1 files changed, 115 insertions, 48 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 9e0f8a7ef8b1..b7f1a9919033 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev);
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -830,7 +832,8 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			}
 
 			new_active->delay = 0;
-			bond_set_slave_link_state(new_active, BOND_LINK_UP);
+			bond_set_slave_link_state(new_active, BOND_LINK_UP,
+						  BOND_SLAVE_NOTIFY_NOW);
 
 			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
@@ -1066,12 +1069,12 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	return features;
 }
 
-#define BOND_VLAN_FEATURES	(NETIF_F_ALL_CSUM | NETIF_F_SG | \
+#define BOND_VLAN_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
 				 NETIF_F_HIGHDMA | NETIF_F_LRO)
 
-#define BOND_ENC_FEATURES	(NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\
-				 NETIF_F_ALL_TSO)
+#define BOND_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
+				 NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
 
 static void bond_compute_features(struct bonding *bond)
 {
@@ -1198,26 +1201,42 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 	return ret;
 }
 
-static int bond_master_upper_dev_link(struct net_device *bond_dev,
-				      struct net_device *slave_dev,
-				      struct slave *slave)
+static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
 {
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+		return NETDEV_LAG_TX_TYPE_ROUNDROBIN;
+	case BOND_MODE_ACTIVEBACKUP:
+		return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP;
+	case BOND_MODE_BROADCAST:
+		return NETDEV_LAG_TX_TYPE_BROADCAST;
+	case BOND_MODE_XOR:
+	case BOND_MODE_8023AD:
+		return NETDEV_LAG_TX_TYPE_HASH;
+	default:
+		return NETDEV_LAG_TX_TYPE_UNKNOWN;
+	}
+}
+
+static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave)
+{
+	struct netdev_lag_upper_info lag_upper_info;
 	int err;
 
-	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
+	lag_upper_info.tx_type = bond_lag_tx_type(bond);
+	err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
+					   &lag_upper_info);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
+	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
 
-static void bond_upper_dev_unlink(struct net_device *bond_dev,
-				  struct net_device *slave_dev)
+static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave)
 {
-	netdev_upper_dev_unlink(slave_dev, bond_dev);
-	slave_dev->flags &= ~IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
+	netdev_upper_dev_unlink(slave->dev, bond->dev);
+	slave->dev->flags &= ~IFF_SLAVE;
+	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
 }
 
 static struct slave *bond_alloc_slave(struct bonding *bond)
@@ -1299,6 +1318,16 @@ void bond_queue_slave_event(struct slave *slave)
 	queue_delayed_work(slave->bond->wq, &nnw->work, 0);
 }
 
+void bond_lower_state_changed(struct slave *slave)
+{
+	struct netdev_lag_lower_state_info info;
+
+	info.link_up = slave->link == BOND_LINK_UP ||
+		       slave->link == BOND_LINK_FAIL;
+	info.tx_enabled = bond_is_active_slave(slave);
+	netdev_lower_state_changed(slave->dev, &info);
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {
@@ -1351,7 +1380,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * the current ifenslave will set the interface down prior to
 	 * enslaving it; the old ifenslave will not.
 	 */
-	if ((slave_dev->flags & IFF_UP)) {
+	if (slave_dev->flags & IFF_UP) {
 		netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n",
 			   slave_dev->name);
 		res = -EPERM;
@@ -1465,6 +1494,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
+	/* set slave flag before open to prevent IPv6 addrconf */
+	slave_dev->flags |= IFF_SLAVE;
+
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
@@ -1563,21 +1595,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
 				bond_set_slave_link_state(new_slave,
-							  BOND_LINK_BACK);
+							  BOND_LINK_BACK,
+							  BOND_SLAVE_NOTIFY_NOW);
 				new_slave->delay = bond->params.updelay;
 			} else {
 				bond_set_slave_link_state(new_slave,
-							  BOND_LINK_UP);
+							  BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_NOW);
 			}
 		} else {
-			bond_set_slave_link_state(new_slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(new_slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 		}
 	} else if (bond->params.arp_interval) {
 		bond_set_slave_link_state(new_slave,
 					  (netif_carrier_ok(slave_dev) ?
-					  BOND_LINK_UP : BOND_LINK_DOWN));
+					  BOND_LINK_UP : BOND_LINK_DOWN),
+					  BOND_SLAVE_NOTIFY_NOW);
 	} else {
-		bond_set_slave_link_state(new_slave, BOND_LINK_UP);
+		bond_set_slave_link_state(new_slave, BOND_LINK_UP,
+					  BOND_SLAVE_NOTIFY_NOW);
 	}
 
 	if (new_slave->link != BOND_LINK_DOWN)
@@ -1662,7 +1699,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_detach;
 	}
 
-	res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave);
+	res = bond_master_upper_dev_link(bond, new_slave);
 	if (res) {
 		netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
 		goto err_unregister;
@@ -1698,7 +1735,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 /* Undo stages on error */
 err_upper_unlink:
-	bond_upper_dev_unlink(bond_dev, slave_dev);
+	bond_upper_dev_unlink(bond, new_slave);
 
 err_unregister:
 	netdev_rx_handler_unregister(slave_dev);
@@ -1725,6 +1762,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
+	slave_dev->flags &= ~IFF_SLAVE;
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
@@ -1799,12 +1837,14 @@ static int __bond_release_one(struct net_device *bond_dev,
 		return -EINVAL;
 	}
 
+	bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);
+
 	bond_sysfs_slave_del(slave);
 
 	/* recompute stats just before removing the slave */
 	bond_get_stats(bond->dev, &bond->bond_stats);
 
-	bond_upper_dev_unlink(bond_dev, slave_dev);
+	bond_upper_dev_unlink(bond, slave);
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
 	 */
@@ -1996,7 +2036,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_FAIL);
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_LATER);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2011,7 +2052,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				bond_set_slave_link_state(slave, BOND_LINK_UP);
+				bond_set_slave_link_state(slave, BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_LATER);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
@@ -2033,7 +2075,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_BACK);
+			bond_set_slave_link_state(slave, BOND_LINK_BACK,
+						  BOND_SLAVE_NOTIFY_LATER);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -2047,7 +2090,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_BACK:
 			if (!link_state) {
 				bond_set_slave_link_state(slave,
-							  BOND_LINK_DOWN);
+							  BOND_LINK_DOWN,
+							  BOND_SLAVE_NOTIFY_LATER);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
@@ -2085,7 +2129,9 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			bond_set_slave_link_state(slave, BOND_LINK_UP);
+			bond_update_speed_duplex(slave);
+			bond_set_slave_link_state(slave, BOND_LINK_UP,
+						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
 
 			primary = rtnl_dereference(bond->primary_slave);
@@ -2125,7 +2171,8 @@ static void bond_miimon_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 
 			if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
 			    BOND_MODE(bond) == BOND_MODE_8023AD)
@@ -2415,7 +2462,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2462,26 +2509,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		     &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/* Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
+	 *
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
+	 *
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)
@@ -2708,7 +2770,8 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				struct slave *current_arp_slave;
 
 				current_arp_slave = rtnl_dereference(bond->current_arp_slave);
-				bond_set_slave_link_state(slave, BOND_LINK_UP);
+				bond_set_slave_link_state(slave, BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_NOW);
 				if (current_arp_slave) {
 					bond_set_slave_inactive_flags(
 						current_arp_slave,
@@ -2731,7 +2794,8 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 			bond_set_slave_inactive_flags(slave,
 						      BOND_SLAVE_NOTIFY_NOW);
 
@@ -2810,7 +2874,8 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 		 * up when it is actually down
 		 */
 		if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_LATER);
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
@@ -2830,7 +2895,8 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 	if (!new_slave)
 		goto check_state;
 
-	bond_set_slave_link_state(new_slave, BOND_LINK_BACK);
+	bond_set_slave_link_state(new_slave, BOND_LINK_BACK,
+				  BOND_SLAVE_NOTIFY_LATER);
 	bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
 	bond_arp_send_all(bond, new_slave);
 	new_slave->last_link_up = jiffies;
@@ -2838,7 +2904,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 
 check_state:
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (slave->should_notify) {
+		if (slave->should_notify || slave->should_notify_link) {
 			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
 			break;
 		}
@@ -2893,8 +2959,10 @@ re_arm:
 		if (should_notify_peers)
 			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
 						 bond->dev);
-		if (should_notify_rtnl)
+		if (should_notify_rtnl) {
 			bond_slave_state_notify(bond);
+			bond_slave_link_notify(bond);
+		}
 
 		rtnl_unlock();
 	}
@@ -4135,7 +4203,6 @@ void bond_setup(struct net_device *bond_dev)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM);
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
 	bond_dev->features |= bond_dev->hw_features;
 }