Merge branch 'mlx4'

Amir Vadai says:

====================
This series from Yan Burman adds support for unicast MAC address filtering and
ndo FDB operations.  It also includes some optimizations to loopback related
decisions and checks in the TX/RX fast path and one cleanup, all in separate
patches.

Today, when adding macvlan devices, the NIC goes into promiscuous mode, since
unicast MAC filtering is not supported. With these changes, macvlan devices can
be added without the penalty of promiscuous mode.

If for some reason adding a unicast address filter fails e.g as of missing space in
the HW mac table, the device forces itself into promiscuous mode (and out of this
forced state when enough space is available).

Also, now it is possible to have bridge under multi-function configuration that include
PF and VFs.  In order to use bridge over PF/VFs, VM MAC fdb entries must be added e.g.
using 'bridge fdb add' command.

Changes from v1 - based on more comments from Eric Dumazet:
* added failure handling when adding unicast address filter

Changes from v0 - based on comments from Eric Dumazet:
* Removed unneeded synchronize_rcu()
* Use kfree_rcu() instead of synchronize_rcu() + kfree()
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 709 insertions, 388 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index f523f0204f1..8a08c5e71e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -712,16 +712,13 @@ static int mlx4_en_ethtool_add_mac_rule_by_ipv4(struct mlx4_en_priv *priv,
 						__be32 ipv4_dst)
 {
 #ifdef CONFIG_INET
-	__be64 be_mac = 0;
 	unsigned char mac[ETH_ALEN];
 
 	if (!ipv4_is_multicast(ipv4_dst)) {
-		if (cmd->fs.flow_type & FLOW_MAC_EXT) {
+		if (cmd->fs.flow_type & FLOW_MAC_EXT)
 			memcpy(&mac, cmd->fs.h_ext.h_dest, ETH_ALEN);
-		} else {
-			be_mac = cpu_to_be64((priv->mac & MLX4_MAC_MASK) << 16);
-			memcpy(&mac, &be_mac, ETH_ALEN);
-		}
+		else
+			memcpy(&mac, priv->dev->dev_addr, ETH_ALEN);
 	} else {
 		ip_eth_mc_map(ipv4_dst, mac);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index f3c7961a271..e3c3d122979 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -95,6 +95,28 @@ int en_print(const char *level, const struct mlx4_en_priv *priv,
 	return i;
 }
 
+void mlx4_en_update_loopback_state(struct net_device *dev,
+				   netdev_features_t features)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	priv->flags &= ~(MLX4_EN_FLAG_RX_FILTER_NEEDED|
+			MLX4_EN_FLAG_ENABLE_HW_LOOPBACK);
+
+	/* Drop the packet if SRIOV is not enabled
+	 * and not performing the selftest or flb disabled
+	 */
+	if (mlx4_is_mfunc(priv->mdev->dev) &&
+	    !(features & NETIF_F_LOOPBACK) && !priv->validate_loopback)
+		priv->flags |= MLX4_EN_FLAG_RX_FILTER_NEEDED;
+
+	/* Set dmac in Tx WQE if we are in SRIOV mode or if loopback selftest
+	 * is requested
+	 */
+	if (mlx4_is_mfunc(priv->mdev->dev) || priv->validate_loopback)
+		priv->flags |= MLX4_EN_FLAG_ENABLE_HW_LOOPBACK;
+}
+
 static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_en_profile *params = &mdev->profile;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index ac1c14f7424..4671fa556c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -132,17 +132,14 @@ static void mlx4_en_filter_work(struct work_struct *work)
 		.priority = MLX4_DOMAIN_RFS,
 	};
 	int rc;
-	__be64 mac;
 	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
 
 	list_add_tail(&spec_eth.list, &rule.list);
 	list_add_tail(&spec_ip.list, &rule.list);
 	list_add_tail(&spec_tcp.list, &rule.list);
 
-	mac = cpu_to_be64((priv->mac & MLX4_MAC_MASK) << 16);
-
 	rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
-	memcpy(spec_eth.eth.dst_mac, &mac, ETH_ALEN);
+	memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
 	memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
 
 	filter->activated = 0;
@@ -413,6 +410,235 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	return 0;
 }
 
