Merge branch 'mlx5-sriov-updates'

Saeed Mahameed says:

====================
Mellanox 100G ethernet SRIOV Upgrades

This series introduces new features and upgrades for mlx5 etherenet SRIOV,
while the first patch provides a bug fixes for a compilation issue introduced
buy the previous aRFS series for when CONFIG_RFS_ACCEL=y and CONFIG_MLX5_CORE_EN=n.

Changes from V0:
    - 1st patch: Don't add a new Kconfig flag.  Instead, compile out en_arfs.c \
contents when CONFIG_RFS_ACCEL=n

SRIOV upgrades:
    - Use synchronize_irq instead of the vport events spin_lock
    - Fix memory leak in error flow
    - Added full VST support
    - Spoofcheck support
    - Trusted VF promiscuous and allmulti support

VST and Spoofcheck in details:
    - Adding Low level firmware commands support for creating ACLs
     (Access Control Lists) Flow tables.  ACLs are regular flow tables with
     the only exception that they are bound to a specific e-Switch vport (VF)
     and they can be one of two types
        > egress ACL: filters traffic going from e-Switch to VF.
        > ingress ACL: filters traffic going from VF to e-Switch.
    - Ingress/Egress ACLs (per vport) for VF VST mode filtering.
    - Ingress/Egress ACLs (per vport) for VF spoofcheck filtering.
    - Ingress/Egress ACLs (per vport) configuration:
        > Created only when at least one of (VST, spoofcheck) is configured.
	> if (!spoofchk && !vst) allow all traffic.  i.e. no ACLs.
        > if (spoofchk && vst) allow only untagged traffic with smac=original mac \
                sent from the VF.
        > if (spoofchk && !vst) allow only traffic with smac=original mac sent from \
the VF.  > if (!spoofchk && vst) allow only untagged traffic.

Trusted VF promiscuous and allmulti support in details:
    - Added two flow groups for allmulti and promisc VFs to the e-Switch FDB table
        > Allmulti group: One rule that forwards any mcast traffic coming from
                          either uplink or VFs/PF vports.
        > Promisc group: One rule that forwards all unmatched traffic coming from \
                uplink.
    - Add vport context change event handling for promisc and allmulti
      If VF is trusted respect the request and:
        > if allmulti request: add the vport to the allmulti group.
          and to all other L2 mcast address in the FDB table.
        > if promisc request: add the vport to the promisc group.
        > Note: A promisc VF can only see traffic that was not explicitly matched to
                or requested by any other VF.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -6,7 +6,6 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \
 		en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \
-		en_txrx.o en_clock.o vxlan.o en_tc.o
+		en_txrx.o en_clock.o vxlan.o en_tc.o en_arfs.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o
-mlx5_core-$(CONFIG_RFS_ACCEL) +=  en_arfs.o

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

@@ -30,6 +30,8 @@
  * SOFTWARE.
  */
 
+#ifdef CONFIG_RFS_ACCEL
+
 #include <linux/hash.h>
 #include <linux/mlx5/fs.h>
 #include <linux/ip.h>
@@ -747,3 +749,4 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&arfs->arfs_lock);
 	return arfs_rule->filter_id;
 }
+#endif

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

@@ -2438,6 +2438,21 @@ static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos)
 					   vlan, qos);
 }
 
+static int mlx5e_set_vf_spoofchk(struct net_device *dev, int vf, bool setting)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	return mlx5_eswitch_set_vport_spoofchk(mdev->priv.eswitch, vf + 1, setting);
+}
+
+static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
+}
 static int mlx5_vport_link2ifla(u8 esw_link)
 {
 	switch (esw_link) {
@@ -2607,6 +2622,8 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 #endif
 	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
 	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
+	.ndo_set_vf_spoofchk     = mlx5e_set_vf_spoofchk,
+	.ndo_set_vf_trust        = mlx5e_set_vf_trust,
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,

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

@@ -77,16 +77,20 @@ struct vport_addr {
 	u8                     action;
 	u32                    vport;
 	struct mlx5_flow_rule *flow_rule; /* SRIOV only */
+	/* 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),
 };
 
 /* Vport context events */
 #define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
-			    MC_ADDR_CHANGE)
+			    MC_ADDR_CHANGE | \
+			    PROMISC_CHANGE)
 
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
@@ -116,6 +120,9 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 	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);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -323,30 +330,45 @@ static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index)
 
 /* E-Switch FDB */
 static struct mlx5_flow_rule *
-esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
+__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
+			 u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
 {
-	int match_header = MLX5_MATCH_OUTER_HEADERS;
-	struct mlx5_flow_destination dest;
+	int match_header = (is_zero_ether_addr(mac_c) ? 0 :
+			    MLX5_MATCH_OUTER_HEADERS);
 	struct mlx5_flow_rule *flow_rule = NULL;
+	struct mlx5_flow_destination dest;
+	void *mv_misc = NULL;
+	void *mc_misc = NULL;
+	u8 *dmac_v = NULL;
+	u8 *dmac_c = NULL;
 	u32 *match_v;
 	u32 *match_c;
-	u8 *dmac_v;
-	u8 *dmac_c;
 
