net: Fix inconsistent teardown and release of private netdev state.

Network devices can allocate reasources and private memory using
netdev_ops->ndo_init().  However, the release of these resources
can occur in one of two different places.

Either netdev_ops->ndo_uninit() or netdev->destructor().

The decision of which operation frees the resources depends upon
whether it is necessary for all netdev refs to be released before it
is safe to perform the freeing.

netdev_ops->ndo_uninit() presumably can occur right after the
NETDEV_UNREGISTER notifier completes and the unicast and multicast
address lists are flushed.

netdev->destructor(), on the other hand, does not run until the
netdev references all go away.

Further complicating the situation is that netdev->destructor()
almost universally does also a free_netdev().

This creates a problem for the logic in register_netdevice().
Because all callers of register_netdevice() manage the freeing
of the netdev, and invoke free_netdev(dev) if register_netdevice()
fails.

If netdev_ops->ndo_init() succeeds, but something else fails inside
of register_netdevice(), it does call ndo_ops->ndo_uninit().  But
it is not able to invoke netdev->destructor().

This is because netdev->destructor() will do a free_netdev() and
then the caller of register_netdevice() will do the same.

However, this means that the resources that would normally be released
by netdev->destructor() will not be.

Over the years drivers have added local hacks to deal with this, by
invoking their destructor parts by hand when register_netdevice()
fails.

Many drivers do not try to deal with this, and instead we have leaks.

Let's close this hole by formalizing the distinction between what
private things need to be freed up by netdev->destructor() and whether
the driver needs unregister_netdevice() to perform the free_netdev().

netdev->priv_destructor() performs all actions to free up the private
resources that used to be freed by netdev->destructor(), except for
free_netdev().

netdev->needs_free_netdev is a boolean that indicates whether
free_netdev() should be done at the end of unregister_netdevice().

Now, register_netdevice() can sanely release all resources after
ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit()
and netdev->priv_destructor().

And at the end of unregister_netdevice(), we invoke
netdev->priv_destructor() and optionally call free_netdev().

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/bonding/bond_main.c

@@ -4192,7 +4192,6 @@ static void bond_destructor(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
-	free_netdev(bond_dev);
 }
 
 void bond_setup(struct net_device *bond_dev)
@@ -4212,7 +4211,8 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
 
-	bond_dev->destructor = bond_destructor;
+	bond_dev->needs_free_netdev = true;
+	bond_dev->priv_destructor = bond_destructor;
 
 	SET_NETDEV_DEVTYPE(bond_dev, &bond_type);
 
@@ -4736,7 +4736,7 @@ int bond_create(struct net *net, const char *name)
 
 	rtnl_unlock();
 	if (res < 0)
-		bond_destructor(bond_dev);
+		free_netdev(bond_dev);
 	return res;
 }
 

drivers/net/caif/caif_hsi.c

@@ -1121,7 +1121,7 @@ static void cfhsi_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->netdev_ops = &cfhsi_netdevops;
 	for (i = 0; i < CFHSI_PRIO_LAST; ++i)
 		skb_queue_head_init(&cfhsi->qhead[i]);

drivers/net/caif/caif_serial.c

@@ -428,7 +428,7 @@ static void caifdev_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CAIF_MAX_MTU;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&serdev->head);
 	serdev->common.link_select = CAIF_LINK_LOW_LATENCY;
 	serdev->common.use_frag = true;

drivers/net/caif/caif_spi.c

@@ -712,7 +712,7 @@ static void cfspi_setup(struct net_device *dev)
 	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&cfspi->qhead);
 	skb_queue_head_init(&cfspi->chead);
 	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;

drivers/net/caif/caif_virtio.c

@@ -617,7 +617,7 @@ static void cfv_netdev_setup(struct net_device *netdev)
 	netdev->tx_queue_len = 100;
 	netdev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	netdev->mtu = CFV_DEF_MTU_SIZE;
-	netdev->destructor = free_netdev;
+	netdev->needs_free_netdev = true;
 }
 
 /* Create debugfs counters for the device */

drivers/net/can/slcan.c

@@ -417,7 +417,7 @@ static int slc_open(struct net_device *dev)
 static void slc_free_netdev(struct net_device *dev)
 {
 	int i = dev->base_addr;
-	free_netdev(dev);
+
 	slcan_devs[i] = NULL;
 }
 
@@ -436,7 +436,8 @@ static const struct net_device_ops slc_netdev_ops = {
 static void slc_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &slc_netdev_ops;
-	dev->destructor		= slc_free_netdev;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= slc_free_netdev;
 
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
@@ -761,8 +762,6 @@ static void __exit slcan_exit(void)
 		if (sl->tty) {
 			printk(KERN_ERR "%s: tty discipline still running\n",
 			       dev->name);
-			/* Intentionally leak the control block. */
-			dev->destructor = NULL;
 		}
 
 		unregister_netdev(dev);

drivers/net/can/vcan.c

@@ -163,7 +163,7 @@ static void vcan_setup(struct net_device *dev)
 		dev->flags |= IFF_ECHO;
 
 	dev->netdev_ops		= &vcan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static struct rtnl_link_ops vcan_link_ops __read_mostly = {

drivers/net/can/vxcan.c

@@ -156,7 +156,7 @@ static void vxcan_setup(struct net_device *dev)
 	dev->tx_queue_len	= 0;
 	dev->flags		= (IFF_NOARP|IFF_ECHO);
 	dev->netdev_ops		= &vxcan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 /* forward declaration for rtnl_create_link() */

drivers/net/dummy.c

@@ -328,7 +328,6 @@ static void dummy_free_netdev(struct net_device *dev)
 	struct dummy_priv *priv = netdev_priv(dev);
 
 	kfree(priv->vfinfo);
-	free_netdev(dev);
 }
 
 static void dummy_setup(struct net_device *dev)
@@ -338,7 +337,8 @@ static void dummy_setup(struct net_device *dev)
 	/* Initialize the device structure. */
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
-	dev->destructor = dummy_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = dummy_free_netdev;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -4525,7 +4525,7 @@ static void dummy_setup(struct net_device *dev)
 	/* Initialize the device structure. */
 	dev->netdev_ops = &cxgb4_mgmt_netdev_ops;
 	dev->ethtool_ops = &cxgb4_mgmt_ethtool_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 }
 
 static int config_mgmt_dev(struct pci_dev *pdev)