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 ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2012-10-03 00:38:27 +0400
committer: Linus Torvalds <torvalds@linux-foundation.org> 2012-10-03 00:38:27 +0400
commit: aecdc33e111b2c447b622e287c6003726daa1426 (patch)
tree: 3e7657eae4b785e1a1fb5dfb225dbae0b2f0cfc6 /drivers/net/ethernet
parent: a20acf99f75e49271381d65db097c9763060a1e8 (diff)
parent: a3a6cab5ea10cca64d036851fe0d932448f2fe4f (diff)
download: linux-aecdc33e111b2c447b622e287c6003726daa1426.tar.xz
113 files changed, 8935 insertions, 4083 deletions
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index a11af5cc4844..e4ff38949112 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -89,15 +89,6 @@ source "drivers/net/ethernet/marvell/Kconfig"
 source "drivers/net/ethernet/mellanox/Kconfig"
 source "drivers/net/ethernet/micrel/Kconfig"
 source "drivers/net/ethernet/microchip/Kconfig"
-
-config MIPS_SIM_NET
-	tristate "MIPS simulator Network device"
-	depends on MIPS_SIM
-	---help---
-	  The MIPSNET device is a simple Ethernet network device which is
-	  emulated by the MIPS Simulator.
-	  If you are not using a MIPSsim or are unsure, say N.
-
 source "drivers/net/ethernet/myricom/Kconfig"
 
 config FEALNX
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 878ad32b93f2..d4473072654a 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -40,7 +40,6 @@ obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/
 obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/
 obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/
 obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/
-obj-$(CONFIG_MIPS_SIM_NET) += mipsnet.o
 obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
 obj-$(CONFIG_FEALNX) += fealnx.o
 obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index f15e72e81ac4..4bd416b72e65 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -101,6 +101,7 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	select PHYLIB
+	select HWMON
 	---help---
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index eac25236856c..72897c47b8c8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -23,8 +23,8 @@
  * (you will need to reboot afterwards) */
 /* #define BNX2X_STOP_ON_ERROR */
 
-#define DRV_MODULE_VERSION      "1.72.51-0"
-#define DRV_MODULE_RELDATE      "2012/06/18"
+#define DRV_MODULE_VERSION      "1.78.00-0"
+#define DRV_MODULE_RELDATE      "2012/09/27"
 #define BNX2X_BC_VER            0x040200
 
 #if defined(CONFIG_DCB)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e8e97a7d1d06..30f04a389227 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2285,7 +2285,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 	/* Wait for all pending SP commands to complete */
 	if (!bnx2x_wait_sp_comp(bp, ~0x0UL)) {
 		BNX2X_ERR("Timeout waiting for SP elements to complete\n");
-		bnx2x_nic_unload(bp, UNLOAD_CLOSE);
+		bnx2x_nic_unload(bp, UNLOAD_CLOSE, false);
 		return -EBUSY;
 	}
 
@@ -2333,7 +2333,7 @@ load_error0:
 }
 
 /* must be called with rtnl_lock */
-int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
+int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 {
 	int i;
 	bool global = false;
@@ -2395,7 +2395,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
 
 	/* Cleanup the chip if needed */
 	if (unload_mode != UNLOAD_RECOVERY)
-		bnx2x_chip_cleanup(bp, unload_mode);
+		bnx2x_chip_cleanup(bp, unload_mode, keep_link);
 	else {
 		/* Send the UNLOAD_REQUEST to the MCP */
 		bnx2x_send_unload_req(bp, unload_mode);
@@ -2419,7 +2419,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode)
 		bnx2x_free_irq(bp);
 
 		/* Report UNLOAD_DONE to MCP */
-		bnx2x_send_unload_done(bp);
+		bnx2x_send_unload_done(bp, false);
 	}
 
 	/*
@@ -3026,8 +3026,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	first_bd = tx_start_bd;
 
 	tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD;
-	SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_ETH_ADDR_TYPE,
-		 mac_type);
+	SET_FLAG(tx_start_bd->general_data,
+		 ETH_TX_START_BD_PARSE_NBDS,
+		 0);
 
 	/* header nbd */
 	SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_HDR_NBDS, 1);
@@ -3077,13 +3078,20 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					      &pbd_e2->dst_mac_addr_lo,
 					      eth->h_dest);
 		}
+
+		SET_FLAG(pbd_e2_parsing_data,
+			 ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE, mac_type);
 	} else {
+		u16 global_data = 0;
 		pbd_e1x = &txdata->tx_desc_ring[bd_prod].parse_bd_e1x;
 		memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x));
 		/* Set PBD in checksum offload case */
 		if (xmit_type & XMIT_CSUM)
 			hlen = bnx2x_set_pbd_csum(bp, skb, pbd_e1x, xmit_type);
 
+		SET_FLAG(global_data,
+			 ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE, mac_type);
+		pbd_e1x->global_data |= cpu_to_le16(global_data);
 	}
 
 	/* Setup the data pointer of the first BD of the packet */
@@ -3770,7 +3778,7 @@ int bnx2x_reload_if_running(struct net_device *dev)
 	if (unlikely(!netif_running(dev)))
 		return 0;
 
-	bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+	bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 	return bnx2x_nic_load(bp, LOAD_NORMAL);
 }
 
@@ -3967,7 +3975,7 @@ int bnx2x_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	netif_device_detach(dev);
 
-	bnx2x_nic_unload(bp, UNLOAD_CLOSE);
+	bnx2x_nic_unload(bp, UNLOAD_CLOSE, false);
 
 	bnx2x_set_power_state(bp, pci_choose_state(pdev, state));
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index dfd86a55f1dc..9c5ea6c5b4c7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -83,8 +83,9 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode);
  * bnx2x_send_unload_done - send UNLOAD_DONE command to the MCP.
  *
  * @bp:		driver handle
+ * @keep_link:		true iff link should be kept up
  */
-void bnx2x_send_unload_done(struct bnx2x *bp);
+void bnx2x_send_unload_done(struct bnx2x *bp, bool keep_link);
 
 /**
  * bnx2x_config_rss_pf - configure RSS parameters in a PF.
@@ -153,6 +154,14 @@ u8 bnx2x_initial_phy_init(struct bnx2x *bp, int load_mode);
 void bnx2x_link_set(struct bnx2x *bp);
 
 /**
+ * bnx2x_force_link_reset - Forces link reset, and put the PHY
+ * in reset as well.
+ *
+ * @bp:		driver handle
+ */
+void bnx2x_force_link_reset(struct bnx2x *bp);
+
+/**
  * bnx2x_link_test - query link status.
  *
  * @bp:		driver handle
@@ -312,12 +321,13 @@ void bnx2x_set_num_queues(struct bnx2x *bp);
  *
  * @bp:			driver handle
  * @unload_mode:	COMMON, PORT, FUNCTION
+ * @keep_link:		true iff link should be kept up.
  *
  * - Cleanup MAC configuration.
  * - Closes clients.
  * - etc.
  */
-void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode);
+void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link);
 
 /**
  * bnx2x_acquire_hw_lock - acquire HW lock.
@@ -446,7 +456,7 @@ void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl);
 bool bnx2x_test_firmware_version(struct bnx2x *bp, bool is_err);
 
 /* dev_close main block */
-int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode);
+int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link);
 
 /* dev_open main block */
 int bnx2x_nic_load(struct bnx2x *bp, int load_mode);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 8a73374e52a7..2245c3895409 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -91,25 +91,21 @@ static void bnx2x_pfc_set(struct bnx2x *bp)
 	/*
 	 * Rx COS configuration
 	 * Changing PFC RX configuration .
-	 * In RX COS0 will always be configured to lossy and COS1 to lossless
+	 * In RX COS0 will always be configured to lossless and COS1 to lossy
 	 */
 	for (i = 0 ; i < MAX_PFC_PRIORITIES ; i++) {
 		pri_bit = 1 << i;
 
-		if (pri_bit & DCBX_PFC_PRI_PAUSE_MASK(bp))
+		if (!(pri_bit & DCBX_PFC_PRI_PAUSE_MASK(bp)))
 			val |= 1 << (i * 4);
 	}
 
 	pfc_params.pkt_priority_to_cos = val;
 
 	/* RX COS0 */
-	pfc_params.llfc_low_priority_classes = 0;
+	pfc_params.llfc_low_priority_classes = DCBX_PFC_PRI_PAUSE_MASK(bp);
 	/* RX COS1 */
-	pfc_params.llfc_high_priority_classes = DCBX_PFC_PRI_PAUSE_MASK(bp);
-
-	/* BRB configuration */
-	pfc_params.cos0_pauseable = false;
-	pfc_params.cos1_pauseable = true;
+	pfc_params.llfc_high_priority_classes = 0;
 
 	bnx2x_acquire_phy_lock(bp);
 	bp->link_params.feature_config_flags |= FEATURE_CONFIG_PFC_ENABLED;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index ebf40cd7aa10..c65295dded39 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -905,6 +905,7 @@ static int bnx2x_nway_reset(struct net_device *dev)
 
 	if (netif_running(dev)) {
 		bnx2x_stats_handle(bp, STATS_EVENT_STOP);
+		bnx2x_force_link_reset(bp);
 		bnx2x_link_set(bp);
 	}
 
@@ -1606,7 +1607,7 @@ static int bnx2x_set_pauseparam(struct net_device *dev,
 	return 0;
 }
 
-static char *bnx2x_tests_str_arr[BNX2X_NUM_TESTS_SF] = {
+static const char bnx2x_tests_str_arr[BNX2X_NUM_TESTS_SF][ETH_GSTRING_LEN] = {
 	"register_test (offline)    ",
 	"memory_test (offline)      ",
 	"int_loopback_test (offline)",
@@ -1653,7 +1654,7 @@ static int bnx2x_get_eee(struct net_device *dev, struct ethtool_eee *edata)
 		return -EOPNOTSUPP;
 	}
 
-	eee_cfg = SHMEM2_RD(bp, eee_status[BP_PORT(bp)]);
+	eee_cfg = bp->link_vars.eee_status;
 
 	edata->supported =
 		bnx2x_eee_to_adv((eee_cfg & SHMEM_EEE_SUPPORTED_MASK) >>
@@ -1690,7 +1691,7 @@ static int bnx2x_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 		return -EOPNOTSUPP;
 	}
 
-	eee_cfg = SHMEM2_RD(bp, eee_status[BP_PORT(bp)]);
+	eee_cfg = bp->link_vars.eee_status;
 
 	if (!(eee_cfg & SHMEM_EEE_SUPPORTED_MASK)) {
 		DP(BNX2X_MSG_ETHTOOL, "Board does not support EEE!\n");
@@ -1739,6 +1740,7 @@ static int bnx2x_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	/* Restart link to propogate changes */
 	if (netif_running(dev)) {
 		bnx2x_stats_handle(bp, STATS_EVENT_STOP);
+		bnx2x_force_link_reset(bp);
 		bnx2x_link_set(bp);
 	}
 
@@ -2038,8 +2040,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	u16 pkt_prod, bd_prod;
 	struct sw_tx_bd *tx_buf;
 	struct eth_tx_start_bd *tx_start_bd;
-	struct eth_tx_parse_bd_e1x  *pbd_e1x = NULL;
-	struct eth_tx_parse_bd_e2  *pbd_e2 = NULL;
 	dma_addr_t mapping;
 	union eth_rx_cqe *cqe;
 	u8 cqe_fp_flags, cqe_fp_type;
@@ -2131,21 +2131,32 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	tx_start_bd->vlan_or_ethertype = cpu_to_le16(pkt_prod);
 	tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD;
 	SET_FLAG(tx_start_bd->general_data,
-		 ETH_TX_START_BD_ETH_ADDR_TYPE,
-		 UNICAST_ADDRESS);
-	SET_FLAG(tx_start_bd->general_data,
 		 ETH_TX_START_BD_HDR_NBDS,
 		 1);
+	SET_FLAG(tx_start_bd->general_data,
+		 ETH_TX_START_BD_PARSE_NBDS,
+		 0);
 
 	/* turn on parsing and get a BD */
 	bd_prod = TX_BD(NEXT_TX_IDX(bd_prod));
 
-	pbd_e1x = &txdata->tx_desc_ring[bd_prod].parse_bd_e1x;
-	pbd_e2 = &txdata->tx_desc_ring[bd_prod].parse_bd_e2;
-
-	memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2));
-	memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x));
-
+	if (CHIP_IS_E1x(bp)) {
+		u16 global_data = 0;
+		struct eth_tx_parse_bd_e1x  *pbd_e1x =
+			&txdata->tx_desc_ring[bd_prod].parse_bd_e1x;
+		memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x));
+		SET_FLAG(global_data,
+			 ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE, UNICAST_ADDRESS);
+		pbd_e1x->global_data = cpu_to_le16(global_data);
+	} else {
+		u32 parsing_data = 0;
+		struct eth_tx_parse_bd_e2  *pbd_e2 =
+			&txdata->tx_desc_ring[bd_prod].parse_bd_e2;
+		memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2));
+		SET_FLAG(parsing_data,
+			 ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE, UNICAST_ADDRESS);
+		pbd_e2->parsing_data = cpu_to_le32(parsing_data);
+	}
 	wmb();
 
 	txdata->tx_db.data.prod += 2;
@@ -2263,7 +2274,7 @@ static int bnx2x_test_ext_loopback(struct bnx2x *bp)
 	if (!netif_running(bp->dev))
 		return BNX2X_EXT_LOOPBACK_FAILED;
 
-	bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+	bnx2x_nic_unload(bp, UNLOAD_NORMAL, false);
 	rc = bnx2x_nic_load(bp, LOAD_LOOPBACK_EXT);
 	if (rc) {
 		DP(BNX2X_MSG_ETHTOOL,
@@ -2414,7 +2425,7 @@ static void bnx2x_self_test(struct net_device *dev,
 
 		link_up = bp->link_vars.link_up;
 
-		bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+		bnx2x_nic_unload(bp, UNLOAD_NORMAL, false);
 		rc = bnx2x_nic_load(bp, LOAD_DIAG);
 		if (rc) {
 			etest->flags |= ETH_TEST_FL_FAILED;
@@ -2446,7 +2457,7 @@ static void bnx2x_self_test(struct net_device *dev,
 			etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
 		}
 
-		bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+		bnx2x_nic_unload(bp, UNLOAD_NORMAL, false);
 
 		/* restore input for TX port IF */
 		REG_WR(bp, NIG_REG_EGRESS_UMP0_IN_EN + port*4, val);
@@ -2534,7 +2545,7 @@ static int bnx2x_get_sset_count(struct net_device *dev, int stringset)
 static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	int i, j, k, offset, start;
+	int i, j, k, start;
 	char queue_name[MAX_QUEUE_NAME_LEN+1];
 
 	switch (stringset) {
@@ -2570,13 +2581,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 			start = 0;
 		else
 			start = 4;
-		for (i = 0, j = start; j < (start + BNX2X_NUM_TESTS(bp));
-		     i++, j++) {
-			offset = sprintf(buf+32*i, "%s",
-					 bnx2x_tests_str_arr[j]);
-			*(buf+offset) = '\0';
-		}
-		break;
+		memcpy(buf, bnx2x_tests_str_arr + start,
+		       ETH_GSTRING_LEN * BNX2X_NUM_TESTS(bp));
 	}
 }
 
@@ -2940,7 +2946,7 @@ static int bnx2x_set_channels(struct net_device *dev,
 		bnx2x_change_num_queues(bp, channels->combined_count);
 		return 0;
 	}
-	bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+	bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 	bnx2x_change_num_queues(bp, channels->combined_count);
 	return bnx2x_nic_load(bp, LOAD_NORMAL);
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
index bbc66ced9c25..620fe939ecfd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
@@ -88,9 +88,6 @@
 #define TSTORM_ASSERT_LIST_INDEX_OFFSET	(IRO[102].base)
 #define TSTORM_ASSERT_LIST_OFFSET(assertListEntry) \
 	(IRO[101].base + ((assertListEntry) * IRO[101].m1))
-#define TSTORM_COMMON_SAFC_WORKAROUND_ENABLE_OFFSET (IRO[107].base)
-#define TSTORM_COMMON_SAFC_WORKAROUND_TIMEOUT_10USEC_OFFSET \
-	(IRO[108].base)
 #define TSTORM_FUNCTION_COMMON_CONFIG_OFFSET(pfId) \
 	(IRO[201].base + ((pfId) * IRO[201].m1))
 #define TSTORM_FUNC_EN_OFFSET(funcId) \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index 76b6e65790f8..18704929e642 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -1286,6 +1286,9 @@ struct drv_func_mb {
 	#define DRV_MSG_CODE_SET_MF_BW_MIN_MASK         0x00ff0000
 	#define DRV_MSG_CODE_SET_MF_BW_MAX_MASK         0xff000000
 
+	#define DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET     0x00000002
+
+	#define DRV_MSG_CODE_LOAD_REQ_WITH_LFA          0x0000100a
 	u32 fw_mb_header;
 	#define FW_MSG_CODE_MASK                        0xffff0000
 	#define FW_MSG_CODE_DRV_LOAD_COMMON             0x10100000
@@ -1909,6 +1912,54 @@ struct lldp_local_mib {
 };
 /***END OF DCBX STRUCTURES DECLARATIONS***/
 
+/***********************************************************/
+/*                         Elink section                   */
+/***********************************************************/
+#define SHMEM_LINK_CONFIG_SIZE 2
+struct shmem_lfa {
+	u32 req_duplex;
+	#define REQ_DUPLEX_PHY0_MASK        0x0000ffff
+	#define REQ_DUPLEX_PHY0_SHIFT       0
+	#define REQ_DUPLEX_PHY1_MASK        0xffff0000
+	#define REQ_DUPLEX_PHY1_SHIFT       16
+	u32 req_flow_ctrl;
+	#define REQ_FLOW_CTRL_PHY0_MASK     0x0000ffff
+	#define REQ_FLOW_CTRL_PHY0_SHIFT    0
+	#define REQ_FLOW_CTRL_PHY1_MASK     0xffff0000
+	#define REQ_FLOW_CTRL_PHY1_SHIFT    16
+	u32 req_line_speed; /* Also determine AutoNeg */
+	#define REQ_LINE_SPD_PHY0_MASK      0x0000ffff
+	#define REQ_LINE_SPD_PHY0_SHIFT     0
+	#define REQ_LINE_SPD_PHY1_MASK      0xffff0000
+	#define REQ_LINE_SPD_PHY1_SHIFT     16
+	u32 speed_cap_mask[SHMEM_LINK_CONFIG_SIZE];
+	u32 additional_config;
+	#define REQ_FC_AUTO_ADV_MASK        0x0000ffff
+	#define REQ_FC_AUTO_ADV0_SHIFT      0
+	#define NO_LFA_DUE_TO_DCC_MASK      0x00010000
+	u32 lfa_sts;
+	#define LFA_LINK_FLAP_REASON_OFFSET		0
+	#define LFA_LINK_FLAP_REASON_MASK		0x000000ff
+		#define LFA_LINK_DOWN			    0x1
+		#define LFA_LOOPBACK_ENABLED		0x2
+		#define LFA_DUPLEX_MISMATCH		    0x3
+		#define LFA_MFW_IS_TOO_OLD		    0x4
+		#define LFA_LINK_SPEED_MISMATCH		0x5
+		#define LFA_FLOW_CTRL_MISMATCH		0x6
+		#define LFA_SPEED_CAP_MISMATCH		0x7
+		#define LFA_DCC_LFA_DISABLED		0x8
+		#define LFA_EEE_MISMATCH		0x9
+
+	#define LINK_FLAP_AVOIDANCE_COUNT_OFFSET	8
+	#define LINK_FLAP_AVOIDANCE_COUNT_MASK		0x0000ff00
+
+	#define LINK_FLAP_COUNT_OFFSET			16
+	#define LINK_FLAP_COUNT_MASK			0x00ff0000
+
+	#define LFA_FLAGS_MASK				0xff000000
+	#define SHMEM_LFA_DONT_CLEAR_STAT		(1<<24)
+};
+
 struct ncsi_oem_fcoe_features {
 	u32 fcoe_features1;
 	#define FCOE_FEATURES1_IOS_PER_CONNECTION_MASK          0x0000FFFF
@@ -2738,8 +2789,8 @@ struct afex_stats {
 };
 
 #define BCM_5710_FW_MAJOR_VERSION			7
-#define BCM_5710_FW_MINOR_VERSION			2
-#define BCM_5710_FW_REVISION_VERSION			51
+#define BCM_5710_FW_MINOR_VERSION			8
+#define BCM_5710_FW_REVISION_VERSION		2
 #define BCM_5710_FW_ENGINEERING_VERSION			0
 #define BCM_5710_FW_COMPILE_FLAGS			1
 
@@ -3861,10 +3912,8 @@ struct eth_rss_update_ramrod_data {
 #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_TCP_CAPABILITY_SHIFT 4
 #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY (0x1<<5)
 #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY_SHIFT 5
-#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<6)
-#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 6
-#define __ETH_RSS_UPDATE_RAMROD_DATA_RESERVED0 (0x1<<7)
-#define __ETH_RSS_UPDATE_RAMROD_DATA_RESERVED0_SHIFT 7
+#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<7)
+#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 7
 	u8 rss_result_mask;
 	u8 rss_mode;
 	__le32 __reserved2;
@@ -4080,27 +4129,29 @@ struct eth_tx_start_bd {
 #define ETH_TX_START_BD_HDR_NBDS_SHIFT 0
 #define ETH_TX_START_BD_FORCE_VLAN_MODE (0x1<<4)
 #define ETH_TX_START_BD_FORCE_VLAN_MODE_SHIFT 4
-#define ETH_TX_START_BD_RESREVED (0x1<<5)
-#define ETH_TX_START_BD_RESREVED_SHIFT 5
-#define ETH_TX_START_BD_ETH_ADDR_TYPE (0x3<<6)
-#define ETH_TX_START_BD_ETH_ADDR_TYPE_SHIFT 6
+#define ETH_TX_START_BD_PARSE_NBDS (0x3<<5)
+#define ETH_TX_START_BD_PARSE_NBDS_SHIFT 5
+#define ETH_TX_START_BD_RESREVED (0x1<<7)
+#define ETH_TX_START_BD_RESREVED_SHIFT 7
 };
 
 /*
  * Tx parsing BD structure for ETH E1/E1h
  */
 struct eth_tx_parse_bd_e1x {
-	u8 global_data;
+	__le16 global_data;
 #define ETH_TX_PARSE_BD_E1X_IP_HDR_START_OFFSET_W (0xF<<0)
 #define ETH_TX_PARSE_BD_E1X_IP_HDR_START_OFFSET_W_SHIFT 0
-#define ETH_TX_PARSE_BD_E1X_RESERVED0 (0x1<<4)
-#define ETH_TX_PARSE_BD_E1X_RESERVED0_SHIFT 4
-#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN (0x1<<5)
-#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN_SHIFT 5
-#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN (0x1<<6)
-#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT 6
-#define ETH_TX_PARSE_BD_E1X_NS_FLG (0x1<<7)
-#define ETH_TX_PARSE_BD_E1X_NS_FLG_SHIFT 7
+#define ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE (0x3<<4)
+#define ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE_SHIFT 4
+#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN (0x1<<6)
+#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN_SHIFT 6
+#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN (0x1<<7)
+#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT 7
+#define ETH_TX_PARSE_BD_E1X_NS_FLG (0x1<<8)
+#define ETH_TX_PARSE_BD_E1X_NS_FLG_SHIFT 8
+#define ETH_TX_PARSE_BD_E1X_RESERVED0 (0x7F<<9)
+#define ETH_TX_PARSE_BD_E1X_RESERVED0_SHIFT 9
 	u8 tcp_flags;
 #define ETH_TX_PARSE_BD_E1X_FIN_FLG (0x1<<0)
 #define ETH_TX_PARSE_BD_E1X_FIN_FLG_SHIFT 0
@@ -4119,7 +4170,6 @@ struct eth_tx_parse_bd_e1x {
 #define ETH_TX_PARSE_BD_E1X_CWR_FLG (0x1<<7)
 #define ETH_TX_PARSE_BD_E1X_CWR_FLG_SHIFT 7
 	u8 ip_hlen_w;
-	s8 reserved;
 	__le16 total_hlen_w;
 	__le16 tcp_pseudo_csum;
 	__le16 lso_mss;
@@ -4138,14 +4188,16 @@ struct eth_tx_parse_bd_e2 {
 	__le16 src_mac_addr_mid;
 	__le16 src_mac_addr_hi;
 	__le32 parsing_data;
-#define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W (0x1FFF<<0)
+#define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W (0x7FF<<0)
 #define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT 0
-#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW (0xF<<13)
-#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT 13
-#define ETH_TX_PARSE_BD_E2_LSO_MSS (0x3FFF<<17)
-#define ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT 17
-#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR (0x1<<31)
-#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR_SHIFT 31
+#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW (0xF<<11)
+#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT 11
+#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR (0x1<<15)
+#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR_SHIFT 15
+#define ETH_TX_PARSE_BD_E2_LSO_MSS (0x3FFF<<16)
+#define ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT 16
+#define ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE (0x3<<30)
+#define ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE_SHIFT 30
 };
 
 /*
@@ -4913,7 +4965,8 @@ struct flow_control_configuration {
  *
  */
 struct function_start_data {
-	__le16 function_mode;
+	u8 function_mode;
+	u8 reserved;
 	__le16 sd_vlan_tag;
 	__le16 vif_id;
 	u8 path_id;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index 559c396d45cc..c8f10f0e8a0d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -566,7 +566,7 @@ static const struct {
 		u32 e2;		/* 57712 */
 		u32 e3;		/* 578xx */
 	} reg_mask;		/* Register mask (all valid bits) */
-	char name[7];		/* Block's longest name is 6 characters long
+	char name[8];		/* Block's longest name is 7 characters long
 				 * (name + suffix)
 				 */
 } bnx2x_blocks_parity_data[] = {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index b046beb435b2..e2e45ee5df33 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -161,120 +161,6 @@
 #define EDC_MODE_LIMITING				0x0044
 #define EDC_MODE_PASSIVE_DAC			0x0055
 
-/* BRB default for class 0 E2 */
-#define DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR	170
-#define DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR		250
-#define DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR		10
-#define DEFAULT0_E2_BRB_MAC_FULL_XON_THR		50
-
-/* BRB thresholds for E2*/
-#define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE		170
-#define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE		0
-
-#define PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE		250
-#define PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE		0
-
-#define PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE		10
-#define PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE		90
-
-#define PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE			50
-#define PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE		250
-
-/* BRB default for class 0 E3A0 */
-#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR	290
-#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR	410
-#define DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR	10
-#define DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR	50
-
-/* BRB thresholds for E3A0 */
-#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE		290
-#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE		0
-
-#define PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE		410
-#define PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE		0
-
-#define PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE		10
-#define PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE		170
-
-#define PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE		50
-#define PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE		410
-
-/* BRB default for E3B0 */
-#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR	330
-#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR	490
-#define DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR	15
-#define DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR	55
-
-/* BRB thresholds for E3B0 2 port mode*/
-#define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE		1025
-#define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE	0
-
-#define PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE		1025
-#define PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE	0
-
-#define PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE		10
-#define PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE	1025
-
-#define PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE		50
-#define PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE	1025
-
-/* only for E3B0*/
-#define PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR			1025
-#define PFC_E3B0_2P_BRB_FULL_LB_XON_THR			1025
-
-/* Lossy +Lossless GUARANTIED == GUART */
-#define PFC_E3B0_2P_MIX_PAUSE_LB_GUART			284
-/* Lossless +Lossless*/
-#define PFC_E3B0_2P_PAUSE_LB_GUART			236
-/* Lossy +Lossy*/
-#define PFC_E3B0_2P_NON_PAUSE_LB_GUART			342
-
-/* Lossy +Lossless*/
-#define PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART		284
-/* Lossless +Lossless*/
-#define PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART		236
-/* Lossy +Lossy*/
-#define PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART		336
-#define PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST		80
-
-#define PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART		0
-#define PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST		0
-
-/* BRB thresholds for E3B0 4 port mode */
-#define PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE		304
-#define PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE	0
-
-#define PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE		384
-#define PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE	0
-
-#define PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE		10
-#define PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE	304
-
-#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE		50
-#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE	384
-
-/* only for E3B0*/
-#define PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR			304
-#define PFC_E3B0_4P_BRB_FULL_LB_XON_THR			384
-#define PFC_E3B0_4P_LB_GUART		120
-
-#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART		120
-#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST	80
-
-#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART		80
-#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST	120
-
-/* Pause defines*/
-#define DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR			330
-#define DEFAULT_E3B0_BRB_FULL_LB_XON_THR			490
-#define DEFAULT_E3B0_LB_GUART		40
-
-#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART		40
-#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST	0
-
-#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART		40
-#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST	0
-
 /* ETS defines*/
 #define DCBX_INVALID_COS					(0xFF)
 
@@ -321,6 +207,127 @@ static u32 bnx2x_bits_dis(struct bnx2x *bp, u32 reg, u32 bits)
 	return val;
 }
 
+/*
+ * bnx2x_check_lfa - This function checks if link reinitialization is required,
+ *                   or link flap can be avoided.
+ *
+ * @params:	link parameters
+ * Returns 0 if Link Flap Avoidance conditions are met otherwise, the failed
+ *         condition code.
+ */
+static int bnx2x_check_lfa(struct link_params *params)
+{
+	u32 link_status, cfg_idx, lfa_mask, cfg_size;
+	u32 cur_speed_cap_mask, cur_req_fc_auto_adv, additional_config;
+	u32 saved_val, req_val, eee_status;
+	struct bnx2x *bp = params->bp;
+
+	additional_config =
+		REG_RD(bp, params->lfa_base +
+			   offsetof(struct shmem_lfa, additional_config));
+
+	/* NOTE: must be first condition checked -
+	* to verify DCC bit is cleared in any case!
+	*/
+	if (additional_config & NO_LFA_DUE_TO_DCC_MASK) {
+		DP(NETIF_MSG_LINK, "No LFA due to DCC flap after clp exit\n");
+		REG_WR(bp, params->lfa_base +
+			   offsetof(struct shmem_lfa, additional_config),
+		       additional_config & ~NO_LFA_DUE_TO_DCC_MASK);
+		return LFA_DCC_LFA_DISABLED;
+	}
+
+	/* Verify that link is up */
+	link_status = REG_RD(bp, params->shmem_base +
+			     offsetof(struct shmem_region,
+				      port_mb[params->port].link_status));
+	if (!(link_status & LINK_STATUS_LINK_UP))
+		return LFA_LINK_DOWN;
+
+	/* Verify that loopback mode is not set */
+	if (params->loopback_mode)
+		return LFA_LOOPBACK_ENABLED;
+
+	/* Verify that MFW supports LFA */
+	if (!params->lfa_base)
+		return LFA_MFW_IS_TOO_OLD;
+
+	if (params->num_phys == 3) {
+		cfg_size = 2;
+		lfa_mask = 0xffffffff;
+	} else {
+		cfg_size = 1;
+		lfa_mask = 0xffff;
+	}
+
+	/* Compare Duplex */
+	saved_val = REG_RD(bp, params->lfa_base +
+			   offsetof(struct shmem_lfa, req_duplex));
+	req_val = params->req_duplex[0] | (params->req_duplex[1] << 16);
+	if ((saved_val & lfa_mask) != (req_val & lfa_mask)) {
+		DP(NETIF_MSG_LINK, "Duplex mismatch %x vs. %x\n",
+			       (saved_val & lfa_mask), (req_val & lfa_mask));
+		return LFA_DUPLEX_MISMATCH;
+	}
+	/* Compare Flow Control */
+	saved_val = REG_RD(bp, params->lfa_base +
+			   offsetof(struct shmem_lfa, req_flow_ctrl));
+	req_val = params->req_flow_ctrl[0] | (params->req_flow_ctrl[1] << 16);
+	if ((saved_val & lfa_mask) != (req_val & lfa_mask)) {
+		DP(NETIF_MSG_LINK, "Flow control mismatch %x vs. %x\n",
+			       (saved_val & lfa_mask), (req_val & lfa_mask));
+		return LFA_FLOW_CTRL_MISMATCH;
+	}
+	/* Compare Link Speed */
+	saved_val = REG_RD(bp, params->lfa_base +
+			   offsetof(struct shmem_lfa, req_line_speed));
+	req_val = params->req_line_speed[0] | (params->req_line_speed[1] << 16);
+	if ((saved_val & lfa_mask) != (req_val & lfa_mask)) {
+		DP(NETIF_MSG_LINK, "Link speed mismatch %x vs. %x\n",
+			       (saved_val & lfa_mask), (req_val & lfa_mask));
+		return LFA_LINK_SPEED_MISMATCH;
+	}
+
+	for (cfg_idx = 0; cfg_idx < cfg_size; cfg_idx++) {
+		cur_speed_cap_mask = REG_RD(bp, params->lfa_base +
+					    offsetof(struct shmem_lfa,
+						     speed_cap_mask[cfg_idx]));
+
+		if (cur_speed_cap_mask != params->speed_cap_mask[cfg_idx]) {
+			DP(NETIF_MSG_LINK, "Speed Cap mismatch %x vs. %x\n",
+				       cur_speed_cap_mask,
+				       params->speed_cap_mask[cfg_idx]);
+			return LFA_SPEED_CAP_MISMATCH;
+		}
+	}
+
+	cur_req_fc_auto_adv =
+		REG_RD(bp, params->lfa_base +
+		       offsetof(struct shmem_lfa, additional_config)) &
+		REQ_FC_AUTO_ADV_MASK;
+
+	if ((u16)cur_req_fc_auto_adv != params->req_fc_auto_adv) {
+		DP(NETIF_MSG_LINK, "Flow Ctrl AN mismatch %x vs. %x\n",
+			       cur_req_fc_auto_adv, params->req_fc_auto_adv);
+		return LFA_FLOW_CTRL_MISMATCH;
+	}
+
+	eee_status = REG_RD(bp, params->shmem2_base +
+			    offsetof(struct shmem2_region,
+				     eee_status[params->port]));
+
+	if (((eee_status & SHMEM_EEE_LPI_REQUESTED_BIT) ^
+	     (params->eee_mode & EEE_MODE_ENABLE_LPI)) ||
+	    ((eee_status & SHMEM_EEE_REQUESTED_BIT) ^
+	     (params->eee_mode & EEE_MODE_ADV_LPI))) {
+		DP(NETIF_MSG_LINK, "EEE mismatch %x vs. %x\n", params->eee_mode,
+			       eee_status);
+		return LFA_EEE_MISMATCH;
+	}
+
+	/* LFA conditions are met */
+	return 0;
+}
 /******************************************************************/
 /*			EPIO/GPIO section			  */
 /******************************************************************/
@@ -1307,93 +1314,6 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos)
 }
 
 /******************************************************************/
-/*			EEE section				   */
-/******************************************************************/
-static u8 bnx2x_eee_has_cap(struct link_params *params)
-{
-	struct bnx2x *bp = params->bp;
-
-	if (REG_RD(bp, params->shmem2_base) <=
-		   offsetof(struct shmem2_region, eee_status[params->port]))
-		return 0;
-
-	return 1;
-}
-
-static int bnx2x_eee_nvram_to_time(u32 nvram_mode, u32 *idle_timer)
-{
-	switch (nvram_mode) {
-	case PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED:
-		*idle_timer = EEE_MODE_NVRAM_BALANCED_TIME;
-		break;
-	case PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE:
-		*idle_timer = EEE_MODE_NVRAM_AGGRESSIVE_TIME;
-		break;
-	case PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY:
-		*idle_timer = EEE_MODE_NVRAM_LATENCY_TIME;
-		break;
-	default:
-		*idle_timer = 0;
-		break;
-	}
-
-	return 0;
-}
-
-static int bnx2x_eee_time_to_nvram(u32 idle_timer, u32 *nvram_mode)
-{
-	switch (idle_timer) {
-	case EEE_MODE_NVRAM_BALANCED_TIME:
-		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED;
-		break;
-	case EEE_MODE_NVRAM_AGGRESSIVE_TIME:
-		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE;
-		break;
-	case EEE_MODE_NVRAM_LATENCY_TIME:
-		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY;
-		break;
-	default:
-		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_DISABLED;
-		break;
-	}
-
-	return 0;
-}
-
-static u32 bnx2x_eee_calc_timer(struct link_params *params)
-{
-	u32 eee_mode, eee_idle;
-	struct bnx2x *bp = params->bp;
-
-	if (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) {
-		if (params->eee_mode & EEE_MODE_OUTPUT_TIME) {
-			/* time value in eee_mode --> used directly*/
-			eee_idle = params->eee_mode & EEE_MODE_TIMER_MASK;
-		} else {
-			/* hsi value in eee_mode --> time */
-			if (bnx2x_eee_nvram_to_time(params->eee_mode &
-						    EEE_MODE_NVRAM_MASK,
-						    &eee_idle))
-				return 0;
-		}
-	} else {
-		/* hsi values in nvram --> time*/
-		eee_mode = ((REG_RD(bp, params->shmem_base +
-				    offsetof(struct shmem_region, dev_info.
-				    port_feature_config[params->port].
-				    eee_power_mode)) &
-			     PORT_FEAT_CFG_EEE_POWER_MODE_MASK) >>
-			    PORT_FEAT_CFG_EEE_POWER_MODE_SHIFT);
-
-		if (bnx2x_eee_nvram_to_time(eee_mode, &eee_idle))
-			return 0;
-	}
-
-	return eee_idle;
-}
-
-
-/******************************************************************/
 /*			PFC section				  */
 /******************************************************************/
 static void bnx2x_update_pfc_xmac(struct link_params *params,
@@ -1606,16 +1526,23 @@ static void bnx2x_set_xumac_nig(struct link_params *params,
 	       NIG_REG_P0_MAC_PAUSE_OUT_EN, tx_pause_en);
 }
 
-static void bnx2x_umac_disable(struct link_params *params)
+static void bnx2x_set_umac_rxtx(struct link_params *params, u8 en)
 {
 	u32 umac_base = params->port ? GRCBASE_UMAC1 : GRCBASE_UMAC0;
+	u32 val;
 	struct bnx2x *bp = params->bp;
 	if (!(REG_RD(bp, MISC_REG_RESET_REG_2) &
 		   (MISC_REGISTERS_RESET_REG_2_UMAC0 << params->port)))
 		return;
-
+	val = REG_RD(bp, umac_base + UMAC_REG_COMMAND_CONFIG);
+	if (en)
+		val |= (UMAC_COMMAND_CONFIG_REG_TX_ENA |
+			UMAC_COMMAND_CONFIG_REG_RX_ENA);
+	else
+		val &= ~(UMAC_COMMAND_CONFIG_REG_TX_ENA |
+			 UMAC_COMMAND_CONFIG_REG_RX_ENA);
 	/* Disable RX and TX */
-	REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, 0);
+	REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, val);
 }
 
 static void bnx2x_umac_enable(struct link_params *params,
@@ -1671,6 +1598,16 @@ static void bnx2x_umac_enable(struct link_params *params,
 	REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, val);
 	udelay(50);
 
+	/* Configure UMAC for EEE */
+	if (vars->eee_status & SHMEM_EEE_ADV_STATUS_MASK) {
+		DP(NETIF_MSG_LINK, "configured UMAC for EEE\n");
+		REG_WR(bp, umac_base + UMAC_REG_UMAC_EEE_CTRL,
+		       UMAC_UMAC_EEE_CTRL_REG_EEE_EN);
+		REG_WR(bp, umac_base + UMAC_REG_EEE_WAKE_TIMER, 0x11);
+	} else {
+		REG_WR(bp, umac_base + UMAC_REG_UMAC_EEE_CTRL, 0x0);
+	}
+
 	/* Set MAC address for source TX Pause/PFC frames (under SW reset) */
 	REG_WR(bp, umac_base + UMAC_REG_MAC_ADDR0,
 	       ((params->mac_addr[2] << 24) |
@@ -1766,11 +1703,12 @@ static void bnx2x_xmac_init(struct link_params *params, u32 max_speed)
 
 }
 
-static void bnx2x_xmac_disable(struct link_params *params)
+static void bnx2x_set_xmac_rxtx(struct link_params *params, u8 en)
 {
 	u8 port = params->port;
 	struct bnx2x *bp = params->bp;
 	u32 pfc_ctrl, xmac_base = (port) ? GRCBASE_XMAC1 : GRCBASE_XMAC0;
+	u32 val;
 
 	if (REG_RD(bp, MISC_REG_RESET_REG_2) &
 	    MISC_REGISTERS_RESET_REG_2_XMAC) {
@@ -1784,7 +1722,12 @@ static void bnx2x_xmac_disable(struct link_params *params)
 		REG_WR(bp, xmac_base + XMAC_REG_PFC_CTRL_HI,
 		       (pfc_ctrl | (1<<1)));
 		DP(NETIF_MSG_LINK, "Disable XMAC on port %x\n", port);
-		REG_WR(bp, xmac_base + XMAC_REG_CTRL, 0);
+		val = REG_RD(bp, xmac_base + XMAC_REG_CTRL);
+		if (en)
+			val |= (XMAC_CTRL_REG_TX_EN | XMAC_CTRL_REG_RX_EN);
+		else
+			val &= ~(XMAC_CTRL_REG_TX_EN | XMAC_CTRL_REG_RX_EN);
+		REG_WR(bp, xmac_base + XMAC_REG_CTRL, val);
 	}
 }
 
@@ -2087,391 +2030,6 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params,
 	REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2);
 }
 
-/* PFC BRB internal port configuration params */
-struct bnx2x_pfc_brb_threshold_val {
-	u32 pause_xoff;
-	u32 pause_xon;
-	u32 full_xoff;
-	u32 full_xon;
-};
-
-struct bnx2x_pfc_brb_e3b0_val {
-	u32 per_class_guaranty_mode;
-	u32 lb_guarantied_hyst;
-	u32 full_lb_xoff_th;
-	u32 full_lb_xon_threshold;
-	u32 lb_guarantied;
-	u32 mac_0_class_t_guarantied;
-	u32 mac_0_class_t_guarantied_hyst;
-	u32 mac_1_class_t_guarantied;
-	u32 mac_1_class_t_guarantied_hyst;
-};
-
-struct bnx2x_pfc_brb_th_val {
-	struct bnx2x_pfc_brb_threshold_val pauseable_th;
-	struct bnx2x_pfc_brb_threshold_val non_pauseable_th;
-	struct bnx2x_pfc_brb_threshold_val default_class0;
-	struct bnx2x_pfc_brb_threshold_val default_class1;
-
-};
-static int bnx2x_pfc_brb_get_config_params(
-				struct link_params *params,
-				struct bnx2x_pfc_brb_th_val *config_val)
-{
-	struct bnx2x *bp = params->bp;
-	DP(NETIF_MSG_LINK, "Setting PFC BRB configuration\n");
-
-	config_val->default_class1.pause_xoff = 0;
-	config_val->default_class1.pause_xon = 0;
-	config_val->default_class1.full_xoff = 0;
-	config_val->default_class1.full_xon = 0;
-
-	if (CHIP_IS_E2(bp)) {
-		/* Class0 defaults */
-		config_val->default_class0.pause_xoff =
-			DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR;
-		config_val->default_class0.pause_xon =
-			DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR;
-		config_val->default_class0.full_xoff =
-			DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR;
-		config_val->default_class0.full_xon =
-			DEFAULT0_E2_BRB_MAC_FULL_XON_THR;
-		/* Pause able*/
-		config_val->pauseable_th.pause_xoff =
-			PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
-		config_val->pauseable_th.pause_xon =
-			PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE;
-		config_val->pauseable_th.full_xoff =
-			PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE;
-		config_val->pauseable_th.full_xon =
-			PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE;
-		/* Non pause able*/
-		config_val->non_pauseable_th.pause_xoff =
-			PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.pause_xon =
-			PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xoff =
-			PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xon =
-			PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-	} else if (CHIP_IS_E3A0(bp)) {
-		/* Class0 defaults */
-		config_val->default_class0.pause_xoff =
-			DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR;
-		config_val->default_class0.pause_xon =
-			DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR;
-		config_val->default_class0.full_xoff =
-			DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR;
-		config_val->default_class0.full_xon =
-			DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR;
-		/* Pause able */
-		config_val->pauseable_th.pause_xoff =
-			PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
-		config_val->pauseable_th.pause_xon =
-			PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE;
-		config_val->pauseable_th.full_xoff =
-			PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE;
-		config_val->pauseable_th.full_xon =
-			PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE;
-		/* Non pause able*/
-		config_val->non_pauseable_th.pause_xoff =
-			PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.pause_xon =
-			PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xoff =
-			PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xon =
-			PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-	} else if (CHIP_IS_E3B0(bp)) {
-		/* Class0 defaults */
-		config_val->default_class0.pause_xoff =
-			DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR;
-		config_val->default_class0.pause_xon =
-		    DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR;
-		config_val->default_class0.full_xoff =
-		    DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR;
-		config_val->default_class0.full_xon =
-		    DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR;
-
-		if (params->phy[INT_PHY].flags &
-		    FLAGS_4_PORT_MODE) {
-			config_val->pauseable_th.pause_xoff =
-				PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
-			config_val->pauseable_th.pause_xon =
-				PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE;
-			config_val->pauseable_th.full_xoff =
-				PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE;
-			config_val->pauseable_th.full_xon =
-				PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE;
-			/* Non pause able*/
-			config_val->non_pauseable_th.pause_xoff =
-			PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
-			config_val->non_pauseable_th.pause_xon =
-			PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
-			config_val->non_pauseable_th.full_xoff =
-			PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
-			config_val->non_pauseable_th.full_xon =
-			PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-		} else {
-			config_val->pauseable_th.pause_xoff =
-				PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
-			config_val->pauseable_th.pause_xon =
-				PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE;
-			config_val->pauseable_th.full_xoff =
-				PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE;
-			config_val->pauseable_th.full_xon =
-				PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE;
-			/* Non pause able*/
-			config_val->non_pauseable_th.pause_xoff =
-				PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
-			config_val->non_pauseable_th.pause_xon =
-				PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
-			config_val->non_pauseable_th.full_xoff =
-				PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
-			config_val->non_pauseable_th.full_xon =
-				PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-		}
-	} else
-	    return -EINVAL;
-
-	return 0;
-}
-
-static void bnx2x_pfc_brb_get_e3b0_config_params(
-		struct link_params *params,
-		struct bnx2x_pfc_brb_e3b0_val
-		*e3b0_val,
-		struct bnx2x_nig_brb_pfc_port_params *pfc_params,
-		const u8 pfc_enabled)
-{
-	if (pfc_enabled && pfc_params) {
-		e3b0_val->per_class_guaranty_mode = 1;
-		e3b0_val->lb_guarantied_hyst = 80;
-
-		if (params->phy[INT_PHY].flags &
-		    FLAGS_4_PORT_MODE) {
-			e3b0_val->full_lb_xoff_th =
-				PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR;
-			e3b0_val->full_lb_xon_threshold =
-				PFC_E3B0_4P_BRB_FULL_LB_XON_THR;
-			e3b0_val->lb_guarantied =
-				PFC_E3B0_4P_LB_GUART;
-			e3b0_val->mac_0_class_t_guarantied =
-				PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART;
-			e3b0_val->mac_0_class_t_guarantied_hyst =
-				PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST;
-			e3b0_val->mac_1_class_t_guarantied =
-				PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART;
-			e3b0_val->mac_1_class_t_guarantied_hyst =
-				PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST;
-		} else {
-			e3b0_val->full_lb_xoff_th =
-				PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR;
-			e3b0_val->full_lb_xon_threshold =
-				PFC_E3B0_2P_BRB_FULL_LB_XON_THR;
-			e3b0_val->mac_0_class_t_guarantied_hyst =
-				PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST;
-			e3b0_val->mac_1_class_t_guarantied =
-				PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART;
-			e3b0_val->mac_1_class_t_guarantied_hyst =
-				PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST;
-
-			if (pfc_params->cos0_pauseable !=
-				pfc_params->cos1_pauseable) {
-				/* Nonpauseable= Lossy + pauseable = Lossless*/
-				e3b0_val->lb_guarantied =
-					PFC_E3B0_2P_MIX_PAUSE_LB_GUART;
-				e3b0_val->mac_0_class_t_guarantied =
-			       PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART;
-			} else if (pfc_params->cos0_pauseable) {
-				/* Lossless +Lossless*/
-				e3b0_val->lb_guarantied =
-					PFC_E3B0_2P_PAUSE_LB_GUART;
-				e3b0_val->mac_0_class_t_guarantied =
-				   PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART;
-			} else {
-				/* Lossy +Lossy*/
-				e3b0_val->lb_guarantied =
-					PFC_E3B0_2P_NON_PAUSE_LB_GUART;
-				e3b0_val->mac_0_class_t_guarantied =
-			       PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART;
-			}
-		}
-	} else {
-		e3b0_val->per_class_guaranty_mode = 0;
-		e3b0_val->lb_guarantied_hyst = 0;
-		e3b0_val->full_lb_xoff_th =
-			DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR;
-		e3b0_val->full_lb_xon_threshold =
-			DEFAULT_E3B0_BRB_FULL_LB_XON_THR;
-		e3b0_val->lb_guarantied =
-			DEFAULT_E3B0_LB_GUART;
-		e3b0_val->mac_0_class_t_guarantied =
-			DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART;
-		e3b0_val->mac_0_class_t_guarantied_hyst =
-			DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST;
-		e3b0_val->mac_1_class_t_guarantied =
-			DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART;
-		e3b0_val->mac_1_class_t_guarantied_hyst =
-			DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST;
-	}
-}
-static int bnx2x_update_pfc_brb(struct link_params *params,
-				struct link_vars *vars,
-				struct bnx2x_nig_brb_pfc_port_params
-				*pfc_params)
-{
-	struct bnx2x *bp = params->bp;
-	struct bnx2x_pfc_brb_th_val config_val = { {0} };
-	struct bnx2x_pfc_brb_threshold_val *reg_th_config =
-		&config_val.pauseable_th;
-	struct bnx2x_pfc_brb_e3b0_val e3b0_val = {0};
-	const int set_pfc = params->feature_config_flags &
-		FEATURE_CONFIG_PFC_ENABLED;
-	const u8 pfc_enabled = (set_pfc && pfc_params);
-	int bnx2x_status = 0;
-	u8 port = params->port;
-
-	/* default - pause configuration */
-	reg_th_config = &config_val.pauseable_th;
-	bnx2x_status = bnx2x_pfc_brb_get_config_params(params, &config_val);
-	if (bnx2x_status)
-		return bnx2x_status;
-
-	if (pfc_enabled) {
-		/* First COS */
-		if (pfc_params->cos0_pauseable)
-			reg_th_config = &config_val.pauseable_th;
-		else
-			reg_th_config = &config_val.non_pauseable_th;
-	} else
-		reg_th_config = &config_val.default_class0;
-	/* The number of free blocks below which the pause signal to class 0
-	 * of MAC #n is asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_PAUSE_0_XOFF_THRESHOLD_1 :
-	       BRB1_REG_PAUSE_0_XOFF_THRESHOLD_0 ,
-	       reg_th_config->pause_xoff);
-	/* The number of free blocks above which the pause signal to class 0
-	 * of MAC #n is de-asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_PAUSE_0_XON_THRESHOLD_1 :
-	       BRB1_REG_PAUSE_0_XON_THRESHOLD_0 , reg_th_config->pause_xon);
-	/* The number of free blocks below which the full signal to class 0
-	 * of MAC #n is asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_FULL_0_XOFF_THRESHOLD_1 :
-	       BRB1_REG_FULL_0_XOFF_THRESHOLD_0 , reg_th_config->full_xoff);
-	/* The number of free blocks above which the full signal to class 0
-	 * of MAC #n is de-asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_FULL_0_XON_THRESHOLD_1 :
-	       BRB1_REG_FULL_0_XON_THRESHOLD_0 , reg_th_config->full_xon);
-
-	if (pfc_enabled) {
-		/* Second COS */
-		if (pfc_params->cos1_pauseable)
-			reg_th_config = &config_val.pauseable_th;
-		else
-			reg_th_config = &config_val.non_pauseable_th;
-	} else
-		reg_th_config = &config_val.default_class1;
-	/* The number of free blocks below which the pause signal to
-	 * class 1 of MAC #n is asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 :
-	       BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0,
-	       reg_th_config->pause_xoff);
-
-	/* The number of free blocks above which the pause signal to
-	 * class 1 of MAC #n is de-asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 :
-	       BRB1_REG_PAUSE_1_XON_THRESHOLD_0,
-	       reg_th_config->pause_xon);
-	/* The number of free blocks below which the full signal to
-	 * class 1 of MAC #n is asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 :
-	       BRB1_REG_FULL_1_XOFF_THRESHOLD_0,
-	       reg_th_config->full_xoff);
-	/* The number of free blocks above which the full signal to
-	 * class 1 of MAC #n is de-asserted. n=0,1
-	 */
-	REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 :
-	       BRB1_REG_FULL_1_XON_THRESHOLD_0,
-	       reg_th_config->full_xon);
-
-	if (CHIP_IS_E3B0(bp)) {
-		bnx2x_pfc_brb_get_e3b0_config_params(
-			params,
-			&e3b0_val,
-			pfc_params,
-			pfc_enabled);
-
-		REG_WR(bp, BRB1_REG_PER_CLASS_GUARANTY_MODE,
-			   e3b0_val.per_class_guaranty_mode);
-
-		/* The hysteresis on the guarantied buffer space for the Lb
-		 * port before signaling XON.
-		 */
-		REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST,
-			   e3b0_val.lb_guarantied_hyst);
-
-		/* The number of free blocks below which the full signal to the
-		 * LB port is asserted.
-		 */
-		REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD,
-		       e3b0_val.full_lb_xoff_th);
-		/* The number of free blocks above which the full signal to the
-		 * LB port is de-asserted.
-		 */
-		REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD,
-		       e3b0_val.full_lb_xon_threshold);
-		/* The number of blocks guarantied for the MAC #n port. n=0,1
-		 */
-
-		/* The number of blocks guarantied for the LB port. */
-		REG_WR(bp, BRB1_REG_LB_GUARANTIED,
-		       e3b0_val.lb_guarantied);
-
-		/* The number of blocks guarantied for the MAC #n port. */
-		REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0,
-		       2 * e3b0_val.mac_0_class_t_guarantied);
-		REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1,
-		       2 * e3b0_val.mac_1_class_t_guarantied);
-		/* The number of blocks guarantied for class #t in MAC0. t=0,1
-		 */
-		REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED,
-		       e3b0_val.mac_0_class_t_guarantied);
-		REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED,
-		       e3b0_val.mac_0_class_t_guarantied);
-		/* The hysteresis on the guarantied buffer space for class in
-		 * MAC0.  t=0,1
-		 */
-		REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST,
-		       e3b0_val.mac_0_class_t_guarantied_hyst);
-		REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST,
-		       e3b0_val.mac_0_class_t_guarantied_hyst);
-
-		/* The number of blocks guarantied for class #t in MAC1.t=0,1
-		 */
-		REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED,
-		       e3b0_val.mac_1_class_t_guarantied);
-		REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED,
-		       e3b0_val.mac_1_class_t_guarantied);
-		/* The hysteresis on the guarantied buffer space for class #t
-		 * in MAC1.  t=0,1
-		 */
-		REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST,
-		       e3b0_val.mac_1_class_t_guarantied_hyst);
-		REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST,
-		       e3b0_val.mac_1_class_t_guarantied_hyst);
-	}
-
-	return bnx2x_status;
-}
-
 /******************************************************************************
 * Description:
 *  This function is needed because NIG ARB_CREDIT_WEIGHT_X are
@@ -2529,16 +2087,6 @@ static void bnx2x_update_mng(struct link_params *params, u32 link_status)
 			port_mb[params->port].link_status), link_status);
 }
 
