15 files changed, 882 insertions, 157 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 9ca3734ebb6b..5098e7f21987 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -24,13 +24,6 @@ config MLX4_EN_DCB
 
 	  If unsure, set to Y
 
-config MLX4_EN_VXLAN
-	bool "VXLAN offloads Support"
-	default y
-	depends on MLX4_EN && VXLAN && !(MLX4_EN=y && VXLAN=m)
-	---help---
-	  Say Y here if you want to use VXLAN offloads in the driver.
-
 config MLX4_CORE
 	tristate
 	depends on PCI
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index f01918c63f28..99c6bbdff501 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -37,6 +37,11 @@
 #include "mlx4_en.h"
 #include "fw_qos.h"
 
+enum {
+	MLX4_CEE_STATE_DOWN   = 0,
+	MLX4_CEE_STATE_UP     = 1,
+};
+
 /* Definitions for QCN
  */
 
@@ -80,13 +85,202 @@ struct mlx4_congestion_control_mb_prio_802_1_qau_statistics {
 	__be32 reserved3[4];
 };
 
+static u8 mlx4_en_dcbnl_getcap(struct net_device *dev, int capid, u8 *cap)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PFC:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = priv->cee_params.dcbx_cap;
+		break;
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 1 <<  mlx4_max_tc(priv->mdev->dev);
+		break;
+	default:
+		*cap = false;
+		break;
+	}
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	return priv->cee_params.dcb_cfg.pfc_state;
+}
+
+static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.pfc_state = state;
+}
+
+static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 *setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	*setting = priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc;
+}
+
+static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc = setting;
+	priv->cee_params.dcb_cfg.pfc_state = true;
+}
+
+static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	if (!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return -EINVAL;
+
+	if (tcid == DCB_NUMTCS_ATTR_PFC)
+		*num = mlx4_max_tc(priv->mdev->dev);
+	else
+		*num = 0;
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_cee_config *dcb_cfg = &priv->cee_params.dcb_cfg;
+	int err = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	if (dcb_cfg->pfc_state) {
+		int tc;
+
+		priv->prof->rx_pause = 0;
+		priv->prof->tx_pause = 0;
+		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
+			u8 tc_mask = 1 << tc;
+
+			switch (dcb_cfg->tc_config[tc].dcb_pfc) {
+			case pfc_disabled:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_full:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			case pfc_enabled_tx:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_rx:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			default:
+				break;
+			}
+		}
+		en_dbg(DRV, priv, "Set pfc on\n");
+	} else {
+		priv->prof->rx_pause = 1;
+		priv->prof->tx_pause = 1;
+		en_dbg(DRV, priv, "Set pfc off\n");
+	}
+
+	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
+				    priv->rx_skb_size + ETH_FCS_LEN,
+				    priv->prof->tx_pause,
+				    priv->prof->tx_ppp,
+				    priv->prof->rx_pause,
+				    priv->prof->rx_ppp);
+	if (err)
+		en_err(priv, "Failed setting pause params\n");
+	return err;
+}
+
+static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (priv->flags & MLX4_EN_FLAG_DCB_ENABLED)
+		return MLX4_CEE_STATE_UP;
+
+	return MLX4_CEE_STATE_DOWN;
+}
+
+static u8 mlx4_en_dcbnl_set_state(struct net_device *dev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int num_tcs = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 1;
+
+	if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return 0;
+
+	if (state) {
+		priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		num_tcs = IEEE_8021QAZ_MAX_TCS;
+	} else {
+		priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+	}
+
+	return mlx4_en_setup_tc(dev, num_tcs);
+}
+
+/* On success returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to
+ * indicate an error.
+ */
+static int mlx4_en_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app = {
+				.selector = idtype,
+				.protocol = id,
+			     };
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 0;
+
+	return dcb_getapp(netdev, &app);
+}
+
+static int mlx4_en_dcbnl_setapp(struct net_device *netdev, u8 idtype,
+				u16 id, u8 up)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	memset(&app, 0, sizeof(struct dcb_app));
+	app.selector = idtype;
+	app.protocol = id;
+	app.priority = up;
+
+	return dcb_setapp(netdev, &app);
+}
+
 static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct ieee_ets *my_ets = &priv->ets;
 
-	/* No IEEE PFC settings available */
 	if (!my_ets)
 		return -EINVAL;
 
@@ -237,18 +431,51 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 
 static u8 mlx4_en_dcbnl_getdcbx(struct net_device *dev)
 {
-	return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->cee_params.dcbx_cap;
 }
 
 static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct ieee_ets ets = {0};
+	struct ieee_pfc pfc = {0};
+
+	if (mode == priv->cee_params.dcbx_cap)
+		return 0;
+
 	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
-	    (mode & DCB_CAP_DCBX_VER_CEE) ||
-	    !(mode & DCB_CAP_DCBX_VER_IEEE) ||
+	    ((mode & DCB_CAP_DCBX_VER_IEEE) &&
+	     (mode & DCB_CAP_DCBX_VER_CEE)) ||
 	    !(mode & DCB_CAP_DCBX_HOST))
-		return 1;
+		goto err;
+
+	priv->cee_params.dcbx_cap = mode;
+
+	ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+	} else if (mode & DCB_CAP_DCBX_VER_CEE) {
+		if (mlx4_en_dcbnl_set_all(dev))
+			goto err;
+	} else {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+		if (mlx4_en_setup_tc(dev, 0))
+			goto err;
+	}
 
 	return 0;
+err:
+	return 1;
 }
 
 #define MLX4_RATELIMIT_UNITS_IN_KB 100000 /* rate-limit HW unit in Kbps */
@@ -463,24 +690,46 @@ static int mlx4_en_dcbnl_ieee_getqcnstats(struct net_device *dev,
 }
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops = {
-	.ieee_getets	= mlx4_en_dcbnl_ieee_getets,
-	.ieee_setets	= mlx4_en_dcbnl_ieee_setets,
-	.ieee_getmaxrate = mlx4_en_dcbnl_ieee_getmaxrate,
-	.ieee_setmaxrate = mlx4_en_dcbnl_ieee_setmaxrate,
-	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
-	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
+	.ieee_getets		= mlx4_en_dcbnl_ieee_getets,
+	.ieee_setets		= mlx4_en_dcbnl_ieee_setets,
+	.ieee_getmaxrate	= mlx4_en_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate	= mlx4_en_dcbnl_ieee_setmaxrate,
+	.ieee_getqcn		= mlx4_en_dcbnl_ieee_getqcn,
+	.ieee_setqcn		= mlx4_en_dcbnl_ieee_setqcn,
+	.ieee_getqcnstats	= mlx4_en_dcbnl_ieee_getqcnstats,
+	.ieee_getpfc		= mlx4_en_dcbnl_ieee_getpfc,
+	.ieee_setpfc		= mlx4_en_dcbnl_ieee_setpfc,
+
+	.getstate	= mlx4_en_dcbnl_get_state,
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getcap		= mlx4_en_dcbnl_getcap,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
 
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
-	.ieee_getqcn	= mlx4_en_dcbnl_ieee_getqcn,
-	.ieee_setqcn	= mlx4_en_dcbnl_ieee_setqcn,
-	.ieee_getqcnstats = mlx4_en_dcbnl_ieee_getqcnstats,
 };
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops = {
 	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
 	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
 
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
+
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 44cf16d01f42..bdda17d2ea0f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1112,7 +1112,7 @@ static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	return priv->rx_ring_num;
+	return rounddown_pow_of_two(priv->rx_ring_num);
 }
 
 static u32 mlx4_en_get_rxfh_key_size(struct net_device *netdev)
@@ -1146,19 +1146,17 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 			    u8 *hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
-	int rss_rings;
-	size_t n = priv->rx_ring_num;
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
+	u32 i, rss_rings;
 	int err = 0;
 
-	rss_rings = priv->prof->rss_rings ?: priv->rx_ring_num;
-	rss_rings = 1 << ilog2(rss_rings);
+	rss_rings = priv->prof->rss_rings ?: n;
+	rss_rings = rounddown_pow_of_two(rss_rings);
 
-	while (n--) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
 			break;
-		ring_index[n] = rss_map->qps[n % rss_rings].qpn -
-			rss_map->base_qpn;
+		ring_index[i] = i % rss_rings;
 	}
 	if (key)
 		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
@@ -1171,6 +1169,7 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 			    const u8 *key, const u8 hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int port_up = 0;
 	int err = 0;
@@ -1180,18 +1179,18 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	/* Calculate RSS table size and make sure flows are spread evenly
 	 * between rings
 	 */
-	for (i = 0; i < priv->rx_ring_num; i++) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
-			continue;
+			break;
 		if (i > 0 && !ring_index[i] && !rss_rings)
 			rss_rings = i;
 
-		if (ring_index[i] != (i % (rss_rings ?: priv->rx_ring_num)))
+		if (ring_index[i] != (i % (rss_rings ?: n)))
 			return -EINVAL;
 	}
 
 	if (!rss_rings)
-		rss_rings = priv->rx_ring_num;
+		rss_rings = n;
 
 	/* RSS table size must be an order of 2 */
 	if (!is_power_of_2(rss_rings))
@@ -1730,6 +1729,12 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	    !channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
+	if (channel->tx_count * MLX4_EN_NUM_UP <= priv->xdp_ring_num) {
+		en_err(priv, "Minimum %d tx channels required with XDP on\n",
+		       priv->xdp_ring_num / MLX4_EN_NUM_UP + 1);
+		return -EINVAL;
+	}
+
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp)
 		return -ENOMEM;
@@ -1751,7 +1756,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	mlx4_en_safe_replace_resources(priv, tmp);
 
-	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
+	netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
+							priv->xdp_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
 	if (dev->num_tc)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 8359e9e51b3b..4198e9bf89d0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -31,6 +31,7 @@
  *
  */
 
+#include <linux/bpf.h>
 #include <linux/etherdevice.h>
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
@@ -67,6 +68,17 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 		offset += priv->num_tx_rings_p_up;
 	}
 
+#ifdef CONFIG_MLX4_EN_DCB
+	if (!mlx4_is_slave(priv->mdev->dev)) {
+		if (up) {
+			priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		} else {
+			priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+			priv->cee_params.dcb_cfg.pfc_state = false;
+		}
+	}
+#endif /* CONFIG_MLX4_EN_DCB */
+
 	return 0;
 }
 
@@ -1201,8 +1213,8 @@ static void mlx4_en_netpoll(struct net_device *dev)
 	struct mlx4_en_cq *cq;
 	int i;
 
-	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = priv->rx_cq[i];
+	for (i = 0; i < priv->tx_ring_num; i++) {
+		cq = priv->tx_cq[i];
 		napi_schedule(&cq->napi);
 	}
 }
@@ -1510,6 +1522,24 @@ static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
 	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
 }
 
+static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv,
+				      int tx_ring_idx)
+{
+	struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[tx_ring_idx];
+	int rr_index;
+
+	rr_index = (priv->xdp_ring_num - priv->tx_ring_num) + tx_ring_idx;
+	if (rr_index >= 0) {
+		tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
+		tx_ring->recycle_ring = priv->rx_ring[rr_index];
+		en_dbg(DRV, priv,
+		       "Set tx_ring[%d]->recycle_ring = rx_ring[%d]\n",
+		       tx_ring_idx, rr_index);
+	} else {
+		tx_ring->recycle_ring = NULL;
+	}
+}
+
 int mlx4_en_start_port(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1632,6 +1662,8 @@ int mlx4_en_start_port(struct net_device *dev)
 		}
 		tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
 
+		mlx4_en_init_recycle_ring(priv, i);
+
 		/* Arm CQ for TX completions */
 		mlx4_en_arm_cq(priv, cq);
 
