/*
 * originally based on the dummy device.
 *
 * Copyright 1999, Thomas Davis, tadavis@lbl.gov.
 * Licensed under the GPL. Based on dummy.c, and eql.c devices.
 *
 * bonding.c: an Ethernet Bonding driver
 *
 * This is useful to talk to a Cisco EtherChannel compatible equipment:
 *      Cisco 5500
 *      Sun Trunking (Solaris)
 *      Alteon AceDirector Trunks
 *      Linux Bonding
 *      and probably many L2 switches ...
 *
 * How it works:
 *    ifconfig bond0 ipaddress netmask up
 *      will setup a network device, with an ip address.  No mac address
 *      will be assigned at this time.  The hw mac address will come from
 *      the first slave bonded to the channel.  All slaves will then use
 *      this hw mac address.
 *
 *    ifconfig bond0 down
 *         will release all slaves, marking them as down.
 *
 *    ifenslave bond0 eth0
 *      will attach eth0 to bond0 as a slave.  eth0 hw mac address will either
 *      a: be used as initial mac address
 *      b: if a hw mac address already is there, eth0's hw mac address
 *         will then be set from bond0.
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <net/ip.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <asm/system.h>
#include <asm/dma.h>
#include <linux/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include <linux/jiffies.h>
#include <net/route.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"

/*---------------------------- Module parameters ----------------------------*/

/* monitor all links that often (in milliseconds). <=0 disables monitoring */
#define BOND_LINK_MON_INTERV    0
#define BOND_LINK_ARP_INTERV    0

static int max_bonds    = BOND_DEFAULT_MAX_BONDS;
static int num_grat_arp = 1;
static int num_unsol_na = 1;
static int miimon       = BOND_LINK_MON_INTERV;
static int updelay;
static int downdelay;
static int use_carrier  = 1;
static char *mode;
static char *primary;
static char *primary_reselect;
static char *lacp_rate;
static char *ad_select;
static char *xmit_hash_policy;
static int arp_interval = BOND_LINK_ARP_INTERV;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
static char *arp_validate;
static char *fail_over_mac;
static struct bond_params bonding_defaults;

module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(num_grat_arp, int, 0644);
MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
module_param(num_unsol_na, int, 0644);
MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds");
module_param(downdelay, int, 0);
MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
                            "in milliseconds");
module_param(use_carrier, int, 0);
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
                              "0 for off, 1 for on (default)");
module_param(mode, charp, 0);
MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
                       "1 for active-backup, 2 for balance-xor, "
                       "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
                       "6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(primary_reselect, charp, 0);
MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
                                   "once it comes up; "
                                   "0 for always (default), "
                                   "1 for only if speed of primary is "
                                   "better, "
                                   "2 for only on active slave "
                                   "failure");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
                            "(slow/fast)");
module_param(ad_select, charp, 0);
MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)");
module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
                                   ", 1 for layer 3+4");
module_param(arp_interval, int, 0);
MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
module_param_array(arp_ip_target, charp, NULL, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
module_param(arp_validate, charp, 0);
MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all");
module_param(fail_over_mac, charp, 0);
MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC.  none (default), active or follow");

/*----------------------------- Global variables ----------------------------*/

static const char * const version =
        DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";

int bond_net_id __read_mostly;

static __be32 arp_target[BOND_MAX_ARP_TARGETS];
static int arp_ip_count;
static int bond_mode    = BOND_MODE_ROUNDROBIN;
static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
static int lacp_fast;


const struct bond_parm_tbl bond_lacp_tbl[] = {
{       "slow",         AD_LACP_SLOW},
{       "fast",         AD_LACP_FAST},
{       NULL,           -1},
};

const struct bond_parm_tbl bond_mode_tbl[] = {
{       "balance-rr",           BOND_MODE_ROUNDROBIN},
{       "active-backup",        BOND_MODE_ACTIVEBACKUP},
{       "balance-xor",          BOND_MODE_XOR},
{       "broadcast",            BOND_MODE_BROADCAST},
{       "802.3ad",              BOND_MODE_8023AD},
{       "balance-tlb",          BOND_MODE_TLB},
{       "balance-alb",          BOND_MODE_ALB},
{       NULL,                   -1},
};

const struct bond_parm_tbl xmit_hashtype_tbl[] = {
{       "layer2",               BOND_XMIT_POLICY_LAYER2},
{       "layer3+4",             BOND_XMIT_POLICY_LAYER34},
{       "layer2+3",             BOND_XMIT_POLICY_LAYER23},
{       NULL,                   -1},
};

const struct bond_parm_tbl arp_validate_tbl[] = {
{       "none",                 BOND_ARP_VALIDATE_NONE},
{       "active",               BOND_ARP_VALIDATE_ACTIVE},
{       "backup",               BOND_ARP_VALIDATE_BACKUP},
{       "all",                  BOND_ARP_VALIDATE_ALL},
{       NULL,                   -1},
};

const struct bond_parm_tbl fail_over_mac_tbl[] = {
{       "none",                 BOND_FOM_NONE},
{       "active",               BOND_FOM_ACTIVE},
{       "follow",               BOND_FOM_FOLLOW},
{       NULL,                   -1},
};

const struct bond_parm_tbl pri_reselect_tbl[] = {
{       "always",               BOND_PRI_RESELECT_ALWAYS},
{       "better",               BOND_PRI_RESELECT_BETTER},
{       "failure",              BOND_PRI_RESELECT_FAILURE},
{       NULL,                   -1},
};

struct bond_parm_tbl ad_select_tbl[] = {
{       "stable",       BOND_AD_STABLE},
{       "bandwidth",    BOND_AD_BANDWIDTH},
{       "count",        BOND_AD_COUNT},
{       NULL,           -1},
};

/*-------------------------- Forward declarations ---------------------------*/

static void bond_send_gratuitous_arp(struct bonding *bond);
static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);

/*---------------------------- General routines -----------------------------*/

static const char *bond_mode_name(int mode)
{
        static const char *names[] = {
                [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)",
                [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)",
                [BOND_MODE_XOR] = "load balancing (xor)",
                [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)",
                [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation",
                [BOND_MODE_TLB] = "transmit load balancing",
                [BOND_MODE_ALB] = "adaptive load balancing",
        };

        if (mode < 0 || mode > BOND_MODE_ALB)
                return "unknown";

        return names[mode];
}

/*---------------------------------- VLAN -----------------------------------*/

/**
 * bond_add_vlan - add a new vlan id on bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to add
 *
 * Returns -ENOMEM if allocation failed.
 */
static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id)
{
        struct vlan_entry *vlan;

        pr_debug("bond: %s, vlan id %d\n",
                 (bond ? bond->dev->name : "None"), vlan_id);

        vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL);
        if (!vlan)
                return -ENOMEM;

        INIT_LIST_HEAD(&vlan->vlan_list);
        vlan->vlan_id = vlan_id;

        write_lock_bh(&bond->lock);

        list_add_tail(&vlan->vlan_list, &bond->vlan_list);

        write_unlock_bh(&bond->lock);

        pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);

        return 0;
}

/**
 * bond_del_vlan - delete a vlan id from bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to delete
 *
 * returns -ENODEV if @vlan_id was not found in @bond.
 */
static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id)
{
        struct vlan_entry *vlan;
        int res = -ENODEV;

        pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id);

        write_lock_bh(&bond->lock);

        list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
                if (vlan->vlan_id == vlan_id) {
                        list_del(&vlan->vlan_list);

                        if (bond_is_lb(bond))
                                bond_alb_clear_vlan(bond, vlan_id);

                        pr_debug("removed VLAN ID %d from bond %s\n",
                                 vlan_id, bond->dev->name);

                        kfree(vlan);

                        if (list_empty(&bond->vlan_list) &&
                            (bond->slave_cnt == 0)) {
                                /* Last VLAN removed and no slaves, so
                                 * restore block on adding VLANs. This will
                                 * be removed once new slaves that are not
                                 * VLAN challenged will be added.
                                 */
                                bond->dev->features |= NETIF_F_VLAN_CHALLENGED;
                        }

                        res = 0;
                        goto out;
                }
        }

        pr_debug("couldn't find VLAN ID %d in bond %s\n",
                 vlan_id, bond->dev->name);

out:
        write_unlock_bh(&bond->lock);
        return res;
}

/**
 * bond_has_challenged_slaves
 * @bond: the bond we're working on
 *
 * Searches the slave list. Returns 1 if a vlan challenged slave
 * was found, 0 otherwise.
 *
 * Assumes bond->lock is held.
 */
static int bond_has_challenged_slaves(struct bonding *bond)
{
        struct slave *slave;
        int i;

        bond_for_each_slave(bond, slave, i) {
                if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) {
                        pr_debug("found VLAN challenged slave - %s\n",
                                 slave->dev->name);
                        return 1;
                }
        }

        pr_debug("no VLAN challenged slaves found\n");
        return 0;
}

/**
 * bond_next_vlan - safely skip to the next item in the vlans list.
 * @bond: the bond we're working on
 * @curr: item we're advancing from
 *
 * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL,
 * or @curr->next otherwise (even if it is @curr itself again).
 *
 * Caller must hold bond->lock
 */
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
{
        struct vlan_entry *next, *last;

        if (list_empty(&bond->vlan_list))
                return NULL;

        if (!curr) {
                next = list_entry(bond->vlan_list.next,
                                  struct vlan_entry, vlan_list);
        } else {
                last = list_entry(bond->vlan_list.prev,
                                  struct vlan_entry, vlan_list);
                if (last == curr) {
                        next = list_entry(bond->vlan_list.next,
                                          struct vlan_entry, vlan_list);
                } else {
                        next = list_entry(curr->vlan_list.next,
                                          struct vlan_entry, vlan_list);
                }
        }

        return next;
}

/**
 * bond_dev_queue_xmit - Prepare skb for xmit.
 *
 * @bond: bond device that got this skb for tx.
 * @skb: hw accel VLAN tagged skb to transmit
 * @slave_dev: slave that is supposed to xmit this skbuff
 *
 * When the bond gets an skb to transmit that is
 * already hardware accelerated VLAN tagged, and it
 * needs to relay this skb to a slave that is not
 * hw accel capable, the skb needs to be "unaccelerated",
 * i.e. strip the hwaccel tag and re-insert it as part
 * of the payload.
 */
int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
                        struct net_device *slave_dev)
{
        unsigned short uninitialized_var(vlan_id);

        if (!list_empty(&bond->vlan_list) &&
            !(slave_dev->features & NETIF_F_HW_VLAN_TX) &&
            vlan_get_tag(skb, &vlan_id) == 0) {
                skb->dev = slave_dev;
                skb = vlan_put_tag(skb, vlan_id);
                if (!skb) {
                        /* vlan_put_tag() frees the skb in case of error,
                         * so return success here so the calling functions
                         * won't attempt to free is again.
                         */
                        return 0;
                }
        } else {
                skb->dev = slave_dev;
        }

        skb->priority = 1;
        dev_queue_xmit(skb);

        return 0;
}

/*
 * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid
 * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a
 * lock because:
 * a. This operation is performed in IOCTL context,
 * b. The operation is protected by the RTNL semaphore in the 8021q code,
 * c. Holding a lock with BH disabled while directly calling a base driver
 *    entry point is generally a BAD idea.
 *
 * The design of synchronization/protection for this operation in the 8021q
 * module is good for one or more VLAN devices over a single physical device
 * and cannot be extended for a teaming solution like bonding, so there is a
 * potential race condition here where a net device from the vlan group might
 * be referenced (either by a base driver or the 8021q code) while it is being
 * removed from the system. However, it turns out we're not making matters
 * worse, and if it works for regular VLAN usage it will work here too.
*/

