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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

11 files changed, 337 insertions, 138 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 68d763d2d030..e22f24f784fc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -98,6 +98,10 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	drvinfo->eedump_len = 0;
 }
 
+static const char mlx4_en_priv_flags[][ETH_GSTRING_LEN] = {
+	"blueflame",
+};
+
 static const char main_strings[][ETH_GSTRING_LEN] = {
 	"rx_packets", "tx_packets", "rx_bytes", "tx_bytes", "rx_errors",
 	"tx_errors", "rx_dropped", "tx_dropped", "multicast", "collisions",
@@ -235,6 +239,8 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
 	case ETH_SS_TEST:
 		return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
 					& MLX4_DEV_CAP_FLAG_UC_LOOPBACK) * 2;
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(mlx4_en_priv_flags);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -358,6 +364,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
 #endif
 		}
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		for (i = 0; i < ARRAY_SIZE(mlx4_en_priv_flags); i++)
+			strcpy(data + i * ETH_GSTRING_LEN,
+			       mlx4_en_priv_flags[i]);
+		break;
+
 	}
 }
 
@@ -1209,6 +1221,49 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 	return ret;
 }
 
+static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	bool bf_enabled_new = !!(flags & MLX4_EN_PRIV_FLAGS_BLUEFLAME);
+	bool bf_enabled_old = !!(priv->pflags & MLX4_EN_PRIV_FLAGS_BLUEFLAME);
+	int i;
+
+	if (bf_enabled_new == bf_enabled_old)
+		return 0; /* Nothing to do */
+
+	if (bf_enabled_new) {
+		bool bf_supported = true;
+
+		for (i = 0; i < priv->tx_ring_num; i++)
+			bf_supported &= priv->tx_ring[i]->bf_alloced;
+
+		if (!bf_supported) {
+			en_err(priv, "BlueFlame is not supported\n");
+			return -EINVAL;
+		}
+
+		priv->pflags |= MLX4_EN_PRIV_FLAGS_BLUEFLAME;
+	} else {
+		priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
+	}
+
+	for (i = 0; i < priv->tx_ring_num; i++)
+		priv->tx_ring[i]->bf_enabled = bf_enabled_new;
+
+	en_info(priv, "BlueFlame %s\n",
+		bf_enabled_new ?  "Enabled" : "Disabled");
+
+	return 0;
+}
+
+static u32 mlx4_en_get_priv_flags(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->pflags;
+}
+
+
 const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_drvinfo = mlx4_en_get_drvinfo,
 	.get_settings = mlx4_en_get_settings,
@@ -1236,6 +1291,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_channels = mlx4_en_get_channels,
 	.set_channels = mlx4_en_set_channels,
 	.get_ts_info = mlx4_en_get_ts_info,
+	.set_priv_flags = mlx4_en_set_priv_flags,
+	.get_priv_flags = mlx4_en_get_priv_flags,
 };
 
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index f953c1d7eae6..3626fdf4cb5d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -129,8 +129,10 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	int i;
 
 	params->udp_rss = udp_rss;
-	params->num_tx_rings_p_up = min_t(int, num_online_cpus(),
-			MLX4_EN_MAX_TX_RING_P_UP);
+	params->num_tx_rings_p_up = mlx4_low_memory_profile() ?
+		MLX4_EN_MIN_TX_RING_P_UP :
+		min_t(int, num_online_cpus(), MLX4_EN_MAX_TX_RING_P_UP);
+
 	if (params->udp_rss && !(mdev->dev->caps.flags
 					& MLX4_DEV_CAP_FLAG_UDP_RSS)) {
 		mlx4_warn(mdev, "UDP RSS is not supported on this device\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 7345c43b019e..bb536aa613f4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -644,6 +644,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		goto alloc_err;
 	}
 	memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac));
+	memcpy(priv->current_mac, entry->mac, sizeof(priv->current_mac));
 	entry->reg_id = reg_id;
 
 	hlist_add_head_rcu(&entry->hlist,
@@ -760,21 +761,22 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
 	return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
 }
 
-static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
+static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv,
+			      unsigned char new_mac[ETH_ALEN + 2])
 {
 	int err = 0;
 
 	if (priv->port_up) {
 		/* Remove old MAC and insert the new one */
 		err = mlx4_en_replace_mac(priv, priv->base_qpn,
-					  priv->dev->dev_addr, priv->prev_mac);
+					  new_mac, priv->current_mac);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
 	} else
 		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
 
