#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include <net/route.h>
+#include <net/net_namespace.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"
static int arp_interval = BOND_LINK_ARP_INTERV;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };
static char *arp_validate = NULL;
+static int fail_over_mac = 0;
struct bond_params bonding_defaults;
module_param(max_bonds, int, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
module_param(arp_validate, charp, 0);
MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all");
+module_param(fail_over_mac, int, 0);
+MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC. 0 of off (default), 1 for on.");
/*----------------------------- Global variables ----------------------------*/
#endif
extern struct rw_semaphore bonding_rwsem;
-static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
+static __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
static int arp_ip_count = 0;
static int bond_mode = BOND_MODE_ROUNDROBIN;
static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2;
/*-------------------------- Forward declarations ---------------------------*/
static void bond_send_gratuitous_arp(struct bonding *bond);
+static void bond_deinit(struct net_device *bond_dev);
/*---------------------------- General routines -----------------------------*/
if (new_active) {
bond_set_slave_active_flags(new_active);
}
- bond_send_gratuitous_arp(bond);
+
+ /* when bonding does not set the slave MAC address, the bond MAC
+ * address is the one of the active slave.
+ */
+ if (new_active && bond->params.fail_over_mac)
+ memcpy(bond->dev->dev_addr, new_active->dev->dev_addr,
+ new_active->dev->addr_len);
+ if (bond->curr_active_slave &&
+ test_bit(__LINK_STATE_LINKWATCH_PENDING,
+ &bond->curr_active_slave->dev->state)) {
+ dprintk("delaying gratuitous arp on %s\n",
+ bond->curr_active_slave->dev->name);
+ bond->send_grat_arp = 1;
+ } else
+ bond_send_gratuitous_arp(bond);
}
}
struct slave *slave;
struct net_device *bond_dev = bond->dev;
unsigned long features = bond_dev->features;
- unsigned short max_hard_header_len = ETH_HLEN;
+ unsigned short max_hard_header_len = max((u16)ETH_HLEN,
+ bond_dev->hard_header_len);
int i;
features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
return 0;
}
+
+static void bond_setup_by_slave(struct net_device *bond_dev,
+ struct net_device *slave_dev)
+{
+ struct bonding *bond = bond_dev->priv;
+
+ bond_dev->neigh_setup = slave_dev->neigh_setup;
+ bond_dev->header_ops = slave_dev->header_ops;
+
+ bond_dev->type = slave_dev->type;
+ bond_dev->hard_header_len = slave_dev->hard_header_len;
+ bond_dev->addr_len = slave_dev->addr_len;
+
+ memcpy(bond_dev->broadcast, slave_dev->broadcast,
+ slave_dev->addr_len);
+ bond->setup_by_slave = 1;
+}
+
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
/* bond must be initialized by bond_open() before enslaving */
if (!(bond_dev->flags & IFF_UP)) {
- dprintk("Error, master_dev is not up\n");
- return -EPERM;
+ printk(KERN_WARNING DRV_NAME
+ " %s: master_dev is not up in bond_enslave\n",
+ bond_dev->name);
}
/* already enslaved */
goto err_undo_flags;
}
+ /* set bonding device ether type by slave - bonding netdevices are
+ * created with ether_setup, so when the slave type is not ARPHRD_ETHER
+ * there is a need to override some of the type dependent attribs/funcs.
