static int max_bonds = BOND_DEFAULT_MAX_BONDS;
static int tx_queues = BOND_DEFAULT_TX_QUEUES;
-static int num_grat_arp = 1;
-static int num_unsol_na = 1;
+static int num_peer_notif = 1;
static int miimon = BOND_LINK_MON_INTERV;
static int updelay;
static int downdelay;
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(num_grat_arp, int, 0644);
-MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
-module_param(num_unsol_na, int, 0644);
-MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event");
+module_param_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);
/*-------------------------- Forward declarations ---------------------------*/
-static void bond_send_gratuitous_arp(struct bonding *bond);
static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);
return res;
}
-/**
- * bond_has_challenged_slaves
- * @bond: the bond we're working on
- *
- * Searches the slave list. Returns 1 if a vlan challenged slave
- * was found, 0 otherwise.
- *
- * Assumes bond->lock is held.
- */
-static int bond_has_challenged_slaves(struct bonding *bond)
-{
- struct slave *slave;
- int i;
-
- bond_for_each_slave(bond, slave, i) {
- if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) {
- pr_debug("found VLAN challenged slave - %s\n",
- slave->dev->name);
- return 1;
- }
- }
-
- pr_debug("no VLAN challenged slaves found\n");
- return 0;
-}
-
/**
* bond_next_vlan - safely skip to the next item in the vlans list.
* @bond: the bond we're working on
static int bond_update_speed_duplex(struct slave *slave)
{
struct net_device *slave_dev = slave->dev;
- struct ethtool_cmd etool;
+ struct ethtool_cmd etool = { .cmd = ETHTOOL_GSET };
+ u32 slave_speed;
int res;
/* Fake speed and duplex */
if (res < 0)
return -1;
- switch (etool.speed) {
+ slave_speed = ethtool_cmd_speed(&etool);
+ switch (slave_speed) {
case SPEED_10:
case SPEED_100:
case SPEED_1000:
return -1;
}
- slave->speed = etool.speed;
+ slave->speed = slave_speed;
slave->duplex = etool.duplex;
return 0;
static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
- mcast_work.work);
+ mcast_work.work);
bond_resend_igmp_join_requests(bond);
}
return bestslave;
}
+static bool bond_should_notify_peers(struct bonding *bond)
+{
+ struct slave *slave = bond->curr_active_slave;
+
+ pr_debug("bond_should_notify_peers: bond %s slave %s\n",
+ bond->dev->name, slave ? slave->dev->name : "NULL");
+
+ if (!slave || !bond->send_peer_notif ||
+ test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
+ return false;
+
+ bond->send_peer_notif--;
+ return true;
+}
+
/**
* change_active_interface - change the active slave into the specified one
* @bond: our bonding struct
bond_set_slave_inactive_flags(old_active);
if (new_active) {
+ bool should_notify_peers = false;
+
bond_set_slave_active_flags(new_active);
if (bond->params.fail_over_mac)
old_active);
if (netif_running(bond->dev)) {
- bond->send_grat_arp = bond->params.num_grat_arp;
- bond_send_gratuitous_arp(bond);
-
- bond->send_unsol_na = bond->params.num_unsol_na;
- bond_send_unsolicited_na(bond);
+ bond->send_peer_notif =
+ bond->params.num_peer_notif;
+ should_notify_peers =
+ bond_should_notify_peers(bond);
}
write_unlock_bh(&bond->curr_slave_lock);
read_unlock(&bond->lock);
netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER);
+ if (should_notify_peers)
+ netdev_bonding_change(bond->dev,
+ NETDEV_NOTIFY_PEERS);
read_lock(&bond->lock);
write_lock_bh(&bond->curr_slave_lock);
}
/* resend IGMP joins since active slave has changed or
- * all were sent on curr_active_slave */
- if (((USES_PRIMARY(bond->params.mode) && new_active) ||
- bond->params.mode == BOND_MODE_ROUNDROBIN) &&
- netif_running(bond->dev)) {
+ * all were sent on curr_active_slave.
+ * resend only if bond is brought up with the affected
+ * bonding modes and the retransmission is enabled */
+ if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) &&
+ ((USES_PRIMARY(bond->params.mode) && new_active) ||
+ bond->params.mode == BOND_MODE_ROUNDROBIN)) {
bond->igmp_retrans = bond->params.resend_igmp;
queue_delayed_work(bond->wq, &bond->mcast_work, 0);
}
read_lock(&bond->lock);
bond_for_each_slave(bond, slave, i) {
- if (!IS_UP(slave->dev))
- continue;
err = slave_enable_netpoll(slave);
if (err) {
__bond_netpoll_cleanup(bond);
return 0;
}
-#define BOND_VLAN_FEATURES \
- (NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX | \
- NETIF_F_HW_VLAN_FILTER)
-
-/*
- * Compute the common dev->feature set available to all slaves. Some
- * feature bits are managed elsewhere, so preserve those feature bits
- * on the master device.
