Merge branch 'ip_tunnel-support-per-netns-device-unregistration'

Kuniyuki Iwashima says:

====================
ip_tunnel: Support per-netns device unregistration.

Patch 1 - 3 are prep patches to unlink ip_tunnel device from
the hash table in ip_tunnel_dellink() only.

Patch 4 removes ip_tunnel_del() from ip_tunnel_uninit() to
ip_tunnel_dellink().

Patch 5 & 6 adds mutex to protect the per-netns hash table.

Patch 7 uses unregister_netdevice_queue_net() to support
cross-netns device unregistration.

v2: https://lore.kernel.org/netdev/20260909234422.2416506-1-kuniyu@google.com/
v1: https://lore.kernel.org/netdev/20260907225846.3787676-1-kuniyu@google.com/
====================

Link: https://patch.msgid.link/20260912230043.2586313-1-kuniyu@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

6 files changed, 108 insertions, 48 deletions

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index be4cc10f88ed..7102aa11fae2 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -218,6 +218,7 @@ struct ip_tunnel_net {
 	struct net_device *fb_tunnel_dev;
 	struct rtnl_link_ops *rtnl_link_ops;
 	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
+	struct mutex tunnels_lock;
 	struct ip_tunnel __rcu *collect_md_tun;
 	int type;
 };
@@ -401,7 +402,6 @@ int ip_tunnel_get_iflink(const struct net_device *dev);
 int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		       struct rtnl_link_ops *ops, char *devname);
 void ip_tunnel_delete_net(struct net *net, unsigned int id,
-			  struct rtnl_link_ops *ops,
 			  struct list_head *dev_to_kill);
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 82309efd417e..5e877018e006 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1084,7 +1084,7 @@ static int __net_init ipgre_init_net(struct net *net)
 static void __net_exit ipgre_exit_rtnl(struct net *net,
 				       struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_net(net, ipgre_net_id, &ipgre_link_ops, dev_to_kill);
+	ip_tunnel_delete_net(net, ipgre_net_id, dev_to_kill);
 }
 
 static struct pernet_operations ipgre_net_ops = {
@@ -1728,7 +1728,7 @@ static int __net_init ipgre_tap_init_net(struct net *net)
 static void __net_exit ipgre_tap_exit_rtnl(struct net *net,
 					   struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_net(net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill);
+	ip_tunnel_delete_net(net, gre_tap_net_id, dev_to_kill);
 }
 
 static struct pernet_operations ipgre_tap_net_ops = {
@@ -1747,7 +1747,7 @@ static int __net_init erspan_init_net(struct net *net)
 static void __net_exit erspan_exit_rtnl(struct net *net,
 					struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_net(net, erspan_net_id, &erspan_link_ops, dev_to_kill);
+	ip_tunnel_delete_net(net, erspan_net_id, dev_to_kill);
 }
 
 static struct pernet_operations erspan_net_ops = {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 13b5e35e8790..0875474a578a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -205,6 +205,11 @@ static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t)
 	hlist_del_init_rcu(&t->hash_node);
 }
 
+static bool ip_tunnel_unregistering(struct ip_tunnel *t)
+{
+	return hlist_unhashed(&t->hash_node);
+}
+
 static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 					struct ip_tunnel_parm_kern *parms,
 					int type)
@@ -219,7 +224,8 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 
 	ip_tunnel_flags_copy(flags, parms->i_flags);
 
-	hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(t, head, hash_node,
+				 lockdep_is_held(&itn->tunnels_lock)) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
 		    link == READ_ONCE(t->parms.link) &&
@@ -892,13 +898,37 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	netdev_state_change(dev);
 }
 
+static void __ip_tunnel_dellink(struct net *net, struct net_device *dev,
+				struct list_head *head)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct ip_tunnel_net *itn;
+
+	itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);
+	ip_tunnel_del(itn, tunnel);
+	unregister_netdevice_queue_net(net, dev, head);
+}
+
 int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
 		  int cmd)
 {
-	int err = 0;
 	struct ip_tunnel *t = netdev_priv(dev);
+	struct net *orig_net = dev_net(dev);
+	struct ip_tunnel_net *itn;
+	LIST_HEAD(dev_kill_list);
 	struct net *net = t->net;
-	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);
+	int err = 0;
+
+	DEBUG_NET_WARN_ON_ONCE(netdev_need_ops_lock(dev));
+
+	itn = net_generic(net, t->ip_tnl_net_id);
+
+	mutex_lock(&itn->tunnels_lock);
+
+	if (!check_net(net)) {
+		err = -EBUSY;
+		goto done;
+	}
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
@@ -959,7 +989,7 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
 			}
 		}
 
