net/mlx5e: Rearrange tc tunnel code in a modular way

Rearrange tc tunnel code so that it would be easy to add future tunnels:
 - Define tc tunnel object with the fields and callbacks that any
   tunnel must implement.
 - Define tc UDP tunnel object for UDP tunnels, such as VXLAN
 - Move each tunnel code (GRE, VXLAN) to its own separate file
 - Rewrite tc tunnel implementation in a general way - using only
   the objects and their callbacks.
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -32,7 +32,7 @@ mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
-					lib/geneve.o
+					lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o
 
 #
 # Core extra

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h

@@ -14,9 +14,39 @@
 enum {
 	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
 	MLX5E_TC_TUNNEL_TYPE_VXLAN,
-	MLX5E_TC_TUNNEL_TYPE_GRETAP
+	MLX5E_TC_TUNNEL_TYPE_GRETAP,
 };
 
+struct mlx5e_tc_tunnel {
+	int tunnel_type;
+	enum mlx5_flow_match_level match_level;
+
+	bool (*can_offload)(struct mlx5e_priv *priv);
+	int (*calc_hlen)(struct mlx5e_encap_entry *e);
+	int (*init_encap_attr)(struct net_device *tunnel_dev,
+			       struct mlx5e_priv *priv,
+			       struct mlx5e_encap_entry *e,
+			       struct netlink_ext_ack *extack);
+	int (*generate_ip_tun_hdr)(char buf[],
+				   __u8 *ip_proto,
+				   struct mlx5e_encap_entry *e);
+	int (*parse_udp_ports)(struct mlx5e_priv *priv,
+			       struct mlx5_flow_spec *spec,
+			       struct tc_cls_flower_offload *f,
+			       void *headers_c,
+			       void *headers_v);
+	int (*parse_tunnel)(struct mlx5e_priv *priv,
+			    struct mlx5_flow_spec *spec,
+			    struct tc_cls_flower_offload *f,
+			    void *headers_c,
+			    void *headers_v);
+};
+
+extern struct mlx5e_tc_tunnel vxlan_tunnel;
+extern struct mlx5e_tc_tunnel gre_tunnel;
+
+struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev);
+
 int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 				 struct mlx5e_priv *priv,
 				 struct mlx5e_encap_entry *e,
@@ -30,7 +60,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e);
 
-int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev);
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev);
 
@@ -41,4 +70,10 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       void *headers_c,
 		       void *headers_v, u8 *match_level);
 
+int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
+				 struct mlx5_flow_spec *spec,
+				 struct tc_cls_flower_offload *f,
+				 void *headers_c,
+				 void *headers_v);
+
 #endif //__MLX5_EN_TC_TUNNEL_H__

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/gre.h>
+#include "en/tc_tun.h"
+
+static bool mlx5e_tc_tun_can_offload_gretap(struct mlx5e_priv *priv)
+{
+	return !!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap);
+}
+
+static int mlx5e_tc_tun_calc_hlen_gretap(struct mlx5e_encap_entry *e)
+{
+	return gre_calc_hlen(e->tun_info->key.tun_flags);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_gretap(struct net_device *tunnel_dev,
+					       struct mlx5e_priv *priv,
+					       struct mlx5e_encap_entry *e,
+					       struct netlink_ext_ack *extack)
+{
+	e->tunnel = &gre_tunnel;
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header_gretap(char buf[],
+					     __u8 *ip_proto,
+					     struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_key *tun_key  = &e->tun_info->key;
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	int hdr_len;
+
+	*ip_proto = IPPROTO_GRE;
+
+	/* the HW does not calculate GRE csum or sequences */
+	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
+		return -EOPNOTSUPP;
+
+	greh->protocol = htons(ETH_P_TEB);
+
+	/* GRE key */
+	hdr_len	= mlx5e_tc_tun_calc_hlen_gretap(e);
+	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
+	if (tun_key->tun_flags & TUNNEL_KEY) {
+		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
+		*ptr = tun_id;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
+				     struct mlx5_flow_spec *spec,
+				     struct tc_cls_flower_offload *f,
+				     void *headers_c,
+				     void *headers_v)
+{
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_GRE);
+
+	/* gre protocol */
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, gre_protocol);
+	MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB);
+
+	/* gre key */
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid enc_keyid;
+
+		flow_rule_match_enc_keyid(rule, &enc_keyid);
+		MLX5_SET(fte_match_set_misc, misc_c,
+			 gre_key.key, be32_to_cpu(enc_keyid.mask->keyid));
+		MLX5_SET(fte_match_set_misc, misc_v,
+			 gre_key.key, be32_to_cpu(enc_keyid.key->keyid));
+	}
+
+	return 0;
+}
+
+struct mlx5e_tc_tunnel gre_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_GRETAP,
+	.match_level          = MLX5_MATCH_L3,
+	.can_offload          = mlx5e_tc_tun_can_offload_gretap,
+	.calc_hlen            = mlx5e_tc_tun_calc_hlen_gretap,
+	.init_encap_attr      = mlx5e_tc_tun_init_encap_attr_gretap,
+	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_gretap,
+	.parse_udp_ports      = NULL,
+	.parse_tunnel         = mlx5e_tc_tun_parse_gretap,
+};

