/*******************************************************************************

  Intel PRO/1000 Linux driver
  Copyright(c) 1999 - 2006 Intel Corporation.

  This program is free software; you can redistribute it and/or modify it
  under the terms and conditions of the GNU General Public License,
  version 2, as published by the Free Software Foundation.

  This program is distributed in the hope it will be useful, but WITHOUT
  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  more details.

  You should have received a copy of the GNU General Public License along with
  this program; if not, write to the Free Software Foundation, Inc.,
  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.

  The full GNU General Public License is included in this distribution in
  the file called "COPYING".

  Contact Information:
  Linux NICS <linux.nics@intel.com>
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

*******************************************************************************/

#include "e1000.h"
#include <net/ip6_checksum.h>
#include <linux/io.h>
#include <linux/prefetch.h>
#include <linux/bitops.h>
#include <linux/if_vlan.h>

char e1000_driver_name[] = "e1000";
static char e1000_driver_string[] = "Intel(R) PRO/1000 Network Driver";
#define DRV_VERSION "7.3.21-k8-NAPI"
const char e1000_driver_version[] = DRV_VERSION;
static const char e1000_copyright[] = "Copyright (c) 1999-2006 Intel Corporation.";

/* e1000_pci_tbl - PCI Device ID Table
 *
 * Last entry must be all 0s
 *
 * Macro expands to...
 *   {PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
 */
static const struct pci_device_id e1000_pci_tbl[] = {
        INTEL_E1000_ETHERNET_DEVICE(0x1000),
        INTEL_E1000_ETHERNET_DEVICE(0x1001),
        INTEL_E1000_ETHERNET_DEVICE(0x1004),
        INTEL_E1000_ETHERNET_DEVICE(0x1008),
        INTEL_E1000_ETHERNET_DEVICE(0x1009),
        INTEL_E1000_ETHERNET_DEVICE(0x100C),
        INTEL_E1000_ETHERNET_DEVICE(0x100D),
        INTEL_E1000_ETHERNET_DEVICE(0x100E),
        INTEL_E1000_ETHERNET_DEVICE(0x100F),
        INTEL_E1000_ETHERNET_DEVICE(0x1010),
        INTEL_E1000_ETHERNET_DEVICE(0x1011),
        INTEL_E1000_ETHERNET_DEVICE(0x1012),
        INTEL_E1000_ETHERNET_DEVICE(0x1013),
        INTEL_E1000_ETHERNET_DEVICE(0x1014),
        INTEL_E1000_ETHERNET_DEVICE(0x1015),
        INTEL_E1000_ETHERNET_DEVICE(0x1016),
        INTEL_E1000_ETHERNET_DEVICE(0x1017),
        INTEL_E1000_ETHERNET_DEVICE(0x1018),
        INTEL_E1000_ETHERNET_DEVICE(0x1019),
        INTEL_E1000_ETHERNET_DEVICE(0x101A),
        INTEL_E1000_ETHERNET_DEVICE(0x101D),
        INTEL_E1000_ETHERNET_DEVICE(0x101E),
        INTEL_E1000_ETHERNET_DEVICE(0x1026),
        INTEL_E1000_ETHERNET_DEVICE(0x1027),
        INTEL_E1000_ETHERNET_DEVICE(0x1028),
        INTEL_E1000_ETHERNET_DEVICE(0x1075),
        INTEL_E1000_ETHERNET_DEVICE(0x1076),
        INTEL_E1000_ETHERNET_DEVICE(0x1077),
        INTEL_E1000_ETHERNET_DEVICE(0x1078),
        INTEL_E1000_ETHERNET_DEVICE(0x1079),
        INTEL_E1000_ETHERNET_DEVICE(0x107A),
        INTEL_E1000_ETHERNET_DEVICE(0x107B),
        INTEL_E1000_ETHERNET_DEVICE(0x107C),
        INTEL_E1000_ETHERNET_DEVICE(0x108A),
        INTEL_E1000_ETHERNET_DEVICE(0x1099),
        INTEL_E1000_ETHERNET_DEVICE(0x10B5),
        INTEL_E1000_ETHERNET_DEVICE(0x2E6E),
        /* required last entry */
        {0,}
};

MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);

int e1000_up(struct e1000_adapter *adapter);
void e1000_down(struct e1000_adapter *adapter);
void e1000_reinit_locked(struct e1000_adapter *adapter);
void e1000_reset(struct e1000_adapter *adapter);
int e1000_setup_all_tx_resources(struct e1000_adapter *adapter);
int e1000_setup_all_rx_resources(struct e1000_adapter *adapter);
void e1000_free_all_tx_resources(struct e1000_adapter *adapter);
void e1000_free_all_rx_resources(struct e1000_adapter *adapter);
static int e1000_setup_tx_resources(struct e1000_adapter *adapter,
                                    struct e1000_tx_ring *txdr);
static int e1000_setup_rx_resources(struct e1000_adapter *adapter,
                                    struct e1000_rx_ring *rxdr);
static void e1000_free_tx_resources(struct e1000_adapter *adapter,
                                    struct e1000_tx_ring *tx_ring);
static void e1000_free_rx_resources(struct e1000_adapter *adapter,
                                    struct e1000_rx_ring *rx_ring);
void e1000_update_stats(struct e1000_adapter *adapter);

static int e1000_init_module(void);
static void e1000_exit_module(void);
static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
static void e1000_remove(struct pci_dev *pdev);
static int e1000_alloc_queues(struct e1000_adapter *adapter);
static int e1000_sw_init(struct e1000_adapter *adapter);
static int e1000_open(struct net_device *netdev);
static int e1000_close(struct net_device *netdev);
static void e1000_configure_tx(struct e1000_adapter *adapter);
static void e1000_configure_rx(struct e1000_adapter *adapter);
static void e1000_setup_rctl(struct e1000_adapter *adapter);
static void e1000_clean_all_tx_rings(struct e1000_adapter *adapter);
static void e1000_clean_all_rx_rings(struct e1000_adapter *adapter);
static void e1000_clean_tx_ring(struct e1000_adapter *adapter,
                                struct e1000_tx_ring *tx_ring);
static void e1000_clean_rx_ring(struct e1000_adapter *adapter,
                                struct e1000_rx_ring *rx_ring);
static void e1000_set_rx_mode(struct net_device *netdev);
static void e1000_update_phy_info_task(struct work_struct *work);
static void e1000_watchdog(struct work_struct *work);
static void e1000_82547_tx_fifo_stall_task(struct work_struct *work);
static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
                                    struct net_device *netdev);
static struct net_device_stats *e1000_get_stats(struct net_device *netdev);
static int e1000_change_mtu(struct net_device *netdev, int new_mtu);
static int e1000_set_mac(struct net_device *netdev, void *p);
static irqreturn_t e1000_intr(int irq, void *data);
static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
                               struct e1000_tx_ring *tx_ring);
static int e1000_clean(struct napi_struct *napi, int budget);
static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
                               struct e1000_rx_ring *rx_ring,
                               int *work_done, int work_to_do);
static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
                                     struct e1000_rx_ring *rx_ring,
                                     int *work_done, int work_to_do);
static void e1000_alloc_dummy_rx_buffers(struct e1000_adapter *adapter,
                                         struct e1000_rx_ring *rx_ring,
                                         int cleaned_count)
{
}
static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
                                   struct e1000_rx_ring *rx_ring,
                                   int cleaned_count);
static void e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter,
                                         struct e1000_rx_ring *rx_ring,
                                         int cleaned_count);
static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
                           int cmd);
static void e1000_enter_82542_rst(struct e1000_adapter *adapter);
static void e1000_leave_82542_rst(struct e1000_adapter *adapter);
static void e1000_tx_timeout(struct net_device *dev);
static void e1000_reset_task(struct work_struct *work);
static void e1000_smartspeed(struct e1000_adapter *adapter);
static int e1000_82547_fifo_workaround(struct e1000_adapter *adapter,
                                       struct sk_buff *skb);

static bool e1000_vlan_used(struct e1000_adapter *adapter);
static void e1000_vlan_mode(struct net_device *netdev,
                            netdev_features_t features);
static void e1000_vlan_filter_on_off(struct e1000_adapter *adapter,
                                     bool filter_on);
static int e1000_vlan_rx_add_vid(struct net_device *netdev,
                                 __be16 proto, u16 vid);
static int e1000_vlan_rx_kill_vid(struct net_device *netdev,
                                  __be16 proto, u16 vid);
static void e1000_restore_vlan(struct e1000_adapter *adapter);

#ifdef CONFIG_PM
static int e1000_suspend(struct pci_dev *pdev, pm_message_t state);
static int e1000_resume(struct pci_dev *pdev);
#endif
static void e1000_shutdown(struct pci_dev *pdev);

#ifdef CONFIG_NET_POLL_CONTROLLER
/* for netdump / net console */
static void e1000_netpoll (struct net_device *netdev);
#endif

#define COPYBREAK_DEFAULT 256
static unsigned int copybreak __read_mostly = COPYBREAK_DEFAULT;
module_param(copybreak, uint, 0644);
MODULE_PARM_DESC(copybreak,
        "Maximum size of packet that is copied to a new buffer on receive");

static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
                                                pci_channel_state_t state);
static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev);
static void e1000_io_resume(struct pci_dev *pdev);

static const struct pci_error_handlers e1000_err_handler = {
        .error_detected = e1000_io_error_detected,
        .slot_reset = e1000_io_slot_reset,
        .resume = e1000_io_resume,
};

static struct pci_driver e1000_driver = {
        .name     = e1000_driver_name,
        .id_table = e1000_pci_tbl,
        .probe    = e1000_probe,
        .remove   = e1000_remove,
#ifdef CONFIG_PM
        /* Power Management Hooks */
        .suspend  = e1000_suspend,
        .resume   = e1000_resume,
#endif
        .shutdown = e1000_shutdown,
        .err_handler = &e1000_err_handler
};

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
static int debug = -1;
module_param(debug, int, 0);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");

/**
 * e1000_get_hw_dev - return device
 * used by hardware layer to print debugging information
 *
 **/
struct net_device *e1000_get_hw_dev(struct e1000_hw *hw)
{
        struct e1000_adapter *adapter = hw->back;
        return adapter->netdev;
}

/**
 * e1000_init_module - Driver Registration Routine
 *
 * e1000_init_module is the first routine called when the driver is
 * loaded. All it does is register with the PCI subsystem.
 **/
static int __init e1000_init_module(void)
{
        int ret;
        pr_info("%s - version %s\n", e1000_driver_string, e1000_driver_version);

        pr_info("%s\n", e1000_copyright);

        ret = pci_register_driver(&e1000_driver);
        if (copybreak != COPYBREAK_DEFAULT) {
                if (copybreak == 0)
                        pr_info("copybreak disabled\n");
                else
                        pr_info("copybreak enabled for "
                                   "packets <= %u bytes\n", copybreak);
        }
        return ret;
}

module_init(e1000_init_module);

/**
 * e1000_exit_module - Driver Exit Cleanup Routine
 *
 * e1000_exit_module is called just before the driver is removed
 * from memory.
 **/
static void __exit e1000_exit_module(void)
{
        pci_unregister_driver(&e1000_driver);
}

module_exit(e1000_exit_module);

static int e1000_request_irq(struct e1000_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        irq_handler_t handler = e1000_intr;
        int irq_flags = IRQF_SHARED;
        int err;

        err = request_irq(adapter->pdev->irq, handler, irq_flags, netdev->name,
                          netdev);
        if (err) {
                e_err(probe, "Unable to allocate interrupt Error: %d\n", err);
        }

        return err;
}

static void e1000_free_irq(struct e1000_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;

        free_irq(adapter->pdev->irq, netdev);
}

/**
 * e1000_irq_disable - Mask off interrupt generation on the NIC
 * @adapter: board private structure
 **/
static void e1000_irq_disable(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        ew32(IMC, ~0);
        E1000_WRITE_FLUSH();
        synchronize_irq(adapter->pdev->irq);
}

/**
 * e1000_irq_enable - Enable default interrupt generation settings
 * @adapter: board private structure
 **/
static void e1000_irq_enable(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        ew32(IMS, IMS_ENABLE_MASK);
        E1000_WRITE_FLUSH();
}

static void e1000_update_mng_vlan(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        u16 vid = hw->mng_cookie.vlan_id;
        u16 old_vid = adapter->mng_vlan_id;

        if (!e1000_vlan_used(adapter))
                return;

        if (!test_bit(vid, adapter->active_vlans)) {
                if (hw->mng_cookie.status &
                    E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) {
                        e1000_vlan_rx_add_vid(netdev, htons(ETH_P_8021Q), vid);
                        adapter->mng_vlan_id = vid;
                } else {
                        adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
                }
                if ((old_vid != (u16)E1000_MNG_VLAN_NONE) &&
                    (vid != old_vid) &&
                    !test_bit(old_vid, adapter->active_vlans))
                        e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
                                               old_vid);
        } else {
                adapter->mng_vlan_id = vid;
        }
}

static void e1000_init_manageability(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        if (adapter->en_mng_pt) {
                u32 manc = er32(MANC);

