[PATCH nf-next] netfilter: br_netfilter: remove unused conditional and dead code

[PATCH nf-next] netfilter: br_netfilter: remove unused conditional and dead code

[Antoine Tenart]

The SKB_DROP_REASON_IP_INADDRERRORS drop reason is never returned from
any function, as such it cannot be returned from the ip_route_input call
tree. The 'reason != SKB_DROP_REASON_IP_INADDRERRORS' conditional is
thus always true.

Looking back at history, commit 50038bf38e65 ("net: ip: make
ip_route_input() return drop reasons") changed the ip_route_input
returned value check in br_nf_pre_routing_finish from -EHOSTUNREACH to
SKB_DROP_REASON_IP_INADDRERRORS. It turns out -EHOSTUNREACH could not be
returned either from the ip_route_input call tree and this since commit
251da4130115 ("ipv4: Cache ip_error() routes even when not
forwarding.").

Not a fix as this won't change the behavior. While at it use
kfree_skb_reason.

Signed-off-by: Antoine Tenart <atenart@kernel.org>
---
 net/bridge/br_netfilter_hooks.c | 30 +-----------------------------
 1 file changed, 1 insertion(+), 29 deletions(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 451e45b9a6a5..94cbe967d1c1 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -393,38 +393,10 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 		reason = ip_route_input(skb, iph->daddr, iph->saddr,
 					ip4h_dscp(iph), dev);
 		if (reason) {
-			struct in_device *in_dev = __in_dev_get_rcu(dev);
-
-			/* If err equals -EHOSTUNREACH the error is due to a
-			 * martian destination or due to the fact that
-			 * forwarding is disabled. For most martian packets,
-			 * ip_route_output_key() will fail. It won't fail for 2 types of
-			 * martian destinations: loopback destinations and destination
-			 * 0.0.0.0. In both cases the packet will be dropped because the
-			 * destination is the loopback device and not the bridge. */
-			if (reason != SKB_DROP_REASON_IP_INADDRERRORS || !in_dev ||
-			    IN_DEV_FORWARD(in_dev))
-				goto free_skb;
-
-			rt = ip_route_output(net, iph->daddr, 0,
-					     ip4h_dscp(iph), 0,
-					     RT_SCOPE_UNIVERSE);
-			if (!IS_ERR(rt)) {
-				/* - Bridged-and-DNAT'ed traffic doesn't
-				 *   require ip_forwarding. */
-				if (rt->dst.dev == dev) {
-					skb_dst_drop(skb);
-					skb_dst_set(skb, &rt->dst);
-					goto bridged_dnat;
-				}
-				ip_rt_put(rt);
-			}
-free_skb:
-			kfree_skb(skb);
+			kfree_skb_reason(skb, reason);
 			return 0;
 		} else {
 			if (skb_dst(skb)->dev == dev) {
-bridged_dnat:
 				skb->dev = br_indev;
 				nf_bridge_update_protocol(skb);
 				nf_bridge_push_encap_header(skb);
-- 
2.47.1

Re: [PATCH nf-next] netfilter: br_netfilter: remove unused conditional and dead code

[Simon Horman]

On Thu, Jan 09, 2025 at 10:37:09AM +0100, Antoine Tenart wrote:
> The SKB_DROP_REASON_IP_INADDRERRORS drop reason is never returned from
> any function, as such it cannot be returned from the ip_route_input call
> tree. The 'reason != SKB_DROP_REASON_IP_INADDRERRORS' conditional is
> thus always true.
> 
> Looking back at history, commit 50038bf38e65 ("net: ip: make
> ip_route_input() return drop reasons") changed the ip_route_input
> returned value check in br_nf_pre_routing_finish from -EHOSTUNREACH to
> SKB_DROP_REASON_IP_INADDRERRORS. It turns out -EHOSTUNREACH could not be
> returned either from the ip_route_input call tree and this since commit
> 251da4130115 ("ipv4: Cache ip_error() routes even when not
> forwarding.").
> 
> Not a fix as this won't change the behavior. While at it use
> kfree_skb_reason.
> 
> Signed-off-by: Antoine Tenart <atenart@kernel.org>
> ---
>  net/bridge/br_netfilter_hooks.c | 30 +-----------------------------
>  1 file changed, 1 insertion(+), 29 deletions(-)

Nice diffstat :)

Reviewed-by: Simon Horman <horms@kernel.org>