+static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
+{
+	unsigned int i;
+	for (i = ETH_ALEN - 1; i; --i) {
+		dst_mac[i] = src_mac & 0xff;
+		src_mac >>= 8;
+	}
+	memset(&dst_mac[ETH_ALEN], 0, 2);
+}
+
+static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
+				unsigned char *mac, int *qpn, u64 *reg_id)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_dev *dev = mdev->dev;
+	int err;
+
+	switch (dev->caps.steering_mode) {
+	case MLX4_STEERING_MODE_B0: {
+		struct mlx4_qp qp;
+		u8 gid[16] = {0};
+
+		qp.qpn = *qpn;
+		memcpy(&gid[10], mac, ETH_ALEN);
+		gid[5] = priv->port;
+
+		err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+		break;
+	}
+	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+		struct mlx4_spec_list spec_eth = { {NULL} };
+		__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+		struct mlx4_net_trans_rule rule = {
+			.queue_mode = MLX4_NET_TRANS_Q_FIFO,
+			.exclusive = 0,
+			.allow_loopback = 1,
+			.promisc_mode = MLX4_FS_PROMISC_NONE,
+			.priority = MLX4_DOMAIN_NIC,
+		};
+
+		rule.port = priv->port;
+		rule.qpn = *qpn;
+		INIT_LIST_HEAD(&rule.list);
+
+		spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
+		memcpy(spec_eth.eth.dst_mac, mac, ETH_ALEN);
+		memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+		list_add_tail(&spec_eth.list, &rule.list);
+
+		err = mlx4_flow_attach(dev, &rule, reg_id);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+	if (err)
+		en_warn(priv, "Failed Attaching Unicast\n");
+
+	return err;
+}
+
+static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv,
+				     unsigned char *mac, int qpn, u64 reg_id)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_dev *dev = mdev->dev;
+
+	switch (dev->caps.steering_mode) {
+	case MLX4_STEERING_MODE_B0: {
+		struct mlx4_qp qp;
+		u8 gid[16] = {0};
+
+		qp.qpn = qpn;
+		memcpy(&gid[10], mac, ETH_ALEN);
+		gid[5] = priv->port;
+
+		mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+		break;
+	}
+	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+		mlx4_flow_detach(dev, reg_id);
+		break;
+	}
+	default:
+		en_err(priv, "Invalid steering mode.\n");
+	}
+}
+
+static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_dev *dev = mdev->dev;
+	struct mlx4_mac_entry *entry;
+	int index = 0;
+	int err = 0;
+	u64 reg_id;
+	int *qpn = &priv->base_qpn;
+	u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+
+	en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
+	       priv->dev->dev_addr);
+	index = mlx4_register_mac(dev, priv->port, mac);
+	if (index < 0) {
+		err = index;
+		en_err(priv, "Failed adding MAC: %pM\n",
+		       priv->dev->dev_addr);
+		return err;
+	}
+
+	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
+		int base_qpn = mlx4_get_base_qpn(dev, priv->port);
+		*qpn = base_qpn + index;
+		return 0;
+	}
+
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
+	if (err) {
+		en_err(priv, "Failed to reserve qp for mac registration\n");
+		goto qp_err;
+	}
+
+	err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, &reg_id);
+	if (err)
+		goto steer_err;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+	memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac));
+	entry->reg_id = reg_id;
+
+	hlist_add_head_rcu(&entry->hlist,
+			   &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]);
+
+	return 0;
+
+alloc_err:
+	mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);
+
+steer_err:
+	mlx4_qp_release_range(dev, *qpn, 1);
+
+qp_err:
+	mlx4_unregister_mac(dev, priv->port, mac);
+	return err;
+}
+
+static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_dev *dev = mdev->dev;
+	int qpn = priv->base_qpn;
+	u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+
+	en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
+	       priv->dev->dev_addr);
+	mlx4_unregister_mac(dev, priv->port, mac);
+
+	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
+		struct mlx4_mac_entry *entry;
+		struct hlist_node *n, *tmp;
+		struct hlist_head *bucket;
+		unsigned int mac_hash;
+
+		mac_hash = priv->dev->dev_addr[MLX4_EN_MAC_HASH_IDX];
+		bucket = &priv->mac_hash[mac_hash];
+		hlist_for_each_entry_safe(entry, n, tmp, bucket, hlist) {
+			if (ether_addr_equal_64bits(entry->mac,
+						    priv->dev->dev_addr)) {
+				en_dbg(DRV, priv, "Releasing qp: port %d, MAC %pM, qpn %d\n",
+				       priv->port, priv->dev->dev_addr, qpn);
+				mlx4_en_uc_steer_release(priv, entry->mac,
+							 qpn, entry->reg_id);
+				mlx4_qp_release_range(dev, qpn, 1);
+
+				hlist_del_rcu(&entry->hlist);
+				kfree_rcu(entry, rcu);
+				break;
+			}
+		}
+	}
+}
+
+static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
+			       unsigned char *new_mac, unsigned char *prev_mac)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_dev *dev = mdev->dev;
+	int err = 0;
+	u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac);
+
+	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
+		struct hlist_head *bucket;
+		unsigned int mac_hash;
+		struct mlx4_mac_entry *entry;
+		struct hlist_node *n, *tmp;
+		u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac);
+
+		bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
+		hlist_for_each_entry_safe(entry, n, tmp, bucket, hlist) {
+			if (ether_addr_equal_64bits(entry->mac, prev_mac)) {
+				mlx4_en_uc_steer_release(priv, entry->mac,
+							 qpn, entry->reg_id);
+				mlx4_unregister_mac(dev, priv->port,
+						    prev_mac_u64);
+				hlist_del_rcu(&entry->hlist);
+				synchronize_rcu();
+				memcpy(entry->mac, new_mac, ETH_ALEN);
+				entry->reg_id = 0;
+				mac_hash = new_mac[MLX4_EN_MAC_HASH_IDX];
+				hlist_add_head_rcu(&entry->hlist,
+						   &priv->mac_hash[mac_hash]);
+				mlx4_register_mac(dev, priv->port, new_mac_u64);
+				err = mlx4_en_uc_steer_add(priv, new_mac,
+							   &qpn,
+							   &entry->reg_id);
+				return err;
+			}
+		}
+		return -EINVAL;
+	}
+
+	return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
+}
+
 u64 mlx4_en_mac_to_u64(u8 *addr)
 {
 	u64 mac = 0;
@@ -435,7 +661,6 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr)
 		return -EADDRNOTAVAIL;
 
 	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
-	priv->mac = mlx4_en_mac_to_u64(dev->dev_addr);
 	queue_work(mdev->workqueue, &priv->mac_task);
 	return 0;
 }
@@ -450,13 +675,14 @@ static void mlx4_en_do_set_mac(struct work_struct *work)
 	mutex_lock(&mdev->state_lock);
 	if (priv->port_up) {
 		/* Remove old MAC and insert the new one */
-		err = mlx4_replace_mac(mdev->dev, priv->port,
-				       priv->base_qpn, priv->mac);
+		err = mlx4_en_replace_mac(priv, priv->base_qpn,
+					  priv->dev->dev_addr, priv->prev_mac);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
+		memcpy(priv->prev_mac, priv->dev->dev_addr,
+		       sizeof(priv->prev_mac));
 	} else
-		en_dbg(HW, priv, "Port is down while "
-				 "registering mac, exiting...\n");
+		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
 
 	mutex_unlock(&mdev->state_lock);
 }
@@ -540,167 +766,141 @@ static void update_mclist_flags(struct mlx4_en_priv *priv,
 	}
 }
 
-static void mlx4_en_set_multicast(struct net_device *dev)
+static void mlx4_en_set_rx_mode(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
 	if (!priv->port_up)
 		return;
 
-	queue_work(priv->mdev->workqueue, &priv->mcast_task);
+	queue_work(priv->mdev->workqueue, &priv->rx_mode_task);
 }
 
