Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
* [PATCH net] rds: filter RDS_INFO_* getsockopt by caller's netns
@ 2026-05-06  7:50 Maoyi Xie
  2026-05-07  5:17 ` Allison Henderson
  0 siblings, 1 reply; 2+ messages in thread
From: Maoyi Xie @ 2026-05-06  7:50 UTC (permalink / raw)
  To: Allison Henderson
  Cc: David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
	Simon Horman, netdev, linux-rdma, rds-devel, linux-kernel,
	Maoyi Xie, Praveen Kakkolangara

From: Maoyi Xie <maoyi.xie@ntu.edu.sg>

The RDS_INFO_* family of getsockopt(2) options reads several
file-scope global lists that are not per-netns:

  rds_sock_info / rds6_sock_info,
  rds_sock_inc_info / rds6_sock_inc_info        -> rds_sock_list
  rds_tcp_tc_info / rds6_tcp_tc_info            -> rds_tcp_tc_list
  rds_conn_info / rds6_conn_info,
  rds_conn_message_info_cmn (for the *_SEND_MESSAGES and
  *_RETRANS_MESSAGES variants),
  rds_for_each_conn_info (for RDS_INFO_IB_CONNECTIONS)
                                                -> rds_conn_hash[]

The handlers do not filter by the caller's network namespace.
rds_info_getsockopt() has no netns or capable() check, and
rds_create() has no capable() check, so AF_RDS is reachable from
an unprivileged user namespace. As a result, an unprivileged
caller in a fresh user_ns plus netns can read the bound address
and sock inode of every RDS socket on the host, the peer address
of incoming messages on every RDS socket on the host, the peer
address and TCP sequence numbers of every rds-tcp connection on
the host, and the peer address and RDS sequence numbers of every
RDS connection on the host.

The rds-tcp transport is reachable from a non-initial netns (see
rds_set_transport()), so a one-shot init_net gate at
rds_info_getsockopt() would deny legitimate per-netns visibility
to rds-tcp callers. Instead, filter at each handler by comparing
the netns of the caller's socket to the netns of the list entry,
or to rds_conn_net(conn) for connection paths. Only copy entries
whose netns matches the caller. Counters (RDS_INFO_COUNTERS) are
aggregate statistics and remain global.

Reproducer (KASAN VM, rds and rds_tcp loaded): an AF_RDS socket
binds 127.0.0.1:4242 in init_net as root. A child process enters
a fresh user_ns plus netns and opens AF_RDS there, then calls
getsockopt(SOL_RDS, RDS_INFO_SOCKETS). Before this change, the
child sees the init_net socket. After this change, the child
sees zero entries.

Suggested-by: Allison Henderson <achender@kernel.org>
Co-developed-by: Praveen Kakkolangara <praveen.kakkolangara@aumovio.com>
Signed-off-by: Praveen Kakkolangara <praveen.kakkolangara@aumovio.com>
Signed-off-by: Maoyi Xie <maoyi.xie@ntu.edu.sg>
---
 net/rds/af_rds.c     | 24 ++++++++++++++++++++++--
 net/rds/connection.c | 13 +++++++++++++
 net/rds/tcp.c        | 25 +++++++++++++++++++++----
 3 files changed, 56 insertions(+), 6 deletions(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index b396c673d..469891131 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -729,6 +729,7 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
 			      struct rds_info_iterator *iter,
 			      struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(sock->sk);
 	struct rds_sock *rs;
 	struct rds_incoming *inc;
 	unsigned int total = 0;
@@ -738,6 +739,9 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
 	spin_lock_bh(&rds_sock_lock);
 
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
+		/* Only show sockets in the caller's netns. */
+		if (!net_eq(sock_net(rds_rs_to_sk(rs)), net))
+			continue;
 		/* This option only supports IPv4 sockets. */
 		if (!ipv6_addr_v4mapped(&rs->rs_bound_addr))
 			continue;
@@ -768,6 +772,7 @@ static void rds6_sock_inc_info(struct socket *sock, unsigned int len,
 			       struct rds_info_iterator *iter,
 			       struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(sock->sk);
 	struct rds_incoming *inc;
 	unsigned int total = 0;
 	struct rds_sock *rs;
@@ -777,6 +782,9 @@ static void rds6_sock_inc_info(struct socket *sock, unsigned int len,
 	spin_lock_bh(&rds_sock_lock);
 
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
+		/* Only show sockets in the caller's netns. */
+		if (!net_eq(sock_net(rds_rs_to_sk(rs)), net))
+			continue;
 		read_lock(&rs->rs_recv_lock);
 
 		list_for_each_entry(inc, &rs->rs_recv_queue, i_item) {
@@ -800,6 +808,7 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(sock->sk);
 	struct rds_info_socket sinfo;
 	unsigned int cnt = 0;
 	struct rds_sock *rs;
@@ -814,6 +823,9 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
 	}
 
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
+		/* Only show sockets in the caller's netns. */
+		if (!net_eq(sock_net(rds_rs_to_sk(rs)), net))
+			continue;
 		/* This option only supports IPv4 sockets. */
 		if (!ipv6_addr_v4mapped(&rs->rs_bound_addr))
 			continue;
@@ -841,17 +853,24 @@ static void rds6_sock_info(struct socket *sock, unsigned int len,
 			   struct rds_info_iterator *iter,
 			   struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(sock->sk);
 	struct rds6_info_socket sinfo6;
+	unsigned int cnt = 0;
 	struct rds_sock *rs;
 
 	len /= sizeof(struct rds6_info_socket);
 
 	spin_lock_bh(&rds_sock_lock);
 
-	if (len < rds_sock_count)
+	if (len < rds_sock_count) {
+		cnt = rds_sock_count;
 		goto out;
+	}
 
