[PATCH iproute2 V5 0/3] tc: Support for ip tunnel metadata set/unset/classify

[PATCH iproute2 V5 0/3] tc: Support for ip tunnel metadata set/unset/classify

[Amir Vadai]

Hi,

This short series adds support for matching and setting metadata for ip tunnel
shared device using the TC system, introduced in kernel 4.9 [1].

Applied and tested on top of commit b6c7fc61faab ("ss: print new tcp_info
fields: busy, rwnd-limited, sndbuf-limited times")


Example usage:

$ tc filter add dev vxlan0 protocol ip parent ffff: \
    flower \
      enc_src_ip 11.11.0.2 \
      enc_dst_ip 11.11.0.1 \
      enc_key_id 11 \
      dst_ip 11.11.11.1 \
    action mirred egress redirect dev vnet0

$ tc filter add dev net0 protocol ip parent ffff: \
    flower \
      ip_proto 1 \
      dst_ip 11.11.11.2 \
    action tunnel_key set \
      src_ip 11.11.0.1 \
      dst_ip 11.11.0.2 \
      id 11 \
    action mirred egress redirect dev vxlan0

[1] - d1ba24feb466 ("Merge branch 'act_tunnel_key'")

Thanks,
Amir

Changes from V4:
- Fix rebase conflicts for net-next

Changes from V3:
- Fix bad wording in the man page about the use of the 'unset' operation

Changes from V2:
- Use const where needed
- Don't lose return value
- Introduce rta_getattr_be16() and rta_getattr_be32()

Changes from V1:
- Updated Patch 2/2 ("tc/act_tunnel: Introduce ip tunnel action") commit log
	and the man page tc-tunnel_key to reflect the fact that 'unset' operation is
	no mandatory.
	And describe when it might be needed.
- Rename the 'release' operation to 'unset'

Amir Vadai (3):
  libnetlink: Introduce rta_getattr_be*()
  tc/cls_flower: Classify packet in ip tunnels
  tc/act_tunnel: Introduce ip tunnel action

Amir Vadai (3):
  libnetlink: Introduce rta_getattr_be*()
  tc/cls_flower: Classify packet in ip tunnels
  tc/act_tunnel: Introduce ip tunnel action

 bridge/fdb.c                         |   4 +-
 include/libnetlink.h                 |   9 ++
 include/linux/tc_act/tc_tunnel_key.h |  42 ++++++
 ip/iplink_geneve.c                   |   2 +-
 ip/iplink_vxlan.c                    |   2 +-
 man/man8/tc-flower.8                 |  17 ++-
 man/man8/tc-tunnel_key.8             | 112 +++++++++++++++
 tc/Makefile                          |   1 +
 tc/f_flower.c                        |  84 +++++++++++-
 tc/m_tunnel_key.c                    | 258 +++++++++++++++++++++++++++++++++++
 10 files changed, 522 insertions(+), 9 deletions(-)
 create mode 100644 include/linux/tc_act/tc_tunnel_key.h
 create mode 100644 man/man8/tc-tunnel_key.8
 create mode 100644 tc/m_tunnel_key.c

-- 
2.10.2

[PATCH iproute2 V5 1/3] libnetlink: Introduce rta_getattr_be*()

[Amir Vadai]

Add the utility functions rta_getattr_be16() and rta_getattr_be32(), and
change existing code to use it.

Signed-off-by: Amir Vadai <amir@vadai.me>
---
 bridge/fdb.c         | 4 ++--
 include/libnetlink.h | 9 +++++++++
 ip/iplink_geneve.c   | 2 +-
 ip/iplink_vxlan.c    | 2 +-
 tc/f_flower.c        | 2 +-
 5 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/bridge/fdb.c b/bridge/fdb.c
index 90f4b154c5dc..a91521776e99 100644
--- a/bridge/fdb.c
+++ b/bridge/fdb.c
@@ -168,10 +168,10 @@ int print_fdb(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 	if (tb[NDA_PORT]) {
 		if (jw_global)
 			jsonw_uint_field(jw_global, "port",
-					 ntohs(rta_getattr_u16(tb[NDA_PORT])));
+					 rta_getattr_be16(tb[NDA_PORT]));
 		else
 			fprintf(fp, "port %d ",
-				ntohs(rta_getattr_u16(tb[NDA_PORT])));
+				rta_getattr_be16(tb[NDA_PORT]));
 	}
 
 	if (tb[NDA_VNI]) {
diff --git a/include/libnetlink.h b/include/libnetlink.h
index 483509ca9635..751ebf186dd4 100644
--- a/include/libnetlink.h
+++ b/include/libnetlink.h
@@ -10,6 +10,7 @@
 #include <linux/if_addr.h>
 #include <linux/neighbour.h>
 #include <linux/netconf.h>
+#include <arpa/inet.h>
 
 struct rtnl_handle {
 	int			fd;
@@ -140,10 +141,18 @@ static inline __u16 rta_getattr_u16(const struct rtattr *rta)
 {
 	return *(__u16 *)RTA_DATA(rta);
 }
+static inline __be16 rta_getattr_be16(const struct rtattr *rta)
+{
+	return ntohs(rta_getattr_u16(rta));
+}
 static inline __u32 rta_getattr_u32(const struct rtattr *rta)
 {
 	return *(__u32 *)RTA_DATA(rta);
 }
+static inline __be32 rta_getattr_be32(const struct rtattr *rta)
+{
+	return ntohl(rta_getattr_u32(rta));
+}
 static inline __u64 rta_getattr_u64(const struct rtattr *rta)
 {
 	__u64 tmp;
diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
index 3bfba91c644c..1e6669d07d60 100644
--- a/ip/iplink_geneve.c
+++ b/ip/iplink_geneve.c
@@ -234,7 +234,7 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 
 	if (tb[IFLA_GENEVE_PORT])
 		fprintf(f, "dstport %u ",
-			ntohs(rta_getattr_u16(tb[IFLA_GENEVE_PORT])));
+			rta_getattr_be16(tb[IFLA_GENEVE_PORT]));
 
 	if (tb[IFLA_GENEVE_COLLECT_METADATA])
 		fputs("external ", f);
diff --git a/ip/iplink_vxlan.c b/ip/iplink_vxlan.c
index 93af979a1e97..6d02bb47b2f0 100644
--- a/ip/iplink_vxlan.c
+++ b/ip/iplink_vxlan.c
@@ -413,7 +413,7 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 
 	if (tb[IFLA_VXLAN_PORT])
 		fprintf(f, "dstport %u ",
-			ntohs(rta_getattr_u16(tb[IFLA_VXLAN_PORT])));
+			rta_getattr_be16(tb[IFLA_VXLAN_PORT]));
 
 	if (tb[IFLA_VXLAN_LEARNING] &&
 	    !rta_getattr_u8(tb[IFLA_VXLAN_LEARNING]))
diff --git a/tc/f_flower.c b/tc/f_flower.c
index 1555764b9996..e132974e0d1d 100644
--- a/tc/f_flower.c
+++ b/tc/f_flower.c
@@ -511,7 +511,7 @@ static void flower_print_ip_addr(FILE *f, char *name, __be16 eth_type,
 
 static void flower_print_port(FILE *f, char *name, struct rtattr *attr)
 {
-	fprintf(f, "\n  %s %d", name, ntohs(rta_getattr_u16(attr)));
+	fprintf(f, "\n  %s %d", name, rta_getattr_be16(attr));
 }
 
 static int flower_print_opt(struct filter_util *qu, FILE *f,
-- 
2.10.2

[PATCH iproute2 V5 2/3] tc/cls_flower: Classify packet in ip tunnels

[Amir Vadai]

Introduce classifying by metadata extracted by the tunnel device.
Outer header fields - source/dest ip and tunnel id, are extracted from
the metadata when classifying.

For example, the following will add a filter on the ingress Qdisc of shared
vxlan device named 'vxlan0'. To forward packets with outer src ip
11.11.0.2, dst ip 11.11.0.1 and tunnel id 11. The packets will be
forwarded to tap device 'vnet0':

$ tc filter add dev vxlan0 protocol ip parent ffff: \
    flower \
      enc_src_ip 11.11.0.2 \
      enc_dst_ip 11.11.0.1 \
      enc_key_id 11 \
      dst_ip 11.11.11.1 \
    action mirred egress redirect dev vnet0

