[RFC PATCH 0/0] Introduce MPLS over GRE

[RFC PATCH 0/0] Introduce MPLS over GRE

[Amine Kherbouche]

This series introduces the MPLS over GRE encapsulation (RFC 4023).

Various applications of MPLS make use of label stacks with multiple
entries.  In some cases, it is possible to replace the top label of
the stack with an IP-based encapsulation, thereby, it is possible for
two LSRs that are adjacent on an LSP to be separated by an IP network,
even if that IP network does not provide MPLS.

An example of configuration:


         node1                LER1                       LER2                node2
        +-----+             +------+                   +------+             +-----+
        |     |             |      |                   |      |             |     |
        |     |             |      |p3  GRE tunnel   p4|      |             |     |
        |     |p1         p2|      +-------------------+      |p5         p6|     |
        |     +-------------+      +-------------------+      +------------+|     |
        |     |10.100.0.0/24|      |                   |      |10.200.0.0/24|     |
        |     |fd00:100::/64|      |  10.125.0.0/24    |      |fd00:200::/64|     |
        |     |             |      |  fd00:125::/64    |      |             |     |
        |     |             |      |                   |      |             |     |
        |     |             |      |                   |      |             |     |
        |     |             |      |                   |      |             |     |
        |     |             |      |                   |      |             |     |
        +-----+             +------+                   +------+             +-----+


		###	node1	###

ip link set p1 up
ip addr add 10.100.0.1/24 dev p1

		###	LER1	###

ip link set p2 up
ip addr add 10.100.0.2/24 dev p2

ip link set p3 up
ip addr add 10.125.0.1/24 dev p3

modprobe mpls_router
sysctl -w net.mpls.conf.p2.input=1
sysctl -w net.mpls.conf.p3.input=1
sysctl -w net.mpls.platform_labels=1000

ip link add gre1 type gre ttl 64 local 10.125.0.1 remote 10.125.0.2 dev p3
ip link set dev gre1 up

ip -M route add 111 as 222 dev gre1
ip -M route add 555 as 666 via inet 10.100.0.1 dev p2

		###	LER2	###

ip link set p5 up
ip addr add 10.200.0.2/24 dev p5

ip link set p4 up
ip addr add 10.125.0.2/24 dev p4

modprobe mpls_router
sysctl -w net.mpls.conf.p4.input=1
sysctl -w net.mpls.conf.p5.input=1
sysctl -w net.mpls.platform_labels=1000

ip link add gre1 type gre ttl 64 local 10.125.0.2 remote 10.125.0.1 dev p4
ip link set dev gre1 up

ip -M route add 444 as 555 dev gre1
ip -M route add 222 as 333 via inet 10.200.0.1 dev p5

		###	node2	###

ip link set p6 up
ip addr add 10.200.0.1/24 dev p6


Now using this scapy to forge and send packets from the port p1 of node1:

p = Ether(src='de:ed:01:0c:41:09', dst='de:ed:01:2f:3b:ba')
p /= MPLS(s=1, ttl=64, label=111)/Raw(load='\xde')
sendp(p, iface="p1", count=20, inter=0.1)

[PATCH 1/2] mpls: expose stack entry function

[Amine Kherbouche]

Exposing mpls_forward() function to be able to be called from elsewhere
such as MPLS over GRE in the next commit.

