Merge branch 'basic-mpls-support'

Eric W. Biederman says:

====================
Basic MPLS support take 2

On top of my two pending neighbour table prep patches here is the mpls
support refactored to use them, and edited to not drop routes when
an interface goes down.  Additionally the addition of RTA_LLGATEWAY
has been replaced with the addtion of RTA_VIA.  RTA_VIA being an
attribute that includes the address family as well as the address
of the next hop.

MPLS is at it's heart simple and I have endeavoured to maintain that
simplicity in my implemenation.

This is an implementation of a RFC3032 forwarding engine, and basic MPLS
egress logic.  Which should make linux sufficient to be a mpls
forwarding node or to be a LSA (Label Switched Router) as it says in all
of the MPLS documents.  The ingress support will follow but it deserves
it's own discussion so I am pushing it separately.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/mpls-sysctl.txt

+/proc/sys/net/mpls/* Variables:
+
+platform_labels - INTEGER
+	Number of entries in the platform label table.  It is not
+	possible to configure forwarding for label values equal to or
+	greater than the number of platform labels.
+
+	A dense utliziation of the entries in the platform label table
+	is possible and expected aas the platform labels are locally
+	allocated.
+
+	If the number of platform label table entries is set to 0 no
+	label will be recognized by the kernel and mpls forwarding
+	will be disabled.
+
+	Reducing this value will remove all label routing entries that
+	no longer fit in the table.
+
+	Possible values: 0 - 1048575
+	Default: 0

include/linux/socket.h

@@ -181,6 +181,7 @@ struct ucred {
 #define AF_WANPIPE	25	/* Wanpipe API Sockets */
 #define AF_LLC		26	/* Linux LLC			*/
 #define AF_IB		27	/* Native InfiniBand address	*/
+#define AF_MPLS		28	/* MPLS */
 #define AF_CAN		29	/* Controller Area Network      */
 #define AF_TIPC		30	/* TIPC sockets			*/
 #define AF_BLUETOOTH	31	/* Bluetooth sockets 		*/
@@ -226,6 +227,7 @@ struct ucred {
 #define PF_WANPIPE	AF_WANPIPE
 #define PF_LLC		AF_LLC
 #define PF_IB		AF_IB
+#define PF_MPLS		AF_MPLS
 #define PF_CAN		AF_CAN
 #define PF_TIPC		AF_TIPC
 #define PF_BLUETOOTH	AF_BLUETOOTH

include/net/net_namespace.h

@@ -26,6 +26,7 @@
 #endif
 #include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
+#include <net/netns/mpls.h>
 #include <linux/ns_common.h>
 
 struct user_namespace;
@@ -129,6 +130,9 @@ struct net {
 #endif
 #if IS_ENABLED(CONFIG_IP_VS)
 	struct netns_ipvs	*ipvs;
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+	struct netns_mpls	mpls;
 #endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;

include/net/netns/mpls.h

+/*
+ * mpls in net namespaces
+ */
+
+#ifndef __NETNS_MPLS_H__
+#define __NETNS_MPLS_H__
+
+struct mpls_route;
+struct ctl_table_header;
+
+struct netns_mpls {
+	size_t platform_labels;
+	struct mpls_route __rcu * __rcu *platform_label;
+	struct ctl_table_header *ctl;
+};
+
+#endif /* __NETNS_MPLS_H__ */

include/uapi/linux/rtnetlink.h

@@ -303,6 +303,8 @@ enum rtattr_type_t {
 	RTA_TABLE,
 	RTA_MARK,
 	RTA_MFC_STATS,
+	RTA_VIA,
+	RTA_NEWDST,
 	__RTA_MAX
 };
 
@@ -344,6 +346,12 @@ struct rtnexthop {
 #define RTNH_SPACE(len)	RTNH_ALIGN(RTNH_LENGTH(len))
 #define RTNH_DATA(rtnh)   ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0)))
 
