3 files changed, 39 insertions, 14 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca2873698d75..edc5b8565d6d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -495,6 +495,7 @@ void ipoib_dev_cleanup(struct net_device *dev);
 void ipoib_mcast_join_task(struct work_struct *work);
 void ipoib_mcast_carrier_on_task(struct work_struct *work);
 void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
+void ipoib_mcast_free(struct ipoib_mcast *mc);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
@@ -548,6 +549,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce5a3e2..babba05d7a0e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
+		ipoib_mcast_leave(dev, mcast);
+		ipoib_mcast_free(mcast);
+	}
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748f9d13..d750a86042f3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -106,7 +106,7 @@ static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv,
 		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
 }
 
-static void ipoib_mcast_free(struct ipoib_mcast *mcast)
+void ipoib_mcast_free(struct ipoib_mcast *mcast)
 {
 	struct net_device *dev = mcast->dev;
 	int tx_dropped = 0;
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 
 		/*
-		 * Historically Linux IPoIB has never properly supported SEND
-		 * ONLY join. It emulated it by not providing all the required
-		 * attributes, which is enough to prevent group creation and
-		 * detect if there are full members or not. A major problem
-		 * with supporting SEND ONLY is detecting when the group is
-		 * auto-destroyed as IPoIB will cache the MLID..
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
 		 */
-#if 1
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
 			rec.join_state = 4;
 #endif
@@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;