Merge branch 'net-sched-use-the-backlog-for-nested-mirred-ingress'

Davide Caratti says:

====================
net/sched: use the backlog for nested mirred ingress

TC mirred has a protection against excessive stack growth, but that
protection doesn't really guarantee the absence of recursion, nor
it guards against loops. Patch 1/2 rewords "recursion" to "nesting" to
make this more clear.
We can leverage on this existing mechanism to prevent TCP / SCTP from doing
soft lock-up in some specific scenarios that uses mirred egress->ingress:
patch 2 changes mirred so that the networking backlog is used for nested
mirred ingress actions.
====================

Link: https://lore.kernel.org/r/cover.1674233458.git.dcaratti@redhat.comSigned-off-by: Paolo Abeni <pabeni@redhat.com>

net/sched/act_mirred.c

@@ -29,8 +29,8 @@
 static LIST_HEAD(mirred_list);
 static DEFINE_SPINLOCK(mirred_list_lock);
 
-#define MIRRED_RECURSION_LIMIT    4
-static DEFINE_PER_CPU(unsigned int, mirred_rec_level);
+#define MIRRED_NEST_LIMIT    4
+static DEFINE_PER_CPU(unsigned int, mirred_nest_level);
 
 static bool tcf_mirred_is_act_redirect(int action)
 {
@@ -206,12 +206,19 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	return err;
 }
 
+static bool is_mirred_nested(void)
+{
+	return unlikely(__this_cpu_read(mirred_nest_level) > 1);
+}
+
 static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
 {
 	int err;
 
 	if (!want_ingress)
 		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+	else if (is_mirred_nested())
+		err = netif_rx(skb);
 	else
 		err = netif_receive_skb(skb);
 
@@ -226,7 +233,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	struct sk_buff *skb2 = skb;
 	bool m_mac_header_xmit;
 	struct net_device *dev;
-	unsigned int rec_level;
+	unsigned int nest_level;
 	int retval, err = 0;
 	bool use_reinsert;
 	bool want_ingress;
@@ -237,11 +244,11 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	int mac_len;
 	bool at_nh;
 
-	rec_level = __this_cpu_inc_return(mirred_rec_level);
-	if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) {
+	nest_level = __this_cpu_inc_return(mirred_nest_level);
+	if (unlikely(nest_level > MIRRED_NEST_LIMIT)) {
 		net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n",
 				     netdev_name(skb->dev));
-		__this_cpu_dec(mirred_rec_level);
+		__this_cpu_dec(mirred_nest_level);
 		return TC_ACT_SHOT;
 	}
 
@@ -310,7 +317,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 			err = tcf_mirred_forward(want_ingress, skb);
 			if (err)
 				tcf_action_inc_overlimit_qstats(&m->common);
-			__this_cpu_dec(mirred_rec_level);
+			__this_cpu_dec(mirred_nest_level);
 			return TC_ACT_CONSUMED;
 		}
 	}
@@ -322,7 +329,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 		if (tcf_mirred_is_act_redirect(m_eaction))
 			retval = TC_ACT_SHOT;
 	}
-	__this_cpu_dec(mirred_rec_level);
+	__this_cpu_dec(mirred_nest_level);
 
 	return retval;
 }

tools/testing/selftests/net/forwarding/tc_actions.sh

@@ -3,7 +3,8 @@
 
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
 	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
-	gact_trap_test mirred_egress_to_ingress_test"
+	gact_trap_test mirred_egress_to_ingress_test \
+	mirred_egress_to_ingress_tcp_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -198,6 +199,52 @@ mirred_egress_to_ingress_test()
 	log_test "mirred_egress_to_ingress ($tcflags)"
 }
 
+mirred_egress_to_ingress_tcp_test()
+{
+	local tmpfile=$(mktemp) tmpfile1=$(mktemp)
+
+	RET=0
+	dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile
+	tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \
+		$tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \
+			action ct commit nat src addr 192.0.2.2 pipe \
+			action ct clear pipe \
+			action ct commit nat dst addr 192.0.2.1 pipe \
+			action ct clear pipe \
+			action skbedit ptype host pipe \
+			action mirred ingress redirect dev $h1
+	tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \
+		$tcflags ip_proto icmp \
+			action mirred ingress redirect dev $h1
+	tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \
+		ip_proto icmp \
+			action drop
+
+	ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1  &
+	local rpid=$!
+	ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile
+	wait -n $rpid
+	cmp -s $tmpfile $tmpfile1
+	check_err $? "server output check failed"
+
+	$MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \
+		-t icmp "ping,id=42,seq=5" -q
+	tc_check_packets "dev $h1 egress" 101 10
+	check_err $? "didn't mirred redirect ICMP"
+	tc_check_packets "dev $h1 ingress" 102 10
+	check_err $? "didn't drop mirred ICMP"
+	local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits)
+	test ${overlimits} = 10
+	check_err $? "wrong overlimits, expected 10 got ${overlimits}"
+
+	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
+	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
+	tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower
+
+	rm -f $tmpfile $tmpfile1
+	log_test "mirred_egress_to_ingress_tcp ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}