IPoIB: Use multicast loopback blocking if available

Set IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK for IPoIB's UD QPs if
supported by the underlying device.  This creates an improvement of up
to 39% in bandwidth when sending multicast packets with IPoIB, and an
improvment of 12% in cpu usage.

Signed-off-by: Ron Livne <ronli@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 810790a..7b8fa36 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -199,7 +199,10 @@
 	init_attr.recv_cq = priv->recv_cq;
 
 	if (priv->hca_caps & IB_DEVICE_UD_TSO)
-		init_attr.create_flags = IB_QP_CREATE_IPOIB_UD_LSO;
+		init_attr.create_flags |= IB_QP_CREATE_IPOIB_UD_LSO;
+
+	if (priv->hca_caps & IB_DEVICE_BLOCK_MULTICAST_LOOPBACK)
+		init_attr.create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK;
 
 	if (dev->features & NETIF_F_SG)
 		init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;