Merge branch 'unmask-dscp-part-four'

Ido Schimmel says:

====================
Unmask upper DSCP bits - part 4 (last)

tl;dr - This patchset finishes 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 finishes to unmask the upper DSCP bits by adjusting all
the callers of ip_route_output_key() to properly initialize the full
DSCP value in the IPv4 flow key.

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.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 23 insertions, 14 deletions

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 8f9c19d992ac..0e8bc0ea6175 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -36,6 +36,7 @@
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
 #include <net/netns/generic.h>
+#include <net/inet_dscp.h>
 
 #include <linux/uaccess.h>
 #include "br_private.h"
@@ -402,7 +403,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 				goto free_skb;
 
 			rt = ip_route_output(net, iph->daddr, 0,
-					     RT_TOS(iph->tos), 0,
+					     iph->tos & INET_DSCP_MASK, 0,
 					     RT_SCOPE_UNIVERSE);
 			if (!IS_ERR(rt)) {
 				/* - Bridged-and-DNAT'ed traffic doesn't
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index afb05f58b64c..1a14f915b7a4 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -12,6 +12,7 @@
 #include <net/gre.h>
 #include <net/ip6_route.h>
 #include <net/ipv6_stubs.h>
+#include <net/inet_dscp.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
@@ -205,7 +206,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 		fl4.flowi4_oif = oif;
 		fl4.flowi4_mark = skb->mark;
 		fl4.flowi4_uid = sock_net_uid(net, sk);
-		fl4.flowi4_tos = RT_TOS(iph->tos);
+		fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 		fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		fl4.flowi4_proto = iph->protocol;
 		fl4.daddr = iph->daddr;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d2463b6e390e..e1384e7331d8 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -445,7 +445,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.saddr = saddr;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
-	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
+	fl4.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK;
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
 	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index b54c41f3ae3c..5f6fd382af38 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -44,6 +44,7 @@
 #include <net/gre.h>
 #include <net/dst_metadata.h>
 #include <net/erspan.h>
+#include <net/inet_dscp.h>
 
 /*
    Problems & solutions
@@ -930,7 +931,7 @@ static int ipgre_open(struct net_device *dev)
 					 t->parms.iph.daddr,
 					 t->parms.iph.saddr,
 					 t->parms.o_key,
-					 RT_TOS(t->parms.iph.tos),
+					 t->parms.iph.tos & INET_DSCP_MASK,
 					 t->parms.link);
 		if (IS_ERR(rt))
 			return -EADDRNOTAVAIL;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 18964394d6bd..d591c73e2c0e 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -43,6 +43,7 @@
 #include <net/rtnetlink.h>
 #include <net/udp.h>
 #include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -293,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), dev_net(dev),
+				    iph->tos & INET_DSCP_MASK, dev_net(dev),
 				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
@@ -609,9 +610,9 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
-			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
-			    key->flow_flags);
+			    tunnel_id_to_key32(key->tun_id),
+			    tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+			    skb_get_hash(skb), key->flow_flags);
 
 	if (!tunnel_hlen)
 		tunnel_hlen = ip_encap_hlen(&tun_info->encap);
@@ -772,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos),
+			    tunnel->parms.o_key, tos & INET_DSCP_MASK,
 			    dev_net(dev), READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 591a2737808e..e0aab66cd925 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -14,6 +14,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#include <net/inet_dscp.h>
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
@@ -43,7 +44,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un
 	 */
 	fl4.daddr = iph->daddr;
 	fl4.saddr = saddr;
-	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
 	fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev);
 	fl4.flowi4_mark = skb->mark;
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index 6cc5743c553a..f4aed0789d69 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -15,6 +15,7 @@
 #include <net/icmp.h>
 #include <net/ip.h>
 #include <net/route.h>
+#include <net/inet_dscp.h>
 #include <net/netfilter/ipv4/nf_dup_ipv4.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
@@ -32,7 +33,7 @@ static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb,
 		fl4.flowi4_oif = oif;
 
 	fl4.daddr = gw->s_addr;
-	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH;
 	rt = ip_route_output_key(net, &fl4);
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index e4e0fa869fa4..619a53eb672d 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -6,6 +6,7 @@
 #include <net/dst_metadata.h>
 #include <net/udp.h>
 #include <net/udp_tunnel.h>
+#include <net/inet_dscp.h>
 
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
@@ -232,7 +233,7 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
 	fl4.saddr = key->u.ipv4.src;
 	fl4.fl4_dport = dport;
 	fl4.fl4_sport = sport;
-	fl4.flowi4_tos = RT_TOS(tos);
+	fl4.flowi4_tos = tos & INET_DSCP_MASK;
 	fl4.flowi4_flags = key->flow_flags;
 
 	rt = ip_route_output_key(net, &fl4);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 9dcd1548df9d..2f732fae5a83 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -9,6 +9,7 @@
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/ip.h> /* for ipv4 options. */
+#include <net/inet_dscp.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_conntrack_core.h>
@@ -235,7 +236,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 		fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip;
 		fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
 		fl.u.ip4.flowi4_iif = this_dst->dev->ifindex;
-		fl.u.ip4.flowi4_tos = RT_TOS(ip_hdr(pkt->skb)->tos);
+		fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK;
 		fl.u.ip4.flowi4_mark = pkt->skb->mark;
 		fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		break;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5a7436a13b74..39ca5403d4d7 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -44,6 +44,7 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 #include <net/udp_tunnel.h>
+#include <net/inet_dscp.h>
 
 #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
 
@@ -435,7 +436,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl4->flowi4_tos = RT_TOS(tos);
+		fl4->flowi4_tos = tos & INET_DSCP_MASK;
 		fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
 		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
 		fl4->fl4_sport = htons(asoc->base.bind_addr.port);