                /* disable hardware interception of ARP */
                manc &= ~(E1000_MANC_ARP_EN);

                ew32(MANC, manc);
        }
}

static void e1000_release_manageability(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        if (adapter->en_mng_pt) {
                u32 manc = er32(MANC);

                /* re-enable hardware interception of ARP */
                manc |= E1000_MANC_ARP_EN;

                ew32(MANC, manc);
        }
}

/**
 * e1000_configure - configure the hardware for RX and TX
 * @adapter = private board structure
 **/
static void e1000_configure(struct e1000_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        int i;

        e1000_set_rx_mode(netdev);

        e1000_restore_vlan(adapter);
        e1000_init_manageability(adapter);

        e1000_configure_tx(adapter);
        e1000_setup_rctl(adapter);
        e1000_configure_rx(adapter);
        /* call E1000_DESC_UNUSED which always leaves
         * at least 1 descriptor unused to make sure
         * next_to_use != next_to_clean
         */
        for (i = 0; i < adapter->num_rx_queues; i++) {
                struct e1000_rx_ring *ring = &adapter->rx_ring[i];
                adapter->alloc_rx_buf(adapter, ring,
                                      E1000_DESC_UNUSED(ring));
        }
}

int e1000_up(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        /* hardware has been reset, we need to reload some things */
        e1000_configure(adapter);

        clear_bit(__E1000_DOWN, &adapter->flags);

        napi_enable(&adapter->napi);

        e1000_irq_enable(adapter);

        netif_wake_queue(adapter->netdev);

        /* fire a link change interrupt to start the watchdog */
        ew32(ICS, E1000_ICS_LSC);
        return 0;
}

/**
 * e1000_power_up_phy - restore link in case the phy was powered down
 * @adapter: address of board private structure
 *
 * The phy may be powered down to save power and turn off link when the
 * driver is unloaded and wake on lan is not enabled (among others)
 * *** this routine MUST be followed by a call to e1000_reset ***
 **/
void e1000_power_up_phy(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        u16 mii_reg = 0;

        /* Just clear the power down bit to wake the phy back up */
        if (hw->media_type == e1000_media_type_copper) {
                /* according to the manual, the phy will retain its
                 * settings across a power-down/up cycle
                 */
                e1000_read_phy_reg(hw, PHY_CTRL, &mii_reg);
                mii_reg &= ~MII_CR_POWER_DOWN;
                e1000_write_phy_reg(hw, PHY_CTRL, mii_reg);
        }
}

static void e1000_power_down_phy(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;

        /* Power down the PHY so no link is implied when interface is down *
         * The PHY cannot be powered down if any of the following is true *
         * (a) WoL is enabled
         * (b) AMT is active
         * (c) SoL/IDER session is active
         */
        if (!adapter->wol && hw->mac_type >= e1000_82540 &&
           hw->media_type == e1000_media_type_copper) {
                u16 mii_reg = 0;

                switch (hw->mac_type) {
                case e1000_82540:
                case e1000_82545:
                case e1000_82545_rev_3:
                case e1000_82546:
                case e1000_ce4100:
                case e1000_82546_rev_3:
                case e1000_82541:
                case e1000_82541_rev_2:
                case e1000_82547:
                case e1000_82547_rev_2:
                        if (er32(MANC) & E1000_MANC_SMBUS_EN)
                                goto out;
                        break;
                default:
                        goto out;
                }
                e1000_read_phy_reg(hw, PHY_CTRL, &mii_reg);
                mii_reg |= MII_CR_POWER_DOWN;
                e1000_write_phy_reg(hw, PHY_CTRL, mii_reg);
                msleep(1);
        }
out:
        return;
}

static void e1000_down_and_stop(struct e1000_adapter *adapter)
{
        set_bit(__E1000_DOWN, &adapter->flags);

        cancel_delayed_work_sync(&adapter->watchdog_task);

        /*
         * Since the watchdog task can reschedule other tasks, we should cancel
         * it first, otherwise we can run into the situation when a work is
         * still running after the adapter has been turned down.
         */

        cancel_delayed_work_sync(&adapter->phy_info_task);
        cancel_delayed_work_sync(&adapter->fifo_stall_task);

        /* Only kill reset task if adapter is not resetting */
        if (!test_bit(__E1000_RESETTING, &adapter->flags))
                cancel_work_sync(&adapter->reset_task);
}

void e1000_down(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        u32 rctl, tctl;

        netif_carrier_off(netdev);

        /* disable receives in the hardware */
        rctl = er32(RCTL);
        ew32(RCTL, rctl & ~E1000_RCTL_EN);
        /* flush and sleep below */

        netif_tx_disable(netdev);

        /* disable transmits in the hardware */
        tctl = er32(TCTL);
        tctl &= ~E1000_TCTL_EN;
        ew32(TCTL, tctl);
        /* flush both disables and wait for them to finish */
        E1000_WRITE_FLUSH();
        msleep(10);

        napi_disable(&adapter->napi);

        e1000_irq_disable(adapter);

        /* Setting DOWN must be after irq_disable to prevent
         * a screaming interrupt.  Setting DOWN also prevents
         * tasks from rescheduling.
         */
        e1000_down_and_stop(adapter);

        adapter->link_speed = 0;
        adapter->link_duplex = 0;

        e1000_reset(adapter);
        e1000_clean_all_tx_rings(adapter);
        e1000_clean_all_rx_rings(adapter);
}

void e1000_reinit_locked(struct e1000_adapter *adapter)
{
        WARN_ON(in_interrupt());
        while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
                msleep(1);
        e1000_down(adapter);
        e1000_up(adapter);
        clear_bit(__E1000_RESETTING, &adapter->flags);
}

void e1000_reset(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        u32 pba = 0, tx_space, min_tx_space, min_rx_space;
        bool legacy_pba_adjust = false;
        u16 hwm;

        /* Repartition Pba for greater than 9k mtu
         * To take effect CTRL.RST is required.
         */

        switch (hw->mac_type) {
        case e1000_82542_rev2_0:
        case e1000_82542_rev2_1:
        case e1000_82543:
        case e1000_82544:
        case e1000_82540:
        case e1000_82541:
        case e1000_82541_rev_2:
                legacy_pba_adjust = true;
                pba = E1000_PBA_48K;
                break;
        case e1000_82545:
        case e1000_82545_rev_3:
        case e1000_82546:
        case e1000_ce4100:
        case e1000_82546_rev_3:
                pba = E1000_PBA_48K;
                break;
        case e1000_82547:
        case e1000_82547_rev_2:
                legacy_pba_adjust = true;
                pba = E1000_PBA_30K;
                break;
        case e1000_undefined:
        case e1000_num_macs:
                break;
        }

        if (legacy_pba_adjust) {
                if (hw->max_frame_size > E1000_RXBUFFER_8192)
                        pba -= 8; /* allocate more FIFO for Tx */

                if (hw->mac_type == e1000_82547) {
                        adapter->tx_fifo_head = 0;
                        adapter->tx_head_addr = pba << E1000_TX_HEAD_ADDR_SHIFT;
                        adapter->tx_fifo_size =
                                (E1000_PBA_40K - pba) << E1000_PBA_BYTES_SHIFT;
                        atomic_set(&adapter->tx_fifo_stall, 0);
                }
        } else if (hw->max_frame_size >  ETH_FRAME_LEN + ETH_FCS_LEN) {
                /* adjust PBA for jumbo frames */
                ew32(PBA, pba);

                /* To maintain wire speed transmits, the Tx FIFO should be
                 * large enough to accommodate two full transmit packets,
                 * rounded up to the next 1KB and expressed in KB.  Likewise,
                 * the Rx FIFO should be large enough to accommodate at least
                 * one full receive packet and is similarly rounded up and
                 * expressed in KB.
                 */
                pba = er32(PBA);
                /* upper 16 bits has Tx packet buffer allocation size in KB */
                tx_space = pba >> 16;
                /* lower 16 bits has Rx packet buffer allocation size in KB */
                pba &= 0xffff;
                /* the Tx fifo also stores 16 bytes of information about the Tx
                 * but don't include ethernet FCS because hardware appends it
                 */
                min_tx_space = (hw->max_frame_size +
                                sizeof(struct e1000_tx_desc) -
                                ETH_FCS_LEN) * 2;
                min_tx_space = ALIGN(min_tx_space, 1024);
                min_tx_space >>= 10;
                /* software strips receive CRC, so leave room for it */
                min_rx_space = hw->max_frame_size;
                min_rx_space = ALIGN(min_rx_space, 1024);
                min_rx_space >>= 10;

                /* If current Tx allocation is less than the min Tx FIFO size,
                 * and the min Tx FIFO size is less than the current Rx FIFO
                 * allocation, take space away from current Rx allocation
                 */
                if (tx_space < min_tx_space &&
                    ((min_tx_space - tx_space) < pba)) {
                        pba = pba - (min_tx_space - tx_space);

                        /* PCI/PCIx hardware has PBA alignment constraints */
                        switch (hw->mac_type) {
                        case e1000_82545 ... e1000_82546_rev_3:
                                pba &= ~(E1000_PBA_8K - 1);
                                break;
                        default:
                                break;
                        }

                        /* if short on Rx space, Rx wins and must trump Tx
                         * adjustment or use Early Receive if available
                         */
                        if (pba < min_rx_space)
                                pba = min_rx_space;
                }
        }

        ew32(PBA, pba);

        /* flow control settings:
         * The high water mark must be low enough to fit one full frame
         * (or the size used for early receive) above it in the Rx FIFO.
         * Set it to the lower of:
         * - 90% of the Rx FIFO size, and
         * - the full Rx FIFO size minus the early receive size (for parts
         *   with ERT support assuming ERT set to E1000_ERT_2048), or
         * - the full Rx FIFO size minus one full frame
         */
        hwm = min(((pba << 10) * 9 / 10),
                  ((pba << 10) - hw->max_frame_size));

        hw->fc_high_water = hwm & 0xFFF8;       /* 8-byte granularity */
        hw->fc_low_water = hw->fc_high_water - 8;
        hw->fc_pause_time = E1000_FC_PAUSE_TIME;
        hw->fc_send_xon = 1;
        hw->fc = hw->original_fc;

        /* Allow time for pending master requests to run */
        e1000_reset_hw(hw);
        if (hw->mac_type >= e1000_82544)
                ew32(WUC, 0);

        if (e1000_init_hw(hw))
                e_dev_err("Hardware Error\n");
        e1000_update_mng_vlan(adapter);

        /* if (adapter->hwflags & HWFLAGS_PHY_PWR_BIT) { */
        if (hw->mac_type >= e1000_82544 &&
            hw->autoneg == 1 &&
            hw->autoneg_advertised == ADVERTISE_1000_FULL) {
                u32 ctrl = er32(CTRL);
                /* clear phy power management bit if we are in gig only mode,
                 * which if enabled will attempt negotiation to 100Mb, which
                 * can cause a loss of link at power off or driver unload
                 */
                ctrl &= ~E1000_CTRL_SWDPIN3;
                ew32(CTRL, ctrl);
        }

