From 67bf42cae41d847fd6e5749eb68278ca5d748b25 Mon Sep 17 00:00:00 2001 From: Yingnan Zhang <342144303@qq.com> Date: Wed, 15 Apr 2026 22:40:29 +0800 Subject: [PATCH] ipvs: fix MTU check for GSO packets in tunnel mode Currently, IPVS skips MTU checks for GSO packets by excluding them with the !skb_is_gso(skb) condition. This creates problems when IPVS tunnel mode encapsulates GSO packets with IPIP headers. The issue manifests in two ways: 1. MTU violation after encapsulation: When a GSO packet passes through IPVS tunnel mode, the original MTU check is bypassed. After adding the IPIP tunnel header, the packet size may exceed the outgoing interface MTU, leading to unexpected fragmentation at the IP layer. 2. Fragmentation with problematic IP IDs: When net.ipv4.vs.pmtu_disc=1 and a GSO packet with multiple segments is fragmented after encapsulation, each segment gets a sequentially incremented IP ID (0, 1, 2, ...). This happens because: a) The GSO packet bypasses MTU check and gets encapsulated b) At __ip_finish_output, the oversized GSO packet is split into separate SKBs (one per segment), with IP IDs incrementing c) Each SKB is then fragmented again based on the actual MTU This sequential IP ID allocation differs from the expected behavior and can cause issues with fragment reassembly and packet tracking. Fix this by properly validating GSO packets using skb_gso_validate_network_len(). This function correctly validates whether the GSO segments will fit within the MTU after segmentation. If validation fails, send an ICMP Fragmentation Needed message to enable proper PMTU discovery. Fixes: 4cdd34084d53 ("netfilter: nf_conntrack_ipv6: improve fragmentation handling") Signed-off-by: Yingnan Zhang <342144303@qq.com> Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_xmit.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 0fb5162992e5..ce542ed4b013 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -102,6 +102,18 @@ __ip_vs_dst_check(struct ip_vs_dest *dest) return dest_dst; } +/* Based on ip_exceeds_mtu(). */ +static bool ip_vs_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) + return false; + + return true; +} + static inline bool __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) { @@ -111,10 +123,9 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) */ if (IP6CB(skb)->frag_max_size > mtu) return true; /* largest fragment violate MTU */ - } - else if (skb->len > mtu && !skb_is_gso(skb)) { + } else if (ip_vs_exceeds_mtu(skb, mtu)) return true; /* Packet size violate MTU size */ - } + return false; } @@ -232,7 +243,7 @@ static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, return true; if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) && - skb->len > mtu && !skb_is_gso(skb) && + ip_vs_exceeds_mtu(skb, mtu) && !ip_vs_iph_icmp(ipvsh))) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));