bonding: attempt to better support longer hw addresses

People are using bonding over Infiniband IPoIB connections, and who knows
what else. Infiniband has a hardware address length of 20 octets
(INFINIBAND_ALEN), and the network core defines a MAX_ADDR_LEN of 32.
Various places in the bonding code are currently hard-wired to 6 octets
(ETH_ALEN), such as the 3ad code, which I've left untouched here. Besides,
only alb is currently possible on Infiniband links right now anyway, due
to commit 1533e7731522, so the alb code is where most of the changes are.

One major component of this change is the addition of a bond_hw_addr_copy
function that takes a length argument, instead of using ether_addr_copy
everywhere that hardware addresses need to be copied about. The other
major component of this change is converting the bonding code from using
struct sockaddr for address storage to struct sockaddr_storage, as the
former has an address storage space of only 14, while the latter is 128
minus a few, which is necessary to support bonding over device with up to
MAX_ADDR_LEN octet hardware addresses. Additionally, this probably fixes
up some memory corruption issues with the current code, where it's
possible to write an infiniband hardware address into a sockaddr declared
on the stack.

Lightly tested on a dual mlx4 IPoIB setup, which properly shows a 20-octet
hardware address now:

$ cat /proc/net/bonding/bond0
Ethernet Channel Bonding Driver: v3.7.1 (April 27, 2011)

Bonding Mode: fault-tolerance (active-backup) (fail_over_mac active)
Primary Slave: mlx4_ib0 (primary_reselect always)
Currently Active Slave: mlx4_ib0
MII Status: up
MII Polling Interval (ms): 100
Up Delay (ms): 100
Down Delay (ms): 100

Slave Interface: mlx4_ib0
MII Status: up
Speed: Unknown
Duplex: Unknown
Link Failure Count: 0
Permanent HW addr:
80:00:02:08:fe:80:00:00:00:00:00:00:e4:1d:2d:03:00:1d:67:01
Slave queue ID: 0

Slave Interface: mlx4_ib1
MII Status: up
Speed: Unknown
Duplex: Unknown
Link Failure Count: 0
Permanent HW addr:
80:00:02:09:fe:80:00:00:00:00:00:01:e4:1d:2d:03:00:1d:67:02
Slave queue ID: 0

Also tested with a standard 1Gbps NIC bonding setup (with a mix of
e1000 and e1000e cards), running LNST's bonding tests.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 42 insertions, 31 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 535388b15cde..aba7352906a5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -645,8 +645,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  struct slave *new_active,
 				  struct slave *old_active)
 {
-	u8 tmp_mac[ETH_ALEN];
-	struct sockaddr saddr;
+	u8 tmp_mac[MAX_ADDR_LEN];
+	struct sockaddr_storage ss;
 	int rv;
 
 	switch (bond->params.fail_over_mac) {
@@ -666,16 +666,20 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			old_active = bond_get_old_active(bond, new_active);
 
 		if (old_active) {
-			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
-			ether_addr_copy(saddr.sa_data,
-					old_active->dev->dev_addr);
-			saddr.sa_family = new_active->dev->type;
+			bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+					  new_active->dev->addr_len);
+			bond_hw_addr_copy(ss.__data,
+					  old_active->dev->dev_addr,
+					  old_active->dev->addr_len);
+			ss.ss_family = new_active->dev->type;
 		} else {
-			ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
-			saddr.sa_family = bond->dev->type;
+			bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+					  bond->dev->addr_len);
+			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev, &saddr);
+		rv = dev_set_mac_address(new_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv) {
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -685,10 +689,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!old_active)
 			goto out;
 
-		ether_addr_copy(saddr.sa_data, tmp_mac);
-		saddr.sa_family = old_active->dev->type;
+		bond_hw_addr_copy(ss.__data, tmp_mac,
+				  new_active->dev->addr_len);
+		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev, &saddr);
+		rv = dev_set_mac_address(old_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv)
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -1184,7 +1190,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 			kfree_skb(skb);
 			return RX_HANDLER_CONSUMED;
 		}
-		ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
+		bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
+				  bond->dev->addr_len);
 	}
 
 	return ret;
@@ -1323,7 +1330,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct slave *new_slave = NULL, *prev_slave;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int link_reporting;
 	int res = 0, i;
 
@@ -1474,16 +1481,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * that need it, and for restoring it upon release, and then
 	 * set it to the master's address
 	 */
-	ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
+	bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
+			  slave_dev->addr_len);
 
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
 		 */
-		memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-		addr.sa_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, &addr);
+		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);
 		if (res) {
 			netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
 			goto err_restore_mtu;
@@ -1767,9 +1775,10 @@ err_restore_mac:
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
 		 */
-		ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		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);
 	}
 
 err_restore_mtu:
@@ -1812,7 +1821,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int old_flags = bond_dev->flags;
 	netdev_features_t old_features = bond_dev->features;
 
@@ -1947,9 +1956,10 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
-		ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		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);
 	}
 
 	dev_set_mtu(slave_dev, slave->original_mtu);
@@ -3626,7 +3636,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *rollback_slave;
-	struct sockaddr *sa = addr, tmp_sa;
+	struct sockaddr_storage *ss = addr, tmp_ss;
 	struct list_head *iter;
 	int res = 0;
 
@@ -3643,7 +3653,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	    BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	bond_for_each_slave(bond, slave, iter) {
@@ -3662,12 +3672,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	}
 
 	/* success */
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 	return 0;
 
 unwind:
-	memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-	tmp_sa.sa_family = bond_dev->type;
+	memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+	tmp_ss.ss_family = bond_dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
@@ -3676,7 +3686,8 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa);
+		tmp_res = dev_set_mac_address(rollback_slave->dev,
+					      (struct sockaddr *)&tmp_ss);
 		if (tmp_res) {
 			netdev_dbg(bond_dev, "unwind err %d dev %s\n",
 				   tmp_res, rollback_slave->dev->name);