/*
 * Broadcom GENET (Gigabit Ethernet) controller driver
 *
 * Copyright (c) 2014-2017 Broadcom
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt)                             "bcmgenet: " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/string.h>
#include <linux/if_ether.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/delay.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
#include <linux/pm.h>
#include <linux/clk.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_net.h>
#include <linux/of_platform.h>
#include <net/arp.h>

#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/phy.h>
#include <linux/platform_data/bcmgenet.h>

#include <asm/unaligned.h>

#include "bcmgenet.h"

/* Maximum number of hardware queues, downsized if needed */
#define GENET_MAX_MQ_CNT        4

/* Default highest priority queue for multi queue support */
#define GENET_Q0_PRIORITY       0

#define GENET_Q16_RX_BD_CNT     \
        (TOTAL_DESC - priv->hw_params->rx_queues * priv->hw_params->rx_bds_per_q)
#define GENET_Q16_TX_BD_CNT     \
        (TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q)

#define RX_BUF_LENGTH           2048
#define SKB_ALIGNMENT           32

/* Tx/Rx DMA register offset, skip 256 descriptors */
#define WORDS_PER_BD(p)         (p->hw_params->words_per_bd)
#define DMA_DESC_SIZE           (WORDS_PER_BD(priv) * sizeof(u32))

#define GENET_TDMA_REG_OFF      (priv->hw_params->tdma_offset + \
                                TOTAL_DESC * DMA_DESC_SIZE)

#define GENET_RDMA_REG_OFF      (priv->hw_params->rdma_offset + \
                                TOTAL_DESC * DMA_DESC_SIZE)

static inline void bcmgenet_writel(u32 value, void __iomem *offset)
{
        /* MIPS chips strapped for BE will automagically configure the
         * peripheral registers for CPU-native byte order.
         */
        if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
                __raw_writel(value, offset);
        else
                writel_relaxed(value, offset);
}

static inline u32 bcmgenet_readl(void __iomem *offset)
{
        if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
                return __raw_readl(offset);
        else
                return readl_relaxed(offset);
}

static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv,
                                             void __iomem *d, u32 value)
{
        bcmgenet_writel(value, d + DMA_DESC_LENGTH_STATUS);
}

static inline u32 dmadesc_get_length_status(struct bcmgenet_priv *priv,
                                            void __iomem *d)
{
        return bcmgenet_readl(d + DMA_DESC_LENGTH_STATUS);
}

static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
                                    void __iomem *d,
                                    dma_addr_t addr)
{
        bcmgenet_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO);

        /* Register writes to GISB bus can take couple hundred nanoseconds
         * and are done for each packet, save these expensive writes unless
         * the platform is explicitly configured for 64-bits/LPAE.
         */
#ifdef CONFIG_PHYS_ADDR_T_64BIT
        if (priv->hw_params->flags & GENET_HAS_40BITS)
                bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
#endif
}

/* Combined address + length/status setter */
static inline void dmadesc_set(struct bcmgenet_priv *priv,
                               void __iomem *d, dma_addr_t addr, u32 val)
{
        dmadesc_set_addr(priv, d, addr);
        dmadesc_set_length_status(priv, d, val);
}

static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv,
                                          void __iomem *d)
{
        dma_addr_t addr;

        addr = bcmgenet_readl(d + DMA_DESC_ADDRESS_LO);

        /* Register writes to GISB bus can take couple hundred nanoseconds
         * and are done for each packet, save these expensive writes unless
         * the platform is explicitly configured for 64-bits/LPAE.
         */
#ifdef CONFIG_PHYS_ADDR_T_64BIT
        if (priv->hw_params->flags & GENET_HAS_40BITS)
                addr |= (u64)bcmgenet_readl(d + DMA_DESC_ADDRESS_HI) << 32;
#endif
        return addr;
}

#define GENET_VER_FMT   "%1d.%1d EPHY: 0x%04x"

#define GENET_MSG_DEFAULT       (NETIF_MSG_DRV | NETIF_MSG_PROBE | \
                                NETIF_MSG_LINK)

static inline u32 bcmgenet_rbuf_ctrl_get(struct bcmgenet_priv *priv)
{
        if (GENET_IS_V1(priv))
                return bcmgenet_rbuf_readl(priv, RBUF_FLUSH_CTRL_V1);
        else
                return bcmgenet_sys_readl(priv, SYS_RBUF_FLUSH_CTRL);
}

static inline void bcmgenet_rbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
{
        if (GENET_IS_V1(priv))
                bcmgenet_rbuf_writel(priv, val, RBUF_FLUSH_CTRL_V1);
        else
                bcmgenet_sys_writel(priv, val, SYS_RBUF_FLUSH_CTRL);
}

/* These macros are defined to deal with register map change
 * between GENET1.1 and GENET2. Only those currently being used
 * by driver are defined.
 */
static inline u32 bcmgenet_tbuf_ctrl_get(struct bcmgenet_priv *priv)
{
        if (GENET_IS_V1(priv))
                return bcmgenet_rbuf_readl(priv, TBUF_CTRL_V1);
        else
                return bcmgenet_readl(priv->base +
                                      priv->hw_params->tbuf_offset + TBUF_CTRL);
}

static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
{
        if (GENET_IS_V1(priv))
                bcmgenet_rbuf_writel(priv, val, TBUF_CTRL_V1);
        else
                bcmgenet_writel(val, priv->base +
                                priv->hw_params->tbuf_offset + TBUF_CTRL);
}

static inline u32 bcmgenet_bp_mc_get(struct bcmgenet_priv *priv)
{
        if (GENET_IS_V1(priv))
                return bcmgenet_rbuf_readl(priv, TBUF_BP_MC_V1);
        else
                return bcmgenet_readl(priv->base +
                                      priv->hw_params->tbuf_offset + TBUF_BP_MC);
}

static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val)
{
        if (GENET_IS_V1(priv))
                bcmgenet_rbuf_writel(priv, val, TBUF_BP_MC_V1);
        else
                bcmgenet_writel(val, priv->base +
                                priv->hw_params->tbuf_offset + TBUF_BP_MC);
}

/* RX/TX DMA register accessors */
enum dma_reg {
        DMA_RING_CFG = 0,
        DMA_CTRL,
        DMA_STATUS,
        DMA_SCB_BURST_SIZE,
        DMA_ARB_CTRL,
        DMA_PRIORITY_0,
        DMA_PRIORITY_1,
        DMA_PRIORITY_2,
        DMA_INDEX2RING_0,
        DMA_INDEX2RING_1,
        DMA_INDEX2RING_2,
        DMA_INDEX2RING_3,
        DMA_INDEX2RING_4,
        DMA_INDEX2RING_5,
        DMA_INDEX2RING_6,
        DMA_INDEX2RING_7,
        DMA_RING0_TIMEOUT,
        DMA_RING1_TIMEOUT,
        DMA_RING2_TIMEOUT,
        DMA_RING3_TIMEOUT,
        DMA_RING4_TIMEOUT,
        DMA_RING5_TIMEOUT,
        DMA_RING6_TIMEOUT,
        DMA_RING7_TIMEOUT,
        DMA_RING8_TIMEOUT,
        DMA_RING9_TIMEOUT,
        DMA_RING10_TIMEOUT,
        DMA_RING11_TIMEOUT,
        DMA_RING12_TIMEOUT,
        DMA_RING13_TIMEOUT,
        DMA_RING14_TIMEOUT,
        DMA_RING15_TIMEOUT,
        DMA_RING16_TIMEOUT,
};

static const u8 bcmgenet_dma_regs_v3plus[] = {
        [DMA_RING_CFG]          = 0x00,
        [DMA_CTRL]              = 0x04,
        [DMA_STATUS]            = 0x08,
        [DMA_SCB_BURST_SIZE]    = 0x0C,
        [DMA_ARB_CTRL]          = 0x2C,
        [DMA_PRIORITY_0]        = 0x30,
        [DMA_PRIORITY_1]        = 0x34,
        [DMA_PRIORITY_2]        = 0x38,
        [DMA_RING0_TIMEOUT]     = 0x2C,
        [DMA_RING1_TIMEOUT]     = 0x30,
        [DMA_RING2_TIMEOUT]     = 0x34,
        [DMA_RING3_TIMEOUT]     = 0x38,
        [DMA_RING4_TIMEOUT]     = 0x3c,
        [DMA_RING5_TIMEOUT]     = 0x40,
        [DMA_RING6_TIMEOUT]     = 0x44,
        [DMA_RING7_TIMEOUT]     = 0x48,
        [DMA_RING8_TIMEOUT]     = 0x4c,
        [DMA_RING9_TIMEOUT]     = 0x50,
        [DMA_RING10_TIMEOUT]    = 0x54,
        [DMA_RING11_TIMEOUT]    = 0x58,
        [DMA_RING12_TIMEOUT]    = 0x5c,
        [DMA_RING13_TIMEOUT]    = 0x60,
        [DMA_RING14_TIMEOUT]    = 0x64,
        [DMA_RING15_TIMEOUT]    = 0x68,
        [DMA_RING16_TIMEOUT]    = 0x6C,
        [DMA_INDEX2RING_0]      = 0x70,
        [DMA_INDEX2RING_1]      = 0x74,
        [DMA_INDEX2RING_2]      = 0x78,
        [DMA_INDEX2RING_3]      = 0x7C,
        [DMA_INDEX2RING_4]      = 0x80,
        [DMA_INDEX2RING_5]      = 0x84,
        [DMA_INDEX2RING_6]      = 0x88,
        [DMA_INDEX2RING_7]      = 0x8C,
};

static const u8 bcmgenet_dma_regs_v2[] = {
        [DMA_RING_CFG]          = 0x00,
        [DMA_CTRL]              = 0x04,
        [DMA_STATUS]            = 0x08,
        [DMA_SCB_BURST_SIZE]    = 0x0C,
        [DMA_ARB_CTRL]          = 0x30,
        [DMA_PRIORITY_0]        = 0x34,
        [DMA_PRIORITY_1]        = 0x38,
        [DMA_PRIORITY_2]        = 0x3C,
        [DMA_RING0_TIMEOUT]     = 0x2C,
        [DMA_RING1_TIMEOUT]     = 0x30,
        [DMA_RING2_TIMEOUT]     = 0x34,
        [DMA_RING3_TIMEOUT]     = 0x38,
        [DMA_RING4_TIMEOUT]     = 0x3c,
        [DMA_RING5_TIMEOUT]     = 0x40,
        [DMA_RING6_TIMEOUT]     = 0x44,
        [DMA_RING7_TIMEOUT]     = 0x48,
        [DMA_RING8_TIMEOUT]     = 0x4c,
        [DMA_RING9_TIMEOUT]     = 0x50,
        [DMA_RING10_TIMEOUT]    = 0x54,
        [DMA_RING11_TIMEOUT]    = 0x58,
        [DMA_RING12_TIMEOUT]    = 0x5c,
        [DMA_RING13_TIMEOUT]    = 0x60,
        [DMA_RING14_TIMEOUT]    = 0x64,
        [DMA_RING15_TIMEOUT]    = 0x68,
        [DMA_RING16_TIMEOUT]    = 0x6C,
};

static const u8 bcmgenet_dma_regs_v1[] = {
        [DMA_CTRL]              = 0x00,
        [DMA_STATUS]            = 0x04,
        [DMA_SCB_BURST_SIZE]    = 0x0C,
        [DMA_ARB_CTRL]          = 0x30,
        [DMA_PRIORITY_0]        = 0x34,
        [DMA_PRIORITY_1]        = 0x38,
        [DMA_PRIORITY_2]        = 0x3C,
        [DMA_RING0_TIMEOUT]     = 0x2C,
        [DMA_RING1_TIMEOUT]     = 0x30,
        [DMA_RING2_TIMEOUT]     = 0x34,
        [DMA_RING3_TIMEOUT]     = 0x38,
        [DMA_RING4_TIMEOUT]     = 0x3c,
        [DMA_RING5_TIMEOUT]     = 0x40,
        [DMA_RING6_TIMEOUT]     = 0x44,
        [DMA_RING7_TIMEOUT]     = 0x48,
        [DMA_RING8_TIMEOUT]     = 0x4c,
        [DMA_RING9_TIMEOUT]     = 0x50,
        [DMA_RING10_TIMEOUT]    = 0x54,
        [DMA_RING11_TIMEOUT]    = 0x58,
        [DMA_RING12_TIMEOUT]    = 0x5c,
        [DMA_RING13_TIMEOUT]    = 0x60,
        [DMA_RING14_TIMEOUT]    = 0x64,
        [DMA_RING15_TIMEOUT]    = 0x68,
        [DMA_RING16_TIMEOUT]    = 0x6C,
};