/**
 * bond_vlan_rx_register - Propagates registration to slaves
 * @bond_dev: bonding net device that got called
 * @grp: vlan group being registered
 */
static void bond_vlan_rx_register(struct net_device *bond_dev,
                                  struct vlan_group *grp)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave;
        int i;

        bond->vlgrp = grp;

        bond_for_each_slave(bond, slave, i) {
                struct net_device *slave_dev = slave->dev;
                const struct net_device_ops *slave_ops = slave_dev->netdev_ops;

                if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
                    slave_ops->ndo_vlan_rx_register) {
                        slave_ops->ndo_vlan_rx_register(slave_dev, grp);
                }
        }
}

/**
 * bond_vlan_rx_add_vid - Propagates adding an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being added
 */
static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave;
        int i, res;

        bond_for_each_slave(bond, slave, i) {
                struct net_device *slave_dev = slave->dev;
                const struct net_device_ops *slave_ops = slave_dev->netdev_ops;

                if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
                    slave_ops->ndo_vlan_rx_add_vid) {
                        slave_ops->ndo_vlan_rx_add_vid(slave_dev, vid);
                }
        }

        res = bond_add_vlan(bond, vid);
        if (res) {
                pr_err("%s: Error: Failed to add vlan id %d\n",
                       bond_dev->name, vid);
        }
}

/**
 * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being removed
 */
static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave;
        struct net_device *vlan_dev;
        int i, res;

        bond_for_each_slave(bond, slave, i) {
                struct net_device *slave_dev = slave->dev;
                const struct net_device_ops *slave_ops = slave_dev->netdev_ops;

                if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
                    slave_ops->ndo_vlan_rx_kill_vid) {
                        /* Save and then restore vlan_dev in the grp array,
                         * since the slave's driver might clear it.
                         */
                        vlan_dev = vlan_group_get_device(bond->vlgrp, vid);
                        slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid);
                        vlan_group_set_device(bond->vlgrp, vid, vlan_dev);
                }
        }

        res = bond_del_vlan(bond, vid);
        if (res) {
                pr_err("%s: Error: Failed to remove vlan id %d\n",
                       bond_dev->name, vid);
        }
}

static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
{
        struct vlan_entry *vlan;
        const struct net_device_ops *slave_ops = slave_dev->netdev_ops;

        write_lock_bh(&bond->lock);

        if (list_empty(&bond->vlan_list))
                goto out;

        if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
            slave_ops->ndo_vlan_rx_register)
                slave_ops->ndo_vlan_rx_register(slave_dev, bond->vlgrp);

        if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
            !(slave_ops->ndo_vlan_rx_add_vid))
                goto out;

        list_for_each_entry(vlan, &bond->vlan_list, vlan_list)
                slave_ops->ndo_vlan_rx_add_vid(slave_dev, vlan->vlan_id);

out:
        write_unlock_bh(&bond->lock);
}

static void bond_del_vlans_from_slave(struct bonding *bond,
                                      struct net_device *slave_dev)
{
        const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
        struct vlan_entry *vlan;
        struct net_device *vlan_dev;

        write_lock_bh(&bond->lock);

        if (list_empty(&bond->vlan_list))
                goto out;

        if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
            !(slave_ops->ndo_vlan_rx_kill_vid))
                goto unreg;

        list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
                /* Save and then restore vlan_dev in the grp array,
                 * since the slave's driver might clear it.
                 */
                vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
                slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
                vlan_group_set_device(bond->vlgrp, vlan->vlan_id, vlan_dev);
        }

unreg:
        if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
            slave_ops->ndo_vlan_rx_register)
                slave_ops->ndo_vlan_rx_register(slave_dev, NULL);

out:
        write_unlock_bh(&bond->lock);
}

/*------------------------------- Link status -------------------------------*/

/*
 * Set the carrier state for the master according to the state of its
 * slaves.  If any slaves are up, the master is up.  In 802.3ad mode,
 * do special 802.3ad magic.
 *
 * Returns zero if carrier state does not change, nonzero if it does.
 */
static int bond_set_carrier(struct bonding *bond)
{
        struct slave *slave;
        int i;

        if (bond->slave_cnt == 0)
                goto down;

        if (bond->params.mode == BOND_MODE_8023AD)
                return bond_3ad_set_carrier(bond);

        bond_for_each_slave(bond, slave, i) {
                if (slave->link == BOND_LINK_UP) {
                        if (!netif_carrier_ok(bond->dev)) {
                                netif_carrier_on(bond->dev);
                                return 1;
                        }
                        return 0;
                }
        }

down:
        if (netif_carrier_ok(bond->dev)) {
                netif_carrier_off(bond->dev);
                return 1;
        }
        return 0;
}

/*
 * Get link speed and duplex from the slave's base driver
 * using ethtool. If for some reason the call fails or the
 * values are invalid, fake speed and duplex to 100/Full
 * and return error.
 */
static int bond_update_speed_duplex(struct slave *slave)
{
        struct net_device *slave_dev = slave->dev;
        struct ethtool_cmd etool;
        int res;

        /* Fake speed and duplex */
        slave->speed = SPEED_100;
        slave->duplex = DUPLEX_FULL;

        if (!slave_dev->ethtool_ops || !slave_dev->ethtool_ops->get_settings)
                return -1;

        res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool);
        if (res < 0)
                return -1;

        switch (etool.speed) {
        case SPEED_10:
        case SPEED_100:
        case SPEED_1000:
        case SPEED_10000:
                break;
        default:
                return -1;
        }

        switch (etool.duplex) {
        case DUPLEX_FULL:
        case DUPLEX_HALF:
                break;
        default:
                return -1;
        }

        slave->speed = etool.speed;
        slave->duplex = etool.duplex;

        return 0;
}

/*
 * if <dev> supports MII link status reporting, check its link status.
 *
 * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
 * depending upon the setting of the use_carrier parameter.
 *
 * Return either BMSR_LSTATUS, meaning that the link is up (or we
 * can't tell and just pretend it is), or 0, meaning that the link is
 * down.
 *
 * If reporting is non-zero, instead of faking link up, return -1 if
 * both ETHTOOL and MII ioctls fail (meaning the device does not
 * support them).  If use_carrier is set, return whatever it says.
 * It'd be nice if there was a good way to tell if a driver supports
 * netif_carrier, but there really isn't.
 */
static int bond_check_dev_link(struct bonding *bond,
                               struct net_device *slave_dev, int reporting)
{
        const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
        int (*ioctl)(struct net_device *, struct ifreq *, int);
        struct ifreq ifr;
        struct mii_ioctl_data *mii;

        if (!reporting && !netif_running(slave_dev))
                return 0;

        if (bond->params.use_carrier)
                return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;

        /* Try to get link status using Ethtool first. */
        if (slave_dev->ethtool_ops) {
                if (slave_dev->ethtool_ops->get_link) {
                        u32 link;

                        link = slave_dev->ethtool_ops->get_link(slave_dev);

                        return link ? BMSR_LSTATUS : 0;
                }
        }

        /* Ethtool can't be used, fallback to MII ioctls. */
        ioctl = slave_ops->ndo_do_ioctl;
        if (ioctl) {
                /* TODO: set pointer to correct ioctl on a per team member */
                /*       bases to make this more efficient. that is, once  */
                /*       we determine the correct ioctl, we will always    */
                /*       call it and not the others for that team          */
                /*       member.                                           */

                /*
                 * We cannot assume that SIOCGMIIPHY will also read a
                 * register; not all network drivers (e.g., e100)
                 * support that.
                 */

                /* Yes, the mii is overlaid on the ifreq.ifr_ifru */
                strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
                mii = if_mii(&ifr);
                if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
                        mii->reg_num = MII_BMSR;
                        if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0)
                                return mii->val_out & BMSR_LSTATUS;
                }
        }

        /*
         * If reporting, report that either there's no dev->do_ioctl,
         * or both SIOCGMIIREG and get_link failed (meaning that we
         * cannot report link status).  If not reporting, pretend
         * we're ok.
         */
        return reporting ? -1 : BMSR_LSTATUS;
}

/*----------------------------- Multicast list ------------------------------*/

/*
 * Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise
 */
static inline int bond_is_dmi_same(const struct dev_mc_list *dmi1,
                                   const struct dev_mc_list *dmi2)
{
        return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 &&
                        dmi1->dmi_addrlen == dmi2->dmi_addrlen;
}

/*
 * returns dmi entry if found, NULL otherwise
 */
static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi,
                                                 struct dev_mc_list *mc_list)
{
        struct dev_mc_list *idmi;

        for (idmi = mc_list; idmi; idmi = idmi->next) {
                if (bond_is_dmi_same(dmi, idmi))
                        return idmi;
        }

        return NULL;
}

/*
 * Push the promiscuity flag down to appropriate slaves
 */
static int bond_set_promiscuity(struct bonding *bond, int inc)
{
        int err = 0;
        if (USES_PRIMARY(bond->params.mode)) {
                /* write lock already acquired */
                if (bond->curr_active_slave) {
                        err = dev_set_promiscuity(bond->curr_active_slave->dev,
                                                  inc);
                }
        } else {
                struct slave *slave;
                int i;
                bond_for_each_slave(bond, slave, i) {
                        err = dev_set_promiscuity(slave->dev, inc);
                        if (err)
                                return err;
                }
        }
        return err;
}