        /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
        ew32(VET, ETHERNET_IEEE_VLAN_TYPE);

        e1000_reset_adaptive(hw);
        e1000_phy_get_info(hw, &adapter->phy_info);

        e1000_release_manageability(adapter);
}

/* Dump the eeprom for users having checksum issues */
static void e1000_dump_eeprom(struct e1000_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        struct ethtool_eeprom eeprom;
        const struct ethtool_ops *ops = netdev->ethtool_ops;
        u8 *data;
        int i;
        u16 csum_old, csum_new = 0;

        eeprom.len = ops->get_eeprom_len(netdev);
        eeprom.offset = 0;

        data = kmalloc(eeprom.len, GFP_KERNEL);
        if (!data)
                return;

        ops->get_eeprom(netdev, &eeprom, data);

        csum_old = (data[EEPROM_CHECKSUM_REG * 2]) +
                   (data[EEPROM_CHECKSUM_REG * 2 + 1] << 8);
        for (i = 0; i < EEPROM_CHECKSUM_REG * 2; i += 2)
                csum_new += data[i] + (data[i + 1] << 8);
        csum_new = EEPROM_SUM - csum_new;

        pr_err("/*********************/\n");
        pr_err("Current EEPROM Checksum : 0x%04x\n", csum_old);
        pr_err("Calculated              : 0x%04x\n", csum_new);

        pr_err("Offset    Values\n");
        pr_err("========  ======\n");
        print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, data, 128, 0);

        pr_err("Include this output when contacting your support provider.\n");
        pr_err("This is not a software error! Something bad happened to\n");
        pr_err("your hardware or EEPROM image. Ignoring this problem could\n");
        pr_err("result in further problems, possibly loss of data,\n");
        pr_err("corruption or system hangs!\n");
        pr_err("The MAC Address will be reset to 00:00:00:00:00:00,\n");
        pr_err("which is invalid and requires you to set the proper MAC\n");
        pr_err("address manually before continuing to enable this network\n");
        pr_err("device. Please inspect the EEPROM dump and report the\n");
        pr_err("issue to your hardware vendor or Intel Customer Support.\n");
        pr_err("/*********************/\n");

        kfree(data);
}

/**
 * e1000_is_need_ioport - determine if an adapter needs ioport resources or not
 * @pdev: PCI device information struct
 *
 * Return true if an adapter needs ioport resources
 **/
static int e1000_is_need_ioport(struct pci_dev *pdev)
{
        switch (pdev->device) {
        case E1000_DEV_ID_82540EM:
        case E1000_DEV_ID_82540EM_LOM:
        case E1000_DEV_ID_82540EP:
        case E1000_DEV_ID_82540EP_LOM:
        case E1000_DEV_ID_82540EP_LP:
        case E1000_DEV_ID_82541EI:
        case E1000_DEV_ID_82541EI_MOBILE:
        case E1000_DEV_ID_82541ER:
        case E1000_DEV_ID_82541ER_LOM:
        case E1000_DEV_ID_82541GI:
        case E1000_DEV_ID_82541GI_LF:
        case E1000_DEV_ID_82541GI_MOBILE:
        case E1000_DEV_ID_82544EI_COPPER:
        case E1000_DEV_ID_82544EI_FIBER:
        case E1000_DEV_ID_82544GC_COPPER:
        case E1000_DEV_ID_82544GC_LOM:
        case E1000_DEV_ID_82545EM_COPPER:
        case E1000_DEV_ID_82545EM_FIBER:
        case E1000_DEV_ID_82546EB_COPPER:
        case E1000_DEV_ID_82546EB_FIBER:
        case E1000_DEV_ID_82546EB_QUAD_COPPER:
                return true;
        default:
                return false;
        }
}

static netdev_features_t e1000_fix_features(struct net_device *netdev,
        netdev_features_t features)
{
        /* Since there is no support for separate Rx/Tx vlan accel
         * enable/disable make sure Tx flag is always in same state as Rx.
         */
        if (features & NETIF_F_HW_VLAN_CTAG_RX)
                features |= NETIF_F_HW_VLAN_CTAG_TX;
        else
                features &= ~NETIF_F_HW_VLAN_CTAG_TX;

        return features;
}

static int e1000_set_features(struct net_device *netdev,
        netdev_features_t features)
{
        struct e1000_adapter *adapter = netdev_priv(netdev);
        netdev_features_t changed = features ^ netdev->features;

        if (changed & NETIF_F_HW_VLAN_CTAG_RX)
                e1000_vlan_mode(netdev, features);

        if (!(changed & (NETIF_F_RXCSUM | NETIF_F_RXALL)))
                return 0;

        netdev->features = features;
        adapter->rx_csum = !!(features & NETIF_F_RXCSUM);

        if (netif_running(netdev))
                e1000_reinit_locked(adapter);
        else
                e1000_reset(adapter);

        return 0;
}

static const struct net_device_ops e1000_netdev_ops = {
        .ndo_open               = e1000_open,
        .ndo_stop               = e1000_close,
        .ndo_start_xmit         = e1000_xmit_frame,
        .ndo_get_stats          = e1000_get_stats,
        .ndo_set_rx_mode        = e1000_set_rx_mode,
        .ndo_set_mac_address    = e1000_set_mac,
        .ndo_tx_timeout         = e1000_tx_timeout,
        .ndo_change_mtu         = e1000_change_mtu,
        .ndo_do_ioctl           = e1000_ioctl,
        .ndo_validate_addr      = eth_validate_addr,
        .ndo_vlan_rx_add_vid    = e1000_vlan_rx_add_vid,
        .ndo_vlan_rx_kill_vid   = e1000_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
        .ndo_poll_controller    = e1000_netpoll,
#endif
        .ndo_fix_features       = e1000_fix_features,
        .ndo_set_features       = e1000_set_features,
};

/**
 * e1000_init_hw_struct - initialize members of hw struct
 * @adapter: board private struct
 * @hw: structure used by e1000_hw.c
 *
 * Factors out initialization of the e1000_hw struct to its own function
 * that can be called very early at init (just after struct allocation).
 * Fields are initialized based on PCI device information and
 * OS network device settings (MTU size).
 * Returns negative error codes if MAC type setup fails.
 */
static int e1000_init_hw_struct(struct e1000_adapter *adapter,
                                struct e1000_hw *hw)
{
        struct pci_dev *pdev = adapter->pdev;

        /* PCI config space info */
        hw->vendor_id = pdev->vendor;
        hw->device_id = pdev->device;
        hw->subsystem_vendor_id = pdev->subsystem_vendor;
        hw->subsystem_id = pdev->subsystem_device;
        hw->revision_id = pdev->revision;

        pci_read_config_word(pdev, PCI_COMMAND, &hw->pci_cmd_word);

        hw->max_frame_size = adapter->netdev->mtu +
                             ENET_HEADER_SIZE + ETHERNET_FCS_SIZE;
        hw->min_frame_size = MINIMUM_ETHERNET_FRAME_SIZE;

        /* identify the MAC */
        if (e1000_set_mac_type(hw)) {
                e_err(probe, "Unknown MAC Type\n");
                return -EIO;
        }

        switch (hw->mac_type) {
        default:
                break;
        case e1000_82541:
        case e1000_82547:
        case e1000_82541_rev_2:
        case e1000_82547_rev_2:
                hw->phy_init_script = 1;
                break;
        }

        e1000_set_media_type(hw);
        e1000_get_bus_info(hw);

        hw->wait_autoneg_complete = false;
        hw->tbi_compatibility_en = true;
        hw->adaptive_ifs = true;

        /* Copper options */

        if (hw->media_type == e1000_media_type_copper) {
                hw->mdix = AUTO_ALL_MODES;
                hw->disable_polarity_correction = false;
                hw->master_slave = E1000_MASTER_SLAVE;
        }

        return 0;
}

/**
 * e1000_probe - Device Initialization Routine
 * @pdev: PCI device information struct
 * @ent: entry in e1000_pci_tbl
 *
 * Returns 0 on success, negative on failure
 *
 * e1000_probe initializes an adapter identified by a pci_dev structure.
 * The OS initialization, configuring of the adapter private structure,
 * and a hardware reset occur.
 **/
static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
        struct net_device *netdev;
        struct e1000_adapter *adapter;
        struct e1000_hw *hw;

        static int cards_found;
        static int global_quad_port_a; /* global ksp3 port a indication */
        int i, err, pci_using_dac;
        u16 eeprom_data = 0;
        u16 tmp = 0;
        u16 eeprom_apme_mask = E1000_EEPROM_APME;
        int bars, need_ioport;

        /* do not allocate ioport bars when not needed */
        need_ioport = e1000_is_need_ioport(pdev);
        if (need_ioport) {
                bars = pci_select_bars(pdev, IORESOURCE_MEM | IORESOURCE_IO);
                err = pci_enable_device(pdev);
        } else {
                bars = pci_select_bars(pdev, IORESOURCE_MEM);
                err = pci_enable_device_mem(pdev);
        }
        if (err)
                return err;

        err = pci_request_selected_regions(pdev, bars, e1000_driver_name);
        if (err)
                goto err_pci_reg;

        pci_set_master(pdev);
        err = pci_save_state(pdev);
        if (err)
                goto err_alloc_etherdev;

        err = -ENOMEM;
        netdev = alloc_etherdev(sizeof(struct e1000_adapter));
        if (!netdev)
                goto err_alloc_etherdev;

        SET_NETDEV_DEV(netdev, &pdev->dev);

        pci_set_drvdata(pdev, netdev);
        adapter = netdev_priv(netdev);
        adapter->netdev = netdev;
        adapter->pdev = pdev;
        adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
        adapter->bars = bars;
        adapter->need_ioport = need_ioport;

        hw = &adapter->hw;
        hw->back = adapter;

        err = -EIO;
        hw->hw_addr = pci_ioremap_bar(pdev, BAR_0);
        if (!hw->hw_addr)
                goto err_ioremap;

        if (adapter->need_ioport) {
                for (i = BAR_1; i <= BAR_5; i++) {
                        if (pci_resource_len(pdev, i) == 0)

                                continue;
                        if (pci_resource_flags(pdev, i) & IORESOURCE_IO) {
                                hw->io_base = pci_resource_start(pdev, i);
                                break;
                        }
                }
        }

        /* make ready for any if (hw->...) below */
        err = e1000_init_hw_struct(adapter, hw);
        if (err)
                goto err_sw_init;

        /* there is a workaround being applied below that limits
         * 64-bit DMA addresses to 64-bit hardware.  There are some
         * 32-bit adapters that Tx hang when given 64-bit DMA addresses
         */
        pci_using_dac = 0;
        if ((hw->bus_type == e1000_bus_type_pcix) &&
            !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
                pci_using_dac = 1;
        } else {
                err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
                if (err) {
                        pr_err("No usable DMA config, aborting\n");
                        goto err_dma;
                }
        }

        netdev->netdev_ops = &e1000_netdev_ops;
        e1000_set_ethtool_ops(netdev);
        netdev->watchdog_timeo = 5 * HZ;
        netif_napi_add(netdev, &adapter->napi, e1000_clean, 64);

        strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);

        adapter->bd_number = cards_found;

        /* setup the private structure */

        err = e1000_sw_init(adapter);
        if (err)
                goto err_sw_init;

        err = -EIO;
        if (hw->mac_type == e1000_ce4100) {
                hw->ce4100_gbe_mdio_base_virt =
                                        ioremap(pci_resource_start(pdev, BAR_1),
                                                pci_resource_len(pdev, BAR_1));

                if (!hw->ce4100_gbe_mdio_base_virt)
                        goto err_mdio_ioremap;
        }

        if (hw->mac_type >= e1000_82543) {
                netdev->hw_features = NETIF_F_SG |
                                   NETIF_F_HW_CSUM |
                                   NETIF_F_HW_VLAN_CTAG_RX;
                netdev->features = NETIF_F_HW_VLAN_CTAG_TX |
                                   NETIF_F_HW_VLAN_CTAG_FILTER;
        }

        if ((hw->mac_type >= e1000_82544) &&
           (hw->mac_type != e1000_82547))
                netdev->hw_features |= NETIF_F_TSO;

        netdev->priv_flags |= IFF_SUPP_NOFCS;

        netdev->features |= netdev->hw_features;
        netdev->hw_features |= (NETIF_F_RXCSUM |
                                NETIF_F_RXALL |
                                NETIF_F_RXFCS);

        if (pci_using_dac) {
                netdev->features |= NETIF_F_HIGHDMA;
                netdev->vlan_features |= NETIF_F_HIGHDMA;
        }

        netdev->vlan_features |= (NETIF_F_TSO |
                                  NETIF_F_HW_CSUM |
                                  NETIF_F_SG);

        /* Do not set IFF_UNICAST_FLT for VMWare's 82545EM */
        if (hw->device_id != E1000_DEV_ID_82545EM_COPPER ||
            hw->subsystem_vendor_id != PCI_VENDOR_ID_VMWARE)
                netdev->priv_flags |= IFF_UNICAST_FLT;

        adapter->en_mng_pt = e1000_enable_mng_pass_thru(hw);

        /* initialize eeprom parameters */
        if (e1000_init_eeprom_params(hw)) {
                e_err(probe, "EEPROM initialization failed\n");
                goto err_eeprom;
        }

        /* before reading the EEPROM, reset the controller to
         * put the device in a known good starting state
         */

        e1000_reset_hw(hw);

