diff options
Diffstat (limited to 'drivers/net/bonding')
| -rw-r--r-- | drivers/net/bonding/bond_3ad.c | 71 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_3ad.h | 9 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.c | 17 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_debugfs.c | 2 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_ipv6.c | 8 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 485 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_procfs.c | 14 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 219 | ||||
| -rw-r--r-- | drivers/net/bonding/bonding.h | 17 |
9 files changed, 424 insertions, 418 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index c7537abc..aaa7999 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -262,7 +262,7 @@ static inline u32 __get_agg_selection_mode(struct port *port) if (bond == NULL) return BOND_AD_STABLE; - return BOND_AD_INFO(bond).agg_select_mode; + return bond->params.ad_select; } /** @@ -1135,13 +1135,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) __record_pdu(lacpdu, port); port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(port->actor_oper_port_state & AD_STATE_LACP_TIMEOUT)); port->actor_oper_port_state &= ~AD_STATE_EXPIRED; - // verify that if the aggregator is enabled, the port is enabled too. - //(because if the link goes down for a short time, the 802.3ad will not - // catch it, and the port will continue to be disabled) - if (port->aggregator - && port->aggregator->is_active - && !__port_is_enabled(port)) - __enable_port(port); break; default: //to silence the compiler break; @@ -1859,28 +1852,23 @@ static void ad_marker_response_received(struct bond_marker *marker, void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) { BOND_AD_INFO(bond).agg_select_timer = timeout; - BOND_AD_INFO(bond).agg_select_mode = bond->params.ad_select; } -static u16 aggregator_identifier; - /** * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures * @bond: bonding struct to work on * @tick_resolution: tick duration (millisecond resolution) - * @lacp_fast: boolean. whether fast periodic should be used * * Can be called only after the mac address of the bond is set. */ -void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fast) +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) { // check that the bond is not initialized yet if (MAC_ADDRESS_COMPARE(&(BOND_AD_INFO(bond).system.sys_mac_addr), bond->dev->dev_addr)) { - aggregator_identifier = 0; + BOND_AD_INFO(bond).aggregator_identifier = 0; - BOND_AD_INFO(bond).lacp_fast = lacp_fast; BOND_AD_INFO(bond).system.sys_priority = 0xFFFF; BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); @@ -1918,7 +1906,7 @@ int bond_3ad_bind_slave(struct slave *slave) // port initialization port = &(SLAVE_AD_INFO(slave).port); - ad_initialize_port(port, BOND_AD_INFO(bond).lacp_fast); + ad_initialize_port(port, bond->params.lacp_fast); port->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave).id; @@ -1951,7 +1939,7 @@ int bond_3ad_bind_slave(struct slave *slave) ad_initialize_agg(aggregator); aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr); - aggregator->aggregator_identifier = (++aggregator_identifier); + aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier; aggregator->slave = slave; aggregator->is_active = 0; aggregator->num_of_ports = 0; @@ -2120,9 +2108,6 @@ void bond_3ad_state_machine_handler(struct work_struct *work) read_lock(&bond->lock); - if (bond->kill_timers) - goto out; - //check if there are any slaves if (bond->slave_cnt == 0) goto re_arm; @@ -2172,7 +2157,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) re_arm: queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); -out: + read_unlock(&bond->lock); } @@ -2345,8 +2330,17 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) */ int bond_3ad_set_carrier(struct bonding *bond) { - if (__get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator))) { - if (!netif_carrier_ok(bond->dev)) { + struct aggregator *active; + + active = __get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator)); + if (active) { + /* are enough slaves available to consider link up? */ + if (active->num_of_ports < bond->params.min_links) { + if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + return 1; + } + } else if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); return 1; } @@ -2473,3 +2467,34 @@ void bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond, bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len); read_unlock(&bond->lock); } + +/* + * When modify lacp_rate parameter via sysfs, + * update actor_oper_port_state of each port. + * + * Hold slave->state_machine_lock, + * so we can modify port->actor_oper_port_state, + * no matter bond is up or down. + */ +void bond_3ad_update_lacp_rate(struct bonding *bond) +{ + int i; + struct slave *slave; + struct port *port = NULL; + int lacp_fast; + + read_lock(&bond->lock); + lacp_fast = bond->params.lacp_fast; + + bond_for_each_slave(bond, slave, i) { + port = &(SLAVE_AD_INFO(slave).port); + __get_state_machine_lock(port); + if (lacp_fast) + port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; + else + port->actor_oper_port_state &= ~AD_STATE_LACP_TIMEOUT; + __release_state_machine_lock(port); + } + + read_unlock(&bond->lock); +} diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 0ee3f16..20d9c78 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -253,11 +253,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes - u32 agg_select_mode; // Mode of selection of active aggregator(bandwidth/count) - int lacp_fast; /* whether fast periodic tx should be - * requested - */ - struct timer_list ad_timer; + u16 aggregator_identifier; }; struct ad_slave_info { @@ -269,7 +265,7 @@ struct ad_slave_info { }; // ================= AD Exported functions to the main bonding code ================== -void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fast); +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); int bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); @@ -282,5 +278,6 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev); void bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_rate(struct bonding *bond); #endif //__BOND_3AD_H__ diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 5e725e0..30431d8 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -635,7 +635,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon client_info->ntt = 0; } - if (bond->vlgrp) { + if (bond_vlan_used(bond)) { if (!vlan_get_tag(skb, &client_info->vlan_id)) client_info->tag = 1; } @@ -847,7 +847,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]) skb->priority = TC_PRIO_CONTROL; skb->dev = slave->dev; - if (bond->vlgrp) { + if (bond_vlan_used(bond)) { struct vlan_entry *vlan; vlan = bond_next_vlan(bond, @@ -1337,10 +1337,6 @@ void bond_alb_monitor(struct work_struct *work) read_lock(&bond->lock); - if (bond->kill_timers) { - goto out; - } - if (bond->slave_cnt == 0) { bond_info->tx_rebalance_counter = 0; bond_info->lp_counter = 0; @@ -1395,10 +1391,13 @@ void bond_alb_monitor(struct work_struct *work) /* * dev_set_promiscuity requires rtnl and - * nothing else. + * nothing else. Avoid race with bond_close. */ read_unlock(&bond->lock); - rtnl_lock(); + if (!rtnl_trylock()) { + read_lock(&bond->lock); + goto re_arm; + } bond_info->rlb_promisc_timeout_counter = 0; @@ -1435,7 +1434,7 @@ void bond_alb_monitor(struct work_struct *work) re_arm: queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks); -out: + read_unlock(&bond->lock); } diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 3680aa2..2cf084e 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -6,7 +6,7 @@ #include "bonding.h" #include "bond_alb.h" -#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS) #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c index 84fbd4e..027a0ee 100644 --- a/drivers/net/bonding/bond_ipv6.c +++ b/drivers/net/bonding/bond_ipv6.c @@ -183,10 +183,10 @@ static int bond_inet6addr_event(struct notifier_block *this, } list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (!bond->vlgrp) - continue; - vlan_dev = vlan_group_get_device(bond->vlgrp, - vlan->vlan_id); + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond->dev, + vlan->vlan_id); + rcu_read_unlock(); if (vlan_dev == event_dev) { switch (event) { case NETDEV_UP: diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f1b566f..9145834c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -99,6 +99,7 @@ static char *mode; static char *primary; static char *primary_reselect; static char *lacp_rate; +static int min_links; static char *ad_select; static char *xmit_hash_policy; static int arp_interval = BOND_LINK_ARP_INTERV; @@ -151,6 +152,9 @@ module_param(ad_select, charp, 0); MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); +module_param(min_links, int, 0); +MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier"); + module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " @@ -330,16 +334,6 @@ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) kfree(vlan); - if (list_empty(&bond->vlan_list) && - (bond->slave_cnt == 0)) { - /* Last VLAN removed and no slaves, so - * restore block on adding VLANs. This will - * be removed once new slaves that are not - * VLAN challenged will be added. - */ - bond->dev->features |= NETIF_F_VLAN_CHALLENGED; - } - res = 0; goto out; } @@ -400,7 +394,6 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; - skb->priority = 1; BUILD_BUG_ON(sizeof(skb->queue_mapping) != sizeof(qdisc_skb_cb(skb)->bond_queue_mapping)); @@ -415,9 +408,8 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, } /* - * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid - * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a - * lock because: + * 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 @@ -433,33 +425,6 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, */ /** - * bond_vlan_rx_register - Propagates registration to slaves - * @bond_dev: bonding net device that got called - * @grp: vlan group being registered - */ -static void bond_vlan_rx_register(struct net_device *bond_dev, - struct vlan_group *grp) -{ - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave; - int i; - - write_lock_bh(&bond->lock); - bond->vlgrp = grp; - write_unlock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - struct net_device *slave_dev = slave->dev; - const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_ops->ndo_vlan_rx_register) { - slave_ops->ndo_vlan_rx_register(slave_dev, grp); - } - } -} - -/** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called * @vid: vlan id being added @@ -496,7 +461,6 @@ static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - struct net_device *vlan_dev; int i, res; bond_for_each_slave(bond, slave, i) { @@ -505,12 +469,7 @@ static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && slave_ops->ndo_vlan_rx_kill_vid) { - /* Save and then restore vlan_dev in the grp array, - * since the slave's driver might clear it. - */ - vlan_dev = vlan_group_get_device(bond->vlgrp, vid); slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid); - vlan_group_set_device(bond->vlgrp, vid, vlan_dev); } } @@ -526,13 +485,6 @@ static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *sla struct vlan_entry *vlan; const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - if (!bond->vlgrp) - return; - - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_ops->ndo_vlan_rx_register) - slave_ops->ndo_vlan_rx_register(slave_dev, bond->vlgrp); - if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_ops->ndo_vlan_rx_add_vid)) return; @@ -546,30 +498,16 @@ static void bond_del_vlans_from_slave(struct bonding *bond, { const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct vlan_entry *vlan; - struct net_device *vlan_dev; - - if (!bond->vlgrp) - return; if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_ops->ndo_vlan_rx_kill_vid)) - goto unreg; + return; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { if (!vlan->vlan_id) continue; - /* Save and then restore vlan_dev in the grp array, - * since the slave's driver might clear it. - */ - vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id); - vlan_group_set_device(bond->vlgrp, vlan->vlan_id, vlan_dev); } - -unreg: - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_ops->ndo_vlan_rx_register) - slave_ops->ndo_vlan_rx_register(slave_dev, NULL); } /*------------------------------- Link status -------------------------------*/ @@ -613,39 +551,28 @@ down: /* * 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, fake speed and duplex to 100/Full + * values are invalid, set speed and duplex to -1, * and return error. */ static int bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; - struct ethtool_cmd etool = { .cmd = ETHTOOL_GSET }; + struct ethtool_cmd ecmd; u32 slave_speed; int res; - /* Fake speed and duplex */ - slave->speed = SPEED_100; - slave->duplex = DUPLEX_FULL; - - if (!slave_dev->ethtool_ops || !slave_dev->ethtool_ops->get_settings) - return -1; + slave->speed = SPEED_UNKNOWN; + slave->duplex = DUPLEX_UNKNOWN; - res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool); + res = __ethtool_get_settings(slave_dev, &ecmd); if (res < 0) return -1; - slave_speed = ethtool_cmd_speed(&etool); - switch (slave_speed) { - case SPEED_10: - case SPEED_100: - case SPEED_1000: - case SPEED_10000: - break; - default: + slave_speed = ethtool_cmd_speed(&ecmd); + if (slave_speed == 0 || slave_speed == ((__u32) -1)) return -1; - } - switch (etool.duplex) { + switch (ecmd.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; @@ -654,7 +581,7 @@ static int bond_update_speed_duplex(struct slave *slave) } slave->speed = slave_speed; - slave->duplex = etool.duplex; + slave->duplex = ecmd.duplex; return 0; } @@ -850,13 +777,13 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) __bond_resend_igmp_join_requests(bond->dev); /* rejoin all groups on vlan devices */ - if (bond->vlgrp) { - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = vlan_group_get_device(bond->vlgrp, - vlan->vlan_id); - if (vlan_dev) - __bond_resend_igmp_join_requests(vlan_dev); - } + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond->dev, + vlan->vlan_id); + rcu_read_unlock(); + if (vlan_dev) + __bond_resend_igmp_join_requests(vlan_dev); } if (--bond->igmp_retrans > 0) @@ -934,6 +861,23 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, } } +static struct slave *bond_get_old_active(struct bonding *bond, + struct slave *new_active) +{ + struct slave *slave; + int i; + + bond_for_each_slave(bond, slave, i) { + if (slave == new_active) + continue; + + if (!compare_ether_addr(bond->dev->dev_addr, slave->dev->dev_addr)) + return slave; + } + + return NULL; +} + /* * bond_do_fail_over_mac * @@ -971,6 +915,9 @@ static void bond_do_fail_over_mac(struct bonding *bond, write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); + if (!old_active) + old_active = bond_get_old_active(bond, new_active); + if (old_active) { memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN); memcpy(saddr.sa_data, old_active->dev->dev_addr, @@ -1581,7 +1528,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); - if (bond->vlgrp) { + if (bond_vlan_used(bond)) { pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n", bond_dev->name, slave_dev->name, bond_dev->name); return -EPERM; @@ -1788,6 +1735,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_compute_features(bond); + bond_update_speed_duplex(new_slave); + read_lock(&bond->lock); new_slave->last_arp_rx = jiffies; @@ -1831,17 +1780,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) new_slave->link = BOND_LINK_DOWN; } - if (bond_update_speed_duplex(new_slave) && - (new_slave->link != BOND_LINK_DOWN)) { - pr_warning("%s: Warning: failed to get speed and duplex from %s, assumed to be 100Mb/sec and Full.\n", - bond_dev->name, new_slave->dev->name); - - if (bond->params.mode == BOND_MODE_8023AD) { - pr_warning("%s: Warning: Operation of 802.3ad mode requires ETHTOOL support in base driver for proper aggregator selection.\n", - bond_dev->name); - } - } - if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { @@ -1869,8 +1807,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* 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, - bond->params.lacp_fast); + bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); } else { SLAVE_AD_INFO(new_slave).id = SLAVE_AD_INFO(new_slave->prev).id + 1; @@ -2098,7 +2035,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - if (bond->vlgrp) { + if (bond_vlan_used(bond)) { 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", @@ -2286,7 +2223,7 @@ static int bond_release_all(struct net_device *bond_dev) */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - if (bond->vlgrp) { + if (bond_vlan_used(bond)) { 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", @@ -2527,8 +2464,6 @@ static void bond_miimon_commit(struct bonding *bond) bond_set_backup_slave(slave); } - bond_update_speed_duplex(slave); - 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"); @@ -2607,10 +2542,11 @@ 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); - if (bond->kill_timers) - goto out; + + delay = msecs_to_jiffies(bond->params.miimon); if (bond->slave_cnt == 0) goto re_arm; @@ -2619,7 +2555,15 @@ void bond_mii_monitor(struct work_struct *work) if (bond_miimon_inspect(bond)) { read_unlock(&bond->lock); - rtnl_lock(); + + /* 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); @@ -2631,42 +2575,22 @@ void bond_mii_monitor(struct work_struct *work) re_arm: if (bond->params.miimon) - queue_delayed_work(bond->wq, &bond->mii_work, - msecs_to_jiffies(bond->params.miimon)); -out: + queue_delayed_work(bond->wq, &bond->mii_work, delay); + read_unlock(&bond->lock); if (should_notify_peers) { - rtnl_lock(); + if (!rtnl_trylock()) { + read_lock(&bond->lock); + bond->send_peer_notif++; + read_unlock(&bond->lock); + return; + } netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); rtnl_unlock(); } } -static __be32 bond_glean_dev_ip(struct net_device *dev) -{ - struct in_device *idev; - struct in_ifaddr *ifa; - __be32 addr = 0; - - if (!dev) - return 0; - - rcu_read_lock(); - idev = __in_dev_get_rcu(dev); - if (!idev) - goto out; - - ifa = idev->ifa_list; - if (!ifa) - goto out; - - addr = ifa->ifa_local; -out: - rcu_read_unlock(); - return addr; -} - static int bond_has_this_ip(struct bonding *bond, __be32 ip) { struct vlan_entry *vlan; @@ -2724,7 +2648,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) if (!targets[i]) break; pr_debug("basa: target %x\n", targets[i]); - if (!bond->vlgrp) { + if (!bond_vlan_used(bond)) { pr_debug("basa: empty vlan: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond->master_ip, 0); @@ -2759,7 +2683,10 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) vlan_id = 0; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond->dev, + vlan->vlan_id); + rcu_read_unlock(); if (vlan_dev == rt->dst.dev) { vlan_id = vlan->vlan_id; pr_debug("basa: vlan match on %s %d\n", @@ -2876,9 +2803,6 @@ void bond_loadbalance_arp_mon(struct work_struct *work) delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (bond->kill_timers) - goto out; - if (bond->slave_cnt == 0) goto re_arm; @@ -2977,7 +2901,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); -out: + read_unlock(&bond->lock); } @@ -3222,9 +3146,6 @@ void bond_activebackup_arp_mon(struct work_struct *work) read_lock(&bond->lock); - if (bond->kill_timers) - goto out; - delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); if (bond->slave_cnt == 0) @@ -3234,7 +3155,15 @@ void bond_activebackup_arp_mon(struct work_struct *work) if (bond_ab_arp_inspect(bond, delta_in_ticks)) { read_unlock(&bond->lock); - rtnl_lock(); + + /* 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, delta_in_ticks); @@ -3249,11 +3178,16 @@ void bond_activebackup_arp_mon(struct work_struct *work) re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); -out: + read_unlock(&bond->lock); if (should_notify_peers) { - rtnl_lock(); + if (!rtnl_trylock()) { + read_lock(&bond->lock); + bond->send_peer_notif++; + read_unlock(&bond->lock); + return; + } netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); rtnl_unlock(); } @@ -3282,6 +3216,12 @@ static int bond_master_netdev_event(unsigned long event, switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); + case NETDEV_UNREGISTER: + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; default: break; } @@ -3294,6 +3234,7 @@ static int bond_slave_netdev_event(unsigned long event, { struct net_device *bond_dev = slave_dev->master; struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave = NULL; switch (event) { case NETDEV_UNREGISTER: @@ -3304,20 +3245,16 @@ static int bond_slave_netdev_event(unsigned long event, bond_release(bond_dev, slave_dev); } break; + case NETDEV_UP: case NETDEV_CHANGE: - if (bond->params.mode == BOND_MODE_8023AD || bond_is_lb(bond)) { - struct slave *slave; - - slave = bond_get_slave_by_dev(bond, slave_dev); - if (slave) { - u32 old_speed = slave->speed; - u8 old_duplex = slave->duplex; - - bond_update_speed_duplex(slave); + slave = bond_get_slave_by_dev(bond, slave_dev); + if (slave) { + u32 old_speed = slave->speed; + u8 old_duplex = slave->duplex; - if (bond_is_lb(bond)) - break; + bond_update_speed_duplex(slave); + if (bond->params.mode == BOND_MODE_8023AD) { if (old_speed != slave->speed) bond_3ad_adapter_speed_changed(slave); if (old_duplex != slave->duplex) @@ -3409,6 +3346,10 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, struct bonding *bond; struct vlan_entry *vlan; + /* we only care about primary address */ + if(ifa->ifa_flags & IFA_F_SECONDARY) + return NOTIFY_DONE; + list_for_each_entry(bond, &bn->dev_list, bond_list) { if (bond->dev == event_dev) { switch (event) { @@ -3416,7 +3357,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, bond->master_ip = ifa->ifa_local; return NOTIFY_OK; case NETDEV_DOWN: - bond->master_ip = bond_glean_dev_ip(bond->dev); + bond->master_ip = 0; return NOTIFY_OK; default: return NOTIFY_DONE; @@ -3424,17 +3365,15 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, } list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (!bond->vlgrp) - continue; - vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); + vlan_dev = __vlan_find_dev_deep(bond->dev, + vlan->vlan_id); if (vlan_dev == event_dev) { switch (event) { case NETDEV_UP: vlan->vlan_ip = ifa->ifa_local; return NOTIFY_OK; case NETDEV_DOWN: - vlan->vlan_ip = - bond_glean_dev_ip(vlan_dev); + vlan->vlan_ip = 0; return NOTIFY_OK; default: return NOTIFY_DONE; @@ -3485,7 +3424,7 @@ static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) int layer4_xor = 0; if (skb->protocol == htons(ETH_P_IP)) { - if (!