Merge branch 'unmask-upper-dscp-bits-part-1'

Ido Schimmel says:

====================
Unmask upper DSCP bits - part 1

tl;dr - This patchset starts 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 starts to unmask the upper DSCP bits in the various places
that invoke the core FIB lookup functions directly (patches #1-#7) and
in the input route path (patches #8-#12). Future patchsets will do the
same in the output route path.

No functional changes are expected as commit 1fa3314c ("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/20240821125251.1571445-1-idosch@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/core/filter.c

@@ -84,6 +84,7 @@
 #include <net/netkit.h>
 #include <linux/un.h>
 #include <net/xdp_sock_drv.h>
+#include <net/inet_dscp.h>
 
 #include "dev.h"
 
@@ -5899,7 +5900,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		fl4.flowi4_iif = params->ifindex;
 		fl4.flowi4_oif = 0;
 	}
-	fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+	fl4.flowi4_tos = params->tos & INET_DSCP_MASK;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_flags = 0;
 

net/ipv4/fib_frontend.c

@@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
-			.flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
+			.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK,
 			.flowi4_scope = scope,
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
@@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 	struct flowi4           fl4 = {
 		.flowi4_mark = frn->fl_mark,
 		.daddr = frn->fl_addr,
-		.flowi4_tos = frn->fl_tos & IPTOS_RT_MASK,
+		.flowi4_tos = frn->fl_tos & INET_DSCP_MASK,
 		.flowi4_scope = frn->fl_scope,
 	};
 	struct fib_table *tb;

net/ipv4/icmp.c

@@ -545,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 		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,
-				     RT_TOS(tos), rt2->dst.dev);
+				     tos, rt2->dst.dev);
 
 		dst_release(&rt2->dst);
 		rt2 = skb_rtable(skb_in);

net/ipv4/ipmr.c

@@ -62,6 +62,7 @@
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
 #include <net/rtnh.h>
+#include <net/inet_dscp.h>
 
 #include <linux/nospec.h>
 
@@ -2080,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
 	struct flowi4 fl4 = {
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
-		.flowi4_tos = RT_TOS(iph->tos),
+		.flowi4_tos = iph->tos & INET_DSCP_MASK,
 		.flowi4_oif = (rt_is_output_route(rt) ?
 			       skb->dev->ifindex : 0),
 		.flowi4_iif = (rt_is_output_route(rt) ?

net/ipv4/netfilter/ipt_rpfilter.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <net/inet_dscp.h>
 #include <linux/ip.h>
 #include <net/ip.h>
 #include <net/ip_fib.h>
@@ -75,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
+	flow.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
 	flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par));
 	flow.flowi4_uid = sock_net_uid(xt_net(par), NULL);

net/ipv4/netfilter/nft_fib_ipv4.c

@@ -10,6 +10,7 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_fib.h>
 
+#include <net/inet_dscp.h>
 #include <net/ip_fib.h>
 #include <net/route.h>
 
@@ -108,7 +109,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (priv->flags & NFTA_FIB_F_MARK)
 		fl4.flowi4_mark = pkt->skb->mark;
 
-	fl4.flowi4_tos = iph->tos & IPTOS_RT_MASK;
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 
 	if (priv->flags & NFTA_FIB_F_DADDR) {
 		fl4.daddr = iph->daddr;

net/ipv4/route.c

@@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		struct flowi4 fl4 = {
 			.daddr = iph->daddr,
 			.saddr = iph->saddr,
-			.flowi4_tos = iph->tos & IPTOS_RT_MASK,
+			.flowi4_tos = iph->tos & INET_DSCP_MASK,
 			.flowi4_oif = rt->dst.dev->ifindex,
 			.flowi4_iif = skb->dev->ifindex,
 			.flowi4_mark = skb->mark,
@@ -2160,7 +2160,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (rt->rt_type != RTN_LOCAL)
 		goto skip_validate_source;
 
-	tos &= IPTOS_RT_MASK;
+	tos &= INET_DSCP_MASK;
 	err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
 	if (err < 0)
 		goto martian_source;
@@ -2470,7 +2470,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct fib_result res;
 	int err;
 
-	tos &= IPTOS_RT_MASK;
+	tos &= INET_DSCP_MASK;
 	rcu_read_lock();
 	err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
 	rcu_read_unlock();
@@ -3286,7 +3286,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		skb->dev	= dev;
 		skb->mark	= mark;
 		err = ip_route_input_rcu(skb, dst, src,
-					 rtm->rtm_tos & IPTOS_RT_MASK, dev,
+					 rtm->rtm_tos & INET_DSCP_MASK, dev,
 					 &res);
 
 		rt = skb_rtable(skb);

net/ipv4/udp.c

@@ -115,6 +115,7 @@
 #include <net/addrconf.h>
 #include <net/udp_tunnel.h>
 #include <net/gro.h>
+#include <net/inet_dscp.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6_stubs.h>
 #endif
@@ -2618,7 +2619,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 		if (!inet_sk(sk)->inet_daddr && in_dev)
 			return ip_mc_validate_source(skb, iph->daddr,
 						     iph->saddr,
-						     iph->tos & IPTOS_RT_MASK,
+						     iph->tos & INET_DSCP_MASK,
 						     skb->dev, in_dev, &itag);
 	}
 	return 0;