[PATCHv2 net-next 0/4] net: sched: support vxlan and erspan options

[PATCHv2 net-next 0/4] net: sched: support vxlan and erspan options

[Xin Long]

This patchset is to add vxlan and erspan options support in
cls_flower and act_tunnel_key. The form is pretty much like
geneve_opts in:

  https://patchwork.ozlabs.org/patch/935272/
  https://patchwork.ozlabs.org/patch/954564/

but only one option is allowed for vxlan and erspan.

v1->v2:
  - see each patch changelog.

Xin Long (4):
  net: sched: add vxlan option support to act_tunnel_key
  net: sched: add erspan option support to act_tunnel_key
  net: sched: allow flower to match vxlan options
  net: sched: allow flower to match erspan options

 include/uapi/linux/pkt_cls.h              |  29 ++++
 include/uapi/linux/tc_act/tc_tunnel_key.h |  29 ++++
 net/sched/act_tunnel_key.c                | 203 +++++++++++++++++++++++-
 net/sched/cls_flower.c                    | 254 ++++++++++++++++++++++++++++++
 4 files changed, 514 insertions(+), 1 deletion(-)

-- 
2.1.0

[PATCHv2 net-next 1/4] net: sched: add vxlan option support to act_tunnel_key

[Xin Long]

This patch is to allow setting vxlan options using the
act_tunnel_key action. Different from geneve options,
only one option can be set. And also, geneve options
and vxlan options can't be set at the same time.

gbp is the only param for vxlan options:

  # ip link add name vxlan0 type vxlan dstport 0 external
  # tc qdisc add dev eth0 ingress
  # tc filter add dev eth0 protocol ip parent ffff: \
           flower indev eth0 \
              ip_proto udp \
              action tunnel_key \
                  set src_ip 10.0.99.192 \
                  dst_ip 10.0.99.193 \
                  dst_port 6081 \
                  id 11 \
  		  vxlan_opts 01020304 \
          action mirred egress redirect dev vxlan0

v1->v2:
  - add .strict_start_type for enc_opts_policy as Jakub noticed.
  - use Duplicate instead of Wrong in err msg for extack as Jakub
    suggested.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/uapi/linux/tc_act/tc_tunnel_key.h | 13 +++++
 net/sched/act_tunnel_key.c                | 85 ++++++++++++++++++++++++++++++-
 2 files changed, 97 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index 41c8b46..f302c2a 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -50,6 +50,10 @@ enum {
 						 * TCA_TUNNEL_KEY_ENC_OPTS_
 						 * attributes
 						 */
+	TCA_TUNNEL_KEY_ENC_OPTS_VXLAN,		/* Nested
+						 * TCA_TUNNEL_KEY_ENC_OPTS_
+						 * attributes
+						 */
 	__TCA_TUNNEL_KEY_ENC_OPTS_MAX,
 };
 
@@ -67,4 +71,13 @@ enum {
 #define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \
 	(__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1)
 
+enum {
+	TCA_TUNNEL_KEY_ENC_OPT_VXLAN_UNSPEC,
+	TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP,		/* u32 */
+	__TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX \
+	(__TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX - 1)
+
 #endif
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index cb34e5d..ff0909b 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -10,6 +10,7 @@
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -53,7 +54,10 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 
 static const struct nla_policy
 enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC]	= {
+		.strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN },
 	[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE]	= { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_OPTS_VXLAN]		= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -64,6 +68,11 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 						       .len = 128 },
 };
 
+static const struct nla_policy
+vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]	   = { .type = NLA_U32 },
+};
+
 static int
 tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 			   struct netlink_ext_ack *extack)
@@ -116,10 +125,36 @@ tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 	return opt_len;
 }
 