-static void mlx4_en_do_set_multicast(struct work_struct *work)
+static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv,
+				     struct mlx4_en_dev *mdev)
 {
-	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
-						 mcast_task);
-	struct mlx4_en_dev *mdev = priv->mdev;
-	struct net_device *dev = priv->dev;
-	struct mlx4_en_mc_list *mclist, *tmp;
-	u64 mcast_addr = 0;
-	u8 mc_list[16] = {0};
 	int err = 0;
 
-	mutex_lock(&mdev->state_lock);
-	if (!mdev->device_up) {
-		en_dbg(HW, priv, "Card is not up, "
-				 "ignoring multicast change.\n");
-		goto out;
-	}
-	if (!priv->port_up) {
-		en_dbg(HW, priv, "Port is down, "
-				 "ignoring  multicast change.\n");
-		goto out;
-	}
-
-	if (!netif_carrier_ok(dev)) {
-		if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
-			if (priv->port_state.link_state) {
-				priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
-				netif_carrier_on(dev);
-				en_dbg(LINK, priv, "Link Up\n");
-			}
-		}
-	}
-
-	/*
-	 * Promsicuous mode: disable all filters
-	 */
-
-	if (dev->flags & IFF_PROMISC) {
-		if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
-			if (netif_msg_rx_status(priv))
-				en_warn(priv, "Entering promiscuous mode\n");
-			priv->flags |= MLX4_EN_FLAG_PROMISC;
-
-			/* Enable promiscouos mode */
-			switch (mdev->dev->caps.steering_mode) {
-			case MLX4_STEERING_MODE_DEVICE_MANAGED:
-				err = mlx4_flow_steer_promisc_add(mdev->dev,
-								  priv->port,
-								  priv->base_qpn,
-								  MLX4_FS_PROMISC_UPLINK);
-				if (err)
-					en_err(priv, "Failed enabling promiscuous mode\n");
-				priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
-				break;
-
-			case MLX4_STEERING_MODE_B0:
-				err = mlx4_unicast_promisc_add(mdev->dev,
-							       priv->base_qpn,
-							       priv->port);
-				if (err)
-					en_err(priv, "Failed enabling unicast promiscuous mode\n");
-
-				/* Add the default qp number as multicast
-				 * promisc
-				 */
-				if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
-					err = mlx4_multicast_promisc_add(mdev->dev,
-									 priv->base_qpn,
-									 priv->port);
-					if (err)
-						en_err(priv, "Failed enabling multicast promiscuous mode\n");
-					priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
-				}
-				break;
-
-			case MLX4_STEERING_MODE_A0:
-				err = mlx4_SET_PORT_qpn_calc(mdev->dev,
-							     priv->port,
-							     priv->base_qpn,
-							     1);
-				if (err)
-					en_err(priv, "Failed enabling promiscuous mode\n");
-				break;
-			}
-
-			/* Disable port multicast filter (unconditionally) */
-			err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
-						  0, MLX4_MCAST_DISABLE);
-			if (err)
-				en_err(priv, "Failed disabling "
-					     "multicast filter\n");
-
-			/* Disable port VLAN filter */
-			err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
-			if (err)
-				en_err(priv, "Failed disabling VLAN filter\n");
-		}
-		goto out;
-	}
-
-	/*
-	 * Not in promiscuous mode
-	 */
-
-	if (priv->flags & MLX4_EN_FLAG_PROMISC) {
+	if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
 		if (netif_msg_rx_status(priv))
-			en_warn(priv, "Leaving promiscuous mode\n");
-		priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+			en_warn(priv, "Entering promiscuous mode\n");
+		priv->flags |= MLX4_EN_FLAG_PROMISC;
 
-		/* Disable promiscouos mode */
+		/* Enable promiscouos mode */
 		switch (mdev->dev->caps.steering_mode) {
 		case MLX4_STEERING_MODE_DEVICE_MANAGED:
-			err = mlx4_flow_steer_promisc_remove(mdev->dev,
-							     priv->port,
-							     MLX4_FS_PROMISC_UPLINK);
+			err = mlx4_flow_steer_promisc_add(mdev->dev,
+							  priv->port,
+							  priv->base_qpn,
+							  MLX4_FS_PROMISC_UPLINK);
 			if (err)
-				en_err(priv, "Failed disabling promiscuous mode\n");
-			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+				en_err(priv, "Failed enabling promiscuous mode\n");
+			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
 			break;
 
 		case MLX4_STEERING_MODE_B0:
-			err = mlx4_unicast_promisc_remove(mdev->dev,
-							  priv->base_qpn,
-							  priv->port);
+			err = mlx4_unicast_promisc_add(mdev->dev,
+						       priv->base_qpn,
+						       priv->port);
 			if (err)
-				en_err(priv, "Failed disabling unicast promiscuous mode\n");
-			/* Disable Multicast promisc */
-			if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
-				err = mlx4_multicast_promisc_remove(mdev->dev,
-								    priv->base_qpn,
-								    priv->port);
+				en_err(priv, "Failed enabling unicast promiscuous mode\n");
+
+			/* Add the default qp number as multicast
+			 * promisc
+			 */
+			if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
+				err = mlx4_multicast_promisc_add(mdev->dev,
+								 priv->base_qpn,
+								 priv->port);
 				if (err)
-					en_err(priv, "Failed disabling multicast promiscuous mode\n");
-				priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+					en_err(priv, "Failed enabling multicast promiscuous mode\n");
+				priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
 			}
 			break;
 
 		case MLX4_STEERING_MODE_A0:
 			err = mlx4_SET_PORT_qpn_calc(mdev->dev,
 						     priv->port,
-						     priv->base_qpn, 0);
+						     priv->base_qpn,
+						     1);
 			if (err)
-				en_err(priv, "Failed disabling promiscuous mode\n");
+				en_err(priv, "Failed enabling promiscuous mode\n");
 			break;
 		}
 