-	memcpy(priv->prev_mac, priv->dev->dev_addr,
-	       sizeof(priv->prev_mac));
+	if (!err)
+		memcpy(priv->current_mac, new_mac, sizeof(priv->current_mac));
 
 	return err;
 }
@@ -784,14 +786,17 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct sockaddr *saddr = addr;
+	unsigned char new_mac[ETH_ALEN + 2];
 	int err;
 
 	if (!is_valid_ether_addr(saddr->sa_data))
 		return -EADDRNOTAVAIL;
 
 	mutex_lock(&mdev->state_lock);
-	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
-	err = mlx4_en_do_set_mac(priv);
+	memcpy(new_mac, saddr->sa_data, ETH_ALEN);
+	err = mlx4_en_do_set_mac(priv, new_mac);
+	if (!err)
+		memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
 	mutex_unlock(&mdev->state_lock);
 
 	return err;
@@ -940,11 +945,6 @@ static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv,
 					  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");
 	}
 }
 
@@ -993,11 +993,6 @@ static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv,
 			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,
@@ -1166,7 +1161,8 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
 			}
 
 			/* MAC address of the port is not in uc list */
-			if (ether_addr_equal_64bits(entry->mac, dev->dev_addr))
+			if (ether_addr_equal_64bits(entry->mac,
+						    priv->current_mac))
 				found = true;
 
 			if (!found) {
@@ -1476,7 +1472,7 @@ static void mlx4_en_do_get_stats(struct work_struct *work)
 		queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
 	}
 	if (mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port]) {
-		mlx4_en_do_set_mac(priv);
+		mlx4_en_do_set_mac(priv, priv->current_mac);
 		mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port] = 0;
 	}
 	mutex_unlock(&mdev->state_lock);
@@ -2469,6 +2465,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->port = port;
 	priv->port_up = false;
 	priv->flags = prof->flags;
+	priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME;
 	priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
 			MLX4_WQE_CTRL_SOLICITED);
 	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
@@ -2535,7 +2532,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		}
 	}
 
-	memcpy(priv->prev_mac, dev->dev_addr, sizeof(priv->prev_mac));
+	memcpy(priv->current_mac, dev->dev_addr, sizeof(priv->current_mac));
 
 	priv->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
 					  DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 5535862f27cc..9c909d23f14c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -335,8 +335,9 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
 					   dev->caps.comp_pool/
 					   dev->caps.num_ports) - 1;
 
-		num_rx_rings = min_t(int, num_of_eqs,
-				     netif_get_num_default_rss_queues());
+		num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS :
+			min_t(int, num_of_eqs,
+			      netif_get_num_default_rss_queues());
 		mdev->profile.prof[i].rx_ring_num =
 			rounddown_pow_of_two(num_rx_rings);
 	}
@@ -933,7 +934,7 @@ static const int frag_sizes[] = {
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	int eff_mtu = dev->mtu + ETH_HLEN + VLAN_HLEN + ETH_LLC_SNAP_SIZE;
+	int eff_mtu = dev->mtu + ETH_HLEN + VLAN_HLEN;
 	int buf_size = 0;
 	int i = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 03e5f6ac67e7..49d5afc7cfb8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -159,7 +159,8 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf)
 		if (priv->mdev->dev->caps.flags &
 					MLX4_DEV_CAP_FLAG_UC_LOOPBACK) {
 			buf[3] = mlx4_en_test_registers(priv);
-			buf[4] = mlx4_en_test_loopback(priv);
+			if (priv->port_up)
+				buf[4] = mlx4_en_test_loopback(priv);
 		}
 
 		if (carrier_ok)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 5045bab59633..dae3da6d8dd0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -126,8 +126,13 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 		ring->bf.uar = &mdev->priv_uar;
 		ring->bf.uar->map = mdev->uar_map;
 		ring->bf_enabled = false;
-	} else
-		ring->bf_enabled = true;
+		ring->bf_alloced = false;
+		priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
+	} else {
+		ring->bf_alloced = true;
+		ring->bf_enabled = !!(priv->pflags &
+				      MLX4_EN_PRIV_FLAGS_BLUEFLAME);
+	}
 
