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_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 ----------------------------*/
* @skb: hw accel VLAN tagged skb to transmit
* @slave_dev: slave that is supposed to xmit this skbuff
*/
-int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
+void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
struct net_device *slave_dev)
{
skb->dev = slave_dev;
bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
else
dev_queue_xmit(skb);
-
- return 0;
}
/*
* device and retransmit an IGMP JOIN request to the current active
* slave.
*/
-static void bond_resend_igmp_join_requests(struct bonding *bond)
+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);
- rtnl_unlock();
- /* We use curr_slave_lock to protect against concurrent access to
- * igmp_retrans from multiple running instances of this function and
- * bond_change_active_slave
- */
- write_lock_bh(&bond->curr_slave_lock);
if (bond->igmp_retrans > 1) {
bond->igmp_retrans--;
queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
}
- write_unlock_bh(&bond->curr_slave_lock);
-}
-
-static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
-{
- struct bonding *bond = container_of(work, struct bonding,
- mcast_work.work);
-
- bond_resend_igmp_join_requests(bond);
+ rtnl_unlock();
}
/* Flush bond's hardware addresses from slave
*
* Perform special MAC address swapping for fail_over_mac settings
*
- * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh.
+ * 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)
- __releases(&bond->lock)
- __acquires(&bond->lock)
__acquires(&bond->curr_slave_lock)
{
u8 tmp_mac[ETH_ALEN];
case BOND_FOM_ACTIVE:
if (new_active) {
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
bond_set_dev_addr(bond->dev, new_active->dev);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
}
break;
return;
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
if (old_active) {
memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
pr_err("%s: Error %d setting MAC of slave %s\n",
bond->dev->name, -rv, new_active->dev->name);
out:
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
break;
default:
static bool bond_should_notify_peers(struct bonding *bond)
{
- struct slave *slave = bond->curr_active_slave;
+ 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");
* because it is apparently the best available slave we have, even though its
* updelay hasn't timed out yet.
*
- * If new_active is not NULL, caller must hold bond->lock for read and
- * curr_slave_lock for write_bh.
+ * 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)
{
}
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
if (should_notify_peers)
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
}
}
* - The primary_slave has got its link back.
* - A slave has got its link back and there's no old curr_active_slave.
*
- * Caller must hold bond->lock for read and curr_slave_lock for write_bh.
+ * Caller must hold curr_slave_lock for write_bh.
*/
void bond_select_active_slave(struct bonding *bond)
{
bond_set_carrier(bond);
if (USES_PRIMARY(bond->params.mode)) {
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
}
pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
bond_hw_addr_flush(bond_dev, slave_dev);
vlan_vids_del_by_dev(slave_dev, bond_dev);
- write_lock_bh(&bond->lock);
if (bond->primary_slave == new_slave)
bond->primary_slave = NULL;
if (bond->curr_active_slave == new_slave) {
- bond_change_active_slave(bond, NULL);
- write_unlock_bh(&bond->lock);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
+ bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
- } else {
- write_unlock_bh(&bond->lock);
}
slave_disable_netpoll(new_slave);
err_undo_flags:
/* Enslave of first slave has failed and we need to fix master's mac */
if (!bond_has_slaves(bond) &&
- ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr))
+ ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr))
eth_hw_addr_random(bond_dev);
return res;
}
block_netpoll_tx();
- write_lock_bh(&bond->lock);
slave = bond_get_slave_by_dev(bond, slave_dev);
if (!slave) {
/* not a slave of this bond */
pr_info("%s: %s not enslaved\n",
bond_dev->name, slave_dev->name);
- write_unlock_bh(&bond->lock);
unblock_netpoll_tx();
return -EINVAL;
}
- write_unlock_bh(&bond->lock);
-
/* release the slave from its bond */
bond->slave_cnt--;
write_lock_bh(&bond->lock);
/* Inform AD package of unbinding of slave. */
- if (bond->params.mode == BOND_MODE_8023AD) {
- /* must be called before the slave is
- * detached from the list
- */
+ if (bond->params.mode == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
- }
+
+ write_unlock_bh(&bond->lock);
pr_info("%s: releasing %s interface %s\n",
bond_dev->name,
bond->current_arp_slave = NULL;
if (!all && !bond->params.fail_over_mac) {
- if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) &&
+ if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond_has_slaves(bond))
pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
bond_dev->name, slave_dev->name,
if (bond->primary_slave == slave)
bond->primary_slave = NULL;
- if (oldcurrent == slave)
+ if (oldcurrent == slave) {
+ write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, NULL);
+ write_unlock_bh(&bond->curr_slave_lock);
+ }
if (bond_is_lb(bond)) {
/* Must be called only after the slave has been
* has been cleared (if our_slave == old_current),
* but before a new active slave is selected.
*/
- write_unlock_bh(&bond->lock);
bond_alb_deinit_slave(bond, slave);
- write_lock_bh(&bond->lock);
}
if (all) {
* is no concern that another slave add/remove event
* will interfere.
*/
- write_unlock_bh(&bond->lock);
- read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
- write_lock_bh(&bond->lock);
}
if (!bond_has_slaves(bond)) {
}
}
- write_unlock_bh(&bond->lock);
unblock_netpoll_tx();
synchronize_rcu();
ignore_updelay = !bond->curr_active_slave ? true : false;
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
link_state = bond_check_dev_link(bond, slave->dev, 0);
* an acquisition of appropriate locks followed by a commit phase to
* implement whatever link state changes are indicated.
*/
-void bond_mii_monitor(struct work_struct *work)
+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;
- read_lock(&bond->lock);
-
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)) {
- read_unlock(&bond->lock);
+ rcu_read_unlock();
/* Race avoidance with bond_close cancel of workqueue */
if (!rtnl_trylock()) {
- read_lock(&bond->lock);
delay = 1;
should_notify_peers = false;
goto re_arm;
}
- read_lock(&bond->lock);
-
bond_miimon_commit(bond);
- read_unlock(&bond->lock);
rtnl_unlock(); /* might sleep, hold no other locks */
- read_lock(&bond->lock);
- }
+ } else
+ rcu_read_unlock();
re_arm:
if (bond->params.miimon)
queue_delayed_work(bond->wq, &bond->mii_work, delay);
- read_unlock(&bond->lock);
-
if (should_notify_peers) {
if (!rtnl_trylock())
return;
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
-void bond_loadbalance_arp_mon(struct work_struct *work)
+static void bond_loadbalance_arp_mon(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
struct list_head *iter;
int do_failover = 0;
- read_lock(&bond->lock);
-
if (!bond_has_slaves(bond))
goto re_arm;
- oldcurrent = bond->curr_active_slave;
+ rcu_read_lock();
+
+ oldcurrent = ACCESS_ONCE(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->jiffies is not needed
* TODO: what about up/down delay in arp mode? it wasn't here before
* so it can wait
*/
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
unsigned long trans_start = dev_trans_start(slave->dev);
if (slave->link != BOND_LINK_UP) {
bond_arp_send_all(bond, slave);
}
+ rcu_read_unlock();
+
if (do_failover) {
+ /* the bond_select_active_slave must hold RTNL
+ * and curr_slave_lock for write.
+ */
+ if (!rtnl_trylock())
+ goto re_arm;
block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
write_unlock_bh(&bond->curr_slave_lock);
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));
-
- read_unlock(&bond->lock);
}
/*
* place for the slave. Returns 0 if no changes are found, >0 if changes
* to link states must be committed.
*
- * Called with bond->lock held for read.
+ * Called with rcu_read_lock hold.