@@ -1696,10 +1728,9 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 	if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
-		vxlan_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
+
 	priv->port_up = true;
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
@@ -2177,6 +2208,11 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 		en_err(priv, "Bad MTU size:%d.\n", new_mtu);
 		return -EPERM;
 	}
+	if (priv->xdp_ring_num && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
+		en_err(priv, "MTU size:%d requires frags but XDP running\n",
+		       new_mtu);
+		return -EOPNOTSUPP;
+	}
 	dev->mtu = new_mtu;
 
 	if (netif_running(dev)) {
@@ -2434,7 +2470,6 @@ static int mlx4_en_get_phys_port_id(struct net_device *dev,
 	return 0;
 }
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
 {
 	int ret;
@@ -2484,15 +2519,19 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 }
 
 static void mlx4_en_add_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	if (ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2507,15 +2546,19 @@ static void mlx4_en_add_vxlan_port(struct  net_device *dev,
 }
 
 static void mlx4_en_del_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2550,7 +2593,6 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
 
 	return features;
 }
-#endif
 
 static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
 {
@@ -2579,6 +2621,103 @@ static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 m
 	return err;
 }
 
+static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct bpf_prog *old_prog;
+	int xdp_ring_num;
+	int port_up = 0;
+	int err;
+	int i;
+
+	xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0;
+
+	/* No need to reconfigure buffers when simply swapping the
+	 * program for a new one.
+	 */
+	if (priv->xdp_ring_num == xdp_ring_num) {
+		if (prog) {
+			prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+		}
+		for (i = 0; i < priv->rx_ring_num; i++) {
+			/* This xchg is paired with READ_ONCE in the fastpath */
+			old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+			if (old_prog)
+				bpf_prog_put(old_prog);
+		}
+		return 0;
+	}
+
+	if (priv->num_frags > 1) {
+		en_err(priv, "Cannot set XDP if MTU requires multiple frags\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (priv->tx_ring_num < xdp_ring_num + MLX4_EN_NUM_UP) {
+		en_err(priv,
+		       "Minimum %d tx channels required to run XDP\n",
+		       (xdp_ring_num + MLX4_EN_NUM_UP) / MLX4_EN_NUM_UP);
+		return -EINVAL;
+	}
+
+	if (prog) {
+		prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
+		if (IS_ERR(prog))
+			return PTR_ERR(prog);
+	}
+
+	mutex_lock(&mdev->state_lock);
+	if (priv->port_up) {
+		port_up = 1;
+		mlx4_en_stop_port(dev, 1);
+	}
+
+	priv->xdp_ring_num = xdp_ring_num;
+	netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
+							priv->xdp_ring_num);
+
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+	}
+
+	if (port_up) {
+		err = mlx4_en_start_port(dev);
+		if (err) {
+			en_err(priv, "Failed starting port %d for XDP change\n",
+			       priv->port);
+			queue_work(mdev->workqueue, &priv->watchdog_task);
+		}
+	}
+
+	mutex_unlock(&mdev->state_lock);
+	return 0;
+}
+
+static bool mlx4_xdp_attached(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return !!priv->xdp_ring_num;
+}
+
+static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return mlx4_xdp_set(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = mlx4_xdp_attached(dev);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
@@ -2603,12 +2742,11 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
+	.ndo_xdp		= mlx4_xdp,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2641,12 +2779,11 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
+	.ndo_xdp		= mlx4_xdp,
 };
 
 struct mlx4_en_bond {
@@ -2911,6 +3048,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	struct mlx4_en_priv *priv;
 	int i;
 	int err;
+#ifdef CONFIG_MLX4_EN_DCB
+	struct tc_configuration *tc;
+#endif
 
 	dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
 				 MAX_TX_RINGS, MAX_RX_RINGS);
@@ -2936,10 +3076,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
-#ifdef CONFIG_MLX4_EN_VXLAN
 	INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
 	INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
-#endif
 #ifdef CONFIG_RFS_ACCEL
 	INIT_LIST_HEAD(&priv->filters);
 	spin_lock_init(&priv->filters_lock);
@@ -2979,6 +3117,17 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
+					    DCB_CAP_DCBX_HOST |
+					    DCB_CAP_DCBX_VER_IEEE;
+		priv->flags |= MLX4_EN_DCB_ENABLED;
+		priv->cee_params.dcb_cfg.pfc_state = false;
+
+		for (i = 0; i < MLX4_EN_NUM_UP; i++) {
+			tc = &priv->cee_params.dcb_cfg.tc_config[i];
+			tc->dcb_pfc = pfc_disabled;
+		}
+
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
 			dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
 		} else {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 99b5407f2278..2040dad8611d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -32,6 +32,7 @@
  */
 
 #include <net/busy_poll.h>
+#include <linux/bpf.h>
 #include <linux/mlx4/cq.h>
 #include <linux/slab.h>
 #include <linux/mlx4/qp.h>
@@ -57,7 +58,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 	struct page *page;
 	dma_addr_t dma;
 
-	for (order = MLX4_EN_ALLOC_PREFER_ORDER; ;) {
+	for (order = frag_info->order; ;) {
 		gfp_t gfp = _gfp;
 
 		if (order)
@@ -70,7 +71,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 			return -ENOMEM;
 	}
 	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order,
-			   PCI_DMA_FROMDEVICE);
+			   frag_info->dma_dir);
 	if (dma_mapping_error(priv->ddev, dma)) {
 		put_page(page);
 		return -ENOMEM;
@@ -124,7 +125,8 @@ out:
 	while (i--) {
 		if (page_alloc[i].page != ring_alloc[i].page) {
 			dma_unmap_page(priv->ddev, page_alloc[i].dma,
-				page_alloc[i].page_size, PCI_DMA_FROMDEVICE);
+				page_alloc[i].page_size,
+				priv->frag_info[i].dma_dir);
 			page = page_alloc[i].page;
 			/* Revert changes done by mlx4_alloc_pages */
 			page_ref_sub(page, page_alloc[i].page_size /
@@ -145,7 +147,7 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
 
 	if (next_frag_end > frags[i].page_size)
 		dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size,
-			       PCI_DMA_FROMDEVICE);
+			       frag_info->dma_dir);
 
 	if (frags[i].page)
 		put_page(frags[i].page);
@@ -176,7 +178,8 @@ out:
 
 		page_alloc = &ring->page_alloc[i];
 		dma_unmap_page(priv->ddev, page_alloc->dma,
-			       page_alloc->page_size, PCI_DMA_FROMDEVICE);
+			       page_alloc->page_size,
+			       priv->frag_info[i].dma_dir);
 		page = page_alloc->page;
 		/* Revert changes done by mlx4_alloc_pages */
 		page_ref_sub(page, page_alloc->page_size /
@@ -201,7 +204,7 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
 		       i, page_count(page_alloc->page));
 
 		dma_unmap_page(priv->ddev, page_alloc->dma,
-				page_alloc->page_size, PCI_DMA_FROMDEVICE);
+				page_alloc->page_size, frag_info->dma_dir);
 		while (page_alloc->page_offset + frag_info->frag_stride <
 		       page_alloc->page_size) {
 			put_page(page_alloc->page);
@@ -244,6 +247,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
 
+	if (ring->page_cache.index > 0) {
+		frags[0] = ring->page_cache.buf[--ring->page_cache.index];
+		rx_desc->data[0].addr = cpu_to_be64(frags[0].dma);
+		return 0;
+	}
+
 	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
 }
 
@@ -502,13 +511,35 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 	}
 }
 
+/* When the rx ring is running in page-per-packet mode, a released frame can go
+ * directly into a small cache, to avoid unmapping or touching the page
+ * allocator. In bpf prog performance scenarios, buffers are either forwarded
+ * or dropped, never converted to skbs, so every page can come directly from
+ * this cache when it is sized to be a multiple of the napi budget.
+ */
+bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
+			struct mlx4_en_rx_alloc *frame)
+{
+	struct mlx4_en_page_cache *cache = &ring->page_cache;
+
+	if (cache->index >= MLX4_EN_CACHE_SIZE)
+		return false;
+
+	cache->buf[cache->index++] = *frame;
+	return true;
+}
+
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_rx_ring *ring = *pring;
+	struct bpf_prog *old_prog;
 
+	old_prog = READ_ONCE(ring->xdp_prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	vfree(ring->rx_info);
 	ring->rx_info = NULL;
@@ -519,6 +550,16 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_rx_ring *ring)
 {
+	int i;
+
+	for (i = 0; i < ring->page_cache.index; i++) {
+		struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i];
+
+		dma_unmap_page(priv->ddev, frame->dma, frame->page_size,
+			       priv->frag_info[0].dma_dir);
+		put_page(frame->page);
+	}
+	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
@@ -740,7 +781,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
 	struct mlx4_en_rx_alloc *frags;
 	struct mlx4_en_rx_desc *rx_desc;
+	struct bpf_prog *xdp_prog;
+	int doorbell_pending;
 	struct sk_buff *skb;
+	int tx_index;
 	int index;
 	int nr;
 	unsigned int length;
@@ -756,6 +800,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	if (budget <= 0)
 		return polled;
 
+	xdp_prog = READ_ONCE(ring->xdp_prog);
+	doorbell_pending = 0;
+	tx_index = (priv->tx_ring_num - priv->xdp_ring_num) + cq->ring;
+
 	/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
 	 * descriptor offset can be deduced from the CQE index instead of
 	 * reading 'cqe->index' */
@@ -832,6 +880,43 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
 			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
+		/* A bpf program gets first chance to drop the packet. It may
+		 * read bytes but not past the end of the frag.
+		 */
+		if (xdp_prog) {
+			struct xdp_buff xdp;
+			dma_addr_t dma;
+			u32 act;
+
+			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma_sync_single_for_cpu(priv->ddev, dma,
+						priv->frag_info[0].frag_size,
+						DMA_FROM_DEVICE);
+
+			xdp.data = page_address(frags[0].page) +
+							frags[0].page_offset;
+			xdp.data_end = xdp.data + length;
+
+			act = bpf_prog_run_xdp(xdp_prog, &xdp);
+			switch (act) {
+			case XDP_PASS:
+				break;
+			case XDP_TX:
+				if (!mlx4_en_xmit_frame(frags, dev,
+							length, tx_index,
+							&doorbell_pending))
+					goto consumed;
+				break;
+			default:
+				bpf_warn_invalid_xdp_action(act);
+			case XDP_ABORTED:
+			case XDP_DROP:
+				if (mlx4_en_rx_recycle(ring, frags))
+					goto consumed;
+				goto next;
+			}
+		}
+
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {
@@ -983,6 +1068,7 @@ next:
 		for (nr = 0; nr < priv->num_frags; nr++)
 			mlx4_en_free_frag(priv, frags, nr);
 
+consumed:
 		++cq->mcq.cons_index;
 		index = (cq->mcq.cons_index) & ring->size_mask;
 		cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor;
@@ -991,6 +1077,9 @@ next:
 	}
 
 out:
+	if (doorbell_pending)
+		mlx4_en_xmit_doorbell(priv->tx_ring[tx_index]);
+
 	AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
 	mlx4_cq_set_ci(&cq->mcq);
 	wmb(); /* ensure HW sees CQ consumer before we post new buffers */
@@ -1058,22 +1147,35 @@ static const int frag_sizes[] = {
 
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
+	enum dma_data_direction dma_dir = PCI_DMA_FROMDEVICE;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	/* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
-	 * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
-	 */
-	int eff_mtu = dev->mtu + ETH_HLEN + (2 * VLAN_HLEN);
+	int eff_mtu = MLX4_EN_EFF_MTU(dev->mtu);
+	int order = MLX4_EN_ALLOC_PREFER_ORDER;
+	u32 align = SMP_CACHE_BYTES;
 	int buf_size = 0;
 	int i = 0;
 