/*
 * Push the allmulti flag down to all slaves
 */
static int bond_set_allmulti(struct bonding *bond, int inc)
{
        int err = 0;
        if (USES_PRIMARY(bond->params.mode)) {
                /* write lock already acquired */
                if (bond->curr_active_slave) {
                        err = dev_set_allmulti(bond->curr_active_slave->dev,
                                               inc);
                }
        } else {
                struct slave *slave;
                int i;
                bond_for_each_slave(bond, slave, i) {
                        err = dev_set_allmulti(slave->dev, inc);
                        if (err)
                                return err;
                }
        }
        return err;
}

/*
 * Add a Multicast address to slaves
 * according to mode
 */
static void bond_mc_add(struct bonding *bond, void *addr, int alen)
{
        if (USES_PRIMARY(bond->params.mode)) {
                /* write lock already acquired */
                if (bond->curr_active_slave)
                        dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0);
        } else {
                struct slave *slave;
                int i;

                bond_for_each_slave(bond, slave, i)
                        dev_mc_add(slave->dev, addr, alen, 0);
        }
}

/*
 * Remove a multicast address from slave
 * according to mode
 */
static void bond_mc_delete(struct bonding *bond, void *addr, int alen)
{
        if (USES_PRIMARY(bond->params.mode)) {
                /* write lock already acquired */
                if (bond->curr_active_slave)
                        dev_mc_delete(bond->curr_active_slave->dev, addr,
                                      alen, 0);
        } else {
                struct slave *slave;
                int i;
                bond_for_each_slave(bond, slave, i) {
                        dev_mc_delete(slave->dev, addr, alen, 0);
                }
        }
}


/*
 * Retrieve the list of registered multicast addresses for the bonding
 * device and retransmit an IGMP JOIN request to the current active
 * slave.
 */
static void bond_resend_igmp_join_requests(struct bonding *bond)
{
        struct in_device *in_dev;
        struct ip_mc_list *im;

        rcu_read_lock();
        in_dev = __in_dev_get_rcu(bond->dev);
        if (in_dev) {
                for (im = in_dev->mc_list; im; im = im->next)
                        ip_mc_rejoin_group(im);
        }

        rcu_read_unlock();
}

/*
 * Totally destroys the mc_list in bond
 */
static void bond_mc_list_destroy(struct bonding *bond)
{
        struct dev_mc_list *dmi;

        dmi = bond->mc_list;
        while (dmi) {
                bond->mc_list = dmi->next;
                kfree(dmi);
                dmi = bond->mc_list;
        }

        bond->mc_list = NULL;
}

/*
 * Copy all the Multicast addresses from src to the bonding device dst
 */
static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond,
                             gfp_t gfp_flag)
{
        struct dev_mc_list *dmi, *new_dmi;

        for (dmi = mc_list; dmi; dmi = dmi->next) {
                new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag);

                if (!new_dmi) {
                        /* FIXME: Potential memory leak !!! */
                        return -ENOMEM;
                }

                new_dmi->next = bond->mc_list;
                bond->mc_list = new_dmi;
                new_dmi->dmi_addrlen = dmi->dmi_addrlen;
                memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen);
                new_dmi->dmi_users = dmi->dmi_users;
                new_dmi->dmi_gusers = dmi->dmi_gusers;
        }

        return 0;
}

/*
 * flush all members of flush->mc_list from device dev->mc_list
 */
static void bond_mc_list_flush(struct net_device *bond_dev,
                               struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct dev_mc_list *dmi;

        for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next)
                dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);

        if (bond->params.mode == BOND_MODE_8023AD) {
                /* del lacpdu mc addr from mc list */
                u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

                dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
        }
}

/*--------------------------- Active slave change ---------------------------*/

/*
 * Update the mc list and multicast-related flags for the new and
 * old active slaves (if any) according to the multicast mode, and
 * promiscuous flags unconditionally.
 */
static void bond_mc_swap(struct bonding *bond, struct slave *new_active,
                         struct slave *old_active)
{
        struct dev_mc_list *dmi;

        if (!USES_PRIMARY(bond->params.mode))
                /* nothing to do -  mc list is already up-to-date on
                 * all slaves
                 */
                return;

        if (old_active) {
                if (bond->dev->flags & IFF_PROMISC)
                        dev_set_promiscuity(old_active->dev, -1);

                if (bond->dev->flags & IFF_ALLMULTI)
                        dev_set_allmulti(old_active->dev, -1);

                for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next)
                        dev_mc_delete(old_active->dev, dmi->dmi_addr,
                                      dmi->dmi_addrlen, 0);
        }

        if (new_active) {
                /* FIXME: Signal errors upstream. */
                if (bond->dev->flags & IFF_PROMISC)
                        dev_set_promiscuity(new_active->dev, 1);

                if (bond->dev->flags & IFF_ALLMULTI)
                        dev_set_allmulti(new_active->dev, 1);

                for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next)

                        dev_mc_add(new_active->dev, dmi->dmi_addr,
                                   dmi->dmi_addrlen, 0);
                bond_resend_igmp_join_requests(bond);
        }
}

/*
 * bond_do_fail_over_mac
 *
 * Perform special MAC address swapping for fail_over_mac settings
 *
 * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh.
 */
static void bond_do_fail_over_mac(struct bonding *bond,
                                  struct slave *new_active,
                                  struct slave *old_active)
        __releases(&bond->curr_slave_lock)
        __releases(&bond->lock)
        __acquires(&bond->lock)
        __acquires(&bond->curr_slave_lock)
{
        u8 tmp_mac[ETH_ALEN];
        struct sockaddr saddr;
        int rv;

        switch (bond->params.fail_over_mac) {
        case BOND_FOM_ACTIVE:
                if (new_active)
                        memcpy(bond->dev->dev_addr,  new_active->dev->dev_addr,
                               new_active->dev->addr_len);
                break;
        case BOND_FOM_FOLLOW:
                /*
                 * if new_active && old_active, swap them
                 * if just old_active, do nothing (going to no active slave)
                 * if just new_active, set new_active to bond's MAC
                 */
                if (!new_active)
                        return;

                write_unlock_bh(&bond->curr_slave_lock);
                read_unlock(&bond->lock);

                if (old_active) {
                        memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
                        memcpy(saddr.sa_data, old_active->dev->dev_addr,
                               ETH_ALEN);
                        saddr.sa_family = new_active->dev->type;
                } else {
                        memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN);
                        saddr.sa_family = bond->dev->type;
                }

                rv = dev_set_mac_address(new_active->dev, &saddr);
                if (rv) {
                        pr_err("%s: Error %d setting MAC of slave %s\n",
                               bond->dev->name, -rv, new_active->dev->name);
                        goto out;
                }

                if (!old_active)
                        goto out;

                memcpy(saddr.sa_data, tmp_mac, ETH_ALEN);
                saddr.sa_family = old_active->dev->type;

                rv = dev_set_mac_address(old_active->dev, &saddr);
                if (rv)
                        pr_err("%s: Error %d setting MAC of slave %s\n",
                               bond->dev->name, -rv, new_active->dev->name);
out:
                read_lock(&bond->lock);
                write_lock_bh(&bond->curr_slave_lock);
                break;
        default:
                pr_err("%s: bond_do_fail_over_mac impossible: bad policy %d\n",
                       bond->dev->name, bond->params.fail_over_mac);
                break;
        }

}

static bool bond_should_change_active(struct bonding *bond)
{
        struct slave *prim = bond->primary_slave;
        struct slave *curr = bond->curr_active_slave;

        if (!prim || !curr || curr->link != BOND_LINK_UP)
                return true;
        if (bond->force_primary) {
                bond->force_primary = false;
                return true;
        }
        if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
            (prim->speed < curr->speed ||
             (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
                return false;
        if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
                return false;
        return true;
}

/**
 * find_best_interface - select the best available slave to be the active one
 * @bond: our bonding struct
 *
 * Warning: Caller must hold curr_slave_lock for writing.
 */
static struct slave *bond_find_best_slave(struct bonding *bond)
{
        struct slave *new_active, *old_active;
        struct slave *bestslave = NULL;
        int mintime = bond->params.updelay;
        int i;

        new_active = bond->curr_active_slave;

        if (!new_active) { /* there were no active slaves left */
                if (bond->slave_cnt > 0)   /* found one slave */
                        new_active = bond->first_slave;
                else
                        return NULL; /* still no slave, return NULL */
        }

        if ((bond->primary_slave) &&
            bond->primary_slave->link == BOND_LINK_UP &&
            bond_should_change_active(bond)) {
                new_active = bond->primary_slave;
        }

        /* remember where to stop iterating over the slaves */
        old_active = new_active;

        bond_for_each_slave_from(bond, new_active, i, old_active) {
                if (new_active->link == BOND_LINK_UP) {
                        return new_active;
                } else if (new_active->link == BOND_LINK_BACK &&
                           IS_UP(new_active->dev)) {
                        /* link up, but waiting for stabilization */
                        if (new_active->delay < mintime) {
                                mintime = new_active->delay;
                                bestslave = new_active;
                        }
                }
        }

        return bestslave;
}

/**
 * change_active_interface - change the active slave into the specified one
 * @bond: our bonding struct
 * @new: the new slave to make the active one
 *
 * Set the new slave to the bond's settings and unset them on the old
 * curr_active_slave.
 * Setting include flags, mc-list, promiscuity, allmulti, etc.
 *
 * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP,
 * because it is apparently the best available slave we have, even though its
 * updelay hasn't timed out yet.
 *
 * If new_active is not NULL, caller must hold bond->lock for read and
 * curr_slave_lock for write_bh.
 */
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
        struct slave *old_active = bond->curr_active_slave;

        if (old_active == new_active)
                return;

        if (new_active) {
                new_active->jiffies = jiffies;

                if (new_active->link == BOND_LINK_BACK) {
                        if (USES_PRIMARY(bond->params.mode)) {
                                pr_info("%s: making interface %s the new active one %d ms earlier.\n",
                                        bond->dev->name, new_active->dev->name,
                                        (bond->params.updelay - new_active->delay) * bond->params.miimon);
                        }

                        new_active->delay = 0;
                        new_active->link = BOND_LINK_UP;