-		/* Enable port VLAN filter */
+		/* Disable port multicast filter (unconditionally) */
+		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+					  0, MLX4_MCAST_DISABLE);
+		if (err)
+			en_err(priv, "Failed disabling multicast filter\n");
+
+		/* Disable port VLAN filter */
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
 		if (err)
-			en_err(priv, "Failed enabling VLAN filter\n");
+			en_err(priv, "Failed disabling VLAN filter\n");
 	}
+}
+
+static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv,
+				       struct mlx4_en_dev *mdev)
+{
+	int err = 0;
+
+	if (netif_msg_rx_status(priv))
+		en_warn(priv, "Leaving promiscuous mode\n");
+	priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+
+	/* Disable promiscouos mode */
+	switch (mdev->dev->caps.steering_mode) {
+	case MLX4_STEERING_MODE_DEVICE_MANAGED:
+		err = mlx4_flow_steer_promisc_remove(mdev->dev,
+						     priv->port,
+						     MLX4_FS_PROMISC_UPLINK);
+		if (err)
+			en_err(priv, "Failed disabling promiscuous mode\n");
+		priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+		break;
+
+	case MLX4_STEERING_MODE_B0:
+		err = mlx4_unicast_promisc_remove(mdev->dev,
+						  priv->base_qpn,
+						  priv->port);
+		if (err)
+			en_err(priv, "Failed disabling unicast promiscuous mode\n");
+		/* Disable Multicast promisc */
+		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
+			err = mlx4_multicast_promisc_remove(mdev->dev,
+							    priv->base_qpn,
+							    priv->port);
+			if (err)
+				en_err(priv, "Failed disabling multicast promiscuous mode\n");
+			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+		}
+		break;
+
+	case MLX4_STEERING_MODE_A0:
+		err = mlx4_SET_PORT_qpn_calc(mdev->dev,
+					     priv->port,
+					     priv->base_qpn, 0);
+		if (err)
+			en_err(priv, "Failed disabling promiscuous mode\n");
+		break;
+	}
+
+	/* Enable port VLAN filter */
+	err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
+	if (err)
+		en_err(priv, "Failed enabling VLAN filter\n");
+}
+
+static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
+				 struct net_device *dev,
+				 struct mlx4_en_dev *mdev)
+{
+	struct mlx4_en_mc_list *mclist, *tmp;
+	u64 mcast_addr = 0;
+	u8 mc_list[16] = {0};
+	int err = 0;
 
 	/* Enable/disable the multicast filter according to IFF_ALLMULTI */
 	if (dev->flags & IFF_ALLMULTI) {
@@ -814,6 +1014,170 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 			}
 		}
 	}
+}
+
+static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
+				 struct net_device *dev,
+				 struct mlx4_en_dev *mdev)
+{
+	struct netdev_hw_addr *ha;
+	struct mlx4_mac_entry *entry;
+	struct hlist_node *n, *tmp;
+	bool found;
+	u64 mac;
+	int err = 0;
+	struct hlist_head *bucket;
+	unsigned int i;
+	int removed = 0;
+	u32 prev_flags;
+
+	/* Note that we do not need to protect our mac_hash traversal with rcu,
+	 * since all modification code is protected by mdev->state_lock
+	 */
+
+	/* find what to remove */
+	for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
+		bucket = &priv->mac_hash[i];
+		hlist_for_each_entry_safe(entry, n, tmp, bucket, hlist) {
+			found = false;
+			netdev_for_each_uc_addr(ha, dev) {
+				if (ether_addr_equal_64bits(entry->mac,
+							    ha->addr)) {
+					found = true;
+					break;
+				}
+			}
+
+			/* MAC address of the port is not in uc list */
+			if (ether_addr_equal_64bits(entry->mac, dev->dev_addr))
+				found = true;
+
+			if (!found) {
+				mac = mlx4_en_mac_to_u64(entry->mac);
+				mlx4_en_uc_steer_release(priv, entry->mac,
+							 priv->base_qpn,
+							 entry->reg_id);
+				mlx4_unregister_mac(mdev->dev, priv->port, mac);
+
+				hlist_del_rcu(&entry->hlist);
+				kfree_rcu(entry, rcu);
+				en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n",
+				       entry->mac, priv->port);
+				++removed;
+			}
+		}
+	}
+
+	/* if we didn't remove anything, there is no use in trying to add
+	 * again once we are in a forced promisc mode state
+	 */
+	if ((priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) && 0 == removed)
+		return;
+
+	prev_flags = priv->flags;
+	priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;
+
+	/* find what to add */
+	netdev_for_each_uc_addr(ha, dev) {
+		found = false;
+		bucket = &priv->mac_hash[ha->addr[MLX4_EN_MAC_HASH_IDX]];
+		hlist_for_each_entry(entry, n, bucket, hlist) {
+			if (ether_addr_equal_64bits(entry->mac, ha->addr)) {
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+			if (!entry) {
+				en_err(priv, "Failed adding MAC %pM on port:%d (out of memory)\n",
+				       ha->addr, priv->port);
+				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+				break;
+			}
+			mac = mlx4_en_mac_to_u64(ha->addr);
+			memcpy(entry->mac, ha->addr, ETH_ALEN);
+			err = mlx4_register_mac(mdev->dev, priv->port, mac);
+			if (err < 0) {
+				en_err(priv, "Failed registering MAC %pM on port %d: %d\n",
+				       ha->addr, priv->port, err);
+				kfree(entry);
+				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+				break;
+			}
+			err = mlx4_en_uc_steer_add(priv, ha->addr,
+						   &priv->base_qpn,
+						   &entry->reg_id);
+			if (err) {
+				en_err(priv, "Failed adding MAC %pM on port %d: %d\n",
+				       ha->addr, priv->port, err);
+				mlx4_unregister_mac(mdev->dev, priv->port, mac);
+				kfree(entry);
+				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+				break;
+			} else {
+				unsigned int mac_hash;
+				en_dbg(DRV, priv, "Added MAC %pM on port:%d\n",
+				       ha->addr, priv->port);
+				mac_hash = ha->addr[MLX4_EN_MAC_HASH_IDX];
+				bucket = &priv->mac_hash[mac_hash];
+				hlist_add_head_rcu(&entry->hlist, bucket);
+			}
+		}
+	}
+
+	if (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) {
+		en_warn(priv, "Forcing promiscuous mode on port:%d\n",
+			priv->port);
+	} else if (prev_flags & MLX4_EN_FLAG_FORCE_PROMISC) {
+		en_warn(priv, "Stop forcing promiscuous mode on port:%d\n",
+			priv->port);
+	}
+}
+
+static void mlx4_en_do_set_rx_mode(struct work_struct *work)
+{
+	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+						 rx_mode_task);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct net_device *dev = priv->dev;
+
+	mutex_lock(&mdev->state_lock);
+	if (!mdev->device_up) {
+		en_dbg(HW, priv, "Card is not up, ignoring rx mode change.\n");
+		goto out;
+	}
+	if (!priv->port_up) {
+		en_dbg(HW, priv, "Port is down, ignoring rx mode change.\n");
+		goto out;
+	}
+
+	if (!netif_carrier_ok(dev)) {
+		if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
+			if (priv->port_state.link_state) {
+				priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
+				netif_carrier_on(dev);
+				en_dbg(LINK, priv, "Link Up\n");
+			}
+		}
+	}
+
+	if (dev->priv_flags & IFF_UNICAST_FLT)
+		mlx4_en_do_uc_filter(priv, dev, mdev);
+
+	/* Promsicuous mode: disable all filters */
+	if ((dev->flags & IFF_PROMISC) ||
+	    (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC)) {
+		mlx4_en_set_promisc_mode(priv, mdev);
+		goto out;
+	}
+
+	/* Not in promiscuous mode */
+	if (priv->flags & MLX4_EN_FLAG_PROMISC)
+		mlx4_en_clear_promisc_mode(priv, mdev);
+
+	mlx4_en_do_multicast(priv, dev, mdev);
 out:
 	mutex_unlock(&mdev->state_lock);
 }
@@ -876,9 +1240,8 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
 	priv->rx_usecs = MLX4_EN_RX_COAL_TIME;
 	priv->tx_frames = MLX4_EN_TX_COAL_PKTS;
 	priv->tx_usecs = MLX4_EN_TX_COAL_TIME;
-	en_dbg(INTR, priv, "Default coalesing params for mtu:%d - "
-			   "rx_frames:%d rx_usecs:%d\n",
-		 priv->dev->mtu, priv->rx_frames, priv->rx_usecs);
+	en_dbg(INTR, priv, "Default coalesing params for mtu:%d - rx_frames:%d rx_usecs:%d\n",
+	       priv->dev->mtu, priv->rx_frames, priv->rx_usecs);
 