+ *
+ * bond ether type mutual exclusion - don't allow slaves of dissimilar
+ * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
+ */
+ if (bond->slave_cnt == 0) {
+ if (slave_dev->type != ARPHRD_ETHER)
+ bond_setup_by_slave(bond_dev, slave_dev);
+ } else if (bond_dev->type != slave_dev->type) {
+ printk(KERN_ERR DRV_NAME ": %s ether type (%d) is different "
+ "from other slaves (%d), can not enslave it.\n",
+ slave_dev->name,
+ slave_dev->type, bond_dev->type);
+ res = -EINVAL;
+ goto err_undo_flags;
+ }
+
if (slave_dev->set_mac_address == NULL) {
- printk(KERN_ERR DRV_NAME
- ": %s: Error: The slave device you specified does "
- "not support setting the MAC address. "
- "Your kernel likely does not support slave "
- "devices.\n", bond_dev->name);
- res = -EOPNOTSUPP;
- goto err_undo_flags;
+ if (bond->slave_cnt == 0) {
+ printk(KERN_WARNING DRV_NAME
+ ": %s: Warning: The first slave device "
+ "specified does not support setting the MAC "
+ "address. Enabling the fail_over_mac option.",
+ bond_dev->name);
+ bond->params.fail_over_mac = 1;
+ } else if (!bond->params.fail_over_mac) {
+ printk(KERN_ERR DRV_NAME
+ ": %s: Error: The slave device specified "
+ "does not support setting the MAC address, "
+ "but fail_over_mac is not enabled.\n"
+ , bond_dev->name);
+ res = -EOPNOTSUPP;
+ goto err_undo_flags;
+ }
}
new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
*/
memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);
- /*
- * Set slave to master's mac address. The application already
- * set the master's mac address to that of the first slave
- */
- memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
- addr.sa_family = slave_dev->type;
- res = dev_set_mac_address(slave_dev, &addr);
- if (res) {
- dprintk("Error %d calling set_mac_address\n", res);
- goto err_free;
+ if (!bond->params.fail_over_mac) {
+ /*
+ * Set slave to master's mac address. The application already
+ * set the master's mac address to that of the first slave
+ */
+ memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
+ addr.sa_family = slave_dev->type;
+ res = dev_set_mac_address(slave_dev, &addr);
+ if (res) {
+ dprintk("Error %d calling set_mac_address\n", res);
+ goto err_free;
+ }
}
res = netdev_set_master(slave_dev, bond_dev);
case BOND_MODE_TLB:
case BOND_MODE_ALB:
new_slave->state = BOND_STATE_ACTIVE;
- if ((!bond->curr_active_slave) &&
- (new_slave->link != BOND_LINK_DOWN)) {
- /* first slave or no active slave yet, and this link
- * is OK, so make this interface the active one
- */
- bond_change_active_slave(bond, new_slave);
- } else {
- bond_set_slave_inactive_flags(new_slave);
- }
+ bond_set_slave_inactive_flags(new_slave);
break;
default:
dprintk("This slave is always active in trunk mode\n");
dev_close(slave_dev);
err_restore_mac:
- memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ if (!bond->params.fail_over_mac) {
+ memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
+ }
err_free:
kfree(new_slave);
struct slave *slave, *oldcurrent;
struct sockaddr addr;
int mac_addr_differ;
+ DECLARE_MAC_BUF(mac);
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
ETH_ALEN);
if (!mac_addr_differ && (bond->slave_cnt > 1)) {
printk(KERN_WARNING DRV_NAME
- ": %s: Warning: the permanent HWaddr of %s "
- "- %02X:%02X:%02X:%02X:%02X:%02X - is "
- "still in use by %s. Set the HWaddr of "
- "%s to a different address to avoid "
- "conflicts.\n",
+ ": %s: Warning: the permanent HWaddr of %s - "
+ "%s - is still in use by %s. "
+ "Set the HWaddr of %s to a different address "
+ "to avoid conflicts.\n",
bond_dev->name,
slave_dev->name,
- slave->perm_hwaddr[0],
- slave->perm_hwaddr[1],
- slave->perm_hwaddr[2],
- slave->perm_hwaddr[3],
- slave->perm_hwaddr[4],
- slave->perm_hwaddr[5],
+ print_mac(mac, slave->perm_hwaddr),
bond_dev->name,
slave_dev->name);
}
bond_alb_deinit_slave(bond, slave);
}
- if (oldcurrent == slave)
+ if (oldcurrent == slave) {
+ /*
+ * Note that we hold RTNL over this sequence, so there
+ * is no concern that another slave add/remove event
+ * will interfere.
+ */
+ write_unlock_bh(&bond->lock);
+ read_lock(&bond->lock);
+ write_lock_bh(&bond->curr_slave_lock);
+
bond_select_active_slave(bond);
+ write_unlock_bh(&bond->curr_slave_lock);
+ read_unlock(&bond->lock);
+ write_lock_bh(&bond->lock);
+ }
+
if (bond->slave_cnt == 0) {
bond_set_carrier(bond);
/* close slave before restoring its mac address */
dev_close(slave_dev);
- /* restore original ("permanent") mac address */
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ if (!bond->params.fail_over_mac) {
+ /* restore original ("permanent") mac address */
+ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
+ }
slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
IFF_SLAVE_INACTIVE | IFF_BONDING |
return 0; /* deletion OK */
}
+/*
+* Destroy a bonding device.
+* Must be under rtnl_lock when this function is called.