- */
-static int bond_compute_features(struct bonding *bond)
+static u32 bond_fix_features(struct net_device *dev, u32 features)
{
struct slave *slave;
- struct net_device *bond_dev = bond->dev;
- u32 features = bond_dev->features;
- u32 vlan_features = 0;
- unsigned short max_hard_header_len = max((u16)ETH_HLEN,
- bond_dev->hard_header_len);
+ struct bonding *bond = netdev_priv(dev);
+ u32 mask;
int i;
- features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
- features |= NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;
+ read_lock(&bond->lock);
- if (!bond->first_slave)
- goto done;
+ if (!bond->first_slave) {
+ /* Disable adding VLANs to empty bond. But why? --mq */
+ features |= NETIF_F_VLAN_CHALLENGED;
+ goto out;
+ }
+ mask = features;
features &= ~NETIF_F_ONE_FOR_ALL;
+ features |= NETIF_F_ALL_FOR_ALL;
- vlan_features = bond->first_slave->dev->vlan_features;
bond_for_each_slave(bond, slave, i) {
features = netdev_increment_features(features,
slave->dev->features,
- NETIF_F_ONE_FOR_ALL);
+ mask);
+ }
+
+out:
+ read_unlock(&bond->lock);
+ return features;
+}
+
+#define BOND_VLAN_FEATURES (NETIF_F_ALL_TX_OFFLOADS | \
+ NETIF_F_SOFT_FEATURES | \
+ NETIF_F_LRO)
+
+static void bond_compute_features(struct bonding *bond)
+{
+ struct slave *slave;
+ struct net_device *bond_dev = bond->dev;
+ u32 vlan_features = BOND_VLAN_FEATURES;
+ unsigned short max_hard_header_len = ETH_HLEN;
+ int i;
+
+ read_lock(&bond->lock);
+
+ if (!bond->first_slave)
+ goto done;
+
+ bond_for_each_slave(bond, slave, i) {
vlan_features = netdev_increment_features(vlan_features,
- slave->dev->vlan_features,
- NETIF_F_ONE_FOR_ALL);
+ slave->dev->vlan_features, BOND_VLAN_FEATURES);
+
if (slave->dev->hard_header_len > max_hard_header_len)
max_hard_header_len = slave->dev->hard_header_len;
}
done:
- features |= (bond_dev->features & BOND_VLAN_FEATURES);
- bond_dev->features = netdev_fix_features(bond_dev, features);
- bond_dev->vlan_features = netdev_fix_features(bond_dev, vlan_features);
+ bond_dev->vlan_features = vlan_features;
bond_dev->hard_header_len = max_hard_header_len;
- return 0;
+ read_unlock(&bond->lock);
+
+ netdev_change_features(bond_dev);
}
static void bond_setup_by_slave(struct net_device *bond_dev,
}
/* On bonding slaves other than the currently active slave, suppress
- * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
- * ARP on active-backup slaves with arp_validate enabled.
+ * duplicates except for alb non-mcast/bcast.
*/
static bool bond_should_deliver_exact_match(struct sk_buff *skb,
- struct net_device *slave_dev,
- struct net_device *bond_dev)
+ struct slave *slave,
+ struct bonding *bond)
{
- if (slave_dev->priv_flags & IFF_SLAVE_INACTIVE) {
- if (slave_dev->priv_flags & IFF_SLAVE_NEEDARP &&
- skb->protocol == __cpu_to_be16(ETH_P_ARP))
- return false;
-
- if (bond_dev->priv_flags & IFF_MASTER_ALB &&
+ if (bond_is_slave_inactive(slave)) {
+ if (bond->params.mode == BOND_MODE_ALB &&
skb->pkt_type != PACKET_BROADCAST &&
skb->pkt_type != PACKET_MULTICAST)
- return false;
-
- if (bond_dev->priv_flags & IFF_MASTER_8023AD &&
- skb->protocol == __cpu_to_be16(ETH_P_SLOW))
return false;
-
return true;
}
return false;
}
-static struct sk_buff *bond_handle_frame(struct sk_buff *skb)
+static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
{
- struct net_device *slave_dev;
- struct net_device *bond_dev;
+ struct sk_buff *skb = *pskb;
+ struct slave *slave;
+ struct bonding *bond;
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
- return NULL;
- slave_dev = skb->dev;
- bond_dev = ACCESS_ONCE(slave_dev->master);
- if (unlikely(!bond_dev))
- return skb;
+ return RX_HANDLER_CONSUMED;
+
+ *pskb = skb;
- if (bond_dev->priv_flags & IFF_MASTER_ARPMON)
- slave_dev->last_rx = jiffies;
+ slave = bond_slave_get_rcu(skb->dev);
+ bond = slave->bond;
+
+ if (bond->params.arp_interval)
+ slave->dev->last_rx = jiffies;
- if (bond_should_deliver_exact_match(skb, slave_dev, bond_dev)) {
- skb->deliver_no_wcard = 1;
- return skb;
+ if (bond->recv_probe) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ bond->recv_probe(nskb, bond, slave);
+ dev_kfree_skb(nskb);
+ }
}
- skb->dev = bond_dev;
