eswitch.c

/*
 * Copyright (c) 2015, 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 "lib/eq.h"
#include "eswitch.h"
#include "fs_core.h"
#include "ecpf.h"

enum {
	MLX5_ACTION_NONE = 0,
	MLX5_ACTION_ADD  = 1,
	MLX5_ACTION_DEL  = 2,
};

/* Vport UC/MC hash node */
struct vport_addr {
	struct l2addr_node     node;
	u8                     action;
	u16                    vport;
	struct mlx5_flow_handle *flow_rule;
	bool mpfs; /* UC MAC was added to MPFs */
	/* A flag indicating that mac was added due to mc promiscuous vport */
	bool mc_promisc;
};

enum {
	UC_ADDR_CHANGE = BIT(0),
	MC_ADDR_CHANGE = BIT(1),
	PROMISC_CHANGE = BIT(3),
};

static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw);
static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw);

/* Vport context events */
#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
			    MC_ADDR_CHANGE | \
			    PROMISC_CHANGE)

/* The vport getter/iterator are only valid after esw->total_vports
 * and vport->vport are initialized in mlx5_eswitch_init.
 */
#define mlx5_esw_for_all_vports(esw, i, vport)			\
	for ((i) = MLX5_VPORT_PF;				\
	     (vport) = &(esw)->vports[i],			\
	     (i) < (esw)->total_vports; (i)++)

#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
	for ((i) = MLX5_VPORT_FIRST_VF;				\
	     (vport) = &(esw)->vports[i],			\
	     (i) <= (nvfs); (i)++)

static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw,
						 u16 vport_num)
{
	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);

	WARN_ON(idx > esw->total_vports - 1);
	return &esw->vports[idx];
}

static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
					u32 events_mask)
{
	int in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)]   = {0};
	int out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)] = {0};
	void *nic_vport_ctx;

	MLX5_SET(modify_nic_vport_context_in, in,
		 opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
	MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1);
	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
	if (vport)
		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
				     in, nic_vport_context);

	MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1);

	if (events_mask & UC_ADDR_CHANGE)
		MLX5_SET(nic_vport_context, nic_vport_ctx,
			 event_on_uc_address_change, 1);
	if (events_mask & MC_ADDR_CHANGE)
		MLX5_SET(nic_vport_context, nic_vport_ctx,
			 event_on_mc_address_change, 1);
	if (events_mask & PROMISC_CHANGE)
		MLX5_SET(nic_vport_context, nic_vport_ctx,
			 event_on_promisc_change, 1);

	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}

/* E-Switch vport context HW commands */
static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
					void *in, int inlen)
{
	u32 out[MLX5_ST_SZ_DW(modify_esw_vport_context_out)] = {0};

	MLX5_SET(modify_esw_vport_context_in, in, opcode,
		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
	if (vport)
		MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
}

static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
				  u16 vlan, u8 qos, u8 set_flags)
{
	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};

	if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) ||
	    !MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
		return -EOPNOTSUPP;

	esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%x\n",
		  vport, vlan, qos, set_flags);

	if (set_flags & SET_VLAN_STRIP)
		MLX5_SET(modify_esw_vport_context_in, in,
			 esw_vport_context.vport_cvlan_strip, 1);

	if (set_flags & SET_VLAN_INSERT) {
		/* insert only if no vlan in packet */
		MLX5_SET(modify_esw_vport_context_in, in,
			 esw_vport_context.vport_cvlan_insert, 1);

		MLX5_SET(modify_esw_vport_context_in, in,
			 esw_vport_context.cvlan_pcp, qos);
		MLX5_SET(modify_esw_vport_context_in, in,
			 esw_vport_context.cvlan_id, vlan);
	}

	MLX5_SET(modify_esw_vport_context_in, in,
		 field_select.vport_cvlan_strip, 1);
	MLX5_SET(modify_esw_vport_context_in, in,
		 field_select.vport_cvlan_insert, 1);

	return modify_esw_vport_context_cmd(dev, vport, in, sizeof(in));
}

/* E-Switch FDB */
static struct mlx5_flow_handle *
__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
			 u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
{
	int match_header = (is_zero_ether_addr(mac_c) ? 0 :
			    MLX5_MATCH_OUTER_HEADERS);
	struct mlx5_flow_handle *flow_rule = NULL;
	struct mlx5_flow_act flow_act = {0};
	struct mlx5_flow_destination dest = {};
	struct mlx5_flow_spec *spec;
	void *mv_misc = NULL;
	void *mc_misc = NULL;
	u8 *dmac_v = NULL;
	u8 *dmac_c = NULL;

	if (rx_rule)
		match_header |= MLX5_MATCH_MISC_PARAMETERS;

