rds: rdma: update rdma transport for tos

For RDMA transports, RDS TOS is an extension of IB QoS(Annex A13)
to provide clients the ability to segregate traffic flows for
different type of data. RDMA CM abstract it for ULPs using
rdma_set_service_type(). Internally, each traffic flow is
represented by a connection with all of its independent resources
like that of a normal connection, and is differentiated by
service type. In other words, there can be multiple qp connections
between an IP pair and each supports a unique service type.

The feature has been added from RDSv4.1 onwards and supports
rolling upgrades. RDMA connection metadata also carries the tos
information to set up SL on end to end context. The original
code was developed by Bang Nguyen in downstream kernel back in
2.6.32 kernel days and it has evolved over period of time.
Reviewed-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
[yanjun.zhu@oracle.com: Adapted original patch with ipv6 changes]
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>

net/rds/ib.h

@@ -67,7 +67,9 @@ struct rds_ib_conn_priv_cmn {
 	u8			ricpc_protocol_major;
 	u8			ricpc_protocol_minor;
 	__be16			ricpc_protocol_minor_mask;	/* bitmask */
-	__be32			ricpc_reserved1;
+	u8			ricpc_dp_toss;
+	u8			ripc_reserved1;
+	__be16			ripc_reserved2;
 	__be64			ricpc_ack_seq;
 	__be32			ricpc_credit;	/* non-zero enables flow ctl */
 };

net/rds/ib_cm.c

@@ -144,9 +144,9 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 		}
 	}
 
-	pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n",
+	pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c,%d> version %u.%u%s\n",
 		  ic->i_active_side ? "Active" : "Passive",
-		  &conn->c_laddr, &conn->c_faddr,
+		  &conn->c_laddr, &conn->c_faddr, conn->c_tos,
 		  RDS_PROTOCOL_MAJOR(conn->c_version),
 		  RDS_PROTOCOL_MINOR(conn->c_version),
 		  ic->i_flowctl ? ", flow control" : "");
@@ -222,6 +222,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
 			    cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
 			dp->ricp_v6.dp_ack_seq =
 			    cpu_to_be64(rds_ib_piggyb_ack(ic));
+			dp->ricp_v6.dp_cmn.ricpc_dp_toss = conn->c_tos;
 
 			conn_param->private_data = &dp->ricp_v6;
 			conn_param->private_data_len = sizeof(dp->ricp_v6);
@@ -236,6 +237,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
 			    cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
 			dp->ricp_v4.dp_ack_seq =
 			    cpu_to_be64(rds_ib_piggyb_ack(ic));
+			dp->ricp_v4.dp_cmn.ricpc_dp_toss = conn->c_tos;
 
 			conn_param->private_data = &dp->ricp_v4;
 			conn_param->private_data_len = sizeof(dp->ricp_v4);
@@ -391,10 +393,9 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
 		rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST);
 		break;
 	default:
-		rdsdebug("Fatal QP Event %u (%s) "
-			"- connection %pI6c->%pI6c, reconnecting\n",
-			event->event, ib_event_msg(event->event),
-			&conn->c_laddr, &conn->c_faddr);
+		rdsdebug("Fatal QP Event %u (%s) - connection %pI6c->%pI6c, reconnecting\n",
+			 event->event, ib_event_msg(event->event),
+			 &conn->c_laddr, &conn->c_faddr);
 		rds_conn_drop(conn);
 		break;
 	}
@@ -662,11 +663,11 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 
 	/* Even if len is crap *now* I still want to check it. -ASG */
 	if (event->param.conn.private_data_len < data_len || major == 0)
-		return RDS_PROTOCOL_3_0;
+		return RDS_PROTOCOL_4_0;
 
 	common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS;
-	if (major == 3 && common) {
-		version = RDS_PROTOCOL_3_0;
+	if (major == 4 && common) {
+		version = RDS_PROTOCOL_4_0;
 		while ((common >>= 1) != 0)
 			version++;
 	} else if (RDS_PROTOCOL_COMPAT_VERSION ==
@@ -778,15 +779,16 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		daddr6 = &d_mapped_addr;
 	}
 
-	rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid "
-		 "0x%llx\n", saddr6, daddr6,
-		 RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version),
+	rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid 0x%llx, tos:%d\n",
+		 saddr6, daddr6, RDS_PROTOCOL_MAJOR(version),
+		 RDS_PROTOCOL_MINOR(version),
 		 (unsigned long long)be64_to_cpu(lguid),
-		 (unsigned long long)be64_to_cpu(fguid));
+		 (unsigned long long)be64_to_cpu(fguid), dp_cmn->ricpc_dp_toss);
 
 	/* RDS/IB is not currently netns aware, thus init_net */
 	conn = rds_conn_create(&init_net, daddr6, saddr6,
-			       &rds_ib_transport, 0, GFP_KERNEL, ifindex);
+			       &rds_ib_transport, dp_cmn->ricpc_dp_toss,
+			       GFP_KERNEL, ifindex);
 	if (IS_ERR(conn)) {
 		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
 		conn = NULL;
@@ -868,7 +870,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
 
 	/* If the peer doesn't do protocol negotiation, we must
 	 * default to RDSv3.0 */
-	rds_ib_set_protocol(conn, RDS_PROTOCOL_VERSION);
+	rds_ib_set_protocol(conn, RDS_PROTOCOL_4_1);
 	ic->i_flowctl = rds_ib_sysctl_flow_control;	/* advertise flow control */
 
 	ret = rds_ib_setup_qp(conn);

net/rds/ib_recv.c

@@ -986,9 +986,9 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
 	} else {
 		/* We expect errors as the qp is drained during shutdown */
 		if (rds_conn_up(conn) || rds_conn_connecting(conn))
-			rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
+			rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c, %d> had status %u (%s), disconnecting and reconnecting\n",
 					  &conn->c_laddr, &conn->c_faddr,
-					  wc->status,
+					  conn->c_tos, wc->status,
 					  ib_wc_status_msg(wc->status));
 	}
 

net/rds/ib_send.c

@@ -305,8 +305,9 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 
 	/* We expect errors as the qp is drained during shutdown */
 	if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) {
-		rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
-				  &conn->c_laddr, &conn->c_faddr, wc->status,
+		rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c,%d> had status %u (%s), disconnecting and reconnecting\n",
+				  &conn->c_laddr, &conn->c_faddr,
+				  conn->c_tos, wc->status,
 				  ib_wc_status_msg(wc->status));
 	}
 }

net/rds/rdma_transport.c

@@ -83,6 +83,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		break;
 
 	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		rdma_set_service_type(cm_id, conn->c_tos);
 		/* XXX do we need to clean up if this fails? */
 		ret = rdma_resolve_route(cm_id,
 					 RDS_RDMA_RESOLVE_TIMEOUT_MS);

net/rds/send.c

@@ -1277,12 +1277,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* rds_conn_create has a spinlock that runs with IRQ off.
 	 * Caching the conn in the socket helps a lot. */
-	if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) {
+	if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr) &&
+	    rs->rs_tos == rs->rs_conn->c_tos) {
 		conn = rs->rs_conn;
 	} else {
 		conn = rds_conn_create_outgoing(sock_net(sock->sk),
 						&rs->rs_bound_addr, &daddr,
-						rs->rs_transport, 0,
+						rs->rs_transport, rs->rs_tos,
 						sock->sk->sk_allocation,
 						scope_id);
 		if (IS_ERR(conn)) {