                        if (bond->params.mode == BOND_MODE_8023AD)
                                bond_3ad_handle_link_change(new_active, BOND_LINK_UP);

                        if (bond_is_lb(bond))
                                bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
                } else {
                        if (USES_PRIMARY(bond->params.mode)) {
                                pr_info("%s: making interface %s the new active one.\n",
                                        bond->dev->name, new_active->dev->name);
                        }
                }
        }

        if (USES_PRIMARY(bond->params.mode))
                bond_mc_swap(bond, new_active, old_active);

        if (bond_is_lb(bond)) {
                bond_alb_handle_active_change(bond, new_active);
                if (old_active)
                        bond_set_slave_inactive_flags(old_active);
                if (new_active)
                        bond_set_slave_active_flags(new_active);
        } else {
                bond->curr_active_slave = new_active;
        }

        if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
                if (old_active)
                        bond_set_slave_inactive_flags(old_active);

                if (new_active) {
                        bond_set_slave_active_flags(new_active);

                        if (bond->params.fail_over_mac)
                                bond_do_fail_over_mac(bond, new_active,
                                                      old_active);

                        bond->send_grat_arp = bond->params.num_grat_arp;
                        bond_send_gratuitous_arp(bond);

                        bond->send_unsol_na = bond->params.num_unsol_na;
                        bond_send_unsolicited_na(bond);

                        write_unlock_bh(&bond->curr_slave_lock);
                        read_unlock(&bond->lock);

                        netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER);

                        read_lock(&bond->lock);
                        write_lock_bh(&bond->curr_slave_lock);
                }
        }
}

/**
 * bond_select_active_slave - select a new active slave, if needed
 * @bond: our bonding struct
 *
 * This functions should be called when one of the following occurs:
 * - The old curr_active_slave has been released or lost its link.
 * - The primary_slave has got its link back.
 * - A slave has got its link back and there's no old curr_active_slave.
 *
 * Caller must hold bond->lock for read and curr_slave_lock for write_bh.
 */
void bond_select_active_slave(struct bonding *bond)
{
        struct slave *best_slave;
        int rv;

        best_slave = bond_find_best_slave(bond);
        if (best_slave != bond->curr_active_slave) {
                bond_change_active_slave(bond, best_slave);
                rv = bond_set_carrier(bond);
                if (!rv)
                        return;

                if (netif_carrier_ok(bond->dev)) {
                        pr_info("%s: first active interface up!\n",
                                bond->dev->name);
                } else {
                        pr_info("%s: now running without any active interface !\n",
                                bond->dev->name);
                }
        }
}

/*--------------------------- slave list handling ---------------------------*/

/*
 * This function attaches the slave to the end of list.
 *
 * bond->lock held for writing by caller.
 */
static void bond_attach_slave(struct bonding *bond, struct slave *new_slave)
{
        if (bond->first_slave == NULL) { /* attaching the first slave */
                new_slave->next = new_slave;
                new_slave->prev = new_slave;
                bond->first_slave = new_slave;
        } else {
                new_slave->next = bond->first_slave;
                new_slave->prev = bond->first_slave->prev;
                new_slave->next->prev = new_slave;
                new_slave->prev->next = new_slave;
        }

        bond->slave_cnt++;
}

/*
 * This function detaches the slave from the list.
 * WARNING: no check is made to verify if the slave effectively
 * belongs to <bond>.
 * Nothing is freed on return, structures are just unchained.
 * If any slave pointer in bond was pointing to <slave>,
 * it should be changed by the calling function.
 *
 * bond->lock held for writing by caller.
 */
static void bond_detach_slave(struct bonding *bond, struct slave *slave)
{
        if (slave->next)
                slave->next->prev = slave->prev;

        if (slave->prev)
                slave->prev->next = slave->next;

        if (bond->first_slave == slave) { /* slave is the first slave */
                if (bond->slave_cnt > 1) { /* there are more slave */
                        bond->first_slave = slave->next;
                } else {
                        bond->first_slave = NULL; /* slave was the last one */
                }
        }

        slave->next = NULL;
        slave->prev = NULL;
        bond->slave_cnt--;
}

/*---------------------------------- IOCTL ----------------------------------*/

static int bond_sethwaddr(struct net_device *bond_dev,
                          struct net_device *slave_dev)
{
        pr_debug("bond_dev=%p\n", bond_dev);
        pr_debug("slave_dev=%p\n", slave_dev);
        pr_debug("slave_dev->addr_len=%d\n", slave_dev->addr_len);
        memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
        return 0;
}

#define BOND_VLAN_FEATURES \
        (NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX | \
         NETIF_F_HW_VLAN_FILTER)

/*
 * Compute the common dev->feature set available to all slaves.  Some
 * feature bits are managed elsewhere, so preserve those feature bits
 * on the master device.
 */
static int bond_compute_features(struct bonding *bond)
{
        struct slave *slave;
        struct net_device *bond_dev = bond->dev;
        unsigned long features = bond_dev->features;
        unsigned long vlan_features = 0;
        unsigned short max_hard_header_len = max((u16)ETH_HLEN,
                                                bond_dev->hard_header_len);
        int i;

        features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
        features |=  NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;

        if (!bond->first_slave)
                goto done;

        features &= ~NETIF_F_ONE_FOR_ALL;

        vlan_features = bond->first_slave->dev->vlan_features;
        bond_for_each_slave(bond, slave, i) {
                features = netdev_increment_features(features,
                                                     slave->dev->features,
                                                     NETIF_F_ONE_FOR_ALL);
                vlan_features = netdev_increment_features(vlan_features,
                                                        slave->dev->vlan_features,
                                                        NETIF_F_ONE_FOR_ALL);
                if (slave->dev->hard_header_len > max_hard_header_len)
                        max_hard_header_len = slave->dev->hard_header_len;
        }

done:
        features |= (bond_dev->features & BOND_VLAN_FEATURES);
        bond_dev->features = netdev_fix_features(features, NULL);
        bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL);
        bond_dev->hard_header_len = max_hard_header_len;

        return 0;
}

static void bond_setup_by_slave(struct net_device *bond_dev,
                                struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);

        bond_dev->header_ops        = slave_dev->header_ops;

        bond_dev->type              = slave_dev->type;
        bond_dev->hard_header_len   = slave_dev->hard_header_len;
        bond_dev->addr_len          = slave_dev->addr_len;

        memcpy(bond_dev->broadcast, slave_dev->broadcast,
                slave_dev->addr_len);
        bond->setup_by_slave = 1;
}

/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
        struct slave *new_slave = NULL;
        struct dev_mc_list *dmi;
        struct sockaddr addr;
        int link_reporting;
        int old_features = bond_dev->features;
        int res = 0;

        if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL &&
                slave_ops->ndo_do_ioctl == NULL) {
                pr_warning("%s: Warning: no link monitoring support for %s\n",
                           bond_dev->name, slave_dev->name);
        }

        /* bond must be initialized by bond_open() before enslaving */
        if (!(bond_dev->flags & IFF_UP)) {
                pr_warning("%s: master_dev is not up in bond_enslave\n",
                           bond_dev->name);
        }

        /* already enslaved */
        if (slave_dev->flags & IFF_SLAVE) {
                pr_debug("Error, Device was already enslaved\n");
                return -EBUSY;
        }

        /* vlan challenged mutual exclusion */
        /* no need to lock since we're protected by rtnl_lock */
        if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
                pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
                if (!list_empty(&bond->vlan_list)) {
                        pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
                               bond_dev->name, slave_dev->name, bond_dev->name);
                        return -EPERM;
                } else {
                        pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
                                   bond_dev->name, slave_dev->name,
                                   slave_dev->name, bond_dev->name);
                        bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
                }
        } else {
                pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
                if (bond->slave_cnt == 0) {
                        /* First slave, and it is not VLAN challenged,
                         * so remove the block of adding VLANs over the bond.
                         */
                        bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
                }
        }

        /*
         * Old ifenslave binaries are no longer supported.  These can
         * be identified with moderate accuracy by the state of the slave:
         * the current ifenslave will set the interface down prior to
         * enslaving it; the old ifenslave will not.
         */
        if ((slave_dev->flags & IFF_UP)) {
                pr_err("%s is up. This may be due to an out of date ifenslave.\n",
                       slave_dev->name);
                res = -EPERM;
                goto err_undo_flags;
        }

        /* set bonding device ether type by slave - bonding netdevices are
         * created with ether_setup, so when the slave type is not ARPHRD_ETHER
         * there is a need to override some of the type dependent attribs/funcs.
         *
         * bond ether type mutual exclusion - don't allow slaves of dissimilar
         * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
         */
        if (bond->slave_cnt == 0) {
                if (bond_dev->type != slave_dev->type) {
                        pr_debug("%s: change device type from %d to %d\n",
                                 bond_dev->name,
                                 bond_dev->type, slave_dev->type);

                        netdev_bonding_change(bond_dev, NETDEV_BONDING_OLDTYPE);

                        if (slave_dev->type != ARPHRD_ETHER)
                                bond_setup_by_slave(bond_dev, slave_dev);
                        else
                                ether_setup(bond_dev);

                        netdev_bonding_change(bond_dev, NETDEV_BONDING_NEWTYPE);
                }
        } else if (bond_dev->type != slave_dev->type) {
                pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n",
                       slave_dev->name,
                       slave_dev->type, bond_dev->type);
                res = -EINVAL;
                goto err_undo_flags;
        }

        if (slave_ops->ndo_set_mac_address == NULL) {
                if (bond->slave_cnt == 0) {
                        pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.",
                                   bond_dev->name);
                        bond->params.fail_over_mac = BOND_FOM_ACTIVE;
                } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
                        pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n",
                               bond_dev->name);
                        res = -EOPNOTSUPP;
                        goto err_undo_flags;
                }
        }

        new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
        if (!new_slave) {
                res = -ENOMEM;
                goto err_undo_flags;
        }

        /* save slave's original flags before calling
         * netdev_set_master and dev_open
         */
        new_slave->original_flags = slave_dev->flags;

