MPLS: Add limited GSO support

In the case where a non-MPLS packet is received and an MPLS stack is
added it may well be the case that the original skb is GSO but the
NIC used for transmit does not support GSO of MPLS packets.

The aim of this code is to provide GSO in software for MPLS packets
whose skbs are GSO.

SKB Usage:

When an implementation adds an MPLS stack to a non-MPLS packet it should do
the following to skb metadata:

* Set skb->inner_protocol to the old non-MPLS ethertype of the packet.
  skb->inner_protocol is added by this patch.

* Set skb->protocol to the new MPLS ethertype of the packet.

* Set skb->network_header to correspond to the
  end of the L3 header, including the MPLS label stack.

I have posted a patch, "[PATCH v3.29] datapath: Add basic MPLS support to
kernel" which adds MPLS support to the kernel datapath of Open vSwtich.
That patch sets the above requirements in datapath/actions.c:push_mpls()
and was used to exercise this code.  The datapath patch is against the Open
vSwtich tree but it is intended that it be added to the Open vSwtich code
present in the mainline Linux kernel at some point.

Features:

I believe that the approach that I have taken is at least partially
consistent with the handling of other protocols.  Jesse, I understand that
you have some ideas here.  I am more than happy to change my implementation.

This patch adds dev->mpls_features which may be used by devices
to advertise features supported for MPLS packets.

A new NETIF_F_MPLS_GSO feature is added for devices which support
hardware MPLS GSO offload.  Currently no devices support this
and MPLS GSO always falls back to software.

Alternate Implementation:

One possible alternate implementation is to teach netif_skb_features()
and skb_network_protocol() about MPLS, in a similar way to their
understanding of VLANs. I believe this would avoid the need
for net/mpls/mpls_gso.c and in particular the calls to
__skb_push() and __skb_push() in mpls_gso_segment().

I have decided on the implementation in this patch as it should
not introduce any overhead in the case where mpls_gso is not compiled
into the kernel or inserted as a module.

MPLS GSO suggested by Jesse Gross.
Based in part on "v4 GRE: Add TCP segmentation offload for GRE"
by Pravin B Shelar.

Cc: Jesse Gross <jesse@nicira.com>
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdev_features.h

@@ -43,8 +43,9 @@ enum {
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
+	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_UDP_TUNNEL_BIT,
+		NETIF_F_GSO_MPLS_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CSUM_BIT,		/* SCTP checksum offload */
@@ -107,6 +108,7 @@ enum {
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
+#define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)

include/linux/netdevice.h

@@ -1088,6 +1088,8 @@ struct net_device {
 	 * need to set them appropriately.
 	 */
 	netdev_features_t	hw_enc_features;
+	/* mask of fetures inheritable by MPLS */
+	netdev_features_t	mpls_features;
 
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;

include/linux/skbuff.h

@@ -319,6 +319,8 @@ enum {
 	SKB_GSO_GRE = 1 << 6,
 
 	SKB_GSO_UDP_TUNNEL = 1 << 7,
+
+	SKB_GSO_MPLS = 1 << 8,
 };
 
 #if BITS_PER_LONG > 32
@@ -389,6 +391,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@dropcount: total number of sk_receive_queue overflows
  *	@vlan_proto: vlan encapsulation protocol
  *	@vlan_tci: vlan tag control information
+ *	@inner_protocol: Protocol (encapsulation)
  *	@inner_transport_header: Inner transport layer header (encapsulation)
  *	@inner_network_header: Network layer header (encapsulation)
  *	@inner_mac_header: Link layer header (encapsulation)
@@ -509,6 +512,7 @@ struct sk_buff {
 		__u32		reserved_tailroom;
 	};
 
+	__be16			inner_protocol;
 	__u16			inner_transport_header;
 	__u16			inner_network_header;
 	__u16			inner_mac_header;

net/Kconfig

@@ -218,6 +218,7 @@ source "net/batman-adv/Kconfig"
 source "net/openvswitch/Kconfig"
 source "net/vmw_vsock/Kconfig"
 source "net/netlink/Kconfig"
+source "net/mpls/Kconfig"
 
 config RPS
 	boolean

net/Makefile

@@ -70,3 +70,4 @@ 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/

net/core/dev.c

@@ -5277,6 +5277,10 @@ int register_netdevice(struct net_device *dev)
 	 */
 	dev->hw_enc_features |= NETIF_F_SG;
 