+static int
+tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla,
+			       vxlan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+		return -EINVAL;
+	}
+
+	if (dst) {
+		struct vxlan_metadata *md = dst;
+
+		md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]);
+	}
+
+	return sizeof(struct vxlan_metadata);
+}
+
 static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 				int dst_len, struct netlink_ext_ack *extack)
 {
-	int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
+	int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0;
 	const struct nlattr *attr, *head = nla_data(nla);
 
 	err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
@@ -130,6 +165,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 	nla_for_each_attr(attr, head, len, rem) {
 		switch (nla_type(attr)) {
 		case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+			if (type && type != TUNNEL_GENEVE_OPT) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+				return -EINVAL;
+			}
 			opt_len = tunnel_key_copy_geneve_opt(attr, dst,
 							     dst_len, extack);
 			if (opt_len < 0)
@@ -139,6 +178,19 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 				dst_len -= opt_len;
 				dst += opt_len;
 			}
+			type = TUNNEL_GENEVE_OPT;
+			break;
+		case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+			if (type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+				return -EINVAL;
+			}
+			opt_len = tunnel_key_copy_vxlan_opt(attr, dst,
+							    dst_len, extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_VXLAN_OPT;
 			break;
 		}
 	}
@@ -175,6 +227,14 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
 #else
 		return -EAFNOSUPPORT;
 #endif
+	case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+#if IS_ENABLED(CONFIG_INET)
+		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+		return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+					    opts_len, extack);
+#else
+		return -EAFNOSUPPORT;
+#endif
 	default:
 		NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
 		return -EINVAL;
@@ -451,6 +511,25 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 	return 0;
 }
 
+static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
+				      const struct ip_tunnel_info *info)
+{
+	struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
+	struct nlattr *start;
+
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) {
+		nla_nest_cancel(skb, start);
+		return -EMSGSIZE;
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+}
+
 static int tunnel_key_opts_dump(struct sk_buff *skb,
 				const struct ip_tunnel_info *info)
 {
@@ -468,6 +547,10 @@ static int tunnel_key_opts_dump(struct sk_buff *skb,
 		err = tunnel_key_geneve_opts_dump(skb, info);
 		if (err)
 			goto err_out;
+	} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+		err = tunnel_key_vxlan_opts_dump(skb, info);
+		if (err)
+			goto err_out;
 	} else {
 err_out:
 		nla_nest_cancel(skb, start);
-- 
2.1.0

[PATCHv2 net-next 2/4] net: sched: add erspan option support to act_tunnel_key

[Xin Long]

This patch is to allow setting erspan options using the
act_tunnel_key action. Different from geneve options,
only one option can be set. And also, geneve options,
vxlan options or erspan options can't be set at the
same time.

Options are expressed as ver:index:dir:hwid, when ver
is set to 1, index will be applied while dir and hwid
will be ignored, and when ver is set to 2, dir and
hwid will be used while index will be ignored.

  # ip link add name erspan1 type erspan external
  # tc qdisc add dev eth0 ingress
  # tc filter add dev eth0 protocol ip parent ffff: \
           flower indev eth0 \
              ip_proto udp \
              action tunnel_key \
                  set src_ip 10.0.99.192 \
                  dst_ip 10.0.99.193 \
                  dst_port 6081 \
                  id 11 \
  		erspan_opts 1:2:0:0 \
          action mirred egress redirect dev erspan1

v1->v2:
  - do the validation when dst is not yet allocated as Jakub suggested.
  - use Duplicate instead of Wrong in err msg for extack.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/uapi/linux/tc_act/tc_tunnel_key.h |  16 ++++
 net/sched/act_tunnel_key.c                | 118 ++++++++++++++++++++++++++++++
 2 files changed, 134 insertions(+)

diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index f302c2a..3f10dc4 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -54,6 +54,10 @@ enum {
 						 * TCA_TUNNEL_KEY_ENC_OPTS_
 						 * attributes
 						 */
+	TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN,		/* Nested
+						 * TCA_TUNNEL_KEY_ENC_OPTS_
+						 * attributes
+						 */
 	__TCA_TUNNEL_KEY_ENC_OPTS_MAX,
 };
 
@@ -80,4 +84,16 @@ enum {
 #define TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX \
 	(__TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX - 1)
 
