Merge tag 'mlx5-updates-2019-05-31' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-05-31

This series provides some updates to mlx5 core and netdevice driver.

1) use __netdev_tx_sent_queue() to improve performance under GSO workload

2) Allow matching only enc_key_id/enc_dst_port for decapsulation action

3) Geneve support:
This patchset adds support for GENEVE tunnel encap/decap flows offload:
encapsulating layer 2 Ethernet frames within layer 4 UDP datagrams.
The driver supports 6081 destination UDP port number, which is the
default IANA-assigned port.

Encap:
  ConnectX-5 inserts the header (w/ or w/o Geneve TLV options) that is
  provided by the mlx5 driver to the outgoing packet.

Decap:
  Geneve header is matched and the packet is decapsulated.
  Notes about decap flows with Geneve TLV Options:
   - Support offloading of 32-bit options data only
   - At any given time, only one combination of class/type parameters
     can be offloaded, but the same class/type combination can have
     many different flows offloaded with different 32-bit option data
   - Options with value of 0 can't be offloaded

Managing Geneve TLV options:
  Matching (on receive) is done by ConnectX-5 flex parser.
  Geneve TLV options are managed using General Object of type
  “Geneve TLV Options”.

  When the first flow with a certain class/type values is requested
  to be offloaded, the driver creates a FW object with FW command
  (Geneve TLV Options general object) and starts counting the number
  of flows using this object.

  During this time, any request with a different class/type values
  will fail to be offloaded.
  Once the refcount reaches 0, the driver destroys the TLV options
  general object, and can now offload a flow with any class/type parameters.

  Geneve TLV Options object is added to core device.
  It is currently used to manage Geneve TLV options general
  object allocation in FW and its reference counting only.

  In the future it will also be used for managing geneve ports
  by registering callbacks for ndo_udp_tunnel_add/del.

TC tunnel code refactoring:
  As a preparation for Geneve code, the TC tunnel code in mlx5
  was rearranged in a modular way, so that it would be easier
  to add future tunnels:
   - Defined 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.

4) Termination tables:
Actions in tables set with the termination flag are guaranteed to terminate
the action list. Thus, potential looping functionality (e.g. haripin) can safely be
executed without potential loops.
====================

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

26 files changed, 1430 insertions, 388 deletions

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 269b24a3baa1..aa9acebfcc23 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -60,7 +60,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	if (!__mlx5_ib_add(ibdev, profile))
 		return -EINVAL;
 
-	rep->rep_if[REP_IB].priv = ibdev;
+	rep->rep_data[REP_IB].priv = ibdev;
 
 	return 0;
 }
@@ -70,13 +70,13 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 {
 	struct mlx5_ib_dev *dev;
 
-	if (!rep->rep_if[REP_IB].priv ||
+	if (!rep->rep_data[REP_IB].priv ||
 	    rep->vport != MLX5_VPORT_UPLINK)
 		return;
 
 	dev = mlx5_ib_rep_to_dev(rep);
 	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
-	rep->rep_if[REP_IB].priv = NULL;
+	rep->rep_data[REP_IB].priv = NULL;
 }
 
 static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
@@ -84,16 +84,17 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return mlx5_ib_rep_to_dev(rep);
 }
 
+static const struct mlx5_eswitch_rep_ops rep_ops = {
+	.load = mlx5_ib_vport_rep_load,
+	.unload = mlx5_ib_vport_rep_unload,
+	.get_proto_dev = mlx5_ib_vport_get_proto_dev,
+};
+
 void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if = {};
-
-	rep_if.load = mlx5_ib_vport_rep_load;
-	rep_if.unload = mlx5_ib_vport_rep_unload;
-	rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
 
-	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_IB);
+	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
 }
 
 void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev)
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h
index 8336e0517a5c..7a917e6d5c09 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.h
+++ b/drivers/infiniband/hw/mlx5/ib_rep.h
@@ -72,6 +72,6 @@ struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
 static inline
 struct mlx5_ib_dev *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep)
 {
-	return (struct mlx5_ib_dev *)rep->rep_if[REP_IB].priv;
+	return rep->rep_data[REP_IB].priv;
 }
 #endif /* __MLX5_IB_REP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 243368dc23db..d9d363fe5cf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -31,12 +31,15 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(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-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
+					lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
+					en/tc_tun_geneve.o
 
