tunnel: drop packet if ECN present with not-ECT

Linux tunnels were written before RFC6040 and therefore never
implemented the corner case of ECN getting set in the outer header
and the inner header not being ready for it.

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.

This patch moves the ECN decap logic out of the individual tunnels
into a common place.

It also adds logging to allow detecting broken systems that
set ECN bits incorrectly when tunneling (or an intermediate
router might be changing the header).

Overloads rx_frame_error to keep track of ECN related error.

Thanks to Chris Wright who caught this while reviewing the new VXLAN
tunnel.

This code was tested by injecting faulty logic in other end GRE
to send incorrectly encapsulated packets.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 24 insertions, 30 deletions

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b987d4db790f..613a16647741 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -56,6 +56,10 @@
 #include <net/ip6_tunnel.h>
 
 
+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");
+
 #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
 #define IPV6_TCLASS_SHIFT 20
 
@@ -149,7 +153,9 @@ static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
         tot->rx_crc_errors = dev->stats.rx_crc_errors;
         tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
         tot->rx_length_errors = dev->stats.rx_length_errors;
+        tot->rx_frame_errors = dev->stats.rx_frame_errors;
         tot->rx_errors = dev->stats.rx_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;
@@ -489,28 +495,6 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
         t->err_time = jiffies;
 }
 
-static inline void ip6gre_ecn_decapsulate_ipv4(const struct ip6_tnl *t,
-                const struct ipv6hdr *ipv6h, struct sk_buff *skb)
-{
-        __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
-
-        if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
-                ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);
-
-        if (INET_ECN_is_ce(dsfield))
-                IP_ECN_set_ce(ip_hdr(skb));
-}
-
-static inline void ip6gre_ecn_decapsulate_ipv6(const struct ip6_tnl *t,
-                const struct ipv6hdr *ipv6h, struct sk_buff *skb)
-{
-        if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
-                ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));
-
-        if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h)))
-                IP6_ECN_set_ce(ipv6_hdr(skb));
-}
-
 static int ip6gre_rcv(struct sk_buff *skb)
 {
         const struct ipv6hdr *ipv6h;
@@ -522,6 +506,7 @@ static int ip6gre_rcv(struct sk_buff *skb)
         struct ip6_tnl *tunnel;
         int    offset = 4;
         __be16 gre_proto;
+        int err;
 
         if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
                 goto drop;
@@ -625,20 +610,29 @@ static int ip6gre_rcv(struct sk_buff *skb)
                         skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
                 }
 
+                __skb_tunnel_rx(skb, tunnel->dev);
+
+                skb_reset_network_header(skb);
+
+                err = IP6_ECN_decapsulate(ipv6h, skb);
+                if (unlikely(err)) {
+                        if (log_ecn_error)
+                                net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n",
+                                                     &ipv6h->saddr,
+                                                     ipv6_get_dsfield(ipv6h));
+                        if (err > 1) {
+                                ++tunnel->dev->stats.rx_frame_errors;
+                                ++tunnel->dev->stats.rx_errors;
+                                goto drop;
+                        }
+                }
+
                 tstats = this_cpu_ptr(tunnel->dev->tstats);
                 u64_stats_update_begin(&tstats->syncp);
                 tstats->rx_packets++;
                 tstats->rx_bytes += skb->len;
                 u64_stats_update_end(&tstats->syncp);
 
-                __skb_tunnel_rx(skb, tunnel->dev);
-
-                skb_reset_network_header(skb);
-                if (skb->protocol == htons(ETH_P_IP))
-                        ip6gre_ecn_decapsulate_ipv4(tunnel, ipv6h, skb);
-                else if (skb->protocol == htons(ETH_P_IPV6))
-                        ip6gre_ecn_decapsulate_ipv6(tunnel, ipv6h, skb);
-
                 netif_rx(skb);
 
                 return 0;