        /* make sure the EEPROM is good */
        if (e1000_validate_eeprom_checksum(hw) < 0) {
                e_err(probe, "The EEPROM Checksum Is Not Valid\n");
                e1000_dump_eeprom(adapter);
                /* set MAC address to all zeroes to invalidate and temporary
                 * disable this device for the user. This blocks regular
                 * traffic while still permitting ethtool ioctls from reaching
                 * the hardware as well as allowing the user to run the
                 * interface after manually setting a hw addr using
                 * `ip set address`
                 */
                memset(hw->mac_addr, 0, netdev->addr_len);
        } else {
                /* copy the MAC address out of the EEPROM */
                if (e1000_read_mac_addr(hw))
                        e_err(probe, "EEPROM Read Error\n");
        }
        /* don't block initialization here due to bad MAC address */
        memcpy(netdev->dev_addr, hw->mac_addr, netdev->addr_len);

        if (!is_valid_ether_addr(netdev->dev_addr))
                e_err(probe, "Invalid MAC Address\n");


        INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog);
        INIT_DELAYED_WORK(&adapter->fifo_stall_task,
                          e1000_82547_tx_fifo_stall_task);
        INIT_DELAYED_WORK(&adapter->phy_info_task, e1000_update_phy_info_task);
        INIT_WORK(&adapter->reset_task, e1000_reset_task);

        e1000_check_options(adapter);

        /* Initial Wake on LAN setting
         * If APM wake is enabled in the EEPROM,
         * enable the ACPI Magic Packet filter
         */

        switch (hw->mac_type) {
        case e1000_82542_rev2_0:
        case e1000_82542_rev2_1:
        case e1000_82543:
                break;
        case e1000_82544:
                e1000_read_eeprom(hw,
                        EEPROM_INIT_CONTROL2_REG, 1, &eeprom_data);
                eeprom_apme_mask = E1000_EEPROM_82544_APM;
                break;
        case e1000_82546:
        case e1000_82546_rev_3:
                if (er32(STATUS) & E1000_STATUS_FUNC_1) {
                        e1000_read_eeprom(hw,
                                EEPROM_INIT_CONTROL3_PORT_B, 1, &eeprom_data);
                        break;
                }
                /* Fall Through */
        default:
                e1000_read_eeprom(hw,
                        EEPROM_INIT_CONTROL3_PORT_A, 1, &eeprom_data);
                break;
        }
        if (eeprom_data & eeprom_apme_mask)
                adapter->eeprom_wol |= E1000_WUFC_MAG;

        /* now that we have the eeprom settings, apply the special cases
         * where the eeprom may be wrong or the board simply won't support
         * wake on lan on a particular port
         */
        switch (pdev->device) {
        case E1000_DEV_ID_82546GB_PCIE:
                adapter->eeprom_wol = 0;
                break;
        case E1000_DEV_ID_82546EB_FIBER:
        case E1000_DEV_ID_82546GB_FIBER:
                /* Wake events only supported on port A for dual fiber
                 * regardless of eeprom setting
                 */
                if (er32(STATUS) & E1000_STATUS_FUNC_1)
                        adapter->eeprom_wol = 0;
                break;
        case E1000_DEV_ID_82546GB_QUAD_COPPER_KSP3:
                /* if quad port adapter, disable WoL on all but port A */
                if (global_quad_port_a != 0)
                        adapter->eeprom_wol = 0;
                else
                        adapter->quad_port_a = true;
                /* Reset for multiple quad port adapters */
                if (++global_quad_port_a == 4)
                        global_quad_port_a = 0;
                break;
        }

        /* initialize the wol settings based on the eeprom settings */
        adapter->wol = adapter->eeprom_wol;
        device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);

        /* Auto detect PHY address */
        if (hw->mac_type == e1000_ce4100) {
                for (i = 0; i < 32; i++) {
                        hw->phy_addr = i;
                        e1000_read_phy_reg(hw, PHY_ID2, &tmp);

                        if (tmp != 0 && tmp != 0xFF)
                                break;
                }

                if (i >= 32)
                        goto err_eeprom;
        }

        /* reset the hardware with the new settings */
        e1000_reset(adapter);

        strcpy(netdev->name, "eth%d");
        err = register_netdev(netdev);
        if (err)
                goto err_register;

        e1000_vlan_filter_on_off(adapter, false);

        /* print bus type/speed/width info */
        e_info(probe, "(PCI%s:%dMHz:%d-bit) %pM\n",
               ((hw->bus_type == e1000_bus_type_pcix) ? "-X" : ""),
               ((hw->bus_speed == e1000_bus_speed_133) ? 133 :
                (hw->bus_speed == e1000_bus_speed_120) ? 120 :
                (hw->bus_speed == e1000_bus_speed_100) ? 100 :
                (hw->bus_speed == e1000_bus_speed_66) ? 66 : 33),
               ((hw->bus_width == e1000_bus_width_64) ? 64 : 32),
               netdev->dev_addr);

        /* carrier off reporting is important to ethtool even BEFORE open */
        netif_carrier_off(netdev);

        e_info(probe, "Intel(R) PRO/1000 Network Connection\n");

        cards_found++;
        return 0;

err_register:
err_eeprom:
        e1000_phy_hw_reset(hw);

        if (hw->flash_address)
                iounmap(hw->flash_address);
        kfree(adapter->tx_ring);
        kfree(adapter->rx_ring);
err_dma:
err_sw_init:
err_mdio_ioremap:
        iounmap(hw->ce4100_gbe_mdio_base_virt);
        iounmap(hw->hw_addr);
err_ioremap:
        free_netdev(netdev);
err_alloc_etherdev:
        pci_release_selected_regions(pdev, bars);
err_pci_reg:
        pci_disable_device(pdev);
        return err;
}

/**
 * e1000_remove - Device Removal Routine
 * @pdev: PCI device information struct
 *
 * e1000_remove is called by the PCI subsystem to alert the driver
 * that it should release a PCI device. That could be caused by a
 * Hot-Plug event, or because the driver is going to be removed from
 * memory.
 **/
static void e1000_remove(struct pci_dev *pdev)
{
        struct net_device *netdev = pci_get_drvdata(pdev);
        struct e1000_adapter *adapter = netdev_priv(netdev);
        struct e1000_hw *hw = &adapter->hw;

        e1000_down_and_stop(adapter);
        e1000_release_manageability(adapter);

        unregister_netdev(netdev);

        e1000_phy_hw_reset(hw);

        kfree(adapter->tx_ring);
        kfree(adapter->rx_ring);

        if (hw->mac_type == e1000_ce4100)
                iounmap(hw->ce4100_gbe_mdio_base_virt);
        iounmap(hw->hw_addr);
        if (hw->flash_address)
                iounmap(hw->flash_address);
        pci_release_selected_regions(pdev, adapter->bars);

        free_netdev(netdev);

        pci_disable_device(pdev);
}

/**
 * e1000_sw_init - Initialize general software structures (struct e1000_adapter)
 * @adapter: board private structure to initialize
 *
 * e1000_sw_init initializes the Adapter private data structure.
 * e1000_init_hw_struct MUST be called before this function
 **/
static int e1000_sw_init(struct e1000_adapter *adapter)
{
        adapter->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE;

        adapter->num_tx_queues = 1;
        adapter->num_rx_queues = 1;

        if (e1000_alloc_queues(adapter)) {
                e_err(probe, "Unable to allocate memory for queues\n");
                return -ENOMEM;
        }

        /* Explicitly disable IRQ since the NIC can be in any state. */
        e1000_irq_disable(adapter);

        spin_lock_init(&adapter->stats_lock);

        set_bit(__E1000_DOWN, &adapter->flags);

        return 0;
}

/**
 * e1000_alloc_queues - Allocate memory for all rings
 * @adapter: board private structure to initialize
 *
 * We allocate one ring per queue at run-time since we don't know the
 * number of queues at compile-time.
 **/
static int e1000_alloc_queues(struct e1000_adapter *adapter)
{
        adapter->tx_ring = kcalloc(adapter->num_tx_queues,
                                   sizeof(struct e1000_tx_ring), GFP_KERNEL);
        if (!adapter->tx_ring)
                return -ENOMEM;

        adapter->rx_ring = kcalloc(adapter->num_rx_queues,
                                   sizeof(struct e1000_rx_ring), GFP_KERNEL);
        if (!adapter->rx_ring) {
                kfree(adapter->tx_ring);
                return -ENOMEM;
        }

        return E1000_SUCCESS;
}

/**
 * e1000_open - Called when a network interface is made active
 * @netdev: network interface device structure
 *
 * Returns 0 on success, negative value on failure
 *
 * The open entry point is called when a network interface is made
 * active by the system (IFF_UP).  At this point all resources needed
 * for transmit and receive operations are allocated, the interrupt
 * handler is registered with the OS, the watchdog task is started,
 * and the stack is notified that the interface is ready.
 **/
static int e1000_open(struct net_device *netdev)
{
        struct e1000_adapter *adapter = netdev_priv(netdev);
        struct e1000_hw *hw = &adapter->hw;
        int err;

        /* disallow open during test */
        if (test_bit(__E1000_TESTING, &adapter->flags))
                return -EBUSY;

        netif_carrier_off(netdev);

        /* allocate transmit descriptors */
        err = e1000_setup_all_tx_resources(adapter);
        if (err)
                goto err_setup_tx;

        /* allocate receive descriptors */
        err = e1000_setup_all_rx_resources(adapter);
        if (err)
                goto err_setup_rx;

        e1000_power_up_phy(adapter);

        adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
        if ((hw->mng_cookie.status &
                          E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT)) {
                e1000_update_mng_vlan(adapter);
        }

        /* before we allocate an interrupt, we must be ready to handle it.
         * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
         * as soon as we call pci_request_irq, so we have to setup our
         * clean_rx handler before we do so.
         */
        e1000_configure(adapter);

        err = e1000_request_irq(adapter);
        if (err)
                goto err_req_irq;

        /* From here on the code is the same as e1000_up() */
        clear_bit(__E1000_DOWN, &adapter->flags);

        napi_enable(&adapter->napi);

        e1000_irq_enable(adapter);

        netif_start_queue(netdev);

        /* fire a link status change interrupt to start the watchdog */
        ew32(ICS, E1000_ICS_LSC);

        return E1000_SUCCESS;

err_req_irq:
        e1000_power_down_phy(adapter);
        e1000_free_all_rx_resources(adapter);
err_setup_rx:
        e1000_free_all_tx_resources(adapter);
err_setup_tx:
        e1000_reset(adapter);

        return err;
}

/**
 * e1000_close - Disables a network interface
 * @netdev: network interface device structure
 *
 * Returns 0, this is not allowed to fail
 *
 * The close entry point is called when an interface is de-activated
 * by the OS.  The hardware is still under the drivers control, but
 * needs to be disabled.  A global MAC reset is issued to stop the
 * hardware, and all transmit and receive resources are freed.
 **/
static int e1000_close(struct net_device *netdev)
{
        struct e1000_adapter *adapter = netdev_priv(netdev);
        struct e1000_hw *hw = &adapter->hw;
        int count = E1000_CHECK_RESET_COUNT;

        while (test_bit(__E1000_RESETTING, &adapter->flags) && count--)
                usleep_range(10000, 20000);

        WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
        e1000_down(adapter);
        e1000_power_down_phy(adapter);
        e1000_free_irq(adapter);

        e1000_free_all_tx_resources(adapter);
        e1000_free_all_rx_resources(adapter);

        /* kill manageability vlan ID if supported, but not if a vlan with
         * the same ID is registered on the host OS (let 8021q kill it)
         */
        if ((hw->mng_cookie.status &
             E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) &&
            !test_bit(adapter->mng_vlan_id, adapter->active_vlans)) {
                e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
                                       adapter->mng_vlan_id);
        }

        return 0;
}

/**
 * e1000_check_64k_bound - check that memory doesn't cross 64kB boundary
 * @adapter: address of board private structure
 * @start: address of beginning of memory
 * @len: length of memory
 **/
static bool e1000_check_64k_bound(struct e1000_adapter *adapter, void *start,
                                  unsigned long len)
{
        struct e1000_hw *hw = &adapter->hw;
        unsigned long begin = (unsigned long)start;
        unsigned long end = begin + len;

        /* First rev 82545 and 82546 need to not allow any memory
         * write location to cross 64k boundary due to errata 23
         */
        if (hw->mac_type == e1000_82545 ||
            hw->mac_type == e1000_ce4100 ||
            hw->mac_type == e1000_82546) {
                return ((begin ^ (end - 1)) >> 16) != 0 ? false : true;
        }

        return true;
}

/**
 * e1000_setup_tx_resources - allocate Tx resources (Descriptors)
 * @adapter: board private structure
 * @txdr:    tx descriptor ring (for a specific queue) to setup
 *
 * Return 0 on success, negative on failure
 **/
static int e1000_setup_tx_resources(struct e1000_adapter *adapter,
                                    struct e1000_tx_ring *txdr)
{
        struct pci_dev *pdev = adapter->pdev;
        int size;

        size = sizeof(struct e1000_tx_buffer) * txdr->count;
        txdr->buffer_info = vzalloc(size);
        if (!txdr->buffer_info)
                return -ENOMEM;

