From 505b6d296c486ef7d1274f279d4c43a172f63224 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Thu, 13 Aug 2026 00:22:34 +0800 Subject: [PATCH 1/2] ip6_gre: fix hardware header length for NBMA tunnels ip6gre_tnl_link_config_route() accumulates the lower device's hardware header length into dev->hard_header_len whenever header_ops is set. This is incorrect for both users of header_ops. ip6gretap and ip6erspan have a fixed Ethernet hardware header length. For an NBMA ip6gre tunnel, ip6gre_header() creates only the GRE header, the optional FOU or GUE header, and the outer IPv6 header. The lower device header is headroom needed later, not part of the tunnel device's hardware header. Keep the lower device header in needed_headroom. Set hard_header_len to the tunnel header length only for ARPHRD_IP6GRE devices with header_ops, and leave the fixed Ethernet header length unchanged for tap and erspan devices. Fixes: 832ba596494b ("net: ip6_gre: set dev->hard_header_len when using header_ops") Cc: stable@vger.kernel.org Suggested-by: Ido Schimmel Signed-off-by: Zhiling Zou Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/64b46542bbe1701f07702aaa50273e2a87903db5.1786542637.git.zhilinz@nebusec.ai Signed-off-by: Paolo Abeni --- net/ipv6/ip6_gre.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b843116e9b70..70c171091020 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1137,13 +1137,8 @@ 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; - - if (t->dev->header_ops) - dev->hard_header_len = dst_len; - else - dev->needed_headroom = dst_len; + dev->needed_headroom = rt->dst.dev->hard_header_len + + t_hlen; if (set_mtu) { int mtu = rt->dst.dev->mtu - t_hlen; @@ -1171,8 +1166,8 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - if (tunnel->dev->header_ops) - tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + if (tunnel->dev->header_ops && tunnel->dev->type == ARPHRD_IP6GRE) + tunnel->dev->hard_header_len = t_hlen; else tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; From 6b222adeb9340306e2ff97127c76117abb9b3df8 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Thu, 13 Aug 2026 00:22:35 +0800 Subject: [PATCH 2/2] net: cap advertised IP tunnel headroom IP tunnel devices derive their advertised needed_headroom 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 same cap when tunnel configuration publishes needed_headroom derived from a lower output device. Capping the advertised value is safe: IP tunnel transmit still expands the skb when a 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: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/ba04a1fd6bfae2377607fad5d8f80f7eb80fd4c4.1786542637.git.zhilinz@nebusec.ai Signed-off-by: Paolo Abeni --- include/net/ip_tunnels.h | 11 +++++++++-- net/ipv4/ip_tunnel.c | 2 +- net/ipv6/ip6_gre.c | 7 +++++-- net/ipv6/ip6_tunnel.c | 7 +++++-- net/ipv6/sit.c | 2 +- 5 files changed, 21 insertions(+), 8 deletions(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index d708b66e55cd..85e3455cea25 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 9d114bd575f9..5b1f180485d4 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 70c171091020..200d0ba1a40e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1137,8 +1137,11 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - dev->needed_headroom = 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); + 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 6a1b901ecc9b..cc96bb8b706e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1514,8 +1514,11 @@ 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 a38b24fb8384..19b7fa8d1a2a 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,