+*/
+void bond_destroy(struct bonding *bond)
+{
+ unregister_netdevice(bond->dev);
+ bond_deinit(bond->dev);
+ bond_destroy_sysfs_entry(bond);
+}
+
+/*
+* First release a slave and than destroy the bond if no more slaves iare left.
+* Must be under rtnl_lock when this function is called.
+*/
+int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev)
+{
+ struct bonding *bond = bond_dev->priv;
+ int ret;
+
+ ret = bond_release(bond_dev, slave_dev);
+ if ((ret == 0) && (bond->slave_cnt == 0)) {
+ printk(KERN_INFO DRV_NAME ": %s: destroying bond %s.\n",
+ bond_dev->name, bond_dev->name);
+ bond_destroy(bond);
+ }
+ return ret;
+}
+
/*
* This function releases all slaves.
*/
/* close slave before restoring its mac address */
dev_close(slave_dev);
- /* restore original ("permanent") mac address*/
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ if (!bond->params.fail_over_mac) {
+ /* restore original ("permanent") mac address*/
+ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+ addr.sa_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, &addr);
+ }
slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
IFF_SLAVE_INACTIVE);
return -EINVAL;
}
- write_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
+ read_lock(&bond->curr_slave_lock);
old_active = bond->curr_active_slave;
+ read_unlock(&bond->curr_slave_lock);
+
new_active = bond_get_slave_by_dev(bond, slave_dev);
/*
* Changing to the current active: do nothing; return success.
*/
if (new_active && (new_active == old_active)) {
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return 0;
}
(old_active) &&
(new_active->link == BOND_LINK_UP) &&
IS_UP(new_active->dev)) {
+ write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, new_active);
+ write_unlock_bh(&bond->curr_slave_lock);
} else {
res = -EINVAL;
}
- write_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return res;
}
info->bond_mode = bond->params.mode;
info->miimon = bond->params.miimon;
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
info->num_slaves = bond->slave_cnt;
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
return 0;
}
return -ENODEV;
}
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
bond_for_each_slave(bond, slave, i) {
if (i == (int)info->slave_id) {
}
}
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
if (found) {
strcpy(info->slave_name, slave->dev->name);
/*-------------------------------- Monitoring -------------------------------*/
-/* this function is called regularly to monitor each slave's link. */
-void bond_mii_monitor(struct net_device *bond_dev)
+/*
+ * if !have_locks, return nonzero if a failover is necessary. if
+ * have_locks, do whatever failover activities are needed.
+ *
+ * This is to separate the inspection and failover steps for locking
+ * purposes; failover requires rtnl, but acquiring it for every
+ * inspection is undesirable, so a wrapper first does inspection, and
+ * the acquires the necessary locks and calls again to perform
+ * failover if needed. Since all locks are dropped, a complete
+ * restart is needed between calls.
+ */
+static int __bond_mii_monitor(struct bonding *bond, int have_locks)
{
- struct bonding *bond = bond_dev->priv;
struct slave *slave, *oldcurrent;
int do_failover = 0;
- int delta_in_ticks;
int i;
- read_lock(&bond->lock);
-
- delta_in_ticks = (bond->params.miimon * HZ) / 1000;
-
- if (bond->kill_timers) {
+ if (bond->slave_cnt == 0)
goto out;
- }
-
- if (bond->slave_cnt == 0) {
- goto re_arm;
- }
/* we will try to read the link status of each of our slaves, and
* set their IFF_RUNNING flag appropriately. For each slave not
* program could monitor the link itself if needed.
*/
+ if (bond->send_grat_arp) {
+ if (bond->curr_active_slave && test_bit(__LINK_STATE_LINKWATCH_PENDING,
+ &bond->curr_active_slave->dev->state))
+ dprintk("Needs to send gratuitous arp but not yet\n");
+ else {
+ dprintk("sending delayed gratuitous arp on on %s\n",
+ bond->curr_active_slave->dev->name);
+ bond_send_gratuitous_arp(bond);
+ bond->send_grat_arp = 0;
+ }
+ }
read_lock(&bond->curr_slave_lock);
oldcurrent = bond->curr_active_slave;
read_unlock(&bond->curr_slave_lock);
switch (slave->link) {
case BOND_LINK_UP: /* the link was up */
if (link_state == BMSR_LSTATUS) {
- /* link stays up, nothing more to do */
+ if (!oldcurrent) {
+ if (!have_locks)
+ return 1;
+ do_failover = 1;
+ }
break;
} else { /* link going down */
slave->link = BOND_LINK_FAIL;
": %s: link status down for %s "
"interface %s, disabling it in "
"%d ms.\n",
- bond_dev->name,
+ bond->dev->name,
IS_UP(slave_dev)
? ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
? ((slave == oldcurrent)
if (link_state != BMSR_LSTATUS) {
/* link stays down */
if (slave->delay <= 0) {
+ if (!have_locks)
+ return 1;
+
/* link down for too long time */
slave->link = BOND_LINK_DOWN;
": %s: link status definitely "
"down for interface %s, "
"disabling it\n",
- bond_dev->name,
+ bond->dev->name,
slave_dev->name);
/* notify ad that the link status has changed */
printk(KERN_INFO DRV_NAME
": %s: link status up again after %d "
"ms for interface %s.\n",
- bond_dev->name,
+ bond->dev->name,
(bond->params.downdelay - slave->delay) * bond->params.miimon,
slave_dev->name);
}
": %s: link status up for "
"interface %s, enabling it "
"in %d ms.\n",
- bond_dev->name,
+ bond->dev->name,
slave_dev->name,
bond->params.updelay * bond->params.miimon);
}
printk(KERN_INFO DRV_NAME
": %s: link status down again after %d "
"ms for interface %s.\n",
- bond_dev->name,
+ bond->dev->name,
(bond->params.updelay - slave->delay) * bond->params.miimon,
slave_dev->name);
} else {
/* link stays up */
if (slave->delay == 0) {
+ if (!have_locks)
+ return 1;
+
/* now the link has been up for long time enough */
slave->link = BOND_LINK_UP;
slave->jiffies = jiffies;
printk(KERN_INFO DRV_NAME
": %s: link status definitely "
"up for interface %s.\n",
- bond_dev->name,
+ bond->dev->name,
slave_dev->name);
/* notify ad that the link status has changed */
/* Should not happen */
printk(KERN_ERR DRV_NAME
": %s: Error: %s Illegal value (link=%d)\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name,
slave->link);
goto out;
} /* end of for */
if (do_failover) {
- write_lock(&bond->curr_slave_lock);
+ ASSERT_RTNL();
+
+ write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+
} else
bond_set_carrier(bond);
-re_arm:
- if (bond->params.miimon) {
- mod_timer(&bond->mii_timer, jiffies + delta_in_ticks);
- }
out:
- read_unlock(&bond->lock);
+ return 0;
}
+/*
+ * 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 another pass
+ * to implement whatever link state changes are indicated.
+ */
+void bond_mii_monitor(struct work_struct *work)
+{
+ struct bonding *bond = container_of(work, struct bonding,
+ mii_work.work);
+ unsigned long delay;
+
+ read_lock(&bond->lock);
+ if (bond->kill_timers) {
+ read_unlock(&bond->lock);
+ return;
+ }
+ if (__bond_mii_monitor(bond, 0)) {
+ read_unlock(&bond->lock);
+ rtnl_lock();
+ read_lock(&bond->lock);
+ __bond_mii_monitor(bond, 1);
+ rtnl_unlock();
+ }
+
+ delay = ((bond->params.miimon * HZ) / 1000) ? : 1;
+ read_unlock(&bond->lock);
+ queue_delayed_work(bond->wq, &bond->mii_work, delay);
+}
-static u32 bond_glean_dev_ip(struct net_device *dev)
+static __be32 bond_glean_dev_ip(struct net_device *dev)
{
struct in_device *idev;
struct in_ifaddr *ifa;
return 0;
}
-static int bond_has_this_ip(struct bonding *bond, u32 ip)
+static int bond_has_this_ip(struct bonding *bond, __be32 ip)
{
struct vlan_entry *vlan, *vlan_next;
* 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, u32 dest_ip, u32 src_ip, unsigned short vlan_id)
+static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
{
struct sk_buff *skb;
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
int i, vlan_id, rv;
- u32 *targets = bond->params.arp_targets;
+ __be32 *targets = bond->params.arp_targets;
struct vlan_entry *vlan, *vlan_next;
struct net_device *vlan_dev;
struct flowi fl;
if (bond->master_ip) {
bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
- bond->master_ip, 0);
+ bond->master_ip, 0);
}
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
}
}
-static void bond_validate_arp(struct bonding *bond, struct slave *slave, u32 sip, u32 tip)
+static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
int i;
- u32 *targets = bond->params.arp_targets;
+ __be32 *targets = bond->params.arp_targets;
targets = bond->params.arp_targets;
for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
struct slave *slave;
struct bonding *bond;
unsigned char *arp_ptr;
- u32 sip, tip;
+ __be32 sip, tip;
+
+ if (dev->nd_net != &init_net)
+ goto out;
if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
goto out;
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
-void bond_loadbalance_arp_mon(struct net_device *bond_dev)
+void bond_loadbalance_arp_mon(struct work_struct *work)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = container_of(work, struct bonding,
+ arp_work.work);
struct slave *slave, *oldcurrent;
int do_failover = 0;
int delta_in_ticks;
printk(KERN_INFO DRV_NAME
": %s: link status definitely "
"up for interface %s, ",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
do_failover = 1;
} else {
printk(KERN_INFO DRV_NAME
": %s: interface %s is now up\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
}
}
printk(KERN_INFO DRV_NAME
": %s: interface %s is now down.\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
if (slave == oldcurrent) {
}
if (do_failover) {
- write_lock(&bond->curr_slave_lock);
+ rtnl_lock();
+ write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+ rtnl_unlock();
+
}
re_arm:
- if (bond->params.arp_interval) {
- mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
- }
+ if (bond->params.arp_interval)
+ queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
out:
read_unlock(&bond->lock);
}
* may have received.
