/* Packet completions only seem to propagate to raise
		 * interrupts when interrupts are enabled at the time, so if
		 * packets were sent while interrupts were disabled,
		 * they will not cause another interrupt to be generated when
		 * interrupts are re-enabled.
		 * Check for this case here to avoid losing a wakeup. This can
		 * potentially race with the interrupt handler doing the same
		 * actions if an interrupt is raised just after enabling them,
		 * but this should be harmless.
		 */
		if (macb_tx_complete_pending(queue)) {
			queue_writel(queue, IDR, MACB_BIT(TCOMP));
			macb_queue_isr_clear(bp, queue, MACB_BIT(TCOMP));
			netdev_vdbg(bp->netdev, "TX poll: packets pending, reschedule\n");
			napi_schedule(napi);
		}
	}

	return work_done;
}

static void macb_hresp_error_task(struct work_struct *work)
{
	struct macb *bp = from_work(bp, work, hresp_err_bh_work);
	struct net_device *netdev = bp->netdev;
	struct macb_queue *queue;
	unsigned int q;
	u32 ctrl;

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		queue_writel(queue, IDR, bp->rx_intr_mask |
					 MACB_TX_INT_FLAGS |
					 MACB_BIT(HRESP));
	}
	ctrl = macb_readl(bp, NCR);
	ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE));
	macb_writel(bp, NCR, ctrl);

	netif_tx_stop_all_queues(netdev);
	netif_carrier_off(netdev);

	bp->macbgem_ops.mog_init_rings(bp);

	/* Initialize TX and RX buffers */
	macb_init_buffers(bp);

	/* Enable interrupts */
	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
		queue_writel(queue, IER,
			     bp->rx_intr_mask |
			     MACB_TX_INT_FLAGS |
			     MACB_BIT(HRESP));

	ctrl |= MACB_BIT(RE) | MACB_BIT(TE);
	macb_writel(bp, NCR, ctrl);

	netif_carrier_on(netdev);
	netif_tx_start_all_queues(netdev);
}

static void macb_wol_interrupt(struct macb_queue *queue, u32 status)
{
	struct macb *bp = queue->bp;

	queue_writel(queue, IDR, MACB_BIT(WOL));
	macb_writel(bp, WOL, 0);
	netdev_vdbg(bp->netdev, "MACB WoL: queue = %u, isr = 0x%08lx\n",
		    (unsigned int)(queue - bp->queues),
		    (unsigned long)status);
	macb_queue_isr_clear(bp, queue, MACB_BIT(WOL));
	pm_wakeup_event(&bp->pdev->dev, 0);
}

static void gem_wol_interrupt(struct macb_queue *queue, u32 status)
{
	struct macb *bp = queue->bp;

	queue_writel(queue, IDR, GEM_BIT(WOL));
	gem_writel(bp, WOL, 0);
	netdev_vdbg(bp->netdev, "GEM WoL: queue = %u, isr = 0x%08lx\n",
		    (unsigned int)(queue - bp->queues),
		    (unsigned long)status);
	macb_queue_isr_clear(bp, queue, GEM_BIT(WOL));
	pm_wakeup_event(&bp->pdev->dev, 0);
}

static int macb_interrupt_misc(struct macb_queue *queue, u32 status)
{
	struct macb *bp = queue->bp;
	struct net_device *netdev;
	u32 ctrl;

	netdev = bp->netdev;

	if (unlikely(status & (MACB_TX_ERR_FLAGS))) {
		queue_writel(queue, IDR, MACB_TX_INT_FLAGS);
		schedule_work(&queue->tx_error_task);
		macb_queue_isr_clear(bp, queue, MACB_TX_ERR_FLAGS);
		return -1;
	}

	/* Link change detection isn't possible with RMII, so we'll
	 * add that if/when we get our hands on a full-blown MII PHY.
	 */

	/* There is a hardware issue under heavy load where DMA can
	 * stop, this causes endless "used buffer descriptor read"
	 * interrupts but it can be cleared by re-enabling RX. See
	 * the at91rm9200 manual, section 41.3.1 or the Zynq manual
	 * section 16.7.4 for details. RXUBR is only enabled for
	 * these two versions.
	 */
	if (status & MACB_BIT(RXUBR)) {
		ctrl = macb_readl(bp, NCR);
		macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE));
		wmb();
		macb_writel(bp, NCR, ctrl | MACB_BIT(RE));
		macb_queue_isr_clear(bp, queue, MACB_BIT(RXUBR));
	}

	if (status & MACB_BIT(ISR_ROVR)) {
		/* We missed at least one packet */
		spin_lock(&bp->stats_lock);
		if (macb_is_gem(bp))
			bp->hw_stats.gem.rx_overruns++;
		else
			bp->hw_stats.macb.rx_overruns++;
		spin_unlock(&bp->stats_lock);
		macb_queue_isr_clear(bp, queue, MACB_BIT(ISR_ROVR));
	}

	if (status & MACB_BIT(HRESP)) {
		queue_work(system_bh_wq, &bp->hresp_err_bh_work);
		netdev_err(netdev, "DMA bus error: HRESP not OK\n");
		macb_queue_isr_clear(bp, queue, MACB_BIT(HRESP));
	}

	if (macb_is_gem(bp)) {
		if (status & GEM_BIT(WOL))
			gem_wol_interrupt(queue, status);
	} else {
		if (status & MACB_BIT(WOL))
			macb_wol_interrupt(queue, status);
	}

	return 0;
}

static irqreturn_t macb_interrupt(int irq, void *dev_id)
{
	struct macb_queue *queue = dev_id;
	struct macb *bp = queue->bp;
	struct net_device *netdev = bp->netdev;
	u32 status;

	status = queue_readl(queue, ISR);

	if (unlikely(!status))
		return IRQ_NONE;

	spin_lock(&bp->lock);

	while (status) {
		/* close possible race with dev_close */
		if (unlikely(!netif_running(netdev))) {
			queue_writel(queue, IDR, -1);
			macb_queue_isr_clear(bp, queue, -1);
			break;
		}

		netdev_vdbg(netdev, "queue = %u, isr = 0x%08lx\n",
			    (unsigned int)(queue - bp->queues),
			    (unsigned long)status);

		if (status & bp->rx_intr_mask) {
			/* There's no point taking any more interrupts
			 * until we have processed the buffers. The
			 * scheduling call may fail if the poll routine
			 * is already scheduled, so disable interrupts
			 * now.
			 */
			queue_writel(queue, IDR, bp->rx_intr_mask);
			macb_queue_isr_clear(bp, queue, MACB_BIT(RCOMP));
			napi_schedule_irqoff(&queue->napi_rx);
		}

		if (status & (MACB_BIT(TCOMP) |
			      MACB_BIT(TXUBR))) {
			queue_writel(queue, IDR, MACB_BIT(TCOMP));
			macb_queue_isr_clear(bp, queue, MACB_BIT(TCOMP) |
							MACB_BIT(TXUBR));
			if (status & MACB_BIT(TXUBR)) {
				queue->txubr_pending = true;
				wmb(); // ensure softirq can see update
			}

			napi_schedule_irqoff(&queue->napi_tx);
		}

		if (unlikely(status & MACB_INT_MISC_FLAGS))
			if (macb_interrupt_misc(queue, status))
				break;

		status = queue_readl(queue, ISR);
	}

	spin_unlock(&bp->lock);

	return IRQ_HANDLED;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
/* Polling receive - used by netconsole and other diagnostic tools
 * to allow network i/o with interrupts disabled.
 */
static void macb_poll_controller(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned long flags;
	unsigned int q;

	local_irq_save(flags);
	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
		macb_interrupt(netdev->irq, queue);
	local_irq_restore(flags);
}
#endif

static unsigned int macb_tx_map(struct macb *bp,
				struct macb_queue *queue,
				struct sk_buff *skb,
				unsigned int hdrlen,
				u8 fcs_len)
{
	unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags;
	unsigned int len, i, tx_head = queue->tx_head;
	u32 ctrl, lso_ctrl = 0, seq_ctrl = 0;
	unsigned int eof = 1, mss_mfs = 0;
	struct macb_tx_skb *tx_skb = NULL;
	struct macb_dma_desc *desc;
	unsigned int offset, size;
	dma_addr_t mapping;

	/* LSO */
	if (skb_shinfo(skb)->gso_size != 0) {
		if (ip_hdr(skb)->protocol == IPPROTO_UDP)
			/* UDP - UFO */
			lso_ctrl = MACB_LSO_UFO_ENABLE;
		else
			/* TCP - TSO */
			lso_ctrl = MACB_LSO_TSO_ENABLE;
	}

	/* First, map non-paged data */
	len = skb_headlen(skb);

	/* first buffer length */
	size = hdrlen;

	offset = 0;
	while (len) {
		tx_skb = macb_tx_skb(queue, tx_head);

		mapping = dma_map_single(&bp->pdev->dev,
					 skb->data + offset,
					 size, DMA_TO_DEVICE);
		if (dma_mapping_error(&bp->pdev->dev, mapping))
			goto dma_error;

		/* Save info to properly release resources */
		tx_skb->skb = NULL;
		tx_skb->mapping = mapping;
		tx_skb->size = size;
		tx_skb->mapped_as_page = false;

		len -= size;
		offset += size;
		tx_head++;

		size = umin(len, bp->max_tx_length);
	}

	/* Then, map paged data from fragments */
	for (f = 0; f < nr_frags; f++) {
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];

		len = skb_frag_size(frag);
		offset = 0;
		while (len) {
			size = umin(len, bp->max_tx_length);
			tx_skb = macb_tx_skb(queue, tx_head);

			mapping = skb_frag_dma_map(&bp->pdev->dev, frag,
						   offset, size, DMA_TO_DEVICE);
			if (dma_mapping_error(&bp->pdev->dev, mapping))
				goto dma_error;

			/* Save info to properly release resources */
			tx_skb->skb = NULL;
			tx_skb->mapping = mapping;
			tx_skb->size = size;
			tx_skb->mapped_as_page = true;

			len -= size;
			offset += size;
			tx_head++;
		}
	}

	/* Should never happen */
	if (unlikely(!tx_skb)) {
		netdev_err(bp->netdev, "BUG! empty skb!\n");
		return 0;
	}

	/* This is the last buffer of the frame: save socket buffer */
	tx_skb->skb = skb;
	tx_skb->fcs_len = fcs_len;

	/* Update TX ring: update buffer descriptors in reverse order
	 * to avoid race condition
	 */

	/* Set 'TX_USED' bit in buffer descriptor at tx_head position
	 * to set the end of TX queue
	 */
	i = tx_head;
	ctrl = MACB_BIT(TX_USED);
	desc = macb_tx_desc(queue, i);
	desc->ctrl = ctrl;

	if (lso_ctrl) {
		if (lso_ctrl == MACB_LSO_UFO_ENABLE)
			/* include header and FCS in value given to h/w */
			mss_mfs = skb_shinfo(skb)->gso_size +
					skb_transport_offset(skb) +
					ETH_FCS_LEN;
		else /* TSO */ {
			mss_mfs = skb_shinfo(skb)->gso_size;
			/* TCP Sequence Number Source Select
			 * can be set only for TSO
			 */
			seq_ctrl = 0;
		}
	}

	do {
		i--;
		tx_skb = macb_tx_skb(queue, i);
		desc = macb_tx_desc(queue, i);

		ctrl = (u32)tx_skb->size;
		if (eof) {
			ctrl |= MACB_BIT(TX_LAST);
			eof = 0;
		}
		if (unlikely(macb_tx_ring_wrap(bp, i) == bp->tx_ring_size - 1))
			ctrl |= MACB_BIT(TX_WRAP);

		/* First descriptor is header descriptor */
		if (i == queue->tx_head) {
			ctrl |= MACB_BF(TX_LSO, lso_ctrl);
			ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
			if ((bp->netdev->features & NETIF_F_HW_CSUM) &&
			    skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl &&
			    !ptp_one_step_sync(skb))
				ctrl |= MACB_BIT(TX_NOCRC);
		} else
			/* Only set MSS/MFS on payload descriptors
			 * (second or later descriptor)
			 */
			ctrl |= MACB_BF(MSS_MFS, mss_mfs);

		/* Set TX buffer descriptor */
		macb_set_addr(bp, desc, tx_skb->mapping);
		/* desc->addr must be visible to hardware before clearing
		 * 'TX_USED' bit in desc->ctrl.
		 */
		wmb();
		desc->ctrl = ctrl;
	} while (i != queue->tx_head);

	queue->tx_head = tx_head;

	return 0;

dma_error:
	netdev_err(bp->netdev, "TX DMA map failed\n");

	for (i = queue->tx_head; i != tx_head; i++) {
		tx_skb = macb_tx_skb(queue, i);

		macb_tx_unmap(bp, tx_skb, 0);
	}

	return -ENOMEM;
}

static netdev_features_t macb_features_check(struct sk_buff *skb,
					     struct net_device *netdev,
					     netdev_features_t features)
{
	unsigned int nr_frags, f;
	unsigned int hdrlen;

	/* Validate LSO compatibility */

	/* there is only one buffer or protocol is not UDP */
	if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP))
		return features;

	/* length of header */
	hdrlen = skb_transport_offset(skb);

	/* For UFO only:
	 * When software supplies two or more payload buffers all payload buffers
	 * apart from the last must be a multiple of 8 bytes in size.
	 */
	if (!IS_ALIGNED(skb_headlen(skb) - hdrlen, MACB_TX_LEN_ALIGN))
		return features & ~MACB_NETIF_LSO;

	nr_frags = skb_shinfo(skb)->nr_frags;
	/* No need to check last fragment */
	nr_frags--;
	for (f = 0; f < nr_frags; f++) {
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];

		if (!IS_ALIGNED(skb_frag_size(frag), MACB_TX_LEN_ALIGN))
			return features & ~MACB_NETIF_LSO;
	}
	return features;
}

static inline int macb_clear_csum(struct sk_buff *skb)
{
	/* no change for packets without checksum offloading */
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	/* make sure we can modify the header */
	if (unlikely(skb_cow_head(skb, 0)))
		return -1;

	/* initialize checksum field
	 * This is required - at least for Zynq, which otherwise calculates
	 * wrong UDP header checksums for UDP packets with UDP data len <=2
	 */
	*(__sum16 *)(skb_checksum_start(skb) + skb->csum_offset) = 0;
	return 0;
}

/* Returns a negative errno, or the FCS bytes appended (0 or ETH_FCS_LEN). */
static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev)
{
	bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
		      skb_is_nonlinear(*skb);
	int padlen = ETH_ZLEN - (*skb)->len;
	int tailroom = skb_tailroom(*skb);
	struct sk_buff *nskb;
	u32 fcs;

	if (!(netdev->features & NETIF_F_HW_CSUM) ||
	    !((*skb)->ip_summed != CHECKSUM_PARTIAL) ||
	    skb_shinfo(*skb)->gso_size || ptp_one_step_sync(*skb))
		return 0;

	if (padlen <= 0) {
		/* FCS could be appeded to tailroom. */
		if (tailroom >= ETH_FCS_LEN)
			goto add_fcs;
		/* No room for FCS, need to reallocate skb. */
		else
			padlen = ETH_FCS_LEN;
	} else {
		/* Add room for FCS. */
		padlen += ETH_FCS_LEN;
	}

	if (cloned || tailroom < padlen) {
		nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC);
		if (!nskb)
			return -ENOMEM;

		dev_consume_skb_any(*skb);
		*skb = nskb;
	}

	if (padlen > ETH_FCS_LEN)
		skb_put_zero(*skb, padlen - ETH_FCS_LEN);

add_fcs:
	/* set FCS to packet */
	fcs = crc32_le(~0, (*skb)->data, (*skb)->len);
	fcs = ~fcs;

	skb_put_u8(*skb, fcs		& 0xff);
	skb_put_u8(*skb, (fcs >> 8)	& 0xff);
	skb_put_u8(*skb, (fcs >> 16)	& 0xff);
	skb_put_u8(*skb, (fcs >> 24)	& 0xff);

	return ETH_FCS_LEN;
}

static netdev_tx_t macb_start_xmit(struct sk_buff *skb,
				   struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	unsigned int q = skb_get_queue_mapping(skb);
	unsigned int desc_cnt, nr_frags, frag_size, f;
	struct macb_queue *queue = &bp->queues[q];
	netdev_tx_t ret = NETDEV_TX_OK;
	unsigned int hdrlen;
	unsigned long flags;
	int fcs_len;
	bool is_lso;

	if (macb_clear_csum(skb)) {
		dev_kfree_skb_any(skb);
		return ret;
	}

	fcs_len = macb_pad_and_fcs(&skb, netdev);
	if (fcs_len < 0) {
		dev_kfree_skb_any(skb);
		return ret;
	}

	if (macb_dma_ptp(bp) &&
	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;

	is_lso = (skb_shinfo(skb)->gso_size != 0);

	if (is_lso) {
		/* length of headers */
		if (ip_hdr(skb)->protocol == IPPROTO_UDP)
			/* only queue eth + ip headers separately for UDP */
			hdrlen = skb_transport_offset(skb);
		else
			hdrlen = skb_tcp_all_headers(skb);
		if (skb_headlen(skb) < hdrlen) {
			netdev_err(bp->netdev, "Error - LSO headers fragmented!!!\n");
			/* if this is required, would need to copy to single buffer */
			return NETDEV_TX_BUSY;
		}
	} else
		hdrlen = umin(skb_headlen(skb), bp->max_tx_length);

#if defined(DEBUG) && defined(VERBOSE_DEBUG)
	netdev_vdbg(bp->netdev,
		    "start_xmit: queue %u len %u head %p data %p tail %p end %p\n",
		    q, skb->len, skb->head, skb->data,
		    skb_tail_pointer(skb), skb_end_pointer(skb));
	print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_OFFSET, 16, 1,
		       skb->data, 16, true);
#endif

