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>

21 files changed, 48 insertions, 45 deletions

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 953b6728bd00..abc5f400fc71 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -813,7 +813,6 @@ static void vlan_dev_free(struct net_device *dev)
 
 	free_percpu(vlan->vlan_pcpu_stats);
 	vlan->vlan_pcpu_stats = NULL;
-	free_netdev(dev);
 }
 
 void vlan_setup(struct net_device *dev)
@@ -826,7 +825,8 @@ void vlan_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 
 	dev->netdev_ops		= &vlan_netdev_ops;
-	dev->destructor		= vlan_dev_free;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
 	dev->min_mtu		= 0;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index b25789abf7b9..10f7edfb176e 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1034,8 +1034,6 @@ static void batadv_softif_free(struct net_device *dev)
 	 * netdev and its private data (bat_priv)
 	 */
 	rcu_barrier();
-
-	free_netdev(dev);
 }
 
 /**
@@ -1047,7 +1045,8 @@ static void batadv_softif_init_early(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &batadv_netdev_ops;
-	dev->destructor = batadv_softif_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = batadv_softif_free;
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL;
 	dev->priv_flags |= IFF_NO_QUEUE;
 
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 608959989f8e..ab3b654b05cc 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -598,7 +598,7 @@ static void netdev_setup(struct net_device *dev)
 
 	dev->netdev_ops		= &netdev_ops;
 	dev->header_ops		= &header_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static struct device_type bt_type = {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 430b53e7d941..f0f3447e8aa4 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -379,7 +379,7 @@ void br_dev_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &br_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 1816fc9f1ee7..fe3c53efb949 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -392,14 +392,14 @@ static void chnl_net_destructor(struct net_device *dev)
 {
 	struct chnl_net *priv = netdev_priv(dev);
 	caif_free_client(&priv->chnl);
-	free_netdev(dev);
 }
 
 static void ipcaif_net_setup(struct net_device *dev)
 {
 	struct chnl_net *priv;
 	dev->netdev_ops = &netdev_ops;
-	dev->destructor = chnl_net_destructor;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = chnl_net_destructor;
 	dev->flags |= IFF_NOARP;
 	dev->flags |= IFF_POINTOPOINT;
 	dev->mtu = GPRS_PDP_MTU;
diff --git a/net/core/dev.c b/net/core/dev.c
index 84e1e86a4bce..4c15466305c3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7502,6 +7502,8 @@ out:
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
+	if (dev->priv_destructor)
+		dev->priv_destructor(dev);
 	goto out;
 }
 EXPORT_SYMBOL(register_netdevice);
@@ -7709,8 +7711,10 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 		WARN_ON(dev->dn_ptr);
 
-		if (dev->destructor)
-			dev->destructor(dev);
+		if (dev->priv_destructor)
+			dev->priv_destructor(dev);
+		if (dev->needs_free_netdev)
+			free_netdev(dev);
 
 		/* Report a network device has been unregistered */
 		rtnl_lock();
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index c73160fb11e7..0a0a392dc2bd 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -378,7 +378,6 @@ static void hsr_dev_destroy(struct net_device *hsr_dev)
 	del_timer_sync(&hsr->announce_timer);
 
 	synchronize_rcu();
-	free_netdev(hsr_dev);
 }
 
 static const struct net_device_ops hsr_device_ops = {
@@ -404,7 +403,8 @@ void hsr_dev_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &hsr_type);
 	dev->priv_flags |= IFF_NO_QUEUE;
 
-	dev->destructor = hsr_dev_destroy;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = hsr_dev_destroy;
 
