Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (56 commits)
  route: Take the right src and dst addresses in ip_route_newports
  ipv4: Fix nexthop caching wrt. scoping.
  ipv4: Invalidate nexthop cache nh_saddr more correctly.
  net: fix pch_gbe section mismatch warning
  ipv4: fix fib metrics
  mlx4_en: Removing HW info from ethtool -i report.
  net_sched: fix THROTTLED/RUNNING race
  drivers/net/a2065.c: Convert release_resource to release_region/release_mem_region
  drivers/net/ariadne.c: Convert release_resource to release_region/release_mem_region
  bonding: fix rx_handler locking
  myri10ge: fix rmmod crash
  mlx4_en: updated driver version to 1.5.4.1
  mlx4_en: Using blue flame support
  mlx4_core: reserve UARs for userspace consumers
  mlx4_core: maintain available field in bitmap allocator
  mlx4: Add blue flame support for kernel consumers
  mlx4_en: Enabling new steering
  mlx4: Add support for promiscuous mode in the new steering model.
  mlx4: generalization of multicast steering.
  mlx4_en: Reporting HW revision in ethtool -i
  ...

66 files changed, 1906 insertions, 364 deletions

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c7a6213c699..fbe1973f77b 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -625,7 +625,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
 				    !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROTOCOL_IB);
+				    MLX4_PROT_IB_IPV6);
 	if (err)
 		return err;
 
@@ -636,7 +636,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	return 0;
 
 err_add:
-	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROTOCOL_IB);
+	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
 	return err;
 }
 
@@ -666,7 +666,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct mlx4_ib_gid_entry *ge;
 
 	err = mlx4_multicast_detach(mdev->dev,
-				    &mqp->mqp, gid->raw, MLX4_PROTOCOL_IB);
+				    &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
 	if (err)
 		return err;
 
@@ -721,7 +721,6 @@ static int init_node_data(struct mlx4_ib_dev *dev)
 	if (err)
 		goto out;
 
-	dev->dev->rev_id = be32_to_cpup((__be32 *) (out_mad->data + 32));
 	memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8);
 
 out:
@@ -954,7 +953,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event
 	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
 		oldnd = iboe->netdevs[port - 1];
 		iboe->netdevs[port - 1] =
-			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROTOCOL_EN, port);
+			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
 		if (oldnd != iboe->netdevs[port - 1]) {
 			if (iboe->netdevs[port - 1])
 				netdev_added(ibdev, port);
@@ -1207,7 +1206,7 @@ static struct mlx4_interface mlx4_ib_interface = {
 	.add		= mlx4_ib_add,
 	.remove		= mlx4_ib_remove,
 	.event		= mlx4_ib_event,
-	.protocol	= MLX4_PROTOCOL_IB
+	.protocol	= MLX4_PROT_IB_IPV6
 };
 
 static int __init mlx4_ib_init(void)
diff --git a/drivers/net/a2065.c b/drivers/net/a2065.c
index f142cc21e45..deaa8bc16cf 100644
--- a/drivers/net/a2065.c
+++ b/drivers/net/a2065.c
@@ -711,14 +711,14 @@ static int __devinit a2065_init_one(struct zorro_dev *z,
 		return -EBUSY;
 	r2 = request_mem_region(mem_start, A2065_RAM_SIZE, "RAM");
 	if (!r2) {
-		release_resource(r1);
+		release_mem_region(base_addr, sizeof(struct lance_regs));
 		return -EBUSY;
 	}
 
 	dev = alloc_etherdev(sizeof(struct lance_private));
 	if (dev == NULL) {
-		release_resource(r1);
-		release_resource(r2);
+		release_mem_region(base_addr, sizeof(struct lance_regs));
+		release_mem_region(mem_start, A2065_RAM_SIZE);
 		return -ENOMEM;
 	}
 
@@ -764,8 +764,8 @@ static int __devinit a2065_init_one(struct zorro_dev *z,
 
 	err = register_netdev(dev);
 	if (err) {
-		release_resource(r1);
-		release_resource(r2);
+		release_mem_region(base_addr, sizeof(struct lance_regs));
+		release_mem_region(mem_start, A2065_RAM_SIZE);
 		free_netdev(dev);
 		return err;
 	}
diff --git a/drivers/net/ariadne.c b/drivers/net/ariadne.c
index 7ca0eded256..b7f45cd756a 100644
--- a/drivers/net/ariadne.c
+++ b/drivers/net/ariadne.c
@@ -182,14 +182,14 @@ static int __devinit ariadne_init_one(struct zorro_dev *z,
 	return -EBUSY;
     r2 = request_mem_region(mem_start, ARIADNE_RAM_SIZE, "RAM");
     if (!r2) {
-	release_resource(r1);
+	release_mem_region(base_addr, sizeof(struct Am79C960));
 	return -EBUSY;
     }
 
     dev = alloc_etherdev(sizeof(struct ariadne_private));
     if (dev == NULL) {
-	release_resource(r1);
-	release_resource(r2);
+	release_mem_region(base_addr, sizeof(struct Am79C960));
+	release_mem_region(mem_start, ARIADNE_RAM_SIZE);
 	return -ENOMEM;
     }
 
@@ -213,8 +213,8 @@ static int __devinit ariadne_init_one(struct zorro_dev *z,
 
     err = register_netdev(dev);
     if (err) {
-	release_resource(r1);
-	release_resource(r2);
+	release_mem_region(base_addr, sizeof(struct Am79C960));
+	release_mem_region(mem_start, ARIADNE_RAM_SIZE);
 	free_netdev(dev);
 	return err;
     }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 338bea147c6..16d6fe95469 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1482,21 +1482,16 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 {
 	struct sk_buff *skb = *pskb;
 	struct slave *slave;
-	struct net_device *bond_dev;
 	struct bonding *bond;
 
-	slave = bond_slave_get_rcu(skb->dev);
-	bond_dev = ACCESS_ONCE(slave->dev->master);
-	if (unlikely(!bond_dev))
-		return RX_HANDLER_PASS;
-
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return RX_HANDLER_CONSUMED;
 
 	*pskb = skb;
 
-	bond = netdev_priv(bond_dev);
+	slave = bond_slave_get_rcu(skb->dev);
+	bond = slave->bond;
 
 	if (bond->params.arp_interval)
 		slave->dev->last_rx = jiffies;
@@ -1505,10 +1500,10 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		return RX_HANDLER_EXACT;
 	}
 
-	skb->dev = bond_dev;
+	skb->dev = bond->dev;
 
 	if (bond->params.mode == BOND_MODE_ALB &&
-	    bond_dev->priv_flags & IFF_BRIDGE_PORT &&
+	    bond->dev->priv_flags & IFF_BRIDGE_PORT &&
 	    skb->pkt_type == PACKET_HOST) {
 
 		if (unlikely(skb_cow_head(skb,
@@ -1516,7 +1511,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 			kfree_skb(skb);
 			return RX_HANDLER_CONSUMED;
 		}
-		memcpy(eth_hdr(skb)->h_dest, bond_dev->dev_addr, ETH_ALEN);
+		memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN);
 	}
 
 	return RX_HANDLER_ANOTHER;
@@ -1698,20 +1693,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		pr_debug("Error %d calling netdev_set_bond_master\n", res);
 		goto err_restore_mac;
 	}
-	res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
-					 new_slave);
-	if (res) {
-		pr_debug("Error %d calling netdev_rx_handler_register\n", res);
-		goto err_unset_master;
-	}
 
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
 		pr_debug("Opening slave %s failed\n", slave_dev->name);
-		goto err_unreg_rxhandler;
+		goto err_unset_master;
 	}
 
+	new_slave->bond = bond;
 	new_slave->dev = slave_dev;
 	slave_dev->priv_flags |= IFF_BONDING;
 
@@ -1907,6 +1897,13 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	if (res)
 		goto err_close;
 
+	res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
+					 new_slave);
+	if (res) {
+		pr_debug("Error %d calling netdev_rx_handler_register\n", res);
+		goto err_dest_symlinks;
+	}
+
 	pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
 		bond_dev->name, slave_dev->name,
 		bond_is_active_slave(new_slave) ? "n active" : " backup",
@@ -1916,13 +1913,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	return 0;
 
 /* Undo stages on error */
+err_dest_symlinks:
+	bond_destroy_slave_symlinks(bond_dev, slave_dev);
+
 err_close:
 	dev_close(slave_dev);
 
-err_unreg_rxhandler:
-	netdev_rx_handler_unregister(slave_dev);
-	synchronize_net();
-
 err_unset_master:
 	netdev_set_bond_master(slave_dev, NULL);
 
@@ -1988,6 +1984,14 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 		return -EINVAL;
 	}
 
+	/* unregister rx_handler early so bond_handle_frame wouldn't be called
+	 * for this slave anymore.
+	 */
+	netdev_rx_handler_unregister(slave_dev);
+	write_unlock_bh(&bond->lock);
+	synchronize_net();
+	write_lock_bh(&bond->lock);
+
 	if (!bond->params.fail_over_mac) {
 		if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond->slave_cnt > 1)
@@ -2104,8 +2108,6 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 		netif_addr_unlock_bh(bond_dev);
 	}
 
-	netdev_rx_handler_unregister(slave_dev);
-	synchronize_net();
 	netdev_set_bond_master(slave_dev, NULL);
 
 	slave_disable_netpoll(slave);
@@ -2186,6 +2188,12 @@ static int bond_release_all(struct net_device *bond_dev)
 		 */
 		write_unlock_bh(&bond->lock);
 
+		/* unregister rx_handler early so bond_handle_frame wouldn't
+		 * be called for this slave anymore.
+		 */
+		netdev_rx_handler_unregister(slave_dev);
+		synchronize_net();
+
 		if (bond_is_lb(bond)) {
 			/* must be called only after the slave
 			 * has been detached from the list
@@ -2217,8 +2225,6 @@ static int bond_release_all(struct net_device *bond_dev)
 			netif_addr_unlock_bh(bond_dev);
 		}
 
-		netdev_rx_handler_unregister(slave_dev);
-		synchronize_net();
 		netdev_set_bond_master(slave_dev, NULL);
 
 		slave_disable_netpoll(slave);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 6b26962fd0e..90736cb4d97 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -187,6 +187,7 @@ struct slave {
 	struct net_device *dev; /* first - useful for panic debug */
 	struct slave *next;
 	struct slave *prev;
+	struct bonding *bond; /* our master */
 	int    delay;
 	unsigned long jiffies;
 	unsigned long last_arp_rx;
diff --git a/drivers/net/davinci_cpdma.c b/drivers/net/davinci_cpdma.c
index e92b2b6cd8c..ae47f23ba93 100644
--- a/drivers/net/davinci_cpdma.c
+++ b/drivers/net/davinci_cpdma.c
@@ -76,6 +76,7 @@ struct cpdma_desc {
 
 struct cpdma_desc_pool {
 	u32			phys;
+	u32			hw_addr;
 	void __iomem		*iomap;		/* ioremap map */
 	void			*cpumap;	/* dma_alloc map */
 	int			desc_size, mem_size;
@@ -137,7 +138,8 @@ struct cpdma_chan {
  * abstract out these details
  */
 static struct cpdma_desc_pool *
-cpdma_desc_pool_create(struct device *dev, u32 phys, int size, int align)
+cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr,
+				int size, int align)
 {
 	int bitmap_size;
 	struct cpdma_desc_pool *pool;
@@ -161,10 +163,12 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, int size, int align)
 	if (phys) {
 		pool->phys  = phys;
 		pool->iomap = ioremap(phys, size);
+		pool->hw_addr = hw_addr;
 	} else {
 		pool->cpumap = dma_alloc_coherent(dev, size, &pool->phys,
 						  GFP_KERNEL);
 		pool->iomap = (void __force __iomem *)pool->cpumap;
+		pool->hw_addr = pool->phys;
 	}
 
 	if (pool->iomap)
@@ -201,14 +205,14 @@ static inline dma_addr_t desc_phys(struct cpdma_desc_pool *pool,
 {
 	if (!desc)
 		return 0;
-	return pool->phys + (__force dma_addr_t)desc -
+	return pool->hw_addr + (__force dma_addr_t)desc -
 			    (__force dma_addr_t)pool->iomap;
 }
 
 static inline struct cpdma_desc __iomem *
 desc_from_phys(struct cpdma_desc_pool *pool, dma_addr_t dma)
 {
-	return dma ? pool->iomap + dma - pool->phys : NULL;
+	return dma ? pool->iomap + dma - pool->hw_addr : NULL;
 }
 
 static struct cpdma_desc __iomem *
@@ -260,6 +264,7 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
 
 	ctlr->pool = cpdma_desc_pool_create(ctlr->dev,
 					    ctlr->params.desc_mem_phys,
+					    ctlr->params.desc_hw_addr,
 					    ctlr->params.desc_mem_size,
 					    ctlr->params.desc_align);
 	if (!ctlr->pool) {
diff --git a/drivers/net/davinci_cpdma.h b/drivers/net/davinci_cpdma.h
index 868e50ebde4..afa19a0c0d8 100644
--- a/drivers/net/davinci_cpdma.h
+++ b/drivers/net/davinci_cpdma.h
@@ -33,6 +33,7 @@ struct cpdma_params {
 	bool			has_soft_reset;
 	int			min_packet_size;
 	u32			desc_mem_phys;
+	u32			desc_hw_addr;
 	int			desc_mem_size;
 	int			desc_align;
 
diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c
index 082d6ea6992..baca6bfcb08 100644
--- a/drivers/net/davinci_emac.c
+++ b/drivers/net/davinci_emac.c
@@ -1854,10 +1854,13 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
 	dma_params.rxcp			= priv->emac_base + 0x660;
 	dma_params.num_chan		= EMAC_MAX_TXRX_CHANNELS;
 	dma_params.min_packet_size	= EMAC_DEF_MIN_ETHPKTSIZE;
-	dma_params.desc_mem_phys	= hw_ram_addr;
+	dma_params.desc_hw_addr		= hw_ram_addr;
 	dma_params.desc_mem_size	= pdata->ctrl_ram_size;
 	dma_params.desc_align		= 16;
 
+	dma_params.desc_mem_phys = pdata->no_bd_ram ? 0 :
+			(u32 __force)res->start + pdata->ctrl_ram_offset;
+
 	priv->dma = cpdma_ctlr_create(&dma_params);
 	if (!priv->dma) {
 		dev_err(emac_dev, "DaVinci EMAC: Error initializing DMA\n");
diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index 3a4277f6fac..116cae334da 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -62,6 +62,9 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 	} else
 		obj = -1;
 
+	if (obj != -1)
+		--bitmap->avail;
+
 	spin_unlock(&bitmap->lock);
 
 	return obj;
@@ -101,11 +104,19 @@ u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
 	} else
 		obj = -1;
 
+	if (obj != -1)
+		bitmap->avail -= cnt;
+
 	spin_unlock(&bitmap->lock);
 
 	return obj;
 }
 
+u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap)
+{
+	return bitmap->avail;
+}
+
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
 {
 	obj &= bitmap->max + bitmap->reserved_top - 1;
@@ -115,6 +126,7 @@ void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
 	bitmap->last = min(bitmap->last, obj);
 	bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
 			& bitmap->mask;
+	bitmap->avail += cnt;
 	spin_unlock(&bitmap->lock);
 }
 
@@ -130,6 +142,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 	bitmap->max  = num - reserved_top;
 	bitmap->mask = mask;
 	bitmap->reserved_top = reserved_top;
+	bitmap->avail = num - reserved_top - reserved_bot;
 	spin_lock_init(&bitmap->lock);
 	bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
 				sizeof (long), GFP_KERNEL);
diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 7cd34e9c7c7..bd8ef9f2fa7 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -198,7 +198,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 	u64 mtt_addr;
 	int err;
 
-	if (vector >= dev->caps.num_comp_vectors)
+	if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool)
 		return -EINVAL;
 
 	cq->vector = vector;
diff --git a/drivers/net/mlx4/en_cq.c b/drivers/net/mlx4/en_cq.c
index 21786ad4455..ec4b6d047fe 100644
--- a/drivers/net/mlx4/en_cq.c
+++ b/drivers/net/mlx4/en_cq.c
@@ -51,13 +51,10 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	int err;
 
 	cq->size = entries;
-	if (mode == RX) {
+	if (mode == RX)
 		cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
-		cq->vector   = ring % mdev->dev->caps.num_comp_vectors;
-	} else {
+	else
 		cq->buf_size = sizeof(struct mlx4_cqe);
-		cq->vector   = 0;
-	}
 
 	cq->ring = ring;
 	cq->is_tx = mode;
@@ -80,7 +77,8 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err;
+	int err = 0;
+	char name[25];
 
 	cq->dev = mdev->pndev[priv->port];
 	cq->mcq.set_ci_db  = cq->wqres.db.db;
@@ -89,6 +87,29 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	*cq->mcq.arm_db    = 0;
 	memset(cq->buf, 0, cq->buf_size);
 
+	if (cq->is_tx == RX) {
+		if (mdev->dev->caps.comp_pool) {
+			if (!cq->vector) {
+				sprintf(name , "%s-rx-%d", priv->dev->name, cq->ring);
+				if (mlx4_assign_eq(mdev->dev, name, &cq->vector)) {
+					cq->vector = (cq->ring + 1 + priv->port) %
+						mdev->dev->caps.num_comp_vectors;
+					mlx4_warn(mdev, "Failed Assigning an EQ to "
+						  "%s_rx-%d ,Falling back to legacy EQ's\n",
+						  priv->dev->name, cq->ring);
+				}
+			}
+		} else {
+			cq->vector = (cq->ring + 1 + priv->port) %
+				mdev->dev->caps.num_comp_vectors;
+		}
+	} else {
+		if (!cq->vector || !mdev->dev->caps.comp_pool) {
+			/*Fallback to legacy pool in case of error*/
+			cq->vector   = 0;
+		}
+	}
+
 	if (!cq->is_tx)
 		cq->size = priv->rx_ring[cq->ring].actual_size;
 
@@ -112,12 +133,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	return 0;
 }
 
-void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
+			bool reserve_vectors)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 
 	mlx4_en_unmap_buffer(&cq->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
+	if (priv->mdev->dev->caps.comp_pool && cq->vector && !reserve_vectors)
+		mlx4_release_eq(priv->mdev->dev, cq->vector);
 	cq->buf_size = 0;
 	cq->buf = NULL;
 }
diff --git a/drivers/net/mlx4/en_ethtool.c b/drivers/net/mlx4/en_ethtool.c
index 056152b3ff5..d54b7abf022 100644
--- a/drivers/net/mlx4/en_ethtool.c
+++ b/drivers/net/mlx4/en_ethtool.c
@@ -45,7 +45,7 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 
-	sprintf(drvinfo->driver, DRV_NAME " (%s)", mdev->dev->board_id);
+	strncpy(drvinfo->driver, DRV_NAME, 32);
 	strncpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")", 32);
 	sprintf(drvinfo->fw_version, "%d.%d.%d",
 		(u16) (mdev->dev->caps.fw_ver >> 32),
@@ -131,8 +131,65 @@ static void mlx4_en_set_msglevel(struct net_device *dev, u32 val)
 static void mlx4_en_get_wol(struct net_device *netdev,
 			    struct ethtool_wolinfo *wol)
 {
-	wol->supported = 0;
-	wol->wolopts = 0;
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	int err = 0;
+	u64 config = 0;
+
+	if (!priv->mdev->dev->caps.wol) {
+		wol->supported = 0;
+		wol->wolopts = 0;
+		return;
+	}
+
+	err = mlx4_wol_read(priv->mdev->dev, &config, priv->port);
+	if (err) {
+		en_err(priv, "Failed to get WoL information\n");
+		return;
+	}
+
+	if (config & MLX4_EN_WOL_MAGIC)
+		wol->supported = WAKE_MAGIC;
+	else
+		wol->supported = 0;
+
+	if (config & MLX4_EN_WOL_ENABLED)
+		wol->wolopts = WAKE_MAGIC;
+	else
+		wol->wolopts = 0;
+}
+
+static int mlx4_en_set_wol(struct net_device *netdev,
+			    struct ethtool_wolinfo *wol)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	u64 config = 0;
+	int err = 0;
+
+	if (!priv->mdev->dev->caps.wol)
+		return -EOPNOTSUPP;
+
+	if (wol->supported & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	err = mlx4_wol_read(priv->mdev->dev, &config, priv->port);
+	if (err) {
+		en_err(priv, "Failed to get WoL info, unable to modify\n");
+		return err;
+	}
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		config |= MLX4_EN_WOL_DO_MODIFY | MLX4_EN_WOL_ENABLED |
+				MLX4_EN_WOL_MAGIC;
+	} else {
+		config &= ~(MLX4_EN_WOL_ENABLED | MLX4_EN_WOL_MAGIC);
+		config |= MLX4_EN_WOL_DO_MODIFY;
+	}
+
+	err = mlx4_wol_write(priv->mdev->dev, config, priv->port);
+	if (err)
+		en_err(priv, "Failed to set WoL information\n");
+
+	return err;
 }
 
 static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
@@ -388,7 +445,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 		mlx4_en_stop_port(dev);
 	}
 
-	mlx4_en_free_resources(priv);
+	mlx4_en_free_resources(priv, true);
 
 	priv->prof->tx_ring_size = tx_size;
 	priv->prof->rx_ring_size = rx_size;
@@ -442,6 +499,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_ethtool_stats = mlx4_en_get_ethtool_stats,
 	.self_test = mlx4_en_self_test,
 	.get_wol = mlx4_en_get_wol,
+	.set_wol = mlx4_en_set_wol,
 	.get_msglevel = mlx4_en_get_msglevel,
 	.set_msglevel = mlx4_en_set_msglevel,
 	.get_coalesce = mlx4_en_get_coalesce,
diff --git a/drivers/net/mlx4/en_main.c b/drivers/net/mlx4/en_main.c
index 1ff6ca6466e..9317b61a75b 100644
--- a/drivers/net/mlx4/en_main.c
+++ b/drivers/net/mlx4/en_main.c
@@ -241,16 +241,18 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
 		mdev->port_cnt++;
 
-	/* If we did not receive an explicit number of Rx rings, default to
-	 * the number of completion vectors populated by the mlx4_core */
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
-		mlx4_info(mdev, "Using %d tx rings for port:%d\n",
-			  mdev->profile.prof[i].tx_ring_num, i);
-		mdev->profile.prof[i].rx_ring_num = min_t(int,
-			roundup_pow_of_two(dev->caps.num_comp_vectors),
-			MAX_RX_RINGS);
-		mlx4_info(mdev, "Defaulting to %d rx rings for port:%d\n",
-			  mdev->profile.prof[i].rx_ring_num, i);
+		if (!dev->caps.comp_pool) {
+			mdev->profile.prof[i].rx_ring_num =
+				rounddown_pow_of_two(max_t(int, MIN_RX_RINGS,
+							   min_t(int,
+								 dev->caps.num_comp_vectors,
+								 MAX_RX_RINGS)));
+		} else {
+			mdev->profile.prof[i].rx_ring_num = rounddown_pow_of_two(
+				min_t(int, dev->caps.comp_pool/
+				      dev->caps.num_ports - 1 , MAX_MSIX_P_PORT - 1));
+		}
 	}
 
 	/* Create our own workqueue for reset/multicast tasks
@@ -294,7 +296,7 @@ static struct mlx4_interface mlx4_en_interface = {
 	.remove		= mlx4_en_remove,
 	.event		= mlx4_en_event,
 	.get_dev	= mlx4_en_get_netdev,
-	.protocol	= MLX4_PROTOCOL_EN,
+	.protocol	= MLX4_PROT_ETH,
 };
 
 static int __init mlx4_en_init(void)
diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c
index 897f576b8b1..5762ebde445 100644
--- a/drivers/net/mlx4/en_netdev.c
+++ b/drivers/net/mlx4/en_netdev.c
@@ -156,9 +156,8 @@ 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 */
-		mlx4_unregister_mac(mdev->dev, priv->port, priv->mac_index);
-		err = mlx4_register_mac(mdev->dev, priv->port,
-					priv->mac, &priv->mac_index);
+		err = mlx4_replace_mac(mdev->dev, priv->port,
+				       priv->base_qpn, priv->mac, 0);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
 	} else
@@ -214,6 +213,7 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct net_device *dev = priv->dev;
 	u64 mcast_addr = 0;
+	u8 mc_list[16] = {0};
 	int err;
 
 	mutex_lock(&mdev->state_lock);
@@ -239,8 +239,12 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 			priv->flags |= MLX4_EN_FLAG_PROMISC;
 
 			/* Enable promiscouos mode */
-			err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
-						     priv->base_qpn, 1);
+			if (!mdev->dev->caps.vep_uc_steering)
+				err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
+							     priv->base_qpn, 1);
+			else
+				err = mlx4_unicast_promisc_add(mdev->dev, priv->base_qpn,
+							       priv->port);
 			if (err)
 				en_err(priv, "Failed enabling "
 					     "promiscous mode\n");
@@ -252,10 +256,21 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 				en_err(priv, "Failed disabling "
 					     "multicast filter\n");
 
-			/* Disable port VLAN filter */
-			err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, NULL);
-			if (err)
-				en_err(priv, "Failed disabling VLAN filter\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 entering multicast promisc mode\n");
+				priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
+			}
+
+			if (priv->vlgrp) {
+				/* Disable port VLAN filter */
+				err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, NULL);
+				if (err)
+					en_err(priv, "Failed disabling VLAN filter\n");
+			}
 		}
 		goto out;
 	}
@@ -270,11 +285,24 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 		priv->flags &= ~MLX4_EN_FLAG_PROMISC;
 
 		/* Disable promiscouos mode */
-		err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
-					     priv->base_qpn, 0);
+		if (!mdev->dev->caps.vep_uc_steering)
+			err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
+						     priv->base_qpn, 0);
+		else
+			err = mlx4_unicast_promisc_remove(mdev->dev, priv->base_qpn,
+							  priv->port);
 		if (err)
 			en_err(priv, "Failed disabling promiscous 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 promiscous mode\n");
+			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+		}
+
 		/* Enable port VLAN filter */
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp);
 		if (err)
@@ -287,14 +315,38 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 					  0, MLX4_MCAST_DISABLE);
 		if (err)
 			en_err(priv, "Failed disabling multicast filter\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 entering multicast promisc mode\n");
+			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
+		}
 	} else {
 		int i;
+		/* 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 promiscous mode\n");
+			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+		}
 
 		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
 					  0, MLX4_MCAST_DISABLE);
 		if (err)
 			en_err(priv, "Failed disabling multicast filter\n");
 
+		/* Detach our qp from all the multicast addresses */
+		for (i = 0; i < priv->mc_addrs_cnt; i++) {
+			memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
+			mc_list[5] = priv->port;
+			mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
+					      mc_list, MLX4_PROT_ETH);
+		}
 		/* Flush mcast filter and init it with broadcast address */
 		mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, ETH_BCAST,
 				    1, MLX4_MCAST_CONFIG);
@@ -307,6 +359,10 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 		for (i = 0; i < priv->mc_addrs_cnt; i++) {
 			mcast_addr =
 			      mlx4_en_mac_to_u64(priv->mc_addrs + i * ETH_ALEN);
+			memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
+			mc_list[5] = priv->port;
+			mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp,
+					      mc_list, 0, MLX4_PROT_ETH);
 			mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
 					    mcast_addr, 0, MLX4_MCAST_CONFIG);
 		}
@@ -314,8 +370,6 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 					  0, MLX4_MCAST_ENABLE);
 		if (err)
 			en_err(priv, "Failed enabling multicast filter\n");
-
-		mlx4_en_clear_list(dev);
 	}
 out:
 	mutex_unlock(&mdev->state_lock);
@@ -417,7 +471,6 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 	unsigned long avg_pkt_size;
 	unsigned long rx_packets;
 	unsigned long rx_bytes;
-	unsigned long rx_byte_diff;
 	unsigned long tx_packets;
 	unsigned long tx_pkt_diff;
 	unsigned long rx_pkt_diff;
@@ -441,25 +494,20 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 	rx_pkt_diff = ((unsigned long) (rx_packets -
 					priv->last_moder_packets));
 	packets = max(tx_pkt_diff, rx_pkt_diff);
-	rx_byte_diff = rx_bytes - priv->last_moder_bytes;
-	rx_byte_diff = rx_byte_diff ? rx_byte_diff : 1;
 	rate = packets * HZ / period;
 	avg_pkt_size = packets ? ((unsigned long) (rx_bytes -
 				 priv->last_moder_bytes)) / packets : 0;
 
 	/* Apply auto-moderation only when packet rate exceeds a rate that
 	 * it matters */
-	if (rate > MLX4_EN_RX_RATE_THRESH) {
+	if (rate > MLX4_EN_RX_RATE_THRESH && avg_pkt_size > MLX4_EN_AVG_PKT_SMALL) {
 		/* If tx and rx packet rates are not balanced, assume that
 		 * traffic is mainly BW bound and apply maximum moderation.
 		 * Otherwise, moderate according to packet rate */
-		if (2 * tx_pkt_diff > 3 * rx_pkt_diff &&
-		    rx_pkt_diff / rx_byte_diff <
-		    MLX4_EN_SMALL_PKT_SIZE)
-			moder_time = priv->rx_usecs_low;
-		else if (2 * rx_pkt_diff > 3 * tx_pkt_diff)
+		if (2 * tx_pkt_diff > 3 * rx_pkt_diff ||
+		    2 * rx_pkt_diff > 3 * tx_pkt_diff) {
 			moder_time = priv->rx_usecs_high;
-		else {
+		} else {
 			if (rate < priv->pkt_rate_low)
 				moder_time = priv->rx_usecs_low;
 			else if (rate > priv->pkt_rate_high)
@@ -471,9 +519,7 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
 					priv->rx_usecs_low;
 		}
 	} else {
-		/* When packet rate is low, use default moderation rather than
-		 * 0 to prevent interrupt storms if traffic suddenly increases */
-		moder_time = priv->rx_usecs;
+		moder_time = priv->rx_usecs_low;
 	}
 
 	en_dbg(INTR, priv, "tx rate:%lu rx_rate:%lu\n",
@@ -565,6 +611,8 @@ int mlx4_en_start_port(struct net_device *dev)
 	int err = 0;
 	int i;
 	int j;
+	u8 mc_list[16] = {0};
+	char name[32];
 
 	if (priv->port_up) {
 		en_dbg(DRV, priv, "start port called while port already up\n");
@@ -603,16 +651,35 @@ int mlx4_en_start_port(struct net_device *dev)
 		++rx_index;
 	}
 
+	/* Set port mac number */
+	en_dbg(DRV, priv, "Setting mac for port %d\n", priv->port);
+	err = mlx4_register_mac(mdev->dev, priv->port,
+				priv->mac, &priv->base_qpn, 0);
+	if (err) {
+		en_err(priv, "Failed setting port mac\n");
+		goto cq_err;
+	}
+	mdev->mac_removed[priv->port] = 0;
+
 	err = mlx4_en_config_rss_steer(priv);
 	if (err) {
 		en_err(priv, "Failed configuring rss steering\n");
-		goto cq_err;
+		goto mac_err;
 	}
 
+	if (mdev->dev->caps.comp_pool && !priv->tx_vector) {
+		sprintf(name , "%s-tx", priv->dev->name);
+		if (mlx4_assign_eq(mdev->dev , name, &priv->tx_vector)) {
+			mlx4_warn(mdev, "Failed Assigning an EQ to "
+					"%s_tx ,Falling back to legacy "
+					"EQ's\n", priv->dev->name);
+		}
+	}
 	/* Configure tx cq's and rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		/* Configure cq */
 		cq = &priv->tx_cq[i];
+		cq->vector = priv->tx_vector;
 		err = mlx4_en_activate_cq(priv, cq);
 		if (err) {
 			en_err(priv, "Failed allocating Tx CQ\n");
@@ -659,24 +726,22 @@ int mlx4_en_start_port(struct net_device *dev)
 		en_err(priv, "Failed setting default qp numbers\n");
 		goto tx_err;
 	}
-	/* Set port mac number */
-	en_dbg(DRV, priv, "Setting mac for port %d\n", priv->port);
-	err = mlx4_register_mac(mdev->dev, priv->port,
-				priv->mac, &priv->mac_index);
-	if (err) {
-		en_err(priv, "Failed setting port mac\n");
-		goto tx_err;
-	}
-	mdev->mac_removed[priv->port] = 0;
 
 	/* Init port */
 	en_dbg(HW, priv, "Initializing port\n");
 	err = mlx4_INIT_PORT(mdev->dev, priv->port);
 	if (err) {
 		en_err(priv, "Failed Initializing port\n");
-		goto mac_err;
+		goto tx_err;
 	}
 
+	/* Attach rx QP to bradcast address */
+	memset(&mc_list[10], 0xff, ETH_ALEN);
+	mc_list[5] = priv->port;
+	if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
+				  0, MLX4_PROT_ETH))
+		mlx4_warn(mdev, "Failed Attaching Broadcast\n");
+
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->mcast_task);
 
@@ -684,8 +749,6 @@ int mlx4_en_start_port(struct net_device *dev)
 	netif_tx_start_all_queues(dev);
 	return 0;
 
-mac_err:
-	mlx4_unregister_mac(mdev->dev, priv->port, priv->mac_index);
 tx_err:
 	while (tx_index--) {
 		mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[tx_index]);
@@ -693,6 +756,8 @@ tx_err:
 	}
 
 	mlx4_en_release_rss_steer(priv);
+mac_err:
+	mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
 cq_err:
 	while (rx_index--)
 		mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
@@ -708,6 +773,7 @@ void mlx4_en_stop_port(struct net_device *dev)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int i;
+	u8 mc_list[16] = {0};
 
 	if (!priv->port_up) {
 		en_dbg(DRV, priv, "stop port called while port already down\n");
@@ -722,8 +788,23 @@ void mlx4_en_stop_port(struct net_device *dev)
 	/* Set port as not active */
 	priv->port_up = false;
 
+	/* Detach All multicasts */
+	memset(&mc_list[10], 0xff, ETH_ALEN);
+	mc_list[5] = priv->port;
+	mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
+			      MLX4_PROT_ETH);
+	for (i = 0; i < priv->mc_addrs_cnt; i++) {
+		memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
+		mc_list[5] = priv->port;
+		mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
+				      mc_list, MLX4_PROT_ETH);
+	}
+	mlx4_en_clear_list(dev);
+	/* Flush multicast filter */
+	mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);
+
 	/* Unregister Mac address for the port */
-	mlx4_unregister_mac(mdev->dev, priv->port, priv->mac_index);
+	mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
 	mdev->mac_removed[priv->port] = 1;
 
 	/* Free TX Rings */
@@ -801,7 +882,6 @@ static int mlx4_en_open(struct net_device *dev)
 		priv->rx_ring[i].packets = 0;
 	}
 
-	mlx4_en_set_default_moderation(priv);
 	err = mlx4_en_start_port(dev);
 	if (err)
 		en_err(priv, "Failed starting port:%d\n", priv->port);
@@ -828,7 +908,7 @@ static int mlx4_en_close(struct net_device *dev)
 	return 0;
 }
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv)
+void mlx4_en_free_resources(struct mlx4_en_priv *priv, bool reserve_vectors)
 {
 	int i;
 
@@ -836,14 +916,14 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 		if (priv->tx_ring[i].tx_info)
 			mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
 		if (priv->tx_cq[i].buf)
-			mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+			mlx4_en_destroy_cq(priv, &priv->tx_cq[i], reserve_vectors);
 	}
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		if (priv->rx_ring[i].rx_info)
 			mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i]);
 		if (priv->rx_cq[i].buf)
-			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
+			mlx4_en_destroy_cq(priv, &priv->rx_cq[i], reserve_vectors);
 	}
 }
 
@@ -851,6 +931,13 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
+	int base_tx_qpn, err;
+
+	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &base_tx_qpn);
+	if (err) {
+		en_err(priv, "failed reserving range for TX rings\n");
+		return err;
+	}
 
 	/* Create tx Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
@@ -858,7 +945,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 				      prof->tx_ring_size, i, TX))
 			goto err;
 
-		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
+		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], base_tx_qpn + i,
 					   prof->tx_ring_size, TXBB_SIZE))
 			goto err;
 	}
@@ -878,6 +965,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 
 err:
 	en_err(priv, "Failed to allocate NIC resources\n");
+	mlx4_qp_release_range(priv->mdev->dev, base_tx_qpn, priv->tx_ring_num);
 	return -ENOMEM;
 }
 
@@ -905,7 +993,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	mdev->pndev[priv->port] = NULL;
 	mutex_unlock(&mdev->state_lock);
 
-	mlx4_en_free_resources(priv);
+	mlx4_en_free_resources(priv, false);
 	free_netdev(dev);
 }
 
@@ -932,7 +1020,6 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 			en_dbg(DRV, priv, "Change MTU called with card down!?\n");
 		} else {
 			mlx4_en_stop_port(dev);
-			mlx4_en_set_default_moderation(priv);
 			err = mlx4_en_start_port(dev);
 			if (err) {
 				en_err(priv, "Failed restarting port:%d\n",
@@ -1079,7 +1166,25 @@ 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);
 