	/* Count how many TX buffer descriptors are needed to send this
	 * socket buffer: skb fragments of jumbo frames may need to be
	 * split into many buffer descriptors.
	 */
	if (is_lso && (skb_headlen(skb) > hdrlen))
		/* extra header descriptor if also payload in first buffer */
		desc_cnt = DIV_ROUND_UP((skb_headlen(skb) - hdrlen), bp->max_tx_length) + 1;
	else
		desc_cnt = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
	nr_frags = skb_shinfo(skb)->nr_frags;
	for (f = 0; f < nr_frags; f++) {
		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
		desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length);
	}

	spin_lock_irqsave(&queue->tx_ptr_lock, flags);

	/* This is a hard error, log it. */
	if (CIRC_SPACE(queue->tx_head, queue->tx_tail,
		       bp->tx_ring_size) < desc_cnt) {
		netif_stop_subqueue(netdev, q);
		netdev_dbg(netdev, "tx_head = %u, tx_tail = %u\n",
			   queue->tx_head, queue->tx_tail);
		ret = NETDEV_TX_BUSY;
		goto unlock;
	}

	/* Map socket buffer for DMA transfer */
	if (macb_tx_map(bp, queue, skb, hdrlen, fcs_len)) {
		dev_kfree_skb_any(skb);
		goto unlock;
	}

	/* Make newly initialized descriptor visible to hardware */
	wmb();
	skb_tx_timestamp(skb);
	netdev_tx_sent_queue(netdev_get_tx_queue(bp->netdev, q),
			     skb->len);

	spin_lock(&bp->lock);
	macb_tx_lpi_wake(bp);
	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
	spin_unlock(&bp->lock);

	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
		netif_stop_subqueue(netdev, q);

unlock:
	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);

	return ret;
}

static void macb_init_rx_buffer_size(struct macb *bp, size_t size)
{
	if (!macb_is_gem(bp)) {
		bp->rx_buffer_size = MACB_RX_BUFFER_SIZE;
	} else {
		bp->rx_buffer_size = MIN(size, RX_BUFFER_MAX);

		if (bp->rx_buffer_size % RX_BUFFER_MULTIPLE) {
			netdev_dbg(bp->netdev,
				   "RX buffer must be multiple of %d bytes, expanding\n",
				   RX_BUFFER_MULTIPLE);
			bp->rx_buffer_size =
				roundup(bp->rx_buffer_size, RX_BUFFER_MULTIPLE);
		}
	}

	netdev_dbg(bp->netdev, "mtu [%u] rx_buffer_size [%zu]\n",
		   bp->netdev->mtu, bp->rx_buffer_size);
}

static void gem_free_rx_buffers(struct macb *bp)
{
	struct sk_buff		*skb;
	struct macb_dma_desc	*desc;
	struct macb_queue *queue;
	dma_addr_t		addr;
	unsigned int q;
	int i;

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		if (!queue->rx_skbuff)
			continue;

		for (i = 0; i < bp->rx_ring_size; i++) {
			skb = queue->rx_skbuff[i];

			if (!skb)
				continue;

			desc = macb_rx_desc(queue, i);
			addr = macb_get_addr(bp, desc);

			dma_unmap_single(&bp->pdev->dev, addr, bp->rx_buffer_size,
					DMA_FROM_DEVICE);
			dev_kfree_skb_any(skb);
			skb = NULL;
		}

		kfree(queue->rx_skbuff);
		queue->rx_skbuff = NULL;
	}
}

static void macb_free_rx_buffers(struct macb *bp)
{
	struct macb_queue *queue = &bp->queues[0];

	if (queue->rx_buffers) {
		dma_free_coherent(&bp->pdev->dev,
				  bp->rx_ring_size * bp->rx_buffer_size,
				  queue->rx_buffers, queue->rx_buffers_dma);
		queue->rx_buffers = NULL;
	}
}

static unsigned int macb_tx_ring_size_per_queue(struct macb *bp)
{
	return macb_dma_desc_get_size(bp) * bp->tx_ring_size + bp->tx_bd_rd_prefetch;
}

static unsigned int macb_rx_ring_size_per_queue(struct macb *bp)
{
	return macb_dma_desc_get_size(bp) * bp->rx_ring_size + bp->rx_bd_rd_prefetch;
}

static void macb_free(struct macb *bp)
{
	struct device *dev = &bp->pdev->dev;
	struct macb_queue *queue;
	unsigned int q;
	size_t size;

	bp->macbgem_ops.mog_free_rx_buffers(bp);

	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
	dma_free_coherent(dev, size, bp->queues[0].tx_ring, bp->queues[0].tx_ring_dma);

	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
	dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma);

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		if (queue->tx_skb) {
			unsigned int dropped = 0, tail;

			for (tail = queue->tx_tail; tail != queue->tx_head;
			     tail++) {
				if (macb_tx_skb(queue, tail)->skb)
					dropped++;
				macb_tx_unmap(bp, macb_tx_skb(queue, tail), 0);
			}

			queue->stats.tx_dropped += dropped;
			bp->netdev->stats.tx_dropped += dropped;

			kfree(queue->tx_skb);
			queue->tx_skb = NULL;
		}

		queue->tx_head = 0;
		queue->tx_tail = 0;
		queue->tx_ring = NULL;
		queue->rx_ring = NULL;
	}
}

static int gem_alloc_rx_buffers(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int q;
	int size;

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		size = bp->rx_ring_size * sizeof(struct sk_buff *);
		queue->rx_skbuff = kzalloc(size, GFP_KERNEL);
		if (!queue->rx_skbuff)
			return -ENOMEM;
		else
			netdev_dbg(bp->netdev,
				   "Allocated %d RX struct sk_buff entries at %p\n",
				   bp->rx_ring_size, queue->rx_skbuff);
	}
	return 0;
}

static int macb_alloc_rx_buffers(struct macb *bp)
{
	struct macb_queue *queue = &bp->queues[0];
	int size;

	size = bp->rx_ring_size * bp->rx_buffer_size;
	queue->rx_buffers = dma_alloc_coherent(&bp->pdev->dev, size,
					    &queue->rx_buffers_dma, GFP_KERNEL);
	if (!queue->rx_buffers)
		return -ENOMEM;

	netdev_dbg(bp->netdev,
		   "Allocated RX buffers of %d bytes at %08lx (mapped %p)\n",
		   size, (unsigned long)queue->rx_buffers_dma, queue->rx_buffers);
	return 0;
}

static int macb_alloc(struct macb *bp)
{
	struct device *dev = &bp->pdev->dev;
	dma_addr_t tx_dma, rx_dma;
	struct macb_queue *queue;
	unsigned int q;
	void *tx, *rx;
	size_t size;

	/*
	 * Upper 32-bits of Tx/Rx DMA descriptor for each queues much match!
	 * We cannot enforce this guarantee, the best we can do is do a single
	 * allocation and hope it will land into alloc_pages() that guarantees
	 * natural alignment of physical addresses.
	 */

	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
	tx = dma_alloc_coherent(dev, size, &tx_dma, GFP_KERNEL);
	if (!tx || upper_32_bits(tx_dma) != upper_32_bits(tx_dma + size - 1))
		goto out_err;
	netdev_dbg(bp->netdev, "Allocated %zu bytes for %u TX rings at %08lx (mapped %p)\n",
		   size, bp->num_queues, (unsigned long)tx_dma, tx);

	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
	rx = dma_alloc_coherent(dev, size, &rx_dma, GFP_KERNEL);
	if (!rx || upper_32_bits(rx_dma) != upper_32_bits(rx_dma + size - 1))
		goto out_err;
	netdev_dbg(bp->netdev, "Allocated %zu bytes for %u RX rings at %08lx (mapped %p)\n",
		   size, bp->num_queues, (unsigned long)rx_dma, rx);

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		queue->tx_ring = tx + macb_tx_ring_size_per_queue(bp) * q;
		queue->tx_ring_dma = tx_dma + macb_tx_ring_size_per_queue(bp) * q;

		queue->rx_ring = rx + macb_rx_ring_size_per_queue(bp) * q;
		queue->rx_ring_dma = rx_dma + macb_rx_ring_size_per_queue(bp) * q;

		size = bp->tx_ring_size * sizeof(struct macb_tx_skb);
		queue->tx_skb = kmalloc(size, GFP_KERNEL);
		if (!queue->tx_skb)
			goto out_err;
	}
	if (bp->macbgem_ops.mog_alloc_rx_buffers(bp))
		goto out_err;

	return 0;

out_err:
	macb_free(bp);
	return -ENOMEM;
}

static void gem_init_rx_ring(struct macb_queue *queue)
{
	queue->rx_tail = 0;
	queue->rx_prepared_head = 0;

	gem_rx_refill(queue);
}

static void gem_init_rings(struct macb *bp)
{
	struct macb_queue *queue;
	struct macb_dma_desc *desc = NULL;
	unsigned int q;
	int i;

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		for (i = 0; i < bp->tx_ring_size; i++) {
			desc = macb_tx_desc(queue, i);
			macb_set_addr(bp, desc, 0);
			desc->ctrl = MACB_BIT(TX_USED);
		}
		desc->ctrl |= MACB_BIT(TX_WRAP);
		queue->tx_head = 0;
		queue->tx_tail = 0;

		gem_init_rx_ring(queue);
	}
}

static void macb_init_rings(struct macb *bp)
{
	int i;
	struct macb_dma_desc *desc = NULL;

	macb_init_rx_ring(&bp->queues[0]);

	for (i = 0; i < bp->tx_ring_size; i++) {
		desc = macb_tx_desc(&bp->queues[0], i);
		macb_set_addr(bp, desc, 0);
		desc->ctrl = MACB_BIT(TX_USED);
	}
	bp->queues[0].tx_head = 0;
	bp->queues[0].tx_tail = 0;
	desc->ctrl |= MACB_BIT(TX_WRAP);
}

static void macb_reset_hw(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int q;
	u32 ctrl = macb_readl(bp, NCR);

	/* Disable RX and TX (XXX: Should we halt the transmission
	 * more gracefully?)
	 */
	ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE));

	/* Clear the stats registers (XXX: Update stats first?) */
	ctrl |= MACB_BIT(CLRSTAT);

	macb_writel(bp, NCR, ctrl);

	/* Clear all status flags */
	macb_writel(bp, TSR, -1);
	macb_writel(bp, RSR, -1);

	/* Disable RX partial store and forward and reset watermark value */
	gem_writel(bp, PBUFRXCUT, 0);

	/* Disable all interrupts */
	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		queue_writel(queue, IDR, -1);
		queue_readl(queue, ISR);
		macb_queue_isr_clear(bp, queue, -1);
	}
}

static u32 gem_mdc_clk_div(struct macb *bp)
{
	u32 config;
	unsigned long pclk_hz = clk_get_rate(bp->pclk);

	if (pclk_hz <= 20000000)
		config = GEM_BF(CLK, GEM_CLK_DIV8);
	else if (pclk_hz <= 40000000)
		config = GEM_BF(CLK, GEM_CLK_DIV16);
	else if (pclk_hz <= 80000000)
		config = GEM_BF(CLK, GEM_CLK_DIV32);
	else if (pclk_hz <= 120000000)
		config = GEM_BF(CLK, GEM_CLK_DIV48);
	else if (pclk_hz <= 160000000)
		config = GEM_BF(CLK, GEM_CLK_DIV64);
	else if (pclk_hz <= 240000000)
		config = GEM_BF(CLK, GEM_CLK_DIV96);
	else if (pclk_hz <= 320000000)
		config = GEM_BF(CLK, GEM_CLK_DIV128);
	else
		config = GEM_BF(CLK, GEM_CLK_DIV224);

	return config;
}

static u32 macb_mdc_clk_div(struct macb *bp)
{
	u32 config;
	unsigned long pclk_hz;

	if (macb_is_gem(bp))
		return gem_mdc_clk_div(bp);

	pclk_hz = clk_get_rate(bp->pclk);
	if (pclk_hz <= 20000000)
		config = MACB_BF(CLK, MACB_CLK_DIV8);
	else if (pclk_hz <= 40000000)
		config = MACB_BF(CLK, MACB_CLK_DIV16);
	else if (pclk_hz <= 80000000)
		config = MACB_BF(CLK, MACB_CLK_DIV32);
	else
		config = MACB_BF(CLK, MACB_CLK_DIV64);

	return config;
}

/* Get the DMA bus width field of the network configuration register that we
 * should program.  We find the width from decoding the design configuration
 * register to find the maximum supported data bus width.
 */
static u32 macb_dbw(struct macb *bp)
{
	if (!macb_is_gem(bp))
		return 0;

	switch (GEM_BFEXT(DBWDEF, gem_readl(bp, DCFG1))) {
	case 4:
		return GEM_BF(DBW, GEM_DBW128);
	case 2:
		return GEM_BF(DBW, GEM_DBW64);
	case 1:
	default:
		return GEM_BF(DBW, GEM_DBW32);
	}
}

/* Configure the receive DMA engine
 * - use the correct receive buffer size
 * - set best burst length for DMA operations
 *   (if not supported by FIFO, it will fallback to default)
 * - set both rx/tx packet buffers to full memory size
 * These are configurable parameters for GEM.
 */
static void macb_configure_dma(struct macb *bp)
{
	struct macb_queue *queue;
	u32 buffer_size;
	unsigned int q;
	u32 dmacfg;

	buffer_size = bp->rx_buffer_size / RX_BUFFER_MULTIPLE;
	if (macb_is_gem(bp)) {
		dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
			if (q)
				queue_writel(queue, RBQS, buffer_size);
			else
				dmacfg |= GEM_BF(RXBS, buffer_size);
		}
		if (bp->dma_burst_length)
			dmacfg = GEM_BFINS(FBLDO, bp->dma_burst_length, dmacfg);
		dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
		dmacfg &= ~GEM_BIT(ENDIA_PKT);

		if (bp->native_io)
			dmacfg &= ~GEM_BIT(ENDIA_DESC);
		else
			dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */

		if (bp->netdev->features & NETIF_F_HW_CSUM)
			dmacfg |= GEM_BIT(TXCOEN);
		else
			dmacfg &= ~GEM_BIT(TXCOEN);

		dmacfg &= ~GEM_BIT(ADDR64);
		if (macb_dma64(bp))
			dmacfg |= GEM_BIT(ADDR64);
		if (macb_dma_ptp(bp))
			dmacfg |= GEM_BIT(RXEXT) | GEM_BIT(TXEXT);
		netdev_dbg(bp->netdev, "Cadence configure DMA with 0x%08x\n",
			   dmacfg);
		gem_writel(bp, DMACFG, dmacfg);
	}
}

static void macb_init_hw(struct macb *bp)
{
	u32 config;

	macb_reset_hw(bp);
	macb_set_hwaddr(bp);

	config = macb_mdc_clk_div(bp);
	/* Make eth data aligned.
	 * If RSC capable, that offset is ignored by HW.
	 */
	if (!(bp->caps & MACB_CAPS_RSC))
		config |= MACB_BF(RBOF, NET_IP_ALIGN);
	config |= MACB_BIT(DRFCS);		/* Discard Rx FCS */
	if (bp->caps & MACB_CAPS_JUMBO)
		config |= MACB_BIT(JFRAME);	/* Enable jumbo frames */
	else
		config |= MACB_BIT(BIG);	/* Receive oversized frames */
	if (bp->netdev->flags & IFF_PROMISC)
		config |= MACB_BIT(CAF);	/* Copy All Frames */
	else if (macb_is_gem(bp) && bp->netdev->features & NETIF_F_RXCSUM)
		config |= GEM_BIT(RXCOEN);
	if (!(bp->netdev->flags & IFF_BROADCAST))
		config |= MACB_BIT(NBC);	/* No BroadCast */
	config |= macb_dbw(bp);
	macb_writel(bp, NCFGR, config);
	if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len)
		gem_writel(bp, JML, bp->jumbo_max_len);
	bp->rx_frm_len_mask = MACB_RX_FRMLEN_MASK;
	if (bp->caps & MACB_CAPS_JUMBO)
		bp->rx_frm_len_mask = MACB_RX_JFRMLEN_MASK;

	macb_configure_dma(bp);

	/* Enable RX partial store and forward and set watermark */
	if (bp->rx_watermark)
		gem_writel(bp, PBUFRXCUT, (bp->rx_watermark | GEM_BIT(ENCUTTHRU)));
}

/* The hash address register is 64 bits long and takes up two
 * locations in the memory map.  The least significant bits are stored
 * in EMAC_HSL and the most significant bits in EMAC_HSH.
 *
 * The unicast hash enable and the multicast hash enable bits in the
 * network configuration register enable the reception of hash matched
 * frames. The destination address is reduced to a 6 bit index into
 * the 64 bit hash register using the following hash function.  The
 * hash function is an exclusive or of every sixth bit of the
 * destination address.
 *
 * hi[5] = da[5] ^ da[11] ^ da[17] ^ da[23] ^ da[29] ^ da[35] ^ da[41] ^ da[47]
 * hi[4] = da[4] ^ da[10] ^ da[16] ^ da[22] ^ da[28] ^ da[34] ^ da[40] ^ da[46]
 * hi[3] = da[3] ^ da[09] ^ da[15] ^ da[21] ^ da[27] ^ da[33] ^ da[39] ^ da[45]
 * hi[2] = da[2] ^ da[08] ^ da[14] ^ da[20] ^ da[26] ^ da[32] ^ da[38] ^ da[44]
 * hi[1] = da[1] ^ da[07] ^ da[13] ^ da[19] ^ da[25] ^ da[31] ^ da[37] ^ da[43]
 * hi[0] = da[0] ^ da[06] ^ da[12] ^ da[18] ^ da[24] ^ da[30] ^ da[36] ^ da[42]
 *
 * da[0] represents the least significant bit of the first byte
 * received, that is, the multicast/unicast indicator, and da[47]
 * represents the most significant bit of the last byte received.  If
 * the hash index, hi[n], points to a bit that is set in the hash
 * register then the frame will be matched according to whether the
 * frame is multicast or unicast.  A multicast match will be signalled
 * if the multicast hash enable bit is set, da[0] is 1 and the hash
 * index points to a bit set in the hash register.  A unicast match
 * will be signalled if the unicast hash enable bit is set, da[0] is 0
 * and the hash index points to a bit set in the hash register.  To
 * receive all multicast frames, the hash register should be set with
 * all ones and the multicast hash enable bit should be set in the
 * network configuration register.
 */

static inline int hash_bit_value(int bitnr, __u8 *addr)
{
	if (addr[bitnr / 8] & (1 << (bitnr % 8)))
		return 1;
	return 0;
}