+ if (bond_should_deliver_exact_match(skb, slave, bond)) {
+ return RX_HANDLER_EXACT;
+ }
- if (bond_dev->priv_flags & IFF_MASTER_ALB &&
- bond_dev->priv_flags & IFF_BRIDGE_PORT &&
+ skb->dev = bond->dev;
+
+ if (bond->params.mode == 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 NULL;
+ return RX_HANDLER_CONSUMED;
}
- memcpy(eth_hdr(skb)->h_dest, bond_dev->dev_addr, ETH_ALEN);
+ memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN);
}
- return skb;
+ return RX_HANDLER_ANOTHER;
}
/* enslave device <slave> to bond device <master> */
struct netdev_hw_addr *ha;
struct sockaddr addr;
int link_reporting;
- int old_features = bond_dev->features;
int res = 0;
if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL &&
bond_dev->name, slave_dev->name);
}
- /* bond must be initialized by bond_open() before enslaving */
- if (!(bond_dev->flags & IFF_UP)) {
- pr_warning("%s: master_dev is not up in bond_enslave\n",
- bond_dev->name);
- }
-
/* already enslaved */
if (slave_dev->flags & IFF_SLAVE) {
pr_debug("Error, Device was already enslaved\n");
pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
bond_dev->name, slave_dev->name,
slave_dev->name, bond_dev->name);
- bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
}
} else {
pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
- if (bond->slave_cnt == 0) {
- /* First slave, and it is not VLAN challenged,
- * so remove the block of adding VLANs over the bond.
- */
- bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
- }
}
/*
}
}
+ 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 (is_zero_ether_addr(bond->dev->dev_addr))
pr_debug("Error %d calling netdev_set_bond_master\n", res);
goto err_restore_mac;
}
- res = netdev_rx_handler_register(slave_dev, bond_handle_frame, NULL);
- if (res) {
- pr_debug("Error %d calling netdev_rx_handler_register\n", res);
- goto err_unset_master;
- }
/* open the slave since the application closed it */
res = dev_open(slave_dev);
if (res) {
pr_debug("Opening slave %s failed\n", slave_dev->name);
- goto err_unreg_rxhandler;
+ goto err_unset_master;
}
+ new_slave->bond = bond;
new_slave->dev = slave_dev;
slave_dev->priv_flags |= IFF_BONDING;
new_slave->delay = 0;
new_slave->link_failure_count = 0;
- bond_compute_features(bond);
-
write_unlock_bh(&bond->lock);
+ bond_compute_features(bond);
+
read_lock(&bond->lock);
new_slave->last_arp_rx = jiffies;
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
- new_slave->state = BOND_STATE_ACTIVE;
+ bond_set_active_slave(new_slave);
bond_set_slave_inactive_flags(new_slave);
bond_select_active_slave(bond);
break;
pr_debug("This slave is always active in trunk mode\n");
/* always active in trunk mode */
- new_slave->state = BOND_STATE_ACTIVE;
+ 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),
if (res)
goto err_close;
+ res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
+ new_slave);
+ if (res) {
+ pr_debug("Error %d calling netdev_rx_handler_register\n", res);
+ goto err_dest_symlinks;
+ }
+
pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
bond_dev->name, slave_dev->name,
- new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup",
+ bond_is_active_slave(new_slave) ? "n active" : " backup",
new_slave->link != BOND_LINK_DOWN ? "n up" : " down");
/* enslave is successful */
return 0;
/* Undo stages on error */
+err_dest_symlinks:
+ bond_destroy_slave_symlinks(bond_dev, slave_dev);
+
err_close:
dev_close(slave_dev);
-err_unreg_rxhandler:
- netdev_rx_handler_unregister(slave_dev);
-
err_unset_master:
netdev_set_bond_master(slave_dev, NULL);
kfree(new_slave);
err_undo_flags:
- bond_dev->features = old_features;
+ bond_compute_features(bond);
return res;
}
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr addr;
+ u32 old_features = bond_dev->features;
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
}
block_netpoll_tx();
- netdev_bonding_change(bond_dev, NETDEV_BONDING_DESLAVE);
+ netdev_bonding_change(bond_dev, NETDEV_RELEASE);
write_lock_bh(&bond->lock);
slave = bond_get_slave_by_dev(bond, slave_dev);
return -EINVAL;
}
+ /* unregister rx_handler early so bond_handle_frame wouldn't be called
+ * for this slave anymore.
