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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 237 insertions, 173 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index b3e3294cfe5..68478d6dfa2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
 
   Intel 10 Gigabit PCI Express Linux driver
-  Copyright(c) 1999 - 2012 Intel Corporation.
+  Copyright(c) 1999 - 2013 Intel Corporation.
 
   This program is free software; you can redistribute it and/or modify it
   under the terms and conditions of the GNU General Public License,
@@ -66,7 +66,7 @@ static char ixgbe_default_device_descr[] =
 #define DRV_VERSION "3.11.33-k"
 const char ixgbe_driver_version[] = DRV_VERSION;
 static const char ixgbe_copyright[] =
-				"Copyright (c) 1999-2012 Intel Corporation.";
+				"Copyright (c) 1999-2013 Intel Corporation.";
 
 static const struct ixgbe_info *ixgbe_info_tbl[] = {
 	[board_82598] = &ixgbe_82598_info,
@@ -803,6 +803,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
 	/* Do the reset outside of interrupt context */
 	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
 		adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
+		e_warn(drv, "initiating reset due to tx timeout\n");
 		ixgbe_service_event_schedule(adapter);
 	}
 }
@@ -837,7 +838,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		rmb();
+		read_barrier_depends();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
@@ -850,9 +851,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
-		if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP))
-			ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb);
-
 		/* free the skb */
 		dev_kfree_skb_any(tx_buffer->skb);
 
@@ -1442,7 +1440,7 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
 
 	ixgbe_rx_checksum(rx_ring, rx_desc, skb);
 
-	ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
+	ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
 
 	if ((dev->features & NETIF_F_HW_VLAN_RX) &&
 	    ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
@@ -2181,10 +2179,10 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
 			return;
 
 		if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) {
-			u32 autoneg;
+			u32 speed;
 			bool link_up = false;
 
-			hw->mac.ops.check_link(hw, &autoneg, &link_up, false);
+			hw->mac.ops.check_link(hw, &speed, &link_up, false);
 
 			if (link_up)
 				return;
@@ -2788,13 +2786,19 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 
 	/*
 	 * set WTHRESH to encourage burst writeback, it should not be set
-	 * higher than 1 when ITR is 0 as it could cause false TX hangs
+	 * higher than 1 when:
+	 * - ITR is 0 as it could cause false TX hangs
+	 * - ITR is set to > 100k int/sec and BQL is enabled
 	 *
 	 * In order to avoid issues WTHRESH + PTHRESH should always be equal
 	 * to or less than the number of on chip descriptors, which is
 	 * currently 40.
 	 */
+#if IS_ENABLED(CONFIG_BQL)
+	if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR))
+#else
 	if (!ring->q_vector || (ring->q_vector->itr < 8))
+#endif
 		txdctl |= (1 << 16);	/* WTHRESH = 1 */
 	else
 		txdctl |= (8 << 16);	/* WTHRESH = 8 */
@@ -2815,6 +2819,16 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 		ring->atr_sample_rate = 0;
 	}
 
+	/* initialize XPS */
+	if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) {
+		struct ixgbe_q_vector *q_vector = ring->q_vector;
+
+		if (q_vector)
+			netif_set_xps_queue(adapter->netdev,
+					    &q_vector->affinity_mask,
+					    ring->queue_index);
+	}
+
 	clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);
 
 	/* enable queue */
@@ -3997,25 +4011,25 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 {
-	u32 autoneg;
-	bool negotiation, link_up = false;
+	u32 speed;
+	bool autoneg, link_up = false;
 	u32 ret = IXGBE_ERR_LINK_SETUP;
 
 	if (hw->mac.ops.check_link)
-		ret = hw->mac.ops.check_link(hw, &autoneg, &link_up, false);
+		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
 
 	if (ret)
 		goto link_cfg_out;
 