/* Return the hash index value for the specified address. */
static int hash_get_index(__u8 *addr)
{
	int i, j, bitval;
	int hash_index = 0;

	for (j = 0; j < 6; j++) {
		for (i = 0, bitval = 0; i < 8; i++)
			bitval ^= hash_bit_value(i * 6 + j, addr);

		hash_index |= (bitval << j);
	}

	return hash_index;
}

/* Add multicast addresses to the internal multicast-hash table. */
static void macb_sethashtable(struct net_device *netdev)
{
	struct netdev_hw_addr *ha;
	unsigned long mc_filter[2];
	unsigned int bitnr;
	struct macb *bp = netdev_priv(netdev);

	mc_filter[0] = 0;
	mc_filter[1] = 0;

	netdev_for_each_mc_addr(ha, netdev) {
		bitnr = hash_get_index(ha->addr);
		mc_filter[bitnr >> 5] |= 1 << (bitnr & 31);
	}

	macb_or_gem_writel(bp, HRB, mc_filter[0]);
	macb_or_gem_writel(bp, HRT, mc_filter[1]);
}

/* Enable/Disable promiscuous and multicast modes. */
static void macb_set_rx_mode(struct net_device *netdev)
{
	unsigned long cfg;
	struct macb *bp = netdev_priv(netdev);

	cfg = macb_readl(bp, NCFGR);

	if (netdev->flags & IFF_PROMISC) {
		/* Enable promiscuous mode */
		cfg |= MACB_BIT(CAF);

		/* Disable RX checksum offload */
		if (macb_is_gem(bp))
			cfg &= ~GEM_BIT(RXCOEN);
	} else {
		/* Disable promiscuous mode */
		cfg &= ~MACB_BIT(CAF);

		/* Enable RX checksum offload only if requested */
		if (macb_is_gem(bp) && netdev->features & NETIF_F_RXCSUM)
			cfg |= GEM_BIT(RXCOEN);
	}

	if (netdev->flags & IFF_ALLMULTI) {
		/* Enable all multicast mode */
		macb_or_gem_writel(bp, HRB, -1);
		macb_or_gem_writel(bp, HRT, -1);
		cfg |= MACB_BIT(NCFGR_MTI);
	} else if (!netdev_mc_empty(netdev)) {
		/* Enable specific multicasts */
		macb_sethashtable(netdev);
		cfg |= MACB_BIT(NCFGR_MTI);
	} else if (netdev->flags & (~IFF_ALLMULTI)) {
		/* Disable all multicast mode */
		macb_or_gem_writel(bp, HRB, 0);
		macb_or_gem_writel(bp, HRT, 0);
		cfg &= ~MACB_BIT(NCFGR_MTI);
	}

	macb_writel(bp, NCFGR, cfg);
}

static int macb_open(struct net_device *netdev)
{
	size_t bufsz = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN;
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned int q;
	int err;

	netdev_dbg(bp->netdev, "open\n");

	err = pm_runtime_resume_and_get(&bp->pdev->dev);
	if (err < 0)
		return err;

	/* RX buffers initialization */
	macb_init_rx_buffer_size(bp, bufsz);

	err = macb_alloc(bp);
	if (err) {
		netdev_err(netdev, "Unable to allocate DMA memory (error %d)\n",
			   err);
		goto pm_exit;
	}

	bp->macbgem_ops.mog_init_rings(bp);
	macb_init_buffers(bp);

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		napi_enable(&queue->napi_rx);
		napi_enable(&queue->napi_tx);
	}

	macb_init_hw(bp);

	err = phy_set_mode_ext(bp->phy, PHY_MODE_ETHERNET, bp->phy_interface);
	if (err)
		goto reset_hw;

	err = phy_power_on(bp->phy);
	if (err)
		goto reset_hw;

	err = macb_phylink_connect(bp);
	if (err)
		goto phy_off;

	netif_tx_start_all_queues(netdev);

	if (bp->ptp_info)
		bp->ptp_info->ptp_init(netdev);

	return 0;

phy_off:
	phy_power_off(bp->phy);

reset_hw:
	macb_reset_hw(bp);
	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		napi_disable(&queue->napi_rx);
		napi_disable(&queue->napi_tx);
	}
	macb_free(bp);
pm_exit:
	pm_runtime_put_sync(&bp->pdev->dev);
	return err;
}

static int macb_close(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned long flags;
	unsigned int q;

	netif_tx_stop_all_queues(netdev);

	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
		napi_disable(&queue->napi_rx);
		napi_disable(&queue->napi_tx);
		netdev_tx_reset_queue(netdev_get_tx_queue(netdev, q));
	}

	cancel_delayed_work_sync(&bp->tx_lpi_work);

	phylink_stop(bp->phylink);
	phylink_disconnect_phy(bp->phylink);

	phy_power_off(bp->phy);

	spin_lock_irqsave(&bp->lock, flags);
	macb_reset_hw(bp);
	netif_carrier_off(netdev);
	spin_unlock_irqrestore(&bp->lock, flags);

	macb_free(bp);

	if (bp->ptp_info)
		bp->ptp_info->ptp_remove(netdev);

	pm_runtime_put(&bp->pdev->dev);

	return 0;
}

static int macb_change_mtu(struct net_device *netdev, int new_mtu)
{
	if (netif_running(netdev))
		return -EBUSY;

	WRITE_ONCE(netdev->mtu, new_mtu);

	return 0;
}

static int macb_set_mac_addr(struct net_device *netdev, void *addr)
{
	int err;

	err = eth_mac_addr(netdev, addr);
	if (err < 0)
		return err;

	macb_set_hwaddr(netdev_priv(netdev));
	return 0;
}

static void gem_update_stats(struct macb *bp)
{
	struct macb_queue *queue;
	unsigned int i, q, idx;
	unsigned long *stat;

	u64 *p = &bp->hw_stats.gem.tx_octets;

	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
		u32 offset = gem_statistics[i].offset;
		u64 val = bp->macb_reg_readl(bp, offset);

		bp->ethtool_stats[i] += val;
		*p += val;

		if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
			/* Add GEM_OCTTXH, GEM_OCTRXH */
			val = bp->macb_reg_readl(bp, offset + 4);
			bp->ethtool_stats[i] += ((u64)val) << 32;
			*p += ((u64)val) << 32;
		}
	}

	idx = GEM_STATS_LEN;
	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
		for (i = 0, stat = &queue->stats.first; i < QUEUE_STATS_LEN; ++i, ++stat)
			bp->ethtool_stats[idx++] = *stat;
}

static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat)
{
	struct gem_stats *hwstat = &bp->hw_stats.gem;

	spin_lock_irq(&bp->stats_lock);
	if (netif_running(bp->netdev))
		gem_update_stats(bp);

	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
			    hwstat->rx_alignment_errors +
			    hwstat->rx_resource_errors +
			    hwstat->rx_overruns +
			    hwstat->rx_oversize_frames +
			    hwstat->rx_jabbers +
			    hwstat->rx_undersized_frames +
			    hwstat->rx_length_field_frame_errors);
	nstat->tx_errors = (hwstat->tx_late_collisions +
			    hwstat->tx_excessive_collisions +
			    hwstat->tx_underrun +
			    hwstat->tx_carrier_sense_errors);
	nstat->multicast = hwstat->rx_multicast_frames;
	nstat->collisions = (hwstat->tx_single_collision_frames +
			     hwstat->tx_multiple_collision_frames +
			     hwstat->tx_excessive_collisions);
	nstat->rx_length_errors = (hwstat->rx_oversize_frames +
				   hwstat->rx_jabbers +
				   hwstat->rx_undersized_frames +
				   hwstat->rx_length_field_frame_errors);
	nstat->rx_over_errors = hwstat->rx_resource_errors;
	nstat->rx_crc_errors = hwstat->rx_frame_check_sequence_errors;
	nstat->rx_frame_errors = hwstat->rx_alignment_errors;
	nstat->rx_fifo_errors = hwstat->rx_overruns;
	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
	nstat->tx_fifo_errors = hwstat->tx_underrun;
	spin_unlock_irq(&bp->stats_lock);
}

static void gem_get_ethtool_stats(struct net_device *netdev,
				  struct ethtool_stats *stats, u64 *data)
{
	struct macb *bp = netdev_priv(netdev);

	spin_lock_irq(&bp->stats_lock);
	gem_update_stats(bp);
	memcpy(data, &bp->ethtool_stats, sizeof(u64)
			* (GEM_STATS_LEN + QUEUE_STATS_LEN * bp->num_queues));
	spin_unlock_irq(&bp->stats_lock);
}

static int gem_get_sset_count(struct net_device *netdev, int sset)
{
	struct macb *bp = netdev_priv(netdev);

	switch (sset) {
	case ETH_SS_STATS:
		return GEM_STATS_LEN + bp->num_queues * QUEUE_STATS_LEN;
	default:
		return -EOPNOTSUPP;
	}
}

static void gem_get_ethtool_strings(struct net_device *netdev, u32 sset, u8 *p)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned int i;
	unsigned int q;

	switch (sset) {
	case ETH_SS_STATS:
		for (i = 0; i < GEM_STATS_LEN; i++, p += ETH_GSTRING_LEN)
			memcpy(p, gem_statistics[i].stat_string,
			       ETH_GSTRING_LEN);

		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
			for (i = 0; i < QUEUE_STATS_LEN; i++)
				ethtool_sprintf(&p, "q%u_%s", q, queue_statistics[i].stat_string);
		}
		break;
	}
}

static void macb_get_stats(struct net_device *netdev,
			   struct rtnl_link_stats64 *nstat)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_stats *hwstat = &bp->hw_stats.macb;

	netdev_stats_to_stats64(nstat, &bp->netdev->stats);
	if (macb_is_gem(bp)) {
		gem_get_stats(bp, nstat);
		return;
	}

	/* read stats from hardware */
	spin_lock_irq(&bp->stats_lock);
	macb_update_stats(bp);

	/* Convert HW stats into netdevice stats */
	nstat->rx_errors = (hwstat->rx_fcs_errors +
			    hwstat->rx_align_errors +
			    hwstat->rx_resource_errors +
			    hwstat->rx_overruns +
			    hwstat->rx_oversize_pkts +
			    hwstat->rx_jabbers +
			    hwstat->rx_undersize_pkts +
			    hwstat->rx_length_mismatch);
	nstat->tx_errors = (hwstat->tx_late_cols +
			    hwstat->tx_excessive_cols +
			    hwstat->tx_underruns +
			    hwstat->tx_carrier_errors +
			    hwstat->sqe_test_errors);
	nstat->collisions = (hwstat->tx_single_cols +
			     hwstat->tx_multiple_cols +
			     hwstat->tx_excessive_cols);
	nstat->rx_length_errors = (hwstat->rx_oversize_pkts +
				   hwstat->rx_jabbers +
				   hwstat->rx_undersize_pkts +
				   hwstat->rx_length_mismatch);
	nstat->rx_over_errors = hwstat->rx_resource_errors +
				   hwstat->rx_overruns;
	nstat->rx_crc_errors = hwstat->rx_fcs_errors;
	nstat->rx_frame_errors = hwstat->rx_align_errors;
	nstat->rx_fifo_errors = hwstat->rx_overruns;
	/* XXX: What does "missed" mean? */
	nstat->tx_aborted_errors = hwstat->tx_excessive_cols;
	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
	nstat->tx_fifo_errors = hwstat->tx_underruns;
	/* Don't know about heartbeat or window errors... */
	spin_unlock_irq(&bp->stats_lock);
}

static void macb_get_pause_stats(struct net_device *netdev,
				 struct ethtool_pause_stats *pause_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_stats *hwstat = &bp->hw_stats.macb;

	spin_lock_irq(&bp->stats_lock);
	macb_update_stats(bp);
	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
	spin_unlock_irq(&bp->stats_lock);
}

static void gem_get_pause_stats(struct net_device *netdev,
				struct ethtool_pause_stats *pause_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct gem_stats *hwstat = &bp->hw_stats.gem;

	spin_lock_irq(&bp->stats_lock);
	gem_update_stats(bp);
	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
	spin_unlock_irq(&bp->stats_lock);
}

static void macb_get_eth_mac_stats(struct net_device *netdev,
				   struct ethtool_eth_mac_stats *mac_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_stats *hwstat = &bp->hw_stats.macb;

	spin_lock_irq(&bp->stats_lock);
	macb_update_stats(bp);
	mac_stats->FramesTransmittedOK = hwstat->tx_ok;
	mac_stats->SingleCollisionFrames = hwstat->tx_single_cols;
	mac_stats->MultipleCollisionFrames = hwstat->tx_multiple_cols;
	mac_stats->FramesReceivedOK = hwstat->rx_ok;
	mac_stats->FrameCheckSequenceErrors = hwstat->rx_fcs_errors;
	mac_stats->AlignmentErrors = hwstat->rx_align_errors;
	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred;
	mac_stats->LateCollisions = hwstat->tx_late_cols;
	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_cols;
	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underruns;
	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_errors;
	mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns;
	mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch;
	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts;
	spin_unlock_irq(&bp->stats_lock);
}

static void gem_get_eth_mac_stats(struct net_device *netdev,
				  struct ethtool_eth_mac_stats *mac_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct gem_stats *hwstat = &bp->hw_stats.gem;

	spin_lock_irq(&bp->stats_lock);
	gem_update_stats(bp);
	mac_stats->FramesTransmittedOK = hwstat->tx_frames;
	mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames;
	mac_stats->MultipleCollisionFrames =
		hwstat->tx_multiple_collision_frames;
	mac_stats->FramesReceivedOK = hwstat->rx_frames;
	mac_stats->FrameCheckSequenceErrors =
		hwstat->rx_frame_check_sequence_errors;
	mac_stats->AlignmentErrors = hwstat->rx_alignment_errors;
	mac_stats->OctetsTransmittedOK = hwstat->tx_octets;
	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred_frames;
	mac_stats->LateCollisions = hwstat->tx_late_collisions;
	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_collisions;
	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underrun;
	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_sense_errors;
	mac_stats->OctetsReceivedOK = hwstat->rx_octets;
	mac_stats->MulticastFramesXmittedOK = hwstat->tx_multicast_frames;
	mac_stats->BroadcastFramesXmittedOK = hwstat->tx_broadcast_frames;
	mac_stats->MulticastFramesReceivedOK = hwstat->rx_multicast_frames;
	mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames;
	mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors;
	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames;
	spin_unlock_irq(&bp->stats_lock);
}

/* TODO: Report SQE test errors when added to phy_stats */
static void macb_get_eth_phy_stats(struct net_device *netdev,
				   struct ethtool_eth_phy_stats *phy_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_stats *hwstat = &bp->hw_stats.macb;

	spin_lock_irq(&bp->stats_lock);
	macb_update_stats(bp);
	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
	spin_unlock_irq(&bp->stats_lock);
}

static void gem_get_eth_phy_stats(struct net_device *netdev,
				  struct ethtool_eth_phy_stats *phy_stats)
{
	struct macb *bp = netdev_priv(netdev);
	struct gem_stats *hwstat = &bp->hw_stats.gem;

	spin_lock_irq(&bp->stats_lock);
	gem_update_stats(bp);
	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
	spin_unlock_irq(&bp->stats_lock);
}

static void macb_get_rmon_stats(struct net_device *netdev,
				struct ethtool_rmon_stats *rmon_stats,
				const struct ethtool_rmon_hist_range **ranges)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_stats *hwstat = &bp->hw_stats.macb;

	spin_lock_irq(&bp->stats_lock);
	macb_update_stats(bp);
	rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts;
	rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts;
	rmon_stats->jabbers = hwstat->rx_jabbers;
	spin_unlock_irq(&bp->stats_lock);
}

static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = {
	{   64,    64 },
	{   65,   127 },
	{  128,   255 },
	{  256,   511 },
	{  512,  1023 },
	{ 1024,  1518 },
	{ 1519, 16384 },
	{ },
};

static void gem_get_rmon_stats(struct net_device *netdev,
			       struct ethtool_rmon_stats *rmon_stats,
			       const struct ethtool_rmon_hist_range **ranges)
{
	struct macb *bp = netdev_priv(netdev);
	struct gem_stats *hwstat = &bp->hw_stats.gem;

	spin_lock_irq(&bp->stats_lock);
	gem_update_stats(bp);
	rmon_stats->undersize_pkts = hwstat->rx_undersized_frames;
	rmon_stats->oversize_pkts = hwstat->rx_oversize_frames;
	rmon_stats->jabbers = hwstat->rx_jabbers;
	rmon_stats->hist[0] = hwstat->rx_64_byte_frames;
	rmon_stats->hist[1] = hwstat->rx_65_127_byte_frames;
	rmon_stats->hist[2] = hwstat->rx_128_255_byte_frames;
	rmon_stats->hist[3] = hwstat->rx_256_511_byte_frames;
	rmon_stats->hist[4] = hwstat->rx_512_1023_byte_frames;
	rmon_stats->hist[5] = hwstat->rx_1024_1518_byte_frames;
	rmon_stats->hist[6] = hwstat->rx_greater_than_1518_byte_frames;
	rmon_stats->hist_tx[0] = hwstat->tx_64_byte_frames;
	rmon_stats->hist_tx[1] = hwstat->tx_65_127_byte_frames;
	rmon_stats->hist_tx[2] = hwstat->tx_128_255_byte_frames;
	rmon_stats->hist_tx[3] = hwstat->tx_256_511_byte_frames;
	rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames;
	rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames;
	rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames;
	spin_unlock_irq(&bp->stats_lock);
	*ranges = gem_rmon_ranges;
}

static int macb_get_regs_len(struct net_device *netdev)
{
	return MACB_GREGS_NBR * sizeof(u32);
}

static void macb_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
			  void *p)
{
	struct macb *bp = netdev_priv(netdev);
	unsigned int tail, head;
	u32 *regs_buff = p;

	regs->version = (macb_readl(bp, MID) & ((1 << MACB_REV_SIZE) - 1))
			| MACB_GREGS_VERSION;

	tail = macb_tx_ring_wrap(bp, bp->queues[0].tx_tail);
	head = macb_tx_ring_wrap(bp, bp->queues[0].tx_head);

	regs_buff[0]  = macb_readl(bp, NCR);
	regs_buff[1]  = macb_or_gem_readl(bp, NCFGR);
	regs_buff[2]  = macb_readl(bp, NSR);
	regs_buff[3]  = macb_readl(bp, TSR);
	regs_buff[4]  = macb_readl(bp, RBQP);
	regs_buff[5]  = macb_readl(bp, TBQP);
	regs_buff[6]  = macb_readl(bp, RSR);
	regs_buff[7]  = macb_readl(bp, IMR);

	regs_buff[8]  = tail;
	regs_buff[9]  = head;
	regs_buff[10] = macb_tx_dma(&bp->queues[0], tail);
	regs_buff[11] = macb_tx_dma(&bp->queues[0], head);

	if (!(bp->caps & MACB_CAPS_USRIO_DISABLED))
		regs_buff[12] = macb_or_gem_readl(bp, USRIO);
	if (macb_is_gem(bp))
		regs_buff[13] = gem_readl(bp, DMACFG);
}

static void macb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
{
	struct macb *bp = netdev_priv(netdev);

	phylink_ethtool_get_wol(bp->phylink, wol);
	wol->supported |= (WAKE_MAGIC | WAKE_ARP);