(iph->frag_off & htons(IP_MF|IP_OFFSET)) && + if (!ip_is_fragment(iph) && (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)) { layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); @@ -3510,47 +3449,71 @@ static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) /*-------------------------- Device entry points ----------------------------*/ +static void bond_work_init_all(struct bonding *bond) +{ + INIT_DELAYED_WORK(&bond->mcast_work, + bond_resend_igmp_join_requests_delayed); + INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); + INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + 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); + INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); +} + +static void bond_work_cancel_all(struct bonding *bond) +{ + cancel_delayed_work_sync(&bond->mii_work); + cancel_delayed_work_sync(&bond->arp_work); + cancel_delayed_work_sync(&bond->alb_work); + cancel_delayed_work_sync(&bond->ad_work); + cancel_delayed_work_sync(&bond->mcast_work); +} + static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i; - bond->kill_timers = 0; + /* reset slave->backup and slave->inactive */ + read_lock(&bond->lock); + if (bond->slave_cnt > 0) { + read_lock(&bond->curr_slave_lock); + bond_for_each_slave(bond, slave, i) { + if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) + && (slave != bond->curr_active_slave)) { + bond_set_slave_inactive_flags(slave); + } else { + bond_set_slave_active_flags(slave); + } + } + read_unlock(&bond->curr_slave_lock); + } + read_unlock(&bond->lock); - INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); + bond_work_init_all(bond); if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ - if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) { - /* something went wrong - fail the open operation */ + if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) return -ENOMEM; - } - - 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_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + if (bond->params.miimon) /* link check interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->mii_work, 0); - } if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - 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->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->recv_probe = bond_3ad_lacpdu_recv; @@ -3565,37 +3528,10 @@ static int bond_close(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); write_lock_bh(&bond->lock); - bond->send_peer_notif = 0; - - /* signal timers not to re-arm */ - bond->kill_timers = 1; - write_unlock_bh(&bond->lock); - if (bond->params.miimon) { /* link check interval, in milliseconds. */ - cancel_delayed_work(&bond->mii_work); - } - - if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - cancel_delayed_work(&bond->arp_work); - } - - switch (bond->params.mode) { - case BOND_MODE_8023AD: - cancel_delayed_work(&bond->ad_work); - break; - case BOND_MODE_TLB: - case BOND_MODE_ALB: - cancel_delayed_work(&bond->alb_work); - break; - default: - break; - } - - if (delayed_work_pending(&bond->mcast_work)) - cancel_delayed_work(&bond->mcast_work); - + bond_work_cancel_all(bond); if (bond_is_lb(bond)) { /* Must be called only after all * slaves have been released @@ -3780,44 +3716,27 @@ static bool bond_addr_in_mc_list(unsigned char *addr, return false; } -static void bond_set_multicast_list(struct net_device *bond_dev) +static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); - struct netdev_hw_addr *ha; - bool found; - - /* - * Do promisc before checking multicast_mode - */ - if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) - /* - * FIXME: Need to handle the error when one of the multi-slaves - * encounters error. - */ - bond_set_promiscuity(bond, 1); + if (change & IFF_PROMISC) + bond_set_promiscuity(bond, + bond_dev->flags & IFF_PROMISC ? 1 : -1); - if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) - bond_set_promiscuity(bond, -1); - - - /* set allmulti flag to slaves */ - if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) - /* - * FIXME: Need to handle the error when one of the multi-slaves - * encounters error. - */ - bond_set_allmulti(bond, 1); - - - if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) - bond_set_allmulti(bond, -1); + if (change & IFF_ALLMULTI) + bond_set_allmulti(bond, + bond_dev->flags & IFF_ALLMULTI ? 1 : -1); +} +static void bond_set_multicast_list(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct netdev_hw_addr *ha; + bool found; read_lock(&bond->lock); - bond->flags = bond_dev->flags; - /* looking for addresses to add to slaves' mc list */ netdev_for_each_mc_addr(ha, bond_dev) { found = bond_addr_in_mc_list(ha->addr, &bond->mc_list, @@ -4376,12 +4295,12 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, .ndo_do_ioctl = bond_do_ioctl, - .ndo_set_multicast_list = bond_set_multicast_list, + .ndo_change_rx_flags = bond_change_rx_flags, + .ndo_set_rx_mode = bond_set_multicast_list, .ndo_change_mtu = bond_change_mtu, - .ndo_set_mac_address = bond_set_mac_address, + .ndo_set_mac_address = bond_set_mac_address, .ndo_neigh_setup = bond_neigh_setup, - .ndo_vlan_rx_register = bond_vlan_rx_register, - .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, + .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, @@ -4456,30 +4375,6 @@ static void bond_setup(struct net_device *bond_dev) bond_dev->features |= bond_dev->hw_features; } -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); - - if (delayed_work_pending(&bond->mcast_work)) - cancel_delayed_work(&bond->mcast_work); -} - /* * Destroy a bonding device. * Must be under rtnl_lock when this function is called. @@ -4498,8 +4393,6 @@ static void bond_uninit(struct net_device *bond_dev) bond_work_cancel_all(bond); - bond_remove_proc_entry(bond); - bond_debug_unregister(bond); __hw_addr_flush(&bond->mc_list); @@ -4788,7 +4681,7 @@ static int bond_check_params(struct bond_params *params) /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ - pr_warning("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n"); + pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n"); } if (primary && !USES_PRIMARY(bond_mode)) { @@ -4845,6 +4738,7 @@ static int