+	/* bpf requires buffers to be set up as 1 packet per page.
+	 * This only works when num_frags == 1.
+	 */
+	if (priv->xdp_ring_num) {
+		dma_dir = PCI_DMA_BIDIRECTIONAL;
+		/* This will gain efficient xdp frame recycling at the expense
+		 * of more costly truesize accounting
+		 */
+		align = PAGE_SIZE;
+		order = 0;
+	}
+
 	while (buf_size < eff_mtu) {
+		priv->frag_info[i].order = order;
 		priv->frag_info[i].frag_size =
 			(eff_mtu > buf_size + frag_sizes[i]) ?
 				frag_sizes[i] : eff_mtu - buf_size;
 		priv->frag_info[i].frag_prefix_size = buf_size;
 		priv->frag_info[i].frag_stride =
-				ALIGN(priv->frag_info[i].frag_size,
-				      SMP_CACHE_BYTES);
+				ALIGN(priv->frag_info[i].frag_size, align);
+		priv->frag_info[i].dma_dir = dma_dir;
 		buf_size += priv->frag_info[i].frag_size;
 		i++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 76aa4d27183c..9df87ca0515a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -196,6 +196,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	ring->last_nr_txbb = 1;
 	memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
 	memset(ring->buf, 0, ring->buf_size);
+	ring->free_tx_desc = mlx4_en_free_tx_desc;
 
 	ring->qp_state = MLX4_QP_STATE_RST;
 	ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
@@ -265,10 +266,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 }
 
 
-static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
-				struct mlx4_en_tx_ring *ring,
-				int index, u8 owner, u64 timestamp,
-				int napi_mode)
+u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+			 struct mlx4_en_tx_ring *ring,
+			 int index, u8 owner, u64 timestamp,
+			 int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
 	struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
@@ -344,6 +345,27 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	return tx_info->nr_txbb;
 }
 
+u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+			    struct mlx4_en_tx_ring *ring,
+			    int index, u8 owner, u64 timestamp,
+			    int napi_mode)
+{
+	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
+	struct mlx4_en_rx_alloc frame = {
+		.page = tx_info->page,
+		.dma = tx_info->map0_dma,
+		.page_offset = 0,
+		.page_size = PAGE_SIZE,
+	};
+
+	if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
+		dma_unmap_page(priv->ddev, tx_info->map0_dma,
+			       PAGE_SIZE, priv->frag_info[0].dma_dir);
+		put_page(tx_info->page);
+	}
+
+	return tx_info->nr_txbb;
+}
 
 int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 {
@@ -362,7 +384,7 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	}
 
 	while (ring->cons != ring->prod) {
-		ring->last_nr_txbb = mlx4_en_free_tx_desc(priv, ring,
+		ring->last_nr_txbb = ring->free_tx_desc(priv, ring,
 						ring->cons & ring->size_mask,
 						!!(ring->cons & ring->size), 0,
 						0 /* Non-NAPI caller */);
@@ -444,7 +466,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-			last_nr_txbb = mlx4_en_free_tx_desc(
+			last_nr_txbb = ring->free_tx_desc(
 					priv, ring, ring_index,
 					!!((ring_cons + txbbs_skipped) &
 					ring->size), timestamp, napi_budget);
@@ -476,6 +498,9 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb;
 	ACCESS_ONCE(ring->cons) = ring_cons + txbbs_skipped;
 
+	if (ring->free_tx_desc == mlx4_en_recycle_tx_desc)
+		return done < budget;
+
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
 	/* Wakeup Tx queue if this stopped, and ring is not full.
@@ -631,8 +656,7 @@ static int get_real_size(const struct sk_buff *skb,
 static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 			     const struct sk_buff *skb,
 			     const struct skb_shared_info *shinfo,
-			     int real_size, u16 *vlan_tag,
-			     int tx_ind, void *fragptr)
+			     void *fragptr)
 {
 	struct mlx4_wqe_inline_seg *inl = &tx_desc->inl;
 	int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl;
@@ -700,10 +724,66 @@ static void mlx4_bf_copy(void __iomem *dst, const void *src,
 	__iowrite64_copy(dst, src, bytecnt / 8);
 }
 
+void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring)
+{
+	wmb();
+	/* Since there is no iowrite*_native() that writes the
+	 * value as is, without byteswapping - using the one
+	 * the doesn't do byteswapping in the relevant arch
+	 * endianness.
+	 */
+#if defined(__LITTLE_ENDIAN)
+	iowrite32(
+#else
+	iowrite32be(
+#endif
+		  ring->doorbell_qpn,
+		  ring->bf.uar->map + MLX4_SEND_DOORBELL);
+}
+
+static void mlx4_en_tx_write_desc(struct mlx4_en_tx_ring *ring,
+				  struct mlx4_en_tx_desc *tx_desc,
+				  union mlx4_wqe_qpn_vlan qpn_vlan,
+				  int desc_size, int bf_index,
+				  __be32 op_own, bool bf_ok,
+				  bool send_doorbell)
+{
+	tx_desc->ctrl.qpn_vlan = qpn_vlan;
+
+	if (bf_ok) {
+		op_own |= htonl((bf_index & 0xffff) << 8);
+		/* Ensure new descriptor hits memory
+		 * before setting ownership of this descriptor to HW
+		 */
+		dma_wmb();
+		tx_desc->ctrl.owner_opcode = op_own;
+
+		wmb();
+
+		mlx4_bf_copy(ring->bf.reg + ring->bf.offset, &tx_desc->ctrl,
+			     desc_size);
+
+		wmb();
+
+		ring->bf.offset ^= ring->bf.buf_size;
+	} else {
+		/* Ensure new descriptor hits memory
+		 * before setting ownership of this descriptor to HW
+		 */
+		dma_wmb();
+		tx_desc->ctrl.owner_opcode = op_own;
+		if (send_doorbell)
+			mlx4_en_xmit_doorbell(ring);
+		else
+			ring->xmit_more++;
+	}
+}
+
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	union mlx4_wqe_qpn_vlan	qpn_vlan = {};
 	struct device *ddev = priv->ddev;
 	struct mlx4_en_tx_ring *ring;
 	struct mlx4_en_tx_desc *tx_desc;
@@ -715,7 +795,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	int real_size;
 	u32 index, bf_index;
 	__be32 op_own;
-	u16 vlan_tag = 0;
 	u16 vlan_proto = 0;
 	int i_frag;
 	int lso_header_size;
@@ -725,6 +804,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool stop_queue;
 	bool inline_ok;
 	u32 ring_cons;
+	bool bf_ok;
 
 	tx_ind = skb_get_queue_mapping(skb);
 	ring = priv->tx_ring[tx_ind];
@@ -749,9 +829,17 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_drop;
 	}
 
