diff options
Diffstat (limited to 'drivers/net/bonding')
| -rw-r--r-- | drivers/net/bonding/bond_3ad.c | 122 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 213 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_netlink.c | 62 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_options.c | 97 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 6 |
5 files changed, 326 insertions, 174 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index c6807e473ab7..49717b7b82a2 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -95,13 +95,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port, bool *update_slave_arr); static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); static void ad_tx_machine(struct port *port); -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params); +static void ad_periodic_machine(struct port *port); static void ad_port_selection_logic(struct port *port, bool *update_slave_arr); static void ad_agg_selection_logic(struct aggregator *aggregator, bool *update_slave_arr); static void ad_clear_agg(struct aggregator *aggregator); static void ad_initialize_agg(struct aggregator *aggregator); -static void ad_initialize_port(struct port *port, int lacp_fast); +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params); static void ad_enable_collecting(struct port *port); static void ad_disable_distributing(struct port *port, bool *update_slave_arr); @@ -436,6 +436,7 @@ static void __ad_actor_update_port(struct port *port) port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; port->actor_system_priority = BOND_AD_INFO(bond).system.sys_priority; + port->actor_port_priority = SLAVE_AD_INFO(port->slave)->port_priority; } /* Conversions */ @@ -746,6 +747,18 @@ static int __agg_active_ports(struct aggregator *agg) return active; } +static unsigned int __agg_ports_priority(const struct aggregator *agg) +{ + struct port *port = agg->lag_ports; + unsigned int prio = 0; + + for (; port; port = port->next_port_in_aggregator) + if (port->is_enabled) + prio += port->actor_port_priority; + + return prio; +} + /** * __get_agg_bandwidth - get the total bandwidth of an aggregator * @aggregator: the aggregator we're looking at @@ -982,6 +995,17 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) return 0; } +static void ad_cond_set_peer_notif(struct port *port) +{ + struct bonding *bond = port->slave->bond; + + if (bond->params.broadcast_neighbor && rtnl_trylock()) { + bond->send_peer_notif = bond->params.num_peer_notif * + max(1, bond->params.peer_notif_delay); + rtnl_unlock(); + } +} + /** * ad_mux_machine - handle a port's mux state machine * @port: the port we're looking at @@ -1296,10 +1320,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) * case of EXPIRED even if LINK_DOWN didn't arrive for * the port. */ - port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->sm_vars &= ~AD_PORT_MATCHED; + /* Based on IEEE 8021AX-2014, Figure 6-18 - Receive + * machine state diagram, the statue should be + * Partner_Oper_Port_State.Synchronization = FALSE; + * Partner_Oper_Port_State.LACP_Timeout = Short Timeout; + * start current_while_timer(Short Timeout); + * Actor_Oper_Port_State.Expired = TRUE; + */ + port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT; - port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY; port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); port->actor_oper_port_state |= LACP_STATE_EXPIRED; port->sm_vars |= AD_PORT_CHURNED; @@ -1378,7 +1408,7 @@ static void ad_tx_machine(struct port *port) /* check if tx timer expired, to verify that we do not send more than * 3 packets per second */ - if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) { + if (!port->sm_tx_timer_counter || !(--port->sm_tx_timer_counter)) { /* check if there is something to send */ if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { __update_lacpdu_from_port(port); @@ -1393,23 +1423,23 @@ static void ad_tx_machine(struct port *port) * again until demanded */ port->ntt = false; + + /* restart tx timer(to verify that we will not + * exceed AD_MAX_TX_IN_SECOND + */ + port->sm_tx_timer_counter = ad_ticks_per_sec / AD_MAX_TX_IN_SECOND; } } - /* restart tx timer(to verify that we will not exceed - * AD_MAX_TX_IN_SECOND - */ - port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; } } /** * ad_periodic_machine - handle a port's periodic state machine * @port: the port we're looking at - * @bond_params: bond parameters we will use * * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. */ -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params) +static void ad_periodic_machine(struct port *port) { periodic_states_t last_state; @@ -1418,8 +1448,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || - (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) || - !bond_params->lacp_active) { + (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) { port->sm_periodic_state = AD_NO_PERIODIC; } /* check if state machine should change state */ @@ -1691,6 +1720,9 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, * 4. Therefore, current and best both have partner replies or * both do not, so perform selection policy: * + * BOND_AD_PRIO: Select by total priority of ports. If priority + * is equal, select by count. + * * BOND_AD_COUNT: Select by count of ports. If count is equal, * select by bandwidth. * @@ -1712,6 +1744,14 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, return best; switch (__get_agg_selection_mode(curr->lag_ports)) { + case BOND_AD_PRIO: + if (__agg_ports_priority(curr) > __agg_ports_priority(best)) + return curr; + + if (__agg_ports_priority(curr) < __agg_ports_priority(best)) + return best; + + fallthrough; case BOND_AD_COUNT: if (__agg_active_ports(curr) > __agg_active_ports(best)) return curr; @@ -1777,6 +1817,10 @@ static int agg_device_up(const struct aggregator *agg) * (slaves), and reselect whenever a link state change takes place or the * set of slaves in the bond changes. * + * BOND_AD_PRIO: select the aggregator with highest total priority of ports + * (slaves), and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. + * * FIXME: this function MUST be called with the first agg in the bond, or * __get_active_agg() won't work correctly. This function should be better * called with the bond itself, and retrieve the first agg from it. @@ -1943,16 +1987,16 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters * @port: the port we're looking at - * @lacp_fast: boolean. whether fast periodic should be used + * @bond_params: bond parameters we will use */ -static void ad_initialize_port(struct port *port, int lacp_fast) +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params) { static const struct port_params tmpl = { .system_priority = 0xffff, .key = 1, .port_number = 1, .port_priority = 0xff, - .port_state = 1, + .port_state = 0, }; static const struct lacpdu lacpdu = { .subtype = 0x01, @@ -1970,12 +2014,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->actor_port_priority = 0xff; port->actor_port_aggregator_identifier = 0; port->ntt = false; - port->actor_admin_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; - port->actor_oper_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; + port->actor_admin_port_state = LACP_STATE_AGGREGATION; + port->actor_oper_port_state = LACP_STATE_AGGREGATION; + if (bond_params->lacp_active) { + port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY; + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + } - if (lacp_fast) + if (bond_params->lacp_fast) port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT; memcpy(&port->partner_admin, &tmpl, sizeof(tmpl)); @@ -2061,6 +2107,8 @@ static void ad_enable_collecting_distributing(struct port *port, __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; + /* Should notify peers if possible */ + ad_cond_set_peer_notif(port); } } @@ -2187,7 +2235,10 @@ void bond_3ad_bind_slave(struct slave *slave) /* port initialization */ port = &(SLAVE_AD_INFO(slave)->port); - ad_initialize_port(port, bond->params.lacp_fast); + ad_initialize_port(port, &bond->params); + + /* Port priority is initialized. Update it to slave's ad info */ + SLAVE_AD_INFO(slave)->port_priority = port->actor_port_priority; port->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave)->id; @@ -2499,7 +2550,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } ad_rx_machine(NULL, port); - ad_periodic_machine(port, &bond->params); + ad_periodic_machine(port); ad_port_selection_logic(port, &update_slave_arr); ad_mux_machine(port, &update_slave_arr); ad_tx_machine(port); @@ -2869,6 +2920,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } +/** + * bond_3ad_update_lacp_active - change the lacp active + * @bond: bonding struct + * + * Update actor_oper_port_state when lacp_active is modified. + */ +void bond_3ad_update_lacp_active(struct bonding *bond) +{ + struct port *port = NULL; + struct list_head *iter; + struct slave *slave; + int lacp_active; + + lacp_active = bond->params.lacp_active; + spin_lock_bh(&bond->mode_lock); + bond_for_each_slave(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->port); + if (lacp_active) + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + else + port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY; + } + spin_unlock_bh(&bond->mode_lock); +} + size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c4d53e8e7c15..4da619210c1f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -142,8 +142,7 @@ module_param(downdelay, int, 0); MODULE_PARM_DESC(downdelay, "Delay before considering link down, " "in milliseconds"); module_param(use_carrier, int, 0); -MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " - "0 for off, 1 for on (default)"); +MODULE_PARM_DESC(use_carrier, "option obsolete, use_carrier cannot be disabled"); module_param(mode, charp, 0); MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, " "1 for active-backup, 2 for balance-xor, " @@ -212,6 +211,8 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0); unsigned int bond_net_id __read_mostly; +DEFINE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled); + static const struct flow_dissector_key flow_keys_bonding_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -828,77 +829,6 @@ const char *bond_slave_link_status(s8 link) } } -/* if <dev> supports MII link status reporting, check its link status. - * - * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), - * depending upon the setting of the use_carrier parameter. - * - * Return either BMSR_LSTATUS, meaning that the link is up (or we - * can't tell and just pretend it is), or 0, meaning that the link is - * down. - * - * If reporting is non-zero, instead of faking link up, return -1 if - * both ETHTOOL and MII ioctls fail (meaning the device does not - * support them). If use_carrier is set, return whatever it says. - * It'd be nice if there was a good way to tell if a driver supports - * netif_carrier, but there really isn't. - */ -static int bond_check_dev_link(struct bonding *bond, - struct net_device *slave_dev, int reporting) -{ - const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - struct mii_ioctl_data *mii; - struct ifreq ifr; - int ret; - - if (!reporting && !netif_running(slave_dev)) - return 0; - - if (bond->params.use_carrier) - return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; - - /* Try to get link status using Ethtool first. */ - if (slave_dev->ethtool_ops->get_link) { - netdev_lock_ops(slave_dev); - ret = slave_dev->ethtool_ops->get_link(slave_dev); - netdev_unlock_ops(slave_dev); - - return ret ? BMSR_LSTATUS : 0; - } - - /* Ethtool can't be used, fallback to MII ioctls. */ - if (slave_ops->ndo_eth_ioctl) { - /* TODO: set pointer to correct ioctl on a per team member - * bases to make this more efficient. that is, once - * we determine the correct ioctl, we will always - * call it and not the others for that team - * member. - */ - - /* We cannot assume that SIOCGMIIPHY will also read a - * register; not all network drivers (e.g., e100) - * support that. - */ - - /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ - strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); - mii = if_mii(&ifr); - - if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { - mii->reg_num = MII_BMSR; - if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) - return mii->val_out & BMSR_LSTATUS; - } - } - - /* If reporting, report that either there's no ndo_eth_ioctl, - * or both SIOCGMIIREG and get_link failed (meaning that we - * cannot report link status). If not reporting, pretend - * we're ok. - */ - return reporting ? -1 : BMSR_LSTATUS; -} - /*----------------------------- Multicast list ------------------------------*/ /* Push the promiscuity flag down to appropriate slaves */ @@ -1038,7 +968,7 @@ static int bond_set_dev_addr(struct net_device *bond_dev, slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", bond_dev, slave_dev, slave_dev->addr_len); - err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); + err = netif_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; @@ -1235,17 +1165,32 @@ static struct slave *bond_find_best_slave(struct bonding *bond) /* must be called in RCU critical section or with RTNL held */ static bool bond_should_notify_peers(struct bonding *bond) { - struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); + struct bond_up_slave *usable; + struct slave *slave = NULL; - if (!slave || !bond->send_peer_notif || + if (!bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || - !netif_carrier_ok(bond->dev) || - test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) + !netif_carrier_ok(bond->dev)) return false; + /* The send_peer_notif is set by active-backup or 8023ad + * mode, and cleared in bond_close() when changing mode. + * It is safe to only check bond mode here. + */ + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + usable = rcu_dereference_rtnl(bond->usable_slaves); + if (!usable || !READ_ONCE(usable->count)) + return false; + } else { + slave = rcu_dereference_rtnl(bond->curr_active_slave); + if (!slave || test_bit(__LINK_STATE_LINKWATCH_PENDING, + &slave->dev->state)) + return false; + } + netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", - slave ? slave->dev->name : "NULL"); + slave ? slave->dev->name : "all"); return true; } @@ -1949,7 +1894,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL, *prev_slave; struct sockaddr_storage ss; - int link_reporting; int res = 0, i; if (slave_dev->flags & IFF_MASTER && @@ -1959,12 +1903,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, return -EPERM; } - if (!bond->params.use_carrier && - slave_dev->ethtool_ops->get_link == NULL && - slave_ops->ndo_eth_ioctl == NULL) { - slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); - } - /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, @@ -2115,6 +2053,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + bond_has_slaves(bond) && memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) { /* Set slave to random address to avoid duplicate mac * address in later fail over. @@ -2178,29 +2117,10 @@ skip_mac_set: new_slave->last_tx = new_slave->last_rx; - if (bond->params.miimon && !bond->params.use_carrier) { - link_reporting = bond_check_dev_link(bond, slave_dev, 1); - - if ((link_reporting == -1) && !bond->params.arp_interval) { - /* miimon is set but a bonded network driver - * does not support ETHTOOL/MII and - * arp_interval is not set. Note: if - * use_carrier is enabled, we will never go - * here (because netif_carrier is always - * supported); thus, we don't need to change - * the messages for netif_carrier. - */ - slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n"); - } else if (link_reporting == -1) { - /* unable get link status using mii/ethtool */ - slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n"); - } - } - /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { - if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { + if (netif_carrier_ok(slave_dev)) { if (bond->params.updelay) { bond_set_slave_link_state(new_slave, BOND_LINK_BACK, @@ -2652,7 +2572,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (unregister) { netdev_lock_ops(slave_dev); - __dev_set_mtu(slave_dev, slave->original_mtu); + __netif_set_mtu(slave_dev, slave->original_mtu); netdev_unlock_ops(slave_dev); } else { dev_set_mtu(slave_dev, slave->original_mtu); @@ -2742,7 +2662,7 @@ static int bond_miimon_inspect(struct bonding *bond) bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); - link_state = bond_check_dev_link(bond, slave->dev, 0); + link_state = netif_carrier_ok(slave->dev); switch (slave->link) { case BOND_LINK_UP: @@ -3338,7 +3258,6 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave) /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; - fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { @@ -4394,7 +4313,7 @@ void bond_work_init_all(struct bonding *bond) INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } -static void bond_work_cancel_all(struct bonding *bond) +void bond_work_cancel_all(struct bonding *bond) { cancel_delayed_work_sync(&bond->mii_work); cancel_delayed_work_sync(&bond->arp_work); @@ -4456,6 +4375,9 @@ static int bond_open(struct net_device *bond_dev) bond_for_each_slave(bond, slave, iter) dev_mc_add(slave->dev, lacpdu_mcast_addr); + + if (bond->params.broadcast_neighbor) + static_branch_inc(&bond_bcast_neigh_enabled); } if (bond_mode_can_use_xmit_hash(bond)) @@ -4475,6 +4397,10 @@ static int bond_close(struct net_device *bond_dev) bond_alb_deinitialize(bond); bond->recv_probe = NULL; + if (BOND_MODE(bond) == BOND_MODE_8023AD && + bond->params.broadcast_neighbor) + static_branch_dec(&bond_bcast_neigh_enabled); + if (bond_uses_primary(bond)) { rcu_read_lock(); slave = rcu_dereference(bond->curr_active_slave); @@ -5310,6 +5236,37 @@ static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, return slaves->arr[hash % count]; } +static bool bond_should_broadcast_neighbor(struct sk_buff *skb, + struct net_device *dev) +{ + struct bonding *bond = netdev_priv(dev); + struct { + struct ipv6hdr ip6; + struct icmp6hdr icmp6; + } *combined, _combined; + + if (!static_branch_unlikely(&bond_bcast_neigh_enabled)) + return false; + + if (!bond->params.broadcast_neighbor) + return false; + + if (skb->protocol == htons(ETH_P_ARP)) + return true; + + if (skb->protocol == htons(ETH_P_IPV6)) { + combined = skb_header_pointer(skb, skb_mac_header_len(skb), + sizeof(_combined), + &_combined); + if (combined && combined->ip6.nexthdr == NEXTHDR_ICMP && + (combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || + combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) + return true; + } + + return false; +} + /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. @@ -5329,17 +5286,27 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, return bond_tx_drop(dev, skb); } -/* in broadcast mode, we send everything to all usable interfaces. */ +/* in broadcast mode, we send everything to all or usable slave interfaces. + * under rcu_read_lock when this function is called. + */ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, - struct net_device *bond_dev) + struct net_device *bond_dev, + bool all_slaves) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave = NULL; - struct list_head *iter; + struct bond_up_slave *slaves; bool xmit_suc = false; bool skb_used = false; + int slaves_count, i; - bond_for_each_slave_rcu(bond, slave, iter) { + if (all_slaves) + slaves = rcu_dereference(bond->all_slaves); + else + slaves = rcu_dereference(bond->usable_slaves); + + slaves_count = slaves ? READ_ONCE(slaves->count) : 0; + for (i = 0; i < slaves_count; i++) { + struct slave *slave = slaves->arr[i]; struct sk_buff *skb2; if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)) @@ -5577,10 +5544,13 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev case BOND_MODE_ACTIVEBACKUP: return bond_xmit_activebackup(skb, dev); case BOND_MODE_8023AD: + if (bond_should_broadcast_neighbor(skb, dev)) + return bond_xmit_broadcast(skb, dev, false); + fallthrough; case BOND_MODE_XOR: return bond_3ad_xor_xmit(skb, dev); case BOND_MODE_BROADCAST: - return bond_xmit_broadcast(skb, dev); + return bond_xmit_broadcast(skb, dev, true); case BOND_MODE_ALB: return bond_alb_xmit(skb, dev); case BOND_MODE_TLB: @@ -6189,10 +6159,10 @@ static int __init bond_check_params(struct bond_params *params) downdelay = 0; } - if ((use_carrier != 0) && (use_carrier != 1)) { - pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", - use_carrier); - use_carrier = 1; + if (use_carrier != 1) { + pr_err("Error: invalid use_carrier parameter (%d)\n", + use_carrier); + return -EINVAL; } if (num_peer_notif < 0 || num_peer_notif > 255) { @@ -6439,7 +6409,6 @@ static int __init bond_check_params(struct bond_params *params) params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; - params->use_carrier = use_carrier; params->lacp_active = 1; params->lacp_fast = lacp_fast; params->primary[0] = 0; @@ -6456,6 +6425,7 @@ static int __init bond_check_params(struct bond_params *params) eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; params->coupled_control = 1; + params->broadcast_neighbor = 0; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); @@ -6674,3 +6644,4 @@ module_exit(bonding_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index ac5e402c34bc..286f11c517f7 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -28,6 +28,7 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev, nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */ nla_total_size(sizeof(s32)) + /* IFLA_BOND_SLAVE_PRIO */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_ACTOR_PORT_PRIO */ 0; } @@ -77,6 +78,10 @@ static int bond_fill_slave_info(struct sk_buff *skb, ad_port->partner_oper.port_state)) goto nla_put_failure; } + + if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, + SLAVE_AD_INFO(slave)->port_priority)) + goto nla_put_failure; } return 0; @@ -124,11 +129,13 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 }, + [IFLA_BOND_BROADCAST_NEIGH] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { [IFLA_BOND_SLAVE_QUEUE_ID] = { .type = NLA_U16 }, [IFLA_BOND_SLAVE_PRIO] = { .type = NLA_S32 }, + [IFLA_BOND_SLAVE_ACTOR_PORT_PRIO] = { .type = NLA_U16 }, }; static int bond_validate(struct nlattr *tb[], struct nlattr *data[], @@ -179,6 +186,16 @@ static int bond_slave_changelink(struct net_device *bond_dev, return err; } + if (data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]) { + u16 ad_prio = nla_get_u16(data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]); + + bond_opt_slave_initval(&newval, &slave_dev, ad_prio); + err = __bond_opt_set(bond, BOND_OPT_ACTOR_PORT_PRIO, &newval, + data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO], extack); + if (err) + return err; + } + return 0; } @@ -258,13 +275,11 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; } if (data[IFLA_BOND_USE_CARRIER]) { - int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]); - - bond_opt_initval(&newval, use_carrier); - err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval, - data[IFLA_BOND_USE_CARRIER], extack); - if (err) - return err; + if (nla_get_u8(data[IFLA_BOND_USE_CARRIER]) != 1) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_USE_CARRIER], + "option obsolete, use_carrier cannot be disabled"); + return -EINVAL; + } } if (data[IFLA_BOND_ARP_INTERVAL]) { int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); @@ -561,6 +576,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; } + if (data[IFLA_BOND_BROADCAST_NEIGH]) { + int broadcast_neigh = nla_get_u8(data[IFLA_BOND_BROADCAST_NEIGH]); + + bond_opt_initval(&newval, broadcast_neigh); + err = __bond_opt_set(bond, BOND_OPT_BROADCAST_NEIGH, &newval, + data[IFLA_BOND_BROADCAST_NEIGH], extack); + if (err) + return err; + } + return 0; } @@ -568,20 +593,22 @@ static int bond_newlink(struct net_device *bond_dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct bonding *bond = netdev_priv(bond_dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; - err = bond_changelink(bond_dev, tb, data, extack); - if (err < 0) + err = register_netdevice(bond_dev); + if (err) return err; - err = register_netdevice(bond_dev); - if (!err) { - struct bonding *bond = netdev_priv(bond_dev); + netif_carrier_off(bond_dev); + bond_work_init_all(bond); - netif_carrier_off(bond_dev); - bond_work_init_all(bond); + err = bond_changelink(bond_dev, tb, data, extack); + if (err) { + bond_work_cancel_all(bond); + unregister_netdevice(bond_dev); } return err; @@ -630,6 +657,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_BROADCAST_NEIGH */ 0; } @@ -676,7 +704,7 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.peer_notif_delay * bond->params.miimon)) goto nla_put_failure; - if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier)) + if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, 1)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) @@ -793,6 +821,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.coupled_control)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH, + bond->params.broadcast_neighbor)) + goto nla_put_failure; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 91893c29b899..495a87f2ea7c 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -79,6 +79,8 @@ static int bond_option_tlb_dynamic_lb_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_actor_sys_prio_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_actor_port_prio_set(struct bonding *bond, + const struct bond_opt_value *newval); static int bond_option_ad_actor_system_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_user_port_key_set(struct bonding *bond, @@ -87,6 +89,8 @@ static int bond_option_missed_max_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_coupled_control_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_broadcast_neigh_set(struct bonding *bond, + const struct bond_opt_value *newval); static const struct bond_opt_value bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT}, @@ -158,10 +162,11 @@ static const struct bond_opt_value bond_lacp_rate_tbl[] = { }; static const struct bond_opt_value bond_ad_select_tbl[] = { - { "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT}, - { "bandwidth", BOND_AD_BANDWIDTH, 0}, - { "count", BOND_AD_COUNT, 0}, - { NULL, -1, 0}, + { "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT}, + { "bandwidth", BOND_AD_BANDWIDTH, 0}, + { "count", BOND_AD_COUNT, 0}, + { "actor_port_prio", BOND_AD_PRIO, 0}, + { NULL, -1, 0}, }; static const struct bond_opt_value bond_num_peer_notif_tbl[] = { @@ -185,7 +190,6 @@ static const struct bond_opt_value bond_primary_reselect_tbl[] = { }; static const struct bond_opt_value bond_use_carrier_tbl[] = { - { "off", 0, 0}, { "on", 1, BOND_VALFLAG_DEFAULT}, { NULL, -1, 0} }; @@ -221,6 +225,13 @@ static const struct bond_opt_value bond_ad_actor_sys_prio_tbl[] = { { NULL, -1, 0}, }; +static const struct bond_opt_value bond_actor_port_prio_tbl[] = { + { "minval", 0, BOND_VALFLAG_MIN}, + { "maxval", 65535, BOND_VALFLAG_MAX}, + { "default", 255, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0}, +}; + static const struct bond_opt_value bond_ad_user_port_key_tbl[] = { { "minval", 0, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT}, { "maxval", 1023, BOND_VALFLAG_MAX}, @@ -240,6 +251,12 @@ static const struct bond_opt_value bond_coupled_control_tbl[] = { { NULL, -1, 0}, }; +static const struct bond_opt_value bond_broadcast_neigh_tbl[] = { + { "off", 0, BOND_VALFLAG_DEFAULT}, + { "on", 1, 0}, + { NULL, -1, 0} +}; + static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_MODE] = { .id = BOND_OPT_MODE, @@ -362,7 +379,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_AD_SELECT] = { .id = BOND_OPT_AD_SELECT, .name = "ad_select", - .desc = "803.ad aggregation selection logic", + .desc = "802.3ad aggregation selection logic", .flags = BOND_OPTFLAG_IFDOWN, .values = bond_ad_select_tbl, .set = bond_option_ad_select_set @@ -411,7 +428,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_USE_CARRIER] = { .id = BOND_OPT_USE_CARRIER, .name = "use_carrier", - .desc = "Use netif_carrier_ok (vs MII ioctls) in miimon", + .desc = "option obsolete, use_carrier cannot be disabled", .values = bond_use_carrier_tbl, .set = bond_option_use_carrier_set }, @@ -476,6 +493,13 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_ad_actor_sys_prio_tbl, .set = bond_option_ad_actor_sys_prio_set, }, + [BOND_OPT_ACTOR_PORT_PRIO] = { + .id = BOND_OPT_ACTOR_PORT_PRIO, + .name = "actor_port_prio", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .values = bond_actor_port_prio_tbl, + .set = bond_option_actor_port_prio_set, + }, [BOND_OPT_AD_ACTOR_SYSTEM] = { .id = BOND_OPT_AD_ACTOR_SYSTEM, .name = "ad_actor_system", @@ -513,6 +537,14 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .flags = BOND_OPTFLAG_IFDOWN, .values = bond_coupled_control_tbl, .set = bond_option_coupled_control_set, + }, + [BOND_OPT_BROADCAST_NEIGH] = { + .id = BOND_OPT_BROADCAST_NEIGH, + .name = "broadcast_neighbor", + .desc = "Broadcast neighbor packets to all active slaves", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .values = bond_broadcast_neigh_tbl, + .set = bond_option_broadcast_neigh_set, } }; @@ -894,6 +926,13 @@ static int bond_option_mode_set(struct bonding *bond, bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; bond->params.mode = newval->value; + /* When changing mode, the bond device is down, we may reduce + * the bond_bcast_neigh_enabled in bond_close() if broadcast_neighbor + * enabled in 8023ad mode. Therefore, only clear broadcast_neighbor + * to 0. + */ + bond->params.broadcast_neighbor = 0; + if (bond->dev->reg_state == NETREG_REGISTERED) { bool update = false; @@ -1068,10 +1107,6 @@ static int bond_option_peer_notif_delay_set(struct bonding *bond, static int bond_option_use_carrier_set(struct bonding *bond, const struct bond_opt_value *newval) { - netdev_dbg(bond->dev, "Setting use_carrier to %llu\n", - newval->value); - bond->params.use_carrier = newval->value; - return 0; } @@ -1637,6 +1672,7 @@ static int bond_option_lacp_active_set(struct bonding *bond, netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n", newval->string, newval->value); bond->params.lacp_active = newval->value; + bond_3ad_update_lacp_active(bond); return 0; } @@ -1793,6 +1829,26 @@ static int bond_option_ad_actor_sys_prio_set(struct bonding *bond, return 0; } +static int bond_option_actor_port_prio_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + struct slave *slave; + + slave = bond_slave_get_rtnl(newval->slave_dev); + if (!slave) { + netdev_dbg(bond->dev, "%s called on NULL slave\n", __func__); + return -ENODEV; + } + + netdev_dbg(newval->slave_dev, "Setting actor_port_prio to %llu\n", + newval->value); + + SLAVE_AD_INFO(slave)->port_priority = newval->value; + bond_3ad_update_ad_actor_settings(bond); + + return 0; +} + static int bond_option_ad_actor_system_set(struct bonding *bond, const struct bond_opt_value *newval) { @@ -1840,3 +1896,22 @@ static int bond_option_coupled_control_set(struct bonding *bond, bond->params.coupled_control = newval->value; return 0; } + +static int bond_option_broadcast_neigh_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + if (bond->params.broadcast_neighbor == newval->value) + return 0; + + bond->params.broadcast_neighbor = newval->value; + if (bond->dev->flags & IFF_UP) { + if (bond->params.broadcast_neighbor) + static_branch_inc(&bond_bcast_neigh_enabled); + else + static_branch_dec(&bond_bcast_neigh_enabled); + } + + netdev_dbg(bond->dev, "Setting broadcast_neighbor to %s (%llu)\n", + newval->string, newval->value); + return 0; +} diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 1e13bb170515..9a75ad3181ab 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -467,14 +467,12 @@ static ssize_t bonding_show_primary_reselect(struct device *d, static DEVICE_ATTR(primary_reselect, 0644, bonding_show_primary_reselect, bonding_sysfs_store_option); -/* Show the use_carrier flag. */ +/* use_carrier is obsolete, but print value for compatibility */ static ssize_t bonding_show_carrier(struct device *d, struct device_attribute *attr, char *buf) { - struct bonding *bond = to_bond(d); - - return sysfs_emit(buf, "%d\n", bond->params.use_carrier); + return sysfs_emit(buf, "1\n"); } static DEVICE_ATTR(use_carrier, 0644, bonding_show_carrier, bonding_sysfs_store_option); |