vxlan: add adjacent link to limit depth level

Current vxlan code doesn't limit the number of nested devices.
Nested devices would be handled recursively and this routine needs
huge stack memory. So, unlimited nested devices could make
stack overflow.

In order to fix this issue, this patch adds adjacent links.
The adjacent link APIs internally check the depth level.

Test commands:
    ip link add dummy0 type dummy
    ip link add vxlan0 type vxlan id 0 group 239.1.1.1 dev dummy0 \
	    dstport 4789
    for i in {1..100}
    do
	    let A=$i-1
	    ip link add vxlan$i type vxlan id $i group 239.1.1.1 \
		    dev vxlan$A dstport 4789
    done
    ip link del dummy0

The top upper link is vxlan100 and the lowest link is vxlan0.
When vxlan0 is deleting, the upper devices will be deleted recursively.
It needs huge stack memory so it makes stack overflow.

Splat looks like:
[  229.628477] =============================================================================
[  229.629785] BUG page->ptl (Not tainted): Padding overwritten. 0x0000000026abf214-0x0000000091f6abb2
[  229.629785] -----------------------------------------------------------------------------
[  229.629785]
[  229.655439] ==================================================================
[  229.629785] INFO: Slab 0x00000000ff7cfda8 objects=19 used=19 fp=0x00000000fe33776c flags=0x200000000010200
[  229.655688] BUG: KASAN: stack-out-of-bounds in unmap_single_vma+0x25a/0x2e0
[  229.655688] Read of size 8 at addr ffff888113076928 by task vlan-network-in/2334
[  229.655688]
[  229.629785] Padding 0000000026abf214: 00 80 14 0d 81 88 ff ff 68 91 81 14 81 88 ff ff  ........h.......
[  229.629785] Padding 0000000001e24790: 38 91 81 14 81 88 ff ff 68 91 81 14 81 88 ff ff  8.......h.......
[  229.629785] Padding 00000000b39397c8: 33 30 62 a7 ff ff ff ff ff eb 60 22 10 f1 ff 1f  30b.......`"....
[  229.629785] Padding 00000000bc98f53a: 80 60 07 13 81 88 ff ff 00 80 14 0d 81 88 ff ff  .`..............
[  229.629785] Padding 000000002aa8123d: 68 91 81 14 81 88 ff ff f7 21 17 a7 ff ff ff ff  h........!......
[  229.629785] Padding 000000001c8c2369: 08 81 14 0d 81 88 ff ff 03 02 00 00 00 00 00 00  ................
[  229.629785] Padding 000000004e290c5d: 21 90 a2 21 10 ed ff ff 00 00 00 00 00 fc ff df  !..!............
[  229.629785] Padding 000000000e25d731: 18 60 07 13 81 88 ff ff c0 8b 13 05 81 88 ff ff  .`..............
[  229.629785] Padding 000000007adc7ab3: b3 8a b5 41 00 00 00 00                          ...A....
[  229.629785] FIX page->ptl: Restoring 0x0000000026abf214-0x0000000091f6abb2=0x5a
[  ... ]

Fixes: acaf4e7 ("net: vxlan: when lower dev unregisters remove vxlan dev as well")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: TaeheeYoo

drivers/net/vxlan.c

@@ -3566,25 +3566,28 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct net_device *remote_dev = NULL;
 	struct vxlan_fdb *f = NULL;
 	bool unregister = false;
+	struct vxlan_rdst *dst;
 	int err;
 
+	dst = &vxlan->default_dst;
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
 	if (err)
 		return err;
 
 	dev->ethtool_ops = &vxlan_ethtool_ops;
 
 	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+	if (!vxlan_addr_any(&dst->remote_ip)) {
 		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &vxlan->default_dst.remote_ip,
+				       &dst->remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
 				       vxlan->cfg.dst_port,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_ifindex,
+				       dst->remote_vni,
+				       dst->remote_vni,
+				       dst->remote_ifindex,
 				       NTF_SELF, &f);
 		if (err)
 			return err;
@@ -3595,26 +3598,41 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 		goto errout;
 	unregister = true;
 
+	if (dst->remote_ifindex) {
+		remote_dev = __dev_get_by_index(net, dst->remote_ifindex);
+		if (!remote_dev)
+			goto errout;
+
+		err = netdev_upper_dev_link(remote_dev, dev, extack);
+		if (err)
+			goto errout;
+	}
+
 	err = rtnl_configure_link(dev, NULL);
 	if (err)
-		goto errout;
+		goto unlink;
 
 	if (f) {
-		vxlan_fdb_insert(vxlan, all_zeros_mac,
-				 vxlan->default_dst.remote_vni, f);
+		vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f);
 
 		/* notify default fdb entry */
 		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
 				       RTM_NEWNEIGH, true, extack);
 		if (err) {
 			vxlan_fdb_destroy(vxlan, f, false, false);
+			if (remote_dev)
+				netdev_upper_dev_unlink(remote_dev, dev);
 			goto unregister;
 		}
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
+	if (remote_dev)
+		dst->remote_dev = remote_dev;
 	return 0;
-
+unlink:
+	if (remote_dev)
+		netdev_upper_dev_unlink(remote_dev, dev);
 errout:
 	/* unregister_netdevice() destroys the default FDB entry with deletion
 	 * notification. But the addition notification was not sent yet, so
@@ -3932,11 +3950,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct net_device *lowerdev;
 	struct vxlan_config conf;
+	struct vxlan_rdst *dst;
 	int err;
 
+	dst = &vxlan->default_dst;
 	err = vxlan_nl2conf(tb, data, dev, &conf, true, extack);
 	if (err)
 		return err;
@@ -3946,6 +3965,11 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev,
+					     extack);
+	if (err)
+		return err;
+
 	/* handle default dst entry */
 	if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) {
 		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
@@ -3962,6 +3986,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       NTF_SELF, true, extack);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+				netdev_adjacent_change_abort(dst->remote_dev,
+							     lowerdev, dev);
 				return err;
 			}
 		}
@@ -3979,6 +4005,11 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (conf.age_interval != vxlan->cfg.age_interval)
 		mod_timer(&vxlan->age_timer, jiffies);
 
+	netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev);
+	if (lowerdev && lowerdev != dst->remote_dev)
+		dst->remote_dev = lowerdev;
+
+	netdev_update_lockdep_key(lowerdev);
 	vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true);
 	return 0;
 }
@@ -3991,6 +4022,8 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
+	if (vxlan->default_dst.remote_dev)
+		netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev);
 }
 
 static size_t vxlan_get_size(const struct net_device *dev)

include/net/vxlan.h

@@ -197,6 +197,7 @@ struct vxlan_rdst {
 	u8			 offloaded:1;
 	__be32			 remote_vni;
 	u32			 remote_ifindex;
+	struct net_device	 *remote_dev;
 	struct list_head	 list;
 	struct rcu_head		 rcu;
 	struct dst_cache	 dst_cache;