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

	dmac_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
			      outer_headers.dmac_47_16);
	dmac_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
			      outer_headers.dmac_47_16);

	if (match_header & MLX5_MATCH_OUTER_HEADERS) {
		ether_addr_copy(dmac_v, mac_v);
		ether_addr_copy(dmac_c, mac_c);
	}

	if (match_header & MLX5_MATCH_MISC_PARAMETERS) {
		mv_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_value,
					misc_parameters);
		mc_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
					misc_parameters);
		MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK);
		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
	}

	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
	dest.vport.num = vport;

	esw_debug(esw->dev,
		  "\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n",
		  dmac_v, dmac_c, vport);
	spec->match_criteria_enable = match_header;
	flow_act.action =  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	flow_rule =
		mlx5_add_flow_rules(esw->fdb_table.legacy.fdb, spec,
				    &flow_act, &dest, 1);
	if (IS_ERR(flow_rule)) {
		esw_warn(esw->dev,
			 "FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
			 dmac_v, dmac_c, vport, PTR_ERR(flow_rule));
		flow_rule = NULL;
	}

	kvfree(spec);
	return flow_rule;
}

static struct mlx5_flow_handle *
esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport)
{
	u8 mac_c[ETH_ALEN];

	eth_broadcast_addr(mac_c);
	return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac);
}

static struct mlx5_flow_handle *
esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport)
{
	u8 mac_c[ETH_ALEN];
	u8 mac_v[ETH_ALEN];

	eth_zero_addr(mac_c);
	eth_zero_addr(mac_v);
	mac_c[0] = 0x01;
	mac_v[0] = 0x01;
	return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac_v);
}

static struct mlx5_flow_handle *
esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport)
{
	u8 mac_c[ETH_ALEN];
	u8 mac_v[ETH_ALEN];

	eth_zero_addr(mac_c);
	eth_zero_addr(mac_v);
	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
}

enum {
	LEGACY_VEPA_PRIO = 0,
	LEGACY_FDB_PRIO,
};

static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
{
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_namespace *root_ns;
	struct mlx5_flow_table *fdb;
	int err;

	root_ns = mlx5_get_fdb_sub_ns(dev, 0);
	if (!root_ns) {
		esw_warn(dev, "Failed to get FDB flow namespace\n");
		return -EOPNOTSUPP;
	}

	/* num FTE 2, num FG 2 */
	fdb = mlx5_create_auto_grouped_flow_table(root_ns, LEGACY_VEPA_PRIO,
						  2, 2, 0, 0);
	if (IS_ERR(fdb)) {
		err = PTR_ERR(fdb);
		esw_warn(dev, "Failed to create VEPA FDB err %d\n", err);
		return err;
	}
	esw->fdb_table.legacy.vepa_fdb = fdb;

	return 0;
}

static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_flow_table_attr ft_attr = {};
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_namespace *root_ns;
	struct mlx5_flow_table *fdb;
	struct mlx5_flow_group *g;
	void *match_criteria;
	int table_size;
	u32 *flow_group_in;
	u8 *dmac;
	int err = 0;

	esw_debug(dev, "Create FDB log_max_size(%d)\n",
		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));

	root_ns = mlx5_get_fdb_sub_ns(dev, 0);
	if (!root_ns) {
		esw_warn(dev, "Failed to get FDB flow namespace\n");
		return -EOPNOTSUPP;
	}

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

	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
	ft_attr.max_fte = table_size;
	ft_attr.prio = LEGACY_FDB_PRIO;
	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
	if (IS_ERR(fdb)) {
		err = PTR_ERR(fdb);
		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
		goto out;
	}
	esw->fdb_table.legacy.fdb = fdb;