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
 			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index d7efbf0dad20..0a866f332290 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -107,7 +107,7 @@ static void lowpan_setup(struct net_device *ldev)
 
 	ldev->netdev_ops	= &lowpan_netdev_ops;
 	ldev->header_ops	= &lowpan_header_ops;
-	ldev->destructor	= free_netdev;
+	ldev->needs_free_netdev	= true;
 	ldev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index b878ecbc0608..b436d0775631 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -967,7 +967,6 @@ static void ip_tunnel_dev_free(struct net_device *dev)
 	gro_cells_destroy(&tunnel->gro_cells);
 	dst_cache_destroy(&tunnel->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
@@ -1155,7 +1154,8 @@ int ip_tunnel_init(struct net_device *dev)
 	struct iphdr *iph = &tunnel->parms.iph;
 	int err;
 
-	dev->destructor	= ip_tunnel_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip_tunnel_dev_free;
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 551de4d023a8..b4f9622ee9f5 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -501,7 +501,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 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/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;
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index 74d09f91709e..3be852808a9d 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -65,7 +65,7 @@ static void irlan_eth_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops		= &irlan_eth_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->min_mtu		= 0;
 	dev->max_mtu		= ETH_MAX_MTU;
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 8b21af7321b9..f7c54ece3733 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -141,7 +141,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
 	dev->features		|= NETIF_F_LLTX;
 	dev->netdev_ops		= &l2tp_eth_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 8fae1a72e6a7..915d7e1b4545 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1213,7 +1213,6 @@ static const struct net_device_ops ieee80211_monitorif_ops = {
 static void ieee80211_if_free(struct net_device *dev)
 {
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static void ieee80211_if_setup(struct net_device *dev)
@@ -1221,7 +1220,8 @@ static void ieee80211_if_setup(struct net_device *dev)
 	ether_setup(dev);
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->netdev_ops = &ieee80211_dataif_ops;
-	dev->destructor = ieee80211_if_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ieee80211_if_free;
 }
 
 static void ieee80211_if_setup_no_queue(struct net_device *dev)
@@ -1905,7 +1905,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		ret = register_netdevice(ndev);
 		if (ret) {
-			ieee80211_if_free(ndev);
+			free_netdev(ndev);
 			return ret;
 		}
 	}
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 06019dba4b10..bd88a9b80773 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -526,8 +526,6 @@ static void mac802154_wpan_free(struct net_device *dev)
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	mac802154_llsec_destroy(&sdata->sec);
-
-	free_netdev(dev);
 }
 
 static void ieee802154_if_setup(struct net_device *dev)
@@ -593,7 +591,8 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
 					sdata->dev->dev_addr);
 
 		sdata->dev->header_ops = &mac802154_header_ops;
-		sdata->dev->destructor = mac802154_wpan_free;
+		sdata->dev->needs_free_netdev = true;
+		sdata->dev->priv_destructor = mac802154_wpan_free;
 		sdata->dev->netdev_ops = &mac802154_wpan_ops;
 		sdata->dev->ml_priv = &mac802154_mlme_wpan;
 		wpan_dev->promiscuous_mode = false;
@@ -608,7 +607,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
 
 		break;
 	case NL802154_IFTYPE_MONITOR:
-		sdata->dev->destructor = free_netdev;
+		sdata->dev->needs_free_netdev = true;
 		sdata->dev->netdev_ops = &mac802154_monitor_ops;
 		wpan_dev->promiscuous_mode = true;
 		break;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 89193a634da4..04a3128adcf0 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -94,7 +94,6 @@ static void internal_dev_destructor(struct net_device *dev)
 	struct vport *vport = ovs_internal_dev_get_vport(dev);
 
 	ovs_vport_free(vport);
-	free_netdev(dev);
 }
 
 static void
@@ -156,7 +155,8 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
 			      IFF_PHONY_HEADROOM | IFF_NO_QUEUE;
-	netdev->destructor = internal_dev_destructor;
+	netdev->needs_free_netdev = true;
+	netdev->priv_destructor = internal_dev_destructor;
 	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->rtnl_link_ops = &internal_dev_link_ops;
 
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index 21c28b51be94..2c9337946e30 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -236,7 +236,7 @@ static void gprs_setup(struct net_device *dev)
 	dev->tx_queue_len	= 10;
 
 	dev->netdev_ops		= &gprs_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 /*