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

  Intel 10 Gigabit PCI Express Linux driver
  Copyright(c) 1999 - 2013 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:
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

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

#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
#include <linux/pkt_sched.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/if_bridge.h>
#include <linux/prefetch.h>
#include <scsi/fc/fc_fcoe.h>

#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
#include "ixgbe_sriov.h"

char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
                              "Intel(R) 10 Gigabit PCI Express Network Driver";
#ifdef IXGBE_FCOE
char ixgbe_default_device_descr[] =
                              "Intel(R) 10 Gigabit Network Connection";
#else
static char ixgbe_default_device_descr[] =
                              "Intel(R) 10 Gigabit Network Connection";
#endif
#define DRV_VERSION "3.13.10-k"
const char ixgbe_driver_version[] = DRV_VERSION;
static const char ixgbe_copyright[] =
                                "Copyright (c) 1999-2013 Intel Corporation.";

static const struct ixgbe_info *ixgbe_info_tbl[] = {
        [board_82598] = &ixgbe_82598_info,
        [board_82599] = &ixgbe_82599_info,
        [board_X540] = &ixgbe_X540_info,
};

/* ixgbe_pci_tbl - PCI Device ID Table
 *
 * Wildcard entries (PCI_ANY_ID) should come last
 * Last entry must be all 0s
 *
 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
 *   Class, Class Mask, private data (not used) }
 */
static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 },
        {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 },
        /* required last entry */
        {0, }
};
MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl);

#ifdef CONFIG_IXGBE_DCA
static int ixgbe_notify_dca(struct notifier_block *, unsigned long event,
                            void *p);
static struct notifier_block dca_notifier = {
        .notifier_call = ixgbe_notify_dca,
        .next          = NULL,
        .priority      = 0
};
#endif

#ifdef CONFIG_PCI_IOV
static unsigned int max_vfs;
module_param(max_vfs, uint, 0);
MODULE_PARM_DESC(max_vfs,
                 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63");
#endif /* CONFIG_PCI_IOV */

static unsigned int allow_unsupported_sfp;
module_param(allow_unsupported_sfp, uint, 0);
MODULE_PARM_DESC(allow_unsupported_sfp,
                 "Allow unsupported and untested SFP+ modules on 82599-based adapters");

#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)");

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
                                          u32 reg, u16 *value)
{
        int pos = 0;
        struct pci_dev *parent_dev;
        struct pci_bus *parent_bus;

        parent_bus = adapter->pdev->bus->parent;
        if (!parent_bus)
                return -1;

        parent_dev = parent_bus->self;
        if (!parent_dev)
                return -1;

        pos = pci_find_capability(parent_dev, PCI_CAP_ID_EXP);
        if (!pos)
                return -1;

        pci_read_config_word(parent_dev, pos + reg, value);
        return 0;
}

static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u16 link_status = 0;
        int err;

        hw->bus.type = ixgbe_bus_type_pci_express;

        /* Get the negotiated link width and speed from PCI config space of the
         * parent, as this device is behind a switch
         */
        err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status);

        /* assume caller will handle error case */
        if (err)
                return err;

        hw->bus.width = ixgbe_convert_bus_width(link_status);
        hw->bus.speed = ixgbe_convert_bus_speed(link_status);

        return 0;
}

static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter)
{
        if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
            !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state))
                schedule_work(&adapter->service_task);
}

static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
{
        BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));

        /* flush memory to make sure state is correct before next watchdog */
        smp_mb__before_clear_bit();
        clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
}

struct ixgbe_reg_info {
        u32 ofs;
        char *name;
};

static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {

        /* General Registers */
        {IXGBE_CTRL, "CTRL"},
        {IXGBE_STATUS, "STATUS"},
        {IXGBE_CTRL_EXT, "CTRL_EXT"},

        /* Interrupt Registers */
        {IXGBE_EICR, "EICR"},

        /* RX Registers */
        {IXGBE_SRRCTL(0), "SRRCTL"},
        {IXGBE_DCA_RXCTRL(0), "DRXCTL"},
        {IXGBE_RDLEN(0), "RDLEN"},
        {IXGBE_RDH(0), "RDH"},
        {IXGBE_RDT(0), "RDT"},
        {IXGBE_RXDCTL(0), "RXDCTL"},
        {IXGBE_RDBAL(0), "RDBAL"},
        {IXGBE_RDBAH(0), "RDBAH"},

        /* TX Registers */
        {IXGBE_TDBAL(0), "TDBAL"},
        {IXGBE_TDBAH(0), "TDBAH"},
        {IXGBE_TDLEN(0), "TDLEN"},
        {IXGBE_TDH(0), "TDH"},
        {IXGBE_TDT(0), "TDT"},
        {IXGBE_TXDCTL(0), "TXDCTL"},

        /* List Terminator */
        {}
};


/*
 * ixgbe_regdump - register printout routine
 */
static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
{
        int i = 0, j = 0;
        char rname[16];
        u32 regs[64];

        switch (reginfo->ofs) {
        case IXGBE_SRRCTL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i));
                break;
        case IXGBE_DCA_RXCTRL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
                break;
        case IXGBE_RDLEN(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i));
                break;
        case IXGBE_RDH(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i));
                break;
        case IXGBE_RDT(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i));
                break;
        case IXGBE_RXDCTL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i));
                break;
        case IXGBE_RDBAL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i));
                break;
        case IXGBE_RDBAH(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i));
                break;
        case IXGBE_TDBAL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i));
                break;
        case IXGBE_TDBAH(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i));
                break;
        case IXGBE_TDLEN(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i));
                break;
        case IXGBE_TDH(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i));
                break;
        case IXGBE_TDT(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i));
                break;
        case IXGBE_TXDCTL(0):
                for (i = 0; i < 64; i++)
                        regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
                break;
        default:
                pr_info("%-15s %08x\n", reginfo->name,
                        IXGBE_READ_REG(hw, reginfo->ofs));
                return;
        }

        for (i = 0; i < 8; i++) {
                snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7);
                pr_err("%-15s", rname);
                for (j = 0; j < 8; j++)
                        pr_cont(" %08x", regs[i*8+j]);
                pr_cont("\n");
        }

}

/*
 * ixgbe_dump - Print registers, tx-rings and rx-rings
 */
static void ixgbe_dump(struct ixgbe_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        struct ixgbe_hw *hw = &adapter->hw;
        struct ixgbe_reg_info *reginfo;
        int n = 0;
        struct ixgbe_ring *tx_ring;
        struct ixgbe_tx_buffer *tx_buffer;
        union ixgbe_adv_tx_desc *tx_desc;
        struct my_u0 { u64 a; u64 b; } *u0;
        struct ixgbe_ring *rx_ring;
        union ixgbe_adv_rx_desc *rx_desc;
        struct ixgbe_rx_buffer *rx_buffer_info;
        u32 staterr;
        int i = 0;

        if (!netif_msg_hw(adapter))
                return;

        /* Print netdevice Info */
        if (netdev) {
                dev_info(&adapter->pdev->dev, "Net device Info\n");
                pr_info("Device Name     state            "
                        "trans_start      last_rx\n");
                pr_info("%-15s %016lX %016lX %016lX\n",
                        netdev->name,
                        netdev->state,
                        netdev->trans_start,
                        netdev->last_rx);
        }

        /* Print Registers */
        dev_info(&adapter->pdev->dev, "Register Dump\n");
        pr_info(" Register Name   Value\n");
        for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl;
             reginfo->name; reginfo++) {
                ixgbe_regdump(hw, reginfo);
        }

        /* Print TX Ring Summary */
        if (!netdev || !netif_running(netdev))
                goto exit;

        dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
        pr_info(" %s     %s              %s        %s\n",
                "Queue [NTU] [NTC] [bi(ntc)->dma  ]",
                "leng", "ntw", "timestamp");
        for (n = 0; n < adapter->num_tx_queues; n++) {
                tx_ring = adapter->tx_ring[n];
                tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
                pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
                           n, tx_ring->next_to_use, tx_ring->next_to_clean,
                           (u64)dma_unmap_addr(tx_buffer, dma),
                           dma_unmap_len(tx_buffer, len),
                           tx_buffer->next_to_watch,
                           (u64)tx_buffer->time_stamp);
        }

        /* Print TX Rings */
        if (!netif_msg_tx_done(adapter))
                goto rx_ring_summary;

        dev_info(&adapter->pdev->dev, "TX Rings Dump\n");

        /* Transmit Descriptor Formats
         *
         * 82598 Advanced Transmit Descriptor
         *   +--------------------------------------------------------------+
         * 0 |         Buffer Address [63:0]                                |
         *   +--------------------------------------------------------------+
         * 8 |  PAYLEN  | POPTS  | IDX | STA | DCMD  |DTYP |  RSV |  DTALEN |
         *   +--------------------------------------------------------------+
         *   63       46 45    40 39 36 35 32 31   24 23 20 19              0
         *
         * 82598 Advanced Transmit Descriptor (Write-Back Format)
         *   +--------------------------------------------------------------+
         * 0 |                          RSV [63:0]                          |
         *   +--------------------------------------------------------------+
         * 8 |            RSV           |  STA  |          NXTSEQ           |
         *   +--------------------------------------------------------------+
         *   63                       36 35   32 31                         0
         *
         * 82599+ Advanced Transmit Descriptor
         *   +--------------------------------------------------------------+
         * 0 |         Buffer Address [63:0]                                |
         *   +--------------------------------------------------------------+
         * 8 |PAYLEN  |POPTS|CC|IDX  |STA  |DCMD  |DTYP |MAC  |RSV  |DTALEN |
         *   +--------------------------------------------------------------+
         *   63     46 45 40 39 38 36 35 32 31  24 23 20 19 18 17 16 15     0
         *
         * 82599+ Advanced Transmit Descriptor (Write-Back Format)
         *   +--------------------------------------------------------------+
         * 0 |                          RSV [63:0]                          |
         *   +--------------------------------------------------------------+
         * 8 |            RSV           |  STA  |           RSV             |
         *   +--------------------------------------------------------------+
         *   63                       36 35   32 31                         0
         */

        for (n = 0; n < adapter->num_tx_queues; n++) {
                tx_ring = adapter->tx_ring[n];
                pr_info("------------------------------------\n");
                pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
                pr_info("------------------------------------\n");
                pr_info("%s%s    %s              %s        %s          %s\n",
                        "T [desc]     [address 63:0  ] ",
                        "[PlPOIdStDDt Ln] [bi->dma       ] ",
                        "leng", "ntw", "timestamp", "bi->skb");

                for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
                        tx_desc = IXGBE_TX_DESC(tx_ring, i);
                        tx_buffer = &tx_ring->tx_buffer_info[i];
                        u0 = (struct my_u0 *)tx_desc;
                        if (dma_unmap_len(tx_buffer, len) > 0) {
                                pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p",
                                        i,
                                        le64_to_cpu(u0->a),
                                        le64_to_cpu(u0->b),
                                        (u64)dma_unmap_addr(tx_buffer, dma),
                                        dma_unmap_len(tx_buffer, len),
                                        tx_buffer->next_to_watch,
                                        (u64)tx_buffer->time_stamp,
                                        tx_buffer->skb);
                                if (i == tx_ring->next_to_use &&
                                        i == tx_ring->next_to_clean)
                                        pr_cont(" NTC/U\n");
                                else if (i == tx_ring->next_to_use)
                                        pr_cont(" NTU\n");
                                else if (i == tx_ring->next_to_clean)
                                        pr_cont(" NTC\n");
                                else
                                        pr_cont("\n");