+	bf_ok = ring->bf_enabled;
 	if (skb_vlan_tag_present(skb)) {
-		vlan_tag = skb_vlan_tag_get(skb);
+		qpn_vlan.vlan_tag = cpu_to_be16(skb_vlan_tag_get(skb));
 		vlan_proto = be16_to_cpu(skb->vlan_proto);
+		if (vlan_proto == ETH_P_8021AD)
+			qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
+		else if (vlan_proto == ETH_P_8021Q)
+			qpn_vlan.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
+		else
+			qpn_vlan.ins_vlan = 0;
+		bf_ok = false;
 	}
 
 	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
@@ -771,6 +859,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	else {
 		tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf;
 		bounce = true;
+		bf_ok = false;
 	}
 
 	/* Save skb in tx_info ring */
@@ -907,8 +996,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
 
 	if (tx_info->inl)
-		build_inline_wqe(tx_desc, skb, shinfo, real_size, &vlan_tag,
-				 tx_ind, fragptr);
+		build_inline_wqe(tx_desc, skb, shinfo, fragptr);
 
 	if (skb->encapsulation) {
 		union {
@@ -946,60 +1034,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	real_size = (real_size / 16) & 0x3f;
 
-	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce &&
-	    !skb_vlan_tag_present(skb) && send_doorbell) {
-		tx_desc->ctrl.bf_qpn = ring->doorbell_qpn |
-				       cpu_to_be32(real_size);
-
-		op_own |= htonl((bf_index & 0xffff) << 8);
-		/* Ensure new descriptor hits memory
-		 * before setting ownership of this descriptor to HW
-		 */
-		dma_wmb();
-		tx_desc->ctrl.owner_opcode = op_own;
-
-		wmb();
+	bf_ok &= desc_size <= MAX_BF && send_doorbell;
 
-		mlx4_bf_copy(ring->bf.reg + ring->bf.offset, &tx_desc->ctrl,
-			     desc_size);
-
-		wmb();
-
-		ring->bf.offset ^= ring->bf.buf_size;
-	} else {
-		tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
-		if (vlan_proto == ETH_P_8021AD)
-			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
-		else if (vlan_proto == ETH_P_8021Q)
-			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
-		else
-			tx_desc->ctrl.ins_vlan = 0;
-
-		tx_desc->ctrl.fence_size = real_size;
+	if (bf_ok)
+		qpn_vlan.bf_qpn = ring->doorbell_qpn | cpu_to_be32(real_size);
+	else
+		qpn_vlan.fence_size = real_size;
 
-		/* Ensure new descriptor hits memory
-		 * before setting ownership of this descriptor to HW
-		 */
-		dma_wmb();
-		tx_desc->ctrl.owner_opcode = op_own;
-		if (send_doorbell) {
-			wmb();
-			/* Since there is no iowrite*_native() that writes the
-			 * value as is, without byteswapping - using the one
-			 * the doesn't do byteswapping in the relevant arch
-			 * endianness.
-			 */
-#if defined(__LITTLE_ENDIAN)
-			iowrite32(
-#else
-			iowrite32be(
-#endif
-				  ring->doorbell_qpn,
-				  ring->bf.uar->map + MLX4_SEND_DOORBELL);
-		} else {
-			ring->xmit_more++;
-		}
-	}
+	mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, desc_size, bf_index,
+			      op_own, bf_ok, send_doorbell);
 
 	if (unlikely(stop_queue)) {
 		/* If queue was emptied after the if (stop_queue) , and before
@@ -1034,3 +1077,106 @@ tx_drop:
 	return NETDEV_TX_OK;
 }
 