 	/* Setup cq moderation params */
 	for (i = 0; i < priv->rx_ring_num; i++) {
@@ -959,8 +1322,8 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 			cq->moder_time = moder_time;
 			err = mlx4_en_set_cq_moder(priv, cq);
 			if (err)
-				en_err(priv, "Failed modifying moderation "
-					     "for cq:%d\n", ring);
+				en_err(priv, "Failed modifying moderation for cq:%d\n",
+				       ring);
 		}
 		priv->last_moder_packets[ring] = rx_packets;
 		priv->last_moder_bytes[ring] = rx_bytes;
@@ -1077,8 +1440,7 @@ int mlx4_en_start_port(struct net_device *dev)
 
 	/* Set qp number */
 	en_dbg(DRV, priv, "Getting qp number for port %d\n", priv->port);
-	err = mlx4_get_eth_qp(mdev->dev, priv->port,
-				priv->mac, &priv->base_qpn);
+	err = mlx4_en_get_qp(priv);
 	if (err) {
 		en_err(priv, "Failed getting eth qp\n");
 		goto cq_err;
@@ -1141,8 +1503,8 @@ int mlx4_en_start_port(struct net_device *dev)
 				    priv->prof->rx_pause,
 				    priv->prof->rx_ppp);
 	if (err) {
-		en_err(priv, "Failed setting port general configurations "
-			     "for port %d, with error %d\n", priv->port, err);
+		en_err(priv, "Failed setting port general configurations for port %d, with error %d\n",
+		       priv->port, err);
 		goto tx_err;
 	}
 	/* Set default qp number */
@@ -1172,7 +1534,7 @@ int mlx4_en_start_port(struct net_device *dev)
 	priv->flags &= ~(MLX4_EN_FLAG_PROMISC | MLX4_EN_FLAG_MC_PROMISC);
 
 	/* Schedule multicast task to populate multicast list */
-	queue_work(mdev->workqueue, &priv->mcast_task);
+	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
 	mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
 
@@ -1191,7 +1553,7 @@ tx_err:
 rss_err:
 	mlx4_en_release_rss_steer(priv);
 mac_err:
-	mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
+	mlx4_en_put_qp(priv);
 cq_err:
 	while (rx_index--)
 		mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
@@ -1290,7 +1652,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 	mlx4_en_release_rss_steer(priv);
 
 	/* Unregister Mac address for the port */
-	mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
+	mlx4_en_put_qp(priv);
 	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN))
 		mdev->mac_removed[priv->port] = 1;
 
@@ -1563,17 +1925,91 @@ static int mlx4_en_set_features(struct net_device *netdev,
 		priv->ctrl_flags &=
 			cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);
 
+	mlx4_en_update_loopback_state(netdev, features);
+
 	return 0;
 
