netfilter: br_netfilter: remove unused conditional and dead code
Subsystems (4)
PATCH 1/1 netfilter: br_netfilter: remove unused conditional and dead code
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.
--- net/bridge/br_netfilter_hooks.c | 30 +----------------------------- 1 file changed, 1 insertion(+), 29 deletions(-)
net/bridge/br_netfilter_hooks.c +1 -29
@@ -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);
Signature · 1 line
2.47.1
Quoted 13 lines · Antoine Tenart
The
SKB_DROP_REASON_IP_INADDRERRORSdrop reason is never returned from any function, as such it cannot be returned from theip_route_inputcall tree. The 'reason !=SKB_DROP_REASON_IP_INADDRERRORS' conditional is thus always true.Looking back at history, commit
50038bf38e65("net: ip: makeip_route_input()return drop reasons") changed theip_route_inputreturned value check inbr_nf_pre_routing_finishfrom-EHOSTUNREACHtoSKB_DROP_REASON_IP_INADDRERRORS. It turns out-EHOSTUNREACHcould not be returned either from theip_route_inputcall tree and this since commit251da4130115("ipv4: Cacheip_error()routes even when not forwarding.").
Quoted 7 lines
Not a fix as this won't change the behavior. While at it use
kfree_skb_reason.Signed-off-by Antoine Tenart <[email protected]>--- net/bridge/br_netfilter_hooks.c | 30 +----------------------------- 1 file changed, 1 insertion(+), 29 deletions(-)
Nice diffstat :)