                                if (netif_msg_pktdata(adapter) &&
                                    tx_buffer->skb)
                                        print_hex_dump(KERN_INFO, "",
                                                DUMP_PREFIX_ADDRESS, 16, 1,
                                                tx_buffer->skb->data,
                                                dma_unmap_len(tx_buffer, len),
                                                true);
                        }
                }
        }

        /* Print RX Rings Summary */
rx_ring_summary:
        dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
        pr_info("Queue [NTU] [NTC]\n");
        for (n = 0; n < adapter->num_rx_queues; n++) {
                rx_ring = adapter->rx_ring[n];
                pr_info("%5d %5X %5X\n",
                        n, rx_ring->next_to_use, rx_ring->next_to_clean);
        }

        /* Print RX Rings */
        if (!netif_msg_rx_status(adapter))
                goto exit;

        dev_info(&adapter->pdev->dev, "RX Rings Dump\n");

        /* Receive Descriptor Formats
         *
         * 82598 Advanced Receive Descriptor (Read) Format
         *    63                                           1        0
         *    +-----------------------------------------------------+
         *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
         *    +----------------------------------------------+------+
         *  8 |       Header Buffer Address [63:1]           |  DD  |
         *    +-----------------------------------------------------+
         *
         *
         * 82598 Advanced Receive Descriptor (Write-Back) Format
         *
         *   63       48 47    32 31  30      21 20 16 15   4 3     0
         *   +------------------------------------------------------+
         * 0 |       RSS Hash /  |SPH| HDR_LEN  | RSV |Packet|  RSS |
         *   | Packet   | IP     |   |          |     | Type | Type |
         *   | Checksum | Ident  |   |          |     |      |      |
         *   +------------------------------------------------------+
         * 8 | VLAN Tag | Length | Extended Error | Extended Status |
         *   +------------------------------------------------------+
         *   63       48 47    32 31            20 19               0
         *
         * 82599+ Advanced Receive Descriptor (Read) Format
         *    63                                           1        0
         *    +-----------------------------------------------------+
         *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
         *    +----------------------------------------------+------+
         *  8 |       Header Buffer Address [63:1]           |  DD  |
         *    +-----------------------------------------------------+
         *
         *
         * 82599+ Advanced Receive Descriptor (Write-Back) Format
         *
         *   63       48 47    32 31  30      21 20 17 16   4 3     0
         *   +------------------------------------------------------+
         * 0 |RSS / Frag Checksum|SPH| HDR_LEN  |RSC- |Packet|  RSS |
         *   |/ RTT / PCoE_PARAM |   |          | CNT | Type | Type |
         *   |/ Flow Dir Flt ID  |   |          |     |      |      |
         *   +------------------------------------------------------+
         * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP |
         *   +------------------------------------------------------+
         *   63       48 47    32 31          20 19                 0
         */

        for (n = 0; n < adapter->num_rx_queues; n++) {
                rx_ring = adapter->rx_ring[n];
                pr_info("------------------------------------\n");
                pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
                pr_info("------------------------------------\n");
                pr_info("%s%s%s",
                        "R  [desc]      [ PktBuf     A0] ",
                        "[  HeadBuf   DD] [bi->dma       ] [bi->skb       ] ",
                        "<-- Adv Rx Read format\n");
                pr_info("%s%s%s",
                        "RWB[desc]      [PcsmIpSHl PtRs] ",
                        "[vl er S cks ln] ---------------- [bi->skb       ] ",
                        "<-- Adv Rx Write-Back format\n");

                for (i = 0; i < rx_ring->count; i++) {
                        rx_buffer_info = &rx_ring->rx_buffer_info[i];
                        rx_desc = IXGBE_RX_DESC(rx_ring, i);
                        u0 = (struct my_u0 *)rx_desc;
                        staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
                        if (staterr & IXGBE_RXD_STAT_DD) {
                                /* Descriptor Done */
                                pr_info("RWB[0x%03X]     %016llX "
                                        "%016llX ---------------- %p", i,
                                        le64_to_cpu(u0->a),
                                        le64_to_cpu(u0->b),
                                        rx_buffer_info->skb);
                        } else {
                                pr_info("R  [0x%03X]     %016llX "
                                        "%016llX %016llX %p", i,
                                        le64_to_cpu(u0->a),
                                        le64_to_cpu(u0->b),
                                        (u64)rx_buffer_info->dma,
                                        rx_buffer_info->skb);

                                if (netif_msg_pktdata(adapter) &&
                                    rx_buffer_info->dma) {
                                        print_hex_dump(KERN_INFO, "",
                                           DUMP_PREFIX_ADDRESS, 16, 1,
                                           page_address(rx_buffer_info->page) +
                                                    rx_buffer_info->page_offset,
                                           ixgbe_rx_bufsz(rx_ring), true);
                                }
                        }

                        if (i == rx_ring->next_to_use)
                                pr_cont(" NTU\n");
                        else if (i == rx_ring->next_to_clean)
                                pr_cont(" NTC\n");
                        else
                                pr_cont("\n");

                }
        }

exit:
        return;
}

static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
{
        u32 ctrl_ext;

        /* Let firmware take over control of h/w */
        ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
        IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
                        ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD);
}

static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter)
{
        u32 ctrl_ext;

        /* Let firmware know the driver has taken over */
        ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
        IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
                        ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD);
}

/**
 * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
 * @adapter: pointer to adapter struct
 * @direction: 0 for Rx, 1 for Tx, -1 for other causes
 * @queue: queue to map the corresponding interrupt to
 * @msix_vector: the vector to map to the corresponding queue
 *
 */
static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
                           u8 queue, u8 msix_vector)
{
        u32 ivar, index;
        struct ixgbe_hw *hw = &adapter->hw;
        switch (hw->mac.type) {
        case ixgbe_mac_82598EB:
                msix_vector |= IXGBE_IVAR_ALLOC_VAL;
                if (direction == -1)
                        direction = 0;
                index = (((direction * 64) + queue) >> 2) & 0x1F;
                ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
                ivar &= ~(0xFF << (8 * (queue & 0x3)));
                ivar |= (msix_vector << (8 * (queue & 0x3)));
                IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                if (direction == -1) {
                        /* other causes */
                        msix_vector |= IXGBE_IVAR_ALLOC_VAL;
                        index = ((queue & 1) * 8);
                        ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC);
                        ivar &= ~(0xFF << index);
                        ivar |= (msix_vector << index);
                        IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar);
                        break;
                } else {
                        /* tx or rx causes */
                        msix_vector |= IXGBE_IVAR_ALLOC_VAL;
                        index = ((16 * (queue & 1)) + (8 * direction));
                        ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1));
                        ivar &= ~(0xFF << index);
                        ivar |= (msix_vector << index);
                        IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar);
                        break;
                }
        default:
                break;
        }
}

static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
                                          u64 qmask)
{
        u32 mask;

        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82598EB:
                mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                mask = (qmask & 0xFFFFFFFF);
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
                mask = (qmask >> 32);
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
                break;
        default:
                break;
        }
}

void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring,
                                      struct ixgbe_tx_buffer *tx_buffer)
{
        if (tx_buffer->skb) {
                dev_kfree_skb_any(tx_buffer->skb);
                if (dma_unmap_len(tx_buffer, len))
                        dma_unmap_single(ring->dev,
                                         dma_unmap_addr(tx_buffer, dma),
                                         dma_unmap_len(tx_buffer, len),
                                         DMA_TO_DEVICE);
        } else if (dma_unmap_len(tx_buffer, len)) {
                dma_unmap_page(ring->dev,
                               dma_unmap_addr(tx_buffer, dma),
                               dma_unmap_len(tx_buffer, len),
                               DMA_TO_DEVICE);
        }
        tx_buffer->next_to_watch = NULL;
        tx_buffer->skb = NULL;
        dma_unmap_len_set(tx_buffer, len, 0);
        /* tx_buffer must be completely set up in the transmit path */
}

static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;
        struct ixgbe_hw_stats *hwstats = &adapter->stats;
        int i;
        u32 data;

        if ((hw->fc.current_mode != ixgbe_fc_full) &&
            (hw->fc.current_mode != ixgbe_fc_rx_pause))
                return;

        switch (hw->mac.type) {
        case ixgbe_mac_82598EB:
                data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
                break;
        default:
                data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
        }
        hwstats->lxoffrxc += data;

        /* refill credits (no tx hang) if we received xoff */
        if (!data)
                return;

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

static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;
        struct ixgbe_hw_stats *hwstats = &adapter->stats;
        u32 xoff[8] = {0};
        u8 tc;
        int i;
        bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;

        if (adapter->ixgbe_ieee_pfc)
                pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);

        if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) {
                ixgbe_update_xoff_rx_lfc(adapter);
                return;
        }

        /* update stats for each tc, only valid with PFC enabled */
        for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
                u32 pxoffrxc;

                switch (hw->mac.type) {
                case ixgbe_mac_82598EB:
                        pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
                        break;
                default:
                        pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
                }
                hwstats->pxoffrxc[i] += pxoffrxc;
                /* Get the TC for given UP */
                tc = netdev_get_prio_tc_map(adapter->netdev, i);
                xoff[tc] += pxoffrxc;
        }

        /* disarm tx queues that have received xoff frames */
        for (i = 0; i < adapter->num_tx_queues; i++) {
                struct ixgbe_ring *tx_ring = adapter->tx_ring[i];

                tc = tx_ring->dcb_tc;
                if (xoff[tc])
                        clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
        }
}

static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
{
        return ring->stats.packets;
}

static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
{
        struct ixgbe_adapter *adapter = netdev_priv(ring->netdev);
        struct ixgbe_hw *hw = &adapter->hw;

        u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
        u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));

        if (head != tail)
                return (head < tail) ?
                        tail - head : (tail + ring->count - head);

        return 0;
}

static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
{
        u32 tx_done = ixgbe_get_tx_completed(tx_ring);
        u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
        u32 tx_pending = ixgbe_get_tx_pending(tx_ring);
        bool ret = false;

        clear_check_for_tx_hang(tx_ring);

        /*
         * Check for a hung queue, but be thorough. This verifies
         * that a transmit has been completed since the previous
         * check AND there is at least one packet pending. The
         * ARMED bit is set to indicate a potential hang. The
         * bit is cleared if a pause frame is received to remove
         * false hang detection due to PFC or 802.3x frames. By
         * requiring this to fail twice we avoid races with
         * pfc clearing the ARMED bit and conditions where we
         * run the check_tx_hang logic with a transmit completion
         * pending but without time to complete it yet.
         */
        if ((tx_done_old == tx_done) && tx_pending) {
                /* make sure it is true for two checks in a row */
                ret = test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
                                       &tx_ring->state);
        } else {
                /* update completed stats and continue */
                tx_ring->tx_stats.tx_done_old = tx_done;
                /* reset the countdown */
                clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
        }

        return ret;
}

/**
 * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout
 * @adapter: driver private struct
 **/
static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
{

        /* Do the reset outside of interrupt context */
        if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
                adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
                e_warn(drv, "initiating reset due to tx timeout\n");
                ixgbe_service_event_schedule(adapter);
        }
}

/**
 * ixgbe_clean_tx_irq - Reclaim resources after transmit completes
 * @q_vector: structure containing interrupt and ring information
 * @tx_ring: tx ring to clean
 **/
static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
                               struct ixgbe_ring *tx_ring)
{
        struct ixgbe_adapter *adapter = q_vector->adapter;
        struct ixgbe_tx_buffer *tx_buffer;
        union ixgbe_adv_tx_desc *tx_desc;
        unsigned int total_bytes = 0, total_packets = 0;
        unsigned int budget = q_vector->tx.work_limit;
        unsigned int i = tx_ring->next_to_clean;

        if (test_bit(__IXGBE_DOWN, &adapter->state))
                return true;

        tx_buffer = &tx_ring->tx_buffer_info[i];
        tx_desc = IXGBE_TX_DESC(tx_ring, i);
        i -= tx_ring->count;

        do {
                union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;

                /* if next_to_watch is not set then there is no work pending */
                if (!eop_desc)
                        break;

                /* prevent any other reads prior to eop_desc */
                read_barrier_depends();

                /* if DD is not set pending work has not been completed */
                if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
                        break;

                /* clear next_to_watch to prevent false hangs */
                tx_buffer->next_to_watch = NULL;

                /* update the statistics for this packet */
                total_bytes += tx_buffer->bytecount;
                total_packets += tx_buffer->gso_segs;

                /* free the skb */
                dev_kfree_skb_any(tx_buffer->skb);

                /* unmap skb header data */
                dma_unmap_single(tx_ring->dev,
                                 dma_unmap_addr(tx_buffer, dma),
                                 dma_unmap_len(tx_buffer, len),
                                 DMA_TO_DEVICE);

                /* clear tx_buffer data */
                tx_buffer->skb = NULL;
                dma_unmap_len_set(tx_buffer, len, 0);

                /* unmap remaining buffers */
                while (tx_desc != eop_desc) {
                        tx_buffer++;
                        tx_desc++;
                        i++;
                        if (unlikely(!i)) {
                                i -= tx_ring->count;
                                tx_buffer = tx_ring->tx_buffer_info;
                                tx_desc = IXGBE_TX_DESC(tx_ring, 0);
                        }

                        /* unmap any remaining paged data */
                        if (dma_unmap_len(tx_buffer, len)) {
                                dma_unmap_page(tx_ring->dev,
                                               dma_unmap_addr(tx_buffer, dma),
                                               dma_unmap_len(tx_buffer, len),
                                               DMA_TO_DEVICE);
                                dma_unmap_len_set(tx_buffer, len, 0);
                        }
                }

                /* move us one more past the eop_desc for start of next pkt */
                tx_buffer++;
                tx_desc++;
                i++;
                if (unlikely(!i)) {
                        i -= tx_ring->count;
                        tx_buffer = tx_ring->tx_buffer_info;
                        tx_desc = IXGBE_TX_DESC(tx_ring, 0);
                }

                /* issue prefetch for next Tx descriptor */
                prefetch(tx_desc);

                /* update budget accounting */
                budget--;
        } while (likely(budget));

        i += tx_ring->count;
        tx_ring->next_to_clean = i;
        u64_stats_update_begin(&tx_ring->syncp);
        tx_ring->stats.bytes += total_bytes;
        tx_ring->stats.packets += total_packets;
        u64_stats_update_end(&tx_ring->syncp);
        q_vector->tx.total_bytes += total_bytes;
        q_vector->tx.total_packets += total_packets;

        if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
                /* schedule immediate reset if we believe we hung */
                struct ixgbe_hw *hw = &adapter->hw;
                e_err(drv, "Detected Tx Unit Hang\n"
                        "  Tx Queue             <%d>\n"
                        "  TDH, TDT             <%x>, <%x>\n"
                        "  next_to_use          <%x>\n"
                        "  next_to_clean        <%x>\n"
                        "tx_buffer_info[next_to_clean]\n"
                        "  time_stamp           <%lx>\n"
                        "  jiffies              <%lx>\n",
                        tx_ring->queue_index,
                        IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
                        IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
                        tx_ring->next_to_use, i,
                        tx_ring->tx_buffer_info[i].time_stamp, jiffies);

                netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);

                e_info(probe,
                       "tx hang %d detected on queue %d, resetting adapter\n",
                        adapter->tx_timeout_count + 1, tx_ring->queue_index);

                /* schedule immediate reset if we believe we hung */
                ixgbe_tx_timeout_reset(adapter);

                /* the adapter is about to reset, no point in enabling stuff */
                return true;
        }

        netdev_tx_completed_queue(txring_txq(tx_ring),
                                  total_packets, total_bytes);

#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
        if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
                     (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
                /* Make sure that anybody stopping the queue after this
                 * sees the new next_to_clean.
                 */
                smp_mb();
                if (__netif_subqueue_stopped(tx_ring->netdev,

                                             tx_ring->queue_index)
                    && !test_bit(__IXGBE_DOWN, &adapter->state)) {
                        netif_wake_subqueue(tx_ring->netdev,
                                            tx_ring->queue_index);
                        ++tx_ring->tx_stats.restart_queue;
                }
        }

        return !!budget;
}

#ifdef CONFIG_IXGBE_DCA
static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
                                struct ixgbe_ring *tx_ring,
                                int cpu)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u32 txctrl = dca3_get_tag(tx_ring->dev, cpu);
        u16 reg_offset;

        switch (hw->mac.type) {
        case ixgbe_mac_82598EB:
                reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                reg_offset = IXGBE_DCA_TXCTRL_82599(tx_ring->reg_idx);
                txctrl <<= IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599;
                break;
        default:
                /* for unknown hardware do not write register */
                return;
        }

        /*
         * We can enable relaxed ordering for reads, but not writes when
         * DCA is enabled.  This is due to a known issue in some chipsets
         * which will cause the DCA tag to be cleared.
         */
        txctrl |= IXGBE_DCA_TXCTRL_DESC_RRO_EN |
                  IXGBE_DCA_TXCTRL_DATA_RRO_EN |
                  IXGBE_DCA_TXCTRL_DESC_DCA_EN;

        IXGBE_WRITE_REG(hw, reg_offset, txctrl);
}

static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
                                struct ixgbe_ring *rx_ring,
                                int cpu)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u32 rxctrl = dca3_get_tag(rx_ring->dev, cpu);
        u8 reg_idx = rx_ring->reg_idx;


        switch (hw->mac.type) {
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                rxctrl <<= IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599;
                break;
        default:
                break;
        }

        /*
         * We can enable relaxed ordering for reads, but not writes when
         * DCA is enabled.  This is due to a known issue in some chipsets
         * which will cause the DCA tag to be cleared.
         */
        rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN |
                  IXGBE_DCA_RXCTRL_DESC_DCA_EN;

        IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl);
}

static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
{
        struct ixgbe_adapter *adapter = q_vector->adapter;
        struct ixgbe_ring *ring;
        int cpu = get_cpu();

        if (q_vector->cpu == cpu)
                goto out_no_update;

        ixgbe_for_each_ring(ring, q_vector->tx)
                ixgbe_update_tx_dca(adapter, ring, cpu);

        ixgbe_for_each_ring(ring, q_vector->rx)
                ixgbe_update_rx_dca(adapter, ring, cpu);

        q_vector->cpu = cpu;
out_no_update:
        put_cpu();
}

static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
{
        int i;

        if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED))
                return;

        /* always use CB2 mode, difference is masked in the CB driver */
        IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2);

        for (i = 0; i < adapter->num_q_vectors; i++) {
                adapter->q_vector[i]->cpu = -1;
                ixgbe_update_dca(adapter->q_vector[i]);
        }
}

static int __ixgbe_notify_dca(struct device *dev, void *data)
{
        struct ixgbe_adapter *adapter = dev_get_drvdata(dev);
        unsigned long event = *(unsigned long *)data;

        if (!(adapter->flags & IXGBE_FLAG_DCA_CAPABLE))
                return 0;

        switch (event) {
        case DCA_PROVIDER_ADD:
                /* if we're already enabled, don't do it again */
                if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
                        break;
                if (dca_add_requester(dev) == 0) {
                        adapter->flags |= IXGBE_FLAG_DCA_ENABLED;
                        ixgbe_setup_dca(adapter);
                        break;
                }
                /* Fall Through since DCA is disabled. */
        case DCA_PROVIDER_REMOVE:
                if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
                        dca_remove_requester(dev);
                        adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED;
                        IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 1);
                }
                break;
        }

        return 0;
}

#endif /* CONFIG_IXGBE_DCA */
static inline void ixgbe_rx_hash(struct ixgbe_ring *ring,
                                 union ixgbe_adv_rx_desc *rx_desc,
                                 struct sk_buff *skb)
{
        if (ring->netdev->features & NETIF_F_RXHASH)
                skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
}