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
 	ring->queue_index = queue_index;
@@ -161,7 +166,7 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 	struct mlx4_en_tx_ring *ring = *pring;
 	en_dbg(DRV, priv, "Destroying tx ring, qpn: %d\n", ring->qpn);
 
-	if (ring->bf_enabled)
+	if (ring->bf_alloced)
 		mlx4_bf_free(mdev->dev, &ring->bf);
 	mlx4_qp_remove(mdev->dev, &ring->qp);
 	mlx4_qp_free(mdev->dev, &ring->qp);
@@ -195,7 +200,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
 				ring->cqn, user_prio, &ring->context);
-	if (ring->bf_enabled)
+	if (ring->bf_alloced)
 		ring->context.usr_page = cpu_to_be32(ring->bf.uar->index);
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 82ab427290c3..80b8c5f30e4e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -120,6 +120,16 @@ static struct mlx4_profile default_profile = {
 	.num_mtt	= 1 << 20, /* It is really num mtt segements */
 };
 
+static struct mlx4_profile low_mem_profile = {
+	.num_qp		= 1 << 17,
+	.num_srq	= 1 << 6,
+	.rdmarc_per_qp	= 1 << 4,
+	.num_cq		= 1 << 8,
+	.num_mcg	= 1 << 8,
+	.num_mpt	= 1 << 9,
+	.num_mtt	= 1 << 7,
+};
+
 static int log_num_mac = 7;
 module_param_named(log_num_mac, log_num_mac, int, 0444);
 MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
@@ -129,6 +139,8 @@ module_param_named(log_num_vlan, log_num_vlan, int, 0444);
 MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
 /* Log2 max number of VLANs per ETH port (0-7) */
 #define MLX4_LOG_NUM_VLANS 7
+#define MLX4_MIN_LOG_NUM_VLANS 0
+#define MLX4_MIN_LOG_NUM_MAC 1
 
 static bool use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
@@ -287,8 +299,13 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (mlx4_is_mfunc(dev))
 		dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
 
-	dev->caps.log_num_macs  = log_num_mac;
-	dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
+	if (mlx4_low_memory_profile()) {
+		dev->caps.log_num_macs  = MLX4_MIN_LOG_NUM_MAC;
+		dev->caps.log_num_vlans = MLX4_MIN_LOG_NUM_VLANS;
+	} else {
+		dev->caps.log_num_macs  = log_num_mac;
+		dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
+	}
 
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
@@ -1587,7 +1604,12 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		if (mlx4_is_master(dev))
 			mlx4_parav_master_pf_caps(dev);
 
-		profile = default_profile;
+		if (mlx4_low_memory_profile()) {
+			mlx4_info(dev, "Running from within kdump kernel. Using low memory profile\n");
+			profile = low_mem_profile;
+		} else {
+			profile = default_profile;
+		}
 		if (dev->caps.steering_mode ==
 		    MLX4_STEERING_MODE_DEVICE_MANAGED)
 			profile.num_mcg = MLX4_FS_NUM_MCG;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 4c36def8e10f..d80e7a6fac74 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -270,7 +270,7 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 port,
 	 * we need to add it as a duplicate to this entry
 	 * for future references */
 	list_for_each_entry(dqp, &entry->duplicates, list) {
-		if (qpn == pqp->qpn)
+		if (qpn == dqp->qpn)
 			return 0; /* qp is already duplicated */
 	}
 
@@ -324,24 +324,22 @@ static bool check_duplicate_entry(struct mlx4_dev *dev, u8 port,
 	return true;
 }
 