/* Set at runtime once bcmgenet version is known */
static const u8 *bcmgenet_dma_regs;

static inline struct bcmgenet_priv *dev_to_priv(struct device *dev)
{
        return netdev_priv(dev_get_drvdata(dev));
}

static inline u32 bcmgenet_tdma_readl(struct bcmgenet_priv *priv,
                                      enum dma_reg r)
{
        return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF +
                              DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
}

static inline void bcmgenet_tdma_writel(struct bcmgenet_priv *priv,
                                        u32 val, enum dma_reg r)
{
        bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF +
                        DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
}

static inline u32 bcmgenet_rdma_readl(struct bcmgenet_priv *priv,
                                      enum dma_reg r)
{
        return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF +
                              DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
}

static inline void bcmgenet_rdma_writel(struct bcmgenet_priv *priv,
                                        u32 val, enum dma_reg r)
{
        bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF +
                        DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
}

/* RDMA/TDMA ring registers and accessors
 * we merge the common fields and just prefix with T/D the registers
 * having different meaning depending on the direction
 */
enum dma_ring_reg {
        TDMA_READ_PTR = 0,
        RDMA_WRITE_PTR = TDMA_READ_PTR,
        TDMA_READ_PTR_HI,
        RDMA_WRITE_PTR_HI = TDMA_READ_PTR_HI,
        TDMA_CONS_INDEX,
        RDMA_PROD_INDEX = TDMA_CONS_INDEX,
        TDMA_PROD_INDEX,
        RDMA_CONS_INDEX = TDMA_PROD_INDEX,
        DMA_RING_BUF_SIZE,
        DMA_START_ADDR,
        DMA_START_ADDR_HI,
        DMA_END_ADDR,
        DMA_END_ADDR_HI,
        DMA_MBUF_DONE_THRESH,
        TDMA_FLOW_PERIOD,
        RDMA_XON_XOFF_THRESH = TDMA_FLOW_PERIOD,
        TDMA_WRITE_PTR,
        RDMA_READ_PTR = TDMA_WRITE_PTR,
        TDMA_WRITE_PTR_HI,
        RDMA_READ_PTR_HI = TDMA_WRITE_PTR_HI
};

/* GENET v4 supports 40-bits pointer addressing
 * for obvious reasons the LO and HI word parts
 * are contiguous, but this offsets the other
 * registers.
 */
static const u8 genet_dma_ring_regs_v4[] = {
        [TDMA_READ_PTR]                 = 0x00,
        [TDMA_READ_PTR_HI]              = 0x04,
        [TDMA_CONS_INDEX]               = 0x08,
        [TDMA_PROD_INDEX]               = 0x0C,
        [DMA_RING_BUF_SIZE]             = 0x10,
        [DMA_START_ADDR]                = 0x14,
        [DMA_START_ADDR_HI]             = 0x18,
        [DMA_END_ADDR]                  = 0x1C,
        [DMA_END_ADDR_HI]               = 0x20,
        [DMA_MBUF_DONE_THRESH]          = 0x24,
        [TDMA_FLOW_PERIOD]              = 0x28,
        [TDMA_WRITE_PTR]                = 0x2C,
        [TDMA_WRITE_PTR_HI]             = 0x30,
};

static const u8 genet_dma_ring_regs_v123[] = {
        [TDMA_READ_PTR]                 = 0x00,
        [TDMA_CONS_INDEX]               = 0x04,
        [TDMA_PROD_INDEX]               = 0x08,
        [DMA_RING_BUF_SIZE]             = 0x0C,
        [DMA_START_ADDR]                = 0x10,
        [DMA_END_ADDR]                  = 0x14,
        [DMA_MBUF_DONE_THRESH]          = 0x18,
        [TDMA_FLOW_PERIOD]              = 0x1C,
        [TDMA_WRITE_PTR]                = 0x20,
};

/* Set at runtime once GENET version is known */
static const u8 *genet_dma_ring_regs;

static inline u32 bcmgenet_tdma_ring_readl(struct bcmgenet_priv *priv,
                                           unsigned int ring,
                                           enum dma_ring_reg r)
{
        return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF +
                              (DMA_RING_SIZE * ring) +
                              genet_dma_ring_regs[r]);
}

static inline void bcmgenet_tdma_ring_writel(struct bcmgenet_priv *priv,
                                             unsigned int ring, u32 val,
                                             enum dma_ring_reg r)
{
        bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF +
                        (DMA_RING_SIZE * ring) +
                        genet_dma_ring_regs[r]);
}

static inline u32 bcmgenet_rdma_ring_readl(struct bcmgenet_priv *priv,
                                           unsigned int ring,
                                           enum dma_ring_reg r)
{
        return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF +
                              (DMA_RING_SIZE * ring) +
                              genet_dma_ring_regs[r]);
}

static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
                                             unsigned int ring, u32 val,
                                             enum dma_ring_reg r)
{
        bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF +
                        (DMA_RING_SIZE * ring) +
                        genet_dma_ring_regs[r]);
}

static int bcmgenet_begin(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        /* Turn on the clock */
        return clk_prepare_enable(priv->clk);
}

static void bcmgenet_complete(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        /* Turn off the clock */
        clk_disable_unprepare(priv->clk);
}

static int bcmgenet_get_link_ksettings(struct net_device *dev,
                                       struct ethtool_link_ksettings *cmd)
{
        if (!netif_running(dev))
                return -EINVAL;

        if (!dev->phydev)
                return -ENODEV;

        phy_ethtool_ksettings_get(dev->phydev, cmd);

        return 0;
}

static int bcmgenet_set_link_ksettings(struct net_device *dev,
                                       const struct ethtool_link_ksettings *cmd)
{
        if (!netif_running(dev))
                return -EINVAL;

        if (!dev->phydev)
                return -ENODEV;

        return phy_ethtool_ksettings_set(dev->phydev, cmd);
}

static int bcmgenet_set_rx_csum(struct net_device *dev,
                                netdev_features_t wanted)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        u32 rbuf_chk_ctrl;
        bool rx_csum_en;

        rx_csum_en = !!(wanted & NETIF_F_RXCSUM);

        rbuf_chk_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CHK_CTRL);

        /* enable rx checksumming */
        if (rx_csum_en)
                rbuf_chk_ctrl |= RBUF_RXCHK_EN;
        else
                rbuf_chk_ctrl &= ~RBUF_RXCHK_EN;
        priv->desc_rxchk_en = rx_csum_en;

        /* If UniMAC forwards CRC, we need to skip over it to get
         * a valid CHK bit to be set in the per-packet status word
        */
        if (rx_csum_en && priv->crc_fwd_en)
                rbuf_chk_ctrl |= RBUF_SKIP_FCS;
        else
                rbuf_chk_ctrl &= ~RBUF_SKIP_FCS;

        bcmgenet_rbuf_writel(priv, rbuf_chk_ctrl, RBUF_CHK_CTRL);

        return 0;
}

static int bcmgenet_set_tx_csum(struct net_device *dev,
                                netdev_features_t wanted)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        bool desc_64b_en;
        u32 tbuf_ctrl, rbuf_ctrl;

        tbuf_ctrl = bcmgenet_tbuf_ctrl_get(priv);
        rbuf_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CTRL);

        desc_64b_en = !!(wanted & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM));

        /* enable 64 bytes descriptor in both directions (RBUF and TBUF) */
        if (desc_64b_en) {
                tbuf_ctrl |= RBUF_64B_EN;
                rbuf_ctrl |= RBUF_64B_EN;
        } else {
                tbuf_ctrl &= ~RBUF_64B_EN;
                rbuf_ctrl &= ~RBUF_64B_EN;
        }
        priv->desc_64b_en = desc_64b_en;

        bcmgenet_tbuf_ctrl_set(priv, tbuf_ctrl);
        bcmgenet_rbuf_writel(priv, rbuf_ctrl, RBUF_CTRL);

        return 0;
}

static int bcmgenet_set_features(struct net_device *dev,
                                 netdev_features_t features)
{
        netdev_features_t changed = features ^ dev->features;
        netdev_features_t wanted = dev->wanted_features;
        int ret = 0;

        if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))
                ret = bcmgenet_set_tx_csum(dev, wanted);
        if (changed & (NETIF_F_RXCSUM))
                ret = bcmgenet_set_rx_csum(dev, wanted);

        return ret;
}

static u32 bcmgenet_get_msglevel(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        return priv->msg_enable;
}

static void bcmgenet_set_msglevel(struct net_device *dev, u32 level)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        priv->msg_enable = level;
}

static int bcmgenet_get_coalesce(struct net_device *dev,
                                 struct ethtool_coalesce *ec)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        struct bcmgenet_rx_ring *ring;
        unsigned int i;

        ec->tx_max_coalesced_frames =
                bcmgenet_tdma_ring_readl(priv, DESC_INDEX,
                                         DMA_MBUF_DONE_THRESH);
        ec->rx_max_coalesced_frames =
                bcmgenet_rdma_ring_readl(priv, DESC_INDEX,
                                         DMA_MBUF_DONE_THRESH);
        ec->rx_coalesce_usecs =
                bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000;

        for (i = 0; i < priv->hw_params->rx_queues; i++) {
                ring = &priv->rx_rings[i];
                ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
        }
        ring = &priv->rx_rings[DESC_INDEX];
        ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;

        return 0;
}

static void bcmgenet_set_rx_coalesce(struct bcmgenet_rx_ring *ring,
                                     u32 usecs, u32 pkts)
{
        struct bcmgenet_priv *priv = ring->priv;
        unsigned int i = ring->index;
        u32 reg;

        bcmgenet_rdma_ring_writel(priv, i, pkts, DMA_MBUF_DONE_THRESH);

        reg = bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT + i);
        reg &= ~DMA_TIMEOUT_MASK;
        reg |= DIV_ROUND_UP(usecs * 1000, 8192);
        bcmgenet_rdma_writel(priv, reg, DMA_RING0_TIMEOUT + i);
}

static void bcmgenet_set_ring_rx_coalesce(struct bcmgenet_rx_ring *ring,
                                          struct ethtool_coalesce *ec)
{
        struct net_dim_cq_moder moder;
        u32 usecs, pkts;

        ring->rx_coalesce_usecs = ec->rx_coalesce_usecs;
        ring->rx_max_coalesced_frames = ec->rx_max_coalesced_frames;
        usecs = ring->rx_coalesce_usecs;
        pkts = ring->rx_max_coalesced_frames;

        if (ec->use_adaptive_rx_coalesce && !ring->dim.use_dim) {
                moder = net_dim_get_def_profile(ring->dim.dim.mode);
                usecs = moder.usec;
                pkts = moder.pkts;
        }

        ring->dim.use_dim = ec->use_adaptive_rx_coalesce;
        bcmgenet_set_rx_coalesce(ring, usecs, pkts);
}

static int bcmgenet_set_coalesce(struct net_device *dev,
                                 struct ethtool_coalesce *ec)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        unsigned int i;

        /* Base system clock is 125Mhz, DMA timeout is this reference clock
         * divided by 1024, which yields roughly 8.192us, our maximum value
         * has to fit in the DMA_TIMEOUT_MASK (16 bits)
         */
        if (ec->tx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK ||
            ec->tx_max_coalesced_frames == 0 ||
            ec->rx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK ||
            ec->rx_coalesce_usecs > (DMA_TIMEOUT_MASK * 8) + 1)
                return -EINVAL;

        if (ec->rx_coalesce_usecs == 0 && ec->rx_max_coalesced_frames == 0)
                return -EINVAL;

        /* GENET TDMA hardware does not support a configurable timeout, but will
         * always generate an interrupt either after MBDONE packets have been
         * transmitted, or when the ring is empty.
         */
        if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high ||
            ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low ||
            ec->use_adaptive_tx_coalesce)
                return -EOPNOTSUPP;