+	if (rx_rule)
+		match_header |= MLX5_MATCH_MISC_PARAMETERS;
 	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
 	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
 	if (!match_v || !match_c) {
 		pr_warn("FDB: Failed to alloc match parameters\n");
 		goto out;
 	}
+
 	dmac_v = MLX5_ADDR_OF(fte_match_param, match_v,
 			      outer_headers.dmac_47_16);
 	dmac_c = MLX5_ADDR_OF(fte_match_param, match_c,
 			      outer_headers.dmac_47_16);
 
-	ether_addr_copy(dmac_v, mac);
-	/* Match criteria mask */
-	memset(dmac_c, 0xff, 6);
+	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, match_v, misc_parameters);
+		mc_misc  = MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters);
+		MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
+		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
+	}
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest.vport_num = vport;
@@ -373,6 +395,39 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
 	return flow_rule;
 }
 
+static struct mlx5_flow_rule *
+esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 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_rule *
+esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 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_rule *
+esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 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);
+}
+
 static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -407,28 +462,74 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
 		goto out;
 	}
+	esw->fdb_table.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);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1);
+	/* 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_OR_NULL(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create flow group err(%d)\n", err);
 		goto out;
 	}
-
 	esw->fdb_table.addr_grp = g;
-	esw->fdb_table.fdb = fdb;
+
+	/* 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_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err);
+		goto out;
+	}
+	esw->fdb_table.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_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err);
+		goto out;
+	}
+	esw->fdb_table.promisc_grp = g;
+
 out:
+	if (err) {
+		if (!IS_ERR_OR_NULL(esw->fdb_table.allmulti_grp)) {
+			mlx5_destroy_flow_group(esw->fdb_table.allmulti_grp);
+			esw->fdb_table.allmulti_grp = NULL;
+		}
+		if (!IS_ERR_OR_NULL(esw->fdb_table.addr_grp)) {
+			mlx5_destroy_flow_group(esw->fdb_table.addr_grp);
+			esw->fdb_table.addr_grp = NULL;
+		}
+		if (!IS_ERR_OR_NULL(esw->fdb_table.fdb)) {
+			mlx5_destroy_flow_table(esw->fdb_table.fdb);
+			esw->fdb_table.fdb = NULL;
+		}
+	}
+
 	kfree(flow_group_in);
-	if (err && !IS_ERR_OR_NULL(fdb))
-		mlx5_destroy_flow_table(fdb);
 	return err;
 }
 
@@ -438,10 +539,14 @@ static void esw_destroy_fdb_table(struct mlx5_eswitch *esw)
 		return;
 
 	esw_debug(esw->dev, "Destroy FDB Table\n");
+	mlx5_destroy_flow_group(esw->fdb_table.promisc_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.allmulti_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.addr_grp);
 	mlx5_destroy_flow_table(esw->fdb_table.fdb);
 	esw->fdb_table.fdb = NULL;
 	esw->fdb_table.addr_grp = NULL;
+	esw->fdb_table.allmulti_grp = NULL;
+	esw->fdb_table.promisc_grp = NULL;
 }
 
 /* E-Switch vport UC/MC lists management */
@@ -511,6 +616,52 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	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;
+	u32 vport_idx = 0;
+
+	for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
+		struct mlx5_vport *vport = &esw->vports[vport_idx];
+		struct hlist_head *vport_hash = vport->mc_list;
+		struct vport_addr *iter_vaddr =
+					l2addr_hash_find(vport_hash,
+							 mac,
+							 struct vport_addr);
+		if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
+		    vaddr->vport == vport_idx)
+			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_idx);
+				continue;
+			}
+			iter_vaddr->vport = vport_idx;
+			iter_vaddr->flow_rule =
+					esw_fdb_set_vport_rule(esw,
+							       mac,
+							       vport_idx);
+			break;
+		case MLX5_ACTION_DEL:
+			if (!iter_vaddr)
+				continue;
+			mlx5_del_flow_rule(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;
@@ -531,8 +682,17 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 	esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
 		esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT);
+
+	/* 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,
@@ -568,9 +728,15 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 		mlx5_del_flow_rule(vaddr->flow_rule);
 	vaddr->flow_rule = NULL;
 
-	if (--esw_mc->refcnt)
+	/* 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_rule(esw_mc->uplink_rule);
 
@@ -643,10 +809,13 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 		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)
-		return;
+		goto out;
 	esw_debug(esw->dev, "vport[%d] context update %s list size (%d)\n",
 		  vport_num, is_uc ? "UC" : "MC", size);
 
@@ -660,6 +829,24 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 		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;
 		}
 
@@ -674,13 +861,121 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 		addr->vport = vport_num;
 		addr->action = MLX5_ACTION_ADD;
 	}
+out:
 	kfree(mac_list);
 }
 
