/*
 * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/etherdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/mlx5_ifc.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
#include "mlx5_core.h"
#include "eswitch.h"
#include "rdma.h"
#include "en.h"
#include "fs_core.h"
#include "lib/devcom.h"
#include "lib/eq.h"

/* There are two match-all miss flows, one for unicast dst mac and
 * one for multicast.
 */
#define MLX5_ESW_MISS_FLOWS (2)

#define fdb_prio_table(esw, chain, prio, level) \
	(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]

#define UPLINK_REP_INDEX 0

static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
						     u16 vport_num)
{
	int idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);

	WARN_ON(idx > esw->total_vports - 1);
	return &esw->offloads.vport_reps[idx];
}

static struct mlx5_flow_table *
esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
static void
esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);

bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw)
{
	return (!!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED));
}

u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)
{
	if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
		return FDB_TC_MAX_CHAIN;

	return 0;
}

u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
{
	if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
		return FDB_TC_MAX_PRIO;

	return 1;
}

static bool
esw_check_ingress_prio_tag_enabled(const struct mlx5_eswitch *esw,
				   const struct mlx5_vport *vport)
{
	return (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
		mlx5_eswitch_is_vf_vport(esw, vport->vport));
}

static void
mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
				  struct mlx5_flow_spec *spec,
				  struct mlx5_esw_flow_attr *attr)
{
	void *misc2;
	void *misc;

	/* Use metadata matching because vport is not represented by single
	 * VHCA in dual-port RoCE mode, and matching on source vport may fail.
	 */
	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
		MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0,
			 mlx5_eswitch_get_vport_metadata_for_match(attr->in_mdev->priv.eswitch,
								   attr->in_rep->vport));

		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
		MLX5_SET_TO_ONES(fte_match_set_misc2, misc2, metadata_reg_c_0);

		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
		if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc)))
			spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
	} else {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
		MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);

		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
			MLX5_SET(fte_match_set_misc, misc,
				 source_eswitch_owner_vhca_id,
				 MLX5_CAP_GEN(attr->in_mdev, vhca_id));

		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
			MLX5_SET_TO_ONES(fte_match_set_misc, misc,
					 source_eswitch_owner_vhca_id);

		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
	}

	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
	    attr->in_rep->vport == MLX5_VPORT_UPLINK)
		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
}

struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
				struct mlx5_flow_spec *spec,
				struct mlx5_esw_flow_attr *attr)
{
	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
	bool split = !!(attr->split_count);
	struct mlx5_flow_handle *rule;
	struct mlx5_flow_table *fdb;
	int j, i = 0;

	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
		return ERR_PTR(-EOPNOTSUPP);

	flow_act.action = attr->action;
	/* if per flow vlan pop/push is emulated, don't set that into the firmware */
	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
		flow_act.vlan[0].vid = attr->vlan_vid[0];
		flow_act.vlan[0].prio = attr->vlan_prio[0];
		if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
			flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
			flow_act.vlan[1].vid = attr->vlan_vid[1];
			flow_act.vlan[1].prio = attr->vlan_prio[1];
		}
	}

	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
		if (attr->dest_chain) {
			struct mlx5_flow_table *ft;

			ft = esw_get_prio_table(esw, attr->dest_chain, 1, 0);
			if (IS_ERR(ft)) {
				rule = ERR_CAST(ft);
				goto err_create_goto_table;
			}

			dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
			dest[i].ft = ft;
			i++;
		} else {
			for (j = attr->split_count; j < attr->out_count; j++) {
				dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
				dest[i].vport.num = attr->dests[j].rep->vport;
				dest[i].vport.vhca_id =
					MLX5_CAP_GEN(attr->dests[j].mdev, vhca_id);
				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
					dest[i].vport.flags |=
						MLX5_FLOW_DEST_VPORT_VHCA_ID;
				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
					flow_act.pkt_reformat = attr->dests[j].pkt_reformat;
					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
					dest[i].vport.pkt_reformat =
						attr->dests[j].pkt_reformat;
				}
				i++;
			}
		}
	}
	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
		dest[i].counter_id = mlx5_fc_id(attr->counter);
		i++;
	}

	mlx5_eswitch_set_rule_source_port(esw, spec, attr);

	if (attr->outer_match_level != MLX5_MATCH_NONE)
		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
	if (attr->inner_match_level != MLX5_MATCH_NONE)
		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;

	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
		flow_act.modify_hdr = attr->modify_hdr;

	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
	if (IS_ERR(fdb)) {
		rule = ERR_CAST(fdb);
		goto err_esw_get;
	}

	if (mlx5_eswitch_termtbl_required(esw, &flow_act, spec))
		rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr,
						     &flow_act, dest, i);
	else
		rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
	if (IS_ERR(rule))
		goto err_add_rule;
	else
		atomic64_inc(&esw->offloads.num_flows);

	return rule;

err_add_rule:
	esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
err_esw_get:
	if (attr->dest_chain)
		esw_put_prio_table(esw, attr->dest_chain, 1, 0);
err_create_goto_table:
	return rule;
}

struct mlx5_flow_handle *
mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
			  struct mlx5_flow_spec *spec,
			  struct mlx5_esw_flow_attr *attr)
{
	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
	struct mlx5_flow_table *fast_fdb;
	struct mlx5_flow_table *fwd_fdb;
	struct mlx5_flow_handle *rule;
	int i;

	fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
	if (IS_ERR(fast_fdb)) {
		rule = ERR_CAST(fast_fdb);
		goto err_get_fast;
	}

	fwd_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 1);
	if (IS_ERR(fwd_fdb)) {
		rule = ERR_CAST(fwd_fdb);
		goto err_get_fwd;
	}

	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	for (i = 0; i < attr->split_count; i++) {
		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
		dest[i].vport.num = attr->dests[i].rep->vport;
		dest[i].vport.vhca_id =
			MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
			dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat;
		}
	}
	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
	dest[i].ft = fwd_fdb,
	i++;

	mlx5_eswitch_set_rule_source_port(esw, spec, attr);

	if (attr->outer_match_level != MLX5_MATCH_NONE)
		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;

	rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);

	if (IS_ERR(rule))
		goto add_err;

	atomic64_inc(&esw->offloads.num_flows);

	return rule;
add_err:
	esw_put_prio_table(esw, attr->chain, attr->prio, 1);
err_get_fwd:
	esw_put_prio_table(esw, attr->chain, attr->prio, 0);
err_get_fast:
	return rule;
}

static void
__mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
			struct mlx5_flow_handle *rule,
			struct mlx5_esw_flow_attr *attr,
			bool fwd_rule)
{
	bool split = (attr->split_count > 0);
	int i;

	mlx5_del_flow_rules(rule);

	/* unref the term table */
	for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
		if (attr->dests[i].termtbl)
			mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl);
	}

	atomic64_dec(&esw->offloads.num_flows);

	if (fwd_rule)  {
		esw_put_prio_table(esw, attr->chain, attr->prio, 1);
		esw_put_prio_table(esw, attr->chain, attr->prio, 0);
	} else {
		esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
		if (attr->dest_chain)
			esw_put_prio_table(esw, attr->dest_chain, 1, 0);
	}
}

void
mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
				struct mlx5_flow_handle *rule,
				struct mlx5_esw_flow_attr *attr)
{
	__mlx5_eswitch_del_rule(esw, rule, attr, false);
}

void
mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
			  struct mlx5_flow_handle *rule,
			  struct mlx5_esw_flow_attr *attr)
{
	__mlx5_eswitch_del_rule(esw, rule, attr, true);
}

static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
{
	struct mlx5_eswitch_rep *rep;
	int i, err = 0;