-		if (t) {
+		if (t && !ip_tunnel_unregistering(t)) {
 			err = 0;
 			ip_tunnel_update(itn, t, dev, p, true, 0);
 		} else {
@@ -982,7 +1012,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
 				goto done;
 			dev = t->dev;
 		}
-		unregister_netdevice(dev);
+
+		if (!ip_tunnel_unregistering(t))
+			__ip_tunnel_dellink(orig_net, dev, &dev_kill_list);
+
 		err = 0;
 		break;
 
@@ -991,6 +1024,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
 	}
 
 done:
+	mutex_unlock(&itn->tunnels_lock);
+
+	unregister_netdevice_many(&dev_kill_list);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ctl);
@@ -1085,8 +1122,10 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
 	itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);
 
 	if (itn->fb_tunnel_dev != dev) {
-		ip_tunnel_del(itn, netdev_priv(dev));
-		unregister_netdevice_queue(dev, head);
+		mutex_lock(&itn->tunnels_lock);
+		if (!ip_tunnel_unregistering(tunnel))
+			__ip_tunnel_dellink(dev_net(dev), dev, head);
+		mutex_unlock(&itn->tunnels_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
@@ -1118,6 +1157,8 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 	for (i = 0; i < IP_TNL_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&itn->tunnels[i]);
 
+	mutex_init(&itn->tunnels_lock);
+
 	if (!ops || !net_has_fallback_tunnels(net)) {
 		struct ip_tunnel_net *it_init_net;
 
@@ -1149,31 +1190,27 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
 void ip_tunnel_delete_net(struct net *net, unsigned int id,
-			  struct rtnl_link_ops *ops,
 			  struct list_head *head)
 {
 	struct ip_tunnel_net *itn = net_generic(net, id);
-	struct net_device *dev, *aux;
 	int h;
 
 	ASSERT_RTNL_NET(net);
 
-	for_each_netdev_safe(net, dev, aux)
-		if (dev->rtnl_link_ops == ops)
-			unregister_netdevice_queue(dev, head);
+	mutex_lock(&itn->tunnels_lock);
+
+	WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
-		struct ip_tunnel *t;
-		struct hlist_node *n;
 		struct hlist_head *thead = &itn->tunnels[h];
+		struct hlist_node *n;
+		struct ip_tunnel *t;
 
 		hlist_for_each_entry_safe(t, n, thead, hash_node)
-			/* If dev is in the same netns, it has already
-			 * been added to the list by the previous loop.
-			 */
-			if (!net_eq(dev_net(t->dev), net))
-				unregister_netdevice_queue(t->dev, head);
+			__ip_tunnel_dellink(net, t->dev, head);
 	}
+
+	mutex_unlock(&itn->tunnels_lock);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
 
@@ -1181,21 +1218,25 @@ int ip_tunnel_newlink(struct net *net, struct net_device *dev,
 		      struct nlattr *tb[], struct ip_tunnel_parm_kern *p,
 		      __u32 fwmark)
 {
-	struct ip_tunnel *nt;
 	struct ip_tunnel_net *itn;
+	struct ip_tunnel *nt;
+	int err = 0;
 	int mtu;
-	int err;
 
 	nt = netdev_priv(dev);
 	itn = net_generic(net, nt->ip_tnl_net_id);
 
+	mutex_lock(&itn->tunnels_lock);
+
 	if (nt->collect_md) {
 		if (rtnl_dereference(itn->collect_md_tun))
-			return -EEXIST;
+			err = -EEXIST;
 	} else {
 		if (ip_tunnel_find(itn, p, dev->type))
-			return -EEXIST;
+			err = -EEXIST;
 	}
+	if (err)
+		goto out;
 
 	nt->net = net;
 	nt->parms = *p;
@@ -1222,31 +1263,41 @@ int ip_tunnel_newlink(struct net *net, struct net_device *dev,
 		goto err_dev_set_mtu;
 
 	ip_tunnel_add(itn, nt);
-	return 0;
+out:
+	mutex_unlock(&itn->tunnels_lock);
+
+	return err;
 
 err_dev_set_mtu:
 	unregister_netdevice(dev);
 err_register_netdevice:
-	return err;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
 