        /* Program all TX queues with the same values, as there is no
         * ethtool knob to do coalescing on a per-queue basis
         */
        for (i = 0; i < priv->hw_params->tx_queues; i++)
                bcmgenet_tdma_ring_writel(priv, i,
                                          ec->tx_max_coalesced_frames,
                                          DMA_MBUF_DONE_THRESH);
        bcmgenet_tdma_ring_writel(priv, DESC_INDEX,
                                  ec->tx_max_coalesced_frames,
                                  DMA_MBUF_DONE_THRESH);

        for (i = 0; i < priv->hw_params->rx_queues; i++)
                bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[i], ec);
        bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[DESC_INDEX], ec);

        return 0;
}

/* standard ethtool support functions. */
enum bcmgenet_stat_type {
        BCMGENET_STAT_NETDEV = -1,
        BCMGENET_STAT_MIB_RX,
        BCMGENET_STAT_MIB_TX,
        BCMGENET_STAT_RUNT,
        BCMGENET_STAT_MISC,
        BCMGENET_STAT_SOFT,
};

struct bcmgenet_stats {
        char stat_string[ETH_GSTRING_LEN];
        int stat_sizeof;
        int stat_offset;
        enum bcmgenet_stat_type type;
        /* reg offset from UMAC base for misc counters */
        u16 reg_offset;
};

#define STAT_NETDEV(m) { \
        .stat_string = __stringify(m), \
        .stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
        .stat_offset = offsetof(struct net_device_stats, m), \
        .type = BCMGENET_STAT_NETDEV, \
}

#define STAT_GENET_MIB(str, m, _type) { \
        .stat_string = str, \
        .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \
        .stat_offset = offsetof(struct bcmgenet_priv, m), \
        .type = _type, \
}

#define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX)
#define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX)
#define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT)
#define STAT_GENET_SOFT_MIB(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_SOFT)

#define STAT_GENET_MISC(str, m, offset) { \
        .stat_string = str, \
        .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \
        .stat_offset = offsetof(struct bcmgenet_priv, m), \
        .type = BCMGENET_STAT_MISC, \
        .reg_offset = offset, \
}

#define STAT_GENET_Q(num) \
        STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
                        tx_rings[num].packets), \
        STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
                        tx_rings[num].bytes), \
        STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
                        rx_rings[num].bytes),    \
        STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
                        rx_rings[num].packets), \
        STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
                        rx_rings[num].errors), \
        STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
                        rx_rings[num].dropped)

/* There is a 0xC gap between the end of RX and beginning of TX stats and then
 * between the end of TX stats and the beginning of the RX RUNT
 */
#define BCMGENET_STAT_OFFSET    0xc

/* Hardware counters must be kept in sync because the order/offset
 * is important here (order in structure declaration = order in hardware)
 */
static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
        /* general stats */
        STAT_NETDEV(rx_packets),
        STAT_NETDEV(tx_packets),
        STAT_NETDEV(rx_bytes),
        STAT_NETDEV(tx_bytes),
        STAT_NETDEV(rx_errors),
        STAT_NETDEV(tx_errors),
        STAT_NETDEV(rx_dropped),
        STAT_NETDEV(tx_dropped),
        STAT_NETDEV(multicast),
        /* UniMAC RSV counters */
        STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
        STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
        STAT_GENET_MIB_RX("rx_128_255_oct", mib.rx.pkt_cnt.cnt_255),
        STAT_GENET_MIB_RX("rx_256_511_oct", mib.rx.pkt_cnt.cnt_511),
        STAT_GENET_MIB_RX("rx_512_1023_oct", mib.rx.pkt_cnt.cnt_1023),
        STAT_GENET_MIB_RX("rx_1024_1518_oct", mib.rx.pkt_cnt.cnt_1518),
        STAT_GENET_MIB_RX("rx_vlan_1519_1522_oct", mib.rx.pkt_cnt.cnt_mgv),
        STAT_GENET_MIB_RX("rx_1522_2047_oct", mib.rx.pkt_cnt.cnt_2047),
        STAT_GENET_MIB_RX("rx_2048_4095_oct", mib.rx.pkt_cnt.cnt_4095),
        STAT_GENET_MIB_RX("rx_4096_9216_oct", mib.rx.pkt_cnt.cnt_9216),
        STAT_GENET_MIB_RX("rx_pkts", mib.rx.pkt),
        STAT_GENET_MIB_RX("rx_bytes", mib.rx.bytes),
        STAT_GENET_MIB_RX("rx_multicast", mib.rx.mca),
        STAT_GENET_MIB_RX("rx_broadcast", mib.rx.bca),
        STAT_GENET_MIB_RX("rx_fcs", mib.rx.fcs),
        STAT_GENET_MIB_RX("rx_control", mib.rx.cf),
        STAT_GENET_MIB_RX("rx_pause", mib.rx.pf),
        STAT_GENET_MIB_RX("rx_unknown", mib.rx.uo),
        STAT_GENET_MIB_RX("rx_align", mib.rx.aln),
        STAT_GENET_MIB_RX("rx_outrange", mib.rx.flr),
        STAT_GENET_MIB_RX("rx_code", mib.rx.cde),
        STAT_GENET_MIB_RX("rx_carrier", mib.rx.fcr),
        STAT_GENET_MIB_RX("rx_oversize", mib.rx.ovr),
        STAT_GENET_MIB_RX("rx_jabber", mib.rx.jbr),
        STAT_GENET_MIB_RX("rx_mtu_err", mib.rx.mtue),
        STAT_GENET_MIB_RX("rx_good_pkts", mib.rx.pok),
        STAT_GENET_MIB_RX("rx_unicast", mib.rx.uc),
        STAT_GENET_MIB_RX("rx_ppp", mib.rx.ppp),
        STAT_GENET_MIB_RX("rx_crc", mib.rx.rcrc),
        /* UniMAC TSV counters */
        STAT_GENET_MIB_TX("tx_64_octets", mib.tx.pkt_cnt.cnt_64),
        STAT_GENET_MIB_TX("tx_65_127_oct", mib.tx.pkt_cnt.cnt_127),
        STAT_GENET_MIB_TX("tx_128_255_oct", mib.tx.pkt_cnt.cnt_255),
        STAT_GENET_MIB_TX("tx_256_511_oct", mib.tx.pkt_cnt.cnt_511),
        STAT_GENET_MIB_TX("tx_512_1023_oct", mib.tx.pkt_cnt.cnt_1023),
        STAT_GENET_MIB_TX("tx_1024_1518_oct", mib.tx.pkt_cnt.cnt_1518),
        STAT_GENET_MIB_TX("tx_vlan_1519_1522_oct", mib.tx.pkt_cnt.cnt_mgv),
        STAT_GENET_MIB_TX("tx_1522_2047_oct", mib.tx.pkt_cnt.cnt_2047),
        STAT_GENET_MIB_TX("tx_2048_4095_oct", mib.tx.pkt_cnt.cnt_4095),
        STAT_GENET_MIB_TX("tx_4096_9216_oct", mib.tx.pkt_cnt.cnt_9216),
        STAT_GENET_MIB_TX("tx_pkts", mib.tx.pkts),
        STAT_GENET_MIB_TX("tx_multicast", mib.tx.mca),
        STAT_GENET_MIB_TX("tx_broadcast", mib.tx.bca),
        STAT_GENET_MIB_TX("tx_pause", mib.tx.pf),
        STAT_GENET_MIB_TX("tx_control", mib.tx.cf),
        STAT_GENET_MIB_TX("tx_fcs_err", mib.tx.fcs),
        STAT_GENET_MIB_TX("tx_oversize", mib.tx.ovr),
        STAT_GENET_MIB_TX("tx_defer", mib.tx.drf),
        STAT_GENET_MIB_TX("tx_excess_defer", mib.tx.edf),
        STAT_GENET_MIB_TX("tx_single_col", mib.tx.scl),
        STAT_GENET_MIB_TX("tx_multi_col", mib.tx.mcl),
        STAT_GENET_MIB_TX("tx_late_col", mib.tx.lcl),
        STAT_GENET_MIB_TX("tx_excess_col", mib.tx.ecl),
        STAT_GENET_MIB_TX("tx_frags", mib.tx.frg),
        STAT_GENET_MIB_TX("tx_total_col", mib.tx.ncl),
        STAT_GENET_MIB_TX("tx_jabber", mib.tx.jbr),
        STAT_GENET_MIB_TX("tx_bytes", mib.tx.bytes),
        STAT_GENET_MIB_TX("tx_good_pkts", mib.tx.pok),
        STAT_GENET_MIB_TX("tx_unicast", mib.tx.uc),
        /* UniMAC RUNT counters */
        STAT_GENET_RUNT("rx_runt_pkts", mib.rx_runt_cnt),
        STAT_GENET_RUNT("rx_runt_valid_fcs", mib.rx_runt_fcs),
        STAT_GENET_RUNT("rx_runt_inval_fcs_align", mib.rx_runt_fcs_align),
        STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
        /* Misc UniMAC counters */
        STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt,
                        UMAC_RBUF_OVFL_CNT_V1),
        STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt,
                        UMAC_RBUF_ERR_CNT_V1),
        STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT),
        STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
        STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed),
        STAT_GENET_SOFT_MIB("tx_dma_failed", mib.tx_dma_failed),
        /* Per TX queues */
        STAT_GENET_Q(0),
        STAT_GENET_Q(1),
        STAT_GENET_Q(2),
        STAT_GENET_Q(3),
        STAT_GENET_Q(16),
};

#define BCMGENET_STATS_LEN      ARRAY_SIZE(bcmgenet_gstrings_stats)

static void bcmgenet_get_drvinfo(struct net_device *dev,
                                 struct ethtool_drvinfo *info)
{
        strlcpy(info->driver, "bcmgenet", sizeof(info->driver));
        strlcpy(info->version, "v2.0", sizeof(info->version));
}

static int bcmgenet_get_sset_count(struct net_device *dev, int string_set)
{
        switch (string_set) {
        case ETH_SS_STATS:
                return BCMGENET_STATS_LEN;
        default:
                return -EOPNOTSUPP;
        }
}

static void bcmgenet_get_strings(struct net_device *dev, u32 stringset,
                                 u8 *data)
{
        int i;

        switch (stringset) {
        case ETH_SS_STATS:
                for (i = 0; i < BCMGENET_STATS_LEN; i++) {
                        memcpy(data + i * ETH_GSTRING_LEN,
                               bcmgenet_gstrings_stats[i].stat_string,
                               ETH_GSTRING_LEN);
                }
                break;
        }
}

static u32 bcmgenet_update_stat_misc(struct bcmgenet_priv *priv, u16 offset)
{
        u16 new_offset;
        u32 val;

        switch (offset) {
        case UMAC_RBUF_OVFL_CNT_V1:
                if (GENET_IS_V2(priv))
                        new_offset = RBUF_OVFL_CNT_V2;
                else
                        new_offset = RBUF_OVFL_CNT_V3PLUS;

                val = bcmgenet_rbuf_readl(priv, new_offset);
                /* clear if overflowed */
                if (val == ~0)
                        bcmgenet_rbuf_writel(priv, 0, new_offset);
                break;
        case UMAC_RBUF_ERR_CNT_V1:
                if (GENET_IS_V2(priv))
                        new_offset = RBUF_ERR_CNT_V2;
                else
                        new_offset = RBUF_ERR_CNT_V3PLUS;

                val = bcmgenet_rbuf_readl(priv, new_offset);
                /* clear if overflowed */
                if (val == ~0)
                        bcmgenet_rbuf_writel(priv, 0, new_offset);
                break;
        default:
                val = bcmgenet_umac_readl(priv, offset);
                /* clear if overflowed */
                if (val == ~0)
                        bcmgenet_umac_writel(priv, 0, offset);
                break;
        }

        return val;
}

static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
{
        int i, j = 0;

        for (i = 0; i < BCMGENET_STATS_LEN; i++) {
                const struct bcmgenet_stats *s;
                u8 offset = 0;
                u32 val = 0;
                char *p;