	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
	mlx5_esw_for_each_host_func_rep(esw, i, rep, esw->esw_funcs.num_vfs) {
		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
			continue;

		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
		if (err)
			goto out;
	}

out:
	return err;
}

static struct mlx5_eswitch_rep *
esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
{
	struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;

	in_rep  = attr->in_rep;
	out_rep = attr->dests[0].rep;

	if (push)
		vport = in_rep;
	else if (pop)
		vport = out_rep;
	else
		vport = in_rep;

	return vport;
}

static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
				     bool push, bool pop, bool fwd)
{
	struct mlx5_eswitch_rep *in_rep, *out_rep;

	if ((push || pop) && !fwd)
		goto out_notsupp;

	in_rep  = attr->in_rep;
	out_rep = attr->dests[0].rep;

	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
		goto out_notsupp;

	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
		goto out_notsupp;

	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
	if (!push && !pop && fwd)
		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
			goto out_notsupp;

	/* protects against (1) setting rules with different vlans to push and
	 * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
	 */
	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
		goto out_notsupp;

	return 0;

out_notsupp:
	return -EOPNOTSUPP;
}

int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
				 struct mlx5_esw_flow_attr *attr)
{
	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
	struct mlx5_eswitch_rep *vport = NULL;
	bool push, pop, fwd;
	int err = 0;

	/* nop if we're on the vlan push/pop non emulation mode */
	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
		return 0;

	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
	pop  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
	fwd  = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
		   !attr->dest_chain);

	mutex_lock(&esw->state_lock);

	err = esw_add_vlan_action_check(attr, push, pop, fwd);
	if (err)
		goto unlock;

	attr->vlan_handled = false;

	vport = esw_vlan_action_get_vport(attr, push, pop);

	if (!push && !pop && fwd) {
		/* tracks VF --> wire rules without vlan push action */
		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
			vport->vlan_refcount++;
			attr->vlan_handled = true;
		}

		goto unlock;
	}

	if (!push && !pop)
		goto unlock;

	if (!(offloads->vlan_push_pop_refcount)) {
		/* it's the 1st vlan rule, apply global vlan pop policy */
		err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP);
		if (err)
			goto out;
	}
	offloads->vlan_push_pop_refcount++;

	if (push) {
		if (vport->vlan_refcount)
			goto skip_set_push;

		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
						    SET_VLAN_INSERT | SET_VLAN_STRIP);
		if (err)
			goto out;
		vport->vlan = attr->vlan_vid[0];
skip_set_push:
		vport->vlan_refcount++;
	}
out:
	if (!err)
		attr->vlan_handled = true;
unlock:
	mutex_unlock(&esw->state_lock);
	return err;
}

int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
				 struct mlx5_esw_flow_attr *attr)
{
	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
	struct mlx5_eswitch_rep *vport = NULL;
	bool push, pop, fwd;
	int err = 0;

	/* nop if we're on the vlan push/pop non emulation mode */
	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
		return 0;

	if (!attr->vlan_handled)
		return 0;

	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
	pop  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
	fwd  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);

	mutex_lock(&esw->state_lock);

	vport = esw_vlan_action_get_vport(attr, push, pop);

	if (!push && !pop && fwd) {
		/* tracks VF --> wire rules without vlan push action */
		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
			vport->vlan_refcount--;

		goto out;
	}

	if (push) {
		vport->vlan_refcount--;
		if (vport->vlan_refcount)
			goto skip_unset_push;

		vport->vlan = 0;
		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport,
						    0, 0, SET_VLAN_STRIP);
		if (err)
			goto out;
	}

skip_unset_push:
	offloads->vlan_push_pop_refcount--;
	if (offloads->vlan_push_pop_refcount)
		goto out;

	/* no more vlan rules, stop global vlan pop policy */
	err = esw_set_global_vlan_pop(esw, 0);

out:
	mutex_unlock(&esw->state_lock);
	return err;
}

struct mlx5_flow_handle *
mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport,
				    u32 sqn)
{
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_destination dest = {};
	struct mlx5_flow_handle *flow_rule;
	struct mlx5_flow_spec *spec;
	void *misc;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec) {
		flow_rule = ERR_PTR(-ENOMEM);
		goto out;
	}

	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
	/* source vport is the esw manager */
	MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);

	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);

	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
	dest.vport.num = vport;
	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;

	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
					&flow_act, &dest, 1);
	if (IS_ERR(flow_rule))
		esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
out:
	kvfree(spec);
	return flow_rule;
}
EXPORT_SYMBOL(mlx5_eswitch_add_send_to_vport_rule);

void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
{
	mlx5_del_flow_rules(rule);
}

static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
{
	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
	u8 fdb_to_vport_reg_c_id;
	int err;

	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
		return 0;

	err = mlx5_eswitch_query_esw_vport_context(esw->dev, 0, false,
						   out, sizeof(out));
	if (err)
		return err;

	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
					 esw_vport_context.fdb_to_vport_reg_c_id);

	if (enable)
		fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
	else
		fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;

	MLX5_SET(modify_esw_vport_context_in, in,
		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);

	MLX5_SET(modify_esw_vport_context_in, in,
		 field_select.fdb_to_vport_reg_c_id, 1);

	return mlx5_eswitch_modify_esw_vport_context(esw->dev, 0, false,
						     in, sizeof(in));
}

static void peer_miss_rules_setup(struct mlx5_eswitch *esw,
				  struct mlx5_core_dev *peer_dev,
				  struct mlx5_flow_spec *spec,
				  struct mlx5_flow_destination *dest)
{
	void *misc;

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
				    misc_parameters_2);
		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);

		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
	} else {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				    misc_parameters);

		MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
			 MLX5_CAP_GEN(peer_dev, vhca_id));

		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;

		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
				    misc_parameters);
		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
				 source_eswitch_owner_vhca_id);
	}

	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
}

static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
					       struct mlx5_eswitch *peer_esw,
					       struct mlx5_flow_spec *spec,
					       u16 vport)
{
	void *misc;

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				    misc_parameters_2);
		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
			 mlx5_eswitch_get_vport_metadata_for_match(peer_esw,
								   vport));
	} else {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				    misc_parameters);
		MLX5_SET(fte_match_set_misc, misc, source_port, vport);
	}
}

static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
				       struct mlx5_core_dev *peer_dev)
{
	struct mlx5_flow_destination dest = {};
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_handle **flows;
	struct mlx5_flow_handle *flow;
	struct mlx5_flow_spec *spec;
	/* total vports is the same for both e-switches */
	int nvports = esw->total_vports;
	void *misc;
	int err, i;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec)
		return -ENOMEM;

	peer_miss_rules_setup(esw, peer_dev, spec, &dest);

	flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
	if (!flows) {
		err = -ENOMEM;
		goto alloc_flows_err;
	}

	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
			    misc_parameters);

	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
						   spec, MLX5_VPORT_PF);

