introduce IFE action

This action allows for a sending side to encapsulate arbitrary metadata
which is decapsulated by the receiving end.
The sender runs in encoding mode and the receiver in decode mode.
Both sender and receiver must specify the same ethertype.
At some point we hope to have a registered ethertype and we'll
then provide a default so the user doesnt have to specify it.
For now we enforce the user specify it.

Lets show example usage where we encode icmp from a sender towards
a receiver with an skbmark of 17; both sender and receiver use
ethertype of 0xdead to interop.

YYYY: Lets start with Receiver-side policy config:
xxx: add an ingress qdisc
sudo tc qdisc add dev $ETH ingress

xxx: any packets with ethertype 0xdead will be subjected to ife decoding
xxx: we then restart the classification so we can match on icmp at prio 3
sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xdead \
u32 match u32 0 0 flowid 1:1 \
action ife decode reclassify

xxx: on restarting the classification from above if it was an icmp
xxx: packet, then match it here and continue to the next rule at prio 4
xxx: which will match based on skb mark of 17
sudo tc filter add dev $ETH parent ffff: prio 3 protocol ip \
u32 match ip protocol 1 0xff flowid 1:1 \
action continue

xxx: match on skbmark of 0x11 (decimal 17) and accept
sudo tc filter add dev $ETH parent ffff: prio 4 protocol ip \
handle 0x11 fw flowid 1:1 \
action ok

xxx: Lets show the decoding policy
sudo tc -s filter ls dev $ETH parent ffff: protocol 0xdead
xxx:
filter pref 2 u32
filter pref 2 u32 fh 800: ht divisor 1
filter pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1  (rule hit 0 success 0)
  match 00000000/00000000 at 0 (success 0 )
        action order 1: ife decode action reclassify
         index 1 ref 1 bind 1 installed 14 sec used 14 sec
         type: 0x0
         Metadata: allow mark allow hash allow prio allow qmap
        Action statistics:
        Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
        backlog 0b 0p requeues 0
xxx:
Observe that above lists all metadatum it can decode. Typically these
submodules will already be compiled into a monolithic kernel or
loaded as modules

YYYY: Lets show the sender side now ..

xxx: Add an egress qdisc on the sender netdev
sudo tc qdisc add dev $ETH root handle 1: prio
xxx:
xxx: Match all icmp packets to 192.168.122.237/24, then
xxx: tag the packet with skb mark of decimal 17, then
xxx: Encode it with:
xxx:	ethertype 0xdead
xxx:	add skb->mark to whitelist of metadatum to send
xxx:	rewrite target dst MAC address to 02:15:15:15:15:15
xxx:
sudo $TC filter add dev $ETH parent 1: protocol ip prio 10  u32 \
match ip dst 192.168.122.237/24 \
match ip protocol 1 0xff \
flowid 1:2 \
action skbedit mark 17 \
action ife encode \
type 0xDEAD \
allow mark \
dst 02:15:15:15:15:15

xxx: Lets show the encoding policy
sudo tc -s filter ls dev $ETH parent 1: protocol ip
xxx:
filter pref 10 u32
filter pref 10 u32 fh 800: ht divisor 1
filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:2  (rule hit 0 success 0)
  match c0a87aed/ffffffff at 16 (success 0 )
  match 00010000/00ff0000 at 8 (success 0 )

	action order 1:  skbedit mark 17
	 index 6 ref 1 bind 1
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

	action order 2: ife encode action pipe
	 index 3 ref 1 bind 1
	 dst MAC: 02:15:15:15:15:15 type: 0xDEAD
 	 Metadata: allow mark
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0
xxx:

test by sending ping from sender to destination
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/tc_act/tc_ife.h