                s = &bcmgenet_gstrings_stats[i];
                switch (s->type) {
                case BCMGENET_STAT_NETDEV:
                case BCMGENET_STAT_SOFT:
                        continue;
                case BCMGENET_STAT_RUNT:
                        offset += BCMGENET_STAT_OFFSET;
                        /* fall through */
                case BCMGENET_STAT_MIB_TX:
                        offset += BCMGENET_STAT_OFFSET;
                        /* fall through */
                case BCMGENET_STAT_MIB_RX:
                        val = bcmgenet_umac_readl(priv,
                                                  UMAC_MIB_START + j + offset);
                        offset = 0;     /* Reset Offset */
                        break;
                case BCMGENET_STAT_MISC:
                        if (GENET_IS_V1(priv)) {
                                val = bcmgenet_umac_readl(priv, s->reg_offset);
                                /* clear if overflowed */
                                if (val == ~0)
                                        bcmgenet_umac_writel(priv, 0,
                                                             s->reg_offset);
                        } else {
                                val = bcmgenet_update_stat_misc(priv,
                                                                s->reg_offset);
                        }
                        break;
                }

                j += s->stat_sizeof;
                p = (char *)priv + s->stat_offset;
                *(u32 *)p = val;
        }
}

static void bcmgenet_get_ethtool_stats(struct net_device *dev,
                                       struct ethtool_stats *stats,
                                       u64 *data)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        int i;

        if (netif_running(dev))
                bcmgenet_update_mib_counters(priv);

        for (i = 0; i < BCMGENET_STATS_LEN; i++) {
                const struct bcmgenet_stats *s;
                char *p;

                s = &bcmgenet_gstrings_stats[i];
                if (s->type == BCMGENET_STAT_NETDEV)
                        p = (char *)&dev->stats;
                else
                        p = (char *)priv;
                p += s->stat_offset;
                if (sizeof(unsigned long) != sizeof(u32) &&
                    s->stat_sizeof == sizeof(unsigned long))
                        data[i] = *(unsigned long *)p;
                else
                        data[i] = *(u32 *)p;
        }
}

static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL;
        u32 reg;

        if (enable && !priv->clk_eee_enabled) {
                clk_prepare_enable(priv->clk_eee);
                priv->clk_eee_enabled = true;
        }

        reg = bcmgenet_umac_readl(priv, UMAC_EEE_CTRL);
        if (enable)
                reg |= EEE_EN;
        else
                reg &= ~EEE_EN;
        bcmgenet_umac_writel(priv, reg, UMAC_EEE_CTRL);

        /* Enable EEE and switch to a 27Mhz clock automatically */
        reg = bcmgenet_readl(priv->base + off);
        if (enable)
                reg |= TBUF_EEE_EN | TBUF_PM_EN;
        else
                reg &= ~(TBUF_EEE_EN | TBUF_PM_EN);
        bcmgenet_writel(reg, priv->base + off);

        /* Do the same for thing for RBUF */
        reg = bcmgenet_rbuf_readl(priv, RBUF_ENERGY_CTRL);
        if (enable)
                reg |= RBUF_EEE_EN | RBUF_PM_EN;
        else
                reg &= ~(RBUF_EEE_EN | RBUF_PM_EN);
        bcmgenet_rbuf_writel(priv, reg, RBUF_ENERGY_CTRL);

        if (!enable && priv->clk_eee_enabled) {
                clk_disable_unprepare(priv->clk_eee);
                priv->clk_eee_enabled = false;
        }

        priv->eee.eee_enabled = enable;
        priv->eee.eee_active = enable;
}

static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        struct ethtool_eee *p = &priv->eee;

        if (GENET_IS_V1(priv))
                return -EOPNOTSUPP;

        if (!dev->phydev)
                return -ENODEV;

        e->eee_enabled = p->eee_enabled;
        e->eee_active = p->eee_active;
        e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);

        return phy_ethtool_get_eee(dev->phydev, e);
}

static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        struct ethtool_eee *p = &priv->eee;
        int ret = 0;

        if (GENET_IS_V1(priv))
                return -EOPNOTSUPP;

        if (!dev->phydev)
                return -ENODEV;

        p->eee_enabled = e->eee_enabled;

        if (!p->eee_enabled) {
                bcmgenet_eee_enable_set(dev, false);
        } else {
                ret = phy_init_eee(dev->phydev, 0);
                if (ret) {
                        netif_err(priv, hw, dev, "EEE initialization failed\n");
                        return ret;
                }

                bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
                bcmgenet_eee_enable_set(dev, true);
        }

        return phy_ethtool_set_eee(dev->phydev, e);
}

/* standard ethtool support functions. */
static const struct ethtool_ops bcmgenet_ethtool_ops = {
        .begin                  = bcmgenet_begin,
        .complete               = bcmgenet_complete,
        .get_strings            = bcmgenet_get_strings,
        .get_sset_count         = bcmgenet_get_sset_count,
        .get_ethtool_stats      = bcmgenet_get_ethtool_stats,
        .get_drvinfo            = bcmgenet_get_drvinfo,
        .get_link               = ethtool_op_get_link,
        .get_msglevel           = bcmgenet_get_msglevel,
        .set_msglevel           = bcmgenet_set_msglevel,
        .get_wol                = bcmgenet_get_wol,
        .set_wol                = bcmgenet_set_wol,
        .get_eee                = bcmgenet_get_eee,
        .set_eee                = bcmgenet_set_eee,
        .nway_reset             = phy_ethtool_nway_reset,
        .get_coalesce           = bcmgenet_get_coalesce,
        .set_coalesce           = bcmgenet_set_coalesce,
        .get_link_ksettings     = bcmgenet_get_link_ksettings,
        .set_link_ksettings     = bcmgenet_set_link_ksettings,
};

/* Power down the unimac, based on mode. */
static int bcmgenet_power_down(struct bcmgenet_priv *priv,
                                enum bcmgenet_power_mode mode)
{
        int ret = 0;
        u32 reg;

        switch (mode) {
        case GENET_POWER_CABLE_SENSE:
                phy_detach(priv->dev->phydev);
                break;

        case GENET_POWER_WOL_MAGIC:
                ret = bcmgenet_wol_power_down_cfg(priv, mode);
                break;

        case GENET_POWER_PASSIVE:
                /* Power down LED */
                if (priv->hw_params->flags & GENET_HAS_EXT) {
                        reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
                        if (GENET_IS_V5(priv))
                                reg |= EXT_PWR_DOWN_PHY_EN |
                                       EXT_PWR_DOWN_PHY_RD |
                                       EXT_PWR_DOWN_PHY_SD |
                                       EXT_PWR_DOWN_PHY_RX |
                                       EXT_PWR_DOWN_PHY_TX |
                                       EXT_IDDQ_GLBL_PWR;
                        else
                                reg |= EXT_PWR_DOWN_PHY;

                        reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
                        bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);

                        bcmgenet_phy_power_set(priv->dev, false);
                }
                break;
        default:
                break;
        }

        return 0;
}

static void bcmgenet_power_up(struct bcmgenet_priv *priv,
                              enum bcmgenet_power_mode mode)
{
        u32 reg;

        if (!(priv->hw_params->flags & GENET_HAS_EXT))
                return;

        reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);

        switch (mode) {
        case GENET_POWER_PASSIVE:
                reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
                if (GENET_IS_V5(priv)) {
                        reg &= ~(EXT_PWR_DOWN_PHY_EN |
                                 EXT_PWR_DOWN_PHY_RD |
                                 EXT_PWR_DOWN_PHY_SD |
                                 EXT_PWR_DOWN_PHY_RX |
                                 EXT_PWR_DOWN_PHY_TX |
                                 EXT_IDDQ_GLBL_PWR);
                        reg |=   EXT_PHY_RESET;
                        bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
                        mdelay(1);

                        reg &=  ~EXT_PHY_RESET;
                } else {
                        reg &= ~EXT_PWR_DOWN_PHY;
                        reg |= EXT_PWR_DN_EN_LD;
                }
                bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
                bcmgenet_phy_power_set(priv->dev, true);
                break;

        case GENET_POWER_CABLE_SENSE:
                /* enable APD */
                if (!GENET_IS_V5(priv)) {
                        reg |= EXT_PWR_DN_EN_LD;
                        bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
                }
                break;
        case GENET_POWER_WOL_MAGIC:
                bcmgenet_wol_power_up_cfg(priv, mode);
                return;
        default:
                break;
        }
}

/* ioctl handle special commands that are not present in ethtool. */
static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
        if (!netif_running(dev))
                return -EINVAL;

        if (!dev->phydev)
                return -ENODEV;

        return phy_mii_ioctl(dev->phydev, rq, cmd);
}

static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
                                         struct bcmgenet_tx_ring *ring)
{
        struct enet_cb *tx_cb_ptr;

        tx_cb_ptr = ring->cbs;
        tx_cb_ptr += ring->write_ptr - ring->cb_ptr;

        /* Advancing local write pointer */
        if (ring->write_ptr == ring->end_ptr)
                ring->write_ptr = ring->cb_ptr;
        else
                ring->write_ptr++;

        return tx_cb_ptr;
}

static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv,
                                         struct bcmgenet_tx_ring *ring)
{
        struct enet_cb *tx_cb_ptr;

        tx_cb_ptr = ring->cbs;
        tx_cb_ptr += ring->write_ptr - ring->cb_ptr;

        /* Rewinding local write pointer */
        if (ring->write_ptr == ring->cb_ptr)
                ring->write_ptr = ring->end_ptr;
        else
                ring->write_ptr--;

        return tx_cb_ptr;
}

static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring)
{
        bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
                                 INTRL2_CPU_MASK_SET);
}

static inline void bcmgenet_rx_ring16_int_enable(struct bcmgenet_rx_ring *ring)
{
        bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
                                 INTRL2_CPU_MASK_CLEAR);
}

static inline void bcmgenet_rx_ring_int_disable(struct bcmgenet_rx_ring *ring)
{
        bcmgenet_intrl2_1_writel(ring->priv,
                                 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index),
                                 INTRL2_CPU_MASK_SET);
}

static inline void bcmgenet_rx_ring_int_enable(struct bcmgenet_rx_ring *ring)
{
        bcmgenet_intrl2_1_writel(ring->priv,
                                 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index),
                                 INTRL2_CPU_MASK_CLEAR);
}

static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_tx_ring *ring)
{
        bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
                                 INTRL2_CPU_MASK_SET);
}

static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_tx_ring *ring)
{
        bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
                                 INTRL2_CPU_MASK_CLEAR);
}

static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_tx_ring *ring)
{
        bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index,
                                 INTRL2_CPU_MASK_CLEAR);
}

static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_tx_ring *ring)
{
        bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index,
                                 INTRL2_CPU_MASK_SET);
}

/* Simple helper to free a transmit control block's resources
 * Returns an skb when the last transmit control block associated with the
 * skb is freed.  The skb should be freed by the caller if necessary.
 */
static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev,
                                           struct enet_cb *cb)
{
        struct sk_buff *skb;

        skb = cb->skb;

        if (skb) {
                cb->skb = NULL;
                if (cb == GENET_CB(skb)->first_cb)
                        dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr),
                                         dma_unmap_len(cb, dma_len),
                                         DMA_TO_DEVICE);
                else
                        dma_unmap_page(dev, dma_unmap_addr(cb, dma_addr),
                                       dma_unmap_len(cb, dma_len),
                                       DMA_TO_DEVICE);
                dma_unmap_addr_set(cb, dma_addr, 0);

                if (cb == GENET_CB(skb)->last_cb)
                        return skb;

        } else if (dma_unmap_addr(cb, dma_addr)) {
                dma_unmap_page(dev,
                               dma_unmap_addr(cb, dma_addr),
                               dma_unmap_len(cb, dma_len),
                               DMA_TO_DEVICE);
                dma_unmap_addr_set(cb, dma_addr, 0);
        }

        return NULL;
}

/* Simple helper to free a receive control block's resources */
static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev,
                                           struct enet_cb *cb)
{
        struct sk_buff *skb;

        skb = cb->skb;
        cb->skb = NULL;

        if (dma_unmap_addr(cb, dma_addr)) {
                dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr),
                                 dma_unmap_len(cb, dma_len), DMA_FROM_DEVICE);
                dma_unmap_addr_set(cb, dma_addr, 0);
        }

        return skb;
}

/* Unlocked version of the reclaim routine */
static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
                                          struct bcmgenet_tx_ring *ring)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        unsigned int txbds_processed = 0;
        unsigned int bytes_compl = 0;
        unsigned int pkts_compl = 0;
        unsigned int txbds_ready;
        unsigned int c_index;
        struct sk_buff *skb;