		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
					   spec, &flow_act, &dest, 1);
		if (IS_ERR(flow)) {
			err = PTR_ERR(flow);
			goto add_pf_flow_err;
		}
		flows[MLX5_VPORT_PF] = flow;
	}

	if (mlx5_ecpf_vport_exists(esw->dev)) {
		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
					   spec, &flow_act, &dest, 1);
		if (IS_ERR(flow)) {
			err = PTR_ERR(flow);
			goto add_ecpf_flow_err;
		}
		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
	}

	mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
		esw_set_peer_miss_rule_source_port(esw,
						   peer_dev->priv.eswitch,
						   spec, i);

		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
					   spec, &flow_act, &dest, 1);
		if (IS_ERR(flow)) {
			err = PTR_ERR(flow);
			goto add_vf_flow_err;
		}
		flows[i] = flow;
	}

	esw->fdb_table.offloads.peer_miss_rules = flows;

	kvfree(spec);
	return 0;

add_vf_flow_err:
	nvports = --i;
	mlx5_esw_for_each_vf_vport_num_reverse(esw, i, nvports)
		mlx5_del_flow_rules(flows[i]);

	if (mlx5_ecpf_vport_exists(esw->dev))
		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
add_ecpf_flow_err:
	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
add_pf_flow_err:
	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
	kvfree(flows);
alloc_flows_err:
	kvfree(spec);
	return err;
}

static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
{
	struct mlx5_flow_handle **flows;
	int i;

	flows = esw->fdb_table.offloads.peer_miss_rules;

	mlx5_esw_for_each_vf_vport_num_reverse(esw, i,
					       mlx5_core_max_vfs(esw->dev))
		mlx5_del_flow_rules(flows[i]);

	if (mlx5_ecpf_vport_exists(esw->dev))
		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);

	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);

	kvfree(flows);
}

static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
{
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_destination dest = {};
	struct mlx5_flow_handle *flow_rule = NULL;
	struct mlx5_flow_spec *spec;
	void *headers_c;
	void *headers_v;
	int err = 0;
	u8 *dmac_c;
	u8 *dmac_v;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec) {
		err = -ENOMEM;
		goto out;
	}

	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
	headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
				 outer_headers);
	dmac_c = MLX5_ADDR_OF(fte_match_param, headers_c,
			      outer_headers.dmac_47_16);
	dmac_c[0] = 0x01;

	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
	dest.vport.num = esw->manager_vport;
	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;

	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
					&flow_act, &dest, 1);
	if (IS_ERR(flow_rule)) {
		err = PTR_ERR(flow_rule);
		esw_warn(esw->dev,  "FDB: Failed to add unicast miss flow rule err %d\n", err);
		goto out;
	}

	esw->fdb_table.offloads.miss_rule_uni = flow_rule;

	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				 outer_headers);
	dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v,
			      outer_headers.dmac_47_16);
	dmac_v[0] = 0x01;
	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
					&flow_act, &dest, 1);
	if (IS_ERR(flow_rule)) {
		err = PTR_ERR(flow_rule);
		esw_warn(esw->dev, "FDB: Failed to add multicast miss flow rule err %d\n", err);
		mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
		goto out;
	}

	esw->fdb_table.offloads.miss_rule_multi = flow_rule;

out:
	kvfree(spec);
	return err;
}

#define ESW_OFFLOADS_NUM_GROUPS  4

/* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS),
 * and a virtual memory region of 16M (ESW_SIZE), this region is duplicated
 * for each flow table pool. We can allocate up to 16M of each pool,
 * and we keep track of how much we used via put/get_sz_to_pool.
 * Firmware doesn't report any of this for now.
 * ESW_POOL is expected to be sorted from large to small
 */
#define ESW_SIZE (16 * 1024 * 1024)
const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
				    64 * 1024, 4 * 1024 };

static int
get_sz_from_pool(struct mlx5_eswitch *esw)
{
	int sz = 0, i;

	for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
		if (esw->fdb_table.offloads.fdb_left[i]) {
			--esw->fdb_table.offloads.fdb_left[i];
			sz = ESW_POOLS[i];
			break;
		}
	}

	return sz;
}

static void
put_sz_to_pool(struct mlx5_eswitch *esw, int sz)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
		if (sz >= ESW_POOLS[i]) {
			++esw->fdb_table.offloads.fdb_left[i];
			break;
		}
	}
}

static struct mlx5_flow_table *
create_next_size_table(struct mlx5_eswitch *esw,
		       struct mlx5_flow_namespace *ns,
		       u16 table_prio,
		       int level,
		       u32 flags)
{
	struct mlx5_flow_table *fdb;
	int sz;

	sz = get_sz_from_pool(esw);
	if (!sz)
		return ERR_PTR(-ENOSPC);

	fdb = mlx5_create_auto_grouped_flow_table(ns,
						  table_prio,
						  sz,
						  ESW_OFFLOADS_NUM_GROUPS,
						  level,
						  flags);
	if (IS_ERR(fdb)) {
		esw_warn(esw->dev, "Failed to create FDB Table err %d (table prio: %d, level: %d, size: %d)\n",
			 (int)PTR_ERR(fdb), table_prio, level, sz);
		put_sz_to_pool(esw, sz);
	}

	return fdb;
}

static struct mlx5_flow_table *
esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
{
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_table *fdb = NULL;
	struct mlx5_flow_namespace *ns;
	int table_prio, l = 0;
	u32 flags = 0;

	if (chain == FDB_TC_SLOW_PATH_CHAIN)
		return esw->fdb_table.offloads.slow_fdb;

	mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);

	fdb = fdb_prio_table(esw, chain, prio, level).fdb;
	if (fdb) {
		/* take ref on earlier levels as well */
		while (level >= 0)
			fdb_prio_table(esw, chain, prio, level--).num_rules++;
		mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
		return fdb;
	}

	ns = mlx5_get_fdb_sub_ns(dev, chain);
	if (!ns) {
		esw_warn(dev, "Failed to get FDB sub namespace\n");
		mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
		return ERR_PTR(-EOPNOTSUPP);
	}

	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
		flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
			  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);

	table_prio = prio - 1;

	/* create earlier levels for correct fs_core lookup when
	 * connecting tables
	 */
	for (l = 0; l <= level; l++) {
		if (fdb_prio_table(esw, chain, prio, l).fdb) {
			fdb_prio_table(esw, chain, prio, l).num_rules++;
			continue;
		}

		fdb = create_next_size_table(esw, ns, table_prio, l, flags);
		if (IS_ERR(fdb)) {
			l--;
			goto err_create_fdb;
		}

		fdb_prio_table(esw, chain, prio, l).fdb = fdb;
		fdb_prio_table(esw, chain, prio, l).num_rules = 1;
	}

	mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
	return fdb;

err_create_fdb:
	mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
	if (l >= 0)
		esw_put_prio_table(esw, chain, prio, l);

	return fdb;
}

static void
esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
{
	int l;

	if (chain == FDB_TC_SLOW_PATH_CHAIN)
		return;

	mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);

	for (l = level; l >= 0; l--) {
		if (--(fdb_prio_table(esw, chain, prio, l).num_rules) > 0)
			continue;

		put_sz_to_pool(esw, fdb_prio_table(esw, chain, prio, l).fdb->max_fte);
		mlx5_destroy_flow_table(fdb_prio_table(esw, chain, prio, l).fdb);
		fdb_prio_table(esw, chain, prio, l).fdb = NULL;
	}

	mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
}

static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
{
	/* If lazy creation isn't supported, deref the fast path tables */
	if (!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)) {
		esw_put_prio_table(esw, 0, 1, 1);
		esw_put_prio_table(esw, 0, 1, 0);
	}
}

