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 <davem@davemloft.net>

5 files changed, 17 insertions, 16 deletions

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0c5b4caa1949..64eea3962733 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -991,13 +991,13 @@ static void ip6gre_dev_free(struct net_device *dev)
 
 	dst_cache_destroy(&t->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static void ip6gre_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &ip6gre_netdev_ops;
-	dev->destructor = ip6gre_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6gre_dev_free;
 
 	dev->type = ARPHRD_IP6GRE;
 
@@ -1148,7 +1148,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	ip6gre_dev_free(ign->fb_tunnel_dev);
+	free_netdev(ign->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
 }
@@ -1300,7 +1300,8 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &ip6gre_tap_netdev_ops;
-	dev->destructor = ip6gre_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6gre_dev_free;
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9b37f9747fc6..c3581973f5d7 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -254,7 +254,6 @@ static void ip6_dev_free(struct net_device *dev)
 	gro_cells_destroy(&t->gro_cells);
 	dst_cache_destroy(&t->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static int ip6_tnl_create2(struct net_device *dev)
@@ -322,7 +321,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	return t;
 
 failed_free:
-	ip6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return ERR_PTR(err);
 }
@@ -1777,7 +1776,8 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 static void ip6_tnl_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &ip6_tnl_netdev_ops;
-	dev->destructor = ip6_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->flags |= IFF_NOARP;
@@ -2224,7 +2224,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	return 0;
 
 err_register:
-	ip6_dev_free(ip6n->fb_tnl_dev);
+	free_netdev(ip6n->fb_tnl_dev);
 err_alloc_dev:
 	return err;
 }
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index d67ef56454b2..837ea1eefe7f 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -180,7 +180,6 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
 static void vti6_dev_free(struct net_device *dev)
 {
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static int vti6_tnl_create2(struct net_device *dev)
@@ -235,7 +234,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	return t;
 
 failed_free:
-	vti6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return NULL;
 }
@@ -842,7 +841,8 @@ static const struct net_device_ops vti6_netdev_ops = {
 static void vti6_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &vti6_netdev_ops;
-	dev->destructor = vti6_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
@@ -1100,7 +1100,7 @@ static int __net_init vti6_init_net(struct net *net)
 	return 0;
 
 err_register:
-	vti6_dev_free(ip6n->fb_tnl_dev);
+	free_netdev(ip6n->fb_tnl_dev);
 err_alloc_dev:
 	return err;
 }
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 374997d26488..2ecb39b943b5 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -733,7 +733,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->mtu		= 1500 - sizeof(struct ipv6hdr) - 8;
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 61e5902f0687..2378503577b0 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -265,7 +265,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	return nt;
 
 failed_free:
-	ipip6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return NULL;
 }
@@ -1336,7 +1336,6 @@ static void ipip6_dev_free(struct net_device *dev)
 
 	dst_cache_destroy(&tunnel->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 #define SIT_FEATURES (NETIF_F_SG	   | \
@@ -1351,7 +1350,8 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	dev->netdev_ops		= &ipip6_netdev_ops;
-	dev->destructor		= ipip6_dev_free;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;