        /* Clear status before servicing to reduce spurious interrupts */
        if (ring->index == DESC_INDEX)
                bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
                                         INTRL2_CPU_CLEAR);
        else
                bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
                                         INTRL2_CPU_CLEAR);

        /* Compute how many buffers are transmitted since last xmit call */
        c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
                & DMA_C_INDEX_MASK;
        txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK;

        netif_dbg(priv, tx_done, dev,
                  "%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
                  __func__, ring->index, ring->c_index, c_index, txbds_ready);

        /* Reclaim transmitted buffers */
        while (txbds_processed < txbds_ready) {
                skb = bcmgenet_free_tx_cb(&priv->pdev->dev,
                                          &priv->tx_cbs[ring->clean_ptr]);
                if (skb) {
                        pkts_compl++;
                        bytes_compl += GENET_CB(skb)->bytes_sent;
                        dev_consume_skb_any(skb);
                }

                txbds_processed++;
                if (likely(ring->clean_ptr < ring->end_ptr))
                        ring->clean_ptr++;
                else
                        ring->clean_ptr = ring->cb_ptr;
        }

        ring->free_bds += txbds_processed;
        ring->c_index = c_index;

        ring->packets += pkts_compl;
        ring->bytes += bytes_compl;

        netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
                                  pkts_compl, bytes_compl);

        return txbds_processed;
}

static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
                                struct bcmgenet_tx_ring *ring)
{
        unsigned int released;

        spin_lock_bh(&ring->lock);
        released = __bcmgenet_tx_reclaim(dev, ring);
        spin_unlock_bh(&ring->lock);

        return released;
}

static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
{
        struct bcmgenet_tx_ring *ring =
                container_of(napi, struct bcmgenet_tx_ring, napi);
        unsigned int work_done = 0;
        struct netdev_queue *txq;

        spin_lock(&ring->lock);
        work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
        if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
                txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
                netif_tx_wake_queue(txq);
        }
        spin_unlock(&ring->lock);

        if (work_done == 0) {
                napi_complete(napi);
                ring->int_enable(ring);

                return 0;
        }

        return budget;
}

static void bcmgenet_tx_reclaim_all(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        int i;

        if (netif_is_multiqueue(dev)) {
                for (i = 0; i < priv->hw_params->tx_queues; i++)
                        bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]);
        }

        bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]);
}

/* Reallocate the SKB to put enough headroom in front of it and insert
 * the transmit checksum offsets in the descriptors
 */
static struct sk_buff *bcmgenet_put_tx_csum(struct net_device *dev,
                                            struct sk_buff *skb)
{
        struct status_64 *status = NULL;
        struct sk_buff *new_skb;
        u16 offset;
        u8 ip_proto;
        __be16 ip_ver;
        u32 tx_csum_info;

        if (unlikely(skb_headroom(skb) < sizeof(*status))) {
                /* If 64 byte status block enabled, must make sure skb has
                 * enough headroom for us to insert 64B status block.
                 */
                new_skb = skb_realloc_headroom(skb, sizeof(*status));
                dev_kfree_skb(skb);
                if (!new_skb) {
                        dev->stats.tx_dropped++;
                        return NULL;
                }
                skb = new_skb;
        }

        skb_push(skb, sizeof(*status));
        status = (struct status_64 *)skb->data;

        if (skb->ip_summed  == CHECKSUM_PARTIAL) {
                ip_ver = skb->protocol;
                switch (ip_ver) {
                case htons(ETH_P_IP):
                        ip_proto = ip_hdr(skb)->protocol;
                        break;
                case htons(ETH_P_IPV6):
                        ip_proto = ipv6_hdr(skb)->nexthdr;
                        break;
                default:
                        return skb;
                }

                offset = skb_checksum_start_offset(skb) - sizeof(*status);
                tx_csum_info = (offset << STATUS_TX_CSUM_START_SHIFT) |
                                (offset + skb->csum_offset);

                /* Set the length valid bit for TCP and UDP and just set
                 * the special UDP flag for IPv4, else just set to 0.
                 */
                if (ip_proto == IPPROTO_TCP || ip_proto == IPPROTO_UDP) {
                        tx_csum_info |= STATUS_TX_CSUM_LV;
                        if (ip_proto == IPPROTO_UDP &&
                            ip_ver == htons(ETH_P_IP))
                                tx_csum_info |= STATUS_TX_CSUM_PROTO_UDP;
                } else {
                        tx_csum_info = 0;
                }

                status->tx_csum_info = tx_csum_info;
        }

        return skb;
}

static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        struct device *kdev = &priv->pdev->dev;
        struct bcmgenet_tx_ring *ring = NULL;
        struct enet_cb *tx_cb_ptr;
        struct netdev_queue *txq;
        int nr_frags, index;
        dma_addr_t mapping;
        unsigned int size;
        skb_frag_t *frag;
        u32 len_stat;
        int ret;
        int i;

        index = skb_get_queue_mapping(skb);
        /* Mapping strategy:
         * queue_mapping = 0, unclassified, packet xmited through ring16
         * queue_mapping = 1, goes to ring 0. (highest priority queue
         * queue_mapping = 2, goes to ring 1.
         * queue_mapping = 3, goes to ring 2.
         * queue_mapping = 4, goes to ring 3.
         */
        if (index == 0)
                index = DESC_INDEX;
        else
                index -= 1;

        ring = &priv->tx_rings[index];
        txq = netdev_get_tx_queue(dev, ring->queue);

        nr_frags = skb_shinfo(skb)->nr_frags;

        spin_lock(&ring->lock);
        if (ring->free_bds <= (nr_frags + 1)) {
                if (!netif_tx_queue_stopped(txq)) {
                        netif_tx_stop_queue(txq);
                        netdev_err(dev,
                                   "%s: tx ring %d full when queue %d awake\n",
                                   __func__, index, ring->queue);
                }
                ret = NETDEV_TX_BUSY;
                goto out;
        }

        if (skb_padto(skb, ETH_ZLEN)) {
                ret = NETDEV_TX_OK;
                goto out;
        }

        /* Retain how many bytes will be sent on the wire, without TSB inserted
         * by transmit checksum offload
         */
        GENET_CB(skb)->bytes_sent = skb->len;

        /* set the SKB transmit checksum */
        if (priv->desc_64b_en) {
                skb = bcmgenet_put_tx_csum(dev, skb);
                if (!skb) {
                        ret = NETDEV_TX_OK;
                        goto out;
                }
        }

        for (i = 0; i <= nr_frags; i++) {
                tx_cb_ptr = bcmgenet_get_txcb(priv, ring);

                BUG_ON(!tx_cb_ptr);

                if (!i) {
                        /* Transmit single SKB or head of fragment list */
                        GENET_CB(skb)->first_cb = tx_cb_ptr;
                        size = skb_headlen(skb);
                        mapping = dma_map_single(kdev, skb->data, size,
                                                 DMA_TO_DEVICE);
                } else {
                        /* xmit fragment */
                        frag = &skb_shinfo(skb)->frags[i - 1];
                        size = skb_frag_size(frag);
                        mapping = skb_frag_dma_map(kdev, frag, 0, size,
                                                   DMA_TO_DEVICE);
                }

                ret = dma_mapping_error(kdev, mapping);
                if (ret) {
                        priv->mib.tx_dma_failed++;
                        netif_err(priv, tx_err, dev, "Tx DMA map failed\n");
                        ret = NETDEV_TX_OK;
                        goto out_unmap_frags;
                }
                dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
                dma_unmap_len_set(tx_cb_ptr, dma_len, size);

                tx_cb_ptr->skb = skb;

                len_stat = (size << DMA_BUFLENGTH_SHIFT) |
                           (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT);

                if (!i) {
                        len_stat |= DMA_TX_APPEND_CRC | DMA_SOP;
                        if (skb->ip_summed == CHECKSUM_PARTIAL)
                                len_stat |= DMA_TX_DO_CSUM;
                }
                if (i == nr_frags)
                        len_stat |= DMA_EOP;

                dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, len_stat);
        }

        GENET_CB(skb)->last_cb = tx_cb_ptr;
        skb_tx_timestamp(skb);

        /* Decrement total BD count and advance our write pointer */
        ring->free_bds -= nr_frags + 1;
        ring->prod_index += nr_frags + 1;
        ring->prod_index &= DMA_P_INDEX_MASK;

        netdev_tx_sent_queue(txq, GENET_CB(skb)->bytes_sent);

        if (ring->free_bds <= (MAX_SKB_FRAGS + 1))
                netif_tx_stop_queue(txq);

        if (!skb->xmit_more || netif_xmit_stopped(txq))
                /* Packets are ready, update producer index */
                bcmgenet_tdma_ring_writel(priv, ring->index,
                                          ring->prod_index, TDMA_PROD_INDEX);
out:
        spin_unlock(&ring->lock);

        return ret;

out_unmap_frags:
        /* Back up for failed control block mapping */
        bcmgenet_put_txcb(priv, ring);

        /* Unmap successfully mapped control blocks */
        while (i-- > 0) {
                tx_cb_ptr = bcmgenet_put_txcb(priv, ring);
                bcmgenet_free_tx_cb(kdev, tx_cb_ptr);
        }

        dev_kfree_skb(skb);
        goto out;
}

static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
                                          struct enet_cb *cb)
{
        struct device *kdev = &priv->pdev->dev;
        struct sk_buff *skb;
        struct sk_buff *rx_skb;
        dma_addr_t mapping;

        /* Allocate a new Rx skb */
        skb = netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT);
        if (!skb) {
                priv->mib.alloc_rx_buff_failed++;
                netif_err(priv, rx_err, priv->dev,
                          "%s: Rx skb allocation failed\n", __func__);
                return NULL;
        }

        /* DMA-map the new Rx skb */
        mapping = dma_map_single(kdev, skb->data, priv->rx_buf_len,
                                 DMA_FROM_DEVICE);
        if (dma_mapping_error(kdev, mapping)) {
                priv->mib.rx_dma_failed++;
                dev_kfree_skb_any(skb);
                netif_err(priv, rx_err, priv->dev,
                          "%s: Rx skb DMA mapping failed\n", __func__);
                return NULL;
        }

        /* Grab the current Rx skb from the ring and DMA-unmap it */
        rx_skb = bcmgenet_free_rx_cb(kdev, cb);

        /* Put the new Rx skb on the ring */
        cb->skb = skb;
        dma_unmap_addr_set(cb, dma_addr, mapping);
        dma_unmap_len_set(cb, dma_len, priv->rx_buf_len);
        dmadesc_set_addr(priv, cb->bd_addr, mapping);

        /* Return the current Rx skb to caller */
        return rx_skb;
}

/* bcmgenet_desc_rx - descriptor based rx process.
 * this could be called from bottom half, or from NAPI polling method.
 */
static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
                                     unsigned int budget)
{
        struct bcmgenet_priv *priv = ring->priv;
        struct net_device *dev = priv->dev;
        struct enet_cb *cb;
        struct sk_buff *skb;
        u32 dma_length_status;
        unsigned long dma_flag;
        int len;
        unsigned int rxpktprocessed = 0, rxpkttoprocess;
        unsigned int bytes_processed = 0;
        unsigned int p_index, mask;
        unsigned int discards;
        unsigned int chksum_ok = 0;

        /* Clear status before servicing to reduce spurious interrupts */
        if (ring->index == DESC_INDEX) {
                bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
                                         INTRL2_CPU_CLEAR);
        } else {
                mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
                bcmgenet_intrl2_1_writel(priv,
                                         mask,
                                         INTRL2_CPU_CLEAR);
        }

        p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);

        discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) &
                   DMA_P_INDEX_DISCARD_CNT_MASK;
        if (discards > ring->old_discards) {
                discards = discards - ring->old_discards;
                ring->errors += discards;
                ring->old_discards += discards;

