RDMA/cma: Add ability to specify type of service

Provide support to specify a type of service for a communication
identifier.  A new function call is used when dealing with IPv4
addresses.  For IPv6 addresses, the ToS is specified through the
traffic class field in the sockaddr_in6 structure.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>

[ The comments Eitan Zahavi and myself have made over the v1 post at 
  <http://lists.openfabrics.org/pipermail/general/2007-August/039247.html>
  were fully addressed. ]
 
Reviewed-by: Or Gerlitz <ogerlitz@voltaire.com> 
Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/core/cma.c

@@ -138,6 +138,7 @@ struct rdma_id_private {
 	u32			qkey;
 	u32			qp_num;
 	u8			srq;
+	u8			tos;
 };
 
 struct cma_multicast {
@@ -1474,6 +1475,15 @@ int rdma_listen(struct rdma_cm_id *id, int backlog)
 }
 EXPORT_SYMBOL(rdma_listen);
 
+void rdma_set_service_type(struct rdma_cm_id *id, int tos)
+{
+	struct rdma_id_private *id_priv;
+
+	id_priv = container_of(id, struct rdma_id_private, id);
+	id_priv->tos = (u8) tos;
+}
+EXPORT_SYMBOL(rdma_set_service_type);
+
 static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 			      void *context)
 {
@@ -1498,23 +1508,37 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
 			      struct cma_work *work)
 {
-	struct rdma_dev_addr *addr = &id_priv->id.route.addr.dev_addr;
+	struct rdma_addr *addr = &id_priv->id.route.addr;
 	struct ib_sa_path_rec path_rec;
+	ib_sa_comp_mask comp_mask;
+	struct sockaddr_in6 *sin6;
 
 	memset(&path_rec, 0, sizeof path_rec);
-	ib_addr_get_sgid(addr, &path_rec.sgid);
-	ib_addr_get_dgid(addr, &path_rec.dgid);
-	path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(addr));
+	ib_addr_get_sgid(&addr->dev_addr, &path_rec.sgid);
+	ib_addr_get_dgid(&addr->dev_addr, &path_rec.dgid);
+	path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
 	path_rec.numb_path = 1;
 	path_rec.reversible = 1;
+	path_rec.service_id = cma_get_service_id(id_priv->id.ps, &addr->dst_addr);
+
+	comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
+		    IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
+		    IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;
+
+	if (addr->src_addr.sa_family == AF_INET) {
+		path_rec.qos_class = cpu_to_be16((u16) id_priv->tos);
+		comp_mask |= IB_SA_PATH_REC_QOS_CLASS;
+	} else {
+		sin6 = (struct sockaddr_in6 *) &addr->src_addr;
+		path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20);
+		comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS;
+	}
 
 	id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device,
-				id_priv->id.port_num, &path_rec,
-				IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
-				IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
-				IB_SA_PATH_REC_REVERSIBLE,
-				timeout_ms, GFP_KERNEL,
-				cma_query_handler, work, &id_priv->query);
+					       id_priv->id.port_num, &path_rec,
+					       comp_mask, timeout_ms,
+					       GFP_KERNEL, cma_query_handler,
+					       work, &id_priv->query);
 
 	return (id_priv->query_id < 0) ? id_priv->query_id : 0;
 }

include/rdma/rdma_cm.h

@@ -314,4 +314,18 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
  */
 void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr);
 
+/**
+ * rdma_set_service_type - Set the type of service associated with a
+ *   connection identifier.
+ * @id: Communication identifier to associated with service type.
+ * @tos: Type of service.
+ *
+ * The type of service is interpretted as a differentiated service
+ * field (RFC 2474).  The service type should be specified before
+ * performing route resolution, as existing communication on the
+ * connection identifier may be unaffected.  The type of service
+ * requested may not be supported by the network to all destinations.
+ */
+void rdma_set_service_type(struct rdma_cm_id *id, int tos);
+
 #endif /* RDMA_CM_H */