blob: ee610721098e628d01ad988b1a9cad40aeef6f70 [file] [log] [blame]
/*
* 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.
*
*/
#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_dissector.h>
#include <net/bonding.h>
#include <net/bond_3ad.h>
#include <net/bond_alb.h>
#include "bonding_priv.h"
/*---------------------------- Module parameters ----------------------------*/
/* monitor all links that often (in milliseconds). <=0 disables monitoring */
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;
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;
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, "802.3ad 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-alb, balance-tlb, balance-xor, 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
unsigned int bond_net_id __read_mostly;
/*-------------------------- Forward declarations ---------------------------*/
static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);
static void bond_get_stats(struct net_device *bond_dev,
struct rtnl_link_stats64 *stats);
static void bond_slave_arr_handler(struct work_struct *work);
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod);
static void bond_netdev_notify_work(struct work_struct *work);
/*---------------------------- 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_set_queue_mapping(skb, 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.
*/
int bond_set_carrier(struct bonding *bond)
{
struct list_head *iter;
struct slave *slave;
if (!bond_has_slaves(bond))
goto down;
if (BOND_MODE(bond) == 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. Return 1 if speed or duplex settings are
* UNKNOWN; 0 otherwise.
*/
static int bond_update_speed_duplex(struct slave *slave)
{
struct net_device *slave_dev = slave->dev;
struct ethtool_link_ksettings ecmd;
int res;
slave->speed = SPEED_UNKNOWN;
slave->duplex = DUPLEX_UNKNOWN;
res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
if (res < 0)
return 1;
if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
return 1;
switch (ecmd.base.duplex) {
case DUPLEX_FULL:
case DUPLEX_HALF:
break;
default:
return 1;
}
slave->speed = ecmd.base.speed;
slave->duplex = ecmd.base.duplex;
return 0;
}
const char *bond_slave_link_status(s8 link)
{
switch (link) {
case BOND_LINK_UP:
return "up";
case BOND_LINK_FAIL:
return "going down";
case BOND_LINK_DOWN:
return "down";
case BOND_LINK_BACK:
return "going back";
default:
return "unknown";
}
}
/* 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 (bond_uses_primary(bond)) {
struct slave *curr_active = rtnl_dereference(bond->curr_active_slave);
if (curr_active)
err = dev_set_promiscuity(curr_active->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 (bond_uses_primary(bond)) {
struct slave *curr_active = rtnl_dereference(bond->curr_active_slave);
if (curr_active)
err = dev_set_allmulti(curr_active->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_MODE(bond) == 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 not using primary keep all
* slaves up date at all times; only the modes that use primary 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)
{
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 int bond_set_dev_addr(struct net_device *bond_dev,
struct net_device *slave_dev)
{
int err;
netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n",
bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len);
err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
if (err)
return err;
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);
return 0;
}
static struct slave *bond_get_old_active(struct bonding *bond,
struct slave *new_active)
{
struct slave *slave;
struct list_head *iter;
bond_for_each_slave(bond, slave, iter) {
if (slave == new_active)
continue;
if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
return slave;
}
return NULL;
}
/* bond_do_fail_over_mac
*
* Perform special MAC address swapping for fail_over_mac settings
*
* Called with RTNL
*/
static void bond_do_fail_over_mac(struct bonding *bond,
struct slave *new_active,
struct slave *old_active)
{
u8 tmp_mac[MAX_ADDR_LEN];
struct sockaddr_storage ss;
int rv;
switch (bond->params.fail_over_mac) {
case BOND_FOM_ACTIVE:
if (new_active) {
rv = bond_set_dev_addr(bond->dev, new_active->dev);
if (rv)
netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
-rv, bond->dev->name);
}
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;
if (!old_active)
old_active = bond_get_old_active(bond, new_active);
if (old_active) {
bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
new_active->dev->addr_len);
bond_hw_addr_copy(ss.__data,
old_active->dev->dev_addr,
old_active->dev->addr_len);
ss.ss_family = new_active->dev->type;
} else {
bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
bond->dev->addr_len);
ss.ss_family = bond->dev->type;
}
rv = dev_set_mac_address(new_active->dev,
(struct sockaddr *)&ss, NULL);
if (rv) {
netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
-rv, new_active->dev->name);
goto out;
}
if (!old_active)
goto out;
bond_hw_addr_copy(ss.__data, tmp_mac,
new_active->dev->addr_len);
ss.ss_family = old_active->dev->type;
rv = dev_set_mac_address(old_active->dev,
(struct sockaddr *)&ss, NULL);
if (rv)
netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
-rv, new_active->dev->name);
out:
break;
default:
netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n",
bond->params.fail_over_mac);
break;
}
}
static struct slave *bond_choose_primary_or_current(struct bonding *bond)
{
struct slave *prim = rtnl_dereference(bond->primary_slave);
struct slave *curr = rtnl_dereference(bond->curr_active_slave);
if (!prim || prim->link != BOND_LINK_UP) {
if (!curr || curr->link != BOND_LINK_UP)
return NULL;
return curr;
}
if (bond->force_primary) {
bond->force_primary = false;
return prim;
}
if (!curr || curr->link != BOND_LINK_UP)
return prim;
/* At this point, prim and curr are both up */
switch (bond->params.primary_reselect) {
case BOND_PRI_RESELECT_ALWAYS:
return prim;
case BOND_PRI_RESELECT_BETTER:
if (prim->speed < curr->speed)
return curr;
if (prim->speed == curr->speed && prim->duplex <= curr->duplex)
return curr;
return prim;
case BOND_PRI_RESELECT_FAILURE:
return curr;
default:
netdev_err(bond->dev, "impossible primary_reselect %d\n",
bond->params.primary_reselect);
return curr;
}
}
/**
* bond_find_best_slave - 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;
slave = bond_choose_primary_or_current(bond);
if (slave)
return slave;
bond_for_each_slave(bond, slave, iter) {
if (slave->link == BOND_LINK_UP)
return slave;
if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) &&
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();
netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n",
slave ? slave->dev->name : "NULL");
if (!slave || !bond->send_peer_notif ||
!netif_carrier_ok(bond->dev) ||
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.