-static void bnx2x_update_mng_eee(struct link_params *params, u32 eee_status)
-{
-	struct bnx2x *bp = params->bp;
-
-	if (bnx2x_eee_has_cap(params))
-		REG_WR(bp, params->shmem2_base +
-		       offsetof(struct shmem2_region,
-				eee_status[params->port]), eee_status);
-}
-
 static void bnx2x_update_pfc_nig(struct link_params *params,
 		struct link_vars *vars,
 		struct bnx2x_nig_brb_pfc_port_params *nig_params)
@@ -2658,11 +2206,6 @@ int bnx2x_update_pfc(struct link_params *params,
 	/* Update NIG params */
 	bnx2x_update_pfc_nig(params, vars, pfc_params);
 
-	/* Update BRB params */
-	bnx2x_status = bnx2x_update_pfc_brb(params, vars, pfc_params);
-	if (bnx2x_status)
-		return bnx2x_status;
-
 	if (!vars->link_up)
 		return bnx2x_status;
 
@@ -2827,16 +2370,18 @@ static int bnx2x_bmac2_enable(struct link_params *params,
 
 static int bnx2x_bmac_enable(struct link_params *params,
 			     struct link_vars *vars,
-			     u8 is_lb)
+			     u8 is_lb, u8 reset_bmac)
 {
 	int rc = 0;
 	u8 port = params->port;
 	struct bnx2x *bp = params->bp;
 	u32 val;
 	/* Reset and unreset the BigMac */
-	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR,
-	       (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port));
-	usleep_range(1000, 2000);
+	if (reset_bmac) {
+		REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR,
+		       (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port));
+		usleep_range(1000, 2000);
+	}
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET,
 	       (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port));
@@ -2868,37 +2413,28 @@ static int bnx2x_bmac_enable(struct link_params *params,
 	return rc;
 }
 
-static void bnx2x_bmac_rx_disable(struct bnx2x *bp, u8 port)
+static void bnx2x_set_bmac_rx(struct bnx2x *bp, u32 chip_id, u8 port, u8 en)
 {
 	u32 bmac_addr = port ? NIG_REG_INGRESS_BMAC1_MEM :
 			NIG_REG_INGRESS_BMAC0_MEM;
 	u32 wb_data[2];
 	u32 nig_bmac_enable = REG_RD(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4);
 
+	if (CHIP_IS_E2(bp))
+		bmac_addr += BIGMAC2_REGISTER_BMAC_CONTROL;
+	else
+		bmac_addr += BIGMAC_REGISTER_BMAC_CONTROL;
 	/* Only if the bmac is out of reset */
 	if (REG_RD(bp, MISC_REG_RESET_REG_2) &
 			(MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port) &&
 	    nig_bmac_enable) {
-
-		if (CHIP_IS_E2(bp)) {
-			/* Clear Rx Enable bit in BMAC_CONTROL register */
-			REG_RD_DMAE(bp, bmac_addr +
-				    BIGMAC2_REGISTER_BMAC_CONTROL,
-				    wb_data, 2);
-			wb_data[0] &= ~BMAC_CONTROL_RX_ENABLE;
-			REG_WR_DMAE(bp, bmac_addr +
-				    BIGMAC2_REGISTER_BMAC_CONTROL,
-				    wb_data, 2);
-		} else {
-			/* Clear Rx Enable bit in BMAC_CONTROL register */
-			REG_RD_DMAE(bp, bmac_addr +
-					BIGMAC_REGISTER_BMAC_CONTROL,
-					wb_data, 2);
+		/* Clear Rx Enable bit in BMAC_CONTROL register */
+		REG_RD_DMAE(bp, bmac_addr, wb_data, 2);
+		if (en)
+			wb_data[0] |= BMAC_CONTROL_RX_ENABLE;
+		else
 			wb_data[0] &= ~BMAC_CONTROL_RX_ENABLE;
-			REG_WR_DMAE(bp, bmac_addr +
-					BIGMAC_REGISTER_BMAC_CONTROL,
-					wb_data, 2);
-		}
+		REG_WR_DMAE(bp, bmac_addr, wb_data, 2);
 		usleep_range(1000, 2000);
 	}
 }
@@ -3233,6 +2769,245 @@ static int bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy,
 			       EMAC_MDIO_STATUS_10MB);
 	return rc;
 }
+
+/******************************************************************/
+/*			EEE section				   */
+/******************************************************************/
+static u8 bnx2x_eee_has_cap(struct link_params *params)
+{
+	struct bnx2x *bp = params->bp;
+
+	if (REG_RD(bp, params->shmem2_base) <=
+		   offsetof(struct shmem2_region, eee_status[params->port]))
+		return 0;
+
+	return 1;
+}
+
+static int bnx2x_eee_nvram_to_time(u32 nvram_mode, u32 *idle_timer)
+{
+	switch (nvram_mode) {
+	case PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED:
+		*idle_timer = EEE_MODE_NVRAM_BALANCED_TIME;
+		break;
+	case PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE:
+		*idle_timer = EEE_MODE_NVRAM_AGGRESSIVE_TIME;
+		break;
+	case PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY:
+		*idle_timer = EEE_MODE_NVRAM_LATENCY_TIME;
+		break;
+	default:
+		*idle_timer = 0;
+		break;
+	}
+
+	return 0;
+}
+
+static int bnx2x_eee_time_to_nvram(u32 idle_timer, u32 *nvram_mode)
+{
+	switch (idle_timer) {
+	case EEE_MODE_NVRAM_BALANCED_TIME:
+		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED;
+		break;
+	case EEE_MODE_NVRAM_AGGRESSIVE_TIME:
+		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE;
+		break;
+	case EEE_MODE_NVRAM_LATENCY_TIME:
+		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY;
+		break;
+	default:
+		*nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_DISABLED;
+		break;
+	}
+
+	return 0;
+}
+
+static u32 bnx2x_eee_calc_timer(struct link_params *params)
+{
+	u32 eee_mode, eee_idle;
+	struct bnx2x *bp = params->bp;
+
+	if (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) {
+		if (params->eee_mode & EEE_MODE_OUTPUT_TIME) {
+			/* time value in eee_mode --> used directly*/
+			eee_idle = params->eee_mode & EEE_MODE_TIMER_MASK;
+		} else {
+			/* hsi value in eee_mode --> time */
+			if (bnx2x_eee_nvram_to_time(params->eee_mode &
+						    EEE_MODE_NVRAM_MASK,
+						    &eee_idle))
+				return 0;
+		}
+	} else {
+		/* hsi values in nvram --> time*/
+		eee_mode = ((REG_RD(bp, params->shmem_base +
+				    offsetof(struct shmem_region, dev_info.
+				    port_feature_config[params->port].
+				    eee_power_mode)) &
+			     PORT_FEAT_CFG_EEE_POWER_MODE_MASK) >>
+			    PORT_FEAT_CFG_EEE_POWER_MODE_SHIFT);
+
+		if (bnx2x_eee_nvram_to_time(eee_mode, &eee_idle))
+			return 0;
+	}
+
+	return eee_idle;
+}
+
+static int bnx2x_eee_set_timers(struct link_params *params,
+				   struct link_vars *vars)
+{
+	u32 eee_idle = 0, eee_mode;
+	struct bnx2x *bp = params->bp;
+
+	eee_idle = bnx2x_eee_calc_timer(params);
+
+	if (eee_idle) {
+		REG_WR(bp, MISC_REG_CPMU_LP_IDLE_THR_P0 + (params->port << 2),
+		       eee_idle);
+	} else if ((params->eee_mode & EEE_MODE_ENABLE_LPI) &&
+		   (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) &&
+		   (params->eee_mode & EEE_MODE_OUTPUT_TIME)) {
+		DP(NETIF_MSG_LINK, "Error: Tx LPI is enabled with timer 0\n");
+		return -EINVAL;
+	}
+
+	vars->eee_status &= ~(SHMEM_EEE_TIMER_MASK | SHMEM_EEE_TIME_OUTPUT_BIT);
+	if (params->eee_mode & EEE_MODE_OUTPUT_TIME) {
+		/* eee_idle in 1u --> eee_status in 16u */
+		eee_idle >>= 4;
+		vars->eee_status |= (eee_idle & SHMEM_EEE_TIMER_MASK) |
+				    SHMEM_EEE_TIME_OUTPUT_BIT;
+	} else {
+		if (bnx2x_eee_time_to_nvram(eee_idle, &eee_mode))
+			return -EINVAL;
+		vars->eee_status |= eee_mode;
+	}
+
+	return 0;
+}
+
+static int bnx2x_eee_initial_config(struct link_params *params,
+				     struct link_vars *vars, u8 mode)
+{
+	vars->eee_status |= ((u32) mode) << SHMEM_EEE_SUPPORTED_SHIFT;
+
+	/* Propogate params' bits --> vars (for migration exposure) */
+	if (params->eee_mode & EEE_MODE_ENABLE_LPI)
+		vars->eee_status |= SHMEM_EEE_LPI_REQUESTED_BIT;
+	else
+		vars->eee_status &= ~SHMEM_EEE_LPI_REQUESTED_BIT;
+
+	if (params->eee_mode & EEE_MODE_ADV_LPI)
+		vars->eee_status |= SHMEM_EEE_REQUESTED_BIT;
+	else
+		vars->eee_status &= ~SHMEM_EEE_REQUESTED_BIT;
+
+	return bnx2x_eee_set_timers(params, vars);
+}
+
+static int bnx2x_eee_disable(struct bnx2x_phy *phy,
+				struct link_params *params,
+				struct link_vars *vars)
+{
+	struct bnx2x *bp = params->bp;
+
+	/* Make Certain LPI is disabled */
+	REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0);
+
+	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0x0);
+
+	vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK;
+
+	return 0;
+}
+
+static int bnx2x_eee_advertise(struct bnx2x_phy *phy,
+				  struct link_params *params,
+				  struct link_vars *vars, u8 modes)
+{
+	struct bnx2x *bp = params->bp;
+	u16 val = 0;
+
+	/* Mask events preventing LPI generation */
+	REG_WR(bp, MISC_REG_CPMU_LP_MASK_EXT_P0 + (params->port << 2), 0xfc20);
+
+	if (modes & SHMEM_EEE_10G_ADV) {
+		DP(NETIF_MSG_LINK, "Advertise 10GBase-T EEE\n");
+		val |= 0x8;
+	}
+	if (modes & SHMEM_EEE_1G_ADV) {
+		DP(NETIF_MSG_LINK, "Advertise 1GBase-T EEE\n");
+		val |= 0x4;
+	}
+
+	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, val);
+
+	vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK;
+	vars->eee_status |= (modes << SHMEM_EEE_ADV_STATUS_SHIFT);
+
+	return 0;
+}
+
+static void bnx2x_update_mng_eee(struct link_params *params, u32 eee_status)
+{
+	struct bnx2x *bp = params->bp;
+
+	if (bnx2x_eee_has_cap(params))
+		REG_WR(bp, params->shmem2_base +
+		       offsetof(struct shmem2_region,
+				eee_status[params->port]), eee_status);
+}
+
+static void bnx2x_eee_an_resolve(struct bnx2x_phy *phy,
+				  struct link_params *params,
+				  struct link_vars *vars)
+{
+	struct bnx2x *bp = params->bp;
+	u16 adv = 0, lp = 0;
+	u32 lp_adv = 0;
+	u8 neg = 0;
+
+	bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, &adv);
+	bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_LP_EEE_ADV, &lp);
+
+	if (lp & 0x2) {
+		lp_adv |= SHMEM_EEE_100M_ADV;
+		if (adv & 0x2) {
+			if (vars->line_speed == SPEED_100)
+				neg = 1;
+			DP(NETIF_MSG_LINK, "EEE negotiated - 100M\n");
+		}
+	}
+	if (lp & 0x14) {
+		lp_adv |= SHMEM_EEE_1G_ADV;
+		if (adv & 0x14) {
+			if (vars->line_speed == SPEED_1000)
+				neg = 1;
+			DP(NETIF_MSG_LINK, "EEE negotiated - 1G\n");
+		}
+	}
+	if (lp & 0x68) {
+		lp_adv |= SHMEM_EEE_10G_ADV;
+		if (adv & 0x68) {
+			if (vars->line_speed == SPEED_10000)
+				neg = 1;
+			DP(NETIF_MSG_LINK, "EEE negotiated - 10G\n");
+		}
+	}
+
+	vars->eee_status &= ~SHMEM_EEE_LP_ADV_STATUS_MASK;
+	vars->eee_status |= (lp_adv << SHMEM_EEE_LP_ADV_STATUS_SHIFT);
+
+	if (neg) {
+		DP(NETIF_MSG_LINK, "EEE is active\n");
+		vars->eee_status |= SHMEM_EEE_ACTIVE_BIT;
+	}
+
+}
+
 /******************************************************************/
 /*			BSC access functions from E3	          */
 /******************************************************************/
@@ -3754,6 +3529,19 @@ static u8 bnx2x_ext_phy_resolve_fc(struct bnx2x_phy *phy,
  * init configuration, and set/clear SGMII flag. Internal
  * phy init is done purely in phy_init stage.
  */
+
+static void bnx2x_warpcore_set_lpi_passthrough(struct bnx2x_phy *phy,
+					       struct link_params *params)
+{
+	struct bnx2x *bp = params->bp;
+
+	DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n");
+	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+			 MDIO_WC_REG_EEE_COMBO_CONTROL0, 0x7c);
+	bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
+				 MDIO_WC_REG_DIGITAL4_MISC5, 0xc000);
+}
+
 static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
 					struct link_params *params,
 					struct link_vars *vars) {
@@ -4013,13 +3801,7 @@ static void bnx2x_warpcore_set_10G_XFI(struct bnx2x_phy *phy,
 	bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
 				 MDIO_WC_REG_DIGITAL4_MISC3, 0x8080);
 
-	/* Enable LPI pass through */
-	DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n");
-	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
-			 MDIO_WC_REG_EEE_COMBO_CONTROL0,
-			 0x7c);
-	bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
-				 MDIO_WC_REG_DIGITAL4_MISC5, 0xc000);
+	bnx2x_warpcore_set_lpi_passthrough(phy, params);
 
 	/* 10G XFI Full Duplex */
 	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
@@ -4116,6 +3898,8 @@ static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy,
 	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
 			 MDIO_WC_REG_RX66_CONTROL, val16 & ~(3<<13));
 
+	bnx2x_warpcore_set_lpi_passthrough(phy, params);
+
 	if (always_autoneg || phy->req_line_speed == SPEED_AUTO_NEG) {
 		/* SGMII Autoneg */
 		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
@@ -4409,7 +4193,7 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy,
 			   "serdes_net_if = 0x%x\n",
 		       vars->line_speed, serdes_net_if);
 	bnx2x_set_aer_mmd(params, phy);
-
+	bnx2x_warpcore_reset_lane(bp, phy, 1);
 	vars->phy_flags |= PHY_XGXS_FLAG;
 	if ((serdes_net_if == PORT_HW_CFG_NET_SERDES_IF_SGMII) ||
 	    (phy->req_line_speed &&
@@ -4718,6 +4502,10 @@ void bnx2x_link_status_update(struct link_params *params,
 	vars->link_status = REG_RD(bp, params->shmem_base +
 				   offsetof(struct shmem_region,
 					    port_mb[port].link_status));
+	if (bnx2x_eee_has_cap(params))
+		vars->eee_status = REG_RD(bp, params->shmem2_base +
+					  offsetof(struct shmem2_region,
+						   eee_status[params->port]));
 
 	vars->phy_flags = PHY_XGXS_FLAG;
 	bnx2x_sync_link(params, vars);
@@ -6530,25 +6318,21 @@ static int bnx2x_update_link_down(struct link_params *params,
 	usleep_range(10000, 20000);
 	/* Reset BigMac/Xmac */
 	if (CHIP_IS_E1x(bp) ||
-	    CHIP_IS_E2(bp)) {
-		bnx2x_bmac_rx_disable(bp, params->port);
-		REG_WR(bp, GRCBASE_MISC +
-		       MISC_REGISTERS_RESET_REG_2_CLEAR,
-	       (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port));
-	}
+	    CHIP_IS_E2(bp))
+		bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 0);
+
 	if (CHIP_IS_E3(bp)) {
 		/* Prevent LPI Generation by chip */
 		REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2),
 		       0);
-		REG_WR(bp, MISC_REG_CPMU_LP_DR_ENABLE, 0);
 		REG_WR(bp, MISC_REG_CPMU_LP_MASK_ENT_P0 + (params->port << 2),
 		       0);
 		vars->eee_status &= ~(SHMEM_EEE_LP_ADV_STATUS_MASK |
 				      SHMEM_EEE_ACTIVE_BIT);
 
 		bnx2x_update_mng_eee(params, vars->eee_status);
-		bnx2x_xmac_disable(params);
-		bnx2x_umac_disable(params);
+		bnx2x_set_xmac_rxtx(params, 0);
+		bnx2x_set_umac_rxtx(params, 0);
 	}
 
 	return 0;
@@ -6600,7 +6384,7 @@ static int bnx2x_update_link_up(struct link_params *params,
 	if ((CHIP_IS_E1x(bp) ||
 	     CHIP_IS_E2(bp))) {
 		if (link_10g) {
-			if (bnx2x_bmac_enable(params, vars, 0) ==
+			if (bnx2x_bmac_enable(params, vars, 0, 1) ==
 			    -ESRCH) {
 				DP(NETIF_MSG_LINK, "Found errors on BMAC\n");
 				vars->link_up = 0;
@@ -7207,6 +6991,22 @@ static void bnx2x_8073_set_pause_cl37(struct link_params *params,
 	msleep(500);
 }
 
+static void bnx2x_8073_specific_func(struct bnx2x_phy *phy,
+				     struct link_params *params,
+				     u32 action)
+{
+	struct bnx2x *bp = params->bp;
+	switch (action) {
+	case PHY_INIT:
+		/* Enable LASI */
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, (1<<2));
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL,  0x0004);
+		break;
+	}
+}
+
 static int bnx2x_8073_config_init(struct bnx2x_phy *phy,
 				  struct link_params *params,
 				  struct link_vars *vars)
@@ -7227,12 +7027,7 @@ static int bnx2x_8073_config_init(struct bnx2x_phy *phy,
 	bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1,
 		       MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port);
 
-	/* Enable LASI */
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, (1<<2));
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL,  0x0004);
-
+	bnx2x_8073_specific_func(phy, params, PHY_INIT);
 	bnx2x_8073_set_pause_cl37(params, phy, vars);
 
 	bnx2x_cl45_read(bp, phy,
@@ -8267,7 +8062,7 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy,
 				     u32 action)
 {
 	struct bnx2x *bp = params->bp;
-
+	u16 val;
 	switch (action) {
 	case DISABLE_TX:
 		bnx2x_sfp_set_transmitter(params, phy, 0);
@@ -8276,6 +8071,40 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy,
 		if (!(phy->flags & FLAGS_SFP_NOT_APPROVED))
 			bnx2x_sfp_set_transmitter(params, phy, 1);
 		break;
+	case PHY_INIT:
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL,
+				 (1<<2) | (1<<5));
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_TXCTRL,
+				 0);
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, 0x0006);
+		/* Make MOD_ABS give interrupt on change */
+		bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD,
+				MDIO_PMA_REG_8727_PCS_OPT_CTRL,
+				&val);
+		val |= (1<<12);
+		if (phy->flags & FLAGS_NOC)
+			val |= (3<<5);
+		/* Set 8727 GPIOs to input to allow reading from the 8727 GPIO0
+		 * status which reflect SFP+ module over-current
+		 */
+		if (!(phy->flags & FLAGS_NOC))
+			val &= 0xff8f; /* Reset bits 4-6 */
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL,
+				 val);
+
+		/* Set 2-wire transfer rate of SFP+ module EEPROM
+		 * to 100Khz since some DACs(direct attached cables) do
+		 * not work at 400Khz.
+		 */
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD,
+				 MDIO_PMA_REG_8727_TWO_WIRE_SLAVE_ADDR,
+				 0xa001);
+		break;
 	default:
 		DP(NETIF_MSG_LINK, "Function 0x%x not supported by 8727\n",
 		   action);
@@ -9058,28 +8887,15 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy,
 				  struct link_vars *vars)
 {
 	u32 tx_en_mode;
-	u16 tmp1, val, mod_abs, tmp2;
-	u16 rx_alarm_ctrl_val;
-	u16 lasi_ctrl_val;
+	u16 tmp1, mod_abs, tmp2;
 	struct bnx2x *bp = params->bp;
 	/* Enable PMD link, MOD_ABS_FLT, and 1G link alarm */
 
 	bnx2x_wait_reset_complete(bp, phy, params);
-	rx_alarm_ctrl_val = (1<<2) | (1<<5) ;
-	/* Should be 0x6 to enable XS on Tx side. */
-	lasi_ctrl_val = 0x0006;
 
 	DP(NETIF_MSG_LINK, "Initializing BCM8727\n");
-	/* Enable LASI */
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL,
-			 rx_alarm_ctrl_val);
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_LASI_TXCTRL,
-			 0);
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, lasi_ctrl_val);
 
+	bnx2x_8727_specific_func(phy, params, PHY_INIT);
 	/* Initially configure MOD_ABS to interrupt when module is
 	 * presence( bit 8)
 	 */
@@ -9095,25 +8911,9 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy,
 	bnx2x_cl45_write(bp, phy,
 			 MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER, mod_abs);
 
-
 	/* Enable/Disable PHY transmitter output */
 	bnx2x_set_disable_pmd_transmit(params, phy, 0);
 
-	/* Make MOD_ABS give interrupt on change */
-	bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL,
-			&val);
-	val |= (1<<12);
-	if (phy->flags & FLAGS_NOC)
-		val |= (3<<5);
-
-	/* Set 8727 GPIOs to input to allow reading from the 8727 GPIO0
-	 * status which reflect SFP+ module over-current
-	 */
-	if (!(phy->flags & FLAGS_NOC))
-		val &= 0xff8f; /* Reset bits 4-6 */
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL, val);
-
 	bnx2x_8727_power_module(bp, phy, 1);
 
 	bnx2x_cl45_read(bp, phy,
@@ -9123,13 +8923,7 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy,
 			MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXSTAT, &tmp1);
 
 	bnx2x_8727_config_speed(phy, params);
-	/* Set 2-wire transfer rate of SFP+ module EEPROM
-	 * to 100Khz since some DACs(direct attached cables) do
-	 * not work at 400Khz.
-	 */
-	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_TWO_WIRE_SLAVE_ADDR,
-			 0xa001);
+
 
 	/* Set TX PreEmphasis if needed */
 	if ((params->feature_config_flags &
@@ -9558,6 +9352,29 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 			 0xFFFB, 0xFFFD);
 }
 
+static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy,
+				      struct link_params *params,
+				      u32 action)
+{
+	struct bnx2x *bp = params->bp;
+	switch (action) {
+	case PHY_INIT:
+		if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
+			/* Save spirom version */
+			bnx2x_save_848xx_spirom_version(phy, bp, params->port);
+		}
+		/* This phy uses the NIG latch mechanism since link indication
+		 * arrives through its LED4 and not via its LASI signal, so we
+		 * get steady signal instead of clear on read
+		 */
+		bnx2x_bits_en(bp, NIG_REG_LATCH_BC_0 + params->port*4,
+			      1 << NIG_LATCH_BC_ENABLE_MI_INT);
+
+		bnx2x_848xx_set_led(bp, phy);
+		break;
+	}
+}
+
 static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy,
 				       struct link_params *params,
 				       struct link_vars *vars)
@@ -9565,22 +9382,10 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	u16 autoneg_val, an_1000_val, an_10_100_val, an_10g_val;
 
-	if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
-		/* Save spirom version */
-		bnx2x_save_848xx_spirom_version(phy, bp, params->port);
-	}
-	/* This phy uses the NIG latch mechanism since link indication
-	 * arrives through its LED4 and not via its LASI signal, so we
-	 * get steady signal instead of clear on read
-	 */
-	bnx2x_bits_en(bp, NIG_REG_LATCH_BC_0 + params->port*4,
-		      1 << NIG_LATCH_BC_ENABLE_MI_INT);
-
+	bnx2x_848xx_specific_func(phy, params, PHY_INIT);
 	bnx2x_cl45_write(bp, phy,
 			 MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 0x0000);
 
-	bnx2x_848xx_set_led(bp, phy);
-
 	/* set 1000 speed advertisement */
 	bnx2x_cl45_read(bp, phy,
 			MDIO_AN_DEVAD, MDIO_AN_REG_8481_1000T_CTRL,
@@ -9887,39 +9692,6 @@ static int bnx2x_84833_hw_reset_phy(struct bnx2x_phy *phy,
 	return 0;
 }
 
-static int bnx2x_8483x_eee_timers(struct link_params *params,
-				   struct link_vars *vars)
-{
-	u32 eee_idle = 0, eee_mode;
-	struct bnx2x *bp = params->bp;
-
-	eee_idle = bnx2x_eee_calc_timer(params);
-
-	if (eee_idle) {
-		REG_WR(bp, MISC_REG_CPMU_LP_IDLE_THR_P0 + (params->port << 2),
-		       eee_idle);
-	} else if ((params->eee_mode & EEE_MODE_ENABLE_LPI) &&
-		   (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) &&
-		   (params->eee_mode & EEE_MODE_OUTPUT_TIME)) {
-		DP(NETIF_MSG_LINK, "Error: Tx LPI is enabled with timer 0\n");
-		return -EINVAL;
-	}
-
-	vars->eee_status &= ~(SHMEM_EEE_TIMER_MASK | SHMEM_EEE_TIME_OUTPUT_BIT);
-	if (params->eee_mode & EEE_MODE_OUTPUT_TIME) {
-		/* eee_idle in 1u --> eee_status in 16u */
-		eee_idle >>= 4;
-		vars->eee_status |= (eee_idle & SHMEM_EEE_TIMER_MASK) |
-				    SHMEM_EEE_TIME_OUTPUT_BIT;
-	} else {
-		if (bnx2x_eee_time_to_nvram(eee_idle, &eee_mode))
-			return -EINVAL;
-		vars->eee_status |= eee_mode;
-	}
-
-	return 0;
-}
-
 static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy,
 				   struct link_params *params,
 				   struct link_vars *vars)
@@ -9930,10 +9702,6 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy,
 
 	DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n");
 
-	/* Make Certain LPI is disabled */
-	REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0);
-	REG_WR(bp, MISC_REG_CPMU_LP_DR_ENABLE, 0);
-
 	/* Prevent Phy from working in EEE and advertising it */
 	rc = bnx2x_84833_cmd_hdlr(phy, params,
 		PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1);
@@ -9942,10 +9710,7 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy,
 		return rc;
 	}
 
-	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0);
-	vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK;
-
-	return 0;
+	return bnx2x_eee_disable(phy, params, vars);
 }
 
 static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy,
@@ -9956,8 +9721,6 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	u16 cmd_args = 1;
 
-	DP(NETIF_MSG_LINK, "Advertise 10GBase-T EEE\n");
-
 	rc = bnx2x_84833_cmd_hdlr(phy, params,
 		PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1);
 	if (rc) {
@@ -9965,15 +9728,7 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy,
 		return rc;
 	}
 
-	bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0x8);
-
-	/* Mask events preventing LPI generation */
-	REG_WR(bp, MISC_REG_CPMU_LP_MASK_EXT_P0 + (params->port << 2), 0xfc20);
-
-	vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK;
-	vars->eee_status |= (SHMEM_EEE_10G_ADV << SHMEM_EEE_ADV_STATUS_SHIFT);
-
-	return 0;
+	return bnx2x_eee_advertise(phy, params, vars, SHMEM_EEE_10G_ADV);
 }
 
 #define PHY84833_CONSTANT_LATENCY 1193
@@ -10105,22 +9860,10 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 			MDIO_84833_TOP_CFG_FW_REV, &val);
 
 	/* Configure EEE support */
-	if ((val >= MDIO_84833_TOP_CFG_FW_EEE) && bnx2x_eee_has_cap(params)) {
-		phy->flags |= FLAGS_EEE_10GBT;
-		vars->eee_status |= SHMEM_EEE_10G_ADV <<
-				    SHMEM_EEE_SUPPORTED_SHIFT;
-		/* Propogate params' bits --> vars (for migration exposure) */
-		if (params->eee_mode & EEE_MODE_ENABLE_LPI)
-			vars->eee_status |= SHMEM_EEE_LPI_REQUESTED_BIT;
-		else
-			vars->eee_status &= ~SHMEM_EEE_LPI_REQUESTED_BIT;
-
-		if (params->eee_mode & EEE_MODE_ADV_LPI)
-			vars->eee_status |= SHMEM_EEE_REQUESTED_BIT;
-		else
-			vars->eee_status &= ~SHMEM_EEE_REQUESTED_BIT;
-
-		rc = bnx2x_8483x_eee_timers(params, vars);
+	if ((val >= MDIO_84833_TOP_CFG_FW_EEE) &&
+	    (val != MDIO_84833_TOP_CFG_FW_NO_EEE) &&
+	    bnx2x_eee_has_cap(params)) {
+		rc = bnx2x_eee_initial_config(params, vars, SHMEM_EEE_10G_ADV);
 		if (rc) {
 			DP(NETIF_MSG_LINK, "Failed to configure EEE timers\n");
 			bnx2x_8483x_disable_eee(phy, params, vars);
@@ -10139,7 +9882,6 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 			return rc;
 		}
 	} else {
-		phy->flags &= ~FLAGS_EEE_10GBT;
 		vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK;
 	}
 
@@ -10278,29 +10020,8 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy,
 				LINK_STATUS_LINK_PARTNER_10GXFD_CAPABLE;
 
 		/* Determine if EEE was negotiated */
-		if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
-			u32 eee_shmem = 0;
-
-			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
-					MDIO_AN_REG_EEE_ADV, &val1);
-			bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
-					MDIO_AN_REG_LP_EEE_ADV, &val2);
-			if ((val1 & val2) & 0x8) {
-				DP(NETIF_MSG_LINK, "EEE negotiated\n");
-				vars->eee_status |= SHMEM_EEE_ACTIVE_BIT;
-			}
-
-			if (val2 & 0x12)
-				eee_shmem |= SHMEM_EEE_100M_ADV;
-			if (val2 & 0x4)
-				eee_shmem |= SHMEM_EEE_1G_ADV;
-			if (val2 & 0x68)
-				eee_shmem |= SHMEM_EEE_10G_ADV;
-
-			vars->eee_status &= ~SHMEM_EEE_LP_ADV_STATUS_MASK;
-			vars->eee_status |= (eee_shmem <<
-					     SHMEM_EEE_LP_ADV_STATUS_SHIFT);
-		}
+		if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833)
+			bnx2x_eee_an_resolve(phy, params, vars);
 	}
 
 	return link_up;
@@ -10569,6 +10290,35 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 /******************************************************************/
 /*			54618SE PHY SECTION			  */
 /******************************************************************/
+static void bnx2x_54618se_specific_func(struct bnx2x_phy *phy,
+					struct link_params *params,
+					u32 action)
+{
+	struct bnx2x *bp = params->bp;
+	u16 temp;
+	switch (action) {
+	case PHY_INIT:
+		/* Configure LED4: set to INTR (0x6). */
+		/* Accessing shadow register 0xe. */
+		bnx2x_cl22_write(bp, phy,
+				 MDIO_REG_GPHY_SHADOW,
+				 MDIO_REG_GPHY_SHADOW_LED_SEL2);
+		bnx2x_cl22_read(bp, phy,
+				MDIO_REG_GPHY_SHADOW,
+				&temp);
+		temp &= ~(0xf << 4);
+		temp |= (0x6 << 4);
+		bnx2x_cl22_write(bp, phy,
+				 MDIO_REG_GPHY_SHADOW,
+				 MDIO_REG_GPHY_SHADOW_WR_ENA | temp);
+		/* Configure INTR based on link status change. */
+		bnx2x_cl22_write(bp, phy,
+				 MDIO_REG_INTR_MASK,
+				 ~MDIO_REG_INTR_MASK_LINK_STATUS);
+		break;
+	}
+}
+
 static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 					       struct link_params *params,
 					       struct link_vars *vars)
@@ -10606,24 +10356,8 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 	/* Wait for GPHY to reset */
 	msleep(50);
 
-	/* Configure LED4: set to INTR (0x6). */
-	/* Accessing shadow register 0xe. */
-	bnx2x_cl22_write(bp, phy,
-			MDIO_REG_GPHY_SHADOW,
-			MDIO_REG_GPHY_SHADOW_LED_SEL2);
-	bnx2x_cl22_read(bp, phy,
-			MDIO_REG_GPHY_SHADOW,
-			&temp);
-	temp &= ~(0xf << 4);
-	temp |= (0x6 << 4);
-	bnx2x_cl22_write(bp, phy,
-			MDIO_REG_GPHY_SHADOW,
-			MDIO_REG_GPHY_SHADOW_WR_ENA | temp);
-	/* Configure INTR based on link status change. */
-	bnx2x_cl22_write(bp, phy,
-			MDIO_REG_INTR_MASK,
-			~MDIO_REG_INTR_MASK_LINK_STATUS);
 
+	bnx2x_54618se_specific_func(phy, params, PHY_INIT);
 	/* Flip the signal detect polarity (set 0x1c.0x1e[8]). */
 	bnx2x_cl22_write(bp, phy,
 			MDIO_REG_GPHY_SHADOW,
@@ -10728,28 +10462,52 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 		DP(NETIF_MSG_LINK, "Setting 10M force\n");
 	}
 
-	/* Check if we should turn on Auto-GrEEEn */
-	bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_PHYID_LSB, &temp);
-	if (temp == MDIO_REG_GPHY_ID_54618SE) {
-		if (params->feature_config_flags &
-		    FEATURE_CONFIG_AUTOGREEEN_ENABLED) {
-			temp = 6;
-			DP(NETIF_MSG_LINK, "Enabling Auto-GrEEEn\n");
+	if ((phy->flags & FLAGS_EEE) && bnx2x_eee_has_cap(params)) {
+		int rc;
+
+		bnx2x_cl22_write(bp, phy, MDIO_REG_GPHY_EXP_ACCESS,
+				 MDIO_REG_GPHY_EXP_ACCESS_TOP |
+				 MDIO_REG_GPHY_EXP_TOP_2K_BUF);
+		bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_EXP_ACCESS_GATE, &temp);
+		temp &= 0xfffe;
+		bnx2x_cl22_write(bp, phy, MDIO_REG_GPHY_EXP_ACCESS_GATE, temp);
+
+		rc = bnx2x_eee_initial_config(params, vars, SHMEM_EEE_1G_ADV);
+		if (rc) {
+			DP(NETIF_MSG_LINK, "Failed to configure EEE timers\n");
+			bnx2x_eee_disable(phy, params, vars);
+		} else if ((params->eee_mode & EEE_MODE_ADV_LPI) &&
+			   (phy->req_duplex == DUPLEX_FULL) &&
+			   (bnx2x_eee_calc_timer(params) ||
+			    !(params->eee_mode & EEE_MODE_ENABLE_LPI))) {
+			/* Need to advertise EEE only when requested,
+			 * and either no LPI assertion was requested,
+			 * or it was requested and a valid timer was set.
+			 * Also notice full duplex is required for EEE.
+			 */
+			bnx2x_eee_advertise(phy, params, vars,
+					    SHMEM_EEE_1G_ADV);
 		} else {
-			temp = 0;
-			DP(NETIF_MSG_LINK, "Disabling Auto-GrEEEn\n");
+			DP(NETIF_MSG_LINK, "Don't Advertise 1GBase-T EEE\n");
+			bnx2x_eee_disable(phy, params, vars);
+		}
+	} else {
+		vars->eee_status &= ~SHMEM_EEE_1G_ADV <<
+				    SHMEM_EEE_SUPPORTED_SHIFT;
+
+		if (phy->flags & FLAGS_EEE) {
+			/* Handle legacy auto-grEEEn */
+			if (params->feature_config_flags &
+			    FEATURE_CONFIG_AUTOGREEEN_ENABLED) {
+				temp = 6;
+				DP(NETIF_MSG_LINK, "Enabling Auto-GrEEEn\n");
+			} else {
+				temp = 0;
+				DP(NETIF_MSG_LINK, "Don't Adv. EEE\n");
+			}
+			bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+					 MDIO_AN_REG_EEE_ADV, temp);
 		}
-		bnx2x_cl22_write(bp, phy,
-				 MDIO_REG_GPHY_CL45_ADDR_REG, MDIO_AN_DEVAD);
-		bnx2x_cl22_write(bp, phy,
-				 MDIO_REG_GPHY_CL45_DATA_REG,
-				 MDIO_REG_GPHY_EEE_ADV);
-		bnx2x_cl22_write(bp, phy,
-				 MDIO_REG_GPHY_CL45_ADDR_REG,
-				 (0x1 << 14) | MDIO_AN_DEVAD);
-		bnx2x_cl22_write(bp, phy,
-				 MDIO_REG_GPHY_CL45_DATA_REG,
-				 temp);
 	}
 
 	bnx2x_cl22_write(bp, phy,
@@ -10896,29 +10654,6 @@ static u8 bnx2x_54618se_read_status(struct bnx2x_phy *phy,
 		DP(NETIF_MSG_LINK, "BCM54618SE: link speed is %d\n",
 			   vars->line_speed);
 
-		/* Report whether EEE is resolved. */
-		bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_PHYID_LSB, &val);
-		if (val == MDIO_REG_GPHY_ID_54618SE) {
-			if (vars->link_status &
-			    LINK_STATUS_AUTO_NEGOTIATE_COMPLETE)
-				val = 0;
-			else {
-				bnx2x_cl22_write(bp, phy,
-					MDIO_REG_GPHY_CL45_ADDR_REG,
-					MDIO_AN_DEVAD);
-				bnx2x_cl22_write(bp, phy,
-					MDIO_REG_GPHY_CL45_DATA_REG,
-					MDIO_REG_GPHY_EEE_RESOLVED);
-				bnx2x_cl22_write(bp, phy,
-					MDIO_REG_GPHY_CL45_ADDR_REG,
-					(0x1 << 14) | MDIO_AN_DEVAD);
-				bnx2x_cl22_read(bp, phy,
-					MDIO_REG_GPHY_CL45_DATA_REG,
-					&val);
-			}
-			DP(NETIF_MSG_LINK, "EEE resolution: 0x%x\n", val);
-		}
-
 		bnx2x_ext_phy_resolve_fc(phy, params, vars);
 
 		if (vars->link_status & LINK_STATUS_AUTO_NEGOTIATE_COMPLETE) {
@@ -10948,6 +10683,10 @@ static u8 bnx2x_54618se_read_status(struct bnx2x_phy *phy,
 			if (val & (1<<11))
 				vars->link_status |=
 				  LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE;
+
+			if ((phy->flags & FLAGS_EEE) &&
+			    bnx2x_eee_has_cap(params))
+				bnx2x_eee_an_resolve(phy, params, vars);
 		}
 	}
 	return link_up;
@@ -11353,7 +11092,7 @@ static struct bnx2x_phy phy_8073 = {
 	.format_fw_ver	= (format_fw_ver_t)bnx2x_format_ver,
 	.hw_reset	= (hw_reset_t)NULL,
 	.set_link_led	= (set_link_led_t)NULL,
-	.phy_specific_func = (phy_specific_func_t)NULL
+	.phy_specific_func = (phy_specific_func_t)bnx2x_8073_specific_func
 };
 static struct bnx2x_phy phy_8705 = {
 	.type		= PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8705,
@@ -11546,7 +11285,7 @@ static struct bnx2x_phy phy_84823 = {
 	.format_fw_ver	= (format_fw_ver_t)bnx2x_848xx_format_ver,
 	.hw_reset	= (hw_reset_t)NULL,
 	.set_link_led	= (set_link_led_t)bnx2x_848xx_set_link_led,
-	.phy_specific_func = (phy_specific_func_t)NULL
+	.phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func
 };
 
 static struct bnx2x_phy phy_84833 = {
@@ -11555,8 +11294,7 @@ static struct bnx2x_phy phy_84833 = {
 	.def_md_devad	= 0,
 	.flags		= (FLAGS_FAN_FAILURE_DET_REQ |
 			   FLAGS_REARM_LATCH_SIGNAL |
-			   FLAGS_TX_ERROR_CHECK |
-			   FLAGS_EEE_10GBT),
+			   FLAGS_TX_ERROR_CHECK),
 	.rx_preemphasis	= {0xffff, 0xffff, 0xffff, 0xffff},
 	.tx_preemphasis	= {0xffff, 0xffff, 0xffff, 0xffff},
 	.mdio_ctrl	= 0,
@@ -11582,7 +11320,7 @@ static struct bnx2x_phy phy_84833 = {
 	.format_fw_ver	= (format_fw_ver_t)bnx2x_848xx_format_ver,
 	.hw_reset	= (hw_reset_t)bnx2x_84833_hw_reset_phy,
 	.set_link_led	= (set_link_led_t)bnx2x_848xx_set_link_led,
-	.phy_specific_func = (phy_specific_func_t)NULL
+	.phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func
 };
 
 static struct bnx2x_phy phy_54618se = {
@@ -11616,7 +11354,7 @@ static struct bnx2x_phy phy_54618se = {
 	.format_fw_ver	= (format_fw_ver_t)NULL,
 	.hw_reset	= (hw_reset_t)NULL,
 	.set_link_led	= (set_link_led_t)bnx2x_5461x_set_link_led,
-	.phy_specific_func = (phy_specific_func_t)NULL
+	.phy_specific_func = (phy_specific_func_t)bnx2x_54618se_specific_func
 };
 /*****************************************************************/
 /*                                                               */
@@ -11862,6 +11600,8 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp,
 	case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54616:
 	case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE:
 		*phy = phy_54618se;
+		if (phy_type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE)
+			phy->flags |= FLAGS_EEE;
 		break;
 	case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_SFX7101:
 		*phy = phy_7101;
@@ -12141,7 +11881,7 @@ void bnx2x_init_bmac_loopback(struct link_params *params,
 		bnx2x_xgxs_deassert(params);
 
 		/* set bmac loopback */
-		bnx2x_bmac_enable(params, vars, 1);
+		bnx2x_bmac_enable(params, vars, 1, 1);
 
 		REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
 }
@@ -12233,7 +11973,7 @@ void bnx2x_init_xgxs_loopback(struct link_params *params,
 		if (USES_WARPCORE(bp))
 			bnx2x_xmac_enable(params, vars, 0);
 		else
-			bnx2x_bmac_enable(params, vars, 0);
+			bnx2x_bmac_enable(params, vars, 0, 1);
 	}
 
 		if (params->loopback_mode == LOOPBACK_XGXS) {
@@ -12258,8 +11998,161 @@ void bnx2x_init_xgxs_loopback(struct link_params *params,
 	bnx2x_set_led(params, vars, LED_MODE_OPER, vars->line_speed);
 }
 
+static void bnx2x_set_rx_filter(struct link_params *params, u8 en)
+{
+	struct bnx2x *bp = params->bp;
+	u8 val = en * 0x1F;
+
+	/* Open the gate between the NIG to the BRB */
+	if (!CHIP_IS_E1x(bp))
+		val |= en * 0x20;
+	REG_WR(bp, NIG_REG_LLH0_BRB1_DRV_MASK + params->port*4, val);
+
+	if (!CHIP_IS_E1(bp)) {
+		REG_WR(bp, NIG_REG_LLH0_BRB1_DRV_MASK_MF + params->port*4,
+		       en*0x3);
+	}
+
+	REG_WR(bp, (params->port ? NIG_REG_LLH1_BRB1_NOT_MCP :
+		    NIG_REG_LLH0_BRB1_NOT_MCP), en);
+}
+static int bnx2x_avoid_link_flap(struct link_params *params,
+					    struct link_vars *vars)
+{
+	u32 phy_idx;
+	u32 dont_clear_stat, lfa_sts;
+	struct bnx2x *bp = params->bp;
+
+	/* Sync the link parameters */
+	bnx2x_link_status_update(params, vars);
+
+	/*
+	 * The module verification was already done by previous link owner,
+	 * so this call is meant only to get warning message
+	 */
+
+	for (phy_idx = INT_PHY; phy_idx < params->num_phys; phy_idx++) {
+		struct bnx2x_phy *phy = &params->phy[phy_idx];
+		if (phy->phy_specific_func) {
+			DP(NETIF_MSG_LINK, "Calling PHY specific func\n");
+			phy->phy_specific_func(phy, params, PHY_INIT);
+		}
+		if ((phy->media_type == ETH_PHY_SFPP_10G_FIBER) ||
+		    (phy->media_type == ETH_PHY_SFP_1G_FIBER) ||
+		    (phy->media_type == ETH_PHY_DA_TWINAX))
+			bnx2x_verify_sfp_module(phy, params);
+	}
+	lfa_sts = REG_RD(bp, params->lfa_base +
+			 offsetof(struct shmem_lfa,
+				  lfa_sts));
+
+	dont_clear_stat = lfa_sts & SHMEM_LFA_DONT_CLEAR_STAT;
+
+	/* Re-enable the NIG/MAC */
+	if (CHIP_IS_E3(bp)) {
+		if (!dont_clear_stat) {
+			REG_WR(bp, GRCBASE_MISC +
+			       MISC_REGISTERS_RESET_REG_2_CLEAR,
+			       (MISC_REGISTERS_RESET_REG_2_MSTAT0 <<
+				params->port));
+			REG_WR(bp, GRCBASE_MISC +
+			       MISC_REGISTERS_RESET_REG_2_SET,
+			       (MISC_REGISTERS_RESET_REG_2_MSTAT0 <<
+				params->port));
+		}
+		if (vars->line_speed < SPEED_10000)
+			bnx2x_umac_enable(params, vars, 0);
+		else
+			bnx2x_xmac_enable(params, vars, 0);
+	} else {
+		if (vars->line_speed < SPEED_10000)
+			bnx2x_emac_enable(params, vars, 0);
+		else
+			bnx2x_bmac_enable(params, vars, 0, !dont_clear_stat);
+	}
+
+	/* Increment LFA count */
+	lfa_sts = ((lfa_sts & ~LINK_FLAP_AVOIDANCE_COUNT_MASK) |
+		   (((((lfa_sts & LINK_FLAP_AVOIDANCE_COUNT_MASK) >>
+		       LINK_FLAP_AVOIDANCE_COUNT_OFFSET) + 1) & 0xff)
+		    << LINK_FLAP_AVOIDANCE_COUNT_OFFSET));
+	/* Clear link flap reason */
+	lfa_sts &= ~LFA_LINK_FLAP_REASON_MASK;
+
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, lfa_sts), lfa_sts);
+
+	/* Disable NIG DRAIN */
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+
+	/* Enable interrupts */
+	bnx2x_link_int_enable(params);
+	return 0;
+}
+
+static void bnx2x_cannot_avoid_link_flap(struct link_params *params,
+					 struct link_vars *vars,
+					 int lfa_status)
+{
+	u32 lfa_sts, cfg_idx, tmp_val;
+	struct bnx2x *bp = params->bp;
+
+	bnx2x_link_reset(params, vars, 1);
+
+	if (!params->lfa_base)
+		return;
+	/* Store the new link parameters */
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, req_duplex),
+	       params->req_duplex[0] | (params->req_duplex[1] << 16));
+
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, req_flow_ctrl),
+	       params->req_flow_ctrl[0] | (params->req_flow_ctrl[1] << 16));
+
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, req_line_speed),
+	       params->req_line_speed[0] | (params->req_line_speed[1] << 16));
+
+	for (cfg_idx = 0; cfg_idx < SHMEM_LINK_CONFIG_SIZE; cfg_idx++) {
+		REG_WR(bp, params->lfa_base +
+		       offsetof(struct shmem_lfa,
+				speed_cap_mask[cfg_idx]),
+		       params->speed_cap_mask[cfg_idx]);
+	}
+
+	tmp_val = REG_RD(bp, params->lfa_base +
+			 offsetof(struct shmem_lfa, additional_config));
+	tmp_val &= ~REQ_FC_AUTO_ADV_MASK;
+	tmp_val |= params->req_fc_auto_adv;
+
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, additional_config), tmp_val);
+
+	lfa_sts = REG_RD(bp, params->lfa_base +
+			 offsetof(struct shmem_lfa, lfa_sts));
+
+	/* Clear the "Don't Clear Statistics" bit, and set reason */
+	lfa_sts &= ~SHMEM_LFA_DONT_CLEAR_STAT;
+
+	/* Set link flap reason */
+	lfa_sts &= ~LFA_LINK_FLAP_REASON_MASK;
+	lfa_sts |= ((lfa_status & LFA_LINK_FLAP_REASON_MASK) <<
+		    LFA_LINK_FLAP_REASON_OFFSET);
+
+	/* Increment link flap counter */
+	lfa_sts = ((lfa_sts & ~LINK_FLAP_COUNT_MASK) |
+		   (((((lfa_sts & LINK_FLAP_COUNT_MASK) >>
+		       LINK_FLAP_COUNT_OFFSET) + 1) & 0xff)
+		    << LINK_FLAP_COUNT_OFFSET));
+	REG_WR(bp, params->lfa_base +
+	       offsetof(struct shmem_lfa, lfa_sts), lfa_sts);
+	/* Proceed with regular link initialization */
+}
+
 int bnx2x_phy_init(struct link_params *params, struct link_vars *vars)
 {
+	int lfa_status;
 	struct bnx2x *bp = params->bp;
 	DP(NETIF_MSG_LINK, "Phy Initialization started\n");
 	DP(NETIF_MSG_LINK, "(1) req_speed %d, req_flowctrl %d\n",
@@ -12274,6 +12167,19 @@ int bnx2x_phy_init(struct link_params *params, struct link_vars *vars)
 	vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
 	vars->mac_type = MAC_TYPE_NONE;
 	vars->phy_flags = 0;
+	/* Driver opens NIG-BRB filters */
+	bnx2x_set_rx_filter(params, 1);
+	/* Check if link flap can be avoided */
+	lfa_status = bnx2x_check_lfa(params);
+
+	if (lfa_status == 0) {
+		DP(NETIF_MSG_LINK, "Link Flap Avoidance in progress\n");
+		return bnx2x_avoid_link_flap(params, vars);
+	}
+
+	DP(NETIF_MSG_LINK, "Cannot avoid link flap lfa_sta=0x%x\n",
+		       lfa_status);
+	bnx2x_cannot_avoid_link_flap(params, vars, lfa_status);
 
 	/* Disable attentions */
 	bnx2x_bits_dis(bp, NIG_REG_MASK_INTERRUPT_PORT0 + params->port*4,
@@ -12356,13 +12262,12 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 		REG_WR(bp, NIG_REG_EGRESS_EMAC0_OUT_EN + port*4, 0);
 	}
 
-	/* Stop BigMac rx */
-	if (!CHIP_IS_E3(bp))
-		bnx2x_bmac_rx_disable(bp, port);
-	else {
-		bnx2x_xmac_disable(params);
-		bnx2x_umac_disable(params);
-	}
+		if (!CHIP_IS_E3(bp)) {
+			bnx2x_set_bmac_rx(bp, params->chip_id, port, 0);
+		} else {
+			bnx2x_set_xmac_rxtx(params, 0);
+			bnx2x_set_umac_rxtx(params, 0);
+		}
 	/* Disable emac */
 	if (!CHIP_IS_E3(bp))
 		REG_WR(bp, NIG_REG_NIG_EMAC0_EN + port*4, 0);
@@ -12420,6 +12325,56 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 	vars->phy_flags = 0;
 	return 0;
 }
+int bnx2x_lfa_reset(struct link_params *params,
+			       struct link_vars *vars)
+{
+	struct bnx2x *bp = params->bp;
+	vars->link_up = 0;
+	vars->phy_flags = 0;
+	if (!params->lfa_base)
+		return bnx2x_link_reset(params, vars, 1);
+	/*
+	 * Activate NIG drain so that during this time the device won't send
+	 * anything while it is unable to response.
+	 */
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 1);
+
+	/*
+	 * Close gracefully the gate from BMAC to NIG such that no half packets
+	 * are passed.
+	 */
+	if (!CHIP_IS_E3(bp))
+		bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 0);
+
+	if (CHIP_IS_E3(bp)) {
+		bnx2x_set_xmac_rxtx(params, 0);
+		bnx2x_set_umac_rxtx(params, 0);
+	}
+	/* Wait 10ms for the pipe to clean up*/
+	usleep_range(10000, 20000);
+
+	/* Clean the NIG-BRB using the network filters in a way that will
+	 * not cut a packet in the middle.
+	 */
+	bnx2x_set_rx_filter(params, 0);
+
+	/*
+	 * Re-open the gate between the BMAC and the NIG, after verifying the
+	 * gate to the BRB is closed, otherwise packets may arrive to the
+	 * firmware before driver had initialized it. The target is to achieve
+	 * minimum management protocol down time.
+	 */
+	if (!CHIP_IS_E3(bp))
+		bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 1);
+
+	if (CHIP_IS_E3(bp)) {
+		bnx2x_set_xmac_rxtx(params, 1);
+		bnx2x_set_umac_rxtx(params, 1);
+	}
+	/* Disable NIG drain */
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+	return 0;
+}
 
 /****************************************************************************/
 /*				Common function				    */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
index 51cac8130051..9165b89a4b19 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
@@ -155,7 +155,7 @@ struct bnx2x_phy {
 #define FLAGS_DUMMY_READ		(1<<9)
 #define FLAGS_MDC_MDIO_WA_B0		(1<<10)
 #define FLAGS_TX_ERROR_CHECK		(1<<12)
-#define FLAGS_EEE_10GBT			(1<<13)
+#define FLAGS_EEE			(1<<13)
 
 	/* preemphasis values for the rx side */
 	u16 rx_preemphasis[4];
@@ -216,6 +216,7 @@ struct bnx2x_phy {
 	phy_specific_func_t phy_specific_func;
 #define DISABLE_TX	1
 #define ENABLE_TX	2
+#define PHY_INIT	3
 };
 
 /* Inputs parameters to the CLC */
@@ -304,6 +305,8 @@ struct link_params {
 	struct bnx2x *bp;
 	u16 req_fc_auto_adv; /* Should be set to TX / BOTH when
 				req_flow_ctrl is set to AUTO */
+	u16 rsrv1;
+	u32 lfa_base;
 };
 
 /* Output parameters */
@@ -356,7 +359,7 @@ int bnx2x_phy_init(struct link_params *params, struct link_vars *vars);
    to 0 */
 int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 		     u8 reset_ext_phy);
-
+int bnx2x_lfa_reset(struct link_params *params, struct link_vars *vars);
 /* bnx2x_link_update should be called upon link interrupt */
 int bnx2x_link_update(struct link_params *params, struct link_vars *vars);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e11485ca037d..f7ed122f4071 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -2166,7 +2166,6 @@ void bnx2x_link_set(struct bnx2x *bp)
 {
 	if (!BP_NOMCP(bp)) {
 		bnx2x_acquire_phy_lock(bp);
-		bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1);
 		bnx2x_phy_init(&bp->link_params, &bp->link_vars);
 		bnx2x_release_phy_lock(bp);
 
@@ -2179,12 +2178,19 @@ static void bnx2x__link_reset(struct bnx2x *bp)
 {
 	if (!BP_NOMCP(bp)) {
 		bnx2x_acquire_phy_lock(bp);
-		bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1);
+		bnx2x_lfa_reset(&bp->link_params, &bp->link_vars);
 		bnx2x_release_phy_lock(bp);
 	} else
 		BNX2X_ERR("Bootcode is missing - can not reset link\n");
 }
 
