1 files changed, 80 insertions, 65 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 65c5a65af0ba..fef599eb822b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1108,7 +1108,9 @@ static void bond_compute_features(struct bonding *bond)
 
 done:
 	bond_dev->vlan_features = vlan_features;
-	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL;
+	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_HW_VLAN_STAG_TX;
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
 
@@ -1177,29 +1179,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
-	/* Link-local multicast packets should be passed to the
-	 * stack on the link they arrive as well as pass them to the
-	 * bond-master device. These packets are mostly usable when
-	 * stack receives it with the link on which they arrive
-	 * (e.g. LLDP) they also must be available on master. Some of
-	 * the use cases include (but are not limited to): LLDP agents
-	 * that must be able to operate both on enslaved interfaces as
-	 * well as on bonds themselves; linux bridges that must be able
-	 * to process/pass BPDUs from attached bonds when any kind of
-	 * STP version is enabled on the network.
+	/*
+	 * For packets determined by bond_should_deliver_exact_match() call to
+	 * be suppressed we want to make an exception for link-local packets.
+	 * This is necessary for e.g. LLDP daemons to be able to monitor
+	 * inactive slave links without being forced to bind to them
+	 * explicitly.
+	 *
+	 * At the same time, packets that are passed to the bonding master
+	 * (including link-local ones) can have their originating interface
+	 * determined via PACKET_ORIGDEV socket option.
 	 */
-	if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
-
-		if (nskb) {
-			nskb->dev = bond->dev;
-			nskb->queue_mapping = 0;
-			netif_rx(nskb);
-		}
-		return RX_HANDLER_PASS;
-	}
-	if (bond_should_deliver_exact_match(skb, slave, bond))
+	if (bond_should_deliver_exact_match(skb, slave, bond)) {
+		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+			return RX_HANDLER_PASS;
 		return RX_HANDLER_EXACT;
+	}
 
 	skb->dev = bond->dev;
 
@@ -1784,7 +1779,8 @@ err_hwaddr_unsync:
 		bond_hw_addr_flush(bond_dev, slave_dev);
 
 err_close:
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
 
 err_restore_mac:
@@ -1990,7 +1986,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	else
 		dev_set_mtu(slave_dev, slave->original_mtu);
 
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 
 	bond_free_slave(slave);
 
@@ -2060,8 +2057,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 	ignore_updelay = !rcu_dereference(bond->curr_active_slave);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
-		slave->link_new_state = slave->link;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
 
@@ -2097,7 +2093,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			}
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				commit++;
 				continue;
 			}
@@ -2136,7 +2132,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				slave->delay = 0;
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 				ignore_updelay = false;
 				continue;
@@ -2156,8 +2152,17 @@ static void bond_miimon_commit(struct bonding *bond)
 	struct slave *slave, *primary;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
+			/* For 802.3ad mode, check current slave speed and
+			 * duplex again in case its port was disabled after
+			 * invalid speed/duplex reporting but recovered before
+			 * link monitoring could make a decision on the actual
+			 * link status
+			 */
+			if (BOND_MODE(bond) == BOND_MODE_8023AD &&
+			    slave->link == BOND_LINK_UP)
+				bond_3ad_adapter_speed_duplex_changed(slave);
 			continue;
 
 		case BOND_LINK_UP:
@@ -2181,9 +2186,6 @@ static void bond_miimon_commit(struct bonding *bond)
 			} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 				/* make it immediately active */
 				bond_set_active_slave(slave);
-			} else if (slave != primary) {
-				/* prevent it from being the active one */
-				bond_set_backup_slave(slave);
 			}
 
 			netdev_info(bond->dev, "link status definitely up for interface %s, %u Mbps %s duplex\n",
@@ -2240,8 +2242,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			netdev_err(bond->dev, "invalid new link %d on slave %s\n",
-				   slave->new_link, slave->dev->name);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				   slave->link_new_state, slave->dev->name);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2640,13 +2642,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2673,7 +2675,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2705,8 +2707,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			goto re_arm;
 
 		bond_for_each_slave(bond, slave, iter) {
-			if (slave->new_link != BOND_LINK_NOCHANGE)
-				slave->link = slave->new_link;
+			if (slave->link_new_state != BOND_LINK_NOCHANGE)
+				slave->link = slave->link_new_state;
 		}
 
 		if (slave_state_changed) {
@@ -2729,9 +2731,9 @@ re_arm:
 }
 
 /* Called to inspect slaves for active-backup mode ARP monitor link state
- * changes.  Sets new_link in slaves to specify what action should take
- * place for the slave.  Returns 0 if no changes are found, >0 if changes
- * to link states must be committed.
+ * changes.  Sets proposed link state in slaves to specify what action
+ * should take place for the slave.  Returns 0 if no changes are found, >0
+ * if changes to link states must be committed.
  *
  * Called with rcu_read_lock held.
  */
@@ -2743,12 +2745,12 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 	int commit = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, last_rx, 1)) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 			}
 			continue;
@@ -2776,7 +2778,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (!bond_is_active_slave(slave) &&
 		    !rcu_access_pointer(bond->current_arp_slave) &&
 		    !bond_time_in_interval(bond, last_rx, 3)) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 
@@ -2789,7 +2791,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (bond_is_active_slave(slave) &&
 		    (!bond_time_in_interval(bond, trans_start, 2) ||
 		     !bond_time_in_interval(bond, last_rx, 2))) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 	}
@@ -2809,7 +2811,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
@@ -2862,7 +2864,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 		default:
 			netdev_err(bond->dev, "impossible: new_link %d on slave %s\n",
-				   slave->new_link, slave->dev->name);
+				   slave->link_new_state, slave->dev->name);
 			continue;
 		}
 
@@ -3176,8 +3178,12 @@ static int bond_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	if (event_dev->flags & IFF_MASTER) {
+		int ret;
+
 		netdev_dbg(event_dev, "IFF_MASTER\n");
-		return bond_master_netdev_event(event, event_dev);
+		ret = bond_master_netdev_event(event, event_dev);
+		if (ret != NOTIFY_DONE)
+			return ret;
 	}
 
 	if (event_dev->flags & IFF_SLAVE) {
@@ -3820,8 +3826,8 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond)
 static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct iphdr *iph = ip_hdr(skb);
 	struct slave *slave;
+	int slave_cnt;
 	u32 slave_id;
 
 	/* Start with the curr_active_slave that joined the bond as the
@@ -3830,23 +3836,32 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
 	 * send the join/membership reports.  The curr_active_slave found
 	 * will send all of this type of traffic.
 	 */
-	if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
-		slave = rcu_dereference(bond->curr_active_slave);
-		if (slave)
-			bond_dev_queue_xmit(bond, skb, slave->dev);
-		else
-			bond_xmit_slave_id(bond, skb, 0);
-	} else {
-		int slave_cnt = ACCESS_ONCE(bond->slave_cnt);
+	if (skb->protocol == htons(ETH_P_IP)) {
+		int noff = skb_network_offset(skb);
+		struct iphdr *iph;
 
-		if (likely(slave_cnt)) {
-			slave_id = bond_rr_gen_slave_id(bond);
-			bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
-		} else {
-			bond_tx_drop(bond_dev, skb);
+		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+			goto non_igmp;
+
+		iph = ip_hdr(skb);
+		if (iph->protocol == IPPROTO_IGMP) {
+			slave = rcu_dereference(bond->curr_active_slave);
+			if (slave)
+				bond_dev_queue_xmit(bond, skb, slave->dev);
+			else
+				bond_xmit_slave_id(bond, skb, 0);
+			return NETDEV_TX_OK;
 		}
 	}
 
+non_igmp:
+	slave_cnt = ACCESS_ONCE(bond->slave_cnt);
+	if (likely(slave_cnt)) {
+		slave_id = bond_rr_gen_slave_id(bond);
+		bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+	} else {
+		bond_tx_drop(bond_dev, skb);
+	}
 	return NETDEV_TX_OK;
 }
 
@@ -3975,7 +3990,7 @@ out:
 		 * this to-be-skipped slave to send a packet out.
 		 */
 		old_arr = rtnl_dereference(bond->slave_arr);
-		for (idx = 0; idx < old_arr->count; idx++) {
+		for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) {
 			if (skipslave == old_arr->arr[idx]) {
 				old_arr->arr[idx] =
 				    old_arr->arr[old_arr->count-1];
@@ -4266,12 +4281,12 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->features |= NETIF_F_NETNS_LOCAL;
 
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
-				NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
 	bond_dev->features |= bond_dev->hw_features;
+	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX;
 }
 
 /* Destroy a bonding device.