* see loadbalance_arp_monitor for arp monitoring in load balancing mode
*/
-void bond_activebackup_arp_mon(struct net_device *bond_dev)
+void bond_activebackup_arp_mon(struct work_struct *work)
{
- struct bonding *bond = bond_dev->priv;
+ struct bonding *bond = container_of(work, struct bonding,
+ arp_work.work);
struct slave *slave;
int delta_in_ticks;
int i;
slave->link = BOND_LINK_UP;
- write_lock(&bond->curr_slave_lock);
+ rtnl_lock();
+
+ write_lock_bh(&bond->curr_slave_lock);
if ((!bond->curr_active_slave) &&
((jiffies - slave->dev->trans_start) <= delta_in_ticks)) {
printk(KERN_INFO DRV_NAME
": %s: %s is up and now the "
"active interface\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
netif_carrier_on(bond->dev);
} else {
printk(KERN_INFO DRV_NAME
": %s: backup interface %s is "
"now up\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
}
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+ rtnl_unlock();
}
} else {
read_lock(&bond->curr_slave_lock);
printk(KERN_INFO DRV_NAME
": %s: backup interface %s is now down\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
} else {
read_unlock(&bond->curr_slave_lock);
printk(KERN_INFO DRV_NAME
": %s: link status down for active interface "
"%s, disabling it\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
- write_lock(&bond->curr_slave_lock);
+ rtnl_lock();
+ write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
slave = bond->curr_active_slave;
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+
+ rtnl_unlock();
bond->current_arp_slave = slave;
printk(KERN_INFO DRV_NAME
": %s: changing from interface %s to primary "
"interface %s\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name,
bond->primary_slave->dev->name);
/* primary is up so switch to it */
- write_lock(&bond->curr_slave_lock);
+ rtnl_lock();
+ write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, bond->primary_slave);
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
+
+ rtnl_unlock();
slave = bond->primary_slave;
slave->jiffies = jiffies;
printk(KERN_INFO DRV_NAME
": %s: backup interface %s is "
"now down.\n",
- bond_dev->name,
+ bond->dev->name,
slave->dev->name);
}
}
re_arm:
if (bond->params.arp_interval) {
- mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
+ queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
}
out:
read_unlock(&bond->lock);
/* make sure the bond won't be taken away */
read_lock(&dev_base_lock);
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
if (*pos == 0) {
return SEQ_START_TOKEN;
{
struct bonding *bond = seq->private;
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
read_unlock(&dev_base_lock);
}
curr = bond->curr_active_slave;
read_unlock(&bond->curr_slave_lock);
- seq_printf(seq, "Bonding Mode: %s\n",
+ seq_printf(seq, "Bonding Mode: %s",
bond_mode_name(bond->params.mode));
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP &&
+ bond->params.fail_over_mac)
+ seq_printf(seq, " (fail_over_mac)");
+
+ seq_printf(seq, "\n");
+
if (bond->params.mode == BOND_MODE_XOR ||
bond->params.mode == BOND_MODE_8023AD) {
seq_printf(seq, "Transmit Hash Policy: %s (%d)\n",
if (bond->params.mode == BOND_MODE_8023AD) {
struct ad_info ad_info;
+ DECLARE_MAC_BUF(mac);