                /* Clear HW register when we reach 75% of maximum 0xFFFF */
                if (ring->old_discards >= 0xC000) {
                        ring->old_discards = 0;
                        bcmgenet_rdma_ring_writel(priv, ring->index, 0,
                                                  RDMA_PROD_INDEX);
                }
        }

        p_index &= DMA_P_INDEX_MASK;
        rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK;

        netif_dbg(priv, rx_status, dev,
                  "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess);

        while ((rxpktprocessed < rxpkttoprocess) &&
               (rxpktprocessed < budget)) {
                cb = &priv->rx_cbs[ring->read_ptr];
                skb = bcmgenet_rx_refill(priv, cb);

                if (unlikely(!skb)) {
                        ring->dropped++;
                        goto next;
                }

                if (!priv->desc_64b_en) {
                        dma_length_status =
                                dmadesc_get_length_status(priv, cb->bd_addr);
                } else {
                        struct status_64 *status;

                        status = (struct status_64 *)skb->data;
                        dma_length_status = status->length_status;
                }

                /* DMA flags and length are still valid no matter how
                 * we got the Receive Status Vector (64B RSB or register)
                 */
                dma_flag = dma_length_status & 0xffff;
                len = dma_length_status >> DMA_BUFLENGTH_SHIFT;

                netif_dbg(priv, rx_status, dev,
                          "%s:p_ind=%d c_ind=%d read_ptr=%d len_stat=0x%08x\n",
                          __func__, p_index, ring->c_index,
                          ring->read_ptr, dma_length_status);

                if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
                        netif_err(priv, rx_status, dev,
                                  "dropping fragmented packet!\n");
                        ring->errors++;
                        dev_kfree_skb_any(skb);
                        goto next;
                }

                /* report errors */
                if (unlikely(dma_flag & (DMA_RX_CRC_ERROR |
                                                DMA_RX_OV |
                                                DMA_RX_NO |
                                                DMA_RX_LG |
                                                DMA_RX_RXER))) {
                        netif_err(priv, rx_status, dev, "dma_flag=0x%x\n",
                                  (unsigned int)dma_flag);
                        if (dma_flag & DMA_RX_CRC_ERROR)
                                dev->stats.rx_crc_errors++;
                        if (dma_flag & DMA_RX_OV)
                                dev->stats.rx_over_errors++;
                        if (dma_flag & DMA_RX_NO)
                                dev->stats.rx_frame_errors++;
                        if (dma_flag & DMA_RX_LG)
                                dev->stats.rx_length_errors++;
                        dev->stats.rx_errors++;
                        dev_kfree_skb_any(skb);
                        goto next;
                } /* error packet */

                chksum_ok = (dma_flag & priv->dma_rx_chk_bit) &&
                             priv->desc_rxchk_en;

                skb_put(skb, len);
                if (priv->desc_64b_en) {
                        skb_pull(skb, 64);
                        len -= 64;
                }

                if (likely(chksum_ok))
                        skb->ip_summed = CHECKSUM_UNNECESSARY;

                /* remove hardware 2bytes added for IP alignment */
                skb_pull(skb, 2);
                len -= 2;

                if (priv->crc_fwd_en) {
                        skb_trim(skb, len - ETH_FCS_LEN);
                        len -= ETH_FCS_LEN;
                }

                bytes_processed += len;

                /*Finish setting up the received SKB and send it to the kernel*/
                skb->protocol = eth_type_trans(skb, priv->dev);
                ring->packets++;
                ring->bytes += len;
                if (dma_flag & DMA_RX_MULT)
                        dev->stats.multicast++;

                /* Notify kernel */
                napi_gro_receive(&ring->napi, skb);
                netif_dbg(priv, rx_status, dev, "pushed up to kernel\n");

next:
                rxpktprocessed++;
                if (likely(ring->read_ptr < ring->end_ptr))
                        ring->read_ptr++;
                else
                        ring->read_ptr = ring->cb_ptr;

                ring->c_index = (ring->c_index + 1) & DMA_C_INDEX_MASK;
                bcmgenet_rdma_ring_writel(priv, ring->index, ring->c_index, RDMA_CONS_INDEX);
        }

        ring->dim.bytes = bytes_processed;
        ring->dim.packets = rxpktprocessed;

        return rxpktprocessed;
}

/* Rx NAPI polling method */
static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
{
        struct bcmgenet_rx_ring *ring = container_of(napi,
                        struct bcmgenet_rx_ring, napi);
        struct net_dim_sample dim_sample;
        unsigned int work_done;

        work_done = bcmgenet_desc_rx(ring, budget);

        if (work_done < budget) {
                napi_complete_done(napi, work_done);
                ring->int_enable(ring);
        }

        if (ring->dim.use_dim) {
                net_dim_sample(ring->dim.event_ctr, ring->dim.packets,
                               ring->dim.bytes, &dim_sample);
                net_dim(&ring->dim.dim, dim_sample);
        }

        return work_done;
}

static void bcmgenet_dim_work(struct work_struct *work)
{
        struct net_dim *dim = container_of(work, struct net_dim, work);
        struct bcmgenet_net_dim *ndim =
                        container_of(dim, struct bcmgenet_net_dim, dim);
        struct bcmgenet_rx_ring *ring =
                        container_of(ndim, struct bcmgenet_rx_ring, dim);
        struct net_dim_cq_moder cur_profile =
                        net_dim_get_profile(dim->mode, dim->profile_ix);

        bcmgenet_set_rx_coalesce(ring, cur_profile.usec, cur_profile.pkts);
        dim->state = NET_DIM_START_MEASURE;
}

/* Assign skb to RX DMA descriptor. */
static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
                                     struct bcmgenet_rx_ring *ring)
{
        struct enet_cb *cb;
        struct sk_buff *skb;
        int i;

        netif_dbg(priv, hw, priv->dev, "%s\n", __func__);

        /* loop here for each buffer needing assign */
        for (i = 0; i < ring->size; i++) {
                cb = ring->cbs + i;
                skb = bcmgenet_rx_refill(priv, cb);
                if (skb)
                        dev_consume_skb_any(skb);
                if (!cb->skb)
                        return -ENOMEM;
        }

        return 0;
}

static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
{
        struct sk_buff *skb;
        struct enet_cb *cb;
        int i;

        for (i = 0; i < priv->num_rx_bds; i++) {
                cb = &priv->rx_cbs[i];

                skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb);
                if (skb)
                        dev_consume_skb_any(skb);
        }
}

static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable)
{
        u32 reg;

        reg = bcmgenet_umac_readl(priv, UMAC_CMD);
        if (enable)
                reg |= mask;
        else
                reg &= ~mask;
        bcmgenet_umac_writel(priv, reg, UMAC_CMD);

        /* UniMAC stops on a packet boundary, wait for a full-size packet
         * to be processed
         */
        if (enable == 0)
                usleep_range(1000, 2000);
}

static void reset_umac(struct bcmgenet_priv *priv)
{
        /* 7358a0/7552a0: bad default in RBUF_FLUSH_CTRL.umac_sw_rst */
        bcmgenet_rbuf_ctrl_set(priv, 0);
        udelay(10);

        /* disable MAC while updating its registers */
        bcmgenet_umac_writel(priv, 0, UMAC_CMD);

        /* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
        bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);

        udelay(2);
        bcmgenet_umac_writel(priv, 0, UMAC_CMD);
}

static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
{
        /* Mask all interrupts.*/
        bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
        bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
        bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
        bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
}

static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
{
        u32 int0_enable = 0;

        /* Monitor cable plug/unplugged event for internal PHY, external PHY
         * and MoCA PHY
         */
        if (priv->internal_phy) {
                int0_enable |= UMAC_IRQ_LINK_EVENT;
        } else if (priv->ext_phy) {
                int0_enable |= UMAC_IRQ_LINK_EVENT;
        } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
                if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
                        int0_enable |= UMAC_IRQ_LINK_EVENT;
        }
        bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
}

static void init_umac(struct bcmgenet_priv *priv)
{
        struct device *kdev = &priv->pdev->dev;
        u32 reg;
        u32 int0_enable = 0;

        dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");

        reset_umac(priv);

        /* clear tx/rx counter */
        bcmgenet_umac_writel(priv,
                             MIB_RESET_RX | MIB_RESET_TX | MIB_RESET_RUNT,
                             UMAC_MIB_CTRL);
        bcmgenet_umac_writel(priv, 0, UMAC_MIB_CTRL);

        bcmgenet_umac_writel(priv, ENET_MAX_MTU_SIZE, UMAC_MAX_FRAME_LEN);

        /* init rx registers, enable ip header optimization */
        reg = bcmgenet_rbuf_readl(priv, RBUF_CTRL);
        reg |= RBUF_ALIGN_2B;
        bcmgenet_rbuf_writel(priv, reg, RBUF_CTRL);

        if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv))
                bcmgenet_rbuf_writel(priv, 1, RBUF_TBUF_SIZE_CTRL);

        bcmgenet_intr_disable(priv);

        /* Configure backpressure vectors for MoCA */
        if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
                reg = bcmgenet_bp_mc_get(priv);
                reg |= BIT(priv->hw_params->bp_in_en_shift);

                /* bp_mask: back pressure mask */
                if (netif_is_multiqueue(priv->dev))
                        reg |= priv->hw_params->bp_in_mask;
                else
                        reg &= ~priv->hw_params->bp_in_mask;
                bcmgenet_bp_mc_set(priv, reg);
        }

        /* Enable MDIO interrupts on GENET v3+ */
        if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
                int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);

        bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);

        dev_dbg(kdev, "done init umac\n");
}

static void bcmgenet_init_dim(struct bcmgenet_rx_ring *ring,
                              void (*cb)(struct work_struct *work))
{
        struct bcmgenet_net_dim *dim = &ring->dim;

        INIT_WORK(&dim->dim.work, cb);
        dim->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
        dim->event_ctr = 0;
        dim->packets = 0;
        dim->bytes = 0;
}

static void bcmgenet_init_rx_coalesce(struct bcmgenet_rx_ring *ring)
{
        struct bcmgenet_net_dim *dim = &ring->dim;
        struct net_dim_cq_moder moder;
        u32 usecs, pkts;

        usecs = ring->rx_coalesce_usecs;
        pkts = ring->rx_max_coalesced_frames;

        /* If DIM was enabled, re-apply default parameters */
        if (dim->use_dim) {
                moder = net_dim_get_def_profile(dim->dim.mode);
                usecs = moder.usec;
                pkts = moder.pkts;
        }

        bcmgenet_set_rx_coalesce(ring, usecs, pkts);
}

/* Initialize a Tx ring along with corresponding hardware registers */
static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
                                  unsigned int index, unsigned int size,
                                  unsigned int start_ptr, unsigned int end_ptr)
{
        struct bcmgenet_tx_ring *ring = &priv->tx_rings[index];
        u32 words_per_bd = WORDS_PER_BD(priv);
        u32 flow_period_val = 0;

        spin_lock_init(&ring->lock);
        ring->priv = priv;
        ring->index = index;
        if (index == DESC_INDEX) {
                ring->queue = 0;
                ring->int_enable = bcmgenet_tx_ring16_int_enable;
                ring->int_disable = bcmgenet_tx_ring16_int_disable;
        } else {
                ring->queue = index + 1;
                ring->int_enable = bcmgenet_tx_ring_int_enable;
                ring->int_disable = bcmgenet_tx_ring_int_disable;
        }
        ring->cbs = priv->tx_cbs + start_ptr;
        ring->size = size;
        ring->clean_ptr = start_ptr;
        ring->c_index = 0;
        ring->free_bds = size;
        ring->write_ptr = start_ptr;
        ring->cb_ptr = start_ptr;
        ring->end_ptr = end_ptr - 1;
        ring->prod_index = 0;

        /* Set flow period for ring != 16 */
        if (index != DESC_INDEX)
                flow_period_val = ENET_MAX_MTU_SIZE << 16;

        bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX);
        bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_CONS_INDEX);
        bcmgenet_tdma_ring_writel(priv, index, 1, DMA_MBUF_DONE_THRESH);
        /* Disable rate control for now */
        bcmgenet_tdma_ring_writel(priv, index, flow_period_val,
                                  TDMA_FLOW_PERIOD);
        bcmgenet_tdma_ring_writel(priv, index,
                                  ((size << DMA_RING_SIZE_SHIFT) |
                                   RX_BUF_LENGTH), DMA_RING_BUF_SIZE);