*
* Caller must hold RTNL.
*/
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
struct slave *old_active;
ASSERT_RTNL();
old_active = rtnl_dereference(bond->curr_active_slave);
if (old_active == new_active)
return;
if (new_active) {
new_active->last_link_up = jiffies;
if (new_active->link == BOND_LINK_BACK) {
if (bond_uses_primary(bond)) {
netdev_info(bond->dev, "making interface %s the new active one %d ms earlier\n",
new_active->dev->name,
(bond->params.updelay - new_active->delay) * bond->params.miimon);
}
new_active->delay = 0;
bond_set_slave_link_state(new_active, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
if (BOND_MODE(bond) == 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 (bond_uses_primary(bond)) {
netdev_info(bond->dev, "making interface %s the new active one\n",
new_active->dev->name);
}
}
}
if (bond_uses_primary(bond))
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,
BOND_SLAVE_NOTIFY_NOW);
if (new_active)
bond_set_slave_active_flags(new_active,
BOND_SLAVE_NOTIFY_NOW);
} else {
rcu_assign_pointer(bond->curr_active_slave, new_active);
}
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) {
if (old_active)
bond_set_slave_inactive_flags(old_active,
BOND_SLAVE_NOTIFY_NOW);
if (new_active) {
bool should_notify_peers = false;
bond_set_slave_active_flags(new_active,
BOND_SLAVE_NOTIFY_NOW);
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);
}
call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
if (should_notify_peers)
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
}
}
/* 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) &&
((bond_uses_primary(bond) && new_active) ||
BOND_MODE(bond) == 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 RTNL.
*/
void bond_select_active_slave(struct bonding *bond)
{
struct slave *best_slave;
int rv;
ASSERT_RTNL();
best_slave = bond_find_best_slave(bond);
if (best_slave != rtnl_dereference(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))
netdev_info(bond->dev, "first active interface up!\n");
else
netdev_info(bond->dev, "now running without any active interface!\n");
}
}
#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_KERNEL);
err = -ENOMEM;
if (!np)
goto out;
err = __netpoll_setup(np, slave->dev);
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(np);
}
static void bond_poll_controller(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave = NULL;
struct list_head *iter;
struct ad_info ad_info;
if (BOND_MODE(bond) == BOND_MODE_8023AD)
if (bond_3ad_get_active_agg_info(bond, &ad_info))
return;
bond_for_each_slave_rcu(bond, slave, iter) {
if (!bond_slave_is_up(slave))
continue;
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct aggregator *agg =
SLAVE_AD_INFO(slave)->port.aggregator;
if (agg &&
agg->aggregator_identifier != ad_info.aggregator_id)
continue;
}
netpoll_poll_dev(slave->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 (bond_slave_is_up(slave))
slave_disable_netpoll(slave);
}
static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
{
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;
mask = features;
features &= ~NETIF_F_ONE_FOR_ALL;
features |= NETIF_F_ALL_FOR_ALL;
bond_for_each_slave(bond, slave, iter) {
features = netdev_increment_features(features,
slave->dev->features,
mask);
}
features = netdev_add_tso_features(features, mask);
return features;
}
#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
NETIF_F_HIGHDMA | NETIF_F_LRO)
#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
static void bond_compute_features(struct bonding *bond)
{
unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
IFF_XMIT_DST_RELEASE_PERM;
netdev_features_t vlan_features = BOND_VLAN_FEATURES;
netdev_features_t enc_features = BOND_ENC_FEATURES;
struct net_device *bond_dev = bond->dev;
struct list_head *iter;
struct slave *slave;
unsigned short max_hard_header_len = ETH_HLEN;
unsigned int gso_max_size = GSO_MAX_SIZE;
u16 gso_max_segs = GSO_MAX_SEGS;
if (!bond_has_slaves(bond))
goto done;
vlan_features &= NETIF_F_ALL_FOR_ALL;
bond_for_each_slave(bond, slave, iter) {
vlan_features = netdev_increment_features(vlan_features,
slave->dev->vlan_features, BOND_VLAN_FEATURES);
enc_features = netdev_increment_features(enc_features,
slave->dev->hw_enc_features,
BOND_ENC_FEATURES);
dst_release_flag &= slave->dev->priv_flags;
if (slave->dev->hard_header_len > max_hard_header_len)
max_hard_header_len = slave->dev->hard_header_len;
gso_max_size = min(gso_max_size, slave->dev->gso_max_size);
gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs);
}
bond_dev->hard_header_len = max_hard_header_len;
done:
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
NETIF_F_GSO_UDP_L4;
bond_dev->gso_max_segs = gso_max_segs;
netif_set_gso_max_size(bond_dev, gso_max_size);
bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE;
netdev_change_features(bond_dev);
}
static void bond_setup_by_slave(struct net_device *bond_dev,
struct net_device *slave_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);
}
/* On bonding slaves other than the currently active slave, suppress
* duplicates except for alb non-mcast/bcast.
*/
static bool bond_should_deliver_exact_match(struct sk_buff *skb,
struct slave *slave,
struct bonding *bond)
{
if (bond_is_slave_inactive(slave)) {
if (BOND_MODE(bond) == BOND_MODE_ALB &&
skb->pkt_type != PACKET_BROADCAST &&
skb->pkt_type != PACKET_MULTICAST)
return false;
return true;
}
return false;
}
static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
struct slave *slave;
struct bonding *bond;
int (*recv_probe)(const struct sk_buff *, struct bonding *,
struct slave *);
int ret = RX_HANDLER_ANOTHER;
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return RX_HANDLER_CONSUMED;
*pskb = skb;
slave = bond_slave_get_rcu(skb->dev);
bond = slave->bond;
recv_probe = READ_ONCE(bond->recv_probe);
if (recv_probe) {
ret = recv_probe(skb, bond, slave);
if (ret == RX_HANDLER_CONSUMED) {
consume_skb(skb);
return ret;
}
}
/*
* For packets determined by bond_should_deliver_exact_match() call to
* be suppressed we want to make an exception for link-local packets.
* This is necessary for e.g. LLDP daemons to be able to monitor
* inactive slave links without being forced to bind to them
* explicitly.
