ipv4: Merge __ip_local_out and __ip_local_out_sk

[deliverable/linux.git] / net / ipv4 / route.c

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a670f894ce13830ad57319db048bf0e0ef68c27e..bf1486bd7e811d64d5c4a69173dfa9c64a877456 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,7 +112,7 @@
 #endif
 #include <net/secure_seq.h>
 #include <net/ip_tunnels.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 #define RT_FL_TOS(oldflp4) \
        ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
@@ -847,7 +847,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
                return;
        }
        log_martians = IN_DEV_LOG_MARTIANS(in_dev);
-       vif = vrf_master_ifindex_rcu(rt->dst.dev);
+       vif = l3mdev_master_ifindex_rcu(rt->dst.dev);
        rcu_read_unlock();
 
        net = dev_net(rt->dst.dev);
@@ -941,7 +941,7 @@ static int ip_error(struct sk_buff *skb)
        }
 
        peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr,
-                              vrf_master_ifindex(skb->dev), 1);
+                              l3mdev_master_ifindex(skb->dev), 1);
 
        send = true;
        if (peer) {
@@ -1651,6 +1651,48 @@ out:
        return err;
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* To make ICMP packets follow the right flow, the multipath hash is
+ * calculated from the inner IP addresses in reverse order.
+ */
+static int ip_multipath_icmp_hash(struct sk_buff *skb)
+{
+       const struct iphdr *outer_iph = ip_hdr(skb);
+       struct icmphdr _icmph;
+       const struct icmphdr *icmph;
+       struct iphdr _inner_iph;
+       const struct iphdr *inner_iph;
+
+       if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
+               goto standard_hash;
+
+       icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
+                                  &_icmph);
+       if (!icmph)
+               goto standard_hash;
+
+       if (icmph->type != ICMP_DEST_UNREACH &&
+           icmph->type != ICMP_REDIRECT &&
+           icmph->type != ICMP_TIME_EXCEEDED &&
+           icmph->type != ICMP_PARAMETERPROB) {
+               goto standard_hash;
+       }
+
+       inner_iph = skb_header_pointer(skb,
+                                      outer_iph->ihl * 4 + sizeof(_icmph),
+                                      sizeof(_inner_iph), &_inner_iph);
+       if (!inner_iph)
+               goto standard_hash;
+
+       return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+
+standard_hash:
+       return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
+}
+
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+
 static int ip_mkroute_input(struct sk_buff *skb,
                            struct fib_result *res,
                            const struct flowi4 *fl4,
@@ -1658,8 +1700,15 @@ static int ip_mkroute_input(struct sk_buff *skb,
                            __be32 daddr, __be32 saddr, u32 tos)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-       if (res->fi && res->fi->fib_nhs > 1)
-               fib_select_multipath(res);
+       if (res->fi && res->fi->fib_nhs > 1) {
+               int h;
+
+               if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
+                       h = ip_multipath_icmp_hash(skb);
+               else
+                       h = fib_multipath_hash(saddr, daddr);
+               fib_select_multipath(res, h);
+       }
 #endif
 
        /* create a routing cache entry */
@@ -1739,10 +1788,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
         *      Now we are ready to route packet.
         */
        fl4.flowi4_oif = 0;
-       fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex;
+       fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev);
        fl4.flowi4_mark = skb->mark;
        fl4.flowi4_tos = tos;
        fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+       fl4.flowi4_flags = 0;
        fl4.daddr = daddr;
        fl4.saddr = saddr;
        err = fib_lookup(net, &fl4, &res, 0);
@@ -2025,7 +2075,8 @@ add:
  * Major route resolver routine.
  */
 
-struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
+                                         int mp_hash)
 {
        struct net_device *dev_out = NULL;
        __u8 tos = RT_FL_TOS(fl4);
@@ -2124,11 +2175,10 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
                                fl4->saddr = inet_select_addr(dev_out, 0,
                                                              RT_SCOPE_HOST);
                }
-               if (netif_is_l3_master(dev_out) &&
-                   !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
-                       rth = vrf_dev_get_rth(dev_out);
+
+               rth = l3mdev_get_rtable(dev_out, fl4);
+               if (rth)
                        goto out;
-               }
        }
 
        if (!fl4->daddr) {
@@ -2188,18 +2238,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
                goto make_route;
        }
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-       if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
-               fib_select_multipath(&res);
-       else
-#endif
-       if (!res.prefixlen &&
-           res.table->tb_num_default > 1 &&
-           res.type == RTN_UNICAST && !fl4->flowi4_oif)
-               fib_select_default(fl4, &res);
-
-       if (!fl4->saddr)
-               fl4->saddr = FIB_RES_PREFSRC(net, res);
+       fib_select_path(net, &res, fl4, mp_hash);
 
        dev_out = FIB_RES_DEV(res);
        fl4->flowi4_oif = dev_out->ifindex;
@@ -2212,7 +2251,7 @@ out:
        rcu_read_unlock();
        return rth;
 }
-EXPORT_SYMBOL_GPL(__ip_route_output_key);
+EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
 
 static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
 {
@@ -2468,6 +2507,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
        fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
        fl4.flowi4_mark = mark;
 
+       if (netif_index_is_l3_master(net, fl4.flowi4_oif))
+               fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF;
+
        if (iif) {
                struct net_device *dev;