+	/* Configure port */
+	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
+				    MLX4_EN_MIN_MTU,
+				    0, 0, 0, 0);
+	if (err) {
+		en_err(priv, "Failed setting port general configurations "
+		       "for port %d, with error %d\n", priv->port, err);
+		goto out;
+	}
+
+	/* Init port */
+	en_warn(priv, "Initializing port\n");
+	err = mlx4_INIT_PORT(mdev->dev, priv->port);
+	if (err) {
+		en_err(priv, "Failed Initializing port\n");
+		goto out;
+	}
 	priv->registered = 1;
+	mlx4_en_set_default_moderation(priv);
 	queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
 	return 0;
 
diff --git a/drivers/net/mlx4/en_port.c b/drivers/net/mlx4/en_port.c
index 7f5a3221e0c..f2a4f5dd313 100644
--- a/drivers/net/mlx4/en_port.c
+++ b/drivers/net/mlx4/en_port.c
@@ -119,6 +119,10 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 	struct mlx4_set_port_rqp_calc_context *context;
 	int err;
 	u32 in_mod;
+	u32 m_promisc = (dev->caps.vep_mc_steering) ? MCAST_DIRECT : MCAST_DEFAULT;
+
+	if (dev->caps.vep_mc_steering && dev->caps.vep_uc_steering)
+		return 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -127,8 +131,11 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 	memset(context, 0, sizeof *context);
 
 	context->base_qpn = cpu_to_be32(base_qpn);
-	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_EN_SHIFT | base_qpn);
-	context->mcast = cpu_to_be32(1 << SET_PORT_PROMISC_MODE_SHIFT | base_qpn);
+	context->n_mac = 0x7;
+	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
+				       base_qpn);
+	context->mcast = cpu_to_be32(m_promisc << SET_PORT_MC_PROMISC_SHIFT |
+				     base_qpn);
 	context->intra_no_vlan = 0;
 	context->no_vlan = MLX4_NO_VLAN_IDX;
 	context->intra_vlan_miss = 0;
@@ -206,7 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	}
 	stats->tx_packets = 0;
 	stats->tx_bytes = 0;
-	for (i = 0; i <= priv->tx_ring_num; i++) {
+	for (i = 0; i < priv->tx_ring_num; i++) {
 		stats->tx_packets += priv->tx_ring[i].packets;
 		stats->tx_bytes += priv->tx_ring[i].bytes;
 	}
diff --git a/drivers/net/mlx4/en_port.h b/drivers/net/mlx4/en_port.h
index 092e814b198..e3d73e41c56 100644
--- a/drivers/net/mlx4/en_port.h
+++ b/drivers/net/mlx4/en_port.h
@@ -36,8 +36,8 @@
 
 
 #define SET_PORT_GEN_ALL_VALID	0x7
-#define SET_PORT_PROMISC_EN_SHIFT	31
-#define SET_PORT_PROMISC_MODE_SHIFT	30
+#define SET_PORT_PROMISC_SHIFT	31
+#define SET_PORT_MC_PROMISC_SHIFT	30
 
 enum {
 	MLX4_CMD_SET_VLAN_FLTR  = 0x47,
@@ -45,6 +45,12 @@ enum {
 	MLX4_CMD_DUMP_ETH_STATS = 0x49,
 };
 
+enum {
+	MCAST_DIRECT_ONLY       = 0,
+	MCAST_DIRECT            = 1,
+	MCAST_DEFAULT           = 2
+};
+
 struct mlx4_set_port_general_context {
 	u8 reserved[3];
 	u8 flags;
@@ -60,14 +66,17 @@ struct mlx4_set_port_general_context {
 
 struct mlx4_set_port_rqp_calc_context {
 	__be32 base_qpn;
-	__be32 flags;
-	u8 reserved[3];
+	u8 rererved;
+	u8 n_mac;
+	u8 n_vlan;
+	u8 n_prio;
+	u8 reserved2[3];
 	u8 mac_miss;
 	u8 intra_no_vlan;
 	u8 no_vlan;
 	u8 intra_vlan_miss;
 	u8 vlan_miss;
-	u8 reserved2[3];
+	u8 reserved3[3];
 	u8 no_vlan_prio;
 	__be32 promisc;
 	__be32 mcast;
diff --git a/drivers/net/mlx4/en_rx.c b/drivers/net/mlx4/en_rx.c
index 570f2508fb3..05998ee297c 100644
--- a/drivers/net/mlx4/en_rx.c
+++ b/drivers/net/mlx4/en_rx.c
@@ -845,16 +845,10 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	}
 
 	/* Configure RSS indirection qp */
-	err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &priv->base_qpn);
-	if (err) {
-		en_err(priv, "Failed to reserve range for RSS "
-			     "indirection qp\n");
-		goto rss_err;
-	}
 	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, &rss_map->indir_qp);
 	if (err) {
 		en_err(priv, "Failed to allocate RSS indirection QP\n");
-		goto reserve_err;
+		goto rss_err;
 	}
 	rss_map->indir_qp.event = mlx4_en_sqp_event;
 	mlx4_en_fill_qp_context(priv, 0, 0, 0, 1, priv->base_qpn,
@@ -881,8 +875,6 @@ indir_err:
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->indir_qp);
 	mlx4_qp_remove(mdev->dev, &rss_map->indir_qp);
 	mlx4_qp_free(mdev->dev, &rss_map->indir_qp);
-reserve_err:
-	mlx4_qp_release_range(mdev->dev, priv->base_qpn, 1);
 rss_err:
 	for (i = 0; i < good_qps; i++) {
 		mlx4_qp_modify(mdev->dev, NULL, rss_map->state[i],
@@ -904,7 +896,6 @@ void mlx4_en_release_rss_steer(struct mlx4_en_priv *priv)
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->indir_qp);
 	mlx4_qp_remove(mdev->dev, &rss_map->indir_qp);
 	mlx4_qp_free(mdev->dev, &rss_map->indir_qp);
-	mlx4_qp_release_range(mdev->dev, priv->base_qpn, 1);
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		mlx4_qp_modify(mdev->dev, NULL, rss_map->state[i],
diff --git a/drivers/net/mlx4/en_tx.c b/drivers/net/mlx4/en_tx.c
index a680cd4a5ab..01feb8fd42a 100644
--- a/drivers/net/mlx4/en_tx.c
+++ b/drivers/net/mlx4/en_tx.c
@@ -44,6 +44,7 @@
 
 enum {
 	MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */
+	MAX_BF = 256,
 };
 
 static int inline_thold __read_mostly = MAX_INLINE;
@@ -52,7 +53,7 @@ module_param_named(inline_thold, inline_thold, int, 0444);
 MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
-			   struct mlx4_en_tx_ring *ring, u32 size,
+			   struct mlx4_en_tx_ring *ring, int qpn, u32 size,
 			   u16 stride)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -103,23 +104,25 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	       "buf_size:%d dma:%llx\n", ring, ring->buf, ring->size,
 	       ring->buf_size, (unsigned long long) ring->wqres.buf.direct.map);
 
-	err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn);
-	if (err) {
-		en_err(priv, "Failed reserving qp for tx ring.\n");
-		goto err_map;
-	}
-
+	ring->qpn = qpn;
 	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp);
 	if (err) {
 		en_err(priv, "Failed allocating qp %d\n", ring->qpn);
-		goto err_reserve;
+		goto err_map;
 	}
 	ring->qp.event = mlx4_en_sqp_event;
 
+	err = mlx4_bf_alloc(mdev->dev, &ring->bf);
+	if (err) {
+		en_dbg(DRV, priv, "working without blueflame (%d)", err);
+		ring->bf.uar = &mdev->priv_uar;
+		ring->bf.uar->map = mdev->uar_map;
+		ring->bf_enabled = false;
+	} else
+		ring->bf_enabled = true;
+
 	return 0;
 
-err_reserve:
-	mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
 err_map:
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 err_hwq_res:
@@ -139,6 +142,8 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	en_dbg(DRV, priv, "Destroying tx ring, qpn: %d\n", ring->qpn);
 
+	if (ring->bf_enabled)
+		mlx4_bf_free(mdev->dev, &ring->bf);
 	mlx4_qp_remove(mdev->dev, &ring->qp);
 	mlx4_qp_free(mdev->dev, &ring->qp);
 	mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
@@ -171,6 +176,8 @@ 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, &ring->context);
+	if (ring->bf_enabled)
+		ring->context.usr_page = cpu_to_be32(ring->bf.uar->index);
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
@@ -591,6 +598,11 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
 	return skb_tx_hash(dev, skb);
 }
 
+static void mlx4_bf_copy(unsigned long *dst, unsigned long *src, unsigned bytecnt)
+{
+	__iowrite64_copy(dst, src, bytecnt / 8);
+}
+
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -609,12 +621,13 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	int desc_size;
 	int real_size;
 	dma_addr_t dma;
-	u32 index;
+	u32 index, bf_index;
 	__be32 op_own;
 	u16 vlan_tag = 0;
 	int i;
 	int lso_header_size;
 	void *fragptr;
+	bool bounce = false;
 
 	if (!priv->port_up)
 		goto tx_drop;
@@ -657,13 +670,16 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Packet is good - grab an index and transmit it */
 	index = ring->prod & ring->size_mask;
+	bf_index = ring->prod;
 
 	/* See if we have enough space for whole descriptor TXBB for setting
 	 * SW ownership on next descriptor; if not, use a bounce buffer. */
 	if (likely(index + nr_txbb <= ring->size))
 		tx_desc = ring->buf + index * TXBB_SIZE;
-	else
+	else {
 		tx_desc = (struct mlx4_en_tx_desc *) ring->bounce_buf;
+		bounce = true;
+	}
 
 	/* Save skb in tx_info ring */
 	tx_info = &ring->tx_info[index];
@@ -768,21 +784,37 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	ring->prod += nr_txbb;
 
 	/* If we used a bounce buffer then copy descriptor back into place */
-	if (tx_desc == (struct mlx4_en_tx_desc *) ring->bounce_buf)
+	if (bounce)
 		tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size);
 
 	/* Run destructor before passing skb to HW */
 	if (likely(!skb_shared(skb)))
 		skb_orphan(skb);
 
-	/* Ensure new descirptor hits memory
-	 * before setting ownership of this descriptor to HW */
-	wmb();
-	tx_desc->ctrl.owner_opcode = op_own;
+	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tag) {
+		*(u32 *) (&tx_desc->ctrl.vlan_tag) |= ring->doorbell_qpn;
+		op_own |= htonl((bf_index & 0xffff) << 8);
+		/* Ensure new descirptor hits memory
+		* before setting ownership of this descriptor to HW */
+		wmb();
+		tx_desc->ctrl.owner_opcode = op_own;
 
-	/* Ring doorbell! */
-	wmb();
-	writel(ring->doorbell_qpn, mdev->uar_map + MLX4_SEND_DOORBELL);
+		wmb();
+
+		mlx4_bf_copy(ring->bf.reg + ring->bf.offset, (unsigned long *) &tx_desc->ctrl,
+		     desc_size);
+
+		wmb();
+
+		ring->bf.offset ^= ring->bf.buf_size;
+	} else {
+		/* Ensure new descirptor hits memory
+		* before setting ownership of this descriptor to HW */
+		wmb();
+		tx_desc->ctrl.owner_opcode = op_own;
+		wmb();
+		writel(ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL);
+	}
 
 	/* Poll CQ here */
 	mlx4_en_xmit_poll(priv, tx_ind);
diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 552d0fce6f6..506cfd0372e 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -42,7 +42,7 @@
 #include "fw.h"
 
 enum {
-	MLX4_IRQNAME_SIZE	= 64
+	MLX4_IRQNAME_SIZE	= 32
 };
 
 enum {
@@ -317,8 +317,8 @@ static int mlx4_num_eq_uar(struct mlx4_dev *dev)
 	 * we need to map, take the difference of highest index and
 	 * the lowest index we'll use and add 1.
 	 */
-	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs) / 4 -
-		dev->caps.reserved_eqs / 4 + 1;
+	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs +
+		 dev->caps.comp_pool)/4 - dev->caps.reserved_eqs/4 + 1;
 }
 
 static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
@@ -496,16 +496,32 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 static void mlx4_free_irqs(struct mlx4_dev *dev)
 {
 	struct mlx4_eq_table *eq_table = &mlx4_priv(dev)->eq_table;
-	int i;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int	i, vec;
 
 	if (eq_table->have_irq)
 		free_irq(dev->pdev->irq, dev);
+
 	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
 		if (eq_table->eq[i].have_irq) {
 			free_irq(eq_table->eq[i].irq, eq_table->eq + i);
 			eq_table->eq[i].have_irq = 0;
 		}
 
+	for (i = 0; i < dev->caps.comp_pool; i++) {
+		/*
+		 * Freeing the assigned irq's
+		 * all bits should be 0, but we need to validate
+		 */
+		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			/* NO need protecting*/
+			vec = dev->caps.num_comp_vectors + 1 + i;
+			free_irq(priv->eq_table.eq[vec].irq,
+				 &priv->eq_table.eq[vec]);
+		}
+	}
+
+
 	kfree(eq_table->irq_names);
 }
 
@@ -578,7 +594,8 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		(priv->eq_table.inta_pin < 32 ? 4 : 0);
 
 	priv->eq_table.irq_names =
-		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1),
+		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 +
+					     dev->caps.comp_pool),
 			GFP_KERNEL);
 	if (!priv->eq_table.irq_names) {
 		err = -ENOMEM;
@@ -601,6 +618,22 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	if (err)
 		goto err_out_comp;
 
+	/*if additional completion vectors poolsize is 0 this loop will not run*/
+	for (i = dev->caps.num_comp_vectors + 1;
+	      i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) {
+
+		err = mlx4_create_eq(dev, dev->caps.num_cqs -
+					  dev->caps.reserved_cqs +
+					  MLX4_NUM_SPARE_EQE,
+				     (dev->flags & MLX4_FLAG_MSI_X) ? i : 0,
+				     &priv->eq_table.eq[i]);
+		if (err) {
+			--i;
+			goto err_out_unmap;
+		}
+	}
+
+
 	if (dev->flags & MLX4_FLAG_MSI_X) {
 		const char *eq_name;
 
@@ -686,7 +719,7 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 
 	mlx4_free_irqs(dev);
 
-	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
+	for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i)
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
 
 	mlx4_unmap_clr_int(dev);
@@ -743,3 +776,65 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 	return err;
 }
 EXPORT_SYMBOL(mlx4_test_interrupts);
+
+int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector)
+{
+
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int vec = 0, err = 0, i;
+
+	spin_lock(&priv->msix_ctl.pool_lock);
+	for (i = 0; !vec && i < dev->caps.comp_pool; i++) {
+		if (~priv->msix_ctl.pool_bm & 1ULL << i) {
+			priv->msix_ctl.pool_bm |= 1ULL << i;
+			vec = dev->caps.num_comp_vectors + 1 + i;
+			snprintf(priv->eq_table.irq_names +
+					vec * MLX4_IRQNAME_SIZE,
+					MLX4_IRQNAME_SIZE, "%s", name);
+			err = request_irq(priv->eq_table.eq[vec].irq,
+					  mlx4_msi_x_interrupt, 0,
+					  &priv->eq_table.irq_names[vec<<5],
+					  priv->eq_table.eq + vec);
+			if (err) {
+				/*zero out bit by fliping it*/
+				priv->msix_ctl.pool_bm ^= 1 << i;
+				vec = 0;
+				continue;
+				/*we dont want to break here*/
+			}
+			eq_set_ci(&priv->eq_table.eq[vec], 1);
+		}
+	}
+	spin_unlock(&priv->msix_ctl.pool_lock);
+
+	if (vec) {
+		*vector = vec;
+	} else {
+		*vector = 0;
+		err = (i == dev->caps.comp_pool) ? -ENOSPC : err;
+	}
+	return err;
+}
+EXPORT_SYMBOL(mlx4_assign_eq);
+
+void mlx4_release_eq(struct mlx4_dev *dev, int vec)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	/*bm index*/
+	int i = vec - dev->caps.num_comp_vectors - 1;
+
+	if (likely(i >= 0)) {
+		/*sanity check , making sure were not trying to free irq's
+		  Belonging to a legacy EQ*/
+		spin_lock(&priv->msix_ctl.pool_lock);
+		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			free_irq(priv->eq_table.eq[vec].irq,
+				 &priv->eq_table.eq[vec]);
+			priv->msix_ctl.pool_bm &= ~(1ULL << i);
+		}
+		spin_unlock(&priv->msix_ctl.pool_lock);
+	}
+
+}
+EXPORT_SYMBOL(mlx4_release_eq);
+
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 5de1db89783..67a209ba939 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -274,8 +274,11 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->stat_rate_support = stat_rate;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_UDP_RSS_OFFSET);
 	dev_cap->udp_rss = field & 0x1;
+	dev_cap->vep_uc_steering = field & 0x2;
+	dev_cap->vep_mc_steering = field & 0x4;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_ETH_UC_LOOPBACK_OFFSET);
 	dev_cap->loopback_support = field & 0x1;
+	dev_cap->wol = field & 0x40;
 	MLX4_GET(dev_cap->flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_UAR_OFFSET);
 	dev_cap->reserved_uars = field >> 4;
@@ -737,6 +740,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define	 INIT_HCA_MC_BASE_OFFSET	 (INIT_HCA_MCAST_OFFSET + 0x00)
 #define	 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12)
 #define	 INIT_HCA_LOG_MC_HASH_SZ_OFFSET	 (INIT_HCA_MCAST_OFFSET + 0x16)
+#define  INIT_HCA_UC_STEERING_OFFSET	 (INIT_HCA_MCAST_OFFSET + 0x18)
 #define	 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b)
 #define INIT_HCA_TPT_OFFSET		 0x0f0
 #define	 INIT_HCA_DMPT_BASE_OFFSET	 (INIT_HCA_TPT_OFFSET + 0x00)
@@ -797,6 +801,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	MLX4_PUT(inbox, param->mc_base,		INIT_HCA_MC_BASE_OFFSET);
 	MLX4_PUT(inbox, param->log_mc_entry_sz, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
 	MLX4_PUT(inbox, param->log_mc_hash_sz,  INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+	if (dev->caps.vep_mc_steering)
+		MLX4_PUT(inbox, (u8) (1 << 3),	INIT_HCA_UC_STEERING_OFFSET);
 	MLX4_PUT(inbox, param->log_mc_table_sz, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
 
 	/* TPT attributes */
@@ -908,3 +914,22 @@ int mlx4_NOP(struct mlx4_dev *dev)
 	/* Input modifier of 0x1f means "finish as soon as possible." */
 	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100);
 }
+
+#define MLX4_WOL_SETUP_MODE (5 << 28)
+int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port)
+{
+	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
+
+	return mlx4_cmd_imm(dev, 0, config, in_mod, 0x3,
+			    MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A);
+}
+EXPORT_SYMBOL_GPL(mlx4_wol_read);
+
+int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port)
+{
+	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
+
+	return mlx4_cmd(dev, config, in_mod, 0x1, MLX4_CMD_MOD_STAT_CFG,
+					MLX4_CMD_TIME_CLASS_A);
+}
+EXPORT_SYMBOL_GPL(mlx4_wol_write);
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index 65cc72eb899..88003ebc618 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -80,6 +80,9 @@ struct mlx4_dev_cap {
 	u16 stat_rate_support;
 	int udp_rss;
 	int loopback_support;
+	int vep_uc_steering;
+	int vep_mc_steering;
+	int wol;
 	u32 flags;
 	int reserved_uars;
 	int uar_size;
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index c83501122d7..62fa7eec5f0 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -39,6 +39,7 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
+#include <linux/io-mapping.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -227,6 +228,9 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.udp_rss	     = dev_cap->udp_rss;
 	dev->caps.loopback_support   = dev_cap->loopback_support;
+	dev->caps.vep_uc_steering    = dev_cap->vep_uc_steering;
+	dev->caps.vep_mc_steering    = dev_cap->vep_mc_steering;
+	dev->caps.wol		     = dev_cap->wol;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
 	dev->caps.log_num_macs  = log_num_mac;
@@ -718,8 +722,31 @@ static void mlx4_free_icms(struct mlx4_dev *dev)
 	mlx4_free_icm(dev, priv->fw.aux_icm, 0);
 }
 
+static int map_bf_area(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	resource_size_t bf_start;
+	resource_size_t bf_len;
+	int err = 0;
+
+	bf_start = pci_resource_start(dev->pdev, 2) + (dev->caps.num_uars << PAGE_SHIFT);
+	bf_len = pci_resource_len(dev->pdev, 2) - (dev->caps.num_uars << PAGE_SHIFT);
+	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
+	if (!priv->bf_mapping)
+		err = -ENOMEM;
+
+	return err;
+}
+
+static void unmap_bf_area(struct mlx4_dev *dev)
+{
+	if (mlx4_priv(dev)->bf_mapping)
+		io_mapping_free(mlx4_priv(dev)->bf_mapping);
+}
+
 static void mlx4_close_hca(struct mlx4_dev *dev)
 {
+	unmap_bf_area(dev);
 	mlx4_CLOSE_HCA(dev, 0);
 	mlx4_free_icms(dev);
 	mlx4_UNMAP_FA(dev);
@@ -772,6 +799,9 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		goto err_stop_fw;
 	}
 
+	if (map_bf_area(dev))
+		mlx4_dbg(dev, "Failed to map blue flame area\n");
+
 	init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
 
 	err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
@@ -802,6 +832,7 @@ err_free_icm:
 	mlx4_free_icms(dev);
 
 err_stop_fw:
+	unmap_bf_area(dev);
 	mlx4_UNMAP_FA(dev);
 	mlx4_free_icm(dev, priv->fw.fw_icm, 0);
 
@@ -969,13 +1000,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct msix_entry *entries;
-	int nreq;
+	int nreq = min_t(int, dev->caps.num_ports *
+			 min_t(int, num_online_cpus() + 1, MAX_MSIX_P_PORT)
+				+ MSIX_LEGACY_SZ, MAX_MSIX);
 	int err;
 	int i;
 
 	if (msi_x) {
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
-			     num_possible_cpus() + 1);
+			     nreq);
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
 			goto no_msi;
@@ -998,7 +1031,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			goto no_msi;
 		}
 
-		dev->caps.num_comp_vectors = nreq - 1;
+		if (nreq <
+		    MSIX_LEGACY_SZ + dev->caps.num_ports * MIN_MSIX_P_PORT) {
+			/*Working in legacy mode , all EQ's shared*/
+			dev->caps.comp_pool           = 0;
+			dev->caps.num_comp_vectors = nreq - 1;
+		} else {
+			dev->caps.comp_pool           = nreq - MSIX_LEGACY_SZ;
+			dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1;
+		}
 		for (i = 0; i < nreq; ++i)
 			priv->eq_table.eq[i].irq = entries[i].vector;
 
@@ -1010,6 +1051,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 no_msi:
 	dev->caps.num_comp_vectors = 1;
+	dev->caps.comp_pool	   = 0;
 
 	for (i = 0; i < 2; ++i)
 		priv->eq_table.eq[i].irq = dev->pdev->irq;
@@ -1049,6 +1091,59 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
 	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
 }
 
+static int mlx4_init_steering(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int num_entries = dev->caps.num_ports;
+	int i, j;
+
+	priv->steer = kzalloc(sizeof(struct mlx4_steer) * num_entries, GFP_KERNEL);
+	if (!priv->steer)
+		return -ENOMEM;
+
+	for (i = 0; i < num_entries; i++) {
+		for (j = 0; j < MLX4_NUM_STEERS; j++) {
+			INIT_LIST_HEAD(&priv->steer[i].promisc_qps[j]);
+			INIT_LIST_HEAD(&priv->steer[i].steer_entries[j]);
+		}
+		INIT_LIST_HEAD(&priv->steer[i].high_prios);
+	}
+	return 0;
+}
+
+static void mlx4_clear_steering(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_steer_index *entry, *tmp_entry;
+	struct mlx4_promisc_qp *pqp, *tmp_pqp;
+	int num_entries = dev->caps.num_ports;
+	int i, j;
+
+	for (i = 0; i < num_entries; i++) {
+		for (j = 0; j < MLX4_NUM_STEERS; j++) {
+			list_for_each_entry_safe(pqp, tmp_pqp,
+						 &priv->steer[i].promisc_qps[j],
+						 list) {
+				list_del(&pqp->list);
+				kfree(pqp);
+			}
+			list_for_each_entry_safe(entry, tmp_entry,
+						 &priv->steer[i].steer_entries[j],
+						 list) {
+				list_del(&entry->list);
+				list_for_each_entry_safe(pqp, tmp_pqp,
+							 &entry->duplicates,
+							 list) {
+					list_del(&pqp->list);
+					kfree(pqp);
+				}
+				kfree(entry);
+			}
+		}
+	}
+	kfree(priv->steer);
+}
+
 static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx4_priv *priv;
@@ -1130,6 +1225,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
 
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &dev->rev_id);
+
+	INIT_LIST_HEAD(&priv->bf_list);
+	mutex_init(&priv->bf_mutex);
+
 	/*
 	 * Now reset the HCA before we touch the PCI capabilities or
 	 * attempt a firmware command, since a boot ROM may have left
@@ -1154,8 +1254,15 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_close;
 
+	priv->msix_ctl.pool_bm = 0;
+	spin_lock_init(&priv->msix_ctl.pool_lock);
+
 	mlx4_enable_msi_x(dev);
 
+	err = mlx4_init_steering(dev);
+	if (err)
+		goto err_free_eq;
+
 	err = mlx4_setup_hca(dev);
 	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X)) {
 		dev->flags &= ~MLX4_FLAG_MSI_X;
@@ -1164,7 +1271,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	if (err)
-		goto err_free_eq;
+		goto err_steer;
 
 	for (port = 1; port <= dev->caps.num_ports; port++) {
 		err = mlx4_init_port_info(dev, port);
@@ -1197,6 +1304,9 @@ err_port:
 	mlx4_cleanup_pd_table(dev);
 	mlx4_cleanup_uar_table(dev);
 
+err_steer:
+	mlx4_clear_steering(dev);
+
 err_free_eq:
 	mlx4_free_eq_table(dev);
 
@@ -1256,6 +1366,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 		iounmap(priv->kar);
 		mlx4_uar_free(dev, &priv->driver_uar);
 		mlx4_cleanup_uar_table(dev);
+		mlx4_clear_steering(dev);
 		mlx4_free_eq_table(dev);
 		mlx4_close_hca(dev);
 		mlx4_cmd_cleanup(dev);
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index 79cf42db2ea..e71372aa9cc 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/string.h>
+#include <linux/etherdevice.h>
 
 #include <linux/mlx4/cmd.h>
 
@@ -40,38 +41,40 @@
 #define MGM_QPN_MASK       0x00FFFFFF
 #define MGM_BLCK_LB_BIT    30
 
-struct mlx4_mgm {
-	__be32			next_gid_index;
-	__be32			members_count;
-	u32			reserved[2];
-	u8			gid[16];
-	__be32			qp[MLX4_QP_PER_MGM];
-};
-
 static const u8 zero_gid[16];	/* automatically initialized to 0 */
 
-static int mlx4_READ_MCG(struct mlx4_dev *dev, int index,
-			 struct mlx4_cmd_mailbox *mailbox)
+static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
+			   struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd_box(dev, 0, mailbox->dma, index, 0, MLX4_CMD_READ_MCG,
 			    MLX4_CMD_TIME_CLASS_A);
 }
 
-static int mlx4_WRITE_MCG(struct mlx4_dev *dev, int index,
-			  struct mlx4_cmd_mailbox *mailbox)
+static int mlx4_WRITE_ENTRY(struct mlx4_dev *dev, int index,
+			    struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd(dev, mailbox->dma, index, 0, MLX4_CMD_WRITE_MCG,
 			MLX4_CMD_TIME_CLASS_A);
 }
 
-static int mlx4_MGID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
-			  u16 *hash)
+static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 vep_num, u8 port, u8 steer,
+			      struct mlx4_cmd_mailbox *mailbox)
+{
+	u32 in_mod;
+
+	in_mod = (u32) vep_num << 24 | (u32) port << 16 | steer << 1;
+	return mlx4_cmd(dev, mailbox->dma, in_mod, 0x1,
+			MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A);
+}
+
+static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
+			 u16 *hash, u8 op_mod)
 {
 	u64 imm;
 	int err;
 
-	err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, 0, MLX4_CMD_MGID_HASH,
-			   MLX4_CMD_TIME_CLASS_A);
+	err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, op_mod,
+			   MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A);
 
 	if (!err)
 		*hash = imm;
@@ -79,6 +82,457 @@ static int mlx4_MGID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox
 	return err;
 }
 
+static struct mlx4_promisc_qp *get_promisc_qp(struct mlx4_dev *dev, u8 pf_num,
+					      enum mlx4_steer_type steer,
+					      u32 qpn)
+{
+	struct mlx4_steer *s_steer = &mlx4_priv(dev)->steer[pf_num];
+	struct mlx4_promisc_qp *pqp;
+
+	list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
+		if (pqp->qpn == qpn)
+			return pqp;
+	}
+	/* not found */
+	return NULL;
+}
+
+/*
+ * Add new entry to steering data structure.
+ * All promisc QPs should be added as well
+ */
+static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			      enum mlx4_steer_type steer,
+			      unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	u32 members_count;
+	struct mlx4_steer_index *new_entry;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u32 prot;
+	int err;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&new_entry->duplicates);
+	new_entry->index = index;
+	list_add_tail(&new_entry->list, &s_steer->steer_entries[steer]);
+
+	/* If the given qpn is also a promisc qp,
+	 * it should be inserted to duplicates list
+	 */
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (pqp) {
+		dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
+		if (!dqp) {
+			err = -ENOMEM;
+			goto out_alloc;
+		}
+		dqp->qpn = qpn;
+		list_add_tail(&dqp->list, &new_entry->duplicates);
+	}
+
+	/* if no promisc qps for this vep, we are done */
+	if (list_empty(&s_steer->promisc_qps[steer]))
+		return 0;
+
+	/* now need to add all the promisc qps to the new
+	 * steering entry, as they should also receive the packets
+	 * destined to this address */
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		goto out_alloc;
+	}
+	mgm = mailbox->buf;
+
+	err = mlx4_READ_ENTRY(dev, index, mailbox);
+	if (err)
+		goto out_mailbox;
+
+	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+	prot = be32_to_cpu(mgm->members_count) >> 30;
+	list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
+		/* don't add already existing qpn */
+		if (pqp->qpn == qpn)
+			continue;
+		if (members_count == MLX4_QP_PER_MGM) {
+			/* out of space */
+			err = -ENOMEM;
+			goto out_mailbox;
+		}
+
+		/* add the qpn */
+		mgm->qp[members_count++] = cpu_to_be32(pqp->qpn & MGM_QPN_MASK);
+	}
+	/* update the qps count and update the entry with all the promisc qps*/
+	mgm->members_count = cpu_to_be32(members_count | (prot << 30));
+	err = mlx4_WRITE_ENTRY(dev, index, mailbox);
+
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	if (!err)
+		return 0;
+out_alloc:
+	if (dqp) {
+		list_del(&dqp->list);
+		kfree(&dqp);
+	}
+	list_del(&new_entry->list);
+	kfree(new_entry);
+	return err;
+}
+
+/* update the data structures with existing steering entry */
+static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+				   enum mlx4_steer_type steer,
+				   unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_steer_index *tmp_entry, *entry = NULL;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (!pqp)
+		return 0; /* nothing to do */
+
+	list_for_each_entry(tmp_entry, &s_steer->steer_entries[steer], list) {
+		if (tmp_entry->index == index) {
+			entry = tmp_entry;
+			break;
+		}
+	}
+	if (unlikely(!entry)) {
+		mlx4_warn(dev, "Steering entry at index %x is not registered\n", index);
+		return -EINVAL;
+	}
+
+	/* the given qpn is listed as a promisc qpn
+	 * we need to add it as a duplicate to this entry
+	 * for future refernce */
+	list_for_each_entry(dqp, &entry->duplicates, list) {
+		if (qpn == dqp->qpn)
+			return 0; /* qp is already duplicated */
+	}
+
+	/* add the qp as a duplicate on this index */
+	dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
+	if (!dqp)
+		return -ENOMEM;
+	dqp->qpn = qpn;
+	list_add_tail(&dqp->list, &entry->duplicates);
+
+	return 0;
+}
+
+/* Check whether a qpn is a duplicate on steering entry
+ * If so, it should not be removed from mgm */
+static bool check_duplicate_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+				  enum mlx4_steer_type steer,
+				  unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_steer_index *tmp_entry, *entry = NULL;
+	struct mlx4_promisc_qp *dqp, *tmp_dqp;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	/* if qp is not promisc, it cannot be duplicated */
+	if (!get_promisc_qp(dev, pf_num, steer, qpn))
+		return false;
+
+	/* The qp is promisc qp so it is a duplicate on this index
+	 * Find the index entry, and remove the duplicate */
+	list_for_each_entry(tmp_entry, &s_steer->steer_entries[steer], list) {
+		if (tmp_entry->index == index) {
+			entry = tmp_entry;
+			break;
+		}
+	}
+	if (unlikely(!entry)) {
+		mlx4_warn(dev, "Steering entry for index %x is not registered\n", index);
+		return false;
+	}
+	list_for_each_entry_safe(dqp, tmp_dqp, &entry->duplicates, list) {
+		if (dqp->qpn == qpn) {
+			list_del(&dqp->list);
+			kfree(dqp);
+		}
+	}
+	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 vep_num, u8 port,
+				      enum mlx4_steer_type steer,
+				      unsigned int index, u32 tqpn)
+{
+	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;
+	bool ret = false;
+	int i;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return false;
+	mgm = mailbox->buf;
+
+	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;
+		if (!get_promisc_qp(dev, pf_num, 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,
+	  * 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)) {
+				list_del(&entry->list);
+				kfree(entry);
+			} else {
+				/* This entry contains duplicates so it shouldn't be removed */
+				ret = false;
+				goto out;
+			}
+		}
+	}
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return ret;
+}
+
+static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			  enum mlx4_steer_type steer, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	struct mlx4_steer_index *entry;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u32 members_count;
+	u32 prot;
+	int i;
+	bool found;
+	int last_index;
+	int err;
+	u8 pf_num;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	mutex_lock(&priv->mcg_table.mutex);
+
+	if (get_promisc_qp(dev, pf_num, steer, qpn)) {
+		err = 0;  /* Noting to do, already exists */
+		goto out_mutex;
+	}
+
+	pqp = kmalloc(sizeof *pqp, GFP_KERNEL);
+	if (!pqp) {
+		err = -ENOMEM;
+		goto out_mutex;
+	}
+	pqp->qpn = qpn;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		goto out_alloc;
+	}
+	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;
+
+		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)
+					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 == MLX4_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;
+		}
+		last_index = entry->index;
+	}
+
+	/* add the new qpn to list of promisc qps */
+	list_add_tail(&pqp->list, &s_steer->promisc_qps[steer]);
+	/* 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)
+		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, vep_num, port, steer, mailbox);
+	if (err)
+		goto out_list;
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	mutex_unlock(&priv->mcg_table.mutex);
+	return 0;
+
+out_list:
+	list_del(&pqp->list);
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+out_alloc:
+	kfree(pqp);
+out_mutex:
+	mutex_unlock(&priv->mcg_table.mutex);
+	return err;
+}
+
+static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			     enum mlx4_steer_type steer, u32 qpn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	struct mlx4_steer_index *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 err;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	mutex_lock(&priv->mcg_table.mutex);
+
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (unlikely(!pqp)) {
+		mlx4_warn(dev, "QP %x is not promiscuous QP\n", qpn);
+		/* nothing to do */
+		err = 0;
+		goto out_mutex;
+	}
+
+	/*remove from list of promisc qps */
+	list_del(&pqp->list);
+	kfree(pqp);
+
+	/* set the default entry not to include the removed one */
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		back_to_list = true;
+		goto out_list;
+	}
+	mgm = mailbox->buf;
+	members_count = 0;
+	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], 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, vep_num, port, steer, mailbox);
+	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 (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;
+
+			err = mlx4_WRITE_ENTRY(dev, entry->index, mailbox);
+				if (err)
+					goto out_mailbox;
+		}
+
+	}
+
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+out_list:
+	if (back_to_list)
+		list_add_tail(&pqp->list, &s_steer->promisc_qps[steer]);
+out_mutex:
+	mutex_unlock(&priv->mcg_table.mutex);
+	return err;
+}
+
 /*
  * Caller must hold MCG table semaphore.  gid and mgm parameters must
  * be properly aligned for command interface.
@@ -94,15 +548,17 @@ static int mlx4_MGID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox
  * If no AMGM exists for given gid, *index = -1, *prev = index of last
  * entry in hash chain and *mgm holds end of hash chain.
  */
-static int find_mgm(struct mlx4_dev *dev,
-		    u8 *gid, enum mlx4_protocol protocol,
-		    struct mlx4_cmd_mailbox *mgm_mailbox,
-		    u16 *hash, int *prev, int *index)
+static int find_entry(struct mlx4_dev *dev, u8 port,
+		      u8 *gid, enum mlx4_protocol prot,
+		      enum mlx4_steer_type steer,
+		      struct mlx4_cmd_mailbox *mgm_mailbox,
+		      u16 *hash, int *prev, int *index)
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_mgm *mgm = mgm_mailbox->buf;
 	u8 *mgid;
 	int err;
+	u8 op_mod = (prot == MLX4_PROT_ETH) ? !!(dev->caps.vep_mc_steering) : 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -111,7 +567,7 @@ static int find_mgm(struct mlx4_dev *dev,
 
 	memcpy(mgid, gid, 16);
 
-	err = mlx4_MGID_HASH(dev, mailbox, hash);
+	err = mlx4_GID_HASH(dev, mailbox, hash, op_mod);
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	if (err)
 		return err;
@@ -123,11 +579,11 @@ static int find_mgm(struct mlx4_dev *dev,
 	*prev  = -1;
 
 	do {
-		err = mlx4_READ_MCG(dev, *index, mgm_mailbox);
+		err = mlx4_READ_ENTRY(dev, *index, mgm_mailbox);
 		if (err)
 			return err;
 
-		if (!memcmp(mgm->gid, zero_gid, 16)) {
+		if (!(be32_to_cpu(mgm->members_count) & 0xffffff)) {
 			if (*index != *hash) {
 				mlx4_err(dev, "Found zero MGID in AMGM.\n");
 				err = -EINVAL;
@@ -136,7 +592,7 @@ static int find_mgm(struct mlx4_dev *dev,
 		}
 
 		if (!memcmp(mgm->gid, gid, 16) &&
-		    be32_to_cpu(mgm->members_count) >> 30 == protocol)
+		    be32_to_cpu(mgm->members_count) >> 30 == prot)
 			return err;
 
 		*prev = *index;
@@ -147,8 +603,9 @@ static int find_mgm(struct mlx4_dev *dev,
 	return err;
 }
 
-int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  int block_mcast_loopback, enum mlx4_protocol protocol)
+int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot,
+			  enum mlx4_steer_type steer)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
@@ -159,6 +616,8 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int link = 0;
 	int i;
 	int err;
+	u8 port = gid[5];
+	u8 new_entry = 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -166,14 +625,16 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	mgm = mailbox->buf;
 
 	mutex_lock(&priv->mcg_table.mutex);
-
-	err = find_mgm(dev, gid, protocol, mailbox, &hash, &prev, &index);
+	err = find_entry(dev, port, gid, prot, steer,
+			 mailbox, &hash, &prev, &index);
 	if (err)
 		goto out;
 
 	if (index != -1) {
-		if (!memcmp(mgm->gid, zero_gid, 16))
+		if (!(be32_to_cpu(mgm->members_count) & 0xffffff)) {
+			new_entry = 1;
 			memcpy(mgm->gid, gid, 16);
+		}
 	} else {
 		link = 1;
 
@@ -209,26 +670,34 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	else
 		mgm->qp[members_count++] = cpu_to_be32(qp->qpn & MGM_QPN_MASK);
 
-	mgm->members_count = cpu_to_be32(members_count | (u32) protocol << 30);
+	mgm->members_count = cpu_to_be32(members_count | (u32) prot << 30);
 
-	err = mlx4_WRITE_MCG(dev, index, mailbox);
+	err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 	if (err)
 		goto out;
 
 	if (!link)
 		goto out;
 
-	err = mlx4_READ_MCG(dev, prev, mailbox);
+	err = mlx4_READ_ENTRY(dev, prev, mailbox);
 	if (err)
 		goto out;
 
 	mgm->next_gid_index = cpu_to_be32(index << 6);
 
-	err = mlx4_WRITE_MCG(dev, prev, mailbox);
+	err = mlx4_WRITE_ENTRY(dev, prev, mailbox);
 	if (err)
 		goto out;
 
 out:
+	if (prot == MLX4_PROT_ETH) {
+		/* manage the steering entry for promisc mode */
+		if (new_entry)
+			new_steering_entry(dev, 0, port, steer, index, qp->qpn);
+		else
+			existing_steering_entry(dev, 0, port, steer,
+						index, qp->qpn);
+	}
 	if (err && link && index != -1) {
 		if (index < dev->caps.num_mgms)
 			mlx4_warn(dev, "Got AMGM index %d < %d",
@@ -242,10 +711,9 @@ out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
 
-int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  enum mlx4_protocol protocol)
+int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot, enum mlx4_steer_type steer)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
@@ -255,6 +723,8 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int prev, index;
 	int i, loc;
 	int err;
+	u8 port = gid[5];
+	bool removed_entry = false;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -263,7 +733,8 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 
 	mutex_lock(&priv->mcg_table.mutex);
 
-	err = find_mgm(dev, gid, protocol, mailbox, &hash, &prev, &index);
+	err = find_entry(dev, port, gid, prot, steer,
+			 mailbox, &hash, &prev, &index);
 	if (err)
 		goto out;
 
@@ -273,6 +744,11 @@ int mlx4_multicast_detach(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 (prot == MLX4_PROT_ETH &&
+	    check_duplicate_entry(dev, 0, port, steer, index, qp->qpn))
+		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)
@@ -285,26 +761,31 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	}
 
 
-	mgm->members_count = cpu_to_be32(--members_count | (u32) protocol << 30);
+	mgm->members_count = cpu_to_be32(--members_count | (u32) prot << 30);
 	mgm->qp[loc]       = mgm->qp[i - 1];
 	mgm->qp[i - 1]     = 0;
 
-	if (i != 1) {
-		err = mlx4_WRITE_MCG(dev, index, mailbox);
+	if (prot == MLX4_PROT_ETH)
+		removed_entry = can_remove_steering_entry(dev, 0, port, steer, index, qp->qpn);
+	if (i != 1 && (prot != MLX4_PROT_ETH || !removed_entry)) {
+		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		goto out;
 	}
 
+	/* We are going to delete the entry, members count should be 0 */
+	mgm->members_count = cpu_to_be32((u32) prot << 30);
+
 	if (prev == -1) {
 		/* Remove entry from MGM */
 		int amgm_index = be32_to_cpu(mgm->next_gid_index) >> 6;
 		if (amgm_index) {
-			err = mlx4_READ_MCG(dev, amgm_index, mailbox);
+			err = mlx4_READ_ENTRY(dev, amgm_index, mailbox);
 			if (err)
 				goto out;
 		} else
 			memset(mgm->gid, 0, 16);
 
-		err = mlx4_WRITE_MCG(dev, index, mailbox);
+		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		if (err)
 			goto out;
 
@@ -319,13 +800,13 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	} else {
 		/* Remove entry from AMGM */
 		int cur_next_index = be32_to_cpu(mgm->next_gid_index) >> 6;
-		err = mlx4_READ_MCG(dev, prev, mailbox);
+		err = mlx4_READ_ENTRY(dev, prev, mailbox);
 		if (err)
 			goto out;
 
 		mgm->next_gid_index = cpu_to_be32(cur_next_index << 6);
 
-		err = mlx4_WRITE_MCG(dev, prev, mailbox);
+		err = mlx4_WRITE_ENTRY(dev, prev, mailbox);
 		if (err)
 			goto out;
 
@@ -343,8 +824,85 @@ out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
+
+
+int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot)
+{
+	enum mlx4_steer_type steer;
+
+	steer = (is_valid_ether_addr(&gid[10])) ? MLX4_UC_STEER : MLX4_MC_STEER;
+
+	if (prot == MLX4_PROT_ETH && !dev->caps.vep_mc_steering)
+		return 0;
+
+	if (prot == MLX4_PROT_ETH)
+		gid[7] |= (steer << 1);
+
+	return mlx4_qp_attach_common(dev, qp, gid,
+				     block_mcast_loopback, prot,
+				     steer);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
+
+int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot)
+{
+	enum mlx4_steer_type steer;
+
+	steer = (is_valid_ether_addr(&gid[10])) ? MLX4_UC_STEER : MLX4_MC_STEER;
+
+	if (prot == MLX4_PROT_ETH && !dev->caps.vep_mc_steering)
+		return 0;
+
+	if (prot == MLX4_PROT_ETH) {
+		gid[7] |= (steer << 1);
+	}
+
+	return mlx4_qp_detach_common(dev, qp, gid, prot, steer);
+}
 EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
 
+
+int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return add_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_add);
+
+int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return remove_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_remove);
+
+int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return add_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_add);
+
+int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+	return remove_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_remove);
+
 int mlx4_init_mcg_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 0da5bb7285b..c1e0e5f1bcd 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -105,6 +105,7 @@ struct mlx4_bitmap {
 	u32			max;
 	u32                     reserved_top;
 	u32			mask;
+	u32			avail;
 	spinlock_t		lock;
 	unsigned long	       *table;
 };
@@ -162,6 +163,27 @@ struct mlx4_fw {
 	u8			catas_bar;
 };
 
+#define MGM_QPN_MASK       0x00FFFFFF
+#define MGM_BLCK_LB_BIT    30
+
+struct mlx4_promisc_qp {
+	struct list_head list;
+	u32 qpn;
+};
+
+struct mlx4_steer_index {
+	struct list_head list;
+	unsigned int index;
+	struct list_head duplicates;
+};
+
+struct mlx4_mgm {
+	__be32			next_gid_index;
+	__be32			members_count;
+	u32			reserved[2];
+	u8			gid[16];
+	__be32			qp[MLX4_QP_PER_MGM];
+};
 struct mlx4_cmd {
 	struct pci_pool	       *pool;
 	void __iomem	       *hcr;
@@ -265,6 +287,10 @@ struct mlx4_vlan_table {
 	int			max;
 };
 
+struct mlx4_mac_entry {
+	u64 mac;
+};
+
 struct mlx4_port_info {
 	struct mlx4_dev	       *dev;
 	int			port;
@@ -272,7 +298,9 @@ struct mlx4_port_info {
 	struct device_attribute port_attr;
 	enum mlx4_port_type	tmp_type;
 	struct mlx4_mac_table	mac_table;
+	struct radix_tree_root	mac_tree;
 	struct mlx4_vlan_table	vlan_table;
+	int			base_qpn;
 };
 
 struct mlx4_sense {
@@ -282,6 +310,17 @@ struct mlx4_sense {
 	struct delayed_work	sense_poll;
 };
 
+struct mlx4_msix_ctl {
+	u64		pool_bm;
+	spinlock_t	pool_lock;
+};
+
+struct mlx4_steer {
+	struct list_head promisc_qps[MLX4_NUM_STEERS];
+	struct list_head steer_entries[MLX4_NUM_STEERS];
+	struct list_head high_prios;
+};
+
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
@@ -313,6 +352,11 @@ struct mlx4_priv {
 	struct mlx4_port_info	port[MLX4_MAX_PORTS + 1];
 	struct mlx4_sense       sense;
 	struct mutex		port_mutex;
+	struct mlx4_msix_ctl	msix_ctl;
+	struct mlx4_steer	*steer;
+	struct list_head	bf_list;
+	struct mutex		bf_mutex;
+	struct io_mapping	*bf_mapping;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -328,6 +372,7 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj);
 u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt);
+u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
 int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 		     u32 reserved_bot, u32 resetrved_top);
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap);
@@ -403,4 +448,9 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
 
+int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot, enum mlx4_steer_type steer);
+int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot,
+			  enum mlx4_steer_type steer);
 #endif /* MLX4_H */
diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h
index dfed6a07c2d..e30f6099c0d 100644
--- a/drivers/net/mlx4/mlx4_en.h
+++ b/drivers/net/mlx4/mlx4_en.h
@@ -49,8 +49,8 @@
 #include "en_port.h"
 
 #define DRV_NAME	"mlx4_en"
-#define DRV_VERSION	"1.5.1.6"
-#define DRV_RELDATE	"August 2010"
+#define DRV_VERSION	"1.5.4.1"
+#define DRV_RELDATE	"March 2011"
 
 #define MLX4_EN_MSG_LEVEL	(NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
 
@@ -62,6 +62,7 @@
 #define MLX4_EN_PAGE_SHIFT	12
 #define MLX4_EN_PAGE_SIZE	(1 << MLX4_EN_PAGE_SHIFT)
 #define MAX_RX_RINGS		16
+#define MIN_RX_RINGS		4
 #define TXBB_SIZE		64
 #define HEADROOM		(2048 / TXBB_SIZE + 1)
 #define STAMP_STRIDE		64
@@ -124,6 +125,7 @@ enum {
 #define MLX4_EN_RX_SIZE_THRESH		1024
 #define MLX4_EN_RX_RATE_THRESH		(1000000 / MLX4_EN_RX_COAL_TIME_HIGH)
 #define MLX4_EN_SAMPLE_INTERVAL		0
+#define MLX4_EN_AVG_PKT_SMALL		256
 
 #define MLX4_EN_AUTO_CONF	0xffff
 
@@ -214,6 +216,9 @@ struct mlx4_en_tx_desc {
 
 #define MLX4_EN_USE_SRQ		0x01000000
 
+#define MLX4_EN_CX3_LOW_ID	0x1000
+#define MLX4_EN_CX3_HIGH_ID	0x1005
+
 struct mlx4_en_rx_alloc {
 	struct page *page;
 	u16 offset;
@@ -243,6 +248,8 @@ struct mlx4_en_tx_ring {
 	unsigned long bytes;
 	unsigned long packets;
 	spinlock_t comp_lock;
+	struct mlx4_bf bf;
+	bool bf_enabled;
 };
 
 struct mlx4_en_rx_desc {
@@ -453,6 +460,7 @@ struct mlx4_en_priv {
 	struct mlx4_en_rss_map rss_map;
 	u32 flags;
 #define MLX4_EN_FLAG_PROMISC	0x1
+#define MLX4_EN_FLAG_MC_PROMISC	0x2
 	u32 tx_ring_num;
 	u32 rx_ring_num;
 	u32 rx_skb_size;
@@ -461,6 +469,7 @@ struct mlx4_en_priv {
 	u16 log_rx_info;
 
 	struct mlx4_en_tx_ring tx_ring[MAX_TX_RINGS];
+	int tx_vector;
 	struct mlx4_en_rx_ring rx_ring[MAX_RX_RINGS];
 	struct mlx4_en_cq tx_cq[MAX_TX_RINGS];
 	struct mlx4_en_cq rx_cq[MAX_RX_RINGS];
@@ -476,6 +485,13 @@ struct mlx4_en_priv {
 	int mc_addrs_cnt;
 	struct mlx4_en_stat_out_mbox hw_stats;
 	int vids[128];
+	bool wol;
+};
+
+enum mlx4_en_wol {
+	MLX4_EN_WOL_MAGIC = (1ULL << 61),
+	MLX4_EN_WOL_ENABLED = (1ULL << 62),
+	MLX4_EN_WOL_DO_MODIFY = (1ULL << 63),
 };
 
 
@@ -486,12 +502,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 int mlx4_en_start_port(struct net_device *dev);
 void mlx4_en_stop_port(struct net_device *dev);
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv);
+void mlx4_en_free_resources(struct mlx4_en_priv *priv, bool reserve_vectors);
 int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		      int entries, int ring, enum cq_type mode);
-void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
+			bool reserve_vectors);
 int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
@@ -503,7 +520,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring,
-			   u32 size, u16 stride);
+			   int qpn, u32 size, u16 stride);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring *ring,
diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c
index c4988d6bd5b..1286b886dce 100644
--- a/drivers/net/mlx4/pd.c
+++ b/drivers/net/mlx4/pd.c
@@ -32,12 +32,17 @@
  */
 
 #include <linux/errno.h>
+#include <linux/io-mapping.h>
 
 #include <asm/page.h>
 
 #include "mlx4.h"
 #include "icm.h"
 
+enum {
+	MLX4_NUM_RESERVED_UARS = 8
+};
+
 int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -77,6 +82,7 @@ int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
 		return -ENOMEM;
 
 	uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + uar->index;
+	uar->map = NULL;
 
 	return 0;
 }
@@ -88,6 +94,102 @@ void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar)
 }
 EXPORT_SYMBOL_GPL(mlx4_uar_free);
 
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_uar *uar;
+	int err = 0;
+	int idx;
+
+	if (!priv->bf_mapping)
+		return -ENOMEM;
+
+	mutex_lock(&priv->bf_mutex);
+	if (!list_empty(&priv->bf_list))
+		uar = list_entry(priv->bf_list.next, struct mlx4_uar, bf_list);
+	else {
+		if (mlx4_bitmap_avail(&priv->uar_table.bitmap) < MLX4_NUM_RESERVED_UARS) {
+			err = -ENOMEM;
+			goto out;
+		}
+		uar = kmalloc(sizeof *uar, GFP_KERNEL);
+		if (!uar) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = mlx4_uar_alloc(dev, uar);
+		if (err)
+			goto free_kmalloc;
+
+		uar->map = ioremap(uar->pfn << PAGE_SHIFT, PAGE_SIZE);
+		if (!uar->map) {
+			err = -ENOMEM;
+			goto free_uar;
+		}
+
+		uar->bf_map = io_mapping_map_wc(priv->bf_mapping, uar->index << PAGE_SHIFT);
+		if (!uar->bf_map) {
+			err = -ENOMEM;
+			goto unamp_uar;
+		}
+		uar->free_bf_bmap = 0;
+		list_add(&uar->bf_list, &priv->bf_list);
+	}
+
+	bf->uar = uar;
+	idx = ffz(uar->free_bf_bmap);
+	uar->free_bf_bmap |= 1 << idx;
+	bf->uar = uar;
+	bf->offset = 0;
+	bf->buf_size = dev->caps.bf_reg_size / 2;
+	bf->reg = uar->bf_map + idx * dev->caps.bf_reg_size;
+	if (uar->free_bf_bmap == (1 << dev->caps.bf_regs_per_page) - 1)
+		list_del_init(&uar->bf_list);
+
+	goto out;
+
+unamp_uar:
+	bf->uar = NULL;
+	iounmap(uar->map);
+
+free_uar:
+	mlx4_uar_free(dev, uar);
+
+free_kmalloc:
+	kfree(uar);
+
+out:
+	mutex_unlock(&priv->bf_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_bf_alloc);
+
+void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int idx;
+
+	if (!bf->uar || !bf->uar->bf_map)
+		return;
+
+	mutex_lock(&priv->bf_mutex);
+	idx = (bf->reg - bf->uar->bf_map) / dev->caps.bf_reg_size;
+	bf->uar->free_bf_bmap &= ~(1 << idx);
+	if (!bf->uar->free_bf_bmap) {
+		if (!list_empty(&bf->uar->bf_list))
+			list_del(&bf->uar->bf_list);
+
+		io_mapping_unmap(bf->uar->bf_map);
+		iounmap(bf->uar->map);
+		mlx4_uar_free(dev, bf->uar);
+		kfree(bf->uar);
+	} else if (list_empty(&bf->uar->bf_list))
+		list_add(&bf->uar->bf_list, &priv->bf_list);
+
+	mutex_unlock(&priv->bf_mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_bf_free);
+
 int mlx4_init_uar_table(struct mlx4_dev *dev)
 {
 	if (dev->caps.num_uars <= 128) {
diff --git a/drivers/net/mlx4/port.c b/drivers/net/mlx4/port.c
index 451339559bd..eca7d8596f8 100644
--- a/drivers/net/mlx4/port.c
+++ b/drivers/net/mlx4/port.c
@@ -90,12 +90,79 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index)
+static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
+			     u64 mac, int *qpn, u8 reserve)
 {
-	struct mlx4_mac_table *table = &mlx4_priv(dev)->port[port].mac_table;
+	struct mlx4_qp qp;
+	u8 gid[16] = {0};
+	int err;
+
+	if (reserve) {
+		err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+		if (err) {
+			mlx4_err(dev, "Failed to reserve qp for mac registration\n");
+			return err;
+		}
+	}
+	qp.qpn = *qpn;
+
+	mac &= 0xffffffffffffULL;
+	mac = cpu_to_be64(mac << 16);
+	memcpy(&gid[10], &mac, ETH_ALEN);
+	gid[5] = port;
+	gid[7] = MLX4_UC_STEER << 1;
+
+	err = mlx4_qp_attach_common(dev, &qp, gid, 0,
+				    MLX4_PROT_ETH, MLX4_UC_STEER);
+	if (err && reserve)
+		mlx4_qp_release_range(dev, *qpn, 1);
+
+	return err;
+}
+
+static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
+				  u64 mac, int qpn, u8 free)
+{
+	struct mlx4_qp qp;
+	u8 gid[16] = {0};
+
+	qp.qpn = qpn;
+	mac &= 0xffffffffffffULL;
+	mac = cpu_to_be64(mac << 16);
+	memcpy(&gid[10], &mac, ETH_ALEN);
+	gid[5] = port;
+	gid[7] = MLX4_UC_STEER << 1;
+
+	mlx4_qp_detach_common(dev, &qp, gid, MLX4_PROT_ETH, MLX4_UC_STEER);
+	if (free)
+		mlx4_qp_release_range(dev, qpn, 1);
+}
+
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	struct mlx4_mac_entry *entry;
 	int i, err = 0;
 	int free = -1;
 
