Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

10 files changed, 240 insertions, 107 deletions

diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 03c3bdf25468..bbf2c82cf7b2 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -16,6 +16,15 @@ config NET_DSA
 
 if NET_DSA
 
+config NET_DSA_LEGACY
+	bool "Support for older platform device and Device Tree registration"
+	default y
+	---help---
+	  Say Y if you want to enable support for the older platform device and
+	  deprecated Device Tree binding registration.
+
+	  This feature is scheduled for removal in 4.17.
+
 # tagging formats
 config NET_DSA_TAG_BRCM
 	bool
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 0e13c1f95d13..9e4d3536f977 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # the core
 obj-$(CONFIG_NET_DSA) += dsa_core.o
-dsa_core-y += dsa.o dsa2.o legacy.o master.o port.o slave.o switch.o
+dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o
+dsa_core-$(CONFIG_NET_DSA_LEGACY) += legacy.o
 
 # tagging formats
 dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 1e287420ff49..adf50fbc4c13 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -241,7 +241,7 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst)
 		for (port = 0; port < ds->num_ports; port++) {
 			dp = &ds->ports[port];
 
-			if (dsa_port_is_user(dp))
+			if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp))
 				dp->cpu_dp = dst->cpu_dp;
 		}
 	}
@@ -271,13 +271,12 @@ static int dsa_port_setup(struct dsa_port *dp)
 		break;
 	case DSA_PORT_TYPE_CPU:
 	case DSA_PORT_TYPE_DSA:
-		err = dsa_port_fixed_link_register_of(dp);
+		err = dsa_port_link_register_of(dp);
 		if (err) {
-			dev_err(ds->dev, "failed to register fixed link for port %d.%d\n",
+			dev_err(ds->dev, "failed to setup link for port %d.%d\n",
 				ds->index, dp->index);
 			return err;
 		}
-
 		break;
 	case DSA_PORT_TYPE_USER:
 		err = dsa_slave_create(dp);
@@ -301,7 +300,7 @@ static void dsa_port_teardown(struct dsa_port *dp)
 		break;
 	case DSA_PORT_TYPE_CPU:
 	case DSA_PORT_TYPE_DSA:
-		dsa_port_fixed_link_unregister_of(dp);
+		dsa_port_link_unregister_of(dp);
 		break;
 	case DSA_PORT_TYPE_USER:
 		if (dp->slave) {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 7d036696e8c4..70de7895e5b8 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -97,8 +97,17 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
 bool dsa_schedule_work(struct work_struct *work);
 
 /* legacy.c */
+#if IS_ENABLED(CONFIG_NET_DSA_LEGACY)
 int dsa_legacy_register(void);
 void dsa_legacy_unregister(void);
+#else
+static inline int dsa_legacy_register(void)
+{
+	return 0;
+}
+
+static inline void dsa_legacy_unregister(void) { }
+#endif
 int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		       struct net_device *dev,
 		       const unsigned char *addr, u16 vid,
@@ -157,8 +166,8 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 		      struct switchdev_trans *trans);
 int dsa_port_vlan_del(struct dsa_port *dp,
 		      const struct switchdev_obj_port_vlan *vlan);
-int dsa_port_fixed_link_register_of(struct dsa_port *dp);
-void dsa_port_fixed_link_unregister_of(struct dsa_port *dp);
+int dsa_port_link_register_of(struct dsa_port *dp);
+void dsa_port_link_unregister_of(struct dsa_port *dp);
 
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 84611d7fcfa2..cb54b81d0bd9 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -86,7 +86,7 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds)
 		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
 			continue;
 
-		ret = dsa_port_fixed_link_register_of(&ds->ports[port]);
+		ret = dsa_port_link_register_of(&ds->ports[port]);
 		if (ret)
 			return ret;
 	}
@@ -275,7 +275,7 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
 	for (port = 0; port < ds->num_ports; port++) {
 		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
 			continue;
-		dsa_port_fixed_link_unregister_of(&ds->ports[port]);
+		dsa_port_link_unregister_of(&ds->ports[port]);
 	}
 
 	if (ds->slave_mii_bus && ds->ops->phy_read)
@@ -718,26 +718,6 @@ static int dsa_resume(struct device *d)
 }
 #endif
 
-/* legacy way, bypassing the bridge *****************************************/
-int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
-		       struct net_device *dev,
-		       const unsigned char *addr, u16 vid,
-		       u16 flags)
-{
-	struct dsa_port *dp = dsa_slave_to_port(dev);
-
-	return dsa_port_fdb_add(dp, addr, vid);
-}
-
-int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
-		       struct net_device *dev,
-		       const unsigned char *addr, u16 vid)
-{
-	struct dsa_port *dp = dsa_slave_to_port(dev);
-
-	return dsa_port_fdb_del(dp, addr, vid);
-}
-
 static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume);
 
 static const struct of_device_id dsa_of_match_table[] = {
diff --git a/net/dsa/port.c b/net/dsa/port.c
index bb4be2679904..7acc1169d75e 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -273,7 +273,56 @@ int dsa_port_vlan_del(struct dsa_port *dp,
 	return 0;
 }
 
-int dsa_port_fixed_link_register_of(struct dsa_port *dp)
+static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable)
+{
+	struct device_node *port_dn = dp->dn;
+	struct device_node *phy_dn;
+	struct dsa_switch *ds = dp->ds;
+	struct phy_device *phydev;
+	int port = dp->index;
+	int err = 0;
+
+	phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
+	if (!phy_dn)
+		return 0;
+
+	phydev = of_phy_find_device(phy_dn);
+	if (!phydev) {
+		err = -EPROBE_DEFER;
+		goto err_put_of;
+	}
+
+	if (enable) {
+		err = genphy_config_init(phydev);
+		if (err < 0)
+			goto err_put_dev;
+
+		err = genphy_resume(phydev);
+		if (err < 0)
+			goto err_put_dev;
+
+		err = genphy_read_status(phydev);
+		if (err < 0)
+			goto err_put_dev;
+	} else {
+		err = genphy_suspend(phydev);
+		if (err < 0)
+			goto err_put_dev;
+	}
+
+	if (ds->ops->adjust_link)
+		ds->ops->adjust_link(ds, port, phydev);
+
+	dev_dbg(ds->dev, "enabled port's phy: %s", phydev_name(phydev));
+
+err_put_dev:
+	put_device(&phydev->mdio.dev);
+err_put_of:
+	of_node_put(phy_dn);
+	return err;
+}
+
+static int dsa_port_fixed_link_register_of(struct dsa_port *dp)
 {
 	struct device_node *dn = dp->dn;
 	struct dsa_switch *ds = dp->ds;
@@ -282,38 +331,44 @@ int dsa_port_fixed_link_register_of(struct dsa_port *dp)
 	int mode;
 	int err;
 
-	if (of_phy_is_fixed_link(dn)) {
-		err = of_phy_register_fixed_link(dn);
-		if (err) {
-			dev_err(ds->dev,
-				"failed to register the fixed PHY of port %d\n",
-				port);
-			return err;
-		}
+	err = of_phy_register_fixed_link(dn);
+	if (err) {
+		dev_err(ds->dev,
+			"failed to register the fixed PHY of port %d\n",
+			port);
+		return err;
+	}
 
-		phydev = of_phy_find_device(dn);
+	phydev = of_phy_find_device(dn);
 
-		mode = of_get_phy_mode(dn);
-		if (mode < 0)
-			mode = PHY_INTERFACE_MODE_NA;
-		phydev->interface = mode;
+	mode = of_get_phy_mode(dn);
+	if (mode < 0)
+		mode = PHY_INTERFACE_MODE_NA;
+	phydev->interface = mode;
 
-		genphy_config_init(phydev);
-		genphy_read_status(phydev);
+	genphy_config_init(phydev);
+	genphy_read_status(phydev);
 
-		if (ds->ops->adjust_link)
-			ds->ops->adjust_link(ds, port, phydev);
+	if (ds->ops->adjust_link)
+		ds->ops->adjust_link(ds, port, phydev);
 
-		put_device(&phydev->mdio.dev);
-	}
+	put_device(&phydev->mdio.dev);
 
 	return 0;
 }
 
-void dsa_port_fixed_link_unregister_of(struct dsa_port *dp)
+int dsa_port_link_register_of(struct dsa_port *dp)
 {
-	struct device_node *dn = dp->dn;
+	if (of_phy_is_fixed_link(dp->dn))
+		return dsa_port_fixed_link_register_of(dp);
+	else
+		return dsa_port_setup_phy_of(dp, true);
+}
 
-	if (of_phy_is_fixed_link(dn))
-		of_phy_deregister_fixed_link(dn);
+void dsa_port_link_unregister_of(struct dsa_port *dp)
+{
+	if (of_phy_is_fixed_link(dp->dn))
+		of_phy_deregister_fixed_link(dp->dn);
+	else
+		dsa_port_setup_phy_of(dp, false);
 }
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a95a55f79137..f52307296de4 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -708,14 +708,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = cls->common.protocol;
-	struct net *net = dev_net(dev);
 	struct dsa_switch *ds = dp->ds;
 	struct net_device *to_dev;
 	const struct tc_action *a;
 	struct dsa_port *to_dp;
 	int err = -EOPNOTSUPP;
 	LIST_HEAD(actions);
-	int ifindex;
 
 	if (!ds->ops->port_mirror_add)
 		return err;
@@ -729,8 +727,7 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 	if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) {
 		struct dsa_mall_mirror_tc_entry *mirror;
 
-		ifindex = tcf_mirred_ifindex(a);
-		to_dev = __dev_get_by_index(net, ifindex);
+		to_dev = tcf_mirred_dev(a);
 		if (!to_dev)
 			return -EINVAL;
 
@@ -943,6 +940,26 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.set_rxnfc		= dsa_slave_set_rxnfc,
 };
 
+/* legacy way, bypassing the bridge *****************************************/
+int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+		       struct net_device *dev,
+		       const unsigned char *addr, u16 vid,
+		       u16 flags)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+
+	return dsa_port_fdb_add(dp, addr, vid);
+}
+
+int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+		       struct net_device *dev,
+		       const unsigned char *addr, u16 vid)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+
+	return dsa_port_fdb_del(dp, addr, vid);
+}
+
 static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 29608d087a7c..b93511726069 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -83,29 +83,52 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 static int dsa_switch_fdb_add(struct dsa_switch *ds,
 			      struct dsa_notifier_fdb_info *info)
 {
-	/* Do not care yet about other switch chips of the fabric */
-	if (ds->index != info->sw_index)
-		return 0;
+	int port = dsa_towards_port(ds, info->sw_index, info->port);
 
 	if (!ds->ops->port_fdb_add)
 		return -EOPNOTSUPP;
 
-	return ds->ops->port_fdb_add(ds, info->port, info->addr,
-				     info->vid);
+	return ds->ops->port_fdb_add(ds, port, info->addr, info->vid);
 }
 
 static int dsa_switch_fdb_del(struct dsa_switch *ds,
 			      struct dsa_notifier_fdb_info *info)
 {
-	/* Do not care yet about other switch chips of the fabric */
-	if (ds->index != info->sw_index)
-		return 0;
+	int port = dsa_towards_port(ds, info->sw_index, info->port);
 
 	if (!ds->ops->port_fdb_del)
 		return -EOPNOTSUPP;
 
-	return ds->ops->port_fdb_del(ds, info->port, info->addr,
-				     info->vid);
+	return ds->ops->port_fdb_del(ds, port, info->addr, info->vid);
+}
+
+static int
+dsa_switch_mdb_prepare_bitmap(struct dsa_switch *ds,
+			      const struct switchdev_obj_port_mdb *mdb,
+			      const unsigned long *bitmap)
+{
+	int port, err;
+
+	if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add)
+		return -EOPNOTSUPP;
+
+	for_each_set_bit(port, bitmap, ds->num_ports) {
+		err = ds->ops->port_mdb_prepare(ds, port, mdb);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void dsa_switch_mdb_add_bitmap(struct dsa_switch *ds,
+				      const struct switchdev_obj_port_mdb *mdb,
+				      const unsigned long *bitmap)
+{
+	int port;
+
+	for_each_set_bit(port, bitmap, ds->num_ports)
+		ds->ops->port_mdb_add(ds, port, mdb);
 }
 
 static int dsa_switch_mdb_add(struct dsa_switch *ds,
@@ -114,7 +137,7 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds,
 	const struct switchdev_obj_port_mdb *mdb = info->mdb;
 	struct switchdev_trans *trans = info->trans;
 	DECLARE_BITMAP(group, ds->num_ports);
-	int port, err;
+	int port;
 
 	/* Build a mask of Multicast group members */
 	bitmap_zero(group, ds->num_ports);
@@ -124,21 +147,10 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds,
 		if (dsa_is_dsa_port(ds, port))
 			set_bit(port, group);
 
-	if (switchdev_trans_ph_prepare(trans)) {
-		if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add)
-			return -EOPNOTSUPP;
-
-		for_each_set_bit(port, group, ds->num_ports) {
-			err = ds->ops->port_mdb_prepare(ds, port, mdb, trans);
-			if (err)
-				return err;
-		}
-
-		return 0;
-	}
+	if (switchdev_trans_ph_prepare(trans))
+		return dsa_switch_mdb_prepare_bitmap(ds, mdb, group);
 
-	for_each_set_bit(port, group, ds->num_ports)
-		ds->ops->port_mdb_add(ds, port, mdb, trans);
+	dsa_switch_mdb_add_bitmap(ds, mdb, group);
 
 	return 0;
 }
@@ -157,13 +169,43 @@ static int dsa_switch_mdb_del(struct dsa_switch *ds,
 	return 0;
 }
 
+static int
+dsa_switch_vlan_prepare_bitmap(struct dsa_switch *ds,
+			       const struct switchdev_obj_port_vlan *vlan,
+			       const unsigned long *bitmap)
+{
+	int port, err;
+
+	if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add)
+		return -EOPNOTSUPP;
+
+	for_each_set_bit(port, bitmap, ds->num_ports) {
+		err = ds->ops->port_vlan_prepare(ds, port, vlan);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void
+dsa_switch_vlan_add_bitmap(struct dsa_switch *ds,
+			   const struct switchdev_obj_port_vlan *vlan,
+			   const unsigned long *bitmap)
+{
+	int port;
+
+	for_each_set_bit(port, bitmap, ds->num_ports)
+		ds->ops->port_vlan_add(ds, port, vlan);
+}
+
 static int dsa_switch_vlan_add(struct dsa_switch *ds,
 			       struct dsa_notifier_vlan_info *info)
 {
 	const struct switchdev_obj_port_vlan *vlan = info->vlan;
 	struct switchdev_trans *trans = info->trans;
 	DECLARE_BITMAP(members, ds->num_ports);
-	int port, err;
+	int port;
 
 	/* Build a mask of VLAN members */
 	bitmap_zero(members, ds->num_ports);
@@ -173,21 +215,10 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds,
 		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
 			set_bit(port, members);
 
-	if (switchdev_trans_ph_prepare(trans)) {
-		if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add)
-			return -EOPNOTSUPP;
-
-		for_each_set_bit(port, members, ds->num_ports) {
-			err = ds->ops->port_vlan_prepare(ds, port, vlan, trans);
-			if (err)
-				return err;
-		}
-
-		return 0;
-	}
+	if (switchdev_trans_ph_prepare(trans))
+		return dsa_switch_vlan_prepare_bitmap(ds, vlan, members);
 
-	for_each_set_bit(port, members, ds->num_ports)
-		ds->ops->port_vlan_add(ds, port, vlan, trans);
+	dsa_switch_vlan_add_bitmap(ds, vlan, members);
 
 	return 0;
 }
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index e6e0b7b6025c..2b06bb91318b 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -70,6 +70,18 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
 	if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
 		return NULL;
 
+	/* The Ethernet switch we are interfaced with needs packets to be at
+	 * least 64 bytes (including FCS) otherwise they will be discarded when
+	 * they enter the switch port logic. When Broadcom tags are enabled, we
+	 * need to make sure that packets are at least 68 bytes
+	 * (including FCS and tag) because the length verification is done after
+	 * the Broadcom tag is stripped off the ingress packet.
+	 *
+	 * Let dsa_slave_xmit() free the SKB
+	 */
+	if (__skb_put_padto(skb, ETH_ZLEN + BRCM_TAG_LEN, false))
+		return NULL;
+
 	skb_push(skb, BRCM_TAG_LEN);
 
 	if (offset)
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 8475434af7d5..11535bc70743 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -13,10 +13,13 @@
  */
 
 #include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
 
 #include "dsa_priv.h"
 
 #define MTK_HDR_LEN		4
+#define MTK_HDR_XMIT_UNTAGGED		0
+#define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
 
@@ -25,20 +28,37 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
+	bool is_vlan_skb = true;
 
-	if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
-		return NULL;
-
-	skb_push(skb, MTK_HDR_LEN);
+	/* Build the special tag after the MAC Source Address. If VLAN header
+	 * is present, it's required that VLAN header and special tag is
+	 * being combined. Only in this way we can allow the switch can parse
+	 * the both special and VLAN tag at the same time and then look up VLAN
+	 * table with VID.
+	 */
+	if (!skb_vlan_tagged(skb)) {
+		if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
+			return NULL;
 
-	memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
+		skb_push(skb, MTK_HDR_LEN);
+		memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
+		is_vlan_skb = false;
+	}
 
-	/* Build the tag after the MAC Source Address */
 	mtk_tag = skb->data + 2 * ETH_ALEN;
-	mtk_tag[0] = 0;
+
+	/* Mark tag attribute on special tag insertion to notify hardware
+	 * whether that's a combined special tag with 802.1Q header.
+	 */
+	mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 :
+		     MTK_HDR_XMIT_UNTAGGED;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
-	mtk_tag[2] = 0;
-	mtk_tag[3] = 0;
+
+	/* Tag control information is kept for 802.1Q */
+	if (!is_vlan_skb) {
+		mtk_tag[2] = 0;
+		mtk_tag[3] = 0;
+	}
 
 	return skb;
 }