-static void esw_vport_change_handler(struct work_struct *work)
+/* 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, u32 vport_num)
+{
+	struct mlx5_vport *vport = &esw->vports[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, u32 vport_num,
+				    bool promisc, bool mc_promisc)
+{
+	struct esw_mc_addr *allmulti_addr = esw->mc_promisc;
+	struct mlx5_vport *vport = &esw->vports[vport_num];
+
+	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,
+								UPLINK_VPORT);
+		allmulti_addr->refcnt++;
+	} else if (vport->allmulti_rule) {
+		mlx5_del_flow_rule(vport->allmulti_rule);
+		vport->allmulti_rule = NULL;
+
+		if (--allmulti_addr->refcnt > 0)
+			goto promisc;
+
+		if (allmulti_addr->uplink_rule)
+			mlx5_del_flow_rule(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_rule(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, u32 vport_num)
+{
+	struct mlx5_vport *vport = &esw->vports[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->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_vport *vport =
-		container_of(work, struct mlx5_vport, vport_change_handler);
 	struct mlx5_core_dev *dev = vport->dev;
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	u8 mac[ETH_ALEN];
@@ -699,6 +994,15 @@ static void esw_vport_change_handler(struct work_struct *work)
 	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);
 	}
@@ -709,15 +1013,477 @@ static void esw_vport_change_handler(struct work_struct *work)
 					     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 void 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) ||
+	    !IS_ERR_OR_NULL(vport->egress.acl))
+		return;
+
+	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_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
+		return;
+	}
+
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return;
+
+	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
+	if (IS_ERR_OR_NULL(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.vlan_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_OR_NULL(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_OR_NULL(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:
+	kfree(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);
+}
+
+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_rule(vport->egress.allowed_vlan);
+
+	if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
+		mlx5_del_flow_rule(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 void 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) ||
+	    !IS_ERR_OR_NULL(vport->ingress.acl))
+		return;
+
+	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_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
+		return;
+	}
+
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return;
+
+	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
+	if (IS_ERR_OR_NULL(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.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
+	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);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+	vport->ingress.allow_untagged_spoofchk_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	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.vlan_tag);
+	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);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+	vport->ingress.allow_untagged_only_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	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.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+	vport->ingress.allow_spoofchk_only_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR_OR_NULL(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+	vport->ingress.drop_grp = g;
+
+out:
+	if (err) {
+		if (!IS_ERR_OR_NULL(vport->ingress.allow_spoofchk_only_grp))
+			mlx5_destroy_flow_group(
+					vport->ingress.allow_spoofchk_only_grp);
+		if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_only_grp))
+			mlx5_destroy_flow_group(
+					vport->ingress.allow_untagged_only_grp);
+		if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_spoofchk_grp))
+			mlx5_destroy_flow_group(
+				vport->ingress.allow_untagged_spoofchk_grp);
+		if (!IS_ERR_OR_NULL(vport->ingress.acl))
+			mlx5_destroy_flow_table(vport->ingress.acl);
+	}
+
+	kfree(flow_group_in);
+}
+
+static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
+					    struct mlx5_vport *vport)
+{
+	if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
+		mlx5_del_flow_rule(vport->ingress.drop_rule);
+
+	if (!IS_ERR_OR_NULL(vport->ingress.allow_rule))
+		mlx5_del_flow_rule(vport->ingress.allow_rule);
+
+	vport->ingress.drop_rule = NULL;
+	vport->ingress.allow_rule = NULL;
+}
+
+static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
+					  struct mlx5_vport *vport)
+{
+	if (IS_ERR_OR_NULL(vport->ingress.acl))
+		return;
+
+	esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport);
+
+	esw_vport_cleanup_ingress_rules(esw, vport);
+	mlx5_destroy_flow_group(vport->ingress.allow_spoofchk_only_grp);
+	mlx5_destroy_flow_group(vport->ingress.allow_untagged_only_grp);
+	mlx5_destroy_flow_group(vport->ingress.allow_untagged_spoofchk_grp);
+	mlx5_destroy_flow_group(vport->ingress.drop_grp);
+	mlx5_destroy_flow_table(vport->ingress.acl);
+	vport->ingress.acl = NULL;
+	vport->ingress.drop_grp = NULL;
+	vport->ingress.allow_spoofchk_only_grp = NULL;
+	vport->ingress.allow_untagged_only_grp = NULL;
+	vport->ingress.allow_untagged_spoofchk_grp = NULL;
+}
+
+static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport)
+{
+	u8 smac[ETH_ALEN];
+	u32 *match_v;
+	u32 *match_c;
+	int err = 0;
+	u8 *smac_v;
+
+	if (vport->spoofchk) {
+		err = mlx5_query_nic_vport_mac_address(esw->dev, vport->vport, smac);
+		if (err) {
+			esw_warn(esw->dev,
+				 "vport[%d] configure ingress rules failed, query smac failed, err(%d)\n",
+				 vport->vport, err);
+			return err;
+		}
+
+		if (!is_valid_ether_addr(smac)) {
+			mlx5_core_warn(esw->dev,
+				       "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
+				       vport->vport);
+			return -EPERM;
+		}
+	}
+
+	esw_vport_cleanup_ingress_rules(esw, vport);
+
+	if (!vport->vlan && !vport->qos && !vport->spoofchk) {
+		esw_vport_disable_ingress_acl(esw, vport);
+		return 0;
+	}
+
+	esw_vport_enable_ingress_acl(esw, vport);
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
+		  vport->vport, vport->vlan, vport->qos);
+
+	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	if (!match_v || !match_c) {
+		err = -ENOMEM;
+		esw_warn(esw->dev, "vport[%d] configure ingress rules failed, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+
+	if (vport->vlan || vport->qos)
+		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.vlan_tag);
+
+	if (vport->spoofchk) {
+		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.smac_47_16);
+		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.smac_15_0);
+		smac_v = MLX5_ADDR_OF(fte_match_param,
+				      match_v,
+				      outer_headers.smac_47_16);
+		ether_addr_copy(smac_v, smac);
+	}
+
+	vport->ingress.allow_rule =
+		mlx5_add_flow_rule(vport->ingress.acl,
+				   MLX5_MATCH_OUTER_HEADERS,
+				   match_c,
+				   match_v,
+				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
+				   0, NULL);
+	if (IS_ERR_OR_NULL(vport->ingress.allow_rule)) {
+		err = PTR_ERR(vport->ingress.allow_rule);
+		pr_warn("vport[%d] configure ingress allow rule, err(%d)\n",
+			vport->vport, err);
+		vport->ingress.allow_rule = NULL;
+		goto out;
+	}
+
+	memset(match_c, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	memset(match_v, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	vport->ingress.drop_rule =
+		mlx5_add_flow_rule(vport->ingress.acl,
+				   0,
+				   match_c,
+				   match_v,
+				   MLX5_FLOW_CONTEXT_ACTION_DROP,
+				   0, NULL);
+	if (IS_ERR_OR_NULL(vport->ingress.drop_rule)) {
+		err = PTR_ERR(vport->ingress.drop_rule);
+		pr_warn("vport[%d] configure ingress drop rule, err(%d)\n",
+			vport->vport, err);
+		vport->ingress.drop_rule = NULL;
+		goto out;
+	}
+
+out:
+	if (err)
+		esw_vport_cleanup_ingress_rules(esw, vport);
+
+	kfree(match_v);
+	kfree(match_c);
+	return err;
+}
+
+static int esw_vport_egress_config(struct mlx5_eswitch *esw,
+				   struct mlx5_vport *vport)
+{
+	u32 *match_v;
+	u32 *match_c;
+	int err = 0;
+
+	esw_vport_cleanup_egress_rules(esw, vport);
+
+	if (!vport->vlan && !vport->qos) {
+		esw_vport_disable_egress_acl(esw, vport);
+		return 0;
+	}
+
+	esw_vport_enable_egress_acl(esw, vport);
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
+		  vport->vport, vport->vlan, vport->qos);
+
+	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	if (!match_v || !match_c) {
+		err = -ENOMEM;
+		esw_warn(esw->dev, "vport[%d] configure egress rules failed, err(%d)\n",
+			 vport->vport, err);
+		goto out;
+	}
+
+	/* Allowed vlan rule */
+	MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match_v, outer_headers.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.first_vid);
+	MLX5_SET(fte_match_param, match_v, outer_headers.first_vid, vport->vlan);
+
+	vport->egress.allowed_vlan =
+		mlx5_add_flow_rule(vport->egress.acl,
+				   MLX5_MATCH_OUTER_HEADERS,
+				   match_c,
+				   match_v,
+				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
+				   0, NULL);
+	if (IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
+		err = PTR_ERR(vport->egress.allowed_vlan);
+		pr_warn("vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
+			vport->vport, err);
+		vport->egress.allowed_vlan = NULL;
+		goto out;
+	}
+
+	/* Drop others rule (star rule) */
+	memset(match_c, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	memset(match_v, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	vport->egress.drop_rule =
+		mlx5_add_flow_rule(vport->egress.acl,
+				   0,
+				   match_c,
+				   match_v,
+				   MLX5_FLOW_CONTEXT_ACTION_DROP,
+				   0, NULL);
+	if (IS_ERR_OR_NULL(vport->egress.drop_rule)) {
+		err = PTR_ERR(vport->egress.drop_rule);
+		pr_warn("vport[%d] configure egress drop rule failed, err(%d)\n",
+			vport->vport, err);
+		vport->egress.drop_rule = NULL;
+	}
+out:
+	kfree(match_v);
+	kfree(match_c);
+	return err;
+}
+
 static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 			     int enable_events)
 {
 	struct mlx5_vport *vport = &esw->vports[vport_num];
-	unsigned long flags;
 
