net/sched: Introduce action ct

Allow sending a packet to conntrack module for connection tracking.

The packet will be marked with conntrack connection's state, and
any metadata such as conntrack mark and label. This state metadata
can later be matched against with tc classifers, for example with the
flower classifier as below.

In addition to committing new connections the user can optionally
specific a zone to track within, set a mark/label and configure nat
with an address range and port range.

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

Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>

Changelog:
V5->V6:
	Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case
V4->V5:
	Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached()
V3->V4:
	Added strict_start_type for act_ct policy
V2->V3:
	Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c
V1->V2:
	Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max
	Refactored NAT_PORT_MIN_MAX range handling as well
	Added ipv4/ipv6 defragmentation
	Removed extra skb pull push of nw offset in exectute nat
	Refactored tcf_ct_skb_network_trim after pull
	Removed TCA_ACT_CT define

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 42 insertions, 0 deletions

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index e22ef4a940bc..31db5589b7ca 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -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
 };
diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h
new file mode 100644
index 000000000000..5fb1d7ac1027
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ct.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CT_H
+#define __UAPI_TC_CT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+	TCA_CT_UNSPEC,
+	TCA_CT_PARMS,
+	TCA_CT_TM,
+	TCA_CT_ACTION,		/* u16 */
+	TCA_CT_ZONE,		/* u16 */
+	TCA_CT_MARK,		/* u32 */
+	TCA_CT_MARK_MASK,	/* u32 */
+	TCA_CT_LABELS,		/* u128 */
+	TCA_CT_LABELS_MASK,	/* u128 */
+	TCA_CT_NAT_IPV4_MIN,	/* be32 */
+	TCA_CT_NAT_IPV4_MAX,	/* be32 */
+	TCA_CT_NAT_IPV6_MIN,	/* struct in6_addr */
+	TCA_CT_NAT_IPV6_MAX,	/* struct in6_addr */
+	TCA_CT_NAT_PORT_MIN,	/* be16 */
+	TCA_CT_NAT_PORT_MAX,	/* be16 */
+	TCA_CT_PAD,
+	__TCA_CT_MAX
+};
+
+#define TCA_CT_MAX (__TCA_CT_MAX - 1)
+
+#define TCA_CT_ACT_COMMIT	(1 << 0)
+#define TCA_CT_ACT_FORCE	(1 << 1)
+#define TCA_CT_ACT_CLEAR	(1 << 2)
+#define TCA_CT_ACT_NAT		(1 << 3)
+#define TCA_CT_ACT_NAT_SRC	(1 << 4)
+#define TCA_CT_ACT_NAT_DST	(1 << 5)
+
+struct tc_ct {
+	tc_gen;
+};
+
+#endif /* __UAPI_TC_CT_H */