#ifdef IXGBE_FCOE
/**
 * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type
 * @ring: structure containing ring specific data
 * @rx_desc: advanced rx descriptor
 *
 * Returns : true if it is FCoE pkt
 */
static inline bool ixgbe_rx_is_fcoe(struct ixgbe_ring *ring,
                                    union ixgbe_adv_rx_desc *rx_desc)
{
        __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;

        return test_bit(__IXGBE_RX_FCOE, &ring->state) &&
               ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) ==
                (cpu_to_le16(IXGBE_ETQF_FILTER_FCOE <<
                             IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT)));
}

#endif /* IXGBE_FCOE */
/**
 * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum
 * @ring: structure containing ring specific data
 * @rx_desc: current Rx descriptor being processed
 * @skb: skb currently being received and modified
 **/
static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
                                     union ixgbe_adv_rx_desc *rx_desc,
                                     struct sk_buff *skb)
{
        skb_checksum_none_assert(skb);

        /* Rx csum disabled */
        if (!(ring->netdev->features & NETIF_F_RXCSUM))
                return;

        /* if IP and error */
        if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) &&
            ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) {
                ring->rx_stats.csum_err++;
                return;
        }

        if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS))
                return;

        if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) {
                __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;

                /*
                 * 82599 errata, UDP frames with a 0 checksum can be marked as
                 * checksum errors.
                 */
                if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_UDP)) &&
                    test_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state))
                        return;

                ring->rx_stats.csum_err++;
                return;
        }

        /* It must be a TCP or UDP packet with a valid checksum */
        skb->ip_summed = CHECKSUM_UNNECESSARY;
}

static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val)
{
        rx_ring->next_to_use = val;

        /* update next to alloc since we have filled the ring */
        rx_ring->next_to_alloc = val;
        /*
         * Force memory writes to complete before letting h/w
         * know there are new descriptors to fetch.  (Only
         * applicable for weak-ordered memory model archs,
         * such as IA-64).
         */
        wmb();
        writel(val, rx_ring->tail);
}

static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
                                    struct ixgbe_rx_buffer *bi)
{
        struct page *page = bi->page;
        dma_addr_t dma = bi->dma;

        /* since we are recycling buffers we should seldom need to alloc */
        if (likely(dma))
                return true;

        /* alloc new page for storage */
        if (likely(!page)) {
                page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP,
                                         bi->skb, ixgbe_rx_pg_order(rx_ring));
                if (unlikely(!page)) {
                        rx_ring->rx_stats.alloc_rx_page_failed++;
                        return false;
                }
                bi->page = page;
        }

        /* map page for use */
        dma = dma_map_page(rx_ring->dev, page, 0,
                           ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);

        /*
         * if mapping failed free memory back to system since
         * there isn't much point in holding memory we can't use
         */
        if (dma_mapping_error(rx_ring->dev, dma)) {
                __free_pages(page, ixgbe_rx_pg_order(rx_ring));
                bi->page = NULL;

                rx_ring->rx_stats.alloc_rx_page_failed++;
                return false;
        }

        bi->dma = dma;
        bi->page_offset = 0;

        return true;
}

/**
 * ixgbe_alloc_rx_buffers - Replace used receive buffers
 * @rx_ring: ring to place buffers on
 * @cleaned_count: number of buffers to replace
 **/
void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
{
        union ixgbe_adv_rx_desc *rx_desc;
        struct ixgbe_rx_buffer *bi;
        u16 i = rx_ring->next_to_use;

        /* nothing to do */
        if (!cleaned_count)
                return;

        rx_desc = IXGBE_RX_DESC(rx_ring, i);
        bi = &rx_ring->rx_buffer_info[i];
        i -= rx_ring->count;

        do {
                if (!ixgbe_alloc_mapped_page(rx_ring, bi))
                        break;

                /*
                 * Refresh the desc even if buffer_addrs didn't change
                 * because each write-back erases this info.
                 */
                rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);

                rx_desc++;
                bi++;
                i++;
                if (unlikely(!i)) {
                        rx_desc = IXGBE_RX_DESC(rx_ring, 0);
                        bi = rx_ring->rx_buffer_info;
                        i -= rx_ring->count;
                }

                /* clear the hdr_addr for the next_to_use descriptor */
                rx_desc->read.hdr_addr = 0;

                cleaned_count--;
        } while (cleaned_count);

        i += rx_ring->count;

        if (rx_ring->next_to_use != i)
                ixgbe_release_rx_desc(rx_ring, i);
}

/**
 * ixgbe_get_headlen - determine size of header for RSC/LRO/GRO/FCOE
 * @data: pointer to the start of the headers
 * @max_len: total length of section to find headers in
 *
 * This function is meant to determine the length of headers that will
 * be recognized by hardware for LRO, GRO, and RSC offloads.  The main
 * motivation of doing this is to only perform one pull for IPv4 TCP
 * packets so that we can do basic things like calculating the gso_size
 * based on the average data per packet.
 **/
static unsigned int ixgbe_get_headlen(unsigned char *data,
                                      unsigned int max_len)
{
        union {
                unsigned char *network;
                /* l2 headers */
                struct ethhdr *eth;
                struct vlan_hdr *vlan;
                /* l3 headers */
                struct iphdr *ipv4;
                struct ipv6hdr *ipv6;
        } hdr;
        __be16 protocol;
        u8 nexthdr = 0; /* default to not TCP */
        u8 hlen;

        /* this should never happen, but better safe than sorry */
        if (max_len < ETH_HLEN)
                return max_len;

        /* initialize network frame pointer */
        hdr.network = data;

        /* set first protocol and move network header forward */
        protocol = hdr.eth->h_proto;
        hdr.network += ETH_HLEN;

        /* handle any vlan tag if present */
        if (protocol == __constant_htons(ETH_P_8021Q)) {
                if ((hdr.network - data) > (max_len - VLAN_HLEN))
                        return max_len;

                protocol = hdr.vlan->h_vlan_encapsulated_proto;
                hdr.network += VLAN_HLEN;
        }

        /* handle L3 protocols */
        if (protocol == __constant_htons(ETH_P_IP)) {
                if ((hdr.network - data) > (max_len - sizeof(struct iphdr)))
                        return max_len;

                /* access ihl as a u8 to avoid unaligned access on ia64 */
                hlen = (hdr.network[0] & 0x0F) << 2;

                /* verify hlen meets minimum size requirements */
                if (hlen < sizeof(struct iphdr))
                        return hdr.network - data;

                /* record next protocol if header is present */
                if (!(hdr.ipv4->frag_off & htons(IP_OFFSET)))
                        nexthdr = hdr.ipv4->protocol;
        } else if (protocol == __constant_htons(ETH_P_IPV6)) {
                if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr)))
                        return max_len;

                /* record next protocol */
                nexthdr = hdr.ipv6->nexthdr;
                hlen = sizeof(struct ipv6hdr);
#ifdef IXGBE_FCOE
        } else if (protocol == __constant_htons(ETH_P_FCOE)) {
                if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN))
                        return max_len;
                hlen = FCOE_HEADER_LEN;
#endif
        } else {
                return hdr.network - data;
        }

        /* relocate pointer to start of L4 header */
        hdr.network += hlen;

        /* finally sort out TCP/UDP */
        if (nexthdr == IPPROTO_TCP) {
                if ((hdr.network - data) > (max_len - sizeof(struct tcphdr)))
                        return max_len;

                /* access doff as a u8 to avoid unaligned access on ia64 */
                hlen = (hdr.network[12] & 0xF0) >> 2;

                /* verify hlen meets minimum size requirements */
                if (hlen < sizeof(struct tcphdr))
                        return hdr.network - data;

                hdr.network += hlen;
        } else if (nexthdr == IPPROTO_UDP) {
                if ((hdr.network - data) > (max_len - sizeof(struct udphdr)))
                        return max_len;

                hdr.network += sizeof(struct udphdr);
        }

        /*
         * If everything has gone correctly hdr.network should be the
         * data section of the packet and will be the end of the header.
         * If not then it probably represents the end of the last recognized
         * header.
         */
        if ((hdr.network - data) < max_len)
                return hdr.network - data;
        else
                return max_len;
}

static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
                                   struct sk_buff *skb)
{
        u16 hdr_len = skb_headlen(skb);

        /* set gso_size to avoid messing up TCP MSS */
        skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len),
                                                 IXGBE_CB(skb)->append_cnt);
        skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
}

static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring,
                                   struct sk_buff *skb)
{
        /* if append_cnt is 0 then frame is not RSC */
        if (!IXGBE_CB(skb)->append_cnt)
                return;

        rx_ring->rx_stats.rsc_count += IXGBE_CB(skb)->append_cnt;
        rx_ring->rx_stats.rsc_flush++;

        ixgbe_set_rsc_gso_size(rx_ring, skb);

        /* gso_size is computed using append_cnt so always clear it last */
        IXGBE_CB(skb)->append_cnt = 0;
}

/**
 * ixgbe_process_skb_fields - Populate skb header fields from Rx descriptor
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @rx_desc: pointer to the EOP Rx descriptor
 * @skb: pointer to current skb being populated
 *
 * This function checks the ring, descriptor, and packet information in
 * order to populate the hash, checksum, VLAN, timestamp, protocol, and
 * other fields within the skb.
 **/
static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
                                     union ixgbe_adv_rx_desc *rx_desc,
                                     struct sk_buff *skb)
{
        struct net_device *dev = rx_ring->netdev;

        ixgbe_update_rsc_stats(rx_ring, skb);

        ixgbe_rx_hash(rx_ring, rx_desc, skb);

        ixgbe_rx_checksum(rx_ring, rx_desc, skb);

        ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);

        if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
            ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
                u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
                __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
        }

        skb_record_rx_queue(skb, rx_ring->queue_index);

        skb->protocol = eth_type_trans(skb, dev);
}

static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
                         struct sk_buff *skb)
{
        struct ixgbe_adapter *adapter = q_vector->adapter;

        if (ixgbe_qv_ll_polling(q_vector))
                netif_receive_skb(skb);
        else if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
                napi_gro_receive(&q_vector->napi, skb);
        else
                netif_rx(skb);
}

/**
 * ixgbe_is_non_eop - process handling of non-EOP buffers
 * @rx_ring: Rx ring being processed
 * @rx_desc: Rx descriptor for current buffer
 * @skb: Current socket buffer containing buffer in progress
 *
 * This function updates next to clean.  If the buffer is an EOP buffer
 * this function exits returning false, otherwise it will place the
 * sk_buff in the next buffer to be chained and return true indicating
 * that this is in fact a non-EOP buffer.
 **/
static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
                             union ixgbe_adv_rx_desc *rx_desc,
                             struct sk_buff *skb)
{
        u32 ntc = rx_ring->next_to_clean + 1;

        /* fetch, update, and store next to clean */
        ntc = (ntc < rx_ring->count) ? ntc : 0;
        rx_ring->next_to_clean = ntc;

        prefetch(IXGBE_RX_DESC(rx_ring, ntc));

        /* update RSC append count if present */
        if (ring_is_rsc_enabled(rx_ring)) {
                __le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data &
                                     cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK);

                if (unlikely(rsc_enabled)) {
                        u32 rsc_cnt = le32_to_cpu(rsc_enabled);

                        rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT;
                        IXGBE_CB(skb)->append_cnt += rsc_cnt - 1;

                        /* update ntc based on RSC value */
                        ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
                        ntc &= IXGBE_RXDADV_NEXTP_MASK;
                        ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
                }
        }

        /* if we are the last buffer then there is nothing else to do */
        if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
                return false;

        /* place skb in next buffer to be received */
        rx_ring->rx_buffer_info[ntc].skb = skb;
        rx_ring->rx_stats.non_eop_descs++;

        return true;
}

/**
 * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @skb: pointer to current skb being adjusted
 *
 * This function is an ixgbe specific version of __pskb_pull_tail.  The
 * main difference between this version and the original function is that
 * this function can make several assumptions about the state of things
 * that allow for significant optimizations versus the standard function.
 * As a result we can do things like drop a frag and maintain an accurate
 * truesize for the skb.
 */
static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
                            struct sk_buff *skb)
{
        struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
        unsigned char *va;
        unsigned int pull_len;

        /*
         * it is valid to use page_address instead of kmap since we are
         * working with pages allocated out of the lomem pool per
         * alloc_page(GFP_ATOMIC)
         */
        va = skb_frag_address(frag);

        /*
         * we need the header to contain the greater of either ETH_HLEN or
         * 60 bytes if the skb->len is less than 60 for skb_pad.
         */
        pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);

        /* align pull length to size of long to optimize memcpy performance */
        skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));

        /* update all of the pointers */
        skb_frag_size_sub(frag, pull_len);
        frag->page_offset += pull_len;
        skb->data_len -= pull_len;
        skb->tail += pull_len;
}

/**
 * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @skb: pointer to current skb being updated
 *
 * This function provides a basic DMA sync up for the first fragment of an
 * skb.  The reason for doing this is that the first fragment cannot be
 * unmapped until we have reached the end of packet descriptor for a buffer
 * chain.
 */
static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
                                struct sk_buff *skb)
{
        /* if the page was released unmap it, else just sync our portion */
        if (unlikely(IXGBE_CB(skb)->page_released)) {
                dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
                               ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
                IXGBE_CB(skb)->page_released = false;
        } else {
                struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];

                dma_sync_single_range_for_cpu(rx_ring->dev,
                                              IXGBE_CB(skb)->dma,
                                              frag->page_offset,
                                              ixgbe_rx_bufsz(rx_ring),
                                              DMA_FROM_DEVICE);
        }
        IXGBE_CB(skb)->dma = 0;
}

/**
 * ixgbe_cleanup_headers - Correct corrupted or empty headers
 * @rx_ring: rx descriptor ring packet is being transacted on
 * @rx_desc: pointer to the EOP Rx descriptor
 * @skb: pointer to current skb being fixed
 *
 * Check for corrupted packet headers caused by senders on the local L2
 * embedded NIC switch not setting up their Tx Descriptors right.  These
 * should be very rare.
 *
 * Also address the case where we are pulling data in on pages only
 * and as such no data is present in the skb header.
 *
 * In addition if skb is not at least 60 bytes we need to pad it so that
 * it is large enough to qualify as a valid Ethernet frame.
 *
 * Returns true if an error was encountered and skb was freed.
 **/
static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
                                  union ixgbe_adv_rx_desc *rx_desc,
                                  struct sk_buff *skb)
{
        struct net_device *netdev = rx_ring->netdev;

        /* verify that the packet does not have any known errors */
        if (unlikely(ixgbe_test_staterr(rx_desc,
                                        IXGBE_RXDADV_ERR_FRAME_ERR_MASK) &&
            !(netdev->features & NETIF_F_RXALL))) {
                dev_kfree_skb_any(skb);
                return true;
        }

        /* place header in linear portion of buffer */
        if (skb_is_nonlinear(skb))
                ixgbe_pull_tail(rx_ring, skb);

#ifdef IXGBE_FCOE
        /* do not attempt to pad FCoE Frames as this will disrupt DDP */
        if (ixgbe_rx_is_fcoe(rx_ring, rx_desc))
                return false;

#endif
        /* if skb_pad returns an error the skb was freed */
        if (unlikely(skb->len < 60)) {
                int pad_len = 60 - skb->len;

                if (skb_pad(skb, pad_len))
                        return true;
                __skb_put(skb, pad_len);
        }

        return false;
}

/**
 * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring
 * @rx_ring: rx descriptor ring to store buffers on
 * @old_buff: donor buffer to have page reused
 *
 * Synchronizes page for reuse by the adapter
 **/
static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
                                struct ixgbe_rx_buffer *old_buff)
{
        struct ixgbe_rx_buffer *new_buff;
        u16 nta = rx_ring->next_to_alloc;

        new_buff = &rx_ring->rx_buffer_info[nta];

        /* update, and store next to alloc */
        nta++;
        rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;

        /* transfer page from old buffer to new buffer */
        new_buff->page = old_buff->page;
        new_buff->dma = old_buff->dma;
        new_buff->page_offset = old_buff->page_offset;

        /* sync the buffer for use by the device */
        dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma,
                                         new_buff->page_offset,
                                         ixgbe_rx_bufsz(rx_ring),
                                         DMA_FROM_DEVICE);
}

/**
 * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff
 * @rx_ring: rx descriptor ring to transact packets on
 * @rx_buffer: buffer containing page to add
 * @rx_desc: descriptor containing length of buffer written by hardware
 * @skb: sk_buff to place the data into
 *
 * This function will add the data contained in rx_buffer->page to the skb.
 * This is done either through a direct copy if the data in the buffer is
 * less than the skb header size, otherwise it will just attach the page as
 * a frag to the skb.
 *
 * The function will then update the page offset if necessary and return
 * true if the buffer can be reused by the adapter.
 **/
static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
                              struct ixgbe_rx_buffer *rx_buffer,
                              union ixgbe_adv_rx_desc *rx_desc,
                              struct sk_buff *skb)
{
        struct page *page = rx_buffer->page;
        unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
#if (PAGE_SIZE < 8192)
        unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
#else
        unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
        unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
                                   ixgbe_rx_bufsz(rx_ring);
#endif

        if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
                unsigned char *va = page_address(page) + rx_buffer->page_offset;

                memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));

                /* we can reuse buffer as-is, just make sure it is local */
                if (likely(page_to_nid(page) == numa_node_id()))
                        return true;

                /* this page cannot be reused so discard it */
                put_page(page);
                return false;
        }

        skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
                        rx_buffer->page_offset, size, truesize);

        /* avoid re-using remote pages */
        if (unlikely(page_to_nid(page) != numa_node_id()))
                return false;

#if (PAGE_SIZE < 8192)
        /* if we are only owner of page we can reuse it */
        if (unlikely(page_count(page) != 1))
                return false;

        /* flip page offset to other buffer */
        rx_buffer->page_offset ^= truesize;

        /*
         * since we are the only owner of the page and we need to
         * increment it, just set the value to 2 in order to avoid
         * an unecessary locked operation
         */
        atomic_set(&page->_count, 2);
#else
        /* move offset up to the next cache line */
        rx_buffer->page_offset += truesize;

        if (rx_buffer->page_offset > last_offset)
                return false;

        /* bump ref count on page before it is given to the stack */
        get_page(page);
#endif

        return true;
}

static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
                                             union ixgbe_adv_rx_desc *rx_desc)
{
        struct ixgbe_rx_buffer *rx_buffer;
        struct sk_buff *skb;
        struct page *page;

        rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
        page = rx_buffer->page;
        prefetchw(page);

        skb = rx_buffer->skb;

        if (likely(!skb)) {
                void *page_addr = page_address(page) +
                                  rx_buffer->page_offset;

                /* prefetch first cache line of first page */
                prefetch(page_addr);
#if L1_CACHE_BYTES < 128
                prefetch(page_addr + L1_CACHE_BYTES);
#endif

                /* allocate a skb to store the frags */
                skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
                                                IXGBE_RX_HDR_SIZE);
                if (unlikely(!skb)) {
                        rx_ring->rx_stats.alloc_rx_buff_failed++;
                        return NULL;
                }

                /*
                 * we will be copying header into skb->data in
                 * pskb_may_pull so it is in our interest to prefetch
                 * it now to avoid a possible cache miss
                 */
                prefetchw(skb->data);

                /*
                 * Delay unmapping of the first packet. It carries the
                 * header information, HW may still access the header
                 * after the writeback.  Only unmap it when EOP is
                 * reached
                 */
                if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
                        goto dma_sync;

                IXGBE_CB(skb)->dma = rx_buffer->dma;
        } else {
                if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
                        ixgbe_dma_sync_frag(rx_ring, skb);

dma_sync:
                /* we are reusing so sync this buffer for CPU use */
                dma_sync_single_range_for_cpu(rx_ring->dev,
                                              rx_buffer->dma,
                                              rx_buffer->page_offset,
                                              ixgbe_rx_bufsz(rx_ring),
                                              DMA_FROM_DEVICE);
        }