-	autoneg = hw->phy.autoneg_advertised;
-	if ((!autoneg) && (hw->mac.ops.get_link_capabilities))
-		ret = hw->mac.ops.get_link_capabilities(hw, &autoneg,
-							&negotiation);
+	speed = hw->phy.autoneg_advertised;
+	if ((!speed) && (hw->mac.ops.get_link_capabilities))
+		ret = hw->mac.ops.get_link_capabilities(hw, &speed,
+							&autoneg);
 	if (ret)
 		goto link_cfg_out;
 
 	if (hw->mac.ops.setup_link)
-		ret = hw->mac.ops.setup_link(hw, autoneg, negotiation, link_up);
+		ret = hw->mac.ops.setup_link(hw, speed, link_up);
 link_cfg_out:
 	return ret;
 }
@@ -4467,7 +4481,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
-	unsigned int rss;
+	unsigned int rss, fdir;
 	u32 fwsm;
 #ifdef CONFIG_IXGBE_DCB
 	int j;
@@ -4482,38 +4496,57 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
 	hw->subsystem_device_id = pdev->subsystem_device;
 
-	/* Set capability flags */
+	/* Set common capability flags and settings */
 	rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus());
 	adapter->ring_feature[RING_F_RSS].limit = rss;
+	adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
+	adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
+	adapter->max_q_vectors = MAX_Q_VECTORS_82599;
+	adapter->atr_sample_rate = 20;
+	fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus());
+	adapter->ring_feature[RING_F_FDIR].limit = fdir;
+	adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K;
+#ifdef CONFIG_IXGBE_DCA
+	adapter->flags |= IXGBE_FLAG_DCA_CAPABLE;
+#endif
+#ifdef IXGBE_FCOE
+	adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
+	adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
+#ifdef CONFIG_IXGBE_DCB
+	/* Default traffic class to use for FCoE */
+	adapter->fcoe.up = IXGBE_FCOE_DEFTC;
+#endif /* CONFIG_IXGBE_DCB */
+#endif /* IXGBE_FCOE */
+
+	/* Set MAC specific capability flags and exceptions */
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
+		adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE;
+		adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED;
+
 		if (hw->device_id == IXGBE_DEV_ID_82598AT)
 			adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE;
+
 		adapter->max_q_vectors = MAX_Q_VECTORS_82598;
+		adapter->ring_feature[RING_F_FDIR].limit = 0;
+		adapter->atr_sample_rate = 0;
+		adapter->fdir_pballoc = 0;
+#ifdef IXGBE_FCOE
+		adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
+		adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
+#ifdef CONFIG_IXGBE_DCB
+		adapter->fcoe.up = 0;
+#endif /* IXGBE_DCB */
+#endif /* IXGBE_FCOE */
+		break;
+	case ixgbe_mac_82599EB:
+		if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM)
+			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
 		break;
 	case ixgbe_mac_X540:
 		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
 		if (fwsm & IXGBE_FWSM_TS_ENABLED)
 			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
-	case ixgbe_mac_82599EB:
-		adapter->max_q_vectors = MAX_Q_VECTORS_82599;
-		adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
-		adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
-		if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM)
-			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
-		/* Flow Director hash filters enabled */
-		adapter->atr_sample_rate = 20;
-		adapter->ring_feature[RING_F_FDIR].limit =
-							 IXGBE_MAX_FDIR_INDICES;
-		adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K;
-#ifdef IXGBE_FCOE
-		adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
-		adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
-#ifdef CONFIG_IXGBE_DCB
-		/* Default traffic class to use for FCoE */
-		adapter->fcoe.up = IXGBE_FCOE_DEFTC;
-#endif
-#endif /* IXGBE_FCOE */
 		break;
 	default:
 		break;
@@ -4872,7 +4905,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 	 */
 	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) &&
 	    (adapter->hw.mac.type == ixgbe_mac_82599EB) &&
-	    (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE))
+	    (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
 		e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n");
 
 	e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);
@@ -5535,6 +5568,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
 		break;
 	}
 
+	adapter->last_rx_ptp_check = jiffies;
+
 	if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED)
 		ixgbe_ptp_start_cyclecounter(adapter);
 
@@ -5615,6 +5650,7 @@ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter)
 			 * to get done, so reset controller to flush Tx.
 			 * (Do the reset outside of interrupt context).
 			 */
+			e_warn(drv, "initiating reset to clear Tx work after link loss\n");
 			adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
 		}
 	}
@@ -5679,6 +5715,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter)
 	    !(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET))
 		return;
 