Signed-off-by: Amir Vadai <amir@vadai.me>
---
 man/man8/tc-flower.8 | 17 ++++++++++-
 tc/f_flower.c        | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 95 insertions(+), 4 deletions(-)

diff --git a/man/man8/tc-flower.8 b/man/man8/tc-flower.8
index 16ef261797ab..dd3564917dcc 100644
--- a/man/man8/tc-flower.8
+++ b/man/man8/tc-flower.8
@@ -34,7 +34,11 @@ flower \- flow based traffic control filter
 .BR dst_ip " | " src_ip " } { "
 .IR ipv4_address " | " ipv6_address " } | { "
 .BR dst_port " | " src_port " } "
-.IR port_number " }"
+.IR port_number " } | "
+.B enc_key_id
+.IR KEY-ID " | {"
+.BR enc_dst_ip " | " enc_src_ip " } { "
+.IR ipv4_address " | " ipv6_address " } | "
 .SH DESCRIPTION
 The
 .B flower
@@ -112,6 +116,17 @@ which has to be specified in beforehand.
 Match on layer 4 protocol source or destination port number. Only available for
 .BR ip_proto " values " udp " and " tcp ,
 which has to be specified in beforehand.
+.TP
+.BI enc_key_id " NUMBER"
+.TQ
+.BI enc_dst_ip " ADDRESS"
+.TQ
+.BI enc_src_ip " ADDRESS"
+Match on IP tunnel metadata. Key id
+.I NUMBER
+is a 32 bit tunnel key id (e.g. VNI for VXLAN tunnel).
+.I ADDRESS
+must be a valid IPv4 or IPv6 address.
 .SH NOTES
 As stated above where applicable, matches of a certain layer implicitly depend
 on the matches of the next lower layer. Precisely, layer one and two matches (
diff --git a/tc/f_flower.c b/tc/f_flower.c
index e132974e0d1d..7e7f4c92a947 100644
--- a/tc/f_flower.c
+++ b/tc/f_flower.c
@@ -41,7 +41,10 @@ static void explain(void)
 		"                       dst_ip [ IPV4-ADDR | IPV6-ADDR ] |\n"
 		"                       src_ip [ IPV4-ADDR | IPV6-ADDR ] |\n"
 		"                       dst_port PORT-NUMBER |\n"
-		"                       src_port PORT-NUMBER }\n"
+		"                       src_port PORT-NUMBER |\n"
+		"                       enc_dst_ip [ IPV4-ADDR | IPV6-ADDR ] |\n"
+		"                       enc_src_ip [ IPV4-ADDR | IPV6-ADDR ] |\n"
+		"                       enc_key_id [ KEY-ID ] }\n"
 		"       FILTERID := X:Y:Z\n"
 		"       ACTION-SPEC := ... look at individual actions\n"
 		"\n"
@@ -125,8 +128,9 @@ static int flower_parse_ip_addr(char *str, __be16 eth_type,
 		family = AF_INET;
 	} else if (eth_type == htons(ETH_P_IPV6)) {
 		family = AF_INET6;
+	} else if (!eth_type) {
+		family = AF_UNSPEC;
 	} else {
-		fprintf(stderr, "Illegal \"eth_type\" for ip address\n");
 		return -1;
 	}
 
@@ -134,8 +138,10 @@ static int flower_parse_ip_addr(char *str, __be16 eth_type,
 	if (ret)
 		return -1;
 
-	if (addr.family != family)
+	if (family && (addr.family != family)) {
+		fprintf(stderr, "Illegal \"eth_type\" for ip address\n");
 		return -1;
+	}
 
 	addattr_l(n, MAX_MSG, addr.family == AF_INET ? addr4_type : addr6_type,
 		  addr.data, addr.bytelen);
@@ -197,6 +203,18 @@ static int flower_parse_port(char *str, __u8 ip_port, bool is_src,
 	return 0;
 }
 
