net/bonding: ADD IPoIB support for the bonding driver

Index: net-2.6/drivers/infiniband/ulp/ipoib/ipoib.h
===================================================================
@@ -328,6 +328,7 @@ struct ipoib_neigh {
 	struct sk_buff_head queue;
 
 	struct neighbour   *neighbour;
+	struct net_device *dev;
 
 	struct list_head    list;
 };

@@ -344,7 +345,8 @@ static inline struct ipoib_neigh **to_ip
 				     INFINIBAND_ALEN, sizeof(void *));
 }
 
-struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neigh);
+struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neigh,
+				      struct net_device *dev);
 void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh);
 
 extern struct workqueue_struct *ipoib_workqueue;

Index: net-2.6/drivers/infiniband/ulp/ipoib/ipoib_main.c
===================================================================
@@ -510,7 +510,7 @@ static void neigh_add_path(struct sk_buf
 	struct ipoib_path *path;
 	struct ipoib_neigh *neigh;
 
-	neigh = ipoib_neigh_alloc(skb->dst->neighbour);
+	neigh = ipoib_neigh_alloc(skb->dst->neighbour, skb->dev);
 	if (!neigh) {
 		++priv->stats.tx_dropped;
 		dev_kfree_skb_any(skb);

@@ -817,6 +817,16 @@ static void ipoib_neigh_cleanup(struct n
 	unsigned long flags;
 	struct ipoib_ah *ah = NULL;
 
+	if (n->dev->flags & IFF_MASTER) {
+		/* n->dev is not an IPoIB device and we have to take priv from elsewhere */
+		neigh = *to_ipoib_neigh(n);
+		if (neigh){
+			priv = netdev_priv(neigh->dev);
+			ipoib_dbg(priv, "neigh_destructor for bonding device: %s\n",
+				  n->dev->name);
+		} else
+			return;
+	}
 	ipoib_dbg(priv,
 		  "neigh_cleanup for %06x " IPOIB_GID_FMT "\n",
 		  IPOIB_QPN(n->ha),

@@ -838,7 +848,9 @@ static void ipoib_neigh_cleanup(struct n
 		ipoib_put_ah(ah);
 }
 
-struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour)
+struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour,
+				      struct net_device *dev)
+
 {
 	struct ipoib_neigh *neigh;
 

@@ -847,6 +859,7 @@ struct ipoib_neigh *ipoib_neigh_alloc(st
 		return NULL;
 
 	neigh->neighbour = neighbour;
+	neigh->dev = dev;
 	*to_ipoib_neigh(neighbour) = neigh;
 	skb_queue_head_init(&neigh->queue);
 	ipoib_cm_set(neigh, NULL);

Index: net-2.6/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
===================================================================
@@ -727,7 +727,7 @@ out:
 		if (skb->dst            &&
 		    skb->dst->neighbour &&
 		    !*to_ipoib_neigh(skb->dst->neighbour)) {
-			struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour);
+			struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour, skb->dev);
 
 			if (neigh) {
 				kref_get(&mcast->ah->ref);

Index: net-2.6/drivers/infiniband/ulp/ipoib/ipoib_main.c
===================================================================
@@ -685,9 +685,10 @@ static int ipoib_start_xmit(struct sk_bu
 				goto out;
 			}
 		} else if (neigh->ah) {
-			if (unlikely(memcmp(&neigh->dgid.raw,
+			if (unlikely((memcmp(&neigh->dgid.raw,
 					    skb->dst->neighbour->ha + 4,
-					    sizeof(union ib_gid)))) {
+					    sizeof(union ib_gid))) ||
+						 (neigh->dev != dev))) {
 				spin_lock(&priv->lock);
 				/*
 				 * It's safe to call ipoib_put_ah() inside

Index: net-2.6/drivers/net/bonding/bond_main.c
===================================================================
@@ -1277,6 +1277,26 @@ static int bond_compute_features(struct 
 	return 0;
 }
 
