ipv4: Update MTU to all related cache entries in ip_rt_frag_needed()

Add struct net_device parameter to ip_rt_frag_needed() and update MTU to
cache entries where ifindex is specified. This is similar to what is
already done in ip_rt_redirect().

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/route.h b/include/net/route.h
index c6338802e8f11a4f727b4a45959dcb32725c6760..fc836ff824cc78eb23f4c38462d4db60b3487d08 100644 (file)
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -116,7 +116,7 @@ extern int          __ip_route_output_key(struct net *, struct rtable **, const struct f
 extern int             ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
 extern int             ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
 extern int             ip_route_input(struct sk_buff*, __be32 dst, __be32 src, u8 tos, struct net_device *devin);
-extern unsigned short  ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu);
+extern unsigned short  ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev);
 extern void            ip_rt_send_redirect(struct sk_buff *skb);
 
 extern unsigned                inet_addr_type(struct net *net, __be32 addr);

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c67d00e8c6003eb49761a44155501124c7c09b9d..87397351ddace424de5f0341482b408cdfaaf363 100644 (file)
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -691,7 +691,8 @@ static void icmp_unreach(struct sk_buff *skb)
                                               NIPQUAD(iph->daddr));
                        } else {
                                info = ip_rt_frag_needed(net, iph,
-                                                    ntohs(icmph->un.frag.mtu));
+                                                        ntohs(icmph->un.frag.mtu),
+                                                        skb->dev);
                                if (!info)
                                        goto out;
                        }

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce25a13f3430b06f27445c8a3fa5e30c6a117baa..5e3685c5c407ac2e6b24c13eaf055319d2d341aa 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1430,11 +1430,13 @@ static inline unsigned short guess_mtu(unsigned short old_mtu)
 }
 
 unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
-                                unsigned short new_mtu)
+                                unsigned short new_mtu,
+                                struct net_device *dev)
 {
-       int i;
+       int i, k;
        unsigned short old_mtu = ntohs(iph->tot_len);
        struct rtable *rth;
+       int  ikeys[2] = { dev->ifindex, 0 };
        __be32  skeys[2] = { iph->saddr, 0, };
        __be32  daddr = iph->daddr;
        unsigned short est_mtu = 0;
@@ -1442,22 +1444,26 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
        if (ipv4_config.no_pmtu_disc)
                return 0;
 
-       for (i = 0; i < 2; i++) {
-               unsigned hash = rt_hash(daddr, skeys[i], 0);
+       for (k = 0; k < 2; k++) {
+               for (i = 0; i < 2; i++) {
+                       unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]);
 
-               rcu_read_lock();
-               for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
-                    rth = rcu_dereference(rth->u.dst.rt_next)) {
-                       if (rth->fl.fl4_dst == daddr &&
-                           rth->fl.fl4_src == skeys[i] &&
-                           rth->rt_dst  == daddr &&
-                           rth->rt_src  == iph->saddr &&
-                           rth->fl.iif == 0 &&
-                           !(dst_metric_locked(&rth->u.dst, RTAX_MTU)) &&
-                           net_eq(dev_net(rth->u.dst.dev), net) &&
-                           rth->rt_genid == atomic_read(&rt_genid)) {
+                       rcu_read_lock();
+                       for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
+                            rth = rcu_dereference(rth->u.dst.rt_next)) {
                                unsigned short mtu = new_mtu;
 
+                               if (rth->fl.fl4_dst != daddr ||
+                                   rth->fl.fl4_src != skeys[i] ||
+                                   rth->rt_dst != daddr ||
+                                   rth->rt_src != iph->saddr ||
+                                   rth->fl.oif != ikeys[k] ||
+                                   rth->fl.iif != 0 ||
+                                   dst_metric_locked(&rth->u.dst, RTAX_MTU) ||
+                                   !net_eq(dev_net(rth->u.dst.dev), net) ||
+                                   rth->rt_genid != atomic_read(&rt_genid))
+                                       continue;
+
                                if (new_mtu < 68 || new_mtu >= old_mtu) {
 
                                        /* BSD 4.2 compatibility hack :-( */
@@ -1483,8 +1489,8 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
                                        est_mtu = mtu;
                                }
                        }
+                       rcu_read_unlock();
                }
-               rcu_read_unlock();
        }
        return est_mtu ? : new_mtu;
 }