Commit 216dcb05 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'net-sched-Introduce-tc-connection-tracking' 



Paul Blakey says:

====================
net/sched: Introduce tc connection tracking

This patch series add connection tracking capabilities in tc sw datapath.
It does so via a new tc action, called act_ct, and new tc flower classifier matching
on conntrack state, mark and label.

Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress

$ tc filter add dev ens1f0_0 ingress \
  prio 1 chain 0 proto ip \
  flower ip_proto tcp ct_state -trk \
  action ct zone 2 pipe \
  action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
  prio 1 chain 2 proto ip \
  flower ct_state +trk+new \
  action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
  action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
  prio 1 chain 2 proto ip \
  flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
  action ct nat pipe \
  action mirred egress redirect dev ens1f0_1

$ tc filter add dev ens1f0_1 ingress \
  prio 1 chain 0 proto ip \
  flower ip_proto tcp ct_state -trk \
  action ct zone 2 pipe \
  action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
  prio 1 chain 1 proto ip \
  flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
  action ct nat pipe \
  action mirred egress redirect dev ens1f0_0

The pattern used in the design here closely resembles OvS, as the plan is to also offload
OvS conntrack rules to tc. OvS datapath rules uses it's recirculation mechanism to send
specific packets to conntrack, and return with the new conntrack state (ct_state) on some other recirc_id
to be matched again (we use goto chain for this).

This results in the following OvS datapath rules:

recirc_id(0),in_port(ens1f0_0),ct_state(-trk),... actions:ct(zone=2),recirc(2)
recirc_id(2),in_port(ens1f0_0),ct_state(+new+trk),ct_mark(0xbb),... actions:ct(commit,zone=2,nat(src=5.5.5.7),mark=0xbb),ens1f0_1
recirc_id(2),in_port(ens1f0_0),ct_state(+est+trk),ct_mark(0xbb),... actions:ct(zone=2,nat),ens1f0_1

recirc_id(1),in_port(ens1f0_1),ct_state(-trk),... actions:ct(zone=2),recirc(1)
recirc_id(1),in_port(ens1f0_1),ct_state(+est+trk),... actions:ct(zone=2,nat),ens1f0_0

Changelog:
	See individual patches.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents f108c887 6e52fca3

include/linux/skbuff.h

+10 −0
Original line number Diff line number Diff line
@@ -1325,6 +1325,16 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, 
			   struct flow_dissector *flow_dissector,

			   void *target_container);



/* Gets a skb connection tracking info, ctinfo map should be a

 * a map of mapsize to translate enum ip_conntrack_info states

 * to user states.

 */

void

skb_flow_dissect_ct(const struct sk_buff *skb,

		    struct flow_dissector *flow_dissector,

		    void *target_container,

		    u16 *ctinfo_map,

		    size_t mapsize);

void

skb_flow_dissect_tunnel_info(const struct sk_buff *skb,

			     struct flow_dissector *flow_dissector,

include/net/flow_dissector.h

+15 −0
Original line number Diff line number Diff line
@@ -208,6 +208,20 @@ struct flow_dissector_key_meta { 
	int ingress_ifindex;

};



/**

 * struct flow_dissector_key_ct:

 * @ct_state: conntrack state after converting with map

 * @ct_mark: conttrack mark

 * @ct_zone: conntrack zone

 * @ct_labels: conntrack labels

 */

struct flow_dissector_key_ct {

	u16	ct_state;

	u16	ct_zone;

	u32	ct_mark;

	u32	ct_labels[4];

};



enum flow_dissector_key_id {

	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */

	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -234,6 +248,7 @@ enum flow_dissector_key_id { 
	FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */

	FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */

	FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */

	FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */



	FLOW_DISSECTOR_KEY_MAX,

};

include/net/flow_offload.h

+5 −0
Original line number Diff line number Diff line
@@ -129,6 +129,7 @@ enum flow_action_id { 
	FLOW_ACTION_QUEUE,

	FLOW_ACTION_SAMPLE,

	FLOW_ACTION_POLICE,

	FLOW_ACTION_CT,

};



/* This is mirroring enum pedit_header_type definition for easy mapping between
@@ -178,6 +179,10 @@ struct flow_action_entry { 
			s64			burst;

			u64			rate_bytes_ps;

		} police;

		struct {				/* FLOW_ACTION_CT */

			int action;

			u16 zone;

		} ct;

	};

};

include/net/tc_act/tc_ct.h

0 → 100644
+63 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0 */

#ifndef __NET_TC_CT_H

#define __NET_TC_CT_H



#include <net/act_api.h>

#include <uapi/linux/tc_act/tc_ct.h>



#if IS_ENABLED(CONFIG_NF_CONNTRACK)

#include <net/netfilter/nf_nat.h>

#include <net/netfilter/nf_conntrack_labels.h>



struct tcf_ct_params {

	struct nf_conn *tmpl;

	u16 zone;



	u32 mark;

	u32 mark_mask;



	u32 labels[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];

	u32 labels_mask[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];



	struct nf_nat_range2 range;

	bool ipv4_range;



	u16 ct_action;



	struct rcu_head rcu;

};



struct tcf_ct {

	struct tc_action common;

	struct tcf_ct_params __rcu *params;

};



#define to_ct(a) ((struct tcf_ct *)a)

#define to_ct_params(a) ((struct tcf_ct_params *) \

			 rtnl_dereference((to_ct(a)->params)))



static inline uint16_t tcf_ct_zone(const struct tc_action *a)

{

	return to_ct_params(a)->zone;

}



static inline int tcf_ct_action(const struct tc_action *a)

{

	return to_ct_params(a)->ct_action;

}



#else

static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }

static inline int tcf_ct_action(const struct tc_action *a) { return 0; }

#endif /* CONFIG_NF_CONNTRACK */



static inline bool is_tcf_ct(const struct tc_action *a)

{

#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK)

	if (a->ops && a->ops->id == TCA_ID_CT)

		return true;

#endif

	return false;

}



#endif /* __NET_TC_CT_H */

include/uapi/linux/pkt_cls.h

+17 −0
Original line number Diff line number Diff line
@@ -106,6 +106,7 @@ enum tca_id { 
	TCA_ID_SAMPLE = TCA_ACT_SAMPLE,

	TCA_ID_CTINFO,

	TCA_ID_MPLS,

	TCA_ID_CT,

	/* other actions go here */

	__TCA_ID_MAX = 255

};
@@ -536,11 +537,27 @@ enum { 
	TCA_FLOWER_KEY_PORT_DST_MIN,	/* be16 */

	TCA_FLOWER_KEY_PORT_DST_MAX,	/* be16 */



	TCA_FLOWER_KEY_CT_STATE,	/* u16 */

	TCA_FLOWER_KEY_CT_STATE_MASK,	/* u16 */

	TCA_FLOWER_KEY_CT_ZONE,		/* u16 */

	TCA_FLOWER_KEY_CT_ZONE_MASK,	/* u16 */

	TCA_FLOWER_KEY_CT_MARK,		/* u32 */

	TCA_FLOWER_KEY_CT_MARK_MASK,	/* u32 */

	TCA_FLOWER_KEY_CT_LABELS,	/* u128 */

	TCA_FLOWER_KEY_CT_LABELS_MASK,	/* u128 */



	__TCA_FLOWER_MAX,

};



#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)



enum {

	TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */

	TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */

	TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */

	TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */

};



enum {

	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,

	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested

CRA Git | Maintained and supported by SUSTech CRA and CCSE