From cf8b49fbd0418168b55c807b7fb62d7031026183 Mon Sep 17 00:00:00 2001 From: Heng Guo Date: Wed, 11 Oct 2023 09:51:37 +0800 Subject: net: fix IPSTATS_MIB_OUTFORWDATAGRAMS increment after fragment check Reproduce environment: network with 3 VM linuxs is connected as below: VM1<---->VM2(latest kernel 6.5.0-rc7)<---->VM3 VM1: eth0 ip: 192.168.122.207 MTU 1800 VM2: eth0 ip: 192.168.122.208, eth1 ip: 192.168.123.224 MTU 1500 VM3: eth0 ip: 192.168.123.240 MTU 1800 Reproduce: VM1 send 1600 bytes UDP data to VM3 using tools scapy with flags='DF'. scapy command: send(IP(dst="192.168.123.240",flags='DF')/UDP()/str('0'*1600),count=1, inter=1.000000) Result: Before IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqdss Ip: 1 64 6 0 2 2 0 0 2 4 0 0 0 0 0 0 0 0 0 ...... root@qemux86-64:~# ---------------------------------------------------------------------- After IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqdss Ip: 1 64 7 0 2 2 0 0 2 5 0 0 0 0 0 0 0 1 0 ...... root@qemux86-64:~# ---------------------------------------------------------------------- ForwDatagrams is always keeping 2 without increment. Issue description and patch: ip_exceeds_mtu() in ip_forward() drops this IP datagram because skb len (1600 sending by scapy) is over MTU(1500 in VM2) if "DF" is set. According to RFC 4293 "3.2.3. IP Statistics Tables", +-------+------>------+----->-----+----->-----+ | InForwDatagrams (6) | OutForwDatagrams (6) | | V +->-+ OutFragReqds | InNoRoutes | | (packets) / (local packet (3) | | | IF is that of the address | +--> OutFragFails | and may not be the receiving IF) | | (packets) the IPSTATS_MIB_OUTFORWDATAGRAMS should be counted before fragment check. The existing implementation, instead, would incease the counter after fragment check: ip_exceeds_mtu() in ipv4 and ip6_pkt_too_big() in ipv6. So do patch to move IPSTATS_MIB_OUTFORWDATAGRAMS counter to ip_forward() for ipv4 and ip6_forward() for ipv6. Test result with patch: Before IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqdss Ip: 1 64 6 0 2 2 0 0 2 4 0 0 0 0 0 0 0 0 0 ...... root@qemux86-64:~# ---------------------------------------------------------------------- After IP data is sent. ---------------------------------------------------------------------- root@qemux86-64:~# cat /proc/net/snmp Ip: Forwarding DefaultTTL InReceives InHdrErrors InAddrErrors ForwDatagrams InUnknownProtos InDiscards InDelivers OutRequests OutDiscards OutNoRoutes ReasmTimeout ReasmReqdss Ip: 1 64 7 0 2 3 0 0 2 5 0 0 0 0 0 0 0 1 0 ...... root@qemux86-64:~# ---------------------------------------------------------------------- ForwDatagrams is updated from 2 to 3. Reviewed-by: Filip Pudak Signed-off-by: Heng Guo Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20231011015137.27262-1-heng.guo@windriver.com Signed-off-by: Jakub Kicinski --- net/ipv4/ip_forward.c | 4 ++-- net/ipv6/ip6_output.c | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 66fac1216d46..8b65f12583eb 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -66,8 +66,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s { struct ip_options *opt = &(IPCB(skb)->opt); - __IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); - #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); @@ -130,6 +128,8 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; + __IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index cdaa9275e990..a471c7e91761 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -446,10 +446,6 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - - __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); - #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); @@ -617,6 +613,8 @@ int ip6_forward(struct sk_buff *skb) } } + __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); + mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; -- cgit v1.2.3-70-g09d2