+static int flower_parse_key_id(const char *str, int type, struct nlmsghdr *n)
+{
+	int ret;
+	__be32 key_id;
+
+	ret = get_be32(&key_id, str, 10);
+	if (!ret)
+		addattr32(n, MAX_MSG, type, key_id);
+
+	return ret;
+}
+
 static int flower_parse_opt(struct filter_util *qu, char *handle,
 			    int argc, char **argv, struct nlmsghdr *n)
 {
@@ -354,6 +372,38 @@ static int flower_parse_opt(struct filter_util *qu, char *handle,
 				fprintf(stderr, "Illegal \"src_port\"\n");
 				return -1;
 			}
+		} else if (matches(*argv, "enc_dst_ip") == 0) {
+			NEXT_ARG();
+			ret = flower_parse_ip_addr(*argv, 0,
+						   TCA_FLOWER_KEY_ENC_IPV4_DST,
+						   TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
+						   TCA_FLOWER_KEY_ENC_IPV6_DST,
+						   TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
+						   n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"enc_dst_ip\"\n");
+				return -1;
+			}
+		} else if (matches(*argv, "enc_src_ip") == 0) {
+			NEXT_ARG();
+			ret = flower_parse_ip_addr(*argv, 0,
+						   TCA_FLOWER_KEY_ENC_IPV4_SRC,
+						   TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+						   TCA_FLOWER_KEY_ENC_IPV6_SRC,
+						   TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+						   n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"enc_src_ip\"\n");
+				return -1;
+			}
+		} else if (matches(*argv, "enc_key_id") == 0) {
+			NEXT_ARG();
+			ret = flower_parse_key_id(*argv,
+						  TCA_FLOWER_KEY_ENC_KEY_ID, n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"enc_key_id\"\n");
+				return -1;
+			}
 		} else if (matches(*argv, "action") == 0) {
 			NEXT_ARG();
 			ret = parse_action(&argc, &argv, TCA_FLOWER_ACT, n);
@@ -514,6 +564,13 @@ static void flower_print_port(FILE *f, char *name, struct rtattr *attr)
 	fprintf(f, "\n  %s %d", name, rta_getattr_be16(attr));
 }
 
+static void flower_print_key_id(FILE *f, const char *name,
+				struct rtattr *attr)
+{
+	if (attr)
+		fprintf(f, "\n  %s %d", name, rta_getattr_be32(attr));
+}
+
 static int flower_print_opt(struct filter_util *qu, FILE *f,
 			    struct rtattr *opt, __u32 handle)
 {
@@ -579,6 +636,25 @@ static int flower_print_opt(struct filter_util *qu, FILE *f,
 	flower_print_port(f, "src_port",
 			  tb[flower_port_attr_type(ip_proto, true)]);
 
+	flower_print_ip_addr(f, "enc_dst_ip",
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] ?
+			     htons(ETH_P_IP) : htons(ETH_P_IPV6),
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_DST],
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_DST_MASK],
+			     tb[TCA_FLOWER_KEY_ENC_IPV6_DST],
+			     tb[TCA_FLOWER_KEY_ENC_IPV6_DST_MASK]);
+
+	flower_print_ip_addr(f, "enc_src_ip",
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] ?
+			     htons(ETH_P_IP) : htons(ETH_P_IPV6),
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_SRC],
+			     tb[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK],
+			     tb[TCA_FLOWER_KEY_ENC_IPV6_SRC],
+			     tb[TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK]);
+
+	flower_print_key_id(f, "enc_key_id",
+			    tb[TCA_FLOWER_KEY_ENC_KEY_ID]);
+
 	if (tb[TCA_FLOWER_FLAGS]) {
 		__u32 flags = rta_getattr_u32(tb[TCA_FLOWER_FLAGS]);
 
-- 
2.10.2

[PATCH iproute2 V5 3/3] tc/act_tunnel: Introduce ip tunnel action

[Amir Vadai]

This action could be used before redirecting packets to a shared tunnel
device, or when redirecting packets arriving from a such a device.

The 'unset' action is optional. It is used to explicitly unset the
metadata created by the tunnel device during decap. If not used, the
metadata will be released automatically by the kernel.
The 'set' operation, will set the metadata with the specified values for
the encap.

For example, the following flower filter will forward all ICMP packets
destined to 11.11.11.2 through the shared vxlan device 'vxlan0'. Before
redirecting, a metadata for the vxlan tunnel is created using the
tunnel_key action and it's arguments:

$ tc filter add dev net0 protocol ip parent ffff: \
    flower \
      ip_proto 1 \
      dst_ip 11.11.11.2 \
    action tunnel_key set \
      src_ip 11.11.0.1 \
      dst_ip 11.11.0.2 \
      id 11 \
    action mirred egress redirect dev vxlan0