*/
static int bond_ab_arp_inspect(struct bonding *bond)
{
struct slave *slave;
int commit = 0;
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
slave->new_link = BOND_LINK_NOCHANGE;
last_rx = slave_last_rx(bond, slave);
* Called to commit link state changes noted by inspection step of
* active-backup mode ARP monitor.
*
- * Called with RTNL and bond->lock for read.
+ * Called with RTNL hold.
*/
static void bond_ab_arp_commit(struct bonding *bond)
{
/*
* Send ARP probes for active-backup mode ARP monitor.
*
- * Called with bond->lock held for read.
+ * Called with rcu_read_lock hold.
*/
static void bond_ab_arp_probe(struct bonding *bond)
{
- struct slave *slave, *before = NULL, *new_slave = NULL;
+ struct slave *slave, *before = NULL, *new_slave = NULL,
+ *curr_arp_slave = rcu_dereference(bond->current_arp_slave);
struct list_head *iter;
bool found = false;
read_lock(&bond->curr_slave_lock);
- if (bond->current_arp_slave && bond->curr_active_slave)
+ if (curr_arp_slave && bond->curr_active_slave)
pr_info("PROBE: c_arp %s && cas %s BAD\n",
- bond->current_arp_slave->dev->name,
+ curr_arp_slave->dev->name,
bond->curr_active_slave->dev->name);
if (bond->curr_active_slave) {
* for becoming the curr_active_slave
*/
- if (!bond->current_arp_slave) {
- bond->current_arp_slave = bond_first_slave(bond);
- if (!bond->current_arp_slave)
+ if (!curr_arp_slave) {
+ curr_arp_slave = bond_first_slave_rcu(bond);
+ if (!curr_arp_slave)
return;
}
- bond_set_slave_inactive_flags(bond->current_arp_slave);
+ bond_set_slave_inactive_flags(curr_arp_slave);
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
if (!found && !before && IS_UP(slave->dev))
before = slave;
pr_info("%s: backup interface %s is now down.\n",
bond->dev->name, slave->dev->name);
}
- if (slave == bond->current_arp_slave)
+ if (slave == curr_arp_slave)
found = true;
}
bond_set_slave_active_flags(new_slave);
bond_arp_send_all(bond, new_slave);
new_slave->jiffies = jiffies;
- bond->current_arp_slave = new_slave;
-
+ rcu_assign_pointer(bond->current_arp_slave, new_slave);
}
-void bond_activebackup_arp_mon(struct work_struct *work)
+static void bond_activebackup_arp_mon(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
bool should_notify_peers = false;
int delta_in_ticks;
- read_lock(&bond->lock);
-
delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
if (!bond_has_slaves(bond))
goto re_arm;
+ rcu_read_lock();
+
should_notify_peers = bond_should_notify_peers(bond);
if (bond_ab_arp_inspect(bond)) {
- read_unlock(&bond->lock);
+ rcu_read_unlock();
/* Race avoidance with bond_close flush of workqueue */
if (!rtnl_trylock()) {
- read_lock(&bond->lock);
delta_in_ticks = 1;
should_notify_peers = false;
goto re_arm;
}
- read_lock(&bond->lock);
-
bond_ab_arp_commit(bond);
- read_unlock(&bond->lock);
rtnl_unlock();
- read_lock(&bond->lock);
+ rcu_read_lock();
}
bond_ab_arp_probe(bond);
+ rcu_read_unlock();
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
- read_unlock(&bond->lock);
-
if (should_notify_peers) {
if (!rtnl_trylock())
return;
* it fails, it tries to find the first available slave for transmission.
* The skb is consumed in all cases, thus the function is void.