*
* At the same time, packets that are passed to the bonding master
* (including link-local ones) can have their originating interface
* determined via PACKET_ORIGDEV socket option.
*/
if (bond_should_deliver_exact_match(skb, slave, bond)) {
if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
return RX_HANDLER_PASS;
return RX_HANDLER_EXACT;
}
skb->dev = bond->dev;
if (BOND_MODE(bond) == BOND_MODE_ALB &&
bond->dev->priv_flags & IFF_BRIDGE_PORT &&
skb->pkt_type == PACKET_HOST) {
if (unlikely(skb_cow_head(skb,
skb->data - skb_mac_header(skb)))) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
bond->dev->addr_len);
}
return ret;
}
static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
{
switch (BOND_MODE(bond)) {
case BOND_MODE_ROUNDROBIN:
return NETDEV_LAG_TX_TYPE_ROUNDROBIN;
case BOND_MODE_ACTIVEBACKUP:
return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP;
case BOND_MODE_BROADCAST:
return NETDEV_LAG_TX_TYPE_BROADCAST;
case BOND_MODE_XOR:
case BOND_MODE_8023AD:
return NETDEV_LAG_TX_TYPE_HASH;
default:
return NETDEV_LAG_TX_TYPE_UNKNOWN;
}
}
static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond,
enum netdev_lag_tx_type type)
{
if (type != NETDEV_LAG_TX_TYPE_HASH)
return NETDEV_LAG_HASH_NONE;
switch (bond->params.xmit_policy) {
case BOND_XMIT_POLICY_LAYER2:
return NETDEV_LAG_HASH_L2;
case BOND_XMIT_POLICY_LAYER34:
return NETDEV_LAG_HASH_L34;
case BOND_XMIT_POLICY_LAYER23:
return NETDEV_LAG_HASH_L23;
case BOND_XMIT_POLICY_ENCAP23:
return NETDEV_LAG_HASH_E23;
case BOND_XMIT_POLICY_ENCAP34:
return NETDEV_LAG_HASH_E34;
default:
return NETDEV_LAG_HASH_UNKNOWN;
}
}
static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave,
struct netlink_ext_ack *extack)
{
struct netdev_lag_upper_info lag_upper_info;
enum netdev_lag_tx_type type;
type = bond_lag_tx_type(bond);
lag_upper_info.tx_type = type;
lag_upper_info.hash_type = bond_lag_hash_type(bond, type);
return netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
&lag_upper_info, extack);
}
static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave)
{
netdev_upper_dev_unlink(slave->dev, bond->dev);
slave->dev->flags &= ~IFF_SLAVE;
}
static struct slave *bond_alloc_slave(struct bonding *bond)
{
struct slave *slave = NULL;
slave = kzalloc(sizeof(*slave), GFP_KERNEL);
if (!slave)
return NULL;
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info),
GFP_KERNEL);
if (!SLAVE_AD_INFO(slave)) {
kfree(slave);
return NULL;
}
}
INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work);
return slave;
}
static void bond_free_slave(struct slave *slave)
{
struct bonding *bond = bond_get_bond_by_slave(slave);
cancel_delayed_work_sync(&slave->notify_work);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
kfree(SLAVE_AD_INFO(slave));
kfree(slave);
}
static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info)
{
info->bond_mode = BOND_MODE(bond);
info->miimon = bond->params.miimon;
info->num_slaves = bond->slave_cnt;
}
static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
{
strcpy(info->slave_name, slave->dev->name);
info->link = slave->link;
info->state = bond_slave_state(slave);
info->link_failure_count = slave->link_failure_count;
}
static void bond_netdev_notify_work(struct work_struct *_work)
{
struct slave *slave = container_of(_work, struct slave,
notify_work.work);
if (rtnl_trylock()) {
struct netdev_bonding_info binfo;
bond_fill_ifslave(slave, &binfo.slave);
bond_fill_ifbond(slave->bond, &binfo.master);
netdev_bonding_info_change(slave->dev, &binfo);
rtnl_unlock();
} else {
queue_delayed_work(slave->bond->wq, &slave->notify_work, 1);
}
}
void bond_queue_slave_event(struct slave *slave)
{
queue_delayed_work(slave->bond->wq, &slave->notify_work, 0);
}
void bond_lower_state_changed(struct slave *slave)
{
struct netdev_lag_lower_state_info info;
info.link_up = slave->link == BOND_LINK_UP ||
slave->link == BOND_LINK_FAIL;
info.tx_enabled = bond_is_active_slave(slave);
netdev_lower_state_changed(slave->dev, &info);
}
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
struct netlink_ext_ack *extack)
{
struct bonding *bond = netdev_priv(bond_dev);
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct slave *new_slave = NULL, *prev_slave;
struct sockaddr_storage ss;
int link_reporting;
int res = 0, i;
if (!bond->params.use_carrier &&
slave_dev->ethtool_ops->get_link == NULL &&
slave_ops->ndo_do_ioctl == NULL) {
netdev_warn(bond_dev, "no link monitoring support for %s\n",
slave_dev->name);
}
/* already in-use? */
if (netdev_is_rx_handler_busy(slave_dev)) {
NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved");
netdev_err(bond_dev,
"Error: Device is in use and cannot be enslaved\n");
return -EBUSY;
}
if (bond_dev == slave_dev) {
NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself.");
netdev_err(bond_dev, "cannot enslave bond to itself.\n");
return -EPERM;
}
/* vlan challenged mutual exclusion */
/* no need to lock since we're protected by rtnl_lock */
if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
netdev_dbg(bond_dev, "%s is NETIF_F_VLAN_CHALLENGED\n",
slave_dev->name);
if (vlan_uses_dev(bond_dev)) {
NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond");
netdev_err(bond_dev, "Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
slave_dev->name, bond_dev->name);
return -EPERM;
} else {
netdev_warn(bond_dev, "enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
slave_dev->name, slave_dev->name,
bond_dev->name);
}
} else {
