[PATCH net v3 1/1] net: cap advertised IP tunnel headroom

IP tunnel devices derive their advertised needed_headroom and, for IP6GRE
devices with header_ops, hard_header_len from lower output devices. A stack
of user-created devices can make the derived value larger than the 16-bit
skb header offsets can represent. Once IP output reserves it, skb head
expansion can wrap those offsets.

The runtime transmit path already caps a growing needed_headroom at 512.
Apply the cap when configuration publishes headroom or header lengths
derived from a lower output device.

Capping the advertised value is safe: IP tunnel transmit still expands the
skb when the packet needs more headroom. A nonsensical stacked configuration
can therefore incur an extra reallocation, but it cannot publish an unbounded
reservation to upper layers.

Fixes: 1a37e412a022 ("net: Use 16bits for *_headers fields of struct skbuff")
Cc: [email protected]
Reported-by: Vega <[email protected]>
Signed-off-by: Zhiling Zou <[email protected]>
---
changes in v3:
- Split netkit handling into a separate follow-up.
- Explain why capping advertised headroom is safe.
- Use local variables for derived headroom.
- v2 Link: https://lore.kernel.org/all/0ae4aa29223b89049727aec4d36f144bad41537e.1785476387.git.zhilinz@nebusec.ai/

changes in v2:
- Move the fix from IP send paths to tunnel and netkit device control paths.
- Cap advertised IP tunnel headroom at 512 and reject netkit headroom
  values above that limit at device creation.
- v1 Link: https://lore.kernel.org/all/0c6c64e9bbd71a0decc8504a384061e0e631be13.1785054561.git.zhilinz@nebusec.ai/

 include/net/ip_tunnels.h | 11 +++++++++--
 net/ipv4/ip_tunnel.c     |  2 +-
 net/ipv6/ip6_gre.c       | 10 ++++++----
 net/ipv6/ip6_tunnel.c    |  7 +++++--
 net/ipv6/sit.c           |  2 +-
 5 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d708b66e55cda..85e3455cea259 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -629,8 +629,7 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 			  int headroom, bool reply);
 
-static inline void ip_tunnel_adj_headroom(struct net_device *dev,
-					  unsigned int headroom)
+static inline unsigned int ip_tunnel_limit_headroom(unsigned int headroom)
 {
 	/* we must cap headroom to some upperlimit, else pskb_expand_head
 	 * will overflow header offsets in skb_headers_offset_update().
@@ -640,6 +639,14 @@ static inline void ip_tunnel_adj_headroom(struct net_device *dev,
 	if (headroom > max_allowed)
 		headroom = max_allowed;
 
+	return headroom;
+}
+
+static inline void ip_tunnel_adj_headroom(struct net_device *dev,
+					  unsigned int headroom)
+{
+	headroom = ip_tunnel_limit_headroom(headroom);
+
 	if (headroom > READ_ONCE(dev->needed_headroom))
 		WRITE_ONCE(dev->needed_headroom, headroom);
 }
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 9d114bd575f92..5b1f180485d42 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		mtu = min(tdev->mtu, IP_MAX_MTU);
 	}
 
-	dev->needed_headroom = t_hlen + hlen;
+	dev->needed_headroom = ip_tunnel_limit_headroom(t_hlen + hlen);
 	mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
 
 	if (mtu < IPV4_MIN_MTU)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b843116e9b703..cc757586be90a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1137,13 +1137,15 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
 			return;
 
 		if (rt->dst.dev) {
-			unsigned short dst_len = rt->dst.dev->hard_header_len +
-						 t_hlen;
+			unsigned int headroom;
+
+			headroom = rt->dst.dev->hard_header_len + t_hlen;
+			headroom = ip_tunnel_limit_headroom(headroom);
 
 			if (t->dev->header_ops)
-				dev->hard_header_len = dst_len;
+				dev->hard_header_len = headroom;
 			else
-				dev->needed_headroom = dst_len;
+				dev->needed_headroom = headroom;
 
 			if (set_mtu) {
 				int mtu = rt->dst.dev->mtu - t_hlen;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index bf8e40af60b08..2c941acb081fa 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1522,8 +1522,11 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 			tdev = __dev_get_by_index(t->net, p->link);
 
 		if (tdev) {
-			dev->needed_headroom = tdev->hard_header_len +
-				tdev->needed_headroom + t_hlen;
+			unsigned int headroom;
+
+			headroom = tdev->hard_header_len + tdev->needed_headroom;
+			headroom += t_hlen;
+			dev->needed_headroom = ip_tunnel_limit_headroom(headroom);
 			mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
 
 			mtu = mtu - t_hlen;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a38b24fb83842..19b7fa8d1a2a0 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1131,7 +1131,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 		WRITE_ONCE(dev->mtu, mtu);
 		hlen = tdev->hard_header_len + tdev->needed_headroom;
 	}
-	dev->needed_headroom = t_hlen + hlen;
+	dev->needed_headroom = ip_tunnel_limit_headroom(t_hlen + hlen);
 }
 
 static void ipip6_tunnel_update(struct ip_tunnel *t,
-- 
2.43.0