+	/* concurent i2c reads are not supported */
+	if (test_bit(__IXGBE_READ_I2C, &adapter->state))
+		return;
+
 	/* someone else is in init, wait until next service event */
 	if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state))
 		return;
@@ -5739,8 +5779,8 @@ sfp_out:
 static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 autoneg;
-	bool negotiation;
+	u32 speed;
+	bool autoneg = false;
 
 	if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_CONFIG))
 		return;
@@ -5751,11 +5791,11 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
 
 	adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
 
-	autoneg = hw->phy.autoneg_advertised;
-	if ((!autoneg) && (hw->mac.ops.get_link_capabilities))
-		hw->mac.ops.get_link_capabilities(hw, &autoneg, &negotiation);
+	speed = hw->phy.autoneg_advertised;
+	if ((!speed) && (hw->mac.ops.get_link_capabilities))
+		hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg);
 	if (hw->mac.ops.setup_link)
-		hw->mac.ops.setup_link(hw, autoneg, negotiation, true);
+		hw->mac.ops.setup_link(hw, speed, true);
 
 	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
 	adapter->link_check_timeout = jiffies;
@@ -5879,7 +5919,6 @@ static void ixgbe_service_task(struct work_struct *work)
 	struct ixgbe_adapter *adapter = container_of(work,
 						     struct ixgbe_adapter,
 						     service_task);
-
 	ixgbe_reset_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
 	ixgbe_sfp_link_config_subtask(adapter);
@@ -5887,7 +5926,11 @@ static void ixgbe_service_task(struct work_struct *work)
 	ixgbe_watchdog_subtask(adapter);
 	ixgbe_fdir_reinit_subtask(adapter);
 	ixgbe_check_hang_subtask(adapter);
-	ixgbe_ptp_overflow_check(adapter);
+
+	if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) {
+		ixgbe_ptp_overflow_check(adapter);
+		ixgbe_ptp_rx_hang(adapter);
+	}
 
 	ixgbe_service_event_complete(adapter);
 }
@@ -5900,6 +5943,9 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 	u32 vlan_macip_lens, type_tucmd;
 	u32 mss_l4len_idx, l4len;
 
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
 	if (!skb_is_gso(skb))
 		return 0;
 
@@ -5942,10 +5988,9 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
 	first->bytecount += (first->gso_segs - 1) * *hdr_len;
 
-	/* mss_l4len_id: use 1 as index for TSO */
+	/* mss_l4len_id: use 0 as index for TSO */
 	mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
-	mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_SHIFT;
 
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
 	vlan_macip_lens = skb_network_header_len(skb);
@@ -5967,12 +6012,9 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring,
 	u32 type_tucmd = 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
-		if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN)) {
-			if (unlikely(skb->no_fcs))
-				first->tx_flags |= IXGBE_TX_FLAGS_NO_IFCS;
-			if (!(first->tx_flags & IXGBE_TX_FLAGS_TXSW))
-				return;
-		}
+		if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN) &&
+		    !(first->tx_flags & IXGBE_TX_FLAGS_CC))
+			return;
 	} else {
 		u8 l4_hdr = 0;
 		switch (first->protocol) {
@@ -6030,30 +6072,32 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring,
 			  type_tucmd, mss_l4len_idx);
 }
 
-static __le32 ixgbe_tx_cmd_type(u32 tx_flags)
+#define IXGBE_SET_FLAG(_input, _flag, _result) \
+	((_flag <= _result) ? \
+	 ((u32)(_input & _flag) * (_result / _flag)) : \
+	 ((u32)(_input & _flag) / (_flag / _result)))
+
+static u32 ixgbe_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
 {
 	/* set type for advanced descriptor with frame checksum insertion */
-	__le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA |
-				      IXGBE_ADVTXD_DCMD_DEXT);
+	u32 cmd_type = IXGBE_ADVTXD_DTYP_DATA |
+		       IXGBE_ADVTXD_DCMD_DEXT |
+		       IXGBE_ADVTXD_DCMD_IFCS;
 
 	/* set HW vlan bit if vlan is present */
-	if (tx_flags & IXGBE_TX_FLAGS_HW_VLAN)
-		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE);
-
-	if (tx_flags & IXGBE_TX_FLAGS_TSTAMP)
-		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_MAC_TSTAMP);
+	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_HW_VLAN,
+				   IXGBE_ADVTXD_DCMD_VLE);
 
 	/* set segmentation enable bits for TSO/FSO */
-#ifdef IXGBE_FCOE
-	if (tx_flags & (IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_FSO))
-#else
-	if (tx_flags & IXGBE_TX_FLAGS_TSO)
-#endif
-		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE);
+	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSO,
+				   IXGBE_ADVTXD_DCMD_TSE);
+
+	/* set timestamp bit if present */
+	cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSTAMP,
+				   IXGBE_ADVTXD_MAC_TSTAMP);
 
 	/* insert frame checksum */
-	if (!(tx_flags & IXGBE_TX_FLAGS_NO_IFCS))
-		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS);
+	cmd_type ^= IXGBE_SET_FLAG(skb->no_fcs, 1, IXGBE_ADVTXD_DCMD_IFCS);
 
 	return cmd_type;
 }
@@ -6061,36 +6105,27 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags)
 static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc,
 				   u32 tx_flags, unsigned int paylen)
 {
-	__le32 olinfo_status = cpu_to_le32(paylen << IXGBE_ADVTXD_PAYLEN_SHIFT);
+	u32 olinfo_status = paylen << IXGBE_ADVTXD_PAYLEN_SHIFT;
 
 	/* enable L4 checksum for TSO and TX checksum offload */
-	if (tx_flags & IXGBE_TX_FLAGS_CSUM)
-		olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM);
+	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
+					IXGBE_TX_FLAGS_CSUM,
+					IXGBE_ADVTXD_POPTS_TXSM);
 
 	/* enble IPv4 checksum for TSO */
-	if (tx_flags & IXGBE_TX_FLAGS_IPV4)
-		olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM);
-
-	/* use index 1 context for TSO/FSO/FCOE */
-#ifdef IXGBE_FCOE
-	if (tx_flags & (IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_FCOE))
-#else
-	if (tx_flags & IXGBE_TX_FLAGS_TSO)
-#endif
-		olinfo_status |= cpu_to_le32(1 << IXGBE_ADVTXD_IDX_SHIFT);
+	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
+					IXGBE_TX_FLAGS_IPV4,
+					IXGBE_ADVTXD_POPTS_IXSM);
 
 	/*
 	 * Check Context must be set if Tx switch is enabled, which it
 	 * always is for case where virtual functions are running
 	 */
-#ifdef IXGBE_FCOE
-	if (tx_flags & (IXGBE_TX_FLAGS_TXSW | IXGBE_TX_FLAGS_FCOE))
-#else
-	if (tx_flags & IXGBE_TX_FLAGS_TXSW)
-#endif
-		olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC);
+	olinfo_status |= IXGBE_SET_FLAG(tx_flags,
+					IXGBE_TX_FLAGS_CC,
+					IXGBE_ADVTXD_CC);
 
-	tx_desc->read.olinfo_status = olinfo_status;
+	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
 
 #define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
@@ -6100,22 +6135,22 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 			 struct ixgbe_tx_buffer *first,
 			 const u8 hdr_len)
 {
-	dma_addr_t dma;
 	struct sk_buff *skb = first->skb;
 	struct ixgbe_tx_buffer *tx_buffer;
 	union ixgbe_adv_tx_desc *tx_desc;
-	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
-	unsigned int data_len = skb->data_len;
-	unsigned int size = skb_headlen(skb);
-	unsigned int paylen = skb->len - hdr_len;
+	struct skb_frag_struct *frag;
+	dma_addr_t dma;
+	unsigned int data_len, size;
 	u32 tx_flags = first->tx_flags;
-	__le32 cmd_type;
+	u32 cmd_type = ixgbe_tx_cmd_type(skb, tx_flags);
 	u16 i = tx_ring->next_to_use;
 
 	tx_desc = IXGBE_TX_DESC(tx_ring, i);
 