        /*
         * Save slave's original ("permanent") mac address for modes
         * that need it, and for restoring it upon release, and then
         * set it to the master's address
         */
        memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);

        if (!bond->params.fail_over_mac) {
                /*
                 * Set slave to master's mac address.  The application already
                 * set the master's mac address to that of the first slave
                 */
                memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
                addr.sa_family = slave_dev->type;
                res = dev_set_mac_address(slave_dev, &addr);
                if (res) {
                        pr_debug("Error %d calling set_mac_address\n", res);
                        goto err_free;
                }
        }

        res = netdev_set_master(slave_dev, bond_dev);
        if (res) {
                pr_debug("Error %d calling netdev_set_master\n", res);
                goto err_restore_mac;
        }
        /* open the slave since the application closed it */
        res = dev_open(slave_dev);
        if (res) {
                pr_debug("Opening slave %s failed\n", slave_dev->name);
                goto err_unset_master;
        }

        new_slave->dev = slave_dev;
        slave_dev->priv_flags |= IFF_BONDING;

        if (bond_is_lb(bond)) {
                /* bond_alb_init_slave() must be called before all other stages since
                 * it might fail and we do not want to have to undo everything
                 */
                res = bond_alb_init_slave(bond, new_slave);
                if (res)
                        goto err_close;
        }

        /* If the mode USES_PRIMARY, then the new slave gets the
         * master's promisc (and mc) settings only if it becomes the
         * curr_active_slave, and that is taken care of later when calling
         * bond_change_active()
         */
        if (!USES_PRIMARY(bond->params.mode)) {
                /* set promiscuity level to new slave */
                if (bond_dev->flags & IFF_PROMISC) {
                        res = dev_set_promiscuity(slave_dev, 1);
                        if (res)
                                goto err_close;
                }

                /* set allmulti level to new slave */
                if (bond_dev->flags & IFF_ALLMULTI) {
                        res = dev_set_allmulti(slave_dev, 1);
                        if (res)
                                goto err_close;
                }

                netif_addr_lock_bh(bond_dev);
                /* upload master's mc_list to new slave */
                for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next)
                        dev_mc_add(slave_dev, dmi->dmi_addr,
                                   dmi->dmi_addrlen, 0);
                netif_addr_unlock_bh(bond_dev);
        }

        if (bond->params.mode == BOND_MODE_8023AD) {
                /* add lacpdu mc addr to mc list */
                u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

                dev_mc_add(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
        }

        bond_add_vlans_on_slave(bond, slave_dev);

        write_lock_bh(&bond->lock);

        bond_attach_slave(bond, new_slave);

        new_slave->delay = 0;
        new_slave->link_failure_count = 0;

        bond_compute_features(bond);

        write_unlock_bh(&bond->lock);

        read_lock(&bond->lock);

        new_slave->last_arp_rx = jiffies;

        if (bond->params.miimon && !bond->params.use_carrier) {
                link_reporting = bond_check_dev_link(bond, slave_dev, 1);

                if ((link_reporting == -1) && !bond->params.arp_interval) {
                        /*
                         * miimon is set but a bonded network driver
                         * does not support ETHTOOL/MII and
                         * arp_interval is not set.  Note: if
                         * use_carrier is enabled, we will never go
                         * here (because netif_carrier is always
                         * supported); thus, we don't need to change
                         * the messages for netif_carrier.
                         */
                        pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n",
                               bond_dev->name, slave_dev->name);
                } else if (link_reporting == -1) {
                        /* unable get link status using mii/ethtool */
                        pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n",
                                   bond_dev->name, slave_dev->name);
                }
        }

        /* check for initial state */
        if (!bond->params.miimon ||
            (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) {
                if (bond->params.updelay) {
                        pr_debug("Initial state of slave_dev is BOND_LINK_BACK\n");
                        new_slave->link  = BOND_LINK_BACK;
                        new_slave->delay = bond->params.updelay;
                } else {
                        pr_debug("Initial state of slave_dev is BOND_LINK_UP\n");
                        new_slave->link  = BOND_LINK_UP;
                }
                new_slave->jiffies = jiffies;
        } else {
                pr_debug("Initial state of slave_dev is BOND_LINK_DOWN\n");
                new_slave->link  = BOND_LINK_DOWN;
        }

        if (bond_update_speed_duplex(new_slave) &&
            (new_slave->link != BOND_LINK_DOWN)) {
                pr_warning("%s: Warning: failed to get speed and duplex from %s, assumed to be 100Mb/sec and Full.\n",
                           bond_dev->name, new_slave->dev->name);

                if (bond->params.mode == BOND_MODE_8023AD) {
                        pr_warning("%s: Warning: Operation of 802.3ad mode requires ETHTOOL support in base driver for proper aggregator selection.\n",
                                   bond_dev->name);
                }
        }

        if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
                /* if there is a primary slave, remember it */
                if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
                        bond->primary_slave = new_slave;
                        bond->force_primary = true;
                }
        }

        write_lock_bh(&bond->curr_slave_lock);

        switch (bond->params.mode) {
        case BOND_MODE_ACTIVEBACKUP:
                bond_set_slave_inactive_flags(new_slave);
                bond_select_active_slave(bond);
                break;
        case BOND_MODE_8023AD:
                /* in 802.3ad mode, the internal mechanism
                 * will activate the slaves in the selected
                 * aggregator
                 */
                bond_set_slave_inactive_flags(new_slave);
                /* if this is the first slave */
                if (bond->slave_cnt == 1) {
                        SLAVE_AD_INFO(new_slave).id = 1;
                        /* Initialize AD with the number of times that the AD timer is called in 1 second
                         * can be called only after the mac address of the bond is set
                         */
                        bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL,
                                            bond->params.lacp_fast);
                } else {
                        SLAVE_AD_INFO(new_slave).id =
                                SLAVE_AD_INFO(new_slave->prev).id + 1;
                }

                bond_3ad_bind_slave(new_slave);
                break;
        case BOND_MODE_TLB:
        case BOND_MODE_ALB:
                new_slave->state = BOND_STATE_ACTIVE;
                bond_set_slave_inactive_flags(new_slave);
                bond_select_active_slave(bond);
                break;
        default:
                pr_debug("This slave is always active in trunk mode\n");

                /* always active in trunk mode */
                new_slave->state = BOND_STATE_ACTIVE;

                /* In trunking mode there is little meaning to curr_active_slave
                 * anyway (it holds no special properties of the bond device),
                 * so we can change it without calling change_active_interface()
                 */
                if (!bond->curr_active_slave)
                        bond->curr_active_slave = new_slave;

                break;
        } /* switch(bond_mode) */

        write_unlock_bh(&bond->curr_slave_lock);

        bond_set_carrier(bond);

        read_unlock(&bond->lock);

        res = bond_create_slave_symlinks(bond_dev, slave_dev);
        if (res)
                goto err_close;

        pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
                bond_dev->name, slave_dev->name,
                new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup",
                new_slave->link != BOND_LINK_DOWN ? "n up" : " down");

        /* enslave is successful */
        return 0;

/* Undo stages on error */
err_close:
        dev_close(slave_dev);

err_unset_master:
        netdev_set_master(slave_dev, NULL);

err_restore_mac:
        if (!bond->params.fail_over_mac) {
                /* XXX TODO - fom follow mode needs to change master's
                 * MAC if this slave's MAC is in use by the bond, or at
                 * least print a warning.
                 */
                memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
                addr.sa_family = slave_dev->type;
                dev_set_mac_address(slave_dev, &addr);
        }

err_free:
        kfree(new_slave);

err_undo_flags:
        bond_dev->features = old_features;

        return res;
}

/*
 * Try to release the slave device <slave> from the bond device <master>
 * It is legal to access curr_active_slave without a lock because all the function
 * is write-locked.
 *
 * The rules for slave state should be:
 *   for Active/Backup:
 *     Active stays on all backups go down
 *   for Bonded connections:
 *     The first up interface should be left on and all others downed.
 */
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave, *oldcurrent;
        struct sockaddr addr;

        /* slave is not a slave or master is not master of this slave */
        if (!(slave_dev->flags & IFF_SLAVE) ||
            (slave_dev->master != bond_dev)) {
                pr_err("%s: Error: cannot release %s.\n",
                       bond_dev->name, slave_dev->name);
                return -EINVAL;
        }

        write_lock_bh(&bond->lock);

        slave = bond_get_slave_by_dev(bond, slave_dev);
        if (!slave) {
                /* not a slave of this bond */
                pr_info("%s: %s not enslaved\n",
                        bond_dev->name, slave_dev->name);
                write_unlock_bh(&bond->lock);
                return -EINVAL;
        }

        if (!bond->params.fail_over_mac) {
                if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) &&
                    bond->slave_cnt > 1)
                        pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
                                   bond_dev->name, slave_dev->name,
                                   slave->perm_hwaddr,
                                   bond_dev->name, slave_dev->name);
        }

        /* Inform AD package of unbinding of slave. */
        if (bond->params.mode == BOND_MODE_8023AD) {
                /* must be called before the slave is
                 * detached from the list
                 */
                bond_3ad_unbind_slave(slave);
        }

        pr_info("%s: releasing %s interface %s\n",
                bond_dev->name,
                (slave->state == BOND_STATE_ACTIVE) ? "active" : "backup",
                slave_dev->name);

        oldcurrent = bond->curr_active_slave;

        bond->current_arp_slave = NULL;

        /* release the slave from its bond */
        bond_detach_slave(bond, slave);

        bond_compute_features(bond);

        if (bond->primary_slave == slave)
                bond->primary_slave = NULL;

        if (oldcurrent == slave)
                bond_change_active_slave(bond, NULL);

        if (bond_is_lb(bond)) {
                /* Must be called only after the slave has been
                 * detached from the list and the curr_active_slave
                 * has been cleared (if our_slave == old_current),
                 * but before a new active slave is selected.
                 */
                write_unlock_bh(&bond->lock);
                bond_alb_deinit_slave(bond, slave);
                write_lock_bh(&bond->lock);
        }

        if (oldcurrent == slave) {
                /*
                 * Note that we hold RTNL over this sequence, so there
                 * is no concern that another slave add/remove event
                 * will interfere.
                 */
                write_unlock_bh(&bond->lock);
                read_lock(&bond->lock);
                write_lock_bh(&bond->curr_slave_lock);

                bond_select_active_slave(bond);

                write_unlock_bh(&bond->curr_slave_lock);
                read_unlock(&bond->lock);
                write_lock_bh(&bond->lock);
        }

        if (bond->slave_cnt == 0) {
                bond_set_carrier(bond);

