IPVS callers already parse the packet into struct ip_vs_iphdr before updating connection state. For IPv6 this records the real transport-header offset after extension headers in iph.len. Pass this parsed transport offset through ip_vs_set_state() and the protocol state_transition() callback so protocol handlers can use the same packet context as scheduling and NAT handling. This patch only changes the common callback plumbing and adapts the protocol callback signatures; TCP and SCTP start using the value in follow-up patches. Signed-off-by: Yizhou Zhao --- include/net/ip_vs.h | 3 ++- net/netfilter/ipvs/ip_vs_core.c | 10 +++++----- net/netfilter/ipvs/ip_vs_proto_sctp.c | 3 ++- net/netfilter/ipvs/ip_vs_proto_tcp.c | 3 ++- net/netfilter/ipvs/ip_vs_proto_udp.c | 3 ++- 5 files changed, 13 insertions(+), 9 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 49297fec448a..417ff51f62fc 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -752,7 +752,8 @@ struct ip_vs_protocol { void (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd); + struct ip_vs_proto_data *pd, + unsigned int iph_len); int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d40b404c1bf6..bd90f03fe3a4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -398,10 +398,10 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, unsigned int iph_len) { if (likely(pd->pp->state_transition)) - pd->pp->state_transition(cp, direction, skb, pd); + pd->pp->state_transition(cp, direction, skb, pd, iph_len); } static inline int @@ -803,7 +803,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph->len); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); @@ -1484,7 +1484,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, after_nat: ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd, iph->len); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); @@ -2233,7 +2233,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph.len); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 63c78a1f3918..394367b7b388 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -468,7 +468,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void sctp_state_transition(struct ip_vs_conn *cp, int direction, - const struct sk_buff *skb, struct ip_vs_proto_data *pd) + const struct sk_buff *skb, struct ip_vs_proto_data *pd, + unsigned int iph_len) { spin_lock_bh(&cp->lock); set_sctp_state(pd, cp, direction, skb); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8cc0a8ce6241..2d3f6aeafe52 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -579,7 +579,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { struct tcphdr _tcph, *th; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f9de632e38cd..58f9e255927e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -444,7 +444,8 @@ static const char * udp_state_name(int state) static void udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { if (unlikely(!pd)) { pr_err("UDP no ns data\n"); -- 2.34.1 TCP state handling reparses the skb to find the TCP header. For IPv6 it uses sizeof(struct ipv6hdr), while the surrounding IPVS code already parsed the packet with ip_vs_fill_iph_skb() and has the real transport-header offset in iph.len. This makes TCP state handling look at the wrong bytes when an IPv6 packet carries extension headers. Use the parsed transport offset passed down from ip_vs_set_state() when reading the TCP header. For IPv4 and for IPv6 packets without extension headers, the passed offset matches the previous value. Fixes: 0bbdd42b7efa6 ("IPVS: Extend protocol DNAT/SNAT and state handlers") Link: https://lore.kernel.org/netdev/20260705125659.37744-1-zhaoyz24@mails.tsinghua.edu.cn/ Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Assisted-by: Claude Code:GLM-5.2 Signed-off-by: Yizhou Zhao --- net/netfilter/ipvs/ip_vs_proto_tcp.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 2d3f6aeafe52..f86b763efcc4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -584,13 +584,7 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction, { struct tcphdr _tcph, *th; -#ifdef CONFIG_IP_VS_IPV6 - int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - int ihl = ip_hdrlen(skb); -#endif - - th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, iph_len, sizeof(_tcph), &_tcph); if (th == NULL) return; -- 2.34.1 set_sctp_state() reads the SCTP chunk header again in order to drive the IPVS SCTP state table. For IPv6 it computes the offset with sizeof(struct ipv6hdr), while the surrounding IPVS code uses iph.len from ip_vs_fill_iph_skb(), where ipv6_find_hdr() has already skipped extension headers and found the real transport header. This makes the state machine read from the wrong offset for IPv6 SCTP packets that carry extension headers. For example, an INIT packet with an 8-byte destination options header can be scheduled correctly by sctp_conn_schedule(), but set_sctp_state() reads the first byte of the SCTP verification tag as a DATA chunk type. The connection then moves from NONE to ESTABLISHED instead of INIT1, gets the longer established timeout, and updates the active/inactive destination counters incorrectly. This happens even though the SCTP handshake has not completed. Use the parsed transport offset passed down from ip_vs_set_state() for the SCTP chunk-header lookup. For IPv4 and IPv6 packets without extension headers this preserves the existing offset. Fixes: 2906f66a5682 ("ipvs: SCTP Trasport Loadbalancing Support") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/netdev/20260705123040.35755-1-zhaoyz24@mails.tsinghua.edu.cn/ Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Ao Wang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Assisted-by: Claude Code:GLM-5.2 Signed-off-by: Yizhou Zhao --- net/netfilter/ipvs/ip_vs_proto_sctp.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 394367b7b388..c67317be17df 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -372,20 +372,15 @@ static const char *sctp_state_name(int state) static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, - int direction, const struct sk_buff *skb) + int direction, const struct sk_buff *skb, + unsigned int iph_len) { struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; - int ihl, cofs; - -#ifdef CONFIG_IP_VS_IPV6 - ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - ihl = ip_hdrlen(skb); -#endif + int cofs; - cofs = ihl + sizeof(struct sctphdr); + cofs = iph_len + sizeof(struct sctphdr); sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -472,7 +467,7 @@ sctp_state_transition(struct ip_vs_conn *cp, int direction, unsigned int iph_len) { spin_lock_bh(&cp->lock); - set_sctp_state(pd, cp, direction, skb); + set_sctp_state(pd, cp, direction, skb, iph_len); spin_unlock_bh(&cp->lock); } -- 2.34.1