netdev_dbg(bond_dev, "%s is !NETIF_F_VLAN_CHALLENGED\n",
slave_dev->name);
}
/* 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) {
NL_SET_ERR_MSG(extack, "Device can not be enslaved while up");
netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n",
slave_dev->name);
return -EPERM;
}
/* 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_has_slaves(bond)) {
if (bond_dev->type != slave_dev->type) {
netdev_dbg(bond_dev, "change device type from %d to %d\n",
bond_dev->type, slave_dev->type);
res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE,
bond_dev);
res = notifier_to_errno(res);
if (res) {
netdev_err(bond_dev, "refused to change device type\n");
return -EBUSY;
}
/* Flush unicast and multicast addresses */
dev_uc_flush(bond_dev);
dev_mc_flush(bond_dev);
if (slave_dev->type != ARPHRD_ETHER)
bond_setup_by_slave(bond_dev, slave_dev);
else {
ether_setup(bond_dev);
bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
}
call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,
bond_dev);
}
} else if (bond_dev->type != slave_dev->type) {
NL_SET_ERR_MSG(extack, "Device type is different from other slaves");
netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n",
slave_dev->name, slave_dev->type, bond_dev->type);
return -EINVAL;
}
if (slave_dev->type == ARPHRD_INFINIBAND &&
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves");
netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n",
slave_dev->type);
res = -EOPNOTSUPP;
goto err_undo_flags;
}
if (!slave_ops->ndo_set_mac_address ||
slave_dev->type == ARPHRD_INFINIBAND) {
netdev_warn(bond_dev, "The slave device specified does not support setting the MAC address\n");
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
if (!bond_has_slaves(bond)) {
bond->params.fail_over_mac = BOND_FOM_ACTIVE;
netdev_warn(bond_dev, "Setting fail_over_mac to active for active-backup mode\n");
} else {
NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
netdev_err(bond_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n");
res = -EOPNOTSUPP;
goto err_undo_flags;
}
}
}
call_netdevice_notifiers(NETDEV_JOIN, slave_dev);
/* If this is the first slave, then we need to set the master's hardware
* address to be the same as the slave's.
*/
if (!bond_has_slaves(bond) &&
bond->dev->addr_assign_type == NET_ADDR_RANDOM) {
res = bond_set_dev_addr(bond->dev, slave_dev);
if (res)
goto err_undo_flags;
}
new_slave = bond_alloc_slave(bond);
if (!new_slave) {
res = -ENOMEM;
goto err_undo_flags;
}
new_slave->bond = bond;
new_slave->dev = slave_dev;
/* Set the new_slave's queue_id to be zero. Queue ID mapping
* is set via sysfs or module option if desired.
*/
new_slave->queue_id = 0;
/* Save slave's original mtu and then set it to match the bond */
new_slave->original_mtu = slave_dev->mtu;
res = dev_set_mtu(slave_dev, bond->dev->mtu);
if (res) {
netdev_dbg(bond_dev, "Error %d calling dev_set_mtu\n", res);
goto err_free;
}
/* 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
*/
bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
slave_dev->addr_len);
if (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* Set slave to master's mac address. The application already
* set the master's mac address to that of the first slave
*/
memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
ss.ss_family = slave_dev->type;
res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
extack);
if (res) {
netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
goto err_restore_mtu;
}
}
/* set slave flag before open to prevent IPv6 addrconf */
slave_dev->flags |= IFF_SLAVE;
/* open the slave since the application closed it */
res = dev_open(slave_dev, extack);
if (res) {
netdev_dbg(bond_dev, "Opening slave %s failed\n", slave_dev->name);
goto err_restore_mac;
}
slave_dev->priv_flags |= IFF_BONDING;
/* initialize slave stats */
dev_get_stats(new_slave->dev, &new_slave->slave_stats);
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;
}
res = vlan_vids_add_by_dev(slave_dev, bond_dev);
if (res) {
netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
slave_dev->name);
goto err_close;
}
prev_slave = bond_last_slave(bond);
new_slave->delay = 0;
new_slave->link_failure_count = 0;
if (bond_update_speed_duplex(new_slave) &&
bond_needs_speed_duplex(bond))
new_slave->link = BOND_LINK_DOWN;
new_slave->last_rx = jiffies -
(msecs_to_jiffies(bond->params.arp_interval) + 1);
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
new_slave->target_last_arp_rx[i] = new_slave->last_rx;
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.
*/
netdev_warn(bond_dev, "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",
slave_dev->name);
} else if (link_reporting == -1) {
/* unable get link status using mii/ethtool */
netdev_warn(bond_dev, "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",
slave_dev->name);
}
}
/* check for initial state */
new_slave->link = BOND_LINK_NOCHANGE;
if (bond->params.miimon) {
if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
if (bond->params.updelay) {
bond_set_slave_link_state(new_slave,
BOND_LINK_BACK,
BOND_SLAVE_NOTIFY_NOW);
new_slave->delay = bond->params.updelay;
} else {
bond_set_slave_link_state(new_slave,
BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
}
} else {
bond_set_slave_link_state(new_slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_NOW);
}
} else if (bond->params.arp_interval) {
bond_set_slave_link_state(new_slave,
(netif_carrier_ok(slave_dev) ?