	/* Add macb wolopts to phy wolopts */
	wol->wolopts |= bp->wolopts;
}

static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
{
	struct macb *bp = netdev_priv(netdev);
	int ret;

	/* Pass the order to phylink layer */
	ret = phylink_ethtool_set_wol(bp->phylink, wol);
	/* Don't manage WoL on MAC, if PHY set_wol() fails */
	if (ret && ret != -EOPNOTSUPP)
		return ret;

	bp->wolopts = (wol->wolopts & WAKE_MAGIC) ? WAKE_MAGIC : 0;
	bp->wolopts |= (wol->wolopts & WAKE_ARP) ? WAKE_ARP : 0;
	bp->wol = (wol->wolopts) ? MACB_WOL_ENABLED : 0;

	device_set_wakeup_enable(&bp->pdev->dev, bp->wol);

	return 0;
}

static int macb_get_link_ksettings(struct net_device *netdev,
				   struct ethtool_link_ksettings *kset)
{
	struct macb *bp = netdev_priv(netdev);

	return phylink_ethtool_ksettings_get(bp->phylink, kset);
}

static int macb_set_link_ksettings(struct net_device *netdev,
				   const struct ethtool_link_ksettings *kset)
{
	struct macb *bp = netdev_priv(netdev);

	return phylink_ethtool_ksettings_set(bp->phylink, kset);
}

static void macb_get_ringparam(struct net_device *netdev,
			       struct ethtool_ringparam *ring,
			       struct kernel_ethtool_ringparam *kernel_ring,
			       struct netlink_ext_ack *extack)
{
	struct macb *bp = netdev_priv(netdev);

	ring->rx_max_pending = MAX_RX_RING_SIZE;
	ring->tx_max_pending = MAX_TX_RING_SIZE;

	ring->rx_pending = bp->rx_ring_size;
	ring->tx_pending = bp->tx_ring_size;
}

static int macb_set_ringparam(struct net_device *netdev,
			      struct ethtool_ringparam *ring,
			      struct kernel_ethtool_ringparam *kernel_ring,
			      struct netlink_ext_ack *extack)
{
	struct macb *bp = netdev_priv(netdev);
	u32 new_rx_size, new_tx_size;
	unsigned int reset = 0;

	if (bp->caps & MACB_CAPS_MACB_IS_EMAC)
		return -EOPNOTSUPP;

	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
		return -EINVAL;

	new_rx_size = clamp_t(u32, ring->rx_pending,
			      MIN_RX_RING_SIZE, MAX_RX_RING_SIZE);
	new_rx_size = roundup_pow_of_two(new_rx_size);

	new_tx_size = clamp_t(u32, ring->tx_pending,
			      MIN_TX_RING_SIZE, MAX_TX_RING_SIZE);
	new_tx_size = roundup_pow_of_two(new_tx_size);

	if ((new_tx_size == bp->tx_ring_size) &&
	    (new_rx_size == bp->rx_ring_size)) {
		/* nothing to do */
		return 0;
	}

	if (netif_running(bp->netdev)) {
		reset = 1;
		macb_close(bp->netdev);
	}

	bp->rx_ring_size = new_rx_size;
	bp->tx_ring_size = new_tx_size;

	if (reset)
		macb_open(bp->netdev);

	return 0;
}

#ifdef CONFIG_MACB_USE_HWSTAMP
static unsigned int gem_get_tsu_rate(struct macb *bp)
{
	struct clk *tsu_clk;
	unsigned int tsu_rate;

	if (!IS_ERR_OR_NULL(bp->tsu_clk)) {
		tsu_rate = clk_get_rate(bp->tsu_clk);
	} else {
		tsu_clk = bp->pclk;
		tsu_rate = clk_get_rate(tsu_clk);
		dev_warn(&bp->pdev->dev, "devicetree missing tsu_clk, using pclk as fallback\n");
	}

	return tsu_rate;
}

static s32 gem_get_ptp_max_adj(void)
{
	return 64000000;
}

static int gem_get_ts_info(struct net_device *netdev,
			   struct kernel_ethtool_ts_info *info)
{
	struct macb *bp = netdev_priv(netdev);

	if (!macb_dma_ptp(bp)) {
		ethtool_op_get_ts_info(netdev, info);
		return 0;
	}

	info->so_timestamping =
		SOF_TIMESTAMPING_TX_SOFTWARE |
		SOF_TIMESTAMPING_TX_HARDWARE |
		SOF_TIMESTAMPING_RX_HARDWARE |
		SOF_TIMESTAMPING_RAW_HARDWARE;
	info->tx_types =
		(1 << HWTSTAMP_TX_ONESTEP_SYNC) |
		(1 << HWTSTAMP_TX_OFF) |
		(1 << HWTSTAMP_TX_ON);
	info->rx_filters =
		(1 << HWTSTAMP_FILTER_NONE) |
		(1 << HWTSTAMP_FILTER_ALL);

	if (bp->ptp_clock)
		info->phc_index = ptp_clock_index(bp->ptp_clock);

	return 0;
}

static struct macb_ptp_info gem_ptp_info = {
	.ptp_init	 = gem_ptp_init,
	.ptp_remove	 = gem_ptp_remove,
	.get_ptp_max_adj = gem_get_ptp_max_adj,
	.get_tsu_rate	 = gem_get_tsu_rate,
	.get_ts_info	 = gem_get_ts_info,
	.get_hwtst	 = gem_get_hwtst,
	.set_hwtst	 = gem_set_hwtst,
};
#endif

static int macb_get_ts_info(struct net_device *netdev,
			    struct kernel_ethtool_ts_info *info)
{
	struct macb *bp = netdev_priv(netdev);

	if (bp->ptp_info)
		return bp->ptp_info->get_ts_info(netdev, info);

	return ethtool_op_get_ts_info(netdev, info);
}

static void gem_enable_flow_filters(struct macb *bp, bool enable)
{
	struct net_device *netdev = bp->netdev;
	struct ethtool_rx_fs_item *item;
	u32 t2_scr;
	int num_t2_scr;

	if (!(netdev->features & NETIF_F_NTUPLE))
		return;

	num_t2_scr = GEM_BFEXT(T2SCR, gem_readl(bp, DCFG8));

	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
		struct ethtool_rx_flow_spec *fs = &item->fs;
		struct ethtool_tcpip4_spec *tp4sp_m;

		if (fs->location >= num_t2_scr)
			continue;

		t2_scr = gem_readl_n(bp, SCRT2, fs->location);

		/* enable/disable screener regs for the flow entry */
		t2_scr = GEM_BFINS(ETHTEN, enable, t2_scr);

		/* only enable fields with no masking */
		tp4sp_m = &(fs->m_u.tcp_ip4_spec);

		if (enable && (tp4sp_m->ip4src == 0xFFFFFFFF))
			t2_scr = GEM_BFINS(CMPAEN, 1, t2_scr);
		else
			t2_scr = GEM_BFINS(CMPAEN, 0, t2_scr);

		if (enable && (tp4sp_m->ip4dst == 0xFFFFFFFF))
			t2_scr = GEM_BFINS(CMPBEN, 1, t2_scr);
		else
			t2_scr = GEM_BFINS(CMPBEN, 0, t2_scr);

		if (enable && ((tp4sp_m->psrc == 0xFFFF) || (tp4sp_m->pdst == 0xFFFF)))
			t2_scr = GEM_BFINS(CMPCEN, 1, t2_scr);
		else
			t2_scr = GEM_BFINS(CMPCEN, 0, t2_scr);

		gem_writel_n(bp, SCRT2, fs->location, t2_scr);
	}
}

static void gem_prog_cmp_regs(struct macb *bp, struct ethtool_rx_flow_spec *fs)
{
	struct ethtool_tcpip4_spec *tp4sp_v, *tp4sp_m;
	uint16_t index = fs->location;
	u32 w0, w1, t2_scr;
	bool cmp_a = false;
	bool cmp_b = false;
	bool cmp_c = false;

	if (!macb_is_gem(bp))
		return;

	tp4sp_v = &(fs->h_u.tcp_ip4_spec);
	tp4sp_m = &(fs->m_u.tcp_ip4_spec);

	/* ignore field if any masking set */
	if (tp4sp_m->ip4src == 0xFFFFFFFF) {
		/* 1st compare reg - IP source address */
		w0 = 0;
		w1 = 0;
		w0 = tp4sp_v->ip4src;
		w1 = GEM_BFINS(T2DISMSK, 1, w1); /* 32-bit compare */
		w1 = GEM_BFINS(T2CMPOFST, GEM_T2COMPOFST_ETYPE, w1);
		w1 = GEM_BFINS(T2OFST, ETYPE_SRCIP_OFFSET, w1);
		gem_writel_n(bp, T2CMPW0, T2CMP_OFST(GEM_IP4SRC_CMP(index)), w0);
		gem_writel_n(bp, T2CMPW1, T2CMP_OFST(GEM_IP4SRC_CMP(index)), w1);
		cmp_a = true;
	}

	/* ignore field if any masking set */
	if (tp4sp_m->ip4dst == 0xFFFFFFFF) {
		/* 2nd compare reg - IP destination address */
		w0 = 0;
		w1 = 0;
		w0 = tp4sp_v->ip4dst;
		w1 = GEM_BFINS(T2DISMSK, 1, w1); /* 32-bit compare */
		w1 = GEM_BFINS(T2CMPOFST, GEM_T2COMPOFST_ETYPE, w1);
		w1 = GEM_BFINS(T2OFST, ETYPE_DSTIP_OFFSET, w1);
		gem_writel_n(bp, T2CMPW0, T2CMP_OFST(GEM_IP4DST_CMP(index)), w0);
		gem_writel_n(bp, T2CMPW1, T2CMP_OFST(GEM_IP4DST_CMP(index)), w1);
		cmp_b = true;
	}

	/* ignore both port fields if masking set in both */
	if ((tp4sp_m->psrc == 0xFFFF) || (tp4sp_m->pdst == 0xFFFF)) {
		/* 3rd compare reg - source port, destination port */
		w0 = 0;
		w1 = 0;
		w1 = GEM_BFINS(T2CMPOFST, GEM_T2COMPOFST_IPHDR, w1);
		if (tp4sp_m->psrc == tp4sp_m->pdst) {
			w0 = GEM_BFINS(T2MASK, tp4sp_v->psrc, w0);
			w0 = GEM_BFINS(T2CMP, tp4sp_v->pdst, w0);
			w1 = GEM_BFINS(T2DISMSK, 1, w1); /* 32-bit compare */
			w1 = GEM_BFINS(T2OFST, IPHDR_SRCPORT_OFFSET, w1);
		} else {
			/* only one port definition */
			w1 = GEM_BFINS(T2DISMSK, 0, w1); /* 16-bit compare */
			w0 = GEM_BFINS(T2MASK, 0xFFFF, w0);
			if (tp4sp_m->psrc == 0xFFFF) { /* src port */
				w0 = GEM_BFINS(T2CMP, tp4sp_v->psrc, w0);
				w1 = GEM_BFINS(T2OFST, IPHDR_SRCPORT_OFFSET, w1);
			} else { /* dst port */
				w0 = GEM_BFINS(T2CMP, tp4sp_v->pdst, w0);
				w1 = GEM_BFINS(T2OFST, IPHDR_DSTPORT_OFFSET, w1);
			}
		}
		gem_writel_n(bp, T2CMPW0, T2CMP_OFST(GEM_PORT_CMP(index)), w0);
		gem_writel_n(bp, T2CMPW1, T2CMP_OFST(GEM_PORT_CMP(index)), w1);
		cmp_c = true;
	}

	t2_scr = 0;
	t2_scr = GEM_BFINS(QUEUE, (fs->ring_cookie) & 0xFF, t2_scr);
	t2_scr = GEM_BFINS(ETHT2IDX, SCRT2_ETHT, t2_scr);
	if (cmp_a)
		t2_scr = GEM_BFINS(CMPA, GEM_IP4SRC_CMP(index), t2_scr);
	if (cmp_b)
		t2_scr = GEM_BFINS(CMPB, GEM_IP4DST_CMP(index), t2_scr);
	if (cmp_c)
		t2_scr = GEM_BFINS(CMPC, GEM_PORT_CMP(index), t2_scr);
	gem_writel_n(bp, SCRT2, index, t2_scr);
}

static int gem_add_flow_filter(struct net_device *netdev,
		struct ethtool_rxnfc *cmd)
{
	struct macb *bp = netdev_priv(netdev);
	struct ethtool_rx_flow_spec *fs = &cmd->fs;
	struct ethtool_rx_fs_item *item, *newfs;
	unsigned long flags;
	int ret = -EINVAL;
	bool added = false;

	newfs = kmalloc_obj(*newfs);
	if (newfs == NULL)
		return -ENOMEM;
	memcpy(&newfs->fs, fs, sizeof(newfs->fs));

	netdev_dbg(netdev,
			"Adding flow filter entry,type=%u,queue=%u,loc=%u,src=%08X,dst=%08X,ps=%u,pd=%u\n",
			fs->flow_type, (int)fs->ring_cookie, fs->location,
			htonl(fs->h_u.tcp_ip4_spec.ip4src),
			htonl(fs->h_u.tcp_ip4_spec.ip4dst),
			be16_to_cpu(fs->h_u.tcp_ip4_spec.psrc),
			be16_to_cpu(fs->h_u.tcp_ip4_spec.pdst));

	spin_lock_irqsave(&bp->rx_fs_lock, flags);

	/* find correct place to add in list */
	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
		if (item->fs.location > newfs->fs.location) {
			list_add_tail(&newfs->list, &item->list);
			added = true;
			break;
		} else if (item->fs.location == fs->location) {
			netdev_err(netdev, "Rule not added: location %d not free!\n",
					fs->location);
			ret = -EBUSY;
			goto err;
		}
	}
	if (!added)
		list_add_tail(&newfs->list, &bp->rx_fs_list.list);

	gem_prog_cmp_regs(bp, fs);
	bp->rx_fs_list.count++;
	/* enable filtering if NTUPLE on */
	gem_enable_flow_filters(bp, 1);

	spin_unlock_irqrestore(&bp->rx_fs_lock, flags);
	return 0;

err:
	spin_unlock_irqrestore(&bp->rx_fs_lock, flags);
	kfree(newfs);
	return ret;
}

static int gem_del_flow_filter(struct net_device *netdev,
		struct ethtool_rxnfc *cmd)
{
	struct macb *bp = netdev_priv(netdev);
	struct ethtool_rx_fs_item *item;
	struct ethtool_rx_flow_spec *fs;
	unsigned long flags;

	spin_lock_irqsave(&bp->rx_fs_lock, flags);

	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
		if (item->fs.location == cmd->fs.location) {
			/* disable screener regs for the flow entry */
			fs = &(item->fs);
			netdev_dbg(netdev,
					"Deleting flow filter entry,type=%u,queue=%u,loc=%u,src=%08X,dst=%08X,ps=%u,pd=%u\n",
					fs->flow_type, (int)fs->ring_cookie, fs->location,
					htonl(fs->h_u.tcp_ip4_spec.ip4src),
					htonl(fs->h_u.tcp_ip4_spec.ip4dst),
					be16_to_cpu(fs->h_u.tcp_ip4_spec.psrc),
					be16_to_cpu(fs->h_u.tcp_ip4_spec.pdst));

			gem_writel_n(bp, SCRT2, fs->location, 0);

			list_del(&item->list);
			bp->rx_fs_list.count--;
			spin_unlock_irqrestore(&bp->rx_fs_lock, flags);
			kfree(item);
			return 0;
		}
	}

	spin_unlock_irqrestore(&bp->rx_fs_lock, flags);
	return -EINVAL;
}

static int gem_get_flow_entry(struct net_device *netdev,
		struct ethtool_rxnfc *cmd)
{
	struct macb *bp = netdev_priv(netdev);
	struct ethtool_rx_fs_item *item;

	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
		if (item->fs.location == cmd->fs.location) {
			memcpy(&cmd->fs, &item->fs, sizeof(cmd->fs));
			return 0;
		}
	}
	return -EINVAL;
}

static int gem_get_all_flow_entries(struct net_device *netdev,
		struct ethtool_rxnfc *cmd, u32 *rule_locs)
{
	struct macb *bp = netdev_priv(netdev);
	struct ethtool_rx_fs_item *item;
	uint32_t cnt = 0;

	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
		if (cnt == cmd->rule_cnt)
			return -EMSGSIZE;
		rule_locs[cnt] = item->fs.location;
		cnt++;
	}
	cmd->data = bp->max_tuples;
	cmd->rule_cnt = cnt;

	return 0;
}

static u32 gem_get_rx_ring_count(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);

	return bp->num_queues;
}

static int gem_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
		u32 *rule_locs)
{
	struct macb *bp = netdev_priv(netdev);
	int ret = 0;

	switch (cmd->cmd) {
	case ETHTOOL_GRXCLSRLCNT:
		cmd->rule_cnt = bp->rx_fs_list.count;
		break;
	case ETHTOOL_GRXCLSRULE:
		ret = gem_get_flow_entry(netdev, cmd);
		break;
	case ETHTOOL_GRXCLSRLALL:
		ret = gem_get_all_flow_entries(netdev, cmd, rule_locs);
		break;
	default:
		netdev_err(netdev,
			  "Command parameter %d is not supported\n", cmd->cmd);
		ret = -EOPNOTSUPP;
	}

	return ret;
}

static int gem_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
{
	struct macb *bp = netdev_priv(netdev);
	int ret;

	if (!(netdev->hw_features & NETIF_F_NTUPLE))
		return -EOPNOTSUPP;

	switch (cmd->cmd) {
	case ETHTOOL_SRXCLSRLINS:
		if ((cmd->fs.location >= bp->max_tuples)
				|| (cmd->fs.ring_cookie >= bp->num_queues)) {
			ret = -EINVAL;
			break;
		}
		ret = gem_add_flow_filter(netdev, cmd);
		break;
	case ETHTOOL_SRXCLSRLDEL:
		ret = gem_del_flow_filter(netdev, cmd);
		break;
	default:
		netdev_err(netdev,
			  "Command parameter %d is not supported\n", cmd->cmd);
		ret = -EOPNOTSUPP;
	}

	return ret;
}

static const struct ethtool_ops macb_ethtool_ops = {
	.get_regs_len		= macb_get_regs_len,
	.get_regs		= macb_get_regs,
	.get_link		= ethtool_op_get_link,
	.get_ts_info		= ethtool_op_get_ts_info,
	.get_pause_stats	= macb_get_pause_stats,
	.get_eth_mac_stats	= macb_get_eth_mac_stats,
	.get_eth_phy_stats	= macb_get_eth_phy_stats,
	.get_rmon_stats		= macb_get_rmon_stats,
	.get_wol		= macb_get_wol,
	.set_wol		= macb_set_wol,
	.get_link_ksettings     = macb_get_link_ksettings,
	.set_link_ksettings     = macb_set_link_ksettings,
	.get_ringparam		= macb_get_ringparam,
	.set_ringparam		= macb_set_ringparam,
};

static int macb_get_eee(struct net_device *netdev, struct ethtool_keee *eee)
{
	struct macb *bp = netdev_priv(netdev);

	return phylink_ethtool_get_eee(bp->phylink, eee);
}

static int macb_set_eee(struct net_device *netdev, struct ethtool_keee *eee)
{
	struct macb *bp = netdev_priv(netdev);

	return phylink_ethtool_set_eee(bp->phylink, eee);
}

static const struct ethtool_ops gem_ethtool_ops = {
	.get_regs_len		= macb_get_regs_len,
	.get_regs		= macb_get_regs,
	.get_wol		= macb_get_wol,
	.set_wol		= macb_set_wol,
	.get_link		= ethtool_op_get_link,
	.get_ts_info		= macb_get_ts_info,
	.get_ethtool_stats	= gem_get_ethtool_stats,
	.get_strings		= gem_get_ethtool_strings,
	.get_sset_count		= gem_get_sset_count,
	.get_pause_stats	= gem_get_pause_stats,
	.get_eth_mac_stats	= gem_get_eth_mac_stats,
	.get_eth_phy_stats	= gem_get_eth_phy_stats,
	.get_rmon_stats		= gem_get_rmon_stats,
	.get_link_ksettings     = macb_get_link_ksettings,
	.set_link_ksettings     = macb_set_link_ksettings,
	.get_ringparam		= macb_get_ringparam,
	.set_ringparam		= macb_set_ringparam,
	.get_rxnfc			= gem_get_rxnfc,
	.set_rxnfc			= gem_set_rxnfc,
	.get_rx_ring_count		= gem_get_rx_ring_count,
	.nway_reset			= phy_ethtool_nway_reset,
	.get_eee		= macb_get_eee,
	.set_eee		= macb_set_eee,
};

static int macb_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
{
	struct macb *bp = netdev_priv(netdev);

	if (!netif_running(netdev))
		return -EINVAL;

	return phylink_mii_ioctl(bp->phylink, rq, cmd);
}

static int macb_hwtstamp_get(struct net_device *netdev,
			     struct kernel_hwtstamp_config *cfg)
{
	struct macb *bp = netdev_priv(netdev);

	if (!netif_running(netdev))
		return -EINVAL;

	if (!bp->ptp_info)
		return -EOPNOTSUPP;

	return bp->ptp_info->get_hwtst(netdev, cfg);
}

static int macb_hwtstamp_set(struct net_device *netdev,
			     struct kernel_hwtstamp_config *cfg,
			     struct netlink_ext_ack *extack)
{
	struct macb *bp = netdev_priv(netdev);

	if (!netif_running(netdev))
		return -EINVAL;

	if (!bp->ptp_info)
		return -EOPNOTSUPP;

	return bp->ptp_info->set_hwtst(netdev, cfg, extack);
}

static inline void macb_set_txcsum_feature(struct macb *bp,
					   netdev_features_t features)
{
	u32 val;

	if (!macb_is_gem(bp))
		return;

	val = gem_readl(bp, DMACFG);
	if (features & NETIF_F_HW_CSUM)
		val |= GEM_BIT(TXCOEN);
	else
		val &= ~GEM_BIT(TXCOEN);

	gem_writel(bp, DMACFG, val);
}

static inline void macb_set_rxcsum_feature(struct macb *bp,
					   netdev_features_t features)
{
	struct net_device *netdev = bp->netdev;
	u32 val;

	if (!macb_is_gem(bp))
		return;

	val = gem_readl(bp, NCFGR);
	if ((features & NETIF_F_RXCSUM) && !(netdev->flags & IFF_PROMISC))
		val |= GEM_BIT(RXCOEN);
	else
		val &= ~GEM_BIT(RXCOEN);

	gem_writel(bp, NCFGR, val);
}

static inline void macb_set_rxflow_feature(struct macb *bp,
					   netdev_features_t features)
{
	if (!macb_is_gem(bp))
		return;

	gem_enable_flow_filters(bp, !!(features & NETIF_F_NTUPLE));
}

static int macb_set_features(struct net_device *netdev,
			     netdev_features_t features)
{
	struct macb *bp = netdev_priv(netdev);
	netdev_features_t changed = features ^ netdev->features;

	/* TX checksum offload */
	if (changed & NETIF_F_HW_CSUM)
		macb_set_txcsum_feature(bp, features);

	/* RX checksum offload */
	if (changed & NETIF_F_RXCSUM)
		macb_set_rxcsum_feature(bp, features);

	/* RX Flow Filters */
	if (changed & NETIF_F_NTUPLE)
		macb_set_rxflow_feature(bp, features);

	return 0;
}

static void macb_restore_features(struct macb *bp)
{
	struct net_device *netdev = bp->netdev;
	netdev_features_t features = netdev->features;
	struct ethtool_rx_fs_item *item;

	/* TX checksum offload */
	macb_set_txcsum_feature(bp, features);

	/* RX checksum offload */
	macb_set_rxcsum_feature(bp, features);

	/* RX Flow Filters */
	list_for_each_entry(item, &bp->rx_fs_list.list, list)
		gem_prog_cmp_regs(bp, &item->fs);

	macb_set_rxflow_feature(bp, features);
}

static int macb_taprio_setup_replace(struct net_device *netdev,
				     struct tc_taprio_qopt_offload *conf)
{
	u64 total_on_time = 0, start_time_sec = 0, start_time = conf->base_time;
	u32 configured_queues = 0, speed = 0, start_time_nsec;
	struct macb_queue_enst_config *enst_queue;
	struct ethtool_link_ksettings kset = {};
	struct macb *bp = netdev_priv(netdev);
	struct tc_taprio_sched_entry *entry;
	struct macb_queue *queue;
	u32 queue_mask;
	u8 queue_id;
	size_t i;
	int err;

	if (conf->num_entries > bp->num_queues) {
		netdev_err(netdev, "Too many TAPRIO entries: %zu > %d queues\n",
			   conf->num_entries, bp->num_queues);
		return -EINVAL;
	}

	if (conf->base_time < 0) {
		netdev_err(netdev, "Invalid base_time: must be 0 or positive, got %lld\n",
			   conf->base_time);
		return -ERANGE;
	}

	/* Get the current link speed */
	err = phylink_ethtool_ksettings_get(bp->phylink, &kset);
	if (unlikely(err)) {
		netdev_err(netdev, "Failed to get link settings: %d\n", err);
		return err;
	}

	speed = kset.base.speed;
	if (unlikely(speed == SPEED_UNKNOWN || !speed)) {
		netdev_err(netdev, "Invalid speed %d, link-down?\n", speed);
		return -EINVAL;
	}

	enst_queue = kzalloc_objs(*enst_queue, conf->num_entries);
	if (unlikely(!enst_queue))
		return -ENOMEM;

	/* Pre-validate all entries before making any hardware changes */
	for (i = 0; i < conf->num_entries; i++) {
		entry = &conf->entries[i];

		if (entry->command != TC_TAPRIO_CMD_SET_GATES) {
			netdev_err(netdev, "Entry %zu: unsupported command %d\n",
				   i, entry->command);
			err = -EOPNOTSUPP;
			goto cleanup;
		}

		/* Validate gate_mask: must be nonzero, single queue, and within range */
		if (!is_power_of_2(entry->gate_mask)) {
			netdev_err(netdev, "Entry %zu: gate_mask 0x%x is not a power of 2 (only one queue per entry allowed)\n",
				   i, entry->gate_mask);
			err = -EINVAL;
			goto cleanup;
		}

		/* gate_mask must not select queues outside the valid queues */
		queue_id = order_base_2(entry->gate_mask);
		if (queue_id >= bp->num_queues) {
			netdev_err(netdev, "Entry %zu: gate_mask 0x%x exceeds queue range (max_queues=%d)\n",
				   i, entry->gate_mask, bp->num_queues);
			err = -EINVAL;
			goto cleanup;
		}

		/* Check for start time limits */
		start_time_sec = start_time;
		start_time_nsec = do_div(start_time_sec, NSEC_PER_SEC);
		if (start_time_sec > GENMASK(GEM_START_TIME_SEC_SIZE - 1, 0)) {
			netdev_err(netdev, "Entry %zu: Start time %llu s exceeds hardware limit\n",
				   i, start_time_sec);
			err = -ERANGE;
			goto cleanup;
		}

		/* Check for on time limit */
		if (entry->interval > enst_max_hw_interval(speed)) {
			netdev_err(netdev, "Entry %zu: interval %u ns exceeds hardware limit %llu ns\n",
				   i, entry->interval, enst_max_hw_interval(speed));
			err = -ERANGE;
			goto cleanup;
		}

		/* Check for off time limit*/
		if ((conf->cycle_time - entry->interval) > enst_max_hw_interval(speed)) {
			netdev_err(netdev, "Entry %zu: off_time %llu ns exceeds hardware limit %llu ns\n",
				   i, conf->cycle_time - entry->interval,
				   enst_max_hw_interval(speed));
			err = -ERANGE;
			goto cleanup;
		}

		enst_queue[i].queue_id = queue_id;
		enst_queue[i].start_time_mask =
			(start_time_sec << GEM_START_TIME_SEC_OFFSET) |
			start_time_nsec;
		enst_queue[i].on_time_bytes =
			enst_ns_to_hw_units(entry->interval, speed);
		enst_queue[i].off_time_bytes =
			enst_ns_to_hw_units(conf->cycle_time - entry->interval, speed);

		configured_queues |= entry->gate_mask;
		total_on_time += entry->interval;
		start_time += entry->interval;
	}

	/* Check total interval doesn't exceed cycle time */
	if (total_on_time > conf->cycle_time) {
		netdev_err(netdev, "Total ON %llu ns exceeds cycle time %llu ns\n",
			   total_on_time, conf->cycle_time);
		err = -EINVAL;
		goto cleanup;
	}

	netdev_dbg(netdev, "TAPRIO setup: %zu entries, base_time=%lld ns, cycle_time=%llu ns\n",
		   conf->num_entries, conf->base_time, conf->cycle_time);

	/* All validations passed - proceed with hardware configuration */
	scoped_guard(spinlock_irqsave, &bp->lock) {
		/* Disable ENST queues if running before configuring */
		queue_mask = BIT_U32(bp->num_queues) - 1;
		gem_writel(bp, ENST_CONTROL,
			   queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET);

		for (i = 0; i < conf->num_entries; i++) {
			queue = &bp->queues[enst_queue[i].queue_id];
			/* Configure queue timing registers */
			queue_writel(queue, ENST_START_TIME,
				     enst_queue[i].start_time_mask);
			queue_writel(queue, ENST_ON_TIME,
				     enst_queue[i].on_time_bytes);
			queue_writel(queue, ENST_OFF_TIME,
				     enst_queue[i].off_time_bytes);
		}

		/* Enable ENST for all configured queues in one write */
		gem_writel(bp, ENST_CONTROL, configured_queues);
	}

	netdev_info(netdev, "TAPRIO configuration completed successfully: %zu entries, %d queues configured\n",
		    conf->num_entries, hweight32(configured_queues));

cleanup:
	kfree(enst_queue);
	return err;
}

static void macb_taprio_destroy(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	u32 queue_mask;
	unsigned int q;

	netdev_reset_tc(netdev);
	queue_mask = BIT_U32(bp->num_queues) - 1;

	scoped_guard(spinlock_irqsave, &bp->lock) {
		/* Single disable command for all queues */
		gem_writel(bp, ENST_CONTROL,
			   queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET);

		/* Clear all queue ENST registers in batch */
		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
			queue_writel(queue, ENST_START_TIME, 0);
			queue_writel(queue, ENST_ON_TIME, 0);
			queue_writel(queue, ENST_OFF_TIME, 0);
		}
	}
	netdev_info(netdev, "TAPRIO destroy: All gates disabled\n");
}

static int macb_setup_taprio(struct net_device *netdev,
			     struct tc_taprio_qopt_offload *taprio)
{
	struct macb *bp = netdev_priv(netdev);
	int err = 0;

	if (unlikely(!(netdev->hw_features & NETIF_F_HW_TC)))
		return -EOPNOTSUPP;

	/* Check if Device is in runtime suspend */
	if (unlikely(pm_runtime_suspended(&bp->pdev->dev))) {
		netdev_err(netdev, "Device is in runtime suspend\n");
		return -EOPNOTSUPP;
	}

	switch (taprio->cmd) {
	case TAPRIO_CMD_REPLACE:
		err = macb_taprio_setup_replace(netdev, taprio);
		break;
	case TAPRIO_CMD_DESTROY:
		macb_taprio_destroy(netdev);
		break;
	default:
		err = -EOPNOTSUPP;
	}

	return err;
}

static int macb_setup_tc(struct net_device *netdev, enum tc_setup_type type,
			 void *type_data)
{
	if (!netdev || !type_data)
		return -EINVAL;

	switch (type) {
	case TC_SETUP_QDISC_TAPRIO:
		return macb_setup_taprio(netdev, type_data);
	default:
		return -EOPNOTSUPP;
	}
}

static void macb_tx_timeout(struct net_device *netdev, unsigned int q)
{
	struct macb *bp = netdev_priv(netdev);

	macb_tx_restart(&bp->queues[q]);
}

static const struct net_device_ops macb_netdev_ops = {
	.ndo_open		= macb_open,
	.ndo_stop		= macb_close,
	.ndo_start_xmit		= macb_start_xmit,
	.ndo_set_rx_mode	= macb_set_rx_mode,
	.ndo_get_stats64	= macb_get_stats,
	.ndo_eth_ioctl		= macb_ioctl,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_change_mtu		= macb_change_mtu,
	.ndo_set_mac_address	= macb_set_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= macb_poll_controller,
#endif
	.ndo_set_features	= macb_set_features,
	.ndo_features_check	= macb_features_check,
	.ndo_hwtstamp_set	= macb_hwtstamp_set,
	.ndo_hwtstamp_get	= macb_hwtstamp_get,
	.ndo_setup_tc		= macb_setup_tc,
	.ndo_tx_timeout		= macb_tx_timeout,
};

/* Configure peripheral capabilities according to device tree
 * and integration options used
 */
static void macb_configure_caps(struct macb *bp,
				const struct macb_config *dt_conf)
{
	u32 dcfg;

	bp->caps = dt_conf->caps;

	if (!dt_conf->usrio)
		bp->caps |= MACB_CAPS_USRIO_DISABLED;

	if (hw_is_gem(bp->regs, bp->native_io)) {
		bp->caps |= MACB_CAPS_MACB_IS_GEM;

		dcfg = gem_readl(bp, DCFG1);
		if (GEM_BFEXT(IRQCOR, dcfg) == 0)
			bp->caps |= MACB_CAPS_ISR_CLEAR_ON_WRITE;
		if (GEM_BFEXT(NO_PCS, dcfg) == 0)
			bp->caps |= MACB_CAPS_PCS;
		if (!(dcfg & GEM_BIT(USERIO)))
			bp->caps |= MACB_CAPS_USRIO_DISABLED;
		dcfg = gem_readl(bp, DCFG12);
		if (GEM_BFEXT(HIGH_SPEED, dcfg) == 1)
			bp->caps |= MACB_CAPS_HIGH_SPEED;
		dcfg = gem_readl(bp, DCFG2);
		if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0)
			bp->caps |= MACB_CAPS_FIFO_MODE;
		if (GEM_BFEXT(PBUF_RSC, gem_readl(bp, DCFG6)))
			bp->caps |= MACB_CAPS_RSC;
		if (gem_has_ptp(bp)) {
			if (!GEM_BFEXT(TSU, gem_readl(bp, DCFG5)))
				dev_err(&bp->pdev->dev,
					"GEM doesn't support hardware ptp.\n");
			else {
#ifdef CONFIG_MACB_USE_HWSTAMP
				bp->caps |= MACB_CAPS_DMA_PTP;
				bp->ptp_info = &gem_ptp_info;
#endif
			}
		}
	}

