The current code retrieves the TOS field after the lookup
on the ipv4 routing table. The routing process currently
only allows routing based on the original 3 TOS bits, and
not on the full 6 DSCP bits.
As a result the retrieved TOS is cut to the 3 bits.
However for inheriting purposes the full 6 bits should be used.
Extract the full 6 bits before the route lookup and use
that instead of the cut off 3 TOS bits.
This patch is the functional equivalent for IPv4 to the patch
"geneve: do not use RT_TOS for IPv6 flowlabel"
Fixes: e305ac6cf5a1 ("geneve: Add support to collect tunnel metadata.")
Signed-off-by: Matthias May <[email protected]>
---
v1 -> v2:
- Fix typo in "Fixes" tag
---
drivers/net/geneve.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 2495a5719e1c..4c380c06f178 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -797,7 +797,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
struct geneve_sock *gs4,
struct flowi4 *fl4,
const struct ip_tunnel_info *info,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ __u8 *full_tos)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
@@ -822,6 +823,7 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
use_cache = false;
}
fl4->flowi4_tos = RT_TOS(tos);
+ *full_tos = tos;
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
@@ -910,6 +912,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
const struct ip_tunnel_key *key = &info->key;
struct rtable *rt;
struct flowi4 fl4;
+ __u8 full_tos;
__u8 tos, ttl;
__be16 df = 0;
__be16 sport;
@@ -920,7 +923,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
- geneve->cfg.info.key.tp_dst, sport);
+ geneve->cfg.info.key.tp_dst, sport, &full_tos);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -964,7 +967,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
} else {
- tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
+ tos = ip_tunnel_ecn_encap(full_tos, ip_hdr(skb), skb);
if (geneve->cfg.ttl_inherit)
ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
else
@@ -1137,6 +1140,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct ip_tunnel_info *info = skb_tunnel_info(skb);
struct geneve_dev *geneve = netdev_priv(dev);
+ __u8 full_tos;
__be16 sport;
if (ip_tunnel_info_af(info) == AF_INET) {
@@ -1148,7 +1152,8 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
- geneve->cfg.info.key.tp_dst, sport);
+ geneve->cfg.info.key.tp_dst, sport,
+ &full_tos);
if (IS_ERR(rt))
return PTR_ERR(rt);
--
2.35.1