        /* round up to nearest 4K */

        txdr->size = txdr->count * sizeof(struct e1000_tx_desc);
        txdr->size = ALIGN(txdr->size, 4096);

        txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
                                        GFP_KERNEL);
        if (!txdr->desc) {
setup_tx_desc_die:
                vfree(txdr->buffer_info);
                return -ENOMEM;
        }

        /* Fix for errata 23, can't cross 64kB boundary */
        if (!e1000_check_64k_bound(adapter, txdr->desc, txdr->size)) {
                void *olddesc = txdr->desc;
                dma_addr_t olddma = txdr->dma;
                e_err(tx_err, "txdr align check failed: %u bytes at %p\n",
                      txdr->size, txdr->desc);
                /* Try again, without freeing the previous */
                txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size,
                                                &txdr->dma, GFP_KERNEL);
                /* Failed allocation, critical failure */
                if (!txdr->desc) {
                        dma_free_coherent(&pdev->dev, txdr->size, olddesc,
                                          olddma);
                        goto setup_tx_desc_die;
                }

                if (!e1000_check_64k_bound(adapter, txdr->desc, txdr->size)) {
                        /* give up */
                        dma_free_coherent(&pdev->dev, txdr->size, txdr->desc,
                                          txdr->dma);
                        dma_free_coherent(&pdev->dev, txdr->size, olddesc,
                                          olddma);
                        e_err(probe, "Unable to allocate aligned memory "
                              "for the transmit descriptor ring\n");
                        vfree(txdr->buffer_info);
                        return -ENOMEM;
                } else {
                        /* Free old allocation, new allocation was successful */
                        dma_free_coherent(&pdev->dev, txdr->size, olddesc,
                                          olddma);
                }
        }
        memset(txdr->desc, 0, txdr->size);

        txdr->next_to_use = 0;
        txdr->next_to_clean = 0;

        return 0;
}

/**
 * e1000_setup_all_tx_resources - wrapper to allocate Tx resources
 *                                (Descriptors) for all queues
 * @adapter: board private structure
 *
 * Return 0 on success, negative on failure
 **/
int e1000_setup_all_tx_resources(struct e1000_adapter *adapter)
{
        int i, err = 0;

        for (i = 0; i < adapter->num_tx_queues; i++) {
                err = e1000_setup_tx_resources(adapter, &adapter->tx_ring[i]);
                if (err) {
                        e_err(probe, "Allocation for Tx Queue %u failed\n", i);
                        for (i-- ; i >= 0; i--)
                                e1000_free_tx_resources(adapter,
                                                        &adapter->tx_ring[i]);
                        break;
                }
        }

        return err;
}

/**
 * e1000_configure_tx - Configure 8254x Transmit Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Tx unit of the MAC after a reset.
 **/
static void e1000_configure_tx(struct e1000_adapter *adapter)
{
        u64 tdba;
        struct e1000_hw *hw = &adapter->hw;
        u32 tdlen, tctl, tipg;
        u32 ipgr1, ipgr2;

        /* Setup the HW Tx Head and Tail descriptor pointers */

        switch (adapter->num_tx_queues) {
        case 1:
        default:
                tdba = adapter->tx_ring[0].dma;
                tdlen = adapter->tx_ring[0].count *
                        sizeof(struct e1000_tx_desc);
                ew32(TDLEN, tdlen);
                ew32(TDBAH, (tdba >> 32));
                ew32(TDBAL, (tdba & 0x00000000ffffffffULL));
                ew32(TDT, 0);
                ew32(TDH, 0);
                adapter->tx_ring[0].tdh = ((hw->mac_type >= e1000_82543) ?
                                           E1000_TDH : E1000_82542_TDH);
                adapter->tx_ring[0].tdt = ((hw->mac_type >= e1000_82543) ?
                                           E1000_TDT : E1000_82542_TDT);
                break;
        }

        /* Set the default values for the Tx Inter Packet Gap timer */
        if ((hw->media_type == e1000_media_type_fiber ||
             hw->media_type == e1000_media_type_internal_serdes))
                tipg = DEFAULT_82543_TIPG_IPGT_FIBER;
        else
                tipg = DEFAULT_82543_TIPG_IPGT_COPPER;

        switch (hw->mac_type) {
        case e1000_82542_rev2_0:
        case e1000_82542_rev2_1:
                tipg = DEFAULT_82542_TIPG_IPGT;
                ipgr1 = DEFAULT_82542_TIPG_IPGR1;
                ipgr2 = DEFAULT_82542_TIPG_IPGR2;
                break;
        default:
                ipgr1 = DEFAULT_82543_TIPG_IPGR1;
                ipgr2 = DEFAULT_82543_TIPG_IPGR2;
                break;
        }
        tipg |= ipgr1 << E1000_TIPG_IPGR1_SHIFT;
        tipg |= ipgr2 << E1000_TIPG_IPGR2_SHIFT;
        ew32(TIPG, tipg);

        /* Set the Tx Interrupt Delay register */

        ew32(TIDV, adapter->tx_int_delay);
        if (hw->mac_type >= e1000_82540)
                ew32(TADV, adapter->tx_abs_int_delay);

        /* Program the Transmit Control Register */

        tctl = er32(TCTL);
        tctl &= ~E1000_TCTL_CT;
        tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC |
                (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT);

        e1000_config_collision_dist(hw);

        /* Setup Transmit Descriptor Settings for eop descriptor */
        adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_IFCS;

        /* only set IDE if we are delaying interrupts using the timers */
        if (adapter->tx_int_delay)
                adapter->txd_cmd |= E1000_TXD_CMD_IDE;

        if (hw->mac_type < e1000_82543)
                adapter->txd_cmd |= E1000_TXD_CMD_RPS;
        else
                adapter->txd_cmd |= E1000_TXD_CMD_RS;

        /* Cache if we're 82544 running in PCI-X because we'll
         * need this to apply a workaround later in the send path.
         */
        if (hw->mac_type == e1000_82544 &&
            hw->bus_type == e1000_bus_type_pcix)
                adapter->pcix_82544 = true;

        ew32(TCTL, tctl);

}

/**
 * e1000_setup_rx_resources - allocate Rx resources (Descriptors)
 * @adapter: board private structure
 * @rxdr:    rx descriptor ring (for a specific queue) to setup
 *
 * Returns 0 on success, negative on failure
 **/
static int e1000_setup_rx_resources(struct e1000_adapter *adapter,
                                    struct e1000_rx_ring *rxdr)
{
        struct pci_dev *pdev = adapter->pdev;
        int size, desc_len;

        size = sizeof(struct e1000_rx_buffer) * rxdr->count;
        rxdr->buffer_info = vzalloc(size);
        if (!rxdr->buffer_info)
                return -ENOMEM;

        desc_len = sizeof(struct e1000_rx_desc);

        /* Round up to nearest 4K */

        rxdr->size = rxdr->count * desc_len;
        rxdr->size = ALIGN(rxdr->size, 4096);

        rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
                                        GFP_KERNEL);
        if (!rxdr->desc) {
setup_rx_desc_die:
                vfree(rxdr->buffer_info);
                return -ENOMEM;
        }

        /* Fix for errata 23, can't cross 64kB boundary */
        if (!e1000_check_64k_bound(adapter, rxdr->desc, rxdr->size)) {
                void *olddesc = rxdr->desc;
                dma_addr_t olddma = rxdr->dma;
                e_err(rx_err, "rxdr align check failed: %u bytes at %p\n",
                      rxdr->size, rxdr->desc);
                /* Try again, without freeing the previous */
                rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size,
                                                &rxdr->dma, GFP_KERNEL);
                /* Failed allocation, critical failure */
                if (!rxdr->desc) {
                        dma_free_coherent(&pdev->dev, rxdr->size, olddesc,
                                          olddma);
                        goto setup_rx_desc_die;
                }

                if (!e1000_check_64k_bound(adapter, rxdr->desc, rxdr->size)) {
                        /* give up */
                        dma_free_coherent(&pdev->dev, rxdr->size, rxdr->desc,
                                          rxdr->dma);
                        dma_free_coherent(&pdev->dev, rxdr->size, olddesc,
                                          olddma);
                        e_err(probe, "Unable to allocate aligned memory for "
                              "the Rx descriptor ring\n");
                        goto setup_rx_desc_die;
                } else {
                        /* Free old allocation, new allocation was successful */
                        dma_free_coherent(&pdev->dev, rxdr->size, olddesc,
                                          olddma);
                }
        }
        memset(rxdr->desc, 0, rxdr->size);

        rxdr->next_to_clean = 0;
        rxdr->next_to_use = 0;
        rxdr->rx_skb_top = NULL;

        return 0;
}

/**
 * e1000_setup_all_rx_resources - wrapper to allocate Rx resources
 *                                (Descriptors) for all queues
 * @adapter: board private structure
 *
 * Return 0 on success, negative on failure
 **/
int e1000_setup_all_rx_resources(struct e1000_adapter *adapter)
{
        int i, err = 0;

        for (i = 0; i < adapter->num_rx_queues; i++) {
                err = e1000_setup_rx_resources(adapter, &adapter->rx_ring[i]);
                if (err) {
                        e_err(probe, "Allocation for Rx Queue %u failed\n", i);
                        for (i-- ; i >= 0; i--)
                                e1000_free_rx_resources(adapter,
                                                        &adapter->rx_ring[i]);
                        break;
                }
        }

        return err;
}

/**
 * e1000_setup_rctl - configure the receive control registers
 * @adapter: Board private structure
 **/
static void e1000_setup_rctl(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        u32 rctl;

        rctl = er32(RCTL);

        rctl &= ~(3 << E1000_RCTL_MO_SHIFT);

        rctl |= E1000_RCTL_BAM | E1000_RCTL_LBM_NO |
                E1000_RCTL_RDMTS_HALF |
                (hw->mc_filter_type << E1000_RCTL_MO_SHIFT);

        if (hw->tbi_compatibility_on == 1)
                rctl |= E1000_RCTL_SBP;
        else
                rctl &= ~E1000_RCTL_SBP;

        if (adapter->netdev->mtu <= ETH_DATA_LEN)
                rctl &= ~E1000_RCTL_LPE;
        else
                rctl |= E1000_RCTL_LPE;

        /* Setup buffer sizes */
        rctl &= ~E1000_RCTL_SZ_4096;
        rctl |= E1000_RCTL_BSEX;
        switch (adapter->rx_buffer_len) {
        case E1000_RXBUFFER_2048:
        default:
                rctl |= E1000_RCTL_SZ_2048;
                rctl &= ~E1000_RCTL_BSEX;
                break;
        case E1000_RXBUFFER_4096:
                rctl |= E1000_RCTL_SZ_4096;
                break;
        case E1000_RXBUFFER_8192:
                rctl |= E1000_RCTL_SZ_8192;
                break;
        case E1000_RXBUFFER_16384:
                rctl |= E1000_RCTL_SZ_16384;
                break;
        }

        /* This is useful for sniffing bad packets. */
        if (adapter->netdev->features & NETIF_F_RXALL) {
                /* UPE and MPE will be handled by normal PROMISC logic
                 * in e1000e_set_rx_mode
                 */
                rctl |= (E1000_RCTL_SBP | /* Receive bad packets */
                         E1000_RCTL_BAM | /* RX All Bcast Pkts */
                         E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */

                rctl &= ~(E1000_RCTL_VFE | /* Disable VLAN filter */
                          E1000_RCTL_DPF | /* Allow filtered pause */
                          E1000_RCTL_CFIEN); /* Dis VLAN CFIEN Filter */
                /* Do not mess with E1000_CTRL_VME, it affects transmit as well,
                 * and that breaks VLANs.
                 */
        }

        ew32(RCTL, rctl);
}

/**
 * e1000_configure_rx - Configure 8254x Receive Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Rx unit of the MAC after a reset.
 **/
static void e1000_configure_rx(struct e1000_adapter *adapter)
{
        u64 rdba;
        struct e1000_hw *hw = &adapter->hw;
        u32 rdlen, rctl, rxcsum;

        if (adapter->netdev->mtu > ETH_DATA_LEN) {
                rdlen = adapter->rx_ring[0].count *
                        sizeof(struct e1000_rx_desc);
                adapter->clean_rx = e1000_clean_jumbo_rx_irq;
                adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers;
        } else {
                rdlen = adapter->rx_ring[0].count *
                        sizeof(struct e1000_rx_desc);
                adapter->clean_rx = e1000_clean_rx_irq;
                adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
        }

        /* disable receives while setting up the descriptors */
        rctl = er32(RCTL);
        ew32(RCTL, rctl & ~E1000_RCTL_EN);

