1 files changed, 67 insertions, 34 deletions

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index c16f0a362c32..3cc2f303bf78 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -61,9 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0);
 
 static struct kmem_cache *rds_tcp_conn_slab;
 
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *fpos);
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos);
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos);
 
 static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
 static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -75,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 		/* data is per-net pointer */
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
-		.proc_handler   = rds_tcp_skbuf_handler,
+		.proc_handler   = rds_tcp_sndbuf_handler,
 		.extra1		= &rds_tcp_min_sndbuf,
 	},
 #define	RDS_TCP_RCVBUF	1
@@ -84,21 +85,11 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 		/* data is per-net pointer */
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
-		.proc_handler   = rds_tcp_skbuf_handler,
+		.proc_handler   = rds_tcp_rcvbuf_handler,
 		.extra1		= &rds_tcp_min_rcvbuf,
 	},
-	{ }
 };
 
-/* doing it this way avoids calling tcp_sk() */
-void rds_tcp_nonagle(struct socket *sock)
-{
-	int val = 1;
-
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val,
-			      sizeof(val));
-}
-
 u32 rds_tcp_write_seq(struct rds_tcp_connection *tc)
 {
 	/* seq# of the last byte of data in tcp send buffer */
@@ -176,10 +167,10 @@ void rds_tcp_reset_callbacks(struct socket *sock,
 	 */
 	atomic_set(&cp->cp_state, RDS_CONN_RESETTING);
 	wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags));
-	lock_sock(osock->sk);
 	/* reset receive side state for rds_tcp_data_recv() for osock  */
 	cancel_delayed_work_sync(&cp->cp_send_w);
 	cancel_delayed_work_sync(&cp->cp_recv_w);
+	lock_sock(osock->sk);
 	if (tc->t_tinc) {
 		rds_inc_put(&tc->t_tinc->ti_inc);
 		tc->t_tinc = NULL;
@@ -267,6 +258,7 @@ 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));
 	}
@@ -322,8 +314,8 @@ out:
 }
 #endif
 
-static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
-			       __u32 scope_id)
+int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
+			__u32 scope_id)
 {
 	struct net_device *dev = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -452,6 +444,12 @@ static void rds_tcp_destroy_conns(void)
 
 static void rds_tcp_exit(void);
 
+static u8 rds_tcp_get_tos_map(u8 tos)
+{
+	/* all user tos mapped to default 0 for TCP transport */
+	return 0;
+}
+
 struct rds_transport rds_tcp_transport = {
 	.laddr_check		= rds_tcp_laddr_check,
 	.xmit_path_prepare	= rds_tcp_xmit_path_prepare,
@@ -466,6 +464,7 @@ struct rds_transport rds_tcp_transport = {
 	.inc_free		= rds_tcp_inc_free,
 	.stats_info_copy	= rds_tcp_stats_info_copy,
 	.exit			= rds_tcp_exit,
+	.get_tos_map		= rds_tcp_get_tos_map,
 	.t_owner		= THIS_MODULE,
 	.t_name			= "tcp",
 	.t_type			= RDS_TRANS_TCP,
@@ -489,23 +488,36 @@ struct rds_tcp_net {
 /* All module specific customizations to the RDS-TCP socket should be done in
  * rds_tcp_tune() and applied after socket creation.
  */
-void rds_tcp_tune(struct socket *sock)
+bool rds_tcp_tune(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
-	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+	struct rds_tcp_net *rtn;
 
-	rds_tcp_nonagle(sock);
+	tcp_sock_set_nodelay(sock->sk);
 	lock_sock(sk);
+	/* TCP timer functions might access net namespace even after
+	 * a process which created this net namespace terminated.
+	 */
+	if (!sk->sk_net_refcnt) {
+		if (!maybe_get_net(net)) {
+			release_sock(sk);
+			return false;
+		}
+		sk_net_refcnt_upgrade(sk);
+		put_net(net);
+	}
+	rtn = net_generic(net, rds_tcp_netid);
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	}
 	if (rtn->rcvbuf_size > 0) {
-		sk->sk_sndbuf = rtn->rcvbuf_size;
+		sk->sk_rcvbuf = rtn->rcvbuf_size;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
 	release_sock(sk);
+	return true;
 }
 
 static void rds_tcp_accept_worker(struct work_struct *work)
@@ -543,14 +555,15 @@ static __net_init int rds_tcp_init_net(struct net *net)
 		tbl = kmemdup(rds_tcp_sysctl_table,
 			      sizeof(rds_tcp_sysctl_table), GFP_KERNEL);
 		if (!tbl) {
-			pr_warn("could not set allocate syctl table\n");
+			pr_warn("could not set allocate sysctl table\n");
 			return -ENOMEM;
 		}
 		rtn->ctl_table = tbl;
 	}
 	tbl[RDS_TCP_SNDBUF].data = &rtn->sndbuf_size;
 	tbl[RDS_TCP_RCVBUF].data = &rtn->rcvbuf_size;
-	rtn->rds_tcp_sysctl = register_net_sysctl(net, "net/rds/tcp", tbl);
+	rtn->rds_tcp_sysctl = register_net_sysctl_sz(net, "net/rds/tcp", tbl,
+						     ARRAY_SIZE(rds_tcp_sysctl_table));
 	if (!rtn->rds_tcp_sysctl) {
 		pr_warn("could not register sysctl\n");
 		err = -ENOMEM;
@@ -600,7 +613,7 @@ static void rds_tcp_kill_sock(struct net *net)
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
 		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
-		if (net != c_net || !tc->t_sock)
+		if (net != c_net)
 			continue;
 		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
 			list_move_tail(&tc->t_tcp_node, &tmp_list);
@@ -667,11 +680,10 @@ static void rds_tcp_sysctl_reset(struct net *net)
 	spin_unlock_irq(&rds_tcp_conn_lock);
 }
 
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *fpos)
+static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn,
+				 const struct ctl_table *ctl, int write,
+				 void *buffer, size_t *lenp, loff_t *fpos)
 {
-	struct net *net = current->nsproxy->net_ns;
 	int err;
 
 	err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos);
@@ -680,11 +692,34 @@ static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
 			*(int *)(ctl->extra1));
 		return err;
 	}
-	if (write)
+
+	if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) {
+		struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk);
+
 		rds_tcp_sysctl_reset(net);
+	}
+
 	return 0;
 }
 
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos)
+{
+	struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+					       sndbuf_size);
+
+	return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos)
+{
+	struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+					       rcvbuf_size);
+
+	return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
 static void rds_tcp_exit(void)
 {
 	rds_tcp_set_unloading();
@@ -701,13 +736,11 @@ static void rds_tcp_exit(void)
 }
 module_exit(rds_tcp_exit);
 
-static int rds_tcp_init(void)
+static int __init rds_tcp_init(void)
 {
 	int ret;
 
-	rds_tcp_conn_slab = kmem_cache_create("rds_tcp_connection",
-					      sizeof(struct rds_tcp_connection),
-					      0, 0, NULL);
+	rds_tcp_conn_slab = KMEM_CACHE(rds_tcp_connection, 0);
 	if (!rds_tcp_conn_slab) {
 		ret = -ENOMEM;
 		goto out;