BOND_LINK_UP : BOND_LINK_DOWN),
BOND_SLAVE_NOTIFY_NOW);
} else {
bond_set_slave_link_state(new_slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
}
if (new_slave->link != BOND_LINK_DOWN)
new_slave->last_link_up = jiffies;
netdev_dbg(bond_dev, "Initial state of slave_dev is BOND_LINK_%s\n",
new_slave->link == BOND_LINK_DOWN ? "DOWN" :
(new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));
if (bond_uses_primary(bond) && bond->params.primary[0]) {
/* if there is a primary slave, remember it */
if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
rcu_assign_pointer(bond->primary_slave, new_slave);
bond->force_primary = true;
}
}
switch (BOND_MODE(bond)) {
case BOND_MODE_ACTIVEBACKUP:
bond_set_slave_inactive_flags(new_slave,
BOND_SLAVE_NOTIFY_NOW);
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, BOND_SLAVE_NOTIFY_NOW);
/* if this is the first slave */
if (!prev_slave) {
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);
} else {
SLAVE_AD_INFO(new_slave)->id =
SLAVE_AD_INFO(prev_slave)->id + 1;
}
bond_3ad_bind_slave(new_slave);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
bond_set_active_slave(new_slave);
bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
break;
default:
netdev_dbg(bond_dev, "This slave is always active in trunk mode\n");
/* always active in trunk mode */
bond_set_active_slave(new_slave);
/* 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 (!rcu_access_pointer(bond->curr_active_slave) &&
new_slave->link == BOND_LINK_UP)
rcu_assign_pointer(bond->curr_active_slave, new_slave);
break;
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
goto err_detach;
}
}
#endif
if (!(bond_dev->features & NETIF_F_LRO))
dev_disable_lro(slave_dev);
res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
new_slave);
if (res) {
netdev_dbg(bond_dev, "Error %d calling netdev_rx_handler_register\n", res);
goto err_detach;
}
res = bond_master_upper_dev_link(bond, new_slave, extack);
if (res) {
netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
goto err_unregister;
}
res = bond_sysfs_slave_add(new_slave);
if (res) {
netdev_dbg(bond_dev, "Error %d calling bond_sysfs_slave_add\n", res);
goto err_upper_unlink;
}
bond->nest_level = dev_get_nest_level(bond_dev) + 1;
/* If the mode uses primary, then the following is handled by
* bond_change_active_slave().
*/
if (!bond_uses_primary(bond)) {
/* set promiscuity level to new slave */
if (bond_dev->flags & IFF_PROMISC) {
res = dev_set_promiscuity(slave_dev, 1);
if (res)
goto err_sysfs_del;
}
/* set allmulti level to new slave */
if (bond_dev->flags & IFF_ALLMULTI) {
res = dev_set_allmulti(slave_dev, 1);
if (res) {
if (bond_dev->flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
goto err_sysfs_del;
}
}
netif_addr_lock_bh(bond_dev);
dev_mc_sync_multiple(slave_dev, bond_dev);
dev_uc_sync_multiple(slave_dev, bond_dev);
netif_addr_unlock_bh(bond_dev);
if (BOND_MODE(bond) == 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);
}
}
bond->slave_cnt++;
bond_compute_features(bond);
bond_set_carrier(bond);
if (bond_uses_primary(bond)) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
slave_dev->name,
bond_is_active_slave(new_slave) ? "an active" : "a backup",
new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
/* enslave is successful */
bond_queue_slave_event(new_slave);
return 0;
/* Undo stages on error */
err_sysfs_del:
bond_sysfs_slave_del(new_slave);
err_upper_unlink:
bond_upper_dev_unlink(bond, new_slave);
err_unregister:
netdev_rx_handler_unregister(slave_dev);
err_detach:
vlan_vids_del_by_dev(slave_dev, bond_dev);
if (rcu_access_pointer(bond->primary_slave) == new_slave)
RCU_INIT_POINTER(bond->primary_slave, NULL);
if (rcu_access_pointer(bond->curr_active_slave) == new_slave) {
block_netpoll_tx();
bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
/* either primary_slave or curr_active_slave might've changed */
synchronize_rcu();
slave_disable_netpoll(new_slave);
err_close:
slave_dev->priv_flags &= ~IFF_BONDING;
dev_close(slave_dev);
err_restore_mac:
slave_dev->flags &= ~IFF_SLAVE;
if (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* 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.
*/
bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
new_slave->dev->addr_len);
ss.ss_family = slave_dev->type;
dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
}
err_restore_mtu:
dev_set_mtu(slave_dev, new_slave->original_mtu);
err_free:
bond_free_slave(new_slave);
err_undo_flags:
/* Enslave of first slave has failed and we need to fix master's mac */
if (!bond_has_slaves(bond)) {
if (ether_addr_equal_64bits(bond_dev->dev_addr,
slave_dev->dev_addr))
eth_hw_addr_random(bond_dev);
if (bond_dev->type != ARPHRD_ETHER) {
dev_close(bond_dev);
ether_setup(bond_dev);
bond_dev->flags |= IFF_MASTER;
bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
}
}
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 RTNL-locked. If "all" is true it means that the function is being called
* while destroying a bond interface and all slaves are being released.
*
* 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.
*/
static int __bond_release_one(struct net_device *bond_dev,
struct net_device *slave_dev,
bool all, bool unregister)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr_storage ss;
int old_flags = bond_dev->flags;
netdev_features_t old_features = bond_dev->features;
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
!netdev_has_upper_dev(slave_dev, bond_dev)) {
netdev_dbg(bond_dev, "cannot release %s\n",
slave_dev->name);
return -EINVAL;
}
block_netpoll_tx();
slave = bond_get_slave_by_dev(bond, slave_dev);
if (!slave) {
/* not a slave of this bond */
netdev_info(bond_dev, "%s not enslaved\n",
slave_dev->name);
unblock_netpoll_tx();
return -EINVAL;
}
bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);
bond_sysfs_slave_del(slave);
/* recompute stats just before removing the slave */
bond_get_stats(bond->dev, &bond->bond_stats);
bond_upper_dev_unlink(bond, slave);
/* unregister rx_handler early so bond_handle_frame wouldn't be called
* for this slave anymore.
*/
netdev_rx_handler_unregister(slave_dev);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, slave);
netdev_info(bond_dev, "Releasing %s interface %s\n",
bond_is_active_slave(slave) ? "active" : "backup",
slave_dev->name);
oldcurrent = rcu_access_pointer(bond->curr_active_slave);
RCU_INIT_POINTER(bond->current_arp_slave, NULL);
if (!all && (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond_has_slaves(bond))
netdev_warn(bond_dev, "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",
slave_dev->name, slave->perm_hwaddr,
bond_dev->name, slave_dev->name);
}
if (rtnl_dereference(bond->primary_slave) == slave)
RCU_INIT_POINTER(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.
*/
bond_alb_deinit_slave(bond, slave);
}
if (all) {
RCU_INIT_POINTER(bond->curr_active_slave, NULL);
} else if (oldcurrent == slave) {
/* Note that we hold RTNL over this sequence, so there
* is no concern that another slave add/remove event
* will interfere.