        /* set the Receive Delay Timer Register */
        ew32(RDTR, adapter->rx_int_delay);

        if (hw->mac_type >= e1000_82540) {
                ew32(RADV, adapter->rx_abs_int_delay);
                if (adapter->itr_setting != 0)
                        ew32(ITR, 1000000000 / (adapter->itr * 256));
        }

        /* Setup the HW Rx Head and Tail Descriptor Pointers and
         * the Base and Length of the Rx Descriptor Ring
         */
        switch (adapter->num_rx_queues) {
        case 1:
        default:
                rdba = adapter->rx_ring[0].dma;
                ew32(RDLEN, rdlen);
                ew32(RDBAH, (rdba >> 32));
                ew32(RDBAL, (rdba & 0x00000000ffffffffULL));
                ew32(RDT, 0);
                ew32(RDH, 0);
                adapter->rx_ring[0].rdh = ((hw->mac_type >= e1000_82543) ?
                                           E1000_RDH : E1000_82542_RDH);
                adapter->rx_ring[0].rdt = ((hw->mac_type >= e1000_82543) ?
                                           E1000_RDT : E1000_82542_RDT);
                break;
        }

        /* Enable 82543 Receive Checksum Offload for TCP and UDP */
        if (hw->mac_type >= e1000_82543) {
                rxcsum = er32(RXCSUM);
                if (adapter->rx_csum)
                        rxcsum |= E1000_RXCSUM_TUOFL;
                else
                        /* don't need to clear IPPCSE as it defaults to 0 */
                        rxcsum &= ~E1000_RXCSUM_TUOFL;
                ew32(RXCSUM, rxcsum);
        }

        /* Enable Receives */
        ew32(RCTL, rctl | E1000_RCTL_EN);
}

/**
 * e1000_free_tx_resources - Free Tx Resources per Queue
 * @adapter: board private structure
 * @tx_ring: Tx descriptor ring for a specific queue
 *
 * Free all transmit software resources
 **/
static void e1000_free_tx_resources(struct e1000_adapter *adapter,
                                    struct e1000_tx_ring *tx_ring)
{
        struct pci_dev *pdev = adapter->pdev;

        e1000_clean_tx_ring(adapter, tx_ring);

        vfree(tx_ring->buffer_info);
        tx_ring->buffer_info = NULL;

        dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
                          tx_ring->dma);

        tx_ring->desc = NULL;
}

/**
 * e1000_free_all_tx_resources - Free Tx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all transmit software resources
 **/
void e1000_free_all_tx_resources(struct e1000_adapter *adapter)
{
        int i;

        for (i = 0; i < adapter->num_tx_queues; i++)
                e1000_free_tx_resources(adapter, &adapter->tx_ring[i]);
}

static void
e1000_unmap_and_free_tx_resource(struct e1000_adapter *adapter,
                                 struct e1000_tx_buffer *buffer_info)
{
        if (buffer_info->dma) {
                if (buffer_info->mapped_as_page)
                        dma_unmap_page(&adapter->pdev->dev, buffer_info->dma,
                                       buffer_info->length, DMA_TO_DEVICE);
                else
                        dma_unmap_single(&adapter->pdev->dev, buffer_info->dma,
                                         buffer_info->length,
                                         DMA_TO_DEVICE);
                buffer_info->dma = 0;
        }
        if (buffer_info->skb) {
                dev_kfree_skb_any(buffer_info->skb);
                buffer_info->skb = NULL;
        }
        buffer_info->time_stamp = 0;
        /* buffer_info must be completely set up in the transmit path */
}

/**
 * e1000_clean_tx_ring - Free Tx Buffers
 * @adapter: board private structure
 * @tx_ring: ring to be cleaned
 **/
static void e1000_clean_tx_ring(struct e1000_adapter *adapter,
                                struct e1000_tx_ring *tx_ring)
{
        struct e1000_hw *hw = &adapter->hw;
        struct e1000_tx_buffer *buffer_info;
        unsigned long size;
        unsigned int i;

        /* Free all the Tx ring sk_buffs */

        for (i = 0; i < tx_ring->count; i++) {
                buffer_info = &tx_ring->buffer_info[i];
                e1000_unmap_and_free_tx_resource(adapter, buffer_info);
        }

        netdev_reset_queue(adapter->netdev);

        size = sizeof(struct e1000_tx_buffer) * tx_ring->count;
        memset(tx_ring->buffer_info, 0, size);

        /* Zero out the descriptor ring */

        memset(tx_ring->desc, 0, tx_ring->size);

        tx_ring->next_to_use = 0;
        tx_ring->next_to_clean = 0;
        tx_ring->last_tx_tso = false;

        writel(0, hw->hw_addr + tx_ring->tdh);
        writel(0, hw->hw_addr + tx_ring->tdt);
}

/**
 * e1000_clean_all_tx_rings - Free Tx Buffers for all queues
 * @adapter: board private structure
 **/
static void e1000_clean_all_tx_rings(struct e1000_adapter *adapter)
{
        int i;

        for (i = 0; i < adapter->num_tx_queues; i++)
                e1000_clean_tx_ring(adapter, &adapter->tx_ring[i]);
}

/**
 * e1000_free_rx_resources - Free Rx Resources
 * @adapter: board private structure
 * @rx_ring: ring to clean the resources from
 *
 * Free all receive software resources
 **/
static void e1000_free_rx_resources(struct e1000_adapter *adapter,
                                    struct e1000_rx_ring *rx_ring)
{
        struct pci_dev *pdev = adapter->pdev;

        e1000_clean_rx_ring(adapter, rx_ring);

        vfree(rx_ring->buffer_info);
        rx_ring->buffer_info = NULL;

        dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
                          rx_ring->dma);

        rx_ring->desc = NULL;
}

/**
 * e1000_free_all_rx_resources - Free Rx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all receive software resources
 **/
void e1000_free_all_rx_resources(struct e1000_adapter *adapter)
{
        int i;

        for (i = 0; i < adapter->num_rx_queues; i++)
                e1000_free_rx_resources(adapter, &adapter->rx_ring[i]);
}

#define E1000_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN)
static unsigned int e1000_frag_len(const struct e1000_adapter *a)
{
        return SKB_DATA_ALIGN(a->rx_buffer_len + E1000_HEADROOM) +
                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
}

static void *e1000_alloc_frag(const struct e1000_adapter *a)
{
        unsigned int len = e1000_frag_len(a);
        u8 *data = netdev_alloc_frag(len);

        if (likely(data))
                data += E1000_HEADROOM;
        return data;
}

/**
 * e1000_clean_rx_ring - Free Rx Buffers per Queue
 * @adapter: board private structure
 * @rx_ring: ring to free buffers from
 **/
static void e1000_clean_rx_ring(struct e1000_adapter *adapter,
                                struct e1000_rx_ring *rx_ring)
{
        struct e1000_hw *hw = &adapter->hw;
        struct e1000_rx_buffer *buffer_info;
        struct pci_dev *pdev = adapter->pdev;
        unsigned long size;
        unsigned int i;

        /* Free all the Rx netfrags */
        for (i = 0; i < rx_ring->count; i++) {
                buffer_info = &rx_ring->buffer_info[i];
                if (adapter->clean_rx == e1000_clean_rx_irq) {
                        if (buffer_info->dma)
                                dma_unmap_single(&pdev->dev, buffer_info->dma,
                                                 adapter->rx_buffer_len,
                                                 DMA_FROM_DEVICE);
                        if (buffer_info->rxbuf.data) {
                                skb_free_frag(buffer_info->rxbuf.data);
                                buffer_info->rxbuf.data = NULL;
                        }
                } else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq) {
                        if (buffer_info->dma)
                                dma_unmap_page(&pdev->dev, buffer_info->dma,
                                               adapter->rx_buffer_len,
                                               DMA_FROM_DEVICE);
                        if (buffer_info->rxbuf.page) {
                                put_page(buffer_info->rxbuf.page);
                                buffer_info->rxbuf.page = NULL;
                        }
                }

                buffer_info->dma = 0;
        }

        /* there also may be some cached data from a chained receive */
        napi_free_frags(&adapter->napi);
        rx_ring->rx_skb_top = NULL;

        size = sizeof(struct e1000_rx_buffer) * rx_ring->count;
        memset(rx_ring->buffer_info, 0, size);

        /* Zero out the descriptor ring */
        memset(rx_ring->desc, 0, rx_ring->size);

        rx_ring->next_to_clean = 0;
        rx_ring->next_to_use = 0;

        writel(0, hw->hw_addr + rx_ring->rdh);
        writel(0, hw->hw_addr + rx_ring->rdt);
}

/**
 * e1000_clean_all_rx_rings - Free Rx Buffers for all queues
 * @adapter: board private structure
 **/
static void e1000_clean_all_rx_rings(struct e1000_adapter *adapter)
{
        int i;

        for (i = 0; i < adapter->num_rx_queues; i++)
                e1000_clean_rx_ring(adapter, &adapter->rx_ring[i]);
}

/* The 82542 2.0 (revision 2) needs to have the receive unit in reset
 * and memory write and invalidate disabled for certain operations
 */
static void e1000_enter_82542_rst(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        u32 rctl;

        e1000_pci_clear_mwi(hw);

        rctl = er32(RCTL);
        rctl |= E1000_RCTL_RST;
        ew32(RCTL, rctl);
        E1000_WRITE_FLUSH();
        mdelay(5);

        if (netif_running(netdev))
                e1000_clean_all_rx_rings(adapter);
}

static void e1000_leave_82542_rst(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        u32 rctl;

        rctl = er32(RCTL);
        rctl &= ~E1000_RCTL_RST;
        ew32(RCTL, rctl);
        E1000_WRITE_FLUSH();
        mdelay(5);

        if (hw->pci_cmd_word & PCI_COMMAND_INVALIDATE)
                e1000_pci_set_mwi(hw);

        if (netif_running(netdev)) {
                /* No need to loop, because 82542 supports only 1 queue */
                struct e1000_rx_ring *ring = &adapter->rx_ring[0];
                e1000_configure_rx(adapter);
                adapter->alloc_rx_buf(adapter, ring, E1000_DESC_UNUSED(ring));
        }
}

/**
 * e1000_set_mac - Change the Ethernet Address of the NIC
 * @netdev: network interface device structure
 * @p: pointer to an address structure
 *
 * Returns 0 on success, negative on failure
 **/
static int e1000_set_mac(struct net_device *netdev, void *p)
{
        struct e1000_adapter *adapter = netdev_priv(netdev);
        struct e1000_hw *hw = &adapter->hw;
        struct sockaddr *addr = p;

        if (!is_valid_ether_addr(addr->sa_data))
                return -EADDRNOTAVAIL;

        /* 82542 2.0 needs to be in reset to write receive address registers */

        if (hw->mac_type == e1000_82542_rev2_0)
                e1000_enter_82542_rst(adapter);

        memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
        memcpy(hw->mac_addr, addr->sa_data, netdev->addr_len);

        e1000_rar_set(hw, hw->mac_addr, 0);

        if (hw->mac_type == e1000_82542_rev2_0)
                e1000_leave_82542_rst(adapter);

        return 0;
}

/**
 * e1000_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
 * @netdev: network interface device structure
 *
 * The set_rx_mode entry point is called whenever the unicast or multicast
 * address lists or the network interface flags are updated. This routine is
 * responsible for configuring the hardware for proper unicast, multicast,
 * promiscuous mode, and all-multi behavior.
 **/
static void e1000_set_rx_mode(struct net_device *netdev)
{
        struct e1000_adapter *adapter = netdev_priv(netdev);
        struct e1000_hw *hw = &adapter->hw;
        struct netdev_hw_addr *ha;
        bool use_uc = false;
        u32 rctl;
        u32 hash_value;
        int i, rar_entries = E1000_RAR_ENTRIES;
        int mta_reg_count = E1000_NUM_MTA_REGISTERS;
        u32 *mcarray = kcalloc(mta_reg_count, sizeof(u32), GFP_ATOMIC);

        if (!mcarray)
                return;

        /* Check for Promiscuous and All Multicast modes */

        rctl = er32(RCTL);

        if (netdev->flags & IFF_PROMISC) {
                rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
                rctl &= ~E1000_RCTL_VFE;
        } else {
                if (netdev->flags & IFF_ALLMULTI)
                        rctl |= E1000_RCTL_MPE;
                else
                        rctl &= ~E1000_RCTL_MPE;
                /* Enable VLAN filter if there is a VLAN */
                if (e1000_vlan_used(adapter))
                        rctl |= E1000_RCTL_VFE;
        }

        if (netdev_uc_count(netdev) > rar_entries - 1) {
                rctl |= E1000_RCTL_UPE;
        } else if (!(netdev->flags & IFF_PROMISC)) {
                rctl &= ~E1000_RCTL_UPE;
                use_uc = true;
        }

        ew32(RCTL, rctl);