	/* Addresses group : Full match unicast/multicast addresses */
	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);
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
	/* Preserve 2 entries for allmulti and promisc rules*/
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 3);
	eth_broadcast_addr(dmac);
	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create flow group err(%d)\n", err);
		goto out;
	}
	esw->fdb_table.legacy.addr_grp = g;

	/* Allmulti group : One rule that forwards any mcast traffic */
	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
		 MLX5_MATCH_OUTER_HEADERS);
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 2);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 2);
	eth_zero_addr(dmac);
	dmac[0] = 0x01;
	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err);
		goto out;
	}
	esw->fdb_table.legacy.allmulti_grp = g;

	/* Promiscuous group :
	 * One rule that forward all unmatched traffic from previous groups
	 */
	eth_zero_addr(dmac);
	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);
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 1);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1);
	g = mlx5_create_flow_group(fdb, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err);
		goto out;
	}
	esw->fdb_table.legacy.promisc_grp = g;

out:
	if (err)
		esw_destroy_legacy_fdb_table(esw);

	kvfree(flow_group_in);
	return err;
}

static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw)
{
	esw_debug(esw->dev, "Destroy VEPA Table\n");
	if (!esw->fdb_table.legacy.vepa_fdb)
		return;

	mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb);
	esw->fdb_table.legacy.vepa_fdb = NULL;
}

static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
{
	esw_debug(esw->dev, "Destroy FDB Table\n");
	if (!esw->fdb_table.legacy.fdb)
		return;

	if (esw->fdb_table.legacy.promisc_grp)
		mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
	if (esw->fdb_table.legacy.allmulti_grp)
		mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
	if (esw->fdb_table.legacy.addr_grp)
		mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
	mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);

	esw->fdb_table.legacy.fdb = NULL;
	esw->fdb_table.legacy.addr_grp = NULL;
	esw->fdb_table.legacy.allmulti_grp = NULL;
	esw->fdb_table.legacy.promisc_grp = NULL;
}

static int esw_create_legacy_table(struct mlx5_eswitch *esw)
{
	int err;

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

	err = esw_create_legacy_fdb_table(esw);
	if (err)
		esw_destroy_legacy_vepa_table(esw);

	return err;
}

static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
{
	esw_cleanup_vepa_rules(esw);
	esw_destroy_legacy_fdb_table(esw);
	esw_destroy_legacy_vepa_table(esw);
}

/* E-Switch vport UC/MC lists management */
typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
				 struct vport_addr *vaddr);

static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
	u8 *mac = vaddr->node.addr;
	u16 vport = vaddr->vport;
	int err;

	/* Skip mlx5_mpfs_add_mac for eswitch_managers,
	 * it is already done by its netdev in mlx5e_execute_l2_action
	 */
	if (esw->manager_vport == vport)
		goto fdb_add;

	err = mlx5_mpfs_add_mac(esw->dev, mac);
	if (err) {
		esw_warn(esw->dev,
			 "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n",
			 mac, vport, err);
		return err;
	}
	vaddr->mpfs = true;

fdb_add:
	/* SRIOV is enabled: Forward UC MAC to vport */
	if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY)
		vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);

	esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n",
		  vport, mac, vaddr->flow_rule);

	return 0;
}

static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
	u8 *mac = vaddr->node.addr;
	u16 vport = vaddr->vport;
	int err = 0;

	/* Skip mlx5_mpfs_del_mac for eswitch managerss,
	 * it is already done by its netdev in mlx5e_execute_l2_action
	 */
	if (!vaddr->mpfs || esw->manager_vport == vport)
		goto fdb_del;

	err = mlx5_mpfs_del_mac(esw->dev, mac);
	if (err)
		esw_warn(esw->dev,
			 "Failed to del L2 table mac(%pM) for vport(%d), err(%d)\n",
			 mac, vport, err);
	vaddr->mpfs = false;

fdb_del:
	if (vaddr->flow_rule)
		mlx5_del_flow_rules(vaddr->flow_rule);
	vaddr->flow_rule = NULL;

	return 0;
}

static void update_allmulti_vports(struct mlx5_eswitch *esw,
				   struct vport_addr *vaddr,
				   struct esw_mc_addr *esw_mc)
{
	u8 *mac = vaddr->node.addr;
	struct mlx5_vport *vport;
	u16 i, vport_num;