Signed-off-by: Amine Kherbouche <amine.kherbouche@6wind.com>
---
 include/linux/mpls.h | 3 +++
 net/mpls/af_mpls.c   | 5 +++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/mpls.h b/include/linux/mpls.h
index 384fb22..d5c7599 100644
--- a/include/linux/mpls.h
+++ b/include/linux/mpls.h
@@ -2,10 +2,13 @@
 #define _LINUX_MPLS_H
 
 #include <uapi/linux/mpls.h>
+#include <linux/netdevice.h>
 
 #define MPLS_TTL_MASK		(MPLS_LS_TTL_MASK >> MPLS_LS_TTL_SHIFT)
 #define MPLS_BOS_MASK		(MPLS_LS_S_MASK >> MPLS_LS_S_SHIFT)
 #define MPLS_TC_MASK		(MPLS_LS_TC_MASK >> MPLS_LS_TC_SHIFT)
 #define MPLS_LABEL_MASK		(MPLS_LS_LABEL_MASK >> MPLS_LS_LABEL_SHIFT)
 
+int mpls_forward(struct sk_buff *skb, struct net_device *dev,
+		 struct packet_type *pt, struct net_device *orig_dev);
 #endif  /* _LINUX_MPLS_H */
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c5b9ce4..36ea2ad 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -307,8 +307,8 @@ static bool mpls_egress(struct net *net, struct mpls_route *rt,
 	return success;
 }
 
-static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
-			struct packet_type *pt, struct net_device *orig_dev)
+int mpls_forward(struct sk_buff *skb, struct net_device *dev,
+		 struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct net *net = dev_net(dev);
 	struct mpls_shim_hdr *hdr;
@@ -442,6 +442,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	kfree_skb(skb);
 	return NET_RX_DROP;
 }
+EXPORT_SYMBOL(mpls_forward);
 
 static struct packet_type mpls_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_MPLS_UC),
-- 
2.1.4

[PATCH 2/2] ip_tunnel: add mpls over gre encapsulation

[Amine Kherbouche]

This commit introduces the MPLSoGRE support (RFC 4023), using ip tunnel
API.

Encap:
  - Add a new iptunnel type mpls.

Decap:
  - pull gre hdr and call mpls_forward().

Signed-off-by: Amine Kherbouche <amine.kherbouche@6wind.com>
---
 include/net/gre.h              |  3 +++
 include/uapi/linux/if_tunnel.h |  1 +
 net/ipv4/gre_demux.c           | 22 ++++++++++++++++++++++
 net/ipv4/ip_gre.c              |  9 +++++++++
 net/ipv6/ip6_gre.c             |  7 +++++++
 net/mpls/af_mpls.c             | 37 +++++++++++++++++++++++++++++++++++++
 6 files changed, 79 insertions(+)

diff --git a/include/net/gre.h b/include/net/gre.h
index d25d836..88a8343 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -35,6 +35,9 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 				       u8 name_assign_type);
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs);
+#if IS_ENABLED(CONFIG_MPLS)
+int mpls_gre_rcv(struct sk_buff *skb, int gre_hdr_len);
+#endif
 
 static inline int gre_calc_hlen(__be16 o_flags)
 {
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 2e52088..a2f48c0 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -84,6 +84,7 @@ enum tunnel_encap_types {
 	TUNNEL_ENCAP_NONE,
 	TUNNEL_ENCAP_FOU,
 	TUNNEL_ENCAP_GUE,
+	TUNNEL_ENCAP_MPLS,
 };
 
 #define TUNNEL_ENCAP_FLAG_CSUM		(1<<0)
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index b798862..a6a937e 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -23,6 +23,9 @@
 #include <linux/netdevice.h>
 #include <linux/if_tunnel.h>
 #include <linux/spinlock.h>
+#if IS_ENABLED(CONFIG_MPLS)
+#include <linux/mpls.h>
+#endif
 #include <net/protocol.h>
 #include <net/gre.h>
 
@@ -122,6 +125,25 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 }
 EXPORT_SYMBOL(gre_parse_header);
 