        /* 82542 2.0 needs to be in reset to write receive address registers */

        if (hw->mac_type == e1000_82542_rev2_0)
                e1000_enter_82542_rst(adapter);

        /* load the first 14 addresses into the exact filters 1-14. Unicast
         * addresses take precedence to avoid disabling unicast filtering
         * when possible.
         *
         * RAR 0 is used for the station MAC address
         * if there are not 14 addresses, go ahead and clear the filters
         */
        i = 1;
        if (use_uc)
                netdev_for_each_uc_addr(ha, netdev) {
                        if (i == rar_entries)
                                break;
                        e1000_rar_set(hw, ha->addr, i++);
                }

        netdev_for_each_mc_addr(ha, netdev) {
                if (i == rar_entries) {
                        /* load any remaining addresses into the hash table */
                        u32 hash_reg, hash_bit, mta;
                        hash_value = e1000_hash_mc_addr(hw, ha->addr);
                        hash_reg = (hash_value >> 5) & 0x7F;
                        hash_bit = hash_value & 0x1F;
                        mta = (1 << hash_bit);
                        mcarray[hash_reg] |= mta;
                } else {
                        e1000_rar_set(hw, ha->addr, i++);
                }
        }

        for (; i < rar_entries; i++) {
                E1000_WRITE_REG_ARRAY(hw, RA, i << 1, 0);
                E1000_WRITE_FLUSH();
                E1000_WRITE_REG_ARRAY(hw, RA, (i << 1) + 1, 0);
                E1000_WRITE_FLUSH();
        }

        /* write the hash table completely, write from bottom to avoid
         * both stupid write combining chipsets, and flushing each write
         */
        for (i = mta_reg_count - 1; i >= 0 ; i--) {
                /* If we are on an 82544 has an errata where writing odd
                 * offsets overwrites the previous even offset, but writing
                 * backwards over the range solves the issue by always
                 * writing the odd offset first
                 */
                E1000_WRITE_REG_ARRAY(hw, MTA, i, mcarray[i]);
        }
        E1000_WRITE_FLUSH();

        if (hw->mac_type == e1000_82542_rev2_0)
                e1000_leave_82542_rst(adapter);

        kfree(mcarray);
}

/**
 * e1000_update_phy_info_task - get phy info
 * @work: work struct contained inside adapter struct
 *
 * Need to wait a few seconds after link up to get diagnostic information from
 * the phy
 */
static void e1000_update_phy_info_task(struct work_struct *work)
{
        struct e1000_adapter *adapter = container_of(work,
                                                     struct e1000_adapter,
                                                     phy_info_task.work);

        e1000_phy_get_info(&adapter->hw, &adapter->phy_info);
}

/**
 * e1000_82547_tx_fifo_stall_task - task to complete work
 * @work: work struct contained inside adapter struct
 **/
static void e1000_82547_tx_fifo_stall_task(struct work_struct *work)
{
        struct e1000_adapter *adapter = container_of(work,
                                                     struct e1000_adapter,
                                                     fifo_stall_task.work);
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        u32 tctl;

        if (atomic_read(&adapter->tx_fifo_stall)) {
                if ((er32(TDT) == er32(TDH)) &&
                   (er32(TDFT) == er32(TDFH)) &&
                   (er32(TDFTS) == er32(TDFHS))) {
                        tctl = er32(TCTL);
                        ew32(TCTL, tctl & ~E1000_TCTL_EN);
                        ew32(TDFT, adapter->tx_head_addr);
                        ew32(TDFH, adapter->tx_head_addr);
                        ew32(TDFTS, adapter->tx_head_addr);
                        ew32(TDFHS, adapter->tx_head_addr);
                        ew32(TCTL, tctl);
                        E1000_WRITE_FLUSH();

                        adapter->tx_fifo_head = 0;
                        atomic_set(&adapter->tx_fifo_stall, 0);
                        netif_wake_queue(netdev);
                } else if (!test_bit(__E1000_DOWN, &adapter->flags)) {
                        schedule_delayed_work(&adapter->fifo_stall_task, 1);
                }
        }
}

bool e1000_has_link(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        bool link_active = false;

        /* get_link_status is set on LSC (link status) interrupt or rx
         * sequence error interrupt (except on intel ce4100).
         * get_link_status will stay false until the
         * e1000_check_for_link establishes link for copper adapters
         * ONLY
         */
        switch (hw->media_type) {
        case e1000_media_type_copper:
                if (hw->mac_type == e1000_ce4100)
                        hw->get_link_status = 1;
                if (hw->get_link_status) {
                        e1000_check_for_link(hw);
                        link_active = !hw->get_link_status;
                } else {
                        link_active = true;
                }
                break;
        case e1000_media_type_fiber:
                e1000_check_for_link(hw);
                link_active = !!(er32(STATUS) & E1000_STATUS_LU);
                break;
        case e1000_media_type_internal_serdes:
                e1000_check_for_link(hw);
                link_active = hw->serdes_has_link;
                break;
        default:
                break;
        }

        return link_active;
}

/**
 * e1000_watchdog - work function
 * @work: work struct contained inside adapter struct
 **/
static void e1000_watchdog(struct work_struct *work)
{
        struct e1000_adapter *adapter = container_of(work,
                                                     struct e1000_adapter,
                                                     watchdog_task.work);
        struct e1000_hw *hw = &adapter->hw;
        struct net_device *netdev = adapter->netdev;
        struct e1000_tx_ring *txdr = adapter->tx_ring;
        u32 link, tctl;

        link = e1000_has_link(adapter);
        if ((netif_carrier_ok(netdev)) && link)
                goto link_up;

        if (link) {
                if (!netif_carrier_ok(netdev)) {
                        u32 ctrl;
                        bool txb2b = true;
                        /* update snapshot of PHY registers on LSC */
                        e1000_get_speed_and_duplex(hw,
                                                   &adapter->link_speed,
                                                   &adapter->link_duplex);

                        ctrl = er32(CTRL);
                        pr_info("%s NIC Link is Up %d Mbps %s, "
                                "Flow Control: %s\n",
                                netdev->name,
                                adapter->link_speed,
                                adapter->link_duplex == FULL_DUPLEX ?
                                "Full Duplex" : "Half Duplex",
                                ((ctrl & E1000_CTRL_TFCE) && (ctrl &
                                E1000_CTRL_RFCE)) ? "RX/TX" : ((ctrl &
                                E1000_CTRL_RFCE) ? "RX" : ((ctrl &
                                E1000_CTRL_TFCE) ? "TX" : "None")));

                        /* adjust timeout factor according to speed/duplex */
                        adapter->tx_timeout_factor = 1;
                        switch (adapter->link_speed) {
                        case SPEED_10:
                                txb2b = false;
                                adapter->tx_timeout_factor = 16;
                                break;
                        case SPEED_100:
                                txb2b = false;
                                /* maybe add some timeout factor ? */
                                break;
                        }

                        /* enable transmits in the hardware */
                        tctl = er32(TCTL);
                        tctl |= E1000_TCTL_EN;
                        ew32(TCTL, tctl);

                        netif_carrier_on(netdev);
                        if (!test_bit(__E1000_DOWN, &adapter->flags))
                                schedule_delayed_work(&adapter->phy_info_task,
                                                      2 * HZ);
                        adapter->smartspeed = 0;
                }
        } else {
                if (netif_carrier_ok(netdev)) {
                        adapter->link_speed = 0;
                        adapter->link_duplex = 0;
                        pr_info("%s NIC Link is Down\n",
                                netdev->name);
                        netif_carrier_off(netdev);

                        if (!test_bit(__E1000_DOWN, &adapter->flags))
                                schedule_delayed_work(&adapter->phy_info_task,
                                                      2 * HZ);
                }

                e1000_smartspeed(adapter);
        }

link_up:
        e1000_update_stats(adapter);

        hw->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old;
        adapter->tpt_old = adapter->stats.tpt;
        hw->collision_delta = adapter->stats.colc - adapter->colc_old;
        adapter->colc_old = adapter->stats.colc;

        adapter->gorcl = adapter->stats.gorcl - adapter->gorcl_old;
        adapter->gorcl_old = adapter->stats.gorcl;
        adapter->gotcl = adapter->stats.gotcl - adapter->gotcl_old;
        adapter->gotcl_old = adapter->stats.gotcl;

        e1000_update_adaptive(hw);

        if (!netif_carrier_ok(netdev)) {
                if (E1000_DESC_UNUSED(txdr) + 1 < txdr->count) {
                        /* We've lost link, so the controller stops DMA,
                         * but we've got queued Tx work that's never going
                         * to get done, so reset controller to flush Tx.
                         * (Do the reset outside of interrupt context).
                         */
                        adapter->tx_timeout_count++;
                        schedule_work(&adapter->reset_task);
                        /* exit immediately since reset is imminent */
                        return;
                }
        }

        /* Simple mode for Interrupt Throttle Rate (ITR) */
        if (hw->mac_type >= e1000_82540 && adapter->itr_setting == 4) {
                /* Symmetric Tx/Rx gets a reduced ITR=2000;
                 * Total asymmetrical Tx or Rx gets ITR=8000;
                 * everyone else is between 2000-8000.
                 */
                u32 goc = (adapter->gotcl + adapter->gorcl) / 10000;
                u32 dif = (adapter->gotcl > adapter->gorcl ?
                            adapter->gotcl - adapter->gorcl :
                            adapter->gorcl - adapter->gotcl) / 10000;
                u32 itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000;

                ew32(ITR, 1000000000 / (itr * 256));
        }

        /* Cause software interrupt to ensure rx ring is cleaned */
        ew32(ICS, E1000_ICS_RXDMT0);

        /* Force detection of hung controller every watchdog period */
        adapter->detect_tx_hung = true;

        /* Reschedule the task */
        if (!test_bit(__E1000_DOWN, &adapter->flags))
                schedule_delayed_work(&adapter->watchdog_task, 2 * HZ);
}

enum latency_range {
        lowest_latency = 0,
        low_latency = 1,
        bulk_latency = 2,
        latency_invalid = 255
};

/**
 * e1000_update_itr - update the dynamic ITR value based on statistics
 * @adapter: pointer to adapter
 * @itr_setting: current adapter->itr
 * @packets: the number of packets during this measurement interval
 * @bytes: the number of bytes during this measurement interval
 *
 *      Stores a new ITR value based on packets and byte
 *      counts during the last interrupt.  The advantage of per interrupt
 *      computation is faster updates and more accurate ITR for the current
 *      traffic pattern.  Constants in this function were computed
 *      based on theoretical maximum wire speed and thresholds were set based
 *      on testing data as well as attempting to minimize response time
 *      while increasing bulk throughput.
 *      this functionality is controlled by the InterruptThrottleRate module
 *      parameter (see e1000_param.c)
 **/
static unsigned int e1000_update_itr(struct e1000_adapter *adapter,
                                     u16 itr_setting, int packets, int bytes)
{
        unsigned int retval = itr_setting;
        struct e1000_hw *hw = &adapter->hw;

        if (unlikely(hw->mac_type < e1000_82540))
                goto update_itr_done;

        if (packets == 0)
                goto update_itr_done;

        switch (itr_setting) {
        case lowest_latency:
                /* jumbo frames get bulk treatment*/
                if (bytes/packets > 8000)
                        retval = bulk_latency;
                else if ((packets < 5) && (bytes > 512))
                        retval = low_latency;
                break;
        case low_latency:  /* 50 usec aka 20000 ints/s */
                if (bytes > 10000) {
                        /* jumbo frames need bulk latency setting */
                        if (bytes/packets > 8000)
                                retval = bulk_latency;
                        else if ((packets < 10) || ((bytes/packets) > 1200))
                                retval = bulk_latency;
                        else if ((packets > 35))
                                retval = lowest_latency;
                } else if (bytes/packets > 2000)
                        retval = bulk_latency;
                else if (packets <= 2 && bytes < 512)
                        retval = lowest_latency;
                break;
        case bulk_latency: /* 250 usec aka 4000 ints/s */
                if (bytes > 25000) {
                        if (packets > 35)
                                retval = low_latency;
                } else if (bytes < 6000) {
                        retval = low_latency;
                }
                break;
        }

update_itr_done:
        return retval;
}

static void e1000_set_itr(struct e1000_adapter *adapter)
{
        struct e1000_hw *hw = &adapter->hw;
        u16 current_itr;
        u32 new_itr = adapter->itr;

        if (unlikely(hw->mac_type < e1000_82540))
                return;