	mlx5_esw_for_all_vports(esw, i, vport) {
		struct hlist_head *vport_hash = vport->mc_list;
		struct vport_addr *iter_vaddr =
					l2addr_hash_find(vport_hash,
							 mac,
							 struct vport_addr);
		vport_num = vport->vport;
		if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
		    vaddr->vport == vport_num)
			continue;
		switch (vaddr->action) {
		case MLX5_ACTION_ADD:
			if (iter_vaddr)
				continue;
			iter_vaddr = l2addr_hash_add(vport_hash, mac,
						     struct vport_addr,
						     GFP_KERNEL);
			if (!iter_vaddr) {
				esw_warn(esw->dev,
					 "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n",
					 mac, vport_num);
				continue;
			}
			iter_vaddr->vport = vport_num;
			iter_vaddr->flow_rule =
					esw_fdb_set_vport_rule(esw,
							       mac,
							       vport_num);
			iter_vaddr->mc_promisc = true;
			break;
		case MLX5_ACTION_DEL:
			if (!iter_vaddr)
				continue;
			mlx5_del_flow_rules(iter_vaddr->flow_rule);
			l2addr_hash_del(iter_vaddr);
			break;
		}
	}
}

static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
	struct hlist_head *hash = esw->mc_table;
	struct esw_mc_addr *esw_mc;
	u8 *mac = vaddr->node.addr;
	u16 vport = vaddr->vport;

	if (!esw->fdb_table.legacy.fdb)
		return 0;

	esw_mc = l2addr_hash_find(hash, mac, struct esw_mc_addr);
	if (esw_mc)
		goto add;

	esw_mc = l2addr_hash_add(hash, mac, struct esw_mc_addr, GFP_KERNEL);
	if (!esw_mc)
		return -ENOMEM;

	esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
		esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK);

	/* Add this multicast mac to all the mc promiscuous vports */
	update_allmulti_vports(esw, vaddr, esw_mc);

add:
	/* If the multicast mac is added as a result of mc promiscuous vport,
	 * don't increment the multicast ref count
	 */
	if (!vaddr->mc_promisc)
		esw_mc->refcnt++;

	/* Forward MC MAC to vport */
	vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
	esw_debug(esw->dev,
		  "\tADDED MC MAC: vport[%d] %pM fr(%p) refcnt(%d) uplinkfr(%p)\n",
		  vport, mac, vaddr->flow_rule,
		  esw_mc->refcnt, esw_mc->uplink_rule);
	return 0;
}

static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
	struct hlist_head *hash = esw->mc_table;
	struct esw_mc_addr *esw_mc;
	u8 *mac = vaddr->node.addr;
	u16 vport = vaddr->vport;

	if (!esw->fdb_table.legacy.fdb)
		return 0;

	esw_mc = l2addr_hash_find(hash, mac, struct esw_mc_addr);
	if (!esw_mc) {
		esw_warn(esw->dev,
			 "Failed to find eswitch MC addr for MAC(%pM) vport(%d)",
			 mac, vport);
		return -EINVAL;
	}
	esw_debug(esw->dev,
		  "\tDELETE MC MAC: vport[%d] %pM fr(%p) refcnt(%d) uplinkfr(%p)\n",
		  vport, mac, vaddr->flow_rule, esw_mc->refcnt,
		  esw_mc->uplink_rule);

	if (vaddr->flow_rule)
		mlx5_del_flow_rules(vaddr->flow_rule);
	vaddr->flow_rule = NULL;

	/* If the multicast mac is added as a result of mc promiscuous vport,
	 * don't decrement the multicast ref count.
	 */
	if (vaddr->mc_promisc || (--esw_mc->refcnt > 0))
		return 0;