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
+		/* Only show sockets in the caller's netns. */
+		if (!net_eq(sock_net(rds_rs_to_sk(rs)), net))
+			continue;
 		sinfo6.sndbuf = rds_sk_sndbuf(rs);
 		sinfo6.rcvbuf = rds_sk_rcvbuf(rs);
 		sinfo6.bound_addr = rs->rs_bound_addr;
@@ -861,10 +880,11 @@ static void rds6_sock_info(struct socket *sock, unsigned int len,
 		sinfo6.inum = sock_i_ino(rds_rs_to_sk(rs));
 
 		rds_info_copy(iter, &sinfo6, sizeof(sinfo6));
+		cnt++;
 	}
 
  out:
-	lens->nr = rds_sock_count;
+	lens->nr = cnt;
 	lens->each = sizeof(struct rds6_info_socket);
 
 	spin_unlock_bh(&rds_sock_lock);
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 412441aaa..a73554816 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -568,6 +568,7 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 				      struct rds_info_lengths *lens,
 				      int want_send, bool isv6)
 {
+	struct net *net = sock_net(sock->sk);
 	struct hlist_head *head;
 	struct list_head *list;
 	struct rds_connection *conn;
@@ -590,6 +591,9 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 			struct rds_conn_path *cp;
 			int npaths;
 
+			/* Only show connections in the caller's netns. */
+			if (!net_eq(rds_conn_net(conn), net))
+				continue;
 			if (!isv6 && conn->c_isv6)
 				continue;
 
@@ -688,6 +692,7 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  u64 *buffer,
 			  size_t item_len)
 {
+	struct net *net = sock_net(sock->sk);
 	struct hlist_head *head;
 	struct rds_connection *conn;
 	size_t i;
@@ -700,6 +705,9 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 	for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
 	     i++, head++) {
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
+			/* Only show connections in the caller's netns. */
+			if (!net_eq(rds_conn_net(conn), net))
+				continue;
 
 			/* XXX no c_lock usage.. */
 			if (!visitor(conn, buffer))
@@ -726,6 +734,7 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 				    u64 *buffer,
 				    size_t item_len)
 {
+	struct net *net = sock_net(sock->sk);
 	struct hlist_head *head;
 	struct rds_connection *conn;
 	size_t i;
@@ -740,6 +749,10 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
 			struct rds_conn_path *cp;
 
+			/* Only show connections in the caller's netns. */
+			if (!net_eq(rds_conn_net(conn), net))
+				continue;
+
 			/* XXX We only copy the information from the first
 			 * path for now.  The problem is that if there are
 			 * more than one underlying paths, we cannot report
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 654e23d13..ef9e958ca 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -235,20 +235,27 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 			    struct rds_info_iterator *iter,
 			    struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(rds_sock->sk);
 	struct rds_info_tcp_socket tsinfo;
 	struct rds_tcp_connection *tc;
+	unsigned int cnt = 0;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
 
-	if (len / sizeof(tsinfo) < rds_tcp_tc_count)
+	if (len / sizeof(tsinfo) < rds_tcp_tc_count) {
+		cnt = rds_tcp_tc_count;
 		goto out;
+	}
 
 	list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) {
 		struct inet_sock *inet = inet_sk(tc->t_sock->sk);
 
 		if (tc->t_cpath->cp_conn->c_isv6)
 			continue;
+		/* Only show connections in the caller's netns. */
+		if (!net_eq(rds_conn_net(tc->t_cpath->cp_conn), net))
+			continue;
 
 		tsinfo.local_addr = inet->inet_saddr;
 		tsinfo.local_port = inet->inet_sport;
@@ -263,10 +270,11 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 		tsinfo.tos = tc->t_cpath->cp_conn->c_tos;
 
 		rds_info_copy(iter, &tsinfo, sizeof(tsinfo));
+		cnt++;
 	}
 
 out:
-	lens->nr = rds_tcp_tc_count;
+	lens->nr = cnt;
 	lens->each = sizeof(tsinfo);
 
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
@@ -281,19 +289,27 @@ static void rds6_tcp_tc_info(struct socket *sock, unsigned int len,
 			     struct rds_info_iterator *iter,
 			     struct rds_info_lengths *lens)
 {
+	struct net *net = sock_net(sock->sk);
 	struct rds6_info_tcp_socket tsinfo6;
 	struct rds_tcp_connection *tc;
+	unsigned int cnt = 0;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
 
-	if (len / sizeof(tsinfo6) < rds6_tcp_tc_count)
+	if (len / sizeof(tsinfo6) < rds6_tcp_tc_count) {
+		cnt = 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);
 
+		/* Only show connections in the caller's netns. */
+		if (!net_eq(rds_conn_net(tc->t_cpath->cp_conn), net))
+			continue;
+
 		tsinfo6.local_addr = sk->sk_v6_rcv_saddr;
 		tsinfo6.local_port = inet->inet_sport;
 		tsinfo6.peer_addr = sk->sk_v6_daddr;
@@ -306,10 +322,11 @@ static void rds6_tcp_tc_info(struct socket *sock, unsigned int len,
 		tsinfo6.last_seen_una = tc->t_last_seen_una;
 
 		rds_info_copy(iter, &tsinfo6, sizeof(tsinfo6));
+		cnt++;
 	}
 
 out:
-	lens->nr = rds6_tcp_tc_count;
+	lens->nr = cnt;
 	lens->each = sizeof(tsinfo6);
 
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);

base-commit: 028ef9c96e96197026887c0f092424679298aae8
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-05-07  5:17 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-06  7:50 [PATCH net] rds: filter RDS_INFO_* getsockopt by caller's netns Maoyi Xie
2026-05-07  5:17 ` Allison Henderson

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox