diff options
| author | John Heffner <jheffner@psc.edu> | 2007-04-20 15:53:27 -0700 |
|---|---|---|
| committer | David S. Miller <davem@sunset.davemloft.net> | 2007-04-25 22:29:10 -0700 |
| commit | 628a5c561890a9a9a74dea017873530584aab06e (patch) | |
| tree | f10edc4078c3f19487bbe3a902ecadda89273361 /net/ipv4 | |
| parent | b881ef7603230550aa0150b22af94089f07ab00d (diff) | |
| download | linux-628a5c561890a9a9a74dea017873530584aab06e.tar.gz linux-628a5c561890a9a9a74dea017873530584aab06e.tar.bz2 linux-628a5c561890a9a9a74dea017873530584aab06e.zip | |
[INET]: Add IP(V6)_PMTUDISC_RPOBE
Add IP(V6)_PMTUDISC_PROBE value for IP(V6)_MTU_DISCOVER. This option forces
us not to fragment, but does not make use of the kernel path MTU discovery.
That is, it allows for user-mode MTU probing (or, packetization-layer path
MTU discovery). This is particularly useful for diagnostic utilities, like
traceroute/tracepath.
Signed-off-by: John Heffner <jheffner@psc.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/ip_output.c | 20 | ||||
| -rw-r--r-- | net/ipv4/ip_sockglue.c | 2 |
2 files changed, 16 insertions, 6 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 34606eff8a05..534650cad3a8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -189,6 +189,14 @@ static inline int ip_finish_output2(struct sk_buff *skb) return -EINVAL; } +static inline int ip_skb_dst_mtu(struct sk_buff *skb) +{ + struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL; + + return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ? + skb->dst->dev->mtu : dst_mtu(skb->dst); +} + static inline int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) @@ -198,7 +206,7 @@ static inline int ip_finish_output(struct sk_buff *skb) return dst_output(skb); } #endif - if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) + if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb)) return ip_fragment(skb, ip_finish_output2); else return ip_finish_output2(skb); @@ -422,7 +430,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) { IP_INC_STATS(IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(dst_mtu(&rt->u.dst))); + htonl(ip_skb_dst_mtu(skb))); kfree_skb(skb); return -EMSGSIZE; } @@ -787,7 +795,9 @@ int ip_append_data(struct sock *sk, inet->cork.addr = ipc->addr; } dst_hold(&rt->u.dst); - inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path); + inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ? + rt->u.dst.dev->mtu : + dst_mtu(rt->u.dst.path); inet->cork.rt = rt; inet->cork.length = 0; sk->sk_sndmsg_page = NULL; @@ -1203,13 +1213,13 @@ int ip_push_pending_frames(struct sock *sk) * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ - if (inet->pmtudisc != IP_PMTUDISC_DO) + if (inet->pmtudisc < IP_PMTUDISC_DO) skb->local_df = 1; /* DF bit is set when we want to see DF on outgoing frames. * If local_df is set too, we still allow to fragment this frame * locally. */ - if (inet->pmtudisc == IP_PMTUDISC_DO || + if (inet->pmtudisc >= IP_PMTUDISC_DO || (skb->len <= dst_mtu(&rt->u.dst) && ip_dont_fragment(sk, &rt->u.dst))) df = htons(IP_DF); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index c199d2311731..4d544573f48a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -542,7 +542,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->hdrincl = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val<0 || val>2) + if (val<0 || val>3) goto e_inval; inet->pmtudisc = val; break; |