*/
bond_select_active_slave(bond);
}
if (!bond_has_slaves(bond)) {
bond_set_carrier(bond);
eth_hw_addr_random(bond_dev);
bond->nest_level = SINGLE_DEPTH_NESTING;
} else {
bond->nest_level = dev_get_nest_level(bond_dev) + 1;
}
unblock_netpoll_tx();
synchronize_rcu();
bond->slave_cnt--;
if (!bond_has_slaves(bond)) {
call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
call_netdevice_notifiers(NETDEV_RELEASE, bond->dev);
}
bond_compute_features(bond);
if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
(old_features & NETIF_F_VLAN_CHALLENGED))
netdev_info(bond_dev, "last VLAN challenged slave %s left bond %s - VLAN blocking is removed\n",
slave_dev->name, bond_dev->name);
vlan_vids_del_by_dev(slave_dev, bond_dev);
/* If the mode uses primary, then this case was handled above by
* bond_change_active_slave(..., NULL)
*/
if (!bond_uses_primary(bond)) {
/* unset promiscuity level from slave
* NOTE: The NETDEV_CHANGEADDR call above may change the value
* of the IFF_PROMISC flag in the bond_dev, but we need the
* value of that flag before that change, as that was the value
* when this slave was attached, so we cache at the start of the
* function and use it here. Same goes for ALLMULTI below
*/
if (old_flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
/* unset allmulti level from slave */
if (old_flags & IFF_ALLMULTI)
dev_set_allmulti(slave_dev, -1);
bond_hw_addr_flush(bond_dev, slave_dev);
}
slave_disable_netpoll(slave);
/* close slave before restoring its mac address */
dev_close(slave_dev);
if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* restore original ("permanent") mac address */
bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
slave->dev->addr_len);
ss.ss_family = slave_dev->type;
dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
}
if (unregister)
__dev_set_mtu(slave_dev, slave->original_mtu);
else
dev_set_mtu(slave_dev, slave->original_mtu);
slave_dev->priv_flags &= ~IFF_BONDING;
bond_free_slave(slave);
return 0;
}
/* A wrapper used because of ndo_del_link */
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
return __bond_release_one(bond_dev, slave_dev, false, false);
}
/* First release a slave and then destroy the bond if no more slaves are left.
* Must be under rtnl_lock when this function is called.
*/
static 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_one(bond_dev, slave_dev, false, true);
if (ret == 0 && !bond_has_slaves(bond)) {
bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
netdev_info(bond_dev, "Destroying bond %s\n",
bond_dev->name);
bond_remove_proc_entry(bond);
unregister_netdevice(bond_dev);
}
return ret;
}
static void bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
struct bonding *bond = netdev_priv(bond_dev);
bond_fill_ifbond(bond, info);
}
static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
int i = 0, res = -ENODEV;
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
if (i++ == (int)info->slave_id) {
res = 0;
bond_fill_ifslave(slave, info);
break;
}
}
return res;
}
/*-------------------------------- Monitoring -------------------------------*/
/* called with rcu_read_lock() */
static int bond_miimon_inspect(struct bonding *bond)
{
int link_state, commit = 0;
struct list_head *iter;
struct slave *slave;
bool ignore_updelay;
ignore_updelay = !rcu_dereference(bond->curr_active_slave);
bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
slave->link_new_state = slave->link;
link_state = bond_check_dev_link(bond, slave->dev, 0);
switch (slave->link) {
case BOND_LINK_UP:
if (link_state)
continue;
bond_propose_link_state(slave, BOND_LINK_FAIL);
commit++;
slave->delay = bond->params.downdelay;
if (slave->delay) {
netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
(BOND_MODE(bond) ==
BOND_MODE_ACTIVEBACKUP) ?
(bond_is_active_slave(slave) ?
"active " : "backup ") : "",
slave->dev->name,
bond->params.downdelay * bond->params.miimon);
}
/*FALLTHRU*/
case BOND_LINK_FAIL:
if (link_state) {
/* recovered before downdelay expired */
bond_propose_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
(bond->params.downdelay - slave->delay) *
bond->params.miimon,
slave->dev->name);
commit++;
continue;
}
if (slave->delay <= 0) {
slave->new_link = BOND_LINK_DOWN;
commit++;
continue;
}
slave->delay--;
break;
case BOND_LINK_DOWN:
if (!link_state)
continue;
bond_propose_link_state(slave, BOND_LINK_BACK);
commit++;
slave->delay = bond->params.updelay;
if (slave->delay) {
netdev_info(bond->dev, "link status up for interface %s, enabling it in %d ms\n",
slave->dev->name,
ignore_updelay ? 0 :
bond->params.updelay *
bond->params.miimon);
}
/*FALLTHRU*/
case BOND_LINK_BACK:
if (!link_state) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
(bond->params.updelay - slave->delay) *
bond->params.miimon,
slave->dev->name);
commit++;
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_link_change(struct bonding *bond,
struct slave *slave,
char link)
{
switch (BOND_MODE(bond)) {
case BOND_MODE_8023AD:
bond_3ad_handle_link_change(slave, link);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
bond_alb_handle_link_change(bond, slave, link);
break;
case BOND_MODE_XOR:
bond_update_slave_arr(bond, NULL);
break;
}
}
static void bond_miimon_commit(struct bonding *bond)
{
struct list_head *iter;
struct slave *slave, *primary;
bond_for_each_slave(bond, slave, iter) {
switch (slave->new_link) {
case BOND_LINK_NOCHANGE:
continue;
case BOND_LINK_UP:
if (bond_update_speed_duplex(slave) &&
bond_needs_speed_duplex(bond)) {
slave->link = BOND_LINK_DOWN;
if (net_ratelimit())
netdev_warn(bond->dev,
"failed to get link speed/duplex for %s\n",
slave->dev->name);
continue;
}
bond_set_slave_link_state(slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
slave->last_link_up = jiffies;
primary = rtnl_dereference(bond->primary_slave);
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
/* prevent it from being the active one */
bond_set_backup_slave(slave);
} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* make it immediately active */
bond_set_active_slave(slave);
} else if (slave != primary) {
/* prevent it from being the active one */
bond_set_backup_slave(slave);
}
netdev_info(bond->dev, "link status definitely up for interface %s, %u Mbps %s duplex\n",
slave->dev->name,
slave->speed == SPEED_UNKNOWN ? 0 : slave->speed,
slave->duplex ? "full" : "half");
bond_miimon_link_change(bond, slave, BOND_LINK_UP);
if (!bond->curr_active_slave || slave == primary)
goto do_failover;
continue;
case BOND_LINK_DOWN:
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
bond_set_slave_link_state(slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_NOW);
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
BOND_MODE(bond) == BOND_MODE_8023AD)
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
netdev_info(bond->dev, "link status definitely down for interface %s, disabling it\n",
slave->dev->name);
bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);
if (slave == rcu_access_pointer(bond->curr_active_slave))
goto do_failover;
continue;
default:
netdev_err(bond->dev, "invalid new link %d on slave %s\n",
slave->new_link, slave->dev->name);
slave->new_link = BOND_LINK_NOCHANGE;
continue;
}
do_failover:
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
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.