+	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
 
 	esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
+
+	if (vport_num) { /* Only VFs need ACLs for VST and spoofchk filtering */
+		esw_vport_ingress_config(esw, vport);
+		esw_vport_egress_config(esw, vport);
+	}
+
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
 				      vport_num,
@@ -725,53 +1491,32 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 
 	/* Sync with current vport context */
 	vport->enabled_events = enable_events;
-	esw_vport_change_handler(&vport->vport_change_handler);
+	esw_vport_change_handle_locked(vport);
 
-	spin_lock_irqsave(&vport->lock, flags);
 	vport->enabled = true;
-	spin_unlock_irqrestore(&vport->lock, flags);
+
+	/* only PF is trusted by default */
+	vport->trusted = (vport_num) ? false : true;
 
 	arm_vport_context_events_cmd(esw->dev, vport_num, enable_events);
 
 	esw->enabled_vports++;
 	esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
-}
-
-static void esw_cleanup_vport(struct mlx5_eswitch *esw, u16 vport_num)
-{
-	struct mlx5_vport *vport = &esw->vports[vport_num];
-	struct l2addr_node *node;
-	struct vport_addr *addr;
-	struct hlist_node *tmp;
-	int hi;
-
-	for_each_l2hash_node(node, tmp, vport->uc_list, hi) {
-		addr = container_of(node, struct vport_addr, node);
-		addr->action = MLX5_ACTION_DEL;
-	}
-	esw_apply_vport_addr_list(esw, vport_num, MLX5_NVPRT_LIST_TYPE_UC);
-
-	for_each_l2hash_node(node, tmp, vport->mc_list, hi) {
-		addr = container_of(node, struct vport_addr, node);
-		addr->action = MLX5_ACTION_DEL;
-	}
-	esw_apply_vport_addr_list(esw, vport_num, MLX5_NVPRT_LIST_TYPE_MC);
+	mutex_unlock(&esw->state_lock);
 }
 
 static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 {
 	struct mlx5_vport *vport = &esw->vports[vport_num];
-	unsigned long flags;
 
 	if (!vport->enabled)
 		return;
 
 	esw_debug(esw->dev, "Disabling vport(%d)\n", vport_num);
 	/* Mark this vport as disabled to discard new events */
-	spin_lock_irqsave(&vport->lock, flags);
 	vport->enabled = false;
-	vport->enabled_events = 0;
-	spin_unlock_irqrestore(&vport->lock, flags);
+
+	synchronize_irq(mlx5_get_msix_vec(esw->dev, MLX5_EQ_VEC_ASYNC));
 
