rds: add type of service(tos) infrastructure

RDS Service type (TOS) is user-defined and needs to be configured
via RDS IOCTL interface. It must be set before initiating any
traffic and once set the TOS can not be changed. All out-going
traffic from the socket will be associated with its TOS.

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>

include/uapi/linux/rds.h

@@ -69,6 +69,12 @@
 #define RDS_TRANS_COUNT	3
 #define	RDS_TRANS_NONE	(~0)
 
+/* IOCTLS commands for SOL_RDS */
+#define SIOCRDSSETTOS		(SIOCPROTOPRIVATE)
+#define SIOCRDSGETTOS		(SIOCPROTOPRIVATE + 1)
+
+typedef __u8	rds_tos_t;
+
 /*
  * Control message types for SOL_RDS.
  *
@@ -149,6 +155,7 @@ struct rds_info_connection {
 	__be32		faddr;
 	__u8		transport[TRANSNAMSIZ];		/* null term ascii */
 	__u8		flags;
+	__u8		tos;
 } __attribute__((packed));
 
 struct rds6_info_connection {
@@ -171,6 +178,7 @@ struct rds_info_message {
 	__be16		lport;
 	__be16		fport;
 	__u8		flags;
+	__u8		tos;
 } __attribute__((packed));
 
 struct rds6_info_message {
@@ -214,6 +222,7 @@ struct rds_info_tcp_socket {
 	__u32           last_sent_nxt;
 	__u32           last_expected_una;
 	__u32           last_seen_una;
+	__u8		tos;
 } __attribute__((packed));
 
 struct rds6_info_tcp_socket {
@@ -240,6 +249,7 @@ struct rds_info_rdma_connection {
 	__u32		max_send_sge;
 	__u32		rdma_mr_max;
 	__u32		rdma_mr_size;
+	__u8		tos;
 };
 
 struct rds6_info_rdma_connection {
@@ -253,6 +263,7 @@ struct rds6_info_rdma_connection {
 	__u32		max_send_sge;
 	__u32		rdma_mr_max;
 	__u32		rdma_mr_size;
+	__u8		tos;
 };
 
 /* RDS message Receive Path Latency points */

net/rds/af_rds.c

@@ -254,7 +254,38 @@ static __poll_t rds_poll(struct file *file, struct socket *sock,
 
 static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
+	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
+	rds_tos_t tos;
+
+	switch (cmd) {
+	case SIOCRDSSETTOS:
+		if (get_user(tos, (rds_tos_t __user *)arg))
+			return -EFAULT;
+
+		if (rs->rs_transport &&
+		    rs->rs_transport->t_type == RDS_TRANS_TCP)
+			tos = 0;
+
+		spin_lock_bh(&rds_sock_lock);
+		if (rs->rs_tos || rs->rs_conn) {
+			spin_unlock_bh(&rds_sock_lock);
+			return -EINVAL;
+		}
+		rs->rs_tos = tos;
+		spin_unlock_bh(&rds_sock_lock);
+		break;
+	case SIOCRDSGETTOS:
+		spin_lock_bh(&rds_sock_lock);
+		tos = rs->rs_tos;
+		spin_unlock_bh(&rds_sock_lock);
+		if (put_user(tos, (rds_tos_t __user *)arg))
+			return -EFAULT;
+		break;
+	default:
 		return -ENOIOCTLCMD;
+	}
+
+	return 0;
 }
 
 static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
@@ -650,6 +681,8 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
 	spin_lock_init(&rs->rs_rdma_lock);
 	rs->rs_rdma_keys = RB_ROOT;
 	rs->rs_rx_traces = 0;
+	rs->rs_tos = 0;
+	rs->rs_conn = NULL;
 
 	spin_lock_bh(&rds_sock_lock);
 	list_add_tail(&rs->rs_item, &rds_sock_list);

net/rds/connection.c

@@ -84,7 +84,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net,
 					      const struct in6_addr *laddr,
 					      const struct in6_addr *faddr,
 					      struct rds_transport *trans,
-					      int dev_if)
+					      u8 tos, int dev_if)
 {
 	struct rds_connection *conn, *ret = NULL;
 
@@ -92,6 +92,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net,
 		if (ipv6_addr_equal(&conn->c_faddr, faddr) &&
 		    ipv6_addr_equal(&conn->c_laddr, laddr) &&
 		    conn->c_trans == trans &&
+		    conn->c_tos == tos &&
 		    net == rds_conn_net(conn) &&
 		    conn->c_dev_if == dev_if) {
 			ret = conn;
@@ -160,7 +161,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 						const struct in6_addr *laddr,
 						const struct in6_addr *faddr,
 						struct rds_transport *trans,
-						gfp_t gfp,
+						gfp_t gfp, u8 tos,
 						int is_outgoing,
 						int dev_if)
 {
@@ -172,7 +173,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
 
 	rcu_read_lock();
-	conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if);
+	conn = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if);
 	if (conn &&
 	    conn->c_loopback &&
 	    conn->c_trans != &rds_loop_transport &&
@@ -206,6 +207,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
 	conn->c_faddr = *faddr;
 	conn->c_dev_if = dev_if;
+	conn->c_tos = tos;
 