        /* pull page into skb */
        if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
                /* hand second half of page back to the ring */
                ixgbe_reuse_rx_page(rx_ring, rx_buffer);
        } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
                /* the page has been released from the ring */
                IXGBE_CB(skb)->page_released = true;
        } else {
                /* we are not reusing the buffer so unmap it */
                dma_unmap_page(rx_ring->dev, rx_buffer->dma,
                               ixgbe_rx_pg_size(rx_ring),
                               DMA_FROM_DEVICE);
        }

        /* clear contents of buffer_info */
        rx_buffer->skb = NULL;
        rx_buffer->dma = 0;
        rx_buffer->page = NULL;

        return skb;
}

/**
 * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
 * @q_vector: structure containing interrupt and ring information
 * @rx_ring: rx descriptor ring to transact packets on
 * @budget: Total limit on number of packets to process
 *
 * This function provides a "bounce buffer" approach to Rx interrupt
 * processing.  The advantage to this is that on systems that have
 * expensive overhead for IOMMU access this provides a means of avoiding
 * it by maintaining the mapping of the page to the syste.
 *
 * Returns amount of work completed
 **/
static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
                               struct ixgbe_ring *rx_ring,
                               const int budget)
{
        unsigned int total_rx_bytes = 0, total_rx_packets = 0;
#ifdef IXGBE_FCOE
        struct ixgbe_adapter *adapter = q_vector->adapter;
        int ddp_bytes;
        unsigned int mss = 0;
#endif /* IXGBE_FCOE */
        u16 cleaned_count = ixgbe_desc_unused(rx_ring);

        do {
                union ixgbe_adv_rx_desc *rx_desc;
                struct sk_buff *skb;

                /* return some buffers to hardware, one at a time is too slow */
                if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
                        ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
                        cleaned_count = 0;
                }

                rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);

                if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD))
                        break;

                /*
                 * This memory barrier is needed to keep us from reading
                 * any other fields out of the rx_desc until we know the
                 * RXD_STAT_DD bit is set
                 */
                rmb();

                /* retrieve a buffer from the ring */
                skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc);

                /* exit if we failed to retrieve a buffer */
                if (!skb)
                        break;

                cleaned_count++;

                /* place incomplete frames back on ring for completion */
                if (ixgbe_is_non_eop(rx_ring, rx_desc, skb))
                        continue;

                /* verify the packet layout is correct */
                if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb))
                        continue;

                /* probably a little skewed due to removing CRC */
                total_rx_bytes += skb->len;

                /* populate checksum, timestamp, VLAN, and protocol */
                ixgbe_process_skb_fields(rx_ring, rx_desc, skb);

#ifdef IXGBE_FCOE
                /* if ddp, not passing to ULD unless for FCP_RSP or error */
                if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) {
                        ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb);
                        /* include DDPed FCoE data */
                        if (ddp_bytes > 0) {
                                if (!mss) {
                                        mss = rx_ring->netdev->mtu -
                                                sizeof(struct fcoe_hdr) -
                                                sizeof(struct fc_frame_header) -
                                                sizeof(struct fcoe_crc_eof);
                                        if (mss > 512)
                                                mss &= ~511;
                                }
                                total_rx_bytes += ddp_bytes;
                                total_rx_packets += DIV_ROUND_UP(ddp_bytes,
                                                                 mss);
                        }
                        if (!ddp_bytes) {
                                dev_kfree_skb_any(skb);
                                continue;
                        }
                }

#endif /* IXGBE_FCOE */
                skb_mark_napi_id(skb, &q_vector->napi);
                ixgbe_rx_skb(q_vector, skb);

                /* update budget accounting */
                total_rx_packets++;
        } while (likely(total_rx_packets < budget));

        u64_stats_update_begin(&rx_ring->syncp);
        rx_ring->stats.packets += total_rx_packets;
        rx_ring->stats.bytes += total_rx_bytes;
        u64_stats_update_end(&rx_ring->syncp);
        q_vector->rx.total_packets += total_rx_packets;
        q_vector->rx.total_bytes += total_rx_bytes;

        if (cleaned_count)
                ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);

        return total_rx_packets;
}

#ifdef CONFIG_NET_RX_BUSY_POLL
/* must be called with local_bh_disable()d */
static int ixgbe_low_latency_recv(struct napi_struct *napi)
{
        struct ixgbe_q_vector *q_vector =
                        container_of(napi, struct ixgbe_q_vector, napi);
        struct ixgbe_adapter *adapter = q_vector->adapter;
        struct ixgbe_ring  *ring;
        int found = 0;

        if (test_bit(__IXGBE_DOWN, &adapter->state))
                return LL_FLUSH_FAILED;

        if (!ixgbe_qv_lock_poll(q_vector))
                return LL_FLUSH_BUSY;

        ixgbe_for_each_ring(ring, q_vector->rx) {
                found = ixgbe_clean_rx_irq(q_vector, ring, 4);
#ifdef LL_EXTENDED_STATS
                if (found)
                        ring->stats.cleaned += found;
                else
                        ring->stats.misses++;
#endif
                if (found)
                        break;
        }

        ixgbe_qv_unlock_poll(q_vector);

        return found;
}
#endif  /* CONFIG_NET_RX_BUSY_POLL */

/**
 * ixgbe_configure_msix - Configure MSI-X hardware
 * @adapter: board private structure
 *
 * ixgbe_configure_msix sets up the hardware to properly generate MSI-X
 * interrupts.
 **/
static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
{
        struct ixgbe_q_vector *q_vector;
        int v_idx;
        u32 mask;

        /* Populate MSIX to EITR Select */
        if (adapter->num_vfs > 32) {
                u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1;
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel);
        }

        /*
         * Populate the IVAR table and set the ITR values to the
         * corresponding register.
         */
        for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) {
                struct ixgbe_ring *ring;
                q_vector = adapter->q_vector[v_idx];

                ixgbe_for_each_ring(ring, q_vector->rx)
                        ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx);

                ixgbe_for_each_ring(ring, q_vector->tx)
                        ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx);

                ixgbe_write_eitr(q_vector);
        }

        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82598EB:
                ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX,
                               v_idx);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                ixgbe_set_ivar(adapter, -1, 1, v_idx);
                break;
        default:
                break;
        }
        IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950);

        /* set up to autoclear timer, and the vectors */
        mask = IXGBE_EIMS_ENABLE_MASK;
        mask &= ~(IXGBE_EIMS_OTHER |
                  IXGBE_EIMS_MAILBOX |
                  IXGBE_EIMS_LSC);

        IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
}

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

/**
 * ixgbe_update_itr - update the dynamic ITR value based on statistics
 * @q_vector: structure containing interrupt and ring information
 * @ring_container: structure containing ring performance data
 *
 *      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 ixgbe_param.c)
 **/
static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
                             struct ixgbe_ring_container *ring_container)
{
        int bytes = ring_container->total_bytes;
        int packets = ring_container->total_packets;
        u32 timepassed_us;
        u64 bytes_perint;
        u8 itr_setting = ring_container->itr;

        if (packets == 0)
                return;

        /* simple throttlerate management
         *   0-10MB/s   lowest (100000 ints/s)
         *  10-20MB/s   low    (20000 ints/s)
         *  20-1249MB/s bulk   (8000 ints/s)
         */
        /* what was last interrupt timeslice? */
        timepassed_us = q_vector->itr >> 2;
        if (timepassed_us == 0)
                return;

        bytes_perint = bytes / timepassed_us; /* bytes/usec */

        switch (itr_setting) {
        case lowest_latency:
                if (bytes_perint > 10)
                        itr_setting = low_latency;
                break;
        case low_latency:
                if (bytes_perint > 20)
                        itr_setting = bulk_latency;
                else if (bytes_perint <= 10)
                        itr_setting = lowest_latency;
                break;
        case bulk_latency:
                if (bytes_perint <= 20)
                        itr_setting = low_latency;
                break;
        }

        /* clear work counters since we have the values we need */
        ring_container->total_bytes = 0;
        ring_container->total_packets = 0;

        /* write updated itr to ring container */
        ring_container->itr = itr_setting;
}

/**
 * ixgbe_write_eitr - write EITR register in hardware specific way
 * @q_vector: structure containing interrupt and ring information
 *
 * This function is made to be called by ethtool and by the driver
 * when it needs to update EITR registers at runtime.  Hardware
 * specific quirks/differences are taken care of here.
 */
void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
{
        struct ixgbe_adapter *adapter = q_vector->adapter;
        struct ixgbe_hw *hw = &adapter->hw;
        int v_idx = q_vector->v_idx;
        u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR;

        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82598EB:
                /* must write high and low 16 bits to reset counter */
                itr_reg |= (itr_reg << 16);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                /*
                 * set the WDIS bit to not clear the timer bits and cause an
                 * immediate assertion of the interrupt
                 */
                itr_reg |= IXGBE_EITR_CNT_WDIS;
                break;
        default:
                break;
        }
        IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
}

static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
{
        u32 new_itr = q_vector->itr;
        u8 current_itr;

        ixgbe_update_itr(q_vector, &q_vector->tx);
        ixgbe_update_itr(q_vector, &q_vector->rx);

        current_itr = max(q_vector->rx.itr, q_vector->tx.itr);

        switch (current_itr) {
        /* counts and packets in update_itr are dependent on these numbers */
        case lowest_latency:
                new_itr = IXGBE_100K_ITR;
                break;
        case low_latency:
                new_itr = IXGBE_20K_ITR;
                break;
        case bulk_latency:
                new_itr = IXGBE_8K_ITR;
                break;
        default:
                break;
        }

        if (new_itr != q_vector->itr) {
                /* do an exponential smoothing */
                new_itr = (10 * new_itr * q_vector->itr) /
                          ((9 * new_itr) + q_vector->itr);