+#if IS_ENABLED(CONFIG_MPLS)
+int mpls_gre_rcv(struct sk_buff *skb, int gre_hdr_len)
+{
+	if (unlikely(!pskb_may_pull(skb, gre_hdr_len)))
+		goto drop;
+
+	/* Pop GRE hdr and reset the skb */
+	skb_pull(skb, gre_hdr_len);
+	skb_reset_network_header(skb);
+
+	mpls_forward(skb, skb->dev, NULL, NULL);
+
+	return 0;
+drop:
+	return NET_RX_DROP;
+}
+EXPORT_SYMBOL(mpls_gre_rcv);
+#endif
+
 static int gre_rcv(struct sk_buff *skb)
 {
 	const struct gre_protocol *proto;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 9cee986..dd4431c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -412,10 +412,19 @@ static int gre_rcv(struct sk_buff *skb)
 			return 0;
 	}
 
+#if IS_ENABLED(CONFIG_MPLS)
+	if (unlikely(tpi.proto == htons(ETH_P_MPLS_UC))) {
+		if (mpls_gre_rcv(skb, hdr_len))
+			goto drop;
+		return 0;
+	}
+#endif
+
 	if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
 		return 0;
 
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
 drop:
 	kfree_skb(skb);
 	return 0;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c82d41e..e52396d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -476,6 +476,13 @@ static int gre_rcv(struct sk_buff *skb)
 	if (hdr_len < 0)
 		goto drop;
 
+#if IS_ENABLED(CONFIG_MPLS)
+	if (unlikely(tpi.proto == htons(ETH_P_MPLS_UC))) {
+		if (mpls_gre_rcv(skb, hdr_len))
+			goto drop;
+		return 0;
+	}
+#endif
 	if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false))
 		goto drop;
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 36ea2ad..060ed07 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -16,6 +16,7 @@
 #include <net/arp.h>
 #include <net/ip_fib.h>
 #include <net/netevent.h>
+#include <net/ip_tunnels.h>
 #include <net/netns/generic.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -39,6 +40,40 @@ static int one = 1;
 static int label_limit = (1 << 20) - 1;
 static int ttl_max = 255;
 
+size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct mpls_shim_hdr);
+}
+
+int ipgre_mpls_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    u8 *protocol, struct flowi4 *fl4)
+{
+	return 0;
+}
+
+static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
+	.encap_hlen = ipgre_mpls_encap_hlen,
+	.build_header = ipgre_mpls_build_header,
+};
+
+int ipgre_tunnel_encap_add_mpls_ops(void)
+{
+	int ret;
+
+	ret = ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
+	if (ret < 0) {
+		pr_err("can't add mplsgre ops\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ipgre_tunnel_encap_del_mpls_ops(void)
+{
+	ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
+}
+
 static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
 		       struct nlmsghdr *nlh, struct net *net, u32 portid,
 		       unsigned int nlm_flags);
@@ -2486,6 +2521,7 @@ static int __init mpls_init(void)
 		      0);
 	rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
 		      mpls_netconf_dump_devconf, 0);
+	ipgre_tunnel_encap_add_mpls_ops();
 	err = 0;
 out:
 	return err;
@@ -2503,6 +2539,7 @@ static void __exit mpls_exit(void)
 	dev_remove_pack(&mpls_packet_type);
 	unregister_netdevice_notifier(&mpls_dev_notifier);
 	unregister_pernet_subsys(&mpls_net_ops);
+	ipgre_tunnel_encap_del_mpls_ops();
 }
 module_exit(mpls_exit);
 
-- 
2.1.4

Re: [PATCH 2/2] ip_tunnel: add mpls over gre encapsulation

[Francois Romieu]

Amine Kherbouche <amine.kherbouche@6wind.com> :
[...]
> diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
> index 36ea2ad..060ed07 100644
> --- a/net/mpls/af_mpls.c
> +++ b/net/mpls/af_mpls.c
[...]
> @@ -39,6 +40,40 @@ static int one = 1;
>  static int label_limit = (1 << 20) - 1;
>  static int ttl_max = 255;
>  
> +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
> +{
> +	return sizeof(struct mpls_shim_hdr);
> +}
> +
> +int ipgre_mpls_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> +			    u8 *protocol, struct flowi4 *fl4)
> +{
> +	return 0;
> +}
> +
> +static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
> +	.encap_hlen = ipgre_mpls_encap_hlen,
> +	.build_header = ipgre_mpls_build_header,
> +};

Nit: af_mpls.c uses tab before '=' in such places.

