[net-next,2/5] ipv4: Convert ip_route_input() to dscp_t.

Commit Message

Guillaume Nault Oct. 1, 2024, 7:28 p.m. UTC

Pass a dscp_t variable to ip_route_input(), instead of a plain u8, to
prevent accidental setting of ECN bits in ->flowi4_tos.

Callers of ip_route_input() to consider are:

  * input_action_end_dx4_finish() and input_action_end_dt4() in
    net/ipv6/seg6_local.c. These functions set the tos parameter to 0,
    which is already a valid dscp_t value, so they don't need to be
    adjusted for the new prototype.

  * icmp_route_lookup(), which already has a dscp_t variable to pass as
    parameter. We just need to remove the inet_dscp_to_dsfield()
    conversion.

  * br_nf_pre_routing_finish(), ip_options_rcv_srr() and ip4ip6_err(),
    which get the DSCP directly from IPv4 headers. Define a helper to
    read the .tos field of struct iphdr as dscp_t, so that these
    function don't have to do the conversion manually.

While there, declare *iph as const in br_nf_pre_routing_finish(),
declare its local variables in reverse-christmas-tree order and move
the "err = ip_route_input()" assignment out of the conditional to avoid
checkpatch warning.

Signed-off-by: Guillaume Nault <[e-mail]>
---
 include/net/ip.h                | 5 +++++
 include/net/route.h             | 5 +++--
 net/bridge/br_netfilter_hooks.c | 8 +++++---
 net/ipv4/icmp.c                 | 2 +-
 net/ipv4/ip_options.c           | 3 ++-
 net/ipv6/ip6_tunnel.c           | 4 ++--
 6 files changed, 18 insertions(+), 9 deletions(-)

Patch

diff --git a/include/net/ip.h b/include/net/ip.h
index d92d3bc3ec0e..bab084df1567 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -424,6 +424,11 @@  int ip_decrease_ttl(struct iphdr *iph)
 	return --iph->ttl;
 }
 
+static inline dscp_t ip4h_dscp(const struct iphdr *ip4h)
+{
+	return inet_dsfield_to_dscp(ip4h->tos);
+}
+
 static inline int ip_mtu_locked(const struct dst_entry *dst)
 {
 	const struct rtable *rt = dst_rtable(dst);
diff --git a/include/net/route.h b/include/net/route.h
index 1789f1e6640b..03dd28cf4bc4 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -208,12 +208,13 @@  int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
 		      const struct sk_buff *hint);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
-				 u8 tos, struct net_device *devin)
+				 dscp_t dscp, struct net_device *devin)
 {
 	int err;
 
 	rcu_read_lock();
-	err = ip_route_input_noref(skb, dst, src, tos, devin);
+	err = ip_route_input_noref(skb, dst, src, inet_dscp_to_dsfield(dscp),
+				   devin);
 	if (!err) {
 		skb_dst_force(skb);
 		if (!skb_dst(skb))
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 0e8bc0ea6175..c6bab2b5e834 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -369,9 +369,9 @@  br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
  */
 static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb->dev, *br_indev;
-	struct iphdr *iph = ip_hdr(skb);
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	struct net_device *dev = skb->dev, *br_indev;
+	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	int err;
 
@@ -389,7 +389,9 @@  static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 	}
 	nf_bridge->in_prerouting = 0;
 	if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
-		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
+		err = ip_route_input(skb, iph->daddr, iph->saddr,
+				     ip4h_dscp(iph), dev);
+		if (err) {
 			struct in_device *in_dev = __in_dev_get_rcu(dev);
 
 			/* If err equals -EHOSTUNREACH the error is due to a
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7d7b25ed8d21..23664434922e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -545,7 +545,7 @@  static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
 		orefdst = skb_in->_skb_refdst; /* save old refdst */
 		skb_dst_set(skb_in, NULL);
 		err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
-				     inet_dscp_to_dsfield(dscp), rt2->dst.dev);
+				     dscp, rt2->dst.dev);
 
 		dst_release(&rt2->dst);
 		rt2 = skb_rtable(skb_in);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index a9e22a098872..b4c59708fc09 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -617,7 +617,8 @@  int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph),
+				     dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b60e13c42bca..48fd53b98972 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -630,8 +630,8 @@  ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		skb_dst_set(skb2, &rt->dst);
 	} else {
-		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
-				   skb2->dev) ||
+		if (ip_route_input(skb2, eiph->daddr, eiph->saddr,
+				   ip4h_dscp(eiph), skb2->dev) ||
 		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
 			goto out;
 	}