vxlan: add ttl inherit support

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 with ip cmd.

Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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;

include/net/ip_tunnels.h

@@ -379,6 +379,17 @@ 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;
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return ((const struct ipv6hdr *)iph)->hop_limit;
+	else
+		return 0;
+}
+
 /* Propogate ECN bits out */
 static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 				     const struct sk_buff *skb)

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

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)