*/
static void bond_mii_monitor(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
mii_work.work);
bool should_notify_peers = false;
unsigned long delay;
struct slave *slave;
struct list_head *iter;
delay = msecs_to_jiffies(bond->params.miimon);
if (!bond_has_slaves(bond))
goto re_arm;
rcu_read_lock();
should_notify_peers = bond_should_notify_peers(bond);
if (bond_miimon_inspect(bond)) {
rcu_read_unlock();
/* Race avoidance with bond_close cancel of workqueue */
if (!rtnl_trylock()) {
delay = 1;
should_notify_peers = false;
goto re_arm;
}
bond_for_each_slave(bond, slave, iter) {
bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
}
bond_miimon_commit(bond);
rtnl_unlock(); /* might sleep, hold no other locks */
} else
rcu_read_unlock();
re_arm:
if (bond->params.miimon)
queue_delayed_work(bond->wq, &bond->mii_work, delay);
if (should_notify_peers) {
if (!rtnl_trylock())
return;
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
rtnl_unlock();
}
}
static int bond_upper_dev_walk(struct net_device *upper, void *data)
{
__be32 ip = *((__be32 *)data);
return ip == bond_confirm_addr(upper, 0, ip);
}
static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
bool ret = false;
if (ip == bond_confirm_addr(bond->dev, 0, ip))
return true;
rcu_read_lock();
if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip))
ret = true;
rcu_read_unlock();
return ret;
}
/* 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,
struct bond_vlan_tag *tags)
{
struct sk_buff *skb;
struct bond_vlan_tag *outer_tag = tags;
netdev_dbg(slave_dev, "arp %d on slave %s: dst %pI4 src %pI4\n",
arp_op, slave_dev->name, &dest_ip, &src_ip);
skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
NULL, slave_dev->dev_addr, NULL);
if (!skb) {
net_err_ratelimited("ARP packet allocation failed\n");
return;
}
if (!tags || tags->vlan_proto == VLAN_N_VID)
goto xmit;
tags++;
/* Go through all the tags backwards and add them to the packet */
while (tags->vlan_proto != VLAN_N_VID) {
if (!tags->vlan_id) {
tags++;
continue;
}
netdev_dbg(slave_dev, "inner tag: proto %X vid %X\n",
ntohs(outer_tag->vlan_proto), tags->vlan_id);
skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto,
tags->vlan_id);
if (!skb) {
net_err_ratelimited("failed to insert inner VLAN tag\n");
return;
}
tags++;
}
/* Set the outer tag */
if (outer_tag->vlan_id) {
netdev_dbg(slave_dev, "outer tag: proto %X vid %X\n",
ntohs(outer_tag->vlan_proto), outer_tag->vlan_id);
__vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto,
outer_tag->vlan_id);
}
xmit:
arp_xmit(skb);
}
/* Validate the device path between the @start_dev and the @end_dev.
* The path is valid if the @end_dev is reachable through device
* stacking.
* When the path is validated, collect any vlan information in the
* path.
*/
struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
struct net_device *end_dev,
int level)
{
struct bond_vlan_tag *tags;
struct net_device *upper;
struct list_head *iter;
if (start_dev == end_dev) {
tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC);
if (!tags)
return ERR_PTR(-ENOMEM);
tags[level].vlan_proto = VLAN_N_VID;
return tags;
}
netdev_for_each_upper_dev_rcu(start_dev, upper, iter) {
tags = bond_verify_device_path(upper, end_dev, level + 1);
if (IS_ERR_OR_NULL(tags)) {
if (IS_ERR(tags))
return tags;
continue;
}
if (is_vlan_dev(upper)) {
tags[level].vlan_proto = vlan_dev_vlan_proto(upper);
tags[level].vlan_id = vlan_dev_vlan_id(upper);
}
return tags;
}
return NULL;
}
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
struct rtable *rt;
struct bond_vlan_tag *tags;
__be32 *targets = bond->params.arp_targets, addr;
int i;
for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
netdev_dbg(bond->dev, "basa: target %pI4\n", &targets[i]);
tags = NULL;
/* Find out through which dev should the packet go */
rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
RTO_ONLINK, 0);
if (IS_ERR(rt)) {
/* there's no route to target - try to send arp
* probe to generate any traffic (arp_validate=0)
*/
if (bond->params.arp_validate)
net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
bond->dev->name,
&targets[i]);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
0, tags);
continue;
}
/* bond device itself */
if (rt->dst.dev == bond->dev)
goto found;
rcu_read_lock();
tags = bond_verify_device_path(bond->dev, rt->dst.dev, 0);
rcu_read_unlock();
if (!IS_ERR_OR_NULL(tags))
goto found;
/* Not our device - skip */
netdev_dbg(bond->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n",
&targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL");
ip_rt_put(rt);
continue;
found:
addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
ip_rt_put(rt);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
addr, tags);
kfree(tags);
}
}
static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
int i;
if (!sip || !bond_has_this_ip(bond, tip)) {
netdev_dbg(bond->dev, "bva: sip %pI4 tip %pI4 not found\n",
&sip, &tip);
return;
}
i = bond_get_targets_ip(bond->params.arp_targets, sip);
if (i == -1) {
netdev_dbg(bond->dev, "bva: sip %pI4 not found in targets\n",
&sip);
return;
}
slave->last_rx = jiffies;
slave->target_last_arp_rx[i] = jiffies;
}
int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
struct slave *slave)
{
struct arphdr *arp = (struct arphdr *)skb->data;
struct slave *curr_active_slave, *curr_arp_slave;
unsigned char *arp_ptr;
__be32 sip, tip;
int is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
unsigned int alen;
if (!slave_do_arp_validate(bond, slave)) {
if ((slave_do_arp_validate_only(bond) && is_arp) ||
