ipvlan: Protect ipvl_port.ipvlans with mutex.

struct ipvl_port is shared between a lower device and its upper
ipvlan devices.

All upper devices are linked to ipvl_port.ipvlans.

Once RTNL is removed, the list can be modified concurrently from
different netns due to device removal.

Let's protect it with a per-port mutex.

NETDEV_PRECHANGEUPPER and NETDEV_CHANGEUPPER are explicitly
skipped to avoid deadlock for netdev_upper_dev_unlink() called
from NETDEV_UNREGISTER.

Note that __ipvtap_dellink_ptr is added for CONFIG_IPVLAN=y
but CONFIG_TAP=m and CONFIG_IPVTAP=m.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260703001009.1572444-14-kuniyu@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

drivers/net/ipvlan/ipvlan.h

@@ -91,6 +91,7 @@ struct ipvl_port {
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	spinlock_t		addrs_lock; /* guards hash-table and addrs */
 	struct list_head	ipvlans;
+	struct mutex		pnodes_lock;
 	u16			mode;
 	u16			flags;
 	u16			dev_id_start;
@@ -168,7 +169,7 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 		     unsigned int len, bool success, bool mcast);
 int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack);
-void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
+void __ipvlan_link_delete(struct net_device *dev, struct list_head *head);
 void ipvlan_link_setup(struct net_device *dev);
 int ipvlan_link_register(struct rtnl_link_ops *ops);
 #ifdef CONFIG_IPVLAN_L3S
@@ -207,4 +208,9 @@ static inline bool netif_is_ipvlan_port(const struct net_device *dev)
 	return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame;
 }
 
+#if IS_ENABLED(CONFIG_IPVTAP)
+extern void (*__ipvtap_dellink_ptr)(struct net_device *dev,
+				    struct list_head *head);
+#endif
+
 #endif /* __IPVLAN_H */

drivers/net/ipvlan/ipvlan_main.c

@@ -7,6 +7,12 @@
 
 #include "ipvlan.h"
 
+#if IS_ENABLED(CONFIG_IPVTAP)
+void (*__ipvtap_dellink_ptr)(struct net_device *dev,
+			     struct list_head *head);
+EXPORT_SYMBOL(__ipvtap_dellink_ptr);
+#endif
+
 static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 				struct netlink_ext_ack *extack)
 {
@@ -16,6 +22,8 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 
 	ASSERT_RTNL();
 	if (port->mode != nval) {
+		mutex_lock(&port->pnodes_lock);
+
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			flags = ipvlan->dev->flags;
 			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
@@ -40,6 +48,8 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 			ipvlan_l3s_unregister(port);
 		}
 		port->mode = nval;
+
+		mutex_unlock(&port->pnodes_lock);
 	}
 	return 0;
 
@@ -56,6 +66,8 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
 					 NULL);
 	}
 
+	mutex_unlock(&port->pnodes_lock);
+
 	return err;
 }
 
@@ -76,6 +88,7 @@ static int ipvlan_port_create(struct net_device *dev)
 		INIT_HLIST_HEAD(&port->hlhead[idx]);
 
 	spin_lock_init(&port->addrs_lock);
+	mutex_init(&port->pnodes_lock);
 	skb_queue_head_init(&port->backlog);
 	INIT_WORK(&port->wq, ipvlan_process_multicast);
 	ida_init(&port->ida);
@@ -676,7 +689,10 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 	if (err)
 		goto unlink_netdev;
 
+	mutex_lock(&port->pnodes_lock);
 	list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
+	mutex_unlock(&port->pnodes_lock);
+
 	netif_stacked_transfer_operstate(phy_dev, dev);
 	return 0;
 
@@ -690,7 +706,7 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 }
 EXPORT_SYMBOL_GPL(ipvlan_link_new);
 
-void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+void __ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
@@ -708,7 +724,16 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
 }
-EXPORT_SYMBOL_GPL(ipvlan_link_delete);
+EXPORT_SYMBOL(__ipvlan_link_delete);
+
+static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	mutex_lock(&ipvlan->port->pnodes_lock);
+	__ipvlan_link_delete(dev, head);
+	mutex_unlock(&ipvlan->port->pnodes_lock);
+}
 
 void ipvlan_link_setup(struct net_device *dev)
 {
@@ -770,10 +795,16 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	struct ipvl_port *port;
 	LIST_HEAD(lst_kill);
 
+	if (event == NETDEV_PRECHANGEUPPER ||
+	    event == NETDEV_CHANGEUPPER)
+		return ret;
+
 	port = ipvlan_port_get(dev);
 	if (!port)
 		return ret;
 
+	mutex_lock(&port->pnodes_lock);
+
 	switch (event) {
 	case NETDEV_UP:
 	case NETDEV_DOWN:
@@ -800,9 +831,15 @@ static int ipvlan_device_event(struct notifier_block *unused,
 		if (dev->reg_state != NETREG_UNREGISTERING)
 			break;
 
-		list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode)
+		list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) {
-			ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev,
+#if IS_ENABLED(CONFIG_IPVTAP)
-							    &lst_kill);
+			if (ipvlan->dev->rtnl_link_ops != &ipvlan_link_ops)
+				__ipvtap_dellink_ptr(ipvlan->dev, &lst_kill);
+			else
+#endif
+				__ipvlan_link_delete(ipvlan->dev, &lst_kill);
+		}
+
 		unregister_netdevice_many(&lst_kill);
 		break;
 
@@ -850,6 +887,8 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			call_netdevice_notifiers(event, ipvlan->dev);
 	}
 
+	mutex_unlock(&port->pnodes_lock);
+
 	ipvlan_port_put(port);
 
 	return ret;

drivers/net/ipvlan/ipvtap.c

@@ -109,14 +109,24 @@ static int ipvtap_newlink(struct net_device *dev,
 	return err;
 }
 
+static void __ipvtap_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+
+	netdev_rx_handler_unregister(dev);
+	tap_del_queues(&vlantap->tap);
+	__ipvlan_link_delete(dev, head);
+}
+
 static void ipvtap_dellink(struct net_device *dev,
 			   struct list_head *head)
 {
-	struct ipvtap_dev *vlan = netdev_priv(dev);
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+	struct ipvl_port *port = vlantap->vlan.port;
 
-	netdev_rx_handler_unregister(dev);
+	mutex_lock(&port->pnodes_lock);
-	tap_del_queues(&vlan->tap);
+	__ipvtap_dellink(dev, head);
-	ipvlan_link_delete(dev, head);
+	mutex_unlock(&port->pnodes_lock);
 }
 
 static void ipvtap_setup(struct net_device *dev)
@@ -198,6 +208,8 @@ static int __init ipvtap_init(void)
 {
 	int err;
 
+	__ipvtap_dellink_ptr = __ipvtap_dellink;
+
 	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
 			      THIS_MODULE);
 	if (err)
@@ -224,6 +236,8 @@ static int __init ipvtap_init(void)
 out2:
 	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
 out1:
+	__ipvtap_dellink_ptr = NULL;
+
 	return err;
 }
 module_init(ipvtap_init);
@@ -234,6 +248,7 @@ static void __exit ipvtap_exit(void)
 	unregister_netdevice_notifier(&ipvtap_notifier_block);
 	class_unregister(&ipvtap_class);
 	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+	__ipvtap_dellink_ptr = NULL;
 }
 module_exit(ipvtap_exit);
 MODULE_ALIAS_RTNL_LINK("ipvtap");