bond_main.c

/*
 * 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/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/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 <linux/preempt.h>
#include <net/route.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/pkt_sched.h>
#include <linux/rculist.h>
#include <net/flow_keys.h>
#include <linux/reciprocal_div.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 tx_queues	= BOND_DEFAULT_TX_QUEUES;
static int num_peer_notif = 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 int min_links;
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 *arp_all_targets;
static char *fail_over_mac;
static int all_slaves_active;
static struct bond_params bonding_defaults;
static int resend_igmp = BOND_DEFAULT_RESEND_IGMP;
static int packets_per_slave = 1;
static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;

module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(tx_queues, int, 0);
MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
module_param_named(num_grat_arp, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on "
			       "failover event (alias of num_unsol_na)");
module_param_named(num_unsol_na, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on "
			       "failover event (alias of num_grat_arp)");
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; "
			    "0 for slow, 1 for fast");
module_param(ad_select, charp, 0);
MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; "
			    "0 for stable (default), 1 for bandwidth, "
			    "2 for count");
module_param(min_links, int, 0);
MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier");

module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "
				   "0 for layer 2 (default), 1 for layer 3+4, "
				   "2 for layer 2+3, 3 for encap layer 2+3, "
				   "4 for encap 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; "
			       "0 for none (default), 1 for active, "
			       "2 for backup, 3 for all");
module_param(arp_all_targets, charp, 0);
MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for 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; 0 for none (default), "
				"1 for active, 2 for follow");
module_param(all_slaves_active, int, 0);
MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface"
				     "by setting active flag for all slaves; "
				     "0 for never (default), 1 for always.");
module_param(resend_igmp, int, 0);
MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on "
			      "link failure");
module_param(packets_per_slave, int, 0);
MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr "
				    "mode; 0 for a random slave, 1 packet per "
				    "slave (default), >1 packets per slave.");
module_param(lp_interval, uint, 0);
MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where "
			      "the bonding driver sends learning packets to "
			      "each slaves peer switch. The default is 1.");

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

#ifdef CONFIG_NET_POLL_CONTROLLER
atomic_t netpoll_block_tx = ATOMIC_INIT(0);
#endif

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},
{	"encap2+3",		BOND_XMIT_POLICY_ENCAP23},
{	"encap3+4",		BOND_XMIT_POLICY_ENCAP34},
{	NULL,			-1},
};

const struct bond_parm_tbl arp_all_targets_tbl[] = {
{	"any",			BOND_ARP_TARGETS_ANY},
{	"all",			BOND_ARP_TARGETS_ALL},
{	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 int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);

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

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 < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB)
		return "unknown";

	return names[mode];
}

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

/**
 * 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
 */
void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
			struct net_device *slave_dev)
{
	skb->dev = slave_dev;

	BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
		     sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping));
	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;

	if (unlikely(netpoll_tx_running(bond->dev)))
		bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
	else
		dev_queue_xmit(skb);
}

/*
 * In the following 2 functions, 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_add_vid - Propagates adding an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being added
 */
static int bond_vlan_rx_add_vid(struct net_device *bond_dev,
				__be16 proto, u16 vid)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct slave *slave, *rollback_slave;
	struct list_head *iter;
	int res;

	bond_for_each_slave(bond, slave, iter) {
		res = vlan_vid_add(slave->dev, proto, vid);
		if (res)
			goto unwind;
	}

	return 0;

unwind:
	/* unwind to the slave that failed */
	bond_for_each_slave(bond, rollback_slave, iter) {
		if (rollback_slave == slave)
			break;

		vlan_vid_del(rollback_slave->dev, proto, vid);
	}

	return res;
}

/**
 * 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 int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
				 __be16 proto, u16 vid)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter)
		vlan_vid_del(slave->dev, proto, vid);

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

	return 0;
}

/*------------------------------- 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 list_head *iter;
	struct slave *slave;

	if (!bond_has_slaves(bond))
		goto down;

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

	bond_for_each_slave(bond, slave, iter) {
		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, set speed and duplex to -1,
 * and return.
 */
static void bond_update_speed_duplex(struct slave *slave)
{
	struct net_device *slave_dev = slave->dev;
	struct ethtool_cmd ecmd;
	u32 slave_speed;
	int res;

	slave->speed = SPEED_UNKNOWN;
	slave->duplex = DUPLEX_UNKNOWN;

	res = __ethtool_get_settings(slave_dev, &ecmd);
	if (res < 0)
		return;

	slave_speed = ethtool_cmd_speed(&ecmd);
	if (slave_speed == 0 || slave_speed == ((__u32) -1))
		return;

	switch (ecmd.duplex) {
	case DUPLEX_FULL:
	case DUPLEX_HALF:
		break;
	default:
		return;
	}

	slave->speed = slave_speed;
	slave->duplex = ecmd.duplex;

	return;
}

/*
 * 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->get_link)
		return slave_dev->ethtool_ops->get_link(slave_dev) ?
			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 ------------------------------*/

/*
 * Push the promiscuity flag down to appropriate slaves
 */
static int bond_set_promiscuity(struct bonding *bond, int inc)
{
	struct list_head *iter;
	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;

		bond_for_each_slave(bond, slave, iter) {
			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)
{
	struct list_head *iter;
	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;

		bond_for_each_slave(bond, slave, iter) {
			err = dev_set_allmulti(slave->dev, inc);
			if (err)
				return err;
		}
	}
	return err;
}

/*
 * 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_delayed(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    mcast_work.work);

	if (!rtnl_trylock()) {
		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
		return;
	}
	call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev);

	if (bond->igmp_retrans > 1) {
		bond->igmp_retrans--;
		queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
	}
	rtnl_unlock();
}

/* Flush bond's hardware addresses from slave
 */
static void bond_hw_addr_flush(struct net_device *bond_dev,
			       struct net_device *slave_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);

	dev_uc_unsync(slave_dev, bond_dev);
	dev_mc_unsync(slave_dev, bond_dev);

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

		dev_mc_del(slave_dev, lacpdu_multicast);
	}
}

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

/* Update the hardware address list and promisc/allmulti for the new and
 * old active slaves (if any).  Modes that are !USES_PRIMARY keep all
 * slaves up date at all times; only the USES_PRIMARY modes need to call
 * this function to swap these settings during a failover.
 */
static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
			      struct slave *old_active)
{
	ASSERT_RTNL();

	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);

		bond_hw_addr_flush(bond->dev, old_active->dev);
	}

	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);

		netif_addr_lock_bh(bond->dev);
		dev_uc_sync(new_active->dev, bond->dev);
		dev_mc_sync(new_active->dev, bond->dev);
		netif_addr_unlock_bh(bond->dev);
	}
}

/**
 * bond_set_dev_addr - clone slave's address to bond
 * @bond_dev: bond net device
 * @slave_dev: slave net device
 *
 * Should be called with RTNL held.
 */
static void bond_set_dev_addr(struct net_device *bond_dev,
			      struct net_device *slave_dev)
{
	pr_debug("bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
		 bond_dev, slave_dev, slave_dev->addr_len);
	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
	bond_dev->addr_assign_type = NET_ADDR_STOLEN;
	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
}

/*
 * bond_do_fail_over_mac
 *
 * Perform special MAC address swapping for fail_over_mac settings
 *
 * Called with RTNL, 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)
	__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) {
			write_unlock_bh(&bond->curr_slave_lock);
			bond_set_dev_addr(bond->dev, new_active->dev);
			write_lock_bh(&bond->curr_slave_lock);
		}
		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);

		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:
		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
 */
static struct slave *bond_find_best_slave(struct bonding *bond)
{
	struct slave *slave, *bestslave = NULL;
	struct list_head *iter;
	int mintime = bond->params.updelay;

	if (bond->primary_slave && bond->primary_slave->link == BOND_LINK_UP &&
	    bond_should_change_active(bond))
		return bond->primary_slave;

	bond_for_each_slave(bond, slave, iter) {
		if (slave->link == BOND_LINK_UP)
			return slave;
		if (slave->link == BOND_LINK_BACK && IS_UP(slave->dev) &&
		    slave->delay < mintime) {
			mintime = slave->delay;
			bestslave = slave;
		}
	}

	return bestslave;
}

static bool bond_should_notify_peers(struct bonding *bond)
{
	struct slave *slave;

	rcu_read_lock();
	slave = rcu_dereference(bond->curr_active_slave);
	rcu_read_unlock();

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

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

	return true;
}

/**
 * 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 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_hw_addr_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 {
		rcu_assign_pointer(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) {
			bool should_notify_peers = false;

			bond_set_slave_active_flags(new_active);

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

			if (netif_running(bond->dev)) {
				bond->send_peer_notif =
					bond->params.num_peer_notif;
				should_notify_peers =
					bond_should_notify_peers(bond);
			}

			write_unlock_bh(&bond->curr_slave_lock);

			call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
			if (should_notify_peers)
				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
							 bond->dev);

			write_lock_bh(&bond->curr_slave_lock);
		}
	}

	/* resend IGMP joins since active slave has changed or
	 * all were sent on curr_active_slave.
	 * resend only if bond is brought up with the affected
	 * bonding modes and the retransmission is enabled */
	if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) &&
	    ((USES_PRIMARY(bond->params.mode) && new_active) ||
	     bond->params.mode == BOND_MODE_ROUNDROBIN)) {
		bond->igmp_retrans = bond->params.resend_igmp;
		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
	}
}

/**
 * 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 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);
		}
	}
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static inline int slave_enable_netpoll(struct slave *slave)
{
	struct netpoll *np;
	int err = 0;

	np = kzalloc(sizeof(*np), GFP_ATOMIC);
	err = -ENOMEM;
	if (!np)
		goto out;

	err = __netpoll_setup(np, slave->dev, GFP_ATOMIC);
	if (err) {
		kfree(np);
		goto out;
	}
	slave->np = np;
out:
	return err;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
	struct netpoll *np = slave->np;

	if (!np)
		return;

	slave->np = NULL;
	__netpoll_free_async(np);
}
static inline bool slave_dev_support_netpoll(struct net_device *slave_dev)
{
	if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL)
		return false;
	if (!slave_dev->netdev_ops->ndo_poll_controller)
		return false;
	return true;
}

static void bond_poll_controller(struct net_device *bond_dev)
{
}

static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter)
		if (IS_UP(slave->dev))
			slave_disable_netpoll(slave);
}

static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
{
	struct bonding *bond = netdev_priv(dev);
	struct list_head *iter;
	struct slave *slave;
	int err = 0;

	bond_for_each_slave(bond, slave, iter) {
		err = slave_enable_netpoll(slave);
		if (err) {
			bond_netpoll_cleanup(dev);
			break;
		}
	}
	return err;
}
#else
static inline int slave_enable_netpoll(struct slave *slave)
{
	return 0;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
}
static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
}
#endif

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

static netdev_features_t bond_fix_features(struct net_device *dev,
					   netdev_features_t features)
{
	struct bonding *bond = netdev_priv(dev);
	struct list_head *iter;
	netdev_features_t mask;
	struct slave *slave;

	if (!bond_has_slaves(bond)) {
		/* Disable adding VLANs to empty bond. But why? --mq */
		features |= NETIF_F_VLAN_CHALLENGED;
		return features;
	}