bridge: only expire the mdb entry when query is received

Currently we arm the expire timer when the mdb entry is added,
however, this causes problem when there is no querier sent
out after that.

So we should only arm the timer when a corresponding query is
received, as suggested by Herbert.

And he also mentioned "if there is no querier then group
subscriptions shouldn't expire. There has to be at least one querier
in the network for this thing to work.  Otherwise it just degenerates
into a non-snooping switch, which is OK."

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Adam Baker <linux@baker-net.org.uk>
Signed-off-by: Cong Wang <amwang@redhat.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 13 insertions, 27 deletions

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 247514793101..40bda804fbd9 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -617,8 +617,6 @@ rehash:
 
         mp->br = br;
         mp->addr = *group;
-        setup_timer(&mp->timer, br_multicast_group_expired,
-                    (unsigned long)mp);
 
         hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]);
         mdb->size++;
@@ -656,7 +654,6 @@ static int br_multicast_add_group(struct net_bridge *br,
         struct net_bridge_mdb_entry *mp;
         struct net_bridge_port_group *p;
         struct net_bridge_port_group __rcu **pp;
-        unsigned long now = jiffies;
         int err;
 
         spin_lock(&br->multicast_lock);
@@ -671,7 +668,6 @@ static int br_multicast_add_group(struct net_bridge *br,
 
         if (!port) {
                 mp->mglist = true;
-                mod_timer(&mp->timer, now + br->multicast_membership_interval);
                 goto out;
         }
 
@@ -679,7 +675,7 @@ static int br_multicast_add_group(struct net_bridge *br,
              (p = mlock_dereference(*pp, br)) != NULL;
              pp = &p->next) {
                 if (p->port == port)
-                        goto found;
+                        goto out;
                 if ((unsigned long)p->port < (unsigned long)port)
                         break;
         }
@@ -690,8 +686,6 @@ static int br_multicast_add_group(struct net_bridge *br,
         rcu_assign_pointer(*pp, p);
         br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 
-found:
-        mod_timer(&p->timer, now + br->multicast_membership_interval);
 out:
         err = 0;
 
@@ -1131,6 +1125,10 @@ static int br_ip4_multicast_query(struct net_bridge *br,
         if (!mp)
                 goto out;
 
+        setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp);
+        mod_timer(&mp->timer, now + br->multicast_membership_interval);
+        mp->timer_armed = true;
+
         max_delay *= br->multicast_last_member_count;
 
         if (mp->mglist &&
@@ -1205,6 +1203,10 @@ static int br_ip6_multicast_query(struct net_bridge *br,
         if (!mp)
                 goto out;
 
+        setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp);
+        mod_timer(&mp->timer, now + br->multicast_membership_interval);
+        mp->timer_armed = true;
+
         max_delay *= br->multicast_last_member_count;
         if (mp->mglist &&
             (timer_pending(&mp->timer) ?
@@ -1263,7 +1265,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
                         call_rcu_bh(&p->rcu, br_multicast_free_pg);
                         br_mdb_notify(br->dev, port, group, RTM_DELMDB);
 
-                        if (!mp->ports && !mp->mglist &&
+                        if (!mp->ports && !mp->mglist && mp->timer_armed &&
                             netif_running(br->dev))
                                 mod_timer(&mp->timer, jiffies);
                 }
@@ -1275,30 +1277,12 @@ static void br_multicast_leave_group(struct net_bridge *br,
                      br->multicast_last_member_interval;
 
         if (!port) {
-                if (mp->mglist &&
+                if (mp->mglist && mp->timer_armed &&
                     (timer_pending(&mp->timer) ?
                      time_after(mp->timer.expires, time) :
                      try_to_del_timer_sync(&mp->timer) >= 0)) {
                         mod_timer(&mp->timer, time);
                 }
-
-                goto out;
-        }
-
-        for (p = mlock_dereference(mp->ports, br);
-             p != NULL;
-             p = mlock_dereference(p->next, br)) {
-                if (p->port != port)
-                        continue;
-
-                if (!hlist_unhashed(&p->mglist) &&
-                    (timer_pending(&p->timer) ?
-                     time_after(p->timer.expires, time) :
-                     try_to_del_timer_sync(&p->timer) >= 0)) {
-                        mod_timer(&p->timer, time);
-                }
-
-                break;
         }
 
 out:
@@ -1674,6 +1658,7 @@ void br_multicast_stop(struct net_bridge *br)
                 hlist_for_each_entry_safe(mp, n, &mdb->mhash[i],
                                           hlist[ver]) {
                         del_timer(&mp->timer);
+                        mp->timer_armed = false;
                         call_rcu_bh(&mp->rcu, br_multicast_free_group);
                 }
         }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e260710a01d4..1b0ac95a5c37 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -112,6 +112,7 @@ struct net_bridge_mdb_entry
         struct timer_list               timer;
         struct br_ip                    addr;
         bool                            mglist;
+        bool                            timer_armed;
 };
 
 struct net_bridge_mdb_htable