                /* save the algorithm value here */
                q_vector->itr = new_itr;

                ixgbe_write_eitr(q_vector);
        }
}

/**
 * ixgbe_check_overtemp_subtask - check for over temperature
 * @adapter: pointer to adapter
 **/
static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u32 eicr = adapter->interrupt_event;

        if (test_bit(__IXGBE_DOWN, &adapter->state))
                return;

        if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
            !(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_EVENT))
                return;

        adapter->flags2 &= ~IXGBE_FLAG2_TEMP_SENSOR_EVENT;

        switch (hw->device_id) {
        case IXGBE_DEV_ID_82599_T3_LOM:
                /*
                 * Since the warning interrupt is for both ports
                 * we don't have to check if:
                 *  - This interrupt wasn't for our port.
                 *  - We may have missed the interrupt so always have to
                 *    check if we  got a LSC
                 */
                if (!(eicr & IXGBE_EICR_GPI_SDP0) &&
                    !(eicr & IXGBE_EICR_LSC))
                        return;

                if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) {
                        u32 speed;
                        bool link_up = false;

                        hw->mac.ops.check_link(hw, &speed, &link_up, false);

                        if (link_up)
                                return;
                }

                /* Check if this is not due to overtemp */
                if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP)
                        return;

                break;
        default:
                if (!(eicr & IXGBE_EICR_GPI_SDP0))
                        return;
                break;
        }
        e_crit(drv,
               "Network adapter has been stopped because it has over heated. "
               "Restart the computer. If the problem persists, "
               "power off the system and replace the adapter\n");

        adapter->interrupt_event = 0;
}

static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr)
{
        struct ixgbe_hw *hw = &adapter->hw;

        if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) &&
            (eicr & IXGBE_EICR_GPI_SDP1)) {
                e_crit(probe, "Fan has stopped, replace the adapter\n");
                /* write to clear the interrupt */
                IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
        }
}

static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
        if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE))
                return;

        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82599EB:
                /*
                 * Need to check link state so complete overtemp check
                 * on service task
                 */
                if (((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)) &&
                    (!test_bit(__IXGBE_DOWN, &adapter->state))) {
                        adapter->interrupt_event = eicr;
                        adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT;
                        ixgbe_service_event_schedule(adapter);
                        return;
                }
                return;
        case ixgbe_mac_X540:
                if (!(eicr & IXGBE_EICR_TS))
                        return;
                break;
        default:
                return;
        }

        e_crit(drv,
               "Network adapter has been stopped because it has over heated. "
               "Restart the computer. If the problem persists, "
               "power off the system and replace the adapter\n");
}

static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
        struct ixgbe_hw *hw = &adapter->hw;

        if (eicr & IXGBE_EICR_GPI_SDP2) {
                /* Clear the interrupt */
                IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
                if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
                        adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
                        ixgbe_service_event_schedule(adapter);
                }
        }

        if (eicr & IXGBE_EICR_GPI_SDP1) {
                /* Clear the interrupt */
                IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
                if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
                        adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
                        ixgbe_service_event_schedule(adapter);
                }
        }
}

static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;

        adapter->lsc_int++;
        adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
        adapter->link_check_timeout = jiffies;
        if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
                IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC);
                IXGBE_WRITE_FLUSH(hw);
                ixgbe_service_event_schedule(adapter);
        }
}

static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
                                           u64 qmask)
{
        u32 mask;
        struct ixgbe_hw *hw = &adapter->hw;

        switch (hw->mac.type) {
        case ixgbe_mac_82598EB:
                mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
                IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                mask = (qmask & 0xFFFFFFFF);
                if (mask)
                        IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
                mask = (qmask >> 32);
                if (mask)
                        IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
                break;
        default:
                break;
        }
        /* skip the flush */
}

static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
                                            u64 qmask)
{
        u32 mask;
        struct ixgbe_hw *hw = &adapter->hw;

        switch (hw->mac.type) {
        case ixgbe_mac_82598EB:
                mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
                IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                mask = (qmask & 0xFFFFFFFF);
                if (mask)
                        IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask);
                mask = (qmask >> 32);
                if (mask)
                        IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask);
                break;
        default:
                break;
        }
        /* skip the flush */
}

/**
 * ixgbe_irq_enable - Enable default interrupt generation settings
 * @adapter: board private structure
 **/
static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
                                    bool flush)
{
        u32 mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);

        /* don't reenable LSC while waiting for link */
        if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)
                mask &= ~IXGBE_EIMS_LSC;

        if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
                switch (adapter->hw.mac.type) {
                case ixgbe_mac_82599EB:
                        mask |= IXGBE_EIMS_GPI_SDP0;
                        break;
                case ixgbe_mac_X540:
                        mask |= IXGBE_EIMS_TS;
                        break;
                default:
                        break;
                }
        if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
                mask |= IXGBE_EIMS_GPI_SDP1;
        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82599EB:
                mask |= IXGBE_EIMS_GPI_SDP1;
                mask |= IXGBE_EIMS_GPI_SDP2;
        case ixgbe_mac_X540:
                mask |= IXGBE_EIMS_ECC;
                mask |= IXGBE_EIMS_MAILBOX;
                break;
        default:
                break;
        }

        if (adapter->hw.mac.type == ixgbe_mac_X540)
                mask |= IXGBE_EIMS_TIMESYNC;

        if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
            !(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT))
                mask |= IXGBE_EIMS_FLOW_DIR;

        IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
        if (queues)
                ixgbe_irq_enable_queues(adapter, ~0);
        if (flush)
                IXGBE_WRITE_FLUSH(&adapter->hw);
}

static irqreturn_t ixgbe_msix_other(int irq, void *data)
{
        struct ixgbe_adapter *adapter = data;
        struct ixgbe_hw *hw = &adapter->hw;
        u32 eicr;

        /*
         * Workaround for Silicon errata.  Use clear-by-write instead
         * of clear-by-read.  Reading with EICS will return the
         * interrupt causes without clearing, which later be done
         * with the write to EICR.
         */
        eicr = IXGBE_READ_REG(hw, IXGBE_EICS);

        /* The lower 16bits of the EICR register are for the queue interrupts
         * which should be masked here in order to not accidently clear them if
         * the bits are high when ixgbe_msix_other is called. There is a race
         * condition otherwise which results in possible performance loss
         * especially if the ixgbe_msix_other interrupt is triggering
         * consistently (as it would when PPS is turned on for the X540 device)
         */
        eicr &= 0xFFFF0000;

        IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr);

        if (eicr & IXGBE_EICR_LSC)
                ixgbe_check_lsc(adapter);

        if (eicr & IXGBE_EICR_MAILBOX)
                ixgbe_msg_task(adapter);

        switch (hw->mac.type) {
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                if (eicr & IXGBE_EICR_ECC)
                        e_info(link, "Received unrecoverable ECC Err, please "
                               "reboot\n");
                /* Handle Flow Director Full threshold interrupt */
                if (eicr & IXGBE_EICR_FLOW_DIR) {
                        int reinit_count = 0;
                        int i;
                        for (i = 0; i < adapter->num_tx_queues; i++) {
                                struct ixgbe_ring *ring = adapter->tx_ring[i];
                                if (test_and_clear_bit(__IXGBE_TX_FDIR_INIT_DONE,
                                                       &ring->state))
                                        reinit_count++;
                        }
                        if (reinit_count) {
                                /* no more flow director interrupts until after init */
                                IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_FLOW_DIR);
                                adapter->flags2 |= IXGBE_FLAG2_FDIR_REQUIRES_REINIT;
                                ixgbe_service_event_schedule(adapter);
                        }
                }
                ixgbe_check_sfp_event(adapter, eicr);
                ixgbe_check_overtemp_event(adapter, eicr);
                break;
        default:
                break;
        }

        ixgbe_check_fan_failure(adapter, eicr);

        if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
                ixgbe_ptp_check_pps_event(adapter, eicr);

        /* re-enable the original interrupt state, no lsc, no queues */
        if (!test_bit(__IXGBE_DOWN, &adapter->state))
                ixgbe_irq_enable(adapter, false, false);

        return IRQ_HANDLED;
}

static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data)
{
        struct ixgbe_q_vector *q_vector = data;

        /* EIAM disabled interrupts (on this vector) for us */

        if (q_vector->rx.ring || q_vector->tx.ring)
                napi_schedule(&q_vector->napi);

        return IRQ_HANDLED;
}

/**
 * ixgbe_poll - NAPI Rx polling callback
 * @napi: structure for representing this polling device
 * @budget: how many packets driver is allowed to clean
 *
 * This function is used for legacy and MSI, NAPI mode
 **/
int ixgbe_poll(struct napi_struct *napi, int budget)
{
        struct ixgbe_q_vector *q_vector =
                                container_of(napi, struct ixgbe_q_vector, napi);
        struct ixgbe_adapter *adapter = q_vector->adapter;
        struct ixgbe_ring *ring;
        int per_ring_budget;
        bool clean_complete = true;

#ifdef CONFIG_IXGBE_DCA
        if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
                ixgbe_update_dca(q_vector);
#endif

        ixgbe_for_each_ring(ring, q_vector->tx)
                clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring);

        if (!ixgbe_qv_lock_napi(q_vector))
                return budget;

        /* attempt to distribute budget to each queue fairly, but don't allow
         * the budget to go below 1 because we'll exit polling */
        if (q_vector->rx.count > 1)
                per_ring_budget = max(budget/q_vector->rx.count, 1);
        else
                per_ring_budget = budget;

        ixgbe_for_each_ring(ring, q_vector->rx)
                clean_complete &= (ixgbe_clean_rx_irq(q_vector, ring,
                                   per_ring_budget) < per_ring_budget);

        ixgbe_qv_unlock_napi(q_vector);
        /* If all work not completed, return budget and keep polling */
        if (!clean_complete)
                return budget;