	/* Remove this multicast mac from all the mc promiscuous vports */
	update_allmulti_vports(esw, vaddr, esw_mc);

	if (esw_mc->uplink_rule)
		mlx5_del_flow_rules(esw_mc->uplink_rule);

	l2addr_hash_del(esw_mc);
	return 0;
}

/* Apply vport UC/MC list to HW l2 table and FDB table */
static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
				      u16 vport_num, int list_type)
{
	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
	vport_addr_action vport_addr_add;
	vport_addr_action vport_addr_del;
	struct vport_addr *addr;
	struct l2addr_node *node;
	struct hlist_head *hash;
	struct hlist_node *tmp;
	int hi;

	vport_addr_add = is_uc ? esw_add_uc_addr :
				 esw_add_mc_addr;
	vport_addr_del = is_uc ? esw_del_uc_addr :
				 esw_del_mc_addr;

	hash = is_uc ? vport->uc_list : vport->mc_list;
	for_each_l2hash_node(node, tmp, hash, hi) {
		addr = container_of(node, struct vport_addr, node);
		switch (addr->action) {
		case MLX5_ACTION_ADD:
			vport_addr_add(esw, addr);
			addr->action = MLX5_ACTION_NONE;
			break;
		case MLX5_ACTION_DEL:
			vport_addr_del(esw, addr);
			l2addr_hash_del(addr);
			break;
		}
	}
}

/* Sync vport UC/MC list from vport context */
static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
				       u16 vport_num, int list_type)
{
	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
	u8 (*mac_list)[ETH_ALEN];
	struct l2addr_node *node;
	struct vport_addr *addr;
	struct hlist_head *hash;
	struct hlist_node *tmp;
	int size;
	int err;
	int hi;
	int i;

	size = is_uc ? MLX5_MAX_UC_PER_VPORT(esw->dev) :
		       MLX5_MAX_MC_PER_VPORT(esw->dev);

	mac_list = kcalloc(size, ETH_ALEN, GFP_KERNEL);
	if (!mac_list)
		return;

	hash = is_uc ? vport->uc_list : vport->mc_list;

	for_each_l2hash_node(node, tmp, hash, hi) {
		addr = container_of(node, struct vport_addr, node);
		addr->action = MLX5_ACTION_DEL;
	}

	if (!vport->enabled)
		goto out;

	err = mlx5_query_nic_vport_mac_list(esw->dev, vport_num, list_type,
					    mac_list, &size);
	if (err)
		goto out;
	esw_debug(esw->dev, "vport[%d] context update %s list size (%d)\n",
		  vport_num, is_uc ? "UC" : "MC", size);

	for (i = 0; i < size; i++) {
		if (is_uc && !is_valid_ether_addr(mac_list[i]))
			continue;

		if (!is_uc && !is_multicast_ether_addr(mac_list[i]))
			continue;

		addr = l2addr_hash_find(hash, mac_list[i], struct vport_addr);
		if (addr) {
			addr->action = MLX5_ACTION_NONE;
			/* If this mac was previously added because of allmulti
			 * promiscuous rx mode, its now converted to be original
			 * vport mac.
			 */
			if (addr->mc_promisc) {
				struct esw_mc_addr *esw_mc =
					l2addr_hash_find(esw->mc_table,
							 mac_list[i],
							 struct esw_mc_addr);
				if (!esw_mc) {
					esw_warn(esw->dev,
						 "Failed to MAC(%pM) in mcast DB\n",
						 mac_list[i]);
					continue;
				}
				esw_mc->refcnt++;
				addr->mc_promisc = false;
			}
			continue;
		}

		addr = l2addr_hash_add(hash, mac_list[i], struct vport_addr,
				       GFP_KERNEL);
		if (!addr) {
			esw_warn(esw->dev,
				 "Failed to add MAC(%pM) to vport[%d] DB\n",
				 mac_list[i], vport_num);
			continue;
		}
		addr->vport = vport_num;
		addr->action = MLX5_ACTION_ADD;
	}
out:
	kfree(mac_list);
}

/* Sync vport UC/MC list from vport context
 * Must be called after esw_update_vport_addr_list
 */
static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num)
{
	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
	struct l2addr_node *node;
	struct vport_addr *addr;
	struct hlist_head *hash;
	struct hlist_node *tmp;
	int hi;

	hash = vport->mc_list;

	for_each_l2hash_node(node, tmp, esw->mc_table, hi) {
		u8 *mac = node->addr;

		addr = l2addr_hash_find(hash, mac, struct vport_addr);
		if (addr) {
			if (addr->action == MLX5_ACTION_DEL)
				addr->action = MLX5_ACTION_NONE;
			continue;
		}
		addr = l2addr_hash_add(hash, mac, struct vport_addr,
				       GFP_KERNEL);
		if (!addr) {
			esw_warn(esw->dev,
				 "Failed to add allmulti MAC(%pM) to vport[%d] DB\n",
				 mac, vport_num);
			continue;
		}
		addr->vport = vport_num;
		addr->action = MLX5_ACTION_ADD;
		addr->mc_promisc = true;
	}
}

