vxlan: add support for flowlabel inherit

By default, VXLAN encapsulation over IPv6 sets the flow label to 0, with
an option for a fixed value. This commits add the ability to inherit the
flow label from the inner packet, like for other tunnel implementations.
This enables devices using only L3 headers for ECMP to correctly balance
VXLAN-encapsulated IPv6 packets.

```
$ ./ip/ip link add dummy1 type dummy
$ ./ip/ip addr add 2001:db8::2/64 dev dummy1
$ ./ip/ip link set up dev dummy1
$ ./ip/ip link add vxlan1 type vxlan id 100 flowlabel inherit remote 2001:db8::1 local 2001:db8::2
$ ./ip/ip link set up dev vxlan1
$ ./ip/ip addr add 2001:db8:1::2/64 dev vxlan1
$ ./ip/ip link set arp off dev vxlan1
$ ping -q 2001:db8:1::1 &
$ tshark -d udp.port==8472,vxlan -Vpni dummy1 -c1
[...]
Internet Protocol Version 6, Src: 2001:db8::2, Dst: 2001:db8::1
    0110 .... = Version: 6
    .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT)
        .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0)
        .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0)
    .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb
[...]
Virtual eXtensible Local Area Network
    Flags: 0x0800, VXLAN Network ID (VNI)
    Group Policy ID: 0
    VXLAN Network Identifier (VNI): 100
[...]
Internet Protocol Version 6, Src: 2001:db8:1::2, Dst: 2001:db8:1::1
    0110 .... = Version: 6
    .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT)
        .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0)
        .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0)
    .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb
```

Signed-off-by: Alce Lafranque <alce@lafranque.net>
Co-developed-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 28 insertions, 16 deletions

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f346b4efbc30..2d746f4c9a0a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -416,6 +416,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 		return 0;
 }
 
+static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph,
+					     const struct sk_buff *skb)
+{
+	__be16 payload_protocol = skb_protocol(skb, true);
+
+	if (payload_protocol == htons(ETH_P_IPV6))
+		return ip6_flowlabel((const struct ipv6hdr *)iph);
+	else
+		return 0;
+}
+
 static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 				       const struct sk_buff *skb)
 {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 6a9f8a5f387c..33ba6fc151cf 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -210,22 +210,23 @@ struct vxlan_rdst {
 };
 
 struct vxlan_config {
-	union vxlan_addr	remote_ip;
-	union vxlan_addr	saddr;
-	__be32			vni;
-	int			remote_ifindex;
-	int			mtu;
-	__be16			dst_port;
-	u16			port_min;
-	u16			port_max;
-	u8			tos;
-	u8			ttl;
-	__be32			label;
-	u32			flags;
-	unsigned long		age_interval;
-	unsigned int		addrmax;
-	bool			no_share;
-	enum ifla_vxlan_df	df;
+	union vxlan_addr		remote_ip;
+	union vxlan_addr		saddr;
+	__be32				vni;
+	int				remote_ifindex;
+	int				mtu;
+	__be16				dst_port;
+	u16				port_min;
+	u16				port_max;
+	u8				tos;
+	u8				ttl;
+	__be32				label;
+	enum ifla_vxlan_label_policy	label_policy;
+	u32				flags;
+	unsigned long			age_interval;
+	unsigned int			addrmax;
+	bool				no_share;
+	enum ifla_vxlan_df		df;
 };
 
 enum {