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>

2 files changed, 24 insertions, 17 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c67d00e8c600..87397351ddac 100644
--- 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 ce25a13f3430..5e3685c5c407 100644
--- 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;
 }