*/
-void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
+static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
{
struct list_head *iter;
struct slave *slave;
struct sk_buff *skb)
{
struct slave *slave = NULL;
- struct slave *check_slave;
struct list_head *iter;
- int res = 1;
if (!skb->queue_mapping)
return 1;
/* Find out if any slaves have the same mapping as this skb. */
- bond_for_each_slave_rcu(bond, check_slave, iter) {
- if (check_slave->queue_id == skb->queue_mapping) {
- slave = check_slave;
+ bond_for_each_slave_rcu(bond, slave, iter) {
+ if (slave->queue_id == skb->queue_mapping) {
+ if (slave_can_tx(slave)) {
+ bond_dev_queue_xmit(bond, skb, slave->dev);
+ return 0;
+ }
+ /* If the slave isn't UP, use default transmit policy. */
break;
}
}
- /* If the slave isn't UP, use default transmit policy. */
- if (slave && slave->queue_id && IS_UP(slave->dev) &&
- (slave->link == BOND_LINK_UP)) {
- res = bond_dev_queue_xmit(bond, skb, slave->dev);
- }
-
- return res;
+ return 1;
}
/*------------------------- Module initialization ---------------------------*/
+int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl)
+{
+ int i;
+
+ for (i = 0; tbl[i].modename; i++)
+ if (mode == tbl[i].mode)
+ return tbl[i].mode;
+
+ return -1;
+}
+
+static int bond_parm_tbl_lookup_name(const char *modename,
+ const struct bond_parm_tbl *tbl)
+{
+ int i;
+
+ for (i = 0; tbl[i].modename; i++)
+ if (strcmp(modename, tbl[i].modename) == 0)
+ return tbl[i].mode;
+
+ return -1;
+}
+
/*
* Convert string input module parms. Accept either the
* number of the mode or its string name. A bit complicated because
*/
int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
{
- int modeint = -1, i, rv;
- char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, };
+ int modeint;
+ char *p, modestr[BOND_MAX_MODENAME_LEN + 1];
for (p = (char *)buf; *p; p++)
if (!(isdigit(*p) || isspace(*p)))
break;
- if (*p)
- rv = sscanf(buf, "%20s", modestr);
- else
- rv = sscanf(buf, "%d", &modeint);
-
- if (!rv)
- return -1;
-
- for (i = 0; tbl[i].modename; i++) {
- if (modeint == tbl[i].mode)
- return tbl[i].mode;
- if (strcmp(modestr, tbl[i].modename) == 0)
- return tbl[i].mode;
- }
+ if (*p && sscanf(buf, "%20s", modestr) != 0)
+ return bond_parm_tbl_lookup_name(modestr, tbl);
+ else if (sscanf(buf, "%d", &modeint) != 0)
+ return bond_parm_tbl_lookup(modeint, tbl);
return -1;
}
num_peer_notif = 1;
}
- /* reset values for 802.3ad */
- if (bond_mode == BOND_MODE_8023AD) {
+ /* reset values for 802.3ad/TLB/ALB */
+ if (BOND_NO_USES_ARP(bond_mode)) {
if (!miimon) {
pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
pr_warning("Forcing miimon to 100msec\n");
packets_per_slave = 1;
}
- /* reset values for TLB/ALB */
- if ((bond_mode == BOND_MODE_TLB) ||
- (bond_mode == BOND_MODE_ALB)) {
- if (!miimon) {
- pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure and link speed which are essential for TLB/ALB load balancing\n");
- pr_warning("Forcing miimon to 100msec\n");
- miimon = BOND_DEFAULT_MIIMON;
- }
- }
-
if (bond_mode == BOND_MODE_ALB) {
pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n",
updelay);
fail_over_mac_value = BOND_FOM_NONE;
}
+ if (lp_interval == 0) {
+ pr_warning("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
+ INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
+ lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
+ }
+
/* fill params struct with the proper values */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->all_slaves_active = all_slaves_active;
params->resend_igmp = resend_igmp;
params->min_links = min_links;
- params->lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
+ params->lp_interval = lp_interval;
if (packets_per_slave > 1)
params->packets_per_slave = reciprocal_value(packets_per_slave);
else
projects / ~andy / linux / blobdiff