[PATCHv2 net-next] vxlan: add ttl inherit support

[Hangbin Liu <liuhangbin@gmail.com>]

Like tos inherit, ttl inherit should also means inherit the inner protocol's
ttl values, which actually not implemented in vxlan yet.

But we could not treat ttl == 0 as "use the inner TTL", because that would be
used also when the "ttl" option is not specified and that would be a behavior
change, and breaking real use cases.

So add a different attribute IFLA_VXLAN_TTL_INHERIT when "ttl inherit" is
specified.

---
v2: As suggested by Stefano, clean up function ip_tunnel_get_ttl().

Suggested-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
 drivers/net/vxlan.c          | 17 ++++++++++++++---
 include/net/ip_tunnels.h     | 12 ++++++++++++
 include/net/vxlan.h          |  1 +
 include/uapi/linux/if_link.h |  1 +
 4 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aa5f034..209a840 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2085,9 +2085,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		local_ip = vxlan->cfg.saddr;
 		dst_cache = &rdst->dst_cache;
 		md->gbp = skb->mark;
-		ttl = vxlan->cfg.ttl;
-		if (!ttl && vxlan_addr_multicast(dst))
-			ttl = 1;
+		if (flags & VXLAN_F_TTL_INHERIT) {
+			ttl = ip_tunnel_get_ttl(old_iph, skb);
+		} else {
+			ttl = vxlan->cfg.ttl;
+			if (!ttl && vxlan_addr_multicast(dst))
+				ttl = 1;
+		}
 
 		tos = vxlan->cfg.tos;
 		if (tos == 1)
@@ -2709,6 +2713,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_GBP]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_GPE]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG },
+	[IFLA_VXLAN_TTL_INHERIT]	= { .type = NLA_FLAG },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -3254,6 +3259,12 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_VXLAN_TTL])
 		conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
 
+	if (data[IFLA_VXLAN_TTL_INHERIT]) {
+		if (changelink)
+			return -EOPNOTSUPP;
+		conf->flags |= VXLAN_F_TTL_INHERIT;
+	}
+
 	if (data[IFLA_VXLAN_LABEL])
 		conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
 			     IPV6_FLOWLABEL_MASK;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index cbe5add..5a8ab9f 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -377,6 +377,18 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 		return 0;
 }
 
+static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
+				       const struct sk_buff *skb)
+{
+	if (skb->protocol == htons(ETH_P_IP))
+		return iph->ttl;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		return ((const struct ipv6hdr *)iph)->hop_limit;
+
+	return 0;
+}
+
 /* Propogate ECN bits out */
 static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 				     const struct sk_buff *skb)
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index ad73d8b..b99a02ae 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -262,6 +262,7 @@ struct vxlan_dev {
 #define VXLAN_F_COLLECT_METADATA	0x2000
 #define VXLAN_F_GPE			0x4000
 #define VXLAN_F_IPV6_LINKLOCAL		0x8000
+#define VXLAN_F_TTL_INHERIT		0x10000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 11d0c0e..e771a63 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -516,6 +516,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
-- 
2.5.5