bond_check_params(struct bond_params *params) params->tx_queues = tx_queues; params->all_slaves_active = all_slaves_active; params->resend_igmp = resend_igmp; + params->min_links = min_links; if (primary) { strncpy(params->primary, primary, IFNAMSIZ); @@ -4900,7 +4794,6 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); @@ -4922,11 +4815,20 @@ static int bond_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static int bond_get_tx_queues(struct net *net, struct nlattr *tb[], + unsigned int *num_queues, + unsigned int *real_num_queues) +{ + *num_queues = tx_queues; + return 0; +} + static struct rtnl_link_ops bond_link_ops __read_mostly = { .kind = "bond", .priv_size = sizeof(struct bonding), .setup = bond_setup, .validate = bond_validate, + .get_tx_queues = bond_get_tx_queues, }; /* Create a new bond based on the specified name and bonding parameters. @@ -4971,6 +4873,7 @@ static int __net_init bond_net_init(struct net *net) INIT_LIST_HEAD(&bn->dev_list); bond_create_proc_dir(bn); + bond_create_sysfs(bn); return 0; } @@ -4978,8 +4881,18 @@ static int __net_init bond_net_init(struct net *net) static void __net_exit bond_net_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); + struct bonding *bond, *tmp_bond; + LIST_HEAD(list); + bond_destroy_sysfs(bn); bond_destroy_proc_dir(bn); + + /* Kill off any bonds created after unregistering bond rtnl ops */ + rtnl_lock(); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); } static struct pernet_operations bond_net_ops = { @@ -5016,15 +4929,12 @@ static int __init bonding_init(void) goto err; } - res = bond_create_sysfs(); - if (res) - goto err; - register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); out: return res; err: + bond_destroy_debugfs(); rtnl_link_unregister(&bond_link_ops); err_link: unregister_pernet_subsys(&bond_net_ops); @@ -5037,7 +4947,6 @@ static void __exit bonding_exit(void) unregister_netdevice_notifier(&bond_netdev_notifier); unregister_inetaddr_notifier(&bond_inetaddr_notifier); - bond_destroy_sysfs(); bond_destroy_debugfs(); rtnl_link_unregister(&bond_link_ops); diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index c97307d..ad284ba 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -1,4 +1,5 @@ #include <linux/proc_fs.h> +#include <linux/export.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include "bonding.h" @@ -125,6 +126,7 @@ static void bond_info_show_master(struct seq_file *seq) seq_puts(seq, "\n802.3ad info\n"); seq_printf(seq, "LACP rate: %s\n", (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Min links: %d\n", bond->params.min_links); seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", ad_select_tbl[bond->params.ad_select].modename); @@ -156,8 +158,16 @@ static void bond_info_show_slave(struct seq_file *seq, seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", (slave->link == BOND_LINK_UP) ? "up" : "down"); - seq_printf(seq, "Speed: %d Mbps\n", slave->speed); - seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); + if (slave->speed == SPEED_UNKNOWN) + seq_printf(seq, "Speed: %s\n", "Unknown"); + else + seq_printf(seq, "Speed: %d Mbps\n", slave->speed); + + if (slave->duplex == DUPLEX_UNKNOWN) + seq_printf(seq, "Duplex: %s\n", "Unknown"); + else + seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); + seq_printf(seq, "Link Failure Count: %u\n", slave->link_failure_count); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8a96735..cf95bd8 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -55,8 +55,8 @@ static ssize_t bonding_show_bonds(struct class *cls, struct class_attribute *attr, char *buf) { - struct net *net = current->nsproxy->net_ns; - struct bond_net *bn = net_generic(net, bond_net_id); + struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); int res = 0; struct bonding *bond; @@ -79,9 +79,8 @@ static ssize_t bonding_show_bonds(struct class *cls, return res; } -static struct net_device *bond_get_by_name(struct net *net, const char *ifname) +static struct net_device *bond_get_by_name(struct bond_net *bn, const char *ifname) { - struct bond_net *bn = net_generic(net, bond_net_id); struct bonding *bond; list_for_each_entry(bond, &bn->dev_list, bond_list) { @@ -103,7 +102,8 @@ static ssize_t bonding_store_bonds(struct class *cls, struct class_attribute *attr, const char *buffer, size_t count) { - struct net *net = current->nsproxy->net_ns; + struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); char command[IFNAMSIZ + 1] = {0, }; char *ifname; int rv, res = count; @@ -116,7 +116,7 @@ static ssize_t bonding_store_bonds(struct class *cls, if (command[0] == '+') { pr_info("%s is being created...\n", ifname); - rv = bond_create(net, ifname); + rv = bond_create(bn->net, ifname); if (rv) { if (rv == -EEXIST) pr_info("%s already exists.\n", ifname); @@ -128,7 +128,7 @@ static ssize_t bonding_store_bonds(struct class *cls, struct net_device *bond_dev; rtnl_lock(); - bond_dev = bond_get_by_name(net, ifname); + bond_dev = bond_get_by_name(bn, ifname); if (bond_dev) { pr_info("%s is being deleted...\n", ifname); unregister_netdevice(bond_dev); @@ -150,9 +150,24 @@ err_no_cmd: return -EPERM; } +static const void *bonding_namespace(struct class *cls, + const struct class_attribute *attr) +{ + const struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); + return bn->net; +} + /* class attribute for bond_masters file. This ends up in /sys/class/net */ -static CLASS_ATTR(bonding_masters, S_IWUSR | S_IRUGO, - bonding_show_bonds, bonding_store_bonds); +static const struct class_attribute class_attr_bonding_masters = { + .attr = { + .name = "bonding_masters", + .mode = S_IWUSR | S_IRUGO, + }, + .show = bonding_show_bonds, + .store = bonding_store_bonds, + .namespace = bonding_namespace, +}; int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave) @@ -169,6 +184,11 @@ int bond_create_slave_symlinks(struct net_device *master, sprintf(linkname, "slave_%s", slave->name); ret = sysfs_create_link(&(master->dev.kobj), &(slave->dev.kobj), linkname); + + /* free the master link created earlier in case of error */ + if (ret) + sysfs_remove_link(&(slave->dev.kobj), "master"); + return ret; } @@ -304,6 +324,13 @@ static ssize_t bonding_store_mode(struct device *d, goto out; } + if (bond->slave_cnt > 0) { + pr_err("unable to update mode of %s because it has slaves.