/* Apply vport rx mode to HW FDB table */
static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num,
				    bool promisc, bool mc_promisc)
{
	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
	struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;

	if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
		goto promisc;

	if (mc_promisc) {
		vport->allmulti_rule =
				esw_fdb_set_vport_allmulti_rule(esw, vport_num);
		if (!allmulti_addr->uplink_rule)
			allmulti_addr->uplink_rule =
				esw_fdb_set_vport_allmulti_rule(esw,
								MLX5_VPORT_UPLINK);
		allmulti_addr->refcnt++;
	} else if (vport->allmulti_rule) {
		mlx5_del_flow_rules(vport->allmulti_rule);
		vport->allmulti_rule = NULL;

		if (--allmulti_addr->refcnt > 0)
			goto promisc;

		if (allmulti_addr->uplink_rule)
			mlx5_del_flow_rules(allmulti_addr->uplink_rule);
		allmulti_addr->uplink_rule = NULL;
	}

promisc:
	if (IS_ERR_OR_NULL(vport->promisc_rule) != promisc)
		return;

	if (promisc) {
		vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw,
								     vport_num);
	} else if (vport->promisc_rule) {
		mlx5_del_flow_rules(vport->promisc_rule);
		vport->promisc_rule = NULL;
	}
}

/* Sync vport rx mode from vport context */
static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num)
{
	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
	int promisc_all = 0;
	int promisc_uc = 0;
	int promisc_mc = 0;
	int err;

	err = mlx5_query_nic_vport_promisc(esw->dev,
					   vport_num,
					   &promisc_uc,
					   &promisc_mc,
					   &promisc_all);
	if (err)
		return;
	esw_debug(esw->dev, "vport[%d] context update rx mode promisc_all=%d, all_multi=%d\n",
		  vport_num, promisc_all, promisc_mc);

	if (!vport->info.trusted || !vport->enabled) {
		promisc_uc = 0;
		promisc_mc = 0;
		promisc_all = 0;
	}

	esw_apply_vport_rx_mode(esw, vport_num, promisc_all,
				(promisc_all || promisc_mc));
}

static void esw_vport_change_handle_locked(struct mlx5_vport *vport)
{
	struct mlx5_core_dev *dev = vport->dev;
	struct mlx5_eswitch *esw = dev->priv.eswitch;
	u8 mac[ETH_ALEN];

	mlx5_query_nic_vport_mac_address(dev, vport->vport, mac);
	esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
		  vport->vport, mac);

	if (vport->enabled_events & UC_ADDR_CHANGE) {
		esw_update_vport_addr_list(esw, vport->vport,
					   MLX5_NVPRT_LIST_TYPE_UC);
		esw_apply_vport_addr_list(esw, vport->vport,
					  MLX5_NVPRT_LIST_TYPE_UC);
	}

	if (vport->enabled_events & MC_ADDR_CHANGE) {
		esw_update_vport_addr_list(esw, vport->vport,
					   MLX5_NVPRT_LIST_TYPE_MC);
	}

	if (vport->enabled_events & PROMISC_CHANGE) {
		esw_update_vport_rx_mode(esw, vport->vport);
		if (!IS_ERR_OR_NULL(vport->allmulti_rule))
			esw_update_vport_mc_promisc(esw, vport->vport);
	}

	if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) {
		esw_apply_vport_addr_list(esw, vport->vport,
					  MLX5_NVPRT_LIST_TYPE_MC);
	}

	esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport);
	if (vport->enabled)
		arm_vport_context_events_cmd(dev, vport->vport,
					     vport->enabled_events);
}

static void esw_vport_change_handler(struct work_struct *work)
{
	struct mlx5_vport *vport =
		container_of(work, struct mlx5_vport, vport_change_handler);
	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;

