From 5c9f7c1dfc2e0776551ef1ceb335187c6698d1ff Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 5 Apr 2019 16:30:34 -0700 Subject: ipv4: Add helpers for neigh lookup for nexthop A common theme in the output path is looking up a neigh entry for a nexthop, either the gateway in an rtable or a fallback to the daddr in the skb: nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr); neigh = __ipv4_neigh_lookup_noref(dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); To allow the nexthop to be an IPv6 address we need to consider the family of the nexthop and then call __ipv{4,6}_neigh_lookup_noref based on it. To make this simpler, add a ip_neigh_gw4 helper similar to ip_neigh_gw6 added in an earlier patch which handles: neigh = __ipv4_neigh_lookup_noref(dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); And then add a second one, ip_neigh_for_gw, that calls either ip_neigh_gw4 or ip_neigh_gw6 based on the address family of the gateway. Update the output paths in the VRF driver and core v4 code to use ip_neigh_for_gw simplifying the family based lookup and making both ready for a v6 nexthop. ipv4_neigh_lookup has a different need - the potential to resolve a passed in address in addition to any gateway in the rtable or skb. Since this is a one-off, add ip_neigh_gw4 and ip_neigh_gw6 diectly. The difference between __neigh_create used by the helpers and neigh_create called by ipv4_neigh_lookup is taking a refcount, so add rcu_read_lock_bh and bump the refcnt on the neigh entry. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'net/ipv4/ip_output.c') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index cca4892b8cb2..4e42c1974ba2 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -188,7 +188,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; - u32 nexthop; + bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); @@ -218,16 +218,13 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s } rcu_read_lock_bh(); - nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr); - neigh = __ipv4_neigh_lookup_noref(dev, nexthop); - if (unlikely(!neigh)) - neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); + neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); - res = neigh_output(neigh, skb, false); - + /* if crossing protocols, can not use the cached header */ + res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock_bh(); return res; } -- cgit v1.2.3