!slave_do_arp_validate_only(bond))
slave->last_rx = jiffies;
return RX_HANDLER_ANOTHER;
} else if (!is_arp) {
return RX_HANDLER_ANOTHER;
}
alen = arp_hdr_len(bond->dev);
netdev_dbg(bond->dev, "bond_arp_rcv: skb->dev %s\n",
skb->dev->name);
if (alen > skb_headlen(skb)) {
arp = kmalloc(alen, GFP_ATOMIC);
if (!arp)
goto out_unlock;
if (skb_copy_bits(skb, 0, arp, alen) < 0)
goto out_unlock;
}
if (arp->ar_hln != bond->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 += bond->dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4 + bond->dev->addr_len;
memcpy(&tip, arp_ptr, 4);
netdev_dbg(bond->dev, "bond_arp_rcv: %s/%d av %d sv %d sip %pI4 tip %pI4\n",
slave->dev->name, bond_slave_state(slave),
bond->params.arp_validate, slave_do_arp_validate(bond, slave),
&sip, &tip);
curr_active_slave = rcu_dereference(bond->curr_active_slave);
curr_arp_slave = rcu_dereference(bond->current_arp_slave);
/* We 'trust' the received ARP enough to validate it if:
*
* (a) the slave receiving the ARP is active (which includes the
* current ARP slave, if any), or
*
* (b) the receiving slave isn't active, but there is a currently
* active slave and it received valid arp reply(s) after it became
* the currently active slave, or
*
* (c) there is an ARP slave that sent an ARP during the prior ARP
* interval, and we receive an ARP reply on any slave. We accept
* these because switch FDB update delays may deliver the ARP
* reply to a slave other than the sender of the ARP request.
*
* Note: for (b), backup slaves are receiving the broadcast ARP
* request, not a reply. This request passes from the sending
* slave through the L2 switch(es) to the receiving slave. Since
* this is checking the request, sip/tip are swapped for
* validation.
*
* This is done to avoid endless looping when we can't reach the
* arp_ip_target and fool ourselves with our own arp requests.
*/
if (bond_is_active_slave(slave))
bond_validate_arp(bond, slave, sip, tip);
else if (curr_active_slave &&
time_after(slave_last_rx(bond, curr_active_slave),
curr_active_slave->last_link_up))
bond_validate_arp(bond, slave, tip, sip);
else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
bond_time_in_interval(bond,
dev_trans_start(curr_arp_slave->dev), 1))
bond_validate_arp(bond, slave, sip, tip);
out_unlock:
if (arp != (struct arphdr *)skb->data)
kfree(arp);
return RX_HANDLER_ANOTHER;
}
/* function to verify if we're in the arp_interval timeslice, returns true if
* (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval +
* arp_interval/2) . the arp_interval/2 is needed for really fast networks.
*/
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod)
{
int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
return time_in_range(jiffies,
last_act - delta_in_ticks,
last_act + mod * delta_in_ticks + delta_in_ticks/2);
}
/* 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.
*/
static void bond_loadbalance_arp_mon(struct bonding *bond)
{
struct slave *slave, *oldcurrent;
struct list_head *iter;
int do_failover = 0, slave_state_changed = 0;
if (!bond_has_slaves(bond))
goto re_arm;
rcu_read_lock();
oldcurrent = rcu_dereference(bond->curr_active_slave);
/* 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->last_link_up 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_rcu(bond, slave, iter) {
unsigned long trans_start = dev_trans_start(slave->dev);
slave->new_link = BOND_LINK_NOCHANGE;
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, trans_start, 1) &&
bond_time_in_interval(bond, slave->last_rx, 1)) {
slave->new_link = BOND_LINK_UP;
slave_state_changed = 1;
/* 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) {
netdev_info(bond->dev, "link status definitely up for interface %s\n",
slave->dev->name);
do_failover = 1;
} else {
netdev_info(bond->dev, "interface %s is now up\n",
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 (!bond_time_in_interval(bond, trans_start, 2) ||
!bond_time_in_interval(bond, slave->last_rx, 2)) {
slave->new_link = BOND_LINK_DOWN;
slave_state_changed = 1;
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
netdev_info(bond->dev, "interface %s is now down\n",
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 (bond_slave_is_up(slave))
bond_arp_send_all(bond, slave);
}
rcu_read_unlock();
if (do_failover || slave_state_changed) {
if (!rtnl_trylock())
goto re_arm;
bond_for_each_slave(bond, slave, iter) {
if (slave->new_link != BOND_LINK_NOCHANGE)
slave->link = slave->new_link;
}
if (slave_state_changed) {
bond_slave_state_change(bond);
if (BOND_MODE(bond) == BOND_MODE_XOR)
bond_update_slave_arr(bond, NULL);
}
if (do_failover) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
rtnl_unlock();
}
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work,
msecs_to_jiffies(bond->params.arp_interval));
}
/* 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 rcu_read_lock held.
*/
static int bond_ab_arp_inspect(struct bonding *bond)
{
unsigned long trans_start, last_rx;
struct list_head *iter;
struct slave *slave;
int commit = 0;
bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
last_rx = slave_last_rx(bond, slave);
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, last_rx, 1)) {
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 (bond_time_in_interval(bond, slave->last_link_up, 2))
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 (!bond_is_active_slave(slave) &&
!rcu_access_pointer(bond->current_arp_slave) &&
!bond_time_in_interval(bond, last_rx, 3)) {
slave->new_link = BOND_LINK_DOWN;
commit++;
}
/* Active slave is down if:
* - more than 2*delta since transmitting OR