diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 3a098cc4d349..70e95324a97d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -161,12 +161,16 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	cq->mcq.comp  = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
 	cq->mcq.event = mlx4_en_cq_event;
 
-	if (!cq->is_tx) {
+	if (cq->is_tx) {
+		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
+			       NAPI_POLL_WEIGHT);
+	} else {
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
 		napi_hash_add(&cq->napi);
-		napi_enable(&cq->napi);
 	}
 
+	napi_enable(&cq->napi);
+
 	return 0;
 }
 
@@ -188,12 +192,12 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 {
+	napi_disable(&cq->napi);
 	if (!cq->is_tx) {
-		napi_disable(&cq->napi);
 		napi_hash_del(&cq->napi);
 		synchronize_rcu();
-		netif_napi_del(&cq->napi);
 	}
+	netif_napi_del(&cq->napi);
 
 	mlx4_cq_free(priv->mdev->dev, &cq->mcq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 0d087b03a7b0..725a4e1b5f67 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -174,6 +174,9 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 		mlx4_err(mdev, "Internal error detected, restarting device\n");
 		break;
 
+	case MLX4_DEV_EVENT_SLAVE_INIT:
+	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
+		break;
 	default:
 		if (port < 1 || port > dev->caps.num_ports ||
 		    !mdev->pndev[port])
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 709e5ec5ce14..6f920900e841 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1910,8 +1910,10 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 				      prof->tx_ring_size, i, TX, node))
 			goto err;
 
-		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
-					   prof->tx_ring_size, TXBB_SIZE, node))
+		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
+					   priv->base_tx_qpn + i,
+					   prof->tx_ring_size, TXBB_SIZE,
+					   node, i))
 			goto err;
 	}
 
@@ -2164,6 +2166,27 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st
 
 	return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state);
 }
+
+#define PORT_ID_BYTE_LEN 8
+static int mlx4_en_get_phys_port_id(struct net_device *dev,
+				    struct netdev_phys_port_id *ppid)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_dev *mdev = priv->mdev->dev;
+	int i;
+	u64 phys_port_id = mdev->caps.phys_port_id[priv->port];
+
+	if (!phys_port_id)
+		return -EOPNOTSUPP;
+
+	ppid->id_len = sizeof(phys_port_id);
+	for (i = PORT_ID_BYTE_LEN - 1; i >= 0; --i) {
+		ppid->id[i] =  phys_port_id & 0xff;
+		phys_port_id >>= 8;
+	}
+	return 0;
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
@@ -2189,6 +2212,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= mlx4_en_low_latency_recv,
 #endif
+	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2217,6 +2241,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
+	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
 };
 
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5a1702..e3adcebfdfb8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -55,7 +55,7 @@ MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring, int qpn, u32 size,
-			   u16 stride, int node)
+			   u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_tx_ring *ring;
@@ -140,6 +140,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 		ring->bf_enabled = true;
 
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
+	ring->queue_index = queue_index;
+
+	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
+		cpumask_set_cpu(queue_index, &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -206,6 +210,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
+	if (!user_prio && cpu_online(ring->queue_index))
+		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
+				    ring->queue_index);
 
 	return err;
 }
@@ -317,7 +324,7 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			}
 		}
 	}
-	dev_kfree_skb_any(skb);
+	dev_kfree_skb(skb);
 	return tx_info->nr_txbb;
 }
 
@@ -354,7 +361,9 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
+static int mlx4_en_process_tx_cq(struct net_device *dev,
+				 struct mlx4_en_cq *cq,
+				 int budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
@@ -372,9 +381,10 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
 	u64 timestamp = 0;
+	int done = 0;
 
 	if (!priv->port_up)
-		return;
+		return 0;
 
 	index = cons_index & size_mask;
 	cqe = &buf[(index << factor) + factor];
@@ -383,7 +393,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 
 	/* Process all completed CQEs */
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
-			cons_index & size)) {
+			cons_index & size) && (done < budget)) {
 		/*
 		 * make sure we read the CQE after we read the
 		 * ownership bit
@@ -421,7 +431,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 			txbbs_stamp = txbbs_skipped;
 			packets++;
 			bytes += ring->tx_info[ring_index].nr_bytes;
-		} while (ring_index != new_index);
+		} while ((++done < budget) && (ring_index != new_index));
 
 		++cons_index;
 		index = cons_index & size_mask;
@@ -447,6 +457,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 		netif_tx_wake_queue(ring->tx_queue);
 		priv->port_stats.wake_queue++;
 	}
+	return done;
 }
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@@ -454,10 +465,31 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq)
 	struct mlx4_en_cq *cq = container_of(mcq, struct mlx4_en_cq, mcq);
 	struct mlx4_en_priv *priv = netdev_priv(cq->dev);
 
-	mlx4_en_process_tx_cq(cq->dev, cq);
-	mlx4_en_arm_cq(priv, cq);
+	if (priv->port_up)
+		napi_schedule(&cq->napi);
+	else
+		mlx4_en_arm_cq(priv, cq);
 }
 
+/* TX CQ polling - called by NAPI */
+int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
+{
+	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
+	struct net_device *dev = cq->dev;
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int done;
+
+	done = mlx4_en_process_tx_cq(dev, cq, budget);
+
+	/* If we used up all the quota - we're probably not done yet... */
+	if (done < budget) {
+		/* Done for now */
+		napi_complete(napi);
+		mlx4_en_arm_cq(priv, cq);
+		return done;
+	}
+	return budget;
+}
 
 static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
 						      struct mlx4_en_tx_ring *ring,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 194928214606..27a84342525f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -207,25 +207,25 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 
 /* when opcode modifier = 1 */
 #define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
-#define QUERY_FUNC_CAP_RDMA_PROPS_OFFSET	0x8
-#define QUERY_FUNC_CAP_ETH_PROPS_OFFSET		0xc
+#define QUERY_FUNC_CAP_FLAGS0_OFFSET		0x8
+#define QUERY_FUNC_CAP_FLAGS1_OFFSET		0xc
 
 #define QUERY_FUNC_CAP_QP0_TUNNEL		0x10
 #define QUERY_FUNC_CAP_QP0_PROXY		0x14
 #define QUERY_FUNC_CAP_QP1_TUNNEL		0x18
 #define QUERY_FUNC_CAP_QP1_PROXY		0x1c
+#define QUERY_FUNC_CAP_PHYS_PORT_ID		0x28
 
-#define QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC	0x40
-#define QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN	0x80
+#define QUERY_FUNC_CAP_FLAGS1_FORCE_MAC		0x40
+#define QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN	0x80
+#define QUERY_FUNC_CAP_FLAGS1_NIC_INFO			0x10
 
-#define QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID 0x80
+#define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
 
 	if (vhcr->op_modifier == 1) {
-		field = 0;
-		/* ensure force vlan and force mac bits are not set */
-		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
-		/* ensure that phy_wqe_gid bit is not set */
-		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET);
+		/* Set nic_info bit to mark new fields support */
+		field  = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
 
 		field = vhcr->in_modifier; /* phys-port = logical-port */
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
@@ -243,6 +243,9 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		size += 2;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_PROXY);
 
+		MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier],
+			 QUERY_FUNC_CAP_PHYS_PORT_ID);
+
 	} else if (vhcr->op_modifier == 0) {
 		/* enable rdma and ethernet interfaces, and new quota locations */
 		field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
@@ -391,22 +394,22 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 		goto out;
 	}
 
+	MLX4_GET(func_cap->flags1, outbox, QUERY_FUNC_CAP_FLAGS1_OFFSET);
 	if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) {
-		MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
-		if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN) {
+		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_OFFSET) {
 			mlx4_err(dev, "VLAN is enforced on this port\n");
 			err = -EPROTONOSUPPORT;
 			goto out;
 		}
 
-		if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC) {
+		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_FORCE_MAC) {
 			mlx4_err(dev, "Force mac is enabled on this port\n");
 			err = -EPROTONOSUPPORT;
 			goto out;
 		}
 	} else if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_IB) {
-		MLX4_GET(field, outbox, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET);
-		if (field & QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID) {
+		MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
+		if (field & QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID) {
 			mlx4_err(dev, "phy_wqe_gid is "
 				 "enforced on this ib port\n");
 			err = -EPROTONOSUPPORT;
@@ -433,6 +436,10 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 	MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_PROXY);
 	func_cap->qp1_proxy_qpn = size & 0xFFFFFF;
 
+	if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_NIC_INFO)
+		MLX4_GET(func_cap->phys_port_id, outbox,
+			 QUERY_FUNC_CAP_PHYS_PORT_ID);
+
 	/* All other resources are allocated by the master, but we still report
 	 * 'num' and 'reserved' capabilities as follows:
 	 * - num remains the maximum resource index
@@ -1713,6 +1720,43 @@ int mlx4_NOP(struct mlx4_dev *dev)
 	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE);
 }
 
+int mlx4_get_phys_port_id(struct mlx4_dev *dev)
+{
+	u8 port;
+	u32 *outbox;
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 in_mod;
+	u32 guid_hi, guid_lo;
+	int err, ret = 0;
+#define MOD_STAT_CFG_PORT_OFFSET 8
+#define MOD_STAT_CFG_GUID_H	 0X14
+#define MOD_STAT_CFG_GUID_L	 0X1c
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	outbox = mailbox->buf;
+
+	for (port = 1; port <= dev->caps.num_ports; port++) {
+		in_mod = port << MOD_STAT_CFG_PORT_OFFSET;
+		err = mlx4_cmd_box(dev, 0, mailbox->dma, in_mod, 0x2,
+				   MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A,
+				   MLX4_CMD_NATIVE);
+		if (err) {
+			mlx4_err(dev, "Fail to get port %d uplink guid\n",
+				 port);
+			ret = err;
+		} else {
+			MLX4_GET(guid_hi, outbox, MOD_STAT_CFG_GUID_H);
+			MLX4_GET(guid_lo, outbox, MOD_STAT_CFG_GUID_L);
+			dev->caps.phys_port_id[port] = (u64)guid_lo |
+						       (u64)guid_hi << 32;
+		}
+	}
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return ret;
+}
+
 #define MLX4_WOL_SETUP_MODE (5 << 28)
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index a0a368b7c939..6811ee00ba7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -140,6 +140,8 @@ struct mlx4_func_cap {
 	u32	qp1_proxy_qpn;
 	u8	physical_port;
 	u8	port_flags;
+	u8	flags1;
+	u64	phys_port_id;
 };
 
 struct mlx4_adapter {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index b37478db9851..fbebfb0a6436 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -96,10 +96,10 @@ MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " To activate device managed"
 					 " flow steering when available, set to -1");
 
