From 9ee6c5dc816aa8256257f2cd4008a9291ec7e985 Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Wed, 2 Nov 2016 16:36:17 -0400 Subject: [PATCH] ipv4: allow local fragmentation in ip_finish_output_gso() Some configurations (e.g. geneve interface with default MTU of 1500 over an ethernet interface with 1500 MTU) result in the transmission of packets that exceed the configured MTU. While this should be considered to be a "bad" configuration, it is still allowed and should not result in the sending of packets that exceed the configured MTU. Fix by dropping the assumption in ip_finish_output_gso() that locally originated gso packets will never need fragmentation. Basic testing using iperf (observing CPU usage and bandwidth) have shown no measurable performance impact for traffic not requiring fragmentation. Fixes: c7ba65d7b649 ("net: ip: push gso skb forwarding handling down the stack") Reported-by: Jan Tluka Signed-off-by: Lance Richardson Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 3 +-- net/ipv4/ip_forward.c | 2 +- net/ipv4/ip_output.c | 6 ++---- net/ipv4/ip_tunnel_core.c | 11 ----------- net/ipv4/ipmr.c | 2 +- 5 files changed, 5 insertions(+), 19 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 5413883ac47f..d3a107850a41 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -47,8 +47,7 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) -#define IPSKB_FRAG_SEGS BIT(7) -#define IPSKB_L3SLAVE BIT(8) +#define IPSKB_L3SLAVE BIT(7) u16 frag_max_size; }; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 8b4ffd216839..9f0a7b96646f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 03e7f7310423..49714010ac2e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -239,11 +239,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *segs; int ret = 0; - /* common case: fragmentation of segments is not allowed, - * or seglen is <= mtu + /* common case: seglen is <= mtu */ - if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) || - skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 777bc1883870..fed3d29f9eb3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; - int skb_iif = skb->skb_iif; struct iphdr *iph; int err; @@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && !(df & htons(IP_DF))) { - /* Arrived from an ingress interface, got encapsulated, with - * fragmentation of encapulating frames allowed. - * If skb is gso, the resulting encapsulated network segments - * may exceed dst mtu. - * Allow IP Fragmentation of segments. - */ - IPCB(skb)->flags |= IPSKB_FRAG_SEGS; - } - /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5f006e13de56..27089f5ebbb1 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->dev->stats.tx_bytes += skb->len; } - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output -- 2.20.1