        /* Set start and end address, read and write pointers */
        bcmgenet_tdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  DMA_START_ADDR);
        bcmgenet_tdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  TDMA_READ_PTR);
        bcmgenet_tdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  TDMA_WRITE_PTR);
        bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
                                  DMA_END_ADDR);

        /* Initialize Tx NAPI */
        netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
                       NAPI_POLL_WEIGHT);
}

/* Initialize a RDMA ring */
static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
                                 unsigned int index, unsigned int size,
                                 unsigned int start_ptr, unsigned int end_ptr)
{
        struct bcmgenet_rx_ring *ring = &priv->rx_rings[index];
        u32 words_per_bd = WORDS_PER_BD(priv);
        int ret;

        ring->priv = priv;
        ring->index = index;
        if (index == DESC_INDEX) {
                ring->int_enable = bcmgenet_rx_ring16_int_enable;
                ring->int_disable = bcmgenet_rx_ring16_int_disable;
        } else {
                ring->int_enable = bcmgenet_rx_ring_int_enable;
                ring->int_disable = bcmgenet_rx_ring_int_disable;
        }
        ring->cbs = priv->rx_cbs + start_ptr;
        ring->size = size;
        ring->c_index = 0;
        ring->read_ptr = start_ptr;
        ring->cb_ptr = start_ptr;
        ring->end_ptr = end_ptr - 1;

        ret = bcmgenet_alloc_rx_buffers(priv, ring);
        if (ret)
                return ret;

        bcmgenet_init_dim(ring, bcmgenet_dim_work);
        bcmgenet_init_rx_coalesce(ring);

        /* Initialize Rx NAPI */
        netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll,
                       NAPI_POLL_WEIGHT);

        bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_PROD_INDEX);
        bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_CONS_INDEX);
        bcmgenet_rdma_ring_writel(priv, index,
                                  ((size << DMA_RING_SIZE_SHIFT) |
                                   RX_BUF_LENGTH), DMA_RING_BUF_SIZE);
        bcmgenet_rdma_ring_writel(priv, index,
                                  (DMA_FC_THRESH_LO <<
                                   DMA_XOFF_THRESHOLD_SHIFT) |
                                   DMA_FC_THRESH_HI, RDMA_XON_XOFF_THRESH);

        /* Set start and end address, read and write pointers */
        bcmgenet_rdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  DMA_START_ADDR);
        bcmgenet_rdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  RDMA_READ_PTR);
        bcmgenet_rdma_ring_writel(priv, index, start_ptr * words_per_bd,
                                  RDMA_WRITE_PTR);
        bcmgenet_rdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
                                  DMA_END_ADDR);

        return ret;
}

static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_tx_ring *ring;

        for (i = 0; i < priv->hw_params->tx_queues; ++i) {
                ring = &priv->tx_rings[i];
                napi_enable(&ring->napi);
                ring->int_enable(ring);
        }

        ring = &priv->tx_rings[DESC_INDEX];
        napi_enable(&ring->napi);
        ring->int_enable(ring);
}

static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_tx_ring *ring;

        for (i = 0; i < priv->hw_params->tx_queues; ++i) {
                ring = &priv->tx_rings[i];
                napi_disable(&ring->napi);
        }

        ring = &priv->tx_rings[DESC_INDEX];
        napi_disable(&ring->napi);
}

static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_tx_ring *ring;

        for (i = 0; i < priv->hw_params->tx_queues; ++i) {
                ring = &priv->tx_rings[i];
                netif_napi_del(&ring->napi);
        }

        ring = &priv->tx_rings[DESC_INDEX];
        netif_napi_del(&ring->napi);
}

/* Initialize Tx queues
 *
 * Queues 0-3 are priority-based, each one has 32 descriptors,
 * with queue 0 being the highest priority queue.
 *
 * Queue 16 is the default Tx queue with
 * GENET_Q16_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
 *
 * The transmit control block pool is then partitioned as follows:
 * - Tx queue 0 uses tx_cbs[0..31]
 * - Tx queue 1 uses tx_cbs[32..63]
 * - Tx queue 2 uses tx_cbs[64..95]
 * - Tx queue 3 uses tx_cbs[96..127]
 * - Tx queue 16 uses tx_cbs[128..255]
 */
static void bcmgenet_init_tx_queues(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        u32 i, dma_enable;
        u32 dma_ctrl, ring_cfg;
        u32 dma_priority[3] = {0, 0, 0};

        dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL);
        dma_enable = dma_ctrl & DMA_EN;
        dma_ctrl &= ~DMA_EN;
        bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);

        dma_ctrl = 0;
        ring_cfg = 0;

        /* Enable strict priority arbiter mode */
        bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);

        /* Initialize Tx priority queues */
        for (i = 0; i < priv->hw_params->tx_queues; i++) {
                bcmgenet_init_tx_ring(priv, i, priv->hw_params->tx_bds_per_q,
                                      i * priv->hw_params->tx_bds_per_q,
                                      (i + 1) * priv->hw_params->tx_bds_per_q);
                ring_cfg |= (1 << i);
                dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
                dma_priority[DMA_PRIO_REG_INDEX(i)] |=
                        ((GENET_Q0_PRIORITY + i) << DMA_PRIO_REG_SHIFT(i));
        }

        /* Initialize Tx default queue 16 */
        bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_Q16_TX_BD_CNT,
                              priv->hw_params->tx_queues *
                              priv->hw_params->tx_bds_per_q,
                              TOTAL_DESC);
        ring_cfg |= (1 << DESC_INDEX);
        dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
        dma_priority[DMA_PRIO_REG_INDEX(DESC_INDEX)] |=
                ((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) <<
                 DMA_PRIO_REG_SHIFT(DESC_INDEX));

        /* Set Tx queue priorities */
        bcmgenet_tdma_writel(priv, dma_priority[0], DMA_PRIORITY_0);
        bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
        bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);

        /* Enable Tx queues */
        bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);

        /* Enable Tx DMA */
        if (dma_enable)
                dma_ctrl |= DMA_EN;
        bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
}

static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_rx_ring *ring;

        for (i = 0; i < priv->hw_params->rx_queues; ++i) {
                ring = &priv->rx_rings[i];
                napi_enable(&ring->napi);
                ring->int_enable(ring);
        }

        ring = &priv->rx_rings[DESC_INDEX];
        napi_enable(&ring->napi);
        ring->int_enable(ring);
}

static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_rx_ring *ring;

        for (i = 0; i < priv->hw_params->rx_queues; ++i) {
                ring = &priv->rx_rings[i];
                napi_disable(&ring->napi);
                cancel_work_sync(&ring->dim.dim.work);
        }

        ring = &priv->rx_rings[DESC_INDEX];
        napi_disable(&ring->napi);
        cancel_work_sync(&ring->dim.dim.work);
}

static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
{
        unsigned int i;
        struct bcmgenet_rx_ring *ring;

        for (i = 0; i < priv->hw_params->rx_queues; ++i) {
                ring = &priv->rx_rings[i];
                netif_napi_del(&ring->napi);
        }

        ring = &priv->rx_rings[DESC_INDEX];
        netif_napi_del(&ring->napi);
}

/* Initialize Rx queues
 *
 * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be
 * used to direct traffic to these queues.
 *
 * Queue 16 is the default Rx queue with GENET_Q16_RX_BD_CNT descriptors.
 */
static int bcmgenet_init_rx_queues(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        u32 i;
        u32 dma_enable;
        u32 dma_ctrl;
        u32 ring_cfg;
        int ret;

        dma_ctrl = bcmgenet_rdma_readl(priv, DMA_CTRL);
        dma_enable = dma_ctrl & DMA_EN;
        dma_ctrl &= ~DMA_EN;
        bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);

        dma_ctrl = 0;
        ring_cfg = 0;

        /* Initialize Rx priority queues */
        for (i = 0; i < priv->hw_params->rx_queues; i++) {
                ret = bcmgenet_init_rx_ring(priv, i,
                                            priv->hw_params->rx_bds_per_q,
                                            i * priv->hw_params->rx_bds_per_q,
                                            (i + 1) *
                                            priv->hw_params->rx_bds_per_q);
                if (ret)
                        return ret;

                ring_cfg |= (1 << i);
                dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
        }

        /* Initialize Rx default queue 16 */
        ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, GENET_Q16_RX_BD_CNT,
                                    priv->hw_params->rx_queues *
                                    priv->hw_params->rx_bds_per_q,
                                    TOTAL_DESC);
        if (ret)
                return ret;

        ring_cfg |= (1 << DESC_INDEX);
        dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));

        /* Enable rings */
        bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);

        /* Configure ring as descriptor ring and re-enable DMA if enabled */
        if (dma_enable)
                dma_ctrl |= DMA_EN;
        bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);

        return 0;
}

static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
{
        int ret = 0;
        int timeout = 0;
        u32 reg;
        u32 dma_ctrl;
        int i;

        /* Disable TDMA to stop add more frames in TX DMA */
        reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
        reg &= ~DMA_EN;
        bcmgenet_tdma_writel(priv, reg, DMA_CTRL);

        /* Check TDMA status register to confirm TDMA is disabled */
        while (timeout++ < DMA_TIMEOUT_VAL) {
                reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
                if (reg & DMA_DISABLED)
                        break;

                udelay(1);
        }

        if (timeout == DMA_TIMEOUT_VAL) {
                netdev_warn(priv->dev, "Timed out while disabling TX DMA\n");
                ret = -ETIMEDOUT;
        }

        /* Wait 10ms for packet drain in both tx and rx dma */
        usleep_range(10000, 20000);

        /* Disable RDMA */
        reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
        reg &= ~DMA_EN;
        bcmgenet_rdma_writel(priv, reg, DMA_CTRL);

        timeout = 0;
        /* Check RDMA status register to confirm RDMA is disabled */
        while (timeout++ < DMA_TIMEOUT_VAL) {
                reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
                if (reg & DMA_DISABLED)
                        break;

                udelay(1);
        }

        if (timeout == DMA_TIMEOUT_VAL) {
                netdev_warn(priv->dev, "Timed out while disabling RX DMA\n");
                ret = -ETIMEDOUT;
        }

        dma_ctrl = 0;
        for (i = 0; i < priv->hw_params->rx_queues; i++)
                dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
        reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
        reg &= ~dma_ctrl;
        bcmgenet_rdma_writel(priv, reg, DMA_CTRL);

        dma_ctrl = 0;
        for (i = 0; i < priv->hw_params->tx_queues; i++)
                dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
        reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
        reg &= ~dma_ctrl;
        bcmgenet_tdma_writel(priv, reg, DMA_CTRL);

        return ret;
}

static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
{
        struct netdev_queue *txq;
        struct sk_buff *skb;
        struct enet_cb *cb;
        int i;

        bcmgenet_fini_rx_napi(priv);
        bcmgenet_fini_tx_napi(priv);

        for (i = 0; i < priv->num_tx_bds; i++) {
                cb = priv->tx_cbs + i;
                skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb);
                if (skb)
                        dev_kfree_skb(skb);
        }

        for (i = 0; i < priv->hw_params->tx_queues; i++) {
                txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[i].queue);
                netdev_tx_reset_queue(txq);
        }

        txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[DESC_INDEX].queue);
        netdev_tx_reset_queue(txq);

        bcmgenet_free_rx_buffers(priv);
        kfree(priv->rx_cbs);
        kfree(priv->tx_cbs);
}

/* init_edma: Initialize DMA control register */
static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
{
        int ret;
        unsigned int i;
        struct enet_cb *cb;

        netif_dbg(priv, hw, priv->dev, "%s\n", __func__);

        /* Initialize common Rx ring structures */
        priv->rx_bds = priv->base + priv->hw_params->rdma_offset;
        priv->num_rx_bds = TOTAL_DESC;
        priv->rx_cbs = kcalloc(priv->num_rx_bds, sizeof(struct enet_cb),
                               GFP_KERNEL);
        if (!priv->rx_cbs)
                return -ENOMEM;

        for (i = 0; i < priv->num_rx_bds; i++) {
                cb = priv->rx_cbs + i;
                cb->bd_addr = priv->rx_bds + i * DMA_DESC_SIZE;
        }

