diff options
Diffstat (limited to 'drivers/net/bonding')
| -rw-r--r-- | drivers/net/bonding/bond_3ad.c | 91 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.c | 8 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 339 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_netlink.c | 22 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_options.c | 101 |
5 files changed, 388 insertions, 173 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index c6807e473ab7..4edc8e6b6b64 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); @@ -982,6 +982,17 @@ 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 +1307,16 @@ 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 +1395,7 @@ 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 +1410,23 @@ 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 +1435,7 @@ 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 */ @@ -1943,16 +1959,16 @@ 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 +1986,14 @@ 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 +2079,8 @@ 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 +2207,7 @@ 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->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave)->id; @@ -2499,7 +2519,7 @@ 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 +2889,31 @@ 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_alb.c b/drivers/net/bonding/bond_alb.c index 7edf0fd58c34..2d37b07c8215 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1035,7 +1035,7 @@ static int alb_set_slave_mac_addr(struct slave *slave, const u8 addr[], */ memcpy(ss.__data, addr, len); ss.ss_family = dev->type; - if (dev_set_mac_address(dev, (struct sockaddr *)&ss, NULL)) { + if (dev_set_mac_address(dev, &ss, NULL)) { slave_err(slave->bond->dev, dev, "dev_set_mac_address on slave failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n"); return -EOPNOTSUPP; } @@ -1273,8 +1273,7 @@ unwind: break; bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr, rollback_slave->dev->addr_len); - dev_set_mac_address(rollback_slave->dev, - (struct sockaddr *)&ss, NULL); + dev_set_mac_address(rollback_slave->dev, &ss, NULL); dev_addr_set(rollback_slave->dev, tmp_addr); } @@ -1763,8 +1762,7 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave bond->dev->addr_len); ss.ss_family = bond->dev->type; /* we don't care if it can't change its mac, best effort */ - dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss, - NULL); + dev_set_mac_address(new_slave->dev, &ss, NULL); dev_addr_set(new_slave->dev, tmp_addr); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e45bba240cbc..257333c88710 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -90,6 +90,7 @@ #include <net/tls.h> #endif #include <net/ip6_route.h> +#include <net/netdev_lock.h> #include <net/xdp.h> #include "bonding_priv.h" @@ -211,6 +212,8 @@ 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, @@ -322,9 +325,9 @@ static bool bond_sk_check(struct bonding *bond) } } -static bool bond_xdp_check(struct bonding *bond) +bool bond_xdp_check(struct bonding *bond, int mode) { - switch (BOND_MODE(bond)) { + switch (mode) { case BOND_MODE_ROUNDROBIN: case BOND_MODE_ACTIVEBACKUP: return true; @@ -432,9 +435,6 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs) struct bonding *bond; struct slave *slave; - if (!bond_dev) - return NULL; - bond = netdev_priv(bond_dev); if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return NULL; @@ -455,13 +455,14 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs) /** * bond_ipsec_add_sa - program device with a security association + * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ -static int bond_ipsec_add_sa(struct xfrm_state *xs, +static int bond_ipsec_add_sa(struct net_device *bond_dev, + struct xfrm_state *xs, struct netlink_ext_ack *extack) { - struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; @@ -497,9 +498,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs, goto out; } - xs->xso.real_dev = real_dev; - err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack); + err = real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, xs, extack); if (!err) { + xs->xso.real_dev = real_dev; ipsec->xs = xs; INIT_LIST_HEAD(&ipsec->list); mutex_lock(&bond->ipsec_lock); @@ -541,11 +542,25 @@ static void bond_ipsec_add_sa_all(struct bonding *bond) if (ipsec->xs->xso.real_dev == real_dev) continue; - ipsec->xs->xso.real_dev = real_dev; - if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) { + if (real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, + ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); - ipsec->xs->xso.real_dev = NULL; + continue; } + + spin_lock_bh(&ipsec->xs->lock); + /* xs might have been killed by the user during the migration + * to the new dev, but bond_ipsec_del_sa() should have done + * nothing, as xso.real_dev is NULL. + * Delete it from the device we just added it to. The pending + * bond_ipsec_free_sa() call will do the rest of the cleanup. + */ + if (ipsec->xs->km.state == XFRM_STATE_DEAD && + real_dev->xfrmdev_ops->xdo_dev_state_delete) + real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, + ipsec->xs); + ipsec->xs->xso.real_dev = real_dev; + spin_unlock_bh(&ipsec->xs->lock); } out: mutex_unlock(&bond->ipsec_lock); @@ -553,54 +568,27 @@ out: /** * bond_ipsec_del_sa - clear out this specific SA + * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct **/ -static void bond_ipsec_del_sa(struct xfrm_state *xs) +static void bond_ipsec_del_sa(struct net_device *bond_dev, + struct xfrm_state *xs) { - struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; - netdevice_tracker tracker; - struct bond_ipsec *ipsec; - struct bonding *bond; - struct slave *slave; - if (!bond_dev) + if (!bond_dev || !xs->xso.real_dev) return; - rcu_read_lock(); - bond = netdev_priv(bond_dev); - slave = rcu_dereference(bond->curr_active_slave); - real_dev = slave ? slave->dev : NULL; - netdev_hold(real_dev, &tracker, GFP_ATOMIC); - rcu_read_unlock(); - - if (!slave) - goto out; - - if (!xs->xso.real_dev) - goto out; - - WARN_ON(xs->xso.real_dev != real_dev); + real_dev = xs->xso.real_dev; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); - goto out; + return; } - real_dev->xfrmdev_ops->xdo_dev_state_delete(xs); -out: - netdev_put(real_dev, &tracker); - mutex_lock(&bond->ipsec_lock); - list_for_each_entry(ipsec, &bond->ipsec_list, list) { - if (ipsec->xs == xs) { - list_del(&ipsec->list); - kfree(ipsec); - break; - } - } - mutex_unlock(&bond->ipsec_lock); + real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs); } static void bond_ipsec_del_sa_all(struct bonding *bond) @@ -626,46 +614,55 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); - } else { - real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); - if (real_dev->xfrmdev_ops->xdo_dev_state_free) - real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs); + continue; } + + spin_lock_bh(&ipsec->xs->lock); + ipsec->xs->xso.real_dev = NULL; + /* Don't double delete states killed by the user. */ + if (ipsec->xs->km.state != XFRM_STATE_DEAD) + real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, + ipsec->xs); + spin_unlock_bh(&ipsec->xs->lock); + + if (real_dev->xfrmdev_ops->xdo_dev_state_free) + real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, + ipsec->xs); } mutex_unlock(&bond->ipsec_lock); } -static void bond_ipsec_free_sa(struct xfrm_state *xs) +static void bond_ipsec_free_sa(struct net_device *bond_dev, + struct xfrm_state *xs) { - struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; - netdevice_tracker tracker; + struct bond_ipsec *ipsec; struct bonding *bond; - struct slave *slave; if (!bond_dev) return; - rcu_read_lock(); bond = netdev_priv(bond_dev); - slave = rcu_dereference(bond->curr_active_slave); - real_dev = slave ? slave->dev : NULL; - netdev_hold(real_dev, &tracker, GFP_ATOMIC); - rcu_read_unlock(); - - if (!slave) - goto out; + mutex_lock(&bond->ipsec_lock); if (!xs->xso.real_dev) goto out; - WARN_ON(xs->xso.real_dev != real_dev); + real_dev = xs->xso.real_dev; - if (real_dev && real_dev->xfrmdev_ops && + xs->xso.real_dev = NULL; + if (real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) - real_dev->xfrmdev_ops->xdo_dev_state_free(xs); + real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs); out: - netdev_put(real_dev, &tracker); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + if (ipsec->xs == xs) { + list_del(&ipsec->list); + kfree(ipsec); + break; + } + } + mutex_unlock(&bond->ipsec_lock); } /** @@ -676,22 +673,16 @@ out: static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *real_dev; - bool ok = false; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); - if (!real_dev) - goto out; - - if (!real_dev->xfrmdev_ops || - !real_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(real_dev)) - goto out; + if (!real_dev || netif_is_bond_master(real_dev)) { + rcu_read_unlock(); + return false; + } - ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); -out: rcu_read_unlock(); - return ok; + return true; } /** @@ -858,9 +849,9 @@ 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; - int (*ioctl)(struct net_device *, struct ifreq *, int); - struct ifreq ifr; struct mii_ioctl_data *mii; + struct ifreq ifr; + int ret; if (!reporting && !netif_running(slave_dev)) return 0; @@ -869,13 +860,16 @@ static int bond_check_dev_link(struct bonding *bond, return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; /* Try to get link status using Ethtool first. */ - if (slave_dev->ethtool_ops->get_link) - return slave_dev->ethtool_ops->get_link(slave_dev) ? - BMSR_LSTATUS : 0; + 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. */ - ioctl = slave_ops->ndo_eth_ioctl; - if (ioctl) { + 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 @@ -891,9 +885,10 @@ static int bond_check_dev_link(struct bonding *bond, /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); - if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { + + if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; - if (ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) + if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) return mii->val_out & BMSR_LSTATUS; } } @@ -1045,7 +1040,7 @@ 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; @@ -1119,8 +1114,7 @@ static void bond_do_fail_over_mac(struct bonding *bond, ss.ss_family = bond->dev->type; } - rv = dev_set_mac_address(new_active->dev, - (struct sockaddr *)&ss, NULL); + rv = dev_set_mac_address(new_active->dev, &ss, NULL); if (rv) { slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n", -rv); @@ -1134,8 +1128,7 @@ static void bond_do_fail_over_mac(struct bonding *bond, new_active->dev->addr_len); ss.ss_family = old_active->dev->type; - rv = dev_set_mac_address(old_active->dev, - (struct sockaddr *)&ss, NULL); + rv = dev_set_mac_address(old_active->dev, &ss, NULL); if (rv) slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n", -rv); @@ -1244,17 +1237,32 @@ 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; } @@ -1937,7 +1945,7 @@ void bond_xdp_set_features(struct net_device *bond_dev) ASSERT_RTNL(); - if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) { + if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } @@ -2122,15 +2130,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, * set the master's mac address to that of the first slave */ memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); - ss.ss_family = slave_dev->type; - res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, - extack); - if (res) { - slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); - goto err_restore_mtu; - } + } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && + BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + 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. + */ + eth_random_addr(ss.__data); + } else { + goto skip_mac_set; } + ss.ss_family = slave_dev->type; + res = dev_set_mac_address(slave_dev, &ss, extack); + if (res) { + slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); + goto err_restore_mtu; + } + +skip_mac_set: + /* set no_addrconf flag before open to prevent IPv6 addrconf */ slave_dev->priv_flags |= IFF_NO_ADDRCONF; @@ -2451,7 +2470,7 @@ err_restore_mac: bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr, new_slave->dev->addr_len); ss.ss_family = slave_dev->type; - dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); + dev_set_mac_address(slave_dev, &ss, NULL); } err_restore_mtu: @@ -2551,7 +2570,7 @@ static int __bond_release_one(struct net_device *bond_dev, RCU_INIT_POINTER(bond->current_arp_slave, NULL); - if (!all && (!bond->params.fail_over_mac || + if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) @@ -2645,13 +2664,16 @@ static int __bond_release_one(struct net_device *bond_dev, bond_hw_addr_copy(ss.__data, slave->perm_hwaddr, slave->dev->addr_len); ss.ss_family = slave_dev->type; - dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); + dev_set_mac_address(slave_dev, &ss, NULL); } - if (unregister) - __dev_set_mtu(slave_dev, slave->original_mtu); - else + if (unregister) { + netdev_lock_ops(slave_dev); + __netif_set_mtu(slave_dev, slave->original_mtu); + netdev_unlock_ops(slave_dev); + } else { dev_set_mtu(slave_dev, slave->original_mtu); + } if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; @@ -4217,7 +4239,7 @@ static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void * } if (l34 && *ip_proto >= 0) - fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); + fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); return true; } @@ -4451,6 +4473,9 @@ 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)) @@ -4470,6 +4495,10 @@ 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); @@ -4929,8 +4958,7 @@ unwind: if (rollback_slave == slave) break; - tmp_res = dev_set_mac_address(rollback_slave->dev, - (struct sockaddr *)&tmp_ss, NULL); + tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_ss, NULL); if (tmp_res) { slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n", __func__, tmp_res); @@ -5306,6 +5334,37 @@ 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. @@ -5325,17 +5384,27 @@ 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)) @@ -5573,10 +5642,13 @@ 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: @@ -5699,7 +5771,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, ASSERT_RTNL(); - if (!bond_xdp_check(bond)) { + if (!bond_xdp_check(bond, BOND_MODE(bond))) { BOND_NL_ERR(dev, extack, "No native XDP support for the current bonding mode"); return -EOPNOTSUPP; @@ -6028,7 +6100,7 @@ void bond_setup(struct net_device *bond_dev) bond_dev->lltx = true; /* Don't allow bond devices to change network namespaces. */ - bond_dev->netns_local = true; + bond_dev->netns_immutable = true; /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special @@ -6452,6 +6524,7 @@ 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); @@ -6564,7 +6637,7 @@ static int __net_init bond_net_init(struct net *net) /* According to commit 69b0216ac255 ("bonding: fix bonding_masters * race condition in bond unloading") we need to remove sysfs files - * before we remove our devices (done later in bond_net_exit_batch_rtnl()) + * before we remove our devices (done later in bond_net_exit_rtnl()) */ static void __net_exit bond_net_pre_exit(struct net *net) { @@ -6573,25 +6646,20 @@ static void __net_exit bond_net_pre_exit(struct net *net) bond_destroy_sysfs(bn); } -static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list, - struct list_head *dev_kill_list) +static void __net_exit bond_net_exit_rtnl(struct net *net, + struct list_head *dev_kill_list) { - struct bond_net *bn; - struct net *net; + struct bond_net *bn = net_generic(net, bond_net_id); + struct bonding *bond, *tmp_bond; /* Kill off any bonds created after unregistering bond rtnl ops */ - list_for_each_entry(net, net_list, exit_list) { - struct bonding *bond, *tmp_bond; - - bn = net_generic(net, bond_net_id); - list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) - unregister_netdevice_queue(bond->dev, dev_kill_list); - } + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, dev_kill_list); } /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory * only after all bonds are gone") bond_destroy_proc_dir() is called - * after bond_net_exit_batch_rtnl() has completed. + * after bond_net_exit_rtnl() has completed. */ static void __net_exit bond_net_exit_batch(struct list_head *net_list) { @@ -6607,7 +6675,7 @@ static void __net_exit bond_net_exit_batch(struct list_head *net_list) static struct pernet_operations bond_net_ops = { .init = bond_net_init, .pre_exit = bond_net_pre_exit, - .exit_batch_rtnl = bond_net_exit_batch_rtnl, + .exit_rtnl = bond_net_exit_rtnl, .exit_batch = bond_net_exit_batch, .id = &bond_net_id, .size = sizeof(struct bond_net), @@ -6675,3 +6743,4 @@ 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 2a6a424806aa..57fff2421f1b 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -124,6 +124,7 @@ 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] = { @@ -561,13 +562,25 @@ 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; } -static int bond_newlink(struct net *src_net, struct net_device *bond_dev, - struct nlattr *tb[], struct nlattr *data[], +static int bond_newlink(struct net_device *bond_dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; int err; err = bond_changelink(bond_dev, tb, data, extack); @@ -628,6 +641,7 @@ 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; } @@ -791,6 +805,10 @@ 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 327b6ecdc77e..3b6f815c55ff 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -87,6 +87,8 @@ 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}, @@ -240,6 +242,12 @@ 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, @@ -513,6 +521,14 @@ 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, } }; @@ -868,6 +884,9 @@ static bool bond_set_xfrm_features(struct bonding *bond) static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { + if (bond->xdp_prog && !bond_xdp_check(bond, newval->value)) + return -EOPNOTSUPP; + if (!bond_mode_uses_arp(newval->value)) { if (bond->params.arp_interval) { netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", @@ -891,6 +910,13 @@ 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; @@ -1242,10 +1268,28 @@ static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *sla slave->dev->flags & IFF_MULTICAST; } +/** + * slave_set_ns_maddrs - add/del all NS mac addresses for slave + * @bond: bond device + * @slave: slave device + * @add: add or remove all the NS mac addresses + * + * This function tries to add or delete all the NS mac addresses on the slave + * + * Note, the IPv6 NS target address is the unicast address in Neighbor + * Solicitation (NS) message. The dest address of NS message should be + * solicited-node multicast address of the target. The dest mac of NS message + * is converted from the solicited-node multicast address. + * + * This function is called when + * * arp_validate changes + * * enslaving, releasing new slaves + */ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) { struct in6_addr *targets = bond->params.ns_targets; char slot_maddr[MAX_ADDR_LEN]; + struct in6_addr mcaddr; int i; if (!slave_can_set_ns_maddr(bond, slave)) @@ -1255,7 +1299,8 @@ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool if (ipv6_addr_any(&targets[i])) break; - if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) { + addrconf_addr_solict_mult(&targets[i], &mcaddr); + if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) { if (add) dev_mc_add(slave->dev, slot_maddr); else @@ -1278,23 +1323,43 @@ void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) slave_set_ns_maddrs(bond, slave, false); } +/** + * slave_set_ns_maddr - set new NS mac address for slave + * @bond: bond device + * @slave: slave device + * @target: the new IPv6 target + * @slot: the old IPv6 target in the slot + * + * This function tries to replace the old mac address to new one on the slave. + * + * Note, the target/slot IPv6 address is the unicast address in Neighbor + * Solicitation (NS) message. The dest address of NS message should be + * solicited-node multicast address of the target. The dest mac of NS message + * is converted from the solicited-node multicast address. + * + * This function is called when + * * An IPv6 NS target is added or removed. + */ static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave, struct in6_addr *target, struct in6_addr *slot) { - char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN]; + char mac_addr[MAX_ADDR_LEN]; + struct in6_addr mcast_addr; if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave)) return; - /* remove the previous maddr from slave */ + /* remove the previous mac addr from slave */ + addrconf_addr_solict_mult(slot, &mcast_addr); if (!ipv6_addr_any(slot) && - !ndisc_mc_map(slot, slot_maddr, slave->dev, 0)) - dev_mc_del(slave->dev, slot_maddr); + !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0)) + dev_mc_del(slave->dev, mac_addr); - /* add new maddr on slave if target is set */ + /* add new mac addr on slave if target is set */ + addrconf_addr_solict_mult(target, &mcast_addr); if (!ipv6_addr_any(target) && - !ndisc_mc_map(target, target_maddr, slave->dev, 0)) - dev_mc_add(slave->dev, target_maddr); + !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0)) + dev_mc_add(slave->dev, mac_addr); } static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, @@ -1595,6 +1660,7 @@ 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; } @@ -1798,3 +1864,22 @@ 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; +} |