 #if IS_ENABLED(CONFIG_IPV6)
 	/* If the local address is link local, set c_bound_if to be the
@@ -298,7 +300,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		struct rds_connection *found;
 
 		found = rds_conn_lookup(net, head, laddr, faddr, trans,
-					dev_if);
+					tos, dev_if);
 		if (found) {
 			struct rds_conn_path *cp;
 			int i;
@@ -333,10 +335,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 struct rds_connection *rds_conn_create(struct net *net,
 				       const struct in6_addr *laddr,
 				       const struct in6_addr *faddr,
-				       struct rds_transport *trans, gfp_t gfp,
+				       struct rds_transport *trans, u8 tos,
-				       int dev_if)
+				       gfp_t gfp, int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 0, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create);
 
@@ -344,9 +346,9 @@ struct rds_connection *rds_conn_create_outgoing(struct net *net,
 						const struct in6_addr *laddr,
 						const struct in6_addr *faddr,
 						struct rds_transport *trans,
-						gfp_t gfp, int dev_if)
+						u8 tos, gfp_t gfp, int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 1, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 

net/rds/ib.c

@@ -301,6 +301,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 
 	iinfo->src_addr = conn->c_laddr.s6_addr32[3];
 	iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
+	iinfo->tos = conn->c_tos;
 
 	memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
 	memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));

net/rds/ib_cm.c

@@ -786,7 +786,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 
 	/* RDS/IB is not currently netns aware, thus init_net */
 	conn = rds_conn_create(&init_net, daddr6, saddr6,
-			       &rds_ib_transport, GFP_KERNEL, ifindex);
+			       &rds_ib_transport, 0, GFP_KERNEL, ifindex);
 	if (IS_ERR(conn)) {
 		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
 		conn = NULL;

net/rds/rdma_transport.c

@@ -115,6 +115,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 			pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n",
 				&conn->c_laddr, &conn->c_faddr);
 			conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
+			conn->c_tos = 0;
 			rds_conn_drop(conn);
 		}
 		rdsdebug("Connection rejected: %s\n",

net/rds/rds.h

@@ -158,6 +158,9 @@ struct rds_connection {
 	unsigned int		c_version;
 	possible_net_t		c_net;
 
+	/* TOS */
+	u8			c_tos;
+
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;
 
@@ -652,6 +655,7 @@ struct rds_sock {
 	u8			rs_rx_traces;
 	u8			rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX];
 	struct rds_msg_zcopy_queue rs_zcookie_queue;
+	u8			rs_tos;
 };
 
 static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk)
@@ -760,13 +764,14 @@ void rds_conn_exit(void);
 struct rds_connection *rds_conn_create(struct net *net,
 				       const struct in6_addr *laddr,
 				       const struct in6_addr *faddr,
-				       struct rds_transport *trans, gfp_t gfp,
+				       struct rds_transport *trans,
+				       u8 tos, gfp_t gfp,
 				       int dev_if);
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
 						const struct in6_addr *laddr,
 						const struct in6_addr *faddr,
 						struct rds_transport *trans,
-						gfp_t gfp, int dev_if);
+						u8 tos, gfp_t gfp, int dev_if);
 void rds_conn_shutdown(struct rds_conn_path *cpath);
 void rds_conn_destroy(struct rds_connection *conn);
 void rds_conn_drop(struct rds_connection *conn);

net/rds/recv.c

@@ -782,6 +782,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 
 	minfo.seq = be64_to_cpu(inc->i_hdr.h_sequence);
 	minfo.len = be32_to_cpu(inc->i_hdr.h_len);
+	minfo.tos = inc->i_conn->c_tos;
 
 	if (flip) {
 		minfo.laddr = daddr;

net/rds/send.c

@@ -1277,12 +1277,12 @@ 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)) {
 		conn = rs->rs_conn;
-	else {
+	} else {
 		conn = rds_conn_create_outgoing(sock_net(sock->sk),
 						&rs->rs_bound_addr, &daddr,
-						rs->rs_transport,
+						rs->rs_transport, 0,
 						sock->sk->sk_allocation,
 						scope_id);
 		if (IS_ERR(conn)) {

net/rds/tcp.c

@@ -267,6 +267,7 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 		tsinfo.last_sent_nxt = tc->t_last_sent_nxt;
 		tsinfo.last_expected_una = tc->t_last_expected_una;
 		tsinfo.last_seen_una = tc->t_last_seen_una;
+		tsinfo.tos = tc->t_cpath->cp_conn->c_tos;
 
 		rds_info_copy(iter, &tsinfo, sizeof(tsinfo));
 	}

net/rds/tcp_listen.c

@@ -200,7 +200,7 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	conn = rds_conn_create(sock_net(sock->sk),
 			       my_addr, peer_addr,
-			       &rds_tcp_transport, GFP_KERNEL, dev_if);
+			       &rds_tcp_transport, 0, GFP_KERNEL, dev_if);
 
 	if (IS_ERR(conn)) {
 		ret = PTR_ERR(conn);