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+			       struct net_device *dev, unsigned int length,
+			       int tx_ind, int *doorbell_pending)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	union mlx4_wqe_qpn_vlan	qpn_vlan = {};
+	struct mlx4_en_tx_ring *ring;
+	struct mlx4_en_tx_desc *tx_desc;
+	struct mlx4_wqe_data_seg *data;
+	struct mlx4_en_tx_info *tx_info;
+	int index, bf_index;
+	bool send_doorbell;
+	int nr_txbb = 1;
+	bool stop_queue;
+	dma_addr_t dma;
+	int real_size;
+	__be32 op_own;
+	u32 ring_cons;
+	bool bf_ok;
+
+	BUILD_BUG_ON_MSG(ALIGN(CTRL_SIZE + DS_SIZE, TXBB_SIZE) != TXBB_SIZE,
+			 "mlx4_en_xmit_frame requires minimum size tx desc");
+
+	ring = priv->tx_ring[tx_ind];
+
+	if (!priv->port_up)
+		goto tx_drop;
+
+	if (mlx4_en_is_tx_ring_full(ring))
+		goto tx_drop;
+
+	/* fetch ring->cons far ahead before needing it to avoid stall */
+	ring_cons = READ_ONCE(ring->cons);
+
+	index = ring->prod & ring->size_mask;
+	tx_info = &ring->tx_info[index];
+
+	bf_ok = ring->bf_enabled;
+
+	/* Track current inflight packets for performance analysis */
+	AVG_PERF_COUNTER(priv->pstats.inflight_avg,
+			 (u32)(ring->prod - ring_cons - 1));
+
+	bf_index = ring->prod;
+	tx_desc = ring->buf + index * TXBB_SIZE;
+	data = &tx_desc->data;
+
+	dma = frame->dma;
+
+	tx_info->page = frame->page;
+	frame->page = NULL;
+	tx_info->map0_dma = dma;
+	tx_info->map0_byte_count = length;
+	tx_info->nr_txbb = nr_txbb;
+	tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
+	tx_info->data_offset = (void *)data - (void *)tx_desc;
+	tx_info->ts_requested = 0;
+	tx_info->nr_maps = 1;
+	tx_info->linear = 1;
+	tx_info->inl = 0;
+
+	dma_sync_single_for_device(priv->ddev, dma, length, PCI_DMA_TODEVICE);
+
+	data->addr = cpu_to_be64(dma);
+	data->lkey = ring->mr_key;
+	dma_wmb();
+	data->byte_count = cpu_to_be32(length);
+
+	/* tx completion can avoid cache line miss for common cases */
+	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
+
+	op_own = cpu_to_be32(MLX4_OPCODE_SEND) |
+		((ring->prod & ring->size) ?
+		 cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
+
+	ring->packets++;
+	ring->bytes += tx_info->nr_bytes;
+	AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length);
+
+	ring->prod += nr_txbb;
+
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
+	send_doorbell = stop_queue ||
+				*doorbell_pending > MLX4_EN_DOORBELL_BUDGET;
+	bf_ok &= send_doorbell;
+
+	real_size = ((CTRL_SIZE + nr_txbb * DS_SIZE) / 16) & 0x3f;
+
+	if (bf_ok)
+		qpn_vlan.bf_qpn = ring->doorbell_qpn | cpu_to_be32(real_size);
+	else
+		qpn_vlan.fence_size = real_size;
+
+	mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, bf_index,
+			      op_own, bf_ok, send_doorbell);
+	*doorbell_pending = send_doorbell ? 0 : *doorbell_pending + 1;
+
+	return NETDEV_TX_OK;
+
+tx_drop:
+	ring->tx_dropped++;
+	return NETDEV_TX_BUSY;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e97094598b2d..f4497cf4d06d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1128,6 +1128,7 @@ int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_c
 		port_cap->max_pkeys	   = 1 << (field & 0xf);
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
 		port_cap->max_vl	   = field & 0xf;
+		port_cap->max_tc_eth	   = field >> 4;
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
 		port_cap->log_max_macs  = field & 0xf;
 		port_cap->log_max_vlans = field >> 4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 7ea258af636a..cdbd76f10ced 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -53,6 +53,7 @@ struct mlx4_port_cap {
 	int ib_mtu;
 	int max_port_width;
 	int max_vl;
+	int max_tc_eth;
 	int max_gids;
 	int max_pkeys;
 	u64 def_mac;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index dec77d6f0ac9..0e8b7c44931f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -147,7 +147,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 	if (enable) {
 		dev->flags |= MLX4_FLAG_BONDED;
 	} else {
-		 ret = mlx4_virt2phy_port_map(dev, 1, 2);
+		ret = mlx4_virt2phy_port_map(dev, 1, 2);
 		if (ret) {
 			mlx4_err(dev, "Fail to reset port map\n");
 			return ret;
@@ -218,6 +218,9 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_interface *intf;
 
+	if (!(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP))
+		return;
+
 	mlx4_stop_catas_poll(dev);
 	mutex_lock(&intf_mutex);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 546fab0ecc3b..75dd2e3d3059 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -292,6 +292,7 @@ static int _mlx4_dev_port(struct mlx4_dev *dev, int port,
 	dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
 	dev->caps.port_width_cap[port] = port_cap->max_port_width;
 	dev->caps.eth_mtu_cap[port]    = port_cap->eth_mtu;
+	dev->caps.max_tc_eth	       = port_cap->max_tc_eth;
 	dev->caps.def_mac[port]        = port_cap->def_mac;
 	dev->caps.supported_type[port] = port_cap->supported_port_types;
 	dev->caps.suggested_type[port] = port_cap->suggested_type;
@@ -2599,7 +2600,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 	err = mlx4_init_uar_table(dev);
 	if (err) {
 		mlx4_err(dev, "Failed to initialize user access region table, aborting\n");
-		 return err;
+		return err;
 	}
 
 	err = mlx4_uar_alloc(dev, &priv->driver_uar);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index f2d0920018a5..94b891c118c1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -618,8 +618,8 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 				err = mlx4_READ_ENTRY(dev,
 						      entry->index,
 						      mailbox);
-					if (err)
-						goto out_mailbox;
+				if (err)
+					goto out_mailbox;
 				members_count =
 					be32_to_cpu(mgm->members_count) &
 					0xffffff;
@@ -657,8 +657,8 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 				err = mlx4_WRITE_ENTRY(dev,
 						       entry->index,
 						       mailbox);
-					if (err)
-						goto out_mailbox;
+				if (err)
+					goto out_mailbox;
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 13d297ee34bb..2c2913dcae98 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -132,6 +132,7 @@ enum {
 					 MLX4_EN_NUM_UP)
 
 #define MLX4_EN_DEFAULT_TX_WORK		256
+#define MLX4_EN_DOORBELL_BUDGET		8
 
 /* Target number of packets to coalesce with interrupt moderation */
 #define MLX4_EN_RX_COAL_TARGET	44
@@ -164,6 +165,10 @@ enum {
 #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN)
 
 #define MLX4_EN_MIN_MTU		46
+/* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
+ * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
+ */
+#define MLX4_EN_EFF_MTU(mtu)	((mtu) + ETH_HLEN + (2 * VLAN_HLEN))
 #define ETH_BCAST		0xffffffffffffULL
 
 #define MLX4_EN_LOOPBACK_RETRIES	5
@@ -215,7 +220,10 @@ enum cq_type {
 
 
 struct mlx4_en_tx_info {
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		struct page *page;
+	};
 	dma_addr_t	map0_dma;
 	u32		map0_byte_count;
 	u32		nr_txbb;
@@ -255,6 +263,14 @@ struct mlx4_en_rx_alloc {
 	u32		page_size;
 };
 
+#define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
+struct mlx4_en_page_cache {
+	u32 index;
+	struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE];
+};
+
+struct mlx4_en_priv;
+
 struct mlx4_en_tx_ring {
 	/* cache line used and dirtied in tx completion
 	 * (mlx4_en_free_tx_buf())
@@ -288,6 +304,11 @@ struct mlx4_en_tx_ring {
 	__be32			mr_key;
 	void			*buf;
 	struct mlx4_en_tx_info	*tx_info;
+	struct mlx4_en_rx_ring	*recycle_ring;
+	u32			(*free_tx_desc)(struct mlx4_en_priv *priv,
+						struct mlx4_en_tx_ring *ring,
+						int index, u8 owner,
+						u64 timestamp, int napi_mode);
 	u8			*bounce_buf;
 	struct mlx4_qp_context	context;
 	int			qpn;
@@ -319,6 +340,8 @@ struct mlx4_en_rx_ring {
 	u8  fcs_del;
 	void *buf;
 	void *rx_info;
+	struct bpf_prog *xdp_prog;
+	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long csum_ok;
@@ -440,7 +463,9 @@ struct mlx4_en_mc_list {
 struct mlx4_en_frag_info {
 	u16 frag_size;
 	u16 frag_prefix_size;
-	u16 frag_stride;
+	u32 frag_stride;
+	enum dma_data_direction dma_dir;
+	int order;
 };
 