        /* Initialize common TX ring structures */
        priv->tx_bds = priv->base + priv->hw_params->tdma_offset;
        priv->num_tx_bds = TOTAL_DESC;
        priv->tx_cbs = kcalloc(priv->num_tx_bds, sizeof(struct enet_cb),
                               GFP_KERNEL);
        if (!priv->tx_cbs) {
                kfree(priv->rx_cbs);
                return -ENOMEM;
        }

        for (i = 0; i < priv->num_tx_bds; i++) {
                cb = priv->tx_cbs + i;
                cb->bd_addr = priv->tx_bds + i * DMA_DESC_SIZE;
        }

        /* Init rDma */
        bcmgenet_rdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE);

        /* Initialize Rx queues */
        ret = bcmgenet_init_rx_queues(priv->dev);
        if (ret) {
                netdev_err(priv->dev, "failed to initialize Rx queues\n");
                bcmgenet_free_rx_buffers(priv);
                kfree(priv->rx_cbs);
                kfree(priv->tx_cbs);
                return ret;
        }

        /* Init tDma */
        bcmgenet_tdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE);

        /* Initialize Tx queues */
        bcmgenet_init_tx_queues(priv->dev);

        return 0;
}

/* Interrupt bottom half */
static void bcmgenet_irq_task(struct work_struct *work)
{
        unsigned int status;
        struct bcmgenet_priv *priv = container_of(
                        work, struct bcmgenet_priv, bcmgenet_irq_work);

        netif_dbg(priv, intr, priv->dev, "%s\n", __func__);

        spin_lock_irq(&priv->lock);
        status = priv->irq0_stat;
        priv->irq0_stat = 0;
        spin_unlock_irq(&priv->lock);

        /* Link UP/DOWN event */
        if (status & UMAC_IRQ_LINK_EVENT) {
                priv->dev->phydev->link = !!(status & UMAC_IRQ_LINK_UP);
                phy_mac_interrupt(priv->dev->phydev);
        }
}

/* bcmgenet_isr1: handle Rx and Tx priority queues */
static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
{
        struct bcmgenet_priv *priv = dev_id;
        struct bcmgenet_rx_ring *rx_ring;
        struct bcmgenet_tx_ring *tx_ring;
        unsigned int index, status;

        /* Read irq status */
        status = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
                ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);

        /* clear interrupts */
        bcmgenet_intrl2_1_writel(priv, status, INTRL2_CPU_CLEAR);

        netif_dbg(priv, intr, priv->dev,
                  "%s: IRQ=0x%x\n", __func__, status);

        /* Check Rx priority queue interrupts */
        for (index = 0; index < priv->hw_params->rx_queues; index++) {
                if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
                        continue;

                rx_ring = &priv->rx_rings[index];
                rx_ring->dim.event_ctr++;

                if (likely(napi_schedule_prep(&rx_ring->napi))) {
                        rx_ring->int_disable(rx_ring);
                        __napi_schedule_irqoff(&rx_ring->napi);
                }
        }

        /* Check Tx priority queue interrupts */
        for (index = 0; index < priv->hw_params->tx_queues; index++) {
                if (!(status & BIT(index)))
                        continue;

                tx_ring = &priv->tx_rings[index];

                if (likely(napi_schedule_prep(&tx_ring->napi))) {
                        tx_ring->int_disable(tx_ring);
                        __napi_schedule_irqoff(&tx_ring->napi);
                }
        }

        return IRQ_HANDLED;
}

/* bcmgenet_isr0: handle Rx and Tx default queues + other stuff */
static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
{
        struct bcmgenet_priv *priv = dev_id;
        struct bcmgenet_rx_ring *rx_ring;
        struct bcmgenet_tx_ring *tx_ring;
        unsigned int status;
        unsigned long flags;

        /* Read irq status */
        status = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
                ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);

        /* clear interrupts */
        bcmgenet_intrl2_0_writel(priv, status, INTRL2_CPU_CLEAR);

        netif_dbg(priv, intr, priv->dev,
                  "IRQ=0x%x\n", status);

        if (status & UMAC_IRQ_RXDMA_DONE) {
                rx_ring = &priv->rx_rings[DESC_INDEX];
                rx_ring->dim.event_ctr++;

                if (likely(napi_schedule_prep(&rx_ring->napi))) {
                        rx_ring->int_disable(rx_ring);
                        __napi_schedule_irqoff(&rx_ring->napi);
                }
        }

        if (status & UMAC_IRQ_TXDMA_DONE) {
                tx_ring = &priv->tx_rings[DESC_INDEX];

                if (likely(napi_schedule_prep(&tx_ring->napi))) {
                        tx_ring->int_disable(tx_ring);
                        __napi_schedule_irqoff(&tx_ring->napi);
                }
        }

        if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
                status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
                wake_up(&priv->wq);
        }

        /* all other interested interrupts handled in bottom half */
        status &= UMAC_IRQ_LINK_EVENT;
        if (status) {
                /* Save irq status for bottom-half processing. */
                spin_lock_irqsave(&priv->lock, flags);
                priv->irq0_stat |= status;
                spin_unlock_irqrestore(&priv->lock, flags);

                schedule_work(&priv->bcmgenet_irq_work);
        }

        return IRQ_HANDLED;
}

static irqreturn_t bcmgenet_wol_isr(int irq, void *dev_id)
{
        struct bcmgenet_priv *priv = dev_id;

        pm_wakeup_event(&priv->pdev->dev, 0);

        return IRQ_HANDLED;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void bcmgenet_poll_controller(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        /* Invoke the main RX/TX interrupt handler */
        disable_irq(priv->irq0);
        bcmgenet_isr0(priv->irq0, priv);
        enable_irq(priv->irq0);

        /* And the interrupt handler for RX/TX priority queues */
        disable_irq(priv->irq1);
        bcmgenet_isr1(priv->irq1, priv);
        enable_irq(priv->irq1);
}
#endif

static void bcmgenet_umac_reset(struct bcmgenet_priv *priv)
{
        u32 reg;

        reg = bcmgenet_rbuf_ctrl_get(priv);
        reg |= BIT(1);
        bcmgenet_rbuf_ctrl_set(priv, reg);
        udelay(10);

        reg &= ~BIT(1);
        bcmgenet_rbuf_ctrl_set(priv, reg);
        udelay(10);
}

static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv,
                                 unsigned char *addr)
{
        bcmgenet_umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) |
                        (addr[2] << 8) | addr[3], UMAC_MAC0);
        bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1);
}

/* Returns a reusable dma control register value */
static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv)
{
        u32 reg;
        u32 dma_ctrl;

        /* disable DMA */
        dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
        reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
        reg &= ~dma_ctrl;
        bcmgenet_tdma_writel(priv, reg, DMA_CTRL);

        reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
        reg &= ~dma_ctrl;
        bcmgenet_rdma_writel(priv, reg, DMA_CTRL);

        bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
        udelay(10);
        bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);

        return dma_ctrl;
}

static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
{
        u32 reg;

        reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
        reg |= dma_ctrl;
        bcmgenet_rdma_writel(priv, reg, DMA_CTRL);

        reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
        reg |= dma_ctrl;
        bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
}

/* bcmgenet_hfb_clear
 *
 * Clear Hardware Filter Block and disable all filtering.
 */
static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
{
        u32 i;

        bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
        bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
        bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);

        for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
                bcmgenet_rdma_writel(priv, 0x0, i);

        for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
                bcmgenet_hfb_reg_writel(priv, 0x0,
                                        HFB_FLT_LEN_V3PLUS + i * sizeof(u32));

        for (i = 0; i < priv->hw_params->hfb_filter_cnt *
                        priv->hw_params->hfb_filter_size; i++)
                bcmgenet_hfb_writel(priv, 0x0, i * sizeof(u32));
}

static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
{
        if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
                return;

        bcmgenet_hfb_clear(priv);
}

static void bcmgenet_netif_start(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        /* Start the network engine */
        bcmgenet_enable_rx_napi(priv);

        umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);

        netif_tx_start_all_queues(dev);
        bcmgenet_enable_tx_napi(priv);

        /* Monitor link interrupts now */
        bcmgenet_link_intr_enable(priv);

        phy_start(dev->phydev);
}

static int bcmgenet_open(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        unsigned long dma_ctrl;
        u32 reg;
        int ret;

        netif_dbg(priv, ifup, dev, "bcmgenet_open\n");

        /* Turn on the clock */
        clk_prepare_enable(priv->clk);

        /* If this is an internal GPHY, power it back on now, before UniMAC is
         * brought out of reset as absolutely no UniMAC activity is allowed
         */
        if (priv->internal_phy)
                bcmgenet_power_up(priv, GENET_POWER_PASSIVE);

        /* take MAC out of reset */
        bcmgenet_umac_reset(priv);

        init_umac(priv);

        /* Make sure we reflect the value of CRC_CMD_FWD */
        reg = bcmgenet_umac_readl(priv, UMAC_CMD);
        priv->crc_fwd_en = !!(reg & CMD_CRC_FWD);

        bcmgenet_set_hw_addr(priv, dev->dev_addr);

        if (priv->internal_phy) {
                reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
                reg |= EXT_ENERGY_DET_MASK;
                bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
        }

        /* Disable RX/TX DMA and flush TX queues */
        dma_ctrl = bcmgenet_dma_disable(priv);

        /* Reinitialize TDMA and RDMA and SW housekeeping */
        ret = bcmgenet_init_dma(priv);
        if (ret) {
                netdev_err(dev, "failed to initialize DMA\n");
                goto err_clk_disable;
        }

        /* Always enable ring 16 - descriptor ring */
        bcmgenet_enable_dma(priv, dma_ctrl);

        /* HFB init */
        bcmgenet_hfb_init(priv);

        ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
                          dev->name, priv);
        if (ret < 0) {
                netdev_err(dev, "can't request IRQ %d\n", priv->irq0);
                goto err_fini_dma;
        }

        ret = request_irq(priv->irq1, bcmgenet_isr1, IRQF_SHARED,
                          dev->name, priv);
        if (ret < 0) {
                netdev_err(dev, "can't request IRQ %d\n", priv->irq1);
                goto err_irq0;
        }

        ret = bcmgenet_mii_probe(dev);
        if (ret) {
                netdev_err(dev, "failed to connect to PHY\n");
                goto err_irq1;
        }

        bcmgenet_netif_start(dev);

        return 0;

err_irq1:
        free_irq(priv->irq1, priv);
err_irq0:
        free_irq(priv->irq0, priv);
err_fini_dma:
        bcmgenet_dma_teardown(priv);
        bcmgenet_fini_dma(priv);
err_clk_disable:
        if (priv->internal_phy)
                bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
        clk_disable_unprepare(priv->clk);
        return ret;
}

static void bcmgenet_netif_stop(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);

        bcmgenet_disable_tx_napi(priv);
        netif_tx_stop_all_queues(dev);

        /* Disable MAC receive */
        umac_enable_set(priv, CMD_RX_EN, false);

        bcmgenet_dma_teardown(priv);

        /* Disable MAC transmit. TX DMA disabled must be done before this */
        umac_enable_set(priv, CMD_TX_EN, false);

        phy_stop(dev->phydev);
        bcmgenet_disable_rx_napi(priv);
        bcmgenet_intr_disable(priv);

        /* Wait for pending work items to complete. Since interrupts are
         * disabled no new work will be scheduled.
         */
        cancel_work_sync(&priv->bcmgenet_irq_work);

        priv->old_link = -1;
        priv->old_speed = -1;
        priv->old_duplex = -1;
        priv->old_pause = -1;

        /* tx reclaim */
        bcmgenet_tx_reclaim_all(dev);
        bcmgenet_fini_dma(priv);
}

static int bcmgenet_close(struct net_device *dev)
{
        struct bcmgenet_priv *priv = netdev_priv(dev);
        int ret = 0;

        netif_dbg(priv, ifdown, dev, "bcmgenet_close\n");

        bcmgenet_netif_stop(dev);

        /* Really kill the PHY state machine and disconnect from it */
        phy_disconnect(dev->phydev);