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o rdma.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
+				      ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d2ab8cd8ad9f..30f7dffb5b1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -316,7 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
-	case MLX5_CMD_OP_QUERY_HOST_PARAMS:
+	case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -628,7 +628,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT);
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
-	MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS);
+	MLX5_COMMAND_STR_CASE(QUERY_ESW_FUNCTIONS);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index 0ccd6d40baf7..d2228e37450f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -83,30 +83,3 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 
 	mlx5_peer_pf_cleanup(dev);
 }
-
-static int mlx5_query_host_params_context(struct mlx5_core_dev *dev,
-					  u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {};
-
-	MLX5_SET(query_host_params_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_HOST_PARAMS);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
-int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
-{
-	u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {};
-	int err;
-
-	err = mlx5_query_host_params_context(dev, out, sizeof(out));
-	if (err)
-		return err;
-
-	*num_vf = MLX5_GET(query_host_params_out, out,
-			   host_params_context.host_num_of_vfs);
-	mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf);
-
-	return 0;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
index 346372df218f..d3d7a00a02ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
@@ -16,7 +16,6 @@ enum {
 bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev);
 int mlx5_ec_init(struct mlx5_core_dev *dev);
 void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
-int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf);
 
 #else  /* CONFIG_MLX5_ESWITCH */
 
@@ -24,9 +23,6 @@ static inline bool
 mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; }
 static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {}
-static inline int
-mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
-{ return -EOPNOTSUPP; }
 
 #endif /* CONFIG_MLX5_ESWITCH */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index fe5d4d7f15ed..b099968b2b7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -3,9 +3,22 @@
 
 #include <net/vxlan.h>
 #include <net/gre.h>
-#include "lib/vxlan.h"
+#include <net/geneve.h>
 #include "en/tc_tun.h"
 
+struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
+{
+	if (netif_is_vxlan(tunnel_dev))
+		return &vxlan_tunnel;
+	else if (netif_is_geneve(tunnel_dev))
+		return &geneve_tunnel;
+	else if (netif_is_gretap(tunnel_dev) ||
+		 netif_is_ip6gretap(tunnel_dev))
+		return &gre_tunnel;
+	else
+		return NULL;
+}
+
 static int get_route_and_out_devs(struct mlx5e_priv *priv,
 				  struct net_device *dev,
 				  struct net_device **route_dev,
@@ -141,63 +154,15 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
-{
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
-	struct udphdr *udp = (struct udphdr *)(buf);
-	struct vxlanhdr *vxh = (struct vxlanhdr *)
-			       ((char *)udp + sizeof(struct udphdr));
-
-	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_gen_gre_header(char buf[], struct ip_tunnel_key *tun_key)
-{
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
-	int hdr_len;
-	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
-
-	/* 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 = gre_calc_hlen(tun_key->tun_flags);
-	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_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
 				      struct mlx5e_encap_entry *e)
 {
-	int err = 0;
-	struct ip_tunnel_key *key = &e->tun_info.key;
-
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		*ip_proto = IPPROTO_UDP;
-		err = mlx5e_gen_vxlan_header(buf, key);
-	} else if  (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		*ip_proto = IPPROTO_GRE;
-		err = mlx5e_gen_gre_header(buf, key);
-	} else {
-		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
-			, e->tunnel_type);
-		err = -EOPNOTSUPP;
+	if (!e->tunnel) {
+		pr_warn("mlx5: Cannot generate tunnel header for this tunnel\n");
+		return -EOPNOTSUPP;
 	}
 
-	return err;
+	return e->tunnel->generate_ip_tun_hdr(buf, ip_proto, e);
 }
 
 static char *gen_eth_tnl_hdr(char *buf, struct net_device *dev,
@@ -229,7 +194,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
@@ -253,7 +218,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	ipv4_encap_size =
 		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct iphdr) +
-		e->tunnel_hlen;
+		e->tunnel->calc_hlen(e);
 
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -345,7 +310,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
@@ -369,7 +334,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	ipv6_encap_size =
 		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct ipv6hdr) +
-		e->tunnel_hlen;
+		e->tunnel->calc_hlen(e);
 
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -455,27 +420,12 @@ out:
 	return err;
 }
 
-int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev)
-{
-	if (netif_is_vxlan(tunnel_dev))
-		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
-	else if (netif_is_gretap(tunnel_dev) ||
-		 netif_is_ip6gretap(tunnel_dev))
-		return MLX5E_TC_TUNNEL_TYPE_GRETAP;
-	else
-		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
-}
-
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev)
 {
-	int tunnel_type = mlx5e_tc_tun_get_type(netdev);
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(netdev);
 
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
-	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
-		return true;
-	else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP &&
-		 MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap))
+	if (tunnel && tunnel->can_offload(priv))
 		return true;
 	else
 		return false;
@@ -486,71 +436,87 @@ int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 				 struct mlx5e_encap_entry *e,
 				 struct netlink_ext_ack *extack)
 {
-	e->tunnel_type = mlx5e_tc_tun_get_type(tunnel_dev);
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(tunnel_dev);
 
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
-
-		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;
-		e->tunnel_hlen = VXLAN_HLEN;
-	} else if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
-		e->tunnel_hlen = gre_calc_hlen(e->tun_info.key.tun_flags);
-	} else {
+	if (!tunnel) {
 		e->reformat_type = -1;
-		e->tunnel_hlen = -1;
 		return -EOPNOTSUPP;
 	}
-	return 0;
+
+	return tunnel->init_encap_attr(tunnel_dev, priv, e, extack);
 }
 
-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)
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct tc_cls_flower_offload *f,
+		       void *headers_c,
+		       void *headers_v, u8 *match_level)
+{
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(filter_dev);
+	int err = 0;
+
+	if (!tunnel) {
+		netdev_warn(priv->netdev,
+			    "decapsulation offload is not supported for %s net device\n",
+			    mlx5e_netdev_kind(filter_dev));
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	*match_level = tunnel->match_level;
+
+	if (tunnel->parse_udp_ports) {
+		err = tunnel->parse_udp_ports(priv, spec, f,
+					      headers_c, headers_v);
+		if (err)
+			goto out;
+	}
+
+	if (tunnel->parse_tunnel) {
+		err = tunnel->parse_tunnel(priv, spec, f,
+					   headers_c, headers_v);
+		if (err)
+			goto out;
+	}
+
+out:
+	return err;
+}
+
+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)
 {
 	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
-	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_match_ports enc_ports;
 
-	flow_rule_match_enc_ports(rule, &enc_ports);
-
 	/* Full udp dst port must be given */
-	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
-	    memchr_inv(&enc_ports.mask->dst, 0xff, sizeof(enc_ports.mask->dst))) {
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "VXLAN decap filter must include enc_dst_port condition");
+				   "UDP tunnel decap filter must include enc_dst_port condition");
 		netdev_warn(priv->netdev,
-			    "VXLAN decap filter must include enc_dst_port condition\n");
+			    "UDP tunnel decap filter must include enc_dst_port condition\n");
 		return -EOPNOTSUPP;
 	}
 
-	/* udp dst port must be knonwn as a VXLAN port */
-	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(enc_ports.key->dst))) {
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	if (memchr_inv(&enc_ports.mask->dst, 0xff,
+		       sizeof(enc_ports.mask->dst))) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Matched UDP port is not registered as a VXLAN port");
+				   "UDP tunnel decap filter must match enc_dst_port fully");
 		netdev_warn(priv->netdev,
-			    "UDP port %d is not registered as a VXLAN port\n",
-			    be16_to_cpu(enc_ports.key->dst));
+			    "UDP tunnel decap filter must match enc_dst_port fully\n");
 		return -EOPNOTSUPP;
 	}
 
-	/* dst UDP port is valid here */
+	/* match on UDP protocol and dst port number */
+
 	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_UDP);
 
@@ -559,92 +525,15 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport,
 		 ntohs(enc_ports.key->dst));
 
+	/* UDP src port on outer header is generated by HW,
+	 * so it is probably a bad idea to request matching it.
+	 * Nonetheless, it is allowed.
+	 */
+
 	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport,
 		 ntohs(enc_ports.mask->src));
 	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport,
 		 ntohs(enc_ports.key->src));
 