Signed-off-by: Amir Vadai <amir@vadai.me>
---
 include/linux/tc_act/tc_tunnel_key.h |  42 ++++++
 man/man8/tc-tunnel_key.8             | 112 +++++++++++++++
 tc/Makefile                          |   1 +
 tc/m_tunnel_key.c                    | 258 +++++++++++++++++++++++++++++++++++
 4 files changed, 413 insertions(+)
 create mode 100644 include/linux/tc_act/tc_tunnel_key.h
 create mode 100644 man/man8/tc-tunnel_key.8
 create mode 100644 tc/m_tunnel_key.c

diff --git a/include/linux/tc_act/tc_tunnel_key.h b/include/linux/tc_act/tc_tunnel_key.h
new file mode 100644
index 000000000000..f9ddf5369a45
--- /dev/null
+++ b/include/linux/tc_act/tc_tunnel_key.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (c) 2016, Amir Vadai <amir@vadai.me>
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * 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.
+ */
+
+#ifndef __LINUX_TC_TUNNEL_KEY_H
+#define __LINUX_TC_TUNNEL_KEY_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_TUNNEL_KEY 17
+
+#define TCA_TUNNEL_KEY_ACT_SET	    1
+#define TCA_TUNNEL_KEY_ACT_RELEASE  2
+
+struct tc_tunnel_key {
+	tc_gen;
+	int t_action;
+};
+
+enum {
+	TCA_TUNNEL_KEY_UNSPEC,
+	TCA_TUNNEL_KEY_TM,
+	TCA_TUNNEL_KEY_PARMS,
+	TCA_TUNNEL_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_TUNNEL_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_TUNNEL_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_TUNNEL_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_TUNNEL_KEY_ENC_KEY_ID,	/* be64 */
+	TCA_TUNNEL_KEY_PAD,
+	__TCA_TUNNEL_KEY_MAX,
+};
+
+#define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1)
+
+#endif
+
diff --git a/man/man8/tc-tunnel_key.8 b/man/man8/tc-tunnel_key.8
new file mode 100644
index 000000000000..17b15b9b34b9
--- /dev/null
+++ b/man/man8/tc-tunnel_key.8
@@ -0,0 +1,112 @@
+.TH "Tunnel metadata manipulation action in tc" 8 "10 Nov 2016" "iproute2" "Linux"
+
+.SH NAME
+tunnel_key - Tunnel metadata manipulation
+.SH SYNOPSIS
+.in +8
+.ti -8
+.BR tc " ... " "action tunnel_key" " { " unset " | "
+.IR SET " }"
+
+.ti -8
+.IR SET " := "
+.BR set " " src_ip
+.IR ADDRESS
+.BR dst_ip
+.IR ADDRESS
+.BI id " KEY_ID"
+
+.SH DESCRIPTION
+The
+.B tunnel_key
+action combined with a shared IP tunnel device, allows to perform IP tunnel en-
+or decapsulation on a packet, reflected by
+the operation modes
+.IR UNSET " and " SET .
+The
+.I UNSET
+mode is optional - even without using it, the metadata information will be
+released automatically when packet processing will be finished.
+.IR UNSET
+function could be used in cases when traffic is forwarded between two tunnels,
+where the metadata from the first tunnel will be used for encapsulation done by
+the second tunnel.
+.IR SET
+mode requires the source and destination ip
+.I ADDRESS
+and the tunnel key id
+.I KEY_ID
+which will be used by the ip tunnel shared device to create the tunnel header. The
+.B tunnel_key
+action is useful only in combination with a
+.B mirred redirect
+action to a shared IP tunnel device which will use the metadata (for
+.I SET
+) and unset the metadata created by it (for
+.I UNSET
+).
+
+.SH OPTIONS
+.TP
+.B unset
+Unset the tunnel metadata created by the IP tunnel device.  This function is
+not mandatory and might be used only in some specific use cases (as explained
+above).
+.TP
+.B set
+Set tunnel metadata to be used by the IP tunnel device. Requires
+.B id
+,
+.B src_ip
+and
+.B dst_ip
+options.
+.RS
+.TP
+.B id
+Tunnel ID (for example VNI in VXLAN tunnel)
+.TP
+.B src_ip
+Outer header source IP address (IPv4 or IPv6)
+.TP
+.B dst_ip
+Outer header destination IP address (IPv4 or IPv6)
+.RE
+.SH EXAMPLES
+The following example encapsulates incoming ICMP packets on eth0 into a vxlan
