Merge commit '900cfa46191a7d87cf1891924cb90499287fd235'; branches 'timers/nohz',...

[~andy/linux] / net / ipv4 / route.c

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce25a13f3430b06f27445c8a3fa5e30c6a117baa..96be336064fb1f5f3851cb440a051e2c190de617 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -160,7 +160,7 @@ static struct dst_ops ipv4_dst_ops = {
        .negative_advice =      ipv4_negative_advice,
        .link_failure =         ipv4_link_failure,
        .update_pmtu =          ip_rt_update_pmtu,
-       .local_out =            ip_local_out,
+       .local_out =            __ip_local_out,
        .entry_size =           sizeof(struct rtable),
        .entries =              ATOMIC_INIT(0),
 };
@@ -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;
@@ -1442,34 +1444,38 @@ 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 :-( */
                                        if (mtu == 0 &&
-                                           old_mtu >= rth->u.dst.metrics[RTAX_MTU-1] &&
+                                           old_mtu >= dst_metric(&rth->u.dst, RTAX_MTU) &&
                                            old_mtu >= 68 + (iph->ihl << 2))
                                                old_mtu -= iph->ihl << 2;
 
                                        mtu = guess_mtu(old_mtu);
                                }
-                               if (mtu <= rth->u.dst.metrics[RTAX_MTU-1]) {
-                                       if (mtu < rth->u.dst.metrics[RTAX_MTU-1]) {
+                               if (mtu <= dst_metric(&rth->u.dst, RTAX_MTU)) {
+                                       if (mtu < dst_metric(&rth->u.dst, RTAX_MTU)) {
                                                dst_confirm(&rth->u.dst);
                                                if (mtu < ip_rt_min_pmtu) {
                                                        mtu = ip_rt_min_pmtu;
@@ -1483,15 +1489,15 @@ 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;
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
-       if (dst->metrics[RTAX_MTU-1] > mtu && mtu >= 68 &&
+       if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= 68 &&
            !(dst_metric_locked(dst, RTAX_MTU))) {
                if (mtu < ip_rt_min_pmtu) {
                        mtu = ip_rt_min_pmtu;
@@ -1607,7 +1613,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
                       sizeof(rt->u.dst.metrics));
                if (fi->fib_mtu == 0) {
                        rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
-                       if (rt->u.dst.metrics[RTAX_LOCK-1] & (1 << RTAX_MTU) &&
+                       if (dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
                            rt->rt_gateway != rt->rt_dst &&
                            rt->u.dst.dev->mtu > 576)
                                rt->u.dst.metrics[RTAX_MTU-1] = 576;
@@ -1618,14 +1624,14 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
        } else
                rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu;
 
-       if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0)
+       if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0)
                rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
-       if (rt->u.dst.metrics[RTAX_MTU-1] > IP_MAX_MTU)
+       if (dst_metric(&rt->u.dst, RTAX_MTU) > IP_MAX_MTU)
                rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
-       if (rt->u.dst.metrics[RTAX_ADVMSS-1] == 0)
+       if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0)
                rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40,
                                       ip_rt_min_advmss);
-       if (rt->u.dst.metrics[RTAX_ADVMSS-1] > 65535 - 40)
+       if (dst_metric(&rt->u.dst, RTAX_ADVMSS) > 65535 - 40)
                rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
 
 #ifdef CONFIG_NET_CLS_ROUTE
@@ -1786,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb,
        if (err)
                flags |= RTCF_DIRECTSRC;
 
-       if (out_dev == in_dev && err && !(flags & RTCF_MASQ) &&
+       if (out_dev == in_dev && err &&
            (IN_DEV_SHARED_MEDIA(out_dev) ||
             inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
                flags |= RTCF_DOREDIRECT;