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + new_value = bond_parse_parm(buf, bond_mode_tbl); if (new_value < 0) { pr_err("%s: Ignoring invalid mode value %.*s.\n", @@ -492,6 +519,8 @@ static ssize_t bonding_store_arp_interval(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (sscanf(buf, "%d", &new_value) != 1) { pr_err("%s: no arp_interval value specified.\n", bond->dev->name); @@ -499,14 +528,15 @@ static ssize_t bonding_store_arp_interval(struct device *d, goto out; } if (new_value < 0) { - pr_err("%s: Invalid arp_interval value %d not in range 1-%d; rejected.\n", + pr_err("%s: Invalid arp_interval value %d not in range 0-%d; rejected.\n", bond->dev->name, new_value, INT_MAX); ret = -EINVAL; goto out; } if (bond->params.mode == BOND_MODE_ALB || - bond->params.mode == BOND_MODE_TLB) { - pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n", + bond->params.mode == BOND_MODE_TLB || + bond->params.mode == BOND_MODE_8023AD) { + pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n", bond->dev->name, bond->dev->name); ret = -EINVAL; goto out; @@ -514,18 +544,15 @@ static ssize_t bonding_store_arp_interval(struct device *d, pr_info("%s: Setting ARP monitoring interval to %d.\n", bond->dev->name, new_value); bond->params.arp_interval = new_value; - if (bond->params.miimon) { - pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n", - bond->dev->name, bond->dev->name); - bond->params.miimon = 0; - if (delayed_work_pending(&bond->mii_work)) { - cancel_delayed_work(&bond->mii_work); - flush_workqueue(bond->wq); + if (new_value) { + if (bond->params.miimon) { + pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n", + bond->dev->name, bond->dev->name); + bond->params.miimon = 0; } - } - if (!bond->params.arp_targets[0]) { - pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n", - bond->dev->name); + if (!bond->params.arp_targets[0]) + pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n", + bond->dev->name); } if (bond->dev->flags & IFF_UP) { /* If the interface is up, we may need to fire off @@ -533,19 +560,15 @@ static ssize_t bonding_store_arp_interval(struct device *d, * timer will get fired off when the open function * is called. */ - if (!delayed_work_pending(&bond->arp_work)) { - 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); - + if (!new_value) { + cancel_delayed_work_sync(&bond->arp_work); + } else { + cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } } - out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(arp_interval, S_IRUGO | S_IWUSR, @@ -671,6 +694,8 @@ static ssize_t bonding_store_downdelay(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (!(bond->params.miimon)) { pr_err("%s: Unable to set down delay as MII monitoring is disabled\n", bond->dev->name); @@ -685,7 +710,7 @@ static ssize_t bonding_store_downdelay(struct device *d, } if (new_value < 0) { pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n", - bond->dev->name, new_value, 1, INT_MAX); + bond->dev->name, new_value, 0, INT_MAX); ret = -EINVAL; goto out; } else { @@ -704,6 +729,7 @@ static ssize_t bonding_store_downdelay(struct device *d, } out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR, @@ -726,6 +752,8 @@ static ssize_t bonding_store_updelay(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (!(bond->params.miimon)) { pr_err("%s: Unable to set up delay as MII monitoring is disabled\n", bond->dev->name); @@ -740,8 +768,8 @@ static ssize_t bonding_store_updelay(struct device *d, goto out; } if (new_value < 0) { - pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n", - bond->dev->name, new_value, 1, INT_MAX); + pr_err("%s: Invalid up delay value %d not in range %d-%d; rejected.\n", + bond->dev->name, new_value, 0, INT_MAX); ret = -EINVAL; goto out; } else { @@ -759,6 +787,7 @@ static ssize_t bonding_store_updelay(struct device *d, } out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR, @@ -804,6 +833,7 @@ static ssize_t bonding_store_lacp(struct device *d, if ((new_value == 1) || (new_value == 0)) { bond->params.lacp_fast = new_value; + bond_3ad_update_lacp_rate(bond); pr_info("%s: Setting LACP rate to %s (%d).\n", bond->dev->name, bond_lacp_tbl[new_value].modename, new_value); @@ -818,6 +848,38 @@ out: static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, bonding_show_lacp, bonding_store_lacp); +static ssize_t bonding_show_min_links(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.min_links); +} + +static ssize_t bonding_store_min_links(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bonding *bond = to_bond(d); + int ret; + unsigned int new_value; + + ret = kstrtouint(buf, 0, &new_value); + if (ret < 0) { + pr_err("%s: Ignoring invalid min links value %s.\n", + bond->dev->name, buf); + return ret; + } + + pr_info("%s: Setting min links value to %u\n", + bond->dev->name, new_value); + bond->params.min_links = new_value; + return count; +} +static DEVICE_ATTR(min_links, S_IRUGO | S_IWUSR, + bonding_show_min_links, bonding_store_min_links); + static ssize_t bonding_show_ad_select(struct device *d, struct device_attribute *attr, char *buf) @@ -908,6 +970,8 @@ static ssize_t bonding_store_miimon(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (sscanf(buf, "%d", &new_value) != 1) { pr_err("%s: no miimon value specified.