+enum {
+	TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_UNSPEC,
+	TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX,		/* be32 */
+	TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID,		/* u8 */
+	__TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX \
+	(__TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX - 1)
+
 #endif
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index ff0909b..30b5825 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -11,6 +11,7 @@
 #include <linux/rtnetlink.h>
 #include <net/geneve.h>
 #include <net/vxlan.h>
+#include <net/erspan.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -58,6 +59,7 @@ enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
 		.strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN },
 	[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE]	= { .type = NLA_NESTED },
 	[TCA_TUNNEL_KEY_ENC_OPTS_VXLAN]		= { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -73,6 +75,14 @@ vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]	   = { .type = NLA_U32 },
 };
 
+static const struct nla_policy
+erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]	   = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]	   = { .type = NLA_U32 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]	   = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]	   = { .type = NLA_U8 },
+};
+
 static int
 tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 			   struct netlink_ext_ack *extack)
@@ -151,6 +161,59 @@ tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
 	return sizeof(struct vxlan_metadata);
 }
 
+static int
+tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len,
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1];
+	int err;
+	u8 ver;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla,
+			       erspan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+		return -EINVAL;
+	}
+
+	ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]);
+	if (ver == 1) {
+		if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+			return -EINVAL;
+		}
+	} else if (ver == 2) {
+		if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] ||
+		    !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+			return -EINVAL;
+		}
+	} else {
+		NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+		return -EINVAL;
+	}
+
+	if (dst) {
+		struct erspan_metadata *md = dst;
+
+		md->version = ver;
+		if (ver == 1) {
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX];
+			md->u.index = nla_get_be32(nla);
+		} else {
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR];
+			md->u.md2.dir = nla_get_u8(nla);
+			nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID];
+			set_hwid(&md->u.md2, nla_get_u8(nla));
+		}
+	}
+
+	return sizeof(struct erspan_metadata);
+}
+
 static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 				int dst_len, struct netlink_ext_ack *extack)
 {
@@ -192,6 +255,18 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 			opts_len += opt_len;
 			type = TUNNEL_VXLAN_OPT;
 			break;
+		case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+			if (type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+				return -EINVAL;
+			}
+			opt_len = tunnel_key_copy_erspan_opt(attr, dst,
+							     dst_len, extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			type = TUNNEL_ERSPAN_OPT;
+			break;
 		}
 	}
 
@@ -235,6 +310,14 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
 #else
 		return -EAFNOSUPPORT;
 #endif
+	case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+#if IS_ENABLED(CONFIG_INET)
+		info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+		return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+					    opts_len, extack);
+#else
+		return -EAFNOSUPPORT;
+#endif
 	default:
 		NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
 		return -EINVAL;
@@ -530,6 +613,37 @@ static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
 	return 0;
 }
 
+static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
+				       const struct ip_tunnel_info *info)
+{
+	struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
+	struct nlattr *start;
+
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version))
+		goto err;
+
+	if (md->version == 1 &&
+	    nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+		goto err;
+
+	if (md->version == 2 &&
+	    (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR,
+			md->u.md2.dir) ||
+	     nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID,
+			get_hwid(&md->u.md2))))
+		goto err;
+
+	nla_nest_end(skb, start);
+	return 0;
+err:
+	nla_nest_cancel(skb, start);
+	return -EMSGSIZE;
+}
+
 static int tunnel_key_opts_dump(struct sk_buff *skb,
 				const struct ip_tunnel_info *info)
 {
@@ -551,6 +665,10 @@ static int tunnel_key_opts_dump(struct sk_buff *skb,
 		err = tunnel_key_vxlan_opts_dump(skb, info);
 		if (err)
 			goto err_out;
+	} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+		err = tunnel_key_erspan_opts_dump(skb, info);
+		if (err)
+			goto err_out;
 	} else {
 err_out:
 		nla_nest_cancel(skb, start);
-- 
2.1.0

[PATCHv2 net-next 3/4] net: sched: allow flower to match vxlan options

[Xin Long]

This patch is to allow matching gbp option in vxlan.

The options can be described in the form GBP/GBP_MASK,
where GBP is represented as a 32bit hexadecimal value.
Different from geneve, only one option can be set. And
also, geneve options and vxlan options can't be set at
the same time.

  # ip link add name vxlan0 type vxlan dstport 0 external
  # tc qdisc add dev vxlan0 ingress
  # tc filter add dev vxlan0 protocol ip parent ffff: \
      flower \
        enc_src_ip 10.0.99.192 \
        enc_dst_ip 10.0.99.193 \
        enc_key_id 11 \
        vxlan_opts 01020304/ffffffff \
        ip_proto udp \
        action mirred egress redirect dev eth0

v1->v2:
  - add .strict_start_type for enc_opts_policy as Jakub noticed.
  - use Duplicate instead of Wrong in err msg for extack as Jakub
    suggested.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/uapi/linux/pkt_cls.h |  13 ++++++
 net/sched/cls_flower.c       | 109 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index c6ad22f..929825d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -571,6 +571,10 @@ enum {
 					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
 					 * attributes
 					 */
+	TCA_FLOWER_KEY_ENC_OPTS_VXLAN,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_VXLAN_
+					 * attributes
+					 */
 	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
 };
 
@@ -589,6 +593,15 @@ enum {
 		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
 
 enum {
+	TCA_FLOWER_KEY_ENC_OPT_VXLAN_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP,		/* u32 */
+	__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX - 1)
+
+enum {
 	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
 	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
 };
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 74221e3..abc7380 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -22,6 +22,7 @@
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -688,7 +689,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 
 static const struct nla_policy
 enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPTS_UNSPEC]        = {
+		.strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN },
 	[TCA_FLOWER_KEY_ENC_OPTS_GENEVE]        = { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_OPTS_VXLAN]         = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -699,6 +703,11 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 						       .len = 128 },
 };
 
+static const struct nla_policy
+vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]         = { .type = NLA_U32 },
+};
+
 static void fl_set_key_val(struct nlattr **tb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -928,6 +937,41 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
 	return sizeof(struct geneve_opt) + data_len;
 }
 
+static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+			    int depth, int option_len,
+			    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1];
+	struct vxlan_metadata *md;
+	int err;
+
+	md = (struct vxlan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+	memset(md, 0xff, sizeof(*md));
+
+	if (!depth)
+		return sizeof(*md);
+
+	if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_VXLAN) {
+		NL_SET_ERR_MSG(extack, "Non-vxlan option type for mask");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX, nla,
+			       vxlan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+		return -EINVAL;
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP])
+		md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]);
+
+	return sizeof(*md);
+}
+
 static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct fl_flow_key *mask,
 			  struct netlink_ext_ack *extack)
@@ -958,6 +1002,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) {
 		switch (nla_type(nla_opt_key)) {
 		case TCA_FLOWER_KEY_ENC_OPTS_GENEVE:
+			if (key->enc_opts.dst_opt_type &&
+			    key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+				return -EINVAL;
+			}
 			option_len = 0;
 			key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
 			option_len = fl_set_geneve_opt(nla_opt_key, key,
@@ -986,6 +1035,39 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			if (msk_depth)
 				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
+		case TCA_FLOWER_KEY_ENC_OPTS_VXLAN:
+			if (key->enc_opts.dst_opt_type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+				return -EINVAL;
+			}
+			option_len = 0;
+			key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+			option_len = fl_set_vxlan_opt(nla_opt_key, key,
+						      key_depth, option_len,
+						      extack);
+			if (option_len < 0)
+				return option_len;
+
+			key->enc_opts.len += option_len;
+			/* At the same time we need to parse through the mask
+			 * in order to verify exact and mask attribute lengths.
+			 */
+			mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT;
+			option_len = fl_set_vxlan_opt(nla_opt_msk, mask,
+						      msk_depth, option_len,
+						      extack);
+			if (option_len < 0)
+				return option_len;
+
+			mask->enc_opts.len += option_len;
+			if (key->enc_opts.len != mask->enc_opts.len) {
+				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+				return -EINVAL;
+			}
+
+			if (msk_depth)
+				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+			break;
 		default:
 			NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
 			return -EINVAL;
@@ -2135,6 +2217,28 @@ static int fl_dump_key_geneve_opt(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
+static int fl_dump_key_vxlan_opt(struct sk_buff *skb,
+				 struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct vxlan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_VXLAN);
+	if (!nest)
+		goto nla_put_failure;
+
+	md = (struct vxlan_metadata *)&enc_opts->data[0];
+	if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, md->gbp))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static int fl_dump_key_ct(struct sk_buff *skb,
 			  struct flow_dissector_key_ct *key,
 			  struct flow_dissector_key_ct *mask)
@@ -2188,6 +2292,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
 		if (err)
 			goto nla_put_failure;
 		break;
+	case TUNNEL_VXLAN_OPT:
+		err = fl_dump_key_vxlan_opt(skb, enc_opts);
+		if (err)
+			goto nla_put_failure;
+		break;
 	default:
 		goto nla_put_failure;
 	}
-- 
2.1.0