+ */
+ netdev_rx_handler_unregister(slave_dev);
+ write_unlock_bh(&bond->lock);
+ synchronize_net();
+ write_lock_bh(&bond->lock);
+
if (!bond->params.fail_over_mac) {
if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond->slave_cnt > 1)
pr_info("%s: releasing %s interface %s\n",
bond_dev->name,
- (slave->state == BOND_STATE_ACTIVE) ? "active" : "backup",
+ bond_is_active_slave(slave) ? "active" : "backup",
slave_dev->name);
oldcurrent = bond->curr_active_slave;
/* release the slave from its bond */
bond_detach_slave(bond, slave);
- bond_compute_features(bond);
-
if (bond->primary_slave == slave)
bond->primary_slave = NULL;
*/
memset(bond_dev->dev_addr, 0, bond_dev->addr_len);
- if (!bond->vlgrp) {
- bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
- } else {
+ if (bond->vlgrp) {
pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
bond_dev->name, bond_dev->name);
pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
bond_dev->name);
}
- } else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
- !bond_has_challenged_slaves(bond)) {
- pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
- bond_dev->name, slave_dev->name, bond_dev->name);
- bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
}
write_unlock_bh(&bond->lock);
unblock_netpoll_tx();
+ bond_compute_features(bond);
+ if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
+ (old_features & NETIF_F_VLAN_CHALLENGED))
+ pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
+ bond_dev->name, slave_dev->name, bond_dev->name);
+
/* must do this from outside any spinlocks */
bond_destroy_slave_symlinks(bond_dev, slave_dev);
netif_addr_unlock_bh(bond_dev);
}
- netdev_rx_handler_unregister(slave_dev);
netdev_set_bond_master(slave_dev, NULL);
slave_disable_netpoll(slave);
dev_set_mtu(slave_dev, slave->original_mtu);
- slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
- IFF_SLAVE_INACTIVE | IFF_BONDING |
- IFF_SLAVE_NEEDARP);
+ slave_dev->priv_flags &= ~IFF_BONDING;
kfree(slave);
}
/*
-* First release a slave and than destroy the bond if no more slaves are left.
+* 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,
*/
write_unlock_bh(&bond->lock);
+ /* unregister rx_handler early so bond_handle_frame wouldn't
+ * be called for this slave anymore.
+ */
+ netdev_rx_handler_unregister(slave_dev);
+ synchronize_net();
+
if (bond_is_lb(bond)) {
/* must be called only after the slave
* has been detached from the list
bond_alb_deinit_slave(bond, slave);
}
- bond_compute_features(bond);
-
bond_destroy_slave_symlinks(bond_dev, slave_dev);
bond_del_vlans_from_slave(bond, slave_dev);
netif_addr_unlock_bh(bond_dev);
}
- netdev_rx_handler_unregister(slave_dev);
netdev_set_bond_master(slave_dev, NULL);
slave_disable_netpoll(slave);
dev_set_mac_address(slave_dev, &addr);
}
- slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
- IFF_SLAVE_INACTIVE);
-
kfree(slave);
/* re-acquire the lock before getting the next slave */
*/
memset(bond_dev->dev_addr, 0, bond_dev->addr_len);
- if (!bond->vlgrp) {
- bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
- } else {
+ if (bond->vlgrp) {
pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
bond_dev->name, bond_dev->name);
pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
out:
write_unlock_bh(&bond->lock);
+
+ bond_compute_features(bond);
+
return 0;
}
res = 0;
strcpy(info->slave_name, slave->dev->name);
info->link = slave->link;
- info->state = slave->state;
+ info->state = bond_slave_state(slave);
info->link_failure_count = slave->link_failure_count;
break;
}
bond->dev->name,
(bond->params.mode ==
BOND_MODE_ACTIVEBACKUP) ?
- ((slave->state == BOND_STATE_ACTIVE) ?
+ (bond_is_active_slave(slave) ?
"active " : "backup ") : "",
slave->dev->name,
bond->params.downdelay * bond->params.miimon);
if (bond->params.mode == BOND_MODE_8023AD) {
/* prevent it from being the active one */
- slave->state = BOND_STATE_BACKUP;
+ bond_set_backup_slave(slave);
} else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
/* make it immediately active */
- slave->state = BOND_STATE_ACTIVE;
+ bond_set_active_slave(slave);
} else if (slave != bond->primary_slave) {
/* prevent it from being the active one */
- slave->state = BOND_STATE_BACKUP;
+ bond_set_backup_slave(slave);
}
bond_update_speed_duplex(slave);
- pr_info("%s: link status definitely up for interface %s, %d Mbps %s duplex.\n",
+ pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n",
bond->dev->name, slave->dev->name,
slave->speed, slave->duplex ? "full" : "half");
{
struct bonding *bond = container_of(work, struct bonding,
mii_work.work);
+ bool should_notify_peers = false;
read_lock(&bond->lock);
if (bond->kill_timers)
if (bond->slave_cnt == 0)
goto re_arm;
- if (bond->send_grat_arp) {
- read_lock(&bond->curr_slave_lock);
- bond_send_gratuitous_arp(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
- if (bond->send_unsol_na) {
- read_lock(&bond->curr_slave_lock);
- bond_send_unsolicited_na(bond);
- read_unlock(&bond->curr_slave_lock);
- }
+ should_notify_peers = bond_should_notify_peers(bond);
if (bond_miimon_inspect(bond)) {
read_unlock(&bond->lock);
msecs_to_jiffies(bond->params.miimon));
out:
read_unlock(&bond->lock);
+
+ if (should_notify_peers) {
+ rtnl_lock();
+ netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS);
+ rtnl_unlock();
+ }
}
static __be32 bond_glean_dev_ip(struct net_device *dev)
}
}
-/*
- * Kick out a gratuitous ARP for an IP on the bonding master plus one
- * for each VLAN above us.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-static void bond_send_gratuitous_arp(struct bonding *bond)
-{
- struct slave *slave = bond->curr_active_slave;
- struct vlan_entry *vlan;
- struct net_device *vlan_dev;
-
- pr_debug("bond_send_grat_arp: bond %s slave %s\n",
- bond->dev->name, slave ? slave->dev->name : "NULL");
-
- if (!slave || !bond->send_grat_arp ||
- test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
- return;
-
- bond->send_grat_arp--;
-
- if (bond->master_ip) {
- bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
- bond->master_ip, 0);
- }
-
- if (!bond->vlgrp)
- return;
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id);
- if (vlan->vlan_ip) {
- bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
- vlan->vlan_ip, vlan->vlan_id);
- }
- }
-}
-
static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
int i;
}
}
-static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
struct arphdr *arp;
- struct slave *slave;
- struct bonding *bond;
unsigned char *arp_ptr;
__be32 sip, tip;
- if (dev->priv_flags & IFF_802_1Q_VLAN) {
- /*
- * When using VLANS and bonding, dev and oriv_dev may be
- * incorrect if the physical interface supports VLAN
- * acceleration. With this change ARP validation now
- * works for hosts only reachable on the VLAN interface.
- */
- dev = vlan_dev_real_dev(dev);
- orig_dev = dev_get_by_index_rcu(dev_net(skb->dev),skb->skb_iif);
- }
-
- if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
- goto out;
+ if (skb->protocol != __cpu_to_be16(ETH_P_ARP))
+ return;
- bond = netdev_priv(dev);
read_lock(&bond->lock);
- pr_debug("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n",
- bond->dev->name, skb->dev ? skb->dev->name : "NULL",
- orig_dev ? orig_dev->name : "NULL");
+ pr_debug("bond_arp_rcv: bond %s skb->dev %s\n",
+ bond->dev->name, skb->dev->name);
- slave = bond_get_slave_by_dev(bond, orig_dev);
- if (!slave || !slave_do_arp_validate(bond, slave))
- goto out_unlock;
-
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (!skb)
- goto out_unlock;
-
- if (!pskb_may_pull(skb, arp_hdr_len(dev)))
+ if (!pskb_may_pull(skb, arp_hdr_len(bond->dev)))
goto out_unlock;
arp = arp_hdr(skb);
- if (arp->ar_hln != dev->addr_len ||
+ if (arp->ar_hln != bond->dev->addr_len ||
skb->pkt_type == PACKET_OTHERHOST ||
skb->pkt_type == PACKET_LOOPBACK ||
arp->ar_hrd != htons(ARPHRD_ETHER) ||
goto out_unlock;
arp_ptr = (unsigned char *)(arp + 1);
- arp_ptr += dev->addr_len;
+ arp_ptr += bond->dev->addr_len;
memcpy(&sip, arp_ptr, 4);
- arp_ptr += 4 + dev->addr_len;
+ arp_ptr += 4 + bond->dev->addr_len;
memcpy(&tip, arp_ptr, 4);
pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n",
- bond->dev->name, slave->dev->name, slave->state,
+ bond->dev->name, slave->dev->name, bond_slave_state(slave),
bond->params.arp_validate, slave_do_arp_validate(bond, slave),
&sip, &tip);
* the active, through one switch, the router, then the other
* switch before reaching the backup.