 }
 
+static int mlx4_en_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			   struct net_device *dev,
+			   const unsigned char *addr, u16 flags)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_dev *mdev = priv->mdev->dev;
+	int err;
+
+	if (!mlx4_is_mfunc(mdev))
+		return -EOPNOTSUPP;
+
+	/* Hardware does not support aging addresses, allow only
+	 * permanent addresses if ndm_state is given
+	 */
+	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+		en_info(priv, "Add FDB only supports static addresses\n");
+		return -EINVAL;
+	}
+
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+		err = dev_uc_add_excl(dev, addr);
+	else if (is_multicast_ether_addr(addr))
+		err = dev_mc_add_excl(dev, addr);
+	else
+		err = -EINVAL;
+
+	/* Only return duplicate errors if NLM_F_EXCL is set */
+	if (err == -EEXIST && !(flags & NLM_F_EXCL))
+		err = 0;
+
+	return err;
+}
+
+static int mlx4_en_fdb_del(struct ndmsg *ndm,
+			   struct net_device *dev,
+			   const unsigned char *addr)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_dev *mdev = priv->mdev->dev;
+	int err;
+
+	if (!mlx4_is_mfunc(mdev))
+		return -EOPNOTSUPP;
+
+	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+		en_info(priv, "Del FDB only supports static addresses\n");
+		return -EINVAL;
+	}
+
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+		err = dev_uc_del(dev, addr);
+	else if (is_multicast_ether_addr(addr))
+		err = dev_mc_del(dev, addr);
+	else
+		err = -EINVAL;
+
+	return err;
+}
+
+static int mlx4_en_fdb_dump(struct sk_buff *skb,
+			    struct netlink_callback *cb,
+			    struct net_device *dev, int idx)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_dev *mdev = priv->mdev->dev;
+
+	if (mlx4_is_mfunc(mdev))
+		idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
+
+	return idx;
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
 	.ndo_start_xmit		= mlx4_en_xmit,
 	.ndo_select_queue	= mlx4_en_select_queue,
 	.ndo_get_stats		= mlx4_en_get_stats,
-	.ndo_set_rx_mode	= mlx4_en_set_multicast,
+	.ndo_set_rx_mode	= mlx4_en_set_rx_mode,
 	.ndo_set_mac_address	= mlx4_en_set_mac,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= mlx4_en_change_mtu,
@@ -1588,6 +2024,9 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
+	.ndo_fdb_add		= mlx4_en_fdb_add,
+	.ndo_fdb_del		= mlx4_en_fdb_del,
+	.ndo_fdb_dump		= mlx4_en_fdb_dump,
 };
 
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
@@ -1644,7 +2083,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->mac_index = -1;
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 	spin_lock_init(&priv->stats_lock);
-	INIT_WORK(&priv->mcast_task, mlx4_en_do_set_multicast);
+	INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
 	INIT_WORK(&priv->mac_task, mlx4_en_do_set_mac);
 	INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
@@ -1654,16 +2093,24 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
 #endif
 
+	for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i)
+		INIT_HLIST_HEAD(&priv->mac_hash[i]);
+
 	/* Query for default mac and max mtu */
 	priv->max_mtu = mdev->dev->caps.eth_mtu_cap[priv->port];
-	priv->mac = mdev->dev->caps.def_mac[priv->port];
-	if (ILLEGAL_MAC(priv->mac)) {
-		en_err(priv, "Port: %d, invalid mac burned: 0x%llx, quiting\n",
-			 priv->port, priv->mac);
+
+	/* Set default MAC */
+	dev->addr_len = ETH_ALEN;
+	mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
+	if (!is_valid_ether_addr(dev->dev_addr)) {
+		en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
+		       priv->port, dev->dev_addr);
 		err = -EINVAL;
 		goto out;
 	}
 
+	memcpy(priv->prev_mac, dev->dev_addr, sizeof(priv->prev_mac));
+
 	priv->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
 					  DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
 	err = mlx4_en_alloc_resources(priv);
@@ -1694,11 +2141,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops);
 
-	/* Set defualt MAC */
-	dev->addr_len = ETH_ALEN;
-	for (i = 0; i < ETH_ALEN; i++)
-		dev->dev_addr[ETH_ALEN - 1 - i] = (u8) (priv->mac >> (8 * i));
-
 	/*
 	 * Set driver features
 	 */
@@ -1718,6 +2160,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	    MLX4_STEERING_MODE_DEVICE_MANAGED)
 		dev->hw_features |= NETIF_F_NTUPLE;
 
+	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
+		dev->priv_flags |= IFF_UNICAST_FLT;
+
 	mdev->pndev[port] = dev;
 
 	netif_carrier_off(dev);
@@ -1731,6 +2176,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
 	en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
 
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
+
 	/* Configure port */
 	mlx4_en_calc_rx_buf(dev);
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index fed26d867f4..91bb8e15725 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -563,9 +563,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	unsigned int length;
 	int polled = 0;
 	int ip_summed;
-	struct ethhdr *ethh;
-	dma_addr_t dma;
-	u64 s_mac;
 	int factor = priv->cqe_factor;
 
 	if (!priv->port_up)
@@ -603,21 +600,41 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			goto next;
 		}
 
-		/* Get pointer to first fragment since we haven't skb yet and
-		 * cast it to ethhdr struct */
-		dma = be64_to_cpu(rx_desc->data[0].addr);
-		dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
-					DMA_FROM_DEVICE);
-		ethh = (struct ethhdr *)(page_address(frags[0].page) +
-					 frags[0].offset);
-		s_mac = mlx4_en_mac_to_u64(ethh->h_source);
-
-		/* If source MAC is equal to our own MAC and not performing
-		 * the selftest or flb disabled - drop the packet */
-		if (s_mac == priv->mac &&
-		    !((dev->features & NETIF_F_LOOPBACK) ||
-		      priv->validate_loopback))
-			goto next;
+		/* Check if we need to drop the packet if SRIOV is not enabled
+		 * and not performing the selftest or flb disabled
+		 */
+		if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) {
+			struct ethhdr *ethh;
+			dma_addr_t dma;
+			/* Get pointer to first fragment since we haven't
+			 * skb yet and cast it to ethhdr struct
+			 */
+			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
+						DMA_FROM_DEVICE);
+			ethh = (struct ethhdr *)(page_address(frags[0].page) +
+						 frags[0].offset);
+
+			if (is_multicast_ether_addr(ethh->h_dest)) {
+				struct mlx4_mac_entry *entry;
+				struct hlist_node *n;
+				struct hlist_head *bucket;
+				unsigned int mac_hash;
+
+				/* Drop the packet, since HW loopback-ed it */
+				mac_hash = ethh->h_source[MLX4_EN_MAC_HASH_IDX];
+				bucket = &priv->mac_hash[mac_hash];
+				rcu_read_lock();
+				hlist_for_each_entry_rcu(entry, n, bucket, hlist) {
+					if (ether_addr_equal_64bits(entry->mac,
+								    ethh->h_source)) {
+						rcu_read_unlock();
+						goto next;
+					}
+				}
+				rcu_read_unlock();
+			}
+		}
 
 		/*
 		 * Packet is OK - process it.
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index bf2e5d3f177..3488c6d9e6b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -87,6 +87,8 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
         priv->loopback_ok = 0;
 	priv->validate_loopback = 1;
 