\n", bond->dev->name); @@ -916,50 +980,43 @@ static ssize_t bonding_store_miimon(struct device *d, } if (new_value < 0) { pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n", - bond->dev->name, new_value, 1, INT_MAX); + bond->dev->name, new_value, 0, INT_MAX); ret = -EINVAL; goto out; - } else { - pr_info("%s: Setting MII monitoring interval to %d.\n", - bond->dev->name, new_value); - bond->params.miimon = new_value; - if (bond->params.updelay) - pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n", - bond->dev->name, - bond->params.updelay * bond->params.miimon); - if (bond->params.downdelay) - pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n", - bond->dev->name, - bond->params.downdelay * bond->params.miimon); - if (bond->params.arp_interval) { - pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n", - bond->dev->name); - bond->params.arp_interval = 0; - if (bond->params.arp_validate) { - bond->params.arp_validate = - BOND_ARP_VALIDATE_NONE; - } - if (delayed_work_pending(&bond->arp_work)) { - cancel_delayed_work(&bond->arp_work); - flush_workqueue(bond->wq); - } - } - - if (bond->dev->flags & IFF_UP) { - /* If the interface is up, we may need to fire off - * the MII timer. If the interface is down, the - * timer will get fired off when the open function - * is called. - */ - if (!delayed_work_pending(&bond->mii_work)) { - INIT_DELAYED_WORK(&bond->mii_work, - bond_mii_monitor); - queue_delayed_work(bond->wq, - &bond->mii_work, 0); - } + } + pr_info("%s: Setting MII monitoring interval to %d.\n", + bond->dev->name, new_value); + bond->params.miimon = new_value; + if (bond->params.updelay) + pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n", + bond->dev->name, + bond->params.updelay * bond->params.miimon); + if (bond->params.downdelay) + pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n", + bond->dev->name, + bond->params.downdelay * bond->params.miimon); + if (new_value && bond->params.arp_interval) { + pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n", + bond->dev->name); + bond->params.arp_interval = 0; + if (bond->params.arp_validate) + bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; + } + if (bond->dev->flags & IFF_UP) { + /* If the interface is up, we may need to fire off + * the MII timer. If the interface is down, the + * timer will get fired off when the open function + * is called. + */ + if (!new_value) { + cancel_delayed_work_sync(&bond->mii_work); + } else { + cancel_delayed_work_sync(&bond->arp_work); + queue_delayed_work(bond->wq, &bond->mii_work, 0); } } out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(miimon, S_IRUGO | S_IWUSR, @@ -1611,6 +1668,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_queue_id.attr, &dev_attr_all_slaves_active.attr, &dev_attr_resend_igmp.attr, + &dev_attr_min_links.attr, NULL, }; @@ -1623,11 +1681,14 @@ static struct attribute_group bonding_group = { * Initialize sysfs. This sets up the bonding_masters file in * /sys/class/net. */ -int bond_create_sysfs(void) +int bond_create_sysfs(struct bond_net *bn) { int ret; - ret = netdev_class_create_file(&class_attr_bonding_masters); + bn->class_attr_bonding_masters = class_attr_bonding_masters; + sysfs_attr_init(&bn->class_attr_bonding_masters.attr); + + ret = netdev_class_create_file(&bn->class_attr_bonding_masters); /* * Permit multiple loads of the module by ignoring failures to * create the bonding_masters sysfs file. Bonding devices @@ -1641,7 +1702,7 @@ int bond_create_sysfs(void) */ if (ret == -EEXIST) { /* Is someone being kinky and naming a device bonding_master? */ - if (__dev_get_by_name(&init_net, + if (__dev_get_by_name(bn->net, class_attr_bonding_masters.attr.name)) pr_err("network device named %s already exists in sysfs", class_attr_bonding_masters.attr.name); @@ -1655,9 +1716,9 @@ int bond_create_sysfs(void) /* * Remove /sys/class/net/bonding_masters. */ -void bond_destroy_sysfs(void) +void bond_destroy_sysfs(struct bond_net *bn) { - netdev_class_remove_file(&class_attr_bonding_masters); + netdev_class_remove_file(&bn->class_attr_bonding_masters); } /* diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index ea1d005..1aecc37 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -147,6 +147,7 @@ struct bond_params { int updelay; int downdelay; int lacp_fast; + unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; @@ -221,7 +222,6 @@ struct bonding { struct slave *); rwlock_t lock; rwlock_t curr_slave_lock; - s8 kill_timers; u8 send_peer_notif; s8 setup_by_slave; s8 igmp_retrans; @@ -233,14 +233,11 @@ struct bonding { struct netdev_hw_addr_list mc_list; int (*xmit_hash_policy)(struct sk_buff *, int); __be32 master_ip; - u16 flags; u16 rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct list_head vlan_list; - struct vlan_group *vlgrp; - struct packet_type arp_mon_pt; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; @@ -253,6 +250,11 @@ struct bonding { #endif /* CONFIG_DEBUG_FS */ }; +static inline bool bond_vlan_used(struct bonding *bond) +{ + return !list_empty(&bond->vlan_list); +} + #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) @@ -376,11 +378,13 @@ static inline bool bond_is_slave_inactive(struct slave *slave) return slave->inactive; } +struct bond_net; + struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr); int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); -int bond_create_sysfs(void); -void bond_destroy_sysfs(void); +int bond_create_sysfs(struct bond_net *net); +void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave); void bond_destroy_slave_symlinks(struct net_device *master, struct net_device *slave); @@ -406,6 +410,7 @@ struct bond_net { #ifdef CONFIG_PROC_FS struct proc_dir_entry * proc_dir; #endif + struct class_attribute class_attr_bonding_masters; }; #ifdef CONFIG_PROC_FS |