net: make free_netdev() more lenient with unregistering devices

There are two flavors of handling netdev registration:
 - ones called without holding rtnl_lock: register_netdev() and
   unregister_netdev(); and
 - those called with rtnl_lock held: register_netdevice() and
   unregister_netdevice().

While the semantics of the former are pretty clear, the same can't
be said about the latter. The netdev_todo mechanism is utilized to
perform some of the device unregistering tasks and it hooks into
rtnl_unlock() so the locked variants can't actually finish the work.
In general free_netdev() does not mix well with locked calls. Most
drivers operating under rtnl_lock set dev->needs_free_netdev to true
and expect core to make the free_netdev() call some time later.

The part where this becomes most problematic is error paths. There is
no way to unwind the state cleanly after a call to register_netdevice(),
since unreg can't be performed fully without dropping locks.

Make free_netdev() more lenient, and defer the freeing if device
is being unregistered. This allows error paths to simply call
free_netdev() both after register_netdevice() failed, and after
a call to unregister_netdevice() but before dropping rtnl_lock.

Simplify the error paths which are currently doing gymnastics
around free_netdev() handling.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 15bbfaf943fd12dea78bf8eda8f024a49005e6ef..8b644113715e9db49effcaa60cfe45572304bb13 100644 (file)
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -284,9 +284,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
        return 0;
 
 out_free_newdev:
-       if (new_dev->reg_state == NETREG_UNINITIALIZED ||
-           new_dev->reg_state == NETREG_UNREGISTERED)
-               free_netdev(new_dev);
+       free_netdev(new_dev);
        return err;
 }
 

diff --git a/net/core/dev.c b/net/core/dev.c
index 8fa739259041aaa03585b5a7b8ebce862f4b7d1d..adde93cbca9f0b1934f45383d23cc61f899e0dd1 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10631,6 +10631,17 @@ void free_netdev(struct net_device *dev)
        struct napi_struct *p, *n;
 
        might_sleep();
+
+       /* When called immediately after register_netdevice() failed the unwind
+        * handling may still be dismantling the device. Handle that case by
+        * deferring the free.
+        */
+       if (dev->reg_state == NETREG_UNREGISTERING) {
+               ASSERT_RTNL();
+               dev->needs_free_netdev = true;
+               return;
+       }
+
        netif_free_tx_queues(dev);
        netif_free_rx_queues(dev);
 

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 79f514afb17d02e09521df37c195660b7ad92fdc..3d6ab194d0f58c909ada67d6bd6dd6f28576c932 100644 (file)
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3439,26 +3439,15 @@ replay:
 
        dev->ifindex = ifm->ifi_index;
 
-       if (ops->newlink) {
+       if (ops->newlink)
                err = ops->newlink(link_net ? : net, dev, tb, data, extack);
-               /* Drivers should set dev->needs_free_netdev
-                * and unregister it on failure after registration
-                * so that device could be finally freed in rtnl_unlock.
-                */
-               if (err < 0) {
-                       /* If device is not registered at all, free it now */
-                       if (dev->reg_state == NETREG_UNINITIALIZED ||
-                           dev->reg_state == NETREG_UNREGISTERED)
-                               free_netdev(dev);
-                       goto out;
-               }
-       } else {
+       else
                err = register_netdevice(dev);
-               if (err < 0) {
-                       free_netdev(dev);
-                       goto out;
-               }
+       if (err < 0) {
+               free_netdev(dev);
+               goto out;
        }
+
        err = rtnl_configure_link(dev, ifm);
        if (err < 0)
                goto out_unregister;