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
+
 	/* xmit */
 	if (mlx4_en_test_loopback_xmit(priv)) {
 		en_err(priv, "Transmitting loopback packet failed\n");
@@ -107,6 +109,7 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
 mlx4_en_test_loopback_exit:
 
 	priv->validate_loopback = 0;
+	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
 	return !loopback_ok;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 30724d81111..3b28e167b05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -640,7 +640,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		ring->tx_csum++;
 	}
 
-	if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) {
+	if (priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK) {
 		/* Copy dst mac address to wqe. This allows loopback in eSwitch,
 		 * so that VFs and PF can communicate with each other
 		 */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12ddae6efce..2d7b9377883 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1833,12 +1833,9 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 	info->dev = dev;
 	info->port = port;
 	if (!mlx4_is_slave(dev)) {
-		INIT_RADIX_TREE(&info->mac_tree, GFP_KERNEL);
 		mlx4_init_mac_table(dev, &info->mac_table);
 		mlx4_init_vlan_table(dev, &info->vlan_table);
-		info->base_qpn =
-			dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
-			(port - 1) * (1 << log_num_mac);
+		info->base_qpn = mlx4_get_base_qpn(dev, port);
 	}
 
 	sprintf(info->dev_name, "mlx4_port%d", port);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 172daaa29a9..ed4a6959e82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -653,11 +653,6 @@ struct mlx4_set_port_rqp_calc_context {
 	__be32 mcast;
 };
 
-struct mlx4_mac_entry {
-	u64 mac;
-	u64 reg_id;
-};
-
 struct mlx4_port_info {
 	struct mlx4_dev	       *dev;
 	int			port;
@@ -667,7 +662,6 @@ struct mlx4_port_info {
 	char			dev_mtu_name[16];
 	struct device_attribute port_mtu_attr;
 	struct mlx4_mac_table	mac_table;
-	struct radix_tree_root	mac_tree;
 	struct mlx4_vlan_table	vlan_table;
 	int			base_qpn;
 };
@@ -916,7 +910,6 @@ int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
 void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
-int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
 int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		     int start_index, int npages, u64 *page_list);
 int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 43f01650e58..c313d7e943a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -198,7 +198,6 @@ enum cq_type {
  */
 #define ROUNDUP_LOG2(x)		ilog2(roundup_pow_of_two(x))
 #define XNOR(x, y)		(!(x) == !(y))
-#define ILLEGAL_MAC(addr)	(addr == 0xffffffffffffULL || addr == 0x0)
 
 
 struct mlx4_en_tx_info {
@@ -432,6 +431,21 @@ struct ethtool_flow_id {
 	u64 id;
 };
 
+enum {
+	MLX4_EN_FLAG_PROMISC		= (1 << 0),
+	MLX4_EN_FLAG_MC_PROMISC		= (1 << 1),
+	/* whether we need to enable hardware loopback by putting dmac
+	 * in Tx WQE
+	 */
+	MLX4_EN_FLAG_ENABLE_HW_LOOPBACK	= (1 << 2),
+	/* whether we need to drop packets that hardware loopback-ed */
+	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3),
+	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4)
+};
+
+#define MLX4_EN_MAC_HASH_SIZE (1 << BITS_PER_BYTE)
+#define MLX4_EN_MAC_HASH_IDX 5
+
 struct mlx4_en_priv {
 	struct mlx4_en_dev *mdev;
 	struct mlx4_en_port_profile *prof;
@@ -472,7 +486,7 @@ struct mlx4_en_priv {
 	int registered;
 	int allocated;
 	int stride;
-	u64 mac;
+	unsigned char prev_mac[ETH_ALEN + 2];
 	int mac_index;
 	unsigned max_mtu;
 	int base_qpn;
@@ -481,8 +495,6 @@ struct mlx4_en_priv {
 	struct mlx4_en_rss_map rss_map;
 	__be32 ctrl_flags;
 	u32 flags;
-#define MLX4_EN_FLAG_PROMISC	0x1
-#define MLX4_EN_FLAG_MC_PROMISC	0x2
 	u8 num_tx_rings_p_up;
 	u32 tx_ring_num;
 	u32 rx_ring_num;
@@ -496,7 +508,7 @@ struct mlx4_en_priv {
 	struct mlx4_en_cq *tx_cq;
 	struct mlx4_en_cq rx_cq[MAX_RX_RINGS];
 	struct mlx4_qp drop_qp;
-	struct work_struct mcast_task;
+	struct work_struct rx_mode_task;
 	struct work_struct mac_task;
 	struct work_struct watchdog_task;
 	struct work_struct linkstate_task;
@@ -513,6 +525,7 @@ struct mlx4_en_priv {
 	bool wol;
 	struct device *ddev;
 	int base_tx_qpn;
+	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
 
 #ifdef CONFIG_MLX4_EN_DCB
 	struct ieee_ets ets;
@@ -532,8 +545,18 @@ enum mlx4_en_wol {
 	MLX4_EN_WOL_ENABLED = (1ULL << 62),
 };
 
+struct mlx4_mac_entry {
+	struct hlist_node hlist;
+	unsigned char mac[ETH_ALEN + 2];
+	u64 reg_id;
+	struct rcu_head rcu;
+};
+
 #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
 
+void mlx4_en_update_loopback_state(struct net_device *dev,
+				   netdev_features_t features);
+
 void mlx4_en_destroy_netdev(struct net_device *dev);
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			struct mlx4_en_port_profile *prof);
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 4c51b05efa2..719ead15e49 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -74,87 +74,6 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table)
 	table->total = 0;
 }
 
