ipv4: Stop taking ECN bits into account in fib4-rules

Use the new dscp_t type to replace the tos field of struct fib4_rule,
so that fib4-rules consistently ignore ECN bits.

Before this patch, fib4-rules did accept rules with the high order ECN
bit set (but not the low order one). Also, it relied on its callers
masking the ECN bits of ->flowi4_tos to prevent those from influencing
the result. This was brittle and a few call paths still do the lookup
without masking the ECN bits first.

After this patch fib4-rules only compare the DSCP bits. ECN can't
influence the result anymore, even if the caller didn't mask these
bits. Also, fib4-rules now must have both ECN bits cleared or they will
be rejected.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/ipv4/fib_rules.c

@@ -23,6 +23,7 @@
 #include <linux/list.h>
 #include <linux/rcupdate.h>
 #include <linux/export.h>
+#include <net/inet_dscp.h>
 #include <net/ip.h>
 #include <net/route.h>
 #include <net/tcp.h>
@@ -35,7 +36,7 @@ struct fib4_rule {
 	struct fib_rule		common;
 	u8			dst_len;
 	u8			src_len;
-	u8			tos;
+	dscp_t			dscp;
 	__be32			src;
 	__be32			srcmask;
 	__be32			dst;
@@ -49,7 +50,7 @@ static bool fib4_rule_matchall(const struct fib_rule *rule)
 {
 	struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
 
-	if (r->dst_len || r->src_len || r->tos)
+	if (r->dst_len || r->src_len || r->dscp)
 		return false;
 	return fib_rule_matchall(rule);
 }
@@ -185,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
 	    ((daddr ^ r->dst) & r->dstmask))
 		return 0;
 
-	if (r->tos && (r->tos != fl4->flowi4_tos))
+	if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos))
 		return 0;
 
 	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
@@ -225,10 +226,12 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	int err = -EINVAL;
 	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
 
-	if (frh->tos & ~IPTOS_TOS_MASK) {
+	if (!inet_validate_dscp(frh->tos)) {
-		NL_SET_ERR_MSG(extack, "Invalid tos");
+		NL_SET_ERR_MSG(extack,
+			       "Invalid dsfield (tos): ECN bits must be 0");
 		goto errout;
 	}
+	rule4->dscp = inet_dsfield_to_dscp(frh->tos);
 
 	/* split local/main if they are not already split */
 	err = fib_unmerge(net);
@@ -270,7 +273,6 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->srcmask = inet_make_mask(rule4->src_len);
 	rule4->dst_len = frh->dst_len;
 	rule4->dstmask = inet_make_mask(rule4->dst_len);
-	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
 
@@ -313,7 +315,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->dst_len && (rule4->dst_len != frh->dst_len))
 		return 0;
 
-	if (frh->tos && (rule4->tos != frh->tos))
+	if (frh->tos && inet_dscp_to_dsfield(rule4->dscp) != frh->tos)
 		return 0;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -337,7 +339,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 
 	frh->dst_len = rule4->dst_len;
 	frh->src_len = rule4->src_len;
-	frh->tos = rule4->tos;
+	frh->tos = inet_dscp_to_dsfield(rule4->dscp);
 
 	if ((rule4->dst_len &&
 	     nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||

tools/testing/selftests/net/fib_rule_tests.sh

@@ -215,10 +215,25 @@ fib_rule4_test_match_n_redirect()
 	log_test $? 0 "rule4 del by pref: $description"
 }
 
+fib_rule4_test_reject()
+{
+	local match="$1"
+	local rc
+
+	$IP rule add $match table $RTABLE 2>/dev/null
+	rc=$?
+	log_test $rc 2 "rule4 check: $match"
+
+	if [ $rc -eq 0 ]; then
+		$IP rule del $match table $RTABLE
+	fi
+}
+
 fib_rule4_test()
 {
 	local getmatch
 	local match
+	local cnt
 
 	# setup the fib rule redirect route
 	$IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
@@ -234,8 +249,21 @@ fib_rule4_test()
 	fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
 	ip netns exec testns sysctl -qw net.ipv4.ip_forward=0
 
+	# Reject dsfield (tos) options which have ECN bits set
+	for cnt in $(seq 1 3); do
+		match="dsfield $cnt"
+		fib_rule4_test_reject "$match"
+	done
+
+	# Don't take ECN bits into account when matching on dsfield
 	match="tos 0x10"
-	fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table"
+	for cnt in "0x10" "0x11" "0x12" "0x13"; do
+		# Using option 'tos' instead of 'dsfield' as old iproute2
+		# versions don't support 'dsfield' in ip rule show.
+		getmatch="tos $cnt"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+						"$getmatch redirect to table"
+	done
 
 	match="fwmark 0x64"
 	getmatch="mark 0x64"