1 files changed, 182 insertions, 107 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 950d8e4d86f8..257333c88710 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -212,6 +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,
@@ -453,13 +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;
@@ -495,9 +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);
@@ -539,11 +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);
@@ -551,54 +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)
@@ -624,46 +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);
 }
 
 /**
@@ -850,8 +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;
-	struct ifreq ifr;
 	struct mii_ioctl_data *mii;
+	struct ifreq ifr;
+	int ret;
 
 	if (!reporting && !netif_running(slave_dev))
 		return 0;
@@ -860,9 +860,13 @@ 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. */
 	if (slave_ops->ndo_eth_ioctl) {
@@ -1036,7 +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;
 
@@ -1110,8 +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);
@@ -1125,8 +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);
@@ -1235,17 +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;
 }
@@ -2113,15 +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;
 
@@ -2442,7 +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:
@@ -2636,12 +2664,12 @@ 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) {
 		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);
@@ -4445,6 +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))
@@ -4464,6 +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);
@@ -4923,8 +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);
@@ -5300,6 +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.
@@ -5319,17 +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))
@@ -5567,10 +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:
@@ -6446,6 +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);
@@ -6558,7 +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)
 {
@@ -6567,25 +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)
 {
@@ -6601,7 +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),
@@ -6669,3 +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");