bonding: Add "follow" option to fail_over_mac

	Add a "follow" selection for fail_over_mac.  This option
causes the MAC address to move from slave to slave as the active
slave changes.  This is in addition to the existing fail_over_mac option
that causes the bond's MAC address to change during failover.

	This new option is useful for devices that cannot tolerate
multiple ports using the same MAC address simultaneously, either
because it confuses them or incurs a performance penalty (as is the
case with some LPAR-aware multiport devices).  Because the MAC of the
bond itself does not change, the "follow" option is slightly more
reliable during failover and doesn't change the MAC of the bond during
operation.

	This patch requires a previous ARP monitor change to properly
handle RTNL during failovers.
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

Documentation/networking/bonding.txt

@@ -289,35 +289,73 @@ downdelay
 fail_over_mac
 
 	Specifies whether active-backup mode should set all slaves to
-	the same MAC address (the traditional behavior), or, when
-	enabled, change the bond's MAC address when changing the
-	active interface (i.e., fail over the MAC address itself).
-
-	Fail over MAC is useful for devices that cannot ever alter
-	their MAC address, or for devices that refuse incoming
-	broadcasts with their own source MAC (which interferes with
-	the ARP monitor).
-
-	The down side of fail over MAC is that every device on the
-	network must be updated via gratuitous ARP, vs. just updating
-	a switch or set of switches (which often takes place for any
-	traffic, not just ARP traffic, if the switch snoops incoming
-	traffic to update its tables) for the traditional method.  If
-	the gratuitous ARP is lost, communication may be disrupted.
-
-	When fail over MAC is used in conjuction with the mii monitor,
-	devices which assert link up prior to being able to actually
-	transmit and receive are particularly susecptible to loss of
-	the gratuitous ARP, and an appropriate updelay setting may be
-	required.
-
-	A value of 0 disables fail over MAC, and is the default.  A
-	value of 1 enables fail over MAC.  This option is enabled
-	automatically if the first slave added cannot change its MAC
-	address.  This option may be modified via sysfs only when no
-	slaves are present in the bond.
-
-	This option was added in bonding version 3.2.0.
+	the same MAC address at enslavement (the traditional
+	behavior), or, when enabled, perform special handling of the
+	bond's MAC address in accordance with the selected policy.
+
+	Possible values are:
+
+	none or 0
+
+		This setting disables fail_over_mac, and causes
+		bonding to set all slaves of an active-backup bond to
+		the same MAC address at enslavement time.  This is the
+		default.
+
+	active or 1
+
+		The "active" fail_over_mac policy indicates that the
+		MAC address of the bond should always be the MAC
+		address of the currently active slave.  The MAC
+		address of the slaves is not changed; instead, the MAC
+		address of the bond changes during a failover.
+
+		This policy is useful for devices that cannot ever
+		alter their MAC address, or for devices that refuse
+		incoming broadcasts with their own source MAC (which
+		interferes with the ARP monitor).
+
+		The down side of this policy is that every device on
+		the network must be updated via gratuitous ARP,
+		vs. just updating a switch or set of switches (which
+		often takes place for any traffic, not just ARP
+		traffic, if the switch snoops incoming traffic to
+		update its tables) for the traditional method.  If the
+		gratuitous ARP is lost, communication may be
+		disrupted.
+
+		When this policy is used in conjuction with the mii
+		monitor, devices which assert link up prior to being
+		able to actually transmit and receive are particularly
+		susecptible to loss of the gratuitous ARP, and an
+		appropriate updelay setting may be required.
+
+	follow or 2
+
+		The "follow" fail_over_mac policy causes the MAC
+		address of the bond to be selected normally (normally
+		the MAC address of the first slave added to the bond).
+		However, the second and subsequent slaves are not set
+		to this MAC address while they are in a backup role; a
+		slave is programmed with the bond's MAC address at
+		failover time (and the formerly active slave receives
+		the newly active slave's MAC address).
+
+		This policy is useful for multiport devices that
+		either become confused or incur a performance penalty
+		when multiple ports are programmed with the same MAC
+		address.
+
+
+	The default policy is none, unless the first slave cannot
+	change its MAC address, in which case the active policy is
+	selected by default.
+
+	This option may be modified via sysfs only when no slaves are
+	present in the bond.
+
+	This option was added in bonding version 3.2.0.  The "follow"
+	policy was added in bonding version 3.3.0.
 
 lacp_rate
 

drivers/net/bonding/bond_sysfs.c

@@ -50,6 +50,7 @@ extern struct bond_parm_tbl bond_mode_tbl[];
 extern struct bond_parm_tbl bond_lacp_tbl[];
 extern struct bond_parm_tbl xmit_hashtype_tbl[];
 extern struct bond_parm_tbl arp_validate_tbl[];
+extern struct bond_parm_tbl fail_over_mac_tbl[];
 
 static int expected_refcount = -1;
 static struct class *netdev_class;
@@ -547,42 +548,37 @@ static ssize_t bonding_show_fail_over_mac(struct device *d, struct device_attrib
 {
 	struct bonding *bond = to_bond(d);
 
-	return sprintf(buf, "%d\n", bond->params.fail_over_mac) + 1;
+	return sprintf(buf, "%s %d\n",
+		       fail_over_mac_tbl[bond->params.fail_over_mac].modename,
+		       bond->params.fail_over_mac);
 }
 
 static ssize_t bonding_store_fail_over_mac(struct device *d, struct device_attribute *attr, const char *buf, size_t count)
 {
 	int new_value;
-	int ret = count;
 	struct bonding *bond = to_bond(d);
 
 	if (bond->slave_cnt != 0) {
 		printk(KERN_ERR DRV_NAME
 		       ": %s: Can't alter fail_over_mac with slaves in bond.\n",
 		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
+		return -EPERM;
 	}
 
-	if (sscanf(buf, "%d", &new_value) != 1) {
+	new_value = bond_parse_parm(buf, fail_over_mac_tbl);
+	if (new_value < 0) {
 		printk(KERN_ERR DRV_NAME
-		       ": %s: no fail_over_mac value specified.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		       ": %s: Ignoring invalid fail_over_mac value %s.\n",
+		       bond->dev->name, buf);
+		return -EINVAL;
 	}
 
-	if ((new_value == 0) || (new_value == 1)) {
 	bond->params.fail_over_mac = new_value;
-		printk(KERN_INFO DRV_NAME ": %s: Setting fail_over_mac to %d.\n",
-		       bond->dev->name, new_value);
-	} else {
-		printk(KERN_INFO DRV_NAME
-		       ": %s: Ignoring invalid fail_over_mac value %d.\n",
-		       bond->dev->name, new_value);
-	}
-out:
-	return ret;
+	printk(KERN_INFO DRV_NAME ": %s: Setting fail_over_mac to %s (%d).\n",
+	       bond->dev->name, fail_over_mac_tbl[new_value].modename,
+	       new_value);
+
+	return count;
 }
 
 static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR, bonding_show_fail_over_mac, bonding_store_fail_over_mac);

drivers/net/bonding/bonding.h

@@ -248,6 +248,10 @@ static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
 	return (struct bonding *)slave->dev->master->priv;
 }
 
+#define BOND_FOM_NONE			0
+#define BOND_FOM_ACTIVE			1
+#define BOND_FOM_FOLLOW			2
+
 #define BOND_ARP_VALIDATE_NONE		0
 #define BOND_ARP_VALIDATE_ACTIVE	(1 << BOND_STATE_ACTIVE)
 #define BOND_ARP_VALIDATE_BACKUP	(1 << BOND_STATE_BACKUP)