1 files changed, 457 insertions, 132 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0ade0cd5ef53..bd8f5239dfe6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -44,6 +44,7 @@
 #include <linux/ethtool.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
+#include <linux/if_macvlan.h>
 #include <linux/if_bridge.h>
 #include <linux/prefetch.h>
 #include <scsi/fc/fc_fcoe.h>
@@ -132,7 +133,7 @@ static struct notifier_block dca_notifier = {
 static unsigned int max_vfs;
 module_param(max_vfs, uint, 0);
 MODULE_PARM_DESC(max_vfs,
-		 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63");
+		 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)");
 #endif /* CONFIG_PCI_IOV */
 
 static unsigned int allow_unsupported_sfp;
@@ -153,7 +154,6 @@ MODULE_VERSION(DRV_VERSION);
 static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
 					  u32 reg, u16 *value)
 {
-	int pos = 0;
 	struct pci_dev *parent_dev;
 	struct pci_bus *parent_bus;
 
@@ -165,11 +165,10 @@ static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
 	if (!parent_dev)
 		return -1;
 
-	pos = pci_find_capability(parent_dev, PCI_CAP_ID_EXP);
-	if (!pos)
+	if (!pci_is_pcie(parent_dev))
 		return -1;
 
-	pci_read_config_word(parent_dev, pos + reg, value);
+	pcie_capability_read_word(parent_dev, reg, value);
 	return 0;
 }
 
@@ -247,7 +246,7 @@ static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter,
 		max_gts = 4 * width;
 		break;
 	case PCIE_SPEED_8_0GT:
-		/* 128b/130b encoding only reduces throughput by 1% */
+		/* 128b/130b encoding reduces throughput by less than 2% */
 		max_gts = 8 * width;
 		break;
 	default:
@@ -265,7 +264,7 @@ static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter,
 		   width,
 		   (speed == PCIE_SPEED_2_5GT ? "20%" :
 		    speed == PCIE_SPEED_5_0GT ? "20%" :
-		    speed == PCIE_SPEED_8_0GT ? "N/a" :
+		    speed == PCIE_SPEED_8_0GT ? "<2%" :
 		    "Unknown"));
 
 	if (max_gts < expected_gts) {
@@ -872,11 +871,18 @@ static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
 
 static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(ring->netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_adapter *adapter;
+	struct ixgbe_hw *hw;
+	u32 head, tail;
 
-	u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
-	u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));
+	if (ring->l2_accel_priv)
+		adapter = ring->l2_accel_priv->real_adapter;
+	else
+		adapter = netdev_priv(ring->netdev);
+
+	hw = &adapter->hw;
+	head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
+	tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));
 
 	if (head != tail)
 		return (head < tail) ?
@@ -1585,7 +1591,7 @@ static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
 {
 	struct ixgbe_adapter *adapter = q_vector->adapter;
 
-	if (ixgbe_qv_ll_polling(q_vector))
+	if (ixgbe_qv_busy_polling(q_vector))
 		netif_receive_skb(skb);
 	else if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
 		napi_gro_receive(&q_vector->napi, skb);
@@ -2097,7 +2103,7 @@ static int ixgbe_low_latency_recv(struct napi_struct *napi)
 
 	ixgbe_for_each_ring(ring, q_vector->rx) {
 		found = ixgbe_clean_rx_irq(q_vector, ring, 4);
-#ifdef LL_EXTENDED_STATS
+#ifdef BP_EXTENDED_STATS
 		if (found)
 			ring->stats.cleaned += found;
 		else
@@ -3005,7 +3011,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 		struct ixgbe_q_vector *q_vector = ring->q_vector;
 
 		if (q_vector)
-			netif_set_xps_queue(adapter->netdev,
+			netif_set_xps_queue(ring->netdev,
 					    &q_vector->affinity_mask,
 					    ring->queue_index);
 	}
@@ -3395,7 +3401,7 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	int rss_i = adapter->ring_feature[RING_F_RSS].indices;
-	int p;
+	u16 pool;
 
 	/* PSRTYPE must be initialized in non 82598 adapters */
 	u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
@@ -3412,9 +3418,8 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
 	else if (rss_i > 1)
 		psrtype |= 1 << 29;
 
-	for (p = 0; p < adapter->num_rx_pools; p++)
-		IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(p)),
-				psrtype);
+	for_each_set_bit(pool, &adapter->fwd_bitmask, 32)
+		IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype);
 }
 
 static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
@@ -3683,7 +3688,11 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
-			j = adapter->rx_ring[i]->reg_idx;
+			struct ixgbe_ring *ring = adapter->rx_ring[i];
+
+			if (ring->l2_accel_priv)
+				continue;
+			j = ring->reg_idx;
 			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
 			vlnctrl &= ~IXGBE_RXDCTL_VME;
 			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
@@ -3713,7 +3722,11 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
 		for (i = 0; i < adapter->num_rx_queues; i++) {
-			j = adapter->rx_ring[i]->reg_idx;
+			struct ixgbe_ring *ring = adapter->rx_ring[i];
+
+			if (ring->l2_accel_priv)
+				continue;
+			j = ring->reg_idx;
 			vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
 			vlnctrl |= IXGBE_RXDCTL_VME;
 			IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
@@ -3750,7 +3763,7 @@ static int ixgbe_write_uc_addr_list(struct net_device *netdev)
 	unsigned int rar_entries = hw->mac.num_rar_entries - 1;
 	int count = 0;
 
-	/* In SR-IOV mode significantly less RAR entries are available */
+	/* In SR-IOV/VMDQ modes significantly less RAR entries are available */
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
 		rar_entries = IXGBE_MAX_PF_MACVLANS - 1;
 
@@ -3825,14 +3838,6 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 		if (netdev->flags & IFF_ALLMULTI) {
 			fctrl |= IXGBE_FCTRL_MPE;
 			vmolr |= IXGBE_VMOLR_MPE;
-		} else {
-			/*
-			 * Write addresses to the MTA, if the attempt fails
-			 * then we should just turn on promiscuous mode so
-			 * that we can at least receive multicast traffic
-			 */
-			hw->mac.ops.update_mc_addr_list(hw, netdev);
-			vmolr |= IXGBE_VMOLR_ROMPE;
 		}
 		ixgbe_vlan_filter_enable(adapter);
 		hw->addr_ctrl.user_set_promisc = false;
@@ -3849,6 +3854,13 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 		vmolr |= IXGBE_VMOLR_ROPE;
 	}
 
+	/* Write addresses to the MTA, if the attempt fails
+	 * then we should just turn on promiscuous mode so
+	 * that we can at least receive multicast traffic
+	 */
+	hw->mac.ops.update_mc_addr_list(hw, netdev);
+	vmolr |= IXGBE_VMOLR_ROMPE;
+
 	if (adapter->num_vfs)
 		ixgbe_restore_vf_multicasts(adapter);
 
@@ -3893,15 +3905,13 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
 {
 	int q_idx;
 
-	local_bh_disable(); /* for ixgbe_qv_lock_napi() */
 	for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) {
 		napi_disable(&adapter->q_vector[q_idx]->napi);
-		while (!ixgbe_qv_lock_napi(adapter->q_vector[q_idx])) {
+		while (!ixgbe_qv_disable(adapter->q_vector[q_idx])) {
 			pr_info("QV %d locked\n", q_idx);
-			mdelay(1);
+			usleep_range(1000, 20000);
 		}
 	}
-	local_bh_enable();
 }
 
 #ifdef CONFIG_IXGBE_DCB
@@ -4118,6 +4128,228 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
 	spin_unlock(&adapter->fdir_perfect_lock);
 }
 
+static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool,
+				      struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 vmolr;
+
+	/* No unicast promiscuous support for VMDQ devices. */
+	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool));
+	vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE);
+
+	/* clear the affected bit */
+	vmolr &= ~IXGBE_VMOLR_MPE;
+
+	if (dev->flags & IFF_ALLMULTI) {
+		vmolr |= IXGBE_VMOLR_MPE;
+	} else {
+		vmolr |= IXGBE_VMOLR_ROMPE;
+		hw->mac.ops.update_mc_addr_list(hw, dev);
+	}
+	ixgbe_write_uc_addr_list(adapter->netdev);
+	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr);
+}
+
+static void ixgbe_add_mac_filter(struct ixgbe_adapter *adapter,
+				 u8 *addr, u16 pool)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	unsigned int entry;
+
+	entry = hw->mac.num_rar_entries - pool;
+	hw->mac.ops.set_rar(hw, entry, addr, VMDQ_P(pool), IXGBE_RAH_AV);
+}
+
+static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter)
+{
+	struct ixgbe_adapter *adapter = vadapter->real_adapter;
+	int rss_i = adapter->num_rx_queues_per_pool;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u16 pool = vadapter->pool;
+	u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
+		      IXGBE_PSRTYPE_UDPHDR |
+		      IXGBE_PSRTYPE_IPV4HDR |
+		      IXGBE_PSRTYPE_L2HDR |
+		      IXGBE_PSRTYPE_IPV6HDR;
+
+	if (hw->mac.type == ixgbe_mac_82598EB)
+		return;
+
+	if (rss_i > 3)
+		psrtype |= 2 << 29;
+	else if (rss_i > 1)
+		psrtype |= 1 << 29;
+
+	IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype);
+}
+
+/**
+ * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
+ * @rx_ring: ring to free buffers from
+ **/
+static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
+{
+	struct device *dev = rx_ring->dev;
+	unsigned long size;
+	u16 i;
+
+	/* ring already cleared, nothing to do */
+	if (!rx_ring->rx_buffer_info)
+		return;
+
+	/* Free all the Rx ring sk_buffs */
+	for (i = 0; i < rx_ring->count; i++) {
+		struct ixgbe_rx_buffer *rx_buffer;
+
+		rx_buffer = &rx_ring->rx_buffer_info[i];
+		if (rx_buffer->skb) {
+			struct sk_buff *skb = rx_buffer->skb;
+			if (IXGBE_CB(skb)->page_released) {
+				dma_unmap_page(dev,
+					       IXGBE_CB(skb)->dma,
+					       ixgbe_rx_bufsz(rx_ring),
+					       DMA_FROM_DEVICE);
+				IXGBE_CB(skb)->page_released = false;
+			}
+			dev_kfree_skb(skb);
+		}
+		rx_buffer->skb = NULL;
+		if (rx_buffer->dma)
+			dma_unmap_page(dev, rx_buffer->dma,
+				       ixgbe_rx_pg_size(rx_ring),
+				       DMA_FROM_DEVICE);
+		rx_buffer->dma = 0;
+		if (rx_buffer->page)
+			__free_pages(rx_buffer->page,
+				     ixgbe_rx_pg_order(rx_ring));
+		rx_buffer->page = NULL;
+	}
+
+	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
+	memset(rx_ring->rx_buffer_info, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(rx_ring->desc, 0, rx_ring->size);
+
+	rx_ring->next_to_alloc = 0;
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+}
+
+static void ixgbe_disable_fwd_ring(struct ixgbe_fwd_adapter *vadapter,
+				   struct ixgbe_ring *rx_ring)
+{
+	struct ixgbe_adapter *adapter = vadapter->real_adapter;
+	int index = rx_ring->queue_index + vadapter->rx_base_queue;
+
+	/* shutdown specific queue receive and wait for dma to settle */
+	ixgbe_disable_rx_queue(adapter, rx_ring);
+	usleep_range(10000, 20000);
+	ixgbe_irq_disable_queues(adapter, ((u64)1 << index));
+	ixgbe_clean_rx_ring(rx_ring);
+	rx_ring->l2_accel_priv = NULL;
+}
+
+int ixgbe_fwd_ring_down(struct net_device *vdev,
+			struct ixgbe_fwd_adapter *accel)
+{
+	struct ixgbe_adapter *adapter = accel->real_adapter;
+	unsigned int rxbase = accel->rx_base_queue;
+	unsigned int txbase = accel->tx_base_queue;
+	int i;
+
+	netif_tx_stop_all_queues(vdev);
+
+	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
+		ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]);
+		adapter->rx_ring[rxbase + i]->netdev = adapter->netdev;
+	}
+
+	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
+		adapter->tx_ring[txbase + i]->l2_accel_priv = NULL;
+		adapter->tx_ring[txbase + i]->netdev = adapter->netdev;
+	}
+
+
+	return 0;
+}
+
+static int ixgbe_fwd_ring_up(struct net_device *vdev,
+			     struct ixgbe_fwd_adapter *accel)
+{
+	struct ixgbe_adapter *adapter = accel->real_adapter;
+	unsigned int rxbase, txbase, queues;
+	int i, baseq, err = 0;
+
+	if (!test_bit(accel->pool, &adapter->fwd_bitmask))
+		return 0;
+
+	baseq = accel->pool * adapter->num_rx_queues_per_pool;
+	netdev_dbg(vdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n",
+		   accel->pool, adapter->num_rx_pools,
+		   baseq, baseq + adapter->num_rx_queues_per_pool,
+		   adapter->fwd_bitmask);
+
+	accel->netdev = vdev;
+	accel->rx_base_queue = rxbase = baseq;
+	accel->tx_base_queue = txbase = baseq;
+
+	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
+		ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]);
+
+	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
+		adapter->rx_ring[rxbase + i]->netdev = vdev;
+		adapter->rx_ring[rxbase + i]->l2_accel_priv = accel;
+		ixgbe_configure_rx_ring(adapter, adapter->rx_ring[rxbase + i]);
+	}
+
+	for (i = 0; i < adapter->num_rx_queues_per_pool; i++) {
+		adapter->tx_ring[txbase + i]->netdev = vdev;
+		adapter->tx_ring[txbase + i]->l2_accel_priv = accel;
+	}
+
+	queues = min_t(unsigned int,
+		       adapter->num_rx_queues_per_pool, vdev->num_tx_queues);
+	err = netif_set_real_num_tx_queues(vdev, queues);
+	if (err)
+		goto fwd_queue_err;
+
+	err = netif_set_real_num_rx_queues(vdev, queues);
+	if (err)
+		goto fwd_queue_err;
+
+	if (is_valid_ether_addr(vdev->dev_addr))
+		ixgbe_add_mac_filter(adapter, vdev->dev_addr, accel->pool);
+
+	ixgbe_fwd_psrtype(accel);
+	ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter);
+	return err;
+fwd_queue_err:
+	ixgbe_fwd_ring_down(vdev, accel);
+	return err;
+}
+
+static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
+{
+	struct net_device *upper;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
+		if (netif_is_macvlan(upper)) {
+			struct macvlan_dev *dfwd = netdev_priv(upper);
+			struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+
+			if (dfwd->fwd_priv) {
+				err = ixgbe_fwd_ring_up(upper, vadapter);
+				if (err)
+					continue;
+			}
+		}
+	}
+}
+
 static void ixgbe_configure(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -4169,6 +4401,7 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 #endif /* IXGBE_FCOE */
 	ixgbe_configure_tx(adapter);
 	ixgbe_configure_rx(adapter);
+	ixgbe_configure_dfwd(adapter);
 }
 
 static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
@@ -4322,6 +4555,8 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
 static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *upper;
+	struct list_head *iter;
 	int err;
 	u32 ctrl_ext;
 
@@ -4365,6 +4600,16 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
 	/* enable transmits */
 	netif_tx_start_all_queues(adapter->netdev);
 
+	/* enable any upper devices */
+	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
+		if (netif_is_macvlan(upper)) {
+			struct macvlan_dev *vlan = netdev_priv(upper);
+
+			if (vlan->fwd_priv)
+				netif_tx_start_all_queues(upper);
+		}
+	}
+
 	/* bring the link up in the watchdog, this could race with our first
 	 * link up interrupt but shouldn't be a problem */
 	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
@@ -4456,59 +4701,6 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 }
 
 /**
- * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
- * @rx_ring: ring to free buffers from
- **/
-static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
-{
-	struct device *dev = rx_ring->dev;
-	unsigned long size;
-	u16 i;
-
-	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_buffer_info)
-		return;
-
-	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct ixgbe_rx_buffer *rx_buffer;
-
-		rx_buffer = &rx_ring->rx_buffer_info[i];
-		if (rx_buffer->skb) {
-			struct sk_buff *skb = rx_buffer->skb;
-			if (IXGBE_CB(skb)->page_released) {
-				dma_unmap_page(dev,
-					       IXGBE_CB(skb)->dma,
-					       ixgbe_rx_bufsz(rx_ring),
-					       DMA_FROM_DEVICE);
-				IXGBE_CB(skb)->page_released = false;
-			}
-			dev_kfree_skb(skb);
-		}
-		rx_buffer->skb = NULL;
-		if (rx_buffer->dma)
-			dma_unmap_page(dev, rx_buffer->dma,
-				       ixgbe_rx_pg_size(rx_ring),
-				       DMA_FROM_DEVICE);
-		rx_buffer->dma = 0;
-		if (rx_buffer->page)
-			__free_pages(rx_buffer->page,
-				     ixgbe_rx_pg_order(rx_ring));
-		rx_buffer->page = NULL;
-	}
-
-	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_buffer_info, 0, size);
-
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
-	rx_ring->next_to_alloc = 0;
-	rx_ring->next_to_clean = 0;
-	rx_ring->next_to_use = 0;
-}
-
-/**
  * ixgbe_clean_tx_ring - Free Tx Buffers
  * @tx_ring: ring to be cleaned
  **/
@@ -4585,6 +4777,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *upper;
+	struct list_head *iter;
 	u32 rxctrl;
 	int i;
 
@@ -4608,6 +4802,19 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	netif_carrier_off(netdev);
 	netif_tx_disable(netdev);
 
+	/* disable any upper devices */
+	netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
+		if (netif_is_macvlan(upper)) {
+			struct macvlan_dev *vlan = netdev_priv(upper);
+
+			if (vlan->fwd_priv) {
+				netif_tx_stop_all_queues(upper);
+				netif_carrier_off(upper);
+				netif_tx_disable(upper);
+			}
+		}
+	}
+
 	ixgbe_irq_disable(adapter);
 
 	ixgbe_napi_disable_all(adapter);
@@ -4816,11 +5023,20 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 	hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw);
 
 #ifdef CONFIG_PCI_IOV
+	if (max_vfs > 0)
+		e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n");
+
 	/* assign number of SR-IOV VFs */
-	if (hw->mac.type != ixgbe_mac_82598EB)
-		adapter->num_vfs = (max_vfs > 63) ? 0 : max_vfs;
+	if (hw->mac.type != ixgbe_mac_82598EB) {
+		if (max_vfs > 63) {
+			adapter->num_vfs = 0;
+			e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n");
+		} else {
+			adapter->num_vfs = max_vfs;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
 
-#endif
 	/* enable itr by default in dynamic mode */
 	adapter->rx_itr_setting = 1;
 	adapter->tx_itr_setting = 1;
@@ -4838,6 +5054,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 		return -EIO;
 	}
 
+	/* PF holds first pool slot */
+	set_bit(0, &adapter->fwd_bitmask);
 	set_bit(__IXGBE_DOWN, &adapter->state);
 
 	return 0;
@@ -5143,7 +5361,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 static int ixgbe_open(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	int err;
+	int err, queues;
 
 	/* disallow open during test */
 	if (test_bit(__IXGBE_TESTING, &adapter->state))
@@ -5168,16 +5386,21 @@ static int ixgbe_open(struct net_device *netdev)
 		goto err_req_irq;
 
 	/* Notify the stack of the actual queue counts. */
-	err = netif_set_real_num_tx_queues(netdev,
-					   adapter->num_rx_pools > 1 ? 1 :
-					   adapter->num_tx_queues);
+	if (adapter->num_rx_pools > 1)
+		queues = adapter->num_rx_queues_per_pool;
+	else
+		queues = adapter->num_tx_queues;
+
+	err = netif_set_real_num_tx_queues(netdev, queues);
 	if (err)
 		goto err_set_queues;
 
-
-	err = netif_set_real_num_rx_queues(netdev,
-					   adapter->num_rx_pools > 1 ? 1 :
-					   adapter->num_rx_queues);
+	if (adapter->num_rx_pools > 1 &&
+	    adapter->num_rx_queues > IXGBE_MAX_L2A_QUEUES)
+		queues = IXGBE_MAX_L2A_QUEUES;
+	else
+		queues = adapter->num_rx_queues;
+	err = netif_set_real_num_rx_queues(netdev, queues);
 	if (err)
 		goto err_set_queues;
 
@@ -6767,8 +6990,9 @@ out_drop:
 	return NETDEV_TX_OK;
 }
 
-static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
-				    struct net_device *netdev)
+static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb,
+				      struct net_device *netdev,
+				      struct ixgbe_ring *ring)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_ring *tx_ring;
@@ -6784,10 +7008,17 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
 		skb_set_tail_pointer(skb, 17);
 	}
 
-	tx_ring = adapter->tx_ring[skb->queue_mapping];
+	tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping];
+
 	return ixgbe_xmit_frame_ring(skb, adapter, tx_ring);
 }
 
+static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
+				    struct net_device *netdev)
+{
+	return __ixgbe_xmit_frame(skb, netdev, NULL);
+}
+
 /**
  * ixgbe_set_mac - Change the Ethernet Address of the NIC
  * @netdev: network interface device structure
@@ -7044,6 +7275,7 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	bool pools;
 
 	/* Hardware supports up to 8 traffic classes */
 	if (tc > adapter->dcb_cfg.num_tcs.pg_tcs ||
@@ -7051,6 +7283,10 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 	     tc < MAX_TRAFFIC_CLASS))
 		return -EINVAL;
 
+	pools = (find_first_zero_bit(&adapter->fwd_bitmask, 32) > 1);
+	if (tc && pools && adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS)
+		return -EBUSY;
+
 	/* Hardware has to reinitialize queues and interrupts to
 	 * match packet buffer alignment. Unfortunately, the
 	 * hardware is not flexible enough to do this dynamically.
@@ -7305,6 +7541,104 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode);
 }
 
+static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
+{
+	struct ixgbe_fwd_adapter *fwd_adapter = NULL;
+	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	unsigned int limit;
+	int pool, err;
+
+#ifdef CONFIG_RPS
+	if (vdev->num_rx_queues != vdev->num_tx_queues) {
+		netdev_info(pdev, "%s: Only supports a single queue count for TX and RX\n",
+			    vdev->name);
+		return ERR_PTR(-EINVAL);
+	}
+#endif
+	/* Check for hardware restriction on number of rx/tx queues */
+	if (vdev->num_tx_queues > IXGBE_MAX_L2A_QUEUES ||
+	    vdev->num_tx_queues == IXGBE_BAD_L2A_QUEUE) {
+		netdev_info(pdev,
+			    "%s: Supports RX/TX Queue counts 1,2, and 4\n",
+			    pdev->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
+	      adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS - 1) ||
+	    (adapter->num_rx_pools > IXGBE_MAX_MACVLANS))
+		return ERR_PTR(-EBUSY);
+
+	fwd_adapter = kcalloc(1, sizeof(struct ixgbe_fwd_adapter), GFP_KERNEL);
+	if (!fwd_adapter)
+		return ERR_PTR(-ENOMEM);
+
+	pool = find_first_zero_bit(&adapter->fwd_bitmask, 32);
+	adapter->num_rx_pools++;
+	set_bit(pool, &adapter->fwd_bitmask);
+	limit = find_last_bit(&adapter->fwd_bitmask, 32);
+
+	/* Enable VMDq flag so device will be set in VM mode */
+	adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED;
+	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
+	adapter->ring_feature[RING_F_RSS].limit = vdev->num_tx_queues;
+
+	/* Force reinit of ring allocation with VMDQ enabled */
+	err = ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev));
+	if (err)
+		goto fwd_add_err;
+	fwd_adapter->pool = pool;
+	fwd_adapter->real_adapter = adapter;
+	err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
+	if (err)
+		goto fwd_add_err;
+	netif_tx_start_all_queues(vdev);
+	return fwd_adapter;
+fwd_add_err:
+	/* unwind counter and free adapter struct */
+	netdev_info(pdev,
+		    "%s: dfwd hardware acceleration failed\n", vdev->name);
+	clear_bit(pool, &adapter->fwd_bitmask);
+	adapter->num_rx_pools--;
+	kfree(fwd_adapter);
+	return ERR_PTR(err);
+}
+
+static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
+{
+	struct ixgbe_fwd_adapter *fwd_adapter = priv;
+	struct ixgbe_adapter *adapter = fwd_adapter->real_adapter;
+	unsigned int limit;
+
+	clear_bit(fwd_adapter->pool, &adapter->fwd_bitmask);
+	adapter->num_rx_pools--;
+
+	limit = find_last_bit(&adapter->fwd_bitmask, 32);
+	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
+	ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter);
+	ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev));
+	netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n",
+		   fwd_adapter->pool, adapter->num_rx_pools,
+		   fwd_adapter->rx_base_queue,
+		   fwd_adapter->rx_base_queue + adapter->num_rx_queues_per_pool,
+		   adapter->fwd_bitmask);
+	kfree(fwd_adapter);
+}
+
+static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
+				  struct net_device *dev,
+				  void *priv)
+{
+	struct ixgbe_fwd_adapter *fwd_adapter = priv;
+	unsigned int queue;
+	struct ixgbe_ring *tx_ring;
+
+	queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
+	tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
+
+	return __ixgbe_xmit_frame(skb, dev, tx_ring);
+}
+
 static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
@@ -7349,6 +7683,9 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_fdb_add		= ixgbe_ndo_fdb_add,
 	.ndo_bridge_setlink	= ixgbe_ndo_bridge_setlink,
 	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
+	.ndo_dfwd_add_station	= ixgbe_fwd_add,
+	.ndo_dfwd_del_station	= ixgbe_fwd_del,
+	.ndo_dfwd_start_xmit	= ixgbe_fwd_xmit,
 };
 
 /**
@@ -7362,19 +7699,16 @@ static const struct net_device_ops ixgbe_netdev_ops = {
  **/
 static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
 	struct list_head *entry;
 	int physfns = 0;
 
-	/* Some cards can not use the generic count PCIe functions method, and
-	 * so must be hardcoded to the correct value.
+	/* Some cards can not use the generic count PCIe functions method,
+	 * because they are behind a parent switch, so we hardcode these with
+	 * the correct number of functions.
 	 */
-	switch (hw->device_id) {
-	case IXGBE_DEV_ID_82599_SFP_SF_QP:
-	case IXGBE_DEV_ID_82599_QSFP_SF_QP:
+	if (ixgbe_pcie_from_parent(&adapter->hw)) {
 		physfns = 4;
-		break;
-	default:
+	} else {
 		list_for_each(entry, &adapter->pdev->bus_list) {
 			struct pci_dev *pdev =
 				list_entry(entry, struct pci_dev, bus_list);
@@ -7653,7 +7987,8 @@ skip_sriov:
 			   NETIF_F_TSO |
 			   NETIF_F_TSO6 |
 			   NETIF_F_RXHASH |
-			   NETIF_F_RXCSUM;
+			   NETIF_F_RXCSUM |
+			   NETIF_F_HW_L2FW_DOFFLOAD;
 
 	netdev->hw_features = netdev->features;
 
@@ -7759,29 +8094,6 @@ skip_sriov:
 	if (ixgbe_pcie_from_parent(hw))
 		ixgbe_get_parent_bus_info(adapter);
 
-	/* print bus type/speed/width info */
-	e_dev_info("(PCI Express:%s:%s) %pM\n",
-		   (hw->bus.speed == ixgbe_bus_speed_8000 ? "8.0GT/s" :
-		    hw->bus.speed == ixgbe_bus_speed_5000 ? "5.0GT/s" :
-		    hw->bus.speed == ixgbe_bus_speed_2500 ? "2.5GT/s" :
-		    "Unknown"),
-		   (hw->bus.width == ixgbe_bus_width_pcie_x8 ? "Width x8" :
-		    hw->bus.width == ixgbe_bus_width_pcie_x4 ? "Width x4" :
-		    hw->bus.width == ixgbe_bus_width_pcie_x1 ? "Width x1" :
-		    "Unknown"),
-		   netdev->dev_addr);
-
-	err = ixgbe_read_pba_string_generic(hw, part_str, IXGBE_PBANUM_LENGTH);
-	if (err)
-		strncpy(part_str, "Unknown", IXGBE_PBANUM_LENGTH);
-	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
-		e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n",
-			   hw->mac.type, hw->phy.type, hw->phy.sfp_type,
-		           part_str);
-	else
-		e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n",
-			   hw->mac.type, hw->phy.type, part_str);
-
 	/* calculate the expected PCIe bandwidth required for optimal
 	 * performance. Note that some older parts will never have enough
 	 * bandwidth due to being older generation PCIe parts. We clamp these
@@ -7797,6 +8109,19 @@ skip_sriov:
 	}
 	ixgbe_check_minimum_link(adapter, expected_gts);
 
+	err = ixgbe_read_pba_string_generic(hw, part_str, IXGBE_PBANUM_LENGTH);
+	if (err)
+		strncpy(part_str, "Unknown", IXGBE_PBANUM_LENGTH);
+	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
+		e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n",
+			   hw->mac.type, hw->phy.type, hw->phy.sfp_type,
+		           part_str);
+	else
+		e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n",
+			   hw->mac.type, hw->phy.type, part_str);
+
+	e_dev_info("%pM\n", netdev->dev_addr);
+
 	/* reset the hardware with the new settings */
 	err = hw->mac.ops.start_hw(hw);
 	if (err == IXGBE_ERR_EEPROM_VERSION) {