*/
- if (slave->state == BOND_STATE_ACTIVE)
+ if (bond_is_active_slave(slave))
bond_validate_arp(bond, slave, sip, tip);
else
bond_validate_arp(bond, slave, tip, sip);
out_unlock:
read_unlock(&bond->lock);
-out:
- dev_kfree_skb(skb);
- return NET_RX_SUCCESS;
}
/*
slave->dev->last_rx + delta_in_ticks)) {
slave->link = BOND_LINK_UP;
- slave->state = BOND_STATE_ACTIVE;
+ bond_set_active_slave(slave);
/* primary_slave has no meaning in round-robin
* mode. the window of a slave being up and
slave->dev->last_rx + 2 * delta_in_ticks)) {
slave->link = BOND_LINK_DOWN;
- slave->state = BOND_STATE_BACKUP;
+ bond_set_backup_slave(slave);
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
* gives each slave a chance to tx/rx traffic
* before being taken out
*/
- if (slave->state == BOND_STATE_BACKUP &&
+ if (!bond_is_active_slave(slave) &&
!bond->current_arp_slave &&
!time_in_range(jiffies,
slave_last_rx(bond, slave) - delta_in_ticks,
* the bond has an IP address)
*/
trans_start = dev_trans_start(slave->dev);
- if ((slave->state == BOND_STATE_ACTIVE) &&
+ if (bond_is_active_slave(slave) &&
(!time_in_range(jiffies,
trans_start - delta_in_ticks,
trans_start + 2 * delta_in_ticks) ||
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
+ bool should_notify_peers = false;
int delta_in_ticks;
read_lock(&bond->lock);
if (bond->slave_cnt == 0)
goto re_arm;
- if (bond->send_grat_arp) {
- read_lock(&bond->curr_slave_lock);
- bond_send_gratuitous_arp(bond);
- read_unlock(&bond->curr_slave_lock);
- }
-
- if (bond->send_unsol_na) {
- read_lock(&bond->curr_slave_lock);
- bond_send_unsolicited_na(bond);
- read_unlock(&bond->curr_slave_lock);
- }
+ should_notify_peers = bond_should_notify_peers(bond);
if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
read_unlock(&bond->lock);
queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
out:
read_unlock(&bond->lock);
+
+ if (should_notify_peers) {
+ rtnl_lock();
+ netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS);
+ rtnl_unlock();
+ }
}
/*-------------------------- netdev event handling --------------------------*/
slave = bond_get_slave_by_dev(bond, slave_dev);
if (slave) {
- u16 old_speed = slave->speed;
- u16 old_duplex = slave->duplex;
+ u32 old_speed = slave->speed;
+ u8 old_duplex = slave->duplex;
bond_update_speed_duplex(slave);
.notifier_call = bond_inetaddr_event,
};
-/*-------------------------- Packet type handling ---------------------------*/
-
-/* register to receive lacpdus on a bond */
-static void bond_register_lacpdu(struct bonding *bond)
-{
- struct packet_type *pk_type = &(BOND_AD_INFO(bond).ad_pkt_type);
-
- /* initialize packet type */
- pk_type->type = PKT_TYPE_LACPDU;
- pk_type->dev = bond->dev;
- pk_type->func = bond_3ad_lacpdu_recv;
-
- dev_add_pack(pk_type);
-}
-
-/* unregister to receive lacpdus on a bond */
-static void bond_unregister_lacpdu(struct bonding *bond)
-{
- dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type));
-}
-
-void bond_register_arp(struct bonding *bond)
-{
- struct packet_type *pt = &bond->arp_mon_pt;
-
- if (pt->type)
- return;
-
- pt->type = htons(ETH_P_ARP);
- pt->dev = bond->dev;
- pt->func = bond_arp_rcv;
- dev_add_pack(pt);
-}
-
-void bond_unregister_arp(struct bonding *bond)
-{
- struct packet_type *pt = &bond->arp_mon_pt;
-
- dev_remove_pack(pt);
- pt->type = 0;
-}
-
/*---------------------------- Hashing Policies -----------------------------*/
/*
queue_delayed_work(bond->wq, &bond->arp_work, 0);
if (bond->params.arp_validate)
- bond_register_arp(bond);
+ bond->recv_probe = bond_arp_rcv;
}
if (bond->params.mode == BOND_MODE_8023AD) {
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);
+ bond->recv_probe = bond_3ad_lacpdu_recv;
bond_3ad_initiate_agg_selection(bond, 1);
}
{
struct bonding *bond = netdev_priv(bond_dev);
- if (bond->params.mode == BOND_MODE_8023AD) {
- /* Unregister the receive of LACPDUs */
- bond_unregister_lacpdu(bond);
- }
-
- if (bond->params.arp_validate)
- bond_unregister_arp(bond);
-
write_lock_bh(&bond->lock);
- bond->send_grat_arp = 0;
- bond->send_unsol_na = 0;
+ bond->send_peer_notif = 0;
/* signal timers not to re-arm */
bond->kill_timers = 1;
*/
bond_alb_deinitialize(bond);
}
+ bond->recv_probe = NULL;
return 0;
}
int i, slave_no, res = 1;
struct iphdr *iph = ip_hdr(skb);
- read_lock(&bond->lock);
-
- if (!BOND_IS_OK(bond))
- goto out;
/*
* Start with the curr_active_slave that joined the bond as the
* default for sending IGMP traffic. For failover purposes one
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)) {
+ bond_is_active_slave(slave)) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
break;
}
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
}
- read_unlock(&bond->lock);
+
return NETDEV_TX_OK;
}
struct bonding *bond = netdev_priv(bond_dev);
int res = 1;
- read_lock(&bond->lock);
read_lock(&bond->curr_slave_lock);
- if (!BOND_IS_OK(bond))
- goto out;
-
- if (!bond->curr_active_slave)
- goto out;
+ if (bond->curr_active_slave)
+ res = bond_dev_queue_xmit(bond, skb,
+ bond->curr_active_slave->dev);
- res = bond_dev_queue_xmit(bond, skb, bond->curr_active_slave->dev);
-
-out:
if (res)
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
read_unlock(&bond->curr_slave_lock);
- read_unlock(&bond->lock);
+
return NETDEV_TX_OK;
}
int i;
int res = 1;
- read_lock(&bond->lock);
-
- if (!BOND_IS_OK(bond))
- goto out;
-
slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt);
bond_for_each_slave(bond, slave, i) {
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)) {
+ bond_is_active_slave(slave)) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
break;
}
}
-out:
if (res) {
/* no suitable interface, frame not sent */
dev_kfree_skb(skb);
}
- read_unlock(&bond->lock);
+
return NETDEV_TX_OK;
}
int i;
int res = 1;
- read_lock(&bond->lock);
-
- if (!BOND_IS_OK(bond))
- goto out;
-
read_lock(&bond->curr_slave_lock);
start_at = bond->curr_active_slave;
read_unlock(&bond->curr_slave_lock);
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)) {
+ bond_is_active_slave(slave)) {
if (tx_dev) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2) {
dev_kfree_skb(skb);
/* frame sent to all suitable interfaces */
- read_unlock(&bond->lock);
return NETDEV_TX_OK;
}
struct slave *slave = NULL;
struct slave *check_slave;
- read_lock(&bond->lock);
-
- if (!BOND_IS_OK(bond) || !skb->queue_mapping)
- goto out;
+ if (!skb->queue_mapping)
+ return 1;
/* Find out if any slaves have the same mapping as this skb. */
bond_for_each_slave(bond, check_slave, i) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
}
-out:
- read_unlock(&bond->lock);
return res;
}
u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
if (unlikely(txq >= dev->real_num_tx_queues)) {
- do
+ do {
txq -= dev->real_num_tx_queues;
- while (txq >= dev->real_num_tx_queues);
+ } while (txq >= dev->real_num_tx_queues);
}
return txq;
}
-static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
- /*
- * If we risk deadlock from transmitting this in the
- * netpoll path, tell netpoll to queue the frame for later tx
- */
- if (is_netpoll_tx_blocked(dev))
- return NETDEV_TX_BUSY;
-
if (TX_QUEUE_OVERRIDE(bond->params.mode)) {
if (!bond_slave_override(bond, skb))
return NETDEV_TX_OK;
}
}
+static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct bonding *bond = netdev_priv(dev);
+ netdev_tx_t ret = NETDEV_TX_OK;
+
+ /*
+ * If we risk deadlock from transmitting this in the
+ * netpoll path, tell netpoll to queue the frame for later tx
+ */
+ if (is_netpoll_tx_blocked(dev))
+ return NETDEV_TX_BUSY;
+
+ read_lock(&bond->lock);
+
+ if (bond->slave_cnt)
+ ret = __bond_start_xmit(skb, dev);
+ else
+ dev_kfree_skb(skb);
+
+ read_unlock(&bond->lock);
+
+ return ret;
+}
/*
* set bond mode specific net device operations
case BOND_MODE_BROADCAST:
break;
case BOND_MODE_8023AD:
- bond_set_master_3ad_flags(bond);
bond_set_xmit_hash_policy(bond);
break;
case BOND_MODE_ALB:
- bond_set_master_alb_flags(bond);
/* FALLTHRU */
case BOND_MODE_TLB:
break;
static const struct ethtool_ops bond_ethtool_ops = {
.get_drvinfo = bond_ethtool_get_drvinfo,
.get_link = ethtool_op_get_link,
- .get_tx_csum = ethtool_op_get_tx_csum,
- .get_sg = ethtool_op_get_sg,
- .get_tso = ethtool_op_get_tso,
- .get_ufo = ethtool_op_get_ufo,
- .get_flags = ethtool_op_get_flags,
};
static const struct net_device_ops bond_netdev_ops = {
#endif
.ndo_add_slave = bond_enslave,
.ndo_del_slave = bond_release,
+ .ndo_fix_features = bond_fix_features,
};
static void bond_destructor(struct net_device *bond_dev)
bond_dev->priv_flags |= IFF_BONDING;
bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
- if (bond->params.arp_interval)
- bond_dev->priv_flags |= IFF_MASTER_ARPMON;
-
/* At first, we block adding VLANs. That's the only way to
* prevent problems that occur when adding VLANs over an
* empty bond. The block will be removed once non-challenged
* when there are slaves that are not hw accel
* capable
*/
- bond_dev->features |= (NETIF_F_HW_VLAN_TX |
- NETIF_F_HW_VLAN_RX |
- NETIF_F_HW_VLAN_FILTER);
- /* By default, we enable GRO on bonding devices.