seq_puts(seq, "\n802.3ad info\n");
seq_printf(seq, "LACP rate: %s\n",
ad_info.actor_key);
seq_printf(seq, "\tPartner Key: %d\n",
ad_info.partner_key);
- seq_printf(seq, "\tPartner Mac Address: %02x:%02x:%02x:%02x:%02x:%02x\n",
- ad_info.partner_system[0],
- ad_info.partner_system[1],
- ad_info.partner_system[2],
- ad_info.partner_system[3],
- ad_info.partner_system[4],
- ad_info.partner_system[5]);
+ seq_printf(seq, "\tPartner Mac Address: %s\n",
+ print_mac(mac, ad_info.partner_system));
}
}
}
static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave)
{
struct bonding *bond = seq->private;
+ DECLARE_MAC_BUF(mac);
seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
seq_printf(seq, "MII Status: %s\n",
slave->link_failure_count);
seq_printf(seq,
- "Permanent HW addr: %02x:%02x:%02x:%02x:%02x:%02x\n",
- slave->perm_hwaddr[0], slave->perm_hwaddr[1],
- slave->perm_hwaddr[2], slave->perm_hwaddr[3],
- slave->perm_hwaddr[4], slave->perm_hwaddr[5]);
+ "Permanent HW addr: %s\n",
+ print_mac(mac, slave->perm_hwaddr));
if (bond->params.mode == BOND_MODE_8023AD) {
const struct aggregator *agg
{
int len = strlen(DRV_NAME);
- for (bond_proc_dir = proc_net->subdir; bond_proc_dir;
+ for (bond_proc_dir = init_net.proc_net->subdir; bond_proc_dir;
bond_proc_dir = bond_proc_dir->next) {
if ((bond_proc_dir->namelen == len) &&
!memcmp(bond_proc_dir->name, DRV_NAME, len)) {
}
if (!bond_proc_dir) {
- bond_proc_dir = proc_mkdir(DRV_NAME, proc_net);
+ bond_proc_dir = proc_mkdir(DRV_NAME, init_net.proc_net);
if (bond_proc_dir) {
bond_proc_dir->owner = THIS_MODULE;
} else {
bond_proc_dir->owner = NULL;
}
} else {
- remove_proc_entry(DRV_NAME, proc_net);
+ remove_proc_entry(DRV_NAME, init_net.proc_net);
bond_proc_dir = NULL;
}
}
switch (event) {
case NETDEV_UNREGISTER:
if (bond_dev) {
- bond_release(bond_dev, slave_dev);
+ if (bond->setup_by_slave)
+ bond_release_and_destroy(bond_dev, slave_dev);
+ else
+ bond_release(bond_dev, slave_dev);
}
break;
case NETDEV_CHANGE:
{
struct net_device *event_dev = (struct net_device *)ptr;
+ if (event_dev->nd_net != &init_net)
+ return NOTIFY_DONE;
+
dprintk("event_dev: %s, event: %lx\n",
(event_dev ? event_dev->name : "None"),
event);
{
struct ethhdr *data = (struct ethhdr *)skb->data;
struct iphdr *iph = ip_hdr(skb);
- u16 *layer4hdr = (u16 *)((u32 *)iph + iph->ihl);
+ __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
int layer4_xor = 0;
if (skb->protocol == __constant_htons(ETH_P_IP)) {
if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) &&
(iph->protocol == IPPROTO_TCP ||
iph->protocol == IPPROTO_UDP)) {
- layer4_xor = htons((*layer4hdr ^ *(layer4hdr + 1)));
+ layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1)));
}
return (layer4_xor ^
((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
static int bond_open(struct net_device *bond_dev)
{
struct bonding *bond = bond_dev->priv;
- struct timer_list *mii_timer = &bond->mii_timer;
- struct timer_list *arp_timer = &bond->arp_timer;
bond->kill_timers = 0;
if ((bond->params.mode == BOND_MODE_TLB) ||
(bond->params.mode == BOND_MODE_ALB)) {
- struct timer_list *alb_timer = &(BOND_ALB_INFO(bond).alb_timer);
-
/* bond_alb_initialize must be called before the timer
* is started.