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
@@ -781,9 +1526,19 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
 	arm_vport_context_events_cmd(esw->dev, vport->vport, 0);
-	/* We don't assume VFs will cleanup after themselves */
-	esw_cleanup_vport(esw, vport_num);
+	mutex_lock(&esw->state_lock);
+	/* We don't assume VFs will cleanup after themselves.
+	 * Calling vport change handler while vport is disabled will cleanup
+	 * the vport resources.
+	 */
+	esw_vport_change_handle_locked(vport);
+	vport->enabled_events = 0;
+	if (vport_num) {
+		esw_vport_disable_egress_acl(esw, vport);
+		esw_vport_disable_ingress_acl(esw, vport);
+	}
 	esw->enabled_vports--;
+	mutex_unlock(&esw->state_lock);
 }
 
 /* Public E-Switch API */
@@ -802,6 +1557,12 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs)
 		return -ENOTSUPP;
 	}
 
+	if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
+		esw_warn(esw->dev, "E-Switch ingress ACL is not supported by FW\n");
+
+	if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
+		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
+
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d)\n", nvfs);
 
 	esw_disable_vport(esw, 0);
@@ -824,6 +1585,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs)
 
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 {
+	struct esw_mc_addr *mc_promisc;
 	int i;
 
 	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) ||
@@ -833,9 +1595,14 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	esw_info(esw->dev, "disable SRIOV: active vports(%d)\n",
 		 esw->enabled_vports);
 
+	mc_promisc = esw->mc_promisc;
+
 	for (i = 0; i < esw->total_vports; i++)
 		esw_disable_vport(esw, i);
 
+	if (mc_promisc && mc_promisc->uplink_rule)
+		mlx5_del_flow_rule(mc_promisc->uplink_rule);
+
 	esw_destroy_fdb_table(esw);
 
 	/* VPORT 0 (PF) must be enabled back with non-sriov configuration */
@@ -845,7 +1612,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
 	int l2_table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
-	int total_vports = 1 + pci_sriov_get_totalvfs(dev->pdev);
+	int total_vports = MLX5_TOTAL_VPORTS(dev);
+	struct esw_mc_addr *mc_promisc;
 	struct mlx5_eswitch *esw;
 	int vport_num;
 	int err;
@@ -874,6 +1642,13 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	}
 	esw->l2_table.size = l2_table_size;
 
+	mc_promisc = kzalloc(sizeof(*mc_promisc), GFP_KERNEL);
+	if (!mc_promisc) {
+		err = -ENOMEM;
+		goto abort;
+	}
+	esw->mc_promisc = mc_promisc;
+
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
 		err = -ENOMEM;
@@ -887,6 +1662,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	mutex_init(&esw->state_lock);
+
 	for (vport_num = 0; vport_num < total_vports; vport_num++) {
 		struct mlx5_vport *vport = &esw->vports[vport_num];
 
@@ -894,7 +1671,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
-		spin_lock_init(&vport->lock);
 	}
 
 	esw->total_vports = total_vports;
@@ -925,6 +1701,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	esw->dev->priv.eswitch = NULL;
 	destroy_workqueue(esw->work_queue);
 	kfree(esw->l2_table.bitmap);
+	kfree(esw->mc_promisc);
 	kfree(esw->vports);
 	kfree(esw);
 }
@@ -942,10 +1719,8 @@ void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
 	}
 
 	vport = &esw->vports[vport_num];
-	spin_lock(&vport->lock);
 	if (vport->enabled)
 		queue_work(esw->work_queue, &vport->vport_change_handler);
-	spin_unlock(&vport->lock);
 }
 
 /* Vport Administration */
@@ -957,12 +1732,22 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       int vport, u8 mac[ETH_ALEN])
 {
 	int err = 0;
+	struct mlx5_vport *evport;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
 
+	evport = &esw->vports[vport];
+
+	if (evport->spoofchk && !is_valid_ether_addr(mac)) {
+		mlx5_core_warn(esw->dev,
+			       "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+			       vport);
+		return -EPERM;
+	}
+
 	err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
 	if (err) {
 		mlx5_core_warn(esw->dev,
@@ -971,6 +1756,11 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 		return err;
 	}
 
+	mutex_lock(&esw->state_lock);
+	if (evport->enabled)
+		err = esw_vport_ingress_config(esw, evport);
+	mutex_unlock(&esw->state_lock);
+
 	return err;
 }
 
@@ -990,6 +1780,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 				  int vport, struct ifla_vf_info *ivi)
 {
+	struct mlx5_vport *evport;
 	u16 vlan;
 	u8 qos;
 