+
+static void bond_setup_by_slave(struct net_device *bond_dev,
+				struct net_device *slave_dev)
+{
+	bond_dev->hard_header	        = slave_dev->hard_header;
+	bond_dev->rebuild_header        = slave_dev->rebuild_header;
+	bond_dev->hard_header_cache	= slave_dev->hard_header_cache;
+	bond_dev->header_cache_update   = slave_dev->header_cache_update;
+	bond_dev->hard_header_parse	= slave_dev->hard_header_parse;
+
+	bond_dev->neigh_setup           = slave_dev->neigh_setup;
+
+	bond_dev->type		    = slave_dev->type;
+	bond_dev->hard_header_len   = slave_dev->hard_header_len;
+	bond_dev->addr_len	    = slave_dev->addr_len;
+
+	memcpy(bond_dev->broadcast, slave_dev->broadcast,
+		slave_dev->addr_len);
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {

@@ -1351,6 +1371,24 @@ int bond_enslave(struct net_device *bond
 		goto err_undo_flags;
 	}
 
+	/* set bonding device ether type by slave - bonding netdevices are
+	 * created with ether_setup, so when the slave type is not ARPHRD_ETHER
+	 * there is a need to override some of the type dependent attribs/funcs.
+	 *
+	 * bond ether type mutual exclusion - don't allow slaves of dissimilar
+	 * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
+	 */
+	if (bond->slave_cnt == 0) {
+		if (slave_dev->type != ARPHRD_ETHER)
+			bond_setup_by_slave(bond_dev, slave_dev);
+	} else if (bond_dev->type != slave_dev->type) {
+		printk(KERN_ERR DRV_NAME ": %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;
+	}
+
 	if (slave_dev->set_mac_address == NULL) {
 		printk(KERN_ERR DRV_NAME
 			": %s: Error: The slave device you specified does "

Index: net-2.6/drivers/net/bonding/bond_main.c
===================================================================
@@ -1127,6 +1127,14 @@ void bond_change_active_slave(struct bon
 		if (new_active) {
 			bond_set_slave_active_flags(new_active);
 		}
+
+		/* when bonding does not set the slave MAC address, the bond MAC
+		 * address is the one of the active slave.
+		 */
+		if (new_active && !bond->do_set_mac_addr)
+			memcpy(bond->dev->dev_addr,  new_active->dev->dev_addr,
+				new_active->dev->addr_len);
+
 		bond_send_gratuitous_arp(bond);
 	}
 }

@@ -1390,13 +1398,22 @@ int bond_enslave(struct net_device *bond
 	}
 
 	if (slave_dev->set_mac_address == NULL) {
-		printk(KERN_ERR DRV_NAME
-			": %s: Error: The slave device you specified does "
-			"not support setting the MAC address. "
-			"Your kernel likely does not support slave "
-			"devices.\n", bond_dev->name);
-  		res = -EOPNOTSUPP;
-		goto err_undo_flags;
+		if (bond->slave_cnt == 0) {
+			printk(KERN_WARNING DRV_NAME
+				": %s: Warning: The first slave device you "
+				"specified does not support setting the MAC "
+				"address. This bond MAC address would be that "
+				"of the active slave.\n", bond_dev->name);
+			bond->do_set_mac_addr = 0;
+		} else if (bond->do_set_mac_addr) {
+			printk(KERN_ERR DRV_NAME
+				": %s: Error: The slave device you specified "
+				"does not support setting the MAC addres,."
+				"but this bond uses this practice. \n"
+				, bond_dev->name);
+			res = -EOPNOTSUPP;
+			goto err_undo_flags;
+		}
 	}
 
 	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);

@@ -1417,16 +1434,18 @@ int bond_enslave(struct net_device *bond
 	 */
 	memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);
 
-	/*
-	 * 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);
-	if (res) {
-		dprintk("Error %d calling set_mac_address\n", res);
-		goto err_free;
+	if (bond->do_set_mac_addr) {
+		/*
+		 * 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);
+		if (res) {
+			dprintk("Error %d calling set_mac_address\n", res);
+			goto err_free;
+		}
 	}
 
 	res = netdev_set_master(slave_dev, bond_dev);

@@ -1651,9 +1670,11 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
-	memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
-	addr.sa_family = slave_dev->type;
-	dev_set_mac_address(slave_dev, &addr);
+	if (bond->do_set_mac_addr) {
+		memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
+		addr.sa_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, &addr);
+	}
 
 err_free:
 	kfree(new_slave);

@@ -1831,10 +1852,12 @@ int bond_release(struct net_device *bond
 	/* close slave before restoring its mac address */
 	dev_close(slave_dev);
 