*/
return -1;
}
- init_timer(alb_timer);
- alb_timer->expires = jiffies + 1;
- alb_timer->data = (unsigned long)bond;
- alb_timer->function = (void *)&bond_alb_monitor;
- add_timer(alb_timer);
+ INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
+ queue_delayed_work(bond->wq, &bond->alb_work, 0);
}
if (bond->params.miimon) { /* link check interval, in milliseconds. */
- init_timer(mii_timer);
- mii_timer->expires = jiffies + 1;
- mii_timer->data = (unsigned long)bond_dev;
- mii_timer->function = (void *)&bond_mii_monitor;
- add_timer(mii_timer);
+ INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
+ queue_delayed_work(bond->wq, &bond->mii_work, 0);
}
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
- init_timer(arp_timer);
- arp_timer->expires = jiffies + 1;
- arp_timer->data = (unsigned long)bond_dev;
- if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
- arp_timer->function = (void *)&bond_activebackup_arp_mon;
- } else {
- arp_timer->function = (void *)&bond_loadbalance_arp_mon;
- }
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+ INIT_DELAYED_WORK(&bond->arp_work,
+ bond_activebackup_arp_mon);
+ else
+ INIT_DELAYED_WORK(&bond->arp_work,
+ bond_loadbalance_arp_mon);
+
+ queue_delayed_work(bond->wq, &bond->arp_work, 0);
if (bond->params.arp_validate)
bond_register_arp(bond);
-
- add_timer(arp_timer);
}
if (bond->params.mode == BOND_MODE_8023AD) {
- struct timer_list *ad_timer = &(BOND_AD_INFO(bond).ad_timer);
- init_timer(ad_timer);
- ad_timer->expires = jiffies + 1;
- ad_timer->data = (unsigned long)bond;
- ad_timer->function = (void *)&bond_3ad_state_machine_handler;
- add_timer(ad_timer);
-
+ INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
+ queue_delayed_work(bond->wq, &bond->ad_work, 0);
/* register to receive LACPDUs */
bond_register_lacpdu(bond);
}
write_unlock_bh(&bond->lock);
- /* del_timer_sync must run without holding the bond->lock
- * because a running timer might be trying to hold it too
- */
-
if (bond->params.miimon) { /* link check interval, in milliseconds. */
- del_timer_sync(&bond->mii_timer);
+ cancel_delayed_work(&bond->mii_work);
}
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
- del_timer_sync(&bond->arp_timer);
+ cancel_delayed_work(&bond->arp_work);
}
switch (bond->params.mode) {
case BOND_MODE_8023AD:
- del_timer_sync(&(BOND_AD_INFO(bond).ad_timer));
+ cancel_delayed_work(&bond->ad_work);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
- del_timer_sync(&(BOND_ALB_INFO(bond).alb_timer));
+ cancel_delayed_work(&bond->alb_work);
break;
default:
break;
if (mii->reg_num == 1) {
struct bonding *bond = bond_dev->priv;
mii->val_out = 0;
- read_lock_bh(&bond->lock);
+ read_lock(&bond->lock);
read_lock(&bond->curr_slave_lock);
if (netif_carrier_ok(bond->dev)) {
mii->val_out = BMSR_LSTATUS;
}
read_unlock(&bond->curr_slave_lock);
- read_unlock_bh(&bond->lock);
+ read_unlock(&bond->lock);
}
return 0;
}
down_write(&(bonding_rwsem));
- slave_dev = dev_get_by_name(ifr->ifr_slave);
+ slave_dev = dev_get_by_name(&init_net, ifr->ifr_slave);
dprintk("slave_dev=%p: \n", slave_dev);
dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None"));
+ /*
+ * If fail_over_mac is enabled, do nothing and return success.
+ * Returning an error causes ifenslave to fail.