#define MAX_PF_SQ 256
#define MAX_SQ_NVPORTS 32

static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
					   u32 *flow_group_in)
{
	void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
					    flow_group_in,
					    match_criteria);

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		MLX5_SET(create_flow_group_in, flow_group_in,
			 match_criteria_enable,
			 MLX5_MATCH_MISC_PARAMETERS_2);

		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
				 misc_parameters_2.metadata_reg_c_0);
	} else {
		MLX5_SET(create_flow_group_in, flow_group_in,
			 match_criteria_enable,
			 MLX5_MATCH_MISC_PARAMETERS);

		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
				 misc_parameters.source_port);
	}
}

static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_flow_table_attr ft_attr = {};
	struct mlx5_core_dev *dev = esw->dev;
	u32 *flow_group_in, max_flow_counter;
	struct mlx5_flow_namespace *root_ns;
	struct mlx5_flow_table *fdb = NULL;
	int table_size, ix, err = 0, i;
	struct mlx5_flow_group *g;
	u32 flags = 0, fdb_max;
	void *match_criteria;
	u8 *dmac;

	esw_debug(esw->dev, "Create offloads FDB Tables\n");
	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
	if (!flow_group_in)
		return -ENOMEM;

	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
	if (!root_ns) {
		esw_warn(dev, "Failed to get FDB flow namespace\n");
		err = -EOPNOTSUPP;
		goto ns_err;
	}
	esw->fdb_table.offloads.ns = root_ns;
	err = mlx5_flow_namespace_set_mode(root_ns,
					   esw->dev->priv.steering->mode);
	if (err) {
		esw_warn(dev, "Failed to set FDB namespace steering mode\n");
		goto ns_err;
	}

	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);

	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n",
		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size),
		  max_flow_counter, ESW_OFFLOADS_NUM_GROUPS,
		  fdb_max);

	for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++)
		esw->fdb_table.offloads.fdb_left[i] =
			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;

	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
		MLX5_ESW_MISS_FLOWS + esw->total_vports;

	/* create the slow path fdb with encap set, so further table instances
	 * can be created at run time while VFs are probed if the FW allows that.
	 */
	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
		flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
			  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);

	ft_attr.flags = flags;
	ft_attr.max_fte = table_size;
	ft_attr.prio = FDB_SLOW_PATH;

	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
	if (IS_ERR(fdb)) {
		err = PTR_ERR(fdb);
		esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);
		goto slow_fdb_err;
	}
	esw->fdb_table.offloads.slow_fdb = fdb;

	/* If lazy creation isn't supported, open the fast path tables now */
	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, multi_fdb_encap) &&
	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
		esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
		esw_warn(dev, "Lazy creation of flow tables isn't supported, ignoring priorities\n");
		esw_get_prio_table(esw, 0, 1, 0);
		esw_get_prio_table(esw, 0, 1, 1);
	} else {
		esw_debug(dev, "Lazy creation of flow tables supported, deferring table opening\n");
		esw->fdb_table.flags |= ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
	}

	/* create send-to-vport group */
	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
		 MLX5_MATCH_MISC_PARAMETERS);

	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);

	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn);
	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port);

	ix = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ;
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1);

	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create send-to-vport flow group err(%d)\n", err);
		goto send_vport_err;
	}
	esw->fdb_table.offloads.send_to_vport_grp = g;

	/* create peer esw miss group */
	memset(flow_group_in, 0, inlen);

	esw_set_flow_group_source_port(esw, flow_group_in);

	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
					      flow_group_in,
					      match_criteria);

		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
				 misc_parameters.source_eswitch_owner_vhca_id);

		MLX5_SET(create_flow_group_in, flow_group_in,
			 source_eswitch_owner_vhca_id_valid, 1);
	}

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
		 ix + esw->total_vports - 1);
	ix += esw->total_vports;

	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
		goto peer_miss_err;
	}
	esw->fdb_table.offloads.peer_miss_grp = g;

	/* create miss group */
	memset(flow_group_in, 0, inlen);
	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
		 MLX5_MATCH_OUTER_HEADERS);
	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
				      match_criteria);
	dmac = MLX5_ADDR_OF(fte_match_param, match_criteria,
			    outer_headers.dmac_47_16);
	dmac[0] = 0x01;

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
		 ix + MLX5_ESW_MISS_FLOWS);

	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create miss flow group err(%d)\n", err);
		goto miss_err;
	}
	esw->fdb_table.offloads.miss_grp = g;

	err = esw_add_fdb_miss_rule(esw);
	if (err)
		goto miss_rule_err;

	esw->nvports = nvports;
	kvfree(flow_group_in);
	return 0;

miss_rule_err:
	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
miss_err:
	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
peer_miss_err:
	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
send_vport_err:
	esw_destroy_offloads_fast_fdb_tables(esw);
	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
slow_fdb_err:
	/* Holds true only as long as DMFS is the default */
	mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS);
ns_err:
	kvfree(flow_group_in);
	return err;
}

static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
{
	if (!esw->fdb_table.offloads.slow_fdb)
		return;

	esw_debug(esw->dev, "Destroy offloads FDB Tables\n");
	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);

	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
	esw_destroy_offloads_fast_fdb_tables(esw);
	/* Holds true only as long as DMFS is the default */
	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
				     MLX5_FLOW_STEERING_MODE_DMFS);
}

static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
{
	struct mlx5_flow_table_attr ft_attr = {};
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_table *ft_offloads;
	struct mlx5_flow_namespace *ns;
	int err = 0;

	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
	if (!ns) {
		esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
		return -EOPNOTSUPP;
	}

	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;

	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
	if (IS_ERR(ft_offloads)) {
		err = PTR_ERR(ft_offloads);
		esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err);
		return err;
	}

	esw->offloads.ft_offloads = ft_offloads;
	return 0;
}

static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
{
	struct mlx5_esw_offload *offloads = &esw->offloads;

	mlx5_destroy_flow_table(offloads->ft_offloads);
}

static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_flow_group *g;
	u32 *flow_group_in;
	int err = 0;

	nvports = nvports + MLX5_ESW_MISS_FLOWS;
	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
	if (!flow_group_in)
		return -ENOMEM;

	/* create vport rx group */
	esw_set_flow_group_source_port(esw, flow_group_in);

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1);

	g = mlx5_create_flow_group(esw->offloads.ft_offloads, flow_group_in);

	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		mlx5_core_warn(esw->dev, "Failed to create vport rx group err %d\n", err);
		goto out;
	}

	esw->offloads.vport_rx_group = g;
out:
	kvfree(flow_group_in);
	return err;
}

static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
{
	mlx5_destroy_flow_group(esw->offloads.vport_rx_group);
}

struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
				  struct mlx5_flow_destination *dest)
{
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_handle *flow_rule;
	struct mlx5_flow_spec *spec;
	void *misc;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec) {
		flow_rule = ERR_PTR(-ENOMEM);
		goto out;
	}