+void bnx2x_force_link_reset(struct bnx2x *bp)
+{
+	bnx2x_acquire_phy_lock(bp);
+	bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1);
+	bnx2x_release_phy_lock(bp);
+}
+
 u8 bnx2x_link_test(struct bnx2x *bp, u8 is_serdes)
 {
 	u8 rc = 0;
@@ -6751,7 +6757,6 @@ static int bnx2x_init_hw_port(struct bnx2x *bp)
 	u32 low, high;
 	u32 val;
 
-	bnx2x__link_reset(bp);
 
 	DP(NETIF_MSG_HW, "starting port init  port %d\n", port);
 
@@ -8244,12 +8249,15 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode)
  * bnx2x_send_unload_done - send UNLOAD_DONE command to the MCP.
  *
  * @bp:		driver handle
+ * @keep_link:		true iff link should be kept up
  */
-void bnx2x_send_unload_done(struct bnx2x *bp)
+void bnx2x_send_unload_done(struct bnx2x *bp, bool keep_link)
 {
+	u32 reset_param = keep_link ? DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET : 0;
+
 	/* Report UNLOAD_DONE to MCP */
 	if (!BP_NOMCP(bp))
-		bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, 0);
+		bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, reset_param);
 }
 
 static int bnx2x_func_wait_started(struct bnx2x *bp)
@@ -8318,7 +8326,7 @@ static int bnx2x_func_wait_started(struct bnx2x *bp)
 	return 0;
 }
 
-void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode)
+void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 {
 	int port = BP_PORT(bp);
 	int i, rc = 0;
@@ -8440,7 +8448,7 @@ unload_error:
 
 
 	/* Report UNLOAD_DONE to MCP */
-	bnx2x_send_unload_done(bp);
+	bnx2x_send_unload_done(bp, keep_link);
 }
 
 void bnx2x_disable_close_the_gate(struct bnx2x *bp)
@@ -8852,7 +8860,8 @@ int bnx2x_leader_reset(struct bnx2x *bp)
 	 * driver is owner of the HW
 	 */
 	if (!global && !BP_NOMCP(bp)) {
-		load_code = bnx2x_fw_command(bp, DRV_MSG_CODE_LOAD_REQ, 0);
+		load_code = bnx2x_fw_command(bp, DRV_MSG_CODE_LOAD_REQ,
+					     DRV_MSG_CODE_LOAD_REQ_WITH_LFA);
 		if (!load_code) {
 			BNX2X_ERR("MCP response failure, aborting\n");
 			rc = -EAGAIN;
@@ -8958,7 +8967,7 @@ static void bnx2x_parity_recover(struct bnx2x *bp)
 
 			/* Stop the driver */
 			/* If interface has been removed - break */
-			if (bnx2x_nic_unload(bp, UNLOAD_RECOVERY))
+			if (bnx2x_nic_unload(bp, UNLOAD_RECOVERY, false))
 				return;
 
 			bp->recovery_state = BNX2X_RECOVERY_WAIT;
@@ -9124,7 +9133,7 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 		bp->sp_rtnl_state = 0;
 		smp_mb();
 
-		bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+		bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 		bnx2x_nic_load(bp, LOAD_NORMAL);
 
 		goto sp_rtnl_exit;
@@ -9310,7 +9319,8 @@ static void __devinit bnx2x_prev_unload_undi_inc(struct bnx2x *bp, u8 port,
 
 static int __devinit bnx2x_prev_mcp_done(struct bnx2x *bp)
 {
-	u32 rc = bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, 0);
+	u32 rc = bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE,
+				  DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET);
 	if (!rc) {
 		BNX2X_ERR("MCP response failure, aborting\n");
 		return -EBUSY;
@@ -11000,7 +11010,7 @@ static int bnx2x_close(struct net_device *dev)
 	struct bnx2x *bp = netdev_priv(dev);
 
 	/* Unload the driver, release IRQs */
-	bnx2x_nic_unload(bp, UNLOAD_CLOSE);
+	bnx2x_nic_unload(bp, UNLOAD_CLOSE, false);
 
 	/* Power off */
 	bnx2x_set_power_state(bp, PCI_D3hot);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 28a0bcfe61ff..1b1999d34c71 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -4949,6 +4949,10 @@
 #define UMAC_COMMAND_CONFIG_REG_SW_RESET			 (0x1<<13)
 #define UMAC_COMMAND_CONFIG_REG_TX_ENA				 (0x1<<0)
 #define UMAC_REG_COMMAND_CONFIG					 0x8
+/* [RW 16] This is the duration for which MAC must wait to go back to ACTIVE
+ * state from LPI state when it receives packet for transmission. The
+ * decrement unit is 1 micro-second. */
+#define UMAC_REG_EEE_WAKE_TIMER					 0x6c
 /* [RW 32] Register Bit 0 refers to Bit 16 of the MAC address; Bit 1 refers
  * to bit 17 of the MAC address etc. */
 #define UMAC_REG_MAC_ADDR0					 0xc
@@ -4958,6 +4962,8 @@
 /* [RW 14] Defines a 14-Bit maximum frame length used by the MAC receive
  * logic to check frames. */
 #define UMAC_REG_MAXFR						 0x14
+#define UMAC_REG_UMAC_EEE_CTRL					 0x64
+#define UMAC_UMAC_EEE_CTRL_REG_EEE_EN				 (0x1<<3)
 /* [RW 8] The event id for aggregated interrupt 0 */
 #define USDM_REG_AGG_INT_EVENT_0				 0xc4038
 #define USDM_REG_AGG_INT_EVENT_1				 0xc403c
@@ -6992,6 +6998,7 @@ Theotherbitsarereservedandshouldbezero*/
 /* BCM84833 only */
 #define MDIO_84833_TOP_CFG_FW_REV			0x400f
 #define MDIO_84833_TOP_CFG_FW_EEE		0x10b1
+#define MDIO_84833_TOP_CFG_FW_NO_EEE		0x1f81
 #define MDIO_84833_TOP_CFG_XGPHY_STRAP1			0x401a
 #define MDIO_84833_SUPER_ISOLATE		0x8000
 /* These are mailbox register set used by 84833. */
@@ -7160,10 +7167,11 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_REG_GPHY_ID_54618SE		0x5cd5
 #define MDIO_REG_GPHY_CL45_ADDR_REG			0xd
 #define MDIO_REG_GPHY_CL45_DATA_REG			0xe
-#define MDIO_REG_GPHY_EEE_ADV			0x3c
-#define MDIO_REG_GPHY_EEE_1G		(0x1 << 2)
-#define MDIO_REG_GPHY_EEE_100		(0x1 << 1)
 #define MDIO_REG_GPHY_EEE_RESOLVED		0x803e
+#define MDIO_REG_GPHY_EXP_ACCESS_GATE			0x15
+#define MDIO_REG_GPHY_EXP_ACCESS			0x17
+#define MDIO_REG_GPHY_EXP_ACCESS_TOP		0xd00
+#define MDIO_REG_GPHY_EXP_TOP_2K_BUF		0x40
 #define MDIO_REG_GPHY_AUX_STATUS			0x19
 #define MDIO_REG_INTR_STATUS				0x1a
 #define MDIO_REG_INTR_MASK				0x1b
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 62f754bd0dfe..71971a161bd1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -229,8 +229,7 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 			 */
 			list_add_tail(&spacer.link, &o->pending_comp);
 			mb();
-			list_del(&elem->link);
-			list_add_tail(&elem->link, &o->pending_comp);
+			list_move_tail(&elem->link, &o->pending_comp);
 			list_del(&spacer.link);
 		} else
 			break;
@@ -5620,7 +5619,7 @@ static inline int bnx2x_func_send_start(struct bnx2x *bp,
 	memset(rdata, 0, sizeof(*rdata));
 
 	/* Fill the ramrod data with provided parameters */
-	rdata->function_mode = cpu_to_le16(start_params->mf_mode);
+	rdata->function_mode = (u8)start_params->mf_mode;
 	rdata->sd_vlan_tag   = cpu_to_le16(start_params->sd_vlan_tag);
 	rdata->path_id       = BP_PATH(bp);
 	rdata->network_cos_mode = start_params->network_cos_mode;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index a1d0446b39b3..348ed02d3c69 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -39,14 +39,39 @@ static inline long bnx2x_hilo(u32 *hiref)
 #endif
 }
 
-static u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp)
+static inline u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp)
 {
-	u16 res = sizeof(struct host_port_stats) >> 2;
+	u16 res = 0;
 
-	/* if PFC stats are not supported by the MFW, don't DMA them */
-	if (!(bp->flags &  BC_SUPPORTS_PFC_STATS))
-		res -= (sizeof(u32)*4) >> 2;
+	/* 'newest' convention - shmem2 cotains the size of the port stats */
+	if (SHMEM2_HAS(bp, sizeof_port_stats)) {
+		u32 size = SHMEM2_RD(bp, sizeof_port_stats);
+		if (size)
+			res = size;
 
+		/* prevent newer BC from causing buffer overflow */
+		if (res > sizeof(struct host_port_stats))
+			res = sizeof(struct host_port_stats);
+	}
+
+	/* Older convention - all BCs support the port stats' fields up until
+	 * the 'not_used' field
+	 */
+	if (!res) {
+		res = offsetof(struct host_port_stats, not_used) + 4;
+
+		/* if PFC stats are supported by the MFW, DMA them as well */
+		if (bp->flags & BC_SUPPORTS_PFC_STATS) {
+			res += offsetof(struct host_port_stats,
+					pfc_frames_rx_lo) -
+			       offsetof(struct host_port_stats,
+					pfc_frames_tx_hi) + 4 ;
+		}
+	}
+
+	res >>= 2;
+
+	WARN_ON(res > 2 * DMAE_LEN32_RD_MAX);
 	return res;
 }
 
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 3b4fc61f24cf..cc8434fd606e 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -823,10 +823,8 @@ static void cnic_free_context(struct cnic_dev *dev)
 	}
 }
 
-static void __cnic_free_uio(struct cnic_uio_dev *udev)
+static void __cnic_free_uio_rings(struct cnic_uio_dev *udev)
 {
-	uio_unregister_device(&udev->cnic_uinfo);
-
 	if (udev->l2_buf) {
 		dma_free_coherent(&udev->pdev->dev, udev->l2_buf_size,
 				  udev->l2_buf, udev->l2_buf_map);
@@ -839,6 +837,14 @@ static void __cnic_free_uio(struct cnic_uio_dev *udev)
 		udev->l2_ring = NULL;
 	}
 
+}
+
+static void __cnic_free_uio(struct cnic_uio_dev *udev)
+{
+	uio_unregister_device(&udev->cnic_uinfo);
+
+	__cnic_free_uio_rings(udev);
+
 	pci_dev_put(udev->pdev);
 	kfree(udev);
 }
@@ -862,6 +868,8 @@ static void cnic_free_resc(struct cnic_dev *dev)
 	if (udev) {
 		udev->dev = NULL;
 		cp->udev = NULL;
+		if (udev->uio_dev == -1)
+			__cnic_free_uio_rings(udev);
 	}
 
 	cnic_free_context(dev);
@@ -996,6 +1004,34 @@ static int cnic_alloc_kcq(struct cnic_dev *dev, struct kcq_info *info,
 	return 0;
 }
 
+static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages)
+{
+	struct cnic_local *cp = udev->dev->cnic_priv;
+
+	if (udev->l2_ring)
+		return 0;
+
+	udev->l2_ring_size = pages * BCM_PAGE_SIZE;
+	udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size,
+					   &udev->l2_ring_map,
+					   GFP_KERNEL | __GFP_COMP);
+	if (!udev->l2_ring)
+		return -ENOMEM;
+
+	udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size;
+	udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size);
+	udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size,
+					  &udev->l2_buf_map,
+					  GFP_KERNEL | __GFP_COMP);
+	if (!udev->l2_buf) {
+		__cnic_free_uio_rings(udev);
+		return -ENOMEM;
+	}
+
+	return 0;
+
+}
+
 static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 {
 	struct cnic_local *cp = dev->cnic_priv;
@@ -1005,6 +1041,11 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 	list_for_each_entry(udev, &cnic_udev_list, list) {
 		if (udev->pdev == dev->pcidev) {
 			udev->dev = dev;
+			if (__cnic_alloc_uio_rings(udev, pages)) {
+				udev->dev = NULL;
+				read_unlock(&cnic_dev_lock);
+				return -ENOMEM;
+			}
 			cp->udev = udev;
 			read_unlock(&cnic_dev_lock);
 			return 0;
@@ -1020,20 +1061,9 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 
 	udev->dev = dev;
 	udev->pdev = dev->pcidev;
-	udev->l2_ring_size = pages * BCM_PAGE_SIZE;
-	udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size,
-					   &udev->l2_ring_map,
-					   GFP_KERNEL | __GFP_COMP);
-	if (!udev->l2_ring)
-		goto err_udev;
 
-	udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size;
-	udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size);
-	udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size,
-					  &udev->l2_buf_map,
-					  GFP_KERNEL | __GFP_COMP);
-	if (!udev->l2_buf)
-		goto err_dma;
+	if (__cnic_alloc_uio_rings(udev, pages))
+		goto err_udev;
 
 	write_lock(&cnic_dev_lock);
 	list_add(&udev->list, &cnic_udev_list);
@@ -1044,9 +1074,7 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 	cp->udev = udev;
 
 	return 0;
- err_dma:
-	dma_free_coherent(&udev->pdev->dev, udev->l2_ring_size,
-			  udev->l2_ring, udev->l2_ring_map);
+
  err_udev:
 	kfree(udev);
 	return -ENOMEM;
@@ -1260,7 +1288,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 	if (ret)
 		goto error;
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (CNIC_SUPPORTS_FCOE(cp)) {
 		ret = cnic_alloc_kcq(dev, &cp->kcq2, true);
 		if (ret)
 			goto error;
@@ -1275,6 +1303,9 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 	if (ret)
 		goto error;
 
+	if (cp->ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI)
+		return 0;
+
 	cp->bnx2x_def_status_blk = cp->ethdev->irq_arr[1].status_blk;
 
 	cp->l2_rx_ring_size = 15;
@@ -3050,6 +3081,22 @@ static void cnic_ack_bnx2x_e2_msix(struct cnic_dev *dev)
 			IGU_INT_DISABLE, 0);
 }
 
+static void cnic_arm_bnx2x_msix(struct cnic_dev *dev, u32 idx)
+{
+	struct cnic_local *cp = dev->cnic_priv;
+
+	cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, CSTORM_ID, idx,
+			   IGU_INT_ENABLE, 1);
+}
+
+static void cnic_arm_bnx2x_e2_msix(struct cnic_dev *dev, u32 idx)
+{
+	struct cnic_local *cp = dev->cnic_priv;
+
+	cnic_ack_igu_sb(dev, cp->bnx2x_igu_sb_id, IGU_SEG_ACCESS_DEF, idx,
+			IGU_INT_ENABLE, 1);
+}
+
 static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info)
 {
 	u32 last_status = *info->status_idx_ptr;
@@ -3086,9 +3133,8 @@ static void cnic_service_bnx2x_bh(unsigned long data)
 		CNIC_WR16(dev, cp->kcq1.io_addr,
 			  cp->kcq1.sw_prod_idx + MAX_KCQ_IDX);
 
-		if (!BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
-			cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID,
-					   status_idx, IGU_INT_ENABLE, 1);
+		if (cp->ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE) {
+			cp->arm_int(dev, status_idx);
 			break;
 		}
 
@@ -4845,6 +4891,9 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev,
 	buf_map = udev->l2_buf_map;
 	for (i = 0; i < MAX_TX_DESC_CNT; i += 3, txbd += 3) {
 		struct eth_tx_start_bd *start_bd = &txbd->start_bd;
+		struct eth_tx_parse_bd_e1x *pbd_e1x =
+			&((txbd + 1)->parse_bd_e1x);
+		struct eth_tx_parse_bd_e2 *pbd_e2 = &((txbd + 1)->parse_bd_e2);
 		struct eth_tx_bd *reg_bd = &((txbd + 2)->reg_bd);
 
 		start_bd->addr_hi = cpu_to_le32((u64) buf_map >> 32);
@@ -4854,10 +4903,15 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev,
 		start_bd->nbytes = cpu_to_le16(0x10);
 		start_bd->nbd = cpu_to_le16(3);
 		start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD;
-		start_bd->general_data = (UNICAST_ADDRESS <<
-			ETH_TX_START_BD_ETH_ADDR_TYPE_SHIFT);
+		start_bd->general_data &= ~ETH_TX_START_BD_PARSE_NBDS;
 		start_bd->general_data |= (1 << ETH_TX_START_BD_HDR_NBDS_SHIFT);
 
+		if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id))
+			pbd_e2->parsing_data = (UNICAST_ADDRESS <<
+				 ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE_SHIFT);
+		else
+			 pbd_e1x->global_data = (UNICAST_ADDRESS <<
+				ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE_SHIFT);
 	}
 
 	val = (u64) ring_map >> 32;
@@ -5308,7 +5362,7 @@ static void cnic_stop_hw(struct cnic_dev *dev)
 		/* Need to wait for the ring shutdown event to complete
 		 * before clearing the CNIC_UP flag.
 		 */
-		while (cp->udev->uio_dev != -1 && i < 15) {
+		while (cp->udev && cp->udev->uio_dev != -1 && i < 15) {
 			msleep(100);
 			i++;
 		}
@@ -5473,8 +5527,7 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev)
 
 	if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI))
 		cdev->max_iscsi_conn = ethdev->max_iscsi_conn;
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) &&
-	    !(ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE))
+	if (CNIC_SUPPORTS_FCOE(cp))
 		cdev->max_fcoe_conn = ethdev->max_fcoe_conn;
 
 	if (cdev->max_fcoe_conn > BNX2X_FCOE_NUM_CONNECTIONS)
@@ -5492,10 +5545,13 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev)
 	cp->stop_cm = cnic_cm_stop_bnx2x_hw;
 	cp->enable_int = cnic_enable_bnx2x_int;
 	cp->disable_int_sync = cnic_disable_bnx2x_int_sync;
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id))
+	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
 		cp->ack_int = cnic_ack_bnx2x_e2_msix;
-	else
+		cp->arm_int = cnic_arm_bnx2x_e2_msix;
+	} else {
 		cp->ack_int = cnic_ack_bnx2x_msix;
+		cp->arm_int = cnic_arm_bnx2x_msix;
+	}
 	cp->close_conn = cnic_close_bnx2x_conn;
 	return cdev;
 }
diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h
index 30328097f516..148604c3fa0c 100644
--- a/drivers/net/ethernet/broadcom/cnic.h
+++ b/drivers/net/ethernet/broadcom/cnic.h
@@ -334,6 +334,7 @@ struct cnic_local {
 	void			(*enable_int)(struct cnic_dev *);
 	void			(*disable_int_sync)(struct cnic_dev *);
 	void			(*ack_int)(struct cnic_dev *);
+	void			(*arm_int)(struct cnic_dev *, u32 index);
 	void			(*close_conn)(struct cnic_sock *, u32 opcode);
 };
 
@@ -474,6 +475,10 @@ struct bnx2x_bd_chain_next {
 	  MAX_STAT_COUNTER_ID_E1))
 #endif
 
+#define CNIC_SUPPORTS_FCOE(cp)					\
+	(BNX2X_CHIP_IS_E2_PLUS((cp)->chip_id) &&		\
+	 !((cp)->ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE))
+
 #define CNIC_RAMROD_TMO			(HZ / 4)
 
 #endif
diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h
index 382c98b0cc0c..ede3db35d757 100644
--- a/drivers/net/ethernet/broadcom/cnic_defs.h
+++ b/drivers/net/ethernet/broadcom/cnic_defs.h
@@ -896,7 +896,7 @@ struct tstorm_tcp_tcp_ag_context_section {
 	u32 snd_nxt;
 	u32 rtt_seq;
 	u32 rtt_time;
-	u32 __reserved66;
+	u32 wnd_right_edge_local;
 	u32 wnd_right_edge;
 	u32 tcp_agg_vars1;
 #define TSTORM_TCP_TCP_AG_CONTEXT_SECTION_FIN_SENT_FLAG (0x1<<0)
diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h
index 5cb88881bba1..865095aad1f6 100644
--- a/drivers/net/ethernet/broadcom/cnic_if.h
+++ b/drivers/net/ethernet/broadcom/cnic_if.h
@@ -14,8 +14,8 @@
 
 #include "bnx2x/bnx2x_mfw_req.h"
 
-#define CNIC_MODULE_VERSION	"2.5.12"
-#define CNIC_MODULE_RELDATE	"June 29, 2012"
+#define CNIC_MODULE_VERSION	"2.5.14"
+#define CNIC_MODULE_RELDATE	"Sep 30, 2012"
 
 #define CNIC_ULP_RDMA		0
 #define CNIC_ULP_ISCSI		1
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 388d32213937..46280ba4c5d4 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -44,10 +44,8 @@
 #include <linux/prefetch.h>
 #include <linux/dma-mapping.h>
 #include <linux/firmware.h>
-#if IS_ENABLED(CONFIG_HWMON)
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#endif
 
 #include <net/checksum.h>
 #include <net/ip.h>
@@ -92,10 +90,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 
 #define DRV_MODULE_NAME		"tg3"
 #define TG3_MAJ_NUM			3
-#define TG3_MIN_NUM			124
+#define TG3_MIN_NUM			125
 #define DRV_MODULE_VERSION	\
 	__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE	"March 21, 2012"
+#define DRV_MODULE_RELDATE	"September 26, 2012"
 
 #define RESET_KIND_SHUTDOWN	0
 #define RESET_KIND_INIT		1
@@ -6263,7 +6261,7 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
 		u32 jmb_prod_idx = dpr->rx_jmb_prod_idx;
 
 		tp->rx_refill = false;
-		for (i = 1; i < tp->irq_cnt; i++)
+		for (i = 1; i <= tp->rxq_cnt; i++)
 			err |= tg3_rx_prodring_xfer(tp, dpr,
 						    &tp->napi[i].prodring);
 
@@ -7592,15 +7590,11 @@ static int tg3_init_rings(struct tg3 *tp)
 	return 0;
 }
 
-/*
- * Must not be invoked with interrupt sources disabled and
- * the hardware shutdown down.
- */
-static void tg3_free_consistent(struct tg3 *tp)
+static void tg3_mem_tx_release(struct tg3 *tp)
 {
 	int i;
 
-	for (i = 0; i < tp->irq_cnt; i++) {
+	for (i = 0; i < tp->irq_max; i++) {
 		struct tg3_napi *tnapi = &tp->napi[i];
 
 		if (tnapi->tx_ring) {
@@ -7611,17 +7605,114 @@ static void tg3_free_consistent(struct tg3 *tp)
 
 		kfree(tnapi->tx_buffers);
 		tnapi->tx_buffers = NULL;
+	}
+}
 
-		if (tnapi->rx_rcb) {
-			dma_free_coherent(&tp->pdev->dev,
-					  TG3_RX_RCB_RING_BYTES(tp),
-					  tnapi->rx_rcb,
-					  tnapi->rx_rcb_mapping);
-			tnapi->rx_rcb = NULL;
-		}
+static int tg3_mem_tx_acquire(struct tg3 *tp)
+{
+	int i;
+	struct tg3_napi *tnapi = &tp->napi[0];
+
+	/* If multivector TSS is enabled, vector 0 does not handle
+	 * tx interrupts.  Don't allocate any resources for it.
+	 */
+	if (tg3_flag(tp, ENABLE_TSS))
+		tnapi++;
+
+	for (i = 0; i < tp->txq_cnt; i++, tnapi++) {
+		tnapi->tx_buffers = kzalloc(sizeof(struct tg3_tx_ring_info) *
+					    TG3_TX_RING_SIZE, GFP_KERNEL);
+		if (!tnapi->tx_buffers)
+			goto err_out;
+
+		tnapi->tx_ring = dma_alloc_coherent(&tp->pdev->dev,
+						    TG3_TX_RING_BYTES,
+						    &tnapi->tx_desc_mapping,
+						    GFP_KERNEL);
+		if (!tnapi->tx_ring)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	tg3_mem_tx_release(tp);
+	return -ENOMEM;
+}
+
+static void tg3_mem_rx_release(struct tg3 *tp)
+{
+	int i;
+
+	for (i = 0; i < tp->irq_max; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
 
 		tg3_rx_prodring_fini(tp, &tnapi->prodring);
 
+		if (!tnapi->rx_rcb)
+			continue;
+
+		dma_free_coherent(&tp->pdev->dev,
+				  TG3_RX_RCB_RING_BYTES(tp),
+				  tnapi->rx_rcb,
+				  tnapi->rx_rcb_mapping);
+		tnapi->rx_rcb = NULL;
+	}
+}
+
+static int tg3_mem_rx_acquire(struct tg3 *tp)
+{
+	unsigned int i, limit;
+
+	limit = tp->rxq_cnt;
+
+	/* If RSS is enabled, we need a (dummy) producer ring
+	 * set on vector zero.  This is the true hw prodring.
+	 */
+	if (tg3_flag(tp, ENABLE_RSS))
+		limit++;
+
+	for (i = 0; i < limit; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		if (tg3_rx_prodring_init(tp, &tnapi->prodring))
+			goto err_out;
+
+		/* If multivector RSS is enabled, vector 0
+		 * does not handle rx or tx interrupts.
+		 * Don't allocate any resources for it.
+		 */
+		if (!i && tg3_flag(tp, ENABLE_RSS))
+			continue;
+
+		tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev,
+						   TG3_RX_RCB_RING_BYTES(tp),
+						   &tnapi->rx_rcb_mapping,
+						   GFP_KERNEL);
+		if (!tnapi->rx_rcb)
+			goto err_out;
+
+		memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
+	}
+
+	return 0;
+
+err_out:
+	tg3_mem_rx_release(tp);
+	return -ENOMEM;
+}
+
+/*
+ * Must not be invoked with interrupt sources disabled and
+ * the hardware shutdown down.
+ */
+static void tg3_free_consistent(struct tg3 *tp)
+{
+	int i;
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
 		if (tnapi->hw_status) {
 			dma_free_coherent(&tp->pdev->dev, TG3_HW_STATUS_SIZE,
 					  tnapi->hw_status,
@@ -7630,6 +7721,9 @@ static void tg3_free_consistent(struct tg3 *tp)
 		}
 	}
 
+	tg3_mem_rx_release(tp);
+	tg3_mem_tx_release(tp);
+
 	if (tp->hw_stats) {
 		dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
 				  tp->hw_stats, tp->stats_mapping);
@@ -7668,72 +7762,38 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 		memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE);
 		sblk = tnapi->hw_status;
 
-		if (tg3_rx_prodring_init(tp, &tnapi->prodring))
-			goto err_out;
+		if (tg3_flag(tp, ENABLE_RSS)) {
+			u16 *prodptr = 0;
 
-		/* If multivector TSS is enabled, vector 0 does not handle
-		 * tx interrupts.  Don't allocate any resources for it.
-		 */
-		if ((!i && !tg3_flag(tp, ENABLE_TSS)) ||
-		    (i && tg3_flag(tp, ENABLE_TSS))) {
-			tnapi->tx_buffers = kzalloc(
-					       sizeof(struct tg3_tx_ring_info) *
-					       TG3_TX_RING_SIZE, GFP_KERNEL);
-			if (!tnapi->tx_buffers)
-				goto err_out;
-
-			tnapi->tx_ring = dma_alloc_coherent(&tp->pdev->dev,
-							    TG3_TX_RING_BYTES,
-							&tnapi->tx_desc_mapping,
-							    GFP_KERNEL);
-			if (!tnapi->tx_ring)
-				goto err_out;
-		}
-
-		/*
-		 * When RSS is enabled, the status block format changes
-		 * slightly.  The "rx_jumbo_consumer", "reserved",
-		 * and "rx_mini_consumer" members get mapped to the
-		 * other three rx return ring producer indexes.
-		 */
-		switch (i) {
-		default:
-			if (tg3_flag(tp, ENABLE_RSS)) {
-				tnapi->rx_rcb_prod_idx = NULL;
+			/*
+			 * When RSS is enabled, the status block format changes
+			 * slightly.  The "rx_jumbo_consumer", "reserved",
+			 * and "rx_mini_consumer" members get mapped to the
+			 * other three rx return ring producer indexes.
+			 */
+			switch (i) {
+			case 1:
+				prodptr = &sblk->idx[0].rx_producer;
+				break;
+			case 2:
+				prodptr = &sblk->rx_jumbo_consumer;
+				break;
+			case 3:
+				prodptr = &sblk->reserved;
+				break;
+			case 4:
+				prodptr = &sblk->rx_mini_consumer;
 				break;
 			}
-			/* Fall through */
-		case 1:
+			tnapi->rx_rcb_prod_idx = prodptr;
+		} else {
 			tnapi->rx_rcb_prod_idx = &sblk->idx[0].rx_producer;
-			break;
-		case 2:
-			tnapi->rx_rcb_prod_idx = &sblk->rx_jumbo_consumer;
-			break;
-		case 3:
-			tnapi->rx_rcb_prod_idx = &sblk->reserved;
-			break;
-		case 4:
-			tnapi->rx_rcb_prod_idx = &sblk->rx_mini_consumer;
-			break;
 		}
-
-		/*
-		 * If multivector RSS is enabled, vector 0 does not handle
-		 * rx or tx interrupts.  Don't allocate any resources for it.
-		 */
-		if (!i && tg3_flag(tp, ENABLE_RSS))
-			continue;
-
-		tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev,
-						   TG3_RX_RCB_RING_BYTES(tp),
-						   &tnapi->rx_rcb_mapping,
-						   GFP_KERNEL);
-		if (!tnapi->rx_rcb)
-			goto err_out;
-
-		memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
 	}
 
+	if (tg3_mem_tx_acquire(tp) || tg3_mem_rx_acquire(tp))
+		goto err_out;
+
 	return 0;
 
 err_out:
@@ -8247,9 +8307,10 @@ static void tg3_set_bdinfo(struct tg3 *tp, u32 bdinfo_addr,
 			      nic_addr);
 }
 
-static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
+
+static void tg3_coal_tx_init(struct tg3 *tp, struct ethtool_coalesce *ec)
 {
-	int i;
+	int i = 0;
 
 	if (!tg3_flag(tp, ENABLE_TSS)) {
 		tw32(HOSTCC_TXCOL_TICKS, ec->tx_coalesce_usecs);
@@ -8259,31 +8320,43 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
 		tw32(HOSTCC_TXCOL_TICKS, 0);
 		tw32(HOSTCC_TXMAX_FRAMES, 0);
 		tw32(HOSTCC_TXCOAL_MAXF_INT, 0);
+
+		for (; i < tp->txq_cnt; i++) {
+			u32 reg;
+
+			reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18;
+			tw32(reg, ec->tx_coalesce_usecs);
+			reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18;
+			tw32(reg, ec->tx_max_coalesced_frames);
+			reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18;
+			tw32(reg, ec->tx_max_coalesced_frames_irq);
+		}
 	}
 
+	for (; i < tp->irq_max - 1; i++) {
+		tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0);
+		tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0);
+		tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0);
+	}
+}
+
+static void tg3_coal_rx_init(struct tg3 *tp, struct ethtool_coalesce *ec)
+{
+	int i = 0;
+	u32 limit = tp->rxq_cnt;
+
 	if (!tg3_flag(tp, ENABLE_RSS)) {
 		tw32(HOSTCC_RXCOL_TICKS, ec->rx_coalesce_usecs);
 		tw32(HOSTCC_RXMAX_FRAMES, ec->rx_max_coalesced_frames);
 		tw32(HOSTCC_RXCOAL_MAXF_INT, ec->rx_max_coalesced_frames_irq);
+		limit--;
 	} else {
 		tw32(HOSTCC_RXCOL_TICKS, 0);
 		tw32(HOSTCC_RXMAX_FRAMES, 0);
 		tw32(HOSTCC_RXCOAL_MAXF_INT, 0);
 	}
 
-	if (!tg3_flag(tp, 5705_PLUS)) {
-		u32 val = ec->stats_block_coalesce_usecs;
-
-		tw32(HOSTCC_RXCOAL_TICK_INT, ec->rx_coalesce_usecs_irq);
-		tw32(HOSTCC_TXCOAL_TICK_INT, ec->tx_coalesce_usecs_irq);
-
-		if (!netif_carrier_ok(tp->dev))
-			val = 0;
-
-		tw32(HOSTCC_STAT_COAL_TICKS, val);
-	}
-
-	for (i = 0; i < tp->irq_cnt - 1; i++) {
+	for (; i < limit; i++) {
 		u32 reg;
 
 		reg = HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18;
@@ -8292,27 +8365,30 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
 		tw32(reg, ec->rx_max_coalesced_frames);
 		reg = HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18;
 		tw32(reg, ec->rx_max_coalesced_frames_irq);
-
-		if (tg3_flag(tp, ENABLE_TSS)) {
-			reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18;
-			tw32(reg, ec->tx_coalesce_usecs);
-			reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18;
-			tw32(reg, ec->tx_max_coalesced_frames);
-			reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18;
-			tw32(reg, ec->tx_max_coalesced_frames_irq);
-		}
 	}
 
 	for (; i < tp->irq_max - 1; i++) {
 		tw32(HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18, 0);
 		tw32(HOSTCC_RXMAX_FRAMES_VEC1 + i * 0x18, 0);
 		tw32(HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18, 0);
+	}
+}
 
-		if (tg3_flag(tp, ENABLE_TSS)) {
-			tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0);
-			tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0);
-			tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0);
-		}
+static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec)
+{
+	tg3_coal_tx_init(tp, ec);
+	tg3_coal_rx_init(tp, ec);
+
+	if (!tg3_flag(tp, 5705_PLUS)) {
+		u32 val = ec->stats_block_coalesce_usecs;
+
+		tw32(HOSTCC_RXCOAL_TICK_INT, ec->rx_coalesce_usecs_irq);
+		tw32(HOSTCC_TXCOAL_TICK_INT, ec->tx_coalesce_usecs_irq);
+
+		if (!netif_carrier_ok(tp->dev))
+			val = 0;
+
+		tw32(HOSTCC_STAT_COAL_TICKS, val);
 	}
 }
 
@@ -8570,13 +8646,12 @@ static void __tg3_set_rx_mode(struct net_device *dev)
 	}
 }
 
-static void tg3_rss_init_dflt_indir_tbl(struct tg3 *tp)
+static void tg3_rss_init_dflt_indir_tbl(struct tg3 *tp, u32 qcnt)
 {
 	int i;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		tp->rss_ind_tbl[i] =
-			ethtool_rxfh_indir_default(i, tp->irq_cnt - 1);
+		tp->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, qcnt);
 }
 
 static void tg3_rss_check_indir_tbl(struct tg3 *tp)
@@ -8598,7 +8673,7 @@ static void tg3_rss_check_indir_tbl(struct tg3 *tp)
 	}
 
 	if (i != TG3_RSS_INDIR_TBL_SIZE)
-		tg3_rss_init_dflt_indir_tbl(tp);
+		tg3_rss_init_dflt_indir_tbl(tp, tp->rxq_cnt);
 }
 
 static void tg3_rss_write_indir_tbl(struct tg3 *tp)
@@ -9495,7 +9570,6 @@ static int tg3_init_hw(struct tg3 *tp, int reset_phy)
 	return tg3_reset_hw(tp, reset_phy);
 }
 
-#if IS_ENABLED(CONFIG_HWMON)
 static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir)
 {
 	int i;
@@ -9548,22 +9622,17 @@ static const struct attribute_group tg3_group = {
 	.attrs = tg3_attributes,
 };
 
-#endif
-
 static void tg3_hwmon_close(struct tg3 *tp)
 {
-#if IS_ENABLED(CONFIG_HWMON)
 	if (tp->hwmon_dev) {
 		hwmon_device_unregister(tp->hwmon_dev);
 		tp->hwmon_dev = NULL;
 		sysfs_remove_group(&tp->pdev->dev.kobj, &tg3_group);
 	}
-#endif
 }
 
 static void tg3_hwmon_open(struct tg3 *tp)
 {
-#if IS_ENABLED(CONFIG_HWMON)
 	int i, err;
 	u32 size = 0;
 	struct pci_dev *pdev = tp->pdev;
@@ -9595,7 +9664,6 @@ static void tg3_hwmon_open(struct tg3 *tp)
 		dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n");
 		sysfs_remove_group(&pdev->dev.kobj, &tg3_group);
 	}
-#endif
 }
 
 
@@ -10119,21 +10187,43 @@ static int tg3_request_firmware(struct tg3 *tp)
 	return 0;
 }
 
-static bool tg3_enable_msix(struct tg3 *tp)
+static u32 tg3_irq_count(struct tg3 *tp)
 {
-	int i, rc;
-	struct msix_entry msix_ent[tp->irq_max];
+	u32 irq_cnt = max(tp->rxq_cnt, tp->txq_cnt);
 
-	tp->irq_cnt = netif_get_num_default_rss_queues();
-	if (tp->irq_cnt > 1) {
+	if (irq_cnt > 1) {
 		/* We want as many rx rings enabled as there are cpus.
 		 * In multiqueue MSI-X mode, the first MSI-X vector
 		 * only deals with link interrupts, etc, so we add
 		 * one to the number of vectors we are requesting.
 		 */
-		tp->irq_cnt = min_t(unsigned, tp->irq_cnt + 1, tp->irq_max);
+		irq_cnt = min_t(unsigned, irq_cnt + 1, tp->irq_max);
 	}
 
+	return irq_cnt;
+}
+
+static bool tg3_enable_msix(struct tg3 *tp)
+{
+	int i, rc;
+	struct msix_entry msix_ent[tp->irq_max];
+
+	tp->txq_cnt = tp->txq_req;
+	tp->rxq_cnt = tp->rxq_req;
+	if (!tp->rxq_cnt)
+		tp->rxq_cnt = netif_get_num_default_rss_queues();
+	if (tp->rxq_cnt > tp->rxq_max)
+		tp->rxq_cnt = tp->rxq_max;
+
+	/* Disable multiple TX rings by default.  Simple round-robin hardware
+	 * scheduling of the TX rings can cause starvation of rings with
+	 * small packets when other rings have TSO or jumbo packets.
+	 */
+	if (!tp->txq_req)
+		tp->txq_cnt = 1;
+
+	tp->irq_cnt = tg3_irq_count(tp);
+
 	for (i = 0; i < tp->irq_max; i++) {
 		msix_ent[i].entry  = i;
 		msix_ent[i].vector = 0;
@@ -10148,27 +10238,28 @@ static bool tg3_enable_msix(struct tg3 *tp)
 		netdev_notice(tp->dev, "Requested %d MSI-X vectors, received %d\n",
 			      tp->irq_cnt, rc);
 		tp->irq_cnt = rc;
+		tp->rxq_cnt = max(rc - 1, 1);
+		if (tp->txq_cnt)
+			tp->txq_cnt = min(tp->rxq_cnt, tp->txq_max);
 	}
 
 	for (i = 0; i < tp->irq_max; i++)
 		tp->napi[i].irq_vec = msix_ent[i].vector;
 
-	netif_set_real_num_tx_queues(tp->dev, 1);
-	rc = tp->irq_cnt > 1 ? tp->irq_cnt - 1 : 1;
-	if (netif_set_real_num_rx_queues(tp->dev, rc)) {
+	if (netif_set_real_num_rx_queues(tp->dev, tp->rxq_cnt)) {
 		pci_disable_msix(tp->pdev);
 		return false;
 	}
 
-	if (tp->irq_cnt > 1) {
-		tg3_flag_set(tp, ENABLE_RSS);
+	if (tp->irq_cnt == 1)
+		return true;
 
-		if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
-		    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) {
-			tg3_flag_set(tp, ENABLE_TSS);
-			netif_set_real_num_tx_queues(tp->dev, tp->irq_cnt - 1);
-		}
-	}
+	tg3_flag_set(tp, ENABLE_RSS);
+
+	if (tp->txq_cnt > 1)
+		tg3_flag_set(tp, ENABLE_TSS);
+
+	netif_set_real_num_tx_queues(tp->dev, tp->txq_cnt);
 
 	return true;
 }
@@ -10202,6 +10293,11 @@ defcfg:
 	if (!tg3_flag(tp, USING_MSIX)) {
 		tp->irq_cnt = 1;
 		tp->napi[0].irq_vec = tp->pdev->irq;
+	}
+
+	if (tp->irq_cnt == 1) {
+		tp->txq_cnt = 1;
+		tp->rxq_cnt = 1;
 		netif_set_real_num_tx_queues(tp->dev, 1);
 		netif_set_real_num_rx_queues(tp->dev, 1);
 	}
@@ -10219,38 +10315,11 @@ static void tg3_ints_fini(struct tg3 *tp)
 	tg3_flag_clear(tp, ENABLE_TSS);
 }
 
-static int tg3_open(struct net_device *dev)
+static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq)
 {
-	struct tg3 *tp = netdev_priv(dev);
+	struct net_device *dev = tp->dev;
 	int i, err;
 
-	if (tp->fw_needed) {
-		err = tg3_request_firmware(tp);
-		if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0) {
-			if (err)
-				return err;
-		} else if (err) {
-			netdev_warn(tp->dev, "TSO capability disabled\n");
-			tg3_flag_clear(tp, TSO_CAPABLE);
-		} else if (!tg3_flag(tp, TSO_CAPABLE)) {
-			netdev_notice(tp->dev, "TSO capability restored\n");
-			tg3_flag_set(tp, TSO_CAPABLE);
-		}
-	}
-
-	netif_carrier_off(tp->dev);
-
-	err = tg3_power_up(tp);
-	if (err)
-		return err;
-
-	tg3_full_lock(tp, 0);
-
-	tg3_disable_ints(tp);
-	tg3_flag_clear(tp, INIT_COMPLETE);
-
-	tg3_full_unlock(tp);
-
 	/*
 	 * Setup interrupts first so we know how
 	 * many NAPI resources to allocate
@@ -10284,7 +10353,7 @@ static int tg3_open(struct net_device *dev)
 
 	tg3_full_lock(tp, 0);
 
-	err = tg3_init_hw(tp, 1);
+	err = tg3_init_hw(tp, reset_phy);
 	if (err) {
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
 		tg3_free_rings(tp);
@@ -10295,7 +10364,7 @@ static int tg3_open(struct net_device *dev)
 	if (err)
 		goto err_out3;
 
-	if (tg3_flag(tp, USING_MSI)) {
+	if (test_irq && tg3_flag(tp, USING_MSI)) {
 		err = tg3_test_msi(tp);
 
 		if (err) {
@@ -10351,20 +10420,18 @@ err_out2:
 
 err_out1:
 	tg3_ints_fini(tp);
-	tg3_frob_aux_power(tp, false);
-	pci_set_power_state(tp->pdev, PCI_D3hot);
+
 	return err;
 }
 
-static int tg3_close(struct net_device *dev)
+static void tg3_stop(struct tg3 *tp)
 {
 	int i;
-	struct tg3 *tp = netdev_priv(dev);
 
 	tg3_napi_disable(tp);
 	tg3_reset_task_cancel(tp);
 
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(tp->dev);
 
 	tg3_timer_stop(tp);
 
@@ -10389,13 +10456,60 @@ static int tg3_close(struct net_device *dev)
 
 	tg3_ints_fini(tp);
 
-	/* Clear stats across close / open calls */
-	memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
-	memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
-
 	tg3_napi_fini(tp);
 
 	tg3_free_consistent(tp);
+}
+
+static int tg3_open(struct net_device *dev)
+{
+	struct tg3 *tp = netdev_priv(dev);
+	int err;
+
+	if (tp->fw_needed) {
+		err = tg3_request_firmware(tp);
+		if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0) {
+			if (err)
+				return err;
+		} else if (err) {
+			netdev_warn(tp->dev, "TSO capability disabled\n");
+			tg3_flag_clear(tp, TSO_CAPABLE);
+		} else if (!tg3_flag(tp, TSO_CAPABLE)) {
+			netdev_notice(tp->dev, "TSO capability restored\n");
+			tg3_flag_set(tp, TSO_CAPABLE);
+		}
+	}
+
+	netif_carrier_off(tp->dev);
+
+	err = tg3_power_up(tp);
+	if (err)
+		return err;
+
+	tg3_full_lock(tp, 0);
+
+	tg3_disable_ints(tp);
+	tg3_flag_clear(tp, INIT_COMPLETE);
+
+	tg3_full_unlock(tp);
+
+	err = tg3_start(tp, true, true);
+	if (err) {
+		tg3_frob_aux_power(tp, false);
+		pci_set_power_state(tp->pdev, PCI_D3hot);
+	}
+	return err;
+}
+
+static int tg3_close(struct net_device *dev)
+{
+	struct tg3 *tp = netdev_priv(dev);
+
+	tg3_stop(tp);
+
+	/* Clear stats across close / open calls */
+	memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
+	memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
 
 	tg3_power_down(tp);
 
@@ -11185,11 +11299,11 @@ static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
 		if (netif_running(tp->dev))
-			info->data = tp->irq_cnt;
+			info->data = tp->rxq_cnt;
 		else {
 			info->data = num_online_cpus();
-			if (info->data > TG3_IRQ_MAX_VECS_RSS)
-				info->data = TG3_IRQ_MAX_VECS_RSS;
+			if (info->data > TG3_RSS_MAX_NUM_QS)
+				info->data = TG3_RSS_MAX_NUM_QS;
 		}
 
 		/* The first interrupt vector only
@@ -11246,6 +11360,58 @@ static int tg3_set_rxfh_indir(struct net_device *dev, const u32 *indir)
 	return 0;
 }
 
+static void tg3_get_channels(struct net_device *dev,
+			     struct ethtool_channels *channel)
+{
+	struct tg3 *tp = netdev_priv(dev);
+	u32 deflt_qs = netif_get_num_default_rss_queues();
+
+	channel->max_rx = tp->rxq_max;
+	channel->max_tx = tp->txq_max;
+
+	if (netif_running(dev)) {
+		channel->rx_count = tp->rxq_cnt;
+		channel->tx_count = tp->txq_cnt;
+	} else {
+		if (tp->rxq_req)
+			channel->rx_count = tp->rxq_req;
+		else
+			channel->rx_count = min(deflt_qs, tp->rxq_max);
+
+		if (tp->txq_req)
+			channel->tx_count = tp->txq_req;
+		else
+			channel->tx_count = min(deflt_qs, tp->txq_max);
+	}
+}
+
+static int tg3_set_channels(struct net_device *dev,
+			    struct ethtool_channels *channel)
+{
+	struct tg3 *tp = netdev_priv(dev);
+
+	if (!tg3_flag(tp, SUPPORT_MSIX))
+		return -EOPNOTSUPP;
+
+	if (channel->rx_count > tp->rxq_max ||
+	    channel->tx_count > tp->txq_max)
+		return -EINVAL;
+
+	tp->rxq_req = channel->rx_count;
+	tp->txq_req = channel->tx_count;
+
+	if (!netif_running(dev))
+		return 0;
+
+	tg3_stop(tp);
+
+	netif_carrier_off(dev);
+
+	tg3_start(tp, true, false);
+
+	return 0;
+}
+
 static void tg3_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 {
 	switch (stringset) {
@@ -12494,6 +12660,8 @@ static const struct ethtool_ops tg3_ethtool_ops = {
 	.get_rxfh_indir_size    = tg3_get_rxfh_indir_size,
 	.get_rxfh_indir		= tg3_get_rxfh_indir,
 	.set_rxfh_indir		= tg3_set_rxfh_indir,
+	.get_channels		= tg3_get_channels,
+	.set_channels		= tg3_set_channels,
 	.get_ts_info		= ethtool_op_get_ts_info,
 };
 
@@ -14510,10 +14678,20 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 		if (tg3_flag(tp, 57765_PLUS)) {
 			tg3_flag_set(tp, SUPPORT_MSIX);
 			tp->irq_max = TG3_IRQ_MAX_VECS;
-			tg3_rss_init_dflt_indir_tbl(tp);
 		}
 	}
 
+	tp->txq_max = 1;
+	tp->rxq_max = 1;
+	if (tp->irq_max > 1) {
+		tp->rxq_max = TG3_RSS_MAX_NUM_QS;
+		tg3_rss_init_dflt_indir_tbl(tp, TG3_RSS_MAX_NUM_QS);
+
+		if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
+		    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720)
+			tp->txq_max = tp->irq_max - 1;
+	}
+
 	if (tg3_flag(tp, 5755_PLUS) ||
 	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
 		tg3_flag_set(tp, SHORT_DMA_BUG);
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 6d52cb286826..d9308c32102e 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2860,7 +2860,8 @@ struct tg3_rx_prodring_set {
 	dma_addr_t			rx_jmb_mapping;
 };
 
-#define TG3_IRQ_MAX_VECS_RSS		5
+#define TG3_RSS_MAX_NUM_QS		4
+#define TG3_IRQ_MAX_VECS_RSS		(TG3_RSS_MAX_NUM_QS + 1)
 #define TG3_IRQ_MAX_VECS		TG3_IRQ_MAX_VECS_RSS
 
 struct tg3_napi {
@@ -3037,6 +3038,9 @@ struct tg3 {
 	void				(*write32_tx_mbox) (struct tg3 *, u32,
 							    u32);
 	u32				dma_limit;
+	u32				txq_req;
+	u32				txq_cnt;
+	u32				txq_max;
 
 	/* begin "rx thread" cacheline section */
 	struct tg3_napi			napi[TG3_IRQ_MAX_VECS];
@@ -3051,6 +3055,9 @@ struct tg3 {
 	u32				rx_std_max_post;
 	u32				rx_offset;
 	u32				rx_pkt_map_sz;
+	u32				rxq_req;
+	u32				rxq_cnt;
+	u32				rxq_max;
 	bool				rx_refill;
 
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index b441f33258e7..ce1eac529470 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3268,6 +3268,7 @@ bnad_pci_probe(struct pci_dev *pdev,
 	 *	Output : using_dac = 1 for 64 bit DMA
 	 *			   = 0 for 32 bit DMA
 	 */
+	using_dac = false;
 	err = bnad_pci_init(bnad, pdev, &using_dac);
 	if (err)
 		goto unlock_mutex;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index ec2dafe8ae5b..745a1f53361f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -67,12 +67,12 @@ enum {
 };
 
 enum {
-	MEMWIN0_APERTURE = 65536,
-	MEMWIN0_BASE     = 0x30000,
+	MEMWIN0_APERTURE = 2048,
+	MEMWIN0_BASE     = 0x1b800,
 	MEMWIN1_APERTURE = 32768,
 	MEMWIN1_BASE     = 0x28000,
-	MEMWIN2_APERTURE = 2048,
-	MEMWIN2_BASE     = 0x1b800,
+	MEMWIN2_APERTURE = 65536,
+	MEMWIN2_BASE     = 0x30000,
 };
 
 enum dev_master {
@@ -211,6 +211,9 @@ struct tp_err_stats {
 struct tp_params {
 	unsigned int ntxchan;        /* # of Tx channels */
 	unsigned int tre;            /* log2 of core clocks per TP tick */
+
+	uint32_t dack_re;            /* DACK timer resolution */
+	unsigned short tx_modq[NCHAN];	/* channel to modulation queue map */
 };
 
 struct vpd_params {
@@ -315,6 +318,10 @@ enum {                                 /* adapter flags */
 	USING_MSI          = (1 << 1),
 	USING_MSIX         = (1 << 2),
 	FW_OK              = (1 << 4),
+	RSS_TNLALLLOOKUP   = (1 << 5),
+	USING_SOFT_PARAMS  = (1 << 6),
+	MASTER_PF          = (1 << 7),
+	FW_OFLD_CONN       = (1 << 9),
 };
 
 struct rx_sw_desc;
@@ -467,6 +474,11 @@ struct sge {
 	u16 rdma_rxq[NCHAN];
 	u16 timer_val[SGE_NTIMERS];
 	u8 counter_val[SGE_NCOUNTERS];
+	u32 fl_pg_order;            /* large page allocation size */
+	u32 stat_len;               /* length of status page at ring end */
+	u32 pktshift;               /* padding between CPL & packet data */
+	u32 fl_align;               /* response queue message alignment */
+	u32 fl_starve_thres;        /* Free List starvation threshold */
 	unsigned int starve_thres;
 	u8 idma_state[2];
 	unsigned int egr_start;
@@ -511,6 +523,8 @@ struct adapter {
 	struct net_device *port[MAX_NPORTS];
 	u8 chan_map[NCHAN];                   /* channel -> port map */
 
+	unsigned int l2t_start;
+	unsigned int l2t_end;
 	struct l2t_data *l2t;
 	void *uld_handle[CXGB4_ULD_MAX];
 	struct list_head list_node;
@@ -619,7 +633,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 			  struct net_device *dev, unsigned int iqid);
 irqreturn_t t4_sge_intr_msix(int irq, void *cookie);
-void t4_sge_init(struct adapter *adap);
+int t4_sge_init(struct adapter *adap);
 void t4_sge_start(struct adapter *adap);
 void t4_sge_stop(struct adapter *adap);
 extern int dbfifo_int_thresh;
@@ -638,6 +652,14 @@ static inline unsigned int us_to_core_ticks(const struct adapter *adap,
 	return (us * adap->params.vpd.cclk) / 1000;
 }
 
+static inline unsigned int core_ticks_to_us(const struct adapter *adapter,
+					    unsigned int ticks)
+{
+	/* add Core Clock / 2 to round ticks to nearest uS */
+	return ((ticks * 1000 + adapter->params.vpd.cclk/2) /
+		adapter->params.vpd.cclk);
+}
+
 void t4_set_reg_field(struct adapter *adap, unsigned int addr, u32 mask,
 		      u32 val);
 
@@ -656,6 +678,9 @@ static inline int t4_wr_mbox_ns(struct adapter *adap, int mbox, const void *cmd,
 	return t4_wr_mbox_meat(adap, mbox, cmd, size, rpl, false);
 }
 
+void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
+		       unsigned int data_reg, const u32 *vals,
+		       unsigned int nregs, unsigned int start_idx);
 void t4_intr_enable(struct adapter *adapter);
 void t4_intr_disable(struct adapter *adapter);
 int t4_slow_intr_handler(struct adapter *adapter);
@@ -664,8 +689,12 @@ int t4_wait_dev_ready(struct adapter *adap);
 int t4_link_start(struct adapter *adap, unsigned int mbox, unsigned int port,
 		  struct link_config *lc);
 int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port);
+int t4_memory_write(struct adapter *adap, int mtype, u32 addr, u32 len,
+		    __be32 *buf);
 int t4_seeprom_wp(struct adapter *adapter, bool enable);
+int get_vpd_params(struct adapter *adapter, struct vpd_params *p);
 int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
+unsigned int t4_flash_cfg_addr(struct adapter *adapter);
 int t4_check_fw_version(struct adapter *adapter);
 int t4_prep_adapter(struct adapter *adapter);
 int t4_port_init(struct adapter *adap, int mbox, int pf, int vf);
@@ -680,6 +709,8 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data,
 
 void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p);
 void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log);
+void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr,
+			    unsigned int mask, unsigned int val);
 void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 			 struct tp_tcp_stats *v6);
 void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
@@ -695,6 +726,16 @@ int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox,
 int t4_fw_bye(struct adapter *adap, unsigned int mbox);
 int t4_early_init(struct adapter *adap, unsigned int mbox);
 int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset);
+int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force);
+int t4_fw_restart(struct adapter *adap, unsigned int mbox, int reset);
+int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
+		  const u8 *fw_data, unsigned int size, int force);
+int t4_fw_config_file(struct adapter *adap, unsigned int mbox,
+		      unsigned int mtype, unsigned int maddr,
+		      u32 *finiver, u32 *finicsum, u32 *cfcsum);
+int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
+			  unsigned int cache_line_size);
+int t4_fw_initialize(struct adapter *adap, unsigned int mbox);
 int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int nparams, const u32 *params,
 		    u32 *val);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 933985420acb..6b9f6bb2f7ed 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -78,28 +78,45 @@
  */
 #define MAX_SGE_TIMERVAL 200U
 