@@ -998,6 +1789,8 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
 
+	evport = &esw->vports[vport];
+
 	memset(ivi, 0, sizeof(*ivi));
 	ivi->vf = vport - 1;
 
@@ -1008,7 +1801,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 	query_esw_vport_cvlan(esw->dev, vport, &vlan, &qos);
 	ivi->vlan = vlan;
 	ivi->qos = qos;
-	ivi->spoofchk = 0;
+	ivi->spoofchk = evport->spoofchk;
 
 	return 0;
 }
@@ -1016,6 +1809,8 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				int vport, u16 vlan, u8 qos)
 {
+	struct mlx5_vport *evport;
+	int err = 0;
 	int set = 0;
 
 	if (!ESW_ALLOWED(esw))
@@ -1026,7 +1821,72 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 	if (vlan || qos)
 		set = 1;
 
-	return modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set);
+	evport = &esw->vports[vport];
+
+	err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	evport->vlan = vlan;
+	evport->qos = qos;
+	if (evport->enabled) {
+		err = esw_vport_ingress_config(esw, evport);
+		if (err)
+			goto out;
+		err = esw_vport_egress_config(esw, evport);
+	}
+
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
+				    int vport, bool spoofchk)
+{
+	struct mlx5_vport *evport;
+	bool pschk;
+	int err = 0;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+	if (!LEGAL_VPORT(esw, vport))
+		return -EINVAL;
+
+	evport = &esw->vports[vport];
+
+	mutex_lock(&esw->state_lock);
+	pschk = evport->spoofchk;
+	evport->spoofchk = spoofchk;
+	if (evport->enabled)
+		err = esw_vport_ingress_config(esw, evport);
+	if (err)
+		evport->spoofchk = pschk;
+	mutex_unlock(&esw->state_lock);
+
+	return err;
+}
+
+int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
+				 int vport, bool setting)
+{
+	struct mlx5_vport *evport;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+	if (!LEGAL_VPORT(esw, vport))
+		return -EINVAL;
+
+	evport = &esw->vports[vport];
+
+	mutex_lock(&esw->state_lock);
+	evport->trusted = setting;
+	if (evport->enabled)
+		esw_vport_change_handle_locked(evport);
+	mutex_unlock(&esw->state_lock);
+
+	return 0;
 }
 
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,

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

@@ -88,18 +88,40 @@ struct l2addr_node {
 	kfree(ptr);                                         \
 })
 
+struct vport_ingress {
+	struct mlx5_flow_table *acl;
+	struct mlx5_flow_group *allow_untagged_spoofchk_grp;
+	struct mlx5_flow_group *allow_spoofchk_only_grp;
+	struct mlx5_flow_group *allow_untagged_only_grp;
+	struct mlx5_flow_group *drop_grp;
+	struct mlx5_flow_rule  *allow_rule;
+	struct mlx5_flow_rule  *drop_rule;
+};
+
+struct vport_egress {
+	struct mlx5_flow_table *acl;
+	struct mlx5_flow_group *allowed_vlans_grp;
+	struct mlx5_flow_group *drop_grp;
+	struct mlx5_flow_rule  *allowed_vlan;
+	struct mlx5_flow_rule  *drop_rule;
+};
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	int                     vport;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
 	struct hlist_head       mc_list[MLX5_L2_ADDR_HASH_SIZE];
+	struct mlx5_flow_rule   *promisc_rule;
+	struct mlx5_flow_rule   *allmulti_rule;
 	struct work_struct      vport_change_handler;
 
-	/* This spinlock protects access to vport data, between
-	 * "esw_vport_disable" and ongoing interrupt "mlx5_eswitch_vport_event"
-	 * once vport marked as disabled new interrupts are discarded.
-	 */
-	spinlock_t              lock; /* vport events sync */
+	struct vport_ingress    ingress;
+	struct vport_egress     egress;
+
+	u16                     vlan;
+	u8                      qos;
+	bool                    spoofchk;
+	bool                    trusted;
 	bool                    enabled;
 	u16                     enabled_events;
 };
@@ -113,6 +135,8 @@ struct mlx5_l2_table {
 struct mlx5_eswitch_fdb {
 	void *fdb;
 	struct mlx5_flow_group *addr_grp;
+	struct mlx5_flow_group *allmulti_grp;
+	struct mlx5_flow_group *promisc_grp;
 };
 
 struct mlx5_eswitch {
@@ -124,6 +148,11 @@ struct mlx5_eswitch {
 	struct mlx5_vport       *vports;
 	int                     total_vports;
 	int                     enabled_vports;
+	/* Synchronize between vport change events
+	 * and async SRIOV admin state changes
+	 */
+	struct mutex            state_lock;
+	struct esw_mc_addr      *mc_promisc;
 };
 
 /* E-Switch API */
@@ -138,6 +167,10 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 				 int vport, int link_state);
 int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				int vport, u16 vlan, u8 qos);
+int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
+				    int vport, bool spoofchk);
+int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
+				 int vport_num, bool setting);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 				  int vport, struct ifla_vf_info *ivi);
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,