	mutex_lock(&esw->state_lock);
	esw_vport_change_handle_locked(vport);
	mutex_unlock(&esw->state_lock);
}

static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
				       struct mlx5_vport *vport)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_flow_group *vlan_grp = NULL;
	struct mlx5_flow_group *drop_grp = NULL;
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_namespace *root_ns;
	struct mlx5_flow_table *acl;
	void *match_criteria;
	u32 *flow_group_in;
	/* The egress acl table contains 2 rules:
	 * 1)Allow traffic with vlan_tag=vst_vlan_id
	 * 2)Drop all other traffic.
	 */
	int table_size = 2;
	int err = 0;

	if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
		return -EOPNOTSUPP;

	if (!IS_ERR_OR_NULL(vport->egress.acl))
		return 0;

	esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n",
		  vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));

	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
						    vport->vport);
	if (!root_ns) {
		esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
		return -EOPNOTSUPP;
	}

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

	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
	if (IS_ERR(acl)) {
		err = PTR_ERR(acl);
		esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
			 vport->vport, err);
		goto out;
	}

	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);
	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.first_vid);
	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, 0);

	vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
	if (IS_ERR(vlan_grp)) {
		err = PTR_ERR(vlan_grp);
		esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
			 vport->vport, err);
		goto out;
	}

	memset(flow_group_in, 0, inlen);
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
	drop_grp = mlx5_create_flow_group(acl, flow_group_in);
	if (IS_ERR(drop_grp)) {
		err = PTR_ERR(drop_grp);
		esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
			 vport->vport, err);
		goto out;
	}

	vport->egress.acl = acl;
	vport->egress.drop_grp = drop_grp;
	vport->egress.allowed_vlans_grp = vlan_grp;
out:
	kvfree(flow_group_in);
	if (err && !IS_ERR_OR_NULL(vlan_grp))
		mlx5_destroy_flow_group(vlan_grp);
	if (err && !IS_ERR_OR_NULL(acl))
		mlx5_destroy_flow_table(acl);
	return err;
}

static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
					   struct mlx5_vport *vport)
{
	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
		mlx5_del_flow_rules(vport->egress.allowed_vlan);

	if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
		mlx5_del_flow_rules(vport->egress.drop_rule);

	vport->egress.allowed_vlan = NULL;
	vport->egress.drop_rule = NULL;
}

static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
					 struct mlx5_vport *vport)
{
	if (IS_ERR_OR_NULL(vport->egress.acl))
		return;

	esw_debug(esw->dev, "Destroy vport[%d] E-Switch egress ACL\n", vport->vport);

	esw_vport_cleanup_egress_rules(esw, vport);
	mlx5_destroy_flow_group(vport->egress.allowed_vlans_grp);
	mlx5_destroy_flow_group(vport->egress.drop_grp);
	mlx5_destroy_flow_table(vport->egress.acl);
	vport->egress.allowed_vlans_grp = NULL;
	vport->egress.drop_grp = NULL;
	vport->egress.acl = NULL;
}

static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
					struct mlx5_vport *vport)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_core_dev *dev = esw->dev;
	struct mlx5_flow_namespace *root_ns;
	struct mlx5_flow_table *acl;
	struct mlx5_flow_group *g;
	void *match_criteria;
	u32 *flow_group_in;
	/* The ingress acl table contains 4 groups
	 * (2 active rules at the same time -
	 *      1 allow rule from one of the first 3 groups.
	 *      1 drop rule from the last group):
	 * 1)Allow untagged traffic with smac=original mac.
	 * 2)Allow untagged traffic.
	 * 3)Allow traffic with smac=original mac.
	 * 4)Drop all other traffic.
	 */
	int table_size = 4;
	int err = 0;

	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
		return -EOPNOTSUPP;

	if (!IS_ERR_OR_NULL(vport->ingress.acl))
		return 0;

	esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));

	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
						    vport->vport);
	if (!root_ns) {
		esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport);
		return -EOPNOTSUPP;
	}

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

	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
	if (IS_ERR(acl)) {
		err = PTR_ERR(acl);
		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
			 vport->vport, err);
		goto out;
	}
	vport->ingress.acl = acl;

	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);