[PATCH RESEND net-next 2/2] net: Do not take net_rwsem in __rtnl_link_unregister()

[Kirill Tkhai]

This function calls call_netdevice_notifier(), which also
may take net_rwsem. So, we can't use net_rwsem here.

This patch makes callers of this functions take pernet_ops_rwsem,
like register_netdevice_notifier() does. This will protect
the modifications of net_namespace_list, and allows notifiers
to take it (they won't have to care about context).

Since __rtnl_link_unregister() is used on module load
and unload (which are not frequent operations), this looks
for me better, than make all call_netdevice_notifier()
always executing in "protected net_namespace_list" context.

Also, this fixes the problem we had a deal in 328fbe747ad4
"Close race between {un, }register_netdevice_notifier and ...",
and guarantees __rtnl_link_unregister() does not skip
exitting net.

Signed-off-by: Kirill Tkhai <ktk...@virtuozzo.com>
---
 drivers/net/dummy.c      |    2 ++
 drivers/net/ifb.c        |    2 ++
 net/core/net_namespace.c |    1 +
 net/core/rtnetlink.c     |    6 +++---
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 30b1c8512049..0d15a12a4560 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -219,6 +219,7 @@ static int __init dummy_init_module(void)
 {
        int i, err = 0;
 
+       down_write(&pernet_ops_rwsem);
        rtnl_lock();
        err = __rtnl_link_register(&dummy_link_ops);
        if (err < 0)
@@ -233,6 +234,7 @@ static int __init dummy_init_module(void)
 
 out:
        rtnl_unlock();
+       up_write(&pernet_ops_rwsem);
 
        return err;
 }
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 0008da7e9d4c..5f2897ec0edc 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -330,6 +330,7 @@ static int __init ifb_init_module(void)
 {
        int i, err;
 
+       down_write(&pernet_ops_rwsem);
        rtnl_lock();
        err = __rtnl_link_register(&ifb_link_ops);
        if (err < 0)
@@ -344,6 +345,7 @@ static int __init ifb_init_module(void)
 
 out:
        rtnl_unlock();
+       up_write(&pernet_ops_rwsem);
 
        return err;
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7fdf321d4997..a11e03f920d3 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -51,6 +51,7 @@ static bool init_net_initialized;
  * outside.
  */
 DECLARE_RWSEM(pernet_ops_rwsem);
+EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 #define MIN_PERNET_OPS_ID      \
        ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *))
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e86b28482ca7..45936922d7e2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -412,17 +412,17 @@ static void __rtnl_kill_links(struct net *net, struct 
rtnl_link_ops *ops)
  * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  *
- * The caller must hold the rtnl_mutex.
+ * The caller must hold the rtnl_mutex and guarantee net_namespace_list
+ * integrity (hold pernet_ops_rwsem for writing to close the race
+ * with setup_net() and cleanup_net()).
  */
 void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
        struct net *net;
 
-       down_read(&net_rwsem);
        for_each_net(net) {
                __rtnl_kill_links(net, ops);
        }
-       up_read(&net_rwsem);
        list_del(&ops->list);
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);