        /* for non-gigabit speeds, just fix the interrupt rate at 4000 */
        if (unlikely(adapter->link_speed != SPEED_1000)) {
                current_itr = 0;
                new_itr = 4000;
                goto set_itr_now;
        }

        adapter->tx_itr = e1000_update_itr(adapter, adapter->tx_itr,
                                           adapter->total_tx_packets,
                                           adapter->total_tx_bytes);
        /* conservative mode (itr 3) eliminates the lowest_latency setting */
        if (adapter->itr_setting == 3 && adapter->tx_itr == lowest_latency)
                adapter->tx_itr = low_latency;

        adapter->rx_itr = e1000_update_itr(adapter, adapter->rx_itr,
                                           adapter->total_rx_packets,
                                           adapter->total_rx_bytes);
        /* conservative mode (itr 3) eliminates the lowest_latency setting */
        if (adapter->itr_setting == 3 && adapter->rx_itr == lowest_latency)
                adapter->rx_itr = low_latency;

        current_itr = max(adapter->rx_itr, adapter->tx_itr);

        switch (current_itr) {
        /* counts and packets in update_itr are dependent on these numbers */
        case lowest_latency:
                new_itr = 70000;
                break;
        case low_latency:
                new_itr = 20000; /* aka hwitr = ~200 */
                break;
        case bulk_latency:
                new_itr = 4000;
                break;
        default:
                break;
        }

set_itr_now:
        if (new_itr != adapter->itr) {
                /* this attempts to bias the interrupt rate towards Bulk
                 * by adding intermediate steps when interrupt rate is
                 * increasing
                 */
                new_itr = new_itr > adapter->itr ?
                          min(adapter->itr + (new_itr >> 2), new_itr) :
                          new_itr;
                adapter->itr = new_itr;
                ew32(ITR, 1000000000 / (new_itr * 256));
        }
}

#define E1000_TX_FLAGS_CSUM             0x00000001
#define E1000_TX_FLAGS_VLAN             0x00000002
#define E1000_TX_FLAGS_TSO              0x00000004
#define E1000_TX_FLAGS_IPV4             0x00000008
#define E1000_TX_FLAGS_NO_FCS           0x00000010
#define E1000_TX_FLAGS_VLAN_MASK        0xffff0000
#define E1000_TX_FLAGS_VLAN_SHIFT       16

static int e1000_tso(struct e1000_adapter *adapter,
                     struct e1000_tx_ring *tx_ring, struct sk_buff *skb,
                     __be16 protocol)
{
        struct e1000_context_desc *context_desc;
        struct e1000_tx_buffer *buffer_info;
        unsigned int i;
        u32 cmd_length = 0;
        u16 ipcse = 0, tucse, mss;
        u8 ipcss, ipcso, tucss, tucso, hdr_len;

        if (skb_is_gso(skb)) {
                int err;

                err = skb_cow_head(skb, 0);
                if (err < 0)
                        return err;

                hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
                mss = skb_shinfo(skb)->gso_size;
                if (protocol == htons(ETH_P_IP)) {
                        struct iphdr *iph = ip_hdr(skb);
                        iph->tot_len = 0;
                        iph->check = 0;
                        tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
                                                                 iph->daddr, 0,
                                                                 IPPROTO_TCP,
                                                                 0);
                        cmd_length = E1000_TXD_CMD_IP;
                        ipcse = skb_transport_offset(skb) - 1;
                } else if (skb_is_gso_v6(skb)) {
                        ipv6_hdr(skb)->payload_len = 0;
                        tcp_hdr(skb)->check =
                                ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
                                                 &ipv6_hdr(skb)->daddr,
                                                 0, IPPROTO_TCP, 0);
                        ipcse = 0;
                }
                ipcss = skb_network_offset(skb);
                ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data;
                tucss = skb_transport_offset(skb);
                tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data;
                tucse = 0;

                cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE |
                               E1000_TXD_CMD_TCP | (skb->len - (hdr_len)));

                i = tx_ring->next_to_use;
                context_desc = E1000_CONTEXT_DESC(*tx_ring, i);
                buffer_info = &tx_ring->buffer_info[i];

                context_desc->lower_setup.ip_fields.ipcss  = ipcss;
                context_desc->lower_setup.ip_fields.ipcso  = ipcso;
                context_desc->lower_setup.ip_fields.ipcse  = cpu_to_le16(ipcse);
                context_desc->upper_setup.tcp_fields.tucss = tucss;
                context_desc->upper_setup.tcp_fields.tucso = tucso;
                context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse);
                context_desc->tcp_seg_setup.fields.mss     = cpu_to_le16(mss);
                context_desc->tcp_seg_setup.fields.hdr_len = hdr_len;
                context_desc->cmd_and_length = cpu_to_le32(cmd_length);

                buffer_info->time_stamp = jiffies;
                buffer_info->next_to_watch = i;

                if (++i == tx_ring->count)
                        i = 0;

                tx_ring->next_to_use = i;

                return true;
        }
        return false;
}

static bool e1000_tx_csum(struct e1000_adapter *adapter,
                          struct e1000_tx_ring *tx_ring, struct sk_buff *skb,
                          __be16 protocol)
{
        struct e1000_context_desc *context_desc;
        struct e1000_tx_buffer *buffer_info;
        unsigned int i;
        u8 css;
        u32 cmd_len = E1000_TXD_CMD_DEXT;

        if (skb->ip_summed != CHECKSUM_PARTIAL)
                return false;

        switch (protocol) {
        case cpu_to_be16(ETH_P_IP):
                if (ip_hdr(skb)->protocol == IPPROTO_TCP)
                        cmd_len |= E1000_TXD_CMD_TCP;
                break;
        case cpu_to_be16(ETH_P_IPV6):
                /* XXX not handling all IPV6 headers */
                if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
                        cmd_len |= E1000_TXD_CMD_TCP;
                break;
        default:
                if (unlikely(net_ratelimit()))
                        e_warn(drv, "checksum_partial proto=%x!\n",
                               skb->protocol);
                break;
        }

        css = skb_checksum_start_offset(skb);

        i = tx_ring->next_to_use;
        buffer_info = &tx_ring->buffer_info[i];
        context_desc = E1000_CONTEXT_DESC(*tx_ring, i);

        context_desc->lower_setup.ip_config = 0;
        context_desc->upper_setup.tcp_fields.tucss = css;
        context_desc->upper_setup.tcp_fields.tucso =
                css + skb->csum_offset;
        context_desc->upper_setup.tcp_fields.tucse = 0;
        context_desc->tcp_seg_setup.data = 0;
        context_desc->cmd_and_length = cpu_to_le32(cmd_len);

        buffer_info->time_stamp = jiffies;
        buffer_info->next_to_watch = i;

        if (unlikely(++i == tx_ring->count))
                i = 0;

        tx_ring->next_to_use = i;

        return true;
}

#define E1000_MAX_TXD_PWR       12
#define E1000_MAX_DATA_PER_TXD  (1<<E1000_MAX_TXD_PWR)

static int e1000_tx_map(struct e1000_adapter *adapter,
                        struct e1000_tx_ring *tx_ring,
                        struct sk_buff *skb, unsigned int first,
                        unsigned int max_per_txd, unsigned int nr_frags,
                        unsigned int mss)
{
        struct e1000_hw *hw = &adapter->hw;
        struct pci_dev *pdev = adapter->pdev;
        struct e1000_tx_buffer *buffer_info;
        unsigned int len = skb_headlen(skb);
        unsigned int offset = 0, size, count = 0, i;
        unsigned int f, bytecount, segs;

        i = tx_ring->next_to_use;

        while (len) {
                buffer_info = &tx_ring->buffer_info[i];
                size = min(len, max_per_txd);
                /* Workaround for Controller erratum --
                 * descriptor for non-tso packet in a linear SKB that follows a
                 * tso gets written back prematurely before the data is fully
                 * DMA'd to the controller
                 */
                if (!skb->data_len && tx_ring->last_tx_tso &&
                    !skb_is_gso(skb)) {
                        tx_ring->last_tx_tso = false;
                        size -= 4;
                }

                /* Workaround for premature desc write-backs
                 * in TSO mode.  Append 4-byte sentinel desc
                 */
                if (unlikely(mss && !nr_frags && size == len && size > 8))
                        size -= 4;
                /* work-around for errata 10 and it applies
                 * to all controllers in PCI-X mode
                 * The fix is to make sure that the first descriptor of a
                 * packet is smaller than 2048 - 16 - 16 (or 2016) bytes
                 */
                if (unlikely((hw->bus_type == e1000_bus_type_pcix) &&
                             (size > 2015) && count == 0))
                        size = 2015;

                /* Workaround for potential 82544 hang in PCI-X.  Avoid
                 * terminating buffers within evenly-aligned dwords.
                 */
                if (unlikely(adapter->pcix_82544 &&
                   !((unsigned long)(skb->data + offset + size - 1) & 4) &&
                   size > 4))
                        size -= 4;

                buffer_info->length = size;
                /* set time_stamp *before* dma to help avoid a possible race */
                buffer_info->time_stamp = jiffies;
                buffer_info->mapped_as_page = false;
                buffer_info->dma = dma_map_single(&pdev->dev,
                                                  skb->data + offset,
                                                  size, DMA_TO_DEVICE);
                if (dma_mapping_error(&pdev->dev, buffer_info->dma))
                        goto dma_error;
                buffer_info->next_to_watch = i;

                len -= size;
                offset += size;
                count++;
                if (len) {
                        i++;
                        if (unlikely(i == tx_ring->count))
                                i = 0;
                }
        }

        for (f = 0; f < nr_frags; f++) {
                const struct skb_frag_struct *frag;

                frag = &skb_shinfo(skb)->frags[f];
                len = skb_frag_size(frag);
                offset = 0;

                while (len) {
                        unsigned long bufend;
                        i++;
                        if (unlikely(i == tx_ring->count))
                                i = 0;

                        buffer_info = &tx_ring->buffer_info[i];
                        size = min(len, max_per_txd);
                        /* Workaround for premature desc write-backs
                         * in TSO mode.  Append 4-byte sentinel desc
                         */
                        if (unlikely(mss && f == (nr_frags-1) &&
                            size == len && size > 8))
                                size -= 4;
                        /* Workaround for potential 82544 hang in PCI-X.
                         * Avoid terminating buffers within evenly-aligned
                         * dwords.
                         */
                        bufend = (unsigned long)
                                page_to_phys(skb_frag_page(frag));
                        bufend += offset + size - 1;
                        if (unlikely(adapter->pcix_82544 &&
                                     !(bufend & 4) &&
                                     size > 4))
                                size -= 4;

                        buffer_info->length = size;
                        buffer_info->time_stamp = jiffies;
                        buffer_info->mapped_as_page = true;
                        buffer_info->dma = skb_frag_dma_map(&pdev->dev, frag,
                                                offset, size, DMA_TO_DEVICE);
                        if (dma_mapping_error(&pdev->dev, buffer_info->dma))
                                goto dma_error;
                        buffer_info->next_to_watch = i;

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

        segs = skb_shinfo(skb)->gso_segs ?: 1;
        /* multiply data chunks by size of headers */
        bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len;

        tx_ring->buffer_info[i].skb = skb;
        tx_ring->buffer_info[i].segs = segs;
        tx_ring->buffer_info[i].bytecount = bytecount;
        tx_ring->buffer_info[first].next_to_watch = i;

        return count;

dma_error:
        dev_err(&pdev->dev, "TX DMA map failed\n");
        buffer_info->dma = 0;
        if (count)
                count--;

        while (count--) {
                if (i == 0)
                        i += tx_ring->count;
                i--;
                buffer_info = &tx_ring->buffer_info[i];
                e1000_unmap_and_free_tx_resource(adapter, buffer_info);
        }

        return 0;
}

static void e1000_tx_queue(struct e1000_adapter *adapter,
                           struct e1000_tx_ring *tx_ring, int tx_flags,
                           int count)
{
        struct e1000_tx_desc *tx_desc = NULL;
        struct e1000_tx_buffer *buffer_info;
        u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS;
        unsigned int i;

        if (likely(tx_flags & E1000_TX_FLAGS_TSO)) {
                txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D |
                             E1000_TXD_CMD_TSE;
                txd_upper |= E1000_TXD_POPTS_TXSM << 8;

                if (likely(tx_flags & E1000_TX_FLAGS_IPV4))
                        txd_upper |= E1000_TXD_POPTS_IXSM << 8;
        }

        if (likely(tx_flags & E1000_TX_FLAGS_CSUM)) {
                txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D;
                txd_upper |= E1000_TXD_POPTS_TXSM << 8;