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
			 mlx5_eswitch_get_vport_metadata_for_match(esw, vport));

		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);

		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
	} else {
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
		MLX5_SET(fte_match_set_misc, misc, source_port, vport);

		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);

		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
	}

	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
					&flow_act, dest, 1);
	if (IS_ERR(flow_rule)) {
		esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
		goto out;
	}

out:
	kvfree(spec);
	return flow_rule;
}

static int esw_offloads_start(struct mlx5_eswitch *esw,
			      struct netlink_ext_ack *extack)
{
	int err, err1;

	if (esw->mode != MLX5_ESWITCH_LEGACY &&
	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Can't set offloads mode, SRIOV legacy not enabled");
		return -EINVAL;
	}

	mlx5_eswitch_disable(esw, false);
	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Failed setting eswitch to offloads");
		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
		if (err1) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Failed setting eswitch back to legacy");
		}
	}
	if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
		if (mlx5_eswitch_inline_mode_get(esw,
						 &esw->offloads.inline_mode)) {
			esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
			NL_SET_ERR_MSG_MOD(extack,
					   "Inline mode is different between vports");
		}
	}
	return err;
}

void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
{
	kfree(esw->offloads.vport_reps);
}

int esw_offloads_init_reps(struct mlx5_eswitch *esw)
{
	int total_vports = esw->total_vports;
	struct mlx5_eswitch_rep *rep;
	int vport_index;
	u8 rep_type;

	esw->offloads.vport_reps = kcalloc(total_vports,
					   sizeof(struct mlx5_eswitch_rep),
					   GFP_KERNEL);
	if (!esw->offloads.vport_reps)
		return -ENOMEM;

	mlx5_esw_for_all_reps(esw, vport_index, rep) {
		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index);
		rep->vport_index = vport_index;

		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
			atomic_set(&rep->rep_data[rep_type].state,
				   REP_UNREGISTERED);
	}

	return 0;
}

static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
				      struct mlx5_eswitch_rep *rep, u8 rep_type)
{
	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
			   REP_LOADED, REP_REGISTERED) == REP_LOADED)
		esw->offloads.rep_ops[rep_type]->unload(rep);
}

static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;

	if (mlx5_ecpf_vport_exists(esw->dev)) {
		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
		__esw_offloads_unload_rep(esw, rep, rep_type);
	}

	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
		__esw_offloads_unload_rep(esw, rep, rep_type);
	}

	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
	__esw_offloads_unload_rep(esw, rep, rep_type);
}

static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
				   u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;
	int i;

	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
		__esw_offloads_unload_rep(esw, rep, rep_type);
}

static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
{
	u8 rep_type = NUM_REP_TYPES;

	while (rep_type-- > 0)
		__unload_reps_vf_vport(esw, nvports, rep_type);
}

static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
	__unload_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);

	/* Special vports must be the last to unload. */
	__unload_reps_special_vport(esw, rep_type);
}

static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw)
{
	u8 rep_type = NUM_REP_TYPES;

	while (rep_type-- > 0)
		__unload_reps_all_vport(esw, rep_type);
}

static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
				   struct mlx5_eswitch_rep *rep, u8 rep_type)
{
	int err = 0;

	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED) {
		err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
		if (err)
			atomic_set(&rep->rep_data[rep_type].state,
				   REP_REGISTERED);
	}

	return err;
}

static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;
	int err;

	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
	err = __esw_offloads_load_rep(esw, rep, rep_type);
	if (err)
		return err;

	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
		err = __esw_offloads_load_rep(esw, rep, rep_type);
		if (err)
			goto err_pf;
	}

	if (mlx5_ecpf_vport_exists(esw->dev)) {
		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
		err = __esw_offloads_load_rep(esw, rep, rep_type);
		if (err)
			goto err_ecpf;
	}

	return 0;

err_ecpf:
	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
		__esw_offloads_unload_rep(esw, rep, rep_type);
	}

err_pf:
	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
	__esw_offloads_unload_rep(esw, rep, rep_type);
	return err;
}

static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
				u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;
	int err, i;

	mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
		err = __esw_offloads_load_rep(esw, rep, rep_type);
		if (err)
			goto err_vf;
	}

	return 0;

err_vf:
	__unload_reps_vf_vport(esw, --i, rep_type);
	return err;
}

static int __load_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
	int err;

	/* Special vports must be loaded first, uplink rep creates mdev resource. */
	err = __load_reps_special_vport(esw, rep_type);
	if (err)
		return err;

	err = __load_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
	if (err)
		goto err_vfs;

	return 0;

err_vfs:
	__unload_reps_special_vport(esw, rep_type);
	return err;
}

static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
{
	u8 rep_type = 0;
	int err;

	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
		err = __load_reps_vf_vport(esw, nvports, rep_type);
		if (err)
			goto err_reps;
	}

	return err;

err_reps:
	while (rep_type-- > 0)
		__unload_reps_vf_vport(esw, nvports, rep_type);
	return err;
}

static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw)
{
	u8 rep_type = 0;
	int err;

	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
		err = __load_reps_all_vport(esw, rep_type);
		if (err)
			goto err_reps;
	}

	return err;

err_reps:
	while (rep_type-- > 0)
		__unload_reps_all_vport(esw, rep_type);
	return err;
}

#define ESW_OFFLOADS_DEVCOM_PAIR	(0)
#define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)

static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
				  struct mlx5_eswitch *peer_esw)
{
	int err;

	err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
	if (err)
		return err;

	return 0;
}

static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
{
	mlx5e_tc_clean_fdb_peer_flows(esw);
	esw_del_fdb_peer_miss_rules(esw);
}

static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
					 struct mlx5_eswitch *peer_esw,
					 bool pair)
{
	struct mlx5_flow_root_namespace *peer_ns;
	struct mlx5_flow_root_namespace *ns;
	int err;

	peer_ns = peer_esw->dev->priv.steering->fdb_root_ns;
	ns = esw->dev->priv.steering->fdb_root_ns;

	if (pair) {
		err = mlx5_flow_namespace_set_peer(ns, peer_ns);
		if (err)
			return err;

		err = mlx5_flow_namespace_set_peer(peer_ns, ns);
		if (err) {
			mlx5_flow_namespace_set_peer(ns, NULL);
			return err;
		}
	} else {
		mlx5_flow_namespace_set_peer(ns, NULL);
		mlx5_flow_namespace_set_peer(peer_ns, NULL);
	}

	return 0;
}

static int mlx5_esw_offloads_devcom_event(int event,
					  void *my_data,
					  void *event_data)
{
	struct mlx5_eswitch *esw = my_data;
	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
	struct mlx5_eswitch *peer_esw = event_data;
	int err;

	switch (event) {
	case ESW_OFFLOADS_DEVCOM_PAIR:
		if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
		    mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
			break;

		err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true);
		if (err)
			goto err_out;
		err = mlx5_esw_offloads_pair(esw, peer_esw);
		if (err)
			goto err_peer;

		err = mlx5_esw_offloads_pair(peer_esw, esw);
		if (err)
			goto err_pair;

		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true);
		break;

	case ESW_OFFLOADS_DEVCOM_UNPAIR:
		if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
			break;