 #ifdef CONFIG_MLX4_EN_DCB
@@ -450,6 +475,27 @@ struct mlx4_en_frag_info {
 
 #define MLX4_EN_TC_ETS 7
 
+enum dcb_pfc_type {
+	pfc_disabled = 0,
+	pfc_enabled_full,
+	pfc_enabled_tx,
+	pfc_enabled_rx
+};
+
+struct tc_configuration {
+	enum dcb_pfc_type  dcb_pfc;
+};
+
+struct mlx4_en_cee_config {
+	bool	pfc_state;
+	struct	tc_configuration tc_config[MLX4_EN_NUM_UP];
+};
+
+struct mlx4_en_cee_params {
+	u8 dcbx_cap;
+	struct mlx4_en_cee_config dcb_cfg;
+};
+
 #endif
 
 struct ethtool_flow_id {
@@ -469,6 +515,9 @@ enum {
 	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3),
 	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4),
 	MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP	= (1 << 5),
+#ifdef CONFIG_MLX4_EN_DCB
+	MLX4_EN_FLAG_DCB_ENABLED        = (1 << 6),
+#endif
 };
 
 #define PORT_BEACON_MAX_LIMIT (65535)
@@ -536,6 +585,7 @@ struct mlx4_en_priv {
 	struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
 	u16 num_frags;
 	u16 log_rx_info;
+	int xdp_ring_num;
 
 	struct mlx4_en_tx_ring **tx_ring;
 	struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
@@ -547,10 +597,8 @@ struct mlx4_en_priv {
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
-#ifdef CONFIG_MLX4_EN_VXLAN
 	struct work_struct vxlan_add_task;
 	struct work_struct vxlan_del_task;
-#endif
 	struct mlx4_en_perf_stats pstats;
 	struct mlx4_en_pkt_stats pkstats;
 	struct mlx4_en_counter_stats pf_stats;
@@ -572,9 +620,11 @@ struct mlx4_en_priv {
 	u32 counter_index;
 
 #ifdef CONFIG_MLX4_EN_DCB
+#define MLX4_EN_DCB_ENABLED	0x3
 	struct ieee_ets ets;
 	u16 maxrate[IEEE_8021QAZ_MAX_TCS];
 	enum dcbnl_cndd_states cndd_state[IEEE_8021QAZ_MAX_TCS];
+	struct mlx4_en_cee_params cee_params;
 #endif
 #ifdef CONFIG_RFS_ACCEL
 	spinlock_t filters_lock;
@@ -644,6 +694,12 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 			 void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+			       struct net_device *dev, unsigned int length,
+			       int tx_ind, int *doorbell_pending);
+void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
+bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
+			struct mlx4_en_rx_alloc *frame);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
@@ -672,6 +728,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
 			  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);
+u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+			 struct mlx4_en_tx_ring *ring,
+			 int index, u8 owner, u64 timestamp,
+			 int napi_mode);
+u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+			    struct mlx4_en_tx_ring *ring,
+			    int index, u8 owner, u64 timestamp,
+			    int napi_mode);
 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/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 93195191f45b..395b5463cfd9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -248,7 +248,7 @@ static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
 				  offset, order);
 		return;
 	}
-	 __mlx4_free_mtt_range(dev, offset, order);
+	__mlx4_free_mtt_range(dev, offset, order);
 }
 
 void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 087b23b320cb..3d2095e5c61c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -52,6 +52,7 @@
 
 #define MLX4_FLAG_V_IGNORE_FCS_MASK		0x2
 #define MLX4_IGNORE_FCS_MASK			0x1
+#define MLNX4_TX_MAX_NUMBER			8
 
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
 {
@@ -2015,3 +2016,14 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(mlx4_get_module_info);
+
+int mlx4_max_tc(struct mlx4_dev *dev)
+{
+	u8 num_tc = dev->caps.max_tc_eth;
+
+	if (!num_tc)
+		num_tc = MLNX4_TX_MAX_NUMBER;
+
+	return num_tc;
+}
+EXPORT_SYMBOL(mlx4_max_tc);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index cd9b2b28df88..8b81114bdc72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2372,16 +2372,15 @@ static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		__mlx4_mpt_release(dev, index);
 		break;
 	case RES_OP_MAP_ICM:
-			index = get_param_l(&in_param);
-			id = index & mpt_mask(dev);
-			err = mr_res_start_move_to(dev, slave, id,
-						   RES_MPT_RESERVED, &mpt);
-			if (err)
-				return err;
-
-			__mlx4_mpt_free_icm(dev, mpt->key);
-			res_end_move(dev, slave, RES_MPT, id);
+		index = get_param_l(&in_param);
+		id = index & mpt_mask(dev);
+		err = mr_res_start_move_to(dev, slave, id,
+					   RES_MPT_RESERVED, &mpt);
+		if (err)
 			return err;
+
+		__mlx4_mpt_free_icm(dev, mpt->key);
+		res_end_move(dev, slave, RES_MPT, id);
 		break;
 	default:
 		err = -EINVAL;
@@ -4253,9 +4252,8 @@ int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
 	     (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_MC_LB)) &&
 		!(dev->caps.flags2 &
 		  MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB)) {
-			mlx4_warn(dev,
-				  "Src check LB for slave %d isn't supported\n",
-				   slave);
+		mlx4_warn(dev, "Src check LB for slave %d isn't supported\n",
+			  slave);
 		return -ENOTSUPP;
 	}