ipv4: reset rt_iif for recirculated mcast/bcast out pkts

Multicast or broadcast egress packets have rt_iif set to the oif. These
packets might be recirculated back as input and lookup to the raw
sockets may fail because they are bound to the incoming interface
(skb_iif). If rt_iif is not zero, during the lookup, inet_iif() function
returns rt_iif instead of skb_iif. Hence, the lookup fails.

v2: Make it non vrf specific (David Ahern). Reword the changelog to
    reflect it.
Signed-off-by: Stephen Suryaputra <[email protected]>
Reviewed-by: David Ahern <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: ssuryaextr

include/net/route.h

@@ -221,6 +221,7 @@ void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
 struct rtable *rt_dst_alloc(struct net_device *dev,
 			     unsigned int flags, u16 type,
 			     bool nopolicy, bool noxfrm, bool will_cache);
+struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt);
 
 struct in_ifaddr;
 void fib_add_ifaddr(struct in_ifaddr *);

net/ipv4/ip_output.c

@@ -318,6 +318,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 static int ip_mc_finish_output(struct net *net, struct sock *sk,
 			       struct sk_buff *skb)
 {
+	struct rtable *new_rt;
 	int ret;
 
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
@@ -326,6 +327,17 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk,
 		return ret;
 	}
 
+	/* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting
+	 * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten,
+	 * see ipv4_pktinfo_prepare().
+	 */
+	new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb));
+	if (new_rt) {
+		new_rt->rt_iif = 0;
+		skb_dst_drop(skb);
+		skb_dst_set(skb, &new_rt->dst);
+	}
+
 	return dev_loopback_xmit(net, sk, skb);
 }
 

net/ipv4/route.c

@@ -1647,6 +1647,39 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 }
 EXPORT_SYMBOL(rt_dst_alloc);
 
+struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
+{
+	struct rtable *new_rt;
+
+	new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
+			   rt->dst.flags);
+
+	if (new_rt) {
+		new_rt->rt_genid = rt_genid_ipv4(dev_net(dev));
+		new_rt->rt_flags = rt->rt_flags;
+		new_rt->rt_type = rt->rt_type;
+		new_rt->rt_is_input = rt->rt_is_input;
+		new_rt->rt_iif = rt->rt_iif;
+		new_rt->rt_pmtu = rt->rt_pmtu;
+		new_rt->rt_mtu_locked = rt->rt_mtu_locked;
+		new_rt->rt_gw_family = rt->rt_gw_family;
+		if (rt->rt_gw_family == AF_INET)
+			new_rt->rt_gw4 = rt->rt_gw4;
+		else if (rt->rt_gw_family == AF_INET6)
+			new_rt->rt_gw6 = rt->rt_gw6;
+		INIT_LIST_HEAD(&new_rt->rt_uncached);
+
+		new_rt->dst.flags |= DST_HOST;
+		new_rt->dst.input = rt->dst.input;
+		new_rt->dst.output = rt->dst.output;
+		new_rt->dst.error = rt->dst.error;
+		new_rt->dst.lastuse = jiffies;
+		new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate);
+	}
+	return new_rt;
+}
+EXPORT_SYMBOL(rt_dst_clone);
+
 /* called in rcu_read_lock() section */
 int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			  u8 tos, struct net_device *dev,