-#ifdef CONFIG_PCI_IOV
-/*
- * Virtual Function provisioning constants.  We need two extra Ingress Queues
- * with Interrupt capability to serve as the VF's Firmware Event Queue and
- * Forwarded Interrupt Queue (when using MSI mode) -- neither will have Free
- * Lists associated with them).  For each Ethernet/Control Egress Queue and
- * for each Free List, we need an Egress Context.
- */
 enum {
+	/*
+	 * Physical Function provisioning constants.
+	 */
+	PFRES_NVI = 4,			/* # of Virtual Interfaces */
+	PFRES_NETHCTRL = 128,		/* # of EQs used for ETH or CTRL Qs */
+	PFRES_NIQFLINT = 128,		/* # of ingress Qs/w Free List(s)/intr
+					 */
+	PFRES_NEQ = 256,		/* # of egress queues */
+	PFRES_NIQ = 0,			/* # of ingress queues */
+	PFRES_TC = 0,			/* PCI-E traffic class */
+	PFRES_NEXACTF = 128,		/* # of exact MPS filters */
+
+	PFRES_R_CAPS = FW_CMD_CAP_PF,
+	PFRES_WX_CAPS = FW_CMD_CAP_PF,
+
+#ifdef CONFIG_PCI_IOV
+	/*
+	 * Virtual Function provisioning constants.  We need two extra Ingress
+	 * Queues with Interrupt capability to serve as the VF's Firmware
+	 * Event Queue and Forwarded Interrupt Queue (when using MSI mode) --
+	 * neither will have Free Lists associated with them).  For each
+	 * Ethernet/Control Egress Queue and for each Free List, we need an
+	 * Egress Context.
+	 */
 	VFRES_NPORTS = 1,		/* # of "ports" per VF */
 	VFRES_NQSETS = 2,		/* # of "Queue Sets" per VF */
 
 	VFRES_NVI = VFRES_NPORTS,	/* # of Virtual Interfaces */
 	VFRES_NETHCTRL = VFRES_NQSETS,	/* # of EQs used for ETH or CTRL Qs */
 	VFRES_NIQFLINT = VFRES_NQSETS+2,/* # of ingress Qs/w Free List(s)/intr */
-	VFRES_NIQ = 0,			/* # of non-fl/int ingress queues */
 	VFRES_NEQ = VFRES_NQSETS*2,	/* # of egress queues */
+	VFRES_NIQ = 0,			/* # of non-fl/int ingress queues */
 	VFRES_TC = 0,			/* PCI-E traffic class */
 	VFRES_NEXACTF = 16,		/* # of exact MPS filters */
 
 	VFRES_R_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF|FW_CMD_CAP_PORT,
 	VFRES_WX_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF,
+#endif
 };
 
 /*
@@ -146,7 +163,6 @@ static unsigned int pfvfres_pmask(struct adapter *adapter,
 	}
 	/*NOTREACHED*/
 }
-#endif
 
 enum {
 	MAX_TXQ_ENTRIES      = 16384,
@@ -193,6 +209,7 @@ static DEFINE_PCI_DEVICE_TABLE(cxgb4_pci_tbl) = {
 };
 
 #define FW_FNAME "cxgb4/t4fw.bin"
+#define FW_CFNAME "cxgb4/t4-config.txt"
 
 MODULE_DESCRIPTION(DRV_DESC);
 MODULE_AUTHOR("Chelsio Communications");
@@ -201,6 +218,28 @@ MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl);
 MODULE_FIRMWARE(FW_FNAME);
 
+/*
+ * Normally we're willing to become the firmware's Master PF but will be happy
+ * if another PF has already become the Master and initialized the adapter.
+ * Setting "force_init" will cause this driver to forcibly establish itself as
+ * the Master PF and initialize the adapter.
+ */
+static uint force_init;
+
+module_param(force_init, uint, 0644);
+MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter");
+
+/*
+ * Normally if the firmware we connect to has Configuration File support, we
+ * use that and only fall back to the old Driver-based initialization if the
+ * Configuration File fails for some reason.  If force_old_init is set, then
+ * we'll always use the old Driver-based initialization sequence.
+ */
+static uint force_old_init;
+
+module_param(force_old_init, uint, 0644);
+MODULE_PARM_DESC(force_old_init, "Force old initialization sequence");
+
 static int dflt_msg_enable = DFLT_MSG_ENABLE;
 
 module_param(dflt_msg_enable, int, 0644);
@@ -236,6 +275,20 @@ module_param_array(intr_cnt, uint, NULL, 0644);
 MODULE_PARM_DESC(intr_cnt,
 		 "thresholds 1..3 for queue interrupt packet counters");
 
+/*
+ * Normally we tell the chip to deliver Ingress Packets into our DMA buffers
+ * offset by 2 bytes in order to have the IP headers line up on 4-byte
+ * boundaries.  This is a requirement for many architectures which will throw
+ * a machine check fault if an attempt is made to access one of the 4-byte IP
+ * header fields on a non-4-byte boundary.  And it's a major performance issue
+ * even on some architectures which allow it like some implementations of the
+ * x86 ISA.  However, some architectures don't mind this and for some very
+ * edge-case performance sensitive applications (like forwarding large volumes
+ * of small packets), setting this DMA offset to 0 will decrease the number of
+ * PCI-E Bus transfers enough to measurably affect performance.
+ */
+static int rx_dma_offset = 2;
+
 static bool vf_acls;
 
 #ifdef CONFIG_PCI_IOV
@@ -248,6 +301,30 @@ module_param_array(num_vf, uint, NULL, 0644);
 MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3");
 #endif
 
+/*
+ * The filter TCAM has a fixed portion and a variable portion.  The fixed
+ * portion can match on source/destination IP IPv4/IPv6 addresses and TCP/UDP
+ * ports.  The variable portion is 36 bits which can include things like Exact
+ * Match MAC Index (9 bits), Ether Type (16 bits), IP Protocol (8 bits),
+ * [Inner] VLAN Tag (17 bits), etc. which, if all were somehow selected, would
+ * far exceed the 36-bit budget for this "compressed" header portion of the
+ * filter.  Thus, we have a scarce resource which must be carefully managed.
+ *
+ * By default we set this up to mostly match the set of filter matching
+ * capabilities of T3 but with accommodations for some of T4's more
+ * interesting features:
+ *
+ *   { IP Fragment (1), MPS Match Type (3), IP Protocol (8),
+ *     [Inner] VLAN (17), Port (3), FCoE (1) }
+ */
+enum {
+	TP_VLAN_PRI_MAP_DEFAULT = HW_TPL_FR_MT_PR_IV_P_FC,
+	TP_VLAN_PRI_MAP_FIRST = FCOE_SHIFT,
+	TP_VLAN_PRI_MAP_LAST = FRAGMENTATION_SHIFT,
+};
+
+static unsigned int tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT;
+
 static struct dentry *cxgb4_debugfs_root;
 
 static LIST_HEAD(adapter_list);
@@ -852,11 +929,25 @@ static int upgrade_fw(struct adapter *adap)
 	 */
 	if (FW_HDR_FW_VER_MAJOR_GET(adap->params.fw_vers) != FW_VERSION_MAJOR ||
 	    vers > adap->params.fw_vers) {
-		ret = -t4_load_fw(adap, fw->data, fw->size);
+		dev_info(dev, "upgrading firmware ...\n");
+		ret = t4_fw_upgrade(adap, adap->mbox, fw->data, fw->size,
+				    /*force=*/false);
 		if (!ret)
-			dev_info(dev, "firmware upgraded to version %pI4 from "
-				 FW_FNAME "\n", &hdr->fw_ver);
+			dev_info(dev, "firmware successfully upgraded to "
+				 FW_FNAME " (%d.%d.%d.%d)\n",
+				 FW_HDR_FW_VER_MAJOR_GET(vers),
+				 FW_HDR_FW_VER_MINOR_GET(vers),
+				 FW_HDR_FW_VER_MICRO_GET(vers),
+				 FW_HDR_FW_VER_BUILD_GET(vers));
+		else
+			dev_err(dev, "firmware upgrade failed! err=%d\n", -ret);
+	} else {
+		/*
+		 * Tell our caller that we didn't upgrade the firmware.
+		 */
+		ret = -EINVAL;
 	}
+
 out:	release_firmware(fw);
 	return ret;
 }
@@ -2470,8 +2561,8 @@ int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx,
 		else
 			delta = size - hw_pidx + pidx;
 		wmb();
-		t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL),
-			     V_QID(qid) | V_PIDX(delta));
+		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL),
+			     QID(qid) | PIDX(delta));
 	}
 out:
 	return ret;
@@ -2579,8 +2670,8 @@ static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q)
 		else
 			delta = q->size - hw_pidx + q->db_pidx;
 		wmb();
-		t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL),
-				V_QID(q->cntxt_id) | V_PIDX(delta));
+		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL),
+			     QID(q->cntxt_id) | PIDX(delta));
 	}
 out:
 	q->db_disabled = 0;
@@ -2617,9 +2708,9 @@ static void process_db_full(struct work_struct *work)
 
 	notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
 	drain_db_fifo(adap, dbfifo_drain_delay);
-	t4_set_reg_field(adap, A_SGE_INT_ENABLE3,
-			F_DBFIFO_HP_INT | F_DBFIFO_LP_INT,
-			F_DBFIFO_HP_INT | F_DBFIFO_LP_INT);
+	t4_set_reg_field(adap, SGE_INT_ENABLE3,
+			 DBFIFO_HP_INT | DBFIFO_LP_INT,
+			 DBFIFO_HP_INT | DBFIFO_LP_INT);
 	notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
 }
 
@@ -2639,8 +2730,8 @@ static void process_db_drop(struct work_struct *work)
 
 void t4_db_full(struct adapter *adap)
 {
-	t4_set_reg_field(adap, A_SGE_INT_ENABLE3,
-			F_DBFIFO_HP_INT | F_DBFIFO_LP_INT, 0);
+	t4_set_reg_field(adap, SGE_INT_ENABLE3,
+			 DBFIFO_HP_INT | DBFIFO_LP_INT, 0);
 	queue_work(workq, &adap->db_full_task);
 }
 
@@ -3076,6 +3167,10 @@ static void setup_memwin(struct adapter *adap)
 	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN, 2),
 		     (bar0 + MEMWIN2_BASE) | BIR(0) |
 		     WINDOW(ilog2(MEMWIN2_APERTURE) - 10));
+}
+
+static void setup_memwin_rdma(struct adapter *adap)
+{
 	if (adap->vres.ocq.size) {
 		unsigned int start, sz_kb;
 
@@ -3155,6 +3250,488 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 
 /*
  * Phase 0 of initialization: contact FW, obtain config, perform basic init.
+ *
+ * If the firmware we're dealing with has Configuration File support, then
+ * we use that to perform all configuration
+ */
+
+/*
+ * Tweak configuration based on module parameters, etc.  Most of these have
+ * defaults assigned to them by Firmware Configuration Files (if we're using
+ * them) but need to be explicitly set if we're using hard-coded
+ * initialization.  But even in the case of using Firmware Configuration
+ * Files, we'd like to expose the ability to change these via module
+ * parameters so these are essentially common tweaks/settings for
+ * Configuration Files and hard-coded initialization ...
+ */
+static int adap_init0_tweaks(struct adapter *adapter)
+{
+	/*
+	 * Fix up various Host-Dependent Parameters like Page Size, Cache
+	 * Line Size, etc.  The firmware default is for a 4KB Page Size and
+	 * 64B Cache Line Size ...
+	 */
+	t4_fixup_host_params(adapter, PAGE_SIZE, L1_CACHE_BYTES);
+
+	/*
+	 * Process module parameters which affect early initialization.
+	 */
+	if (rx_dma_offset != 2 && rx_dma_offset != 0) {
+		dev_err(&adapter->pdev->dev,
+			"Ignoring illegal rx_dma_offset=%d, using 2\n",
+			rx_dma_offset);
+		rx_dma_offset = 2;
+	}
+	t4_set_reg_field(adapter, SGE_CONTROL,
+			 PKTSHIFT_MASK,
+			 PKTSHIFT(rx_dma_offset));
+
+	/*
+	 * Don't include the "IP Pseudo Header" in CPL_RX_PKT checksums: Linux
+	 * adds the pseudo header itself.
+	 */
+	t4_tp_wr_bits_indirect(adapter, TP_INGRESS_CONFIG,
+			       CSUM_HAS_PSEUDO_HDR, 0);
+
+	return 0;
+}
+
+/*
+ * Attempt to initialize the adapter via a Firmware Configuration File.
+ */
+static int adap_init0_config(struct adapter *adapter, int reset)
+{
+	struct fw_caps_config_cmd caps_cmd;
+	const struct firmware *cf;
+	unsigned long mtype = 0, maddr = 0;
+	u32 finiver, finicsum, cfcsum;
+	int ret, using_flash;
+
+	/*
+	 * Reset device if necessary.
+	 */
+	if (reset) {
+		ret = t4_fw_reset(adapter, adapter->mbox,
+				  PIORSTMODE | PIORST);
+		if (ret < 0)
+			goto bye;
+	}
+
+	/*
+	 * If we have a T4 configuration file under /lib/firmware/cxgb4/,
+	 * then use that.  Otherwise, use the configuration file stored
+	 * in the adapter flash ...
+	 */
+	ret = request_firmware(&cf, FW_CFNAME, adapter->pdev_dev);
+	if (ret < 0) {
+		using_flash = 1;
+		mtype = FW_MEMTYPE_CF_FLASH;
+		maddr = t4_flash_cfg_addr(adapter);
+	} else {
+		u32 params[7], val[7];
+
+		using_flash = 0;
+		if (cf->size >= FLASH_CFG_MAX_SIZE)
+			ret = -ENOMEM;
+		else {
+			params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) |
+			     FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF));
+			ret = t4_query_params(adapter, adapter->mbox,
+					      adapter->fn, 0, 1, params, val);
+			if (ret == 0) {
+				/*
+				 * For t4_memory_write() below addresses and
+				 * sizes have to be in terms of multiples of 4
+				 * bytes.  So, if the Configuration File isn't
+				 * a multiple of 4 bytes in length we'll have
+				 * to write that out separately since we can't
+				 * guarantee that the bytes following the
+				 * residual byte in the buffer returned by
+				 * request_firmware() are zeroed out ...
+				 */
+				size_t resid = cf->size & 0x3;
+				size_t size = cf->size & ~0x3;
+				__be32 *data = (__be32 *)cf->data;
+
+				mtype = FW_PARAMS_PARAM_Y_GET(val[0]);
+				maddr = FW_PARAMS_PARAM_Z_GET(val[0]) << 16;
+
+				ret = t4_memory_write(adapter, mtype, maddr,
+						      size, data);
+				if (ret == 0 && resid != 0) {
+					union {
+						__be32 word;
+						char buf[4];
+					} last;
+					int i;
+
+					last.word = data[size >> 2];
+					for (i = resid; i < 4; i++)
+						last.buf[i] = 0;
+					ret = t4_memory_write(adapter, mtype,
+							      maddr + size,
+							      4, &last.word);
+				}
+			}
+		}
+
+		release_firmware(cf);
+		if (ret)
+			goto bye;
+	}
+
+	/*
+	 * Issue a Capability Configuration command to the firmware to get it
+	 * to parse the Configuration File.  We don't use t4_fw_config_file()
+	 * because we want the ability to modify various features after we've
+	 * processed the configuration file ...
+	 */
+	memset(&caps_cmd, 0, sizeof(caps_cmd));
+	caps_cmd.op_to_write =
+		htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+		      FW_CMD_REQUEST |
+		      FW_CMD_READ);
+	caps_cmd.retval_len16 =
+		htonl(FW_CAPS_CONFIG_CMD_CFVALID |
+		      FW_CAPS_CONFIG_CMD_MEMTYPE_CF(mtype) |
+		      FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(maddr >> 16) |
+		      FW_LEN16(caps_cmd));
+	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
+			 &caps_cmd);
+	if (ret < 0)
+		goto bye;
+
+	finiver = ntohl(caps_cmd.finiver);
+	finicsum = ntohl(caps_cmd.finicsum);
+	cfcsum = ntohl(caps_cmd.cfcsum);
+	if (finicsum != cfcsum)
+		dev_warn(adapter->pdev_dev, "Configuration File checksum "\
+			 "mismatch: [fini] csum=%#x, computed csum=%#x\n",
+			 finicsum, cfcsum);
+
+	/*
+	 * If we're a pure NIC driver then disable all offloading facilities.
+	 * This will allow the firmware to optimize aspects of the hardware
+	 * configuration which will result in improved performance.
+	 */
+	caps_cmd.ofldcaps = 0;
+	caps_cmd.iscsicaps = 0;
+	caps_cmd.rdmacaps = 0;
+	caps_cmd.fcoecaps = 0;
+
+	/*
+	 * And now tell the firmware to use the configuration we just loaded.
+	 */
+	caps_cmd.op_to_write =
+		htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+		      FW_CMD_REQUEST |
+		      FW_CMD_WRITE);
+	caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd));
+	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
+			 NULL);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Tweak configuration based on system architecture, module
+	 * parameters, etc.
+	 */
+	ret = adap_init0_tweaks(adapter);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * And finally tell the firmware to initialize itself using the
+	 * parameters from the Configuration File.
+	 */
+	ret = t4_fw_initialize(adapter, adapter->mbox);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Return successfully and note that we're operating with parameters
+	 * not supplied by the driver, rather than from hard-wired
+	 * initialization constants burried in the driver.
+	 */
+	adapter->flags |= USING_SOFT_PARAMS;
+	dev_info(adapter->pdev_dev, "Successfully configured using Firmware "\
+		 "Configuration File %s, version %#x, computed checksum %#x\n",
+		 (using_flash
+		  ? "in device FLASH"
+		  : "/lib/firmware/" FW_CFNAME),
+		 finiver, cfcsum);
+	return 0;
+
+	/*
+	 * Something bad happened.  Return the error ...  (If the "error"
+	 * is that there's no Configuration File on the adapter we don't
+	 * want to issue a warning since this is fairly common.)
+	 */
+bye:
+	if (ret != -ENOENT)
+		dev_warn(adapter->pdev_dev, "Configuration file error %d\n",
+			 -ret);
+	return ret;
+}
+
+/*
+ * Attempt to initialize the adapter via hard-coded, driver supplied
+ * parameters ...
+ */
+static int adap_init0_no_config(struct adapter *adapter, int reset)
+{
+	struct sge *s = &adapter->sge;
+	struct fw_caps_config_cmd caps_cmd;
+	u32 v;
+	int i, ret;
+
+	/*
+	 * Reset device if necessary
+	 */
+	if (reset) {
+		ret = t4_fw_reset(adapter, adapter->mbox,
+				  PIORSTMODE | PIORST);
+		if (ret < 0)
+			goto bye;
+	}
+
+	/*
+	 * Get device capabilities and select which we'll be using.
+	 */
+	memset(&caps_cmd, 0, sizeof(caps_cmd));
+	caps_cmd.op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+				     FW_CMD_REQUEST | FW_CMD_READ);
+	caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd));
+	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
+			 &caps_cmd);
+	if (ret < 0)
+		goto bye;
+
+#ifndef CONFIG_CHELSIO_T4_OFFLOAD
+	/*
+	 * If we're a pure NIC driver then disable all offloading facilities.
+	 * This will allow the firmware to optimize aspects of the hardware
+	 * configuration which will result in improved performance.
+	 */
+	caps_cmd.ofldcaps = 0;
+	caps_cmd.iscsicaps = 0;
+	caps_cmd.rdmacaps = 0;
+	caps_cmd.fcoecaps = 0;
+#endif
+
+	if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_VM)) {
+		if (!vf_acls)
+			caps_cmd.niccaps ^= htons(FW_CAPS_CONFIG_NIC_VM);
+		else
+			caps_cmd.niccaps = htons(FW_CAPS_CONFIG_NIC_VM);
+	} else if (vf_acls) {
+		dev_err(adapter->pdev_dev, "virtualization ACLs not supported");
+		goto bye;
+	}
+	caps_cmd.op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+			      FW_CMD_REQUEST | FW_CMD_WRITE);
+	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
+			 NULL);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Tweak configuration based on system architecture, module
+	 * parameters, etc.
+	 */
+	ret = adap_init0_tweaks(adapter);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Select RSS Global Mode we want to use.  We use "Basic Virtual"
+	 * mode which maps each Virtual Interface to its own section of
+	 * the RSS Table and we turn on all map and hash enables ...
+	 */
+	adapter->flags |= RSS_TNLALLLOOKUP;
+	ret = t4_config_glbl_rss(adapter, adapter->mbox,
+				 FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL,
+				 FW_RSS_GLB_CONFIG_CMD_TNLMAPEN |
+				 FW_RSS_GLB_CONFIG_CMD_HASHTOEPLITZ |
+				 ((adapter->flags & RSS_TNLALLLOOKUP) ?
+					FW_RSS_GLB_CONFIG_CMD_TNLALLLKP : 0));
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Set up our own fundamental resource provisioning ...
+	 */
+	ret = t4_cfg_pfvf(adapter, adapter->mbox, adapter->fn, 0,
+			  PFRES_NEQ, PFRES_NETHCTRL,
+			  PFRES_NIQFLINT, PFRES_NIQ,
+			  PFRES_TC, PFRES_NVI,
+			  FW_PFVF_CMD_CMASK_MASK,
+			  pfvfres_pmask(adapter, adapter->fn, 0),
+			  PFRES_NEXACTF,
+			  PFRES_R_CAPS, PFRES_WX_CAPS);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Perform low level SGE initialization.  We need to do this before we
+	 * send the firmware the INITIALIZE command because that will cause
+	 * any other PF Drivers which are waiting for the Master
+	 * Initialization to proceed forward.
+	 */
+	for (i = 0; i < SGE_NTIMERS - 1; i++)
+		s->timer_val[i] = min(intr_holdoff[i], MAX_SGE_TIMERVAL);
+	s->timer_val[SGE_NTIMERS - 1] = MAX_SGE_TIMERVAL;
+	s->counter_val[0] = 1;
+	for (i = 1; i < SGE_NCOUNTERS; i++)
+		s->counter_val[i] = min(intr_cnt[i - 1],
+					THRESHOLD_0_GET(THRESHOLD_0_MASK));
+	t4_sge_init(adapter);
+
+#ifdef CONFIG_PCI_IOV
+	/*
+	 * Provision resource limits for Virtual Functions.  We currently
+	 * grant them all the same static resource limits except for the Port
+	 * Access Rights Mask which we're assigning based on the PF.  All of
+	 * the static provisioning stuff for both the PF and VF really needs
+	 * to be managed in a persistent manner for each device which the
+	 * firmware controls.
+	 */
+	{
+		int pf, vf;
+
+		for (pf = 0; pf < ARRAY_SIZE(num_vf); pf++) {
+			if (num_vf[pf] <= 0)
+				continue;
+
+			/* VF numbering starts at 1! */
+			for (vf = 1; vf <= num_vf[pf]; vf++) {
+				ret = t4_cfg_pfvf(adapter, adapter->mbox,
+						  pf, vf,
+						  VFRES_NEQ, VFRES_NETHCTRL,
+						  VFRES_NIQFLINT, VFRES_NIQ,
+						  VFRES_TC, VFRES_NVI,
+						  FW_PFVF_CMD_CMASK_GET(
+						  FW_PFVF_CMD_CMASK_MASK),
+						  pfvfres_pmask(
+						  adapter, pf, vf),
+						  VFRES_NEXACTF,
+						  VFRES_R_CAPS, VFRES_WX_CAPS);
+				if (ret < 0)
+					dev_warn(adapter->pdev_dev,
+						 "failed to "\
+						 "provision pf/vf=%d/%d; "
+						 "err=%d\n", pf, vf, ret);
+			}
+		}
+	}
+#endif
+
+	/*
+	 * Set up the default filter mode.  Later we'll want to implement this
+	 * via a firmware command, etc. ...  This needs to be done before the
+	 * firmare initialization command ...  If the selected set of fields
+	 * isn't equal to the default value, we'll need to make sure that the
+	 * field selections will fit in the 36-bit budget.
+	 */
+	if (tp_vlan_pri_map != TP_VLAN_PRI_MAP_DEFAULT) {
+		int i, bits = 0;
+
+		for (i = TP_VLAN_PRI_MAP_FIRST; i <= TP_VLAN_PRI_MAP_LAST; i++)
+			switch (tp_vlan_pri_map & (1 << i)) {
+			case 0:
+				/* compressed filter field not enabled */
+				break;
+			case FCOE_MASK:
+				bits +=  1;
+				break;
+			case PORT_MASK:
+				bits +=  3;
+				break;
+			case VNIC_ID_MASK:
+				bits += 17;
+				break;
+			case VLAN_MASK:
+				bits += 17;
+				break;
+			case TOS_MASK:
+				bits +=  8;
+				break;
+			case PROTOCOL_MASK:
+				bits +=  8;
+				break;
+			case ETHERTYPE_MASK:
+				bits += 16;
+				break;
+			case MACMATCH_MASK:
+				bits +=  9;
+				break;
+			case MPSHITTYPE_MASK:
+				bits +=  3;
+				break;
+			case FRAGMENTATION_MASK:
+				bits +=  1;
+				break;
+			}
+
+		if (bits > 36) {
+			dev_err(adapter->pdev_dev,
+				"tp_vlan_pri_map=%#x needs %d bits > 36;"\
+				" using %#x\n", tp_vlan_pri_map, bits,
+				TP_VLAN_PRI_MAP_DEFAULT);
+			tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT;
+		}
+	}
+	v = tp_vlan_pri_map;
+	t4_write_indirect(adapter, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, TP_VLAN_PRI_MAP);
+
+	/*
+	 * We need Five Tuple Lookup mode to be set in TP_GLOBAL_CONFIG order
+	 * to support any of the compressed filter fields above.  Newer
+	 * versions of the firmware do this automatically but it doesn't hurt
+	 * to set it here.  Meanwhile, we do _not_ need to set Lookup Every
+	 * Packet in TP_INGRESS_CONFIG to support matching non-TCP packets
+	 * since the firmware automatically turns this on and off when we have
+	 * a non-zero number of filters active (since it does have a
+	 * performance impact).
+	 */
+	if (tp_vlan_pri_map)
+		t4_set_reg_field(adapter, TP_GLOBAL_CONFIG,
+				 FIVETUPLELOOKUP_MASK,
+				 FIVETUPLELOOKUP_MASK);
+
+	/*
+	 * Tweak some settings.
+	 */
+	t4_write_reg(adapter, TP_SHIFT_CNT, SYNSHIFTMAX(6) |
+		     RXTSHIFTMAXR1(4) | RXTSHIFTMAXR2(15) |
+		     PERSHIFTBACKOFFMAX(8) | PERSHIFTMAX(8) |
+		     KEEPALIVEMAXR1(4) | KEEPALIVEMAXR2(9));
+
+	/*
+	 * Get basic stuff going by issuing the Firmware Initialize command.
+	 * Note that this _must_ be after all PFVF commands ...
+	 */
+	ret = t4_fw_initialize(adapter, adapter->mbox);
+	if (ret < 0)
+		goto bye;
+
+	/*
+	 * Return successfully!
+	 */
+	dev_info(adapter->pdev_dev, "Successfully configured using built-in "\
+		 "driver parameters\n");
+	return 0;
+
+	/*
+	 * Something bad happened.  Return the error ...
+	 */
+bye:
+	return ret;
+}
+
+/*
+ * Phase 0 of initialization: contact FW, obtain config, perform basic init.
  */
 static int adap_init0(struct adapter *adap)
 {
@@ -3162,72 +3739,216 @@ static int adap_init0(struct adapter *adap)
 	u32 v, port_vec;
 	enum dev_state state;
 	u32 params[7], val[7];
-	struct fw_caps_config_cmd c;
-
-	ret = t4_check_fw_version(adap);
-	if (ret == -EINVAL || ret > 0) {
-		if (upgrade_fw(adap) >= 0)             /* recache FW version */
-			ret = t4_check_fw_version(adap);
-	}
-	if (ret < 0)
-		return ret;
+	int reset = 1, j;
 
-	/* contact FW, request master */
-	ret = t4_fw_hello(adap, adap->fn, adap->fn, MASTER_MUST, &state);
+	/*
+	 * Contact FW, advertising Master capability (and potentially forcing
+	 * ourselves as the Master PF if our module parameter force_init is
+	 * set).
+	 */
+	ret = t4_fw_hello(adap, adap->mbox, adap->fn,
+			  force_init ? MASTER_MUST : MASTER_MAY,
+			  &state);
 	if (ret < 0) {
 		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
 			ret);
 		return ret;
 	}
+	if (ret == adap->mbox)
+		adap->flags |= MASTER_PF;
+	if (force_init && state == DEV_STATE_INIT)
+		state = DEV_STATE_UNINIT;
 
-	/* reset device */
-	ret = t4_fw_reset(adap, adap->fn, PIORSTMODE | PIORST);
-	if (ret < 0)
-		goto bye;
-
-	for (v = 0; v < SGE_NTIMERS - 1; v++)
-		adap->sge.timer_val[v] = min(intr_holdoff[v], MAX_SGE_TIMERVAL);
-	adap->sge.timer_val[SGE_NTIMERS - 1] = MAX_SGE_TIMERVAL;
-	adap->sge.counter_val[0] = 1;
-	for (v = 1; v < SGE_NCOUNTERS; v++)
-		adap->sge.counter_val[v] = min(intr_cnt[v - 1],
-					       THRESHOLD_3_MASK);
-#define FW_PARAM_DEV(param) \
-	(FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | \
-	 FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_##param))
+	/*
+	 * If we're the Master PF Driver and the device is uninitialized,
+	 * then let's consider upgrading the firmware ...  (We always want
+	 * to check the firmware version number in order to A. get it for
+	 * later reporting and B. to warn if the currently loaded firmware
+	 * is excessively mismatched relative to the driver.)
+	 */
+	ret = t4_check_fw_version(adap);
+	if ((adap->flags & MASTER_PF) && state != DEV_STATE_INIT) {
+		if (ret == -EINVAL || ret > 0) {
+			if (upgrade_fw(adap) >= 0) {
+				/*
+				 * Note that the chip was reset as part of the
+				 * firmware upgrade so we don't reset it again
+				 * below and grab the new firmware version.
+				 */
+				reset = 0;
+				ret = t4_check_fw_version(adap);
+			}
+		}
+		if (ret < 0)
+			return ret;
+	}
 
-	params[0] = FW_PARAM_DEV(CCLK);
-	ret = t4_query_params(adap, adap->fn, adap->fn, 0, 1, params, val);
+	/*
+	 * Grab VPD parameters.  This should be done after we establish a
+	 * connection to the firmware since some of the VPD parameters
+	 * (notably the Core Clock frequency) are retrieved via requests to
+	 * the firmware.  On the other hand, we need these fairly early on
+	 * so we do this right after getting ahold of the firmware.
+	 */
+	ret = get_vpd_params(adap, &adap->params.vpd);
 	if (ret < 0)
 		goto bye;
-	adap->params.vpd.cclk = val[0];
 
-	ret = adap_init1(adap, &c);
+	/*
+	 * Find out what ports are available to us.  Note that we need to do
+	 * this before calling adap_init0_no_config() since it needs nports
+	 * and portvec ...
+	 */
+	v =
+	    FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) |
+	    FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_PORTVEC);
+	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, &v, &port_vec);
 	if (ret < 0)
 		goto bye;
 
+	adap->params.nports = hweight32(port_vec);
+	adap->params.portvec = port_vec;
+
+	/*
+	 * If the firmware is initialized already (and we're not forcing a
+	 * master initialization), note that we're living with existing
+	 * adapter parameters.  Otherwise, it's time to try initializing the
+	 * adapter ...
+	 */
+	if (state == DEV_STATE_INIT) {
+		dev_info(adap->pdev_dev, "Coming up as %s: "\
+			 "Adapter already initialized\n",
+			 adap->flags & MASTER_PF ? "MASTER" : "SLAVE");
+		adap->flags |= USING_SOFT_PARAMS;
+	} else {
+		dev_info(adap->pdev_dev, "Coming up as MASTER: "\
+			 "Initializing adapter\n");
+
+		/*
+		 * If the firmware doesn't support Configuration
+		 * Files warn user and exit,
+		 */
+		if (ret < 0)
+			dev_warn(adap->pdev_dev, "Firmware doesn't support "
+				 "configuration file.\n");
+		if (force_old_init)
+			ret = adap_init0_no_config(adap, reset);
+		else {
+			/*
+			 * Find out whether we're dealing with a version of
+			 * the firmware which has configuration file support.
+			 */
+			params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) |
+				     FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF));
+			ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1,
+					      params, val);
+
+			/*
+			 * If the firmware doesn't support Configuration
+			 * Files, use the old Driver-based, hard-wired
+			 * initialization.  Otherwise, try using the
+			 * Configuration File support and fall back to the
+			 * Driver-based initialization if there's no
+			 * Configuration File found.
+			 */
+			if (ret < 0)
+				ret = adap_init0_no_config(adap, reset);
+			else {
+				/*
+				 * The firmware provides us with a memory
+				 * buffer where we can load a Configuration
+				 * File from the host if we want to override
+				 * the Configuration File in flash.
+				 */
+
+				ret = adap_init0_config(adap, reset);
+				if (ret == -ENOENT) {
+					dev_info(adap->pdev_dev,
+					    "No Configuration File present "
+					    "on adapter.  Using hard-wired "
+					    "configuration parameters.\n");
+					ret = adap_init0_no_config(adap, reset);
+				}
+			}
+		}
+		if (ret < 0) {
+			dev_err(adap->pdev_dev,
+				"could not initialize adapter, error %d\n",
+				-ret);
+			goto bye;
+		}
+	}
+
+	/*
+	 * If we're living with non-hard-coded parameters (either from a
+	 * Firmware Configuration File or values programmed by a different PF
+	 * Driver), give the SGE code a chance to pull in anything that it
+	 * needs ...  Note that this must be called after we retrieve our VPD
+	 * parameters in order to know how to convert core ticks to seconds.
+	 */
+	if (adap->flags & USING_SOFT_PARAMS) {
+		ret = t4_sge_init(adap);
+		if (ret < 0)
+			goto bye;
+	}
+
+	/*
+	 * Grab some of our basic fundamental operating parameters.
+	 */
+#define FW_PARAM_DEV(param) \
+	(FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | \
+	FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_##param))
+
 #define FW_PARAM_PFVF(param) \
-	(FW_PARAMS_MNEM(FW_PARAMS_MNEM_PFVF) | \
-	 FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_PFVF_##param) | \
-	 FW_PARAMS_PARAM_Y(adap->fn))
+	FW_PARAMS_MNEM(FW_PARAMS_MNEM_PFVF) | \
+	FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_PFVF_##param)|  \
+	FW_PARAMS_PARAM_Y(0) | \
+	FW_PARAMS_PARAM_Z(0)
 
-	params[0] = FW_PARAM_DEV(PORTVEC);
+	params[0] = FW_PARAM_PFVF(EQ_START);
 	params[1] = FW_PARAM_PFVF(L2T_START);
 	params[2] = FW_PARAM_PFVF(L2T_END);
 	params[3] = FW_PARAM_PFVF(FILTER_START);
 	params[4] = FW_PARAM_PFVF(FILTER_END);
 	params[5] = FW_PARAM_PFVF(IQFLINT_START);
-	params[6] = FW_PARAM_PFVF(EQ_START);
-	ret = t4_query_params(adap, adap->fn, adap->fn, 0, 7, params, val);
+	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, val);
 	if (ret < 0)
 		goto bye;
-	port_vec = val[0];
+	adap->sge.egr_start = val[0];
+	adap->l2t_start = val[1];
+	adap->l2t_end = val[2];
 	adap->tids.ftid_base = val[3];
 	adap->tids.nftids = val[4] - val[3] + 1;
 	adap->sge.ingr_start = val[5];
-	adap->sge.egr_start = val[6];
 
-	if (c.ofldcaps) {
+	/* query params related to active filter region */
+	params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START);
+	params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END);
+	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val);
+	/* If Active filter size is set we enable establishing
+	 * offload connection through firmware work request
+	 */
+	if ((val[0] != val[1]) && (ret >= 0)) {
+		adap->flags |= FW_OFLD_CONN;
+		adap->tids.aftid_base = val[0];
+		adap->tids.aftid_end = val[1];
+	}
+
+#ifdef CONFIG_CHELSIO_T4_OFFLOAD
+	/*
+	 * Get device capabilities so we can determine what resources we need
+	 * to manage.
+	 */
+	memset(&caps_cmd, 0, sizeof(caps_cmd));
+	caps_cmd.op_to_write = htonl(V_FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+				     FW_CMD_REQUEST | FW_CMD_READ);
+	caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd));
+	ret = t4_wr_mbox(adap, adap->mbox, &caps_cmd, sizeof(caps_cmd),
+			 &caps_cmd);
+	if (ret < 0)
+		goto bye;
+
+	if (caps_cmd.ofldcaps) {
 		/* query offload-related parameters */
 		params[0] = FW_PARAM_DEV(NTID);
 		params[1] = FW_PARAM_PFVF(SERVER_START);
@@ -3235,28 +3956,55 @@ static int adap_init0(struct adapter *adap)
 		params[3] = FW_PARAM_PFVF(TDDP_START);
 		params[4] = FW_PARAM_PFVF(TDDP_END);
 		params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ);
-		ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params,
-				      val);
+		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6,
+				      params, val);
 		if (ret < 0)
 			goto bye;
 		adap->tids.ntids = val[0];
 		adap->tids.natids = min(adap->tids.ntids / 2, MAX_ATIDS);
 		adap->tids.stid_base = val[1];
 		adap->tids.nstids = val[2] - val[1] + 1;
+		/*
+		 * Setup server filter region. Divide the availble filter
+		 * region into two parts. Regular filters get 1/3rd and server
+		 * filters get 2/3rd part. This is only enabled if workarond
+		 * path is enabled.
+		 * 1. For regular filters.
+		 * 2. Server filter: This are special filters which are used
+		 * to redirect SYN packets to offload queue.
+		 */
+		if (adap->flags & FW_OFLD_CONN && !is_bypass(adap)) {
+			adap->tids.sftid_base = adap->tids.ftid_base +
+					DIV_ROUND_UP(adap->tids.nftids, 3);
+			adap->tids.nsftids = adap->tids.nftids -
+					 DIV_ROUND_UP(adap->tids.nftids, 3);
+			adap->tids.nftids = adap->tids.sftid_base -
+						adap->tids.ftid_base;
+		}
 		adap->vres.ddp.start = val[3];
 		adap->vres.ddp.size = val[4] - val[3] + 1;
 		adap->params.ofldq_wr_cred = val[5];
+
+		params[0] = FW_PARAM_PFVF(ETHOFLD_START);
+		params[1] = FW_PARAM_PFVF(ETHOFLD_END);
+		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2,
+				      params, val);
+		if ((val[0] != val[1]) && (ret >= 0)) {
+			adap->tids.uotid_base = val[0];
+			adap->tids.nuotids = val[1] - val[0] + 1;
+		}
+
 		adap->params.offload = 1;
 	}
-	if (c.rdmacaps) {
+	if (caps_cmd.rdmacaps) {
 		params[0] = FW_PARAM_PFVF(STAG_START);
 		params[1] = FW_PARAM_PFVF(STAG_END);
 		params[2] = FW_PARAM_PFVF(RQ_START);
 		params[3] = FW_PARAM_PFVF(RQ_END);
 		params[4] = FW_PARAM_PFVF(PBL_START);
 		params[5] = FW_PARAM_PFVF(PBL_END);
-		ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params,
-				      val);
+		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6,
+				      params, val);
 		if (ret < 0)
 			goto bye;
 		adap->vres.stag.start = val[0];
@@ -3272,8 +4020,7 @@ static int adap_init0(struct adapter *adap)
 		params[3] = FW_PARAM_PFVF(CQ_END);
 		params[4] = FW_PARAM_PFVF(OCQ_START);
 		params[5] = FW_PARAM_PFVF(OCQ_END);
-		ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params,
-				      val);
+		ret = t4_query_params(adap, 0, 0, 0, 6, params, val);
 		if (ret < 0)
 			goto bye;
 		adap->vres.qp.start = val[0];
@@ -3283,11 +4030,11 @@ static int adap_init0(struct adapter *adap)
 		adap->vres.ocq.start = val[4];
 		adap->vres.ocq.size = val[5] - val[4] + 1;
 	}
-	if (c.iscsicaps) {
+	if (caps_cmd.iscsicaps) {
 		params[0] = FW_PARAM_PFVF(ISCSI_START);
 		params[1] = FW_PARAM_PFVF(ISCSI_END);
-		ret = t4_query_params(adap, adap->fn, adap->fn, 0, 2, params,
-				      val);
+		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2,
+				      params, val);
 		if (ret < 0)
 			goto bye;
 		adap->vres.iscsi.start = val[0];
@@ -3295,63 +4042,33 @@ static int adap_init0(struct adapter *adap)
 	}
 #undef FW_PARAM_PFVF
 #undef FW_PARAM_DEV
+#endif /* CONFIG_CHELSIO_T4_OFFLOAD */
 
-	adap->params.nports = hweight32(port_vec);
-	adap->params.portvec = port_vec;
-	adap->flags |= FW_OK;
-
-	/* These are finalized by FW initialization, load their values now */
+	/*
+	 * These are finalized by FW initialization, load their values now.
+	 */
 	v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
 	adap->params.tp.tre = TIMERRESOLUTION_GET(v);
+	adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v);
 	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
 	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
 		     adap->params.b_wnd);
 
-#ifdef CONFIG_PCI_IOV
-	/*
-	 * Provision resource limits for Virtual Functions.  We currently
-	 * grant them all the same static resource limits except for the Port
-	 * Access Rights Mask which we're assigning based on the PF.  All of
-	 * the static provisioning stuff for both the PF and VF really needs
-	 * to be managed in a persistent manner for each device which the
-	 * firmware controls.
-	 */
-	{
-		int pf, vf;
-
-		for (pf = 0; pf < ARRAY_SIZE(num_vf); pf++) {
-			if (num_vf[pf] <= 0)
-				continue;
+	/* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */
+	for (j = 0; j < NCHAN; j++)
+		adap->params.tp.tx_modq[j] = j;
 
-			/* VF numbering starts at 1! */
-			for (vf = 1; vf <= num_vf[pf]; vf++) {
-				ret = t4_cfg_pfvf(adap, adap->fn, pf, vf,
-						  VFRES_NEQ, VFRES_NETHCTRL,
-						  VFRES_NIQFLINT, VFRES_NIQ,
-						  VFRES_TC, VFRES_NVI,
-						  FW_PFVF_CMD_CMASK_MASK,
-						  pfvfres_pmask(adap, pf, vf),
-						  VFRES_NEXACTF,
-						  VFRES_R_CAPS, VFRES_WX_CAPS);
-				if (ret < 0)
-					dev_warn(adap->pdev_dev, "failed to "
-						 "provision pf/vf=%d/%d; "
-						 "err=%d\n", pf, vf, ret);
-			}
-		}
-	}
-#endif
-
-	setup_memwin(adap);
+	adap->flags |= FW_OK;
 	return 0;
 
 	/*
-	 * If a command timed out or failed with EIO FW does not operate within
-	 * its spec or something catastrophic happened to HW/FW, stop issuing
-	 * commands.
+	 * Something bad happened.  If a command timed out or failed with EIO
+	 * FW does not operate within its spec or something catastrophic
+	 * happened to HW/FW, stop issuing commands.
 	 */
-bye:	if (ret != -ETIMEDOUT && ret != -EIO)
-		t4_fw_bye(adap, adap->fn);
+bye:
+	if (ret != -ETIMEDOUT && ret != -EIO)
+		t4_fw_bye(adap, adap->mbox);
 	return ret;
 }
 
@@ -3806,7 +4523,9 @@ static int __devinit init_one(struct pci_dev *pdev,
 	err = t4_prep_adapter(adapter);
 	if (err)
 		goto out_unmap_bar;
+	setup_memwin(adapter);
 	err = adap_init0(adapter);
+	setup_memwin_rdma(adapter);
 	if (err)
 		goto out_unmap_bar;
 
@@ -3948,8 +4667,11 @@ static void __devexit remove_one(struct pci_dev *pdev)
 {
 	struct adapter *adapter = pci_get_drvdata(pdev);
 
+#ifdef CONFIG_PCI_IOV
 	pci_disable_sriov(pdev);
 
+#endif
+
 	if (adapter) {
 		int i;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index d79980c5fc63..1b899fea1a91 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -100,6 +100,8 @@ struct tid_info {
 
 	unsigned int nftids;
 	unsigned int ftid_base;
+	unsigned int aftid_base;
+	unsigned int aftid_end;
 
 	spinlock_t atid_lock ____cacheline_aligned_in_smp;
 	union aopen_entry *afree;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index d49933ed551f..3ecc087d732d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -68,9 +68,6 @@
  */
 #define RX_PKT_SKB_LEN   512
 
-/* Ethernet header padding prepended to RX_PKTs */
-#define RX_PKT_PAD 2
-
 /*
  * Max number of Tx descriptors we clean up at a time.  Should be modest as
  * freeing skbs isn't cheap and it happens while holding locks.  We just need
@@ -137,13 +134,6 @@
  */
 #define MAX_CTRL_WR_LEN SGE_MAX_WR_LEN
 
-enum {
-	/* packet alignment in FL buffers */
-	FL_ALIGN = L1_CACHE_BYTES < 32 ? 32 : L1_CACHE_BYTES,
-	/* egress status entry size */
-	STAT_LEN = L1_CACHE_BYTES > 64 ? 128 : 64
-};
-
 struct tx_sw_desc {                /* SW state per Tx descriptor */
 	struct sk_buff *skb;
 	struct ulptx_sgl *sgl;
@@ -155,16 +145,57 @@ struct rx_sw_desc {                /* SW state per Rx descriptor */
 };
 
 /*
- * The low bits of rx_sw_desc.dma_addr have special meaning.
+ * Rx buffer sizes for "useskbs" Free List buffers (one ingress packet pe skb
+ * buffer).  We currently only support two sizes for 1500- and 9000-byte MTUs.
+ * We could easily support more but there doesn't seem to be much need for
+ * that ...
+ */
+#define FL_MTU_SMALL 1500
+#define FL_MTU_LARGE 9000
+
+static inline unsigned int fl_mtu_bufsize(struct adapter *adapter,
+					  unsigned int mtu)
+{
+	struct sge *s = &adapter->sge;
+
+	return ALIGN(s->pktshift + ETH_HLEN + VLAN_HLEN + mtu, s->fl_align);
+}
+
+#define FL_MTU_SMALL_BUFSIZE(adapter) fl_mtu_bufsize(adapter, FL_MTU_SMALL)
+#define FL_MTU_LARGE_BUFSIZE(adapter) fl_mtu_bufsize(adapter, FL_MTU_LARGE)
+
+/*
+ * Bits 0..3 of rx_sw_desc.dma_addr have special meaning.  The hardware uses
+ * these to specify the buffer size as an index into the SGE Free List Buffer
+ * Size register array.  We also use bit 4, when the buffer has been unmapped
+ * for DMA, but this is of course never sent to the hardware and is only used
+ * to prevent double unmappings.  All of the above requires that the Free List
+ * Buffers which we allocate have the bottom 5 bits free (0) -- i.e. are
+ * 32-byte or or a power of 2 greater in alignment.  Since the SGE's minimal
+ * Free List Buffer alignment is 32 bytes, this works out for us ...
  */
 enum {
-	RX_LARGE_BUF    = 1 << 0, /* buffer is larger than PAGE_SIZE */
-	RX_UNMAPPED_BUF = 1 << 1, /* buffer is not mapped */
+	RX_BUF_FLAGS     = 0x1f,   /* bottom five bits are special */
+	RX_BUF_SIZE      = 0x0f,   /* bottom three bits are for buf sizes */
+	RX_UNMAPPED_BUF  = 0x10,   /* buffer is not mapped */
+
+	/*
+	 * XXX We shouldn't depend on being able to use these indices.
+	 * XXX Especially when some other Master PF has initialized the
+	 * XXX adapter or we use the Firmware Configuration File.  We
+	 * XXX should really search through the Host Buffer Size register
+	 * XXX array for the appropriately sized buffer indices.
+	 */
+	RX_SMALL_PG_BUF  = 0x0,   /* small (PAGE_SIZE) page buffer */
+	RX_LARGE_PG_BUF  = 0x1,   /* buffer large (FL_PG_ORDER) page buffer */
+
+	RX_SMALL_MTU_BUF = 0x2,   /* small MTU buffer */
+	RX_LARGE_MTU_BUF = 0x3,   /* large MTU buffer */
 };
 
 static inline dma_addr_t get_buf_addr(const struct rx_sw_desc *d)
 {
-	return d->dma_addr & ~(dma_addr_t)(RX_LARGE_BUF | RX_UNMAPPED_BUF);
+	return d->dma_addr & ~(dma_addr_t)RX_BUF_FLAGS;
 }
 
 static inline bool is_buf_mapped(const struct rx_sw_desc *d)
@@ -392,14 +423,35 @@ static inline void reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
 	}
 }
 
-static inline int get_buf_size(const struct rx_sw_desc *d)
+static inline int get_buf_size(struct adapter *adapter,
+			       const struct rx_sw_desc *d)
 {
-#if FL_PG_ORDER > 0
-	return (d->dma_addr & RX_LARGE_BUF) ? (PAGE_SIZE << FL_PG_ORDER) :
-					      PAGE_SIZE;
-#else
-	return PAGE_SIZE;
-#endif
+	struct sge *s = &adapter->sge;
+	unsigned int rx_buf_size_idx = d->dma_addr & RX_BUF_SIZE;
+	int buf_size;
+
+	switch (rx_buf_size_idx) {
+	case RX_SMALL_PG_BUF:
+		buf_size = PAGE_SIZE;
+		break;
+
+	case RX_LARGE_PG_BUF:
+		buf_size = PAGE_SIZE << s->fl_pg_order;
+		break;
+
+	case RX_SMALL_MTU_BUF:
+		buf_size = FL_MTU_SMALL_BUFSIZE(adapter);
+		break;
+
+	case RX_LARGE_MTU_BUF:
+		buf_size = FL_MTU_LARGE_BUFSIZE(adapter);
+		break;
+
+	default:
+		BUG_ON(1);
+	}
+
+	return buf_size;
 }
 
 /**
@@ -418,7 +470,8 @@ static void free_rx_bufs(struct adapter *adap, struct sge_fl *q, int n)
 
 		if (is_buf_mapped(d))
 			dma_unmap_page(adap->pdev_dev, get_buf_addr(d),
-				       get_buf_size(d), PCI_DMA_FROMDEVICE);
+				       get_buf_size(adap, d),
+				       PCI_DMA_FROMDEVICE);
 		put_page(d->page);
 		d->page = NULL;
 		if (++q->cidx == q->size)
@@ -444,7 +497,7 @@ static void unmap_rx_buf(struct adapter *adap, struct sge_fl *q)
 
 	if (is_buf_mapped(d))
 		dma_unmap_page(adap->pdev_dev, get_buf_addr(d),
-			       get_buf_size(d), PCI_DMA_FROMDEVICE);
+			       get_buf_size(adap, d), PCI_DMA_FROMDEVICE);
 	d->page = NULL;
 	if (++q->cidx == q->size)
 		q->cidx = 0;
@@ -485,6 +538,7 @@ static inline void set_rx_sw_desc(struct rx_sw_desc *sd, struct page *pg,
 static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 			      gfp_t gfp)
 {
+	struct sge *s = &adap->sge;
 	struct page *pg;
 	dma_addr_t mapping;
 	unsigned int cred = q->avail;
@@ -493,25 +547,27 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 
 	gfp |= __GFP_NOWARN | __GFP_COLD;
 
-#if FL_PG_ORDER > 0
+	if (s->fl_pg_order == 0)
+		goto alloc_small_pages;
+
 	/*
 	 * Prefer large buffers
 	 */
 	while (n) {
-		pg = alloc_pages(gfp | __GFP_COMP, FL_PG_ORDER);
+		pg = alloc_pages(gfp | __GFP_COMP, s->fl_pg_order);
 		if (unlikely(!pg)) {
 			q->large_alloc_failed++;
 			break;       /* fall back to single pages */
 		}
 
 		mapping = dma_map_page(adap->pdev_dev, pg, 0,
-				       PAGE_SIZE << FL_PG_ORDER,
+				       PAGE_SIZE << s->fl_pg_order,
 				       PCI_DMA_FROMDEVICE);
 		if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) {
-			__free_pages(pg, FL_PG_ORDER);
+			__free_pages(pg, s->fl_pg_order);
 			goto out;   /* do not try small pages for this error */
 		}
-		mapping |= RX_LARGE_BUF;
+		mapping |= RX_LARGE_PG_BUF;
 		*d++ = cpu_to_be64(mapping);
 
 		set_rx_sw_desc(sd, pg, mapping);
@@ -525,8 +581,8 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 		}
 		n--;
 	}
-#endif
 
+alloc_small_pages:
 	while (n--) {
 		pg = __skb_alloc_page(gfp, NULL);
 		if (unlikely(!pg)) {
@@ -769,8 +825,8 @@ static inline void ring_tx_db(struct adapter *adap, struct sge_txq *q, int n)
 	wmb();            /* write descriptors before telling HW */
 	spin_lock(&q->db_lock);
 	if (!q->db_disabled) {
-		t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL),
-			     V_QID(q->cntxt_id) | V_PIDX(n));
+		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL),
+			     QID(q->cntxt_id) | PIDX(n));
 	}
 	q->db_pidx = q->pidx;
 	spin_unlock(&q->db_lock);
@@ -1519,6 +1575,8 @@ static noinline int handle_trace_pkt(struct adapter *adap,
 static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl,
 		   const struct cpl_rx_pkt *pkt)
 {
+	struct adapter *adapter = rxq->rspq.adap;
+	struct sge *s = &adapter->sge;
 	int ret;
 	struct sk_buff *skb;
 
@@ -1529,8 +1587,8 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl,
 		return;
 	}
 
-	copy_frags(skb, gl, RX_PKT_PAD);
-	skb->len = gl->tot_len - RX_PKT_PAD;
+	copy_frags(skb, gl, s->pktshift);
+	skb->len = gl->tot_len - s->pktshift;
 	skb->data_len = skb->len;
 	skb->truesize += skb->data_len;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1566,6 +1624,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 	struct sk_buff *skb;
 	const struct cpl_rx_pkt *pkt;
 	struct sge_eth_rxq *rxq = container_of(q, struct sge_eth_rxq, rspq);
+	struct sge *s = &q->adap->sge;
 
 	if (unlikely(*(u8 *)rsp == CPL_TRACE_PKT))
 		return handle_trace_pkt(q->adap, si);
@@ -1585,7 +1644,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 		return 0;
 	}
 
