IPVS tunnel mode works as simple tunnel (see RFC 3168) copying ECN field
to outer header. That's result in packet drops on egress tunnels in case
the egress tunnel operates as ECN-capable with Full-functionality option
(like ip_tunnel and ip6_tunnel kernel modules), according to RFC 3168
section 9.1.1 recommendation.
This patch implements ECN full-functionality option into ipvs xmit code.
Cc: netdev@vger.kernel.org
Cc: lvs-de...@vger.kernel.org
Signed-off-by: Vadim Fedorenko <vfedore...@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebni...@yandex-team.ru>
---
net/netfilter/ipvs/ip_vs_xmit.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 01d3d89..b3286f3 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -879,6 +879,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff
*skb,
{
struct sk_buff *new_skb = NULL;
struct iphdr *old_iph = NULL;
+ __u8 old_dsfield;
#ifdef CONFIG_IP_VS_IPV6
struct ipv6hdr *old_ipv6h = NULL;
#endif
@@ -903,7 +904,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff
*skb,
*payload_len =
ntohs(old_ipv6h->payload_len) +
sizeof(*old_ipv6h);
- *dsfield = ipv6_get_dsfield(old_ipv6h);
+ old_dsfield = ipv6_get_dsfield(old_ipv6h);
*ttl = old_ipv6h->hop_limit;
if (df)
*df = 0;
@@ -918,12 +919,15 @@ static inline int ip_vs_send_or_cont(int pf, struct
sk_buff *skb,
/* fix old IP header checksum */
ip_send_check(old_iph);
- *dsfield = ipv4_get_dsfield(old_iph);
+ old_dsfield = ipv4_get_dsfield(old_iph);
*ttl = old_iph->ttl;
if (payload_len)
*payload_len = ntohs(old_iph->tot_len);
}
+ /* Implement full-functionality option for ECN encapsulation */
+ *dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield);
+
return skb;
error:
kfree_skb(skb);
--
1.9.1
