1 files changed, 80 insertions, 64 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 56b560558884..941ec99cd3b6 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 -----------------------------*/
 
@@ -374,22 +376,20 @@ down:
 static void bond_update_speed_duplex(struct slave *slave)
 {
 	struct net_device *slave_dev = slave->dev;
-	struct ethtool_cmd ecmd;
-	u32 slave_speed;
+	struct ethtool_link_ksettings ecmd;
 	int res;
 
 	slave->speed = SPEED_UNKNOWN;
 	slave->duplex = DUPLEX_UNKNOWN;
 
-	res = __ethtool_get_settings(slave_dev, &ecmd);
+	res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
 	if (res < 0)
 		return;
 
-	slave_speed = ethtool_cmd_speed(&ecmd);
-	if (slave_speed == 0 || slave_speed == ((__u32) -1))
+	if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
 		return;
 
-	switch (ecmd.duplex) {
+	switch (ecmd.base.duplex) {
 	case DUPLEX_FULL:
 	case DUPLEX_HALF:
 		break;
@@ -397,8 +397,8 @@ static void bond_update_speed_duplex(struct slave *slave)
 		return;
 	}
 
-	slave->speed = slave_speed;
-	slave->duplex = ecmd.duplex;
+	slave->speed = ecmd.base.speed;
+	slave->duplex = ecmd.base.duplex;
 
 	return;
 }
@@ -618,8 +618,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 static void bond_set_dev_addr(struct net_device *bond_dev,
 			      struct net_device *slave_dev)
 {
-	netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
-		   bond_dev, slave_dev, slave_dev->addr_len);
+	netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n",
+		   bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len);
 	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
 	bond_dev->addr_assign_type = NET_ADDR_STOLEN;
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
@@ -928,11 +928,10 @@ void bond_select_active_slave(struct bonding *bond)
 		if (!rv)
 			return;
 
-		if (netif_carrier_ok(bond->dev)) {
+		if (netif_carrier_ok(bond->dev))
 			netdev_info(bond->dev, "first active interface up!\n");
-		} else {
+		else
 			netdev_info(bond->dev, "now running without any active interface!\n");
-		}
 	}
 }
 
@@ -1178,9 +1177,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
-	if (bond_should_deliver_exact_match(skb, slave, bond)) {
+	if (bond_should_deliver_exact_match(skb, slave, bond))
 		return RX_HANDLER_EXACT;
-	}
 
 	skb->dev = bond->dev;
 
@@ -1241,7 +1239,7 @@ static struct slave *bond_alloc_slave(struct bonding *bond)
 {
 	struct slave *slave = NULL;
 
-	slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
+	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
 	if (!slave)
 		return NULL;
 
@@ -1381,8 +1379,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	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;
-		goto err_undo_flags;
+		return -EPERM;
 	}
 
 	/* set bonding device ether type by slave - bonding netdevices are
@@ -1402,8 +1399,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			res = notifier_to_errno(res);
 			if (res) {
 				netdev_err(bond_dev, "refused to change device type\n");
-				res = -EBUSY;
-				goto err_undo_flags;
+				return -EBUSY;
 			}
 
 			/* Flush unicast and multicast addresses */
@@ -1423,8 +1419,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	} else if (bond_dev->type != slave_dev->type) {
 		netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n",
 			   slave_dev->name, slave_dev->type, bond_dev->type);
-		res = -EINVAL;
-		goto err_undo_flags;
+		return -EINVAL;
 	}
 
 	if (slave_ops->ndo_set_mac_address == NULL) {
@@ -2127,6 +2122,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case 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;
@@ -2459,7 +2455,7 @@ 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);
@@ -2506,26 +2502,41 @@ 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:
+	 *
+	 * (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
 	 *
-	 * 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
+	 * (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)
@@ -3290,6 +3301,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3298,43 +3333,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4148,6 +4163,7 @@ 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 */
@@ -4163,7 +4179,7 @@ void bond_setup(struct net_device *bond_dev)
 	SET_NETDEV_DEVTYPE(bond_dev, &bond_type);
 
 	/* Initialize the device options */
-	bond_dev->flags |= IFF_MASTER|IFF_MULTICAST;
+	bond_dev->flags |= IFF_MASTER;
 	bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE;
 	bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);