[PATCHv2 net-next 4/4] net: sched: allow flower to match erspan options

[Xin Long]

This patch is to allow matching options in erspan.

The options can be described in the form:
VER:INDEX:DIR:HWID/VER:INDEX_MASK:DIR_MASK:HWID_MASK.
When ver is set to 1, index will be applied while dir
and hwid will be ignored, and when ver is set to 2,
dir and hwid will be used while index will be ignored.

Different from geneve, only one option can be set. And
also, geneve options, vxlan options or erspan options
can't be set at the same time.

  # ip link add name erspan1 type erspan external
  # tc qdisc add dev erspan1 ingress
  # tc filter add dev erspan1 protocol ip parent ffff: \
      flower \
        enc_src_ip 10.0.99.192 \
        enc_dst_ip 10.0.99.193 \
        enc_key_id 11 \
        erspan_opts 1:12:0:0/1:ffff:0:0 \
        ip_proto udp \
        action mirred egress redirect dev eth0

v1->v2:
  - improve some err msgs of extack.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/uapi/linux/pkt_cls.h |  16 +++++
 net/sched/cls_flower.c       | 145 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 161 insertions(+)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 929825d..449a639 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -575,6 +575,10 @@ enum {
 					 * TCA_FLOWER_KEY_ENC_OPT_VXLAN_
 					 * attributes
 					 */
+	TCA_FLOWER_KEY_ENC_OPTS_ERSPAN,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_ERSPAN_
+					 * attributes
+					 */
 	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
 };
 
@@ -602,6 +606,18 @@ enum {
 		(__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX - 1)
 
 enum {
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER,              /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX,            /* be32 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR,              /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID,             /* u8 */
+	__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
+
+enum {
 	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
 	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
 };
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index abc7380..c307ee1 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -23,6 +23,7 @@
 #include <net/flow_dissector.h>
 #include <net/geneve.h>
 #include <net/vxlan.h>
+#include <net/erspan.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -693,6 +694,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
 		.strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN },
 	[TCA_FLOWER_KEY_ENC_OPTS_GENEVE]        = { .type = NLA_NESTED },
 	[TCA_FLOWER_KEY_ENC_OPTS_VXLAN]         = { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_OPTS_ERSPAN]        = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -708,6 +710,14 @@ vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]         = { .type = NLA_U32 },
 };
 
+static const struct nla_policy
+erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]        = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]      = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]        = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]       = { .type = NLA_U8 },
+};
+
 static void fl_set_key_val(struct nlattr **tb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -972,6 +982,70 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key,
 	return sizeof(*md);
 }
 
