Merge branch 'unmask-upper-dscp-bits-part-3'

Ido Schimmel says:

====================
Unmask upper DSCP bits - part 3

tl;dr - This patchset continues to unmask the upper DSCP bits in the
IPv4 flow key in preparation for allowing IPv4 FIB rules to match on
DSCP. No functional changes are expected.

The TOS field in the IPv4 flow key ('flowi4_tos') is used during FIB
lookup to match against the TOS selector in FIB rules and routes.

It is currently impossible for user space to configure FIB rules that
match on the DSCP value as the upper DSCP bits are either masked in the
various call sites that initialize the IPv4 flow key or along the path
to the FIB core.

In preparation for adding a DSCP selector to IPv4 and IPv6 FIB rules, we
need to make sure the entire DSCP value is present in the IPv4 flow key.
This patchset continues to unmask the upper DSCP bits, but this time in
the output route path, specifically in the callers of
ip_route_output_ports().

The next patchset (last) will handle the callers of
ip_route_output_key(). Split from this patchset to avoid going over the
15 patches limit.

No functional changes are expected as commit 1fa3314c14c6 ("ipv4:
Centralize TOS matching") moved the masking of the upper DSCP bits to
the core where 'flowi4_tos' is matched against the TOS selector.
====================

Link: https://patch.msgid.link/20240903135327.2810535-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 9 insertions, 6 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index eea443b7f65e..49811c9281d4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -494,7 +494,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 					   inet->inet_dport,
 					   inet->inet_sport,
 					   sk->sk_protocol,
-					   RT_TOS(tos),
+					   tos & INET_DSCP_MASK,
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f1a43199551b..089864c6a35e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1869,7 +1869,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 					   vif->remote, vif->local,
 					   0, 0,
 					   IPPROTO_IPIP,
-					   RT_TOS(iph->tos), vif->link);
+					   iph->tos & INET_DSCP_MASK, vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 		encap = sizeof(struct iphdr);
@@ -1877,7 +1877,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0,
 					   0, 0,
 					   IPPROTO_IPIP,
-					   RT_TOS(iph->tos), vif->link);
+					   iph->tos & INET_DSCP_MASK, vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 	}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ec51ab5063e8..b60e13c42bca 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -53,6 +53,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
 
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
@@ -608,7 +609,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	/* Try to guess incoming interface */
 	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,
-				   0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+				   0, 0, 0, IPPROTO_IPIP,
+				   eiph->tos & INET_DSCP_MASK, 0);
 	if (IS_ERR(rt))
 		goto out;
 
@@ -619,7 +621,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (rt->rt_flags & RTCF_LOCAL) {
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr, 0, 0,
-					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+					   IPPROTO_IPIP,
+					   eiph->tos & INET_DSCP_MASK, 0);
 		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 16b90a24c9ba..39bd8951bfca 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1112,7 +1112,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 							  iph->daddr, iph->saddr,
 							  0, 0,
 							  IPPROTO_IPV6,
-							  RT_TOS(iph->tos),
+							  iph->tos & INET_DSCP_MASK,
 							  tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {