ip6tnl/sit: drop packet if ECN present with not-ECT

This patch reports the change made by Stephen Hemminger in ipip and gre[6] in
commit eccc1bb8d4b4 (tunnel: drop packet if ECN present with not-ECT).

Goal is to handle RFC6040, Section 4.2:

Default Tunnel Egress Behaviour.
 o If the inner ECN field is Not-ECT, the decapsulator MUST NOT
      propagate any other ECN codepoint onwards.  This is because the
      inner Not-ECT marking is set by transports that rely on dropped
      packets as an indication of congestion and would not understand or
      respond to any other ECN codepoint [RFC4774].  Specifically:

      *  If the inner ECN field is Not-ECT and the outer ECN field is
         CE, the decapsulator MUST drop the packet.

      *  If the inner ECN field is Not-ECT and the outer ECN field is
         Not-ECT, ECT(0), or ECT(1), the decapsulator MUST forward the
         outgoing packet with the ECN field cleared to Not-ECT.

The patch takes benefits from common function added in net/inet_ecn.h.

Like it was done for Xin4 tunnels, it adds logging to allow detecting broken
systems that set ECN bits incorrectly when tunneling (or an intermediate
router might be changing the header). Errors are also tracked via
rx_frame_error.

CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 21 insertions, 12 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 80cb3829831c..cfba99b2c2a4 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -65,6 +65,10 @@
 #define HASH_SIZE  16
 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
 
+static bool log_ecn_error = true;
+module_param(log_ecn_error, bool, 0644);
+MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
+
 static int ipip6_tunnel_init(struct net_device *dev);
 static void ipip6_tunnel_setup(struct net_device *dev);
 static void ipip6_dev_free(struct net_device *dev);
@@ -106,6 +110,7 @@ static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
 	}
 
 	tot->rx_errors = dev->stats.rx_errors;
+	tot->rx_frame_errors = dev->stats.rx_frame_errors;
 	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
 	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
 	tot->tx_dropped = dev->stats.tx_dropped;
@@ -585,16 +590,11 @@ out:
 	return err;
 }
 
-static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
-{
-	if (INET_ECN_is_ce(iph->tos))
-		IP6_ECN_set_ce(ipv6_hdr(skb));
-}
-
 static int ipip6_rcv(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
+	int err;
 
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto out;
@@ -616,18 +616,27 @@ static int ipip6_rcv(struct sk_buff *skb)
 		if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
 		    !isatap_chksrc(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
-			kfree_skb(skb);
-			return 0;
+			goto out;
+		}
+
+		__skb_tunnel_rx(skb, tunnel->dev);
+
+		err = IP_ECN_decapsulate(iph, skb);
+		if (unlikely(err)) {
+			if (log_ecn_error)
+				net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+						     &iph->saddr, iph->tos);
+			if (err > 1) {
+				++tunnel->dev->stats.rx_frame_errors;
+				++tunnel->dev->stats.rx_errors;
+				goto out;
+			}
 		}
 
 		tstats = this_cpu_ptr(tunnel->dev->tstats);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
 
-		__skb_tunnel_rx(skb, tunnel->dev);
-
-		ipip6_ecn_decapsulate(iph, skb);
-
 		netif_rx(skb);
 
 		return 0;