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/vxlan.h>
+#include "lib/vxlan.h"
+#include "en/tc_tun.h"
+
+static bool mlx5e_tc_tun_can_offload_vxlan(struct mlx5e_priv *priv)
+{
+	return !!MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap);
+}
+
+static int mlx5e_tc_tun_calc_hlen_vxlan(struct mlx5e_encap_entry *e)
+{
+	return VXLAN_HLEN;
+}
+
+static int mlx5e_tc_tun_check_udp_dport_vxlan(struct mlx5e_priv *priv,
+					      struct tc_cls_flower_offload *f)
+{
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_ports enc_ports;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS))
+		return -EOPNOTSUPP;
+
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	/* check the UDP destination port validity */
+
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan,
+				    be16_to_cpu(enc_ports.key->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP dst port is not registered as a VXLAN port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a VXLAN port\n",
+			    be16_to_cpu(enc_ports.key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_udp_ports_vxlan(struct mlx5e_priv *priv,
+					      struct mlx5_flow_spec *spec,
+					      struct tc_cls_flower_offload *f,
+					      void *headers_c,
+					      void *headers_v)
+{
+	int err = 0;
+
+	err = mlx5e_tc_tun_parse_udp_ports(priv, spec, f, headers_c, headers_v);
+	if (err)
+		return err;
+
+	return mlx5e_tc_tun_check_udp_dport_vxlan(priv, f);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_vxlan(struct net_device *tunnel_dev,
+					      struct mlx5e_priv *priv,
+					      struct mlx5e_encap_entry *e,
+					      struct netlink_ext_ack *extack)
+{
+	int dst_port = be16_to_cpu(e->tun_info->key.tp_dst);
+
+	e->tunnel = &vxlan_tunnel;
+
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "vxlan udp dport was not registered with the HW");
+		netdev_warn(priv->netdev,
+			    "%d isn't an offloaded vxlan udp dport\n",
+			    dst_port);
+		return -EOPNOTSUPP;
+	}
+
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
+					    __u8 *ip_proto,
+					    struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlanhdr *vxh;
+
+	vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
+	*ip_proto = IPPROTO_UDP;
+
+	udp->dest = tun_key->tp_dst;
+	vxh->vx_flags = VXLAN_HF_VNI;
+	vxh->vx_vni = vxlan_vni_field(tun_id);
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
+				    struct mlx5_flow_spec *spec,
+				    struct tc_cls_flower_offload *f,
+				    void *headers_c,
+				    void *headers_v)
+{
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_enc_keyid enc_keyid;
+	void *misc_c, *misc_v;
+
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
+		return 0;
+
+	flow_rule_match_enc_keyid(rule, &enc_keyid);
+
+	if (!enc_keyid.mask->keyid)
+		return 0;
+
+	/* match on VNI is required */
+
+	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+					ft_field_support.outer_vxlan_vni)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on VXLAN VNI is not supported");
+		netdev_warn(priv->netdev,
+			    "Matching on VXLAN VNI is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
+		 be32_to_cpu(enc_keyid.mask->keyid));
+	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
+		 be32_to_cpu(enc_keyid.key->keyid));
+
+	return 0;
+}
+
+struct mlx5e_tc_tunnel vxlan_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_VXLAN,
+	.match_level          = MLX5_MATCH_L4,
+	.can_offload          = mlx5e_tc_tun_can_offload_vxlan,
+	.calc_hlen            = mlx5e_tc_tun_calc_hlen_vxlan,
+	.init_encap_attr      = mlx5e_tc_tun_init_encap_attr_vxlan,
+	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_vxlan,
+	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_vxlan,
+	.parse_tunnel         = mlx5e_tc_tun_parse_vxlan,
+};

drivers/net/ethernet/mellanox/mlx5/core/en_rep.h

@@ -155,8 +155,7 @@ struct mlx5e_encap_entry {
 
 	struct net_device *out_dev;
 	struct net_device *route_dev;
-	int tunnel_type;
-	int tunnel_hlen;
+	struct mlx5e_tc_tunnel *tunnel;
 	int reformat_type;
 	u8 flags;
 	char *encap_header;

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -2569,20 +2569,20 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 
 struct encap_key {
 	const struct ip_tunnel_key *ip_tun_key;
-	int tunnel_type;
+	struct mlx5e_tc_tunnel *tc_tunnel;
 };
 
 static inline int cmp_encap_info(struct encap_key *a,
 				 struct encap_key *b)
 {
 	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
-	       a->tunnel_type != b->tunnel_type;
+	       a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type;
 }
 
 static inline int hash_encap_info(struct encap_key *key)
 {
 	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
-		     key->tunnel_type);
+		     key->tc_tunnel->tunnel_type);
 }
 
 
@@ -2624,14 +2624,14 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	tun_info = parse_attr->tun_info[out_index];
 	family = ip_tunnel_info_af(tun_info);
 	key.ip_tun_key = &tun_info->key;
-	key.tunnel_type = mlx5e_tc_tun_get_type(mirred_dev);
+	key.tc_tunnel = mlx5e_get_tc_tun(mirred_dev);
 
 	hash_key = hash_encap_info(&key);
 
 	hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
 				   encap_hlist, hash_key) {
 		e_key.ip_tun_key = &e->tun_info->key;
-		e_key.tunnel_type = e->tunnel_type;
+		e_key.tc_tunnel = e->tunnel;
 		if (!cmp_encap_info(&e_key, &key)) {
 			found = true;
 			break;