-static bool enable_64b_cqe_eqe;
+static bool enable_64b_cqe_eqe = true;
 module_param(enable_64b_cqe_eqe, bool, 0444);
 MODULE_PARM_DESC(enable_64b_cqe_eqe,
-		 "Enable 64 byte CQEs/EQEs when the FW supports this");
+		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
 #define HCA_GLOBAL_CAP_MASK            0
 
@@ -606,6 +606,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn;
 		dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn;
 		dev->caps.port_mask[i] = dev->caps.port_type[i];
+		dev->caps.phys_port_id[i] = func_cap.phys_port_id;
 		if (mlx4_get_slave_pkey_gid_tbl_len(dev, i,
 						    &dev->caps.gid_table_len[i],
 						    &dev->caps.pkey_table_len[i]))
@@ -1484,6 +1485,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		choose_steering_mode(dev, &dev_cap);
 
+		err = mlx4_get_phys_port_id(dev);
+		if (err)
+			mlx4_err(dev, "Fail to get physical port id\n");
+
 		if (mlx4_is_master(dev))
 			mlx4_parav_master_pf_caps(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 40594055b831..7c83e6ccc9da 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -125,9 +125,14 @@ static struct mlx4_promisc_qp *get_promisc_qp(struct mlx4_dev *dev, u8 port,
 					      enum mlx4_steer_type steer,
 					      u32 qpn)
 {
-	struct mlx4_steer *s_steer = &mlx4_priv(dev)->steer[port - 1];
+	struct mlx4_steer *s_steer;
 	struct mlx4_promisc_qp *pqp;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return NULL;
+
+	s_steer = &mlx4_priv(dev)->steer[port - 1];
+
 	list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
 		if (pqp->qpn == qpn)
 			return pqp;
@@ -154,6 +159,9 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 port,
 	u32 prot;
 	int err;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return -EINVAL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 	new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
 	if (!new_entry)
@@ -238,6 +246,9 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 port,
 	struct mlx4_promisc_qp *pqp;
 	struct mlx4_promisc_qp *dqp;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return -EINVAL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
 	pqp = get_promisc_qp(dev, port, steer, qpn);
@@ -283,6 +294,9 @@ static bool check_duplicate_entry(struct mlx4_dev *dev, u8 port,
 	struct mlx4_steer_index *tmp_entry, *entry = NULL;
 	struct mlx4_promisc_qp *dqp, *tmp_dqp;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return NULL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
 	/* if qp is not promisc, it cannot be duplicated */
@@ -324,6 +338,9 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
 	bool ret = false;
 	int i;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return NULL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -378,6 +395,9 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 port,
 	int err;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return -EINVAL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 
 	mutex_lock(&priv->mcg_table.mutex);
@@ -484,6 +504,9 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 	int loc, i;
 	int err;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return -EINVAL;
+
 	s_steer = &mlx4_priv(dev)->steer[port - 1];
 	mutex_lock(&priv->mcg_table.mutex);
 
@@ -910,6 +933,9 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	u8 port = gid[5];
 	u8 new_entry = 0;
 
+	if (port < 1 || port > dev->caps.num_ports)
+		return -EINVAL;
+
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de59c05..123714cbd35f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -255,6 +255,8 @@ struct mlx4_en_tx_ring {
 	u16 poll_cnt;
 	struct mlx4_en_tx_info *tx_info;
 	u8 *bounce_buf;
+	u8 queue_index;
+	cpumask_t affinity_mask;
 	u32 last_nr_txbb;
 	struct mlx4_qp qp;
 	struct mlx4_qp_context context;
@@ -719,7 +721,8 @@ 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,
 			   struct mlx4_en_tx_ring **pring,
-			   int qpn, u32 size, u16 stride, int node);
+			   int qpn, u32 size, u16 stride,
+			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
@@ -741,6 +744,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
 			  struct mlx4_en_cq *cq,
 			  int budget);
 int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget);
+int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget);
 void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 		int is_tx, int rss, int qpn, int cqn, int user_prio,
 		struct mlx4_qp_context *context);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7d3a523160ba..294b7c58fe95 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -454,6 +454,7 @@ struct mlx4_caps {
 	u32			userspace_caps; /* userspace must be aware of these */
 	u32			function_caps;  /* VFs must be aware of these */
 	u16			hca_core_clock;
+	u64			phys_port_id[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_buf_list {
@@ -1113,6 +1114,7 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
+int mlx4_get_phys_port_id(struct mlx4_dev *dev);
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
 int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);