rds: Extend RDS API for IPv6 support

There are many data structures (RDS socket options) used by RDS apps
which use a 32 bit integer to store IP address. To support IPv6,
struct in6_addr needs to be used. To ensure backward compatibility, a
new data structure is introduced for each of those data structures
which use a 32 bit integer to represent an IP address. And new socket
options are introduced to use those new structures. This means that
existing apps should work without a problem with the new RDS module.
For apps which want to use IPv6, those new data structures and socket
options can be used. IPv4 mapped address is used to represent IPv4
address in the new data structures.

v4: Revert changes to SO_RDS_TRANSPORT

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/uapi/linux/rds.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
- * Copyright (c) 2008 Oracle.  All rights reserved.
+ * Copyright (c) 2008, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -118,7 +118,17 @@
 #define RDS_INFO_IB_CONNECTIONS		10008
 #define RDS_INFO_CONNECTION_STATS	10009
 #define RDS_INFO_IWARP_CONNECTIONS	10010
-#define RDS_INFO_LAST			10010
+
+/* PF_RDS6 options */
+#define RDS6_INFO_CONNECTIONS		10011
+#define RDS6_INFO_SEND_MESSAGES		10012
+#define RDS6_INFO_RETRANS_MESSAGES	10013
+#define RDS6_INFO_RECV_MESSAGES		10014
+#define RDS6_INFO_SOCKETS		10015
+#define RDS6_INFO_TCP_SOCKETS		10016
+#define RDS6_INFO_IB_CONNECTIONS	10017
+
+#define RDS_INFO_LAST			10017
 
 struct rds_info_counter {
 	__u8	name[32];
@@ -140,6 +150,15 @@ struct rds_info_connection {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_connection {
+	__u64		next_tx_seq;
+	__u64		next_rx_seq;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__u8		transport[TRANSNAMSIZ];		/* null term ascii */
+	__u8		flags;
+} __attribute__((packed));
+
 #define RDS_INFO_MESSAGE_FLAG_ACK               0x01
 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK          0x02
 
@@ -153,6 +172,17 @@ struct rds_info_message {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_message {
+	__u64	seq;
+	__u32	len;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__be16		lport;
+	__be16		fport;
+	__u8		flags;
+	__u8		tos;
+} __attribute__((packed));
+
 struct rds_info_socket {
 	__u32		sndbuf;
 	__be32		bound_addr;
@@ -163,6 +193,16 @@ struct rds_info_socket {
 	__u64		inum;
 } __attribute__((packed));
 
+struct rds6_info_socket {
+	__u32		sndbuf;
+	struct in6_addr	bound_addr;
+	struct in6_addr	connected_addr;
+	__be16		bound_port;
+	__be16		connected_port;
+	__u32		rcvbuf;
+	__u64		inum;
+} __attribute__((packed));
+
 struct rds_info_tcp_socket {
 	__be32          local_addr;
 	__be16          local_port;
@@ -175,6 +215,18 @@ struct rds_info_tcp_socket {
 	__u32           last_seen_una;
 } __attribute__((packed));
 
+struct rds6_info_tcp_socket {
+	struct in6_addr	local_addr;
+	__be16		local_port;
+	struct in6_addr	peer_addr;
+	__be16		peer_port;
+	__u64		hdr_rem;
+	__u64		data_rem;
+	__u32		last_sent_nxt;
+	__u32		last_expected_una;
+	__u32		last_seen_una;
+} __attribute__((packed));
+
 #define RDS_IB_GID_LEN	16
 struct rds_info_rdma_connection {
 	__be32		src_addr;
@@ -189,6 +241,19 @@ struct rds_info_rdma_connection {
 	__u32		rdma_mr_size;
 };
 
+struct rds6_info_rdma_connection {
+	struct in6_addr	src_addr;
+	struct in6_addr	dst_addr;
+	__u8		src_gid[RDS_IB_GID_LEN];
+	__u8		dst_gid[RDS_IB_GID_LEN];
+
+	__u32		max_send_wr;
+	__u32		max_recv_wr;
+	__u32		max_send_sge;
+	__u32		rdma_mr_max;
+	__u32		rdma_mr_size;
+};
+
 /* RDS message Receive Path Latency points */
 enum rds_message_rxpath_latency {
 	RDS_MSG_RX_HDR_TO_DGRAM_START = 0,

net/rds/connection.c

@@ -498,16 +498,19 @@ EXPORT_SYMBOL_GPL(rds_conn_destroy);
 
 static void __rds_inc_msg_cp(struct rds_incoming *inc,
 			     struct rds_info_iterator *iter,
-			     void *saddr, void *daddr, int flip)
+			     void *saddr, void *daddr, int flip, bool isv6)
 {
-	rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
-			  *(__be32 *)daddr, flip);
+	if (isv6)
+		rds6_inc_info_copy(inc, iter, saddr, daddr, flip);
+	else
+		rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
+				  *(__be32 *)daddr, flip);
 }
 
 static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 				      struct rds_info_iterator *iter,
 				      struct rds_info_lengths *lens,
-				      int want_send)
+				      int want_send, bool isv6)
 {
 	struct hlist_head *head;
 	struct list_head *list;
@@ -518,7 +521,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 	size_t i;
 	int j;
 
-	len /= sizeof(struct rds_info_message);
+	if (isv6)
+		len /= sizeof(struct rds6_info_message);
+	else
+		len /= sizeof(struct rds_info_message);
 
 	rcu_read_lock();
 
@@ -528,6 +534,9 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 			struct rds_conn_path *cp;
 			int npaths;
 
+			if (!isv6 && conn->c_isv6)
+				continue;
+
 			npaths = (conn->c_trans->t_mp_capable ?
 				 RDS_MPATH_WORKERS : 1);
 
@@ -548,7 +557,7 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 								 iter,
 								 &conn->c_laddr,
 								 &conn->c_faddr,
-								 0);
+								 0, isv6);
 				}
 
 				spin_unlock_irqrestore(&cp->cp_lock, flags);
@@ -558,7 +567,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 	rcu_read_unlock();
 
 	lens->nr = total;
-	lens->each = sizeof(struct rds_info_message);
+	if (isv6)
+		lens->each = sizeof(struct rds6_info_message);
+	else
+		lens->each = sizeof(struct rds_info_message);
 }
 
 static void rds_conn_message_info(struct socket *sock, unsigned int len,
@@ -566,7 +578,15 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 				  struct rds_info_lengths *lens,
 				  int want_send)
 {
-	rds_conn_message_info_cmn(sock, len, iter, lens, want_send);
+	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false);
+}
+
+static void rds6_conn_message_info(struct socket *sock, unsigned int len,
+				   struct rds_info_iterator *iter,
+				   struct rds_info_lengths *lens,
+				   int want_send)
+{
+	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true);
 }
 
 static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
@@ -576,6 +596,13 @@ static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
 	rds_conn_message_info(sock, len, iter, lens, 1);
 }
 
+static void rds6_conn_message_info_send(struct socket *sock, unsigned int len,
+					struct rds_info_iterator *iter,
+					struct rds_info_lengths *lens)
+{
+	rds6_conn_message_info(sock, len, iter, lens, 1);
+}
+
 static void rds_conn_message_info_retrans(struct socket *sock,
 					  unsigned int len,
 					  struct rds_info_iterator *iter,
@@ -584,6 +611,14 @@ static void rds_conn_message_info_retrans(struct socket *sock,
 	rds_conn_message_info(sock, len, iter, lens, 0);
 }
 
+static void rds6_conn_message_info_retrans(struct socket *sock,
+					   unsigned int len,
+					   struct rds_info_iterator *iter,
+					   struct rds_info_lengths *lens)
+{
+	rds6_conn_message_info(sock, len, iter, lens, 0);
+}
+
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens,
@@ -699,6 +734,34 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	return 1;
 }
 
+static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
+{
+	struct rds6_info_connection *cinfo6 = buffer;
+	struct rds_connection *conn = cp->cp_conn;
+
+	cinfo6->next_tx_seq = cp->cp_next_tx_seq;
+	cinfo6->next_rx_seq = cp->cp_next_rx_seq;
+	cinfo6->laddr = conn->c_laddr;
+	cinfo6->faddr = conn->c_faddr;
+	strncpy(cinfo6->transport, conn->c_trans->t_name,
+		sizeof(cinfo6->transport));
+	cinfo6->flags = 0;
+
+	rds_conn_info_set(cinfo6->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
+			  SENDING);
+	/* XXX Future: return the state rather than these funky bits */
+	rds_conn_info_set(cinfo6->flags,
+			  atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING,
+			  CONNECTING);
+	rds_conn_info_set(cinfo6->flags,
+			  atomic_read(&cp->cp_state) == RDS_CONN_UP,
+			  CONNECTED);
+	/* Just return 1 as there is no error case. This is a helper function
+	 * for rds_walk_conn_path_info() and it wants a return value.
+	 */
+	return 1;
+}
+
 static void rds_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens)
@@ -711,6 +774,18 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_connection));
 }
 
+static void rds6_conn_info(struct socket *sock, unsigned int len,
+			   struct rds_info_iterator *iter,
+			   struct rds_info_lengths *lens)
+{
+	u64 buffer[(sizeof(struct rds6_info_connection) + 7) / 8];
+
+	rds_walk_conn_path_info(sock, len, iter, lens,
+				rds6_conn_info_visitor,
+				buffer,
+				sizeof(struct rds6_info_connection));
+}
+
 int rds_conn_init(void)
 {
 	int ret;
@@ -732,6 +807,11 @@ int rds_conn_init(void)
 			       rds_conn_message_info_send);
 	rds_info_register_func(RDS_INFO_RETRANS_MESSAGES,
 			       rds_conn_message_info_retrans);
+	rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
+	rds_info_register_func(RDS6_INFO_SEND_MESSAGES,
+			       rds6_conn_message_info_send);
+	rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES,
+			       rds6_conn_message_info_retrans);
 
 	return 0;
 }
@@ -750,6 +830,11 @@ void rds_conn_exit(void)
 				 rds_conn_message_info_send);
 	rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES,
 				 rds_conn_message_info_retrans);
+	rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
+	rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES,
+				 rds6_conn_message_info_send);
+	rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES,
+				 rds6_conn_message_info_retrans);
 }
 
 /*

net/rds/ib.c

@@ -321,6 +321,43 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	return 1;
 }
 
+/* IPv6 version of rds_ib_conn_info_visitor(). */
+static int rds6_ib_conn_info_visitor(struct rds_connection *conn,
+				     void *buffer)
+{
+	struct rds6_info_rdma_connection *iinfo6 = buffer;
+	struct rds_ib_connection *ic;
+
+	/* We will only ever look at IB transports */
+	if (conn->c_trans != &rds_ib_transport)
+		return 0;
+
+	iinfo6->src_addr = conn->c_laddr;
+	iinfo6->dst_addr = conn->c_faddr;
+
+	memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid));
+	memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid));
+
+	if (rds_conn_state(conn) == RDS_CONN_UP) {
+		struct rds_ib_device *rds_ibdev;
+		struct rdma_dev_addr *dev_addr;
+
+		ic = conn->c_transport_data;
+		dev_addr = &ic->i_cm_id->route.addr.dev_addr;
+		rdma_addr_get_sgid(dev_addr,
+				   (union ib_gid *)&iinfo6->src_gid);
+		rdma_addr_get_dgid(dev_addr,
+				   (union ib_gid *)&iinfo6->dst_gid);
+
+		rds_ibdev = ic->rds_ibdev;
+		iinfo6->max_send_wr = ic->i_send_ring.w_nr;
+		iinfo6->max_recv_wr = ic->i_recv_ring.w_nr;
+		iinfo6->max_send_sge = rds_ibdev->max_sge;
+		rds6_ib_get_mr_info(rds_ibdev, iinfo6);
+	}
+	return 1;
+}
+
 static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 			   struct rds_info_iterator *iter,
 			   struct rds_info_lengths *lens)
@@ -333,6 +370,19 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_rdma_connection));
 }
 