> +
> +int ipgre_tunnel_encap_add_mpls_ops(void)
> +{
> +	int ret;
> +
> +	ret = ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);

ip_tunnel_encap_add_ops is CONFIG_NET_IP_TUNNEL dependant.

Afaics CONFIG_MPLS does not enforce it.

[...]
> @@ -2486,6 +2521,7 @@ static int __init mpls_init(void)
>  		      0);
>  	rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
>  		      mpls_netconf_dump_devconf, 0);
> +	ipgre_tunnel_encap_add_mpls_ops();
>  	err = 0;
>  out:
>  	return err;

ipgre_tunnel_encap_add_mpls_ops status return code is not checked.

-- 
Ueimor

Re: [PATCH 2/2] ip_tunnel: add mpls over gre encapsulation

[Amine Kherbouche]

Hi Francois,

Thanks for the feedback, I'll make it for the next version.

On 21/09/2017 23:25, Francois Romieu wrote:
> Amine Kherbouche <amine.kherbouche@6wind.com> :
> [...]
>> diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
>> index 36ea2ad..060ed07 100644
>> --- a/net/mpls/af_mpls.c
>> +++ b/net/mpls/af_mpls.c
> [...]
>> @@ -39,6 +40,40 @@ static int one = 1;
>>   static int label_limit = (1 << 20) - 1;
>>   static int ttl_max = 255;
>>   
>> +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
>> +{
>> +	return sizeof(struct mpls_shim_hdr);
>> +}
>> +
>> +int ipgre_mpls_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
>> +			    u8 *protocol, struct flowi4 *fl4)
>> +{
>> +	return 0;
>> +}
>> +
>> +static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
>> +	.encap_hlen = ipgre_mpls_encap_hlen,
>> +	.build_header = ipgre_mpls_build_header,
>> +};
> Nit: af_mpls.c uses tab before '=' in such places.
>
>> +
>> +int ipgre_tunnel_encap_add_mpls_ops(void)
>> +{
>> +	int ret;
>> +
>> +	ret = ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
> ip_tunnel_encap_add_ops is CONFIG_NET_IP_TUNNEL dependant.
>
> Afaics CONFIG_MPLS does not enforce it.
>
> [...]
>> @@ -2486,6 +2521,7 @@ static int __init mpls_init(void)
>>   		      0);
>>   	rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
>>   		      mpls_netconf_dump_devconf, 0);
>> +	ipgre_tunnel_encap_add_mpls_ops();
>>   	err = 0;
>>   out:
>>   	return err;
> ipgre_tunnel_encap_add_mpls_ops status return code is not checked.
>

Re: [PATCH 2/2] ip_tunnel: add mpls over gre encapsulation

[Roopa Prabhu]

On Thu, Sep 21, 2017 at 2:25 AM, Amine Kherbouche
<amine.kherbouche@6wind.com> wrote:
> This commit introduces the MPLSoGRE support (RFC 4023), using ip tunnel
> API.
>
> Encap:
>   - Add a new iptunnel type mpls.
>
> Decap:
>   - pull gre hdr and call mpls_forward().
>
> Signed-off-by: Amine Kherbouche <amine.kherbouche@6wind.com>
> ---
>  include/net/gre.h              |  3 +++
>  include/uapi/linux/if_tunnel.h |  1 +
>  net/ipv4/gre_demux.c           | 22 ++++++++++++++++++++++
>  net/ipv4/ip_gre.c              |  9 +++++++++
>  net/ipv6/ip6_gre.c             |  7 +++++++
>  net/mpls/af_mpls.c             | 37 +++++++++++++++++++++++++++++++++++++
>  6 files changed, 79 insertions(+)
>
> diff --git a/include/net/gre.h b/include/net/gre.h
> index d25d836..88a8343 100644
> --- a/include/net/gre.h
> +++ b/include/net/gre.h
> @@ -35,6 +35,9 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
>                                        u8 name_assign_type);
>  int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
>                      bool *csum_err, __be16 proto, int nhs);
> +#if IS_ENABLED(CONFIG_MPLS)
> +int mpls_gre_rcv(struct sk_buff *skb, int gre_hdr_len);
> +#endif
>
>  static inline int gre_calc_hlen(__be16 o_flags)
>  {
> diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
> index 2e52088..a2f48c0 100644
> --- a/include/uapi/linux/if_tunnel.h
> +++ b/include/uapi/linux/if_tunnel.h
> @@ -84,6 +84,7 @@ enum tunnel_encap_types {
>         TUNNEL_ENCAP_NONE,
>         TUNNEL_ENCAP_FOU,
>         TUNNEL_ENCAP_GUE,
> +       TUNNEL_ENCAP_MPLS,
>  };
>
>  #define TUNNEL_ENCAP_FLAG_CSUM         (1<<0)
> diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
> index b798862..a6a937e 100644
> --- a/net/ipv4/gre_demux.c
> +++ b/net/ipv4/gre_demux.c
> @@ -23,6 +23,9 @@
>  #include <linux/netdevice.h>
>  #include <linux/if_tunnel.h>
>  #include <linux/spinlock.h>
> +#if IS_ENABLED(CONFIG_MPLS)
> +#include <linux/mpls.h>
> +#endif
>  #include <net/protocol.h>
>  #include <net/gre.h>
>
> @@ -122,6 +125,25 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
>  }
>  EXPORT_SYMBOL(gre_parse_header);
>
> +#if IS_ENABLED(CONFIG_MPLS)
> +int mpls_gre_rcv(struct sk_buff *skb, int gre_hdr_len)
> +{
> +       if (unlikely(!pskb_may_pull(skb, gre_hdr_len)))
> +               goto drop;
> +
> +       /* Pop GRE hdr and reset the skb */
> +       skb_pull(skb, gre_hdr_len);
> +       skb_reset_network_header(skb);
> +
> +       mpls_forward(skb, skb->dev, NULL, NULL);
> +
> +       return 0;
> +drop:
> +       return NET_RX_DROP;
> +}
> +EXPORT_SYMBOL(mpls_gre_rcv);
> +#endif
> +
>  static int gre_rcv(struct sk_buff *skb)
>  {
>         const struct gre_protocol *proto;
> diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
> index 9cee986..dd4431c 100644
> --- a/net/ipv4/ip_gre.c
> +++ b/net/ipv4/ip_gre.c
> @@ -412,10 +412,19 @@ static int gre_rcv(struct sk_buff *skb)
>                         return 0;
>         }
>
> +#if IS_ENABLED(CONFIG_MPLS)
> +       if (unlikely(tpi.proto == htons(ETH_P_MPLS_UC))) {
> +               if (mpls_gre_rcv(skb, hdr_len))
> +                       goto drop;
> +               return 0;
> +       }
> +#endif
> +
>         if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
>                 return 0;
>
>         icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
> +
>  drop:
>         kfree_skb(skb);
>         return 0;
> diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
> index c82d41e..e52396d 100644
> --- a/net/ipv6/ip6_gre.c
> +++ b/net/ipv6/ip6_gre.c
> @@ -476,6 +476,13 @@ static int gre_rcv(struct sk_buff *skb)
>         if (hdr_len < 0)
>                 goto drop;
>
> +#if IS_ENABLED(CONFIG_MPLS)
> +       if (unlikely(tpi.proto == htons(ETH_P_MPLS_UC))) {
> +               if (mpls_gre_rcv(skb, hdr_len))
> +                       goto drop;
> +               return 0;
> +       }
> +#endif
>         if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false))
>                 goto drop;
>
> diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
> index 36ea2ad..060ed07 100644
> --- a/net/mpls/af_mpls.c
> +++ b/net/mpls/af_mpls.c
> @@ -16,6 +16,7 @@
>  #include <net/arp.h>
>  #include <net/ip_fib.h>
>  #include <net/netevent.h>
> +#include <net/ip_tunnels.h>
>  #include <net/netns/generic.h>
>  #if IS_ENABLED(CONFIG_IPV6)
>  #include <net/ipv6.h>
> @@ -39,6 +40,40 @@ static int one = 1;
>  static int label_limit = (1 << 20) - 1;
>  static int ttl_max = 255;
>
> +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
> +{
> +       return sizeof(struct mpls_shim_hdr);
> +}
> +
> +int ipgre_mpls_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> +                           u8 *protocol, struct flowi4 *fl4)
> +{
> +       return 0;
> +}


any reason you are supporting only rx ?


> +
> +static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
> +       .encap_hlen = ipgre_mpls_encap_hlen,
> +       .build_header = ipgre_mpls_build_header,
> +};
> +
> +int ipgre_tunnel_encap_add_mpls_ops(void)
> +{
> +       int ret;
> +
> +       ret = ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
> +       if (ret < 0) {
> +               pr_err("can't add mplsgre ops\n");
> +               return ret;
> +       }
> +
> +       return 0;
> +}
> +
> +static void ipgre_tunnel_encap_del_mpls_ops(void)
> +{
> +       ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
> +}
> +
>  static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
>                        struct nlmsghdr *nlh, struct net *net, u32 portid,
>                        unsigned int nlm_flags);
> @@ -2486,6 +2521,7 @@ static int __init mpls_init(void)
>                       0);
>         rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf,
>                       mpls_netconf_dump_devconf, 0);
> +       ipgre_tunnel_encap_add_mpls_ops();
>         err = 0;
>  out:
>         return err;
> @@ -2503,6 +2539,7 @@ static void __exit mpls_exit(void)
>         dev_remove_pack(&mpls_packet_type);
>         unregister_netdevice_notifier(&mpls_dev_notifier);
>         unregister_pernet_subsys(&mpls_net_ops);
> +       ipgre_tunnel_encap_del_mpls_ops();
>  }
>  module_exit(mpls_exit);
>
> --
> 2.1.4
>

Re: [PATCH 2/2] ip_tunnel: add mpls over gre encapsulation

[Amine Kherbouche]

On 09/22/2017 12:35 AM, Roopa Prabhu wrote:
>> > diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
>> > index 36ea2ad..060ed07 100644
>> > --- a/net/mpls/af_mpls.c
>> > +++ b/net/mpls/af_mpls.c
>> > @@ -16,6 +16,7 @@
>> >  #include <net/arp.h>
>> >  #include <net/ip_fib.h>
>> >  #include <net/netevent.h>
>> > +#include <net/ip_tunnels.h>
>> >  #include <net/netns/generic.h>
>> >  #if IS_ENABLED(CONFIG_IPV6)
>> >  #include <net/ipv6.h>
>> > @@ -39,6 +40,40 @@ static int one = 1;
>> >  static int label_limit = (1 << 20) - 1;
>> >  static int ttl_max = 255;
>> >
>> > +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
>> > +{
>> > +       return sizeof(struct mpls_shim_hdr);
>> > +}
>> > +
>> > +int ipgre_mpls_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
>> > +                           u8 *protocol, struct flowi4 *fl4)
>> > +{
>> > +       return 0;
>> > +}
>
> any reason you are supporting only rx ?

Tx path doesn't need changes, all gre hdr fields remain the same except 
for the protocol type which is loaded from skb->protocol this last is 
set by the mpls stack before entering gre device.