	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
}

static int macb_probe_queues(struct device *dev, void __iomem *mem, bool native_io)
{
	/* BIT(0) is never set but queue 0 always exists. */
	unsigned int queue_mask = 0x1;

	/* Use hw_is_gem() as MACB_CAPS_MACB_IS_GEM is not yet positioned. */
	if (hw_is_gem(mem, native_io)) {
		if (native_io)
			queue_mask |= __raw_readl(mem + GEM_DCFG6) & 0xFF;
		else
			queue_mask |= readl_relaxed(mem + GEM_DCFG6) & 0xFF;

		if (fls(queue_mask) != ffz(queue_mask)) {
			dev_err(dev, "queue mask %#x has a hole\n", queue_mask);
			return -EINVAL;
		}
	}

	return hweight32(queue_mask);
}

static void macb_clks_disable(struct clk *pclk, struct clk *hclk, struct clk *tx_clk,
			      struct clk *rx_clk, struct clk *tsu_clk)
{
	struct clk_bulk_data clks[] = {
		{ .clk = tsu_clk, },
		{ .clk = rx_clk, },
		{ .clk = pclk, },
		{ .clk = hclk, },
		{ .clk = tx_clk },
	};

	clk_bulk_disable_unprepare(ARRAY_SIZE(clks), clks);
}

static int macb_clk_init_dflt(struct platform_device *pdev, struct clk **pclk,
			      struct clk **hclk, struct clk **tx_clk,
			      struct clk **rx_clk, struct clk **tsu_clk)
{
	struct macb_platform_data *pdata;
	int err;

	pdata = dev_get_platdata(&pdev->dev);
	if (pdata) {
		*pclk = pdata->pclk;
		*hclk = pdata->hclk;
	} else {
		*pclk = devm_clk_get(&pdev->dev, "pclk");
		*hclk = devm_clk_get(&pdev->dev, "hclk");
	}

	if (IS_ERR_OR_NULL(*pclk))
		return dev_err_probe(&pdev->dev,
				     IS_ERR(*pclk) ? PTR_ERR(*pclk) : -ENODEV,
				     "failed to get pclk\n");

	if (IS_ERR_OR_NULL(*hclk))
		return dev_err_probe(&pdev->dev,
				     IS_ERR(*hclk) ? PTR_ERR(*hclk) : -ENODEV,
				     "failed to get hclk\n");

	*tx_clk = devm_clk_get_optional(&pdev->dev, "tx_clk");
	if (IS_ERR(*tx_clk))
		return PTR_ERR(*tx_clk);

	*rx_clk = devm_clk_get_optional(&pdev->dev, "rx_clk");
	if (IS_ERR(*rx_clk))
		return PTR_ERR(*rx_clk);

	*tsu_clk = devm_clk_get_optional(&pdev->dev, "tsu_clk");
	if (IS_ERR(*tsu_clk))
		return PTR_ERR(*tsu_clk);

	err = clk_prepare_enable(*pclk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable pclk (%d)\n", err);
		return err;
	}

	err = clk_prepare_enable(*hclk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable hclk (%d)\n", err);
		goto err_disable_pclk;
	}

	err = clk_prepare_enable(*tx_clk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable tx_clk (%d)\n", err);
		goto err_disable_hclk;
	}

	err = clk_prepare_enable(*rx_clk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable rx_clk (%d)\n", err);
		goto err_disable_txclk;
	}

	err = clk_prepare_enable(*tsu_clk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable tsu_clk (%d)\n", err);
		goto err_disable_rxclk;
	}

	return 0;

err_disable_rxclk:
	clk_disable_unprepare(*rx_clk);

err_disable_txclk:
	clk_disable_unprepare(*tx_clk);

err_disable_hclk:
	clk_disable_unprepare(*hclk);

err_disable_pclk:
	clk_disable_unprepare(*pclk);

	return err;
}

static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
			 struct clk **hclk, struct clk **tx_clk,
			 struct clk **rx_clk, struct clk **tsu_clk,
			 const struct macb_config *config)
{
	if (config->clk_init)
		return config->clk_init(pdev, pclk, hclk, tx_clk, rx_clk,
					tsu_clk);
	else
		return macb_clk_init_dflt(pdev, pclk, hclk, tx_clk, rx_clk,
					  tsu_clk);
}

static int macb_init_dflt(struct platform_device *pdev)
{
	struct net_device *netdev = platform_get_drvdata(pdev);
	unsigned int hw_q, q;
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	int err;
	u32 val, reg;

	bp->tx_ring_size = DEFAULT_TX_RING_SIZE;
	bp->rx_ring_size = DEFAULT_RX_RING_SIZE;

	/* set the queue register mapping once for all: queue0 has a special
	 * register mapping but we don't want to test the queue index then
	 * compute the corresponding register offset at run time.
	 */
	for (hw_q = 0, q = 0; hw_q < bp->num_queues; ++hw_q) {
		queue = &bp->queues[q];
		queue->bp = bp;
		spin_lock_init(&queue->tx_ptr_lock);
		netif_napi_add(netdev, &queue->napi_rx, macb_rx_poll);
		netif_napi_add_tx(netdev, &queue->napi_tx, macb_tx_poll);
		if (hw_q) {
			queue->ISR  = GEM_ISR(hw_q - 1);
			queue->IER  = GEM_IER(hw_q - 1);
			queue->IDR  = GEM_IDR(hw_q - 1);
			queue->IMR  = GEM_IMR(hw_q - 1);
			queue->TBQP = GEM_TBQP(hw_q - 1);
			queue->RBQP = GEM_RBQP(hw_q - 1);
			queue->RBQS = GEM_RBQS(hw_q - 1);
		} else {
			/* queue0 uses legacy registers */
			queue->ISR  = MACB_ISR;
			queue->IER  = MACB_IER;
			queue->IDR  = MACB_IDR;
			queue->IMR  = MACB_IMR;
			queue->TBQP = MACB_TBQP;
			queue->RBQP = MACB_RBQP;
		}

		queue->ENST_START_TIME = GEM_ENST_START_TIME(hw_q);
		queue->ENST_ON_TIME = GEM_ENST_ON_TIME(hw_q);
		queue->ENST_OFF_TIME = GEM_ENST_OFF_TIME(hw_q);

		/* get irq: here we use the linux queue index, not the hardware
		 * queue index. the queue irq definitions in the device tree
		 * must remove the optional gaps that could exist in the
		 * hardware queue mask.
		 */
		queue->irq = platform_get_irq(pdev, q);
		err = devm_request_irq(&pdev->dev, queue->irq, macb_interrupt,
				       IRQF_SHARED, netdev->name, queue);
		if (err) {
			dev_err(&pdev->dev,
				"Unable to request IRQ %d (error %d)\n",
				queue->irq, err);
			return err;
		}

		INIT_WORK(&queue->tx_error_task, macb_tx_error_task);
		q++;
	}

	netdev->netdev_ops = &macb_netdev_ops;

	/* setup appropriated routines according to adapter type */
	if (macb_is_gem(bp)) {
		bp->macbgem_ops.mog_alloc_rx_buffers = gem_alloc_rx_buffers;
		bp->macbgem_ops.mog_free_rx_buffers = gem_free_rx_buffers;
		bp->macbgem_ops.mog_init_rings = gem_init_rings;
		bp->macbgem_ops.mog_rx = gem_rx;
		netdev->ethtool_ops = &gem_ethtool_ops;
	} else {
		bp->macbgem_ops.mog_alloc_rx_buffers = macb_alloc_rx_buffers;
		bp->macbgem_ops.mog_free_rx_buffers = macb_free_rx_buffers;
		bp->macbgem_ops.mog_init_rings = macb_init_rings;
		bp->macbgem_ops.mog_rx = macb_rx;
		netdev->ethtool_ops = &macb_ethtool_ops;
	}

	netdev_sw_irq_coalesce_default_on(netdev);

	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

	/* Set features */
	netdev->hw_features = NETIF_F_SG;

	/* Check LSO capability; runtime detection can be overridden by a cap
	 * flag if the hardware is known to be buggy
	 */
	if (!(bp->caps & MACB_CAPS_NO_LSO) &&
	    GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6)))
		netdev->hw_features |= MACB_NETIF_LSO;

	/* Checksum offload is only available on gem with packet buffer */
	if (macb_is_gem(bp) && !(bp->caps & MACB_CAPS_FIFO_MODE))
		netdev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
	if (bp->caps & MACB_CAPS_SG_DISABLED)
		netdev->hw_features &= ~NETIF_F_SG;
	/* Enable HW_TC if hardware supports QBV */
	if (bp->caps & MACB_CAPS_QBV)
		netdev->hw_features |= NETIF_F_HW_TC;

	netdev->features = netdev->hw_features;

	/* Check RX Flow Filters support.
	 * Max Rx flows set by availability of screeners & compare regs:
	 * each 4-tuple define requires 1 T2 screener reg + 3 compare regs
	 */
	reg = gem_readl(bp, DCFG8);
	bp->max_tuples = umin((GEM_BFEXT(SCR2CMP, reg) / 3),
			      GEM_BFEXT(T2SCR, reg));
	INIT_LIST_HEAD(&bp->rx_fs_list.list);
	if (bp->max_tuples > 0) {
		/* also needs one ethtype match to check IPv4 */
		if (GEM_BFEXT(SCR2ETH, reg) > 0) {
			/* program this reg now */
			reg = 0;
			reg = GEM_BFINS(ETHTCMP, (uint16_t)ETH_P_IP, reg);
			gem_writel_n(bp, ETHT, SCRT2_ETHT, reg);
			/* Filtering is supported in hw but don't enable it in kernel now */
			netdev->hw_features |= NETIF_F_NTUPLE;
			/* init Rx flow definitions */
			bp->rx_fs_list.count = 0;
			spin_lock_init(&bp->rx_fs_lock);
		} else
			bp->max_tuples = 0;
	}

	if (!(bp->caps & MACB_CAPS_USRIO_DISABLED)) {
		val = 0;
		if (bp->caps & MACB_CAPS_USRIO_HAS_MII) {
			if (phy_interface_mode_is_rgmii(bp->phy_interface))
				val = bp->usrio->rgmii;
			else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII &&
				 (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
				val = bp->usrio->rmii;
			else if (!(bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
				val = bp->usrio->mii;
		}

		if (bp->caps & MACB_CAPS_USRIO_HAS_CLKEN)
			val |= bp->usrio->clken;

		if (bp->caps & MACB_CAPS_USRIO_HAS_REFCLK_SOURCE) {
			const char *prop;
			bool refclk_ext;
			int ret;

			/* Default to whatever was set in the match data for
			 * this device. There's two properties for refclk
			 * control, but the boolean one is deprecated so is
			 * a lower priority to check, no device should have
			 * both.
			 */
			refclk_ext = bp->usrio->refclk_default_external;

			ret = of_property_read_string(pdev->dev.of_node,
						      "cdns,refclk-source", &prop);
			if (!ret) {
				if (!strcmp(prop, "external"))
					refclk_ext = true;
				else
					refclk_ext = false;
			} else {
				ret = of_property_read_bool(pdev->dev.of_node,
							    "cdns,refclk-ext");
				if (ret)
					refclk_ext = true;
			}

			if (refclk_ext)
				val |= bp->usrio->refclk;
		}

		if (bp->caps & MACB_CAPS_USRIO_HAS_TSUCLK_SOURCE)
			val |= bp->usrio->tsu_source;

		macb_or_gem_writel(bp, USRIO, val);
	}

	/* Set MII management clock divider */
	val = macb_mdc_clk_div(bp);
	val |= macb_dbw(bp);
	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII)
		val |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
	macb_writel(bp, NCFGR, val);

	return 0;
}

static int macb_init(struct platform_device *pdev,
		     const struct macb_config *config)
{
	if (config->init)
		return config->init(pdev);
	else
		return macb_init_dflt(pdev);
}

static const struct macb_usrio_config at91_default_usrio = {
	.mii = MACB_BIT(MII),
	.rmii = MACB_BIT(RMII),
	.rgmii = GEM_BIT(RGMII),
	.clken = MACB_BIT(CLKEN),
};

/* 1518 rounded up */
#define AT91ETHER_MAX_RBUFF_SZ	0x600
/* max number of receive buffers */
#define AT91ETHER_MAX_RX_DESCR	9

static struct sifive_fu540_macb_mgmt *mgmt;

static int at91ether_alloc_coherent(struct macb *bp)
{
	struct macb_queue *queue = &bp->queues[0];

	queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev,
					    (AT91ETHER_MAX_RX_DESCR *
					     macb_dma_desc_get_size(bp)),
					    &queue->rx_ring_dma, GFP_KERNEL);
	if (!queue->rx_ring)
		return -ENOMEM;

	queue->rx_buffers = dma_alloc_coherent(&bp->pdev->dev,
					       AT91ETHER_MAX_RX_DESCR *
					       AT91ETHER_MAX_RBUFF_SZ,
					       &queue->rx_buffers_dma,
					       GFP_KERNEL);
	if (!queue->rx_buffers) {
		dma_free_coherent(&bp->pdev->dev,
				  AT91ETHER_MAX_RX_DESCR *
				  macb_dma_desc_get_size(bp),
				  queue->rx_ring, queue->rx_ring_dma);
		queue->rx_ring = NULL;
		return -ENOMEM;
	}

	return 0;
}

static void at91ether_free_coherent(struct macb *bp)
{
	struct macb_queue *queue = &bp->queues[0];

	if (queue->rx_ring) {
		dma_free_coherent(&bp->pdev->dev,
				  AT91ETHER_MAX_RX_DESCR *
				  macb_dma_desc_get_size(bp),
				  queue->rx_ring, queue->rx_ring_dma);
		queue->rx_ring = NULL;
	}

	if (queue->rx_buffers) {
		dma_free_coherent(&bp->pdev->dev,
				  AT91ETHER_MAX_RX_DESCR *
				  AT91ETHER_MAX_RBUFF_SZ,
				  queue->rx_buffers, queue->rx_buffers_dma);
		queue->rx_buffers = NULL;
	}
}

/* Initialize and start the Receiver and Transmit subsystems */
static int at91ether_start(struct macb *bp)
{
	struct macb_queue *queue = &bp->queues[0];
	struct macb_dma_desc *desc;
	dma_addr_t addr;
	u32 ctl;
	int i, ret;

	ret = at91ether_alloc_coherent(bp);
	if (ret)
		return ret;

	addr = queue->rx_buffers_dma;
	for (i = 0; i < AT91ETHER_MAX_RX_DESCR; i++) {
		desc = macb_rx_desc(queue, i);
		macb_set_addr(bp, desc, addr);
		desc->ctrl = 0;
		addr += AT91ETHER_MAX_RBUFF_SZ;
	}

	/* Set the Wrap bit on the last descriptor */
	desc->addr |= MACB_BIT(RX_WRAP);

	/* Reset buffer index */
	queue->rx_tail = 0;

	/* Program address of descriptor list in Rx Buffer Queue register */
	macb_writel(bp, RBQP, queue->rx_ring_dma);

	/* Enable Receive and Transmit */
	ctl = macb_readl(bp, NCR);
	macb_writel(bp, NCR, ctl | MACB_BIT(RE) | MACB_BIT(TE));

	/* Enable MAC interrupts */
	macb_writel(bp, IER, MACB_BIT(RCOMP)	|
			     MACB_BIT(RXUBR)	|
			     MACB_BIT(ISR_TUND)	|
			     MACB_BIT(ISR_RLE)	|
			     MACB_BIT(TCOMP)	|
			     MACB_BIT(ISR_ROVR)	|
			     MACB_BIT(HRESP));

	return 0;
}

static void at91ether_stop(struct macb *bp)
{
	u32 ctl;

	/* Disable MAC interrupts */
	macb_writel(bp, IDR, MACB_BIT(RCOMP)	|
			     MACB_BIT(RXUBR)	|
			     MACB_BIT(ISR_TUND)	|
			     MACB_BIT(ISR_RLE)	|
			     MACB_BIT(TCOMP)	|
			     MACB_BIT(ISR_ROVR) |
			     MACB_BIT(HRESP));

	/* Disable Receiver and Transmitter */
	ctl = macb_readl(bp, NCR);
	macb_writel(bp, NCR, ctl & ~(MACB_BIT(TE) | MACB_BIT(RE)));

	/* Free resources. */
	at91ether_free_coherent(bp);
}

/* Open the ethernet interface */
static int at91ether_open(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	u32 ctl;
	int ret;

	ret = pm_runtime_resume_and_get(&bp->pdev->dev);
	if (ret < 0)
		return ret;

	/* Clear internal statistics */
	ctl = macb_readl(bp, NCR);
	macb_writel(bp, NCR, ctl | MACB_BIT(CLRSTAT));

	macb_set_hwaddr(bp);

	ret = at91ether_start(bp);
	if (ret)
		goto pm_exit;

	ret = macb_phylink_connect(bp);
	if (ret)
		goto stop;

	netif_start_queue(netdev);

	return 0;

stop:
	at91ether_stop(bp);
pm_exit:
	pm_runtime_put_sync(&bp->pdev->dev);
	return ret;
}

/* Close the interface */
static int at91ether_close(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);

	netif_stop_queue(netdev);

	phylink_stop(bp->phylink);
	phylink_disconnect_phy(bp->phylink);

	at91ether_stop(bp);

	pm_runtime_put(&bp->pdev->dev);

	return 0;
}

/* Transmit packet */
static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb,
					struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	struct device *dev = &bp->pdev->dev;

	if (macb_readl(bp, TSR) & MACB_BIT(RM9200_BNQ)) {
		int desc = 0;

		netif_stop_queue(netdev);