+	if (dev->caps.vep_uc_steering) {
+		err = mlx4_uc_steer_add(dev, port, mac, qpn, 1);
+		if (!err) {
+			entry = kmalloc(sizeof *entry, GFP_KERNEL);
+			if (!entry) {
+				mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
+				return -ENOMEM;
+			}
+			entry->mac = mac;
+			err = radix_tree_insert(&info->mac_tree, *qpn, entry);
+			if (err) {
+				mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
+				return err;
+			}
+		} else
+			return err;
+	}
 	mlx4_dbg(dev, "Registering MAC: 0x%llx\n", (unsigned long long) mac);
 	mutex_lock(&table->mutex);
 	for (i = 0; i < MLX4_MAX_MAC_NUM - 1; i++) {
@@ -106,7 +173,6 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index)
 
 		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
 			/* MAC already registered, increase refernce count */
-			*index = i;
 			++table->refs[i];
 			goto out;
 		}
@@ -137,7 +203,8 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index)
 		goto out;
 	}
 
-	*index = free;
+	if (!dev->caps.vep_uc_steering)
+		*qpn = info->base_qpn + free;
 	++table->total;
 out:
 	mutex_unlock(&table->mutex);
@@ -145,20 +212,52 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx4_register_mac);
 
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index)
+static int validate_index(struct mlx4_dev *dev,
+			  struct mlx4_mac_table *table, int index)
 {
-	struct mlx4_mac_table *table = &mlx4_priv(dev)->port[port].mac_table;
+	int err = 0;
 
-	mutex_lock(&table->mutex);
-	if (!table->refs[index]) {
-		mlx4_warn(dev, "No MAC entry for index %d\n", index);
-		goto out;
+	if (index < 0 || index >= table->max || !table->entries[index]) {
+		mlx4_warn(dev, "No valid Mac entry for the given index\n");
+		err = -EINVAL;
 	}
-	if (--table->refs[index]) {
-		mlx4_warn(dev, "Have more references for index %d,"
-			  "no need to modify MAC table\n", index);
-		goto out;
+	return err;
+}
+
+static int find_index(struct mlx4_dev *dev,
+		      struct mlx4_mac_table *table, u64 mac)
+{
+	int i;
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i])))
+			return i;
 	}
+	/* Mac not found */
+	return -EINVAL;
+}
+
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	int index = qpn - info->base_qpn;
+	struct mlx4_mac_entry *entry;
+
+	if (dev->caps.vep_uc_steering) {
+		entry = radix_tree_lookup(&info->mac_tree, qpn);
+		if (entry) {
+			mlx4_uc_steer_release(dev, port, entry->mac, qpn, 1);
+			radix_tree_delete(&info->mac_tree, qpn);
+			index = find_index(dev, table, entry->mac);
+			kfree(entry);
+		}
+	}
+
+	mutex_lock(&table->mutex);
+
+	if (validate_index(dev, table, index))
+		goto out;
+
 	table->entries[index] = 0;
 	mlx4_set_port_mac_table(dev, port, table->entries);
 	--table->total;
@@ -167,6 +266,44 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_mac);
 
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	int index = qpn - info->base_qpn;
+	struct mlx4_mac_entry *entry;
+	int err;
+
+	if (dev->caps.vep_uc_steering) {
+		entry = radix_tree_lookup(&info->mac_tree, qpn);
+		if (!entry)
+			return -EINVAL;
+		index = find_index(dev, table, entry->mac);
+		mlx4_uc_steer_release(dev, port, entry->mac, qpn, 0);
+		entry->mac = new_mac;
+		err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn, 0);
+		if (err || index < 0)
+			return err;
+	}
+
+	mutex_lock(&table->mutex);
+
+	err = validate_index(dev, table, index);
+	if (err)
+		goto out;
+
+	table->entries[index] = cpu_to_be64(new_mac | MLX4_MAC_VALID);
+
+	err = mlx4_set_port_mac_table(dev, port, table->entries);
+	if (unlikely(err)) {
+		mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) new_mac);
+		table->entries[index] = 0;
+	}
+out:
+	mutex_unlock(&table->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_replace_mac);
 static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
 				    __be32 *entries)
 {
diff --git a/drivers/net/mlx4/profile.c b/drivers/net/mlx4/profile.c
index e749f82865f..b967647d0c7 100644
--- a/drivers/net/mlx4/profile.c
+++ b/drivers/net/mlx4/profile.c
@@ -107,9 +107,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_AUXC].num    = request->num_qp;
 	profile[MLX4_RES_SRQ].num     = request->num_srq;
 	profile[MLX4_RES_CQ].num      = request->num_cq;
-	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs,
-					      dev_cap->reserved_eqs +
-					      num_possible_cpus() + 1);
+	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
 	profile[MLX4_RES_DMPT].num    = request->num_mpt;
 	profile[MLX4_RES_CMPT].num    = MLX4_NUM_CMPTS;
 	profile[MLX4_RES_MTT].num     = request->num_mtt;
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index a7f2eed9a08..1f4e8680a96 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -3645,6 +3645,7 @@ static void myri10ge_free_slices(struct myri10ge_priv *mgp)
 			dma_free_coherent(&pdev->dev, bytes,
 					  ss->fw_stats, ss->fw_stats_bus);
 			ss->fw_stats = NULL;
+			netif_napi_del(&ss->napi);
 		}
 	}
 	kfree(mgp->ss);
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index 8c66e22c3a0..50986840c99 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -2441,7 +2441,7 @@ static struct pci_error_handlers pch_gbe_err_handler = {
 	.resume = pch_gbe_io_resume
 };
 
-static struct pci_driver pch_gbe_pcidev = {
+static struct pci_driver pch_gbe_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = pch_gbe_pcidev_id,
 	.probe = pch_gbe_probe,
@@ -2458,7 +2458,7 @@ static int __init pch_gbe_init_module(void)
 {
 	int ret;
 
-	ret = pci_register_driver(&pch_gbe_pcidev);
+	ret = pci_register_driver(&pch_gbe_driver);
 	if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) {
 		if (copybreak == 0) {
 			pr_info("copybreak disabled\n");
@@ -2472,7 +2472,7 @@ static int __init pch_gbe_init_module(void)
 
 static void __exit pch_gbe_exit_module(void)
 {
-	pci_unregister_driver(&pch_gbe_pcidev);
+	pci_unregister_driver(&pch_gbe_driver);
 }
 
 module_init(pch_gbe_init_module);
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index b8bd936374f..d890679e4c4 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -1054,6 +1054,7 @@ static int efx_init_io(struct efx_nic *efx)
 {
 	struct pci_dev *pci_dev = efx->pci_dev;
 	dma_addr_t dma_mask = efx->type->max_dma_mask;
+	bool use_wc;
 	int rc;
 
 	netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
@@ -1104,8 +1105,21 @@ static int efx_init_io(struct efx_nic *efx)
 		rc = -EIO;
 		goto fail3;
 	}
-	efx->membase = ioremap_wc(efx->membase_phys,
-				  efx->type->mem_map_size);
+
+	/* bug22643: If SR-IOV is enabled then tx push over a write combined
+	 * mapping is unsafe. We need to disable write combining in this case.
+	 * MSI is unsupported when SR-IOV is enabled, and the firmware will
+	 * have removed the MSI capability. So write combining is safe if
+	 * there is an MSI capability.
+	 */
+	use_wc = (!EFX_WORKAROUND_22643(efx) ||
+		  pci_find_capability(pci_dev, PCI_CAP_ID_MSI));
+	if (use_wc)
+		efx->membase = ioremap_wc(efx->membase_phys,
+					  efx->type->mem_map_size);
+	else
+		efx->membase = ioremap_nocache(efx->membase_phys,
+					       efx->type->mem_map_size);
 	if (!efx->membase) {
 		netif_err(efx, probe, efx->net_dev,
 			  "could not map memory BAR at %llx+%x\n",
diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h
index e4dd3a7f304..99ff11400ce 100644
--- a/drivers/net/sfc/workarounds.h
+++ b/drivers/net/sfc/workarounds.h
@@ -38,6 +38,8 @@
 #define EFX_WORKAROUND_15783 EFX_WORKAROUND_ALWAYS
 /* Legacy interrupt storm when interrupt fifo fills */
 #define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA
+/* Write combining and sriov=enabled are incompatible */
+#define EFX_WORKAROUND_22643 EFX_WORKAROUND_SIENA
 
 /* Spurious parity errors in TSORT buffers */
 #define EFX_WORKAROUND_5129 EFX_WORKAROUND_FALCON_A
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index bc86f4b6ecc..727874d9deb 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -49,6 +49,8 @@
 
 struct smsc95xx_priv {
 	u32 mac_cr;
+	u32 hash_hi;
+	u32 hash_lo;
 	spinlock_t mac_cr_lock;
 	bool use_tx_csum;
 	bool use_rx_csum;
@@ -370,10 +372,11 @@ static void smsc95xx_set_multicast(struct net_device *netdev)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
-	u32 hash_hi = 0;
-	u32 hash_lo = 0;
 	unsigned long flags;
 
+	pdata->hash_hi = 0;
+	pdata->hash_lo = 0;
+
 	spin_lock_irqsave(&pdata->mac_cr_lock, flags);
 
 	if (dev->net->flags & IFF_PROMISC) {
@@ -394,13 +397,13 @@ static void smsc95xx_set_multicast(struct net_device *netdev)
 			u32 bitnum = smsc95xx_hash(ha->addr);
 			u32 mask = 0x01 << (bitnum & 0x1F);
 			if (bitnum & 0x20)
-				hash_hi |= mask;
+				pdata->hash_hi |= mask;
 			else
-				hash_lo |= mask;
+				pdata->hash_lo |= mask;
 		}
 
 		netif_dbg(dev, drv, dev->net, "HASHH=0x%08X, HASHL=0x%08X\n",
-				   hash_hi, hash_lo);
+				   pdata->hash_hi, pdata->hash_lo);
 	} else {
 		netif_dbg(dev, drv, dev->net, "receive own packets only\n");
 		pdata->mac_cr &=
@@ -410,8 +413,8 @@ static void smsc95xx_set_multicast(struct net_device *netdev)
 	spin_unlock_irqrestore(&pdata->mac_cr_lock, flags);
 
 	/* Initiate async writes, as we can't wait for completion here */
-	smsc95xx_write_reg_async(dev, HASHH, &hash_hi);
-	smsc95xx_write_reg_async(dev, HASHL, &hash_lo);
+	smsc95xx_write_reg_async(dev, HASHH, &pdata->hash_hi);
+	smsc95xx_write_reg_async(dev, HASHL, &pdata->hash_lo);
 	smsc95xx_write_reg_async(dev, MAC_CR, &pdata->mac_cr);
 }
 
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 115f162c617..524825720a0 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2160,6 +2160,8 @@ static void ath9k_flush(struct ieee80211_hw *hw, bool drop)
 	if (!ath_drain_all_txq(sc, false))
 		ath_reset(sc, false);
 
+	ieee80211_wake_queues(hw);
+
 out:
 	ieee80211_queue_delayed_work(hw, &sc->tx_complete_work, 0);
 	mutex_unlock(&sc->mutex);
diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c
index 960d717ca7c..a3241cd089b 100644
--- a/drivers/net/wireless/ath/ath9k/rc.c
+++ b/drivers/net/wireless/ath/ath9k/rc.c
@@ -1328,7 +1328,7 @@ static void ath_tx_status(void *priv, struct ieee80211_supported_band *sband,
 
 	hdr = (struct ieee80211_hdr *)skb->data;
 	fc = hdr->frame_control;
-	for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
+	for (i = 0; i < sc->hw->max_rates; i++) {
 		struct ieee80211_tx_rate *rate = &tx_info->status.rates[i];
 		if (!rate->count)
 			break;
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index ef22096d40c..26734e53b37 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1725,8 +1725,8 @@ static void ath_tx_start_dma(struct ath_softc *sc, struct ath_buf *bf,
 	u8 tidno;
 
 	spin_lock_bh(&txctl->txq->axq_lock);
-
-	if (ieee80211_is_data_qos(hdr->frame_control) && txctl->an) {
+	if ((sc->sc_flags & SC_OP_TXAGGR) && txctl->an &&
+		ieee80211_is_data_qos(hdr->frame_control)) {
 		tidno = ieee80211_get_qos_ctl(hdr)[0] &
 			IEEE80211_QOS_CTL_TID_MASK;
 		tid = ATH_AN_2_TID(txctl->an, tidno);
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
index 2003c1d4295..08ccb9496f7 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
@@ -2265,7 +2265,7 @@ signed long iwlagn_wait_notification(struct iwl_priv *priv,
 	int ret;
 
 	ret = wait_event_timeout(priv->_agn.notif_waitq,
-				 &wait_entry->triggered,
+				 wait_entry->triggered,
 				 timeout);
 
 	spin_lock_bh(&priv->_agn.notif_wait_lock);
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 581dc9f1027..321b18b5913 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -3009,14 +3009,17 @@ static int iwl_mac_offchannel_tx_cancel_wait(struct ieee80211_hw *hw)
 
 	mutex_lock(&priv->mutex);
 
-	if (!priv->_agn.offchan_tx_skb)
-		return -EINVAL;
+	if (!priv->_agn.offchan_tx_skb) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
 	priv->_agn.offchan_tx_skb = NULL;
 
 	ret = iwl_scan_cancel_timeout(priv, 200);
 	if (ret)
 		ret = -EIO;
+unlock:
 	mutex_unlock(&priv->mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/orinoco/cfg.c b/drivers/net/wireless/orinoco/cfg.c
index 09fae2f0ea0..736bbb9bd1d 100644
--- a/drivers/net/wireless/orinoco/cfg.c
+++ b/drivers/net/wireless/orinoco/cfg.c
@@ -153,6 +153,9 @@ static int orinoco_scan(struct wiphy *wiphy, struct net_device *dev,
 	priv->scan_request = request;
 
 	err = orinoco_hw_trigger_scan(priv, request->ssids);
+	/* On error the we aren't processing the request */
+	if (err)
+		priv->scan_request = NULL;
 
 	return err;
 }
diff --git a/drivers/net/wireless/orinoco/main.c b/drivers/net/wireless/orinoco/main.c
index f3d396e7544..62c6b2b37db 100644
--- a/drivers/net/wireless/orinoco/main.c
+++ b/drivers/net/wireless/orinoco/main.c
@@ -1376,13 +1376,13 @@ static void orinoco_process_scan_results(struct work_struct *work)
 
 	spin_lock_irqsave(&priv->scan_lock, flags);
 	list_for_each_entry_safe(sd, temp, &priv->scan_list, list) {
-		spin_unlock_irqrestore(&priv->scan_lock, flags);
 
 		buf = sd->buf;
 		len = sd->len;
 		type = sd->type;
 
 		list_del(&sd->list);
+		spin_unlock_irqrestore(&priv->scan_lock, flags);
 		kfree(sd);
 
 		if (len > 0) {
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index f1a92144996..4e368657a83 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -719,6 +719,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x0b05, 0x1732), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x0b05, 0x1742), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x0b05, 0x1784), USB_DEVICE_DATA(&rt2800usb_ops) },
+	{ USB_DEVICE(0x1761, 0x0b05), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* AzureWave */
 	{ USB_DEVICE(0x13d3, 0x3247), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x13d3, 0x3273), USB_DEVICE_DATA(&rt2800usb_ops) },
@@ -913,7 +914,6 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x0b05, 0x1760), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x0b05, 0x1761), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x0b05, 0x1790), USB_DEVICE_DATA(&rt2800usb_ops) },
-	{ USB_DEVICE(0x1761, 0x0b05), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* AzureWave */
 	{ USB_DEVICE(0x13d3, 0x3262), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x13d3, 0x3284), USB_DEVICE_DATA(&rt2800usb_ops) },
@@ -937,6 +937,8 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x07d1, 0x3c13), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x07d1, 0x3c15), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x07d1, 0x3c17), USB_DEVICE_DATA(&rt2800usb_ops) },
+	/* Edimax */
+	{ USB_DEVICE(0x7392, 0x4085), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* Encore */
 	{ USB_DEVICE(0x203d, 0x14a1), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* Gemtek */
@@ -961,6 +963,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x1d4d, 0x0010), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x1d4d, 0x0011), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* Planex */
+	{ USB_DEVICE(0x2019, 0x5201), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x2019, 0xab24), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* Qcom */
 	{ USB_DEVICE(0x18e8, 0x6259), USB_DEVICE_DATA(&rt2800usb_ops) },
@@ -972,6 +975,8 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	/* Sweex */
 	{ USB_DEVICE(0x177f, 0x0153), USB_DEVICE_DATA(&rt2800usb_ops) },
 	{ USB_DEVICE(0x177f, 0x0313), USB_DEVICE_DATA(&rt2800usb_ops) },
+	/* Toshiba */
+	{ USB_DEVICE(0x0930, 0x0a07), USB_DEVICE_DATA(&rt2800usb_ops) },
 	/* Zyxel */
 	{ USB_DEVICE(0x0586, 0x341a), USB_DEVICE_DATA(&rt2800usb_ops) },
 #endif
diff --git a/drivers/net/wireless/rtlwifi/efuse.c b/drivers/net/wireless/rtlwifi/efuse.c
index 4f92cba6810..f74a8701c67 100644
--- a/drivers/net/wireless/rtlwifi/efuse.c
+++ b/drivers/net/wireless/rtlwifi/efuse.c
@@ -410,8 +410,8 @@ bool efuse_shadow_update(struct ieee80211_hw *hw)
 
 	if (!efuse_shadow_update_chk(hw)) {
 		efuse_read_all_map(hw, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0]);
-		memcpy((void *)&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
-		       (void *)&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
+		memcpy(&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
+		       &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
 		       rtlpriv->cfg->maps[EFUSE_HWSET_MAX_SIZE]);
 
 		RT_TRACE(rtlpriv, COMP_EFUSE, DBG_LOUD,
@@ -446,9 +446,9 @@ bool efuse_shadow_update(struct ieee80211_hw *hw)
 
 		if (word_en != 0x0F) {
 			u8 tmpdata[8];
-			memcpy((void *)tmpdata,
-			       (void *)(&rtlefuse->
-					efuse_map[EFUSE_MODIFY_MAP][base]), 8);
+			memcpy(tmpdata,
+			       &rtlefuse->efuse_map[EFUSE_MODIFY_MAP][base],
+			       8);
 			RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_LOUD,
 				      ("U-efuse\n"), tmpdata, 8);
 
@@ -465,8 +465,8 @@ bool efuse_shadow_update(struct ieee80211_hw *hw)
 	efuse_power_switch(hw, true, false);
 	efuse_read_all_map(hw, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0]);
 
-	memcpy((void *)&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
-	       (void *)&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
+	memcpy(&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
+	       &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
 	       rtlpriv->cfg->maps[EFUSE_HWSET_MAX_SIZE]);
 
 	RT_TRACE(rtlpriv, COMP_EFUSE, DBG_LOUD, ("<---\n"));
@@ -479,13 +479,12 @@ void rtl_efuse_shadow_map_update(struct ieee80211_hw *hw)
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 
 	if (rtlefuse->autoload_failflag == true) {
-		memset((void *)(&rtlefuse->efuse_map[EFUSE_INIT_MAP][0]), 128,
-		       0xFF);
+		memset(&rtlefuse->efuse_map[EFUSE_INIT_MAP][0], 0xFF, 128);
 	} else
 		efuse_read_all_map(hw, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0]);
 
-	memcpy((void *)&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
-	       (void *)&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
+	memcpy(&rtlefuse->efuse_map[EFUSE_MODIFY_MAP][0],
+	       &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
 	       rtlpriv->cfg->maps[EFUSE_HWSET_MAX_SIZE]);
 
 }
@@ -694,8 +693,8 @@ static int efuse_pg_packet_read(struct ieee80211_hw *hw, u8 offset, u8 *data)
 	if (offset > 15)
 		return false;
 
-	memset((void *)data, PGPKT_DATA_SIZE * sizeof(u8), 0xff);
-	memset((void *)tmpdata, PGPKT_DATA_SIZE * sizeof(u8), 0xff);
+	memset(data, 0xff, PGPKT_DATA_SIZE * sizeof(u8));
+	memset(tmpdata, 0xff, PGPKT_DATA_SIZE * sizeof(u8));
 
 	while (bcontinual && (efuse_addr < EFUSE_MAX_SIZE)) {
 		if (readstate & PG_STATE_HEADER) {
@@ -862,7 +861,7 @@ static void efuse_write_data_case2(struct ieee80211_hw *hw, u16 *efuse_addr,
 
 		tmp_word_cnts = efuse_calculate_word_cnts(tmp_pkt.word_en);
 
-		memset((void *)originaldata, 8 * sizeof(u8), 0xff);
+		memset(originaldata, 0xff, 8 * sizeof(u8));
 
 		if (efuse_pg_packet_read(hw, tmp_pkt.offset, originaldata)) {
 			badworden = efuse_word_enable_data_write(hw,
@@ -917,7 +916,7 @@ static int efuse_pg_packet_write(struct ieee80211_hw *hw,
 	target_pkt.offset = offset;
 	target_pkt.word_en = word_en;
 
-	memset((void *)target_pkt.data, 8 * sizeof(u8), 0xFF);
+	memset(target_pkt.data, 0xFF, 8 * sizeof(u8));
 
 	efuse_word_enable_data_read(word_en, data, target_pkt.data);
 	target_word_cnts = efuse_calculate_word_cnts(target_pkt.word_en);
@@ -1022,7 +1021,7 @@ static u8 efuse_word_enable_data_write(struct ieee80211_hw *hw,
 	u8 badworden = 0x0F;
 	u8 tmpdata[8];
 
-	memset((void *)tmpdata, PGPKT_DATA_SIZE, 0xff);
+	memset(tmpdata, 0xff, PGPKT_DATA_SIZE);
 	RT_TRACE(rtlpriv, COMP_EFUSE, DBG_LOUD,
 		 ("word_en = %x efuse_addr=%x\n", word_en, efuse_addr));
 
diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c
index 81e80489a05..58236e6d092 100644
--- a/drivers/net/wireless/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zd1211rw/zd_usb.c
@@ -60,6 +60,7 @@ static struct usb_device_id usb_ids[] = {
 	{ USB_DEVICE(0x157e, 0x300a), .driver_info = DEVICE_ZD1211 },
 	{ USB_DEVICE(0x157e, 0x300b), .driver_info = DEVICE_ZD1211 },
 	{ USB_DEVICE(0x157e, 0x3204), .driver_info = DEVICE_ZD1211 },
+	{ USB_DEVICE(0x157e, 0x3207), .driver_info = DEVICE_ZD1211 },
 	{ USB_DEVICE(0x1740, 0x2000), .driver_info = DEVICE_ZD1211 },
 	{ USB_DEVICE(0x6891, 0xa727), .driver_info = DEVICE_ZD1211 },
 	/* ZD1211B */
diff --git a/include/linux/davinci_emac.h b/include/linux/davinci_emac.h
index 5dd428532f7..54288850499 100644
--- a/include/linux/davinci_emac.h
+++ b/include/linux/davinci_emac.h
@@ -36,6 +36,7 @@ struct emac_platform_data {
 
 	u8 rmii_en;
 	u8 version;
+	bool no_bd_ram;
 	void (*interrupt_enable) (void);
 	void (*interrupt_disable) (void);
 };
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index b297f288f6e..ae757bcf128 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -648,6 +648,9 @@ enum ethtool_sfeatures_retval_bits {
 
 #include <linux/rculist.h>
 
+/* needed by dev_disable_lro() */
+extern int __ethtool_set_flags(struct net_device *dev, u32 flags);
+
 struct ethtool_rx_ntuple_flow_spec_container {
 	struct ethtool_rx_ntuple_flow_spec fs;
 	struct list_head list;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 04921464203..8985768e2c0 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -39,6 +39,11 @@
 
 #include <asm/atomic.h>
 
+#define MAX_MSIX_P_PORT		17
+#define MAX_MSIX		64
+#define MSIX_LEGACY_SZ		4
+#define MIN_MSIX_P_PORT		5
+
 enum {
 	MLX4_FLAG_MSI_X		= 1 << 0,
 	MLX4_FLAG_OLD_PORT_CMDS	= 1 << 1,
@@ -145,8 +150,10 @@ enum {
 };
 
 enum mlx4_protocol {
-	MLX4_PROTOCOL_IB,
-	MLX4_PROTOCOL_EN,
+	MLX4_PROT_IB_IPV6 = 0,
+	MLX4_PROT_ETH,
+	MLX4_PROT_IB_IPV4,
+	MLX4_PROT_FCOE
 };
 
 enum {
@@ -173,6 +180,12 @@ enum mlx4_special_vlan_idx {
 	MLX4_VLAN_REGULAR
 };
 
+enum mlx4_steer_type {
+	MLX4_MC_STEER = 0,
+	MLX4_UC_STEER,
+	MLX4_NUM_STEERS
+};
+
 enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
@@ -223,6 +236,7 @@ struct mlx4_caps {
 	int			num_eqs;
 	int			reserved_eqs;
 	int			num_comp_vectors;
+	int			comp_pool;
 	int			num_mpts;
 	int			num_mtt_segs;
 	int			mtts_per_seg;
@@ -245,6 +259,9 @@ struct mlx4_caps {
 	u16			stat_rate_support;
 	int			udp_rss;
 	int			loopback_support;
+	int			vep_uc_steering;
+	int			vep_mc_steering;
+	int			wol;
 	u8			port_width_cap[MLX4_MAX_PORTS + 1];
 	int			max_gso_sz;
 	int                     reserved_qps_cnt[MLX4_NUM_QP_REGION];
@@ -334,6 +351,17 @@ struct mlx4_fmr {
 struct mlx4_uar {
 	unsigned long		pfn;
 	int			index;
+	struct list_head	bf_list;
+	unsigned		free_bf_bmap;
+	void __iomem	       *map;
+	void __iomem	       *bf_map;
+};
+
+struct mlx4_bf {
+	unsigned long		offset;
+	int			buf_size;
+	struct mlx4_uar	       *uar;
+	void __iomem	       *reg;
 };
 
 struct mlx4_cq {
@@ -415,7 +443,7 @@ struct mlx4_dev {
 	unsigned long		flags;
 	struct mlx4_caps	caps;
 	struct radix_tree_root	qp_table_tree;
-	u32			rev_id;
+	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 };
 
@@ -461,6 +489,8 @@ void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn);
 
 int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar);
 void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar);
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf);
+void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf);
 
 int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
 		  struct mlx4_mtt *mtt);
@@ -508,9 +538,15 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback, enum mlx4_protocol protocol);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  enum mlx4_protocol protocol);
+int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
+int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
+int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
+int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
+int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mode);
 
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index);
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index);
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap);
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn);
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap);
 
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
@@ -526,5 +562,10 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
+int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector);
+void mlx4_release_eq(struct mlx4_dev *dev, int vec);
+
+int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
+int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
 
 #endif /* MLX4_DEVICE_H */
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 0eeb2a1a867..9e9eb21056c 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -303,6 +303,7 @@ struct mlx4_wqe_data_seg {
 
 enum {
 	MLX4_INLINE_ALIGN	= 64,
+	MLX4_INLINE_SEG		= 1 << 31,
 };
 
 struct mlx4_wqe_inline_seg {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 60f7876b6da..b2b9d28cb4a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -486,7 +486,8 @@ struct rate_info {
  * @plink_state: mesh peer link state
  * @signal: signal strength of last received packet in dBm
  * @signal_avg: signal strength average in dBm
- * @txrate: current unicast bitrate to this station
+ * @txrate: current unicast bitrate from this station
+ * @rxrate: current unicast bitrate to this station
  * @rx_packets: packets received from this station
  * @tx_packets: packets transmitted to this station
  * @tx_retries: cumulative retry counts
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 642a80bb42c..c850e5fb967 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -70,7 +70,7 @@ static inline struct inet_peer *rt6_get_peer(struct rt6_info *rt)
 extern void			ip6_route_input(struct sk_buff *skb);
 
 extern struct dst_entry *	ip6_route_output(struct net *net,
-						 struct sock *sk,
+						 const struct sock *sk,
 						 struct flowi6 *fl6);
 
 extern int			ip6_route_init(void);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a1a85803591..e5d66ec88cf 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -51,7 +51,6 @@ struct fib_nh {
 	struct fib_info		*nh_parent;
 	unsigned		nh_flags;
 	unsigned char		nh_scope;
-	unsigned char		nh_cfg_scope;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			nh_weight;
 	int			nh_power;
@@ -62,6 +61,7 @@ struct fib_nh {
 	int			nh_oif;
 	__be32			nh_gw;
 	__be32			nh_saddr;
+	int			nh_saddr_genid;
 };
 
 /*
@@ -74,9 +74,10 @@ struct fib_info {
 	struct net		*fib_net;
 	int			fib_treeref;
 	atomic_t		fib_clntref;
-	int			fib_dead;
 	unsigned		fib_flags;
-	int			fib_protocol;
+	unsigned char		fib_dead;
+	unsigned char		fib_protocol;
+	unsigned char		fib_scope;
 	__be32			fib_prefsrc;
 	u32			fib_priority;
 	u32			*fib_metrics;
@@ -141,12 +142,19 @@ struct fib_result_nl {
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
-#define FIB_RES_SADDR(res)		(FIB_RES_NH(res).nh_saddr)
+extern __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
+
+#define FIB_RES_SADDR(net, res)				\
+	((FIB_RES_NH(res).nh_saddr_genid ==		\
+	  atomic_read(&(net)->ipv4.dev_addr_genid)) ?	\
+	 FIB_RES_NH(res).nh_saddr :			\
+	 fib_info_update_nh_saddr((net), &FIB_RES_NH(res)))
 #define FIB_RES_GW(res)			(FIB_RES_NH(res).nh_gw)
 #define FIB_RES_DEV(res)		(FIB_RES_NH(res).nh_dev)
 #define FIB_RES_OIF(res)		(FIB_RES_NH(res).nh_oif)
 
-#define FIB_RES_PREFSRC(res)		((res).fi->fib_prefsrc ? : FIB_RES_SADDR(res))
+#define FIB_RES_PREFSRC(net, res)	((res).fi->fib_prefsrc ? : \
+					 FIB_RES_SADDR(net, res))
 
 struct fib_table {
 	struct hlist_node tb_hlist;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8650e7bf2ed..cefe1b37c49 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1160,7 +1160,7 @@ enum ieee80211_hw_flags {
  * @napi_weight: weight used for NAPI polling.  You must specify an
  *	appropriate value here if a napi_poll operation is provided
  *	by your driver.
-
+ *
  * @max_rx_aggregation_subframes: maximum buffer size (number of
  *	sub-frames) to be used for A-MPDU block ack receiver
  *	aggregation.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e2e2ef57eca..542195d9469 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -55,6 +55,7 @@ struct netns_ipv4 {
 	int current_rt_cache_rebuild_count;
 
 	atomic_t rt_genid;
+	atomic_t dev_addr_genid;
 
 #ifdef CONFIG_IP_MROUTE
 #ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES
diff --git a/include/net/route.h b/include/net/route.h
index 30d6cae3841..f88429cad52 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -207,6 +207,7 @@ extern int		ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
 
 struct in_ifaddr;
 extern void fib_add_ifaddr(struct in_ifaddr *);
+extern void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
 static inline void ip_rt_put(struct rtable * rt)
 {
@@ -269,8 +270,8 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 		struct flowi4 fl4 = {
 			.flowi4_oif = rt->rt_oif,
 			.flowi4_mark = rt->rt_mark,
-			.daddr = rt->rt_key_dst,
-			.saddr = rt->rt_key_src,
+			.daddr = rt->rt_dst,
+			.saddr = rt->rt_src,
 			.flowi4_tos = rt->rt_tos,
 			.flowi4_proto = protocol,
 			.fl4_sport = sport,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a9505b6a18e..b931f021d7a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -25,6 +25,7 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_THROTTLED,
 };
 
 /*
@@ -32,7 +33,6 @@ enum qdisc_state_t {
  */
 enum qdisc___state_t {
 	__QDISC___STATE_RUNNING = 1,
-	__QDISC___STATE_THROTTLED = 2,
 };
 
 struct qdisc_size_table {
@@ -106,17 +106,17 @@ static inline void qdisc_run_end(struct Qdisc *qdisc)
 
 static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
 {
-	return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false;
+	return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false;
 }
 
 static inline void qdisc_throttled(struct Qdisc *qdisc)
 {
-	qdisc->__state |= __QDISC___STATE_THROTTLED;
+	set_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
 }
 
 static inline void qdisc_unthrottled(struct Qdisc *qdisc)
 {
-	qdisc->__state &= ~__QDISC___STATE_THROTTLED;
+	clear_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
 }
 
 struct Qdisc_class_ops {
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 030a002ff8e..f61eb2eff3f 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -445,9 +445,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	ip6h->payload_len = htons(8 + sizeof(*mldq));
 	ip6h->nexthdr = IPPROTO_HOPOPTS;
 	ip6h->hop_limit = 1;
+	ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
 	ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			   &ip6h->saddr);
-	ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
 	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
 
 	hopopt = (u8 *)(ip6h + 1);
diff --git a/net/core/dev.c b/net/core/dev.c
index 0b88eba97da..f453370131a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1353,14 +1353,17 @@ EXPORT_SYMBOL(dev_close);
  */
 void dev_disable_lro(struct net_device *dev)
 {
-	if (dev->ethtool_ops && dev->ethtool_ops->get_flags &&
-	    dev->ethtool_ops->set_flags) {
-		u32 flags = dev->ethtool_ops->get_flags(dev);
-		if (flags & ETH_FLAG_LRO) {
-			flags &= ~ETH_FLAG_LRO;
-			dev->ethtool_ops->set_flags(dev, flags);
-		}
-	}
+	u32 flags;
+
+	if (dev->ethtool_ops && dev->ethtool_ops->get_flags)
+		flags = dev->ethtool_ops->get_flags(dev);
+	else
+		flags = ethtool_op_get_flags(dev);
+
+	if (!(flags & ETH_FLAG_LRO))
+		return;
+
+	__ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO);
 	WARN_ON(dev->features & NETIF_F_LRO);
 }
 EXPORT_SYMBOL(dev_disable_lro);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index a1086fb0c0c..24bd57493c0 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -513,7 +513,7 @@ static int ethtool_set_one_feature(struct net_device *dev,
 	}
 }
 
-static int __ethtool_set_flags(struct net_device *dev, u32 data)
+int __ethtool_set_flags(struct net_device *dev, u32 data)
 {
 	u32 changed;
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 6d85800daeb..5345b0bee6d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -64,6 +64,8 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 
+#include "fib_lookup.h"
+
 static struct ipv4_devconf ipv4_devconf = {
 	.data = {
 		[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
@@ -151,6 +153,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 			break;
 		}
 	}
+	if (!result) {
+		struct flowi4 fl4 = { .daddr = addr };
+		struct fib_result res = { 0 };
+		struct fib_table *local;
+
+		/* Fallback to FIB local table so that communication
+		 * over loopback subnets work.
+		 */
+		local = fib_get_table(net, RT_TABLE_LOCAL);
+		if (local &&
+		    !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
+		    res.type == RTN_LOCAL)
+			result = FIB_RES_DEV(res);
+	}
 	if (result && devref)
 		dev_hold(result);
 	rcu_read_unlock();
@@ -345,6 +361,17 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 		}
 	}
 
+	/* On promotion all secondaries from subnet are changing
+	 * the primary IP, we must remove all their routes silently
+	 * and later to add them back with new prefsrc. Do this
+	 * while all addresses are on the device list.
+	 */
+	for (ifa = promote; ifa; ifa = ifa->ifa_next) {
+		if (ifa1->ifa_mask == ifa->ifa_mask &&
+		    inet_ifa_match(ifa1->ifa_address, ifa))
+			fib_del_ifaddr(ifa, ifa1);
+	}
+
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
@@ -364,6 +391,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 	blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
 
 	if (promote) {
+		struct in_ifaddr *next_sec = promote->ifa_next;
 
 		if (prev_prom) {
 			prev_prom->ifa_next = promote->ifa_next;
@@ -375,7 +403,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 		rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
 		blocking_notifier_call_chain(&inetaddr_chain,
 				NETDEV_UP, promote);
-		for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
+		for (ifa = next_sec; ifa; ifa = ifa->ifa_next) {
 			if (ifa1->ifa_mask != ifa->ifa_mask ||
 			    !inet_ifa_match(ifa1->ifa_address, ifa))
 					continue;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a373a259253..f116ce8f1b4 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -228,7 +228,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 		if (res.type != RTN_LOCAL || !accept_local)
 			goto e_inval;
 	}
-	*spec_dst = FIB_RES_PREFSRC(res);
+	*spec_dst = FIB_RES_PREFSRC(net, res);
 	fib_combine_itag(itag, &res);
 	dev_match = false;
 
@@ -258,7 +258,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res) == 0) {
 		if (res.type == RTN_UNICAST) {
-			*spec_dst = FIB_RES_PREFSRC(res);
+			*spec_dst = FIB_RES_PREFSRC(net, res);
 			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
 		}
 	}
@@ -722,12 +722,17 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
 	}
 }
 
-static void fib_del_ifaddr(struct in_ifaddr *ifa)
+/* Delete primary or secondary address.
+ * Optionally, on secondary address promotion consider the addresses
+ * from subnet iprim as deleted, even if they are in device list.
+ * In this case the secondary ifa can be in device list.
+ */
+void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 {
 	struct in_device *in_dev = ifa->ifa_dev;
 	struct net_device *dev = in_dev->dev;
 	struct in_ifaddr *ifa1;
-	struct in_ifaddr *prim = ifa;
+	struct in_ifaddr *prim = ifa, *prim1 = NULL;
 	__be32 brd = ifa->ifa_address | ~ifa->ifa_mask;
 	__be32 any = ifa->ifa_address & ifa->ifa_mask;
 #define LOCAL_OK	1
@@ -735,17 +740,26 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
 #define BRD0_OK		4
 #define BRD1_OK		8
 	unsigned ok = 0;
+	int subnet = 0;		/* Primary network */
+	int gone = 1;		/* Address is missing */
+	int same_prefsrc = 0;	/* Another primary with same IP */
 
-	if (!(ifa->ifa_flags & IFA_F_SECONDARY))
-		fib_magic(RTM_DELROUTE,
-			  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
-			  any, ifa->ifa_prefixlen, prim);
-	else {
+	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (prim == NULL) {
 			printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n");
 			return;
 		}
+		if (iprim && iprim != prim) {
+			printk(KERN_WARNING "fib_del_ifaddr: bug: iprim != prim\n");
+			return;
+		}
+	} else if (!ipv4_is_zeronet(any) &&
+		   (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) {
+		fib_magic(RTM_DELROUTE,
+			  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+			  any, ifa->ifa_prefixlen, prim);
+		subnet = 1;
 	}
 
 	/* Deletion is more complicated than add.
@@ -755,6 +769,49 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
 	 */
 
 	for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
+		if (ifa1 == ifa) {
+			/* promotion, keep the IP */
+			gone = 0;
+			continue;
+		}
+		/* Ignore IFAs from our subnet */
+		if (iprim && ifa1->ifa_mask == iprim->ifa_mask &&
+		    inet_ifa_match(ifa1->ifa_address, iprim))
+			continue;
+
+		/* Ignore ifa1 if it uses different primary IP (prefsrc) */
+		if (ifa1->ifa_flags & IFA_F_SECONDARY) {
+			/* Another address from our subnet? */
+			if (ifa1->ifa_mask == prim->ifa_mask &&
+			    inet_ifa_match(ifa1->ifa_address, prim))
+				prim1 = prim;
+			else {
+				/* We reached the secondaries, so
+				 * same_prefsrc should be determined.
+				 */
+				if (!same_prefsrc)
+					continue;
+				/* Search new prim1 if ifa1 is not
+				 * using the current prim1
+				 */
+				if (!prim1 ||
+				    ifa1->ifa_mask != prim1->ifa_mask ||
+				    !inet_ifa_match(ifa1->ifa_address, prim1))
+					prim1 = inet_ifa_byprefix(in_dev,
+							ifa1->ifa_address,
+							ifa1->ifa_mask);
+				if (!prim1)
+					continue;
+				if (prim1->ifa_local != prim->ifa_local)
+					continue;
+			}
+		} else {
+			if (prim->ifa_local != ifa1->ifa_local)
+				continue;
+			prim1 = ifa1;
+			if (prim != prim1)
+				same_prefsrc = 1;
+		}
 		if (ifa->ifa_local == ifa1->ifa_local)
 			ok |= LOCAL_OK;
 		if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
@@ -763,19 +820,37 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
 			ok |= BRD1_OK;
 		if (any == ifa1->ifa_broadcast)
 			ok |= BRD0_OK;
+		/* primary has network specific broadcasts */
+		if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) {
+			__be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask;
+			__be32 any1 = ifa1->ifa_address & ifa1->ifa_mask;
+
+			if (!ipv4_is_zeronet(any1)) {
+				if (ifa->ifa_broadcast == brd1 ||
+				    ifa->ifa_broadcast == any1)
+					ok |= BRD_OK;
+				if (brd == brd1 || brd == any1)
+					ok |= BRD1_OK;
+				if (any == brd1 || any == any1)
+					ok |= BRD0_OK;
+			}
+		}
 	}
 
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
-	if (!(ok & BRD1_OK))
-		fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
-	if (!(ok & BRD0_OK))
-		fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
+	if (subnet && ifa->ifa_prefixlen < 31) {
+		if (!(ok & BRD1_OK))
+			fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
+		if (!(ok & BRD0_OK))
+			fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
+	}
 	if (!(ok & LOCAL_OK)) {
 		fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
 
 		/* Check, that this local address finally disappeared. */
-		if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
+		if (gone &&
+		    inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
 			/* And the last, but not the least thing.
 			 * We must flush stray FIB entries.
 			 *
@@ -885,6 +960,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 {
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	struct net_device *dev = ifa->ifa_dev->dev;
+	struct net *net = dev_net(dev);
 
 	switch (event) {
 	case NETDEV_UP:
@@ -892,12 +968,12 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		fib_sync_up(dev);
 #endif
-		fib_update_nh_saddrs(dev);
+		atomic_inc(&net->ipv4.dev_addr_genid);
 		rt_cache_flush(dev_net(dev), -1);
 		break;
 	case NETDEV_DOWN:
-		fib_del_ifaddr(ifa);
-		fib_update_nh_saddrs(dev);
+		fib_del_ifaddr(ifa, NULL);
+		atomic_inc(&net->ipv4.dev_addr_genid);
 		if (ifa->ifa_dev->ifa_list == NULL) {
 			/* Last address was deleted from this interface.
 			 * Disable IP.
@@ -915,6 +991,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 {
 	struct net_device *dev = ptr;
 	struct in_device *in_dev = __in_dev_get_rtnl(dev);
+	struct net *net = dev_net(dev);
 
 	if (event == NETDEV_UNREGISTER) {
 		fib_disable_ip(dev, 2, -1);
@@ -932,6 +1009,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		fib_sync_up(dev);
 #endif
+		atomic_inc(&net->ipv4.dev_addr_genid);
 		rt_cache_flush(dev_net(dev), -1);
 		break;
 	case NETDEV_DOWN:
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 4ec323875a0..af0f14aba16 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -10,7 +10,6 @@ struct fib_alias {
 	struct fib_info		*fa_info;
 	u8			fa_tos;
 	u8			fa_type;
-	u8			fa_scope;
 	u8			fa_state;
 	struct rcu_head		rcu;
 };
@@ -29,7 +28,7 @@ extern void fib_release_info(struct fib_info *);
 extern struct fib_info *fib_create_info(struct fib_config *cfg);
 extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi);
 extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-			 u32 tb_id, u8 type, u8 scope, __be32 dst,
+			 u32 tb_id, u8 type, __be32 dst,
 			 int dst_len, u8 tos, struct fib_info *fi,
 			 unsigned int);
 extern void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 622ac4c9502..641a5a2a9f9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -222,7 +222,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 	unsigned int mask = (fib_info_hash_size - 1);
 	unsigned int val = fi->fib_nhs;
 
-	val ^= fi->fib_protocol;
+	val ^= (fi->fib_protocol << 8) | fi->fib_scope;
 	val ^= (__force u32)fi->fib_prefsrc;
 	val ^= fi->fib_priority;
 	for_nexthops(fi) {
@@ -248,10 +248,11 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
 		if (fi->fib_nhs != nfi->fib_nhs)
 			continue;
 		if (nfi->fib_protocol == fi->fib_protocol &&
+		    nfi->fib_scope == fi->fib_scope &&
 		    nfi->fib_prefsrc == fi->fib_prefsrc &&
 		    nfi->fib_priority == fi->fib_priority &&
 		    memcmp(nfi->fib_metrics, fi->fib_metrics,
-			   sizeof(fi->fib_metrics)) == 0 &&
+			   sizeof(u32) * RTAX_MAX) == 0 &&
 		    ((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
 		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
 			return fi;
@@ -328,7 +329,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 		goto errout;
 
 	err = fib_dump_info(skb, info->pid, seq, event, tb_id,
-			    fa->fa_type, fa->fa_scope, key, dst_len,
+			    fa->fa_type, key, dst_len,
 			    fa->fa_tos, fa->fa_info, nlm_flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
@@ -695,6 +696,16 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
 	fib_info_hash_free(old_laddrhash, bytes);
 }
 
+__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
+{
+	nh->nh_saddr = inet_select_addr(nh->nh_dev,
+					nh->nh_gw,
+					nh->nh_parent->fib_scope);
+	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+
+	return nh->nh_saddr;
+}
+
 struct fib_info *fib_create_info(struct fib_config *cfg)
 {
 	int err;
@@ -753,6 +764,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
+	fi->fib_scope = cfg->fc_scope;
 	fi->fib_flags = cfg->fc_flags;
 	fi->fib_priority = cfg->fc_priority;
 	fi->fib_prefsrc = cfg->fc_prefsrc;
@@ -854,10 +866,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	}
 
 	change_nexthops(fi) {
-		nexthop_nh->nh_cfg_scope = cfg->fc_scope;
-		nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev,
-							nexthop_nh->nh_gw,
-							nexthop_nh->nh_cfg_scope);
+		fib_info_update_nh_saddr(net, nexthop_nh);
 	} endfor_nexthops(fi)
 
 link_it:
@@ -906,7 +915,7 @@ failure:
 }
 
 int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-		  u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
+		  u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
 		  struct fib_info *fi, unsigned int flags)
 {
 	struct nlmsghdr *nlh;
@@ -928,7 +937,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 	NLA_PUT_U32(skb, RTA_TABLE, tb_id);
 	rtm->rtm_type = type;
 	rtm->rtm_flags = fi->fib_flags;
-	rtm->rtm_scope = scope;
+	rtm->rtm_scope = fi->fib_scope;
 	rtm->rtm_protocol = fi->fib_protocol;
 
 	if (rtm->rtm_dst_len)
@@ -1084,7 +1093,7 @@ void fib_select_default(struct fib_result *res)
 	list_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
-		if (fa->fa_scope != res->scope ||
+		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
@@ -1128,24 +1137,6 @@ out:
 	return;
 }
 
-void fib_update_nh_saddrs(struct net_device *dev)
-{
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct fib_nh *nh;
-	unsigned int hash;
-
-	hash = fib_devindex_hashfn(dev->ifindex);
-	head = &fib_info_devhash[hash];
-	hlist_for_each_entry(nh, node, head, nh_hash) {
-		if (nh->nh_dev != dev)
-			continue;
-		nh->nh_saddr = inet_select_addr(nh->nh_dev,
-						nh->nh_gw,
-						nh->nh_cfg_scope);
-	}
-}
-
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 /*
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3d28a35c2e1..90a3ff60559 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1245,7 +1245,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			if (fa->fa_info->fib_priority != fi->fib_priority)
 				break;
 			if (fa->fa_type == cfg->fc_type &&
-			    fa->fa_scope == cfg->fc_scope &&
 			    fa->fa_info == fi) {
 				fa_match = fa;
 				break;
@@ -1271,7 +1270,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_tos = fa->fa_tos;
 			new_fa->fa_info = fi;
 			new_fa->fa_type = cfg->fc_type;
-			new_fa->fa_scope = cfg->fc_scope;
 			state = fa->fa_state;
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 
@@ -1308,7 +1306,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->fa_info = fi;
 	new_fa->fa_tos = tos;
 	new_fa->fa_type = cfg->fc_type;
-	new_fa->fa_scope = cfg->fc_scope;
 	new_fa->fa_state = 0;
 	/*
 	 * Insert new entry to the list.
@@ -1362,7 +1359,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 				continue;
-			if (fa->fa_scope < flp->flowi4_scope)
+			if (fa->fa_info->fib_scope < flp->flowi4_scope)
 				continue;
 			fib_alias_accessed(fa);
 			err = fib_props[fa->fa_type].error;
@@ -1388,7 +1385,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 				res->prefixlen = plen;
 				res->nh_sel = nhsel;
 				res->type = fa->fa_type;
-				res->scope = fa->fa_scope;
+				res->scope = fa->fa_info->fib_scope;
 				res->fi = fi;
 				res->table = tb;
 				res->fa_head = &li->falh;
@@ -1664,7 +1661,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 
 		if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) &&
 		    (cfg->fc_scope == RT_SCOPE_NOWHERE ||
-		     fa->fa_scope == cfg->fc_scope) &&
+		     fa->fa_info->fib_scope == cfg->fc_scope) &&
+		    (!cfg->fc_prefsrc ||
+		     fi->fib_prefsrc == cfg->fc_prefsrc) &&
 		    (!cfg->fc_protocol ||
 		     fi->fib_protocol == cfg->fc_protocol) &&
 		    fib_nh_match(cfg, fi) == 0) {
@@ -1861,7 +1860,6 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah,
 				  RTM_NEWROUTE,
 				  tb->tb_id,
 				  fa->fa_type,
-				  fa->fa_scope,
 				  xkey,
 				  plen,
 				  fa->fa_tos,
@@ -2382,7 +2380,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v)
 				seq_indent(seq, iter->depth+1);
 				seq_printf(seq, "  /%d %s %s", li->plen,
 					   rtn_scope(buf1, sizeof(buf1),
-						     fa->fa_scope),
+						     fa->fa_info->fib_scope),
 					   rtn_type(buf2, sizeof(buf2),
 						    fa->fa_type));
 				if (fa->fa_tos)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 870b5182ddd..4b0c8118080 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1593,8 +1593,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 			rt->rt_peer_genid = rt_peer_genid();
 		}
 		check_peer_pmtu(dst, peer);
-
-		inet_putpeer(peer);
 	}
 }
 
@@ -1720,7 +1718,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 
 		rcu_read_lock();
 		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
-			src = FIB_RES_PREFSRC(res);
+			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
 		else
 			src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
 					RT_SCOPE_UNIVERSE);
@@ -2617,7 +2615,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 		fib_select_default(&res);
 
 	if (!fl4.saddr)
-		fl4.saddr = FIB_RES_PREFSRC(res);
+		fl4.saddr = FIB_RES_PREFSRC(net, res);
 
 	dev_out = FIB_RES_DEV(res);
 	fl4.flowi4_oif = dev_out->ifindex;
@@ -3221,6 +3219,8 @@ static __net_init int rt_genid_init(struct net *net)
 {
 	get_random_bytes(&net->ipv4.rt_genid,
 			 sizeof(net->ipv4.rt_genid));
+	get_random_bytes(&net->ipv4.dev_addr_genid,
+			 sizeof(net->ipv4.dev_addr_genid));
 	return 0;
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index da782e7ab16..bef9f04c22b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2659,7 +2659,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 #define DBGUNDO(x...) do { } while (0)
 #endif
 
-static void tcp_undo_cwr(struct sock *sk, const int undo)
+static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2671,14 +2671,13 @@ static void tcp_undo_cwr(struct sock *sk, const int undo)
 		else
 			tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
 
-		if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
+		if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
 			tp->snd_ssthresh = tp->prior_ssthresh;
 			TCP_ECN_withdraw_cwr(tp);
 		}
 	} else {
 		tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
 	}
-	tcp_moderate_cwnd(tp);
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
@@ -2699,7 +2698,7 @@ static int tcp_try_undo_recovery(struct sock *sk)
 		 * or our original transmission succeeded.
 		 */
 		DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
-		tcp_undo_cwr(sk, 1);
+		tcp_undo_cwr(sk, true);
 		if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
 			mib_idx = LINUX_MIB_TCPLOSSUNDO;
 		else
@@ -2726,7 +2725,7 @@ static void tcp_try_undo_dsack(struct sock *sk)
 
 	if (tp->undo_marker && !tp->undo_retrans) {
 		DBGUNDO(sk, "D-SACK");
-		tcp_undo_cwr(sk, 1);
+		tcp_undo_cwr(sk, true);
 		tp->undo_marker = 0;
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
 	}
@@ -2779,7 +2778,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked)
 		tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
 
 		DBGUNDO(sk, "Hoe");
-		tcp_undo_cwr(sk, 0);
+		tcp_undo_cwr(sk, false);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
 
 		/* So... Do not make Hoe's retransmit yet.
@@ -2808,7 +2807,7 @@ static int tcp_try_undo_loss(struct sock *sk)
 
 		DBGUNDO(sk, "partial loss");
 		tp->lost_out = 0;
-		tcp_undo_cwr(sk, 1);
+		tcp_undo_cwr(sk, true);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
 		inet_csk(sk)->icsk_retransmits = 0;
 		tp->undo_marker = 0;
@@ -2822,8 +2821,11 @@ static int tcp_try_undo_loss(struct sock *sk)
 static inline void tcp_complete_cwr(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
-	tp->snd_cwnd_stamp = tcp_time_stamp;
+	/* Do not moderate cwnd if it's already undone in cwr or recovery */
+	if (tp->undo_marker && tp->snd_cwnd > tp->snd_ssthresh) {
+		tp->snd_cwnd = tp->snd_ssthresh;
+		tp->snd_cwnd_stamp = tcp_time_stamp;
+	}
 	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
 }
 
@@ -3494,7 +3496,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag)
 	if (flag & FLAG_ECE)
 		tcp_ratehalving_spur_to_response(sk);
 	else
-		tcp_undo_cwr(sk, 1);
+		tcp_undo_cwr(sk, true);
 }
 
 /* F-RTO spurious RTO detection algorithm (RFC4138)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6814c8722fa..843406f14d7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -854,7 +854,7 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
+struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
 				    struct flowi6 *fl6)
 {
 	int flags = 0;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 5a11078827a..d0311a322dd 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -243,6 +243,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	memcpy(sta->sta.addr, addr, ETH_ALEN);
 	sta->local = local;
 	sta->sdata = sdata;
+	sta->last_rx = jiffies;
 
 	ewma_init(&sta->avg_signal, 1024, 8);