[PATCH v3 5/7] net/sched: Fix ethx:ingress -> ethy:egress -> ethx:ingress mirred loop

[Stephen Hemminger <stephen@networkplumber.org>]

From: Jamal Hadi Salim <jhs@mojatatu.com>

When mirred redirects to ingress (from either ingress or egress) the loop
state from sched_mirred_dev array dev is lost because of 1) the packet
deferral into the backlog and 2) the fact the sched_mirred_dev array is
cleared. In such cases, if there was a loop we won't discover it.

Here's a simple test to reproduce:
ip a add dev port0 10.10.10.11/24

tc qdisc add dev port0 clsact
tc filter add dev port0 egress protocol ip \
   prio 10 matchall action mirred ingress redirect dev port1

tc qdisc add dev port1 clsact
tc filter add dev port1 ingress protocol ip \
   prio 10 matchall action mirred egress redirect dev port0

ping -c 1 -W0.01 10.10.10.10

Fixes: fe946a751d9b ("net/sched: act_mirred: add loop detection")
Tested-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
---
 net/sched/act_mirred.c | 47 +++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 05e0b14b5773..001dd9275e9b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -26,6 +26,10 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_wrapper.h>
 
+#define MIRRED_DEFER_LIMIT 3
+_Static_assert(MIRRED_DEFER_LIMIT <= 3,
+	       "MIRRED_DEFER_LIMIT exceeds tc_depth bitfield width");
+
 static LIST_HEAD(mirred_list);
 static DEFINE_SPINLOCK(mirred_list_lock);
 
@@ -234,12 +238,15 @@ tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb)
 {
 	int err;
 
-	if (!want_ingress)
+	if (!want_ingress) {
 		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
-	else if (!at_ingress)
-		err = netif_rx(skb);
-	else
-		err = netif_receive_skb(skb);
+	} else {
+		skb->tc_depth++;
+		if (!at_ingress)
+			err = netif_rx(skb);
+		else
+			err = netif_receive_skb(skb);
+	}
 
 	return err;
 }
@@ -426,6 +433,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	struct netdev_xmit *xmit;
 	bool m_mac_header_xmit;
 	struct net_device *dev;
+	bool want_ingress;
 	int i, m_eaction;
 	u32 blockid;
 
@@ -434,7 +442,8 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 #else
 	xmit = this_cpu_ptr(&softnet_data.xmit);
 #endif
-	if (unlikely(xmit->sched_mirred_nest >= MIRRED_NEST_LIMIT)) {
+	if (unlikely(xmit->sched_mirred_nest >= MIRRED_NEST_LIMIT ||
+		     skb->tc_depth >= MIRRED_DEFER_LIMIT)) {
 		net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n",
 				     netdev_name(skb->dev));
 		return TC_ACT_SHOT;
@@ -453,23 +462,27 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 		tcf_action_inc_overlimit_qstats(&m->common);
 		return retval;
 	}
-	for (i = 0; i < xmit->sched_mirred_nest; i++) {
-		if (xmit->sched_mirred_dev[i] != dev)
-			continue;
-		pr_notice_once("tc mirred: loop on device %s\n",
-			       netdev_name(dev));
-		tcf_action_inc_overlimit_qstats(&m->common);
-		return retval;
-	}
 
-	xmit->sched_mirred_dev[xmit->sched_mirred_nest++] = dev;
+	m_eaction = READ_ONCE(m->tcfm_eaction);
+	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+	if (!want_ingress) {
+		for (i = 0; i < xmit->sched_mirred_nest; i++) {
+			if (xmit->sched_mirred_dev[i] != dev)
+				continue;
+			pr_notice_once("tc mirred: loop on device %s\n",
+				       netdev_name(dev));
+			tcf_action_inc_overlimit_qstats(&m->common);
+			return retval;
+		}
+		xmit->sched_mirred_dev[xmit->sched_mirred_nest++] = dev;
+	}
 
 	m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
-	m_eaction = READ_ONCE(m->tcfm_eaction);
 
 	retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction,
 				   retval);
-	xmit->sched_mirred_nest--;
+	if (!want_ingress)
+		xmit->sched_mirred_nest--;
 
 	return retval;
 }
-- 
2.53.0