+ */
+ if (bond->params.fail_over_mac)
+ return 0;
+
if (!is_valid_ether_addr(sa->sa_data)) {
return -EADDRNOTAVAIL;
}
{
struct bonding *bond = bond_dev->priv;
struct slave *slave, *start_at;
- int i;
- int res = 1;
+ int i, slave_no, res = 1;
read_lock(&bond->lock);
goto out;
}
- read_lock(&bond->curr_slave_lock);
- slave = start_at = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ /*
+ * Concurrent TX may collide on rr_tx_counter; we accept that
+ * as being rare enough not to justify using an atomic op here
+ */
+ slave_no = bond->rr_tx_counter++ % bond->slave_cnt;
- if (!slave) {
- goto out;
+ bond_for_each_slave(bond, slave, i) {
+ slave_no--;
+ if (slave_no < 0) {
+ break;
+ }
}
+ start_at = slave;
bond_for_each_slave_from(bond, slave, i, start_at) {
if (IS_UP(slave->dev) &&
(slave->link == BOND_LINK_UP) &&
(slave->state == BOND_STATE_ACTIVE)) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
-
- write_lock(&bond->curr_slave_lock);
- bond->curr_active_slave = slave->next;
- write_unlock(&bond->curr_slave_lock);
-
break;
}
}
-
out:
if (res) {
/* no suitable interface, frame not sent */
}
static const struct ethtool_ops bond_ethtool_ops = {
- .get_tx_csum = ethtool_op_get_tx_csum,
- .get_tso = ethtool_op_get_tso,
- .get_ufo = ethtool_op_get_ufo,
- .get_sg = ethtool_op_get_sg,
.get_drvinfo = bond_ethtool_get_drvinfo,
};
bond->params = *params; /* copy params struct */
+ bond->wq = create_singlethread_workqueue(bond_dev->name);
+ if (!bond->wq)
+ return -ENOMEM;
+
/* Initialize pointers */
bond->first_slave = NULL;
bond->curr_active_slave = NULL;
bond->current_arp_slave = NULL;
bond->primary_slave = NULL;
bond->dev = bond_dev;
+ bond->send_grat_arp = 0;
+ bond->setup_by_slave = 0;
INIT_LIST_HEAD(&bond->vlan_list);
/* Initialize the device entry points */
#ifdef CONFIG_PROC_FS
bond_create_proc_entry(bond);
#endif
-
list_add_tail(&bond->bond_list, &bond_dev_list);
return 0;
/* De-initialize device specific data.
* Caller must hold rtnl_lock.
*/
-void bond_deinit(struct net_device *bond_dev)
+static void bond_deinit(struct net_device *bond_dev)
{
struct bonding *bond = bond_dev->priv;
bond_mc_list_destroy(bond);
/* Release the bonded slaves */
bond_release_all(bond_dev);
- bond_deinit(bond_dev);
unregister_netdevice(bond_dev);
+ bond_deinit(bond_dev);
}
#ifdef CONFIG_PROC_FS
arp_ip_target[arp_ip_count]);
arp_interval = 0;
} else {
- u32 ip = in_aton(arp_ip_target[arp_ip_count]);
+ __be32 ip = in_aton(arp_ip_target[arp_ip_count]);
arp_target[arp_ip_count] = ip;
}
}
primary = NULL;
}
+ if (fail_over_mac && (bond_mode != BOND_MODE_ACTIVEBACKUP))
+ printk(KERN_WARNING DRV_NAME
+ ": Warning: fail_over_mac only affects "
+ "active-backup mode.\n");
+
/* fill params struct with the proper values */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->use_carrier = use_carrier;
params->lacp_fast = lacp_fast;
params->primary[0] = 0;
+ params->fail_over_mac = fail_over_mac;
if (primary) {
strncpy(params->primary, primary, IFNAMSIZ);
goto out_netdev;
}
- SET_MODULE_OWNER(bond_dev);
-
res = register_netdevice(bond_dev);
if (res < 0) {
goto out_bond;
return res;
}
+static void bond_work_cancel_all(struct bonding *bond)
+{
+ write_lock_bh(&bond->lock);
+ bond->kill_timers = 1;
+ write_unlock_bh(&bond->lock);
+
+ if (bond->params.miimon && delayed_work_pending(&bond->mii_work))
+ cancel_delayed_work(&bond->mii_work);
+
+ if (bond->params.arp_interval && delayed_work_pending(&bond->arp_work))
+ cancel_delayed_work(&bond->arp_work);
+
+ if (bond->params.mode == BOND_MODE_ALB &&
+ delayed_work_pending(&bond->alb_work))
+ cancel_delayed_work(&bond->alb_work);
+
+ if (bond->params.mode == BOND_MODE_8023AD &&
+ delayed_work_pending(&bond->ad_work))
+ cancel_delayed_work(&bond->ad_work);
+}
+
static int __init bonding_init(void)
{
int i;
int res;
+ struct bonding *bond, *nxt;
printk(KERN_INFO "%s", version);
goto out;
err:
+ list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) {
+ bond_work_cancel_all(bond);
+ destroy_workqueue(bond->wq);
+ }
+
rtnl_lock();
bond_free_all();
bond_destroy_sysfs();
git.openpandora.org / pandora-kernel.git / blobdiff