2 files changed, 148 insertions, 64 deletions

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 8c79bad2a9a5..4f2e6910c623 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	struct bond_vlan_tag *tags;
 
 	if (is_vlan_dev(upper) &&
-	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+	    bond->dev->lower_level == upper->lower_level - 1) {
 		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 21d8fcc83c9c..fcb7c2f7f001 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -41,6 +41,8 @@
 #include <linux/in.h>
 #include <net/ip.h>
 #include <linux/ip.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/slab.h>
@@ -200,6 +202,51 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
+static const struct flow_dissector_key flow_keys_bonding_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_TIPC,
+		.offset = offsetof(struct flow_keys, addrs.tipckey),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_ICMP,
+		.offset = offsetof(struct flow_keys, icmp),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_VLAN,
+		.offset = offsetof(struct flow_keys, vlan),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL,
+		.offset = offsetof(struct flow_keys, tags),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+		.offset = offsetof(struct flow_keys, keyid),
+	},
+};
+
+static struct flow_dissector flow_keys_bonding __read_mostly;
+
 /*-------------------------- Forward declarations ---------------------------*/
 
 static int bond_init(struct net_device *bond_dev);
@@ -1733,8 +1780,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
-	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
-
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1816,7 +1861,8 @@ err_detach:
 	slave_disable_netpoll(new_slave);
 
 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:
@@ -1956,9 +2002,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
-		bond->nest_level = SINGLE_DEPTH_NESTING;
-	} else {
-		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
@@ -2017,7 +2060,8 @@ 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);
 
@@ -2086,8 +2130,7 @@ 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);
 
@@ -2121,7 +2164,7 @@ 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;
 			}
@@ -2158,7 +2201,7 @@ 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;
@@ -2196,7 +2239,7 @@ 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
@@ -2268,8 +2311,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
-				  slave->new_link);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				  slave->link_new_state);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2677,13 +2720,13 @@ 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
@@ -2708,7 +2751,7 @@ 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)
@@ -2739,8 +2782,8 @@ 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) {
@@ -2763,9 +2806,9 @@ 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.
  */
@@ -2777,12 +2820,12 @@ 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;
@@ -2810,7 +2853,7 @@ 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++;
 		}
 
@@ -2823,7 +2866,7 @@ 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++;
 		}
 	}
@@ -2843,7 +2886,7 @@ 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;
 
@@ -2893,8 +2936,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			continue;
 
 		default:
-			slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n",
-				  slave->new_link);
+			slave_err(bond->dev, slave->dev,
+				  "impossible: link_new_state %d on slave\n",
+				  slave->link_new_state);
 			continue;
 		}
 
@@ -3255,39 +3299,78 @@ static inline u32 bond_eth_hash(struct sk_buff *skb)
 	return 0;
 }
 
-/* Extract the appropriate headers based on bond's xmit policy */
-static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
-			      struct flow_keys *fk)
+static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk,
+			 int *noff, int *proto, bool l34)
 {
 	const struct ipv6hdr *iph6;
 	const struct iphdr *iph;
-	int noff, proto = -1;
-
-	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
-		return skb_flow_dissect_flow_keys(skb, fk, 0);
 
-	fk->ports.ports = 0;
-	noff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP)) {
-		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph))))
 			return false;
-		iph = ip_hdr(skb);
+		iph = (const struct iphdr *)(skb->data + *noff);
 		iph_to_flow_copy_v4addrs(fk, iph);
-		noff += iph->ihl << 2;
+		*noff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
-			proto = iph->protocol;
+			*proto = iph->protocol;
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
+		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6))))
 			return false;
-		iph6 = ipv6_hdr(skb);
+		iph6 = (const struct ipv6hdr *)(skb->data + *noff);
 		iph_to_flow_copy_v6addrs(fk, iph6);
-		noff += sizeof(*iph6);
-		proto = iph6->nexthdr;
+		*noff += sizeof(*iph6);
+		*proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
-	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
-		fk->ports.ports = skb_flow_get_ports(skb, noff, proto);
+
+	if (l34 && *proto >= 0)
+		fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto);
+
+	return true;
+}
+
+/* Extract the appropriate headers based on bond's xmit policy */
+static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
+			      struct flow_keys *fk)
+{
+	bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
+	int noff, proto = -1;
+
+	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) {
+		memset(fk, 0, sizeof(*fk));
+		return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
+					  fk, NULL, 0, 0, 0, 0);
+	}
+
+	fk->ports.ports = 0;
+	memset(&fk->icmp, 0, sizeof(fk->icmp));
+	noff = skb_network_offset(skb);
+	if (!bond_flow_ip(skb, fk, &noff, &proto, l34))
+		return false;
+
+	/* ICMP error packets contains at least 8 bytes of the header
+	 * of the packet which generated the error. Use this information
+	 * to correlate ICMP error packets within the same flow which
+	 * generated the error.
+	 */
+	if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) {
+		skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data,
+				      skb_transport_offset(skb),
+				      skb_headlen(skb));
+		if (proto == IPPROTO_ICMP) {
+			if (!icmp_is_err(fk->icmp.type))
+				return true;
+
+			noff += sizeof(struct icmphdr);
+		} else if (proto == IPPROTO_ICMPV6) {
+			if (!icmpv6_is_err(fk->icmp.type))
+				return true;
+
+			noff += sizeof(struct icmp6hdr);
+		}
+		return bond_flow_ip(skb, fk, &noff, &proto, l34);
+	}
 
 	return true;
 }
@@ -3314,10 +3397,14 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 		return bond_eth_hash(skb);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
-	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
+	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
 		hash = bond_eth_hash(skb);
-	else
-		hash = (__force u32)flow.ports.ports;
+	} else {
+		if (flow.icmp.id)
+			memcpy(&hash, &flow.icmp, sizeof(hash));
+		else
+			memcpy(&hash, &flow.ports.ports, sizeof(hash));
+	}
 	hash ^= (__force u32)flow_get_u32_dst(&flow) ^
 		(__force u32)flow_get_u32_src(&flow);
 	hash ^= (hash >> 16);
@@ -3442,13 +3529,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
-static int bond_get_nest_level(struct net_device *bond_dev)
-{
-	struct bonding *bond = netdev_priv(bond_dev);
-
-	return bond->nest_level;
-}
-
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3457,7 +3537,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4268,7 +4348,6 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
-	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4296,7 +4375,6 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
-	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
@@ -4365,6 +4443,7 @@ static void bond_uninit(struct net_device *bond_dev)
 
 	list_del(&bond->bond_list);
 
+	lockdep_unregister_key(&bond->stats_lock_key);
 	bond_debug_unregister(bond);
 }
 
@@ -4768,8 +4847,9 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
-	bond->nest_level = SINGLE_DEPTH_NESTING;
-	netdev_lockdep_set_classes(bond_dev);
+	spin_lock_init(&bond->stats_lock);
+	lockdep_register_key(&bond->stats_lock_key);
+	lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
@@ -4901,6 +4981,10 @@ static int __init bonding_init(void)
 			goto err;
 	}
 
+	skb_flow_dissector_init(&flow_keys_bonding,
+				flow_keys_bonding_keys,
+				ARRAY_SIZE(flow_keys_bonding_keys));
+
 	register_netdevice_notifier(&bond_netdev_notifier);
 out:
 	return res;