		/* Store packet information (to free when Tx completed) */
		bp->rm9200_txq[desc].skb = skb;
		bp->rm9200_txq[desc].size = skb->len;
		bp->rm9200_txq[desc].mapping = dma_map_single(dev, skb->data,
							      skb->len,
							      DMA_TO_DEVICE);
		if (dma_mapping_error(dev, bp->rm9200_txq[desc].mapping)) {
			dev_kfree_skb_any(skb);
			netdev->stats.tx_dropped++;
			netdev_err(netdev, "%s: DMA mapping error\n", __func__);
			return NETDEV_TX_OK;
		}

		/* Set address of the data in the Transmit Address register */
		macb_writel(bp, TAR, bp->rm9200_txq[desc].mapping);
		/* Set length of the packet in the Transmit Control register */
		macb_writel(bp, TCR, skb->len);

	} else {
		netdev_err(netdev, "%s called, but device is busy!\n",
			   __func__);
		return NETDEV_TX_BUSY;
	}

	return NETDEV_TX_OK;
}

/* Extract received frame from buffer descriptors and sent to upper layers.
 * (Called from interrupt context)
 */
static void at91ether_rx(struct net_device *netdev)
{
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue = &bp->queues[0];
	struct macb_dma_desc *desc;
	unsigned char *p_recv;
	struct sk_buff *skb;
	unsigned int pktlen;

	desc = macb_rx_desc(queue, queue->rx_tail);
	while (desc->addr & MACB_BIT(RX_USED)) {
		p_recv = queue->rx_buffers +
			 queue->rx_tail * AT91ETHER_MAX_RBUFF_SZ;
		pktlen = MACB_BF(RX_FRMLEN, desc->ctrl);
		skb = netdev_alloc_skb(netdev, pktlen + 2);
		if (skb) {
			skb_reserve(skb, 2);
			skb_put_data(skb, p_recv, pktlen);

			skb->protocol = eth_type_trans(skb, netdev);
			netdev->stats.rx_packets++;
			netdev->stats.rx_bytes += pktlen;
			netif_rx(skb);
		} else {
			netdev->stats.rx_dropped++;
		}

		if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH))
			netdev->stats.multicast++;

		/* reset ownership bit */
		desc->addr &= ~MACB_BIT(RX_USED);

		/* wrap after last buffer */
		if (queue->rx_tail == AT91ETHER_MAX_RX_DESCR - 1)
			queue->rx_tail = 0;
		else
			queue->rx_tail++;

		desc = macb_rx_desc(queue, queue->rx_tail);
	}
}

/* MAC interrupt handler */
static irqreturn_t at91ether_interrupt(int irq, void *dev_id)
{
	struct net_device *netdev = dev_id;
	struct macb *bp = netdev_priv(netdev);
	u32 intstatus, ctl;
	unsigned int desc;

	/* MAC Interrupt Status register indicates what interrupts are pending.
	 * It is automatically cleared once read.
	 */
	intstatus = macb_readl(bp, ISR);

	/* Receive complete */
	if (intstatus & MACB_BIT(RCOMP))
		at91ether_rx(netdev);

	/* Transmit complete */
	if (intstatus & MACB_BIT(TCOMP)) {
		/* The TCOM bit is set even if the transmission failed */
		if (intstatus & (MACB_BIT(ISR_TUND) | MACB_BIT(ISR_RLE)))
			netdev->stats.tx_errors++;

		desc = 0;
		if (bp->rm9200_txq[desc].skb) {
			dev_consume_skb_irq(bp->rm9200_txq[desc].skb);
			bp->rm9200_txq[desc].skb = NULL;
			dma_unmap_single(&bp->pdev->dev,
					 bp->rm9200_txq[desc].mapping,
					 bp->rm9200_txq[desc].size,
					 DMA_TO_DEVICE);
			netdev->stats.tx_packets++;
			netdev->stats.tx_bytes += bp->rm9200_txq[desc].size;
		}
		netif_wake_queue(netdev);
	}

	/* Work-around for EMAC Errata section 41.3.1 */
	if (intstatus & MACB_BIT(RXUBR)) {
		ctl = macb_readl(bp, NCR);
		macb_writel(bp, NCR, ctl & ~MACB_BIT(RE));
		wmb();
		macb_writel(bp, NCR, ctl | MACB_BIT(RE));
	}

	if (intstatus & MACB_BIT(ISR_ROVR))
		netdev_err(netdev, "ROVR error\n");

	return IRQ_HANDLED;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void at91ether_poll_controller(struct net_device *netdev)
{
	unsigned long flags;

	local_irq_save(flags);
	at91ether_interrupt(netdev->irq, netdev);
	local_irq_restore(flags);
}
#endif

static const struct net_device_ops at91ether_netdev_ops = {
	.ndo_open		= at91ether_open,
	.ndo_stop		= at91ether_close,
	.ndo_start_xmit		= at91ether_start_xmit,
	.ndo_get_stats64	= macb_get_stats,
	.ndo_set_rx_mode	= macb_set_rx_mode,
	.ndo_set_mac_address	= eth_mac_addr,
	.ndo_eth_ioctl		= macb_ioctl,
	.ndo_validate_addr	= eth_validate_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= at91ether_poll_controller,
#endif
	.ndo_hwtstamp_set	= macb_hwtstamp_set,
	.ndo_hwtstamp_get	= macb_hwtstamp_get,
};

static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk,
			      struct clk **hclk, struct clk **tx_clk,
			      struct clk **rx_clk, struct clk **tsu_clk)
{
	int err;

	*hclk = NULL;
	*tx_clk = NULL;
	*rx_clk = NULL;
	*tsu_clk = NULL;

	*pclk = devm_clk_get(&pdev->dev, "ether_clk");
	if (IS_ERR(*pclk))
		return PTR_ERR(*pclk);

	err = clk_prepare_enable(*pclk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable pclk (%d)\n", err);
		return err;
	}

	return 0;
}

static int at91ether_init(struct platform_device *pdev)
{
	struct net_device *netdev = platform_get_drvdata(pdev);
	struct macb *bp = netdev_priv(netdev);
	int err;

	bp->queues[0].bp = bp;

	netdev->netdev_ops = &at91ether_netdev_ops;
	netdev->ethtool_ops = &macb_ethtool_ops;

	err = devm_request_irq(&pdev->dev, netdev->irq, at91ether_interrupt,
			       0, netdev->name, netdev);
	if (err)
		return err;

	macb_writel(bp, NCR, 0);

	macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG));

	return 0;
}

static unsigned long fu540_macb_tx_recalc_rate(struct clk_hw *hw,
					       unsigned long parent_rate)
{
	return mgmt->rate;
}

static int fu540_macb_tx_determine_rate(struct clk_hw *hw,
					struct clk_rate_request *req)
{
	if (WARN_ON(req->rate < 2500000))
		req->rate = 2500000;
	else if (req->rate == 2500000)
		req->rate = 2500000;
	else if (WARN_ON(req->rate < 13750000))
		req->rate = 2500000;
	else if (WARN_ON(req->rate < 25000000))
		req->rate = 25000000;
	else if (req->rate == 25000000)
		req->rate = 25000000;
	else if (WARN_ON(req->rate < 75000000))
		req->rate = 25000000;
	else if (WARN_ON(req->rate < 125000000))
		req->rate = 125000000;
	else if (req->rate == 125000000)
		req->rate = 125000000;
	else if (WARN_ON(req->rate > 125000000))
		req->rate = 125000000;
	else
		req->rate = 125000000;

	return 0;
}

static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate,
				  unsigned long parent_rate)
{
	struct clk_rate_request req;
	int ret;

	clk_hw_init_rate_request(hw, &req, rate);
	ret = fu540_macb_tx_determine_rate(hw, &req);
	if (ret != 0)
		return ret;

	if (req.rate != 125000000)
		iowrite32(1, mgmt->reg);
	else
		iowrite32(0, mgmt->reg);
	mgmt->rate = rate;

	return 0;
}

static const struct clk_ops fu540_c000_ops = {
	.recalc_rate = fu540_macb_tx_recalc_rate,
	.determine_rate = fu540_macb_tx_determine_rate,
	.set_rate = fu540_macb_tx_set_rate,
};

static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
			       struct clk **hclk, struct clk **tx_clk,
			       struct clk **rx_clk, struct clk **tsu_clk)
{
	struct clk_init_data init;
	int err = 0;

	err = macb_clk_init_dflt(pdev, pclk, hclk, tx_clk, rx_clk, tsu_clk);
	if (err)
		return err;

	mgmt = devm_kzalloc(&pdev->dev, sizeof(*mgmt), GFP_KERNEL);
	if (!mgmt) {
		err = -ENOMEM;
		goto err_disable_clks;
	}

	init.name = "sifive-gemgxl-mgmt";
	init.ops = &fu540_c000_ops;
	init.flags = 0;
	init.num_parents = 0;

	mgmt->rate = 0;
	mgmt->hw.init = &init;

	*tx_clk = devm_clk_register(&pdev->dev, &mgmt->hw);
	if (IS_ERR(*tx_clk)) {
		err = PTR_ERR(*tx_clk);
		goto err_disable_clks;
	}

	err = clk_prepare_enable(*tx_clk);
	if (err) {
		dev_err(&pdev->dev, "failed to enable tx_clk (%u)\n", err);
		*tx_clk = NULL;
		goto err_disable_clks;
	} else {
		dev_info(&pdev->dev, "Registered clk switch '%s'\n", init.name);
	}

	return 0;

err_disable_clks:
	macb_clks_disable(*pclk, *hclk, *tx_clk, *rx_clk, *tsu_clk);

	return err;
}

static int fu540_c000_init(struct platform_device *pdev)
{
	mgmt->reg = devm_platform_ioremap_resource(pdev, 1);
	if (IS_ERR(mgmt->reg))
		return PTR_ERR(mgmt->reg);

	return macb_init_dflt(pdev);
}

static int init_reset_optional(struct platform_device *pdev)
{
	struct net_device *netdev = platform_get_drvdata(pdev);
	struct macb *bp = netdev_priv(netdev);
	int ret;

	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) {
		/* Ensure PHY device used in SGMII mode is ready */
		bp->phy = devm_phy_optional_get(&pdev->dev, NULL);

		if (IS_ERR(bp->phy))
			return dev_err_probe(&pdev->dev, PTR_ERR(bp->phy),
					     "failed to get SGMII PHY\n");

		ret = phy_init(bp->phy);
		if (ret)
			return dev_err_probe(&pdev->dev, ret,
					     "failed to init SGMII PHY\n");

		ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG);
		if (!ret) {
			u32 pm_info[2];

			ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains",
							 pm_info, ARRAY_SIZE(pm_info));
			if (ret) {
				dev_err(&pdev->dev, "Failed to read power management information\n");
				goto err_out_phy_exit;
			}
			ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0);
			if (ret)
				goto err_out_phy_exit;

			ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1);
			if (ret)
				goto err_out_phy_exit;
		}

	}

	/* Fully reset controller at hardware level if mapped in device tree */
	ret = device_reset_optional(&pdev->dev);
	if (ret) {
		phy_exit(bp->phy);
		return dev_err_probe(&pdev->dev, ret, "failed to reset controller");
	}

	ret = macb_init_dflt(pdev);

err_out_phy_exit:
	if (ret)
		phy_exit(bp->phy);

	return ret;
}

static int eyeq5_init(struct platform_device *pdev)
{
	struct net_device *netdev = platform_get_drvdata(pdev);
	struct macb *bp = netdev_priv(netdev);
	struct device *dev = &pdev->dev;
	int ret;

	bp->phy = devm_phy_get(dev, NULL);
	if (IS_ERR(bp->phy))
		return dev_err_probe(dev, PTR_ERR(bp->phy),
				     "failed to get PHY\n");

	ret = phy_init(bp->phy);
	if (ret)
		return dev_err_probe(dev, ret, "failed to init PHY\n");

	ret = macb_init_dflt(pdev);
	if (ret)
		phy_exit(bp->phy);
	return ret;
}

static int macb_alloc_tieoff(struct macb *bp)
{
	/* Tieoff is a workaround in case HW cannot disable queues, for PM. */
	if (bp->caps & MACB_CAPS_QUEUE_DISABLE)
		return 0;

	bp->rx_ring_tieoff = dma_alloc_coherent(&bp->pdev->dev,
						macb_dma_desc_get_size(bp),
						&bp->rx_ring_tieoff_dma,
						GFP_KERNEL);
	if (!bp->rx_ring_tieoff)
		return -ENOMEM;

	macb_set_addr(bp, bp->rx_ring_tieoff,
		      MACB_BIT(RX_WRAP) | MACB_BIT(RX_USED));

	bp->rx_ring_tieoff->ctrl = 0;

	return 0;
}

static void macb_free_tieoff(struct macb *bp)
{
	if (!bp->rx_ring_tieoff)
		return;

	dma_free_coherent(&bp->pdev->dev, macb_dma_desc_get_size(bp),
			  bp->rx_ring_tieoff,
			  bp->rx_ring_tieoff_dma);
	bp->rx_ring_tieoff = NULL;
}

static const struct macb_usrio_config mpfs_usrio = {
	.tsu_source = 0,
};

static const struct macb_usrio_config sama7g5_gem_usrio = {
	.mii = 0,
	.rmii = 1,
	.rgmii = 2,
	.refclk = BIT(2),
	.refclk_default_external = false,
	.hdfctlen = BIT(6),
};

static const struct macb_usrio_config sama7g5_emac_usrio = {
	.mii = 0,
	.rmii = 1,
	.rgmii = 2,
	.refclk = BIT(2),
	.refclk_default_external = true,
	.hdfctlen = BIT(6),
};

static const struct macb_config fu540_c000_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.clk_init = fu540_c000_clk_init,
	.init = fu540_c000_init,
	.jumbo_max_len = 10240,
	.usrio = &at91_default_usrio,
};

static const struct macb_config at91sam9260_config = {
	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
		MACB_CAPS_USRIO_HAS_MII,
	.usrio = &at91_default_usrio,
};

static const struct macb_config sama5d3macb_config = {
	.caps = MACB_CAPS_SG_DISABLED |
		MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
		MACB_CAPS_USRIO_HAS_MII,
	.usrio = &at91_default_usrio,
};

static const struct macb_config pc302gem_config = {
	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &at91_default_usrio,
};

static const struct macb_config sama5d2_config = {
	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_JUMBO |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.jumbo_max_len = 10240,
	.usrio = &at91_default_usrio,
};

static const struct macb_config sama5d29_config = {
	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_GEM_HAS_PTP |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &at91_default_usrio,
};

static const struct macb_config sama5d3_config = {
	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE |
		MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_JUMBO |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.jumbo_max_len = 10240,
	.usrio = &at91_default_usrio,
};

static const struct macb_config sama5d4_config = {
	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 4,
	.usrio = &at91_default_usrio,
};

static const struct macb_config emac_config = {
	.caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC |
		MACB_CAPS_USRIO_HAS_MII,
	.clk_init = at91ether_clk_init,
	.init = at91ether_init,
	.usrio = &at91_default_usrio,
};

static const struct macb_config np4_config = {
	.caps = MACB_CAPS_USRIO_DISABLED,
};

static const struct macb_config zynqmp_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
		MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.init = init_reset_optional,
	.jumbo_max_len = 10240,
	.usrio = &at91_default_usrio,
};

static const struct macb_config zynq_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF |
		MACB_CAPS_NEEDS_RSTONUBR |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &at91_default_usrio,
};

static const struct macb_config mpfs_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
		MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP |
		MACB_CAPS_USRIO_HAS_TSUCLK_SOURCE,
	.dma_burst_length = 16,
	.init = init_reset_optional,
	.usrio = &mpfs_usrio,
	.max_tx_length = 4040, /* Cadence Erratum 1686 */
	.jumbo_max_len = 4040,
};

static const struct macb_config sama7g5_gem_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG |
		MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
		MACB_CAPS_USRIO_HAS_REFCLK_SOURCE |
		MACB_CAPS_MIIONRGMII | MACB_CAPS_GEM_HAS_PTP |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &sama7g5_gem_usrio,
};

static const struct macb_config sama7g5_emac_config = {
	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
		MACB_CAPS_MIIONRGMII |
		MACB_CAPS_USRIO_HAS_REFCLK_SOURCE |
		MACB_CAPS_GEM_HAS_PTP |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &sama7g5_emac_usrio,
};

static const struct macb_config versal_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH |
		MACB_CAPS_NEED_TSUCLK | MACB_CAPS_QUEUE_DISABLE |
		MACB_CAPS_QBV |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.init = init_reset_optional,
	.jumbo_max_len = 10240,
	.usrio = &at91_default_usrio,
};

static const struct macb_config eyeq5_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_QUEUE_DISABLE |
		MACB_CAPS_NO_LSO | MACB_CAPS_EEE,
	.dma_burst_length = 16,
	.init = eyeq5_init,
	.jumbo_max_len = 10240,
};

static const struct macb_config raspberrypi_rp1_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG |
		MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP |
		MACB_CAPS_EEE |
		MACB_CAPS_USRIO_HAS_MII,
	.dma_burst_length = 16,
	.usrio = &at91_default_usrio,
	.jumbo_max_len = 10240,
};

static const struct macb_config pic64hpsc_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_USRIO_DISABLED,
	.dma_burst_length = 16,
	.init = init_reset_optional,
	.jumbo_max_len = 16383,
};