+#ifndef __NET_TC_IFE_H
+#define __NET_TC_IFE_H
+
+#include <net/act_api.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+
+#define IFE_METAHDRLEN 2
+struct tcf_ife_info {
+	struct tcf_common common;
+	u8 eth_dst[ETH_ALEN];
+	u8 eth_src[ETH_ALEN];
+	u16 eth_type;
+	u16 flags;
+	/* list of metaids allowed */
+	struct list_head metalist;
+};
+#define to_ife(a) \
+	container_of(a->priv, struct tcf_ife_info, common)
+
+struct tcf_meta_info {
+	const struct tcf_meta_ops *ops;
+	void *metaval;
+	u16 metaid;
+	struct list_head metalist;
+};
+
+struct tcf_meta_ops {
+	u16 metaid; /*Maintainer provided ID */
+	u16 metatype; /*netlink attribute type (look at net/netlink.h) */
+	const char *name;
+	const char *synopsis;
+	struct list_head list;
+	int	(*check_presence)(struct sk_buff *, struct tcf_meta_info *);
+	int	(*encode)(struct sk_buff *, void *, struct tcf_meta_info *);
+	int	(*decode)(struct sk_buff *, void *, u16 len);
+	int	(*get)(struct sk_buff *skb, struct tcf_meta_info *mi);
+	int	(*alloc)(struct tcf_meta_info *, void *);
+	void	(*release)(struct tcf_meta_info *);
+	int	(*validate)(void *val, int len);
+	struct module	*owner;
+};
+
+#define MODULE_ALIAS_IFE_META(metan)   MODULE_ALIAS("ifemeta" __stringify_1(metan))
+
+int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
+int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
+int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
+			const void *dval);
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval);
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval);
+int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi);
+int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi);
+int ife_validate_meta_u32(void *val, int len);
+int ife_validate_meta_u16(void *val, int len);
+void ife_release_meta_gen(struct tcf_meta_info *mi);
+int register_ife_op(struct tcf_meta_ops *mops);
+int unregister_ife_op(struct tcf_meta_ops *mops);
+
+#endif /* __NET_TC_IFE_H */

include/uapi/linux/tc_act/tc_ife.h

+#ifndef __UAPI_TC_IFE_H
+#define __UAPI_TC_IFE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_IFE 25
+/* Flag bits for now just encoding/decoding; mutually exclusive */
+#define IFE_ENCODE 1
+#define IFE_DECODE 0
+
+struct tc_ife {
+	tc_gen;
+	__u16 flags;
+};
+
+/*XXX: We need to encode the total number of bytes consumed */
+enum {
+	TCA_IFE_UNSPEC,
+	TCA_IFE_PARMS,
+	TCA_IFE_TM,
+	TCA_IFE_DMAC,
+	TCA_IFE_SMAC,
+	TCA_IFE_TYPE,
+	TCA_IFE_METALST,
+	__TCA_IFE_MAX
+};
+#define TCA_IFE_MAX (__TCA_IFE_MAX - 1)
+
+#define IFE_META_SKBMARK 1
+#define IFE_META_HASHID 2
+#define	IFE_META_PRIO 3
+#define	IFE_META_QMAP 4
+/*Can be overridden at runtime by module option*/
+#define	__IFE_META_MAX 5
+#define IFE_META_MAX (__IFE_META_MAX - 1)
+
+#endif

net/sched/Kconfig

@@ -739,6 +739,18 @@ config NET_ACT_CONNMARK
 	  To compile this code as a module, choose M here: the
 	  module will be called act_connmark.
 
+config NET_ACT_IFE
+        tristate "Inter-FE action based on IETF ForCES InterFE LFB"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to allow for sourcing and terminating metadata
+	  For details refer to netdev01 paper:
+	  "Distributing Linux Traffic Control Classifier-Action Subsystem"
+	   Authors: Jamal Hadi Salim and Damascene M. Joachimpillai
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_ife.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW

net/sched/Makefile

@@ -19,6 +19,7 @@ obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
 obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
 obj-$(CONFIG_NET_ACT_BPF)	+= act_bpf.o
 obj-$(CONFIG_NET_ACT_CONNMARK)	+= act_connmark.o
+obj-$(CONFIG_NET_ACT_IFE)	+= act_ife.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o