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

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

26 files changed, 221 insertions, 153 deletions

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 31b5340c685..6f4e18644bd 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -710,13 +710,13 @@ static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
 
 	work_done = bcm_sysport_tx_reclaim(ring->priv, ring);
 
-	if (work_done < budget) {
+	if (work_done == 0) {
 		napi_complete(napi);
 		/* re-enable TX interrupt */
 		intrl2_1_mask_clear(ring->priv, BIT(ring->index));
 	}
 
-	return work_done;
+	return 0;
 }
 
 static void bcm_sysport_tx_reclaim_all(struct bcm_sysport_priv *priv)
@@ -1339,28 +1339,17 @@ static inline void umac_enable_set(struct bcm_sysport_priv *priv,
 		usleep_range(1000, 2000);
 }
 
-static inline int umac_reset(struct bcm_sysport_priv *priv)
+static inline void umac_reset(struct bcm_sysport_priv *priv)
 {
-	unsigned int timeout = 0;
 	u32 reg;
-	int ret = 0;
-
-	umac_writel(priv, 0, UMAC_CMD);
-	while (timeout++ < 1000) {
-		reg = umac_readl(priv, UMAC_CMD);
-		if (!(reg & CMD_SW_RESET))
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == 1000) {
-		dev_err(&priv->pdev->dev,
-			"timeout waiting for MAC to come out of reset\n");
-		ret = -ETIMEDOUT;
-	}
 
-	return ret;
+	reg = umac_readl(priv, UMAC_CMD);
+	reg |= CMD_SW_RESET;
+	umac_writel(priv, reg, UMAC_CMD);
+	udelay(10);
+	reg = umac_readl(priv, UMAC_CMD);
+	reg &= ~CMD_SW_RESET;
+	umac_writel(priv, reg, UMAC_CMD);
 }
 
 static void umac_set_hw_addr(struct bcm_sysport_priv *priv,
@@ -1412,11 +1401,7 @@ static int bcm_sysport_open(struct net_device *dev)
 	int ret;
 
 	/* Reset UniMAC */
-	ret = umac_reset(priv);
-	if (ret) {
-		netdev_err(dev, "UniMAC reset failed\n");
-		return ret;
-	}
+	umac_reset(priv);
 
 	/* Flush TX and RX FIFOs at TOPCTRL level */
 	topctrl_flush(priv);
@@ -1699,12 +1684,6 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 	BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8);
 	dev->needed_headroom += sizeof(struct bcm_tsb);
 
-	/* We are interfaced to a switch which handles the multicast
-	 * filtering for us, so we do not support programming any
-	 * multicast hash table in this Ethernet MAC.
-	 */
-	dev->flags &= ~IFF_MULTICAST;
-
 	/* libphy will adjust the link state accordingly */
 	netif_carrier_off(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index cb15e3ac03c..dca1236dd1c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -797,7 +797,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 		return;
 	}
-	bnx2x_frag_free(fp, new_data);
+	if (new_data)
+		bnx2x_frag_free(fp, new_data);
 drop:
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 6af9e3c046a..3871ec49cc4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12946,7 +12946,7 @@ static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev, int cnic_cnt)
 	 * without the default SB.
 	 * For VFs there is no default SB, then we return (index+1).
 	 */
-	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSI_FLAGS, &control);
+	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSIX_FLAGS, &control);
 
 	index = control & PCI_MSIX_FLAGS_QSIZE;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 5ba1cfbd60d..16281ad2da1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1408,13 +1408,6 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv)
 		if (cb->skb)
 			continue;
 
-		/* set the DMA descriptor length once and for all
-		 * it will only change if we support dynamically sizing
-		 * priv->rx_buf_len, but we do not
-		 */
-		dmadesc_set_length_status(priv, priv->rx_bd_assign_ptr,
-				priv->rx_buf_len << DMA_BUFLENGTH_SHIFT);
-
 		ret = bcmgenet_rx_refill(priv, cb);
 		if (ret)
 			break;
@@ -2535,14 +2528,17 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
 	netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
 
-	err = register_netdev(dev);
-	if (err)
-		goto err_clk_disable;
+	/* libphy will determine the link state */
+	netif_carrier_off(dev);
 
 	/* Turn off the main clock, WOL clock is handled separately */
 	if (!IS_ERR(priv->clk))
 		clk_disable_unprepare(priv->clk);
 
+	err = register_netdev(dev);
+	if (err)
+		goto err;
+
 	return err;
 
 err_clk_disable:
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 0f117105fed..e23c993b136 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -331,9 +331,9 @@ struct bcmgenet_mib_counters {
 #define  EXT_ENERGY_DET_MASK		(1 << 12)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
-#define  RGMII_MODE_EN			(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
+#define  RGMII_MODE_EN			(1 << 6)
 #define  ID_MODE_DIS			(1 << 16)
 
 #define EXT_GPHY_CTRL			0x1C
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6297e72b77e..9bced68527a 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2897,7 +2897,7 @@ static int be_open(struct net_device *netdev)
 	for_all_evt_queues(adapter, eqo, i) {
 		napi_enable(&eqo->napi);
 		be_enable_busy_poll(eqo);
-		be_eq_notify(adapter, eqo->q.id, true, false, 0);
+		be_eq_notify(adapter, eqo->q.id, true, true, 0);
 	}
 	adapter->flags |= BE_FLAGS_NAPI_ENABLED;
 
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index fab39e29544..36fc429298e 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -2990,11 +2990,11 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth)
 	if (ug_info->rxExtendedFiltering) {
 		size += THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING;
 		if (ug_info->largestexternallookupkeysize ==
-		    QE_FLTR_TABLE_LOOKUP_KEY_SIZE_8_BYTES)
+		    QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES)
 			size +=
 			    THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING_8;
 		if (ug_info->largestexternallookupkeysize ==
-		    QE_FLTR_TABLE_LOOKUP_KEY_SIZE_16_BYTES)
+		    QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES)
 			size +=
 			    THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING_16;
 	}
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 168a5ee5e0b..72b454ce05a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1480,6 +1480,13 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw)
 	s32 ret_val;
 	u16 i, rar_count = mac->rar_entry_count;
 
+	if ((hw->mac.type >= e1000_i210) &&
+	    !(igb_get_flash_presence_i210(hw))) {
+		ret_val = igb_pll_workaround_i210(hw);
+		if (ret_val)
+			return ret_val;
+	}
+
 	/* Initialize identification LED */
 	ret_val = igb_id_led_init(hw);
 	if (ret_val) {
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 2a8bb35c2df..217f8138851 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -46,14 +46,15 @@
 #define E1000_CTRL_EXT_SDP3_DIR  0x00000800 /* SDP3 Data direction */
 
 /* Physical Func Reset Done Indication */
-#define E1000_CTRL_EXT_PFRSTD    0x00004000
-#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES  0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX  0x00400000
-#define E1000_CTRL_EXT_LINK_MODE_SGMII   0x00800000
-#define E1000_CTRL_EXT_LINK_MODE_GMII   0x00000000
-#define E1000_CTRL_EXT_EIAME          0x01000000
-#define E1000_CTRL_EXT_IRCA           0x00000001
+#define E1000_CTRL_EXT_PFRSTD	0x00004000
+#define E1000_CTRL_EXT_SDLPE	0X00040000  /* SerDes Low Power Enable */
+#define E1000_CTRL_EXT_LINK_MODE_MASK	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX	0x00400000
+#define E1000_CTRL_EXT_LINK_MODE_SGMII	0x00800000
+#define E1000_CTRL_EXT_LINK_MODE_GMII	0x00000000
+#define E1000_CTRL_EXT_EIAME	0x01000000
+#define E1000_CTRL_EXT_IRCA		0x00000001
 /* Interrupt delay cancellation */
 /* Driver loaded bit for FW */
 #define E1000_CTRL_EXT_DRV_LOAD       0x10000000
@@ -62,6 +63,7 @@
 /* packet buffer parity error detection enabled */
 /* descriptor FIFO parity error detection enable */
 #define E1000_CTRL_EXT_PBA_CLR		0x80000000 /* PBA Clear */
+#define E1000_CTRL_EXT_PHYPDEN		0x00100000
 #define E1000_I2CCMD_REG_ADDR_SHIFT	16
 #define E1000_I2CCMD_PHY_ADDR_SHIFT	24
 #define E1000_I2CCMD_OPCODE_READ	0x08000000
diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h
index 89925e40584..ce55ea5d750 100644
--- a/drivers/net/ethernet/intel/igb/e1000_hw.h
+++ b/drivers/net/ethernet/intel/igb/e1000_hw.h
@@ -567,4 +567,7 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw);
 /* These functions must be implemented by drivers */
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
 s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
+
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
 #endif /* _E1000_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 337161f440d..65d931669f8 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -834,3 +834,69 @@ s32 igb_init_nvm_params_i210(struct e1000_hw *hw)
 	}
 	return ret_val;
 }
+
+/**
+ * igb_pll_workaround_i210
+ * @hw: pointer to the HW structure
+ *
+ * Works around an errata in the PLL circuit where it occasionally
+ * provides the wrong clock frequency after power up.
+ **/
+s32 igb_pll_workaround_i210(struct e1000_hw *hw)
+{
+	s32 ret_val;
+	u32 wuc, mdicnfg, ctrl, ctrl_ext, reg_val;
+	u16 nvm_word, phy_word, pci_word, tmp_nvm;
+	int i;
+
+	/* Get and set needed register values */
+	wuc = rd32(E1000_WUC);
+	mdicnfg = rd32(E1000_MDICNFG);
+	reg_val = mdicnfg & ~E1000_MDICNFG_EXT_MDIO;
+	wr32(E1000_MDICNFG, reg_val);
+
+	/* Get data from NVM, or set default */
+	ret_val = igb_read_invm_word_i210(hw, E1000_INVM_AUTOLOAD,
+					  &nvm_word);
+	if (ret_val)
+		nvm_word = E1000_INVM_DEFAULT_AL;
+	tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL;
+	for (i = 0; i < E1000_MAX_PLL_TRIES; i++) {
+		/* check current state directly from internal PHY */
+		igb_read_phy_reg_gs40g(hw, (E1000_PHY_PLL_FREQ_PAGE |
+					 E1000_PHY_PLL_FREQ_REG), &phy_word);
+		if ((phy_word & E1000_PHY_PLL_UNCONF)
+		    != E1000_PHY_PLL_UNCONF) {
+			ret_val = 0;
+			break;
+		} else {
+			ret_val = -E1000_ERR_PHY;
+		}
+		/* directly reset the internal PHY */
+		ctrl = rd32(E1000_CTRL);
+		wr32(E1000_CTRL, ctrl|E1000_CTRL_PHY_RST);
+
+		ctrl_ext = rd32(E1000_CTRL_EXT);
+		ctrl_ext |= (E1000_CTRL_EXT_PHYPDEN | E1000_CTRL_EXT_SDLPE);
+		wr32(E1000_CTRL_EXT, ctrl_ext);
+
+		wr32(E1000_WUC, 0);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (tmp_nvm << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		igb_read_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		pci_word |= E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		usleep_range(1000, 2000);
+		pci_word &= ~E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (nvm_word << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		/* restore WUC register */
+		wr32(E1000_WUC, wuc);
+	}
+	/* restore MDICNFG setting */
+	wr32(E1000_MDICNFG, mdicnfg);
+	return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 9f34976687b..3442b6357d0 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -33,6 +33,7 @@ s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data);
 s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data);
 s32 igb_init_nvm_params_i210(struct e1000_hw *hw);
 bool igb_get_flash_presence_i210(struct e1000_hw *hw);
+s32 igb_pll_workaround_i210(struct e1000_hw *hw);
 
 #define E1000_STM_OPCODE		0xDB00
 #define E1000_EEPROM_FLASH_SIZE_WORD	0x11
@@ -78,4 +79,15 @@ enum E1000_INVM_STRUCTURE_TYPE {
 #define NVM_LED_1_CFG_DEFAULT_I211	0x0184
 #define NVM_LED_0_2_CFG_DEFAULT_I211	0x200C
 
+/* PLL Defines */
+#define E1000_PCI_PMCSR			0x44
+#define E1000_PCI_PMCSR_D3		0x03
+#define E1000_MAX_PLL_TRIES		5
+#define E1000_PHY_PLL_UNCONF		0xFF
+#define E1000_PHY_PLL_FREQ_PAGE		0xFC0000
+#define E1000_PHY_PLL_FREQ_REG		0x000E
+#define E1000_INVM_DEFAULT_AL		0x202F
+#define E1000_INVM_AUTOLOAD		0x0A
+#define E1000_INVM_PLL_WO_VAL		0x0010
+
 #endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 1cc4b1a7e59..f5ba4e4eafb 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -66,6 +66,7 @@
 #define E1000_PBA      0x01000  /* Packet Buffer Allocation - RW */
 #define E1000_PBS      0x01008  /* Packet Buffer Size */
 #define E1000_EEMNGCTL 0x01010  /* MNG EEprom Control */
+#define E1000_EEARBC_I210 0x12024  /* EEPROM Auto Read Bus Control */
 #define E1000_EEWR     0x0102C  /* EEPROM Write Register - RW */
 #define E1000_I2CCMD   0x01028  /* SFPI2C Command Register - RW */
 #define E1000_FRTIMER  0x01048  /* Free Running Timer - RW */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5759a56aab0..4d2dc17fd31 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7217,6 +7217,20 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	}
 }
 
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_read_config_word(adapter->pdev, reg, value);
+}
+
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_write_config_word(adapter->pdev, reg, *value);
+}
+
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
 {
 	struct igb_adapter *adapter = hw->back;
@@ -7580,6 +7594,8 @@ static int igb_sriov_reinit(struct pci_dev *dev)
 
 	if (netif_running(netdev))
 		igb_close(netdev);
+	else
+		igb_reset(adapter);
 
 	igb_clear_interrupt_scheme(adapter);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 45beca17fa5..dadd9a5f632 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1207,7 +1207,7 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 	command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
 	command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
 
-	if (l3_proto == swab16(ETH_P_IP))
+	if (l3_proto == htons(ETH_P_IP))
 		command |= MVNETA_TXD_IP_CSUM;
 	else
 		command |= MVNETA_TX_L3_IP6;
@@ -2529,7 +2529,7 @@ static void mvneta_adjust_link(struct net_device *ndev)
 
 			if (phydev->speed == SPEED_1000)
 				val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
-			else
+			else if (phydev->speed == SPEED_100)
 				val |= MVNETA_GMAC_CONFIG_MII_SPEED;
 
 			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 80f725228f5..56022d64783 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -294,8 +294,6 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	init_completion(&cq->free);
 
 	cq->irq = priv->eq_table.eq[cq->vector].irq;
-	cq->irq_affinity_change = false;
-
 	return 0;
 
 err_radix:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 4b2130760ee..14c00048bbe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -128,6 +128,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
 						  name);
 				}
+
+				cq->irq_desc =
+					irq_to_desc(mlx4_eq_get_irq(mdev->dev,
+								    cq->vector));
 			}
 		} else {
 			cq->vector = (cq->ring + 1 + priv->port) %
@@ -187,8 +191,6 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 	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) {
-		if (!cq->is_tx)
-			irq_set_affinity_hint(cq->mcq.irq, NULL);
 		mlx4_release_eq(priv->mdev->dev, cq->vector);
 	}
 	cq->vector = 0;
@@ -204,6 +206,7 @@ void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	if (!cq->is_tx) {
 		napi_hash_del(&cq->napi);
 		synchronize_rcu();
+		irq_set_affinity_hint(cq->mcq.irq, NULL);
 	}
 	netif_napi_del(&cq->napi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index fa1a069e14e..68d763d2d03 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -417,6 +417,8 @@ static int mlx4_en_get_coalesce(struct net_device *dev,
 
 	coal->tx_coalesce_usecs = priv->tx_usecs;
 	coal->tx_max_coalesced_frames = priv->tx_frames;
+	coal->tx_max_coalesced_frames_irq = priv->tx_work_limit;
+
 	coal->rx_coalesce_usecs = priv->rx_usecs;
 	coal->rx_max_coalesced_frames = priv->rx_frames;
 
@@ -426,6 +428,7 @@ static int mlx4_en_get_coalesce(struct net_device *dev,
 	coal->rx_coalesce_usecs_high = priv->rx_usecs_high;
 	coal->rate_sample_interval = priv->sample_interval;
 	coal->use_adaptive_rx_coalesce = priv->adaptive_rx_coal;
+
 	return 0;
 }
 
@@ -434,6 +437,9 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
+	if (!coal->tx_max_coalesced_frames_irq)
+		return -EINVAL;
+
 	priv->rx_frames = (coal->rx_max_coalesced_frames ==
 			   MLX4_EN_AUTO_CONF) ?
 				MLX4_EN_RX_COAL_TARGET :
@@ -457,6 +463,7 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 	priv->rx_usecs_high = coal->rx_coalesce_usecs_high;
 	priv->sample_interval = coal->rate_sample_interval;
 	priv->adaptive_rx_coal = coal->use_adaptive_rx_coalesce;
+	priv->tx_work_limit = coal->tx_max_coalesced_frames_irq;
 
 	return mlx4_en_moderation_update(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index f384b354c88..887cf01d831 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2331,7 +2331,7 @@ static void mlx4_en_add_vxlan_port(struct  net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	__be16 current_port;
 
-	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS))
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	if (sa_family == AF_INET6)
@@ -2468,6 +2468,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			MLX4_WQE_CTRL_SOLICITED);
 	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
 	priv->tx_ring_num = prof->tx_ring_num;
+	priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
 
 	priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
 				GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b8ec9208e12..7765a08f9e8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -40,6 +40,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
+#include <linux/irq.h>
 
 #include "mlx4_en.h"
 
@@ -782,6 +783,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 							     PKT_HASH_TYPE_L3);
 
 					skb_record_rx_queue(gro_skb, cq->ring);
+					skb_mark_napi_id(gro_skb, &cq->napi);
 
 					if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
 						timestamp = mlx4_en_get_cqe_ts(cqe);
@@ -896,16 +898,25 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget) {
+		int cpu_curr;
+		const struct cpumask *aff;
+
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
-		if (unlikely(cq->mcq.irq_affinity_change)) {
-			cq->mcq.irq_affinity_change = false;
+
+		cpu_curr = smp_processor_id();
+		aff = irq_desc_get_irq_data(cq->irq_desc)->affinity;
+
+		if (unlikely(!cpumask_test_cpu(cpu_curr, aff))) {
+			/* Current cpu is not according to smp_irq_affinity -
+			 * probably affinity changed. need to stop this NAPI
+			 * poll, and restart it on the right CPU
+			 */
 			napi_complete(napi);
 			mlx4_en_arm_cq(priv, cq);
 			return 0;
 		}
 	} else {
 		/* Done for now */
-		cq->mcq.irq_affinity_change = false;
 		napi_complete(napi);
 		mlx4_en_arm_cq(priv, cq);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8be7483f823..5045bab5963 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -351,9 +351,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-static int mlx4_en_process_tx_cq(struct net_device *dev,
-				 struct mlx4_en_cq *cq,
-				 int budget)
+static bool mlx4_en_process_tx_cq(struct net_device *dev,
+				 struct mlx4_en_cq *cq)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
@@ -372,9 +371,10 @@ static int mlx4_en_process_tx_cq(struct net_device *dev,
 	int factor = priv->cqe_factor;
 	u64 timestamp = 0;
 	int done = 0;
+	int budget = priv->tx_work_limit;
 
 	if (!priv->port_up)
-		return 0;
+		return true;
 
 	index = cons_index & size_mask;
 	cqe = &buf[(index << factor) + factor];
@@ -447,7 +447,7 @@ static int mlx4_en_process_tx_cq(struct net_device *dev,
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
-	return done;
+	return done < budget;
 }
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@@ -467,24 +467,16 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
 	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
 	struct net_device *dev = cq->dev;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	int done;
+	int clean_complete;
 
-	done = mlx4_en_process_tx_cq(dev, cq, budget);
+	clean_complete = mlx4_en_process_tx_cq(dev, cq);
+	if (!clean_complete)
+		return budget;
 
-	/* If we used up all the quota - we're probably not done yet... */
-	if (done < budget) {
-		/* Done for now */
-		cq->mcq.irq_affinity_change = false;
-		napi_complete(napi);
-		mlx4_en_arm_cq(priv, cq);
-		return done;
-	} else if (unlikely(cq->mcq.irq_affinity_change)) {
-		cq->mcq.irq_affinity_change = false;
-		napi_complete(napi);
-		mlx4_en_arm_cq(priv, cq);
-		return 0;
-	}
-	return budget;
+	napi_complete(napi);
+	mlx4_en_arm_cq(priv, cq);
+
+	return 0;
 }
 
 static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d954ec1eac1..2a004b347e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -53,11 +53,6 @@ enum {
 	MLX4_EQ_ENTRY_SIZE	= 0x20
 };
 
-struct mlx4_irq_notify {
-	void *arg;
-	struct irq_affinity_notify notify;
-};
-
 #define MLX4_EQ_STATUS_OK	   ( 0 << 28)
 #define MLX4_EQ_STATUS_WRITE_FAIL  (10 << 28)
 #define MLX4_EQ_OWNER_SW	   ( 0 << 24)
@@ -1088,57 +1083,6 @@ static void mlx4_unmap_clr_int(struct mlx4_dev *dev)
 	iounmap(priv->clr_base);
 }
 
-static void mlx4_irq_notifier_notify(struct irq_affinity_notify *notify,
-				     const cpumask_t *mask)
-{
-	struct mlx4_irq_notify *n = container_of(notify,
-						 struct mlx4_irq_notify,
-						 notify);
-	struct mlx4_priv *priv = (struct mlx4_priv *)n->arg;
-	struct radix_tree_iter iter;
-	void **slot;
-
-	radix_tree_for_each_slot(slot, &priv->cq_table.tree, &iter, 0) {
-		struct mlx4_cq *cq = (struct mlx4_cq *)(*slot);
-
-		if (cq->irq == notify->irq)
-			cq->irq_affinity_change = true;
-	}
-}
-
-static void mlx4_release_irq_notifier(struct kref *ref)
-{
-	struct mlx4_irq_notify *n = container_of(ref, struct mlx4_irq_notify,
-						 notify.kref);
-	kfree(n);
-}
-
-static void mlx4_assign_irq_notifier(struct mlx4_priv *priv,
-				     struct mlx4_dev *dev, int irq)
-{
-	struct mlx4_irq_notify *irq_notifier = NULL;
-	int err = 0;
-
-	irq_notifier = kzalloc(sizeof(*irq_notifier), GFP_KERNEL);
-	if (!irq_notifier) {
-		mlx4_warn(dev, "Failed to allocate irq notifier. irq %d\n",
-			  irq);
-		return;
-	}
-
-	irq_notifier->notify.irq = irq;
-	irq_notifier->notify.notify = mlx4_irq_notifier_notify;
-	irq_notifier->notify.release = mlx4_release_irq_notifier;
-	irq_notifier->arg = priv;
-	err = irq_set_affinity_notifier(irq, &irq_notifier->notify);
-	if (err) {
-		kfree(irq_notifier);
-		irq_notifier = NULL;
-		mlx4_warn(dev, "Failed to set irq notifier. irq %d\n", irq);
-	}
-}
-
-
 int mlx4_alloc_eq_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1409,8 +1353,6 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 				continue;
 				/*we dont want to break here*/
 			}
-			mlx4_assign_irq_notifier(priv, dev,
-						 priv->eq_table.eq[vec].irq);
 
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
@@ -1427,6 +1369,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 }
 EXPORT_SYMBOL(mlx4_assign_eq);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return priv->eq_table.eq[vec].irq;
+}
+EXPORT_SYMBOL(mlx4_eq_get_irq);
+
 void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1438,9 +1388,6 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 		  Belonging to a legacy EQ*/
 		mutex_lock(&priv->msix_ctl.pool_lock);
 		if (priv->msix_ctl.pool_bm & 1ULL << i) {
-			irq_set_affinity_notifier(
-				priv->eq_table.eq[vec].irq,
-				NULL);
 			free_irq(priv->eq_table.eq[vec].irq,
 				 &priv->eq_table.eq[vec]);
 			priv->msix_ctl.pool_bm &= ~(1ULL << i);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 7c1b5ec5378..2b19dd1f2c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -126,6 +126,8 @@ enum {
 #define MAX_TX_RINGS			(MLX4_EN_MAX_TX_RING_P_UP * \
 					 MLX4_EN_NUM_UP)
 
+#define MLX4_EN_DEFAULT_TX_WORK		256
+
 /* Target number of packets to coalesce with interrupt moderation */
 #define MLX4_EN_RX_COAL_TARGET	44
 #define MLX4_EN_RX_COAL_TIME	0x10
@@ -341,6 +343,7 @@ struct mlx4_en_cq {
 #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD)
 	spinlock_t poll_lock; /* protects from LLS/napi conflicts */
 #endif  /* CONFIG_NET_RX_BUSY_POLL */
+	struct irq_desc *irq_desc;
 };
 
 struct mlx4_en_port_profile {
@@ -540,6 +543,7 @@ struct mlx4_en_priv {
 	__be32 ctrl_flags;
 	u32 flags;
 	u8 num_tx_rings_p_up;
+	u32 tx_work_limit;
 	u32 tx_ring_num;
 	u32 rx_ring_num;
 	u32 rx_skb_size;
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 51c78ce27b3..6175bd59190 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -540,6 +540,7 @@ enum rtl_register_content {
 	MagicPacket	= (1 << 5),	/* Wake up when receives a Magic Packet */
 	LinkUp		= (1 << 4),	/* Wake up when the cable connection is re-established */
 	Jumbo_En0	= (1 << 2),	/* 8168 only. Reserved in the 8168b */
+	Rdy_to_L23	= (1 << 1),	/* L23 Enable */
 	Beacon_en	= (1 << 0),	/* 8168 only. Reserved in the 8168b */
 
 	/* Config4 register */
@@ -4883,6 +4884,21 @@ static void rtl_enable_clock_request(struct pci_dev *pdev)
 				 PCI_EXP_LNKCTL_CLKREQ_EN);
 }
 
+static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	u8 data;
+
+	data = RTL_R8(Config3);
+
+	if (enable)
+		data |= Rdy_to_L23;
+	else
+		data &= ~Rdy_to_L23;
+
+	RTL_W8(Config3, data);
+}
+
 #define R8168_CPCMD_QUIRK_MASK (\
 	EnableBist | \
 	Mac_dbgo_oe | \
@@ -5232,6 +5248,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168f(tp);
+	rtl_pcie_state_l2l3_enable(tp, false);
 
 	rtl_ephy_init(tp, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
 
@@ -5270,6 +5287,8 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 
 	rtl_w1w0_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
 	rtl_w1w0_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
@@ -5522,6 +5541,8 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp)
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
 
 	rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
@@ -5557,6 +5578,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_w1w0_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00, ERIAR_EXGMAC);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8106(struct rtl8169_private *tp)
@@ -5569,6 +5592,8 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	RTL_W32(MISC, (RTL_R32(MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN);
 	RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8101(struct net_device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index b3e148ef568..9d3748361a1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -320,11 +320,8 @@ static void dwmac1000_set_eee_timer(void __iomem *ioaddr, int ls, int tw)
 
 static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool restart)
 {
-	u32 value;
-
-	value = readl(ioaddr + GMAC_AN_CTRL);
 	/* auto negotiation enable and External Loopback enable */
-	value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
+	u32 value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
 
 	if (restart)
 		value |= GMAC_AN_CTRL_RAN;
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 7e6628a9151..1e2bcf5f89e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -145,7 +145,7 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
 			x->rx_msg_type_delay_req++;
 		else if (p->des4.erx.msg_type == RDES_EXT_DELAY_RESP)
 			x->rx_msg_type_delay_resp++;
-		else if (p->des4.erx.msg_type == RDES_EXT_DELAY_REQ)
+		else if (p->des4.erx.msg_type == RDES_EXT_PDELAY_REQ)
 			x->rx_msg_type_pdelay_req++;
 		else if (p->des4.erx.msg_type == RDES_EXT_PDELAY_RESP)
 			x->rx_msg_type_pdelay_resp++;