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 <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/e9d40781d64d3d69f4c79ac8a008b8d67a033e8d.1727807926.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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);
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))
*/
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;
}
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
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);
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);
}
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;
}