+tunnel, by setting metadata to VNI 11, source IP 11.11.0.1 and destination IP
+11.11.0.2, and by redirecting the packet with the metadata to device vxlan0,
+which will do the actual encapsulation using the metadata:
+
+.RS
+.EX
+#tc qdisc add dev eth0 handle ffff: ingress
+#tc filter add dev eth0 protocol ip parent ffff: \\
+  flower \\
+    ip_proto icmp \\
+  action tunnel_key set \\
+    src_ip 11.11.0.1 \\
+    dst_ip 11.11.0.2 \\
+    id 11 \\
+  action mirred egress redirect dev vxlan0
+.EE
+.RE
+
+Here is an example of the
+.B unset
+function: Incoming VXLAN traffic with outer IP's and VNI 11 is decapsulated by
+vxlan0 and metadata is unset before redirecting to tunl1 device:
+
+.RS
+.EX
+#tc qdisc add dev eth0 handle ffff: ingress
+#tc filter add dev vxlan0 protocol ip parent ffff: \
+  flower \\
+	  enc_src_ip 11.11.0.2 enc_dst_ip 11.11.0.1 enc_key_id 11 \
+	action tunnel_key unset \
+	action mirred egress redirect dev tunl1
+.EE
+.RE
+
+.SH SEE ALSO
+.BR tc (8)
diff --git a/tc/Makefile b/tc/Makefile
index f986fcb9e9fd..bb9011432ea1 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -50,6 +50,7 @@ TCMODULES += m_simple.o
 TCMODULES += m_vlan.o
 TCMODULES += m_connmark.o
 TCMODULES += m_bpf.o
+TCMODULES += m_tunnel_key.o
 TCMODULES += p_ip.o
 TCMODULES += p_icmp.o
 TCMODULES += p_tcp.o
diff --git a/tc/m_tunnel_key.c b/tc/m_tunnel_key.c
new file mode 100644
index 000000000000..f4a20e24e0bf
--- /dev/null
+++ b/tc/m_tunnel_key.c
@@ -0,0 +1,258 @@
+/*
+ * m_tunnel_key.c	ip tunnel manipulation module
+ *
+ *              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.
+ *
+ * Authors:     Amir Vadai <amir@vadai.me>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/if_ether.h>
+#include "utils.h"
+#include "rt_names.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_tunnel_key.h>
+
+static void explain(void)
+{
+	fprintf(stderr, "Usage: tunnel_key unset\n");
+	fprintf(stderr, "       tunnel_key set id TUNNELID src_ip IP dst_ip IP\n");
+}
+
+static void usage(void)
+{
+	explain();
+	exit(-1);
+}
+
+static int tunnel_key_parse_ip_addr(const char *str, int addr4_type,
+				    int addr6_type, struct nlmsghdr *n)
+{
+	inet_prefix addr;
+	int ret;
+
+	ret = get_addr(&addr, str, AF_UNSPEC);
+	if (ret)
+		return ret;
+
+	addattr_l(n, MAX_MSG, addr.family == AF_INET ? addr4_type : addr6_type,
+		  addr.data, addr.bytelen);
+
+	return 0;
+}
+
+static int tunnel_key_parse_key_id(const char *str, int type,
+				   struct nlmsghdr *n)
+{
+	__be32 key_id;
+	int ret;
+
+	ret = get_be32(&key_id, str, 10);
+	if (!ret)
+		addattr32(n, MAX_MSG, type, key_id);
+
+	return ret;
+}
+
+static int parse_tunnel_key(struct action_util *a, int *argc_p, char ***argv_p,
+			    int tca_id, struct nlmsghdr *n)
+{
+	struct tc_tunnel_key parm = { .action = TC_ACT_PIPE };
+	char **argv = *argv_p;
+	int argc = *argc_p;
+	struct rtattr *tail;
+	int action = 0;
+	int ret;
+	int has_src_ip = 0;
+	int has_dst_ip = 0;
+	int has_key_id = 0;
+
+	if (matches(*argv, "tunnel_key") != 0)
+		return -1;
+
+	tail = NLMSG_TAIL(n);
+	addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+
+	NEXT_ARG();
+
+	while (argc > 0) {
+		if (matches(*argv, "unset") == 0) {
+			if (action) {
+				fprintf(stderr, "unexpected \"%s\" - action already specified\n",
+					*argv);
+				explain();
+				return -1;
+			}
+			action = TCA_TUNNEL_KEY_ACT_RELEASE;
+		} else if (matches(*argv, "set") == 0) {
+			if (action) {
+				fprintf(stderr, "unexpected \"%s\" - action already specified\n",
+					*argv);
+				explain();
+				return -1;
+			}
+			action = TCA_TUNNEL_KEY_ACT_SET;
+		} else if (matches(*argv, "src_ip") == 0) {
+			NEXT_ARG();
+			ret = tunnel_key_parse_ip_addr(*argv,
+						       TCA_TUNNEL_KEY_ENC_IPV4_SRC,
+						       TCA_TUNNEL_KEY_ENC_IPV6_SRC,
+						       n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"src_ip\"\n");
+				return -1;
+			}
+			has_src_ip = 1;
+		} else if (matches(*argv, "dst_ip") == 0) {
+			NEXT_ARG();
+			ret = tunnel_key_parse_ip_addr(*argv,
+						       TCA_TUNNEL_KEY_ENC_IPV4_DST,
+						       TCA_TUNNEL_KEY_ENC_IPV6_DST,
+						       n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"dst_ip\"\n");
+				return -1;
+			}
+			has_dst_ip = 1;
+		} else if (matches(*argv, "id") == 0) {
+			NEXT_ARG();
+			ret = tunnel_key_parse_key_id(*argv, TCA_TUNNEL_KEY_ENC_KEY_ID, n);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"id\"\n");
+				return -1;
+			}
+			has_key_id = 1;
+		} else if (matches(*argv, "help") == 0) {
+			usage();
+		} else {
+			break;
+		}
+		NEXT_ARG_FWD();
+	}
+
+	if (argc && !action_a2n(*argv, &parm.action, false))
+		NEXT_ARG_FWD();
+
+	if (argc) {
+		if (matches(*argv, "index") == 0) {
+			NEXT_ARG();
+			if (get_u32(&parm.index, *argv, 10)) {
+				fprintf(stderr, "tunnel_key: Illegal \"index\"\n");
+				return -1;
+			}
+
+			NEXT_ARG_FWD();
+		}
+	}
+
+	if (action == TCA_TUNNEL_KEY_ACT_SET &&
+	    (!has_src_ip || !has_dst_ip || !has_key_id)) {
+		fprintf(stderr, "set needs tunnel_key parameters\n");
+		explain();
+		return -1;
+	}
+
+	parm.t_action = action;
+	addattr_l(n, MAX_MSG, TCA_TUNNEL_KEY_PARMS, &parm, sizeof(parm));
+	tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+	*argc_p = argc;
+	*argv_p = argv;
+
+	return 0;
+}
+
+static void tunnel_key_print_ip_addr(FILE *f, const char *name,
+				     struct rtattr *attr)
+{
+	int family;
+	size_t len;
+
+	if (!attr)
+		return;
+
+	len = RTA_PAYLOAD(attr);
+
+	if (len == 4)
+		family = AF_INET;
+	else if (len == 16)
+		family = AF_INET6;
+	else
+		return;
+
+	fprintf(f, "\n\t%s %s", name, rt_addr_n2a_rta(family, attr));
+}
+
+static void tunnel_key_print_key_id(FILE *f, const char *name,
+				    struct rtattr *attr)
+{
+	if (!attr)
+		return;
+	fprintf(f, "\n\t%s %d", name, rta_getattr_be32(attr));
+}
+
+static int print_tunnel_key(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+	struct rtattr *tb[TCA_TUNNEL_KEY_MAX + 1];
+	struct tc_tunnel_key *parm;
+
+	if (!arg)
+		return -1;
+
+	parse_rtattr_nested(tb, TCA_TUNNEL_KEY_MAX, arg);
+
+	if (!tb[TCA_TUNNEL_KEY_PARMS]) {
+		fprintf(f, "[NULL tunnel_key parameters]");
+		return -1;
+	}
+	parm = RTA_DATA(tb[TCA_TUNNEL_KEY_PARMS]);
+
+	fprintf(f, "tunnel_key");
+
+	switch (parm->t_action) {
+	case TCA_TUNNEL_KEY_ACT_RELEASE:
+		fprintf(f, " unset");
+		break;
+	case TCA_TUNNEL_KEY_ACT_SET:
+		fprintf(f, " set");
+		tunnel_key_print_ip_addr(f, "src_ip",
+					 tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]);
+		tunnel_key_print_ip_addr(f, "dst_ip",
+					 tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
+		tunnel_key_print_ip_addr(f, "src_ip",
+					 tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
+		tunnel_key_print_ip_addr(f, "dst_ip",
+					 tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
+		tunnel_key_print_key_id(f, "key_id",
+					tb[TCA_TUNNEL_KEY_ENC_KEY_ID]);
+		break;
+	}
+	fprintf(f, " %s", action_n2a(parm->action));
+
+	fprintf(f, "\n\tindex %d ref %d bind %d", parm->index, parm->refcnt,
+		parm->bindcnt);
+
+	if (show_stats) {
+		if (tb[TCA_TUNNEL_KEY_TM]) {
+			struct tcf_t *tm = RTA_DATA(tb[TCA_TUNNEL_KEY_TM]);
+
+			print_tm(f, tm);
+		}
+	}
+
+	fprintf(f, "\n ");
+
+	return 0;
+}
+
+struct action_util tunnel_key_action_util = {
+	.id = "tunnel_key",
+	.parse_aopt = parse_tunnel_key,
+	.print_aopt = print_tunnel_key,
+};
-- 
2.10.2

Re: [PATCH iproute2 V5 0/3] tc: Support for ip tunnel metadata set/unset/classify

[Stephen Hemminger]

On Fri,  2 Dec 2016 13:25:12 +0200
Amir Vadai <amir@vadai.me> wrote:

> Hi,
> 
> This short series adds support for matching and setting metadata for ip tunnel
> shared device using the TC system, introduced in kernel 4.9 [1].
> 
> Applied and tested on top of commit b6c7fc61faab ("ss: print new tcp_info
> fields: busy, rwnd-limited, sndbuf-limited times")
> 
> 
> Example usage:
> 
> $ tc filter add dev vxlan0 protocol ip parent ffff: \
>     flower \
>       enc_src_ip 11.11.0.2 \
>       enc_dst_ip 11.11.0.1 \
>       enc_key_id 11 \
>       dst_ip 11.11.11.1 \
>     action mirred egress redirect dev vnet0
> 
> $ tc filter add dev net0 protocol ip parent ffff: \
>     flower \
>       ip_proto 1 \
>       dst_ip 11.11.11.2 \
>     action tunnel_key set \
>       src_ip 11.11.0.1 \
>       dst_ip 11.11.0.2 \
>       id 11 \
>     action mirred egress redirect dev vxlan0
> 
> [1] - d1ba24feb466 ("Merge branch 'act_tunnel_key'")
> 
> Thanks,
> Amir
> 
> Changes from V4:
> - Fix rebase conflicts for net-next
> 
> Changes from V3:
> - Fix bad wording in the man page about the use of the 'unset' operation
> 
> Changes from V2:
> - Use const where needed
> - Don't lose return value
> - Introduce rta_getattr_be16() and rta_getattr_be32()
> 
> Changes from V1:
> - Updated Patch 2/2 ("tc/act_tunnel: Introduce ip tunnel action") commit log
> 	and the man page tc-tunnel_key to reflect the fact that 'unset' operation is
> 	no mandatory.
> 	And describe when it might be needed.
> - Rename the 'release' operation to 'unset'
> 
> Amir Vadai (3):
>   libnetlink: Introduce rta_getattr_be*()
>   tc/cls_flower: Classify packet in ip tunnels
>   tc/act_tunnel: Introduce ip tunnel action
> 
> Amir Vadai (3):
>   libnetlink: Introduce rta_getattr_be*()
>   tc/cls_flower: Classify packet in ip tunnels
>   tc/act_tunnel: Introduce ip tunnel action
> 
>  bridge/fdb.c                         |   4 +-
>  include/libnetlink.h                 |   9 ++
>  include/linux/tc_act/tc_tunnel_key.h |  42 ++++++
>  ip/iplink_geneve.c                   |   2 +-
>  ip/iplink_vxlan.c                    |   2 +-
>  man/man8/tc-flower.8                 |  17 ++-
>  man/man8/tc-tunnel_key.8             | 112 +++++++++++++++
>  tc/Makefile                          |   1 +
>  tc/f_flower.c                        |  84 +++++++++++-
>  tc/m_tunnel_key.c                    | 258 +++++++++++++++++++++++++++++++++++
>  10 files changed, 522 insertions(+), 9 deletions(-)
>  create mode 100644 include/linux/tc_act/tc_tunnel_key.h
>  create mode 100644 man/man8/tc-tunnel_key.8
>  create mode 100644 tc/m_tunnel_key.c
> 
 Series applied