net: Handle l3mdev in ip_tunnel_init_flow

Ido reported that the commit referenced in the Fixes tag broke
a gre use case with dummy devices. Add a check to ip_tunnel_init_flow
to see if the oif is an l3mdev port and if so set the oif to 0 to
avoid the oif comparison in fib_lookup_good_nhc.

Fixes: 40867d7 ("net: Add l3mdev index to flow struct and avoid oif reset for port devices")
Reported-by: Ido Schimmel <[email protected]>
Signed-off-by: David Ahern <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: dsahern

drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c

@@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, parms.link, tun->fwmark, 0);
+			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))

include/net/ip_tunnels.h

@@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id)
 static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 				       int proto,
 				       __be32 daddr, __be32 saddr,
-				       __be32 key, __u8 tos, int oif,
+				       __be32 key, __u8 tos,
+				       struct net *net, int oif,
 				       __u32 mark, __u32 tun_inner_hash)
 {
 	memset(fl4, 0, sizeof(*fl4));
-	fl4->flowi4_oif = oif;
+
+	if (oif) {
+		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+		/* Legacy VRF/l3mdev use case */
+		fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
+	}
+
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->flowi4_tos = tos;

net/ipv4/ip_gre.c

@@ -605,8 +605,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	key = &info->key;
 	ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id),
-			    key->tos & ~INET_ECN_MASK, 0, skb->mark,
-			    skb_get_hash(skb));
+			    key->tos & ~INET_ECN_MASK, dev_net(dev), 0,
+			    skb->mark, skb_get_hash(skb));
 	rt = ip_route_output_key(dev_net(dev), &fl4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);

net/ipv4/ip_tunnel.c

@@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), tunnel->parms.link,
-				    tunnel->fwmark, 0);
+				    RT_TOS(iph->tos), dev_net(dev),
+				    tunnel->parms.link, tunnel->fwmark, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    0, skb->mark, skb_get_hash(skb));
+			    dev_net(dev), 0, skb->mark, skb_get_hash(skb));
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 
@@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+			    tunnel->parms.o_key, RT_TOS(tos),
+			    dev_net(dev), tunnel->parms.link,
 			    tunnel->fwmark, skb_get_hash(skb));
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)