		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
		mlx5_esw_offloads_unpair(peer_esw);
		mlx5_esw_offloads_unpair(esw);
		mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
		break;
	}

	return 0;

err_pair:
	mlx5_esw_offloads_unpair(esw);
err_peer:
	mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
err_out:
	mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
		      event, err);
	return err;
}

static void esw_offloads_devcom_init(struct mlx5_eswitch *esw)
{
	struct mlx5_devcom *devcom = esw->dev->priv.devcom;

	INIT_LIST_HEAD(&esw->offloads.peer_flows);
	mutex_init(&esw->offloads.peer_mutex);

	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
		return;

	mlx5_devcom_register_component(devcom,
				       MLX5_DEVCOM_ESW_OFFLOADS,
				       mlx5_esw_offloads_devcom_event,
				       esw);

	mlx5_devcom_send_event(devcom,
			       MLX5_DEVCOM_ESW_OFFLOADS,
			       ESW_OFFLOADS_DEVCOM_PAIR, esw);
}

static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
{
	struct mlx5_devcom *devcom = esw->dev->priv.devcom;

	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
		return;

	mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
			       ESW_OFFLOADS_DEVCOM_UNPAIR, esw);

	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
}

static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
					     struct mlx5_vport *vport)
{
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_spec *spec;
	int err = 0;

	/* For prio tag mode, there is only 1 FTEs:
	 * 1) Untagged packets - push prio tag VLAN and modify metadata if
	 * required, allow
	 * Unmatched traffic is allowed by default
	 */
	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec)
		return -ENOMEM;

	/* Untagged packets - push prio tag VLAN, allow */
	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
	MLX5_SET(fte_match_param, spec->match_value, outer_headers.cvlan_tag, 0);
	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
	flow_act.vlan[0].ethtype = ETH_P_8021Q;
	flow_act.vlan[0].vid = 0;
	flow_act.vlan[0].prio = 0;

	if (vport->ingress.offloads.modify_metadata_rule) {
		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
		flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
	}

	vport->ingress.allow_rule =
		mlx5_add_flow_rules(vport->ingress.acl, spec,
				    &flow_act, NULL, 0);
	if (IS_ERR(vport->ingress.allow_rule)) {
		err = PTR_ERR(vport->ingress.allow_rule);
		esw_warn(esw->dev,
			 "vport[%d] configure ingress untagged allow rule, err(%d)\n",
			 vport->vport, err);
		vport->ingress.allow_rule = NULL;
	}

	kvfree(spec);
	return err;
}

static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
						     struct mlx5_vport *vport)
{
	u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
	static const struct mlx5_flow_spec spec = {};
	struct mlx5_flow_act flow_act = {};
	int err = 0;

	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
	MLX5_SET(set_action_in, action, data,
		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));

	vport->ingress.offloads.modify_metadata =
		mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
					 1, action);
	if (IS_ERR(vport->ingress.offloads.modify_metadata)) {
		err = PTR_ERR(vport->ingress.offloads.modify_metadata);
		esw_warn(esw->dev,
			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
			 vport->vport, err);
		return err;
	}

	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
	flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
	vport->ingress.offloads.modify_metadata_rule =
				mlx5_add_flow_rules(vport->ingress.acl,
						    &spec, &flow_act, NULL, 0);
	if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) {
		err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule);
		esw_warn(esw->dev,
			 "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
			 vport->vport, err);
		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
		vport->ingress.offloads.modify_metadata_rule = NULL;
	}
	return err;
}

static void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
						      struct mlx5_vport *vport)
{
	if (vport->ingress.offloads.modify_metadata_rule) {
		mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule);
		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);

		vport->ingress.offloads.modify_metadata_rule = NULL;
	}
}

static int esw_vport_create_ingress_acl_group(struct mlx5_eswitch *esw,
					      struct mlx5_vport *vport)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_flow_group *g;
	void *match_criteria;
	u32 *flow_group_in;
	u32 flow_index = 0;
	int ret = 0;

	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
	if (!flow_group_in)
		return -ENOMEM;

	if (esw_check_ingress_prio_tag_enabled(esw, vport)) {
		/* This group is to hold FTE to match untagged packets when prio_tag
		 * is enabled.
		 */
		memset(flow_group_in, 0, inlen);

		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
					      flow_group_in, match_criteria);
		MLX5_SET(create_flow_group_in, flow_group_in,
			 match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
		MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);

		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
		if (IS_ERR(g)) {
			ret = PTR_ERR(g);
			esw_warn(esw->dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
				 vport->vport, ret);
			goto prio_tag_err;
		}
		vport->ingress.offloads.metadata_prio_tag_grp = g;
		flow_index++;
	}

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		/* This group holds an FTE with no matches for add metadata for
		 * tagged packets, if prio-tag is enabled (as a fallthrough),
		 * or all traffic in case prio-tag is disabled.
		 */
		memset(flow_group_in, 0, inlen);
		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);

		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
		if (IS_ERR(g)) {
			ret = PTR_ERR(g);
			esw_warn(esw->dev, "vport[%d] ingress create drop flow group, err(%d)\n",
				 vport->vport, ret);
			goto metadata_err;
		}
		vport->ingress.offloads.metadata_allmatch_grp = g;
	}

	kvfree(flow_group_in);
	return 0;

metadata_err:
	if (!IS_ERR_OR_NULL(vport->ingress.offloads.metadata_prio_tag_grp)) {
		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
	}
prio_tag_err:
	kvfree(flow_group_in);
	return ret;
}

static void esw_vport_destroy_ingress_acl_group(struct mlx5_vport *vport)
{
	if (vport->ingress.offloads.metadata_allmatch_grp) {
		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_allmatch_grp);
		vport->ingress.offloads.metadata_allmatch_grp = NULL;
	}

	if (vport->ingress.offloads.metadata_prio_tag_grp) {
		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
	}
}

static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
				    struct mlx5_vport *vport)
{
	int num_ftes = 0;
	int err;

	if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
	    !esw_check_ingress_prio_tag_enabled(esw, vport))
		return 0;

	esw_vport_cleanup_ingress_rules(esw, vport);

	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
		num_ftes++;
	if (esw_check_ingress_prio_tag_enabled(esw, vport))
		num_ftes++;

	err = esw_vport_create_ingress_acl_table(esw, vport, num_ftes);
	if (err) {
		esw_warn(esw->dev,
			 "failed to enable ingress acl (%d) on vport[%d]\n",
			 err, vport->vport);
		return err;
	}

	err = esw_vport_create_ingress_acl_group(esw, vport);
	if (err)
		goto group_err;

	esw_debug(esw->dev,
		  "vport[%d] configure ingress rules\n", vport->vport);

	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
		err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
		if (err)
			goto metadata_err;
	}

	if (esw_check_ingress_prio_tag_enabled(esw, vport)) {
		err = esw_vport_ingress_prio_tag_config(esw, vport);
		if (err)
			goto prio_tag_err;
	}
	return 0;

prio_tag_err:
	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
metadata_err:
	esw_vport_destroy_ingress_acl_group(vport);
group_err:
	esw_vport_destroy_ingress_acl_table(vport);
	return err;
}

static int esw_vport_egress_config(struct mlx5_eswitch *esw,
				   struct mlx5_vport *vport)
{
	int err;

	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
		return 0;

	esw_vport_cleanup_egress_rules(esw, vport);

	err = esw_vport_enable_egress_acl(esw, vport);
	if (err)
		return err;

	/* For prio tag mode, there is only 1 FTEs:
	 * 1) prio tag packets - pop the prio tag VLAN, allow
	 * Unmatched traffic is allowed by default
	 */
	esw_debug(esw->dev,
		  "vport[%d] configure prio tag egress rules\n", vport->vport);

	/* prio tag vlan rule - pop it so VF receives untagged packets */
	err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, 0,
						    MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
						    MLX5_FLOW_CONTEXT_ACTION_ALLOW);
	if (err)
		esw_vport_disable_egress_acl(esw, vport);

	return err;
}

static bool
esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
{
	if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
		return false;

	if (!(MLX5_CAP_ESW_FLOWTABLE(esw->dev, fdb_to_vport_reg_c_id) &
	      MLX5_FDB_TO_VPORT_REG_C_0))
		return false;

	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
		return false;

	if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
	    mlx5_ecpf_vport_exists(esw->dev))
		return false;

	return true;
}

int
esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
				     struct mlx5_vport *vport)
{
	int err;

	err = esw_vport_ingress_config(esw, vport);
	if (err)
		return err;

	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
		err = esw_vport_egress_config(esw, vport);
		if (err) {
			esw_vport_cleanup_ingress_rules(esw, vport);
			esw_vport_del_ingress_acl_modify_metadata(esw, vport);
			esw_vport_destroy_ingress_acl_group(vport);
			esw_vport_destroy_ingress_acl_table(vport);
		}
	}
	return err;
}

void
esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
				      struct mlx5_vport *vport)
{
	esw_vport_disable_egress_acl(esw, vport);
	esw_vport_cleanup_ingress_rules(esw, vport);
	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
	esw_vport_destroy_ingress_acl_group(vport);
	esw_vport_destroy_ingress_acl_table(vport);
}

static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
{
	struct mlx5_vport *vport;
	int err;

	if (esw_check_vport_match_metadata_supported(esw))
		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;

	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
	err = esw_vport_create_offloads_acl_tables(esw, vport);
	if (err)
		esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
	return err;
}

static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
{
	struct mlx5_vport *vport;

	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
	esw_vport_destroy_offloads_acl_tables(esw, vport);
	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
}

static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
{
	int num_vfs = esw->esw_funcs.num_vfs;
	int total_vports;
	int err;

	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
		total_vports = esw->total_vports;
	else
		total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);

	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);

	err = esw_create_uplink_offloads_acl_tables(esw);
	if (err)
		return err;

	err = esw_create_offloads_fdb_tables(esw, total_vports);
	if (err)
		goto create_fdb_err;

	err = esw_create_offloads_table(esw, total_vports);
	if (err)
		goto create_ft_err;

	err = esw_create_vport_rx_group(esw, total_vports);
	if (err)
		goto create_fg_err;

	return 0;

create_fg_err:
	esw_destroy_offloads_table(esw);

create_ft_err:
	esw_destroy_offloads_fdb_tables(esw);

create_fdb_err:
	esw_destroy_uplink_offloads_acl_tables(esw);

	return err;
}

static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
{
	esw_destroy_vport_rx_group(esw);
	esw_destroy_offloads_table(esw);
	esw_destroy_offloads_fdb_tables(esw);
	esw_destroy_uplink_offloads_acl_tables(esw);
}

static void
esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
{
	bool host_pf_disabled;
	u16 new_num_vfs;

	new_num_vfs = MLX5_GET(query_esw_functions_out, out,
			       host_params_context.host_num_of_vfs);
	host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
				    host_params_context.host_pf_disabled);

	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
		return;

	/* Number of VFs can only change from "0 to x" or "x to 0". */
	if (esw->esw_funcs.num_vfs > 0) {
		esw_offloads_unload_vf_reps(esw, esw->esw_funcs.num_vfs);
	} else {
		int err;

		err = esw_offloads_load_vf_reps(esw, new_num_vfs);
		if (err)
			return;
	}
	esw->esw_funcs.num_vfs = new_num_vfs;
}

static void esw_functions_changed_event_handler(struct work_struct *work)
{
	struct mlx5_host_work *host_work;
	struct mlx5_eswitch *esw;
	const u32 *out;

	host_work = container_of(work, struct mlx5_host_work, work);
	esw = host_work->esw;

	out = mlx5_esw_query_functions(esw->dev);
	if (IS_ERR(out))
		goto out;

	esw_vfs_changed_event_handler(esw, out);
	kvfree(out);
out:
	kfree(host_work);
}

int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data)
{
	struct mlx5_esw_functions *esw_funcs;
	struct mlx5_host_work *host_work;
	struct mlx5_eswitch *esw;

	host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
	if (!host_work)
		return NOTIFY_DONE;

	esw_funcs = mlx5_nb_cof(nb, struct mlx5_esw_functions, nb);
	esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);

	host_work->esw = esw;

	INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
	queue_work(esw->work_queue, &host_work->work);

	return NOTIFY_OK;
}

int esw_offloads_enable(struct mlx5_eswitch *esw)
{
	int err;

	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
	else
		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;

	mlx5_rdma_enable_roce(esw->dev);
	err = esw_offloads_steering_init(esw);
	if (err)
		goto err_steering_init;

	err = esw_set_passing_vport_metadata(esw, true);
	if (err)
		goto err_vport_metadata;

	err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
	if (err)
		goto err_vports;

	err = esw_offloads_load_all_reps(esw);
	if (err)
		goto err_reps;

	esw_offloads_devcom_init(esw);
	mutex_init(&esw->offloads.termtbl_mutex);

	return 0;

err_reps:
	mlx5_eswitch_disable_pf_vf_vports(esw);
err_vports:
	esw_set_passing_vport_metadata(esw, false);
err_vport_metadata:
	esw_offloads_steering_cleanup(esw);
err_steering_init:
	mlx5_rdma_disable_roce(esw->dev);
	return err;
}

static int esw_offloads_stop(struct mlx5_eswitch *esw,
			     struct netlink_ext_ack *extack)
{
	int err, err1;

	mlx5_eswitch_disable(esw, false);
	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
		if (err1) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Failed setting eswitch back to offloads");
		}
	}

	return err;
}

void esw_offloads_disable(struct mlx5_eswitch *esw)
{
	esw_offloads_devcom_cleanup(esw);
	esw_offloads_unload_all_reps(esw);
	mlx5_eswitch_disable_pf_vf_vports(esw);
	esw_set_passing_vport_metadata(esw, false);
	esw_offloads_steering_cleanup(esw);
	mlx5_rdma_disable_roce(esw->dev);
	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}