-/* I a steering entry contains only promisc QPs, it can be removed. */
-static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
-				      enum mlx4_steer_type steer,
-				      unsigned int index, u32 tqpn)
+/* Returns true if all the QPs != tqpn contained in this entry
+ * are Promisc QPs. Returns false otherwise.
+ */
+static bool promisc_steering_entry(struct mlx4_dev *dev, u8 port,
+				   enum mlx4_steer_type steer,
+				   unsigned int index, u32 tqpn,
+				   u32 *members_count)
 {
-	struct mlx4_steer *s_steer;
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_mgm *mgm;
-	struct mlx4_steer_index *entry = NULL, *tmp_entry;
-	u32 qpn;
-	u32 members_count;
+	u32 m_count;
 	bool ret = false;
 	int i;
 
 	if (port < 1 || port > dev->caps.num_ports)
-		return NULL;
-
-	s_steer = &mlx4_priv(dev)->steer[port - 1];
+		return false;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -350,21 +348,61 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
 
 	if (mlx4_READ_ENTRY(dev, index, mailbox))
 		goto out;
-	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
-	for (i = 0;  i < members_count; i++) {
-		qpn = be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK;
+	m_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+	if (members_count)
+		*members_count = m_count;
+
+	for (i = 0;  i < m_count; i++) {
+		u32 qpn = be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK;
 		if (!get_promisc_qp(dev, port, steer, qpn) && qpn != tqpn) {
 			/* the qp is not promisc, the entry can't be removed */
 			goto out;
 		}
 	}
-	 /* All the qps currently registered for this entry are promiscuous,
+	ret = true;
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return ret;
+}
+
+/* IF a steering entry contains only promisc QPs, it can be removed. */
+static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
+				      enum mlx4_steer_type steer,
+				      unsigned int index, u32 tqpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_steer_index *entry = NULL, *tmp_entry;
+	u32 members_count;
+	bool ret = false;
+
+	if (port < 1 || port > dev->caps.num_ports)
+		return NULL;
+
+	s_steer = &mlx4_priv(dev)->steer[port - 1];
+
+	if (!promisc_steering_entry(dev, port, steer, index,
+				    tqpn, &members_count))
+		goto out;
+
+	/* All the qps currently registered for this entry are promiscuous,
 	  * Checking for duplicates */
 	ret = true;
 	list_for_each_entry_safe(entry, tmp_entry, &s_steer->steer_entries[steer], list) {
 		if (entry->index == index) {
-			if (list_empty(&entry->duplicates)) {
+			if (list_empty(&entry->duplicates) ||
+			    members_count == 1) {
+				struct mlx4_promisc_qp *pqp, *tmp_pqp;
+				/* If there is only 1 entry in duplicates then
+				 * this is the QP we want to delete, going over
+				 * the list and deleting the entry.
+				 */
 				list_del(&entry->list);
+				list_for_each_entry_safe(pqp, tmp_pqp,
+							 &entry->duplicates,
+							 list) {
+					list_del(&pqp->list);
+					kfree(pqp);
+				}
 				kfree(entry);
 			} else {
 				/* This entry contains duplicates so it shouldn't be removed */
@@ -375,7 +413,6 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
 	}
 
 out:
-	mlx4_free_cmd_mailbox(dev, mailbox);
 	return ret;
 }
 
@@ -421,42 +458,57 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 port,
 	}
 	mgm = mailbox->buf;
 
-	/* the promisc qp needs to be added for each one of the steering
-	 * entries, if it already exists, needs to be added as a duplicate
-	 * for this entry */
-	list_for_each_entry(entry, &s_steer->steer_entries[steer], list) {
-		err = mlx4_READ_ENTRY(dev, entry->index, mailbox);
-		if (err)
-			goto out_mailbox;
+	if (!(mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)) {
+		/* The promisc QP needs to be added for each one of the steering
+		 * entries. If it already exists, needs to be added as
+		 * a duplicate for this entry.
+		 */
+		list_for_each_entry(entry,
+				    &s_steer->steer_entries[steer],
+				    list) {
+			err = mlx4_READ_ENTRY(dev, entry->index, mailbox);
+			if (err)
+				goto out_mailbox;
 
-		members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
-		prot = be32_to_cpu(mgm->members_count) >> 30;
-		found = false;
-		for (i = 0; i < members_count; i++) {
-			if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qpn) {
-				/* Entry already exists, add to duplicates */
-				dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
-				if (!dqp) {
+			members_count = be32_to_cpu(mgm->members_count) &
+					0xffffff;
+			prot = be32_to_cpu(mgm->members_count) >> 30;
+			found = false;
+			for (i = 0; i < members_count; i++) {
+				if ((be32_to_cpu(mgm->qp[i]) &
+				     MGM_QPN_MASK) == qpn) {
+					/* Entry already exists.
+					 * Add to duplicates.
+					 */
+					dqp = kmalloc(sizeof(*dqp), GFP_KERNEL);
+					if (!dqp) {
+						err = -ENOMEM;
+						goto out_mailbox;
+					}
+					dqp->qpn = qpn;
+					list_add_tail(&dqp->list,
+						      &entry->duplicates);
+					found = true;
+				}
+			}
+			if (!found) {
+				/* Need to add the qpn to mgm */
+				if (members_count ==
+				    dev->caps.num_qp_per_mgm) {
+					/* entry is full */
 					err = -ENOMEM;
 					goto out_mailbox;
 				}
-				dqp->qpn = qpn;
-				list_add_tail(&dqp->list, &entry->duplicates);
-				found = true;
-			}
-		}
-		if (!found) {
-			/* Need to add the qpn to mgm */
-			if (members_count == dev->caps.num_qp_per_mgm) {
-				/* entry is full */
-				err = -ENOMEM;
-				goto out_mailbox;
+				mgm->qp[members_count++] =
+					cpu_to_be32(qpn & MGM_QPN_MASK);
+				mgm->members_count =
+					cpu_to_be32(members_count |
+						    (prot << 30));
+				err = mlx4_WRITE_ENTRY(dev, entry->index,
+						       mailbox);
+				if (err)
+					goto out_mailbox;
 			}
-			mgm->qp[members_count++] = cpu_to_be32(qpn & MGM_QPN_MASK);
-			mgm->members_count = cpu_to_be32(members_count | (prot << 30));
-			err = mlx4_WRITE_ENTRY(dev, entry->index, mailbox);
-			if (err)
-				goto out_mailbox;
 		}
 	}
 
@@ -465,8 +517,14 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 port,
 	/* now need to add all the promisc qps to default entry */
 	memset(mgm, 0, sizeof *mgm);
 	members_count = 0;
-	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
+	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list) {
+		if (members_count == dev->caps.num_qp_per_mgm) {
+			/* entry is full */
+			err = -ENOMEM;
+			goto out_list;
+		}
 		mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
+	}
 	mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
 
 	err = mlx4_WRITE_PROMISC(dev, port, steer, mailbox);
@@ -495,13 +553,13 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 	struct mlx4_steer *s_steer;
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_mgm *mgm;
-	struct mlx4_steer_index *entry;
+	struct mlx4_steer_index *entry, *tmp_entry;
 	struct mlx4_promisc_qp *pqp;
 	struct mlx4_promisc_qp *dqp;
 	u32 members_count;
 	bool found;
 	bool back_to_list = false;
-	int loc, i;
+	int i;
 	int err;
 
 	if (port < 1 || port > dev->caps.num_ports)
@@ -538,39 +596,73 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 	if (err)
 		goto out_mailbox;
 
-	/* remove the qp from all the steering entries*/
-	list_for_each_entry(entry, &s_steer->steer_entries[steer], list) {
-		found = false;
-		list_for_each_entry(dqp, &entry->duplicates, list) {
-			if (dqp->qpn == qpn) {
-				found = true;
-				break;
+	if (!(mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)) {
+		/* Remove the QP from all the steering entries */
+		list_for_each_entry_safe(entry, tmp_entry,
+					 &s_steer->steer_entries[steer],
+					 list) {
+			found = false;
+			list_for_each_entry(dqp, &entry->duplicates, list) {
+				if (dqp->qpn == qpn) {
+					found = true;
+					break;
+				}
 			}
-		}
-		if (found) {
-			/* a duplicate, no need to change the mgm,
-			 * only update the duplicates list */
-			list_del(&dqp->list);
-			kfree(dqp);
-		} else {
-			err = mlx4_READ_ENTRY(dev, entry->index, mailbox);
-				if (err)
-					goto out_mailbox;
-			members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
-			for (loc = -1, i = 0; i < members_count; ++i)
-				if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qpn)
-					loc = i;
-
-			mgm->members_count = cpu_to_be32(--members_count |
-							 (MLX4_PROT_ETH << 30));
-			mgm->qp[loc] = mgm->qp[i - 1];
-			mgm->qp[i - 1] = 0;
+			if (found) {
+				/* A duplicate, no need to change the MGM,
+				 * only update the duplicates list
+				 */
+				list_del(&dqp->list);
+				kfree(dqp);
+			} else {
+				int loc = -1;
+
+				err = mlx4_READ_ENTRY(dev,
+						      entry->index,
+						      mailbox);
+					if (err)
+						goto out_mailbox;
+				members_count =
+					be32_to_cpu(mgm->members_count) &
+					0xffffff;
+				if (!members_count) {
+					mlx4_warn(dev, "QP %06x wasn't found in entry %x mcount=0. deleting entry...\n",
+						  qpn, entry->index);
+					list_del(&entry->list);
+					kfree(entry);
+					continue;
+				}
 
-			err = mlx4_WRITE_ENTRY(dev, entry->index, mailbox);
-				if (err)
+				for (i = 0; i < members_count; ++i)
+					if ((be32_to_cpu(mgm->qp[i]) &
+					     MGM_QPN_MASK) == qpn) {
+						loc = i;
+						break;
+					}
+
+				if (loc < 0) {
+					mlx4_err(dev, "QP %06x wasn't found in entry %d\n",
+						 qpn, entry->index);
+					err = -EINVAL;
 					goto out_mailbox;
-		}
+				}
 
+				/* Copy the last QP in this MGM
+				 * over removed QP
+				 */
+				mgm->qp[loc] = mgm->qp[members_count - 1];
+				mgm->qp[members_count - 1] = 0;
+				mgm->members_count =
+					cpu_to_be32(--members_count |
+						    (MLX4_PROT_ETH << 30));
+
+				err = mlx4_WRITE_ENTRY(dev,
+						       entry->index,
+						       mailbox);
+					if (err)
+						goto out_mailbox;
+			}
+		}
 	}
 
 out_mailbox:
@@ -1062,7 +1154,7 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	struct mlx4_mgm *mgm;
 	u32 members_count;
 	int prev, index;
-	int i, loc;
+	int i, loc = -1;
 	int err;
 	u8 port = gid[5];
 	bool removed_entry = false;
@@ -1085,15 +1177,20 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		goto out;
 	}
 
-	/* if this pq is also a promisc qp, it shouldn't be removed */
+	/* If this QP is also a promisc QP, it shouldn't be removed only if
+	 * at least one none promisc QP is also attached to this MCG
+	 */
 	if (prot == MLX4_PROT_ETH &&
-	    check_duplicate_entry(dev, port, steer, index, qp->qpn))
-		goto out;
+	    check_duplicate_entry(dev, port, steer, index, qp->qpn) &&
+	    !promisc_steering_entry(dev, port, steer, index, qp->qpn, NULL))
+			goto out;
 
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
-	for (loc = -1, i = 0; i < members_count; ++i)
-		if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qp->qpn)
+	for (i = 0; i < members_count; ++i)
+		if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qp->qpn) {
 			loc = i;
+			break;
+		}
 
 	if (loc == -1) {
 		mlx4_err(dev, "QP %06x not found in MGM\n", qp->qpn);
@@ -1101,15 +1198,15 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		goto out;
 	}
 
-
+	/* copy the last QP in this MGM over removed QP */
+	mgm->qp[loc] = mgm->qp[members_count - 1];
+	mgm->qp[members_count - 1] = 0;
 	mgm->members_count = cpu_to_be32(--members_count | (u32) prot << 30);
-	mgm->qp[loc]       = mgm->qp[i - 1];
-	mgm->qp[i - 1]     = 0;
 
 	if (prot == MLX4_PROT_ETH)
 		removed_entry = can_remove_steering_entry(dev, port, steer,
 								index, qp->qpn);
-	if (i != 1 && (prot != MLX4_PROT_ETH || !removed_entry)) {
+	if (members_count && (prot != MLX4_PROT_ETH || !removed_entry)) {
 		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 1d8af7336807..13fbcd03c3e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -62,11 +62,6 @@
 
 #define INIT_HCA_TPT_MW_ENABLE          (1 << 7)
 
-#define MLX4_NUM_UP		8
-#define MLX4_NUM_TC		8
-#define MLX4_RATELIMIT_UNITS 3 /* 100 Mbps */
-#define MLX4_RATELIMIT_DEFAULT 0xffff
-
 struct mlx4_set_port_prio2tc_context {
 	u8 prio2tc[4];
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index d72a5a894fc6..3de41be49425 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -93,6 +93,8 @@
  * OS related constants and tunables
  */
 
+#define MLX4_EN_PRIV_FLAGS_BLUEFLAME 1
+
 #define MLX4_EN_WATCHDOG_TIMEOUT	(15 * HZ)
 
 /* Use the maximum between 16384 and a single page */
@@ -119,6 +121,7 @@ enum {
 #define MLX4_EN_MIN_TX_SIZE	(4096 / TXBB_SIZE)
 
 #define MLX4_EN_SMALL_PKT_SIZE		64
+#define MLX4_EN_MIN_TX_RING_P_UP	1
 #define MLX4_EN_MAX_TX_RING_P_UP	32
 #define MLX4_EN_NUM_UP			8
 #define MLX4_EN_DEF_TX_RING_SIZE	512
@@ -154,8 +157,6 @@ enum {
 #define MLX4_EN_TX_POLL_MODER	16
 #define MLX4_EN_TX_POLL_TIMEOUT	(HZ / 4)
 
-#define ETH_LLC_SNAP_SIZE	8
-
 #define SMALL_PACKET_SIZE      (256 - NET_IP_ALIGN)
 #define HEADER_COPY_SIZE       (128 - NET_IP_ALIGN)
 #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN)
@@ -280,6 +281,7 @@ struct mlx4_en_tx_ring {
 	unsigned long wake_queue;
 	struct mlx4_bf bf;
 	bool bf_enabled;
+	bool bf_alloced;
 	struct netdev_queue *tx_queue;
 	int hwtstamp_tx_type;
 	int inline_thold;
@@ -535,7 +537,7 @@ struct mlx4_en_priv {
 	int registered;
 	int allocated;
 	int stride;
-	unsigned char prev_mac[ETH_ALEN + 2];
+	unsigned char current_mac[ETH_ALEN + 2];
 	int mac_index;
 	unsigned max_mtu;
 	int base_qpn;
@@ -594,6 +596,8 @@ struct mlx4_en_priv {
 #endif
 	u64 tunnel_reg_id;
 	__be16 vxlan_port;
+
+	u32 pflags;
 };
 
 enum mlx4_en_wol {
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 7ab97174886d..9ba0c1ca10d5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -244,10 +244,16 @@ EXPORT_SYMBOL_GPL(mlx4_get_base_qpn);
 
 void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
+	struct mlx4_port_info *info;
+	struct mlx4_mac_table *table;
 	int index;
 
+	if (port < 1 || port > dev->caps.num_ports) {
+		mlx4_warn(dev, "invalid port number (%d), aborting...\n", port);
+		return;
+	}
+	info = &mlx4_priv(dev)->port[port];
+	table = &info->mac_table;
 	mutex_lock(&table->mutex);
 	index = find_index(dev, table, mac);
 
@@ -1051,14 +1057,26 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
 
 	for (i = 0; i < MLX4_NUM_TC; i++) {
 		struct mlx4_port_scheduler_tc_cfg_be *tc = &context->tc[i];
-		u16 r = ratelimit && ratelimit[i] ? ratelimit[i] :
-			MLX4_RATELIMIT_DEFAULT;
+		u16 r;
+
+		if (ratelimit && ratelimit[i]) {
+			if (ratelimit[i] <= MLX4_MAX_100M_UNITS_VAL) {
+				r = ratelimit[i];
+				tc->max_bw_units =
+					htons(MLX4_RATELIMIT_100M_UNITS);
+			} else {
+				r = ratelimit[i]/10;
+				tc->max_bw_units =
+					htons(MLX4_RATELIMIT_1G_UNITS);
+			}
+			tc->max_bw_value = htons(r);
+		} else {
+			tc->max_bw_value = htons(MLX4_RATELIMIT_DEFAULT);
+			tc->max_bw_units = htons(MLX4_RATELIMIT_1G_UNITS);
+		}
 
 		tc->pg = htons(pg[i]);
 		tc->bw_precentage = htons(tc_tx_bw[i]);
-
-		tc->max_bw_units = htons(MLX4_RATELIMIT_UNITS);
-		tc->max_bw_value = htons(r);
 	}
 
 	in_mod = MLX4_SET_PORT_SCHEDULER << 8 | port;