-	ixgbe_tx_olinfo_status(tx_desc, tx_flags, paylen);
-	cmd_type = ixgbe_tx_cmd_type(tx_flags);
+	ixgbe_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len);
+
+	size = skb_headlen(skb);
+	data_len = skb->data_len;
 
 #ifdef IXGBE_FCOE
 	if (tx_flags & IXGBE_TX_FLAGS_FCOE) {
@@ -6129,19 +6164,22 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 #endif
 	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
-	if (dma_mapping_error(tx_ring->dev, dma))
-		goto dma_error;
 
-	/* record length, and DMA address */
-	dma_unmap_len_set(first, len, size);
-	dma_unmap_addr_set(first, dma, dma);
+	tx_buffer = first;
 
-	tx_desc->read.buffer_addr = cpu_to_le64(dma);
+	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+		if (dma_mapping_error(tx_ring->dev, dma))
+			goto dma_error;
+
+		/* record length, and DMA address */
+		dma_unmap_len_set(tx_buffer, len, size);
+		dma_unmap_addr_set(tx_buffer, dma, dma);
+
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
-	for (;;) {
 		while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) {
 			tx_desc->read.cmd_type_len =
-				cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD);
+				cpu_to_le32(cmd_type ^ IXGBE_MAX_DATA_PER_TXD);
 
 			i++;
 			tx_desc++;
@@ -6149,18 +6187,18 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
 				i = 0;
 			}
+			tx_desc->read.olinfo_status = 0;
 
 			dma += IXGBE_MAX_DATA_PER_TXD;
 			size -= IXGBE_MAX_DATA_PER_TXD;
 
 			tx_desc->read.buffer_addr = cpu_to_le64(dma);
-			tx_desc->read.olinfo_status = 0;
 		}
 
 		if (likely(!data_len))
 			break;
 
-		tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size);
+		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size);
 
 		i++;
 		tx_desc++;
@@ -6168,6 +6206,7 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
 			i = 0;
 		}
+		tx_desc->read.olinfo_status = 0;
 
 #ifdef IXGBE_FCOE
 		size = min_t(unsigned int, data_len, skb_frag_size(frag));
@@ -6178,22 +6217,13 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
 				       DMA_TO_DEVICE);
-		if (dma_mapping_error(tx_ring->dev, dma))
-			goto dma_error;
 
 		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.buffer_addr = cpu_to_le64(dma);
-		tx_desc->read.olinfo_status = 0;
-
-		frag++;
 	}
 
 	/* write last descriptor with RS and EOP bits */
-	cmd_type |= cpu_to_le32(size) | cpu_to_le32(IXGBE_TXD_CMD);
-	tx_desc->read.cmd_type_len = cmd_type;
+	cmd_type |= size | IXGBE_TXD_CMD;
+	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
 
 	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
 
@@ -6354,38 +6384,40 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
 	return __ixgbe_maybe_stop_tx(tx_ring, size);
 }
 
+#ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-	int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
-					       smp_processor_id();
-#ifdef IXGBE_FCOE
-	__be16 protocol = vlan_get_protocol(skb);
+	struct ixgbe_adapter *adapter;
+	struct ixgbe_ring_feature *f;
+	int txq;
 
-	if (((protocol == htons(ETH_P_FCOE)) ||
-	    (protocol == htons(ETH_P_FIP))) &&
-	    (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) {
-		struct ixgbe_ring_feature *f;
+	/*
+	 * only execute the code below if protocol is FCoE
+	 * or FIP and we have FCoE enabled on the adapter
+	 */
+	switch (vlan_get_protocol(skb)) {
+	case __constant_htons(ETH_P_FCOE):
+	case __constant_htons(ETH_P_FIP):
+		adapter = netdev_priv(dev);
 
-		f = &adapter->ring_feature[RING_F_FCOE];
+		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+			break;
+	default:
+		return __netdev_pick_tx(dev, skb);
+	}
 
-		while (txq >= f->indices)
-			txq -= f->indices;
-		txq += adapter->ring_feature[RING_F_FCOE].offset;
+	f = &adapter->ring_feature[RING_F_FCOE];
 
-		return txq;
-	}
-#endif
+	txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
+					   smp_processor_id();
 
-	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
-		while (unlikely(txq >= dev->real_num_tx_queues))
-			txq -= dev->real_num_tx_queues;
-		return txq;
-	}
+	while (txq >= f->indices)
+		txq -= f->indices;
 
-	return skb_tx_hash(dev, skb);
+	return txq + f->offset;
 }
 
+#endif
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 			  struct ixgbe_adapter *adapter,
 			  struct ixgbe_ring *tx_ring)
@@ -6446,6 +6478,11 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IXGBE_TX_FLAGS_TSTAMP;
+
+		/* schedule check for Tx timestamp */
+		adapter->ptp_tx_skb = skb_get(skb);
+		adapter->ptp_tx_start = jiffies;
+		schedule_work(&adapter->ptp_tx_work);
 	}
 
 #ifdef CONFIG_PCI_IOV
@@ -6454,7 +6491,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 	 * Tx switch had been disabled.
 	 */
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
-		tx_flags |= IXGBE_TX_FLAGS_TXSW;
+		tx_flags |= IXGBE_TX_FLAGS_CC;
 
 #endif
 	/* DCB maps skb priorities 0-7 onto 3 bit PCP of VLAN tag. */
@@ -6785,6 +6822,7 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter)
 	}
 }
 
+#endif /* CONFIG_IXGBE_DCB */
 /**
  * ixgbe_setup_tc - configure net_device for multiple traffic classes
  *
@@ -6810,6 +6848,7 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 		ixgbe_close(dev);
 	ixgbe_clear_interrupt_scheme(adapter);
 
+#ifdef CONFIG_IXGBE_DCB
 	if (tc) {
 		netdev_set_num_tc(dev, tc);
 		ixgbe_set_prio_tc_map(adapter);
@@ -6832,15 +6871,28 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 		adapter->dcb_cfg.pfc_mode_enable = false;
 	}
 
-	ixgbe_init_interrupt_scheme(adapter);
 	ixgbe_validate_rtr(adapter, tc);
+
+#endif /* CONFIG_IXGBE_DCB */
+	ixgbe_init_interrupt_scheme(adapter);
+
 	if (netif_running(dev))
-		ixgbe_open(dev);
+		return ixgbe_open(dev);
 
 	return 0;
 }
 
-#endif /* CONFIG_IXGBE_DCB */
+#ifdef CONFIG_PCI_IOV
+void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+
+	rtnl_lock();
+	ixgbe_setup_tc(netdev, netdev_get_num_tc(netdev));
+	rtnl_unlock();
+}
+
+#endif
 void ixgbe_do_reset(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
@@ -6986,7 +7038,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	return err;
 }
 
-static int ixgbe_ndo_fdb_del(struct ndmsg *ndm,
+static int ixgbe_ndo_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
 			     const unsigned char *addr)
 {
@@ -7063,7 +7115,8 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 }
 
 static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-				    struct net_device *dev)
+				    struct net_device *dev,
+				    u32 filter_mask)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	u16 mode;
@@ -7083,7 +7136,9 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
+#ifdef IXGBE_FCOE
 	.ndo_select_queue	= ixgbe_select_queue,
+#endif
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -7195,9 +7250,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
 	static int cards_found;
 	int i, err, pci_using_dac;
+	unsigned int indices = MAX_TX_QUEUES;
 	u8 part_str[IXGBE_PBANUM_LENGTH];
-	unsigned int indices = num_possible_cpus();
-	unsigned int dcb_max = 0;
 #ifdef IXGBE_FCOE
 	u16 device_caps;
 #endif
@@ -7246,25 +7300,15 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 	pci_save_state(pdev);
 
+	if (ii->mac == ixgbe_mac_82598EB) {
 #ifdef CONFIG_IXGBE_DCB
-	if (ii->mac == ixgbe_mac_82598EB)
-		dcb_max = min_t(unsigned int, indices * MAX_TRAFFIC_CLASS,
-				IXGBE_MAX_RSS_INDICES);
-	else
-		dcb_max = min_t(unsigned int, indices * MAX_TRAFFIC_CLASS,
-				IXGBE_MAX_FDIR_INDICES);
+		/* 8 TC w/ 4 queues per TC */
+		indices = 4 * MAX_TRAFFIC_CLASS;
+#else
+		indices = IXGBE_MAX_RSS_INDICES;
 #endif
+	}
 
-	if (ii->mac == ixgbe_mac_82598EB)
-		indices = min_t(unsigned int, indices, IXGBE_MAX_RSS_INDICES);
-	else
-		indices = min_t(unsigned int, indices, IXGBE_MAX_FDIR_INDICES);
-
-#ifdef IXGBE_FCOE
-	indices += min_t(unsigned int, num_possible_cpus(),
-			 IXGBE_MAX_FCOE_INDICES);
-#endif
-	indices = max_t(unsigned int, dcb_max, indices);
 	netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices);
 	if (!netdev) {
 		err = -ENOMEM;
@@ -7367,7 +7411,15 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 #ifdef CONFIG_PCI_IOV
-	ixgbe_enable_sriov(adapter, ii);
+	/* SR-IOV not supported on the 82598 */
+	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+		goto skip_sriov;
+	/* Mailbox */
+	ixgbe_init_mbx_params_pf(hw);
+	memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops));
+	ixgbe_enable_sriov(adapter);
+	pci_sriov_set_totalvfs(pdev, 63);
+skip_sriov:
 
 #endif
 	netdev->features = NETIF_F_SG |
@@ -7411,13 +7463,17 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #ifdef IXGBE_FCOE
 	if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) {
+		unsigned int fcoe_l;
+
 		if (hw->mac.ops.get_device_caps) {
 			hw->mac.ops.get_device_caps(hw, &device_caps);
 			if (device_caps & IXGBE_DEVICE_CAPS_FCOE_OFFLOADS)
 				adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE;
 		}
 
-		adapter->ring_feature[RING_F_FCOE].limit = IXGBE_FCRETA_SIZE;
+
+		fcoe_l = min_t(int, IXGBE_FCRETA_SIZE, num_online_cpus());
+		adapter->ring_feature[RING_F_FCOE].limit = fcoe_l;
 
 		netdev->features |= NETIF_F_FSO |
 				    NETIF_F_FCOE_CRC;
@@ -7445,9 +7501,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	memcpy(netdev->dev_addr, hw->mac.perm_addr, netdev->addr_len);
-	memcpy(netdev->perm_addr, hw->mac.perm_addr, netdev->addr_len);
 
-	if (!is_valid_ether_addr(netdev->perm_addr)) {
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
 		e_dev_err("invalid MAC address\n");
 		err = -EIO;
 		goto err_sw_init;
@@ -7624,8 +7679,14 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
-	ixgbe_disable_sriov(adapter);
-
+#ifdef CONFIG_PCI_IOV
+	/*
+	 * Only disable SR-IOV on unload if the user specified the now
+	 * deprecated max_vfs module parameter.
+	 */
+	if (max_vfs)
+		ixgbe_disable_sriov(adapter);
+#endif
 	ixgbe_clear_interrupt_scheme(adapter);
 
 	ixgbe_release_hw_control(adapter);
@@ -7730,6 +7791,8 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
 		if (vfdev) {
 			e_dev_err("Issuing VFLR to VF %d\n", vf);
 			pci_write_config_dword(vfdev, 0xA8, 0x00008000);
+			/* Free device reference count */
+			pci_dev_put(vfdev);
 		}
 
 		pci_cleanup_aer_uncorrect_error_status(pdev);
@@ -7839,6 +7902,7 @@ static struct pci_driver ixgbe_driver = {
 	.resume   = ixgbe_resume,
 #endif
 	.shutdown = ixgbe_shutdown,
+	.sriov_configure = ixgbe_pci_sriov_configure,
 	.err_handler = &ixgbe_err_handler
 };