        /* all work done, exit the polling mode */
        napi_complete(napi);
        if (adapter->rx_itr_setting & 1)
                ixgbe_set_itr(q_vector);
        if (!test_bit(__IXGBE_DOWN, &adapter->state))
                ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));

        return 0;
}

/**
 * ixgbe_request_msix_irqs - Initialize MSI-X interrupts
 * @adapter: board private structure
 *
 * ixgbe_request_msix_irqs allocates MSI-X vectors and requests
 * interrupts from the kernel.
 **/
static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        int vector, err;
        int ri = 0, ti = 0;

        for (vector = 0; vector < adapter->num_q_vectors; vector++) {
                struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
                struct msix_entry *entry = &adapter->msix_entries[vector];

                if (q_vector->tx.ring && q_vector->rx.ring) {
                        snprintf(q_vector->name, sizeof(q_vector->name) - 1,
                                 "%s-%s-%d", netdev->name, "TxRx", ri++);
                        ti++;
                } else if (q_vector->rx.ring) {
                        snprintf(q_vector->name, sizeof(q_vector->name) - 1,
                                 "%s-%s-%d", netdev->name, "rx", ri++);
                } else if (q_vector->tx.ring) {
                        snprintf(q_vector->name, sizeof(q_vector->name) - 1,
                                 "%s-%s-%d", netdev->name, "tx", ti++);
                } else {
                        /* skip this unused q_vector */
                        continue;
                }
                err = request_irq(entry->vector, &ixgbe_msix_clean_rings, 0,
                                  q_vector->name, q_vector);
                if (err) {
                        e_err(probe, "request_irq failed for MSIX interrupt "
                              "Error: %d\n", err);
                        goto free_queue_irqs;
                }
                /* If Flow Director is enabled, set interrupt affinity */
                if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
                        /* assign the mask for this irq */
                        irq_set_affinity_hint(entry->vector,
                                              &q_vector->affinity_mask);
                }
        }

        err = request_irq(adapter->msix_entries[vector].vector,
                          ixgbe_msix_other, 0, netdev->name, adapter);
        if (err) {
                e_err(probe, "request_irq for msix_other failed: %d\n", err);
                goto free_queue_irqs;
        }

        return 0;

free_queue_irqs:
        while (vector) {
                vector--;
                irq_set_affinity_hint(adapter->msix_entries[vector].vector,
                                      NULL);
                free_irq(adapter->msix_entries[vector].vector,
                         adapter->q_vector[vector]);
        }
        adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
        pci_disable_msix(adapter->pdev);
        kfree(adapter->msix_entries);
        adapter->msix_entries = NULL;
        return err;
}

/**
 * ixgbe_intr - legacy mode Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t ixgbe_intr(int irq, void *data)
{
        struct ixgbe_adapter *adapter = data;
        struct ixgbe_hw *hw = &adapter->hw;
        struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
        u32 eicr;

        /*
         * Workaround for silicon errata #26 on 82598.  Mask the interrupt
         * before the read of EICR.
         */
        IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK);

        /* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read
         * therefore no explicit interrupt disable is necessary */
        eicr = IXGBE_READ_REG(hw, IXGBE_EICR);
        if (!eicr) {
                /*
                 * shared interrupt alert!
                 * make sure interrupts are enabled because the read will
                 * have disabled interrupts due to EIAM
                 * finish the workaround of silicon errata on 82598.  Unmask
                 * the interrupt that we masked before the EICR read.
                 */
                if (!test_bit(__IXGBE_DOWN, &adapter->state))
                        ixgbe_irq_enable(adapter, true, true);
                return IRQ_NONE;        /* Not our interrupt */
        }

        if (eicr & IXGBE_EICR_LSC)
                ixgbe_check_lsc(adapter);

        switch (hw->mac.type) {
        case ixgbe_mac_82599EB:
                ixgbe_check_sfp_event(adapter, eicr);
                /* Fall through */
        case ixgbe_mac_X540:
                if (eicr & IXGBE_EICR_ECC)
                        e_info(link, "Received unrecoverable ECC err, please "
                                     "reboot\n");
                ixgbe_check_overtemp_event(adapter, eicr);
                break;
        default:
                break;
        }

        ixgbe_check_fan_failure(adapter, eicr);
        if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
                ixgbe_ptp_check_pps_event(adapter, eicr);

        /* would disable interrupts here but EIAM disabled it */
        napi_schedule(&q_vector->napi);

        /*
         * re-enable link(maybe) and non-queue interrupts, no flush.
         * ixgbe_poll will re-enable the queue interrupts
         */
        if (!test_bit(__IXGBE_DOWN, &adapter->state))
                ixgbe_irq_enable(adapter, false, false);

        return IRQ_HANDLED;
}

/**
 * ixgbe_request_irq - initialize interrupts
 * @adapter: board private structure
 *
 * Attempts to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
static int ixgbe_request_irq(struct ixgbe_adapter *adapter)
{
        struct net_device *netdev = adapter->netdev;
        int err;

        if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
                err = ixgbe_request_msix_irqs(adapter);
        else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED)
                err = request_irq(adapter->pdev->irq, ixgbe_intr, 0,
                                  netdev->name, adapter);
        else
                err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED,
                                  netdev->name, adapter);

        if (err)
                e_err(probe, "request_irq failed, Error %d\n", err);

        return err;
}

static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
{
        int vector;

        if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
                free_irq(adapter->pdev->irq, adapter);
                return;
        }

        for (vector = 0; vector < adapter->num_q_vectors; vector++) {
                struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
                struct msix_entry *entry = &adapter->msix_entries[vector];

                /* free only the irqs that were actually requested */
                if (!q_vector->rx.ring && !q_vector->tx.ring)
                        continue;

                /* clear the affinity_mask in the IRQ descriptor */
                irq_set_affinity_hint(entry->vector, NULL);

                free_irq(entry->vector, q_vector);
        }

        free_irq(adapter->msix_entries[vector++].vector, adapter);
}

/**
 * ixgbe_irq_disable - Mask off interrupt generation on the NIC
 * @adapter: board private structure
 **/
static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
{
        switch (adapter->hw.mac.type) {
        case ixgbe_mac_82598EB:
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0);
                break;
        case ixgbe_mac_82599EB:
        case ixgbe_mac_X540:
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
                IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
                break;
        default:
                break;
        }
        IXGBE_WRITE_FLUSH(&adapter->hw);
        if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
                int vector;

                for (vector = 0; vector < adapter->num_q_vectors; vector++)
                        synchronize_irq(adapter->msix_entries[vector].vector);

                synchronize_irq(adapter->msix_entries[vector++].vector);
        } else {
                synchronize_irq(adapter->pdev->irq);
        }
}

/**
 * ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts
 *
 **/
static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter)
{
        struct ixgbe_q_vector *q_vector = adapter->q_vector[0];

        ixgbe_write_eitr(q_vector);

        ixgbe_set_ivar(adapter, 0, 0, 0);
        ixgbe_set_ivar(adapter, 1, 0, 0);

        e_info(hw, "Legacy interrupt IVAR setup done\n");
}

/**
 * ixgbe_configure_tx_ring - Configure 8259x Tx ring after Reset
 * @adapter: board private structure
 * @ring: structure containing ring specific data
 *
 * Configure the Tx descriptor ring after a reset.
 **/
void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
                             struct ixgbe_ring *ring)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u64 tdba = ring->dma;
        int wait_loop = 10;
        u32 txdctl = IXGBE_TXDCTL_ENABLE;
        u8 reg_idx = ring->reg_idx;

        /* disable queue to avoid issues while updating state */
        IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
        IXGBE_WRITE_FLUSH(hw);

        IXGBE_WRITE_REG(hw, IXGBE_TDBAL(reg_idx),
                        (tdba & DMA_BIT_MASK(32)));
        IXGBE_WRITE_REG(hw, IXGBE_TDBAH(reg_idx), (tdba >> 32));
        IXGBE_WRITE_REG(hw, IXGBE_TDLEN(reg_idx),
                        ring->count * sizeof(union ixgbe_adv_tx_desc));
        IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0);
        IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0);
        ring->tail = hw->hw_addr + IXGBE_TDT(reg_idx);

        /*
         * set WTHRESH to encourage burst writeback, it should not be set
         * higher than 1 when:
         * - ITR is 0 as it could cause false TX hangs
         * - ITR is set to > 100k int/sec and BQL is enabled
         *
         * In order to avoid issues WTHRESH + PTHRESH should always be equal
         * to or less than the number of on chip descriptors, which is
         * currently 40.
         */
#if IS_ENABLED(CONFIG_BQL)
        if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR))
#else
        if (!ring->q_vector || (ring->q_vector->itr < 8))
#endif
                txdctl |= (1 << 16);    /* WTHRESH = 1 */
        else
                txdctl |= (8 << 16);    /* WTHRESH = 8 */

        /*
         * Setting PTHRESH to 32 both improves performance
         * and avoids a TX hang with DFP enabled
         */
        txdctl |= (1 << 8) |    /* HTHRESH = 1 */
                   32;          /* PTHRESH = 32 */

        /* reinitialize flowdirector state */
        if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
                ring->atr_sample_rate = adapter->atr_sample_rate;
                ring->atr_count = 0;
                set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state);
        } else {
                ring->atr_sample_rate = 0;
        }

        /* initialize XPS */
        if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) {
                struct ixgbe_q_vector *q_vector = ring->q_vector;

                if (q_vector)
                        netif_set_xps_queue(adapter->netdev,
                                            &q_vector->affinity_mask,
                                            ring->queue_index);
        }

        clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);

        /* enable queue */
        IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);

        /* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */
        if (hw->mac.type == ixgbe_mac_82598EB &&
            !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
                return;

        /* poll to verify queue is enabled */
        do {
                usleep_range(1000, 2000);
                txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
        } while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE));
        if (!wait_loop)
                e_err(drv, "Could not enable Tx Queue %d\n", reg_idx);
}

static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter)
{
        struct ixgbe_hw *hw = &adapter->hw;
        u32 rttdcs, mtqc;
        u8 tcs = netdev_get_num_tc(adapter->netdev);

        if (hw->mac.type == ixgbe_mac_82598EB)
                return;

        /* disable the arbiter while setting MTQC */
        rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS);
        rttdcs |= IXGBE_RTTDCS_ARBDIS;
        IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);

        /* set transmit pool layout */
        if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
                mtqc = IXGBE_MTQC_VT_ENA;
                if (tcs > 4)
                        mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
                else if (tcs > 1)
                        mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
                else if (adapter->ring_feature[RING_F_RSS].indices == 4)
                        mtqc |= IXGBE_MTQC_32VF;
                else
                        mtqc |= IXGBE_MTQC_64VF;
        } else {
                if (tcs > 4)
                        mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
                else if (tcs > 1)
                        mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
                else
                        mtqc = IXGBE_MTQC_64Q_1PB;
        }

        IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc);

        /* Enable Security TX Buffer IFG for multiple pb */
        if (tcs) {
                u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
                sectx |= IXGBE_SECTX_DCB;
                IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx);
        }

        /* re-enable the arbiter */
        rttdcs &= ~IXGBE_RTTDCS_ARBDIS;
        IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
}

/**
 * ixgbe_configure_tx - Configure 8259x Transmit Unit after Reset