Re: [PATCH net-next] vxlan: add support for flowlabel inherit

[Tom Herbert <tom@herbertland.com>]

On Sat, Sep 30, 2023 at 8:14 AM Alce Lafranque <alce@lafranque.net> wrote:
>
> 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.

Is there any reason not to make setting the flow label on by default?
We've been doing this for TCP for quite a while now and it's not
breaking the network.

Tom

>
> ```
> $ ./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

Alce,

Is there any reason not to always set the flow label or at least make
setting the flow label be the default? We've been doing this for TCP
for quite a while now and it's not breaking the network, and we're
already setting the UDP source port with flow entropy in VXLAN anyway.

Tom

> $ ./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>
> ---
>  drivers/net/vxlan/vxlan_core.c | 20 ++++++++++++++++++--
>  include/net/ip_tunnels.h       | 11 +++++++++++
>  include/net/vxlan.h            |  2 ++
>  include/uapi/linux/if_link.h   |  1 +
>  4 files changed, 32 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
> index 5b5597073b00..aa7fbfdd93b1 100644
> --- a/drivers/net/vxlan/vxlan_core.c
> +++ b/drivers/net/vxlan/vxlan_core.c
> @@ -2475,7 +2475,11 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
>                 else
>                         udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
>  #if IS_ENABLED(CONFIG_IPV6)
> -               label = vxlan->cfg.label;
> +               if (flags & VXLAN_F_LABEL_INHERIT) {
> +                       label = ip_tunnel_get_flowlabel(old_iph, skb);
> +               } else {
> +                       label = vxlan->cfg.label;
> +               }
>  #endif
>         } else {
>                 if (!info) {
> @@ -3286,6 +3290,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
>         [IFLA_VXLAN_DF]         = { .type = NLA_U8 },
>         [IFLA_VXLAN_VNIFILTER]  = { .type = NLA_U8 },
>         [IFLA_VXLAN_LOCALBYPASS]        = NLA_POLICY_MAX(NLA_U8, 1),
> +       [IFLA_VXLAN_LABEL_INHERIT]      = { .type = NLA_FLAG },
>  };
>
>  static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
> @@ -4001,7 +4006,15 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
>
>         if (data[IFLA_VXLAN_LABEL])
>                 conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
> -                            IPV6_FLOWLABEL_MASK;
> +                             IPV6_FLOWLABEL_MASK;
> +
> +       if (data[IFLA_VXLAN_LABEL_INHERIT]) {
> +               err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LABEL_INHERIT,
> +                                   VXLAN_F_LABEL_INHERIT, changelink, false,
> +                                   extack);
> +               if (err)
> +                       return err;
> +       }
>
>         if (data[IFLA_VXLAN_LEARNING]) {
>                 err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING,
> @@ -4315,6 +4328,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
>                 nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_TOS */
>                 nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_DF */
>                 nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
> +               nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_LABEL_INHERIT */
>                 nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_LEARNING */
>                 nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_PROXY */
>                 nla_total_size(sizeof(__u8)) +  /* IFLA_VXLAN_RSC */
> @@ -4387,6 +4401,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
>             nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
>             nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
>             nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
> +           nla_put_u8(skb, IFLA_VXLAN_LABEL_INHERIT,
> +                      !!(vxlan->cfg.flags & VXLAN_F_LABEL_INHERIT)) ||
>             nla_put_u8(skb, IFLA_VXLAN_LEARNING,
>                        !!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||
>             nla_put_u8(skb, IFLA_VXLAN_PROXY,
> 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..f82ce013c8ff 100644
> --- a/include/net/vxlan.h
> +++ b/include/net/vxlan.h
> @@ -329,6 +329,7 @@ struct vxlan_dev {
>  #define VXLAN_F_VNIFILTER               0x20000
>  #define VXLAN_F_MDB                    0x40000
>  #define VXLAN_F_LOCALBYPASS            0x80000
> +#define VXLAN_F_LABEL_INHERIT          0x100000
>
>  /* Flags that are used in the receive path. These flags must match in
>   * order for a socket to be shareable
> @@ -534,6 +535,7 @@ static inline void vxlan_flag_attr_error(int attrtype,
>                 break
>         switch (attrtype) {
>         VXLAN_FLAG(TTL_INHERIT);
> +       VXLAN_FLAG(LABEL_INHERIT);
>         VXLAN_FLAG(LEARNING);
>         VXLAN_FLAG(PROXY);
>         VXLAN_FLAG(RSC);
> diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
> index fac351a93aed..bd69af34feba 100644
> --- a/include/uapi/linux/if_link.h
> +++ b/include/uapi/linux/if_link.h
> @@ -830,6 +830,7 @@ enum {
>         IFLA_VXLAN_DF,
>         IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
>         IFLA_VXLAN_LOCALBYPASS,
> +       IFLA_VXLAN_LABEL_INHERIT,
>         __IFLA_VXLAN_MAX
>  };
>  #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
> --
> 2.39.2
>