+static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
+			     int depth, int option_len,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1];
+	struct erspan_metadata *md;
+	int err;
+
+	md = (struct erspan_metadata *)&key->enc_opts.data[key->enc_opts.len];
+	memset(md, 0xff, sizeof(*md));
+	md->version = 1;
+
+	if (!depth)
+		return sizeof(*md);
+
+	if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_ERSPAN) {
+		NL_SET_ERR_MSG(extack, "Non-erspan option type for mask");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX, nla,
+			       erspan_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+		return -EINVAL;
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER])
+		md->version = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]);
+
+	if (md->version == 1) {
+		if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+			return -EINVAL;
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX];
+			md->u.index = nla_get_be32(nla);
+		}
+	} else if (md->version == 2) {
+		if (!option_len && (!tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] ||
+				    !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID])) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+			return -EINVAL;
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR];
+			md->u.md2.dir = nla_get_u8(nla);
+		}
+		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]) {
+			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID];
+			set_hwid(&md->u.md2, nla_get_u8(nla));
+		}
+	} else {
+		NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+		return -EINVAL;
+	}
+
+	return sizeof(*md);
+}
+
 static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct fl_flow_key *mask,
 			  struct netlink_ext_ack *extack)
@@ -1068,6 +1142,39 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			if (msk_depth)
 				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
+		case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN:
+			if (key->enc_opts.dst_opt_type) {
+				NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+				return -EINVAL;
+			}
+			option_len = 0;
+			key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+			option_len = fl_set_erspan_opt(nla_opt_key, key,
+						       key_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			key->enc_opts.len += option_len;
+			/* At the same time we need to parse through the mask
+			 * in order to verify exact and mask attribute lengths.
+			 */
+			mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT;
+			option_len = fl_set_erspan_opt(nla_opt_msk, mask,
+						       msk_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			mask->enc_opts.len += option_len;
+			if (key->enc_opts.len != mask->enc_opts.len) {
+				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+				return -EINVAL;
+			}
+
+			if (msk_depth)
+				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+			break;
 		default:
 			NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
 			return -EINVAL;
@@ -2239,6 +2346,39 @@ static int fl_dump_key_vxlan_opt(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
+static int fl_dump_key_erspan_opt(struct sk_buff *skb,
+				  struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct erspan_metadata *md;
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_ERSPAN);
+	if (!nest)
+		goto nla_put_failure;
+
+	md = (struct erspan_metadata *)&enc_opts->data[0];
+	if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, md->version))
+		goto nla_put_failure;
+
+	if (md->version == 1 &&
+	    nla_put_be32(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+		goto nla_put_failure;
+
+	if (md->version == 2 &&
+	    (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR,
+			md->u.md2.dir) ||
+	     nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID,
+			get_hwid(&md->u.md2))))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static int fl_dump_key_ct(struct sk_buff *skb,
 			  struct flow_dissector_key_ct *key,
 			  struct flow_dissector_key_ct *mask)
@@ -2297,6 +2437,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
 		if (err)
 			goto nla_put_failure;
 		break;
+	case TUNNEL_ERSPAN_OPT:
+		err = fl_dump_key_erspan_opt(skb, enc_opts);
+		if (err)
+			goto nla_put_failure;
+		break;
 	default:
 		goto nla_put_failure;
 	}
-- 
2.1.0

Re: [PATCHv2 net-next 0/4] net: sched: support vxlan and erspan options

[Jakub Kicinski]

On Thu, 21 Nov 2019 18:03:25 +0800, Xin Long wrote:
> This patchset is to add vxlan and erspan options support in
> cls_flower and act_tunnel_key. The form is pretty much like
> geneve_opts in:
> 
>   https://patchwork.ozlabs.org/patch/935272/
>   https://patchwork.ozlabs.org/patch/954564/
> 
> but only one option is allowed for vxlan and erspan.

I have only cursory understanding of the flower parts, but looks good
to me:

Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>

Re: [PATCHv2 net-next 0/4] net: sched: support vxlan and erspan options

[David Miller]

From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 21 Nov 2019 18:03:25 +0800

> This patchset is to add vxlan and erspan options support in
> cls_flower and act_tunnel_key. The form is pretty much like
> geneve_opts in:
> 
>   https://patchwork.ozlabs.org/patch/935272/
>   https://patchwork.ozlabs.org/patch/954564/
> 
> but only one option is allowed for vxlan and erspan.
> 
> v1->v2:
>   - see each patch changelog.

Series applied.