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
  ...

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)

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;
 	}

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;
     }

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);

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;

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) {

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;
 

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");

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);

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;

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;
 }

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,

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)

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;
 

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;
 	}

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;

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],

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);

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);
+

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);