[PATCH net-next 0/3] set/match the tos/ttl fields of TC based IP tunnels

[PATCH net-next 0/3] set/match the tos/ttl fields of TC based IP tunnels

[Or Gerlitz]

Hi Dave, 

This series comes to address the case to set (encap) and match (decap)
also the tos and ttl fields of TC based IP tunnels.

Example encap (1st one) and decap (2nd) that use the new fields 

tc filter add dev eth0_0 protocol ip parent ffff: prio 10 flower \
	src_mac e4:11:22:33:44:50 dst_mac e4:11:22:33:44:70  \
	action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.10.2 id 100 dst_port 4789 tos 0x30 \
	action mirred egress redirect dev vxlan_sys_4789

tc filter add dev vxlan_sys_4789 protocol ip parent ffff: prio 10 flower \
	enc_src_ip 192.168.10.2 enc_dst_ip 192.168.10.1 enc_key_id 100 enc_dst_port 4789 enc_tos 0x30 \
	src_mac e4:11:22:33:44:70 dst_mac e4:11:22:33:44:50 \
	action tunnel_key unset \
	action mirred egress redirect dev eth0_0

Or.

Or Gerlitz (3):
  net/sched: tunnel_key: Allow to set tos and ttl for tc based ip tunnels
  flow_dissector: Dissect tos and ttl from the tunnel info
  net/sched: cls_flower: Support matching on ip tos and ttl for tunnels

 include/net/flow_dissector.h              |  2 +-
 include/uapi/linux/pkt_cls.h              |  5 ++++
 include/uapi/linux/tc_act/tc_tunnel_key.h |  2 ++
 net/core/flow_dissector.c                 | 14 +++++++++-
 net/sched/act_tunnel_key.c                | 20 ++++++++++++--
 net/sched/cls_flower.c                    | 43 ++++++++++++++++++++-----------
 6 files changed, 67 insertions(+), 19 deletions(-)

-- 
2.5.5

[PATCH net-next 1/3] net/sched: tunnel_key: Allow to set tos and ttl for tc based ip tunnels

[Or Gerlitz]

Allow user-space to provide tos and ttl to be set for the tunnel headers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
 include/uapi/linux/tc_act/tc_tunnel_key.h |  2 ++
 net/sched/act_tunnel_key.c                | 20 ++++++++++++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index e284fec..be384d63 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -39,6 +39,8 @@ enum {
 	TCA_TUNNEL_KEY_ENC_OPTS,	/* Nested TCA_TUNNEL_KEY_ENC_OPTS_
 					 * attributes
 					 */
+	TCA_TUNNEL_KEY_ENC_TOS,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_TTL,		/* u8 */
 	__TCA_TUNNEL_KEY_MAX,
 };
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 3ec585d5..22f26e9 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -197,6 +197,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
 	[TCA_TUNNEL_KEY_NO_CSUM]      = { .type = NLA_U8 },
 	[TCA_TUNNEL_KEY_ENC_OPTS]     = { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_TOS]      = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_TTL]      = { .type = NLA_U8 },
 };
 
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -216,6 +218,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	int opts_len = 0;
 	__be64 key_id;
 	__be16 flags;
+	u8 tos, ttl;
 	int ret = 0;
 	int err;
 
@@ -273,6 +276,13 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			}
 		}
 
+		tos = 0;
+		if (tb[TCA_TUNNEL_KEY_ENC_TOS])
+			tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]);
+		ttl = 0;
+		if (tb[TCA_TUNNEL_KEY_ENC_TTL])
+			ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]);
+
 		if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
 		    tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
 			__be32 saddr;
@@ -281,7 +291,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]);
 			daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
 
-			metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
+			metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl,
 						    dst_port, flags,
 						    key_id, opts_len);
 		} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
@@ -292,7 +302,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
 			daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
 
-			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port,
+			metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port,
 						      0, flags,
 						      key_id, 0);
 		} else {
@@ -504,6 +514,12 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 			       !(key->tun_flags & TUNNEL_CSUM)) ||
 		    tunnel_key_opts_dump(skb, info))
 			goto nla_put_failure;
+
+		if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos))
+			goto nla_put_failure;
+
+		if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl))
+			goto nla_put_failure;
 	}
 
 	tcf_tm_dump(&tm, &t->tcf_tm);
-- 
2.5.5

[PATCH net-next 2/3] flow_dissector: Dissect tos and ttl from the tunnel info

[Or Gerlitz]

Add dissection of the tos and ttl from the ip tunnel headers
fields in case a match is needed on them.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
 include/net/flow_dissector.h |  2 +-
 net/core/flow_dissector.c    | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index c644067..2a17f04 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -207,7 +207,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */
 	FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
-
+	FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_MAX,
 };
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b555fc2..08a5184 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -152,7 +152,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 	    !dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
 	    !dissector_uses_key(flow_dissector,
-				FLOW_DISSECTOR_KEY_ENC_PORTS))
+				FLOW_DISSECTOR_KEY_ENC_PORTS) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_IP))
 		return;
 
 	info = skb_tunnel_info(skb);
@@ -212,6 +214,16 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 		tp->src = key->tp_src;
 		tp->dst = key->tp_dst;
 	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_dissector_key_ip *ip;
+
+		ip = skb_flow_dissector_target(flow_dissector,
+					       FLOW_DISSECTOR_KEY_ENC_IP,
+					       target_container);
+		ip->tos = key->tos;
+		ip->ttl = key->ttl;
+	}
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
-- 
2.5.5

[PATCH net-next 3/3] net/sched: cls_flower: Support matching on ip tos and ttl for tunnels

[Or Gerlitz]

Allow users to set rules matching on ipv4 tos and ttl or
ipv6 traffic-class and hoplimit of tunnel headers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
 include/uapi/linux/pkt_cls.h |  5 +++++
 net/sched/cls_flower.c       | 43 ++++++++++++++++++++++++++++---------------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index c4262d9..b451225 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -473,6 +473,11 @@ enum {
 	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
 	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
 
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c53fdd4..38d7480 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -52,6 +52,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_mpls mpls;
 	struct flow_dissector_key_tcp tcp;
 	struct flow_dissector_key_ip ip;
+	struct flow_dissector_key_ip enc_ip;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -453,6 +454,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_CVLAN_ID]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_CVLAN_PRIO]	= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_CVLAN_ETH_TYPE]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_ENC_IP_TOS]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TTL]	 = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -561,17 +566,17 @@ static int fl_set_key_flags(struct nlattr **tb,
 	return 0;
 }
 
-static void fl_set_key_ip(struct nlattr **tb,
+static void fl_set_key_ip(struct nlattr **tb, bool encap,
 			  struct flow_dissector_key_ip *key,
 			  struct flow_dissector_key_ip *mask)
 {
-		fl_set_key_val(tb, &key->tos, TCA_FLOWER_KEY_IP_TOS,
-			       &mask->tos, TCA_FLOWER_KEY_IP_TOS_MASK,
-			       sizeof(key->tos));
+	int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS;
+	int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL;
+	int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK;
+	int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK;
 
-		fl_set_key_val(tb, &key->ttl, TCA_FLOWER_KEY_IP_TTL,
-			       &mask->ttl, TCA_FLOWER_KEY_IP_TTL_MASK,
-			       sizeof(key->ttl));
+	fl_set_key_val(tb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos));
+	fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl));
 }
 
 static int fl_set_key(struct net *net, struct nlattr **tb,
@@ -633,7 +638,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			       &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			       sizeof(key->basic.ip_proto));
-		fl_set_key_ip(tb, &key->ip, &mask->ip);
+		fl_set_key_ip(tb, false, &key->ip, &mask->ip);
 	}
 
 	if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
@@ -768,6 +773,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		       &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
 		       sizeof(key->enc_tp.dst));
 
+	fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
+
 	if (tb[TCA_FLOWER_KEY_FLAGS])
 		ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
 
@@ -860,6 +867,8 @@ static void fl_init_dissector(struct fl_flow_mask *mask)
 			   enc_control);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
+	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+			     FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
 
 	skb_flow_dissector_init(&mask->dissector, keys, cnt);
 }
@@ -1208,14 +1217,17 @@ static int fl_dump_key_mpls(struct sk_buff *skb,
 	return 0;
 }
 
-static int fl_dump_key_ip(struct sk_buff *skb,
+static int fl_dump_key_ip(struct sk_buff *skb, bool encap,
 			  struct flow_dissector_key_ip *key,
 			  struct flow_dissector_key_ip *mask)
 {
-	if (fl_dump_key_val(skb, &key->tos, TCA_FLOWER_KEY_IP_TOS, &mask->tos,
-			    TCA_FLOWER_KEY_IP_TOS_MASK, sizeof(key->tos)) ||
-	    fl_dump_key_val(skb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, &mask->ttl,
-			    TCA_FLOWER_KEY_IP_TTL_MASK, sizeof(key->ttl)))
+	int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS;
+	int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL;
+	int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK;
+	int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK;
+
+	if (fl_dump_key_val(skb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)) ||
+	    fl_dump_key_val(skb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl)))
 		return -1;
 
 	return 0;
@@ -1361,7 +1373,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	    (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			    &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			    sizeof(key->basic.ip_proto)) ||
-	    fl_dump_key_ip(skb, &key->ip, &mask->ip)))
+	    fl_dump_key_ip(skb, false, &key->ip, &mask->ip)))
 		goto nla_put_failure;
 
 	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
@@ -1486,7 +1498,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 			    TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
 			    &mask->enc_tp.dst,
 			    TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
-			    sizeof(key->enc_tp.dst)))
+			    sizeof(key->enc_tp.dst)) ||
+	    fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip))
 		goto nla_put_failure;
 
 	if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
-- 
2.5.5

Re: [PATCH net-next 0/3] set/match the tos/ttl fields of TC based IP tunnels

[David Miller]

From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 17 Jul 2018 19:27:15 +0300

> This series comes to address the case to set (encap) and match (decap)
> also the tos and ttl fields of TC based IP tunnels.
> 
> Example encap (1st one) and decap (2nd) that use the new fields 
> 
> tc filter add dev eth0_0 protocol ip parent ffff: prio 10 flower \
> 	src_mac e4:11:22:33:44:50 dst_mac e4:11:22:33:44:70  \
> 	action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.10.2 id 100 dst_port 4789 tos 0x30 \
> 	action mirred egress redirect dev vxlan_sys_4789
> 
> tc filter add dev vxlan_sys_4789 protocol ip parent ffff: prio 10 flower \
> 	enc_src_ip 192.168.10.2 enc_dst_ip 192.168.10.1 enc_key_id 100 enc_dst_port 4789 enc_tos 0x30 \
> 	src_mac e4:11:22:33:44:70 dst_mac e4:11:22:33:44:50 \
> 	action tunnel_key unset \
> 	action mirred egress redirect dev eth0_0

Series applied, thanks Or.