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

@@ -50,6 +50,10 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
 	MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
 	MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
+	if (ft->vport) {
+		MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
+		MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
+	}
 
 	memset(out, 0, sizeof(out));
 	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
@@ -57,6 +61,7 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 }
 
 int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
+			       u16 vport,
 			       enum fs_flow_table_type type, unsigned int level,
 			       unsigned int log_size, struct mlx5_flow_table
 			       *next_ft, unsigned int *table_id)
@@ -77,6 +82,10 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
 	MLX5_SET(create_flow_table_in, in, table_type, type);
 	MLX5_SET(create_flow_table_in, in, level, level);
 	MLX5_SET(create_flow_table_in, in, log_size, log_size);
+	if (vport) {
+		MLX5_SET(create_flow_table_in, in, vport_number, vport);
+		MLX5_SET(create_flow_table_in, in, other_vport, 1);
+	}
 
 	memset(out, 0, sizeof(out));
 	err = mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
@@ -101,6 +110,10 @@ int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_DESTROY_FLOW_TABLE);
 	MLX5_SET(destroy_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(destroy_flow_table_in, in, table_id, ft->id);
+	if (ft->vport) {
+		MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
+		MLX5_SET(destroy_flow_table_in, in, other_vport, 1);
+	}
 
 	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
 					  sizeof(out));
@@ -120,6 +133,10 @@ int mlx5_cmd_modify_flow_table(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_MODIFY_FLOW_TABLE);
 	MLX5_SET(modify_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(modify_flow_table_in, in, table_id, ft->id);
+	if (ft->vport) {
+		MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport);
+		MLX5_SET(modify_flow_table_in, in, other_vport, 1);
+	}
 	MLX5_SET(modify_flow_table_in, in, modify_field_select,
 		 MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
 	if (next_ft) {
@@ -148,6 +165,10 @@ int mlx5_cmd_create_flow_group(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_CREATE_FLOW_GROUP);
 	MLX5_SET(create_flow_group_in, in, table_type, ft->type);
 	MLX5_SET(create_flow_group_in, in, table_id, ft->id);
+	if (ft->vport) {
+		MLX5_SET(create_flow_group_in, in, vport_number, ft->vport);
+		MLX5_SET(create_flow_group_in, in, other_vport, 1);
+	}
 
 	err = mlx5_cmd_exec_check_status(dev, in,
 					 inlen, out,
@@ -174,6 +195,10 @@ int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev,
 	MLX5_SET(destroy_flow_group_in, in, table_type, ft->type);
 	MLX5_SET(destroy_flow_group_in, in, table_id, ft->id);
 	MLX5_SET(destroy_flow_group_in, in, group_id, group_id);
+	if (ft->vport) {
+		MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
+		MLX5_SET(destroy_flow_group_in, in, other_vport, 1);
+	}
 
 	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
 					  sizeof(out));
@@ -207,6 +232,10 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(set_fte_in, in, table_type, ft->type);
 	MLX5_SET(set_fte_in, in, table_id,   ft->id);
 	MLX5_SET(set_fte_in, in, flow_index, fte->index);
+	if (ft->vport) {
+		MLX5_SET(set_fte_in, in, vport_number, ft->vport);
+		MLX5_SET(set_fte_in, in, other_vport, 1);
+	}
 
 	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
@@ -285,6 +314,10 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(delete_fte_in, in, table_type, ft->type);
 	MLX5_SET(delete_fte_in, in, table_id, ft->id);
 	MLX5_SET(delete_fte_in, in, flow_index, index);
+	if (ft->vport) {
+		MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
+		MLX5_SET(delete_fte_in, in, other_vport, 1);
+	}
 
 	err =  mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
 

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

@@ -34,6 +34,7 @@
 #define _MLX5_FS_CMD_
 
 int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
+			       u16 vport,
 			       enum fs_flow_table_type type, unsigned int level,
 			       unsigned int log_size, struct mlx5_flow_table
 			       *next_ft, unsigned int *table_id);

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

@@ -457,7 +457,7 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in)
 	return fg;
 }
 
-static struct mlx5_flow_table *alloc_flow_table(int level, int max_fte,
+static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_fte,
 						enum fs_flow_table_type table_type)
 {
 	struct mlx5_flow_table *ft;
@@ -469,6 +469,7 @@ static struct mlx5_flow_table *alloc_flow_table(int level, int max_fte,
 	ft->level = level;
 	ft->node.type = FS_TYPE_FLOW_TABLE;
 	ft->type = table_type;
+	ft->vport = vport;
 	ft->max_fte = max_fte;
 	INIT_LIST_HEAD(&ft->fwd_rules);
 	mutex_init(&ft->lock);
@@ -700,9 +701,9 @@ static void list_add_flow_table(struct mlx5_flow_table *ft,
 	list_add(&ft->node.list, prev);
 }
 
-struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
-					       int prio, int max_fte,
-					       u32 level)
+static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
+							u16 vport, int prio,
+							int max_fte, u32 level)
 {
 	struct mlx5_flow_table *next_ft = NULL;
 	struct mlx5_flow_table *ft;
@@ -732,6 +733,7 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 	 */
 	level += fs_prio->start_level;
 	ft = alloc_flow_table(level,
+			      vport,
 			      roundup_pow_of_two(max_fte),
 			      root->table_type);
 	if (!ft) {
@@ -742,7 +744,7 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 	tree_init_node(&ft->node, 1, del_flow_table);
 	log_table_sz = ilog2(ft->max_fte);
 	next_ft = find_next_chained_ft(fs_prio);
-	err = mlx5_cmd_create_flow_table(root->dev, ft->type, ft->level,
+	err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->type, ft->level,
 					 log_table_sz, next_ft, &ft->id);
 	if (err)
 		goto free_ft;
@@ -766,6 +768,20 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 	return ERR_PTR(err);
 }
 
+struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
+					       int prio, int max_fte,
+					       u32 level)
+{
+	return __mlx5_create_flow_table(ns, 0, prio, max_fte, level);
+}
+
+struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
+						     int prio, int max_fte,
+						     u32 level, u16 vport)
+{
+	return __mlx5_create_flow_table(ns, vport, prio, max_fte, level);
+}
+
 struct mlx5_flow_table *mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 							    int prio,
 							    int num_flow_table_entries,
@@ -1319,6 +1335,16 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 			return &dev->priv.fdb_root_ns->ns;
 		else
 			return NULL;
+	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:
+		if (dev->priv.esw_egress_root_ns)
+			return &dev->priv.esw_egress_root_ns->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
+		if (dev->priv.esw_ingress_root_ns)
+			return &dev->priv.esw_ingress_root_ns->ns;
+		else
+			return NULL;
 	default:
 		return NULL;
 	}
@@ -1699,6 +1725,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 {
 	cleanup_root_ns(dev);
 	cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns);
+	cleanup_single_prio_root_ns(dev, dev->priv.esw_egress_root_ns);
+	cleanup_single_prio_root_ns(dev, dev->priv.esw_ingress_root_ns);
 }
 
 static int init_fdb_root_ns(struct mlx5_core_dev *dev)
@@ -1719,6 +1747,38 @@ static int init_fdb_root_ns(struct mlx5_core_dev *dev)
 	}
 }
 
+static int init_egress_acl_root_ns(struct mlx5_core_dev *dev)
+{
+	struct fs_prio *prio;
+
+	dev->priv.esw_egress_root_ns = create_root_ns(dev, FS_FT_ESW_EGRESS_ACL);
+	if (!dev->priv.esw_egress_root_ns)
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&dev->priv.esw_egress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(dev));
+	if (IS_ERR(prio))
+		return PTR_ERR(prio);
+	else
+		return 0;
+}
+
+static int init_ingress_acl_root_ns(struct mlx5_core_dev *dev)
+{
+	struct fs_prio *prio;
+
+	dev->priv.esw_ingress_root_ns = create_root_ns(dev, FS_FT_ESW_INGRESS_ACL);
+	if (!dev->priv.esw_ingress_root_ns)
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&dev->priv.esw_ingress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(dev));
+	if (IS_ERR(prio))
+		return PTR_ERR(prio);
+	else
+		return 0;
+}
+
 int mlx5_init_fs(struct mlx5_core_dev *dev)
 {
 	int err = 0;
@@ -1731,8 +1791,21 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
 		err = init_fdb_root_ns(dev);
 		if (err)
-			cleanup_root_ns(dev);
+			goto err;
+	}
+	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
+		err = init_egress_acl_root_ns(dev);
+		if (err)
+			goto err;
+	}
+	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
+		err = init_ingress_acl_root_ns(dev);
+		if (err)
+			goto err;
 	}
 
+	return 0;
+err:
+	mlx5_cleanup_fs(dev);
 	return err;
 }

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

@@ -46,6 +46,8 @@ enum fs_node_type {
 
 enum fs_flow_table_type {
 	FS_FT_NIC_RX          = 0x0,
+	FS_FT_ESW_EGRESS_ACL  = 0x2,
+	FS_FT_ESW_INGRESS_ACL = 0x3,
 	FS_FT_FDB             = 0X4,
 };
 
@@ -79,6 +81,7 @@ struct mlx5_flow_rule {
 struct mlx5_flow_table {
 	struct fs_node			node;
 	u32				id;
+	u16				vport;
 	unsigned int			max_fte;
 	unsigned int			level;
 	enum fs_flow_table_type		type;

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -42,6 +42,8 @@
 #define DRIVER_VERSION "3.0-1"
 #define DRIVER_RELDATE  "January 2015"
 
+#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev))
+
 extern int mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\

include/linux/mlx5/device.h

@@ -1349,6 +1349,18 @@ enum mlx5_cap_type {
 #define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap)
 
+#define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap)
+
+#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap)
+
+#define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap)
+
+#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap)
+
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
 		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH], cap)

include/linux/mlx5/driver.h

@@ -518,6 +518,8 @@ struct mlx5_priv {
 	unsigned long		pci_dev_data;
 	struct mlx5_flow_root_namespace *root_ns;
 	struct mlx5_flow_root_namespace *fdb_root_ns;
+	struct mlx5_flow_root_namespace *esw_egress_root_ns;
+	struct mlx5_flow_root_namespace *esw_ingress_root_ns;
 };
 
 enum mlx5_device_state {

include/linux/mlx5/fs.h

@@ -58,6 +58,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_LEFTOVERS,
 	MLX5_FLOW_NAMESPACE_ANCHOR,
 	MLX5_FLOW_NAMESPACE_FDB,
+	MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+	MLX5_FLOW_NAMESPACE_ESW_INGRESS,
 };
 
 struct mlx5_flow_table;
@@ -90,6 +92,11 @@ mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 		       int prio,
 		       int num_flow_table_entries,
 		       u32 level);
+struct mlx5_flow_table *
+mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
+			     int prio,
+			     int num_flow_table_entries,
+			     u32 level, u16 vport);
 int mlx5_destroy_flow_table(struct mlx5_flow_table *ft);
 
 /* inbox should be set with the following values: