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>
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 1c012cb..ef0b861 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -120,6 +120,10 @@
Alexey Kuznetsov.
*/
+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 struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);
@@ -204,7 +208,9 @@
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;
@@ -587,17 +593,6 @@
t->err_time = jiffies;
}
-static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
-{
- if (INET_ECN_is_ce(iph->tos)) {
- if (skb->protocol == htons(ETH_P_IP)) {
- IP_ECN_set_ce(ip_hdr(skb));
- } else if (skb->protocol == htons(ETH_P_IPV6)) {
- IP6_ECN_set_ce(ipv6_hdr(skb));
- }
- }
-}
-
static inline u8
ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
{
@@ -620,6 +615,7 @@
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
+ int err;
if (!pskb_may_pull(skb, 16))
goto drop;
@@ -723,17 +719,27 @@
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
+ __skb_tunnel_rx(skb, tunnel->dev);
+
+ skb_reset_network_header(skb);
+ 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 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);
- ipgre_ecn_decapsulate(iph, skb);
-
netif_rx(skb);
return 0;