- * Actual support requires lowlevel drivers are GRO ready.
- */
- bond_dev->features |= NETIF_F_GRO;
+ bond_dev->hw_features = BOND_VLAN_FEATURES |
+ NETIF_F_HW_VLAN_TX |
+ NETIF_F_HW_VLAN_RX |
+ NETIF_F_HW_VLAN_FILTER;
+
+ bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM);
+ bond_dev->features |= bond_dev->hw_features;
}
static void bond_work_cancel_all(struct bonding *bond)
use_carrier = 1;
}
- if (num_grat_arp < 0 || num_grat_arp > 255) {
- pr_warning("Warning: num_grat_arp (%d) not in range 0-255 so it was reset to 1\n",
- num_grat_arp);
- num_grat_arp = 1;
- }
-
- if (num_unsol_na < 0 || num_unsol_na > 255) {
- pr_warning("Warning: num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
- num_unsol_na);
- num_unsol_na = 1;
+ if (num_peer_notif < 0 || num_peer_notif > 255) {
+ pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
+ num_peer_notif);
+ num_peer_notif = 1;
}
/* reset values for 802.3ad */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->miimon = miimon;
- params->num_grat_arp = num_grat_arp;
- params->num_unsol_na = num_unsol_na;
+ params->num_peer_notif = num_peer_notif;
params->arp_interval = arp_interval;
params->arp_validate = arp_validate_value;
params->updelay = updelay;
{
struct bonding *bond = netdev_priv(bond_dev);
struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
+ struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
pr_debug("Begin bond_init for %s\n", bond_dev->name);
+ /*
+ * Initialize locks that may be required during
+ * en/deslave operations. All of the bond_open work
+ * (of which this is part) should really be moved to
+ * a phase prior to dev_open
+ */
+ spin_lock_init(&(bond_info->tx_hashtbl_lock));
+ spin_lock_init(&(bond_info->rx_hashtbl_lock));
+
bond->wq = create_singlethread_workqueue(bond_dev->name);
if (!bond->wq)
return -ENOMEM;
bond_set_lockdep_class(bond_dev);
- netif_carrier_off(bond_dev);
-
bond_create_proc_entry(bond);
list_add_tail(&bond->bond_list, &bn->dev_list);
rtnl_lock();
- bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "",
- bond_setup, tx_queues);
+ bond_dev = alloc_netdev_mq(sizeof(struct bonding),
+ name ? name : "bond%d",
+ bond_setup, tx_queues);
if (!bond_dev) {
pr_err("%s: eek! can't alloc netdev!\n", name);
rtnl_unlock();
dev_net_set(bond_dev, net);
bond_dev->rtnl_link_ops = &bond_link_ops;
- if (!name) {
- res = dev_alloc_name(bond_dev, "bond%d");
- if (res < 0)
- goto out;
- } else {
- /*
- * If we're given a name to register
- * we need to ensure that its not already
- * registered
- */
- res = -EEXIST;
- if (__dev_get_by_name(net, name) != NULL)
- goto out;
- }
-
res = register_netdevice(bond_dev);
-out:
+ netif_carrier_off(bond_dev);
+
rtnl_unlock();
if (res < 0)
bond_destructor(bond_dev);
register_netdevice_notifier(&bond_netdev_notifier);
register_inetaddr_notifier(&bond_inetaddr_notifier);
- bond_register_ipv6_notifier();
out:
return res;
err:
{
unregister_netdevice_notifier(&bond_netdev_notifier);
unregister_inetaddr_notifier(&bond_inetaddr_notifier);
- bond_unregister_ipv6_notifier();
bond_destroy_sysfs();
bond_destroy_debugfs();