+	/* Make NETIF_F_SG inheritable to MPLS.
+	 */
+	dev->mpls_features |= NETIF_F_SG;
+
 	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
 	ret = notifier_to_errno(ret);
 	if (ret)

net/core/ethtool.c

@@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
+	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CSUM_BIT] =        "tx-checksum-sctp",

net/ipv4/af_inet.c

@@ -1295,6 +1295,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_GRE |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
 

net/ipv4/tcp.c

@@ -2917,6 +2917,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCP_ECN |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
+			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       0) ||
 			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))

net/ipv4/udp.c

@@ -2381,7 +2381,7 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
-				      SKB_GSO_GRE) ||
+				      SKB_GSO_GRE | SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 

net/ipv6/ip6_offload.c

@@ -98,6 +98,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
 		goto out;

net/ipv6/udp_offload.c

@@ -63,7 +63,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (unlikely(type & ~(SKB_GSO_UDP |
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
-				      SKB_GSO_GRE) ||
+				      SKB_GSO_GRE |
+				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 

net/mpls/Kconfig

@@ -0,0 +1,9 @@
+#
+# MPLS configuration
+#
+config NET_MPLS_GSO
+	tristate "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.

net/mpls/Makefile

@@ -0,0 +1,4 @@
+#
+# Makefile for MPLS.
+#
+obj-y += mpls_gso.o

net/mpls/mpls_gso.c

@@ -0,0 +1,108 @@
+/*
+ *	MPLS GSO Support
+ *
+ *	Authors: Simon Horman (horms@verge.net.au)
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Based on: GSO portions of net/ipv4/gre.c
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/netdev_features.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+
+static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
+				       netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	netdev_features_t mpls_features;
+	__be16 mpls_protocol;
+
+	if (unlikely(skb_shinfo(skb)->gso_type &
+				~(SKB_GSO_TCPV4 |
+				  SKB_GSO_TCPV6 |
+				  SKB_GSO_UDP |
+				  SKB_GSO_DODGY |
+				  SKB_GSO_TCP_ECN |
+				  SKB_GSO_GRE |
+				  SKB_GSO_MPLS)))
+		goto out;
+
+	/* Setup inner SKB. */
+	mpls_protocol = skb->protocol;
+	skb->protocol = skb->inner_protocol;
+
+	/* Push back the mac header that skb_mac_gso_segment() has pulled.
+	 * It will be re-pulled by the call to skb_mac_gso_segment() below
+	 */
+	__skb_push(skb, skb->mac_len);
+
+	/* Segment inner packet. */
+	mpls_features = skb->dev->mpls_features & netif_skb_features(skb);
+	segs = skb_mac_gso_segment(skb, mpls_features);
+
+
+	/* Restore outer protocol. */
+	skb->protocol = mpls_protocol;
+
+	/* Re-pull the mac header that the call to skb_mac_gso_segment()
+	 * above pulled.  It will be re-pushed after returning
+	 * skb_mac_gso_segment(), an indirect caller of this function.
+	 */
+	__skb_push(skb, skb->data - skb_mac_header(skb));
+
+out:
+	return segs;
+}
+
+static int mpls_gso_send_check(struct sk_buff *skb)
+{
+	return 0;
+}
+
+static struct packet_offload mpls_mc_offload = {
+	.type = cpu_to_be16(ETH_P_MPLS_MC),
+	.callbacks = {
+		.gso_send_check =	mpls_gso_send_check,
+		.gso_segment    =	mpls_gso_segment,
+	},
+};
+
+static struct packet_offload mpls_uc_offload = {
+	.type = cpu_to_be16(ETH_P_MPLS_UC),
+	.callbacks = {
+		.gso_send_check =	mpls_gso_send_check,
+		.gso_segment    =	mpls_gso_segment,
+	},
+};
+
+static int __init mpls_gso_init(void)
+{
+	pr_info("MPLS GSO support\n");
+
+	dev_add_offload(&mpls_uc_offload);
+	dev_add_offload(&mpls_mc_offload);
+
+	return 0;
+}
+
+static void __exit mpls_gso_exit(void)
+{
+	dev_remove_offload(&mpls_uc_offload);
+	dev_remove_offload(&mpls_mc_offload);
+}
+
+module_init(mpls_gso_init);
+module_exit(mpls_gso_exit);
+
+MODULE_DESCRIPTION("MPLS GSO support");
+MODULE_AUTHOR("Simon Horman (horms@verge.net.au)");
+MODULE_LICENSE("GPL");