-	/* match on VNI */
-	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, 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;
-}
-
-static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
-				     struct mlx5_flow_spec *spec,
-				     struct tc_cls_flower_offload *f,
-				     void *outer_headers_c,
-				     void *outer_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);
-
-	if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) {
-		NL_SET_ERR_MSG_MOD(f->common.extack,
-				   "GRE HW offloading is not supported");
-		netdev_warn(priv->netdev, "GRE HW offloading is not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
-	MLX5_SET(fte_match_set_lyr_2_4, outer_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;
 }
-
-int mlx5e_tc_tun_parse(struct net_device *filter_dev,
-		       struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct tc_cls_flower_offload *f,
-		       void *headers_c,
-		       void *headers_v, u8 *match_level)
-{
-	int tunnel_type;
-	int err = 0;
-
-	tunnel_type = mlx5e_tc_tun_get_type(filter_dev);
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		*match_level = MLX5_MATCH_L4;
-		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
-					       headers_c, headers_v);
-	} else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		*match_level = MLX5_MATCH_L3;
-		err = mlx5e_tc_tun_parse_gretap(priv, spec, f,
-						headers_c, headers_v);
-	} else {
-		netdev_warn(priv->netdev,
-			    "decapsulation offload is not supported for %s (kind: \"%s\")\n",
-			    netdev_name(filter_dev),
-			    mlx5e_netdev_kind(filter_dev));
-
-		return -EOPNOTSUPP;
-	}
-	return err;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index b63f15de899d..3c48f7e62505 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -14,9 +14,41 @@
 enum {
 	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
 	MLX5E_TC_TUNNEL_TYPE_VXLAN,
-	MLX5E_TC_TUNNEL_TYPE_GRETAP
+	MLX5E_TC_TUNNEL_TYPE_GENEVE,
+	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 geneve_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 +62,6 @@ 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 +72,10 @@ 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__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
new file mode 100644
index 000000000000..238ae85d07cc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/geneve.h>
+#include "lib/geneve.h"
+#include "en/tc_tun.h"
+
+#define MLX5E_GENEVE_VER 0
+
+static bool mlx5e_tc_tun_can_offload_geneve(struct mlx5e_priv *priv)
+{
+	return !!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & MLX5_FLEX_PROTO_GENEVE);
+}
+
+static int mlx5e_tc_tun_calc_hlen_geneve(struct mlx5e_encap_entry *e)
+{
+	return sizeof(struct udphdr) +
+	       sizeof(struct genevehdr) +
+	       e->tun_info->options_len;
+}
+
+static int mlx5e_tc_tun_check_udp_dport_geneve(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);
+
+	/* Currently we support only default GENEVE
+	 * port, so udp dst port must match.
+	 */
+	if (be16_to_cpu(enc_ports.key->dst) != GENEVE_UDP_PORT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP dst port is not registered as a GENEVE port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a GENEVE port\n",
+			    be16_to_cpu(enc_ports.key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_udp_ports_geneve(struct mlx5e_priv *priv,
+					       struct mlx5_flow_spec *spec,
+					       struct tc_cls_flower_offload *f,
+					       void *headers_c,
+					       void *headers_v)
+{
+	int err;
+
+	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_geneve(priv, f);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_geneve(struct net_device *tunnel_dev,
+					       struct mlx5e_priv *priv,
+					       struct mlx5e_encap_entry *e,
+					       struct netlink_ext_ack *extack)
+{
+	e->tunnel = &geneve_tunnel;
+
+	/* Reformat type for GENEVE encap is similar to VXLAN:
+	 * in both cases the HW adds in the same place a
+	 * defined encapsulation header that the SW provides.
+	 */
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+	return 0;
+}
+
+static void mlx5e_tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	vni[0] = (__force __u8)(tun_id >> 16);
+	vni[1] = (__force __u8)(tun_id >> 8);
+	vni[2] = (__force __u8)tun_id;
+#else
+	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+static int mlx5e_gen_ip_tunnel_header_geneve(char buf[],
+					     __u8 *ip_proto,
+					     struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_info *tun_info = e->tun_info;
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct genevehdr *geneveh;
+
+	geneveh = (struct genevehdr *)((char *)udp + sizeof(struct udphdr));
+
+	*ip_proto = IPPROTO_UDP;
+
+	udp->dest = tun_info->key.tp_dst;
+
+	memset(geneveh, 0, sizeof(*geneveh));
+	geneveh->ver = MLX5E_GENEVE_VER;
+	geneveh->opt_len = tun_info->options_len / 4;
+	geneveh->oam = !!(tun_info->key.tun_flags & TUNNEL_OAM);
+	geneveh->critical = !!(tun_info->key.tun_flags & TUNNEL_CRIT_OPT);
+	mlx5e_tunnel_id_to_vni(tun_info->key.tun_id, geneveh->vni);
+	geneveh->proto_type = htons(ETH_P_TEB);
+
+	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+		if (!geneveh->opt_len)
+			return -EOPNOTSUPP;
+		ip_tunnel_info_opts_get(geneveh->options, tun_info);
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_geneve_vni(struct mlx5e_priv *priv,
+					 struct mlx5_flow_spec *spec,
+					 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_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_k