+/* RTA_VIA */
+struct rtvia {
+	__kernel_sa_family_t	rtvia_family;
+	__u8			rtvia_addr[0];
+};
+
 /* RTM_CACHEINFO */
 
 struct rta_cacheinfo {
@@ -623,6 +631,8 @@ enum rtnetlink_groups {
 #define RTNLGRP_IPV6_NETCONF	RTNLGRP_IPV6_NETCONF
 	RTNLGRP_MDB,
 #define RTNLGRP_MDB		RTNLGRP_MDB
+	RTNLGRP_MPLS_ROUTE,
+#define RTNLGRP_MPLS_ROUTE	RTNLGRP_MPLS_ROUTE
 	__RTNLGRP_MAX
 };
 #define RTNLGRP_MAX	(__RTNLGRP_MAX - 1)

net/Makefile

@@ -69,7 +69,7 @@ obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
 obj-$(CONFIG_NFC)		+= nfc/
 obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
 obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/
-obj-$(CONFIG_NET_MPLS_GSO)	+= mpls/
+obj-$(CONFIG_MPLS)		+= mpls/
 obj-$(CONFIG_HSR)		+= hsr/
 ifneq ($(CONFIG_NET_SWITCHDEV),)
 obj-y				+= switchdev/

net/mpls/Kconfig

 #
 # MPLS configuration
 #
+
+menuconfig MPLS
+	tristate "MultiProtocol Label Switching"
+	default n
+	---help---
+	  MultiProtocol Label Switching routes packets through logical
+	  circuits.  Originally conceved as a way of routing packets at
+	  hardware speeds (before hardware was capable of routing ipv4 packets),
+	  MPLS remains as simple way of making tunnels.
+
+	  If you have not heard of MPLS you probably want to say N here.
+
+if MPLS
+
 config NET_MPLS_GSO
-	tristate "MPLS: GSO support"
+	bool "MPLS: GSO support"
 	help
 	 This is helper module to allow segmentation of non-MPLS GSO packets
 	 that have had MPLS stack entries pushed onto them and thus
 	 become MPLS GSO packets.
+
+config MPLS_ROUTING
+	bool "MPLS: routing support"
+	help
+	 Add support for forwarding of mpls packets.
+
+endif # MPLS

net/mpls/Makefile

@@ -2,3 +2,4 @@
 # Makefile for MPLS.
 #
 obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o
+obj-$(CONFIG_MPLS_ROUTING) += af_mpls.o

net/mpls/internal.h

+#ifndef MPLS_INTERNAL_H
+#define MPLS_INTERNAL_H
+
+#define LABEL_IPV4_EXPLICIT_NULL	0 /* RFC3032 */
+#define LABEL_ROUTER_ALERT_LABEL	1 /* RFC3032 */
+#define LABEL_IPV6_EXPLICIT_NULL	2 /* RFC3032 */
+#define LABEL_IMPLICIT_NULL		3 /* RFC3032 */
+#define LABEL_ENTROPY_INDICATOR		7 /* RFC6790 */
+#define LABEL_GAL			13 /* RFC5586 */
+#define LABEL_OAM_ALERT			14 /* RFC3429 */
+#define LABEL_EXTENSION			15 /* RFC7274 */
+
+
+struct mpls_shim_hdr {
+	__be32 label_stack_entry;
+};
+
+struct mpls_entry_decoded {
+	u32 label;
+	u8 ttl;
+	u8 tc;
+	u8 bos;
+};
+
+struct sk_buff;
+
+static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb)
+{
+	return (struct mpls_shim_hdr *)skb_network_header(skb);
+}
+
+static inline struct mpls_shim_hdr mpls_entry_encode(u32 label, unsigned ttl, unsigned tc, bool bos)
+{
+	struct mpls_shim_hdr result;
+	result.label_stack_entry =
+		cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) |
+			    (tc << MPLS_LS_TC_SHIFT) |
+			    (bos ? (1 << MPLS_LS_S_SHIFT) : 0) |
+			    (ttl << MPLS_LS_TTL_SHIFT));
+	return result;
+}
+
+static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *hdr)
+{
+	struct mpls_entry_decoded result;
+	unsigned entry = be32_to_cpu(hdr->label_stack_entry);
+
+	result.label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+	result.ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+	result.tc =  (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
+	result.bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
+
+	return result;
+}
+
+int nla_put_labels(struct sk_buff *skb, int attrtype,  u8 labels, const u32 label[]);
+int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]);
+
+#endif /* MPLS_INTERNAL_H */