-	/* restore original ("permanent") mac address */
-	memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
-	addr.sa_family = slave_dev->type;
-	dev_set_mac_address(slave_dev, &addr);
+	if (bond->do_set_mac_addr) {
+		/* restore original ("permanent") mac address */
+		memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+		addr.sa_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, &addr);
+	}
 
 	slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
 				   IFF_SLAVE_INACTIVE | IFF_BONDING |

@@ -1921,10 +1944,12 @@ static int bond_release_all(struct net_d
 		/* close slave before restoring its mac address */
 		dev_close(slave_dev);
 
-		/* restore original ("permanent") mac address*/
-		memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		if (bond->do_set_mac_addr) {
+			/* restore original ("permanent") mac address*/
+			memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+			addr.sa_family = slave_dev->type;
+			dev_set_mac_address(slave_dev, &addr);
+		}
 
 		slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB |
 					   IFF_SLAVE_INACTIVE);

@@ -3961,6 +3986,10 @@ static int bond_set_mac_address(struct n
 
 	dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None"));
 
+	if (!bond->do_set_mac_addr) {
+		return -EOPNOTSUPP;
+	}
+
 	if (!is_valid_ether_addr(sa->sa_data)) {
 		return -EADDRNOTAVAIL;
 	}

@@ -4351,6 +4380,9 @@ static int bond_init(struct net_device *
 	bond_create_proc_entry(bond);
 #endif
 
+	/* set do_set_mac_addr to true on startup */
+	bond->do_set_mac_addr = 1;
+
 	list_add_tail(&bond->bond_list, &bond_dev_list);
 
 	return 0;

Index: net-2.6/drivers/net/bonding/bonding.h
===================================================================
@@ -201,6 +201,7 @@ struct bonding {
 	struct   list_head vlan_list;
 	struct   vlan_group *vlgrp;
 	struct   packet_type arp_mon_pt;
+	s8       do_set_mac_addr;
 };
 
 /**

Index: net-2.6/drivers/net/bonding/bond_main.c
===================================================================
@@ -1325,8 +1325,8 @@ int bond_enslave(struct net_device *bond
 
 	/* bond must be initialized by bond_open() before enslaving */
 	if (!(bond_dev->flags & IFF_UP)) {
-		dprintk("Error, master_dev is not up\n");
-		return -EPERM;
+		printk(KERN_WARNING DRV_NAME
+			" %s: master_dev is not up in bond_enslave\n", bond_dev->name);
 	}
 
 	/* already enslaved */

Index: net-2.6/drivers/net/bonding/bond_sysfs.c
===================================================================
@@ -266,11 +266,9 @@ static ssize_t bonding_store_slaves(stru
 
 	/* Quick sanity check -- is the bond interface up? */
 	if (!(bond->dev->flags & IFF_UP)) {
-		printk(KERN_ERR DRV_NAME
-		       ": %s: Unable to update slaves because interface is down.\n",
+		printk(KERN_WARNING DRV_NAME
+		       ": %s: doing slave updates when interface is down.\n",
 		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
 	}
 
 	/* Note:  We can't hold bond->lock here, as bond_create grabs it. */

Index: net-2.6/drivers/net/bonding/bond_main.c
===================================================================
@@ -1255,7 +1255,7 @@ static int bond_compute_features(struct 
 	unsigned long features = BOND_INTERSECT_FEATURES;
 	struct slave *slave;
 	struct net_device *bond_dev = bond->dev;
-	unsigned short max_hard_header_len = ETH_HLEN;
+	u16 max_hard_header_len = max((u16)ETH_HLEN, bond_dev->hard_header_len);
 	int i;
 
 	bond_for_each_slave(bond, slave, i) {

Index: net-2.6/drivers/net/bonding/bond_sysfs.c
===================================================================
@@ -260,6 +260,7 @@ static ssize_t bonding_store_slaves(stru
 	char command[IFNAMSIZ + 1] = { 0, };
 	char *ifname;
 	int i, res, found, ret = count;
+	u32 original_mtu;
 	struct slave *slave;
 	struct net_device *dev = NULL;
 	struct bonding *bond = to_bond(d);

@@ -325,6 +326,7 @@ static ssize_t bonding_store_slaves(stru
 		}
 
 		/* Set the slave's MTU to match the bond */
+		original_mtu = dev->mtu;
 		if (dev->mtu != bond->dev->mtu) {
 			if (dev->change_mtu) {
 				res = dev->change_mtu(dev,