+/* IPv6 version of rds_ib_ic_info(). */
+static void rds6_ib_ic_info(struct socket *sock, unsigned int len,
+			    struct rds_info_iterator *iter,
+			    struct rds_info_lengths *lens)
+{
+	u64 buffer[(sizeof(struct rds6_info_rdma_connection) + 7) / 8];
+
+	rds_for_each_conn_info(sock, len, iter, lens,
+			       rds6_ib_conn_info_visitor,
+			       buffer,
+			       sizeof(struct rds6_info_rdma_connection));
+}
+
 /*
  * Early RDS/IB was built to only bind to an address if there is an IPoIB
  * device with that address set.
@@ -441,6 +491,7 @@ void rds_ib_exit(void)
 	rds_ib_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+	rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
 	rds_ib_unregister_client();
 	rds_ib_destroy_nodev_conns();
 	rds_ib_sysctl_exit();
@@ -502,6 +553,7 @@ int rds_ib_init(void)
 	rds_trans_register(&rds_ib_transport);
 
 	rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+	rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
 
 	goto out;
 

net/rds/ib_mr.h

@@ -113,6 +113,8 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev,
 					     int npages);
 void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			struct rds_info_rdma_connection *iinfo);
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		    struct rds_sock *rs, u32 *key_ret);

net/rds/ib_rdma.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -180,6 +180,15 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co
 	iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
 }
 
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6)
+{
+	struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
+
+	iinfo6->rdma_mr_max = pool_1m->max_items;
+	iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages;
+}
+
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 {
 	struct rds_ib_mr *ibmr = NULL;

net/rds/recv.c

@@ -792,3 +792,28 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
+
+void rds6_inc_info_copy(struct rds_incoming *inc,
+			struct rds_info_iterator *iter,
+			struct in6_addr *saddr, struct in6_addr *daddr,
+			int flip)
+{
+	struct rds6_info_message minfo6;
+
+	minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
+	minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+
+	if (flip) {
+		minfo6.laddr = *daddr;
+		minfo6.faddr = *saddr;
+		minfo6.lport = inc->i_hdr.h_dport;
+		minfo6.fport = inc->i_hdr.h_sport;
+	} else {
+		minfo6.laddr = *saddr;
+		minfo6.faddr = *daddr;
+		minfo6.lport = inc->i_hdr.h_sport;
+		minfo6.fport = inc->i_hdr.h_dport;
+	}
+
+	rds_info_copy(iter, &minfo6, sizeof(minfo6));
+}

net/rds/tcp.c

@@ -273,6 +273,48 @@ out:
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
+/* Handle RDS6_INFO_TCP_SOCKETS socket option. It returns both IPv4 and
+ * IPv6 connections. IPv4 connection address is returned in an IPv4 mapped
+ * address.
+ */
+static void rds6_tcp_tc_info(struct socket *sock, unsigned int len,
+			     struct rds_info_iterator *iter,
+			     struct rds_info_lengths *lens)
+{
+	struct rds6_info_tcp_socket tsinfo6;
+	struct rds_tcp_connection *tc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
+
+	if (len / sizeof(tsinfo6) < rds6_tcp_tc_count)
+		goto out;
+
+	list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) {
+		struct sock *sk = tc->t_sock->sk;
+		struct inet_sock *inet = inet_sk(sk);
+
+		tsinfo6.local_addr = sk->sk_v6_rcv_saddr;
+		tsinfo6.local_port = inet->inet_sport;
+		tsinfo6.peer_addr = sk->sk_v6_daddr;
+		tsinfo6.peer_port = inet->inet_dport;
+
+		tsinfo6.hdr_rem = tc->t_tinc_hdr_rem;
+		tsinfo6.data_rem = tc->t_tinc_data_rem;
+		tsinfo6.last_sent_nxt = tc->t_last_sent_nxt;
+		tsinfo6.last_expected_una = tc->t_last_expected_una;
+		tsinfo6.last_seen_una = tc->t_last_seen_una;
+
+		rds_info_copy(iter, &tsinfo6, sizeof(tsinfo6));
+	}
+
+out:
+	lens->nr = rds6_tcp_tc_count;
+	lens->each = sizeof(tsinfo6);
+
+	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
+}
+
 static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
 			       __u32 scope_id)
 {
@@ -628,6 +670,7 @@ static void rds_tcp_exit(void)
 	rds_tcp_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	rds_info_deregister_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
 	unregister_pernet_device(&rds_tcp_net_ops);
 	rds_tcp_destroy_conns();
 	rds_trans_unregister(&rds_tcp_transport);
@@ -659,6 +702,7 @@ static int rds_tcp_init(void)
 	rds_trans_register(&rds_tcp_transport);
 
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	rds_info_register_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
 
 	goto out;
 out_recv: