diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 398e299..4b8c58b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3732,7 +3732,8 @@
 }
 
 
-static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
+			     void *accel_priv)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 5504120..bf81156 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1833,7 +1833,8 @@
 		bnx2x_napi_disable_cnic(bp);
 }
 
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index da8fcaa..41f3ca5a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -524,7 +524,8 @@
 int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos);
 
 /* select_queue callback */
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cc06854..5bcc870 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6827,12 +6827,20 @@
 	return __ixgbe_maybe_stop_tx(tx_ring, size);
 }
 
-#ifdef IXGBE_FCOE
-static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
+			      void *accel_priv)
 {
+	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
+#ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
 	int txq;
+#endif
+
+	if (fwd_adapter)
+		return skb->queue_mapping + fwd_adapter->tx_base_queue;
+
+#ifdef IXGBE_FCOE
 
 	/*
 	 * only execute the code below if protocol is FCoE
@@ -6858,9 +6866,11 @@
 		txq -= f->indices;
 
 	return txq + f->offset;
+#else
+	return __netdev_pick_tx(dev, skb);
+#endif
 }
 
-#endif
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 			  struct ixgbe_adapter *adapter,
 			  struct ixgbe_ring *tx_ring)
@@ -7629,27 +7639,11 @@
 	kfree(fwd_adapter);
 }
 
-static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
-				  struct net_device *dev,
-				  void *priv)
-{
-	struct ixgbe_fwd_adapter *fwd_adapter = priv;
-	unsigned int queue;
-	struct ixgbe_ring *tx_ring;
-
-	queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
-	tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
-
-	return __ixgbe_xmit_frame(skb, dev, tx_ring);
-}
-
 static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-#ifdef IXGBE_FCOE
 	.ndo_select_queue	= ixgbe_select_queue,
-#endif
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -7689,7 +7683,6 @@
 	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
 	.ndo_dfwd_add_station	= ixgbe_fwd_add,
 	.ndo_dfwd_del_station	= ixgbe_fwd_del,
-	.ndo_dfwd_start_xmit	= ixgbe_fwd_xmit,
 };
 
 /**
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6a6c1f7..ec94a20 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,8 @@
 }
 
 static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      void *accel_priv)
 {
 	/* we are currently only using the first queue */
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5..a7fcd59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,7 +592,8 @@
 	}
 }
 
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+			 void *accel_priv)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de..d5758ad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -714,7 +714,8 @@
 int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+			 void *accel_priv);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 628b736..0e9fb33 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2080,7 +2080,8 @@
 }
 
 /* Return subqueue id on this core (one per core). */
-static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
+				 void *accel_priv)
 {
 	return smp_processor_id();
 }
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 5360f73..bc8faae 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -299,7 +299,7 @@
 
 	if (vlan->fwd_priv) {
 		skb->dev = vlan->lowerdev;
-		ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+		ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
 	} else {
 		ret = macvlan_queue_xmit(skb, dev);
 	}
@@ -365,10 +365,8 @@
 		 */
 		if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
 			vlan->fwd_priv = NULL;
-		} else {
-			dev->features &= ~NETIF_F_LLTX;
+		} else
 			return 0;
-		}
 	}
 
 	err = -EBUSY;
@@ -702,8 +700,7 @@
 	features = netdev_increment_features(vlan->lowerdev->features,
 					     features,
 					     mask);
-	if (!vlan->fwd_priv)
-		features |= NETIF_F_LLTX;
+	features |= NETIF_F_LLTX;
 
 	return features;
 }
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 736050d..b75ae5b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,7 +1647,8 @@
 	return NETDEV_TX_OK;
 }
 
-static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
+			     void *accel_priv)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c8343a..ecec802 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -348,7 +348,8 @@
  * different rxq no. here. If we could not get rxhash, then we would
  * hope the rxq no. may help here.
  */
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	struct tun_flow_entry *e;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 78e8a66..8bb8988 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -746,7 +746,8 @@
 }
 
 static u16
-mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
+mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
+				void *accel_priv)
 {
 	skb->priority = cfg80211_classify8021d(skb);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 53fee2f..8dfdd27 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -39,7 +39,8 @@
 	return 0;
 }
 
-static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	return ClassifyPacket(netdev_priv(dev), skb);
 }
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 235d2b1..eedffed 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -306,7 +306,8 @@
 	return NETDEV_TX_OK;
 }
 
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb)
+static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
+				void *accel_priv)
 {
 	return (u16)smp_processor_id();
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 17659bb..dd69e34 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -652,7 +652,8 @@
 	return dscp >> 5;
 }
 
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5faaadb..ce2a1f5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ *                         void *accel_priv);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -990,7 +991,8 @@
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
-						    struct sk_buff *skb);
+						    struct sk_buff *skb,
+						    void *accel_priv);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1529,7 +1531,8 @@
 }
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb);
+				    struct sk_buff *skb,
+				    void *accel_priv);
 u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
@@ -1819,6 +1822,7 @@
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
@@ -2426,7 +2430,7 @@
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv);
+			struct netdev_queue *txq);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4fc1722..0ce469e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2539,7 +2539,7 @@
 }
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv)
+			struct netdev_queue *txq)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
@@ -2605,13 +2605,10 @@
 			dev_queue_xmit_nit(skb, dev);
 
 		skb_len = skb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
-		else
 			rc = ops->ndo_start_xmit(skb, dev);
 
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK && txq)
+		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
 	}
@@ -2627,10 +2624,7 @@
 			dev_queue_xmit_nit(nskb, dev);
 
 		skb_len = nskb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
-		else
-			rc = ops->ndo_start_xmit(nskb, dev);
+		rc = ops->ndo_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -2811,7 +2805,7 @@
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-int dev_queue_xmit(struct sk_buff *skb)
+int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -2827,7 +2821,7 @@
 
 	skb_update_prio(skb);
 
-	txq = netdev_pick_tx(dev, skb);
+	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -2863,7 +2857,7 @@
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+				rc = dev_hard_start_xmit(skb, dev, txq);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
@@ -2892,8 +2886,19 @@
 	rcu_read_unlock_bh();
 	return rc;
 }
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+	return __dev_queue_xmit(skb, NULL);
+}
 EXPORT_SYMBOL(dev_queue_xmit);
 
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+{
+	return __dev_queue_xmit(skb, accel_priv);
+}
+EXPORT_SYMBOL(dev_queue_xmit_accel);
+
 
 /*=======================================================================
 			Receiver routines
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef173..2fc5bea 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -395,17 +395,21 @@
 EXPORT_SYMBOL(__netdev_pick_tx);
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb)
+				    struct sk_buff *skb,
+				    void *accel_priv)
 {
 	int queue_index = 0;
 
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb);
+			queue_index = ops->ndo_select_queue(dev, skb,
+							    accel_priv);
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
-		queue_index = dev_cap_txqueue(dev, queue_index);
+
+		if (!accel_priv)
+			queue_index = dev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3030978..19fe9c7 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -375,7 +375,7 @@
 	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
 		struct netdev_queue *txq;
 
-		txq = netdev_pick_tx(dev, skb);
+		txq = netdev_pick_tx(dev, skb, NULL);
 
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 36c3a4c..a075791 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1061,7 +1061,8 @@
 }
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
-					 struct sk_buff *skb)
+					 struct sk_buff *skb,
+					 void *accel_priv)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1078,7 +1079,8 @@
 };
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb,
+					  void *accel_priv)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 922a094..7fc899a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq, NULL);
+		ret = dev_hard_start_xmit(skb, dev, txq);
 
 	HARD_TX_UNLOCK(dev, txq);