@@ -339,6 +341,9 @@ static ssize_t bonding_store_slaves(stru
 		}
 		rtnl_lock();
 		res = bond_enslave(bond->dev, dev);
+		bond_for_each_slave(bond, slave, i)
+			if (strnicmp(slave->dev->name, ifname, IFNAMSIZ) == 0)
+				slave->original_mtu=original_mtu;
 		rtnl_unlock();
 		if (res) {
 			ret = res;

@@ -351,6 +356,7 @@ static ssize_t bonding_store_slaves(stru
 		bond_for_each_slave(bond, slave, i)
 			if (strnicmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
 				dev = slave->dev;
+				original_mtu = slave->original_mtu;
 				break;
 			}
 		if (dev) {

@@ -365,9 +371,9 @@ static ssize_t bonding_store_slaves(stru
 			}
 			/* set the slave MTU to the default */
 			if (dev->change_mtu) {
-				dev->change_mtu(dev, 1500);
+				dev->change_mtu(dev, original_mtu);
 			} else {
-				dev->mtu = 1500;
+				dev->mtu = original_mtu;
 			}
 		}
 		else {

Index: net-2.6/drivers/net/bonding/bonding.h
===================================================================
@@ -156,6 +156,7 @@ struct slave {
 	s8     link;    /* one of BOND_LINK_XXXX */
 	s8     state;   /* one of BOND_STATE_XXXX */
 	u32    original_flags;
+	u32    original_mtu;
 	u32    link_failure_count;
 	u16    speed;
 	u8     duplex;

Index: net-2.6/drivers/net/bonding/bond_main.c
===================================================================
@@ -1134,8 +1134,13 @@ void bond_change_active_slave(struct bon
 		if (new_active && !bond->do_set_mac_addr)
 			memcpy(bond->dev->dev_addr,  new_active->dev->dev_addr,
 				new_active->dev->addr_len);
-
-		bond_send_gratuitous_arp(bond);
+		if (bond->curr_active_slave &&
+			test_bit(__LINK_STATE_LINKWATCH_PENDING, &bond->curr_active_slave->dev->state)){
+			dprintk("delaying gratuitous arp on %s\n",bond->curr_active_slave->dev->name);
+			bond->send_grat_arp=1;
+		}else{
+			bond_send_gratuitous_arp(bond);
+		}
 	}
 }
 

@@ -2120,6 +2125,15 @@ void bond_mii_monitor(struct net_device 
 	 * program could monitor the link itself if needed.
 	 */
 
+	if (bond->send_grat_arp) {
+		if (bond->curr_active_slave && test_bit(__LINK_STATE_LINKWATCH_PENDING, &bond->curr_active_slave->dev->state))
+			dprintk("Needs to send gratuitous arp but not yet\n",__FUNCTION__);
+		else {
+			dprintk("sending delayed gratuitous arp on ond->curr_active_slave->dev->name\n");
+			bond_send_gratuitous_arp(bond);
+			bond->send_grat_arp=0;
+		}
+	}
 	read_lock(&bond->curr_slave_lock);
 	oldcurrent = bond->curr_active_slave;
 	read_unlock(&bond->curr_slave_lock);

@@ -2513,6 +2527,7 @@ static void bond_send_gratuitous_arp(str
 	struct slave *slave = bond->curr_active_slave;
 	struct vlan_entry *vlan;
 	struct net_device *vlan_dev;
+	int i;
 
 	dprintk("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name,
 				slave ? slave->dev->name : "NULL");

@@ -2520,8 +2535,9 @@ static void bond_send_gratuitous_arp(str
 		return;
 
 	if (bond->master_ip) {
-		bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
-				  bond->master_ip, 0);
+		for (i=0;i<3;i++)
+			bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
+					  bond->master_ip, 0);
 	}
 
 	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {

@@ -4331,6 +4347,7 @@ static int bond_init(struct net_device *
 	bond->current_arp_slave = NULL;
 	bond->primary_slave = NULL;
 	bond->dev = bond_dev;
+	bond->send_grat_arp=0;
 	INIT_LIST_HEAD(&bond->vlan_list);
 
 	/* Initialize the device entry points */

Index: net-2.6/drivers/net/bonding/bonding.h
===================================================================
@@ -203,6 +203,7 @@ struct bonding {
 	struct   vlan_group *vlgrp;
 	struct   packet_type arp_mon_pt;
 	s8       do_set_mac_addr;
+	int	 send_grat_arp;
 };
 
 /**