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 			 struct ip_tunnel_parm_kern *p, __u32 fwmark)
 {
-	struct ip_tunnel *t;
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct net *net = tunnel->net;
-	struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+	struct ip_tunnel_net *itn;
+	struct ip_tunnel *t;
+	int err = 0;
+
+	itn = net_generic(net, tunnel->ip_tnl_net_id);
 
 	if (dev == itn->fb_tunnel_dev)
 		return -EINVAL;
 
+	mutex_lock(&itn->tunnels_lock);
+
 	t = ip_tunnel_find(itn, p, dev->type);
 
 	if (t) {
-		if (t->dev != dev)
-			return -EEXIST;
+		if (t->dev != dev) {
+			err = -EEXIST;
+			goto out;
+		}
 	} else {
 		t = tunnel;
 
@@ -1259,13 +1310,23 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 				nflags = IFF_POINTOPOINT;
 
 			if ((dev->flags ^ nflags) &
-			    (IFF_POINTOPOINT | IFF_BROADCAST))
-				return -EINVAL;
+			    (IFF_POINTOPOINT | IFF_BROADCAST)) {
+				err = -EINVAL;
+				goto out;
+			}
 		}
 	}
 
+	if (ip_tunnel_unregistering(t)) {
+		err = -ENODEV;
+		goto out;
+	}
+
 	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark);
-	return 0;
+out:
+	mutex_unlock(&itn->tunnels_lock);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
 
@@ -1303,13 +1364,6 @@ EXPORT_SYMBOL_GPL(__ip_tunnel_init);
 void ip_tunnel_uninit(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct net *net = tunnel->net;
-	struct ip_tunnel_net *itn;
-
-	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	ip_tunnel_del(itn, netdev_priv(dev));
-	if (itn->fb_tunnel_dev == dev)
-		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 3b80929994a0..c4f14d42df24 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -526,7 +526,7 @@ static int __net_init vti_init_net(struct net *net)
 static void __net_exit vti_exit_rtnl(struct net *net,
 				     struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_net(net, vti_net_id, &vti_link_ops, dev_to_kill);
+	ip_tunnel_delete_net(net, vti_net_id, dev_to_kill);
 }
 
 static struct pernet_operations vti_net_ops = {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index f684baf8e58f..2ffe64e736e0 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -645,7 +645,7 @@ static int __net_init ipip_init_net(struct net *net)
 static void __net_exit ipip_exit_rtnl(struct net *net,
 				      struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_net(net, ipip_net_id, &ipip_link_ops, dev_to_kill);
+	ip_tunnel_delete_net(net, ipip_net_id, dev_to_kill);
 }
 
 static struct pernet_operations ipip_net_ops = {
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1187bfc8a09d..e4c51ca47301 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -479,6 +479,7 @@ static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
 {
 	struct net_device *tunnel_dev, *new_dev;
 	struct ip_tunnel_parm_kern p = { };
+	LIST_HEAD(dev_kill_list);
 	int err;
 
 	tunnel_dev = __dev_get_by_name(net, "tunl0");
@@ -520,7 +521,8 @@ static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
 	return new_dev;
 
 out_unregister:
-	unregister_netdevice(new_dev);
+	new_dev->rtnl_link_ops->dellink(new_dev, &dev_kill_list);
+	unregister_netdevice_many(&dev_kill_list);
 out:
 	return ERR_PTR(-ENOBUFS);
 }
@@ -733,8 +735,12 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		ip_rt_multicast_event(in_dev);
 	}
 
-	if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify)
-		unregister_netdevice_queue(dev, head);
+	if (!notify) {
+		if (v->flags & VIFF_TUNNEL)
+			dev->rtnl_link_ops->dellink(dev, head);
+		else if (v->flags & VIFF_REGISTER)
+			unregister_netdevice_queue(dev, head);
+	}
 
 	netdev_put(dev, &v->dev_tracker);
 	return 0;