-static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
-			     u64 mac, int *qpn, u64 *reg_id)
-{
-	__be64 be_mac;
-	int err;
-
-	mac &= MLX4_MAC_MASK;
-	be_mac = cpu_to_be64(mac << 16);
-
-	switch (dev->caps.steering_mode) {
-	case MLX4_STEERING_MODE_B0: {
-		struct mlx4_qp qp;
-		u8 gid[16] = {0};
-
-		qp.qpn = *qpn;
-		memcpy(&gid[10], &be_mac, ETH_ALEN);
-		gid[5] = port;
-
-		err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
-		break;
-	}
-	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
-		struct mlx4_spec_list spec_eth = { {NULL} };
-		__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
-
-		struct mlx4_net_trans_rule rule = {
-			.queue_mode = MLX4_NET_TRANS_Q_FIFO,
-			.exclusive = 0,
-			.allow_loopback = 1,
-			.promisc_mode = MLX4_FS_PROMISC_NONE,
-			.priority = MLX4_DOMAIN_NIC,
-		};
-
-		rule.port = port;
-		rule.qpn = *qpn;
-		INIT_LIST_HEAD(&rule.list);
-
-		spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
-		memcpy(spec_eth.eth.dst_mac, &be_mac, ETH_ALEN);
-		memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
-		list_add_tail(&spec_eth.list, &rule.list);
-
-		err = mlx4_flow_attach(dev, &rule, reg_id);
-		break;
-	}
-	default:
-		return -EINVAL;
-	}
-	if (err)
-		mlx4_warn(dev, "Failed Attaching Unicast\n");
-
-	return err;
-}
-
-static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
-				  u64 mac, int qpn, u64 reg_id)
-{
-	switch (dev->caps.steering_mode) {
-	case MLX4_STEERING_MODE_B0: {
-		struct mlx4_qp qp;
-		u8 gid[16] = {0};
-		__be64 be_mac;
-
-		qp.qpn = qpn;
-		mac &= MLX4_MAC_MASK;
-		be_mac = cpu_to_be64(mac << 16);
-		memcpy(&gid[10], &be_mac, ETH_ALEN);
-		gid[5] = port;
-
-		mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
-		break;
-	}
-	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
-		mlx4_flow_detach(dev, reg_id);
-		break;
-	}
-	default:
-		mlx4_err(dev, "Invalid steering mode.\n");
-	}
-}
-
 static int validate_index(struct mlx4_dev *dev,
 			  struct mlx4_mac_table *table, int index)
 {
@@ -181,92 +100,6 @@ static int find_index(struct mlx4_dev *dev,
 	return -EINVAL;
 }
 
-int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_entry *entry;
-	int index = 0;
-	int err = 0;
-	u64 reg_id;
-
-	mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n",
-			(unsigned long long) mac);
-	index = mlx4_register_mac(dev, port, mac);
-	if (index < 0) {
-		err = index;
-		mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
-			 (unsigned long long) mac);
-		return err;
-	}
-
-	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
-		*qpn = info->base_qpn + index;
-		return 0;
-	}
-
-	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
-	mlx4_dbg(dev, "Reserved qp %d\n", *qpn);
-	if (err) {
-		mlx4_err(dev, "Failed to reserve qp for mac registration\n");
-		goto qp_err;
-	}
-
-	err = mlx4_uc_steer_add(dev, port, mac, qpn, &reg_id);
-	if (err)
-		goto steer_err;
-
-	entry = kmalloc(sizeof *entry, GFP_KERNEL);
-	if (!entry) {
-		err = -ENOMEM;
-		goto alloc_err;
-	}
-	entry->mac = mac;
-	entry->reg_id = reg_id;
-	err = radix_tree_insert(&info->mac_tree, *qpn, entry);
-	if (err)
-		goto insert_err;
-	return 0;
-
-insert_err:
-	kfree(entry);
-
-alloc_err:
-	mlx4_uc_steer_release(dev, port, mac, *qpn, reg_id);
-
-steer_err:
-	mlx4_qp_release_range(dev, *qpn, 1);
-
-qp_err:
-	mlx4_unregister_mac(dev, port, mac);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx4_get_eth_qp);
-
-void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_entry *entry;
-
-	mlx4_dbg(dev, "Registering MAC: 0x%llx for deleting\n",
-		 (unsigned long long) mac);
-	mlx4_unregister_mac(dev, port, mac);
-
-	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
-		entry = radix_tree_lookup(&info->mac_tree, qpn);
-		if (entry) {
-			mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx,"
-				 " qpn %d\n", port,
-				 (unsigned long long) mac, qpn);
-			mlx4_uc_steer_release(dev, port, entry->mac,
-					      qpn, entry->reg_id);
-			mlx4_qp_release_range(dev, qpn, 1);
-			radix_tree_delete(&info->mac_tree, qpn);
-			kfree(entry);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(mlx4_put_eth_qp);
-
 static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 				   __be64 *entries)
 {
@@ -359,6 +192,12 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 }
 EXPORT_SYMBOL_GPL(mlx4_register_mac);
 
+int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port)
+{
+	return dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
+			(port - 1) * (1 << dev->caps.log_num_macs);
+}
+EXPORT_SYMBOL_GPL(mlx4_get_base_qpn);
 
 void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
@@ -397,29 +236,13 @@ void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_mac);
 
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
+int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
 	struct mlx4_mac_table *table = &info->mac_table;
-	struct mlx4_mac_entry *entry;
 	int index = qpn - info->base_qpn;
 	int err = 0;
 
-	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
-		entry = radix_tree_lookup(&info->mac_tree, qpn);
-		if (!entry)
-			return -EINVAL;
-		mlx4_uc_steer_release(dev, port, entry->mac,
-				      qpn, entry->reg_id);
-		mlx4_unregister_mac(dev, port, entry->mac);
-		entry->mac = new_mac;
-		entry->reg_id = 0;
-		mlx4_register_mac(dev, port, new_mac);
-		err = mlx4_uc_steer_add(dev, port, entry->mac,
-					&qpn, &entry->reg_id);
-		return err;
-	}
-
 	/* CX1 doesn't support multi-functions */
 	mutex_lock(&table->mutex);
 
@@ -439,7 +262,7 @@ out:
 	mutex_unlock(&table->mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx4_replace_mac);
+EXPORT_SYMBOL_GPL(__mlx4_replace_mac);
 
 static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
 				    __be32 *entries)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 1883e8e8471..6d48fce06b4 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -956,9 +956,8 @@ int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mo
 
 int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
 void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
-int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn);
-void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn);
+int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port);
+int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
 void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap);
 int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
 			  u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx);