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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

9 files changed, 964 insertions, 728 deletions

diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index ba994fb4cec6..ca4641e2f748 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -2223,11 +2223,10 @@ out:
 s32 igb_set_eee_i350(struct e1000_hw *hw)
 {
 	s32 ret_val = 0;
-	u32 ipcnfg, eeer, ctrl_ext;
+	u32 ipcnfg, eeer;
 
-	ctrl_ext = rd32(E1000_CTRL_EXT);
-	if ((hw->mac.type != e1000_i350) ||
-	    (ctrl_ext & E1000_CTRL_EXT_LINK_MODE_MASK))
+	if ((hw->mac.type < e1000_i350) ||
+	    (hw->phy.media_type != e1000_media_type_copper))
 		goto out;
 	ipcnfg = rd32(E1000_IPCNFG);
 	eeer = rd32(E1000_EEER);
@@ -2240,6 +2239,14 @@ s32 igb_set_eee_i350(struct e1000_hw *hw)
 			E1000_EEER_RX_LPI_EN |
 			E1000_EEER_LPI_FC);
 
+		/* keep the LPI clock running before EEE is enabled */
+		if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
+			u32 eee_su;
+			eee_su = rd32(E1000_EEE_SU);
+			eee_su &= ~E1000_EEE_SU_LPI_CLK_STP;
+			wr32(E1000_EEE_SU, eee_su);
+		}
+
 	} else {
 		ipcnfg &= ~(E1000_IPCNFG_EEE_1G_AN |
 			E1000_IPCNFG_EEE_100M_AN);
@@ -2249,6 +2256,8 @@ s32 igb_set_eee_i350(struct e1000_hw *hw)
 	}
 	wr32(E1000_IPCNFG, ipcnfg);
 	wr32(E1000_EEER, eeer);
+	rd32(E1000_IPCNFG);
+	rd32(E1000_EEER);
 out:
 
 	return ret_val;
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index ec7e4fe3e3ee..de4b41ec3c40 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -322,6 +322,9 @@
 #define E1000_FCRTC_RTH_COAL_SHIFT      4
 #define E1000_PCIEMISC_LX_DECISION      0x00000080 /* Lx power decision */
 
+/* Timestamp in Rx buffer */
+#define E1000_RXPBS_CFG_TS_EN           0x80000000
+
 /* SerDes Control */
 #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400
 
@@ -360,6 +363,7 @@
 #define E1000_ICR_RXDMT0        0x00000010 /* rx desc min. threshold (0) */
 #define E1000_ICR_RXT0          0x00000080 /* rx timer intr (ring 0) */
 #define E1000_ICR_VMMB          0x00000100 /* VM MB event */
+#define E1000_ICR_TS            0x00080000 /* Time Sync Interrupt */
 #define E1000_ICR_DRSTA         0x40000000 /* Device Reset Asserted */
 /* If this bit asserted, the driver should claim the interrupt */
 #define E1000_ICR_INT_ASSERTED  0x80000000
@@ -399,6 +403,7 @@
 #define E1000_IMS_TXDW      E1000_ICR_TXDW      /* Transmit desc written back */
 #define E1000_IMS_LSC       E1000_ICR_LSC       /* Link Status Change */
 #define E1000_IMS_VMMB      E1000_ICR_VMMB      /* Mail box activity */
+#define E1000_IMS_TS        E1000_ICR_TS        /* Time Sync Interrupt */
 #define E1000_IMS_RXSEQ     E1000_ICR_RXSEQ     /* rx sequence error */
 #define E1000_IMS_RXDMT0    E1000_ICR_RXDMT0    /* rx desc min. threshold */
 #define E1000_IMS_RXT0      E1000_ICR_RXT0      /* rx timer intr */
@@ -510,6 +515,9 @@
 
 #define E1000_TIMINCA_16NS_SHIFT 24
 
+#define E1000_TSICR_TXTS 0x00000002
+#define E1000_TSIM_TXTS 0x00000002
+
 #define E1000_MDICNFG_EXT_MDIO    0x80000000      /* MDI ext/int destination */
 #define E1000_MDICNFG_COM_MDIO    0x40000000      /* MDI shared w/ lan 0 */
 #define E1000_MDICNFG_PHY_MASK    0x03E00000
@@ -849,8 +857,9 @@
 #define E1000_IPCNFG_EEE_100M_AN     0x00000004  /* EEE Enable 100M AN */
 #define E1000_EEER_TX_LPI_EN         0x00010000  /* EEE Tx LPI Enable */
 #define E1000_EEER_RX_LPI_EN         0x00020000  /* EEE Rx LPI Enable */
-#define E1000_EEER_FRC_AN            0x10000000 /* Enable EEE in loopback */
+#define E1000_EEER_FRC_AN            0x10000000  /* Enable EEE in loopback */
 #define E1000_EEER_LPI_FC            0x00040000  /* EEE Enable on FC */
+#define E1000_EEE_SU_LPI_CLK_STP     0X00800000  /* EEE LPI Clock Stop */
 
 /* SerDes Control */
 #define E1000_GEN_CTL_READY             0x80000000
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 7be98b6f1052..3404bc79f4ca 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -464,6 +464,32 @@ s32 igb_copper_link_setup_82580(struct e1000_hw *hw)
 	phy_data |= I82580_CFG_ENABLE_DOWNSHIFT;
 
 	ret_val = phy->ops.write_reg(hw, I82580_CFG_REG, phy_data);
+	if (ret_val)
+		goto out;
+
+	/* Set MDI/MDIX mode */
+	ret_val = phy->ops.read_reg(hw, I82580_PHY_CTRL_2, &phy_data);
+	if (ret_val)
+		goto out;
+	phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK;
+	/*
+	 * Options:
+	 *   0 - Auto (default)
+	 *   1 - MDI mode
+	 *   2 - MDI-X mode
+	 */
+	switch (hw->phy.mdix) {
+	case 1:
+		break;
+	case 2:
+		phy_data |= I82580_PHY_CTRL2_MANUAL_MDIX;
+		break;
+	case 0:
+	default:
+		phy_data |= I82580_PHY_CTRL2_AUTO_MDI_MDIX;
+		break;
+	}
+	ret_val = hw->phy.ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data);
 
 out:
 	return ret_val;
@@ -2246,8 +2272,7 @@ s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw)
 	if (ret_val)
 		goto out;
 
-	phy_data &= ~I82580_PHY_CTRL2_AUTO_MDIX;
-	phy_data &= ~I82580_PHY_CTRL2_FORCE_MDI_MDIX;
+	phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK;
 
 	ret_val = phy->ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data);
 	if (ret_val)
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h
index 34e40619f16b..6ac3299bfcb9 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.h
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.h
@@ -111,8 +111,9 @@ s32  igb_check_polarity_m88(struct e1000_hw *hw);
 #define I82580_PHY_STATUS2_SPEED_100MBPS  0x0100
 
 /* I82580 PHY Control 2 */
-#define I82580_PHY_CTRL2_AUTO_MDIX        0x0400
-#define I82580_PHY_CTRL2_FORCE_MDI_MDIX   0x0200
+#define I82580_PHY_CTRL2_MANUAL_MDIX      0x0200
+#define I82580_PHY_CTRL2_AUTO_MDI_MDIX    0x0400
+#define I82580_PHY_CTRL2_MDIX_CFG_MASK    0x0600
 
 /* I82580 PHY Diagnostics Status */
 #define I82580_DSTATUS_CABLE_LENGTH       0x03FC
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 28394bea5253..e5db48594e8a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -91,6 +91,8 @@
 #define E1000_TIMINCA    0x0B608 /* Increment attributes register - RW */
 #define E1000_TSAUXC     0x0B640 /* Timesync Auxiliary Control register */
 #define E1000_SYSTIMR    0x0B6F8 /* System time register Residue */
+#define E1000_TSICR      0x0B66C /* Interrupt Cause Register */
+#define E1000_TSIM       0x0B674 /* Interrupt Mask Register */
 
 /* Filtering Registers */
 #define E1000_SAQF(_n) (0x5980 + 4 * (_n))
@@ -347,6 +349,7 @@
 /* Energy Efficient Ethernet "EEE" register */
 #define E1000_IPCNFG  0x0E38  /* Internal PHY Configuration */
 #define E1000_EEER    0x0E30  /* Energy Efficient Ethernet */
+#define E1000_EEE_SU  0X0E34  /* EEE Setup */
 
 /* Thermal Sensor Register */
 #define E1000_THSTAT    0x08110 /* Thermal Sensor Status */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 9e572dd29ab2..8aad230c0592 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -34,9 +34,11 @@
 #include "e1000_mac.h"
 #include "e1000_82575.h"
 
+#ifdef CONFIG_IGB_PTP
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#endif /* CONFIG_IGB_PTP */
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
 
@@ -99,7 +101,6 @@ struct vf_data_storage {
 	u16 pf_vlan; /* When set, guest VLAN config not allowed. */
 	u16 pf_qos;
 	u16 tx_rate;
-	struct pci_dev *vfdev;
 };
 
 #define IGB_VF_FLAG_CTS            0x00000001 /* VF is clear to send data */
@@ -131,9 +132,9 @@ struct vf_data_storage {
 #define MAXIMUM_ETHERNET_VLAN_SIZE 1522
 
 /* Supported Rx Buffer Sizes */
-#define IGB_RXBUFFER_512   512
+#define IGB_RXBUFFER_256   256
 #define IGB_RXBUFFER_16384 16384
-#define IGB_RX_HDR_LEN     IGB_RXBUFFER_512
+#define IGB_RX_HDR_LEN     IGB_RXBUFFER_256
 
 /* How many Tx Descriptors do we need to call netif_wake_queue ? */
 #define IGB_TX_QUEUE_WAKE	16
@@ -167,8 +168,8 @@ struct igb_tx_buffer {
 	unsigned int bytecount;
 	u16 gso_segs;
 	__be16 protocol;
-	dma_addr_t dma;
-	u32 length;
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
 	u32 tx_flags;
 };
 
@@ -212,7 +213,6 @@ struct igb_q_vector {
 	struct igb_ring_container rx, tx;
 
 	struct napi_struct napi;
-	int numa_node;
 
 	u16 itr_val;
 	u8 set_itr;
@@ -257,7 +257,6 @@ struct igb_ring {
 	};
 	/* Items past this point are only used during ring alloc / free */
 	dma_addr_t dma;                /* phys address of the ring */
-	int numa_node;                  /* node to alloc ring memory on */
 };
 
 enum e1000_ring_flags_t {
@@ -342,7 +341,6 @@ struct igb_adapter {
 
 	/* OS defined structs */
 	struct pci_dev *pdev;
-	struct hwtstamp_config hwtstamp_config;
 
 	spinlock_t stats64_lock;
 	struct rtnl_link_stats64 stats64;
@@ -373,15 +371,19 @@ struct igb_adapter {
 	int vf_rate_link_speed;
 	u32 rss_queues;
 	u32 wvbr;
-	int node;
 	u32 *shadow_vfta;
 
+#ifdef CONFIG_IGB_PTP
 	struct ptp_clock *ptp_clock;
-	struct ptp_clock_info caps;
-	struct delayed_work overflow_work;
+	struct ptp_clock_info ptp_caps;
+	struct delayed_work ptp_overflow_work;
+	struct work_struct ptp_tx_work;
+	struct sk_buff *ptp_tx_skb;
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
+#endif /* CONFIG_IGB_PTP */
+
 	char fw_version[32];
 };
 
@@ -390,6 +392,7 @@ struct igb_adapter {
 #define IGB_FLAG_QUAD_PORT_A       (1 << 2)
 #define IGB_FLAG_QUEUE_PAIRS       (1 << 3)
 #define IGB_FLAG_DMAC              (1 << 4)
+#define IGB_FLAG_PTP               (1 << 5)
 
 /* DMA Coalescing defines */
 #define IGB_MIN_TXPBSIZE           20408
@@ -435,13 +438,17 @@ extern void igb_power_up_link(struct igb_adapter *);
 extern void igb_set_fw_version(struct igb_adapter *);
 #ifdef CONFIG_IGB_PTP
 extern void igb_ptp_init(struct igb_adapter *adapter);
-extern void igb_ptp_remove(struct igb_adapter *adapter);
-
-extern void igb_systim_to_hwtstamp(struct igb_adapter *adapter,
-				   struct skb_shared_hwtstamps *hwtstamps,
-				   u64 systim);
+extern void igb_ptp_stop(struct igb_adapter *adapter);
+extern void igb_ptp_reset(struct igb_adapter *adapter);
+extern void igb_ptp_tx_work(struct work_struct *work);
+extern void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
+extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
+				union e1000_adv_rx_desc *rx_desc,
+				struct sk_buff *skb);
+extern int igb_ptp_hwtstamp_ioctl(struct net_device *netdev,
+				  struct ifreq *ifr, int cmd);
+#endif /* CONFIG_IGB_PTP */
 
-#endif
 static inline s32 igb_reset_phy(struct e1000_hw *hw)
 {
 	if (hw->phy.ops.reset)
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 70591117051b..2ea012849825 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -148,9 +148,9 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 				   SUPPORTED_100baseT_Full |
 				   SUPPORTED_1000baseT_Full|
 				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP);
-		ecmd->advertising = (ADVERTISED_TP |
-				     ADVERTISED_Pause);
+				   SUPPORTED_TP |
+				   SUPPORTED_Pause);
+		ecmd->advertising = ADVERTISED_TP;
 
 		if (hw->mac.autoneg == 1) {
 			ecmd->advertising |= ADVERTISED_Autoneg;
@@ -158,6 +158,21 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 			ecmd->advertising |= hw->phy.autoneg_advertised;
 		}
 
+		if (hw->mac.autoneg != 1)
+			ecmd->advertising &= ~(ADVERTISED_Pause |
+					       ADVERTISED_Asym_Pause);
+
+		if (hw->fc.requested_mode == e1000_fc_full)
+			ecmd->advertising |= ADVERTISED_Pause;
+		else if (hw->fc.requested_mode == e1000_fc_rx_pause)
+			ecmd->advertising |= (ADVERTISED_Pause |
+					      ADVERTISED_Asym_Pause);
+		else if (hw->fc.requested_mode == e1000_fc_tx_pause)
+			ecmd->advertising |=  ADVERTISED_Asym_Pause;
+		else
+			ecmd->advertising &= ~(ADVERTISED_Pause |
+					       ADVERTISED_Asym_Pause);
+
 		ecmd->port = PORT_TP;
 		ecmd->phy_address = hw->phy.addr;
 	} else {
@@ -198,6 +213,19 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	}
 
 	ecmd->autoneg = hw->mac.autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	/* MDI-X => 2; MDI =>1; Invalid =>0 */
+	if (hw->phy.media_type == e1000_media_type_copper)
+		ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+						      ETH_TP_MDI;
+	else
+		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+
+	if (hw->phy.mdix == AUTO_ALL_MODES)
+		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+	else
+		ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+
 	return 0;
 }
 
@@ -214,6 +242,22 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		return -EINVAL;
 	}
 
+	/*
+	 * MDI setting is only allowed when autoneg enabled because
+	 * some hardware doesn't allow MDI setting when speed or
+	 * duplex is forced.
+	 */
+	if (ecmd->eth_tp_mdix_ctrl) {
+		if (hw->phy.media_type != e1000_media_type_copper)
+			return -EOPNOTSUPP;
+
+		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
+	}
+
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
 		msleep(1);
 
@@ -227,12 +271,25 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
 		u32 speed = ethtool_cmd_speed(ecmd);
+		/* calling this overrides forced MDI setting */
 		if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) {
 			clear_bit(__IGB_RESETTING, &adapter->state);
 			return -EINVAL;
 		}
 	}
 
+	/* MDI-X => 2; MDI => 1; Auto => 3 */
+	if (ecmd->eth_tp_mdix_ctrl) {
+		/*
+		 * fix up the value for auto (3 => 0) as zero is mapped
+		 * internally to auto
+		 */
+		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+			hw->phy.mdix = AUTO_ALL_MODES;
+		else
+			hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+	}
+
 	/* reset the link */
 	if (netif_running(adapter->netdev)) {
 		igb_down(adapter);
@@ -1469,33 +1526,22 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl_reg = 0;
-	u16 phy_reg = 0;
 
 	hw->mac.autoneg = false;
 
-	switch (hw->phy.type) {
-	case e1000_phy_m88:
-		/* Auto-MDI/MDIX Off */
-		igb_write_phy_reg(hw, M88E1000_PHY_SPEC_CTRL, 0x0808);
-		/* reset to update Auto-MDI/MDIX */
-		igb_write_phy_reg(hw, PHY_CONTROL, 0x9140);
-		/* autoneg off */
-		igb_write_phy_reg(hw, PHY_CONTROL, 0x8140);
-		break;
-	case e1000_phy_82580:
-		/* enable MII loopback */
-		igb_write_phy_reg(hw, I82580_PHY_LBK_CTRL, 0x8041);
-		break;
-	case e1000_phy_i210:
-		/* set loopback speed in PHY */
-		igb_read_phy_reg(hw, (GS40G_PAGE_SELECT & GS40G_PAGE_2),
-					&phy_reg);
-		phy_reg |= GS40G_MAC_SPEED_1G;
-		igb_write_phy_reg(hw, (GS40G_PAGE_SELECT & GS40G_PAGE_2),
-					phy_reg);
-		ctrl_reg = rd32(E1000_CTRL_EXT);
-	default:
-		break;
+	if (hw->phy.type == e1000_phy_m88) {
+		if (hw->phy.id != I210_I_PHY_ID) {
+			/* Auto-MDI/MDIX Off */
+			igb_write_phy_reg(hw, M88E1000_PHY_SPEC_CTRL, 0x0808);
+			/* reset to update Auto-MDI/MDIX */
+			igb_write_phy_reg(hw, PHY_CONTROL, 0x9140);
+			/* autoneg off */
+			igb_write_phy_reg(hw, PHY_CONTROL, 0x8140);
+		} else {
+			/* force 1000, set loopback  */
+			igb_write_phy_reg(hw, I347AT4_PAGE_SELECT, 0);
+			igb_write_phy_reg(hw, PHY_CONTROL, 0x4140);
+		}
 	}
 
 	/* add small delay to avoid loopback test failure */
@@ -1513,7 +1559,7 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter)
 		     E1000_CTRL_FD |	 /* Force Duplex to FULL */
 		     E1000_CTRL_SLU);	 /* Set link up enable bit */
 
-	if ((hw->phy.type == e1000_phy_m88) || (hw->phy.type == e1000_phy_i210))
+	if (hw->phy.type == e1000_phy_m88)
 		ctrl_reg |= E1000_CTRL_ILOS; /* Invert Loss of Signal */
 
 	wr32(E1000_CTRL, ctrl_reg);
@@ -1521,11 +1567,10 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter)
 	/* Disable the receiver on the PHY so when a cable is plugged in, the
 	 * PHY does not begin to autoneg when a cable is reconnected to the NIC.
 	 */
-	if ((hw->phy.type == e1000_phy_m88) || (hw->phy.type == e1000_phy_i210))
+	if (hw->phy.type == e1000_phy_m88)
 		igb_phy_disable_receiver(adapter);
 
-	udelay(500);
-
+	mdelay(500);
 	return 0;
 }
 
@@ -1785,13 +1830,6 @@ static int igb_loopback_test(struct igb_adapter *adapter, u64 *data)
 		*data = 0;
 		goto out;
 	}
-	if ((adapter->hw.mac.type == e1000_i210)
-		|| (adapter->hw.mac.type == e1000_i211)) {
-		dev_err(&adapter->pdev->dev,
-			"Loopback test not supported on this part at this time.\n");
-		*data = 0;
-		goto out;
-	}
 	*data = igb_setup_desc_rings(adapter);
 	if (*data)
 		goto out;
@@ -2257,6 +2295,54 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	}
 }
 
+static int igb_get_ts_info(struct net_device *dev,
+			   struct ethtool_ts_info *info)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+
+	switch (adapter->hw.mac.type) {
+#ifdef CONFIG_IGB_PTP
+	case e1000_82576:
+	case e1000_82580:
+	case e1000_i350:
+	case e1000_i210:
+	case e1000_i211:
+		info->so_timestamping =
+			SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_RX_HARDWARE |
+			SOF_TIMESTAMPING_RAW_HARDWARE;
+
+		if (adapter->ptp_clock)
+			info->phc_index = ptp_clock_index(adapter->ptp_clock);
+		else
+			info->phc_index = -1;
+
+		info->tx_types =
+			(1 << HWTSTAMP_TX_OFF) |
+			(1 << HWTSTAMP_TX_ON);
+
+		info->rx_filters = 1 << HWTSTAMP_FILTER_NONE;
+
+		/* 82576 does not support timestamping all packets. */
+		if (adapter->hw.mac.type >= e1000_82580)
+			info->rx_filters |= 1 << HWTSTAMP_FILTER_ALL;
+		else
+			info->rx_filters |=
+				(1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
+				(1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+				(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+				(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+				(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+				(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+				(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+		return 0;
+#endif /* CONFIG_IGB_PTP */
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int igb_ethtool_begin(struct net_device *netdev)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -2270,38 +2356,6 @@ static void igb_ethtool_complete(struct net_device *netdev)
 	pm_runtime_put(&adapter->pdev->dev);
 }
 
-#ifdef CONFIG_IGB_PTP
-static int igb_ethtool_get_ts_info(struct net_device *dev,
-				   struct ethtool_ts_info *info)
-{
-	struct igb_adapter *adapter = netdev_priv(dev);
-
-	info->so_timestamping =
-		SOF_TIMESTAMPING_TX_HARDWARE |
-		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RAW_HARDWARE;
-
-	if (adapter->ptp_clock)
-		info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		info->phc_index = -1;
-
-	info->tx_types =
-		(1 << HWTSTAMP_TX_OFF) |
-		(1 << HWTSTAMP_TX_ON);
-
-	info->rx_filters =
-		(1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_ALL) |
-		(1 << HWTSTAMP_FILTER_SOME) |
-		(1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
-
-	return 0;
-}
-
-#endif
 static const struct ethtool_ops igb_ethtool_ops = {
 	.get_settings           = igb_get_settings,
 	.set_settings           = igb_set_settings,
@@ -2328,11 +2382,9 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_ethtool_stats      = igb_get_ethtool_stats,
 	.get_coalesce           = igb_get_coalesce,
 	.set_coalesce           = igb_set_coalesce,
+	.get_ts_info            = igb_get_ts_info,
 	.begin			= igb_ethtool_begin,
 	.complete		= igb_ethtool_complete,
-#ifdef CONFIG_IGB_PTP
-	.get_ts_info		= igb_ethtool_get_ts_info,
-#endif
 };
 
 void igb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f88c822e57a6..e1ceb37ef12e 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -172,8 +172,7 @@ static void igb_check_vf_rate_limit(struct igb_adapter *);
 
 #ifdef CONFIG_PCI_IOV
 static int igb_vf_configure(struct igb_adapter *adapter, int vf);
-static int igb_find_enabled_vfs(struct igb_adapter *adapter);
-static int igb_check_vf_assignment(struct igb_adapter *adapter);
+static bool igb_vfs_are_assigned(struct igb_adapter *adapter);
 #endif
 
 #ifdef CONFIG_PM
@@ -404,8 +403,8 @@ static void igb_dump(struct igb_adapter *adapter)
 		buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
 		pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n",
 			n, tx_ring->next_to_use, tx_ring->next_to_clean,
-			(u64)buffer_info->dma,
-			buffer_info->length,
+			(u64)dma_unmap_addr(buffer_info, dma),
+			dma_unmap_len(buffer_info, len),
 			buffer_info->next_to_watch,
 			(u64)buffer_info->time_stamp);
 	}
@@ -456,8 +455,8 @@ static void igb_dump(struct igb_adapter *adapter)
 				" %04X  %p %016llX %p%s\n", i,
 				le64_to_cpu(u0->a),
 				le64_to_cpu(u0->b),
-				(u64)buffer_info->dma,
-				buffer_info->length,
+				(u64)dma_unmap_addr(buffer_info, dma),
+				dma_unmap_len(buffer_info, len),
 				buffer_info->next_to_watch,
 				(u64)buffer_info->time_stamp,
 				buffer_info->skb, next_desc);
@@ -466,7 +465,8 @@ static void igb_dump(struct igb_adapter *adapter)
 				print_hex_dump(KERN_INFO, "",
 					DUMP_PREFIX_ADDRESS,
 					16, 1, buffer_info->skb->data,
-					buffer_info->length, true);
+					dma_unmap_len(buffer_info, len),
+					true);
 		}
 	}
 
@@ -683,52 +683,29 @@ static int igb_alloc_queues(struct igb_adapter *adapter)
 {
 	struct igb_ring *ring;
 	int i;
-	int orig_node = adapter->node;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		if (orig_node == -1) {
-			int cur_node = next_online_node(adapter->node);
-			if (cur_node == MAX_NUMNODES)
-				cur_node = first_online_node;
-			adapter->node = cur_node;
-		}
-		ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL,
-				    adapter->node);
-		if (!ring)
-			ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL);
+		ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL);
 		if (!ring)
 			goto err;
 		ring->count = adapter->tx_ring_count;
 		ring->queue_index = i;
 		ring->dev = &adapter->pdev->dev;
 		ring->netdev = adapter->netdev;
-		ring->numa_node = adapter->node;
 		/* For 82575, context index must be unique per ring. */
 		if (adapter->hw.mac.type == e1000_82575)
 			set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags);
 		adapter->tx_ring[i] = ring;
 	}
-	/* Restore the adapter's original node */
-	adapter->node = orig_node;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		if (orig_node == -1) {
-			int cur_node = next_online_node(adapter->node);
-			if (cur_node == MAX_NUMNODES)
-				cur_node = first_online_node;
-			adapter->node = cur_node;
-		}
-		ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL,
-				    adapter->node);
-		if (!ring)
-			ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL);
+		ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL);
 		if (!ring)
 			goto err;
 		ring->count = adapter->rx_ring_count;
 		ring->queue_index = i;
 		ring->dev = &adapter->pdev->dev;
 		ring->netdev = adapter->netdev;
-		ring->numa_node = adapter->node;
 		/* set flag indicating ring supports SCTP checksum offload */
 		if (adapter->hw.mac.type >= e1000_82576)
 			set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags);
@@ -742,16 +719,12 @@ static int igb_alloc_queues(struct igb_adapter *adapter)
 
 		adapter->rx_ring[i] = ring;
 	}
-	/* Restore the adapter's original node */
-	adapter->node = orig_node;
 
 	igb_cache_ring_register(adapter);
 
 	return 0;
 
 err:
-	/* Restore the adapter's original node */
-	adapter->node = orig_node;
 	igb_free_queues(adapter);
 
 	return -ENOMEM;
@@ -1117,24 +1090,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter)
 	struct igb_q_vector *q_vector;
 	struct e1000_hw *hw = &adapter->hw;
 	int v_idx;
-	int orig_node = adapter->node;
 
 	for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) {
-		if ((adapter->num_q_vectors == (adapter->num_rx_queues +
-						adapter->num_tx_queues)) &&
-		    (adapter->num_rx_queues == v_idx))
-			adapter->node = orig_node;
-		if (orig_node == -1) {
-			int cur_node = next_online_node(adapter->node);
-			if (cur_node == MAX_NUMNODES)
-				cur_node = first_online_node;
-			adapter->node = cur_node;
-		}
-		q_vector = kzalloc_node(sizeof(struct igb_q_vector), GFP_KERNEL,
-					adapter->node);
-		if (!q_vector)
-			q_vector = kzalloc(sizeof(struct igb_q_vector),
-					   GFP_KERNEL);
+		q_vector = kzalloc(sizeof(struct igb_q_vector),
+				   GFP_KERNEL);
 		if (!q_vector)
 			goto err_out;
 		q_vector->adapter = adapter;
@@ -1143,14 +1102,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter)
 		netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll, 64);
 		adapter->q_vector[v_idx] = q_vector;
 	}
-	/* Restore the adapter's original node */
-	adapter->node = orig_node;
 
 	return 0;
 
 err_out:
-	/* Restore the adapter's original node */
-	adapter->node = orig_node;
 	igb_free_q_vectors(adapter);
 	return -ENOMEM;
 }
@@ -1751,6 +1706,11 @@ void igb_reset(struct igb_adapter *adapter)
 	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
 	wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);
 
+#ifdef CONFIG_IGB_PTP
+	/* Re-enable PTP, where applicable. */
+	igb_ptp_reset(adapter);
+#endif /* CONFIG_IGB_PTP */
+
 	igb_get_phy_info(hw);
 }
 
@@ -2180,11 +2140,12 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	}
 
 #endif
+
 #ifdef CONFIG_IGB_PTP
 	/* do hw tstamp init after resetting */
 	igb_ptp_init(adapter);
+#endif /* CONFIG_IGB_PTP */
 
-#endif
 	dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
 	/* print bus type/speed/width info */
 	dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n",
@@ -2259,9 +2220,9 @@ static void __devexit igb_remove(struct pci_dev *pdev)
 
 	pm_runtime_get_noresume(&pdev->dev);
 #ifdef CONFIG_IGB_PTP
-	igb_ptp_remove(adapter);
+	igb_ptp_stop(adapter);
+#endif /* CONFIG_IGB_PTP */
 
-#endif
 	/*
 	 * The watchdog timer may be rescheduled, so explicitly
 	 * disable watchdog from being rescheduled.
@@ -2294,11 +2255,11 @@ static void __devexit igb_remove(struct pci_dev *pdev)
 	/* reclaim resources allocated to VFs */
 	if (adapter->vf_data) {
 		/* disable iov and allow time for transactions to clear */
-		if (!igb_check_vf_assignment(adapter)) {
+		if (igb_vfs_are_assigned(adapter)) {
+			dev_info(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n");
+		} else {
 			pci_disable_sriov(pdev);
 			msleep(500);
-		} else {
-			dev_info(&pdev->dev, "VF(s) assigned to guests!\n");
 		}
 
 		kfree(adapter->vf_data);
@@ -2338,7 +2299,7 @@ static void __devinit igb_probe_vfs(struct igb_adapter * adapter)
 #ifdef CONFIG_PCI_IOV
 	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
-	int old_vfs = igb_find_enabled_vfs(adapter);
+	int old_vfs = pci_num_vf(adapter->pdev);
 	int i;
 
 	/* Virtualization features not supported on i210 family. */
@@ -2418,8 +2379,6 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 				  VLAN_HLEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
-	adapter->node = -1;
-
 	spin_lock_init(&adapter->stats64_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
@@ -2666,13 +2625,11 @@ static int igb_close(struct net_device *netdev)
 int igb_setup_tx_resources(struct igb_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
-	int orig_node = dev_to_node(dev);
 	int size;
 
 	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
-	tx_ring->tx_buffer_info = vzalloc_node(size, tx_ring->numa_node);
-	if (!tx_ring->tx_buffer_info)
-		tx_ring->tx_buffer_info = vzalloc(size);
+
+	tx_ring->tx_buffer_info = vzalloc(size);
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
@@ -2680,18 +2637,10 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
 	tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 
-	set_dev_node(dev, tx_ring->numa_node);
 	tx_ring->desc = dma_alloc_coherent(dev,
 					   tx_ring->size,
 					   &tx_ring->dma,
 					   GFP_KERNEL);
-	set_dev_node(dev, orig_node);
-	if (!tx_ring->desc)
-		tx_ring->desc = dma_alloc_coherent(dev,
-						   tx_ring->size,
-						   &tx_ring->dma,
-						   GFP_KERNEL);
-
 	if (!tx_ring->desc)
 		goto err;
 
@@ -2702,8 +2651,8 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
 
 err:
 	vfree(tx_ring->tx_buffer_info);
-	dev_err(dev,
-		"Unable to allocate memory for the transmit descriptor ring\n");
+	tx_ring->tx_buffer_info = NULL;
+	dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n");
 	return -ENOMEM;
 }
 
@@ -2820,34 +2769,23 @@ static void igb_configure_tx(struct igb_adapter *adapter)
 int igb_setup_rx_resources(struct igb_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int orig_node = dev_to_node(dev);
-	int size, desc_len;
+	int size;
 
 	size = sizeof(struct igb_rx_buffer) * rx_ring->count;
-	rx_ring->rx_buffer_info = vzalloc_node(size, rx_ring->numa_node);
-	if (!rx_ring->rx_buffer_info)
-		rx_ring->rx_buffer_info = vzalloc(size);
+
+	rx_ring->rx_buffer_info = vzalloc(size);
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
-	desc_len = sizeof(union e1000_adv_rx_desc);
 
 	/* Round up to nearest 4K */
-	rx_ring->size = rx_ring->count * desc_len;
+	rx_ring->size = rx_ring->count * sizeof(union e1000_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 
-	set_dev_node(dev, rx_ring->numa_node);
 	rx_ring->desc = dma_alloc_coherent(dev,
 					   rx_ring->size,
 					   &rx_ring->dma,
 					   GFP_KERNEL);
-	set_dev_node(dev, orig_node);
-	if (!rx_ring->desc)
-		rx_ring->desc = dma_alloc_coherent(dev,
-						   rx_ring->size,
-						   &rx_ring->dma,
-						   GFP_KERNEL);
-
 	if (!rx_ring->desc)
 		goto err;
 
@@ -2859,8 +2797,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 err:
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
-	dev_err(dev, "Unable to allocate memory for the receive descriptor"
-		" ring\n");
+	dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n");
 	return -ENOMEM;
 }
 
@@ -2898,57 +2835,48 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 mrqc, rxcsum;
-	u32 j, num_rx_queues, shift = 0, shift2 = 0;
-	union e1000_reta {
-		u32 dword;
-		u8  bytes[4];
-	} reta;
-	static const u8 rsshash[40] = {
-		0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2, 0x41, 0x67,
-		0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0, 0xd0, 0xca, 0x2b, 0xcb,
-		0xae, 0x7b, 0x30, 0xb4,	0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30,
-		0xf2, 0x0c, 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa };
+	u32 j, num_rx_queues, shift = 0;
+	static const u32 rsskey[10] = { 0xDA565A6D, 0xC20E5B25, 0x3D256741,
+					0xB08FA343, 0xCB2BCAD0, 0xB4307BAE,
+					0xA32DCB77, 0x0CF23080, 0x3BB7426A,
+					0xFA01ACBE };
 
 	/* Fill out hash function seeds */
-	for (j = 0; j < 10; j++) {
-		u32 rsskey = rsshash[(j * 4)];
-		rsskey |= rsshash[(j * 4) + 1] << 8;
-		rsskey |= rsshash[(j * 4) + 2] << 16;
-		rsskey |= rsshash[(j * 4) + 3] << 24;
-		array_wr32(E1000_RSSRK(0), j, rsskey);
-	}
+	for (j = 0; j < 10; j++)
+		wr32(E1000_RSSRK(j), rsskey[j]);
 
 	num_rx_queues = adapter->rss_queues;
 
-	if (adapter->vfs_allocated_count) {
-		/* 82575 and 82576 supports 2 RSS queues for VMDq */
-		switch (hw->mac.type) {
-		case e1000_i350:
-		case e1000_82580:
-			num_rx_queues = 1;
-			shift = 0;
-			break;
-		case e1000_82576:
+	switch (hw->mac.type) {
+	case e1000_82575:
+		shift = 6;
+		break;
+	case e1000_82576:
+		/* 82576 supports 2 RSS queues for SR-IOV */
+		if (adapter->vfs_allocated_count) {
 			shift = 3;
 			num_rx_queues = 2;
-			break;
-		case e1000_82575:
-			shift = 2;
-			shift2 = 6;
-		default:
-			break;
 		}
-	} else {
-		if (hw->mac.type == e1000_82575)
-			shift = 6;
+		break;
+	default:
+		break;
 	}
 
-	for (j = 0; j < (32 * 4); j++) {
-		reta.bytes[j & 3] = (j % num_rx_queues) << shift;
-		if (shift2)
-			reta.bytes[j & 3] |= num_rx_queues << shift2;
-		if ((j & 3) == 3)
-			wr32(E1000_RETA(j >> 2), reta.dword);
+	/*
+	 * Populate the indirection table 4 entries at a time.  To do this
+	 * we are generating the results for n and n+2 and then interleaving
+	 * those with the results with n+1 and n+3.
+	 */
+	for (j = 0; j < 32; j++) {
+		/* first pass generates n and n+2 */
+		u32 base = ((j * 0x00040004) + 0x00020000) * num_rx_queues;
+		u32 reta = (base & 0x07800780) >> (7 - shift);
+
+		/* second pass generates n+1 and n+3 */
+		base += 0x00010001 * num_rx_queues;
+		reta |= (base & 0x07800780) << (1 + shift);
+
+		wr32(E1000_RETA(j), reta);
 	}
 
 	/*
@@ -3184,8 +3112,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 #endif
 	srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
+#ifdef CONFIG_IGB_PTP
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
+#endif /* CONFIG_IGB_PTP */
 	/* Only set Drop Enable if we are supporting multiple queues */
 	if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1)
 		srrctl |= E1000_SRRCTL_DROP_EN;
@@ -3269,20 +3199,20 @@ void igb_unmap_and_free_tx_resource(struct igb_ring *ring,
 {
 	if (tx_buffer->skb) {
 		dev_kfree_skb_any(tx_buffer->skb);
-		if (tx_buffer->dma)
+		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
-					 tx_buffer->dma,
-					 tx_buffer->length,
+					 dma_unmap_addr(tx_buffer, dma),
+					 dma_unmap_len(tx_buffer, len),
 					 DMA_TO_DEVICE);
-	} else if (tx_buffer->dma) {
+	} else if (dma_unmap_len(tx_buffer, len)) {
 		dma_unmap_page(ring->dev,
-			       tx_buffer->dma,
-			       tx_buffer->length,
+			       dma_unmap_addr(tx_buffer, dma),
+			       dma_unmap_len(tx_buffer, len),
 			       DMA_TO_DEVICE);
 	}
 	tx_buffer->next_to_watch = NULL;
 	tx_buffer->skb = NULL;
-	tx_buffer->dma = 0;
+	dma_unmap_len_set(tx_buffer, len, 0);
 	/* buffer_info must be completely set up in the transmit path */
 }
 
@@ -4229,9 +4159,11 @@ static __le32 igb_tx_cmd_type(u32 tx_flags)
 	if (tx_flags & IGB_TX_FLAGS_VLAN)
 		cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE);
 
+#ifdef CONFIG_IGB_PTP
 	/* set timestamp bit if present */
-	if (tx_flags & IGB_TX_FLAGS_TSTAMP)
+	if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP))
 		cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP);
+#endif /* CONFIG_IGB_PTP */
 
 	/* set segmentation bits for TSO */
 	if (tx_flags & IGB_TX_FLAGS_TSO)
@@ -4275,7 +4207,7 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 		       const u8 hdr_len)
 {
 	struct sk_buff *skb = first->skb;
-	struct igb_tx_buffer *tx_buffer_info;
+	struct igb_tx_buffer *tx_buffer;
 	union e1000_adv_tx_desc *tx_desc;
 	dma_addr_t dma;
 	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
@@ -4296,8 +4228,8 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 		goto dma_error;
 
 	/* record length, and DMA address */
-	first->length = size;
-	first->dma = dma;
+	dma_unmap_len_set(first, len, size);
+	dma_unmap_addr_set(first, dma, dma);
 	tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
 	for (;;) {
@@ -4339,9 +4271,9 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 		if (dma_mapping_error(tx_ring->dev, dma))
 			goto dma_error;
 
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		tx_buffer_info->length = size;
-		tx_buffer_info->dma = dma;
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+		dma_unmap_len_set(tx_buffer, len, size);
+		dma_unmap_addr_set(tx_buffer, dma, dma);
 
 		tx_desc->read.olinfo_status = 0;
 		tx_desc->read.buffer_addr = cpu_to_le64(dma);
@@ -4392,9 +4324,9 @@ dma_error:
 
 	/* clear dma mappings for failed tx_buffer_info map */
 	for (;;) {
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
-		if (tx_buffer_info == first)
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+		if (tx_buffer == first)
 			break;
 		if (i == 0)
 			i = tx_ring->count;
@@ -4440,6 +4372,9 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size)
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 				struct igb_ring *tx_ring)
 {
+#ifdef CONFIG_IGB_PTP
+	struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);
+#endif /* CONFIG_IGB_PTP */
 	struct igb_tx_buffer *first;
 	int tso;
 	u32 tx_flags = 0;
@@ -4462,10 +4397,17 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+#ifdef CONFIG_IGB_PTP
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+		     !(adapter->ptp_tx_skb))) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
+
+		adapter->ptp_tx_skb = skb_get(skb);
+		if (adapter->hw.mac.type == e1000_82576)
+			schedule_work(&adapter->ptp_tx_work);
 	}
+#endif /* CONFIG_IGB_PTP */
 
 	if (vlan_tx_tag_present(skb)) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
@@ -4661,11 +4603,13 @@ void igb_update_stats(struct igb_adapter *adapter,
 	bytes = 0;
 	packets = 0;
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		u32 rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0x0FFF;
+		u32 rqdpc = rd32(E1000_RQDPC(i));
 		struct igb_ring *ring = adapter->rx_ring[i];
 
-		ring->rx_stats.drops += rqdpc_tmp;
-		net_stats->rx_fifo_errors += rqdpc_tmp;
+		if (rqdpc) {
+			ring->rx_stats.drops += rqdpc;
+			net_stats->rx_fifo_errors += rqdpc;
+		}
 
 		do {
 			start = u64_stats_fetch_begin_bh(&ring->rx_syncp);
@@ -4755,7 +4699,11 @@ void igb_update_stats(struct igb_adapter *adapter,
 	reg = rd32(E1000_CTRL_EXT);
 	if (!(reg & E1000_CTRL_EXT_LINK_MODE_MASK)) {
 		adapter->stats.rxerrc += rd32(E1000_RXERRC);
-		adapter->stats.tncrs += rd32(E1000_TNCRS);
+
+		/* this stat has invalid values on i210/i211 */
+		if ((hw->mac.type != e1000_i210) &&
+		    (hw->mac.type != e1000_i211))
+			adapter->stats.tncrs += rd32(E1000_TNCRS);
 	}
 
 	adapter->stats.tsctc += rd32(E1000_TSCTC);
@@ -4852,6 +4800,19 @@ static irqreturn_t igb_msix_other(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	wr32(E1000_EIMS, adapter->eims_other);
 
 	return IRQ_HANDLED;
@@ -5002,102 +4963,43 @@ static int igb_notify_dca(struct notifier_block *nb, unsigned long event,
 static int igb_vf_configure(struct igb_adapter *adapter, int vf)
 {
 	unsigned char mac_addr[ETH_ALEN];
-	struct pci_dev *pdev = adapter->pdev;
-	struct e1000_hw *hw = &adapter->hw;
-	struct pci_dev *pvfdev;
-	unsigned int device_id;
-	u16 thisvf_devfn;
 
 	eth_random_addr(mac_addr);
 	igb_set_vf_mac(adapter, vf, mac_addr);
 
-	switch (adapter->hw.mac.type) {
-	case e1000_82576:
-		device_id = IGB_82576_VF_DEV_ID;
-		/* VF Stride for 82576 is 2 */
-		thisvf_devfn = (pdev->devfn + 0x80 + (vf << 1)) |
-			(pdev->devfn & 1);
-		break;
-	case e1000_i350:
-		device_id = IGB_I350_VF_DEV_ID;
-		/* VF Stride for I350 is 4 */
-		thisvf_devfn = (pdev->devfn + 0x80 + (vf << 2)) |
-				(pdev->devfn & 3);
-		break;
-	default:
-		device_id = 0;
-		thisvf_devfn = 0;
-		break;
-	}
-
-	pvfdev = pci_get_device(hw->vendor_id, device_id, NULL);
-	while (pvfdev) {
-		if (pvfdev->devfn == thisvf_devfn)
-			break;
-		pvfdev = pci_get_device(hw->vendor_id,
-					device_id, pvfdev);
-	}
-
-	if (pvfdev)
-		adapter->vf_data[vf].vfdev = pvfdev;
-	else
-		dev_err(&pdev->dev,
-			"Couldn't find pci dev ptr for VF %4.4x\n",
-			thisvf_devfn);
-	return pvfdev != NULL;
+	return 0;
 }
 
-static int igb_find_enabled_vfs(struct igb_adapter *adapter)
+static bool igb_vfs_are_assigned(struct igb_adapter *adapter)
 {
-	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
-	struct pci_dev *pvfdev;
-	u16 vf_devfn = 0;
-	u16 vf_stride;
-	unsigned int device_id;
-	int vfs_found = 0;
+	struct pci_dev *vfdev;
+	int dev_id;
 
 	switch (adapter->hw.mac.type) {
 	case e1000_82576:
-		device_id = IGB_82576_VF_DEV_ID;
-		/* VF Stride for 82576 is 2 */
-		vf_stride = 2;
+		dev_id = IGB_82576_VF_DEV_ID;
 		break;
 	case e1000_i350:
-		device_id = IGB_I350_VF_DEV_ID;
-		/* VF Stride for I350 is 4 */
-		vf_stride = 4;
+		dev_id = IGB_I350_VF_DEV_ID;
 		break;
 	default:
-		device_id = 0;
-		vf_stride = 0;
-		break;
-	}
-
-	vf_devfn = pdev->devfn + 0x80;
-	pvfdev = pci_get_device(hw->vendor_id, device_id, NULL);
-	while (pvfdev) {
-		if (pvfdev->devfn == vf_devfn &&
-		    (pvfdev->bus->number >= pdev->bus->number))
-			vfs_found++;
-		vf_devfn += vf_stride;
-		pvfdev = pci_get_device(hw->vendor_id,
-					device_id, pvfdev);
+		return false;
 	}
 
-	return vfs_found;
-}
-
-static int igb_check_vf_assignment(struct igb_adapter *adapter)
-{
-	int i;
-	for (i = 0; i < adapter->vfs_allocated_count; i++) {
-		if (adapter->vf_data[i].vfdev) {
-			if (adapter->vf_data[i].vfdev->dev_flags &
-			    PCI_DEV_FLAGS_ASSIGNED)
+	/* loop through all the VFs to see if we own any that are assigned */
+	vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL);
+	while (vfdev) {
+		/* if we don't own it we don't care */
+		if (vfdev->is_virtfn && vfdev->physfn == pdev) {
+			/* if it is assigned we cannot release it */
+			if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED)
 				return true;
 		}
+
+		vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev);
 	}
+
 	return false;
 }
 
@@ -5643,6 +5545,19 @@ static irqreturn_t igb_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5684,6 +5599,19 @@ static irqreturn_t igb_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5743,37 +5671,6 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	return 0;
 }
 
-#ifdef CONFIG_IGB_PTP
-/**
- * igb_tx_hwtstamp - utility function which checks for TX time stamp
- * @q_vector: pointer to q_vector containing needed info
- * @buffer: pointer to igb_tx_buffer structure
- *
- * If we were asked to do hardware stamping and such a time stamp is
- * available, then it must have been for this skb here because we only
- * allow only one such packet into the queue.
- */
-static void igb_tx_hwtstamp(struct igb_q_vector *q_vector,
-			    struct igb_tx_buffer *buffer_info)
-{
-	struct igb_adapter *adapter = q_vector->adapter;
-	struct e1000_hw *hw = &adapter->hw;
-	struct skb_shared_hwtstamps shhwtstamps;
-	u64 regval;
-
-	/* if skb does not support hw timestamp or TX stamp not valid exit */
-	if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) ||
-	    !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID))
-		return;
-
-	regval = rd32(E1000_TXSTMPL);
-	regval |= (u64)rd32(E1000_TXSTMPH) << 32;
-
-	igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
-	skb_tstamp_tx(buffer_info->skb, &shhwtstamps);
-}
-
-#endif
 /**
  * igb_clean_tx_irq - Reclaim resources after transmit completes
  * @q_vector: pointer to q_vector containing needed info
@@ -5785,7 +5682,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 	struct igb_adapter *adapter = q_vector->adapter;
 	struct igb_ring *tx_ring = q_vector->tx.ring;
 	struct igb_tx_buffer *tx_buffer;
-	union e1000_adv_tx_desc *tx_desc, *eop_desc;
+	union e1000_adv_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned int budget = q_vector->tx.work_limit;
 	unsigned int i = tx_ring->next_to_clean;
@@ -5797,16 +5694,16 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 	tx_desc = IGB_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
-	for (; budget; budget--) {
-		eop_desc = tx_buffer->next_to_watch;
-
-		/* prevent any other reads prior to eop_desc */
-		rmb();
+	do {
+		union e1000_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;
 
 		/* if next_to_watch is not set then there is no work pending */
 		if (!eop_desc)
 			break;
 
+		/* prevent any other reads prior to eop_desc */
+		rmb();
+
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)))
 			break;
@@ -5818,25 +5715,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
-#ifdef CONFIG_IGB_PTP
-		/* retrieve hardware timestamp */
-		igb_tx_hwtstamp(q_vector, tx_buffer);
-
-#endif
 		/* free the skb */
 		dev_kfree_skb_any(tx_buffer->skb);
-		tx_buffer->skb = NULL;
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
-				 tx_buffer->dma,
-				 tx_buffer->length,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
 				 DMA_TO_DEVICE);
 
+		/* clear tx_buffer data */
+		tx_buffer->skb = NULL;
+		dma_unmap_len_set(tx_buffer, len, 0);
+
 		/* clear last DMA location and unmap remaining buffers */
 		while (tx_desc != eop_desc) {
-			tx_buffer->dma = 0;
-
 			tx_buffer++;
 			tx_desc++;
 			i++;
@@ -5847,17 +5740,15 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 			}
 
 			/* unmap any remaining paged data */
-			if (tx_buffer->dma) {
+			if (dma_unmap_len(tx_buffer, len)) {
 				dma_unmap_page(tx_ring->dev,
-					       tx_buffer->dma,
-					       tx_buffer->length,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
 					       DMA_TO_DEVICE);
+				dma_unmap_len_set(tx_buffer, len, 0);
 			}
 		}
 
-		/* clear last DMA location */
-		tx_buffer->dma = 0;
-
 		/* move us one more past the eop_desc for start of next pkt */
 		tx_buffer++;
 		tx_desc++;
@@ -5867,7 +5758,13 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 			tx_buffer = tx_ring->tx_buffer_info;
 			tx_desc = IGB_TX_DESC(tx_ring, 0);
 		}
-	}
+
+		/* issue prefetch for next Tx descriptor */
+		prefetch(tx_desc);
+
+		/* update budget accounting */
+		budget--;
+	} while (likely(budget));
 
 	netdev_tx_completed_queue(txring_txq(tx_ring),
 				  total_packets, total_bytes);
@@ -5883,12 +5780,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 	if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
 		struct e1000_hw *hw = &adapter->hw;
 
-		eop_desc = tx_buffer->next_to_watch;
-
 		/* Detect a transmit hang in hardware, this serializes the
 		 * check with the clearing of time_stamp and movement of i */
 		clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags);
-		if (eop_desc &&
+		if (tx_buffer->next_to_watch &&
 		    time_after(jiffies, tx_buffer->time_stamp +
 			       (adapter->tx_timeout_factor * HZ)) &&
 		    !(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) {
@@ -5912,9 +5807,9 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 				tx_ring->next_to_use,
 				tx_ring->next_to_clean,
 				tx_buffer->time_stamp,
-				eop_desc,
+				tx_buffer->next_to_watch,
 				jiffies,
-				eop_desc->wb.status);
+				tx_buffer->next_to_watch->wb.status);
 			netif_stop_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 
@@ -5994,47 +5889,6 @@ static inline void igb_rx_hash(struct igb_ring *ring,
 		skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
 }
 
-#ifdef CONFIG_IGB_PTP
-static void igb_rx_hwtstamp(struct igb_q_vector *q_vector,
-			    union e1000_adv_rx_desc *rx_desc,
-			    struct sk_buff *skb)
-{
-	struct igb_adapter *adapter = q_vector->adapter;
-	struct e1000_hw *hw = &adapter->hw;
-	u64 regval;
-
-	if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP |
-				       E1000_RXDADV_STAT_TS))
-		return;
-
-	/*
-	 * If this bit is set, then the RX registers contain the time stamp. No
-	 * other packet will be time stamped until we read these registers, so
-	 * read the registers to make them available again. Because only one
-	 * packet can be time stamped at a time, we know that the register
-	 * values must belong to this one here and therefore we don't need to
-	 * compare any of the additional attributes stored for it.
-	 *
-	 * If nothing went wrong, then it should have a shared tx_flags that we
-	 * can turn into a skb_shared_hwtstamps.
-	 */
-	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
-		u32 *stamp = (u32 *)skb->data;
-		regval = le32_to_cpu(*(stamp + 2));
-		regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32;
-		skb_pull(skb, IGB_TS_HDR_LEN);
-	} else {
-		if(!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID))
-			return;
-
-		regval = rd32(E1000_RXSTMPL);
-		regval |= (u64)rd32(E1000_RXSTMPH) << 32;
-	}
-
-	igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
-}
-
-#endif
 static void igb_rx_vlan(struct igb_ring *ring,
 			union e1000_adv_rx_desc *rx_desc,
 			struct sk_buff *skb)
@@ -6146,8 +6000,8 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
 		}
 
 #ifdef CONFIG_IGB_PTP
-		igb_rx_hwtstamp(q_vector, rx_desc, skb);
-#endif
+		igb_ptp_rx_hwtstamp(q_vector, rx_desc, skb);
+#endif /* CONFIG_IGB_PTP */
 		igb_rx_hash(rx_ring, rx_desc, skb);
 		igb_rx_checksum(rx_ring, rx_desc, skb);
 		igb_rx_vlan(rx_ring, rx_desc, skb);
@@ -6341,181 +6195,6 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 }
 
 /**
- * igb_hwtstamp_ioctl - control hardware time stamping
- * @netdev:
- * @ifreq:
- * @cmd:
- *
- * Outgoing time stamping can be enabled and disabled. Play nice and
- * disable it when requested, although it shouldn't case any overhead
- * when no packet needs it. At most one packet in the queue may be
- * marked for time stamping, otherwise it would be impossible to tell
- * for sure to which packet the hardware time stamp belongs.
- *
- * Incoming time stamping has to be configured via the hardware
- * filters. Not all combinations are supported, in particular event
- * type has to be specified. Matching the kind of event packet is
- * not supported, with the exception of "all V2 events regardless of
- * level 2 or 4".
- *
- **/
-static int igb_hwtstamp_ioctl(struct net_device *netdev,
-			      struct ifreq *ifr, int cmd)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
-	struct hwtstamp_config config;
-	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
-	u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
-	u32 tsync_rx_cfg = 0;
-	bool is_l4 = false;
-	bool is_l2 = false;
-	u32 regval;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	/* reserved for future extensions */
-	if (config.flags)
-		return -EINVAL;
-
-	switch (config.tx_type) {
-	case HWTSTAMP_TX_OFF:
-		tsync_tx_ctl = 0;
-	case HWTSTAMP_TX_ON:
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	switch (config.rx_filter) {
-	case HWTSTAMP_FILTER_NONE:
-		tsync_rx_ctl = 0;
-		break;
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
-	case HWTSTAMP_FILTER_ALL:
-		/*
-		 * register TSYNCRXCFG must be set, therefore it is not
-		 * possible to time stamp both Sync and Delay_Req messages
-		 * => fall back to time stamping all packets
-		 */
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
-		break;
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE;
-		is_l4 = true;
-		break;
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE;
-		is_l4 = true;
-		break;
-	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
-		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE;
-		is_l2 = true;
-		is_l4 = true;
-		config.rx_filter = HWTSTAMP_FILTER_SOME;
-		break;
-	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
-	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
-		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE;
-		is_l2 = true;
-		is_l4 = true;
-		config.rx_filter = HWTSTAMP_FILTER_SOME;
-		break;
-	case HWTSTAMP_FILTER_PTP_V2_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2;
-		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		is_l2 = true;
-		is_l4 = true;
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	if (hw->mac.type == e1000_82575) {
-		if (tsync_rx_ctl | tsync_tx_ctl)
-			return -EINVAL;
-		return 0;
-	}
-
-	/*
-	 * Per-packet timestamping only works if all packets are
-	 * timestamped, so enable timestamping in all packets as
-	 * long as one rx filter was configured.
-	 */
-	if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) {
-		tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
-		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
-	}
-
-	/* enable/disable TX */
-	regval = rd32(E1000_TSYNCTXCTL);
-	regval &= ~E1000_TSYNCTXCTL_ENABLED;
-	regval |= tsync_tx_ctl;
-	wr32(E1000_TSYNCTXCTL, regval);
-
-	/* enable/disable RX */
-	regval = rd32(E1000_TSYNCRXCTL);
-	regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK);
-	regval |= tsync_rx_ctl;
-	wr32(E1000_TSYNCRXCTL, regval);
-
-	/* define which PTP packets are time stamped */
-	wr32(E1000_TSYNCRXCFG, tsync_rx_cfg);
-
-	/* define ethertype filter for timestamped packets */
-	if (is_l2)
-		wr32(E1000_ETQF(3),
-		                (E1000_ETQF_FILTER_ENABLE | /* enable filter */
-		                 E1000_ETQF_1588 | /* enable timestamping */
-		                 ETH_P_1588));     /* 1588 eth protocol type */
-	else
-		wr32(E1000_ETQF(3), 0);
-
-#define PTP_PORT 319
-	/* L4 Queue Filter[3]: filter by destination port and protocol */
-	if (is_l4) {
-		u32 ftqf = (IPPROTO_UDP /* UDP */
-			| E1000_FTQF_VF_BP /* VF not compared */
-			| E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */
-			| E1000_FTQF_MASK); /* mask all inputs */
-		ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */
-
-		wr32(E1000_IMIR(3), htons(PTP_PORT));
-		wr32(E1000_IMIREXT(3),
-		     (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP));
-		if (hw->mac.type == e1000_82576) {
-			/* enable source port check */
-			wr32(E1000_SPQF(3), htons(PTP_PORT));
-			ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP;
-		}
-		wr32(E1000_FTQF(3), ftqf);
-	} else {
-		wr32(E1000_FTQF(3), E1000_FTQF_MASK);
-	}
-	wrfl();
-
-	adapter->hwtstamp_config = config;
-
-	/* clear TX/RX time stamp registers, just to be sure */
-	regval = rd32(E1000_TXSTMPH);
-	regval = rd32(E1000_RXSTMPH);
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
-}
-
-/**
  * igb_ioctl -
  * @netdev:
  * @ifreq:
@@ -6528,8 +6207,10 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
 		return igb_mii_ioctl(netdev, ifr, cmd);
+#ifdef CONFIG_IGB_PTP
 	case SIOCSHWTSTAMP:
-		return igb_hwtstamp_ioctl(netdev, ifr, cmd);
+		return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd);
+#endif /* CONFIG_IGB_PTP */
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -6667,6 +6348,10 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx)
 	default:
 		goto err_inval;
 	}
+
+	/* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+	adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
 	return 0;
 
 err_inval:
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index c846ea9131a3..ee21445157a3 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -69,22 +69,22 @@
  *   2^40 * 10^-9 /  60  = 18.3 minutes.
  */
 
-#define IGB_OVERFLOW_PERIOD	(HZ * 60 * 9)
-#define INCPERIOD_82576		(1 << E1000_TIMINCA_16NS_SHIFT)
-#define INCVALUE_82576_MASK	((1 << E1000_TIMINCA_16NS_SHIFT) - 1)
-#define INCVALUE_82576		(16 << IGB_82576_TSYNC_SHIFT)
-#define IGB_NBITS_82580		40
+#define IGB_SYSTIM_OVERFLOW_PERIOD	(HZ * 60 * 9)
+#define INCPERIOD_82576			(1 << E1000_TIMINCA_16NS_SHIFT)
+#define INCVALUE_82576_MASK		((1 << E1000_TIMINCA_16NS_SHIFT) - 1)
+#define INCVALUE_82576			(16 << IGB_82576_TSYNC_SHIFT)
+#define IGB_NBITS_82580			40
 
 /*
  * SYSTIM read access for the 82576
  */
 
-static cycle_t igb_82576_systim_read(const struct cyclecounter *cc)
+static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc)
 {
-	u64 val;
-	u32 lo, hi;
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
+	u64 val;
+	u32 lo, hi;
 
 	lo = rd32(E1000_SYSTIML);
 	hi = rd32(E1000_SYSTIMH);
@@ -99,12 +99,12 @@ static cycle_t igb_82576_systim_read(const struct cyclecounter *cc)
  * SYSTIM read access for the 82580
  */
 
-static cycle_t igb_82580_systim_read(const struct cyclecounter *cc)
+static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc)
 {
-	u64 val;
-	u32 lo, hi, jk;
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
+	u64 val;
+	u32 lo, hi, jk;
 
 	/*
 	 * The timestamp latches on lowest register read. For the 82580
@@ -122,16 +122,101 @@ static cycle_t igb_82580_systim_read(const struct cyclecounter *cc)
 }
 
 /*
+ * SYSTIM read access for I210/I211
+ */
+
+static void igb_ptp_read_i210(struct igb_adapter *adapter, struct timespec *ts)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 sec, nsec, jk;
+
+	/*
+	 * The timestamp latches on lowest register read. For I210/I211, the
+	 * lowest register is SYSTIMR. Since we only need to provide nanosecond
+	 * resolution, we can ignore it.
+	 */
+	jk = rd32(E1000_SYSTIMR);
+	nsec = rd32(E1000_SYSTIML);
+	sec = rd32(E1000_SYSTIMH);
+
+	ts->tv_sec = sec;
+	ts->tv_nsec = nsec;
+}
+
+static void igb_ptp_write_i210(struct igb_adapter *adapter,
+			       const struct timespec *ts)
+{
+	struct e1000_hw *hw = &adapter->hw;
+
+	/*
+	 * Writing the SYSTIMR register is not necessary as it only provides
+	 * sub-nanosecond resolution.
+	 */
+	wr32(E1000_SYSTIML, ts->tv_nsec);
+	wr32(E1000_SYSTIMH, ts->tv_sec);
+}
+
+/**
+ * igb_ptp_systim_to_hwtstamp - convert system time value to hw timestamp
+ * @adapter: board private structure
+ * @hwtstamps: timestamp structure to update
+ * @systim: unsigned 64bit system time value.
+ *
+ * We need to convert the system time value stored in the RX/TXSTMP registers
+ * into a hwtstamp which can be used by the upper level timestamping functions.
+ *
+ * The 'tmreg_lock' spinlock is used to protect the consistency of the
+ * system time value. This is needed because reading the 64 bit time
+ * value involves reading two (or three) 32 bit registers. The first
+ * read latches the value. Ditto for writing.
+ *
+ * In addition, here have extended the system time with an overflow
+ * counter in software.
+ **/
+static void igb_ptp_systim_to_hwtstamp(struct igb_adapter *adapter,
+				       struct skb_shared_hwtstamps *hwtstamps,
+				       u64 systim)
+{
+	unsigned long flags;
+	u64 ns;
+
+	switch (adapter->hw.mac.type) {
+	case e1000_82576:
+	case e1000_82580:
+	case e1000_i350:
+		spin_lock_irqsave(&adapter->tmreg_lock, flags);
+
+		ns = timecounter_cyc2time(&adapter->tc, systim);
+
+		spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+		memset(hwtstamps, 0, sizeof(*hwtstamps));
+		hwtstamps->hwtstamp = ns_to_ktime(ns);
+		break;
+	case e1000_i210:
+	case e1000_i211:
+		memset(hwtstamps, 0, sizeof(*hwtstamps));
+		/* Upper 32 bits contain s, lower 32 bits contain ns. */
+		hwtstamps->hwtstamp = ktime_set(systim >> 32,
+						systim & 0xFFFFFFFF);
+		break;
+	default:
+		break;
+	}
+}
+
+/*
  * PTP clock operations
  */
 
-static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+static int igb_ptp_adjfreq_82576(struct ptp_clock_info *ptp, s32 ppb)
 {
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
+	int neg_adj = 0;
 	u64 rate;
 	u32 incvalue;
-	int neg_adj = 0;
-	struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
-	struct e1000_hw *hw = &igb->hw;
 
 	if (ppb < 0) {
 		neg_adj = 1;
@@ -153,13 +238,14 @@ static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	return 0;
 }
 
-static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb)
 {
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
+	int neg_adj = 0;
 	u64 rate;
 	u32 inca;
-	int neg_adj = 0;
-	struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
-	struct e1000_hw *hw = &igb->hw;
 
 	if (ppb < 0) {
 		neg_adj = 1;
@@ -178,11 +264,12 @@ static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	return 0;
 }
 
-static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta)
+static int igb_ptp_adjtime_82576(struct ptp_clock_info *ptp, s64 delta)
 {
-	s64 now;
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
 	unsigned long flags;
-	struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+	s64 now;
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
@@ -195,12 +282,32 @@ static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta)
 {
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	unsigned long flags;
+	struct timespec now, then = ns_to_timespec(delta);
+
+	spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+	igb_ptp_read_i210(igb, &now);
+	now = timespec_add(now, then);
+	igb_ptp_write_i210(igb, (const struct timespec *)&now);
+
+	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+	return 0;
+}
+
+static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
+				 struct timespec *ts)
+{
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	unsigned long flags;
 	u64 ns;
 	u32 remainder;
-	unsigned long flags;
-	struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
@@ -214,11 +321,29 @@ static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
 	return 0;
 }
 
-static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts)
+static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp,
+				struct timespec *ts)
 {
-	u64 ns;
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
 	unsigned long flags;
-	struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps);
+
+	spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+	igb_ptp_read_i210(igb, ts);
+
+	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+	return 0;
+}
+
+static int igb_ptp_settime_82576(struct ptp_clock_info *ptp,
+				 const struct timespec *ts)
+{
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	unsigned long flags;
+	u64 ns;
 
 	ns = ts->tv_sec * 1000000000ULL;
 	ns += ts->tv_nsec;
@@ -232,77 +357,369 @@ static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts)
 	return 0;
 }
 
-static int ptp_82576_enable(struct ptp_clock_info *ptp,
-			    struct ptp_clock_request *rq, int on)
+static int igb_ptp_settime_i210(struct ptp_clock_info *ptp,
+				const struct timespec *ts)
 {
-	return -EOPNOTSUPP;
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	unsigned long flags;
+
+	spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+	igb_ptp_write_i210(igb, ts);
+
+	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+	return 0;
 }
 
-static int ptp_82580_enable(struct ptp_clock_info *ptp,
-			    struct ptp_clock_request *rq, int on)
+static int igb_ptp_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *rq, int on)
 {
 	return -EOPNOTSUPP;
 }
 
-static void igb_overflow_check(struct work_struct *work)
+/**
+ * igb_ptp_tx_work
+ * @work: pointer to work struct
+ *
+ * This work function polls the TSYNCTXCTL valid bit to determine when a
+ * timestamp has been taken for the current stored skb.
+ */
+void igb_ptp_tx_work(struct work_struct *work)
+{
+	struct igb_adapter *adapter = container_of(work, struct igb_adapter,
+						   ptp_tx_work);
+	struct e1000_hw *hw = &adapter->hw;
+	u32 tsynctxctl;
+
+	if (!adapter->ptp_tx_skb)
+		return;
+
+	tsynctxctl = rd32(E1000_TSYNCTXCTL);
+	if (tsynctxctl & E1000_TSYNCTXCTL_VALID)
+		igb_ptp_tx_hwtstamp(adapter);
+	else
+		/* reschedule to check later */
+		schedule_work(&adapter->ptp_tx_work);
+}
+
+static void igb_ptp_overflow_check(struct work_struct *work)
 {
-	struct timespec ts;
 	struct igb_adapter *igb =
-		container_of(work, struct igb_adapter, overflow_work.work);
+		container_of(work, struct igb_adapter, ptp_overflow_work.work);
+	struct timespec ts;
 
-	igb_gettime(&igb->caps, &ts);
+	igb->ptp_caps.gettime(&igb->ptp_caps, &ts);
 
 	pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec);
 
-	schedule_delayed_work(&igb->overflow_work, IGB_OVERFLOW_PERIOD);
+	schedule_delayed_work(&igb->ptp_overflow_work,
+			      IGB_SYSTIM_OVERFLOW_PERIOD);
+}
+
+/**
+ * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp
+ * @adapter: Board private structure.
+ *
+ * If we were asked to do hardware stamping and such a time stamp is
+ * available, then it must have been for this skb here because we only
+ * allow only one such packet into the queue.
+ */
+void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	struct skb_shared_hwtstamps shhwtstamps;
+	u64 regval;
+
+	regval = rd32(E1000_TXSTMPL);
+	regval |= (u64)rd32(E1000_TXSTMPH) << 32;
+
+	igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
+	skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
+	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	adapter->ptp_tx_skb = NULL;
+}
+
+void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
+			 union e1000_adv_rx_desc *rx_desc,
+			 struct sk_buff *skb)
+{
+	struct igb_adapter *adapter = q_vector->adapter;
+	struct e1000_hw *hw = &adapter->hw;
+	u64 regval;
+
+	if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP |
+				       E1000_RXDADV_STAT_TS))
+		return;
+
+	/*
+	 * If this bit is set, then the RX registers contain the time stamp. No
+	 * other packet will be time stamped until we read these registers, so
+	 * read the registers to make them available again. Because only one
+	 * packet can be time stamped at a time, we know that the register
+	 * values must belong to this one here and therefore we don't need to
+	 * compare any of the additional attributes stored for it.
+	 *
+	 * If nothing went wrong, then it should have a shared tx_flags that we
+	 * can turn into a skb_shared_hwtstamps.
+	 */
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		u32 *stamp = (u32 *)skb->data;
+		regval = le32_to_cpu(*(stamp + 2));
+		regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32;
+		skb_pull(skb, IGB_TS_HDR_LEN);
+	} else {
+		if (!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID))
+			return;
+
+		regval = rd32(E1000_RXSTMPL);
+		regval |= (u64)rd32(E1000_RXSTMPH) << 32;
+	}
+
+	igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
+}
+
+/**
+ * igb_ptp_hwtstamp_ioctl - control hardware time stamping
+ * @netdev:
+ * @ifreq:
+ * @cmd:
+ *
+ * Outgoing time stamping can be enabled and disabled. Play nice and
+ * disable it when requested, although it shouldn't case any overhead
+ * when no packet needs it. At most one packet in the queue may be
+ * marked for time stamping, otherwise it would be impossible to tell
+ * for sure to which packet the hardware time stamp belongs.
+ *
+ * Incoming time stamping has to be configured via the hardware
+ * filters. Not all combinations are supported, in particular event
+ * type has to be specified. Matching the kind of event packet is
+ * not supported, with the exception of "all V2 events regardless of
+ * level 2 or 4".
+ *
+ **/
+int igb_ptp_hwtstamp_ioctl(struct net_device *netdev,
+			   struct ifreq *ifr, int cmd)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct hwtstamp_config config;
+	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
+	u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
+	u32 tsync_rx_cfg = 0;
+	bool is_l4 = false;
+	bool is_l2 = false;
+	u32 regval;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	/* reserved for future extensions */
+	if (config.flags)
+		return -EINVAL;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		tsync_tx_ctl = 0;
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		tsync_rx_ctl = 0;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_ALL:
+		/*
+		 * register TSYNCRXCFG must be set, therefore it is not
+		 * possible to time stamp both Sync and Delay_Req messages
+		 * => fall back to time stamping all packets
+		 */
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
+		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE;
+		is_l4 = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
+		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE;
+		is_l4 = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
+		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE;
+		is_l2 = true;
+		is_l4 = true;
+		config.rx_filter = HWTSTAMP_FILTER_SOME;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
+		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE;
+		is_l2 = true;
+		is_l4 = true;
+		config.rx_filter = HWTSTAMP_FILTER_SOME;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2;
+		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		is_l2 = true;
+		is_l4 = true;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (hw->mac.type == e1000_82575) {
+		if (tsync_rx_ctl | tsync_tx_ctl)
+			return -EINVAL;
+		return 0;
+	}
+
+	/*
+	 * Per-packet timestamping only works if all packets are
+	 * timestamped, so enable timestamping in all packets as
+	 * long as one rx filter was configured.
+	 */
+	if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) {
+		tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
+
+		if ((hw->mac.type == e1000_i210) ||
+		    (hw->mac.type == e1000_i211)) {
+			regval = rd32(E1000_RXPBS);
+			regval |= E1000_RXPBS_CFG_TS_EN;
+			wr32(E1000_RXPBS, regval);
+		}
+	}
+
+	/* enable/disable TX */
+	regval = rd32(E1000_TSYNCTXCTL);
+	regval &= ~E1000_TSYNCTXCTL_ENABLED;
+	regval |= tsync_tx_ctl;
+	wr32(E1000_TSYNCTXCTL, regval);
+
+	/* enable/disable RX */
+	regval = rd32(E1000_TSYNCRXCTL);
+	regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK);
+	regval |= tsync_rx_ctl;
+	wr32(E1000_TSYNCRXCTL, regval);
+
+	/* define which PTP packets are time stamped */
+	wr32(E1000_TSYNCRXCFG, tsync_rx_cfg);
+
+	/* define ethertype filter for timestamped packets */
+	if (is_l2)
+		wr32(E1000_ETQF(3),
+		     (E1000_ETQF_FILTER_ENABLE | /* enable filter */
+		      E1000_ETQF_1588 | /* enable timestamping */
+		      ETH_P_1588));     /* 1588 eth protocol type */
+	else
+		wr32(E1000_ETQF(3), 0);
+
+#define PTP_PORT 319
+	/* L4 Queue Filter[3]: filter by destination port and protocol */
+	if (is_l4) {
+		u32 ftqf = (IPPROTO_UDP /* UDP */
+			| E1000_FTQF_VF_BP /* VF not compared */
+			| E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */
+			| E1000_FTQF_MASK); /* mask all inputs */
+		ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */
+
+		wr32(E1000_IMIR(3), htons(PTP_PORT));
+		wr32(E1000_IMIREXT(3),
+		     (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP));
+		if (hw->mac.type == e1000_82576) {
+			/* enable source port check */
+			wr32(E1000_SPQF(3), htons(PTP_PORT));
+			ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP;
+		}
+		wr32(E1000_FTQF(3), ftqf);
+	} else {
+		wr32(E1000_FTQF(3), E1000_FTQF_MASK);
+	}
+	wrfl();
+
+	/* clear TX/RX time stamp registers, just to be sure */
+	regval = rd32(E1000_TXSTMPL);
+	regval = rd32(E1000_TXSTMPH);
+	regval = rd32(E1000_RXSTMPL);
+	regval = rd32(E1000_RXSTMPH);
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
 }
 
 void igb_ptp_init(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
 
 	switch (hw->mac.type) {
-	case e1000_i210:
-	case e1000_i211:
-	case e1000_i350:
+	case e1000_82576:
+		snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr);
+		adapter->ptp_caps.owner = THIS_MODULE;
+		adapter->ptp_caps.max_adj = 1000000000;
+		adapter->ptp_caps.n_ext_ts = 0;
+		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576;
+		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
+		adapter->ptp_caps.gettime = igb_ptp_gettime_82576;
+		adapter->ptp_caps.settime = igb_ptp_settime_82576;
+		adapter->ptp_caps.enable = igb_ptp_enable;
+		adapter->cc.read = igb_ptp_read_82576;
+		adapter->cc.mask = CLOCKSOURCE_MASK(64);
+		adapter->cc.mult = 1;
+		adapter->cc.shift = IGB_82576_TSYNC_SHIFT;
+		/* Dial the nominal frequency. */
+		wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+		break;
 	case e1000_82580:
-		adapter->caps.owner	= THIS_MODULE;
-		strcpy(adapter->caps.name, "igb-82580");
-		adapter->caps.max_adj	= 62499999;
-		adapter->caps.n_ext_ts	= 0;
-		adapter->caps.pps	= 0;
-		adapter->caps.adjfreq	= ptp_82580_adjfreq;
-		adapter->caps.adjtime	= igb_adjtime;
-		adapter->caps.gettime	= igb_gettime;
-		adapter->caps.settime	= igb_settime;
-		adapter->caps.enable	= ptp_82580_enable;
-		adapter->cc.read	= igb_82580_systim_read;
-		adapter->cc.mask	= CLOCKSOURCE_MASK(IGB_NBITS_82580);
-		adapter->cc.mult	= 1;
-		adapter->cc.shift	= 0;
+	case e1000_i350:
+		snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr);
+		adapter->ptp_caps.owner = THIS_MODULE;
+		adapter->ptp_caps.max_adj = 62499999;
+		adapter->ptp_caps.n_ext_ts = 0;
+		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580;
+		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
+		adapter->ptp_caps.gettime = igb_ptp_gettime_82576;
+		adapter->ptp_caps.settime = igb_ptp_settime_82576;
+		adapter->ptp_caps.enable = igb_ptp_enable;
+		adapter->cc.read = igb_ptp_read_82580;
+		adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580);
+		adapter->cc.mult = 1;
+		adapter->cc.shift = 0;
 		/* Enable the timer functions by clearing bit 31. */
 		wr32(E1000_TSAUXC, 0x0);
 		break;
-
-	case e1000_82576:
-		adapter->caps.owner	= THIS_MODULE;
-		strcpy(adapter->caps.name, "igb-82576");
-		adapter->caps.max_adj	= 1000000000;
-		adapter->caps.n_ext_ts	= 0;
-		adapter->caps.pps	= 0;
-		adapter->caps.adjfreq	= ptp_82576_adjfreq;
-		adapter->caps.adjtime	= igb_adjtime;
-		adapter->caps.gettime	= igb_gettime;
-		adapter->caps.settime	= igb_settime;
-		adapter->caps.enable	= ptp_82576_enable;
-		adapter->cc.read	= igb_82576_systim_read;
-		adapter->cc.mask	= CLOCKSOURCE_MASK(64);
-		adapter->cc.mult	= 1;
-		adapter->cc.shift	= IGB_82576_TSYNC_SHIFT;
-		/* Dial the nominal frequency. */
-		wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+	case e1000_i210:
+	case e1000_i211:
+		snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr);
+		adapter->ptp_caps.owner = THIS_MODULE;
+		adapter->ptp_caps.max_adj = 62499999;
+		adapter->ptp_caps.n_ext_ts = 0;
+		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580;
+		adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
+		adapter->ptp_caps.gettime = igb_ptp_gettime_i210;
+		adapter->ptp_caps.settime = igb_ptp_settime_i210;
+		adapter->ptp_caps.enable = igb_ptp_enable;
+		/* Enable the timer functions by clearing bit 31. */
+		wr32(E1000_TSAUXC, 0x0);
 		break;
-
 	default:
 		adapter->ptp_clock = NULL;
 		return;
@@ -310,86 +727,114 @@ void igb_ptp_init(struct igb_adapter *adapter)
 
 	wrfl();
 
-	timecounter_init(&adapter->tc, &adapter->cc,
-			 ktime_to_ns(ktime_get_real()));
+	spin_lock_init(&adapter->tmreg_lock);
+	INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
+
+	/* Initialize the clock and overflow work for devices that need it. */
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) {
+		struct timespec ts = ktime_to_timespec(ktime_get_real());
 
-	INIT_DELAYED_WORK(&adapter->overflow_work, igb_overflow_check);
+		igb_ptp_settime_i210(&adapter->ptp_caps, &ts);
+	} else {
+		timecounter_init(&adapter->tc, &adapter->cc,
+				 ktime_to_ns(ktime_get_real()));
 
-	spin_lock_init(&adapter->tmreg_lock);
+		INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
+				  igb_ptp_overflow_check);
 
-	schedule_delayed_work(&adapter->overflow_work, IGB_OVERFLOW_PERIOD);
+		schedule_delayed_work(&adapter->ptp_overflow_work,
+				      IGB_SYSTIM_OVERFLOW_PERIOD);
+	}
+
+	/* Initialize the time sync interrupts for devices that support it. */
+	if (hw->mac.type >= e1000_82580) {
+		wr32(E1000_TSIM, E1000_TSIM_TXTS);
+		wr32(E1000_IMS, E1000_IMS_TS);
+	}
 
-	adapter->ptp_clock = ptp_clock_register(&adapter->caps);
+	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
+						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n");
-	} else
+	} else {
 		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
 			 adapter->netdev->name);
+		adapter->flags |= IGB_FLAG_PTP;
+	}
 }
 
-void igb_ptp_remove(struct igb_adapter *adapter)
+/**
+ * igb_ptp_stop - Disable PTP device and stop the overflow check.
+ * @adapter: Board private structure.
+ *
+ * This function stops the PTP support and cancels the delayed work.
+ **/
+void igb_ptp_stop(struct igb_adapter *adapter)
 {
 	switch (adapter->hw.mac.type) {
-	case e1000_i211:
-	case e1000_i210:
-	case e1000_i350:
-	case e1000_82580:
 	case e1000_82576:
-		cancel_delayed_work_sync(&adapter->overflow_work);
+	case e1000_82580:
+	case e1000_i350:
+		cancel_delayed_work_sync(&adapter->ptp_overflow_work);
+		break;
+	case e1000_i210:
+	case e1000_i211:
+		/* No delayed work to cancel. */
 		break;
 	default:
 		return;
 	}
 
+	cancel_work_sync(&adapter->ptp_tx_work);
+
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
 			 adapter->netdev->name);
+		adapter->flags &= ~IGB_FLAG_PTP;
 	}
 }
 
 /**
- * igb_systim_to_hwtstamp - convert system time value to hw timestamp
- * @adapter: board private structure
- * @hwtstamps: timestamp structure to update
- * @systim: unsigned 64bit system time value.
- *
- * We need to convert the system time value stored in the RX/TXSTMP registers
- * into a hwtstamp which can be used by the upper level timestamping functions.
+ * igb_ptp_reset - Re-enable the adapter for PTP following a reset.
+ * @adapter: Board private structure.
  *
- * The 'tmreg_lock' spinlock is used to protect the consistency of the
- * system time value. This is needed because reading the 64 bit time
- * value involves reading two (or three) 32 bit registers. The first
- * read latches the value. Ditto for writing.
- *
- * In addition, here have extended the system time with an overflow
- * counter in software.
+ * This function handles the reset work required to re-enable the PTP device.
  **/
-void igb_systim_to_hwtstamp(struct igb_adapter *adapter,
-			    struct skb_shared_hwtstamps *hwtstamps,
-			    u64 systim)
+void igb_ptp_reset(struct igb_adapter *adapter)
 {
-	u64 ns;
-	unsigned long flags;
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (!(adapter->flags & IGB_FLAG_PTP))
+		return;
 
 	switch (adapter->hw.mac.type) {
+	case e1000_82576:
+		/* Dial the nominal frequency. */
+		wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+		break;
+	case e1000_82580:
+	case e1000_i350:
 	case e1000_i210:
 	case e1000_i211:
-	case e1000_i350:
-	case e1000_82580:
-	case e1000_82576:
+		/* Enable the timer functions and interrupts. */
+		wr32(E1000_TSAUXC, 0x0);
+		wr32(E1000_TSIM, E1000_TSIM_TXTS);
+		wr32(E1000_IMS, E1000_IMS_TS);
 		break;
 	default:
+		/* No work to do. */
 		return;
 	}
 
-	spin_lock_irqsave(&adapter->tmreg_lock, flags);
+	/* Re-initialize the timer. */
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) {
+		struct timespec ts = ktime_to_timespec(ktime_get_real());
 
-	ns = timecounter_cyc2time(&adapter->tc, systim);
-
-	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
-
-	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(ns);
+		igb_ptp_settime_i210(&adapter->ptp_caps, &ts);
+	} else {
+		timecounter_init(&adapter->tc, &adapter->cc,
+				 ktime_to_ns(ktime_get_real()));
+	}
 }