static const struct of_device_id macb_dt_ids[] = {
	{ .compatible = "cdns,at91sam9260-macb", .data = &at91sam9260_config },
	{ .compatible = "cdns,macb" },
	{ .compatible = "cdns,np4-macb", .data = &np4_config },
	{ .compatible = "cdns,pc302-gem", .data = &pc302gem_config },
	{ .compatible = "cdns,gem", .data = &pc302gem_config },
	{ .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config },
	{ .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config },
	{ .compatible = "atmel,sama5d29-gem", .data = &sama5d29_config },
	{ .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config },
	{ .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config },
	{ .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config },
	{ .compatible = "cdns,at91rm9200-emac", .data = &emac_config },
	{ .compatible = "cdns,emac", .data = &emac_config },
	{ .compatible = "cdns,zynqmp-gem", .data = &zynqmp_config}, /* deprecated */
	{ .compatible = "cdns,zynq-gem", .data = &zynq_config }, /* deprecated */
	{ .compatible = "sifive,fu540-c000-gem", .data = &fu540_c000_config },
	{ .compatible = "microchip,mpfs-macb", .data = &mpfs_config },
	{ .compatible = "microchip,pic64hpsc-gem", .data = &pic64hpsc_config},
	{ .compatible = "microchip,sama7g5-gem", .data = &sama7g5_gem_config },
	{ .compatible = "microchip,sama7g5-emac", .data = &sama7g5_emac_config },
	{ .compatible = "mobileye,eyeq5-gem", .data = &eyeq5_config },
	{ .compatible = "raspberrypi,rp1-gem", .data = &raspberrypi_rp1_config },
	{ .compatible = "xlnx,zynqmp-gem", .data = &zynqmp_config},
	{ .compatible = "xlnx,zynq-gem", .data = &zynq_config },
	{ .compatible = "xlnx,versal-gem", .data = &versal_config},
	{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, macb_dt_ids);

static const struct macb_config default_gem_config = {
	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
		MACB_CAPS_JUMBO |
		MACB_CAPS_GEM_HAS_PTP,
	.dma_burst_length = 16,
	.usrio = &at91_default_usrio,
	.jumbo_max_len = 10240,
};

static int macb_probe(struct platform_device *pdev)
{
	struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
	struct device_node *np = pdev->dev.of_node;
	const struct macb_config *macb_config;
	struct clk *tsu_clk = NULL;
	phy_interface_t interface;
	struct net_device *netdev;
	struct resource *regs;
	u32 wtrmrk_rst_val;
	void __iomem *mem;
	struct macb *bp;
	int num_queues;
	bool native_io;
	int err, val;

	mem = devm_platform_get_and_ioremap_resource(pdev, 0, &regs);
	if (IS_ERR(mem))
		return PTR_ERR(mem);

	macb_config = of_device_get_match_data(&pdev->dev);
	if (!macb_config)
		macb_config = &default_gem_config;

	err = macb_clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk,
			    macb_config);
	if (err)
		return err;

	pm_runtime_set_autosuspend_delay(&pdev->dev, MACB_PM_TIMEOUT);
	pm_runtime_use_autosuspend(&pdev->dev);
	pm_runtime_get_noresume(&pdev->dev);
	pm_runtime_set_active(&pdev->dev);
	pm_runtime_enable(&pdev->dev);
	native_io = hw_is_native_io(mem);

	num_queues = macb_probe_queues(&pdev->dev, mem, native_io);
	if (num_queues < 0) {
		err = num_queues;
		goto err_disable_clocks;
	}

	netdev = alloc_etherdev_mq(sizeof(*bp), num_queues);
	if (!netdev) {
		err = -ENOMEM;
		goto err_disable_clocks;
	}

	netdev->base_addr = regs->start;

	SET_NETDEV_DEV(netdev, &pdev->dev);

	bp = netdev_priv(netdev);
	bp->pdev = pdev;
	bp->netdev = netdev;
	bp->regs = mem;
	bp->native_io = native_io;
	if (native_io) {
		bp->macb_reg_readl = hw_readl_native;
		bp->macb_reg_writel = hw_writel_native;
	} else {
		bp->macb_reg_readl = hw_readl;
		bp->macb_reg_writel = hw_writel;
	}
	bp->num_queues = num_queues;
	bp->dma_burst_length = macb_config->dma_burst_length;
	bp->pclk = pclk;
	bp->hclk = hclk;
	bp->tx_clk = tx_clk;
	bp->rx_clk = rx_clk;
	bp->tsu_clk = tsu_clk;
	bp->jumbo_max_len = macb_config->jumbo_max_len;

	if (!hw_is_gem(bp->regs, bp->native_io))
		bp->max_tx_length = MACB_MAX_TX_LEN;
	else if (macb_config->max_tx_length)
		bp->max_tx_length = macb_config->max_tx_length;
	else
		bp->max_tx_length = GEM_MAX_TX_LEN;

	bp->wol = 0;
	device_set_wakeup_capable(&pdev->dev, 1);

	bp->usrio = macb_config->usrio;

	if (of_property_read_bool(bp->pdev->dev.of_node, "cdns,timer-adjust") &&
			IS_ENABLED(CONFIG_MACB_USE_HWSTAMP)) {
		dev_err(&pdev->dev, "Timer adjust mode is not supported\n");
		err = -EINVAL;
		goto err_out_free_netdev;
	}

	/* By default we set to partial store and forward mode for zynqmp.
	 * Disable if not set in devicetree.
	 */
	if (GEM_BFEXT(PBUF_CUTTHRU, gem_readl(bp, DCFG6))) {
		err = of_property_read_u32(bp->pdev->dev.of_node,
					   "cdns,rx-watermark",
					   &bp->rx_watermark);

		if (!err) {
			/* Disable partial store and forward in case of error or
			 * invalid watermark value
			 */
			wtrmrk_rst_val = (1 << (GEM_BFEXT(RX_PBUF_ADDR, gem_readl(bp, DCFG2)))) - 1;
			if (bp->rx_watermark > wtrmrk_rst_val || !bp->rx_watermark) {
				dev_info(&bp->pdev->dev, "Invalid watermark value\n");
				bp->rx_watermark = 0;
			}
		}
	}
	spin_lock_init(&bp->lock);
	spin_lock_init(&bp->stats_lock);
	spin_lock_init(&bp->tsu_clk_lock);

	/* setup capabilities */
	macb_configure_caps(bp, macb_config);

#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
	if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
		if (err) {
			dev_err(&pdev->dev, "failed to set DMA mask\n");
			goto err_out_free_netdev;
		}
		bp->caps |= MACB_CAPS_DMA_64B;
	}
#endif
	platform_set_drvdata(pdev, netdev);

	netdev->irq = platform_get_irq(pdev, 0);
	if (netdev->irq < 0) {
		err = netdev->irq;
		goto err_out_free_netdev;
	}

	/* MTU range: 68 - 1518 or 10240 */
	netdev->min_mtu = GEM_MTU_MIN_SIZE;
	if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len)
		netdev->max_mtu = MIN(bp->jumbo_max_len, RX_BUFFER_MAX) -
				ETH_HLEN - ETH_FCS_LEN;
	else
		netdev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN;

	if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
		val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
		if (val)
			bp->rx_bd_rd_prefetch = (2 << (val - 1)) *
						macb_dma_desc_get_size(bp);

		val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10));
		if (val)
			bp->tx_bd_rd_prefetch = (2 << (val - 1)) *
						macb_dma_desc_get_size(bp);
	}

	bp->rx_intr_mask = MACB_RX_INT_FLAGS;
	if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR)
		bp->rx_intr_mask |= MACB_BIT(RXUBR);

	err = of_get_ethdev_address(np, bp->netdev);
	if (err == -EPROBE_DEFER)
		goto err_out_free_netdev;
	else if (err)
		macb_get_hwaddr(bp);

	err = of_get_phy_mode(np, &interface);
	if (err)
		/* not found in DT, MII by default */
		bp->phy_interface = PHY_INTERFACE_MODE_MII;
	else
		bp->phy_interface = interface;

	/* IP specific init */
	err = macb_init(pdev, macb_config);
	if (err)
		goto err_out_free_netdev;

	err = macb_mii_init(bp);
	if (err)
		goto err_out_phy_exit;

	netif_carrier_off(netdev);

	err = macb_alloc_tieoff(bp);
	if (err)
		goto err_out_unregister_mdio;

	err = register_netdev(netdev);
	if (err) {
		dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
		goto err_out_free_tieoff;
	}

	INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task);
	INIT_DELAYED_WORK(&bp->tx_lpi_work, macb_tx_lpi_work_fn);

	netdev_info(netdev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n",
		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
		    netdev->base_addr, netdev->irq, netdev->dev_addr);

	pm_runtime_put_autosuspend(&bp->pdev->dev);

	return 0;

err_out_free_tieoff:
	macb_free_tieoff(bp);

err_out_unregister_mdio:
	if (bp->mii_bus) {
		mdiobus_unregister(bp->mii_bus);
		mdiobus_free(bp->mii_bus);
	}
	phylink_destroy(bp->phylink);

err_out_phy_exit:
	phy_exit(bp->phy);

err_out_free_netdev:
	free_netdev(netdev);

err_disable_clocks:
	macb_clks_disable(pclk, hclk, tx_clk, rx_clk, tsu_clk);
	pm_runtime_disable(&pdev->dev);
	pm_runtime_set_suspended(&pdev->dev);
	pm_runtime_dont_use_autosuspend(&pdev->dev);

	return err;
}

static void macb_remove(struct platform_device *pdev)
{
	struct net_device *netdev;
	struct macb *bp;

	netdev = platform_get_drvdata(pdev);

	if (netdev) {
		bp = netdev_priv(netdev);
		unregister_netdev(netdev);
		macb_free_tieoff(bp);
		phy_exit(bp->phy);
		if (bp->mii_bus) {
			mdiobus_unregister(bp->mii_bus);
			mdiobus_free(bp->mii_bus);
		}

		device_set_wakeup_enable(&bp->pdev->dev, 0);
		cancel_delayed_work_sync(&bp->tx_lpi_work);
		cancel_work_sync(&bp->hresp_err_bh_work);
		pm_runtime_disable(&pdev->dev);
		pm_runtime_dont_use_autosuspend(&pdev->dev);
		pm_runtime_set_suspended(&pdev->dev);
		phylink_destroy(bp->phylink);
		free_netdev(netdev);
	}
}

static int __maybe_unused macb_suspend(struct device *dev)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct macb *bp = netdev_priv(netdev);
	struct in_ifaddr *ifa = NULL;
	struct macb_queue *queue;
	struct in_device *idev;
	unsigned long flags;
	u32 tmp, ifa_local;
	unsigned int q;

	if (!device_may_wakeup(&bp->netdev->dev))
		phy_exit(bp->phy);

	if (!netif_running(netdev))
		return 0;

	if (bp->wol & MACB_WOL_ENABLED) {
		if (bp->wolopts & WAKE_ARP) {
			/* Check for IP address in WOL ARP mode */
			rcu_read_lock();
			idev = __in_dev_get_rcu(bp->netdev);
			if (idev)
				ifa = rcu_dereference(idev->ifa_list);
			if (!ifa) {
				rcu_read_unlock();
				netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n");
				return -EOPNOTSUPP;
			}
			ifa_local = be32_to_cpu(ifa->ifa_local);
			rcu_read_unlock();
		}

		spin_lock_irqsave(&bp->lock, flags);

		/* Disable Tx and Rx engines before  disabling the queues,
		 * this is mandatory as per the IP spec sheet
		 */
		tmp = macb_readl(bp, NCR);
		macb_writel(bp, NCR, tmp & ~(MACB_BIT(TE) | MACB_BIT(RE)));
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
		if (!(bp->caps & MACB_CAPS_QUEUE_DISABLE))
			macb_writel(bp, RBQPH,
				    upper_32_bits(bp->rx_ring_tieoff_dma));
#endif
		for (q = 0, queue = bp->queues; q < bp->num_queues;
		     ++q, ++queue) {
			/* Disable RX queues */
			if (bp->caps & MACB_CAPS_QUEUE_DISABLE) {
				queue_writel(queue, RBQP, MACB_BIT(QUEUE_DISABLE));
			} else {
				/* Tie off RX queues */
				queue_writel(queue, RBQP,
					     lower_32_bits(bp->rx_ring_tieoff_dma));
			}
			/* Disable all interrupts */
			queue_writel(queue, IDR, -1);
			queue_readl(queue, ISR);
			macb_queue_isr_clear(bp, queue, -1);
		}
		/* Enable Receive engine */
		macb_writel(bp, NCR, tmp | MACB_BIT(RE));
		/* Flush all status bits */
		macb_writel(bp, TSR, -1);
		macb_writel(bp, RSR, -1);

		tmp = (bp->wolopts & WAKE_MAGIC) ? MACB_BIT(MAG) : 0;
		if (bp->wolopts & WAKE_ARP) {
			tmp |= MACB_BIT(ARP);
			/* write IP address into register */
			tmp |= MACB_BFEXT(IP, ifa_local);
		}

		if (macb_is_gem(bp)) {
			queue_writel(bp->queues, IER, GEM_BIT(WOL));
			gem_writel(bp, WOL, tmp);
		} else {
			queue_writel(bp->queues, IER, MACB_BIT(WOL));
			macb_writel(bp, WOL, tmp);
		}
		spin_unlock_irqrestore(&bp->lock, flags);

		enable_irq_wake(bp->queues[0].irq);
	}

	netif_device_detach(netdev);
	for (q = 0, queue = bp->queues; q < bp->num_queues;
	     ++q, ++queue) {
		napi_disable(&queue->napi_rx);
		napi_disable(&queue->napi_tx);
	}

	if (!(bp->wol & MACB_WOL_ENABLED)) {
		rtnl_lock();
		phylink_stop(bp->phylink);
		rtnl_unlock();
		spin_lock_irqsave(&bp->lock, flags);
		macb_reset_hw(bp);
		spin_unlock_irqrestore(&bp->lock, flags);
	}

	if (!(bp->caps & MACB_CAPS_USRIO_DISABLED))
		bp->pm_data.usrio = macb_or_gem_readl(bp, USRIO);

	if (netdev->hw_features & NETIF_F_NTUPLE)
		bp->pm_data.scrt2 = gem_readl_n(bp, ETHT, SCRT2_ETHT);

	if (bp->ptp_info)
		bp->ptp_info->ptp_remove(netdev);
	if (!device_may_wakeup(dev))
		pm_runtime_force_suspend(dev);

	return 0;
}

static int __maybe_unused macb_resume(struct device *dev)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct macb *bp = netdev_priv(netdev);
	struct macb_queue *queue;
	unsigned long flags;
	unsigned int q;

	if (!device_may_wakeup(&bp->netdev->dev))
		phy_init(bp->phy);

	if (!netif_running(netdev))
		return 0;

	if (!device_may_wakeup(dev))
		pm_runtime_force_resume(dev);

	if (bp->wol & MACB_WOL_ENABLED) {
		spin_lock_irqsave(&bp->lock, flags);
		/* Disable WoL */
		if (macb_is_gem(bp)) {
			queue_writel(bp->queues, IDR, GEM_BIT(WOL));
			gem_writel(bp, WOL, 0);
		} else {
			queue_writel(bp->queues, IDR, MACB_BIT(WOL));
			macb_writel(bp, WOL, 0);
		}
		/* Clear ISR on queue 0 */
		queue_readl(bp->queues, ISR);
		macb_queue_isr_clear(bp, bp->queues, -1);
		spin_unlock_irqrestore(&bp->lock, flags);

		disable_irq_wake(bp->queues[0].irq);

		/* Now make sure we disable phy before moving
		 * to common restore path
		 */
		rtnl_lock();
		phylink_stop(bp->phylink);
		rtnl_unlock();
	}

	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
		macb_init_buffers(bp);

	for (q = 0, queue = bp->queues; q < bp->num_queues;
	     ++q, ++queue) {
		if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
			if (macb_is_gem(bp))
				gem_init_rx_ring(queue);
			else
				macb_init_rx_ring(queue);
		}

		napi_enable(&queue->napi_rx);
		napi_enable(&queue->napi_tx);
	}

	if (netdev->hw_features & NETIF_F_NTUPLE)
		gem_writel_n(bp, ETHT, SCRT2_ETHT, bp->pm_data.scrt2);

	if (!(bp->caps & MACB_CAPS_USRIO_DISABLED))
		macb_or_gem_writel(bp, USRIO, bp->pm_data.usrio);

	macb_writel(bp, NCR, MACB_BIT(MPE));
	macb_init_hw(bp);
	macb_set_rx_mode(netdev);
	macb_restore_features(bp);
	rtnl_lock();

	phylink_start(bp->phylink);
	rtnl_unlock();

	netif_device_attach(netdev);
	if (bp->ptp_info)
		bp->ptp_info->ptp_init(netdev);

	return 0;
}

static int __maybe_unused macb_runtime_suspend(struct device *dev)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct macb *bp = netdev_priv(netdev);

	if (!(device_may_wakeup(dev)))
		macb_clks_disable(bp->pclk, bp->hclk, bp->tx_clk, bp->rx_clk, bp->tsu_clk);
	else if (!(bp->caps & MACB_CAPS_NEED_TSUCLK))
		macb_clks_disable(NULL, NULL, NULL, NULL, bp->tsu_clk);

	return 0;
}

static int __maybe_unused macb_runtime_resume(struct device *dev)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct macb *bp = netdev_priv(netdev);

	if (!(device_may_wakeup(dev))) {
		clk_prepare_enable(bp->pclk);
		clk_prepare_enable(bp->hclk);
		clk_prepare_enable(bp->tx_clk);
		clk_prepare_enable(bp->rx_clk);
		clk_prepare_enable(bp->tsu_clk);
	} else if (!(bp->caps & MACB_CAPS_NEED_TSUCLK)) {
		clk_prepare_enable(bp->tsu_clk);
	}

	return 0;
}

static void macb_shutdown(struct platform_device *pdev)
{
	struct net_device *netdev = platform_get_drvdata(pdev);

	rtnl_lock();

	if (netif_running(netdev))
		dev_close(netdev);

	netif_device_detach(netdev);

	rtnl_unlock();
}

static const struct dev_pm_ops macb_pm_ops = {
	SET_SYSTEM_SLEEP_PM_OPS(macb_suspend, macb_resume)
	SET_RUNTIME_PM_OPS(macb_runtime_suspend, macb_runtime_resume, NULL)
};

static struct platform_driver macb_driver = {
	.probe		= macb_probe,
	.remove		= macb_remove,
	.driver		= {
		.name		= "macb",
		.of_match_table	= macb_dt_ids,
		.pm	= &macb_pm_ops,
	},
	.shutdown	= macb_shutdown,
};

module_platform_driver(macb_driver);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Cadence MACB/GEM Ethernet driver");
MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
MODULE_ALIAS("platform:macb");