rds: tcp: Take explicit refcounts on struct net

It is incorrect for the rds_connection to piggyback on the
sock_net() refcount for the netns because this gives rise to
a chicken-and-egg problem during rds_conn_destroy. Instead explicitly
take a ref on the net, and hold the netns down till the connection
tear-down is complete.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 0e04dcc..1fa75ab 100644 (file)
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -429,6 +429,7 @@ void rds_conn_destroy(struct rds_connection *conn)
         */
        rds_cong_remove_conn(conn);
 
+       put_net(conn->c_net);
        kmem_cache_free(rds_conn_slab, conn);
 
        spin_lock_irqsave(&rds_conn_lock, flags);

diff --git a/net/rds/rds.h b/net/rds/rds.h
index 39518ef..82d38cc 100644 (file)
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -147,7 +147,7 @@ struct rds_connection {
 
        /* Protocol version */
        unsigned int            c_version;
-       possible_net_t          c_net;
+       struct net              *c_net;
 
        struct list_head        c_map_item;
        unsigned long           c_map_queued;
@@ -162,13 +162,13 @@ struct rds_connection {
 static inline
 struct net *rds_conn_net(struct rds_connection *conn)
 {
-       return read_pnet(&conn->c_net);
+       return conn->c_net;
 }
 
 static inline
 void rds_conn_net_set(struct rds_connection *conn, struct net *net)
 {
-       write_pnet(&conn->c_net, net);
+       conn->c_net = get_net(net);
 }
 
 #define RDS_FLAG_CONG_BITMAP   0x01

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index a973d3b..65c8e3b 100644 (file)
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -529,7 +529,7 @@ static void rds_tcp_kill_sock(struct net *net)
        flush_work(&rtn->rds_tcp_accept_w);
        spin_lock_irq(&rds_tcp_conn_lock);
        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);
+               struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
                if (net != c_net || !tc->t_sock)
                        continue;
@@ -584,7 +584,7 @@ static void rds_tcp_sysctl_reset(struct net *net)
 
        spin_lock_irq(&rds_tcp_conn_lock);
        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);
+               struct net *c_net = tc->t_cpath->cp_conn->c_net;
 
                if (net != c_net || !tc->t_sock)
                        continue;