                /* if the last slave was removed, zero the mac address
                 * of the master so it will be set by the application
                 * to the mac address of the first slave
                 */
                memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

                if (list_empty(&bond->vlan_list)) {
                        bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
                } else {
                        pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
                                   bond_dev->name, bond_dev->name);
                        pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
                                   bond_dev->name);
                }
        } else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
                   !bond_has_challenged_slaves(bond)) {
                pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
                        bond_dev->name, slave_dev->name, bond_dev->name);
                bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
        }

        write_unlock_bh(&bond->lock);

        /* must do this from outside any spinlocks */
        bond_destroy_slave_symlinks(bond_dev, slave_dev);

        bond_del_vlans_from_slave(bond, slave_dev);

        /* If the mode USES_PRIMARY, then we should only remove its
         * promisc and mc settings if it was the curr_active_slave, but that was
         * already taken care of above when we detached the slave
         */
        if (!USES_PRIMARY(bond->params.mode)) {
                /* unset promiscuity level from slave */
                if (bond_dev->flags & IFF_PROMISC)
                        dev_set_promiscuity(slave_dev, -1);

                /* unset allmulti level from slave */
                if (bond_dev->flags & IFF_ALLMULTI)
                        dev_set_allmulti(slave_dev, -1);

                /* flush master's mc_list from slave */
                netif_addr_lock_bh(bond_dev);
                bond_mc_list_flush(bond_dev, slave_dev);
                netif_addr_unlock_bh(bond_dev);
        }

        netdev_set_master(slave_dev, NULL);

        /* close slave before restoring its mac address */
        dev_close(slave_dev);

        if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
                /* restore original ("permanent") mac address */
                memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
                addr.sa_family = slave_dev->type;
                dev_set_mac_address(slave_dev, &addr);
        }

        slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
                                   IFF_SLAVE_INACTIVE | IFF_BONDING |
                                   IFF_SLAVE_NEEDARP);

        kfree(slave);

        return 0;  /* deletion OK */
}

/*
* First release a slave and than destroy the bond if no more slaves are left.
* Must be under rtnl_lock when this function is called.
*/
int  bond_release_and_destroy(struct net_device *bond_dev,
                              struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        int ret;

        ret = bond_release(bond_dev, slave_dev);
        if ((ret == 0) && (bond->slave_cnt == 0)) {
                pr_info("%s: destroying bond %s.\n",
                        bond_dev->name, bond_dev->name);
                unregister_netdevice(bond_dev);
        }
        return ret;
}

/*
 * This function releases all slaves.
 */
static int bond_release_all(struct net_device *bond_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave;
        struct net_device *slave_dev;
        struct sockaddr addr;

        write_lock_bh(&bond->lock);

        netif_carrier_off(bond_dev);

        if (bond->slave_cnt == 0)
                goto out;

        bond->current_arp_slave = NULL;
        bond->primary_slave = NULL;
        bond_change_active_slave(bond, NULL);

        while ((slave = bond->first_slave) != NULL) {
                /* Inform AD package of unbinding of slave
                 * before slave is detached from the list.
                 */
                if (bond->params.mode == BOND_MODE_8023AD)
                        bond_3ad_unbind_slave(slave);

                slave_dev = slave->dev;
                bond_detach_slave(bond, slave);

                /* now that the slave is detached, unlock and perform
                 * all the undo steps that should not be called from
                 * within a lock.
                 */
                write_unlock_bh(&bond->lock);

                if (bond_is_lb(bond)) {
                        /* must be called only after the slave
                         * has been detached from the list
                         */
                        bond_alb_deinit_slave(bond, slave);
                }

                bond_compute_features(bond);

                bond_destroy_slave_symlinks(bond_dev, slave_dev);
                bond_del_vlans_from_slave(bond, slave_dev);

                /* If the mode USES_PRIMARY, then we should only remove its
                 * promisc and mc settings if it was the curr_active_slave, but that was
                 * already taken care of above when we detached the slave
                 */
                if (!USES_PRIMARY(bond->params.mode)) {
                        /* unset promiscuity level from slave */
                        if (bond_dev->flags & IFF_PROMISC)
                                dev_set_promiscuity(slave_dev, -1);

                        /* unset allmulti level from slave */
                        if (bond_dev->flags & IFF_ALLMULTI)
                                dev_set_allmulti(slave_dev, -1);

                        /* flush master's mc_list from slave */
                        netif_addr_lock_bh(bond_dev);
                        bond_mc_list_flush(bond_dev, slave_dev);
                        netif_addr_unlock_bh(bond_dev);
                }

                netdev_set_master(slave_dev, NULL);

                /* close slave before restoring its mac address */
                dev_close(slave_dev);

                if (!bond->params.fail_over_mac) {
                        /* restore original ("permanent") mac address*/
                        memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
                        addr.sa_family = slave_dev->type;
                        dev_set_mac_address(slave_dev, &addr);
                }

                slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
                                           IFF_SLAVE_INACTIVE);

                kfree(slave);

                /* re-acquire the lock before getting the next slave */
                write_lock_bh(&bond->lock);
        }

        /* zero the mac address of the master so it will be
         * set by the application to the mac address of the
         * first slave
         */
        memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

        if (list_empty(&bond->vlan_list))
                bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
        else {
                pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
                           bond_dev->name, bond_dev->name);
                pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
                           bond_dev->name);
        }

        pr_info("%s: released all slaves\n", bond_dev->name);

out:
        write_unlock_bh(&bond->lock);

        return 0;
}

/*
 * This function changes the active slave to slave <slave_dev>.
 * It returns -EINVAL in the following cases.
 *  - <slave_dev> is not found in the list.
 *  - There is not active slave now.
 *  - <slave_dev> is already active.
 *  - The link state of <slave_dev> is not BOND_LINK_UP.
 *  - <slave_dev> is not running.
 * In these cases, this function does nothing.
 * In the other cases, current_slave pointer is changed and 0 is returned.
 */
static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *old_active = NULL;
        struct slave *new_active = NULL;
        int res = 0;

        if (!USES_PRIMARY(bond->params.mode))
                return -EINVAL;

        /* Verify that master_dev is indeed the master of slave_dev */
        if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev))
                return -EINVAL;

        read_lock(&bond->lock);

        read_lock(&bond->curr_slave_lock);
        old_active = bond->curr_active_slave;
        read_unlock(&bond->curr_slave_lock);

        new_active = bond_get_slave_by_dev(bond, slave_dev);

        /*
         * Changing to the current active: do nothing; return success.
         */
        if (new_active && (new_active == old_active)) {
                read_unlock(&bond->lock);
                return 0;
        }

        if ((new_active) &&
            (old_active) &&
            (new_active->link == BOND_LINK_UP) &&
            IS_UP(new_active->dev)) {
                write_lock_bh(&bond->curr_slave_lock);
                bond_change_active_slave(bond, new_active);
                write_unlock_bh(&bond->curr_slave_lock);
        } else
                res = -EINVAL;

        read_unlock(&bond->lock);

        return res;
}

static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
        struct bonding *bond = netdev_priv(bond_dev);

        info->bond_mode = bond->params.mode;
        info->miimon = bond->params.miimon;

        read_lock(&bond->lock);
        info->num_slaves = bond->slave_cnt;
        read_unlock(&bond->lock);

        return 0;
}

static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
        struct bonding *bond = netdev_priv(bond_dev);
        struct slave *slave;
        int i, res = -ENODEV;

        read_lock(&bond->lock);

        bond_for_each_slave(bond, slave, i) {
                if (i == (int)info->slave_id) {
                        res = 0;
                        strcpy(info->slave_name, slave->dev->name);
                        info->link = slave->link;
                        info->state = slave->state;
                        info->link_failure_count = slave->link_failure_count;
                        break;
                }
        }

        read_unlock(&bond->lock);

        return res;
}

/*-------------------------------- Monitoring -------------------------------*/


static int bond_miimon_inspect(struct bonding *bond)
{
        struct slave *slave;
        int i, link_state, commit = 0;
        bool ignore_updelay;

        ignore_updelay = !bond->curr_active_slave ? true : false;

        bond_for_each_slave(bond, slave, i) {
                slave->new_link = BOND_LINK_NOCHANGE;

                link_state = bond_check_dev_link(bond, slave->dev, 0);

                switch (slave->link) {
                case BOND_LINK_UP:
                        if (link_state)
                                continue;

                        slave->link = BOND_LINK_FAIL;
                        slave->delay = bond->params.downdelay;
                        if (slave->delay) {
                                pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n",
                                        bond->dev->name,
                                        (bond->params.mode ==
                                         BOND_MODE_ACTIVEBACKUP) ?
                                        ((slave->state == BOND_STATE_ACTIVE) ?
                                         "active " : "backup ") : "",
                                        slave->dev->name,
                                        bond->params.downdelay * bond->params.miimon);
                        }
                        /*FALLTHRU*/
                case BOND_LINK_FAIL:
                        if (link_state) {
                                /*
                                 * recovered before downdelay expired
                                 */
                                slave->link = BOND_LINK_UP;
                                slave->jiffies = jiffies;
                                pr_info("%s: link status up again after %d ms for interface %s.\n",
                                        bond->dev->name,
                                        (bond->params.downdelay - slave->delay) *
                                        bond->params.miimon,
                                        slave->dev->name);
                                continue;
                        }

                        if (slave->delay <= 0) {
                                slave->new_link = BOND_LINK_DOWN;
                                commit++;
                                continue;
                        }

                        slave->delay--;
                        break;

                case BOND_LINK_DOWN:
                        if (!link_state)
                                continue;

                        slave->link = BOND_LINK_BACK;
                        slave->delay = bond->params.updelay;

                        if (slave->delay) {
                                pr_info("%s: link status up for interface %s, enabling it in %d ms.\n",
                                        bond->dev->name, slave->dev->name,
                                        ignore_updelay ? 0 :
                                        bond->params.updelay *
                                        bond->params.miimon);
                        }
                        /*FALLTHRU*/
                case BOND_LINK_BACK:
                        if (!link_state) {
                                slave->link = BOND_LINK_DOWN;
                                pr_info("%s: link status down again after %d ms for interface %s.\n",
                                        bond->dev->name,
                                        (bond->params.updelay - slave->delay) *
                                        bond->params.miimon,
                                        slave->dev->name);

                                continue;
                        }

                        if (ignore_updelay)
                                slave->delay = 0;

                        if (slave->delay <= 0) {
                                slave->new_link = BOND_LINK_UP;
                                commit++;
                                ignore_updelay = false;
                                continue;
                        }

                        slave->delay--;
                        break;
                }
        }

        return commit;
}

static void bond_miimon_commit(struct bonding *bond)
{
        struct slave *slave;
        int i;

        bond_for_each_slave(bond, slave, i) {
                switch (slave->new_link) {
                case BOND_LINK_NOCHANGE:
                        continue;

                case BOND_LINK_UP:
                        slave->link = BOND_LINK_UP;
                        slave->jiffies = jiffies;

                        if (bond->params.mode == BOND_MODE_8023AD) {
                                /* prevent it from being the active one */
                                slave->state = BOND_STATE_BACKUP;
                        } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
                                /* make it immediately active */
                                slave->state = BOND_STATE_ACTIVE;
                        } else if (slave != bond->primary_slave) {
                                /* prevent it from being the active one */
                                slave->state = BOND_STATE_BACKUP;
                        }

                        pr_info("%s: link status definitely up for interface %s.\n",
                                bond->dev->name, slave->dev->name);

                        /* notify ad that the link status has changed */
                        if (bond->params.mode == BOND_MODE_8023AD)
                                bond_3ad_handle_link_change(slave, BOND_LINK_UP);

                        if (bond_is_lb(bond))
                                bond_alb_handle_link_change(bond, slave,
                                                            BOND_LINK_UP);

                        if (!bond->curr_active_slave ||
                            (slave == bond->primary_slave))
                                goto do_failover;

                        continue;

                case BOND_LINK_DOWN:
                        if (slave->link_failure_count < UINT_MAX)
                                slave->link_failure_count++;

                        slave->link = BOND_LINK_DOWN;

                        if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
                            bond->params.mode == BOND_MODE_8023AD)
                                bond_set_slave_inactive_flags(slave);

                        pr_info("%s: link status definitely down for interface %s, disabling it\n",
                                bond->dev->name, slave->dev->name);

                        if (bond->params.mode == BOND_MODE_8023AD)
                                bond_3ad_handle_link_change(slave,
                                                            BOND_LINK_DOWN);

                        if (bond_is_lb(bond))
                                bond_alb_handle_link_change(bond, slave,
                                                            BOND_LINK_DOWN);

                        if (slave == bond->curr_active_slave)
                                goto do_failover;

                        continue;

                default:
                        pr_err("%s: invalid new link %d on slave %s\n",
                               bond->dev->name, slave->new_link,
                               slave->dev->name);
                        slave->new_link = BOND_LINK_NOCHANGE;

                        continue;
                }

do_failover:
                ASSERT_RTNL();
                write_lock_bh(&bond->curr_slave_lock);
                bond_select_active_slave(bond);
                write_unlock_bh(&bond->curr_slave_lock);
        }

        bond_set_carrier(bond);
}

/*
 * bond_mii_monitor
 *
 * Really a wrapper that splits the mii monitor into two phases: an
 * inspection, then (if inspection indicates something needs to be done)
 * an acquisition of appropriate locks followed by a commit phase to
 * implement whatever link state changes are indicated.
 */
void bond_mii_monitor(struct work_struct *work)
{
        struct bonding *bond = container_of(work, struct bonding,
                                            mii_work.work);

        read_lock(&bond->lock);
        if (bond->kill_timers)
                goto out;

        if (bond->slave_cnt == 0)
                goto re_arm;

        if (bond->send_grat_arp) {
                read_lock(&bond->curr_slave_lock);
                bond_send_gratuitous_arp(bond);
                read_unlock(&bond->curr_slave_lock);
        }

        if (bond->send_unsol_na) {
                read_lock(&bond->curr_slave_lock);
                bond_send_unsolicited_na(bond);
                read_unlock(&bond->curr_slave_lock);
        }

        if (bond_miimon_inspect(bond)) {
                read_unlock(&bond->lock);
                rtnl_lock();
                read_lock(&bond->lock);

                bond_miimon_commit(bond);

                read_unlock(&bond->lock);
                rtnl_unlock();  /* might sleep, hold no other locks */
                read_lock(&bond->lock);
        }

re_arm:
        if (bond->params.miimon)
                queue_delayed_work(bond->wq, &bond->mii_work,
                                   msecs_to_jiffies(bond->params.miimon));
out:
        read_unlock(&bond->lock);
}

static __be32 bond_glean_dev_ip(struct net_device *dev)
{
        struct in_device *idev;
        struct in_ifaddr *ifa;
        __be32 addr = 0;

        if (!dev)
                return 0;

        rcu_read_lock();
        idev = __in_dev_get_rcu(dev);
        if (!idev)
                goto out;

        ifa = idev->ifa_list;
        if (!ifa)
                goto out;

        addr = ifa->ifa_local;
out:
        rcu_read_unlock();
        return addr;
}

static int bond_has_this_ip(struct bonding *bond, __be32 ip)
{
        struct vlan_entry *vlan;

        if (ip == bond->master_ip)
                return 1;

        list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
                if (ip == vlan->vlan_ip)
                        return 1;
        }

        return 0;
}

/*
 * We go to the (large) trouble of VLAN tagging ARP frames because
 * switches in VLAN mode (especially if ports are configured as
 * "native" to a VLAN) might not pass non-tagged frames.
 */
static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
{
        struct sk_buff *skb;

        pr_debug("arp %d on slave %s: dst %x src %x vid %d\n", arp_op,
                 slave_dev->name, dest_ip, src_ip, vlan_id);

        skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
                         NULL, slave_dev->dev_addr, NULL);

        if (!skb) {
                pr_err("ARP packet allocation failed\n");
                return;
        }
        if (vlan_id) {
                skb = vlan_put_tag(skb, vlan_id);
                if (!skb) {
                        pr_err("failed to insert VLAN tag\n");
                        return;
                }
        }
        arp_xmit(skb);
}


static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
        int i, vlan_id, rv;
        __be32 *targets = bond->params.arp_targets;
        struct vlan_entry *vlan;
        struct net_device *vlan_dev;
        struct flowi fl;
        struct rtable *rt;

        for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
                if (!targets[i])
                        break;
                pr_debug("basa: target %x\n", targets[i]);
                if (list_empty(&bond->vlan_list)) {
                        pr_debug("basa: empty vlan: arp_send\n");
                        bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
                                      bond->master_ip, 0);
                        continue;
                }

                /*
                 * If VLANs are configured, we do a route lookup to
                 * determine which VLAN interface would be used, so we
                 * can tag the ARP with the proper VLAN tag.
                 */
                memset(&fl, 0, sizeof(fl));
                fl.fl4_dst = targets[i];
                fl.fl4_tos = RTO_ONLINK;

                rv = ip_route_output_key(dev_net(bond->dev), &rt, &fl);
                if (rv) {
                        if (net_ratelimit()) {
                                pr_warning("%s: no route to arp_ip_target %pI4\n",
                                           bond->dev->name, &fl.fl4_dst);
                        }
                        continue;
                }

                /*
                 * This target is not on a VLAN
                 */
                if (rt->u.dst.dev == bond->dev) {
                        ip_rt_put(rt);
                        pr_debug("basa: rtdev == bond->dev: arp_send\n");
                        bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
                                      bond->master_ip, 0);
                        continue;
                }

                vlan_id = 0;
                list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
                        vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
                        if (vlan_dev == rt->u.dst.dev) {
                                vlan_id = vlan->vlan_id;
                                pr_debug("basa: vlan match on %s %d\n",
                                       vlan_dev->name, vlan_id);
                                break;
                        }
                }

                if (vlan_id) {
                        ip_rt_put(rt);
                        bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
                                      vlan->vlan_ip, vlan_id);
                        continue;
                }

                if (net_ratelimit()) {
                        pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
                                   bond->dev->name, &fl.fl4_dst,
                                   rt->u.dst.dev ? rt->u.dst.dev->name : "NULL");
                }
                ip_rt_put(rt);
        }
}

/*
 * Kick out a gratuitous ARP for an IP on the bonding master plus one
 * for each VLAN above us.
 *
 * Caller must hold curr_slave_lock for read or better
 */
static void bond_send_gratuitous_arp(struct bonding *bond)
{
        struct slave *slave = bond->curr_active_slave;
        struct vlan_entry *vlan;
        struct net_device *vlan_dev;

        pr_debug("bond_send_grat_arp: bond %s slave %s\n",
                 bond->dev->name, slave ? slave->dev->name : "NULL");

        if (!slave || !bond->send_grat_arp ||
            test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
                return;

        bond->send_grat_arp--;

        if (bond->master_ip) {
                bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
                                bond->master_ip, 0);
        }

        list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
                vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
                if (vlan->vlan_ip) {
                        bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
                                      vlan->vlan_ip, vlan->vlan_id);
                }
        }
}

static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
        int i;
        __be32 *targets = bond->params.arp_targets;

        for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
                pr_debug("bva: sip %pI4 tip %pI4 t[%d] %pI4 bhti(tip) %d\n",
                         &sip, &tip, i, &targets[i],
                         bond_has_this_ip(bond, tip));
                if (sip == targets[i]) {
                        if (bond_has_this_ip(bond, tip))
                                slave->last_arp_rx = jiffies;
                        return;
                }
        }
}

static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
        struct arphdr *arp;
        struct slave *slave;
        struct bonding *bond;
        unsigned char *arp_ptr;
        __be32 sip, tip;

        if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
                goto out;

        bond = netdev_priv(dev);
        read_lock(&bond->lock);

        pr_debug("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n",
                 bond->dev->name, skb->dev ? skb->dev->name : "NULL",
                 orig_dev ? orig_dev->name : "NULL");

        slave = bond_get_slave_by_dev(bond, orig_dev);
        if (!slave || !slave_do_arp_validate(bond, slave))
                goto out_unlock;

        if (!pskb_may_pull(skb, arp_hdr_len(dev)))
                goto out_unlock;

        arp = arp_hdr(skb);
        if (arp->ar_hln != dev->addr_len ||
            skb->pkt_type == PACKET_OTHERHOST ||
            skb->pkt_type == PACKET_LOOPBACK ||
            arp->ar_hrd != htons(ARPHRD_ETHER) ||
            arp->ar_pro != htons(ETH_P_IP) ||
            arp->ar_pln != 4)
                goto out_unlock;

        arp_ptr = (unsigned char *)(arp + 1);
        arp_ptr += dev->addr_len;
        memcpy(&sip, arp_ptr, 4);
        arp_ptr += 4 + dev->addr_len;
        memcpy(&tip, arp_ptr, 4);

        pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n",
                 bond->dev->name, slave->dev->name, slave->state,
                 bond->params.arp_validate, slave_do_arp_validate(bond, slave),
                 &sip, &tip);

        /*
         * Backup slaves won't see the ARP reply, but do come through
         * here for each ARP probe (so we swap the sip/tip to validate
         * the probe).  In a "redundant switch, common router" type of
         * configuration, the ARP probe will (hopefully) travel from
         * the active, through one switch, the router, then the other
         * switch before reaching the backup.
         */
        if (slave->state == BOND_STATE_ACTIVE)
                bond_validate_arp(bond, slave, sip, tip);
        else
                bond_validate_arp(bond, slave, tip, sip);

out_unlock:
        read_unlock(&bond->lock);
out:
        dev_kfree_skb(skb);
        return NET_RX_SUCCESS;
}

/*
 * this function is called regularly to monitor each slave's link
 * ensuring that traffic is being sent and received when arp monitoring
 * is used in load-balancing mode. if the adapter has been dormant, then an
 * arp is transmitted to generate traffic. see activebackup_arp_monitor for
 * arp monitoring in active backup mode.
 */
void bond_loadbalance_arp_mon(struct work_struct *work)
{
        struct bonding *bond = container_of(work, struct bonding,
                                            arp_work.work);
        struct slave *slave, *oldcurrent;
        int do_failover = 0;
        int delta_in_ticks;
        int i;

        read_lock(&bond->lock);

        delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);

        if (bond->kill_timers)
                goto out;

        if (bond->slave_cnt == 0)
                goto re_arm;

        read_lock(&bond->curr_slave_lock);
        oldcurrent = bond->curr_active_slave;
        read_unlock(&bond->curr_slave_lock);

        /* see if any of the previous devices are up now (i.e. they have
         * xmt and rcv traffic). the curr_active_slave does not come into
         * the picture unless it is null. also, slave->jiffies is not needed
         * here because we send an arp on each slave and give a slave as
         * long as it needs to get the tx/rx within the delta.
         * TODO: what about up/down delay in arp mode? it wasn't here before
         *       so it can wait
         */
        bond_for_each_slave(bond, slave, i) {
                if (slave->link != BOND_LINK_UP) {
                        if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) &&
                            time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) {

                                slave->link  = BOND_LINK_UP;
                                slave->state = BOND_STATE_ACTIVE;

                                /* primary_slave has no meaning in round-robin
                                 * mode. the window of a slave being up and
                                 * curr_active_slave being null after enslaving
                                 * is closed.
                                 */
                                if (!oldcurrent) {
                                        pr_info("%s: link status definitely up for interface %s, ",
                                                bond->dev->name,
                                                slave->dev->name);
                                        do_failover = 1;
                                } else {
                                        pr_info("%s: interface %s is now up\n",
                                                bond->dev->name,
                                                slave->dev->name);
                                }
                        }
                } else {
                        /* slave->link == BOND_LINK_UP */

                        /* not all switches will respond to an arp request
                         * when the source ip is 0, so don't take the link down
                         * if we don't know our ip yet
                         */
                        if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) ||
                            (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) {

                                slave->link  = BOND_LINK_DOWN;
                                slave->state = BOND_STATE_BACKUP;

                                if (slave->link_failure_count < UINT_MAX)
                                        slave->link_failure_count++;

                                pr_info("%s: interface %s is now down.\n",
                                        bond->dev->name,
                                        slave->dev->name);

                                if (slave == oldcurrent)
                                        do_failover = 1;
                        }
                }

                /* note: if switch is in round-robin mode, all links
                 * must tx arp to ensure all links rx an arp - otherwise
                 * links may oscillate or not come up at all; if switch is
                 * in something like xor mode, there is nothing we can
                 * do - all replies will be rx'ed on same link causing slaves
                 * to be unstable during low/no traffic periods
                 */
                if (IS_UP(slave->dev))
                        bond_arp_send_all(bond, slave);
        }

        if (do_failover) {
                write_lock_bh(&bond->curr_slave_lock);

                bond_select_active_slave(bond);

                write_unlock_bh(&bond->curr_slave_lock);
        }

re_arm:
        if (bond->params.arp_interval)
                queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
out:
        read_unlock(&bond->lock);
}

/*
 * Called to inspect slaves for active-backup mode ARP monitor link state
 * changes.  Sets new_link in slaves to specify what action should take
 * place for the slave.  Returns 0 if no changes are found, >0 if changes
 * to link states must be committed.
 *
 * Called with bond->lock held for read.
 */
static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
{
        struct slave *slave;
        int i, commit = 0;

        bond_for_each_slave(bond, slave, i) {
                slave->new_link = BOND_LINK_NOCHANGE;

                if (slave->link != BOND_LINK_UP) {
                        if (time_before_eq(jiffies, slave_last_rx(bond, slave) +
                                           delta_in_ticks)) {
                                slave->new_link = BOND_LINK_UP;
                                commit++;
                        }

                        continue;
                }

                /*
                 * Give slaves 2*delta after being enslaved or made
                 * active.  This avoids bouncing, as the last receive
                 * times need a full ARP monitor cycle to be updated.
                 */
                if (!time_after_eq(jiffies, slave->jiffies +
                                   2 * delta_in_ticks))
                        continue;

                /*
                 * Backup slave is down if:
                 * - No current_arp_slave AND
                 * - more than 3*delta since last receive AND
                 * - the bond has an IP address
                 *
                 * Note: a non-null current_arp_slave indicates
                 * the curr_active_slave went down and we are
                 * searching for a new one; under this condition
                 * we only take the curr_active_slave down - this
                 * gives each slave a chance to tx/rx traffic
                 * before being taken out
                 */
                if (slave->state == BOND_STATE_BACKUP &&
                    !bond->current_arp_slave &&
                    time_after(jiffies, slave_last_rx(bond, slave) +
                               3 * delta_in_ticks)) {
                        slave->new_link = BOND_LINK_DOWN;
                        commit++;
                }

                /*
                 * Active slave is down if:
                 * - more than 2*delta since transmitting OR
                 * - (more than 2*delta since receive AND
                 *    the bond has an IP address)
                 */
                if ((slave->state == BOND_STATE_ACTIVE) &&
                    (time_after_eq(jiffies, dev_trans_start(slave->dev) +
                                    2 * delta_in_ticks) ||
                      (time_after_eq(jiffies, slave_last_rx(bond, slave)
                                     + 2 * delta_in_ticks)))) {
                        slave->new_link = BOND_LINK_DOWN;
                        commit++;
                }
        }

        return commit;
}

/*
 * Called to commit link state changes noted by inspection step of
 * active-backup mode ARP monitor.
 *
 * Called with RTNL and bond->lock for read.
 */
static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks)
{
        struct slave *slave;
        int i;

        bond_for_each_slave(bond, slave, i) {
                switch (slave->new_link) {
                case BOND_LINK_NOCHANGE:
                        continue;

                case BOND_LINK_UP:
                        if ((!bond->curr_active_slave &&
                             time_before_eq(jiffies,
                                            dev_trans_start(slave->dev) +
                                            delta_in_ticks)) ||
                            bond->curr_active_slave != slave) {
                                slave->link = BOND_LINK_UP;
                                bond->current_arp_slave = NULL;

                                pr_info("%s: link status definitely up for interface %s.\n",
                                        bond->dev->name, slave->dev->name);

                                if (!bond->curr_active_slave ||
                                    (slave == bond->primary_slave))
                                        goto do_failover;

                        }

                        continue;

                case BOND_LINK_DOWN:
                        if (slave->link_failure_count < UINT_MAX)
                                slave->link_failure_count++;

                        slave->link = BOND_LINK_DOWN;
                        bond_set_slave_inactive_flags(slave);

                        pr_info("%s: link status definitely down for interface %s, disabling it\n",
                                bond->dev->name, slave->dev->name);

                        if (slave == bond->curr_active_slave) {
                                bond->current_arp_slave = NULL;
                                goto do_failover;
                        }

                        continue;

                default:
                        pr_err("%s: impossible: new_link %d on slave %s\n",
                               bond->dev->name, slave->new_link,
                               slave->dev->name);
                        continue;
                }

do_failover:
                ASSERT_RTNL();
                write_lock_bh(&bond->curr_slave_lock);
                bond_select_active_slave(bond);
                write_unlock_bh(&bond->curr_slave_lock);
        }

        bond_set_carrier(bond);
}

/*
 * Send ARP probes for active-backup mode ARP monitor.
 *
 * Called with bond->lock held for read.
 */
static void bond_ab_arp_probe(struct bonding *bond)
{
        struct slave *slave;
        int i;

        read_lock(&bond->curr_slave_lock);

        if (bond->current_arp_slave && bond->curr_active_slave)
                pr_info("PROBE: c_arp %s && cas %s BAD\n",
                        bond->current_arp_slave->dev->name,
                        bond->curr_active_slave->dev->name);

        if (bond->curr_active_slave) {
                bond_arp_send_all(bond, bond->curr_active_slave);
                read_unlock(&bond->curr_slave_lock);
                return;
        }

        read_unlock(&bond->curr_slave_lock);

        /* if we don't have a curr_active_slave, search for the next available
         * backup slave from the current_arp_slave and make it the candidate
         * for becoming the curr_active_slave
         */

        if (!bond->current_arp_slave) {
                bond->current_arp_slave = bond->first_slave;
                if (!bond->current_arp_slave)
                        return;
        }

        bond_set_slave_inactive_flags(bond->current_arp_slave);

        /* search for next candidate */
        bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
                if (IS_UP(slave->dev)) {
                        slave->link = BOND_LINK_BACK;
                        bond_set_slave_active_flags(slave);
                        bond_arp_send_all(bond, slave);
                        slave->jiffies = jiffies;
                        bond->current_arp_slave = slave;
                        break;
                }

                /* if the link state is up at this point, we
                 * mark it down - this can happen if we have
                 * simultaneous link failures and
                 * reselect_active_interface doesn't make this
                 * one the current slave so it is still marked
                 * up when it is actually down
                 */
                if (slave->link == BOND_LINK_UP) {
                        slave->link = BOND_LINK_DOWN;
                        if (slave->link_failure_count < UINT_MAX)
                                slave->link_failure_count++;

                        bond_set_slave_inactive_flags(slave);

                        pr_info("%s: backup interface %s is now down.\n",
                                bond->dev->name, slave->dev->name);
                }
        }
}