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

Conflicts:
	drivers/net/xen-netfront.c

Minor overlapping changes in xen-netfront.c, mostly to do
with some buffer management changes alongside the split
of stats into TX and RX.

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

18 files changed, 173 insertions, 77 deletions

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e398eda07298..c8af3ce3ea38 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -184,15 +184,16 @@ static void alx_schedule_reset(struct alx_priv *alx)
 	schedule_work(&alx->reset_wk);
 }
 
-static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
+static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
 	struct alx_rrd *rrd;
 	struct alx_buffer *rxb;
 	struct sk_buff *skb;
 	u16 length, rfd_cleaned = 0;
+	int work = 0;
 
-	while (budget > 0) {
+	while (work < budget) {
 		rrd = &rxq->rrd[rxq->rrd_read_idx];
 		if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT)))
 			break;
@@ -203,7 +204,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		    ALX_GET_FIELD(le32_to_cpu(rrd->word0),
 				  RRD_NOR) != 1) {
 			alx_schedule_reset(alx);
-			return 0;
+			return work;
 		}
 
 		rxb = &rxq->bufs[rxq->read_idx];
@@ -243,7 +244,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		}
 
 		napi_gro_receive(&alx->napi, skb);
-		budget--;
+		work++;
 
 next_pkt:
 		if (++rxq->read_idx == alx->rx_ringsz)
@@ -258,21 +259,22 @@ next_pkt:
 	if (rfd_cleaned)
 		alx_refill_rx_ring(alx, GFP_ATOMIC);
 
-	return budget > 0;
+	return work;
 }
 
 static int alx_poll(struct napi_struct *napi, int budget)
 {
 	struct alx_priv *alx = container_of(napi, struct alx_priv, napi);
 	struct alx_hw *hw = &alx->hw;
-	bool complete = true;
 	unsigned long flags;
+	bool tx_complete;
+	int work;
 
-	complete = alx_clean_tx_irq(alx) &&
-		   alx_clean_rx_irq(alx, budget);
+	tx_complete = alx_clean_tx_irq(alx);
+	work = alx_clean_rx_irq(alx, budget);
 
-	if (!complete)
-		return 1;
+	if (!tx_complete || work == budget)
+		return budget;
 
 	napi_complete(&alx->napi);
 
@@ -284,7 +286,7 @@ static int alx_poll(struct napi_struct *napi, int budget)
 
 	alx_post_write(hw);
 
-	return 0;
+	return work;
 }
 
 static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 4cf43bfbc955..615a6dbde047 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7413,6 +7413,8 @@ static inline void tg3_netif_start(struct tg3 *tp)
 }
 
 static void tg3_irq_quiesce(struct tg3 *tp)
+	__releases(tp->lock)
+	__acquires(tp->lock)
 {
 	int i;
 
@@ -7421,8 +7423,12 @@ static void tg3_irq_quiesce(struct tg3 *tp)
 	tp->irq_sync = 1;
 	smp_mb();
 
+	spin_unlock_bh(&tp->lock);
+
 	for (i = 0; i < tp->irq_cnt; i++)
 		synchronize_irq(tp->napi[i].irq_vec);
+
+	spin_lock_bh(&tp->lock);
 }
 
 /* Fully shutdown all tg3 driver activity elsewhere in the system.
@@ -9018,6 +9024,8 @@ static void tg3_restore_clk(struct tg3 *tp)
 
 /* tp->lock is held. */
 static int tg3_chip_reset(struct tg3 *tp)
+	__releases(tp->lock)
+	__acquires(tp->lock)
 {
 	u32 val;
 	void (*write_op)(struct tg3 *, u32, u32);
@@ -9073,9 +9081,13 @@ static int tg3_chip_reset(struct tg3 *tp)
 	}
 	smp_mb();
 
+	tg3_full_unlock(tp);
+
 	for (i = 0; i < tp->irq_cnt; i++)
 		synchronize_irq(tp->napi[i].irq_vec);
 
+	tg3_full_lock(tp, 0);
+
 	if (tg3_asic_rev(tp) == ASIC_REV_57780) {
 		val = tr32(TG3_PCIE_LNKCTL) & ~TG3_PCIE_LNKCTL_L1_PLL_PD_EN;
 		tw32(TG3_PCIE_LNKCTL, val | TG3_PCIE_LNKCTL_L1_PLL_PD_DIS);
@@ -10903,11 +10915,13 @@ static void tg3_timer(unsigned long __opaque)
 {
 	struct tg3 *tp = (struct tg3 *) __opaque;
 
-	if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING))
-		goto restart_timer;
-
 	spin_lock(&tp->lock);
 
+	if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING)) {
+		spin_unlock(&tp->lock);
+		goto restart_timer;
+	}
+
 	if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
 	    tg3_flag(tp, 57765_CLASS))
 		tg3_chk_missed_msi(tp);
@@ -11101,11 +11115,13 @@ static void tg3_reset_task(struct work_struct *work)
 	struct tg3 *tp = container_of(work, struct tg3, reset_task);
 	int err;
 
+	rtnl_lock();
 	tg3_full_lock(tp, 0);
 
 	if (!netif_running(tp->dev)) {
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
 		tg3_full_unlock(tp);
+		rtnl_unlock();
 		return;
 	}
 
@@ -11138,6 +11154,7 @@ out:
 		tg3_phy_start(tp);
 
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
+	rtnl_unlock();
 }
 
 static int tg3_request_irq(struct tg3 *tp, int irq_num)
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 55eb7f2af2b4..7ef55f5fa664 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -340,7 +340,7 @@ static int __init at91ether_probe(struct platform_device *pdev)
 		res = PTR_ERR(lp->pclk);
 		goto err_free_dev;
 	}
-	clk_enable(lp->pclk);
+	clk_prepare_enable(lp->pclk);
 
 	lp->hclk = ERR_PTR(-ENOENT);
 	lp->tx_clk = ERR_PTR(-ENOENT);
@@ -406,7 +406,7 @@ static int __init at91ether_probe(struct platform_device *pdev)
 err_out_unregister_netdev:
 	unregister_netdev(dev);
 err_disable_clock:
-	clk_disable(lp->pclk);
+	clk_disable_unprepare(lp->pclk);
 err_free_dev:
 	free_netdev(dev);
 	return res;
@@ -424,7 +424,7 @@ static int at91ether_remove(struct platform_device *pdev)
 	kfree(lp->mii_bus->irq);
 	mdiobus_free(lp->mii_bus);
 	unregister_netdev(dev);
-	clk_disable(lp->pclk);
+	clk_disable_unprepare(lp->pclk);
 	free_netdev(dev);
 
 	return 0;
@@ -440,7 +440,7 @@ static int at91ether_suspend(struct platform_device *pdev, pm_message_t mesg)
 		netif_stop_queue(net_dev);
 		netif_device_detach(net_dev);
 
-		clk_disable(lp->pclk);
+		clk_disable_unprepare(lp->pclk);
 	}
 	return 0;
 }
@@ -451,7 +451,7 @@ static int at91ether_resume(struct platform_device *pdev)
 	struct macb *lp = netdev_priv(net_dev);
 
 	if (netif_running(net_dev)) {
-		clk_enable(lp->pclk);
+		clk_prepare_enable(lp->pclk);
 
 		netif_device_attach(net_dev);
 		netif_start_queue(net_dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 710e5e2bac9f..122e2964e63b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2426,7 +2426,7 @@ static void cfg_queues(struct adapter *adapter)
 	 */
 	n10g = 0;
 	for_each_port(adapter, pidx)
-		n10g += is_10g_port(&adap2pinfo(adapter, pidx)->link_cfg);
+		n10g += is_x_10g_port(&adap2pinfo(adapter, pidx)->link_cfg);
 
 	/*
 	 * We default to 1 queue per non-10G port and up to # of cores queues
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index fcc610813856..1b5506df35b1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -324,6 +324,8 @@ int t4vf_port_init(struct adapter *adapter, int pidx)
 		return v;
 
 	v = be32_to_cpu(port_rpl.u.info.lstatus_to_modtype);
+	pi->mdio_addr = (v & FW_PORT_CMD_MDIOCAP_F) ?
+			FW_PORT_CMD_MDIOADDR_G(v) : -1;
 	pi->port_type = FW_PORT_CMD_PTYPE_G(v);
 	pi->mod_type = FW_PORT_MOD_TYPE_NA;
 
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index a379c3e4b57f..13d00a38a5bd 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -398,13 +398,8 @@ static int dnet_poll(struct napi_struct *napi, int budget)
 		 * break out of while loop if there are no more
 		 * packets waiting
 		 */
-		if (!(dnet_readl(bp, RX_FIFO_WCNT) >> 16)) {
-			napi_complete(napi);
-			int_enable = dnet_readl(bp, INTR_ENB);
-			int_enable |= DNET_INTR_SRC_RX_CMDFIFOAF;
-			dnet_writel(bp, int_enable, INTR_ENB);
-			return 0;
-		}
+		if (!(dnet_readl(bp, RX_FIFO_WCNT) >> 16))
+			break;
 
 		cmd_word = dnet_readl(bp, RX_LEN_FIFO);
 		pkt_len = cmd_word & 0xFFFF;
@@ -433,20 +428,17 @@ static int dnet_poll(struct napi_struct *napi, int budget)
 			       "size %u.\n", dev->name, pkt_len);
 	}
 
-	budget -= npackets;
-
 	if (npackets < budget) {
 		/* We processed all packets available.  Tell NAPI it can
-		 * stop polling then re-enable rx interrupts */
+		 * stop polling then re-enable rx interrupts.
+		 */
 		napi_complete(napi);
 		int_enable = dnet_readl(bp, INTR_ENB);
 		int_enable |= DNET_INTR_SRC_RX_CMDFIFOAF;
 		dnet_writel(bp, int_enable, INTR_ENB);
-		return 0;
 	}
 
-	/* There are still packets waiting */
-	return 1;
+	return npackets;
 }
 
 static irqreturn_t dnet_interrupt(int irq, void *dev_id)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index d77a96fdf1dd..a86af8a7485d 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -426,6 +426,8 @@ struct bufdesc_ex {
  * (40ns * 6).
  */
 #define FEC_QUIRK_BUG_CAPTURE		(1 << 10)
+/* Controller has only one MDIO bus */
+#define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
 
 struct fec_enet_priv_tx_q {
 	int index;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 49cd358c30fa..1c7a7e43dd9c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -91,7 +91,8 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx28-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME,
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
+				FEC_QUIRK_SINGLE_MDIO,
 	}, {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
@@ -1956,7 +1957,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	int err = -ENXIO, i;
 
 	/*
-	 * The dual fec interfaces are not equivalent with enet-mac.
+	 * The i.MX28 dual fec interfaces are not equal.
 	 * Here are the differences:
 	 *
 	 *  - fec0 supports MII & RMII modes while fec1 only supports RMII
@@ -1971,7 +1972,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	 * mdio interface in board design, and need to be configured by
 	 * fec0 mii_bus.
 	 */
-	if ((fep->quirks & FEC_QUIRK_ENET_MAC) && fep->dev_id > 0) {
+	if ((fep->quirks & FEC_QUIRK_SINGLE_MDIO) && fep->dev_id > 0) {
 		/* fec1 uses fec0 mii_bus */
 		if (mii_cnt && fec0_mii_bus) {
 			fep->mii_bus = fec0_mii_bus;
@@ -2034,7 +2035,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	mii_cnt++;
 
 	/* save fec0 mii_bus */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC)
+	if (fep->quirks & FEC_QUIRK_SINGLE_MDIO)
 		fec0_mii_bus = fep->mii_bus;
 
 	return 0;
@@ -3191,6 +3192,7 @@ fec_probe(struct platform_device *pdev)
 		pdev->id_entry = of_id->data;
 	fep->quirks = pdev->id_entry->driver_data;
 
+	fep->netdev = ndev;
 	fep->num_rx_queues = num_rx_qs;
 	fep->num_tx_queues = num_tx_qs;
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 5b8300a32bf5..4d61ef50b465 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -281,6 +281,17 @@ config I40E_DCB
 
 	  If unsure, say N.
 
+config I40E_FCOE
+	bool "Fibre Channel over Ethernet (FCoE)"
+	default n
+	depends on I40E && DCB && FCOE
+	---help---
+	  Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
+	  in the driver. This will create new netdev for exclusive FCoE
+	  use with XL710 FCoE offloads enabled.
+
+	  If unsure, say N.
+
 config I40EVF
 	tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
 	depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 4b94ddb29c24..c40581999121 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -44,4 +44,4 @@ i40e-objs := i40e_main.o \
 	i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_FCOE:m=y) += i40e_fcoe.o
+i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index 045b5c4b98b3..ad802dd0f67a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,7 @@ do {                                                            \
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#ifdef CONFIG_I40E_FCOE
 #define I40E_FCOE
-#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */
+#endif
 #endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9f536dd8e1ec..bb86390a0967 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -658,6 +658,8 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
 	return le32_to_cpu(*(volatile __le32 *)head);
 }
 
+#define WB_STRIDE 0x3
+
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
  * @tx_ring:  tx ring to clean
@@ -759,6 +761,18 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
+	/* check to see if there are any non-cache aligned descriptors
+	 * waiting to be written back, and kick the hardware to force
+	 * them to be written back in case of napi polling
+	 */
+	if (budget &&
+	    !((i & WB_STRIDE) == WB_STRIDE) &&
+	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+		tx_ring->arm_wb = true;
+	else
+		tx_ring->arm_wb = false;
+
 	if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -777,13 +791,16 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
 		dev_info(tx_ring->dev,
-			 "tx hang detected on queue %d, resetting adapter\n",
+			 "tx hang detected on queue %d, reset requested\n",
 			 tx_ring->queue_index);
 
-		tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev);
+		/* do not fire the reset immediately, wait for the stack to
+		 * decide we are truly stuck, also prevents every queue from
+		 * simultaneously requesting a reset
+		 */
 
-		/* the adapter is about to reset, no point in enabling stuff */
-		return true;
+		/* the adapter is about to reset, no point in enabling polling */
+		budget = 1;
 	}
 
 	netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
@@ -806,7 +823,25 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		}
 	}
 
-	return budget > 0;
+	return !!budget;
+}
+
+/**
+ * i40e_force_wb - Arm hardware to do a wb on noncache aligned descriptors
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+	u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
+		  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+		  I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK
+		  /* allow 00 to be written to the index */;
+
+	wr32(&vsi->back->hw,
+	     I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1),
+	     val);
 }
 
 /**
@@ -1290,9 +1325,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	 * so the total length of IPv4 header is IHL*4 bytes
 	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
 	 */
-	if (ipv4_tunnel &&
-	    (decoded.inner_prot != I40E_RX_PTYPE_INNER_PROT_UDP) &&
-	    !(rx_status & (1 << I40E_RX_DESC_STATUS_UDP_0_SHIFT))) {
+	if (ipv4_tunnel) {
 		skb->transport_header = skb->mac_header +
 					sizeof(struct ethhdr) +
 					(ip_hdr(skb)->ihl * 4);
@@ -1302,15 +1335,19 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 					  skb->protocol == htons(ETH_P_8021AD))
 					  ? VLAN_HLEN : 0;
 
-		rx_udp_csum = udp_csum(skb);
-		iph = ip_hdr(skb);
-		csum = csum_tcpudp_magic(
-				iph->saddr, iph->daddr,
-				(skb->len - skb_transport_offset(skb)),
-				IPPROTO_UDP, rx_udp_csum);
+		if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
+		    (udp_hdr(skb)->check != 0)) {
+			rx_udp_csum = udp_csum(skb);
+			iph = ip_hdr(skb);
+			csum = csum_tcpudp_magic(
+					iph->saddr, iph->daddr,
+					(skb->len - skb_transport_offset(skb)),
+					IPPROTO_UDP, rx_udp_csum);
 
-		if (udp_hdr(skb)->check != csum)
-			goto checksum_fail;
+			if (udp_hdr(skb)->check != csum)
+				goto checksum_fail;
+
+		} /* else its GRE and so no outer UDP header */
 	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1581,6 +1618,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	struct i40e_vsi *vsi = q_vector->vsi;
 	struct i40e_ring *ring;
 	bool clean_complete = true;
+	bool arm_wb = false;
 	int budget_per_ring;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
@@ -1591,8 +1629,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
-	i40e_for_each_ring(ring, q_vector->tx)
+	i40e_for_each_ring(ring, q_vector->tx) {
 		clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+		arm_wb |= ring->arm_wb;
+	}
 
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
@@ -1603,8 +1643,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 		clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		if (arm_wb)
+			i40e_force_wb(vsi, q_vector);
 		return budget;
+	}
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete(napi);
@@ -1840,17 +1883,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (protocol == htons(ETH_P_IP)) {
-		iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+
+	if (iph->version == 4) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
 		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
 						 0, IPPROTO_TCP, 0);
-	} else if (skb_is_gso_v6(skb)) {
-
-		ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb)
-					   : ipv6_hdr(skb);
+	} else if (ipv6h->version == 6) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		ipv6h->payload_len = 0;
 		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
@@ -1946,13 +1988,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			if (tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -1962,7 +2000,10 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-
+		if (this_ip_hdr->version == 6) {
+			tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			tx_flags |= I40E_TX_FLAGS_IPV6;
+		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
 		this_ip_hdr = ip_hdr(skb);
@@ -2198,7 +2239,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* Place RS bit on last descriptor of any packet that spans across the
 	 * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
 	 */
-#define WB_STRIDE 0x3
 	if (((i & WB_STRIDE) != WB_STRIDE) &&
 	    (first <= &tx_ring->tx_bi[i]) &&
 	    (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index e60d3accb2e2..18b00231d2f1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -241,6 +241,7 @@ struct i40e_ring {
 	unsigned long last_rx_timestamp;
 
 	bool ring_active;		/* is ring online or not */
+	bool arm_wb;		/* do something to arm write back */
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index c29ba80ae02b..37583a9d8853 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -473,6 +473,7 @@ static struct sh_eth_cpu_data r8a777x_data = {
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
+	.fdr_value	= 0x00000f0f,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -495,6 +496,7 @@ static struct sh_eth_cpu_data r8a779x_data = {
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
+	.fdr_value	= 0x00000f0f,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -536,6 +538,8 @@ static struct sh_eth_cpu_data sh7724_data = {
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
 
+	.trscer_err_mask = DESC_I_RINT8,
+
 	.apr		= 1,
 	.mpr		= 1,
 	.tpauser	= 1,
@@ -856,6 +860,9 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd)
 
 	if (!cd->eesr_err_check)
 		cd->eesr_err_check = DEFAULT_EESR_ERR_CHECK;
+
+	if (!cd->trscer_err_mask)
+		cd->trscer_err_mask = DEFAULT_TRSCER_ERR_MASK;
 }
 
 static int sh_eth_check_reset(struct net_device *ndev)
@@ -1294,7 +1301,7 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 	/* Frame recv control (enable multiple-packets per rx irq) */
 	sh_eth_write(ndev, RMCR_RNC, RMCR);
 
-	sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);
+	sh_eth_write(ndev, mdp->cd->trscer_err_mask, TRSCER);
 
 	if (mdp->cd->bculr)
 		sh_eth_write(ndev, 0x800, BCULR);	/* Burst sycle set */
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 22301bf9c21d..71f5de1171bd 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -369,6 +369,8 @@ enum DESC_I_BIT {
 	DESC_I_RINT1 = 0x0001,
 };
 
+#define DEFAULT_TRSCER_ERR_MASK (DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2)
+
 /* RPADIR */
 enum RPADIR_BIT {
 	RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000,
@@ -470,6 +472,9 @@ struct sh_eth_cpu_data {
 	unsigned long tx_check;
 	unsigned long eesr_err_check;
 
+	/* Error mask */
+	unsigned long trscer_err_mask;
+
 	/* hardware features */
 	unsigned long irq_flags; /* IRQ configuration flags */
 	unsigned no_psr:1;	/* EtherC DO NOT have PSR */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e61ee8351272..64d1cef4cda1 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -610,7 +610,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 
 			/* Clear all mcast from ALE */
 			cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS <<
-						 priv->host_port);
+						 priv->host_port, -1);
 
 			/* Flood All Unicast Packets to Host port */
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1);
@@ -634,6 +634,12 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	int vid;
+
+	if (priv->data.dual_emac)
+		vid = priv->slaves[priv->emac_port].port_vlan;
+	else
+		vid = priv->data.default_vlan;
 
 	if (ndev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
@@ -649,7 +655,8 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(priv->ale, priv->ndev->flags & IFF_ALLMULTI);
 
 	/* Clear all mcast from ALE */
-	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port);
+	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port,
+				 vid);
 
 	if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 097ebe7077ac..5246b3a18ff8 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -234,7 +234,7 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
 	int ret, idx;
@@ -245,6 +245,14 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
 		if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR)
 			continue;
 
+		/* if vid passed is -1 then remove all multicast entry from
+		 * the table irrespective of vlan id, if a valid vlan id is
+		 * passed then remove only multicast added to that vlan id.
+		 * if vlan id doesn't match then move on to next entry.
+		 */
+		if (vid != -1 && cpsw_ale_get_vlan_id(ale_entry) != vid)
+			continue;
+
 		if (cpsw_ale_get_mcast(ale_entry)) {
 			u8 addr[6];
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index c0d4127aa549..af1e7ecd87c6 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -92,7 +92,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale);
 
 int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout);
 int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask);
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask);
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid);
 int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port,
 		       int flags, u16 vid);
 int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port,