-	__skb_pull(skb, RX_PKT_PAD);      /* remove ethernet header padding */
+	__skb_pull(skb, s->pktshift);      /* remove ethernet header padding */
 	skb->protocol = eth_type_trans(skb, q->netdev);
 	skb_record_rx_queue(skb, q->idx);
 	if (skb->dev->features & NETIF_F_RXHASH)
@@ -1696,6 +1755,8 @@ static int process_responses(struct sge_rspq *q, int budget)
 	int budget_left = budget;
 	const struct rsp_ctrl *rc;
 	struct sge_eth_rxq *rxq = container_of(q, struct sge_eth_rxq, rspq);
+	struct adapter *adapter = q->adap;
+	struct sge *s = &adapter->sge;
 
 	while (likely(budget_left)) {
 		rc = (void *)q->cur_desc + (q->iqe_len - sizeof(*rc));
@@ -1722,7 +1783,7 @@ static int process_responses(struct sge_rspq *q, int budget)
 			/* gather packet fragments */
 			for (frags = 0, fp = si.frags; ; frags++, fp++) {
 				rsd = &rxq->fl.sdesc[rxq->fl.cidx];
-				bufsz = get_buf_size(rsd);
+				bufsz = get_buf_size(adapter, rsd);
 				fp->page = rsd->page;
 				fp->offset = q->offset;
 				fp->size = min(bufsz, len);
@@ -1747,7 +1808,7 @@ static int process_responses(struct sge_rspq *q, int budget)
 			si.nfrags = frags + 1;
 			ret = q->handler(q, q->cur_desc, &si);
 			if (likely(ret == 0))
-				q->offset += ALIGN(fp->size, FL_ALIGN);
+				q->offset += ALIGN(fp->size, s->fl_align);
 			else
 				restore_rx_bufs(&si, &rxq->fl, frags);
 		} else if (likely(rsp_type == RSP_TYPE_CPL)) {
@@ -1983,6 +2044,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 {
 	int ret, flsz = 0;
 	struct fw_iq_cmd c;
+	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
 
 	/* Size needs to be multiple of 16, including status entry. */
@@ -2015,11 +2077,11 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
-				      &fl->sdesc, STAT_LEN, NUMA_NO_NODE);
+				      &fl->sdesc, s->stat_len, NUMA_NO_NODE);
 		if (!fl->desc)
 			goto fl_nomem;
 
-		flsz = fl->size / 8 + STAT_LEN / sizeof(struct tx_desc);
+		flsz = fl->size / 8 + s->stat_len / sizeof(struct tx_desc);
 		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_FL0PACKEN |
 					    FW_IQ_CMD_FL0FETCHRO(1) |
 					    FW_IQ_CMD_FL0DATARO(1) |
@@ -2096,14 +2158,15 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 {
 	int ret, nentries;
 	struct fw_eq_eth_cmd c;
+	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
 
 	/* Add status entries */
-	nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
+	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			&txq->q.phys_addr, &txq->q.sdesc, s->stat_len,
 			netdev_queue_numa_node_read(netdevq));
 	if (!txq->q.desc)
 		return -ENOMEM;
@@ -2149,10 +2212,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 {
 	int ret, nentries;
 	struct fw_eq_ctrl_cmd c;
+	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
 
 	/* Add status entries */
-	nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
+	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, nentries,
 				 sizeof(struct tx_desc), 0, &txq->q.phys_addr,
@@ -2200,14 +2264,15 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 {
 	int ret, nentries;
 	struct fw_eq_ofld_cmd c;
+	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
 
 	/* Add status entries */
-	nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
+	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			&txq->q.phys_addr, &txq->q.sdesc, s->stat_len,
 			NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
@@ -2251,8 +2316,10 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 
 static void free_txq(struct adapter *adap, struct sge_txq *q)
 {
+	struct sge *s = &adap->sge;
+
 	dma_free_coherent(adap->pdev_dev,
-			  q->size * sizeof(struct tx_desc) + STAT_LEN,
+			  q->size * sizeof(struct tx_desc) + s->stat_len,
 			  q->desc, q->phys_addr);
 	q->cntxt_id = 0;
 	q->sdesc = NULL;
@@ -2262,6 +2329,7 @@ static void free_txq(struct adapter *adap, struct sge_txq *q)
 static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq,
 			 struct sge_fl *fl)
 {
+	struct sge *s = &adap->sge;
 	unsigned int fl_id = fl ? fl->cntxt_id : 0xffff;
 
 	adap->sge.ingr_map[rq->cntxt_id - adap->sge.ingr_start] = NULL;
@@ -2276,7 +2344,7 @@ static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq,
 
 	if (fl) {
 		free_rx_bufs(adap, fl, fl->avail);
-		dma_free_coherent(adap->pdev_dev, fl->size * 8 + STAT_LEN,
+		dma_free_coherent(adap->pdev_dev, fl->size * 8 + s->stat_len,
 				  fl->desc, fl->addr);
 		kfree(fl->sdesc);
 		fl->sdesc = NULL;
@@ -2408,18 +2476,112 @@ void t4_sge_stop(struct adapter *adap)
  *	Performs SGE initialization needed every time after a chip reset.
  *	We do not initialize any of the queues here, instead the driver
  *	top-level must request them individually.
+ *
+ *	Called in two different modes:
+ *
+ *	 1. Perform actual hardware initialization and record hard-coded
+ *	    parameters which were used.  This gets used when we're the
+ *	    Master PF and the Firmware Configuration File support didn't
+ *	    work for some reason.
+ *
+ *	 2. We're not the Master PF or initialization was performed with
+ *	    a Firmware Configuration File.  In this case we need to grab
+ *	    any of the SGE operating parameters that we need to have in
+ *	    order to do our job and make sure we can live with them ...
  */
-void t4_sge_init(struct adapter *adap)
+
+static int t4_sge_init_soft(struct adapter *adap)
 {
-	unsigned int i, v;
 	struct sge *s = &adap->sge;
-	unsigned int fl_align_log = ilog2(FL_ALIGN);
+	u32 fl_small_pg, fl_large_pg, fl_small_mtu, fl_large_mtu;
+	u32 timer_value_0_and_1, timer_value_2_and_3, timer_value_4_and_5;
+	u32 ingress_rx_threshold;
 
-	t4_set_reg_field(adap, SGE_CONTROL, PKTSHIFT_MASK |
-			 INGPADBOUNDARY_MASK | EGRSTATUSPAGESIZE,
-			 INGPADBOUNDARY(fl_align_log - 5) | PKTSHIFT(2) |
-			 RXPKTCPLMODE |
-			 (STAT_LEN == 128 ? EGRSTATUSPAGESIZE : 0));
+	/*
+	 * Verify that CPL messages are going to the Ingress Queue for
+	 * process_responses() and that only packet data is going to the
+	 * Free Lists.
+	 */
+	if ((t4_read_reg(adap, SGE_CONTROL) & RXPKTCPLMODE_MASK) !=
+	    RXPKTCPLMODE(X_RXPKTCPLMODE_SPLIT)) {
+		dev_err(adap->pdev_dev, "bad SGE CPL MODE\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Validate the Host Buffer Register Array indices that we want to
+	 * use ...
+	 *
+	 * XXX Note that we should really read through the Host Buffer Size
+	 * XXX register array and find the indices of the Buffer Sizes which
+	 * XXX meet our needs!
+	 */
+	#define READ_FL_BUF(x) \
+		t4_read_reg(adap, SGE_FL_BUFFER_SIZE0+(x)*sizeof(u32))
+
+	fl_small_pg = READ_FL_BUF(RX_SMALL_PG_BUF);
+	fl_large_pg = READ_FL_BUF(RX_LARGE_PG_BUF);
+	fl_small_mtu = READ_FL_BUF(RX_SMALL_MTU_BUF);
+	fl_large_mtu = READ_FL_BUF(RX_LARGE_MTU_BUF);
+
+	#undef READ_FL_BUF
+
+	if (fl_small_pg != PAGE_SIZE ||
+	    (fl_large_pg != 0 && (fl_large_pg <= fl_small_pg ||
+				  (fl_large_pg & (fl_large_pg-1)) != 0))) {
+		dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n",
+			fl_small_pg, fl_large_pg);
+		return -EINVAL;
+	}
+	if (fl_large_pg)
+		s->fl_pg_order = ilog2(fl_large_pg) - PAGE_SHIFT;
+
+	if (fl_small_mtu < FL_MTU_SMALL_BUFSIZE(adap) ||
+	    fl_large_mtu < FL_MTU_LARGE_BUFSIZE(adap)) {
+		dev_err(adap->pdev_dev, "bad SGE FL MTU sizes [%d, %d]\n",
+			fl_small_mtu, fl_large_mtu);
+		return -EINVAL;
+	}
+
+	/*
+	 * Retrieve our RX interrupt holdoff timer values and counter
+	 * threshold values from the SGE parameters.
+	 */
+	timer_value_0_and_1 = t4_read_reg(adap, SGE_TIMER_VALUE_0_AND_1);
+	timer_value_2_and_3 = t4_read_reg(adap, SGE_TIMER_VALUE_2_AND_3);
+	timer_value_4_and_5 = t4_read_reg(adap, SGE_TIMER_VALUE_4_AND_5);
+	s->timer_val[0] = core_ticks_to_us(adap,
+		TIMERVALUE0_GET(timer_value_0_and_1));
+	s->timer_val[1] = core_ticks_to_us(adap,
+		TIMERVALUE1_GET(timer_value_0_and_1));
+	s->timer_val[2] = core_ticks_to_us(adap,
+		TIMERVALUE2_GET(timer_value_2_and_3));
+	s->timer_val[3] = core_ticks_to_us(adap,
+		TIMERVALUE3_GET(timer_value_2_and_3));
+	s->timer_val[4] = core_ticks_to_us(adap,
+		TIMERVALUE4_GET(timer_value_4_and_5));
+	s->timer_val[5] = core_ticks_to_us(adap,
+		TIMERVALUE5_GET(timer_value_4_and_5));
+
+	ingress_rx_threshold = t4_read_reg(adap, SGE_INGRESS_RX_THRESHOLD);
+	s->counter_val[0] = THRESHOLD_0_GET(ingress_rx_threshold);
+	s->counter_val[1] = THRESHOLD_1_GET(ingress_rx_threshold);
+	s->counter_val[2] = THRESHOLD_2_GET(ingress_rx_threshold);
+	s->counter_val[3] = THRESHOLD_3_GET(ingress_rx_threshold);
+
+	return 0;
+}
+
+static int t4_sge_init_hard(struct adapter *adap)
+{
+	struct sge *s = &adap->sge;
+
+	/*
+	 * Set up our basic SGE mode to deliver CPL messages to our Ingress
+	 * Queue and Packet Date to the Free List.
+	 */
+	t4_set_reg_field(adap, SGE_CONTROL, RXPKTCPLMODE_MASK,
+			 RXPKTCPLMODE_MASK);
 
 	/*
 	 * Set up to drop DOORBELL writes when the DOORBELL FIFO overflows
@@ -2433,13 +2595,24 @@ void t4_sge_init(struct adapter *adap)
 	t4_set_reg_field(adap, A_SGE_DOORBELL_CONTROL, F_ENABLE_DROP,
 			F_ENABLE_DROP);
 
-	for (i = v = 0; i < 32; i += 4)
-		v |= (PAGE_SHIFT - 10) << i;
-	t4_write_reg(adap, SGE_HOST_PAGE_SIZE, v);
-	t4_write_reg(adap, SGE_FL_BUFFER_SIZE0, PAGE_SIZE);
-#if FL_PG_ORDER > 0
-	t4_write_reg(adap, SGE_FL_BUFFER_SIZE1, PAGE_SIZE << FL_PG_ORDER);
-#endif
+	/*
+	 * SGE_FL_BUFFER_SIZE0 (RX_SMALL_PG_BUF) is set up by
+	 * t4_fixup_host_params().
+	 */
+	s->fl_pg_order = FL_PG_ORDER;
+	if (s->fl_pg_order)
+		t4_write_reg(adap,
+			     SGE_FL_BUFFER_SIZE0+RX_LARGE_PG_BUF*sizeof(u32),
+			     PAGE_SIZE << FL_PG_ORDER);
+	t4_write_reg(adap, SGE_FL_BUFFER_SIZE0+RX_SMALL_MTU_BUF*sizeof(u32),
+		     FL_MTU_SMALL_BUFSIZE(adap));
+	t4_write_reg(adap, SGE_FL_BUFFER_SIZE0+RX_LARGE_MTU_BUF*sizeof(u32),
+		     FL_MTU_LARGE_BUFSIZE(adap));
+
+	/*
+	 * Note that the SGE Ingress Packet Count Interrupt Threshold and
+	 * Timer Holdoff values must be supplied by our caller.
+	 */
 	t4_write_reg(adap, SGE_INGRESS_RX_THRESHOLD,
 		     THRESHOLD_0(s->counter_val[0]) |
 		     THRESHOLD_1(s->counter_val[1]) |
@@ -2449,14 +2622,54 @@ void t4_sge_init(struct adapter *adap)
 		     TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[0])) |
 		     TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[1])));
 	t4_write_reg(adap, SGE_TIMER_VALUE_2_AND_3,
-		     TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[2])) |
-		     TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[3])));
+		     TIMERVALUE2(us_to_core_ticks(adap, s->timer_val[2])) |
+		     TIMERVALUE3(us_to_core_ticks(adap, s->timer_val[3])));
 	t4_write_reg(adap, SGE_TIMER_VALUE_4_AND_5,
-		     TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[4])) |
-		     TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[5])));
+		     TIMERVALUE4(us_to_core_ticks(adap, s->timer_val[4])) |
+		     TIMERVALUE5(us_to_core_ticks(adap, s->timer_val[5])));
+
+	return 0;
+}
+
+int t4_sge_init(struct adapter *adap)
+{
+	struct sge *s = &adap->sge;
+	u32 sge_control;
+	int ret;
+
+	/*
+	 * Ingress Padding Boundary and Egress Status Page Size are set up by
+	 * t4_fixup_host_params().
+	 */
+	sge_control = t4_read_reg(adap, SGE_CONTROL);
+	s->pktshift = PKTSHIFT_GET(sge_control);
+	s->stat_len = (sge_control & EGRSTATUSPAGESIZE_MASK) ? 128 : 64;
+	s->fl_align = 1 << (INGPADBOUNDARY_GET(sge_control) +
+			    X_INGPADBOUNDARY_SHIFT);
+
+	if (adap->flags & USING_SOFT_PARAMS)
+		ret = t4_sge_init_soft(adap);
+	else
+		ret = t4_sge_init_hard(adap);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * A FL with <= fl_starve_thres buffers is starving and a periodic
+	 * timer will attempt to refill it.  This needs to be larger than the
+	 * SGE's Egress Congestion Threshold.  If it isn't, then we can get
+	 * stuck waiting for new packets while the SGE is waiting for us to
+	 * give it more Free List entries.  (Note that the SGE's Egress
+	 * Congestion Threshold is in units of 2 Free List pointers.)
+	 */
+	s->fl_starve_thres
+		= EGRTHRESHOLD_GET(t4_read_reg(adap, SGE_CONM_CTRL))*2 + 1;
+
 	setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap);
 	setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap);
 	s->starve_thres = core_ticks_per_usec(adap) * 1000000;  /* 1 s */
 	s->idma_state[0] = s->idma_state[1] = 0;
 	spin_lock_init(&s->intrq_lock);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index af1601323173..35b81d8b59e9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -120,6 +120,28 @@ static void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
 	}
 }
 
+/**
+ *	t4_write_indirect - write indirectly addressed registers
+ *	@adap: the adapter
+ *	@addr_reg: register holding the indirect addresses
+ *	@data_reg: register holding the value for the indirect registers
+ *	@vals: values to write
+ *	@nregs: how many indirect registers to write
+ *	@start_idx: address of first indirect register to write
+ *
+ *	Writes a sequential block of registers that are accessed indirectly
+ *	through an address/data register pair.
+ */
+void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
+		       unsigned int data_reg, const u32 *vals,
+		       unsigned int nregs, unsigned int start_idx)
+{
+	while (nregs--) {
+		t4_write_reg(adap, addr_reg, start_idx++);
+		t4_write_reg(adap, data_reg, *vals++);
+	}
+}
+
 /*
  * Get the reply to a mailbox command and store it in @rpl in big-endian order.
  */
@@ -330,6 +352,143 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
 	return 0;
 }
 
+/*
+ *	t4_mem_win_rw - read/write memory through PCIE memory window
+ *	@adap: the adapter
+ *	@addr: address of first byte requested
+ *	@data: MEMWIN0_APERTURE bytes of data containing the requested address
+ *	@dir: direction of transfer 1 => read, 0 => write
+ *
+ *	Read/write MEMWIN0_APERTURE bytes of data from MC starting at a
+ *	MEMWIN0_APERTURE-byte-aligned address that covers the requested
+ *	address @addr.
+ */
+static int t4_mem_win_rw(struct adapter *adap, u32 addr, __be32 *data, int dir)
+{
+	int i;
+
+	/*
+	 * Setup offset into PCIE memory window.  Address must be a
+	 * MEMWIN0_APERTURE-byte-aligned address.  (Read back MA register to
+	 * ensure that changes propagate before we attempt to use the new
+	 * values.)
+	 */
+	t4_write_reg(adap, PCIE_MEM_ACCESS_OFFSET,
+		     addr & ~(MEMWIN0_APERTURE - 1));
+	t4_read_reg(adap, PCIE_MEM_ACCESS_OFFSET);
+
+	/* Collecting data 4 bytes at a time upto MEMWIN0_APERTURE */
+	for (i = 0; i < MEMWIN0_APERTURE; i = i+0x4) {
+		if (dir)
+			*data++ = t4_read_reg(adap, (MEMWIN0_BASE + i));
+		else
+			t4_write_reg(adap, (MEMWIN0_BASE + i), *data++);
+	}
+
+	return 0;
+}
+
+/**
+ *	t4_memory_rw - read/write EDC 0, EDC 1 or MC via PCIE memory window
+ *	@adap: the adapter
+ *	@mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC
+ *	@addr: address within indicated memory type
+ *	@len: amount of memory to transfer
+ *	@buf: host memory buffer
+ *	@dir: direction of transfer 1 => read, 0 => write
+ *
+ *	Reads/writes an [almost] arbitrary memory region in the firmware: the
+ *	firmware memory address, length and host buffer must be aligned on
+ *	32-bit boudaries.  The memory is transferred as a raw byte sequence
+ *	from/to the firmware's memory.  If this memory contains data
+ *	structures which contain multi-byte integers, it's the callers
+ *	responsibility to perform appropriate byte order conversions.
+ */
+static int t4_memory_rw(struct adapter *adap, int mtype, u32 addr, u32 len,
+			__be32 *buf, int dir)
+{
+	u32 pos, start, end, offset, memoffset;
+	int ret;
+
+	/*
+	 * Argument sanity checks ...
+	 */
+	if ((addr & 0x3) || (len & 0x3))
+		return -EINVAL;
+
+	/*
+	 * Offset into the region of memory which is being accessed
+	 * MEM_EDC0 = 0
+	 * MEM_EDC1 = 1
+	 * MEM_MC   = 2
+	 */
+	memoffset = (mtype * (5 * 1024 * 1024));
+
+	/* Determine the PCIE_MEM_ACCESS_OFFSET */
+	addr = addr + memoffset;
+
+	/*
+	 * The underlaying EDC/MC read routines read MEMWIN0_APERTURE bytes
+	 * at a time so we need to round down the start and round up the end.
+	 * We'll start copying out of the first line at (addr - start) a word
+	 * at a time.
+	 */
+	start = addr & ~(MEMWIN0_APERTURE-1);
+	end = (addr + len + MEMWIN0_APERTURE-1) & ~(MEMWIN0_APERTURE-1);
+	offset = (addr - start)/sizeof(__be32);
+
+	for (pos = start; pos < end; pos += MEMWIN0_APERTURE, offset = 0) {
+		__be32 data[MEMWIN0_APERTURE/sizeof(__be32)];
+
+		/*
+		 * If we're writing, copy the data from the caller's memory
+		 * buffer
+		 */
+		if (!dir) {
+			/*
+			 * If we're doing a partial write, then we need to do
+			 * a read-modify-write ...
+			 */
+			if (offset || len < MEMWIN0_APERTURE) {
+				ret = t4_mem_win_rw(adap, pos, data, 1);
+				if (ret)
+					return ret;
+			}
+			while (offset < (MEMWIN0_APERTURE/sizeof(__be32)) &&
+			       len > 0) {
+				data[offset++] = *buf++;
+				len -= sizeof(__be32);
+			}
+		}
+
+		/*
+		 * Transfer a block of memory and bail if there's an error.
+		 */
+		ret = t4_mem_win_rw(adap, pos, data, dir);
+		if (ret)
+			return ret;
+
+		/*
+		 * If we're reading, copy the data into the caller's memory
+		 * buffer.
+		 */
+		if (dir)
+			while (offset < (MEMWIN0_APERTURE/sizeof(__be32)) &&
+			       len > 0) {
+				*buf++ = data[offset++];
+				len -= sizeof(__be32);
+			}
+	}
+
+	return 0;
+}
+
+int t4_memory_write(struct adapter *adap, int mtype, u32 addr, u32 len,
+		    __be32 *buf)
+{
+	return t4_memory_rw(adap, mtype, addr, len, buf, 0);
+}
+
 #define EEPROM_STAT_ADDR   0x7bfc
 #define VPD_BASE           0
 #define VPD_LEN            512
@@ -355,8 +514,9 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable)
  *
  *	Reads card parameters stored in VPD EEPROM.
  */
-static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
+int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 {
+	u32 cclk_param, cclk_val;
 	int i, ret;
 	int ec, sn;
 	u8 vpd[VPD_LEN], csum;
@@ -418,6 +578,19 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE);
 	memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN));
 	strim(p->sn);
+
+	/*
+	 * Ask firmware for the Core Clock since it knows how to translate the
+	 * Reference Clock ('V2') VPD field into a Core Clock value ...
+	 */
+	cclk_param = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) |
+		      FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CCLK));
+	ret = t4_query_params(adapter, adapter->mbox, 0, 0,
+			      1, &cclk_param, &cclk_val);
+	if (ret)
+		return ret;
+	p->cclk = cclk_val;
+
 	return 0;
 }
 
@@ -718,6 +891,77 @@ static int t4_flash_erase_sectors(struct adapter *adapter, int start, int end)
 }
 
 /**
+ *	t4_flash_cfg_addr - return the address of the flash configuration file
+ *	@adapter: the adapter
+ *
+ *	Return the address within the flash where the Firmware Configuration
+ *	File is stored.
+ */
+unsigned int t4_flash_cfg_addr(struct adapter *adapter)
+{
+	if (adapter->params.sf_size == 0x100000)
+		return FLASH_FPGA_CFG_START;
+	else
+		return FLASH_CFG_START;
+}
+
+/**
+ *	t4_load_cfg - download config file
+ *	@adap: the adapter
+ *	@cfg_data: the cfg text file to write
+ *	@size: text file size
+ *
+ *	Write the supplied config text file to the card's serial flash.
+ */
+int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size)
+{
+	int ret, i, n;
+	unsigned int addr;
+	unsigned int flash_cfg_start_sec;
+	unsigned int sf_sec_size = adap->params.sf_size / adap->params.sf_nsec;
+
+	addr = t4_flash_cfg_addr(adap);
+	flash_cfg_start_sec = addr / SF_SEC_SIZE;
+
+	if (size > FLASH_CFG_MAX_SIZE) {
+		dev_err(adap->pdev_dev, "cfg file too large, max is %u bytes\n",
+			FLASH_CFG_MAX_SIZE);
+		return -EFBIG;
+	}
+
+	i = DIV_ROUND_UP(FLASH_CFG_MAX_SIZE,	/* # of sectors spanned */
+			 sf_sec_size);
+	ret = t4_flash_erase_sectors(adap, flash_cfg_start_sec,
+				     flash_cfg_start_sec + i - 1);
+	/*
+	 * If size == 0 then we're simply erasing the FLASH sectors associated
+	 * with the on-adapter Firmware Configuration File.
+	 */
+	if (ret || size == 0)
+		goto out;
+
+	/* this will write to the flash up to SF_PAGE_SIZE at a time */
+	for (i = 0; i < size; i += SF_PAGE_SIZE) {
+		if ((size - i) <  SF_PAGE_SIZE)
+			n = size - i;
+		else
+			n = SF_PAGE_SIZE;
+		ret = t4_write_flash(adap, addr, n, cfg_data);
+		if (ret)
+			goto out;
+
+		addr += SF_PAGE_SIZE;
+		cfg_data += SF_PAGE_SIZE;
+	}
+
+out:
+	if (ret)
+		dev_err(adap->pdev_dev, "config file %s failed %d\n",
+			(size == 0 ? "clear" : "download"), ret);
+	return ret;
+}
+
+/**
  *	t4_load_fw - download firmware
  *	@adap: the adapter
  *	@fw_data: the firmware image to write
@@ -1018,9 +1262,9 @@ static void sge_intr_handler(struct adapter *adapter)
 		{ ERR_INVALID_CIDX_INC,
 		  "SGE GTS CIDX increment too large", -1, 0 },
 		{ ERR_CPL_OPCODE_0, "SGE received 0-length CPL", -1, 0 },
-		{ F_DBFIFO_LP_INT, NULL, -1, 0, t4_db_full },
-		{ F_DBFIFO_HP_INT, NULL, -1, 0, t4_db_full },
-		{ F_ERR_DROPPED_DB, NULL, -1, 0, t4_db_dropped },
+		{ DBFIFO_LP_INT, NULL, -1, 0, t4_db_full },
+		{ DBFIFO_HP_INT, NULL, -1, 0, t4_db_full },
+		{ ERR_DROPPED_DB, NULL, -1, 0, t4_db_dropped },
 		{ ERR_DATA_CPL_ON_HIGH_QID1 | ERR_DATA_CPL_ON_HIGH_QID0,
 		  "SGE IQID > 1023 received CPL for FL", -1, 0 },
 		{ ERR_BAD_DB_PIDX3, "SGE DBP 3 pidx increment too large", -1,
@@ -1520,7 +1764,7 @@ void t4_intr_enable(struct adapter *adapter)
 		     ERR_BAD_DB_PIDX2 | ERR_BAD_DB_PIDX1 |
 		     ERR_BAD_DB_PIDX0 | ERR_ING_CTXT_PRIO |
 		     ERR_EGR_CTXT_PRIO | INGRESS_SIZE_ERR |
-		     F_DBFIFO_HP_INT | F_DBFIFO_LP_INT |
+		     DBFIFO_HP_INT | DBFIFO_LP_INT |
 		     EGRESS_SIZE_ERR);
 	t4_write_reg(adapter, MYPF_REG(PL_PF_INT_ENABLE), PF_INTR_MASK);
 	t4_set_reg_field(adapter, PL_INT_MAP0, 0, 1 << pf);
@@ -1717,6 +1961,23 @@ void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log)
 }
 
 /**
+ *	t4_tp_wr_bits_indirect - set/clear bits in an indirect TP register
+ *	@adap: the adapter
+ *	@addr: the indirect TP register address
+ *	@mask: specifies the field within the register to modify
+ *	@val: new value for the field
+ *
+ *	Sets a field of an indirect TP register to the given value.
+ */
+void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr,
+			    unsigned int mask, unsigned int val)
+{
+	t4_write_reg(adap, TP_PIO_ADDR, addr);
+	val |= t4_read_reg(adap, TP_PIO_DATA) & ~mask;
+	t4_write_reg(adap, TP_PIO_DATA, val);
+}
+
+/**
  *	init_cong_ctrl - initialize congestion control parameters
  *	@a: the alpha values for congestion control
  *	@b: the beta values for congestion control
@@ -2000,9 +2261,9 @@ int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
 	struct fw_ldst_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_addrspace = htonl(V_FW_CMD_OP(FW_LDST_CMD) | F_FW_CMD_REQUEST |
-			    F_FW_CMD_WRITE |
-			    V_FW_LDST_CMD_ADDRSPACE(FW_LDST_ADDRSPC_FIRMWARE));
+	c.op_to_addrspace = htonl(FW_CMD_OP(FW_LDST_CMD) | FW_CMD_REQUEST |
+			    FW_CMD_WRITE |
+			    FW_LDST_CMD_ADDRSPACE(FW_LDST_ADDRSPC_FIRMWARE));
 	c.cycles_to_len16 = htonl(FW_LEN16(c));
 	c.u.addrval.addr = htonl(addr);
 	c.u.addrval.val = htonl(val);
@@ -2033,8 +2294,8 @@ int t4_mem_win_read_len(struct adapter *adap, u32 addr, __be32 *data, int len)
 	if ((addr & 3) || (len + off) > MEMWIN0_APERTURE)
 		return -EINVAL;
 
-	t4_write_reg(adap, A_PCIE_MEM_ACCESS_OFFSET, addr & ~15);
-	t4_read_reg(adap, A_PCIE_MEM_ACCESS_OFFSET);
+	t4_write_reg(adap, PCIE_MEM_ACCESS_OFFSET, addr & ~15);
+	t4_read_reg(adap, PCIE_MEM_ACCESS_OFFSET);
 
 	for (i = 0; i < len; i += 4)
 		*data++ = t4_read_reg(adap, (MEMWIN0_BASE + off + i));
@@ -2102,39 +2363,129 @@ int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
 }
 
 /**
- *	t4_fw_hello - establish communication with FW
- *	@adap: the adapter
- *	@mbox: mailbox to use for the FW command
- *	@evt_mbox: mailbox to receive async FW events
- *	@master: specifies the caller's willingness to be the device master
- *	@state: returns the current device state
+ *      t4_fw_hello - establish communication with FW
+ *      @adap: the adapter
+ *      @mbox: mailbox to use for the FW command
+ *      @evt_mbox: mailbox to receive async FW events
+ *      @master: specifies the caller's willingness to be the device master
+ *	@state: returns the current device state (if non-NULL)
  *
- *	Issues a command to establish communication with FW.
+ *	Issues a command to establish communication with FW.  Returns either
+ *	an error (negative integer) or the mailbox of the Master PF.
  */
 int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox,
 		enum dev_master master, enum dev_state *state)
 {
 	int ret;
 	struct fw_hello_cmd c;
+	u32 v;
+	unsigned int master_mbox;
+	int retries = FW_CMD_HELLO_RETRIES;
 
+retry:
+	memset(&c, 0, sizeof(c));
 	INIT_CMD(c, HELLO, WRITE);
 	c.err_to_mbasyncnot = htonl(
 		FW_HELLO_CMD_MASTERDIS(master == MASTER_CANT) |
 		FW_HELLO_CMD_MASTERFORCE(master == MASTER_MUST) |
-		FW_HELLO_CMD_MBMASTER(master == MASTER_MUST ? mbox : 0xff) |
-		FW_HELLO_CMD_MBASYNCNOT(evt_mbox));
+		FW_HELLO_CMD_MBMASTER(master == MASTER_MUST ? mbox :
+				      FW_HELLO_CMD_MBMASTER_MASK) |
+		FW_HELLO_CMD_MBASYNCNOT(evt_mbox) |
+		FW_HELLO_CMD_STAGE(fw_hello_cmd_stage_os) |
+		FW_HELLO_CMD_CLEARINIT);
 
+	/*
+	 * Issue the HELLO command to the firmware.  If it's not successful
+	 * but indicates that we got a "busy" or "timeout" condition, retry
+	 * the HELLO until we exhaust our retry limit.
+	 */
 	ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
-	if (ret == 0 && state) {
-		u32 v = ntohl(c.err_to_mbasyncnot);
-		if (v & FW_HELLO_CMD_INIT)
-			*state = DEV_STATE_INIT;
-		else if (v & FW_HELLO_CMD_ERR)
+	if (ret < 0) {
+		if ((ret == -EBUSY || ret == -ETIMEDOUT) && retries-- > 0)
+			goto retry;
+		return ret;
+	}
+
+	v = ntohl(c.err_to_mbasyncnot);
+	master_mbox = FW_HELLO_CMD_MBMASTER_GET(v);
+	if (state) {
+		if (v & FW_HELLO_CMD_ERR)
 			*state = DEV_STATE_ERR;
+		else if (v & FW_HELLO_CMD_INIT)
+			*state = DEV_STATE_INIT;
 		else
 			*state = DEV_STATE_UNINIT;
 	}
-	return ret;
+
+	/*
+	 * If we're not the Master PF then we need to wait around for the
+	 * Master PF Driver to finish setting up the adapter.
+	 *
+	 * Note that we also do this wait if we're a non-Master-capable PF and
+	 * there is no current Master PF; a Master PF may show up momentarily
+	 * and we wouldn't want to fail pointlessly.  (This can happen when an
+	 * OS loads lots of different drivers rapidly at the same time).  In
+	 * this case, the Master PF returned by the firmware will be
+	 * FW_PCIE_FW_MASTER_MASK so the test below will work ...
+	 */
+	if ((v & (FW_HELLO_CMD_ERR|FW_HELLO_CMD_INIT)) == 0 &&
+	    master_mbox != mbox) {
+		int waiting = FW_CMD_HELLO_TIMEOUT;
+
+		/*
+		 * Wait for the firmware to either indicate an error or
+		 * initialized state.  If we see either of these we bail out
+		 * and report the issue to the caller.  If we exhaust the
+		 * "hello timeout" and we haven't exhausted our retries, try
+		 * again.  Otherwise bail with a timeout error.
+		 */
+		for (;;) {
+			u32 pcie_fw;
+
+			msleep(50);
+			waiting -= 50;
+
+			/*
+			 * If neither Error nor Initialialized are indicated
+			 * by the firmware keep waiting till we exaust our
+			 * timeout ... and then retry if we haven't exhausted
+			 * our retries ...
+			 */
+			pcie_fw = t4_read_reg(adap, MA_PCIE_FW);
+			if (!(pcie_fw & (FW_PCIE_FW_ERR|FW_PCIE_FW_INIT))) {
+				if (waiting <= 0) {
+					if (retries-- > 0)
+						goto retry;
+
+					return -ETIMEDOUT;
+				}
+				continue;
+			}
+
+			/*
+			 * We either have an Error or Initialized condition
+			 * report errors preferentially.
+			 */
+			if (state) {
+				if (pcie_fw & FW_PCIE_FW_ERR)
+					*state = DEV_STATE_ERR;
+				else if (pcie_fw & FW_PCIE_FW_INIT)
+					*state = DEV_STATE_INIT;
+			}
+
+			/*
+			 * If we arrived before a Master PF was selected and
+			 * there's not a valid Master PF, grab its identity
+			 * for our caller.
+			 */
+			if (master_mbox == FW_PCIE_FW_MASTER_MASK &&
+			    (pcie_fw & FW_PCIE_FW_MASTER_VLD))
+				master_mbox = FW_PCIE_FW_MASTER_GET(pcie_fw);
+			break;
+		}
+	}
+
+	return master_mbox;
 }
 
 /**
@@ -2186,6 +2537,334 @@ int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset)
 }
 
 /**
+ *	t4_fw_halt - issue a reset/halt to FW and put uP into RESET
+ *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW RESET command (if desired)
+ *	@force: force uP into RESET even if FW RESET command fails
+ *
+ *	Issues a RESET command to firmware (if desired) with a HALT indication
+ *	and then puts the microprocessor into RESET state.  The RESET command
+ *	will only be issued if a legitimate mailbox is provided (mbox <=
+ *	FW_PCIE_FW_MASTER_MASK).
+ *
+ *	This is generally used in order for the host to safely manipulate the
+ *	adapter without fear of conflicting with whatever the firmware might
+ *	be doing.  The only way out of this state is to RESTART the firmware
+ *	...
+ */
+int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force)
+{
+	int ret = 0;
+
+	/*
+	 * If a legitimate mailbox is provided, issue a RESET command
+	 * with a HALT indication.
+	 */
+	if (mbox <= FW_PCIE_FW_MASTER_MASK) {
+		struct fw_reset_cmd c;
+
+		memset(&c, 0, sizeof(c));
+		INIT_CMD(c, RESET, WRITE);
+		c.val = htonl(PIORST | PIORSTMODE);
+		c.halt_pkd = htonl(FW_RESET_CMD_HALT(1U));
+		ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
+	}
+
+	/*
+	 * Normally we won't complete the operation if the firmware RESET
+	 * command fails but if our caller insists we'll go ahead and put the
+	 * uP into RESET.  This can be useful if the firmware is hung or even
+	 * missing ...  We'll have to take the risk of putting the uP into
+	 * RESET without the cooperation of firmware in that case.
+	 *
+	 * We also force the firmware's HALT flag to be on in case we bypassed
+	 * the firmware RESET command above or we're dealing with old firmware
+	 * which doesn't have the HALT capability.  This will serve as a flag
+	 * for the incoming firmware to know that it's coming out of a HALT
+	 * rather than a RESET ... if it's new enough to understand that ...
+	 */
+	if (ret == 0 || force) {
+		t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, UPCRST);
+		t4_set_reg_field(adap, PCIE_FW, FW_PCIE_FW_HALT,
+				 FW_PCIE_FW_HALT);
+	}
+
+	/*
+	 * And we always return the result of the firmware RESET command
+	 * even when we force the uP into RESET ...
+	 */
+	return ret;
+}
+
+/**
+ *	t4_fw_restart - restart the firmware by taking the uP out of RESET
+ *	@adap: the adapter
+ *	@reset: if we want to do a RESET to restart things
+ *
+ *	Restart firmware previously halted by t4_fw_halt().  On successful
+ *	return the previous PF Master remains as the new PF Master and there
+ *	is no need to issue a new HELLO command, etc.
+ *
+ *	We do this in two ways:
+ *
+ *	 1. If we're dealing with newer firmware we'll simply want to take
+ *	    the chip's microprocessor out of RESET.  This will cause the
+ *	    firmware to start up from its start vector.  And then we'll loop
+ *	    until the firmware indicates it's started again (PCIE_FW.HALT
+ *	    reset to 0) or we timeout.
+ *
+ *	 2. If we're dealing with older firmware then we'll need to RESET
+ *	    the chip since older firmware won't recognize the PCIE_FW.HALT
+ *	    flag and automatically RESET itself on startup.
+ */
+int t4_fw_restart(struct adapter *adap, unsigned int mbox, int reset)
+{
+	if (reset) {
+		/*
+		 * Since we're directing the RESET instead of the firmware
+		 * doing it automatically, we need to clear the PCIE_FW.HALT
+		 * bit.
+		 */
+		t4_set_reg_field(adap, PCIE_FW, FW_PCIE_FW_HALT, 0);
+
+		/*
+		 * If we've been given a valid mailbox, first try to get the
+		 * firmware to do the RESET.  If that works, great and we can
+		 * return success.  Otherwise, if we haven't been given a
+		 * valid mailbox or the RESET command failed, fall back to
+		 * hitting the chip with a hammer.
+		 */
+		if (mbox <= FW_PCIE_FW_MASTER_MASK) {
+			t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, 0);
+			msleep(100);
+			if (t4_fw_reset(adap, mbox,
+					PIORST | PIORSTMODE) == 0)
+				return 0;
+		}
+
+		t4_write_reg(adap, PL_RST, PIORST | PIORSTMODE);
+		msleep(2000);
+	} else {
+		int ms;
+
+		t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, 0);
+		for (ms = 0; ms < FW_CMD_MAX_TIMEOUT; ) {
+			if (!(t4_read_reg(adap, PCIE_FW) & FW_PCIE_FW_HALT))
+				return 0;
+			msleep(100);
+			ms += 100;
+		}
+		return -ETIMEDOUT;
+	}
+	return 0;
+}
+
+/**
+ *	t4_fw_upgrade - perform all of the steps necessary to upgrade FW
+ *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW RESET command (if desired)
+ *	@fw_data: the firmware image to write
+ *	@size: image size
+ *	@force: force upgrade even if firmware doesn't cooperate
+ *
+ *	Perform all of the steps necessary for upgrading an adapter's
+ *	firmware image.  Normally this requires the cooperation of the
+ *	existing firmware in order to halt all existing activities
+ *	but if an invalid mailbox token is passed in we skip that step
+ *	(though we'll still put the adapter microprocessor into RESET in
+ *	that case).
+ *
+ *	On successful return the new firmware will have been loaded and
+ *	the adapter will have been fully RESET losing all previous setup
+ *	state.  On unsuccessful return the adapter may be completely hosed ...
+ *	positive errno indicates that the adapter is ~probably~ intact, a
+ *	negative errno indicates that things are looking bad ...
+ */
+int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
+		  const u8 *fw_data, unsigned int size, int force)
+{
+	const struct fw_hdr *fw_hdr = (const struct fw_hdr *)fw_data;
+	int reset, ret;
+
+	ret = t4_fw_halt(adap, mbox, force);
+	if (ret < 0 && !force)
+		return ret;
+
+	ret = t4_load_fw(adap, fw_data, size);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Older versions of the firmware don't understand the new
+	 * PCIE_FW.HALT flag and so won't know to perform a RESET when they
+	 * restart.  So for newly loaded older firmware we'll have to do the
+	 * RESET for it so it starts up on a clean slate.  We can tell if
+	 * the newly loaded firmware will handle this right by checking
+	 * its header flags to see if it advertises the capability.
+	 */
+	reset = ((ntohl(fw_hdr->flags) & FW_HDR_FLAGS_RESET_HALT) == 0);
+	return t4_fw_restart(adap, mbox, reset);
+}
+
+
+/**
+ *	t4_fw_config_file - setup an adapter via a Configuration File
+ *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW command
+ *	@mtype: the memory type where the Configuration File is located
+ *	@maddr: the memory address where the Configuration File is located
+ *	@finiver: return value for CF [fini] version
+ *	@finicsum: return value for CF [fini] checksum
+ *	@cfcsum: return value for CF computed checksum
+ *
+ *	Issue a command to get the firmware to process the Configuration
+ *	File located at the specified mtype/maddress.  If the Configuration
+ *	File is processed successfully and return value pointers are
+ *	provided, the Configuration File "[fini] section version and
+ *	checksum values will be returned along with the computed checksum.
+ *	It's up to the caller to decide how it wants to respond to the
+ *	checksums not matching but it recommended that a prominant warning
+ *	be emitted in order to help people rapidly identify changed or
+ *	corrupted Configuration Files.
+ *
+ *	Also note that it's possible to modify things like "niccaps",
+ *	"toecaps",etc. between processing the Configuration File and telling
+ *	the firmware to use the new configuration.  Callers which want to
+ *	do this will need to "hand-roll" their own CAPS_CONFIGS commands for
+ *	Configuration Files if they want to do this.
+ */
+int t4_fw_config_file(struct adapter *adap, unsigned int mbox,
+		      unsigned int mtype, unsigned int maddr,
+		      u32 *finiver, u32 *finicsum, u32 *cfcsum)
+{
+	struct fw_caps_config_cmd caps_cmd;
+	int ret;
+
+	/*
+	 * Tell the firmware to process the indicated Configuration File.
+	 * If there are no errors and the caller has provided return value
+	 * pointers for the [fini] section version, checksum and computed
+	 * checksum, pass those back to the caller.
+	 */
+	memset(&caps_cmd, 0, sizeof(caps_cmd));
+	caps_cmd.op_to_write =
+		htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+		      FW_CMD_REQUEST |
+		      FW_CMD_READ);
+	caps_cmd.retval_len16 =
+		htonl(FW_CAPS_CONFIG_CMD_CFVALID |
+		      FW_CAPS_CONFIG_CMD_MEMTYPE_CF(mtype) |
+		      FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(maddr >> 16) |
+		      FW_LEN16(caps_cmd));
+	ret = t4_wr_mbox(adap, mbox, &caps_cmd, sizeof(caps_cmd), &caps_cmd);
+	if (ret < 0)
+		return ret;
+
+	if (finiver)
+		*finiver = ntohl(caps_cmd.finiver);
+	if (finicsum)
+		*finicsum = ntohl(caps_cmd.finicsum);
+	if (cfcsum)
+		*cfcsum = ntohl(caps_cmd.cfcsum);
+
+	/*
+	 * And now tell the firmware to use the configuration we just loaded.
+	 */
+	caps_cmd.op_to_write =
+		htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
+		      FW_CMD_REQUEST |
+		      FW_CMD_WRITE);
+	caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd));
+	return t4_wr_mbox(adap, mbox, &caps_cmd, sizeof(caps_cmd), NULL);
+}
+
+/**
+ *	t4_fixup_host_params - fix up host-dependent parameters
+ *	@adap: the adapter
+ *	@page_size: the host's Base Page Size
+ *	@cache_line_size: the host's Cache Line Size
+ *
+ *	Various registers in T4 contain values which are dependent on the
+ *	host's Base Page and Cache Line Sizes.  This function will fix all of
+ *	those registers with the appropriate values as passed in ...
+ */
+int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
+			 unsigned int cache_line_size)
+{
+	unsigned int page_shift = fls(page_size) - 1;
+	unsigned int sge_hps = page_shift - 10;
+	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
+	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
+	unsigned int fl_align_log = fls(fl_align) - 1;
+
+	t4_write_reg(adap, SGE_HOST_PAGE_SIZE,
+		     HOSTPAGESIZEPF0(sge_hps) |
+		     HOSTPAGESIZEPF1(sge_hps) |
+		     HOSTPAGESIZEPF2(sge_hps) |
+		     HOSTPAGESIZEPF3(sge_hps) |
+		     HOSTPAGESIZEPF4(sge_hps) |
+		     HOSTPAGESIZEPF5(sge_hps) |
+		     HOSTPAGESIZEPF6(sge_hps) |
+		     HOSTPAGESIZEPF7(sge_hps));
+
+	t4_set_reg_field(adap, SGE_CONTROL,
+			 INGPADBOUNDARY(INGPADBOUNDARY_MASK) |
+			 EGRSTATUSPAGESIZE_MASK,
+			 INGPADBOUNDARY(fl_align_log - 5) |
+			 EGRSTATUSPAGESIZE(stat_len != 64));
+
+	/*
+	 * Adjust various SGE Free List Host Buffer Sizes.
+	 *
+	 * This is something of a crock since we're using fixed indices into
+	 * the array which are also known by the sge.c code and the T4
+	 * Firmware Configuration File.  We need to come up with a much better
+	 * approach to managing this array.  For now, the first four entries
+	 * are:
+	 *
+	 *   0: Host Page Size
+	 *   1: 64KB
+	 *   2: Buffer size corresponding to 1500 byte MTU (unpacked mode)
+	 *   3: Buffer size corresponding to 9000 byte MTU (unpacked mode)
+	 *
+	 * For the single-MTU buffers in unpacked mode we need to include
+	 * space for the SGE Control Packet Shift, 14 byte Ethernet header,
+	 * possible 4 byte VLAN tag, all rounded up to the next Ingress Packet
+	 * Padding boundry.  All of these are accommodated in the Factory
+	 * Default Firmware Configuration File but we need to adjust it for
+	 * this host's cache line size.
+	 */
+	t4_write_reg(adap, SGE_FL_BUFFER_SIZE0, page_size);
+	t4_write_reg(adap, SGE_FL_BUFFER_SIZE2,
+		     (t4_read_reg(adap, SGE_FL_BUFFER_SIZE2) + fl_align-1)
+		     & ~(fl_align-1));
+	t4_write_reg(adap, SGE_FL_BUFFER_SIZE3,
+		     (t4_read_reg(adap, SGE_FL_BUFFER_SIZE3) + fl_align-1)
+		     & ~(fl_align-1));
+
+	t4_write_reg(adap, ULP_RX_TDDP_PSZ, HPZ0(page_shift - 12));
+
+	return 0;
+}
+
+/**
+ *	t4_fw_initialize - ask FW to initialize the device
+ *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW command
+ *
+ *	Issues a command to FW to partially initialize the device.  This
+ *	performs initialization that generally doesn't depend on user input.
+ */
+int t4_fw_initialize(struct adapter *adap, unsigned int mbox)
+{
+	struct fw_initialize_cmd c;
+
+	memset(&c, 0, sizeof(c));
+	INIT_CMD(c, INITIALIZE, WRITE);
+	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
+}
+
+/**
  *	t4_query_params - query FW or device parameters
  *	@adap: the adapter
  *	@mbox: mailbox to use for the FW command
@@ -2835,10 +3514,6 @@ int __devinit t4_prep_adapter(struct adapter *adapter)
 		return ret;
 	}
 
-	ret = get_vpd_params(adapter, &adapter->params.vpd);
-	if (ret < 0)
-		return ret;
-
 	init_cong_ctrl(adapter->params.a_wnd, adapter->params.b_wnd);
 
 	/*
@@ -2846,6 +3521,7 @@ int __devinit t4_prep_adapter(struct adapter *adapter)
 	 */
 	adapter->params.nports = 1;
 	adapter->params.portvec = 1;
+	adapter->params.vpd.cclk = 50000;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index c26b455f37de..f534ed7e10e9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -58,6 +58,7 @@ enum {
 
 enum {
 	SF_PAGE_SIZE = 256,           /* serial flash page size */
+	SF_SEC_SIZE = 64 * 1024,      /* serial flash sector size */
 };
 
 enum { RSP_TYPE_FLBUF, RSP_TYPE_CPL, RSP_TYPE_INTR }; /* response entry types */
@@ -137,4 +138,83 @@ struct rsp_ctrl {
 #define QINTR_CNT_EN       0x1
 #define QINTR_TIMER_IDX(x) ((x) << 1)
 #define QINTR_TIMER_IDX_GET(x) (((x) >> 1) & 0x7)
+
+/*
+ * Flash layout.
+ */
+#define FLASH_START(start)	((start) * SF_SEC_SIZE)
+#define FLASH_MAX_SIZE(nsecs)	((nsecs) * SF_SEC_SIZE)
+
+enum {
+	/*
+	 * Various Expansion-ROM boot images, etc.
+	 */
+	FLASH_EXP_ROM_START_SEC = 0,
+	FLASH_EXP_ROM_NSECS = 6,
+	FLASH_EXP_ROM_START = FLASH_START(FLASH_EXP_ROM_START_SEC),
+	FLASH_EXP_ROM_MAX_SIZE = FLASH_MAX_SIZE(FLASH_EXP_ROM_NSECS),
+
+	/*
+	 * iSCSI Boot Firmware Table (iBFT) and other driver-related
+	 * parameters ...
+	 */
+	FLASH_IBFT_START_SEC = 6,
+	FLASH_IBFT_NSECS = 1,
+	FLASH_IBFT_START = FLASH_START(FLASH_IBFT_START_SEC),
+	FLASH_IBFT_MAX_SIZE = FLASH_MAX_SIZE(FLASH_IBFT_NSECS),
+
+	/*
+	 * Boot configuration data.
+	 */
+	FLASH_BOOTCFG_START_SEC = 7,
+	FLASH_BOOTCFG_NSECS = 1,
+	FLASH_BOOTCFG_START = FLASH_START(FLASH_BOOTCFG_START_SEC),
+	FLASH_BOOTCFG_MAX_SIZE = FLASH_MAX_SIZE(FLASH_BOOTCFG_NSECS),
+
+	/*
+	 * Location of firmware image in FLASH.
+	 */
+	FLASH_FW_START_SEC = 8,
+	FLASH_FW_NSECS = 8,
+	FLASH_FW_START = FLASH_START(FLASH_FW_START_SEC),
+	FLASH_FW_MAX_SIZE = FLASH_MAX_SIZE(FLASH_FW_NSECS),
+
+	/*
+	 * iSCSI persistent/crash information.
+	 */
+	FLASH_ISCSI_CRASH_START_SEC = 29,
+	FLASH_ISCSI_CRASH_NSECS = 1,
+	FLASH_ISCSI_CRASH_START = FLASH_START(FLASH_ISCSI_CRASH_START_SEC),
+	FLASH_ISCSI_CRASH_MAX_SIZE = FLASH_MAX_SIZE(FLASH_ISCSI_CRASH_NSECS),
+
+	/*
+	 * FCoE persistent/crash information.
+	 */
+	FLASH_FCOE_CRASH_START_SEC = 30,
+	FLASH_FCOE_CRASH_NSECS = 1,
+	FLASH_FCOE_CRASH_START = FLASH_START(FLASH_FCOE_CRASH_START_SEC),
+	FLASH_FCOE_CRASH_MAX_SIZE = FLASH_MAX_SIZE(FLASH_FCOE_CRASH_NSECS),
+
+	/*
+	 * Location of Firmware Configuration File in FLASH.  Since the FPGA
+	 * "FLASH" is smaller we need to store the Configuration File in a
+	 * different location -- which will overlap the end of the firmware
+	 * image if firmware ever gets that large ...
+	 */
+	FLASH_CFG_START_SEC = 31,
+	FLASH_CFG_NSECS = 1,
+	FLASH_CFG_START = FLASH_START(FLASH_CFG_START_SEC),
+	FLASH_CFG_MAX_SIZE = FLASH_MAX_SIZE(FLASH_CFG_NSECS),
+
+	FLASH_FPGA_CFG_START_SEC = 15,
+	FLASH_FPGA_CFG_START = FLASH_START(FLASH_FPGA_CFG_START_SEC),
+
+	/*
+	 * Sectors 32-63 are reserved for FLASH failover.
+	 */
+};
+
+#undef FLASH_START
+#undef FLASH_MAX_SIZE
+
 #endif /* __T4_HW_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 111fc323f155..a1a8b57200f6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -86,10 +86,17 @@
 #define  CIDXINC_SHIFT     0
 #define  CIDXINC(x)        ((x) << CIDXINC_SHIFT)
 
+#define X_RXPKTCPLMODE_SPLIT     1
+#define X_INGPADBOUNDARY_SHIFT 5
+
 #define SGE_CONTROL 0x1008
 #define  DCASYSTYPE             0x00080000U
-#define  RXPKTCPLMODE           0x00040000U
-#define  EGRSTATUSPAGESIZE      0x00020000U
+#define  RXPKTCPLMODE_MASK      0x00040000U
+#define  RXPKTCPLMODE_SHIFT     18
+#define  RXPKTCPLMODE(x)        ((x) << RXPKTCPLMODE_SHIFT)
+#define  EGRSTATUSPAGESIZE_MASK  0x00020000U
+#define  EGRSTATUSPAGESIZE_SHIFT 17
+#define  EGRSTATUSPAGESIZE(x)    ((x) << EGRSTATUSPAGESIZE_SHIFT)
 #define  PKTSHIFT_MASK          0x00001c00U
 #define  PKTSHIFT_SHIFT         10
 #define  PKTSHIFT(x)            ((x) << PKTSHIFT_SHIFT)
@@ -108,6 +115,35 @@
 #define  GLOBALENABLE           0x00000001U
 
 #define SGE_HOST_PAGE_SIZE 0x100c
+
+#define  HOSTPAGESIZEPF7_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF7_SHIFT  28
+#define  HOSTPAGESIZEPF7(x)     ((x) << HOSTPAGESIZEPF7_SHIFT)
+
+#define  HOSTPAGESIZEPF6_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF6_SHIFT  24
+#define  HOSTPAGESIZEPF6(x)     ((x) << HOSTPAGESIZEPF6_SHIFT)
+
+#define  HOSTPAGESIZEPF5_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF5_SHIFT  20
+#define  HOSTPAGESIZEPF5(x)     ((x) << HOSTPAGESIZEPF5_SHIFT)
+
+#define  HOSTPAGESIZEPF4_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF4_SHIFT  16
+#define  HOSTPAGESIZEPF4(x)     ((x) << HOSTPAGESIZEPF4_SHIFT)
+
+#define  HOSTPAGESIZEPF3_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF3_SHIFT  12
+#define  HOSTPAGESIZEPF3(x)     ((x) << HOSTPAGESIZEPF3_SHIFT)
+
+#define  HOSTPAGESIZEPF2_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF2_SHIFT  8
+#define  HOSTPAGESIZEPF2(x)     ((x) << HOSTPAGESIZEPF2_SHIFT)
+
+#define  HOSTPAGESIZEPF1_MASK   0x0000000fU
+#define  HOSTPAGESIZEPF1_SHIFT  4
+#define  HOSTPAGESIZEPF1(x)     ((x) << HOSTPAGESIZEPF1_SHIFT)
+
 #define  HOSTPAGESIZEPF0_MASK   0x0000000fU
 #define  HOSTPAGESIZEPF0_SHIFT  0
 #define  HOSTPAGESIZEPF0(x)     ((x) << HOSTPAGESIZEPF0_SHIFT)
@@ -155,6 +191,8 @@
 #define SGE_INT_ENABLE3 0x1040
 #define SGE_FL_BUFFER_SIZE0 0x1044
 #define SGE_FL_BUFFER_SIZE1 0x1048
+#define SGE_FL_BUFFER_SIZE2 0x104c
+#define SGE_FL_BUFFER_SIZE3 0x1050
 #define SGE_INGRESS_RX_THRESHOLD 0x10a0
 #define  THRESHOLD_0_MASK   0x3f000000U
 #define  THRESHOLD_0_SHIFT  24
@@ -173,6 +211,12 @@
 #define  THRESHOLD_3(x)     ((x) << THRESHOLD_3_SHIFT)
 #define  THRESHOLD_3_GET(x) (((x) & THRESHOLD_3_MASK) >> THRESHOLD_3_SHIFT)
 
+#define SGE_CONM_CTRL 0x1094
+#define  EGRTHRESHOLD_MASK   0x00003f00U
+#define  EGRTHRESHOLDshift   8
+#define  EGRTHRESHOLD(x)     ((x) << EGRTHRESHOLDshift)
+#define  EGRTHRESHOLD_GET(x) (((x) & EGRTHRESHOLD_MASK) >> EGRTHRESHOLDshift)
+
 #define SGE_TIMER_VALUE_0_AND_1 0x10b8
 #define  TIMERVALUE0_MASK   0xffff0000U
 #define  TIMERVALUE0_SHIFT  16
@@ -184,64 +228,54 @@
 #define  TIMERVALUE1_GET(x) (((x) & TIMERVALUE1_MASK) >> TIMERVALUE1_SHIFT)
 
 #define SGE_TIMER_VALUE_2_AND_3 0x10bc
+#define  TIMERVALUE2_MASK   0xffff0000U
+#define  TIMERVALUE2_SHIFT  16
+#define  TIMERVALUE2(x)     ((x) << TIMERVALUE2_SHIFT)
+#define  TIMERVALUE2_GET(x) (((x) & TIMERVALUE2_MASK) >> TIMERVALUE2_SHIFT)
+#define  TIMERVALUE3_MASK   0x0000ffffU
+#define  TIMERVALUE3_SHIFT  0
+#define  TIMERVALUE3(x)     ((x) << TIMERVALUE3_SHIFT)
+#define  TIMERVALUE3_GET(x) (((x) & TIMERVALUE3_MASK) >> TIMERVALUE3_SHIFT)
+
 #define SGE_TIMER_VALUE_4_AND_5 0x10c0
+#define  TIMERVALUE4_MASK   0xffff0000U
+#define  TIMERVALUE4_SHIFT  16
+#define  TIMERVALUE4(x)     ((x) << TIMERVALUE4_SHIFT)
+#define  TIMERVALUE4_GET(x) (((x) & TIMERVALUE4_MASK) >> TIMERVALUE4_SHIFT)
+#define  TIMERVALUE5_MASK   0x0000ffffU
+#define  TIMERVALUE5_SHIFT  0
+#define  TIMERVALUE5(x)     ((x) << TIMERVALUE5_SHIFT)
+#define  TIMERVALUE5_GET(x) (((x) & TIMERVALUE5_MASK) >> TIMERVALUE5_SHIFT)
+
 #define SGE_DEBUG_INDEX 0x10cc
 #define SGE_DEBUG_DATA_HIGH 0x10d0
 #define SGE_DEBUG_DATA_LOW 0x10d4
 #define SGE_INGRESS_QUEUES_PER_PAGE_PF 0x10f4
 
-#define S_LP_INT_THRESH    12
-#define V_LP_INT_THRESH(x) ((x) << S_LP_INT_THRESH)
 #define S_HP_INT_THRESH    28
+#define M_HP_INT_THRESH 0xfU
 #define V_HP_INT_THRESH(x) ((x) << S_HP_INT_THRESH)
+#define M_HP_COUNT 0x7ffU
+#define S_HP_COUNT 16
+#define G_HP_COUNT(x) (((x) >> S_HP_COUNT) & M_HP_COUNT)
+#define S_LP_INT_THRESH    12
+#define M_LP_INT_THRESH 0xfU
+#define V_LP_INT_THRESH(x) ((x) << S_LP_INT_THRESH)
+#define M_LP_COUNT 0x7ffU
+#define S_LP_COUNT 0
+#define G_LP_COUNT(x) (((x) >> S_LP_COUNT) & M_LP_COUNT)
 #define A_SGE_DBFIFO_STATUS 0x10a4
 
 #define S_ENABLE_DROP    13
 #define V_ENABLE_DROP(x) ((x) << S_ENABLE_DROP)
 #define F_ENABLE_DROP    V_ENABLE_DROP(1U)
-#define A_SGE_DOORBELL_CONTROL 0x10a8
-
-#define A_SGE_CTXT_CMD 0x11fc
-#define A_SGE_DBQ_CTXT_BADDR 0x1084
-
-#define A_SGE_PF_KDOORBELL 0x0
-
-#define S_QID 15
-#define V_QID(x) ((x) << S_QID)
-
-#define S_PIDX 0
-#define V_PIDX(x) ((x) << S_PIDX)
-
-#define M_LP_COUNT 0x7ffU
-#define S_LP_COUNT 0
-#define G_LP_COUNT(x) (((x) >> S_LP_COUNT) & M_LP_COUNT)
-
-#define M_HP_COUNT 0x7ffU
-#define S_HP_COUNT 16
-#define G_HP_COUNT(x) (((x) >> S_HP_COUNT) & M_HP_COUNT)
-
-#define A_SGE_INT_ENABLE3 0x1040
-
-#define S_DBFIFO_HP_INT 8
-#define V_DBFIFO_HP_INT(x) ((x) << S_DBFIFO_HP_INT)
-#define F_DBFIFO_HP_INT V_DBFIFO_HP_INT(1U)
-
-#define S_DBFIFO_LP_INT 7
-#define V_DBFIFO_LP_INT(x) ((x) << S_DBFIFO_LP_INT)
-#define F_DBFIFO_LP_INT V_DBFIFO_LP_INT(1U)
-
 #define S_DROPPED_DB 0
 #define V_DROPPED_DB(x) ((x) << S_DROPPED_DB)
 #define F_DROPPED_DB V_DROPPED_DB(1U)
+#define A_SGE_DOORBELL_CONTROL 0x10a8
 
-#define S_ERR_DROPPED_DB 18
-#define V_ERR_DROPPED_DB(x) ((x) << S_ERR_DROPPED_DB)
-#define F_ERR_DROPPED_DB V_ERR_DROPPED_DB(1U)
-
-#define A_PCIE_MEM_ACCESS_OFFSET 0x306c
-
-#define M_HP_INT_THRESH 0xfU
-#define M_LP_INT_THRESH 0xfU
+#define A_SGE_CTXT_CMD 0x11fc
+#define A_SGE_DBQ_CTXT_BADDR 0x1084
 
 #define PCIE_PF_CLI 0x44
 #define PCIE_INT_CAUSE 0x3004
@@ -287,6 +321,8 @@
 #define  WINDOW(x)       ((x) << WINDOW_SHIFT)
 #define PCIE_MEM_ACCESS_OFFSET 0x306c
 
+#define PCIE_FW 0x30b8
+
 #define PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS 0x5908
 #define  RNPP 0x80000000U
 #define  RPCP 0x20000000U
@@ -364,7 +400,7 @@
 #define  MEM_WRAP_CLIENT_NUM_MASK   0x0000000fU
 #define  MEM_WRAP_CLIENT_NUM_SHIFT  0
 #define  MEM_WRAP_CLIENT_NUM_GET(x) (((x) & MEM_WRAP_CLIENT_NUM_MASK) >> MEM_WRAP_CLIENT_NUM_SHIFT)
-
+#define MA_PCIE_FW 0x30b8
 #define MA_PARITY_ERROR_STATUS 0x77f4
 
 #define EDC_0_BASE_ADDR 0x7900
@@ -385,6 +421,7 @@
 
 #define CIM_BOOT_CFG 0x7b00
 #define  BOOTADDR_MASK 0xffffff00U
+#define  UPCRST        0x1U
 
 #define CIM_PF_MAILBOX_DATA 0x240
 #define CIM_PF_MAILBOX_CTRL 0x280
@@ -457,6 +494,13 @@
 #define  VLANEXTENABLE_MASK  0x0000f000U
 #define  VLANEXTENABLE_SHIFT 12
 
+#define TP_GLOBAL_CONFIG 0x7d08
+#define  FIVETUPLELOOKUP_SHIFT  17
+#define  FIVETUPLELOOKUP_MASK   0x00060000U
+#define  FIVETUPLELOOKUP(x)     ((x) << FIVETUPLELOOKUP_SHIFT)
+#define  FIVETUPLELOOKUP_GET(x) (((x) & FIVETUPLELOOKUP_MASK) >> \
+				FIVETUPLELOOKUP_SHIFT)
+
 #define TP_PARA_REG2 0x7d68
 #define  MAXRXDATA_MASK    0xffff0000U
 #define  MAXRXDATA_SHIFT   16
@@ -466,8 +510,47 @@
 #define  TIMERRESOLUTION_MASK   0x00ff0000U
 #define  TIMERRESOLUTION_SHIFT  16
 #define  TIMERRESOLUTION_GET(x) (((x) & TIMERRESOLUTION_MASK) >> TIMERRESOLUTION_SHIFT)
+#define  DELAYEDACKRESOLUTION_MASK 0x000000ffU
+#define  DELAYEDACKRESOLUTION_SHIFT     0
+#define  DELAYEDACKRESOLUTION_GET(x) \
+	(((x) & DELAYEDACKRESOLUTION_MASK) >> DELAYEDACKRESOLUTION_SHIFT)
 
 #define TP_SHIFT_CNT 0x7dc0
+#define  SYNSHIFTMAX_SHIFT         24
+#define  SYNSHIFTMAX_MASK          0xff000000U
+#define  SYNSHIFTMAX(x)            ((x) << SYNSHIFTMAX_SHIFT)
+#define  SYNSHIFTMAX_GET(x)        (((x) & SYNSHIFTMAX_MASK) >> \
+				   SYNSHIFTMAX_SHIFT)
+#define  RXTSHIFTMAXR1_SHIFT       20
+#define  RXTSHIFTMAXR1_MASK        0x00f00000U
+#define  RXTSHIFTMAXR1(x)          ((x) << RXTSHIFTMAXR1_SHIFT)
+#define  RXTSHIFTMAXR1_GET(x)      (((x) & RXTSHIFTMAXR1_MASK) >> \
+				   RXTSHIFTMAXR1_SHIFT)
+#define  RXTSHIFTMAXR2_SHIFT       16
+#define  RXTSHIFTMAXR2_MASK        0x000f0000U
+#define  RXTSHIFTMAXR2(x)          ((x) << RXTSHIFTMAXR2_SHIFT)
+#define  RXTSHIFTMAXR2_GET(x)      (((x) & RXTSHIFTMAXR2_MASK) >> \
+				   RXTSHIFTMAXR2_SHIFT)
+#define  PERSHIFTBACKOFFMAX_SHIFT  12
+#define  PERSHIFTBACKOFFMAX_MASK   0x0000f000U
+#define  PERSHIFTBACKOFFMAX(x)     ((x) << PERSHIFTBACKOFFMAX_SHIFT)
+#define  PERSHIFTBACKOFFMAX_GET(x) (((x) & PERSHIFTBACKOFFMAX_MASK) >> \
+				   PERSHIFTBACKOFFMAX_SHIFT)
+#define  PERSHIFTMAX_SHIFT         8
+#define  PERSHIFTMAX_MASK          0x00000f00U
+#define  PERSHIFTMAX(x)            ((x) << PERSHIFTMAX_SHIFT)
+#define  PERSHIFTMAX_GET(x)        (((x) & PERSHIFTMAX_MASK) >> \
+				   PERSHIFTMAX_SHIFT)
+#define  KEEPALIVEMAXR1_SHIFT      4
+#define  KEEPALIVEMAXR1_MASK       0x000000f0U
+#define  KEEPALIVEMAXR1(x)         ((x) << KEEPALIVEMAXR1_SHIFT)
+#define  KEEPALIVEMAXR1_GET(x)     (((x) & KEEPALIVEMAXR1_MASK) >> \
+				   KEEPALIVEMAXR1_SHIFT)
+#define KEEPALIVEMAXR2_SHIFT       0
+#define KEEPALIVEMAXR2_MASK        0x0000000fU
+#define KEEPALIVEMAXR2(x)          ((x) << KEEPALIVEMAXR2_SHIFT)
+#define KEEPALIVEMAXR2_GET(x)      (((x) & KEEPALIVEMAXR2_MASK) >> \
+				   KEEPALIVEMAXR2_SHIFT)
 
 #define TP_CCTRL_TABLE 0x7ddc
 #define TP_MTU_TABLE 0x7de4
@@ -501,6 +584,20 @@
 #define TP_INT_CAUSE 0x7e74
 #define  FLMTXFLSTEMPTY 0x40000000U
 
+#define TP_VLAN_PRI_MAP 0x140
+#define  FRAGMENTATION_SHIFT 9
+#define  FRAGMENTATION_MASK  0x00000200U
+#define  MPSHITTYPE_MASK     0x00000100U
+#define  MACMATCH_MASK       0x00000080U
+#define  ETHERTYPE_MASK      0x00000040U
+#define  PROTOCOL_MASK       0x00000020U
+#define  TOS_MASK            0x00000010U
+#define  VLAN_MASK           0x00000008U
+#define  VNIC_ID_MASK        0x00000004U
+#define  PORT_MASK           0x00000002U
+#define  FCOE_SHIFT          0
+#define  FCOE_MASK           0x00000001U
+
 #define TP_INGRESS_CONFIG 0x141
 #define  VNIC                0x00000800U
 #define  CSUM_HAS_PSEUDO_HDR 0x00000400U
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index ad53f796b574..a6364632b490 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -79,6 +79,8 @@ struct fw_wr_hdr {
 #define FW_WR_FLOWID(x)	((x) << 8)
 #define FW_WR_LEN16(x)	((x) << 0)
 
+#define HW_TPL_FR_MT_PR_IV_P_FC         0X32B
+
 struct fw_ulptx_wr {
 	__be32 op_to_compl;
 	__be32 flowid_len16;
@@ -155,6 +157,17 @@ struct fw_eth_tx_pkt_vm_wr {
 
 #define FW_CMD_MAX_TIMEOUT 3000
 
+/*
+ * If a host driver does a HELLO and discovers that there's already a MASTER
+ * selected, we may have to wait for that MASTER to finish issuing RESET,
+ * configuration and INITIALIZE commands.  Also, there's a possibility that
+ * our own HELLO may get lost if it happens right as the MASTER is issuign a
+ * RESET command, so we need to be willing to make a few retries of our HELLO.
+ */
+#define FW_CMD_HELLO_TIMEOUT	(3 * FW_CMD_MAX_TIMEOUT)
+#define FW_CMD_HELLO_RETRIES	3
+
+
 enum fw_cmd_opcodes {
 	FW_LDST_CMD                    = 0x01,
 	FW_RESET_CMD                   = 0x03,
@@ -304,7 +317,17 @@ struct fw_reset_cmd {
 	__be32 op_to_write;
 	__be32 retval_len16;
 	__be32 val;
-	__be32 r3;
+	__be32 halt_pkd;
+};
+
+#define FW_RESET_CMD_HALT_SHIFT    31
+#define FW_RESET_CMD_HALT_MASK     0x1
+#define FW_RESET_CMD_HALT(x)       ((x) << FW_RESET_CMD_HALT_SHIFT)
+#define FW_RESET_CMD_HALT_GET(x)  \
+	(((x) >> FW_RESET_CMD_HALT_SHIFT) & FW_RESET_CMD_HALT_MASK)
+
+enum fw_hellow_cmd {
+	fw_hello_cmd_stage_os		= 0x0
 };
 
 struct fw_hello_cmd {
@@ -315,8 +338,14 @@ struct fw_hello_cmd {
 #define FW_HELLO_CMD_INIT	    (1U << 30)
 #define FW_HELLO_CMD_MASTERDIS(x)   ((x) << 29)
 #define FW_HELLO_CMD_MASTERFORCE(x) ((x) << 28)
-#define FW_HELLO_CMD_MBMASTER(x)    ((x) << 24)
+#define FW_HELLO_CMD_MBMASTER_MASK   0xfU
+#define FW_HELLO_CMD_MBMASTER_SHIFT  24
+#define FW_HELLO_CMD_MBMASTER(x)     ((x) << FW_HELLO_CMD_MBMASTER_SHIFT)
+#define FW_HELLO_CMD_MBMASTER_GET(x) \
+	(((x) >> FW_HELLO_CMD_MBMASTER_SHIFT) & FW_HELLO_CMD_MBMASTER_MASK)
 #define FW_HELLO_CMD_MBASYNCNOT(x)  ((x) << 20)
+#define FW_HELLO_CMD_STAGE(x)       ((x) << 17)
+#define FW_HELLO_CMD_CLEARINIT      (1U << 16)
 	__be32 fwrev;
 };
 
@@ -401,6 +430,14 @@ enum fw_caps_config_fcoe {
 	FW_CAPS_CONFIG_FCOE_TARGET	= 0x00000002,
 };
 
+enum fw_memtype_cf {
+	FW_MEMTYPE_CF_EDC0		= 0x0,
+	FW_MEMTYPE_CF_EDC1		= 0x1,
+	FW_MEMTYPE_CF_EXTMEM		= 0x2,
+	FW_MEMTYPE_CF_FLASH		= 0x4,
+	FW_MEMTYPE_CF_INTERNAL		= 0x5,
+};
+
 struct fw_caps_config_cmd {
 	__be32 op_to_write;
 	__be32 retval_len16;
@@ -416,10 +453,15 @@ struct fw_caps_config_cmd {
 	__be16 r4;
 	__be16 iscsicaps;
 	__be16 fcoecaps;
-	__be32 r5;
-	__be64 r6;
+	__be32 cfcsum;
+	__be32 finiver;
+	__be32 finicsum;
 };
 
+#define FW_CAPS_CONFIG_CMD_CFVALID          (1U << 27)
+#define FW_CAPS_CONFIG_CMD_MEMTYPE_CF(x)    ((x) << 24)
+#define FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(x) ((x) << 16)
+
 /*
  * params command mnemonics
  */
@@ -451,6 +493,7 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_INTVER_FCOE = 0x0A,
 	FW_PARAMS_PARAM_DEV_FWREV = 0x0B,
 	FW_PARAMS_PARAM_DEV_TPREV = 0x0C,
+	FW_PARAMS_PARAM_DEV_CF = 0x0D,
 };
 
 /*
@@ -492,6 +535,8 @@ enum fw_params_param_pfvf {
 	FW_PARAMS_PARAM_PFVF_IQFLINT_END = 0x2A,
 	FW_PARAMS_PARAM_PFVF_EQ_START	= 0x2B,
 	FW_PARAMS_PARAM_PFVF_EQ_END	= 0x2C,
+	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_START = 0x2D,
+	FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_END = 0x2E
 };
 
 /*
@@ -507,8 +552,16 @@ enum fw_params_param_dmaq {
 
 #define FW_PARAMS_MNEM(x)      ((x) << 24)
 #define FW_PARAMS_PARAM_X(x)   ((x) << 16)
-#define FW_PARAMS_PARAM_Y(x)   ((x) << 8)
-#define FW_PARAMS_PARAM_Z(x)   ((x) << 0)
+#define FW_PARAMS_PARAM_Y_SHIFT  8
+#define FW_PARAMS_PARAM_Y_MASK   0xffU
+#define FW_PARAMS_PARAM_Y(x)     ((x) << FW_PARAMS_PARAM_Y_SHIFT)
+#define FW_PARAMS_PARAM_Y_GET(x) (((x) >> FW_PARAMS_PARAM_Y_SHIFT) &\
+		FW_PARAMS_PARAM_Y_MASK)
+#define FW_PARAMS_PARAM_Z_SHIFT  0
+#define FW_PARAMS_PARAM_Z_MASK   0xffu
+#define FW_PARAMS_PARAM_Z(x)     ((x) << FW_PARAMS_PARAM_Z_SHIFT)
+#define FW_PARAMS_PARAM_Z_GET(x) (((x) >> FW_PARAMS_PARAM_Z_SHIFT) &\
+		FW_PARAMS_PARAM_Z_MASK)
 #define FW_PARAMS_PARAM_XYZ(x) ((x) << 0)
 #define FW_PARAMS_PARAM_YZ(x)  ((x) << 0)
 
@@ -1599,6 +1652,16 @@ struct fw_debug_cmd {
 	} u;
 };
 
+#define FW_PCIE_FW_ERR           (1U << 31)
+#define FW_PCIE_FW_INIT          (1U << 30)
+#define FW_PCIE_FW_HALT          (1U << 29)
+#define FW_PCIE_FW_MASTER_VLD    (1U << 15)
+#define FW_PCIE_FW_MASTER_MASK   0x7
+#define FW_PCIE_FW_MASTER_SHIFT  12
+#define FW_PCIE_FW_MASTER(x)     ((x) << FW_PCIE_FW_MASTER_SHIFT)
+#define FW_PCIE_FW_MASTER_GET(x) (((x) >> FW_PCIE_FW_MASTER_SHIFT) & \
+				 FW_PCIE_FW_MASTER_MASK)
+
 struct fw_hdr {
 	u8 ver;
 	u8 reserved1;
@@ -1613,7 +1676,11 @@ struct fw_hdr {
 	u8 intfver_iscsi;
 	u8 intfver_fcoe;
 	u8 reserved2;
-	__be32  reserved3[27];
+	__u32   reserved3;
+	__u32   reserved4;
+	__u32   reserved5;
+	__be32  flags;
+	__be32  reserved6[23];
 };
 
 #define FW_HDR_FW_VER_MAJOR_GET(x) (((x) >> 24) & 0xff)
@@ -1621,18 +1688,8 @@ struct fw_hdr {
 #define FW_HDR_FW_VER_MICRO_GET(x) (((x) >> 8) & 0xff)
 #define FW_HDR_FW_VER_BUILD_GET(x) (((x) >> 0) & 0xff)
 
-#define S_FW_CMD_OP 24
-#define V_FW_CMD_OP(x) ((x) << S_FW_CMD_OP)
-
-#define S_FW_CMD_REQUEST 23
-#define V_FW_CMD_REQUEST(x) ((x) << S_FW_CMD_REQUEST)
-#define F_FW_CMD_REQUEST V_FW_CMD_REQUEST(1U)
-
-#define S_FW_CMD_WRITE 21
-#define V_FW_CMD_WRITE(x) ((x) << S_FW_CMD_WRITE)
-#define F_FW_CMD_WRITE V_FW_CMD_WRITE(1U)
-
-#define S_FW_LDST_CMD_ADDRSPACE 0
-#define V_FW_LDST_CMD_ADDRSPACE(x) ((x) << S_FW_LDST_CMD_ADDRSPACE)
+enum fw_hdr_flags {
+	FW_HDR_FLAGS_RESET_HALT = 0x00000001,
+};
 
 #endif /* _T4FW_INTERFACE_H_ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 8877fbfefb63..f16745f4b36b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2421,7 +2421,7 @@ int t4vf_sge_init(struct adapter *adapter)
 			fl0, fl1);
 		return -EINVAL;
 	}
-	if ((sge_params->sge_control & RXPKTCPLMODE) == 0) {
+	if ((sge_params->sge_control & RXPKTCPLMODE_MASK) == 0) {
 		dev_err(adapter->pdev_dev, "bad SGE CPL MODE\n");
 		return -EINVAL;
 	}
@@ -2431,7 +2431,8 @@ int t4vf_sge_init(struct adapter *adapter)
 	 */
 	if (fl1)
 		FL_PG_ORDER = ilog2(fl1) - PAGE_SHIFT;
-	STAT_LEN = ((sge_params->sge_control & EGRSTATUSPAGESIZE) ? 128 : 64);
+	STAT_LEN = ((sge_params->sge_control & EGRSTATUSPAGESIZE_MASK)
+		    ? 128 : 64);
 	PKTSHIFT = PKTSHIFT_GET(sge_params->sge_control);
 	FL_ALIGN = 1 << (INGPADBOUNDARY_GET(sge_params->sge_control) +
 			 SGE_INGPADBOUNDARY_SHIFT);
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index d266c86a53f7..cf4c05bdf5fe 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -110,6 +110,7 @@ static inline char *nic_name(struct pci_dev *pdev)
 #define MAX_RX_POST		BE_NAPI_WEIGHT /* Frags posted at a time */
 #define RX_FRAGS_REFILL_WM	(RX_Q_LEN - MAX_RX_POST)
 
+#define MAX_VFS			30 /* Max VFs supported by BE3 FW */
 #define FW_VER_LEN		32
 
 struct be_dma_mem {
@@ -336,7 +337,6 @@ struct phy_info {
 	u16 auto_speeds_supported;
 	u16 fixed_speeds_supported;
 	int link_speed;
-	int forced_port_speed;
 	u32 dac_cable_len;
 	u32 advertising;
 	u32 supported;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 8c63d06ab12b..af60bb26e330 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -120,7 +120,7 @@ static int be_mcc_compl_process(struct be_adapter *adapter,
 
 		if (compl_status == MCC_STATUS_UNAUTHORIZED_REQUEST) {
 			dev_warn(&adapter->pdev->dev,
-				 "opcode %d-%d is not permitted\n",
+				 "VF is not privileged to issue opcode %d-%d\n",
 				 opcode, subsystem);
 		} else {
 			extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
@@ -165,14 +165,13 @@ static void be_async_grp5_cos_priority_process(struct be_adapter *adapter,
 	}
 }
 
-/* Grp5 QOS Speed evt */
+/* Grp5 QOS Speed evt: qos_link_speed is in units of 10 Mbps */
 static void be_async_grp5_qos_speed_process(struct be_adapter *adapter,
 		struct be_async_event_grp5_qos_link_speed *evt)
 {
-	if (evt->physical_port == adapter->port_num) {
-		/* qos_link_speed is in units of 10 Mbps */
-		adapter->phy.link_speed = evt->qos_link_speed * 10;
-	}
+	if (adapter->phy.link_speed >= 0 &&
+	    evt->physical_port == adapter->port_num)
+		adapter->phy.link_speed = le16_to_cpu(evt->qos_link_speed) * 10;
 }
 
 /*Grp5 PVID evt*/
@@ -717,7 +716,7 @@ int be_cmd_eq_create(struct be_adapter *adapter,
 
 /* Use MCC */
 int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
-			u8 type, bool permanent, u32 if_handle, u32 pmac_id)
+			  bool permanent, u32 if_handle, u32 pmac_id)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_mac_query *req;
@@ -734,7 +733,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 		OPCODE_COMMON_NTWK_MAC_QUERY, sizeof(*req), wrb, NULL);
-	req->type = type;
+	req->type = MAC_ADDRESS_TYPE_NETWORK;
 	if (permanent) {
 		req->permanent = 1;
 	} else {
@@ -1326,9 +1325,28 @@ err:
 	return status;
 }
 
-/* Uses synchronous mcc */
-int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
-			     u16 *link_speed, u8 *link_status, u32 dom)
+static int be_mac_to_link_speed(int mac_speed)
+{
+	switch (mac_speed) {
+	case PHY_LINK_SPEED_ZERO:
+		return 0;
+	case PHY_LINK_SPEED_10MBPS:
+		return 10;
+	case PHY_LINK_SPEED_100MBPS:
+		return 100;
+	case PHY_LINK_SPEED_1GBPS:
+		return 1000;
+	case PHY_LINK_SPEED_10GBPS:
+		return 10000;
+	}
+	return 0;
+}
+
+/* Uses synchronous mcc
+ * Returns link_speed in Mbps
+ */
+int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
+			     u8 *link_status, u32 dom)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_link_status *req;
@@ -1357,11 +1375,13 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_link_status *resp = embedded_payload(wrb);
-		if (resp->mac_speed != PHY_LINK_SPEED_ZERO) {
-			if (link_speed)
-				*link_speed = le16_to_cpu(resp->link_speed);
-			if (mac_speed)
-				*mac_speed = resp->mac_speed;
+		if (link_speed) {
+			*link_speed = resp->link_speed ?
+				      le16_to_cpu(resp->link_speed) * 10 :
+				      be_mac_to_link_speed(resp->mac_speed);
+
+			if (!resp->logical_link_status)
+				*link_speed = 0;
 		}
 		if (link_status)
 			*link_status = resp->logical_link_status;
@@ -2405,6 +2425,9 @@ int be_cmd_req_native_mode(struct be_adapter *adapter)
 		struct be_cmd_resp_set_func_cap *resp = embedded_payload(wrb);
 		adapter->be3_native = le32_to_cpu(resp->cap_flags) &
 					CAPABILITY_BE3_NATIVE_ERX_API;
+		if (!adapter->be3_native)
+			dev_warn(&adapter->pdev->dev,
+				 "adapter not in advanced mode\n");
 	}
 err:
 	mutex_unlock(&adapter->mbox_lock);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 250f19b5f7b6..0936e21e3cff 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1687,7 +1687,7 @@ struct be_cmd_req_set_ext_fat_caps {
 extern int be_pci_fnum_get(struct be_adapter *adapter);
 extern int be_fw_wait_ready(struct be_adapter *adapter);
 extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
-			u8 type, bool permanent, u32 if_handle, u32 pmac_id);
+				 bool permanent, u32 if_handle, u32 pmac_id);
 extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 			u32 if_id, u32 *pmac_id, u32 domain);
 extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id,
@@ -1714,8 +1714,8 @@ extern int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 			int type);
 extern int be_cmd_rxq_destroy(struct be_adapter *adapter,
 			struct be_queue_info *q);
-extern int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
-				    u16 *link_speed, u8 *link_status, u32 dom);
+extern int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
+				    u8 *link_status, u32 dom);
 extern int be_cmd_reset(struct be_adapter *adapter);
 extern int be_cmd_get_stats(struct be_adapter *adapter,
 			struct be_dma_mem *nonemb_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index c0e700653f96..8e6fb0ba6aa9 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -512,28 +512,6 @@ static u32 convert_to_et_setting(u32 if_type, u32 if_speeds)
 	return val;
 }
 
-static int convert_to_et_speed(u32 be_speed)
-{
-	int et_speed = SPEED_10000;
-
-	switch (be_speed) {
-	case PHY_LINK_SPEED_10MBPS:
-		et_speed = SPEED_10;
-		break;
-	case PHY_LINK_SPEED_100MBPS:
-		et_speed = SPEED_100;
-		break;
-	case PHY_LINK_SPEED_1GBPS:
-		et_speed = SPEED_1000;
-		break;
-	case PHY_LINK_SPEED_10GBPS:
-		et_speed = SPEED_10000;
-		break;
-	}
-
-	return et_speed;
-}
-
 bool be_pause_supported(struct be_adapter *adapter)
 {
 	return (adapter->phy.interface_type == PHY_TYPE_SFP_PLUS_10GB ||
@@ -544,27 +522,16 @@ bool be_pause_supported(struct be_adapter *adapter)
 static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	u8 port_speed = 0;
-	u16 link_speed = 0;
 	u8 link_status;
-	u32 et_speed = 0;
+	u16 link_speed = 0;
 	int status;
 
-	if (adapter->phy.link_speed < 0 || !(netdev->flags & IFF_UP)) {
-		if (adapter->phy.forced_port_speed < 0) {
-			status = be_cmd_link_status_query(adapter, &port_speed,
-						&link_speed, &link_status, 0);
-			if (!status)
-				be_link_status_update(adapter, link_status);
-			if (link_speed)
-				et_speed = link_speed * 10;
-			else if (link_status)
-				et_speed = convert_to_et_speed(port_speed);
-		} else {
-			et_speed = adapter->phy.forced_port_speed;
-		}
-
-		ethtool_cmd_speed_set(ecmd, et_speed);
+	if (adapter->phy.link_speed < 0) {
+		status = be_cmd_link_status_query(adapter, &link_speed,
+						  &link_status, 0);
+		if (!status)
+			be_link_status_update(adapter, link_status);
+		ethtool_cmd_speed_set(ecmd, link_speed);
 
 		status = be_cmd_get_phy_info(adapter);
 		if (status)
@@ -773,8 +740,8 @@ static void
 be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	u8 mac_speed = 0;
-	u16 qos_link_speed = 0;
+	int status;
+	u8 link_status = 0;
 
 	memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM);
 
@@ -798,11 +765,11 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
 		test->flags |= ETH_TEST_FL_FAILED;
 	}
 
-	if (be_cmd_link_status_query(adapter, &mac_speed,
-				     &qos_link_speed, NULL, 0) != 0) {
+	status = be_cmd_link_status_query(adapter, NULL, &link_status, 0);
+	if (status) {
 		test->flags |= ETH_TEST_FL_FAILED;
 		data[4] = -1;
-	} else if (!mac_speed) {
+	} else if (!link_status) {
 		test->flags |= ETH_TEST_FL_FAILED;
 		data[4] = 1;
 	}
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 95d10472f236..eb3f2cb3b93b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -20,6 +20,7 @@
 #include "be.h"
 #include "be_cmds.h"
 #include <asm/div64.h>
+#include <linux/aer.h>
 
 MODULE_VERSION(DRV_VER);
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
@@ -240,9 +241,8 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	status = be_cmd_mac_addr_query(adapter, current_mac,
-				MAC_ADDRESS_TYPE_NETWORK, false,
-				adapter->if_handle, 0);
+	status = be_cmd_mac_addr_query(adapter, current_mac, false,
+				       adapter->if_handle, 0);
 	if (status)
 		goto err;
 
@@ -1075,7 +1075,7 @@ static int be_set_vf_tx_rate(struct net_device *netdev,
 static int be_find_vfs(struct be_adapter *adapter, int vf_state)
 {
 	struct pci_dev *dev, *pdev = adapter->pdev;
-	int vfs = 0, assigned_vfs = 0, pos, vf_fn;
+	int vfs = 0, assigned_vfs = 0, pos;
 	u16 offset, stride;
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
@@ -1086,9 +1086,7 @@ static int be_find_vfs(struct be_adapter *adapter, int vf_state)
 
 	dev = pci_get_device(pdev->vendor, PCI_ANY_ID, NULL);
 	while (dev) {
-		vf_fn = (pdev->devfn + offset + stride * vfs) & 0xFFFF;
-		if (dev->is_virtfn && dev->devfn == vf_fn &&
-			dev->bus->number == pdev->bus->number) {
+		if (dev->is_virtfn && pci_physfn(dev) == pdev) {
 			vfs++;
 			if (dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED)
 				assigned_vfs++;
@@ -1896,6 +1894,8 @@ static int be_tx_qs_create(struct be_adapter *adapter)
 			return status;
 	}
 
+	dev_info(&adapter->pdev->dev, "created %d TX queue(s)\n",
+		 adapter->num_tx_qs);
 	return 0;
 }
 
@@ -1946,10 +1946,9 @@ static int be_rx_cqs_create(struct be_adapter *adapter)
 			return rc;
 	}
 
-	if (adapter->num_rx_qs != MAX_RX_QS)
-		dev_info(&adapter->pdev->dev,
-			"Created only %d receive queues\n", adapter->num_rx_qs);
-
+	dev_info(&adapter->pdev->dev,
+		 "created %d RSS queue(s) and 1 default RX queue\n",
+		 adapter->num_rx_qs - 1);
 	return 0;
 }
 
@@ -2176,8 +2175,7 @@ static uint be_num_rss_want(struct be_adapter *adapter)
 {
 	u32 num = 0;
 	if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
-	     !sriov_want(adapter) && be_physfn(adapter) &&
-	     !be_is_mc(adapter)) {
+	     !sriov_want(adapter) && be_physfn(adapter)) {
 		num = (adapter->be3_native) ? BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
 		num = min_t(u32, num, (u32)netif_get_num_default_rss_queues());
 	}
@@ -2188,6 +2186,7 @@ static void be_msix_enable(struct be_adapter *adapter)
 {
 #define BE_MIN_MSIX_VECTORS		1
 	int i, status, num_vec, num_roce_vec = 0;
+	struct device *dev = &adapter->pdev->dev;
 
 	/* If RSS queues are not used, need a vec for default RX Q */
 	num_vec = min(be_num_rss_want(adapter), num_online_cpus());
@@ -2212,6 +2211,8 @@ static void be_msix_enable(struct be_adapter *adapter)
 				num_vec) == 0)
 			goto done;
 	}
+
+	dev_warn(dev, "MSIx enable failed\n");
 	return;
 done:
 	if (be_roce_supported(adapter)) {
@@ -2225,6 +2226,7 @@ done:
 		}
 	} else
 		adapter->num_msix_vec = num_vec;
+	dev_info(dev, "enabled %d MSI-x vector(s)\n", adapter->num_msix_vec);
 	return;
 }
 
@@ -2441,8 +2443,7 @@ static int be_open(struct net_device *netdev)
 		be_eq_notify(adapter, eqo->q.id, true, false, 0);
 	}
 
-	status = be_cmd_link_status_query(adapter, NULL, NULL,
-					  &link_status, 0);
+	status = be_cmd_link_status_query(adapter, NULL, &link_status, 0);
 	if (!status)
 		be_link_status_update(adapter, link_status);
 
@@ -2646,8 +2647,8 @@ static int be_vf_setup(struct be_adapter *adapter)
 	}
 
 	for_all_vfs(adapter, vf_cfg, vf) {
-		status = be_cmd_link_status_query(adapter, NULL, &lnk_speed,
-						  NULL, vf + 1);
+		lnk_speed = 1000;
+		status = be_cmd_set_qos(adapter, lnk_speed, vf + 1);
 		if (status)
 			goto err;
 		vf_cfg->tx_rate = lnk_speed * 10;
@@ -2671,7 +2672,6 @@ static void be_setup_init(struct be_adapter *adapter)
 	adapter->be3_native = false;
 	adapter->promiscuous = false;
 	adapter->eq_next_idx = 0;
-	adapter->phy.forced_port_speed = -1;
 }
 
 static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle,
@@ -2693,21 +2693,16 @@ static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle,
 		status = be_cmd_get_mac_from_list(adapter, mac,
 						  active_mac, pmac_id, 0);
 		if (*active_mac) {
-			status = be_cmd_mac_addr_query(adapter, mac,
-						       MAC_ADDRESS_TYPE_NETWORK,
-						       false, if_handle,
-						       *pmac_id);
+			status = be_cmd_mac_addr_query(adapter, mac, false,
+						       if_handle, *pmac_id);
 		}
 	} else if (be_physfn(adapter)) {
 		/* For BE3, for PF get permanent MAC */
-		status = be_cmd_mac_addr_query(adapter, mac,
-					       MAC_ADDRESS_TYPE_NETWORK, true,
-					       0, 0);
+		status = be_cmd_mac_addr_query(adapter, mac, true, 0, 0);
 		*active_mac = false;
 	} else {
 		/* For BE3, for VF get soft MAC assigned by PF*/
-		status = be_cmd_mac_addr_query(adapter, mac,
-					       MAC_ADDRESS_TYPE_NETWORK, false,
+		status = be_cmd_mac_addr_query(adapter, mac, false,
 					       if_handle, 0);
 		*active_mac = true;
 	}
@@ -2724,6 +2719,8 @@ static int be_get_config(struct be_adapter *adapter)
 	if (pos) {
 		pci_read_config_word(adapter->pdev, pos + PCI_SRIOV_TOTAL_VF,
 				     &dev_num_vfs);
+		if (!lancer_chip(adapter))
+			dev_num_vfs = min_t(u16, dev_num_vfs, MAX_VFS);
 		adapter->dev_num_vfs = dev_num_vfs;
 	}
 	return 0;
@@ -3437,6 +3434,7 @@ static void be_ctrl_cleanup(struct be_adapter *adapter)
 	if (mem->va)
 		dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va,
 				  mem->dma);
+	kfree(adapter->pmac_id);
 }
 
 static int be_ctrl_init(struct be_adapter *adapter)
@@ -3473,6 +3471,12 @@ static int be_ctrl_init(struct be_adapter *adapter)
 	}
 	memset(rx_filter->va, 0, rx_filter->size);
 
+	/* primary mac needs 1 pmac entry */
+	adapter->pmac_id = kcalloc(adapter->max_pmac_cnt + 1,
+				   sizeof(*adapter->pmac_id), GFP_KERNEL);
+	if (!adapter->pmac_id)
+		return -ENOMEM;
+
 	mutex_init(&adapter->mbox_lock);
 	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
@@ -3543,6 +3547,8 @@ static void __devexit be_remove(struct pci_dev *pdev)
 
 	be_ctrl_cleanup(adapter);
 
+	pci_disable_pcie_error_reporting(pdev);
+
 	pci_set_drvdata(pdev, NULL);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -3609,12 +3615,6 @@ static int be_get_initial_config(struct be_adapter *adapter)
 	else
 		adapter->max_pmac_cnt = BE_VF_UC_PMAC_COUNT;
 
-	/* primary mac needs 1 pmac entry */
-	adapter->pmac_id = kcalloc(adapter->max_pmac_cnt + 1,
-				  sizeof(u32), GFP_KERNEL);
-	if (!adapter->pmac_id)
-		return -ENOMEM;
-
 	status = be_cmd_get_cntl_attributes(adapter);
 	if (status)
 		return status;
@@ -3800,6 +3800,23 @@ static bool be_reset_required(struct be_adapter *adapter)
 	return be_find_vfs(adapter, ENABLED) > 0 ? false : true;
 }
 
+static char *mc_name(struct be_adapter *adapter)
+{
+	if (adapter->function_mode & FLEX10_MODE)
+		return "FLEX10";
+	else if (adapter->function_mode & VNIC_MODE)
+		return "vNIC";
+	else if (adapter->function_mode & UMC_ENABLED)
+		return "UMC";
+	else
+		return "";
+}
+
+static inline char *func_name(struct be_adapter *adapter)
+{
+	return be_physfn(adapter) ? "PF" : "VF";
+}
+
 static int __devinit be_probe(struct pci_dev *pdev,
 			const struct pci_device_id *pdev_id)
 {
@@ -3844,6 +3861,10 @@ static int __devinit be_probe(struct pci_dev *pdev,
 		}
 	}
 
+	status = pci_enable_pcie_error_reporting(pdev);
+	if (status)
+		dev_err(&pdev->dev, "Could not use PCIe error reporting\n");
+
 	status = be_ctrl_init(adapter);
 	if (status)
 		goto free_netdev;
@@ -3886,7 +3907,7 @@ static int __devinit be_probe(struct pci_dev *pdev,
 
 	status = be_setup(adapter);
 	if (status)
-		goto msix_disable;
+		goto stats_clean;
 
 	be_netdev_init(netdev);
 	status = register_netdev(netdev);
@@ -3900,15 +3921,13 @@ static int __devinit be_probe(struct pci_dev *pdev,
 
 	be_cmd_query_port_name(adapter, &port_name);
 
-	dev_info(&pdev->dev, "%s: %s port %c\n", netdev->name, nic_name(pdev),
-		 port_name);
+	dev_info(&pdev->dev, "%s: %s %s port %c\n", nic_name(pdev),
+		 func_name(adapter), mc_name(adapter), port_name);
 
 	return 0;
 
 unsetup:
 	be_clear(adapter);
-msix_disable:
-	be_msix_disable(adapter);
 stats_clean:
 	be_stats_cleanup(adapter);
 ctrl_clean:
@@ -4066,6 +4085,7 @@ static pci_ers_result_t be_eeh_reset(struct pci_dev *pdev)
 	if (status)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	pci_cleanup_aer_uncorrect_error_status(pdev);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 3574e1499dfc..feff51664dcf 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -62,6 +62,13 @@ config FSL_PQ_MDIO
 	---help---
 	  This driver supports the MDIO bus used by the gianfar and UCC drivers.
 
+config FSL_XGMAC_MDIO
+	tristate "Freescale XGMAC MDIO"
+	depends on FSL_SOC
+	select PHYLIB
+	---help---
+	  This driver supports the MDIO bus on the Fman 10G Ethernet MACs.
+
 config UCC_GETH
 	tristate "Freescale QE Gigabit Ethernet"
 	depends on QUICC_ENGINE
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 1752488c9ee5..3d1839afff65 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y)
 endif
 obj-$(CONFIG_FS_ENET) += fs_enet/
 obj-$(CONFIG_FSL_PQ_MDIO) += fsl_pq_mdio.o
+obj-$(CONFIG_FSL_XGMAC_MDIO) += xgmac_mdio.o
 obj-$(CONFIG_GIANFAR) += gianfar_driver.o
 obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o
 gianfar_driver-objs := gianfar.o \
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 9527b28d70d1..c93a05654b46 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -19,54 +19,90 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
-#include <linux/unistd.h>
 #include <linux/slab.h>
-#include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/crc32.h>
 #include <linux/mii.h>
-#include <linux/phy.h>
-#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
+#include <linux/of_device.h>
 
 #include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/uaccess.h>
-#include <asm/ucc.h>
+#include <asm/ucc.h>	/* for ucc_set_qe_mux_mii_mng() */
 
 #include "gianfar.h"
-#include "fsl_pq_mdio.h"
+
+#define MIIMIND_BUSY		0x00000001
+#define MIIMIND_NOTVALID	0x00000004
+#define MIIMCFG_INIT_VALUE	0x00000007
+#define MIIMCFG_RESET		0x80000000
+
+#define MII_READ_COMMAND	0x00000001
+
+struct fsl_pq_mii {
+	u32 miimcfg;	/* MII management configuration reg */
+	u32 miimcom;	/* MII management command reg */
+	u32 miimadd;	/* MII management address reg */
+	u32 miimcon;	/* MII management control reg */
+	u32 miimstat;	/* MII management status reg */
+	u32 miimind;	/* MII management indication reg */
+};
+
+struct fsl_pq_mdio {
+	u8 res1[16];
+	u32 ieventm;	/* MDIO Interrupt event register (for etsec2)*/
+	u32 imaskm;	/* MDIO Interrupt mask register (for etsec2)*/
+	u8 res2[4];
+	u32 emapm;	/* MDIO Event mapping register (for etsec2)*/
+	u8 res3[1280];
+	struct fsl_pq_mii mii;
+	u8 res4[28];
+	u32 utbipar;	/* TBI phy address reg (only on UCC) */
+	u8 res5[2728];
+} __packed;
 
 /* Number of microseconds to wait for an MII register to respond */
 #define MII_TIMEOUT	1000
 
 struct fsl_pq_mdio_priv {
 	void __iomem *map;
-	struct fsl_pq_mdio __iomem *regs;
+	struct fsl_pq_mii __iomem *regs;
+	int irqs[PHY_MAX_ADDR];
+};
+
+/*
+ * Per-device-type data.  Each type of device tree node that we support gets
+ * one of these.
+ *
+ * @mii_offset: the offset of the MII registers within the memory map of the
+ * node.  Some nodes define only the MII registers, and some define the whole
+ * MAC (which includes the MII registers).
+ *
+ * @get_tbipa: determines the address of the TBIPA register
+ *
+ * @ucc_configure: a special function for extra QE configuration
+ */
+struct fsl_pq_mdio_data {
+	unsigned int mii_offset;	/* offset of the MII registers */
+	uint32_t __iomem * (*get_tbipa)(void __iomem *p);
+	void (*ucc_configure)(phys_addr_t start, phys_addr_t end);
 };
 
 /*
- * Write value to the PHY at mii_id at register regnum,
- * on the bus attached to the local interface, which may be different from the
- * generic mdio bus (tied to a single interface), waiting until the write is
- * done before returning. This is helpful in programming interfaces like
- * the TBI which control interfaces like onchip SERDES and are always tied to
- * the local mdio pins, which may not be the same as system mdio bus, used for
+ * Write value to the PHY at mii_id at register regnum, on the bus attached
+ * to the local interface, which may be different from the generic mdio bus
+ * (tied to a single interface), waiting until the write is done before
+ * returning. This is helpful in programming interfaces like the TBI which
+ * control interfaces like onchip SERDES and are always tied to the local
+ * mdio pins, which may not be the same as system mdio bus, used for
  * controlling the external PHYs, for example.
  */
-int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
-		int regnum, u16 value)
+static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
+		u16 value)
 {
+	struct fsl_pq_mdio_priv *priv = bus->priv;
+	struct fsl_pq_mii __iomem *regs = priv->regs;
 	u32 status;
 
 	/* Set the PHY address and the register address we want to write */
@@ -83,20 +119,21 @@ int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
 }
 
 /*
- * Read the bus for PHY at addr mii_id, register regnum, and
- * return the value.  Clears miimcom first.  All PHY operation
- * done on the bus attached to the local interface,
- * which may be different from the generic mdio bus
- * This is helpful in programming interfaces like
- * the TBI which, in turn, control interfaces like onchip SERDES
- * and are always tied to the local mdio pins, which may not be the
+ * Read the bus for PHY at addr mii_id, register regnum, and return the value.
+ * Clears miimcom first.
+ *
+ * All PHY operation done on the bus attached to the local interface, which
+ * may be different from the generic mdio bus.  This is helpful in programming
+ * interfaces like the TBI which, in turn, control interfaces like on-chip
+ * SERDES and are always tied to the local mdio pins, which may not be the
  * same as system mdio bus, used for controlling the external PHYs, for eg.
  */
-int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs,
-		int mii_id, int regnum)
+static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
-	u16 value;
+	struct fsl_pq_mdio_priv *priv = bus->priv;
+	struct fsl_pq_mii __iomem *regs = priv->regs;
 	u32 status;
+	u16 value;
 
 	/* Set the PHY address and the register address we want to read */
 	out_be32(&regs->miimadd, (mii_id << 8) | regnum);
@@ -115,44 +152,15 @@ int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs,
 	/* Grab the value of the register from miimstat */
 	value = in_be32(&regs->miimstat);
 
+	dev_dbg(&bus->dev, "read %04x from address %x/%x\n", value, mii_id, regnum);
 	return value;
 }
 
-static struct fsl_pq_mdio __iomem *fsl_pq_mdio_get_regs(struct mii_bus *bus)
-{
-	struct fsl_pq_mdio_priv *priv = bus->priv;
-
-	return priv->regs;
-}
-
-/*
- * Write value to the PHY at mii_id at register regnum,
- * on the bus, waiting until the write is done before returning.
- */
-int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value)
-{
-	struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus);
-
-	/* Write to the local MII regs */
-	return fsl_pq_local_mdio_write(regs, mii_id, regnum, value);
-}
-
-/*
- * Read the bus for PHY at addr mii_id, register regnum, and
- * return the value.  Clears miimcom first.
- */
-int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
-{
-	struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus);
-
-	/* Read the local MII regs */
-	return fsl_pq_local_mdio_read(regs, mii_id, regnum);
-}
-
 /* Reset the MIIM registers, and wait for the bus to free */
 static int fsl_pq_mdio_reset(struct mii_bus *bus)
 {
-	struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus);
+	struct fsl_pq_mdio_priv *priv = bus->priv;
+	struct fsl_pq_mii __iomem *regs = priv->regs;
 	u32 status;
 
 	mutex_lock(&bus->mdio_lock);
@@ -170,234 +178,291 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus)
 	mutex_unlock(&bus->mdio_lock);
 
 	if (!status) {
-		printk(KERN_ERR "%s: The MII Bus is stuck!\n",
-				bus->name);
+		dev_err(&bus->dev, "timeout waiting for MII bus\n");
 		return -EBUSY;
 	}
 
 	return 0;
 }
 
-void fsl_pq_mdio_bus_name(char *name, struct device_node *np)
+#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
+/*
+ * This is mildly evil, but so is our hardware for doing this.
+ * Also, we have to cast back to struct gfar because of
+ * definition weirdness done in gianfar.h.
+ */
+static uint32_t __iomem *get_gfar_tbipa(void __iomem *p)
 {
-	const u32 *addr;
-	u64 taddr = OF_BAD_ADDR;
-
-	addr = of_get_address(np, 0, NULL, NULL);
-	if (addr)
-		taddr = of_translate_address(np, addr);
+	struct gfar __iomem *enet_regs = p;
 
-	snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name,
-		(unsigned long long)taddr);
+	return &enet_regs->tbipa;
 }
-EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name);
 
+/*
+ * Return the TBIPAR address for an eTSEC2 node
+ */
+static uint32_t __iomem *get_etsec_tbipa(void __iomem *p)
+{
+	return p;
+}
+#endif
 
-static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np)
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
+/*
+ * Return the TBIPAR address for a QE MDIO node
+ */
+static uint32_t __iomem *get_ucc_tbipa(void __iomem *p)
 {
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
-	struct gfar __iomem *enet_regs;
+	struct fsl_pq_mdio __iomem *mdio = p;
 
-	/*
-	 * This is mildly evil, but so is our hardware for doing this.
-	 * Also, we have to cast back to struct gfar because of
-	 * definition weirdness done in gianfar.h.
-	 */
-	if(of_device_is_compatible(np, "fsl,gianfar-mdio") ||
-		of_device_is_compatible(np, "fsl,gianfar-tbi") ||
-		of_device_is_compatible(np, "gianfar")) {
-		enet_regs = (struct gfar __iomem *)regs;
-		return &enet_regs->tbipa;
-	} else if (of_device_is_compatible(np, "fsl,etsec2-mdio") ||
-			of_device_is_compatible(np, "fsl,etsec2-tbi")) {
-		return of_iomap(np, 1);
-	}
-#endif
-	return NULL;
+	return &mdio->utbipar;
 }
 
-
-static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id)
+/*
+ * Find the UCC node that controls the given MDIO node
+ *
+ * For some reason, the QE MDIO nodes are not children of the UCC devices
+ * that control them.  Therefore, we need to scan all UCC nodes looking for
+ * the one that encompases the given MDIO node.  We do this by comparing
+ * physical addresses.  The 'start' and 'end' addresses of the MDIO node are
+ * passed, and the correct UCC node will cover the entire address range.
+ *
+ * This assumes that there is only one QE MDIO node in the entire device tree.
+ */
+static void ucc_configure(phys_addr_t start, phys_addr_t end)
 {
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
+	static bool found_mii_master;
 	struct device_node *np = NULL;
-	int err = 0;
 
-	for_each_compatible_node(np, NULL, "ucc_geth") {
-		struct resource tempres;
+	if (found_mii_master)
+		return;
 
-		err = of_address_to_resource(np, 0, &tempres);
-		if (err)
+	for_each_compatible_node(np, NULL, "ucc_geth") {
+		struct resource res;
+		const uint32_t *iprop;
+		uint32_t id;
+		int ret;
+
+		ret = of_address_to_resource(np, 0, &res);
+		if (ret < 0) {
+			pr_debug("fsl-pq-mdio: no address range in node %s\n",
+				 np->full_name);
 			continue;
+		}
 
 		/* if our mdio regs fall within this UCC regs range */
-		if ((start >= tempres.start) && (end <= tempres.end)) {
-			/* Find the id of the UCC */
-			const u32 *id;
-
-			id = of_get_property(np, "cell-index", NULL);
-			if (!id) {
-				id = of_get_property(np, "device-id", NULL);
-				if (!id)
-					continue;
+		if ((start < res.start) || (end > res.end))
+			continue;
+
+		iprop = of_get_property(np, "cell-index", NULL);
+		if (!iprop) {
+			iprop = of_get_property(np, "device-id", NULL);
+			if (!iprop) {
+				pr_debug("fsl-pq-mdio: no UCC ID in node %s\n",
+					 np->full_name);
+				continue;
 			}
+		}
 
-			*ucc_id = *id;
+		id = be32_to_cpup(iprop);
 
-			return 0;
+		/*
+		 * cell-index and device-id for QE nodes are
+		 * numbered from 1, not 0.
+		 */
+		if (ucc_set_qe_mux_mii_mng(id - 1) < 0) {
+			pr_debug("fsl-pq-mdio: invalid UCC ID in node %s\n",
+				 np->full_name);
+			continue;
 		}
+
+		pr_debug("fsl-pq-mdio: setting node UCC%u to MII master\n", id);
+		found_mii_master = true;
 	}
+}
 