static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
{
	switch (mode) {
	case DEVLINK_ESWITCH_MODE_LEGACY:
		*mlx5_mode = MLX5_ESWITCH_LEGACY;
		break;
	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
		*mlx5_mode = MLX5_ESWITCH_OFFLOADS;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
{
	switch (mlx5_mode) {
	case MLX5_ESWITCH_LEGACY:
		*mode = DEVLINK_ESWITCH_MODE_LEGACY;
		break;
	case MLX5_ESWITCH_OFFLOADS:
		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int esw_inline_mode_from_devlink(u8 mode, u8 *mlx5_mode)
{
	switch (mode) {
	case DEVLINK_ESWITCH_INLINE_MODE_NONE:
		*mlx5_mode = MLX5_INLINE_MODE_NONE;
		break;
	case DEVLINK_ESWITCH_INLINE_MODE_LINK:
		*mlx5_mode = MLX5_INLINE_MODE_L2;
		break;
	case DEVLINK_ESWITCH_INLINE_MODE_NETWORK:
		*mlx5_mode = MLX5_INLINE_MODE_IP;
		break;
	case DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT:
		*mlx5_mode = MLX5_INLINE_MODE_TCP_UDP;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
{
	switch (mlx5_mode) {
	case MLX5_INLINE_MODE_NONE:
		*mode = DEVLINK_ESWITCH_INLINE_MODE_NONE;
		break;
	case MLX5_INLINE_MODE_L2:
		*mode = DEVLINK_ESWITCH_INLINE_MODE_LINK;
		break;
	case MLX5_INLINE_MODE_IP:
		*mode = DEVLINK_ESWITCH_INLINE_MODE_NETWORK;
		break;
	case MLX5_INLINE_MODE_TCP_UDP:
		*mode = DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int mlx5_devlink_eswitch_check(struct devlink *devlink)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);

	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
		return -EOPNOTSUPP;

	if(!MLX5_ESWITCH_MANAGER(dev))
		return -EPERM;

	if (dev->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
	    !mlx5_core_is_ecpf_esw_manager(dev))
		return -EOPNOTSUPP;

	return 0;
}

int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
				  struct netlink_ext_ack *extack)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	u16 cur_mlx5_mode, mlx5_mode = 0;
	int err;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	cur_mlx5_mode = dev->priv.eswitch->mode;

	if (esw_mode_from_devlink(mode, &mlx5_mode))
		return -EINVAL;

	if (cur_mlx5_mode == mlx5_mode)
		return 0;

	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
		return esw_offloads_start(dev->priv.eswitch, extack);
	else if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
		return esw_offloads_stop(dev->priv.eswitch, extack);
	else
		return -EINVAL;
}

int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	int err;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	return esw_mode_to_devlink(dev->priv.eswitch->mode, mode);
}

int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
					 struct netlink_ext_ack *extack)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	struct mlx5_eswitch *esw = dev->priv.eswitch;
	int err, vport, num_vport;
	u8 mlx5_mode;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
			return 0;
		/* fall through */
	case MLX5_CAP_INLINE_MODE_L2:
		NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set");
		return -EOPNOTSUPP;
	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
		break;
	}

	if (atomic64_read(&esw->offloads.num_flows) > 0) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Can't set inline mode when flows are configured");
		return -EOPNOTSUPP;
	}

	err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
	if (err)
		goto out;

	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
		err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
		if (err) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Failed to set min inline on vport");
			goto revert_inline_mode;
		}
	}

	esw->offloads.inline_mode = mlx5_mode;
	return 0;

revert_inline_mode:
	num_vport = --vport;
	mlx5_esw_for_each_host_func_vport_reverse(esw, vport, num_vport)
		mlx5_modify_nic_vport_min_inline(dev,
						 vport,
						 esw->offloads.inline_mode);
out:
	return err;
}

int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	struct mlx5_eswitch *esw = dev->priv.eswitch;
	int err;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
}

int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode)
{
	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
	struct mlx5_core_dev *dev = esw->dev;
	int vport;

	if (!MLX5_CAP_GEN(dev, vport_group_manager))
		return -EOPNOTSUPP;

	if (esw->mode == MLX5_ESWITCH_NONE)
		return -EOPNOTSUPP;

	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
		mlx5_mode = MLX5_INLINE_MODE_NONE;
		goto out;
	case MLX5_CAP_INLINE_MODE_L2:
		mlx5_mode = MLX5_INLINE_MODE_L2;
		goto out;
	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
		goto query_vports;
	}

query_vports:
	mlx5_query_nic_vport_min_inline(dev, esw->first_host_vport, &prev_mlx5_mode);
	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
		if (prev_mlx5_mode != mlx5_mode)
			return -EINVAL;
		prev_mlx5_mode = mlx5_mode;
	}

out:
	*mode = mlx5_mode;
	return 0;
}

int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
					enum devlink_eswitch_encap_mode encap,
					struct netlink_ext_ack *extack)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	struct mlx5_eswitch *esw = dev->priv.eswitch;
	int err;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE &&
	    (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) ||
	     !MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)))
		return -EOPNOTSUPP;

	if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
		return -EOPNOTSUPP;

	if (esw->mode == MLX5_ESWITCH_LEGACY) {
		esw->offloads.encap = encap;
		return 0;
	}

	if (esw->offloads.encap == encap)
		return 0;

	if (atomic64_read(&esw->offloads.num_flows) > 0) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Can't set encapsulation when flows are configured");
		return -EOPNOTSUPP;
	}

	esw_destroy_offloads_fdb_tables(esw);

	esw->offloads.encap = encap;

	err = esw_create_offloads_fdb_tables(esw, esw->nvports);

	if (err) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Failed re-creating fast FDB table");
		esw->offloads.encap = !encap;
		(void)esw_create_offloads_fdb_tables(esw, esw->nvports);
	}

	return err;
}

int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
					enum devlink_eswitch_encap_mode *encap)
{
	struct mlx5_core_dev *dev = devlink_priv(devlink);
	struct mlx5_eswitch *esw = dev->priv.eswitch;
	int err;

	err = mlx5_devlink_eswitch_check(devlink);
	if (err)
		return err;

	*encap = esw->offloads.encap;
	return 0;
}

void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
				      const struct mlx5_eswitch_rep_ops *ops,
				      u8 rep_type)
{
	struct mlx5_eswitch_rep_data *rep_data;
	struct mlx5_eswitch_rep *rep;
	int i;

	esw->offloads.rep_ops[rep_type] = ops;
	mlx5_esw_for_all_reps(esw, i, rep) {
		rep_data = &rep->rep_data[rep_type];
		atomic_set(&rep_data->state, REP_REGISTERED);
	}
}
EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);

void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;
	int i;

	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
		__unload_reps_all_vport(esw, rep_type);

	mlx5_esw_for_all_reps(esw, i, rep)
		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
}
EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);

void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;

	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
	return rep->rep_data[rep_type].priv;
}

void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
				 u16 vport,
				 u8 rep_type)
{
	struct mlx5_eswitch_rep *rep;

	rep = mlx5_eswitch_get_rep(esw, vport);

	if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED &&
	    esw->offloads.rep_ops[rep_type]->get_proto_dev)
		return esw->offloads.rep_ops[rep_type]->get_proto_dev(rep);
	return NULL;
}
EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);

void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
{
	return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
}
EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);

struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
						u16 vport)
{
	return mlx5_eswitch_get_rep(esw, vport);
}
EXPORT_SYMBOL(mlx5_eswitch_vport_rep);

bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
{
	return vport_num >= MLX5_VPORT_FIRST_VF &&
	       vport_num <= esw->dev->priv.sriov.max_vfs;
}

bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
{
	return !!(esw->flags & MLX5_ESWITCH_VPORT_MATCH_METADATA);
}
EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);

u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
					      u16 vport_num)
{
	return ((MLX5_CAP_GEN(esw->dev, vhca_id) & 0xffff) << 16) | vport_num;
}
EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);