ipv4: Convert ip_route_input_noref() to dscp_t.

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

Callers of ip_route_input_noref() to consider are:

  * arp_process() in net/ipv4/arp.c. This function sets the tos
    parameter to 0, which is already a valid dscp_t value, so it
    doesn't need to be adjusted for the new prototype.

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

  * ipvlan_l3_rcv(), bpf_lwt_input_reroute(), ip_expire(),
    ip_rcv_finish_core(), xfrm4_rcv_encap_finish() and
    xfrm4_rcv_encap(), which get the DSCP directly from IPv4 headers
    and can simply use the ip4h_dscp() helper.

While there, declare the IPv4 header pointers as const in
ipvlan_l3_rcv() and bpf_lwt_input_reroute().
Also, modify the declaration of ip_route_input_noref() in
include/net/route.h so that it matches the prototype of its
implementation in net/ipv4/route.c.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/a8a747bed452519c4d0cc06af32c7e7795d7b627.1727807926.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 18 insertions, 16 deletions

diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c
index d5b05e803219..b4ef386bdb1b 100644
--- a/drivers/net/ipvlan/ipvlan_l3s.c
+++ b/drivers/net/ipvlan/ipvlan_l3s.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
  */
 
+#include <net/ip.h>
+
 #include "ipvlan.h"
 
 static unsigned int ipvlan_netid __read_mostly;
@@ -48,11 +50,11 @@ static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev,
 	switch (proto) {
 	case AF_INET:
 	{
-		struct iphdr *ip4h = ip_hdr(skb);
+		const struct iphdr *ip4h = ip_hdr(skb);
 		int err;
 
 		err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr,
-					   ip4h->tos, sdev);
+					   ip4h_dscp(ip4h), sdev);
 		if (unlikely(err))
 			goto out;
 		break;
diff --git a/include/net/route.h b/include/net/route.h
index 03dd28cf4bc4..5e4374d66927 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -201,8 +201,8 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			  u8 tos, struct net_device *dev,
 			  struct in_device *in_dev, u32 *itag);
-int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-			 u8 tos, struct net_device *devin);
+int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			 dscp_t dscp, struct net_device *dev);
 int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
 		      u8 tos, struct net_device *devin,
 		      const struct sk_buff *hint);
@@ -213,8 +213,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 	int err;
 
 	rcu_read_lock();
-	err = ip_route_input_noref(skb, dst, src, inet_dscp_to_dsfield(dscp),
-				   devin);
+	err = ip_route_input_noref(skb, dst, src, dscp, devin);
 	if (!err) {
 		skb_dst_force(skb);
 		if (!skb_dst(skb))
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 1a14f915b7a4..e0ca24a58810 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -10,6 +10,7 @@
 #include <linux/bpf.h>
 #include <net/lwtunnel.h>
 #include <net/gre.h>
+#include <net/ip.h>
 #include <net/ip6_route.h>
 #include <net/ipv6_stubs.h>
 #include <net/inet_dscp.h>
@@ -91,12 +92,12 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb)
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		struct net_device *dev = skb_dst(skb)->dev;
-		struct iphdr *iph = ip_hdr(skb);
+		const struct iphdr *iph = ip_hdr(skb);
 
 		dev_hold(dev);
 		skb_dst_drop(skb);
 		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					   iph->tos, dev);
+					   ip4h_dscp(iph), dev);
 		dev_put(dev);
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		skb_dst_drop(skb);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a92664a5ef2e..48e2810f1f27 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -175,8 +175,8 @@ static void ip_expire(struct timer_list *t)
 
 	/* skb has no dst, perform route lookup again */
 	iph = ip_hdr(head);
-	err = ip_route_input_noref(head, iph->daddr, iph->saddr,
-					   iph->tos, head->dev);
+	err = ip_route_input_noref(head, iph->daddr, iph->saddr, ip4h_dscp(iph),
+				   head->dev);
 	if (err)
 		goto out;
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b6e7d4921309..c0a2490eb7c1 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -363,7 +363,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	 */
 	if (!skb_valid_dst(skb)) {
 		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					   iph->tos, dev);
+					   ip4h_dscp(iph), dev);
 		if (unlikely(err))
 			goto drop_error;
 	} else {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 723ac9181558..00bfc0a11f64 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2465,14 +2465,14 @@ static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 }
 
 int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			 u8 tos, struct net_device *dev)
+			 dscp_t dscp, struct net_device *dev)
 {
 	struct fib_result res;
 	int err;
 
-	tos &= INET_DSCP_MASK;
 	rcu_read_lock();
-	err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
+	err = ip_route_input_rcu(skb, daddr, saddr, inet_dscp_to_dsfield(dscp),
+				 dev, &res);
 	rcu_read_unlock();
 
 	return err;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index a620618cc568..b5b06323cfd9 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -33,7 +33,7 @@ static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					 iph->tos, skb->dev))
+					 ip4h_dscp(iph), skb->dev))
 			goto drop;
 	}
 
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index b146ce88c5d0..4ee624d8e66f 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -76,7 +76,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					 iph->tos, skb->dev))
+					 ip4h_dscp(iph), skb->dev))
 			goto drop;
 	}