rds: tcp: atomically purge entries from rds_tcp_conn_list during netns delete

BugLink: http://bugs.launchpad.net/bugs/1752119
commit f10b4cff98c6977668434fbf5dd58695eeca2897 upstream.

The rds_tcp_kill_sock() function parses the rds_tcp_conn_list
to find the rds_connection entries marked for deletion as part
of the netns deletion under the protection of the rds_tcp_conn_lock.
Since the rds_tcp_conn_list tracks rds_tcp_connections (which
have a 1:1 mapping with rds_conn_path), multiple tc entries in
the rds_tcp_conn_list will map to a single rds_connection, and will
be deleted as part of the rds_conn_destroy() operation that is
done outside the rds_tcp_conn_lock.

The rds_tcp_conn_list traversal done under the protection of
rds_tcp_conn_lock should not leave any doomed tc entries in
the list after the rds_tcp_conn_lock is released, else another
concurrently executiong netns delete (for a differnt netns) thread
may trip on these entries.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index b7aa02358ac436b51b00baf02917dd97d85fc509..4df21e47d2ab9f675f00330a937f32dcd05a03c9 100644 (file)
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -307,7 +307,8 @@ static void rds_tcp_conn_free(void *arg)
        rdsdebug("freeing tc %p\n", tc);
 
        spin_lock_irqsave(&rds_tcp_conn_lock, flags);
-       list_del(&tc->t_tcp_node);
+       if (!tc->t_tcp_node_detached)
+               list_del(&tc->t_tcp_node);
        spin_unlock_irqrestore(&rds_tcp_conn_lock, flags);
 
        kmem_cache_free(rds_tcp_conn_slab, tc);
@@ -532,8 +533,12 @@ static void rds_tcp_kill_sock(struct net *net)
 
                if (net != c_net || !tc->t_sock)
                        continue;
-               if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn))
+               if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
                        list_move_tail(&tc->t_tcp_node, &tmp_list);
+               } else {
+                       list_del(&tc->t_tcp_node);
+                       tc->t_tcp_node_detached = true;
+               }
        }
        spin_unlock_irq(&rds_tcp_conn_lock);
        list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) {

diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 864ca7d8f01942ef84325e7dcf4d0d330c7e4ef3..c6fa080e9b6d08c76d500c0e16fb281f09acd2b3 100644 (file)
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -12,6 +12,7 @@ struct rds_tcp_incoming {
 struct rds_tcp_connection {
 
        struct list_head        t_tcp_node;
+       bool                    t_tcp_node_detached;
        struct rds_conn_path    *t_cpath;
        /* t_conn_path_lock synchronizes the connection establishment between
         * rds_tcp_accept_one and rds_tcp_conn_path_connect