bonding: remap muticast addresses without using dev_close() and dev_open()

This patch fixes commit e36b9d16c6a6d0f59803b3ef04ff3c22c3844c10. The approach
there is to call dev_close()/dev_open() whenever the device type is changed in
order to remap the device IP multicast addresses to HW multicast addresses.
This approach suffers from 2 drawbacks:

*. It assumes tha the device is UP when calling dev_close(), or otherwise
   dev_close() has no affect. It is worth to mention that initscripts (Redhat)
   and sysconfig (Suse) doesn't act the same in this matter. 
*. dev_close() has other side affects, like deleting entries from the routing
   table, which might be unnecessary.

The fix here is to directly remap the IP multicast addresses to HW multicast
addresses for a bonding device that changes its type, and nothing else.
   
Reported-by:   Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Moni Shoua <monis@voltaire.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 68 insertions, 2 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 84945470ab38..560c8c9c03ab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1017,9 +1017,9 @@ void netdev_state_change(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_state_change);
 
-void netdev_bonding_change(struct net_device *dev)
+void netdev_bonding_change(struct net_device *dev, unsigned long event)
 {
-        call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, dev);
+        call_netdevice_notifiers(event, dev);
 }
 EXPORT_SYMBOL(netdev_bonding_change);
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 3863c3a4223f..07336c6201f0 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1087,6 +1087,12 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
         case NETDEV_DOWN:
                 ip_mc_down(in_dev);
                 break;
+        case NETDEV_BONDING_OLDTYPE:
+                ip_mc_unmap(in_dev);
+                break;
+        case NETDEV_BONDING_NEWTYPE:
+                ip_mc_remap(in_dev);
+                break;
         case NETDEV_CHANGEMTU:
                 if (inetdev_valid_mtu(dev->mtu))
                         break;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 01b4284ed694..d41e5de79a82 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1298,6 +1298,28 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr)
         }
 }
 
+/* Device changing type */
+
+void ip_mc_unmap(struct in_device *in_dev)
+{
+        struct ip_mc_list *i;
+
+        ASSERT_RTNL();
+
+        for (i = in_dev->mc_list; i; i = i->next)
+                igmp_group_dropped(i);
+}
+
+void ip_mc_remap(struct in_device *in_dev)
+{
+        struct ip_mc_list *i;
+
+        ASSERT_RTNL();
+
+        for (i = in_dev->mc_list; i; i = i->next)
+                igmp_group_added(i);
+}
+
 /* Device going down */
 
 void ip_mc_down(struct in_device *in_dev)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c9b369034a40..f216a41ceb22 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -137,6 +137,8 @@ static DEFINE_SPINLOCK(addrconf_verify_lock);
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
 
+static void addrconf_bonding_change(struct net_device *dev,
+                                    unsigned long event);
 static int addrconf_ifdown(struct net_device *dev, int how);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags);
@@ -2582,6 +2584,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
                                 return notifier_from_errno(err);
                 }
                 break;
+        case NETDEV_BONDING_OLDTYPE:
+        case NETDEV_BONDING_NEWTYPE:
+                addrconf_bonding_change(dev, event);
+                break;
         }
 
         return NOTIFY_OK;
@@ -2595,6 +2601,19 @@ static struct notifier_block ipv6_dev_notf = {
         .priority = 0
 };
 
+static void addrconf_bonding_change(struct net_device *dev, unsigned long event)
+{
+        struct inet6_dev *idev;
+        ASSERT_RTNL();
+
+        idev = __in6_dev_get(dev);
+
+        if (event == NETDEV_BONDING_NEWTYPE)
+                ipv6_mc_remap(idev);
+        else if (event == NETDEV_BONDING_OLDTYPE)
+                ipv6_mc_unmap(idev);
+}
+
 static int addrconf_ifdown(struct net_device *dev, int how)
 {
         struct inet6_dev *idev;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 71c3dacec1ed..f9fcf690bd5d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2249,6 +2249,25 @@ static void igmp6_timer_handler(unsigned long data)
         ma_put(ma);
 }
 
+/* Device changing type */
+
+void ipv6_mc_unmap(struct inet6_dev *idev)
+{
+        struct ifmcaddr6 *i;
+
+        /* Install multicast list, except for all-nodes (already installed) */
+
+        read_lock_bh(&idev->lock);
+        for (i = idev->mc_list; i; i = i->next)
+                igmp6_group_dropped(i);
+        read_unlock_bh(&idev->lock);
+}
+
+void ipv6_mc_remap(struct inet6_dev *idev)
+{
+        ipv6_mc_up(idev);
+}
+
 /* Device going down */
 
 void ipv6_mc_down(struct inet6_dev *idev)