-	if (err)
-		return err;
-	else
-		return -EINVAL;
-#else
-	return -ENODEV;
 #endif
-}
 
-static int fsl_pq_mdio_probe(struct platform_device *ofdev)
+static struct of_device_id fsl_pq_mdio_match[] = {
+#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
+	{
+		.compatible = "fsl,gianfar-tbi",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = 0,
+			.get_tbipa = get_gfar_tbipa,
+		},
+	},
+	{
+		.compatible = "fsl,gianfar-mdio",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = 0,
+			.get_tbipa = get_gfar_tbipa,
+		},
+	},
+	{
+		.type = "mdio",
+		.compatible = "gianfar",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = offsetof(struct fsl_pq_mdio, mii),
+			.get_tbipa = get_gfar_tbipa,
+		},
+	},
+	{
+		.compatible = "fsl,etsec2-tbi",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = offsetof(struct fsl_pq_mdio, mii),
+			.get_tbipa = get_etsec_tbipa,
+		},
+	},
+	{
+		.compatible = "fsl,etsec2-mdio",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = offsetof(struct fsl_pq_mdio, mii),
+			.get_tbipa = get_etsec_tbipa,
+		},
+	},
+#endif
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
+	{
+		.compatible = "fsl,ucc-mdio",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = 0,
+			.get_tbipa = get_ucc_tbipa,
+			.ucc_configure = ucc_configure,
+		},
+	},
+	{
+		/* Legacy UCC MDIO node */
+		.type = "mdio",
+		.compatible = "ucc_geth_phy",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = 0,
+			.get_tbipa = get_ucc_tbipa,
+			.ucc_configure = ucc_configure,
+		},
+	},
+#endif
+	/* No Kconfig option for Fman support yet */
+	{
+		.compatible = "fsl,fman-mdio",
+		.data = &(struct fsl_pq_mdio_data) {
+			.mii_offset = 0,
+			/* Fman TBI operations are handled elsewhere */
+		},
+	},
+
+	{},
+};
+MODULE_DEVICE_TABLE(of, fsl_pq_mdio_match);
+
+static int fsl_pq_mdio_probe(struct platform_device *pdev)
 {
-	struct device_node *np = ofdev->dev.of_node;
+	const struct of_device_id *id =
+		of_match_device(fsl_pq_mdio_match, &pdev->dev);
+	const struct fsl_pq_mdio_data *data = id->data;
+	struct device_node *np = pdev->dev.of_node;
+	struct resource res;
 	struct device_node *tbi;
 	struct fsl_pq_mdio_priv *priv;
-	struct fsl_pq_mdio __iomem *regs = NULL;
-	void __iomem *map;
-	u32 __iomem *tbipa;
 	struct mii_bus *new_bus;
-	int tbiaddr = -1;
-	const u32 *addrp;
-	u64 addr = 0, size = 0;
 	int err;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
+	dev_dbg(&pdev->dev, "found %s compatible node\n", id->compatible);
 
-	new_bus = mdiobus_alloc();
-	if (!new_bus) {
-		err = -ENOMEM;
-		goto err_free_priv;
-	}
+	new_bus = mdiobus_alloc_size(sizeof(*priv));
+	if (!new_bus)
+		return -ENOMEM;
 
+	priv = new_bus->priv;
 	new_bus->name = "Freescale PowerQUICC MII Bus",
-	new_bus->read = &fsl_pq_mdio_read,
-	new_bus->write = &fsl_pq_mdio_write,
-	new_bus->reset = &fsl_pq_mdio_reset,
-	new_bus->priv = priv;
-	fsl_pq_mdio_bus_name(new_bus->id, np);
-
-	addrp = of_get_address(np, 0, &size, NULL);
-	if (!addrp) {
-		err = -EINVAL;
-		goto err_free_bus;
+	new_bus->read = &fsl_pq_mdio_read;
+	new_bus->write = &fsl_pq_mdio_write;
+	new_bus->reset = &fsl_pq_mdio_reset;
+	new_bus->irq = priv->irqs;
+
+	err = of_address_to_resource(np, 0, &res);
+	if (err < 0) {
+		dev_err(&pdev->dev, "could not obtain address information\n");
+		goto error;
 	}
 
-	/* Set the PHY base address */
-	addr = of_translate_address(np, addrp);
-	if (addr == OF_BAD_ADDR) {
-		err = -EINVAL;
-		goto err_free_bus;
-	}
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s@%llx", np->name,
+		(unsigned long long)res.start);
 
-	map = ioremap(addr, size);
-	if (!map) {
+	priv->map = of_iomap(np, 0);
+	if (!priv->map) {
 		err = -ENOMEM;
-		goto err_free_bus;
+		goto error;
 	}
-	priv->map = map;
-
-	if (of_device_is_compatible(np, "fsl,gianfar-mdio") ||
-			of_device_is_compatible(np, "fsl,gianfar-tbi") ||
-			of_device_is_compatible(np, "fsl,ucc-mdio") ||
-			of_device_is_compatible(np, "ucc_geth_phy"))
-		map -= offsetof(struct fsl_pq_mdio, miimcfg);
-	regs = map;
-	priv->regs = regs;
-
-	new_bus->irq = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL);
 
-	if (NULL == new_bus->irq) {
-		err = -ENOMEM;
-		goto err_unmap_regs;
+	/*
+	 * Some device tree nodes represent only the MII registers, and
+	 * others represent the MAC and MII registers.  The 'mii_offset' field
+	 * contains the offset of the MII registers inside the mapped register
+	 * space.
+	 */
+	if (data->mii_offset > resource_size(&res)) {
+		dev_err(&pdev->dev, "invalid register map\n");
+		err = -EINVAL;
+		goto error;
 	}
+	priv->regs = priv->map + data->mii_offset;
 
-	new_bus->parent = &ofdev->dev;
-	dev_set_drvdata(&ofdev->dev, new_bus);
-
-	if (of_device_is_compatible(np, "fsl,gianfar-mdio") ||
-			of_device_is_compatible(np, "fsl,gianfar-tbi") ||
-			of_device_is_compatible(np, "fsl,etsec2-mdio") ||
-			of_device_is_compatible(np, "fsl,etsec2-tbi") ||
-			of_device_is_compatible(np, "gianfar")) {
-		tbipa = get_gfar_tbipa(regs, np);
-		if (!tbipa) {
-			err = -EINVAL;
-			goto err_free_irqs;
-		}
-	} else if (of_device_is_compatible(np, "fsl,ucc-mdio") ||
-			of_device_is_compatible(np, "ucc_geth_phy")) {
-		u32 id;
-		static u32 mii_mng_master;
-
-		tbipa = &regs->utbipar;
-
-		if ((err = get_ucc_id_for_range(addr, addr + size, &id)))
-			goto err_free_irqs;
+	new_bus->parent = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, new_bus);
 
-		if (!mii_mng_master) {
-			mii_mng_master = id;
-			ucc_set_qe_mux_mii_mng(id - 1);
+	if (data->get_tbipa) {
+		for_each_child_of_node(np, tbi) {
+			if (strcmp(tbi->type, "tbi-phy") == 0) {
+				dev_dbg(&pdev->dev, "found TBI PHY node %s\n",
+					strrchr(tbi->full_name, '/') + 1);
+				break;
+			}
 		}
-	} else {
-		err = -ENODEV;
-		goto err_free_irqs;
-	}
 
-	for_each_child_of_node(np, tbi) {
-		if (!strncmp(tbi->type, "tbi-phy", 8))
-			break;
-	}
+		if (tbi) {
+			const u32 *prop = of_get_property(tbi, "reg", NULL);
+			uint32_t __iomem *tbipa;
 
-	if (tbi) {
-		const u32 *prop = of_get_property(tbi, "reg", NULL);
+			if (!prop) {
+				dev_err(&pdev->dev,
+					"missing 'reg' property in node %s\n",
+					tbi->full_name);
+				err = -EBUSY;
+				goto error;
+			}
 
-		if (prop)
-			tbiaddr = *prop;
+			tbipa = data->get_tbipa(priv->map);
 
-		if (tbiaddr == -1) {
-			err = -EBUSY;
-			goto err_free_irqs;
-		} else {
-			out_be32(tbipa, tbiaddr);
+			out_be32(tbipa, be32_to_cpup(prop));
 		}
 	}
 
+	if (data->ucc_configure)
+		data->ucc_configure(res.start, res.end);
+
 	err = of_mdiobus_register(new_bus, np);
 	if (err) {
-		printk (KERN_ERR "%s: Cannot register as MDIO bus\n",
-				new_bus->name);
-		goto err_free_irqs;
+		dev_err(&pdev->dev, "cannot register %s as MDIO bus\n",
+			new_bus->name);
+		goto error;
 	}
 
 	return 0;
 
-err_free_irqs:
-	kfree(new_bus->irq);
-err_unmap_regs:
-	iounmap(priv->map);
-err_free_bus:
+error:
+	if (priv->map)
+		iounmap(priv->map);
+
 	kfree(new_bus);
-err_free_priv:
-	kfree(priv);
+
 	return err;
 }
 
 
-static int fsl_pq_mdio_remove(struct platform_device *ofdev)
+static int fsl_pq_mdio_remove(struct platform_device *pdev)
 {
-	struct device *device = &ofdev->dev;
+	struct device *device = &pdev->dev;
 	struct mii_bus *bus = dev_get_drvdata(device);
 	struct fsl_pq_mdio_priv *priv = bus->priv;
 
@@ -406,41 +471,11 @@ static int fsl_pq_mdio_remove(struct platform_device *ofdev)
 	dev_set_drvdata(device, NULL);
 
 	iounmap(priv->map);
-	bus->priv = NULL;
 	mdiobus_free(bus);
-	kfree(priv);
 
 	return 0;
 }
 
-static struct of_device_id fsl_pq_mdio_match[] = {
-	{
-		.type = "mdio",
-		.compatible = "ucc_geth_phy",
-	},
-	{
-		.type = "mdio",
-		.compatible = "gianfar",
-	},
-	{
-		.compatible = "fsl,ucc-mdio",
-	},
-	{
-		.compatible = "fsl,gianfar-tbi",
-	},
-	{
-		.compatible = "fsl,gianfar-mdio",
-	},
-	{
-		.compatible = "fsl,etsec2-tbi",
-	},
-	{
-		.compatible = "fsl,etsec2-mdio",
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, fsl_pq_mdio_match);
-
 static struct platform_driver fsl_pq_mdio_driver = {
 	.driver = {
 		.name = "fsl-pq_mdio",
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.h b/drivers/net/ethernet/freescale/fsl_pq_mdio.h
deleted file mode 100644
index bd17a2a0139b..000000000000
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Freescale PowerQUICC MDIO Driver -- MII Management Bus Implementation
- * Driver for the MDIO bus controller on Freescale PowerQUICC processors
- *
- * Author: Andy Fleming
- * Modifier: Sandeep Gopalpet
- *
- * Copyright 2002-2004, 2008-2009 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-#ifndef __FSL_PQ_MDIO_H
-#define __FSL_PQ_MDIO_H
-
-#define MIIMIND_BUSY            0x00000001
-#define MIIMIND_NOTVALID        0x00000004
-#define MIIMCFG_INIT_VALUE	0x00000007
-#define MIIMCFG_RESET           0x80000000
-
-#define MII_READ_COMMAND       0x00000001
-
-struct fsl_pq_mdio {
-	u8 res1[16];
-	u32 ieventm;	/* MDIO Interrupt event register (for etsec2)*/
-	u32 imaskm;	/* MDIO Interrupt mask register (for etsec2)*/
-	u8 res2[4];
-	u32 emapm;	/* MDIO Event mapping register (for etsec2)*/
-	u8 res3[1280];
-	u32 miimcfg;		/* MII management configuration reg */
-	u32 miimcom;		/* MII management command reg */
-	u32 miimadd;		/* MII management address reg */
-	u32 miimcon;		/* MII management control reg */
-	u32 miimstat;		/* MII management status reg */
-	u32 miimind;		/* MII management indication reg */
-	u8 reserved[28];	/* Space holder */
-	u32 utbipar;		/* TBI phy address reg (only on UCC) */
-	u8 res4[2728];
-} __packed;
-
-int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum);
-int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value);
-int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
-			  int regnum, u16 value);
-int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id, int regnum);
-int __init fsl_pq_mdio_init(void);
-void fsl_pq_mdio_exit(void);
-void fsl_pq_mdio_bus_name(char *name, struct device_node *np);
-#endif /* FSL_PQ_MDIO_H */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index d3233f59a82e..a1b52ec3b930 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -100,7 +100,6 @@
 #include <linux/of_net.h>
 
 #include "gianfar.h"
-#include "fsl_pq_mdio.h"
 
 #define TX_TIMEOUT      (1*HZ)
 
@@ -395,7 +394,13 @@ static void gfar_init_mac(struct net_device *ndev)
 	if (ndev->features & NETIF_F_IP_CSUM)
 		tctrl |= TCTRL_INIT_CSUM;
 
-	tctrl |= TCTRL_TXSCHED_PRIO;
+	if (priv->prio_sched_en)
+		tctrl |= TCTRL_TXSCHED_PRIO;
+	else {
+		tctrl |= TCTRL_TXSCHED_WRRS;
+		gfar_write(&regs->tr03wt, DEFAULT_WRRS_WEIGHT);
+		gfar_write(&regs->tr47wt, DEFAULT_WRRS_WEIGHT);
+	}
 
 	gfar_write(&regs->tctrl, tctrl);
 
@@ -1161,6 +1166,9 @@ static int gfar_probe(struct platform_device *ofdev)
 	priv->rx_filer_enable = 1;
 	/* Enable most messages by default */
 	priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1;
+	/* use pritority h/w tx queue scheduling for single queue devices */
+	if (priv->num_tx_queues == 1)
+		priv->prio_sched_en = 1;
 
 	/* Carrier starts down, phylib will bring it up */
 	netif_carrier_off(dev);
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 2136c7ff5e6d..4141ef2ddafc 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -301,8 +301,16 @@ extern const char gfar_driver_version[];
 #define TCTRL_TFCPAUSE		0x00000008
 #define TCTRL_TXSCHED_MASK	0x00000006
 #define TCTRL_TXSCHED_INIT	0x00000000
+/* priority scheduling */
 #define TCTRL_TXSCHED_PRIO	0x00000002
+/* weighted round-robin scheduling (WRRS) */
 #define TCTRL_TXSCHED_WRRS	0x00000004
+/* default WRRS weight and policy setting,
+ * tailored to the tr03wt and tr47wt registers:
+ * equal weight for all Tx Qs, measured in 64byte units
+ */
+#define DEFAULT_WRRS_WEIGHT	0x18181818
+
 #define TCTRL_INIT_CSUM		(TCTRL_TUCSEN | TCTRL_IPCSEN)
 
 #define IEVENT_INIT_CLEAR	0xffffffff
@@ -1098,7 +1106,8 @@ struct gfar_private {
 		extended_hash:1,
 		bd_stash_en:1,
 		rx_filer_enable:1,
-		wol_en:1; /* Wake-on-LAN enabled */
+		wol_en:1, /* Wake-on-LAN enabled */
+		prio_sched_en:1; /* Enable priorty based Tx scheduling in Hw */
 	unsigned short padding;
 
 	/* PHY stuff */
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 0daa66b8eca0..b9db0e040563 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -510,7 +510,7 @@ static int gianfar_ptp_probe(struct platform_device *dev)
 
 	spin_unlock_irqrestore(&etsects->lock, flags);
 
-	etsects->clock = ptp_clock_register(&etsects->caps);
+	etsects->clock = ptp_clock_register(&etsects->caps, &dev->dev);
 	if (IS_ERR(etsects->clock)) {
 		err = PTR_ERR(etsects->clock);
 		goto no_clock;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 21c6574c5f15..164288439220 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -42,7 +42,6 @@
 #include <asm/machdep.h>
 
 #include "ucc_geth.h"
-#include "fsl_pq_mdio.h"
 
 #undef DEBUG
 
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
new file mode 100644
index 000000000000..1afb5ea2a984
--- /dev/null
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -0,0 +1,274 @@
+/*
+ * QorIQ 10G MDIO Controller
+ *
+ * Copyright 2012 Freescale Semiconductor, Inc.
+ *
+ * Authors: Andy Fleming <afleming@freescale.com>
+ *          Timur Tabi <timur@freescale.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/mdio.h>
+#include <linux/of_platform.h>
+#include <linux/of_mdio.h>
+
+/* Number of microseconds to wait for a register to respond */
+#define TIMEOUT	1000
+
+struct tgec_mdio_controller {
+	__be32	reserved[12];
+	__be32	mdio_stat;	/* MDIO configuration and status */
+	__be32	mdio_ctl;	/* MDIO control */
+	__be32	mdio_data;	/* MDIO data */
+	__be32	mdio_addr;	/* MDIO address */
+} __packed;
+
+#define MDIO_STAT_CLKDIV(x)	(((x>>1) & 0xff) << 8)
+#define MDIO_STAT_BSY		(1 << 0)
+#define MDIO_STAT_RD_ER		(1 << 1)
+#define MDIO_CTL_DEV_ADDR(x) 	(x & 0x1f)
+#define MDIO_CTL_PORT_ADDR(x)	((x & 0x1f) << 5)
+#define MDIO_CTL_PRE_DIS	(1 << 10)
+#define MDIO_CTL_SCAN_EN	(1 << 11)
+#define MDIO_CTL_POST_INC	(1 << 14)
+#define MDIO_CTL_READ		(1 << 15)
+
+#define MDIO_DATA(x)		(x & 0xffff)
+#define MDIO_DATA_BSY		(1 << 31)
+
+/*
+ * Wait untill the MDIO bus is free
+ */
+static int xgmac_wait_until_free(struct device *dev,
+				 struct tgec_mdio_controller __iomem *regs)
+{
+	uint32_t status;
+
+	/* Wait till the bus is free */
+	status = spin_event_timeout(
+		!((in_be32(&regs->mdio_stat)) & MDIO_STAT_BSY), TIMEOUT, 0);
+	if (!status) {
+		dev_err(dev, "timeout waiting for bus to be free\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+/*
+ * Wait till the MDIO read or write operation is complete
+ */
+static int xgmac_wait_until_done(struct device *dev,
+				 struct tgec_mdio_controller __iomem *regs)
+{
+	uint32_t status;
+
+	/* Wait till the MDIO write is complete */
+	status = spin_event_timeout(
+		!((in_be32(&regs->mdio_data)) & MDIO_DATA_BSY), TIMEOUT, 0);
+	if (!status) {
+		dev_err(dev, "timeout waiting for operation to complete\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+/*
+ * Write value to the PHY for this device to the register at regnum,waiting
+ * until the write is done before it returns.  All PHY configuration has to be
+ * done through the TSEC1 MIIM regs.
+ */
+static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value)
+{
+	struct tgec_mdio_controller __iomem *regs = bus->priv;
+	uint16_t dev_addr = regnum >> 16;
+	int ret;
+
+	/* Setup the MII Mgmt clock speed */
+	out_be32(&regs->mdio_stat, MDIO_STAT_CLKDIV(100));
+
+	ret = xgmac_wait_until_free(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	/* Set the port and dev addr */
+	out_be32(&regs->mdio_ctl,
+		 MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr));
+
+	/* Set the register address */
+	out_be32(&regs->mdio_addr, regnum & 0xffff);
+
+	ret = xgmac_wait_until_free(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	/* Write the value to the register */
+	out_be32(&regs->mdio_data, MDIO_DATA(value));
+
+	ret = xgmac_wait_until_done(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Reads from register regnum in the PHY for device dev, returning the value.
+ * Clears miimcom first.  All PHY configuration has to be done through the
+ * TSEC1 MIIM regs.
+ */
+static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct tgec_mdio_controller __iomem *regs = bus->priv;
+	uint16_t dev_addr = regnum >> 16;
+	uint32_t mdio_ctl;
+	uint16_t value;
+	int ret;
+
+	/* Setup the MII Mgmt clock speed */
+	out_be32(&regs->mdio_stat, MDIO_STAT_CLKDIV(100));
+
+	ret = xgmac_wait_until_free(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	/* Set the Port and Device Addrs */
+	mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
+	out_be32(&regs->mdio_ctl, mdio_ctl);
+
+	/* Set the register address */
+	out_be32(&regs->mdio_addr, regnum & 0xffff);
+
+	ret = xgmac_wait_until_free(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	/* Initiate the read */
+	out_be32(&regs->mdio_ctl, mdio_ctl | MDIO_CTL_READ);
+
+	ret = xgmac_wait_until_done(&bus->dev, regs);
+	if (ret)
+		return ret;
+
+	/* Return all Fs if nothing was there */
+	if (in_be32(&regs->mdio_stat) & MDIO_STAT_RD_ER) {
+		dev_err(&bus->dev, "MDIO read error\n");
+		return 0xffff;
+	}
+
+	value = in_be32(&regs->mdio_data) & 0xffff;
+	dev_dbg(&bus->dev, "read %04x\n", value);
+
+	return value;
+}
+
+/* Reset the MIIM registers, and wait for the bus to free */
+static int xgmac_mdio_reset(struct mii_bus *bus)
+{
+	struct tgec_mdio_controller __iomem *regs = bus->priv;
+	int ret;
+
+	mutex_lock(&bus->mdio_lock);
+
+	/* Setup the MII Mgmt clock speed */
+	out_be32(&regs->mdio_stat, MDIO_STAT_CLKDIV(100));
+
+	ret = xgmac_wait_until_free(&bus->dev, regs);
+
+	mutex_unlock(&bus->mdio_lock);
+
+	return ret;
+}
+
+static int __devinit xgmac_mdio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct mii_bus *bus;
+	struct resource res;
+	int ret;
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret) {
+		dev_err(&pdev->dev, "could not obtain address\n");
+		return ret;
+	}
+
+	bus = mdiobus_alloc_size(PHY_MAX_ADDR * sizeof(int));
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "Freescale XGMAC MDIO Bus";
+	bus->read = xgmac_mdio_read;
+	bus->write = xgmac_mdio_write;
+	bus->reset = xgmac_mdio_reset;
+	bus->irq = bus->priv;
+	bus->parent = &pdev->dev;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%llx", (unsigned long long)res.start);
+
+	/* Set the PHY base address */
+	bus->priv = of_iomap(np, 0);
+	if (!bus->priv) {
+		ret = -ENOMEM;
+		goto err_ioremap;
+	}
+
+	ret = of_mdiobus_register(bus, np);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot register MDIO bus\n");
+		goto err_registration;
+	}
+
+	dev_set_drvdata(&pdev->dev, bus);
+
+	return 0;
+
+err_registration:
+	iounmap(bus->priv);
+
+err_ioremap:
+	mdiobus_free(bus);
+
+	return ret;
+}
+
+static int __devexit xgmac_mdio_remove(struct platform_device *pdev)
+{
+	struct mii_bus *bus = dev_get_drvdata(&pdev->dev);
+
+	mdiobus_unregister(bus);
+	iounmap(bus->priv);
+	mdiobus_free(bus);
+
+	return 0;
+}
+
+static struct of_device_id xgmac_mdio_match[] = {
+	{
+		.compatible = "fsl,fman-xmdio",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgmac_mdio_match);
+
+static struct platform_driver xgmac_mdio_driver = {
+	.driver = {
+		.name = "fsl-fman_xmdio",
+		.of_match_table = xgmac_mdio_match,
+	},
+	.probe = xgmac_mdio_probe,
+	.remove = xgmac_mdio_remove,
+};
+
+module_platform_driver(xgmac_mdio_driver);
+
+MODULE_DESCRIPTION("Freescale QorIQ 10G MDIO Controller");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/i825xx/Kconfig b/drivers/net/ethernet/i825xx/Kconfig
index fed5080a6b62..959faf7388e2 100644
--- a/drivers/net/ethernet/i825xx/Kconfig
+++ b/drivers/net/ethernet/i825xx/Kconfig
@@ -150,7 +150,7 @@ config SUN3_82586
 
 config ZNET
 	tristate "Zenith Z-Note support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL && ISA_DMA_API
+	depends on EXPERIMENTAL && ISA_DMA_API && X86
 	---help---
 	  The Zenith Z-Note notebook computer has a built-in network
 	  (Ethernet) card, and this is the Linux driver for it. Note that the
diff --git a/drivers/net/ethernet/i825xx/znet.c b/drivers/net/ethernet/i825xx/znet.c
index ba4e0cea3506..c9479e081b8a 100644
--- a/drivers/net/ethernet/i825xx/znet.c
+++ b/drivers/net/ethernet/i825xx/znet.c
@@ -865,14 +865,14 @@ static void hardware_init(struct net_device *dev)
 	disable_dma(znet->rx_dma); 		/* reset by an interrupting task. */
 	clear_dma_ff(znet->rx_dma);
 	set_dma_mode(znet->rx_dma, DMA_RX_MODE);
-	set_dma_addr(znet->rx_dma, (unsigned int) znet->rx_start);
+	set_dma_addr(znet->rx_dma, isa_virt_to_bus(znet->rx_start));
 	set_dma_count(znet->rx_dma, RX_BUF_SIZE);
 	enable_dma(znet->rx_dma);
 	/* Now set up the Tx channel. */
 	disable_dma(znet->tx_dma);
 	clear_dma_ff(znet->tx_dma);
 	set_dma_mode(znet->tx_dma, DMA_TX_MODE);
-	set_dma_addr(znet->tx_dma, (unsigned int) znet->tx_start);
+	set_dma_addr(znet->tx_dma, isa_virt_to_bus(znet->tx_start));
 	set_dma_count(znet->tx_dma, znet->tx_buf_len<<1);
 	enable_dma(znet->tx_dma);
 	release_dma_lock(flags);
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 736a7d987db5..9089d00f1421 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -174,6 +174,20 @@ static int e1000_get_settings(struct net_device *netdev,
 
 	ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
 			 hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	/* MDI-X => 1; MDI => 0 */
+	if ((hw->media_type == e1000_media_type_copper) &&
+	    netif_carrier_ok(netdev))
+		ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
+							ETH_TP_MDI_X :
+							ETH_TP_MDI);
+	else
+		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+
+	if (hw->mdix == AUTO_ALL_MODES)
+		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+	else
+		ecmd->eth_tp_mdix_ctrl = hw->mdix;
 	return 0;
 }
 
@@ -183,6 +197,22 @@ static int e1000_set_settings(struct net_device *netdev,
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 
+	/*
+	 * 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->media_type != e1000_media_type_copper)
+			return -EOPNOTSUPP;
+
+		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+			e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
+	}
+
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
 
@@ -199,12 +229,21 @@ static int e1000_set_settings(struct net_device *netdev,
 		ecmd->advertising = hw->autoneg_advertised;
 	} else {
 		u32 speed = ethtool_cmd_speed(ecmd);
+		/* calling this overrides forced MDI setting */
 		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
 			clear_bit(__E1000_RESETTING, &adapter->flags);
 			return -EINVAL;
 		}
 	}
 
+	/* MDI-X => 2; MDI => 1; Auto => 3 */
+	if (ecmd->eth_tp_mdix_ctrl) {
+		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+			hw->mdix = AUTO_ALL_MODES;
+		else
+			hw->mdix = ecmd->eth_tp_mdix_ctrl;
+	}
+
 	/* reset the link */
 
 	if (netif_running(adapter->netdev)) {
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index f3f9aeb7d1e1..222bfaff4622 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2014,6 +2014,7 @@ static void e1000_clean_tx_ring(struct e1000_adapter *adapter,
 		e1000_unmap_and_free_tx_resource(adapter, buffer_info);
 	}
 
+	netdev_reset_queue(adapter->netdev);
 	size = sizeof(struct e1000_buffer) * tx_ring->count;
 	memset(tx_ring->buffer_info, 0, size);
 
@@ -3273,6 +3274,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 	                     nr_frags, mss);
 
 	if (count) {
+		netdev_sent_queue(netdev, skb->len);
 		skb_tx_timestamp(skb);
 
 		e1000_tx_queue(adapter, tx_ring, tx_flags, count);
@@ -3860,6 +3862,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 	unsigned int i, eop;
 	unsigned int count = 0;
 	unsigned int total_tx_bytes=0, total_tx_packets=0;
+	unsigned int bytes_compl = 0, pkts_compl = 0;
 
 	i = tx_ring->next_to_clean;
 	eop = tx_ring->buffer_info[i].next_to_watch;
@@ -3877,6 +3880,11 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 			if (cleaned) {
 				total_tx_packets += buffer_info->segs;
 				total_tx_bytes += buffer_info->bytecount;
+				if (buffer_info->skb) {
+					bytes_compl += buffer_info->skb->len;
+					pkts_compl++;
+				}
+
 			}
 			e1000_unmap_and_free_tx_resource(adapter, buffer_info);
 			tx_desc->upper.data = 0;
@@ -3890,6 +3898,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 
 	tx_ring->next_to_clean = i;
 
+	netdev_completed_queue(netdev, pkts_compl, bytes_compl);
+
 #define TX_WAKE_THRESHOLD 32
 	if (unlikely(count && netif_carrier_ok(netdev) &&
 		     E1000_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD)) {
@@ -4950,6 +4960,10 @@ int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx)
 	default:
 		goto err_inval;
 	}
+
+	/* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+	hw->mdix = AUTO_ALL_MODES;
+
 	return 0;
 
 err_inval:
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 080c89093feb..c98586408005 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -653,7 +653,7 @@ static void e1000_put_hw_semaphore_82574(struct e1000_hw *hw)
  **/
 static s32 e1000_set_d0_lplu_state_82574(struct e1000_hw *hw, bool active)
 {
-	u16 data = er32(POEMB);
+	u32 data = er32(POEMB);
 
 	if (active)
 		data |= E1000_PHY_CTRL_D0A_LPLU;
@@ -677,7 +677,7 @@ static s32 e1000_set_d0_lplu_state_82574(struct e1000_hw *hw, bool active)
  **/
 static s32 e1000_set_d3_lplu_state_82574(struct e1000_hw *hw, bool active)
 {
-	u16 data = er32(POEMB);
+	u32 data = er32(POEMB);
 
 	if (!active) {
 		data &= ~E1000_PHY_CTRL_NOND0A_LPLU;
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 0349e2478df8..c11ac2756667 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -199,6 +199,11 @@ static int e1000_get_settings(struct net_device *netdev,
 	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;
 }
 
@@ -241,6 +246,10 @@ static int e1000_set_spd_dplx(struct e1000_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:
@@ -264,6 +273,22 @@ static int e1000_set_settings(struct net_device *netdev,
 		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)) {
+			e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
+	}
+
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
@@ -282,20 +307,32 @@ static int e1000_set_settings(struct net_device *netdev,
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
 		u32 speed = ethtool_cmd_speed(ecmd);
+		/* calling this overrides forced MDI setting */
 		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
 			clear_bit(__E1000_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)) {
 		e1000e_down(adapter);
 		e1000e_up(adapter);
-	} else {
+	} else
 		e1000e_reset(adapter);
-	}
 
 	clear_bit(__E1000_RESETTING, &adapter->state);
 	return 0;
@@ -1905,7 +1942,8 @@ static int e1000_set_coalesce(struct net_device *netdev,
 		return -EINVAL;
 
 	if (ec->rx_coalesce_usecs == 4) {
-		adapter->itr = adapter->itr_setting = 4;
+		adapter->itr_setting = 4;
+		adapter->itr = adapter->itr_setting;
 	} else if (ec->rx_coalesce_usecs <= 3) {
 		adapter->itr = 20000;
 		adapter->itr_setting = ec->rx_coalesce_usecs;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 3f0223ac4c7c..fb659dd8db03 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -56,7 +56,7 @@
 
 #define DRV_EXTRAVERSION "-k"
 
-#define DRV_VERSION "2.0.0" DRV_EXTRAVERSION
+#define DRV_VERSION "2.1.4" DRV_EXTRAVERSION
 char e1000e_driver_name[] = "e1000e";
 const char e1000e_driver_version[] = DRV_VERSION;
 
@@ -3446,7 +3446,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 
 			/*
 			 * if short on Rx space, Rx wins and must trump Tx
-			 * adjustment or use Early Receive if available
+			 * adjustment
 			 */
 			if (pba < min_rx_space)
 				pba = min_rx_space;
@@ -3755,6 +3755,10 @@ static irqreturn_t e1000_intr_msi_test(int irq, void *data)
 	e_dbg("icr is %08X\n", icr);
 	if (icr & E1000_ICR_RXSEQ) {
 		adapter->flags &= ~FLAG_MSI_TEST_FAILED;
+		/*
+		 * Force memory writes to complete before acknowledging the
+		 * interrupt is handled.
+		 */
 		wmb();
 	}
 
@@ -3796,6 +3800,10 @@ static int e1000_test_msi_interrupt(struct e1000_adapter *adapter)
 		goto msi_test_failed;
 	}
 
+	/*
+	 * Force memory writes to complete before enabling and firing an
+	 * interrupt.
+	 */
 	wmb();
 
 	e1000_irq_enable(adapter);
@@ -3807,7 +3815,7 @@ static int e1000_test_msi_interrupt(struct e1000_adapter *adapter)
 
 	e1000_irq_disable(adapter);
 
-	rmb();
+	rmb();			/* read flags after interrupt has been fired */
 
 	if (adapter->flags & FLAG_MSI_TEST_FAILED) {
 		adapter->int_mode = E1000E_INT_MODE_LEGACY;
@@ -4670,7 +4678,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb)
 	struct e1000_buffer *buffer_info;
 	unsigned int i;
 	u32 cmd_length = 0;
-	u16 ipcse = 0, tucse, mss;
+	u16 ipcse = 0, mss;
 	u8 ipcss, ipcso, tucss, tucso, hdr_len;
 
 	if (!skb_is_gso(skb))
@@ -4704,7 +4712,6 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb)
 	ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data;
 	tucss = skb_transport_offset(skb);
 	tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data;
-	tucse = 0;
 
 	cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE |
 	               E1000_TXD_CMD_TCP | (skb->len - (hdr_len)));
@@ -4718,7 +4725,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb)
 	context_desc->lower_setup.ip_fields.ipcse  = cpu_to_le16(ipcse);
 	context_desc->upper_setup.tcp_fields.tucss = tucss;
 	context_desc->upper_setup.tcp_fields.tucso = tucso;
-	context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse);
+	context_desc->upper_setup.tcp_fields.tucse = 0;
 	context_desc->tcp_seg_setup.fields.mss     = cpu_to_le16(mss);
 	context_desc->tcp_seg_setup.fields.hdr_len = hdr_len;
 	context_desc->cmd_and_length = cpu_to_le32(cmd_length);
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index b860d4f7ea2a..fc62a3f3a5be 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -84,8 +84,9 @@ static const u16 e1000_igp_2_cable_length_table[] = {
 #define I82577_PHY_STATUS2_SPEED_1000MBPS 0x0200
 
 /* I82577 PHY Control 2 */
-#define I82577_PHY_CTRL2_AUTO_MDIX        0x0400
-#define I82577_PHY_CTRL2_FORCE_MDI_MDIX   0x0200
+#define I82577_PHY_CTRL2_MANUAL_MDIX      0x0200
+#define I82577_PHY_CTRL2_AUTO_MDI_MDIX    0x0400
+#define I82577_PHY_CTRL2_MDIX_CFG_MASK    0x0600
 
 /* I82577 PHY Diagnostics Status */
 #define I82577_DSTATUS_CABLE_LENGTH       0x03FC
@@ -702,6 +703,32 @@ s32 e1000_copper_link_setup_82577(struct e1000_hw *hw)
 	if (ret_val)
 		return ret_val;
 
+	/* Set MDI/MDIX mode */
+	ret_val = e1e_rphy(hw, I82577_PHY_CTRL_2, &phy_data);
+	if (ret_val)
+		return ret_val;
+	phy_data &= ~I82577_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 |= I82577_PHY_CTRL2_MANUAL_MDIX;
+		break;
+	case 0:
+	default:
+		phy_data |= I82577_PHY_CTRL2_AUTO_MDI_MDIX;
+		break;
+	}
+	ret_val = e1e_wphy(hw, I82577_PHY_CTRL_2, phy_data);
+	if (ret_val)
+		return ret_val;
+
 	return e1000_set_master_slave_mode(hw);
 }
 
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()));
+	}
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 5fd5d04c26c9..89f40e51fc13 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -32,7 +32,7 @@
 
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
-ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
+ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\
               ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
               ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index b9623e9ea895..5bd26763554c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -78,6 +78,9 @@
 
 /* Supported Rx Buffer Sizes */
 #define IXGBE_RXBUFFER_256    256  /* Used for skb receive header */
+#define IXGBE_RXBUFFER_2K    2048
+#define IXGBE_RXBUFFER_3K    3072
+#define IXGBE_RXBUFFER_4K    4096
 #define IXGBE_MAX_RXBUFFER  16384  /* largest size for a single descriptor */
 
 /*
@@ -104,6 +107,7 @@
 #define IXGBE_TX_FLAGS_FSO		(u32)(1 << 6)
 #define IXGBE_TX_FLAGS_TXSW		(u32)(1 << 7)
 #define IXGBE_TX_FLAGS_TSTAMP		(u32)(1 << 8)
+#define IXGBE_TX_FLAGS_NO_IFCS		(u32)(1 << 9)
 #define IXGBE_TX_FLAGS_VLAN_MASK	0xffff0000
 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT  29
@@ -293,16 +297,25 @@ struct ixgbe_ring_feature {
  * this is twice the size of a half page we need to double the page order
  * for FCoE enabled Rx queues.
  */
-#if defined(IXGBE_FCOE) && (PAGE_SIZE < 8192)
-static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring)
+static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring)
 {
-	return test_bit(__IXGBE_RX_FCOE, &ring->state) ? 1 : 0;
+#ifdef IXGBE_FCOE
+	if (test_bit(__IXGBE_RX_FCOE, &ring->state))
+		return (PAGE_SIZE < 8192) ? IXGBE_RXBUFFER_4K :
+					    IXGBE_RXBUFFER_3K;
+#endif
+	return IXGBE_RXBUFFER_2K;
 }
-#else
-#define ixgbe_rx_pg_order(_ring) 0
+
+static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring)
+{
+#ifdef IXGBE_FCOE
+	if (test_bit(__IXGBE_RX_FCOE, &ring->state))
+		return (PAGE_SIZE < 8192) ? 1 : 0;
 #endif
+	return 0;
+}
 #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring))
-#define ixgbe_rx_bufsz(_ring) ((PAGE_SIZE / 2) << ixgbe_rx_pg_order(_ring))
 
 struct ixgbe_ring_container {
 	struct ixgbe_ring *ring;	/* pointer to linked list of rings */
@@ -584,6 +597,9 @@ struct ixgbe_adapter {
 #ifdef CONFIG_IXGBE_HWMON
 	struct hwmon_buff ixgbe_hwmon_buff;
 #endif /* CONFIG_IXGBE_HWMON */
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *ixgbe_dbg_adapter;
+#endif /*CONFIG_DEBUG_FS*/
 };
 
 struct ixgbe_fdir_filter {
@@ -712,7 +728,12 @@ extern int ixgbe_fcoe_get_hbainfo(struct net_device *netdev,
 				  struct netdev_fcoe_hbainfo *info);
 extern u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter);
 #endif /* IXGBE_FCOE */
-
+#ifdef CONFIG_DEBUG_FS
+extern void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter);
+extern void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter);
+extern void ixgbe_dbg_init(void);
+extern void ixgbe_dbg_exit(void);
+#endif /* CONFIG_DEBUG_FS */
 static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring)
 {
 	return netdev_get_tx_queue(ring->netdev, ring->queue_index);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
new file mode 100644
index 000000000000..8d3a21889099
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -0,0 +1,300 @@
+/*******************************************************************************
+
+  Intel 10 Gigabit PCI Express Linux driver
+  Copyright(c) 1999 - 2012 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,
+  version 2, as published by the Free Software Foundation.
+
+  This program is distributed in the hope it will be useful, but WITHOUT
+  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+  more details.
+
+  You should have received a copy of the GNU General Public License along with
+  this program; if not, write to the Free Software Foundation, Inc.,
+  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+  The full GNU General Public License is included in this distribution in
+  the file called "COPYING".
+
+  Contact Information:
+  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+
+*******************************************************************************/
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+#include "ixgbe.h"
+
+static struct dentry *ixgbe_dbg_root;
+
+static char ixgbe_dbg_reg_ops_buf[256] = "";
+
+/**
+ * ixgbe_dbg_reg_ops_open - prep the debugfs pokee data item when opened
+ * @inode: inode that was opened
+ * @filp:  file info
+ *
+ * Stash the adapter pointer hiding in the inode into the file pointer where
+ * we can find it later in the read and write calls
+ **/
+static int ixgbe_dbg_reg_ops_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+	return 0;
+}
+
+/**
+ * ixgbe_dbg_reg_ops_read - read for reg_ops datum
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer,
+				    size_t count, loff_t *ppos)
+{
+	struct ixgbe_adapter *adapter = filp->private_data;
+	char buf[256];
+	int bytes_not_copied;
+	int len;
+
+	/* don't allow partial reads */
+	if (*ppos != 0)
+		return 0;
+
+	len = snprintf(buf, sizeof(buf), "%s: %s\n",
+		       adapter->netdev->name, ixgbe_dbg_reg_ops_buf);
+	if (count < len)
+		return -ENOSPC;
+	bytes_not_copied = copy_to_user(buffer, buf, len);
+	if (bytes_not_copied < 0)
+		return bytes_not_copied;
+
+	*ppos = len;
+	return len;
+}
+
+/**
+ * ixgbe_dbg_reg_ops_write - write into reg_ops datum
+ * @filp: the opened file
+ * @buffer: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ **/
+static ssize_t ixgbe_dbg_reg_ops_write(struct file *filp,
+				     const char __user *buffer,
+				     size_t count, loff_t *ppos)
+{
+	struct ixgbe_adapter *adapter = filp->private_data;
+	int bytes_not_copied;
+
+	/* don't allow partial writes */
+	if (*ppos != 0)
+		return 0;
+	if (count >= sizeof(ixgbe_dbg_reg_ops_buf))
+		return -ENOSPC;
+
+	bytes_not_copied = copy_from_user(ixgbe_dbg_reg_ops_buf, buffer, count);
+	if (bytes_not_copied < 0)
+		return bytes_not_copied;
+	else if (bytes_not_copied < count)
+		count -= bytes_not_copied;
+	else
+		return -ENOSPC;
+	ixgbe_dbg_reg_ops_buf[count] = '\0';
+
+	if (strncmp(ixgbe_dbg_reg_ops_buf, "write", 5) == 0) {
+		u32 reg, value;
+		int cnt;
+		cnt = sscanf(&ixgbe_dbg_reg_ops_buf[5], "%x %x", &reg, &value);
+		if (cnt == 2) {
+			IXGBE_WRITE_REG(&adapter->hw, reg, value);
+			value = IXGBE_READ_REG(&adapter->hw, reg);
+			e_dev_info("write: 0x%08x = 0x%08x\n", reg, value);
+		} else {
+			e_dev_info("write <reg> <value>\n");
+		}
+	} else if (strncmp(ixgbe_dbg_reg_ops_buf, "read", 4) == 0) {
+		u32 reg, value;
+		int cnt;
+		cnt = sscanf(&ixgbe_dbg_reg_ops_buf[4], "%x", &reg);
+		if (cnt == 1) {
+			value = IXGBE_READ_REG(&adapter->hw, reg);
+			e_dev_info("read 0x%08x = 0x%08x\n", reg, value);
+		} else {
+			e_dev_info("read <reg>\n");
+		}
+	} else {
+		e_dev_info("Unknown command %s\n", ixgbe_dbg_reg_ops_buf);
+		e_dev_info("Available commands:\n");
+		e_dev_info("   read <reg>\n");
+		e_dev_info("   write <reg> <value>\n");
+	}
+	return count;
+}
+
+static const struct file_operations ixgbe_dbg_reg_ops_fops = {
+	.owner = THIS_MODULE,
+	.open =  ixgbe_dbg_reg_ops_open,
+	.read =  ixgbe_dbg_reg_ops_read,
+	.write = ixgbe_dbg_reg_ops_write,
+};
+
+static char ixgbe_dbg_netdev_ops_buf[256] = "";
+
+/**
+ * ixgbe_dbg_netdev_ops_open - prep the debugfs netdev_ops data item
+ * @inode: inode that was opened
+ * @filp: file info
+ *
+ * Stash the adapter pointer hiding in the inode into the file pointer
+ * where we can find it later in the read and write calls
+ **/
+static int ixgbe_dbg_netdev_ops_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+	return 0;
+}
+
+/**
+ * ixgbe_dbg_netdev_ops_read - read for netdev_ops datum
+ * @filp: the opened file
+ * @buffer: where to write the data for the user to read
+ * @count: the size of the user's buffer
+ * @ppos: file position offset
+ **/
+static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp,
+					 char __user *buffer,
+					 size_t count, loff_t *ppos)
+{
+	struct ixgbe_adapter *adapter = filp->private_data;
+	char buf[256];
+	int bytes_not_copied;
+	int len;
+
+	/* don't allow partial reads */
+	if (*ppos != 0)
+		return 0;
+
+	len = snprintf(buf, sizeof(buf), "%s: %s\n",
+		       adapter->netdev->name, ixgbe_dbg_netdev_ops_buf);
+	if (count < len)
+		return -ENOSPC;
+	bytes_not_copied = copy_to_user(buffer, buf, len);
+	if (bytes_not_copied < 0)
+		return bytes_not_copied;
+
+	*ppos = len;
+	return len;
+}
+
+/**
+ * ixgbe_dbg_netdev_ops_write - write into netdev_ops datum
+ * @filp: the opened file
+ * @buffer: where to find the user's data
+ * @count: the length of the user's data
+ * @ppos: file position offset
+ **/
+static ssize_t ixgbe_dbg_netdev_ops_write(struct file *filp,
+					  const char __user *buffer,
+					  size_t count, loff_t *ppos)
+{
+	struct ixgbe_adapter *adapter = filp->private_data;
+	int bytes_not_copied;
+
+	/* don't allow partial writes */
+	if (*ppos != 0)
+		return 0;
+	if (count >= sizeof(ixgbe_dbg_netdev_ops_buf))
+		return -ENOSPC;
+
+	bytes_not_copied = copy_from_user(ixgbe_dbg_netdev_ops_buf,
+					  buffer, count);
+	if (bytes_not_copied < 0)
+		return bytes_not_copied;
+	else if (bytes_not_copied < count)
+		count -= bytes_not_copied;
+	else
+		return -ENOSPC;
+	ixgbe_dbg_netdev_ops_buf[count] = '\0';
+
+	if (strncmp(ixgbe_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) {
+		adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev);
+		e_dev_info("tx_timeout called\n");
+	} else {
+		e_dev_info("Unknown command: %s\n", ixgbe_dbg_netdev_ops_buf);
+		e_dev_info("Available commands:\n");
+		e_dev_info("    tx_timeout\n");
+	}
+	return count;
+}
+
+static const struct file_operations ixgbe_dbg_netdev_ops_fops = {
+	.owner = THIS_MODULE,
+	.open = ixgbe_dbg_netdev_ops_open,
+	.read = ixgbe_dbg_netdev_ops_read,
+	.write = ixgbe_dbg_netdev_ops_write,
+};
+
+/**
+ * ixgbe_dbg_adapter_init - setup the debugfs directory for the adapter
+ * @adapter: the adapter that is starting up
+ **/
+void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter)
+{
+	const char *name = pci_name(adapter->pdev);
+	struct dentry *pfile;
+	adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root);
+	if (adapter->ixgbe_dbg_adapter) {
+		pfile = debugfs_create_file("reg_ops", 0600,
+					    adapter->ixgbe_dbg_adapter, adapter,
+					    &ixgbe_dbg_reg_ops_fops);
+		if (!pfile)
+			e_dev_err("debugfs reg_ops for %s failed\n", name);
+		pfile = debugfs_create_file("netdev_ops", 0600,
+					    adapter->ixgbe_dbg_adapter, adapter,
+					    &ixgbe_dbg_netdev_ops_fops);
+		if (!pfile)
+			e_dev_err("debugfs netdev_ops for %s failed\n", name);
+	} else {
+		e_dev_err("debugfs entry for %s failed\n", name);
+	}
+}
+
+/**
+ * ixgbe_dbg_adapter_exit - clear out the adapter's debugfs entries
+ * @pf: the pf that is stopping
+ **/
+void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter)
+{
+	if (adapter->ixgbe_dbg_adapter)
+		debugfs_remove_recursive(adapter->ixgbe_dbg_adapter);
+	adapter->ixgbe_dbg_adapter = NULL;
+}
+
+/**
+ * ixgbe_dbg_init - start up debugfs for the driver
+ **/
+void ixgbe_dbg_init(void)
+{
+	ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL);
+	if (ixgbe_dbg_root == NULL)
+		pr_err("init of debugfs failed\n");
+}
+
+/**
+ * ixgbe_dbg_exit - clean out the driver's debugfs entries
+ **/
+void ixgbe_dbg_exit(void)
+{
+	debugfs_remove_recursive(ixgbe_dbg_root);
+}
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ee61819d6088..868af6938219 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1167,7 +1167,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 	}
 
 	bi->dma = dma;
-	bi->page_offset ^= ixgbe_rx_bufsz(rx_ring);
+	bi->page_offset = 0;
 
 	return true;
 }
@@ -1320,29 +1320,6 @@ static unsigned int ixgbe_get_headlen(unsigned char *data,
 		return max_len;
 }
 
-static void ixgbe_get_rsc_cnt(struct ixgbe_ring *rx_ring,
-			      union ixgbe_adv_rx_desc *rx_desc,
-			      struct sk_buff *skb)
-{
-	__le32 rsc_enabled;
-	u32 rsc_cnt;
-
-	if (!ring_is_rsc_enabled(rx_ring))
-		return;
-
-	rsc_enabled = rx_desc->wb.lower.lo_dword.data &
-		      cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK);
-
-	/* If this is an RSC frame rsc_cnt should be non-zero */
-	if (!rsc_enabled)
-		return;
-
-	rsc_cnt = le32_to_cpu(rsc_enabled);
-	rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT;
-
-	IXGBE_CB(skb)->append_cnt += rsc_cnt - 1;
-}
-
 static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
 				   struct sk_buff *skb)
 {
@@ -1440,16 +1417,28 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
 
 	prefetch(IXGBE_RX_DESC(rx_ring, ntc));
 
-	if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
-		return false;
+	/* update RSC append count if present */
+	if (ring_is_rsc_enabled(rx_ring)) {
+		__le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data &
+				     cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK);
+
+		if (unlikely(rsc_enabled)) {
+			u32 rsc_cnt = le32_to_cpu(rsc_enabled);
+
+			rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT;
+			IXGBE_CB(skb)->append_cnt += rsc_cnt - 1;
 
-	/* append_cnt indicates packet is RSC, if so fetch nextp */
-	if (IXGBE_CB(skb)->append_cnt) {
-		ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
-		ntc &= IXGBE_RXDADV_NEXTP_MASK;
-		ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
+			/* update ntc based on RSC value */
+			ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
+			ntc &= IXGBE_RXDADV_NEXTP_MASK;
+			ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
+		}
 	}
 
+	/* if we are the last buffer then there is nothing else to do */
+	if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
+		return false;
+
 	/* place skb in next buffer to be received */
 	rx_ring->rx_buffer_info[ntc].skb = skb;
 	rx_ring->rx_stats.non_eop_descs++;
@@ -1458,6 +1447,78 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
 }
 
 /**
+ * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @skb: pointer to current skb being adjusted
+ *
+ * This function is an ixgbe specific version of __pskb_pull_tail.  The
+ * main difference between this version and the original function is that
+ * this function can make several assumptions about the state of things
+ * that allow for significant optimizations versus the standard function.
+ * As a result we can do things like drop a frag and maintain an accurate
+ * truesize for the skb.
+ */
+static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
+			    struct sk_buff *skb)
+{
+	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	unsigned char *va;
+	unsigned int pull_len;
+
+	/*
+	 * it is valid to use page_address instead of kmap since we are
+	 * working with pages allocated out of the lomem pool per
+	 * alloc_page(GFP_ATOMIC)
+	 */
+	va = skb_frag_address(frag);
+
+	/*
+	 * we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	frag->page_offset += pull_len;
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+/**
+ * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @skb: pointer to current skb being updated
+ *
+ * This function provides a basic DMA sync up for the first fragment of an
+ * skb.  The reason for doing this is that the first fragment cannot be
+ * unmapped until we have reached the end of packet descriptor for a buffer
+ * chain.
+ */
+static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
+				struct sk_buff *skb)
+{
+	/* if the page was released unmap it, else just sync our portion */
+	if (unlikely(IXGBE_CB(skb)->page_released)) {
+		dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
+			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+		IXGBE_CB(skb)->page_released = false;
+	} else {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      IXGBE_CB(skb)->dma,
+					      frag->page_offset,
+					      ixgbe_rx_bufsz(rx_ring),
+					      DMA_FROM_DEVICE);
+	}
+	IXGBE_CB(skb)->dma = 0;
+}
+
+/**
  * ixgbe_cleanup_headers - Correct corrupted or empty headers
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
@@ -1479,24 +1540,7 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 				  union ixgbe_adv_rx_desc *rx_desc,
 				  struct sk_buff *skb)
 {
-	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
 	struct net_device *netdev = rx_ring->netdev;
-	unsigned char *va;
-	unsigned int pull_len;
-
-	/* if the page was released unmap it, else just sync our portion */
-	if (unlikely(IXGBE_CB(skb)->page_released)) {
-		dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
-			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
-		IXGBE_CB(skb)->page_released = false;
-	} else {
-		dma_sync_single_range_for_cpu(rx_ring->dev,
-					      IXGBE_CB(skb)->dma,
-					      frag->page_offset,
-					      ixgbe_rx_bufsz(rx_ring),
-					      DMA_FROM_DEVICE);
-	}
-	IXGBE_CB(skb)->dma = 0;
 
 	/* verify that the packet does not have any known errors */
 	if (unlikely(ixgbe_test_staterr(rx_desc,
@@ -1506,40 +1550,9 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 		return true;
 	}
 
-	/*
-	 * it is valid to use page_address instead of kmap since we are
-	 * working with pages allocated out of the lomem pool per
-	 * alloc_page(GFP_ATOMIC)
-	 */
-	va = skb_frag_address(frag);
-
-	/*
-	 * we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = skb_frag_size(frag);
-	if (pull_len > IXGBE_RX_HDR_SIZE)
-		pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
-
-	/* update all of the pointers */
-	skb_frag_size_sub(frag, pull_len);
-	frag->page_offset += pull_len;
-	skb->data_len -= pull_len;
-	skb->tail += pull_len;
-
-	/*
-	 * if we sucked the frag empty then we should free it,
-	 * if there are other frags here something is screwed up in hardware
-	 */
-	if (skb_frag_size(frag) == 0) {
-		BUG_ON(skb_shinfo(skb)->nr_frags != 1);
-		skb_shinfo(skb)->nr_frags = 0;
-		__skb_frag_unref(frag);
-		skb->truesize -= ixgbe_rx_bufsz(rx_ring);
-	}
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		ixgbe_pull_tail(rx_ring, skb);
 
 #ifdef IXGBE_FCOE
 	/* do not attempt to pad FCoE Frames as this will disrupt DDP */
@@ -1560,33 +1573,17 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 }
 
 /**
- * ixgbe_can_reuse_page - determine if we can reuse a page
- * @rx_buffer: pointer to rx_buffer containing the page we want to reuse
- *
- * Returns true if page can be reused in another Rx buffer
- **/
-static inline bool ixgbe_can_reuse_page(struct ixgbe_rx_buffer *rx_buffer)
-{
-	struct page *page = rx_buffer->page;
-
-	/* if we are only owner of page and it is local we can reuse it */
-	return likely(page_count(page) == 1) &&
-	       likely(page_to_nid(page) == numa_node_id());
-}
-
-/**
  * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring
  * @rx_ring: rx descriptor ring to store buffers on
  * @old_buff: donor buffer to have page reused
  *
- * Syncronizes page for reuse by the adapter
+ * Synchronizes page for reuse by the adapter
  **/
 static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
 				struct ixgbe_rx_buffer *old_buff)
 {
 	struct ixgbe_rx_buffer *new_buff;
 	u16 nta = rx_ring->next_to_alloc;
-	u16 bufsz = ixgbe_rx_bufsz(rx_ring);
 
 	new_buff = &rx_ring->rx_buffer_info[nta];
 
@@ -1597,17 +1594,13 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
 	/* transfer page from old buffer to new buffer */
 	new_buff->page = old_buff->page;
 	new_buff->dma = old_buff->dma;
-
-	/* flip page offset to other buffer and store to new_buff */
-	new_buff->page_offset = old_buff->page_offset ^ bufsz;
+	new_buff->page_offset = old_buff->page_offset;
 
 	/* sync the buffer for use by the device */
 	dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma,
-					 new_buff->page_offset, bufsz,
+					 new_buff->page_offset,
+					 ixgbe_rx_bufsz(rx_ring),
 					 DMA_FROM_DEVICE);
-
-	/* bump ref count on page before it is given to the stack */
-	get_page(new_buff->page);
 }
 
 /**
@@ -1617,20 +1610,159 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
  * @rx_desc: descriptor containing length of buffer written by hardware
  * @skb: sk_buff to place the data into
  *
- * This function is based on skb_add_rx_frag.  I would have used that
- * function however it doesn't handle the truesize case correctly since we
- * are allocating more memory than might be used for a single receive.
+ * This function will add the data contained in rx_buffer->page to the skb.
+ * This is done either through a direct copy if the data in the buffer is
+ * less than the skb header size, otherwise it will just attach the page as
+ * a frag to the skb.
+ *
+ * The function will then update the page offset if necessary and return
+ * true if the buffer can be reused by the adapter.
  **/
-static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
+static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 			      struct ixgbe_rx_buffer *rx_buffer,
-			      struct sk_buff *skb, int size)
+			      union ixgbe_adv_rx_desc *rx_desc,
+			      struct sk_buff *skb)
 {
-	skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
-			   rx_buffer->page, rx_buffer->page_offset,
-			   size);
-	skb->len += size;
-	skb->data_len += size;
-	skb->truesize += ixgbe_rx_bufsz(rx_ring);
+	struct page *page = rx_buffer->page;
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
+#else
+	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
+				   ixgbe_rx_bufsz(rx_ring);
+#endif
+
+	if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
+		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+
+		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+
+		/* we can reuse buffer as-is, just make sure it is local */
+		if (likely(page_to_nid(page) == numa_node_id()))
+			return true;
+
+		/* this page cannot be reused so discard it */
+		put_page(page);
+		return false;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_buffer->page_offset, size, truesize);
+
+	/* avoid re-using remote pages */
+	if (unlikely(page_to_nid(page) != numa_node_id()))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* flip page offset to other buffer */
+	rx_buffer->page_offset ^= truesize;
+
+	/*
+	 * since we are the only owner of the page and we need to
+	 * increment it, just set the value to 2 in order to avoid
+	 * an unecessary locked operation
+	 */
+	atomic_set(&page->_count, 2);
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > last_offset)
+		return false;
+
+	/* bump ref count on page before it is given to the stack */
+	get_page(page);
+#endif
+
+	return true;
+}
+
+static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
+					     union ixgbe_adv_rx_desc *rx_desc)
+{
+	struct ixgbe_rx_buffer *rx_buffer;
+	struct sk_buff *skb;
+	struct page *page;
+
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	page = rx_buffer->page;
+	prefetchw(page);
+
+	skb = rx_buffer->skb;
+
+	if (likely(!skb)) {
+		void *page_addr = page_address(page) +
+				  rx_buffer->page_offset;
+
+		/* prefetch first cache line of first page */
+		prefetch(page_addr);
+#if L1_CACHE_BYTES < 128
+		prefetch(page_addr + L1_CACHE_BYTES);
+#endif
+
+		/* allocate a skb to store the frags */
+		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
+						IXGBE_RX_HDR_SIZE);
+		if (unlikely(!skb)) {
+			rx_ring->rx_stats.alloc_rx_buff_failed++;
+			return NULL;
+		}
+
+		/*
+		 * we will be copying header into skb->data in
+		 * pskb_may_pull so it is in our interest to prefetch
+		 * it now to avoid a possible cache miss
+		 */
+		prefetchw(skb->data);
+
+		/*
+		 * Delay unmapping of the first packet. It carries the
+		 * header information, HW may still access the header
+		 * after the writeback.  Only unmap it when EOP is
+		 * reached
+		 */
+		if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
+			goto dma_sync;
+
+		IXGBE_CB(skb)->dma = rx_buffer->dma;
+	} else {
+		if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
+			ixgbe_dma_sync_frag(rx_ring, skb);
+
+dma_sync:
+		/* we are reusing so sync this buffer for CPU use */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_buffer->dma,
+					      rx_buffer->page_offset,
+					      ixgbe_rx_bufsz(rx_ring),
+					      DMA_FROM_DEVICE);
+	}
+
+	/* pull page into skb */
+	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
+		/* hand second half of page back to the ring */
+		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
+	} else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
+		/* the page has been released from the ring */
+		IXGBE_CB(skb)->page_released = true;
+	} else {
+		/* we are not reusing the buffer so unmap it */
+		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
+			       ixgbe_rx_pg_size(rx_ring),
+			       DMA_FROM_DEVICE);
+	}
+
+	/* clear contents of buffer_info */
+	rx_buffer->skb = NULL;
+	rx_buffer->dma = 0;
+	rx_buffer->page = NULL;
+
+	return skb;
 }
 
 /**
@@ -1653,16 +1785,14 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 #ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter = q_vector->adapter;
-	int ddp_bytes = 0;
+	int ddp_bytes;
+	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
 
 	do {
-		struct ixgbe_rx_buffer *rx_buffer;
 		union ixgbe_adv_rx_desc *rx_desc;
 		struct sk_buff *skb;
-		struct page *page;
-		u16 ntc;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
@@ -1670,9 +1800,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			cleaned_count = 0;
 		}
 
-		ntc = rx_ring->next_to_clean;
-		rx_desc = IXGBE_RX_DESC(rx_ring, ntc);
-		rx_buffer = &rx_ring->rx_buffer_info[ntc];
+		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
 		if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD))
 			break;
@@ -1684,75 +1812,12 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		rmb();
 
-		page = rx_buffer->page;
-		prefetchw(page);
-
-		skb = rx_buffer->skb;
-
-		if (likely(!skb)) {
-			void *page_addr = page_address(page) +
-					  rx_buffer->page_offset;
-
-			/* prefetch first cache line of first page */
-			prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
-			prefetch(page_addr + L1_CACHE_BYTES);
-#endif
+		/* retrieve a buffer from the ring */
+		skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc);
 
-			/* allocate a skb to store the frags */
-			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-							IXGBE_RX_HDR_SIZE);
-			if (unlikely(!skb)) {
-				rx_ring->rx_stats.alloc_rx_buff_failed++;
-				break;
-			}
-
-			/*
-			 * we will be copying header into skb->data in
-			 * pskb_may_pull so it is in our interest to prefetch
-			 * it now to avoid a possible cache miss
-			 */
-			prefetchw(skb->data);
-
-			/*
-			 * Delay unmapping of the first packet. It carries the
-			 * header information, HW may still access the header
-			 * after the writeback.  Only unmap it when EOP is
-			 * reached
-			 */
-			IXGBE_CB(skb)->dma = rx_buffer->dma;
-		} else {
-			/* we are reusing so sync this buffer for CPU use */
-			dma_sync_single_range_for_cpu(rx_ring->dev,
-						      rx_buffer->dma,
-						      rx_buffer->page_offset,
-						      ixgbe_rx_bufsz(rx_ring),
-						      DMA_FROM_DEVICE);
-		}
-
-		/* pull page into skb */
-		ixgbe_add_rx_frag(rx_ring, rx_buffer, skb,
-				  le16_to_cpu(rx_desc->wb.upper.length));
-
-		if (ixgbe_can_reuse_page(rx_buffer)) {
-			/* hand second half of page back to the ring */
-			ixgbe_reuse_rx_page(rx_ring, rx_buffer);
-		} else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
-			/* the page has been released from the ring */
-			IXGBE_CB(skb)->page_released = true;
-		} else {
-			/* we are not reusing the buffer so unmap it */
-			dma_unmap_page(rx_ring->dev, rx_buffer->dma,
-				       ixgbe_rx_pg_size(rx_ring),
-				       DMA_FROM_DEVICE);
-		}
-
-		/* clear contents of buffer_info */
-		rx_buffer->skb = NULL;
-		rx_buffer->dma = 0;
-		rx_buffer->page = NULL;
-
-		ixgbe_get_rsc_cnt(rx_ring, rx_desc, skb);
+		/* exit if we failed to retrieve a buffer */
+		if (!skb)
+			break;
 
 		cleaned_count++;
 
@@ -1775,6 +1840,20 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		/* if ddp, not passing to ULD unless for FCP_RSP or error */
 		if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) {
 			ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb);
+			/* include DDPed FCoE data */
+			if (ddp_bytes > 0) {
+				if (!mss) {
+					mss = rx_ring->netdev->mtu -
+						sizeof(struct fcoe_hdr) -
+						sizeof(struct fc_frame_header) -
+						sizeof(struct fcoe_crc_eof);
+					if (mss > 512)
+						mss &= ~511;
+				}
+				total_rx_bytes += ddp_bytes;
+				total_rx_packets += DIV_ROUND_UP(ddp_bytes,
+								 mss);
+			}
 			if (!ddp_bytes) {
 				dev_kfree_skb_any(skb);
 				continue;
@@ -1788,21 +1867,6 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		budget--;
 	} while (likely(budget));
 
-#ifdef IXGBE_FCOE
-	/* include DDPed FCoE data */
-	if (ddp_bytes > 0) {
-		unsigned int mss;
-
-		mss = rx_ring->netdev->mtu - sizeof(struct fcoe_hdr) -
-			sizeof(struct fc_frame_header) -
-			sizeof(struct fcoe_crc_eof);
-		if (mss > 512)
-			mss &= ~511;
-		total_rx_bytes += ddp_bytes;
-		total_rx_packets += DIV_ROUND_UP(ddp_bytes, mss);
-	}
-
-#endif /* IXGBE_FCOE */
 	u64_stats_update_begin(&rx_ring->syncp);
 	rx_ring->stats.packets += total_rx_packets;
 	rx_ring->stats.bytes += total_rx_bytes;
@@ -2868,11 +2932,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
 
 	/* configure the packet buffer length */
-#if PAGE_SIZE > IXGBE_MAX_RXBUFFER
-	srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
-#else
 	srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
-#endif
 
 	/* configure descriptor type */
 	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
@@ -2980,13 +3040,7 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
 	 * total size of max desc * buf_len is not greater
 	 * than 65536
 	 */
-#if (PAGE_SIZE <= 8192)
 	rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
-#elif (PAGE_SIZE <= 16384)
-	rscctrl |= IXGBE_RSCCTL_MAXDESC_8;
-#else
-	rscctrl |= IXGBE_RSCCTL_MAXDESC_4;
-#endif
 	IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl);
 }
 
@@ -3606,8 +3660,6 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
 	if (hw->mac.type == ixgbe_mac_82598EB)
 		netif_set_gso_max_size(adapter->netdev, 32768);
 
-	hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true);
-
 #ifdef IXGBE_FCOE
 	if (adapter->netdev->features & NETIF_F_FCOE_MTU)
 		max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
@@ -3807,6 +3859,11 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 #ifdef CONFIG_IXGBE_DCB
 	ixgbe_configure_dcb(adapter);
 #endif
+	/*
+	 * We must restore virtualization before VLANs or else
+	 * the VLVF registers will not be populated
+	 */
+	ixgbe_configure_virtualization(adapter);
 
 	ixgbe_set_rx_mode(adapter->netdev);
 	ixgbe_restore_vlan(adapter);
@@ -3838,8 +3895,6 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 		break;
 	}
 
-	ixgbe_configure_virtualization(adapter);
-
 #ifdef IXGBE_FCOE
 	/* configure FCoE L2 filters, redirection table, and Rx control */
 	ixgbe_configure_fcoe(adapter);
@@ -4130,27 +4185,6 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 }
 
 /**
- * ixgbe_init_rx_page_offset - initialize page offset values for Rx buffers
- * @rx_ring: ring to setup
- *
- * On many IA platforms the L1 cache has a critical stride of 4K, this
- * results in each receive buffer starting in the same cache set.  To help
- * reduce the pressure on this cache set we can interleave the offsets so
- * that only every other buffer will be in the same cache set.
- **/
-static void ixgbe_init_rx_page_offset(struct ixgbe_ring *rx_ring)
-{
-	struct ixgbe_rx_buffer *rx_buffer = rx_ring->rx_buffer_info;
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i += 2) {
-		rx_buffer[0].page_offset = 0;
-		rx_buffer[1].page_offset = ixgbe_rx_bufsz(rx_ring);
-		rx_buffer = &rx_buffer[2];
-	}
-}
-
-/**
  * ixgbe_clean_rx_ring - Free Rx Buffers per Queue
  * @rx_ring: ring to free buffers from
  **/
@@ -4195,8 +4229,6 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
 	memset(rx_ring->rx_buffer_info, 0, size);
 
-	ixgbe_init_rx_page_offset(rx_ring);
-
 	/* Zero out the descriptor ring */
 	memset(rx_ring->desc, 0, rx_ring->size);
 
@@ -4646,8 +4678,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 
-	ixgbe_init_rx_page_offset(rx_ring);
-
 	return 0;
 err:
 	vfree(rx_ring->rx_buffer_info);
@@ -5530,8 +5560,9 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter)
 {
 	u32 ssvpc;
 
-	/* Do not perform spoof check for 82598 */
-	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+	/* Do not perform spoof check for 82598 or if not in IOV mode */
+	if (adapter->hw.mac.type == ixgbe_mac_82598EB ||
+	    adapter->num_vfs == 0)
 		return;
 
 	ssvpc = IXGBE_READ_REG(&adapter->hw, IXGBE_SSVPC);
@@ -5543,7 +5574,7 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter)
 	if (!ssvpc)
 		return;
 
-	e_warn(drv, "%d Spoofed packets detected\n", ssvpc);
+	e_warn(drv, "%u Spoofed packets detected\n", ssvpc);
 }
 
 /**
@@ -5874,9 +5905,12 @@ 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) &&
-		    !(first->tx_flags & IXGBE_TX_FLAGS_TXSW))
-			return;
+		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;
+		}
 	} else {
 		u8 l4_hdr = 0;
 		switch (first->protocol) {
@@ -5938,7 +5972,6 @@ static __le32 ixgbe_tx_cmd_type(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_IFCS |
 				      IXGBE_ADVTXD_DCMD_DEXT);
 
 	/* set HW vlan bit if vlan is present */
@@ -5958,6 +5991,10 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags)
 #endif
 		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE);
 
+	/* insert frame checksum */
+	if (!(tx_flags & IXGBE_TX_FLAGS_NO_IFCS))
+		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS);
+
 	return cmd_type;
 }
 
@@ -6063,8 +6100,6 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 		if (likely(!data_len))
 			break;
 
-		if (unlikely(skb->no_fcs))
-			cmd_type &= ~(cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS));
 		tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size);
 
 		i++;
@@ -6854,9 +6889,9 @@ static int ixgbe_set_features(struct net_device *netdev,
 	return 0;
 }
 
-static int ixgbe_ndo_fdb_add(struct ndmsg *ndm,
+static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
-			     unsigned char *addr,
+			     const unsigned char *addr,
 			     u16 flags)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
@@ -6893,7 +6928,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm,
 
 static int ixgbe_ndo_fdb_del(struct ndmsg *ndm,
 			     struct net_device *dev,
-			     unsigned char *addr)
+			     const unsigned char *addr)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	int err = -EOPNOTSUPP;
@@ -7136,11 +7171,6 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
 		goto err_ioremap;
 	}
 
-	for (i = 1; i <= 5; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-	}
-
 	netdev->netdev_ops = &ixgbe_netdev_ops;
 	ixgbe_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
@@ -7419,6 +7449,10 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
 		e_err(probe, "failed to allocate sysfs resources\n");
 #endif /* CONFIG_IXGBE_HWMON */
 
+#ifdef CONFIG_DEBUG_FS
+	ixgbe_dbg_adapter_init(adapter);
+#endif /* CONFIG_DEBUG_FS */
+
 	return 0;
 
 err_register:
@@ -7453,6 +7487,10 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev)
 	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
 	struct net_device *netdev = adapter->netdev;
 
+#ifdef CONFIG_DEBUG_FS
+	ixgbe_dbg_adapter_exit(adapter);
+#endif /*CONFIG_DEBUG_FS */
+
 	set_bit(__IXGBE_DOWN, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
@@ -7708,6 +7746,10 @@ static int __init ixgbe_init_module(void)
 	pr_info("%s - version %s\n", ixgbe_driver_string, ixgbe_driver_version);
 	pr_info("%s\n", ixgbe_copyright);
 
+#ifdef CONFIG_DEBUG_FS
+	ixgbe_dbg_init();
+#endif /* CONFIG_DEBUG_FS */
+
 #ifdef CONFIG_IXGBE_DCA
 	dca_register_notify(&dca_notifier);
 #endif
@@ -7730,6 +7772,11 @@ static void __exit ixgbe_exit_module(void)
 	dca_unregister_notify(&dca_notifier);
 #endif
 	pci_unregister_driver(&ixgbe_driver);
+
+#ifdef CONFIG_DEBUG_FS
+	ixgbe_dbg_exit();
+#endif /* CONFIG_DEBUG_FS */
+
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 3456d5617143..39881cb17a4b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -960,7 +960,8 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
 	/* (Re)start the overflow check */
 	adapter->flags2 |= IXGBE_FLAG2_OVERFLOW_CHECK_ENABLED;
 
-	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps);
+	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
+						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		e_dev_err("ptp_clock_register failed\n");
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 4fea8716ab64..dce48bf64d96 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -346,6 +346,10 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
 static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
 			     u32 vf)
 {
+	/* VLAN 0 is a special case, don't allow it to be removed */
+	if (!vid && !add)
+		return 0;
+
 	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
 }
 
@@ -414,6 +418,7 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 				  VLAN_PRIO_SHIFT)), vf);
 		ixgbe_set_vmolr(hw, vf, false);
 	} else {
+		ixgbe_set_vf_vlan(adapter, true, 0, vf);
 		ixgbe_set_vmvir(adapter, 0, vf);
 		ixgbe_set_vmolr(hw, vf, true);
 	}
@@ -810,9 +815,9 @@ out:
        return err;
 }
 
-static int ixgbe_link_mbps(int internal_link_speed)
+static int ixgbe_link_mbps(struct ixgbe_adapter *adapter)
 {
-	switch (internal_link_speed) {
+	switch (adapter->link_speed) {
 	case IXGBE_LINK_SPEED_100_FULL:
 		return 100;
 	case IXGBE_LINK_SPEED_1GB_FULL:
@@ -824,27 +829,30 @@ static int ixgbe_link_mbps(int internal_link_speed)
 	}
 }
 
-static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
-				    int link_speed)
+static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
 {
-	int rf_dec, rf_int;
-	u32 bcnrc_val;
+	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 bcnrc_val = 0;
+	u16 queue, queues_per_pool;
+	u16 tx_rate = adapter->vfinfo[vf].tx_rate;
+
+	if (tx_rate) {
+		/* start with base link speed value */
+		bcnrc_val = adapter->vf_rate_link_speed;
 
-	if (tx_rate != 0) {
 		/* Calculate the rate factor values to set */
-		rf_int = link_speed / tx_rate;
-		rf_dec = (link_speed - (rf_int * tx_rate));
-		rf_dec = (rf_dec * (1<<IXGBE_RTTBCNRC_RF_INT_SHIFT)) / tx_rate;
-
-		bcnrc_val = IXGBE_RTTBCNRC_RS_ENA;
-		bcnrc_val |= ((rf_int<<IXGBE_RTTBCNRC_RF_INT_SHIFT) &
-		               IXGBE_RTTBCNRC_RF_INT_MASK);
-		bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK);
-	} else {
-		bcnrc_val = 0;
+		bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
+		bcnrc_val /= tx_rate;
+
+		/* clear everything but the rate factor */
+		bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK |
+			     IXGBE_RTTBCNRC_RF_DEC_MASK;
+
+		/* enable the rate scheduler */
+		bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;
 	}
 
-	IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, 2*vf); /* vf Y uses queue 2*Y */
 	/*
 	 * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
 	 * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported
@@ -861,53 +869,68 @@ static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
 		break;
 	}
 
-	IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
+	/* determine how many queues per pool based on VMDq mask */
+	queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+
+	/* write value for all Tx queues belonging to VF */
+	for (queue = 0; queue < queues_per_pool; queue++) {
+		unsigned int reg_idx = (vf * queues_per_pool) + queue;
+
+		IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx);
+		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
+	}
 }
 
 void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 {
-	int actual_link_speed, i;
-	bool reset_rate = false;
+	int i;
 
 	/* VF Tx rate limit was not set */
-	if (adapter->vf_rate_link_speed == 0)
+	if (!adapter->vf_rate_link_speed)
 		return;
 
-	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
-	if (actual_link_speed != adapter->vf_rate_link_speed) {
-		reset_rate = true;
+	if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) {
 		adapter->vf_rate_link_speed = 0;
 		dev_info(&adapter->pdev->dev,
-		         "Link speed has been changed. VF Transmit rate "
-		         "is disabled\n");
+			 "Link speed has been changed. VF Transmit rate is disabled\n");
 	}
 
 	for (i = 0; i < adapter->num_vfs; i++) {
-		if (reset_rate)
+		if (!adapter->vf_rate_link_speed)
 			adapter->vfinfo[i].tx_rate = 0;
 
-		ixgbe_set_vf_rate_limit(&adapter->hw, i,
-					adapter->vfinfo[i].tx_rate,
-					actual_link_speed);
+		ixgbe_set_vf_rate_limit(adapter, i);
 	}
 }
 
 int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
-	int actual_link_speed;
+	int link_speed;
+
+	/* verify VF is active */
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
 
-	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
-	if ((vf >= adapter->num_vfs) || (!adapter->link_up) ||
-	    (tx_rate > actual_link_speed) || (actual_link_speed != 10000) ||
-	    ((tx_rate != 0) && (tx_rate <= 10)))
-	    /* rate limit cannot be set to 10Mb or less in 10Gb adapters */
+	/* verify link is up */
+	if (!adapter->link_up)
 		return -EINVAL;
 
-	adapter->vf_rate_link_speed = actual_link_speed;
-	adapter->vfinfo[vf].tx_rate = (u16)tx_rate;
-	ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);
+	/* verify we are linked at 10Gbps */
+	link_speed = ixgbe_link_mbps(adapter);
+	if (link_speed != 10000)
+		return -EINVAL;
+
+	/* rate limit cannot be less than 10Mbs or greater than link speed */
+	if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed)))
+		return -EINVAL;
+
+	/* store values */
+	adapter->vf_rate_link_speed = link_speed;
+	adapter->vfinfo[vf].tx_rate = tx_rate;
+
+	/* update hardware configuration */
+	ixgbe_set_vf_rate_limit(adapter, vf);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 418af827b230..da17ccf5c09d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -272,5 +272,6 @@ struct ixgbe_adv_tx_context_desc {
 /* Error Codes */
 #define IXGBE_ERR_INVALID_MAC_ADDR              -1
 #define IXGBE_ERR_RESET_FAILED                  -2
+#define IXGBE_ERR_INVALID_ARGUMENT              -3
 
 #endif /* _IXGBEVF_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 98cadb0c4dab..383b4e1cd175 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -101,7 +101,9 @@ struct ixgbevf_ring {
 
 /* Supported Rx Buffer Sizes */
 #define IXGBEVF_RXBUFFER_256   256    /* Used for packet split */
-#define IXGBEVF_RXBUFFER_2048  2048
+#define IXGBEVF_RXBUFFER_3K    3072
+#define IXGBEVF_RXBUFFER_7K    7168
+#define IXGBEVF_RXBUFFER_15K   15360
 #define IXGBEVF_MAX_RXBUFFER   16384  /* largest size for single descriptor */
 
 #define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256
@@ -259,6 +261,11 @@ enum ixbgevf_state_t {
 	__IXGBEVF_DOWN
 };
 
+struct ixgbevf_cb {
+	struct sk_buff *prev;
+};
+#define IXGBE_CB(skb) ((struct ixgbevf_cb *)(skb)->cb)
+
 enum ixgbevf_boards {
 	board_82599_vf,
 	board_X540_vf,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 6647383c4ddc..0ee9bd4819f4 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -263,6 +263,8 @@ cont_loop:
 	tx_ring->total_bytes += total_bytes;
 	tx_ring->total_packets += total_packets;
 	u64_stats_update_end(&tx_ring->syncp);
+	q_vector->tx.total_bytes += total_bytes;
+	q_vector->tx.total_packets += total_packets;
 
 	return count < tx_ring->count;
 }
@@ -272,12 +274,10 @@ cont_loop:
  * @q_vector: structure containing interrupt and ring information
  * @skb: packet to send up
  * @status: hardware indication of status of receive
- * @rx_ring: rx descriptor ring (for a specific queue) to setup
  * @rx_desc: rx descriptor
  **/
 static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
 				struct sk_buff *skb, u8 status,
-				struct ixgbevf_ring *ring,
 				union ixgbe_adv_rx_desc *rx_desc)
 {
 	struct ixgbevf_adapter *adapter = q_vector->adapter;
@@ -433,11 +433,21 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 
 		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
 			skb->next = next_buffer->skb;
-			skb->next->prev = skb;
+			IXGBE_CB(skb->next)->prev = skb;
 			adapter->non_eop_descs++;
 			goto next_desc;
 		}
 
+		/* we should not be chaining buffers, if we did drop the skb */
+		if (IXGBE_CB(skb)->prev) {
+			do {
+				struct sk_buff *this = skb;
+				skb = IXGBE_CB(skb)->prev;
+				dev_kfree_skb(this);
+			} while (skb);
+			goto next_desc;
+		}
+
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) {
 			dev_kfree_skb_irq(skb);
@@ -461,7 +471,7 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		}
 		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
-		ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
+		ixgbevf_receive_skb(q_vector, skb, staterr, rx_desc);
 
 next_desc:
 		rx_desc->wb.upper.status_error = 0;
@@ -490,6 +500,8 @@ next_desc:
 	rx_ring->total_packets += total_rx_packets;
 	rx_ring->total_bytes += total_rx_bytes;
 	u64_stats_update_end(&rx_ring->syncp);
+	q_vector->rx.total_packets += total_rx_packets;
+	q_vector->rx.total_bytes += total_rx_bytes;
 
 	return !!budget;
 }
@@ -716,40 +728,15 @@ static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector)
 	}
 }
 
-static irqreturn_t ixgbevf_msix_mbx(int irq, void *data)
+static irqreturn_t ixgbevf_msix_other(int irq, void *data)
 {
 	struct ixgbevf_adapter *adapter = data;
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 msg;
-	bool got_ack = false;
-
-	if (!hw->mbx.ops.check_for_ack(hw))
-		got_ack = true;
 
-	if (!hw->mbx.ops.check_for_msg(hw)) {
-		hw->mbx.ops.read(hw, &msg, 1);
+	hw->mac.get_link_status = 1;
 
-		if ((msg & IXGBE_MBVFICR_VFREQ_MASK) == IXGBE_PF_CONTROL_MSG)
-			mod_timer(&adapter->watchdog_timer,
-				  round_jiffies(jiffies + 1));
-
-		if (msg & IXGBE_VT_MSGTYPE_NACK)
-			pr_warn("Last Request of type %2.2x to PF Nacked\n",
-				msg & 0xFF);
-		/*
-		 * Restore the PFSTS bit in case someone is polling for a
-		 * return message from the PF
-		 */
-		hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFSTS;
-	}
-
-	/*
-	 * checking for the ack clears the PFACK bit.  Place
-	 * it back in the v2p_mailbox cache so that anyone
-	 * polling for an ack will not miss it
-	 */
-	if (got_ack)
-		hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFACK;
+	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+		mod_timer(&adapter->watchdog_timer, jiffies);
 
 	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other);
 
@@ -899,10 +886,10 @@ static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter)
 	}
 
 	err = request_irq(adapter->msix_entries[vector].vector,
-			  &ixgbevf_msix_mbx, 0, netdev->name, adapter);
+			  &ixgbevf_msix_other, 0, netdev->name, adapter);
 	if (err) {
 		hw_dbg(&adapter->hw,
-		       "request_irq for msix_mbx failed: %d\n", err);
+		       "request_irq for msix_other failed: %d\n", err);
 		goto free_queue_irqs;
 	}
 
@@ -1057,15 +1044,46 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
 
 	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
 
-	if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE)
-		srrctl |= IXGBEVF_RXBUFFER_2048 >>
-			IXGBE_SRRCTL_BSIZEPKT_SHIFT;
-	else
-		srrctl |= rx_ring->rx_buf_len >>
-			IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >>
+		  IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+
 	IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
 }
 
+static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
+	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+	int i;
+	u16 rx_buf_len;
+
+	/* notify the PF of our intent to use this size of frame */
+	ixgbevf_rlpml_set_vf(hw, max_frame);
+
+	/* PF will allow an extra 4 bytes past for vlan tagged frames */
+	max_frame += VLAN_HLEN;
+
+	/*
+	 * Make best use of allocation by using all but 1K of a
+	 * power of 2 allocation that will be used for skb->head.
+	 */
+	if ((hw->mac.type == ixgbe_mac_X540_vf) &&
+	    (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE))
+		rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
+	else if (max_frame <= IXGBEVF_RXBUFFER_3K)
+		rx_buf_len = IXGBEVF_RXBUFFER_3K;
+	else if (max_frame <= IXGBEVF_RXBUFFER_7K)
+		rx_buf_len = IXGBEVF_RXBUFFER_7K;
+	else if (max_frame <= IXGBEVF_RXBUFFER_15K)
+		rx_buf_len = IXGBEVF_RXBUFFER_15K;
+	else
+		rx_buf_len = IXGBEVF_MAX_RXBUFFER;
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		adapter->rx_ring[i].rx_buf_len = rx_buf_len;
+}
+
 /**
  * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset
  * @adapter: board private structure
@@ -1076,18 +1094,14 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
 {
 	u64 rdba;
 	struct ixgbe_hw *hw = &adapter->hw;
-	struct net_device *netdev = adapter->netdev;
-	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	int i, j;
 	u32 rdlen;
-	int rx_buf_len;
 
 	/* PSRTYPE must be initialized in 82599 */
 	IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
-	if (netdev->mtu <= ETH_DATA_LEN)
-		rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
-	else
-		rx_buf_len = ALIGN(max_frame, 1024);
+
+	/* set_rx_buffer_len must be called before ring initialization */
+	ixgbevf_set_rx_buffer_len(adapter);
 
 	rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc);
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
@@ -1103,7 +1117,6 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
 		IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0);
 		adapter->rx_ring[i].head = IXGBE_VFRDH(j);
 		adapter->rx_ring[i].tail = IXGBE_VFRDT(j);
-		adapter->rx_ring[i].rx_buf_len = rx_buf_len;
 
 		ixgbevf_configure_srrctl(adapter, j);
 	}
@@ -1113,36 +1126,47 @@ static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	if (!hw->mac.ops.set_vfta)
+		return -EOPNOTSUPP;
 
 	spin_lock(&adapter->mbx_lock);
 
 	/* add VID to filter table */
-	if (hw->mac.ops.set_vfta)
-		hw->mac.ops.set_vfta(hw, vid, 0, true);
+	err = hw->mac.ops.set_vfta(hw, vid, 0, true);
 
 	spin_unlock(&adapter->mbx_lock);
 
+	/* translate error return types so error makes sense */
+	if (err == IXGBE_ERR_MBX)
+		return -EIO;
+
+	if (err == IXGBE_ERR_INVALID_ARGUMENT)
+		return -EACCES;
+
 	set_bit(vid, adapter->active_vlans);
 
-	return 0;
+	return err;
 }
 
 static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	int err = -EOPNOTSUPP;
 
 	spin_lock(&adapter->mbx_lock);
 
 	/* remove VID from filter table */
 	if (hw->mac.ops.set_vfta)
-		hw->mac.ops.set_vfta(hw, vid, 0, false);
+		err = hw->mac.ops.set_vfta(hw, vid, 0, false);
 
 	spin_unlock(&adapter->mbx_lock);
 
 	clear_bit(vid, adapter->active_vlans);
 
-	return 0;
+	return err;
 }
 
 static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
@@ -1308,6 +1332,25 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
 	adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
 }
 
+static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int api[] = { ixgbe_mbox_api_10,
+		      ixgbe_mbox_api_unknown };
+	int err = 0, idx = 0;
+
+	spin_lock(&adapter->mbx_lock);
+
+	while (api[idx] != ixgbe_mbox_api_unknown) {
+		err = ixgbevf_negotiate_api_version(hw, api[idx]);
+		if (!err)
+			break;
+		idx++;
+	}
+
+	spin_unlock(&adapter->mbx_lock);
+}
+
 static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -1315,7 +1358,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 	int i, j = 0;
 	int num_rx_rings = adapter->num_rx_queues;
 	u32 txdctl, rxdctl;
-	u32 msg[2];
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		j = adapter->tx_ring[i].reg_idx;
@@ -1356,10 +1398,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 			hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0);
 	}
 
-	msg[0] = IXGBE_VF_SET_LPE;
-	msg[1] = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
-	hw->mbx.ops.write_posted(hw, msg, 2);
-
 	spin_unlock(&adapter->mbx_lock);
 
 	clear_bit(__IXGBEVF_DOWN, &adapter->state);
@@ -1371,6 +1409,7 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 	ixgbevf_save_reset_stats(adapter);
 	ixgbevf_init_last_counter_stats(adapter);
 
+	hw->mac.get_link_status = 1;
 	mod_timer(&adapter->watchdog_timer, jiffies);
 }
 
@@ -1378,6 +1417,8 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 
+	ixgbevf_negotiate_api(adapter);
+
 	ixgbevf_configure(adapter);
 
 	ixgbevf_up_complete(adapter);
@@ -1419,7 +1460,7 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
 			rx_buffer_info->skb = NULL;
 			do {
 				struct sk_buff *this = skb;
-				skb = skb->prev;
+				skb = IXGBE_CB(skb)->prev;
 				dev_kfree_skb(this);
 			} while (skb);
 		}
@@ -1547,8 +1588,6 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter)
 
 void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
-
 	WARN_ON(in_interrupt());
 
 	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
@@ -1561,10 +1600,8 @@ void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter)
 	 * watchdog task will continue to schedule reset tasks until
 	 * the PF is up and running.
 	 */
-	if (!hw->mac.ops.reset_hw(hw)) {
-		ixgbevf_down(adapter);
-		ixgbevf_up(adapter);
-	}
+	ixgbevf_down(adapter);
+	ixgbevf_up(adapter);
 
 	clear_bit(__IXGBEVF_RESETTING, &adapter->state);
 }
@@ -1867,6 +1904,22 @@ err_set_interrupt:
 }
 
 /**
+ * ixgbevf_clear_interrupt_scheme - Clear the current interrupt scheme settings
+ * @adapter: board private structure to clear interrupt scheme on
+ *
+ * We go through and clear interrupt specific resources and reset the structure
+ * to pre-load conditions
+ **/
+static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter)
+{
+	adapter->num_tx_queues = 0;
+	adapter->num_rx_queues = 0;
+
+	ixgbevf_free_q_vectors(adapter);
+	ixgbevf_reset_interrupt_capability(adapter);
+}
+
+/**
  * ixgbevf_sw_init - Initialize general software structures
  * (struct ixgbevf_adapter)
  * @adapter: board private structure to initialize
@@ -2351,6 +2404,8 @@ static int ixgbevf_open(struct net_device *netdev)
 		}
 	}
 
+	ixgbevf_negotiate_api(adapter);
+
 	/* allocate transmit descriptors */
 	err = ixgbevf_setup_all_tx_resources(adapter);
 	if (err)
@@ -2860,10 +2915,8 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p)
 static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 	int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE;
-	u32 msg[2];
 
 	if (adapter->hw.mac.type == ixgbe_mac_X540_vf)
 		max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE;
@@ -2877,35 +2930,91 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	/* must set new MTU before calling down or up */
 	netdev->mtu = new_mtu;
 
-	if (!netif_running(netdev)) {
-		msg[0] = IXGBE_VF_SET_LPE;
-		msg[1] = max_frame;
-		hw->mbx.ops.write_posted(hw, msg, 2);
-	}
-
 	if (netif_running(netdev))
 		ixgbevf_reinit_locked(adapter);
 
 	return 0;
 }
 
-static void ixgbevf_shutdown(struct pci_dev *pdev)
+static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+#ifdef CONFIG_PM
+	int retval = 0;
+#endif
 
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev)) {
+		rtnl_lock();
 		ixgbevf_down(adapter);
 		ixgbevf_free_irq(adapter);
 		ixgbevf_free_all_tx_resources(adapter);
 		ixgbevf_free_all_rx_resources(adapter);
+		rtnl_unlock();
 	}
 
-	pci_save_state(pdev);
+	ixgbevf_clear_interrupt_scheme(adapter);
 
+#ifdef CONFIG_PM
+	retval = pci_save_state(pdev);
+	if (retval)
+		return retval;
+
+#endif
 	pci_disable_device(pdev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int ixgbevf_resume(struct pci_dev *pdev)
+{
+	struct ixgbevf_adapter *adapter = pci_get_drvdata(pdev);
+	struct net_device *netdev = adapter->netdev;
+	u32 err;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	/*
+	 * pci_restore_state clears dev->state_saved so call
+	 * pci_save_state to restore it.
+	 */
+	pci_save_state(pdev);
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
+		return err;
+	}
+	pci_set_master(pdev);
+
+	rtnl_lock();
+	err = ixgbevf_init_interrupt_scheme(adapter);
+	rtnl_unlock();
+	if (err) {
+		dev_err(&pdev->dev, "Cannot initialize interrupts\n");
+		return err;
+	}
+
+	ixgbevf_reset(adapter);
+
+	if (netif_running(netdev)) {
+		err = ixgbevf_open(netdev);
+		if (err)
+			return err;
+	}
+
+	netif_device_attach(netdev);
+
+	return err;
+}
+
+#endif /* CONFIG_PM */
+static void ixgbevf_shutdown(struct pci_dev *pdev)
+{
+	ixgbevf_suspend(pdev, PMSG_SUSPEND);
 }
 
 static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
@@ -2946,7 +3055,7 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	return stats;
 }
 
-static const struct net_device_ops ixgbe_netdev_ops = {
+static const struct net_device_ops ixgbevf_netdev_ops = {
 	.ndo_open		= ixgbevf_open,
 	.ndo_stop		= ixgbevf_close,
 	.ndo_start_xmit		= ixgbevf_xmit_frame,
@@ -2962,7 +3071,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 
 static void ixgbevf_assign_netdev_ops(struct net_device *dev)
 {
-	dev->netdev_ops = &ixgbe_netdev_ops;
+	dev->netdev_ops = &ixgbevf_netdev_ops;
 	ixgbevf_set_ethtool_ops(dev);
 	dev->watchdog_timeo = 5 * HZ;
 }
@@ -3131,6 +3240,7 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
 	return 0;
 
 err_register:
+	ixgbevf_clear_interrupt_scheme(adapter);
 err_sw_init:
 	ixgbevf_reset_interrupt_capability(adapter);
 	iounmap(hw->hw_addr);
@@ -3168,6 +3278,7 @@ static void __devexit ixgbevf_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
+	ixgbevf_clear_interrupt_scheme(adapter);
 	ixgbevf_reset_interrupt_capability(adapter);
 
 	iounmap(adapter->hw.hw_addr);
@@ -3267,6 +3378,11 @@ static struct pci_driver ixgbevf_driver = {
 	.id_table = ixgbevf_pci_tbl,
 	.probe    = ixgbevf_probe,
 	.remove   = __devexit_p(ixgbevf_remove),
+#ifdef CONFIG_PM
+	/* Power Management Hooks */
+	.suspend  = ixgbevf_suspend,
+	.resume   = ixgbevf_resume,
+#endif
 	.shutdown = ixgbevf_shutdown,
 	.err_handler = &ixgbevf_err_handler
 };
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index 9c955900fe64..d5028ddf4b31 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -86,14 +86,17 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = IXGBE_ERR_MBX;
+	s32 ret_val = -IXGBE_ERR_MBX;
+
+	if (!mbx->ops.read)
+		goto out;
 
 	ret_val = ixgbevf_poll_for_msg(hw);
 
 	/* if ack received read message, otherwise we timed out */
 	if (!ret_val)
 		ret_val = mbx->ops.read(hw, msg, size);
-
+out:
 	return ret_val;
 }
 
@@ -109,7 +112,11 @@ static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val;
+	s32 ret_val = -IXGBE_ERR_MBX;
+
+	/* exit if either we can't write or there isn't a defined timeout */
+	if (!mbx->ops.write || !mbx->timeout)
+		goto out;
 
 	/* send msg */
 	ret_val = mbx->ops.write(hw, msg, size);
@@ -117,7 +124,7 @@ static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 	/* if msg sent wait until we receive an ack */
 	if (!ret_val)
 		ret_val = ixgbevf_poll_for_ack(hw);
-
+out:
 	return ret_val;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h
index cf9131c5c115..946ce86f337f 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.h
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h
@@ -76,12 +76,29 @@
 /* bits 23:16 are used for exra info for certain messages */
 #define IXGBE_VT_MSGINFO_MASK     (0xFF << IXGBE_VT_MSGINFO_SHIFT)
 
+/* definitions to support mailbox API version negotiation */
+
+/*
+ * each element denotes a version of the API; existing numbers may not
+ * change; any additions must go at the end
+ */
+enum ixgbe_pfvf_api_rev {
+	ixgbe_mbox_api_10,	/* API version 1.0, linux/freebsd VF driver */
+	ixgbe_mbox_api_20,	/* API version 2.0, solaris Phase1 VF driver */
+	/* This value should always be last */
+	ixgbe_mbox_api_unknown,	/* indicates that API version is not known */
+};
+
+/* mailbox API, legacy requests */
 #define IXGBE_VF_RESET            0x01 /* VF requests reset */
 #define IXGBE_VF_SET_MAC_ADDR     0x02 /* VF requests PF to set MAC addr */
 #define IXGBE_VF_SET_MULTICAST    0x03 /* VF requests PF to set MC addr */
 #define IXGBE_VF_SET_VLAN         0x04 /* VF requests PF to set VLAN */
-#define IXGBE_VF_SET_LPE          0x05 /* VF requests PF to set VMOLR.LPE */
-#define IXGBE_VF_SET_MACVLAN      0x06 /* VF requests PF for unicast filter */
+
+/* mailbox API, version 1.0 VF requests */
+#define IXGBE_VF_SET_LPE	0x05 /* VF requests PF to set VMOLR.LPE */
+#define IXGBE_VF_SET_MACVLAN	0x06 /* VF requests PF for unicast filter */
+#define IXGBE_VF_API_NEGOTIATE	0x08 /* negotiate API version */
 
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN 4
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index ec89b86f7ca4..0c7447e6fcc8 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -79,6 +79,9 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
 	/* Call adapter stop to disable tx/rx and clear interrupts */
 	hw->mac.ops.stop_adapter(hw);
 
+	/* reset the api version */
+	hw->api_version = ixgbe_mbox_api_10;
+
 	IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST);
 	IXGBE_WRITE_FLUSH(hw);
 
@@ -97,7 +100,7 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
 	msgbuf[0] = IXGBE_VF_RESET;
 	mbx->ops.write_posted(hw, msgbuf, 1);
 
-	msleep(10);
+	mdelay(10);
 
 	/* set our "perm_addr" based on info provided by PF */
 	/* also set up the mc_filter_type which is piggy backed
@@ -346,16 +349,32 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
 static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 			       bool vlan_on)
 {
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
 	u32 msgbuf[2];
+	s32 err;
 
 	msgbuf[0] = IXGBE_VF_SET_VLAN;
 	msgbuf[1] = vlan;
 	/* Setting the 8 bit field MSG INFO to TRUE indicates "add" */
 	msgbuf[0] |= vlan_on << IXGBE_VT_MSGINFO_SHIFT;
 
-	ixgbevf_write_msg_read_ack(hw, msgbuf, 2);
+	err = mbx->ops.write_posted(hw, msgbuf, 2);
+	if (err)
+		goto mbx_err;
 
-	return 0;
+	err = mbx->ops.read_posted(hw, msgbuf, 2);
+	if (err)
+		goto mbx_err;
+
+	/* remove extra bits from the message */
+	msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS;
+	msgbuf[0] &= ~(0xFF << IXGBE_VT_MSGINFO_SHIFT);
+
+	if (msgbuf[0] != (IXGBE_VF_SET_VLAN | IXGBE_VT_MSGTYPE_ACK))
+		err = IXGBE_ERR_INVALID_ARGUMENT;
+
+mbx_err:
+	return err;
 }
 
 /**
@@ -389,20 +408,23 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 				     bool *link_up,
 				     bool autoneg_wait_to_complete)
 {
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	struct ixgbe_mac_info *mac = &hw->mac;
+	s32 ret_val = 0;
 	u32 links_reg;
+	u32 in_msg = 0;
 
-	if (!(hw->mbx.ops.check_for_rst(hw))) {
-		*link_up = false;
-		*speed = 0;
-		return -1;
-	}
+	/* If we were hit with a reset drop the link */
+	if (!mbx->ops.check_for_rst(hw) || !mbx->timeout)
+		mac->get_link_status = true;
 
-	links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+	if (!mac->get_link_status)
+		goto out;
 
-	if (links_reg & IXGBE_LINKS_UP)
-		*link_up = true;
-	else
-		*link_up = false;
+	/* if link status is down no point in checking to see if pf is up */
+	links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+	if (!(links_reg & IXGBE_LINKS_UP))
+		goto out;
 
 	switch (links_reg & IXGBE_LINKS_SPEED_82599) {
 	case IXGBE_LINKS_SPEED_10G_82599:
@@ -416,7 +438,79 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 		break;
 	}
 
-	return 0;
+	/* if the read failed it could just be a mailbox collision, best wait
+	 * until we are called again and don't report an error */
+	if (mbx->ops.read(hw, &in_msg, 1))
+		goto out;
+
+	if (!(in_msg & IXGBE_VT_MSGTYPE_CTS)) {
+		/* msg is not CTS and is NACK we must have lost CTS status */
+		if (in_msg & IXGBE_VT_MSGTYPE_NACK)
+			ret_val = -1;
+		goto out;
+	}
+
+	/* the pf is talking, if we timed out in the past we reinit */
+	if (!mbx->timeout) {
+		ret_val = -1;
+		goto out;
+	}
+
+	/* if we passed all the tests above then the link is up and we no
+	 * longer need to check for link */
+	mac->get_link_status = false;
+
+out:
+	*link_up = !mac->get_link_status;
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_rlpml_set_vf - Set the maximum receive packet length
+ *  @hw: pointer to the HW structure
+ *  @max_size: value to assign to max frame size
+ **/
+void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size)
+{
+	u32 msgbuf[2];
+
+	msgbuf[0] = IXGBE_VF_SET_LPE;
+	msgbuf[1] = max_size;
+	ixgbevf_write_msg_read_ack(hw, msgbuf, 2);
+}
+
+/**
+ *  ixgbevf_negotiate_api_version - Negotiate supported API version
+ *  @hw: pointer to the HW structure
+ *  @api: integer containing requested API version
+ **/
+int ixgbevf_negotiate_api_version(struct ixgbe_hw *hw, int api)
+{
+	int err;
+	u32 msg[3];
+
+	/* Negotiate the mailbox API version */
+	msg[0] = IXGBE_VF_API_NEGOTIATE;
+	msg[1] = api;
+	msg[2] = 0;
+	err = hw->mbx.ops.write_posted(hw, msg, 3);
+
+	if (!err)
+		err = hw->mbx.ops.read_posted(hw, msg, 3);
+
+	if (!err) {
+		msg[0] &= ~IXGBE_VT_MSGTYPE_CTS;
+
+		/* Store value and return 0 on success */
+		if (msg[0] == (IXGBE_VF_API_NEGOTIATE | IXGBE_VT_MSGTYPE_ACK)) {
+			hw->api_version = api;
+			return 0;
+		}
+
+		err = IXGBE_ERR_INVALID_ARGUMENT;
+	}
+
+	return err;
 }
 
 static const struct ixgbe_mac_operations ixgbevf_mac_ops = {
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h
index 25c951daee5d..47f11a584d8c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.h
@@ -137,6 +137,8 @@ struct ixgbe_hw {
 
 	u8  revision_id;
 	bool adapter_stopped;
+
+	int api_version;
 };
 
 struct ixgbevf_hw_stats {
@@ -170,5 +172,7 @@ struct ixgbevf_info {
 	const struct ixgbe_mac_operations *mac_ops;
 };
 
+void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size);
+int ixgbevf_negotiate_api_version(struct ixgbe_hw *hw, int api);
 #endif /* __IXGBE_VF_H__ */
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 10bba09c44ea..c10e3a6de09f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -712,10 +712,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (bounce)
 		tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size);
 
-	/* Run destructor before passing skb to HW */
-	if (likely(!skb_shared(skb)))
-		skb_orphan(skb);
-
 	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tag) {
 		*(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn);
 		op_own |= htonl((bf_index & 0xffff) << 8);
diff --git a/drivers/net/ethernet/mipsnet.c b/drivers/net/ethernet/mipsnet.c
deleted file mode 100644
index db5285befe2a..000000000000
--- a/drivers/net/ethernet/mipsnet.c
+++ /dev/null
@@ -1,345 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/platform_device.h>
-#include <asm/mips-boards/simint.h>
-
-#define MIPSNET_VERSION "2007-11-17"
-
-/*
- * Net status/control block as seen by sw in the core.
- */
-struct mipsnet_regs {
-	/*
-	 * Device info for probing, reads as MIPSNET%d where %d is some
-	 * form of version.
-	 */
-	u64 devId;		/*0x00 */
-
-	/*
-	 * read only busy flag.
-	 * Set and cleared by the Net Device to indicate that an rx or a tx
-	 * is in progress.
-	 */
-	u32 busy;		/*0x08 */
-
-	/*
-	 * Set by the Net Device.
-	 * The device will set it once data has been received.
-	 * The value is the number of bytes that should be read from
-	 * rxDataBuffer.  The value will decrease till 0 until all the data
-	 * from rxDataBuffer has been read.
-	 */
-	u32 rxDataCount;	/*0x0c */
-#define MIPSNET_MAX_RXTX_DATACOUNT (1 << 16)
-
-	/*
-	 * Settable from the MIPS core, cleared by the Net Device.
-	 * The core should set the number of bytes it wants to send,
-	 * then it should write those bytes of data to txDataBuffer.
-	 * The device will clear txDataCount has been processed (not
-	 * necessarily sent).
-	 */
-	u32 txDataCount;	/*0x10 */
-
-	/*
-	 * Interrupt control
-	 *
-	 * Used to clear the interrupted generated by this dev.
-	 * Write a 1 to clear the interrupt. (except bit31).
-	 *
-	 * Bit0 is set if it was a tx-done interrupt.
-	 * Bit1 is set when new rx-data is available.
-	 *    Until this bit is cleared there will be no other RXs.
-	 *
-	 * Bit31 is used for testing, it clears after a read.
-	 *    Writing 1 to this bit will cause an interrupt to be generated.
-	 *    To clear the test interrupt, write 0 to this register.
-	 */
-	u32 interruptControl;	/*0x14 */
-#define MIPSNET_INTCTL_TXDONE     (1u << 0)
-#define MIPSNET_INTCTL_RXDONE     (1u << 1)
-#define MIPSNET_INTCTL_TESTBIT    (1u << 31)
-
-	/*
-	 * Readonly core-specific interrupt info for the device to signal
-	 * the core. The meaning of the contents of this field might change.
-	 */
-	/* XXX: the whole memIntf interrupt scheme is messy: the device
-	 * should have no control what so ever of what VPE/register set is
-	 * being used.
-	 * The MemIntf should only expose interrupt lines, and something in
-	 * the config should be responsible for the line<->core/vpe bindings.
-	 */
-	u32 interruptInfo;	/*0x18 */
-
-	/*
-	 * This is where the received data is read out.
-	 * There is more data to read until rxDataReady is 0.
-	 * Only 1 byte at this regs offset is used.
-	 */
-	u32 rxDataBuffer;	/*0x1c */
-
-	/*
-	 * This is where the data to transmit is written.
-	 * Data should be written for the amount specified in the
-	 * txDataCount register.
-	 * Only 1 byte at this regs offset is used.
-	 */
-	u32 txDataBuffer;	/*0x20 */
-};
-
-#define regaddr(dev, field) \
-  (dev->base_addr + offsetof(struct mipsnet_regs, field))
-
-static char mipsnet_string[] = "mipsnet";
-
-/*
- * Copy data from the MIPSNET rx data port
- */
-static int ioiocpy_frommipsnet(struct net_device *dev, unsigned char *kdata,
-			int len)
-{
-	for (; len > 0; len--, kdata++)
-		*kdata = inb(regaddr(dev, rxDataBuffer));
-
-	return inl(regaddr(dev, rxDataCount));
-}
-
-static inline void mipsnet_put_todevice(struct net_device *dev,
-	struct sk_buff *skb)
-{
-	int count_to_go = skb->len;
-	char *buf_ptr = skb->data;
-
-	outl(skb->len, regaddr(dev, txDataCount));
-
-	for (; count_to_go; buf_ptr++, count_to_go--)
-		outb(*buf_ptr, regaddr(dev, txDataBuffer));
-
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	dev_kfree_skb(skb);
-}
-
-static int mipsnet_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	/*
-	 * Only one packet at a time. Once TXDONE interrupt is serviced, the
-	 * queue will be restarted.
-	 */
-	netif_stop_queue(dev);
-	mipsnet_put_todevice(dev, skb);
-
-	return NETDEV_TX_OK;
-}
-
-static inline ssize_t mipsnet_get_fromdev(struct net_device *dev, size_t len)
-{
-	struct sk_buff *skb;
-
-	if (!len)
-		return len;
-
-	skb = netdev_alloc_skb(dev, len + NET_IP_ALIGN);
-	if (!skb) {
-		dev->stats.rx_dropped++;
-		return -ENOMEM;
-	}
-
-	skb_reserve(skb, NET_IP_ALIGN);
-	if (ioiocpy_frommipsnet(dev, skb_put(skb, len), len))
-		return -EFAULT;
-
-	skb->protocol = eth_type_trans(skb, dev);
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-
-	netif_rx(skb);
-
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += len;
-
-	return len;
-}
-
-static irqreturn_t mipsnet_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	u32 int_flags;
-	irqreturn_t ret = IRQ_NONE;
-
-	if (irq != dev->irq)
-		goto out_badirq;
-
-	/* TESTBIT is cleared on read. */
-	int_flags = inl(regaddr(dev, interruptControl));
-	if (int_flags & MIPSNET_INTCTL_TESTBIT) {
-		/* TESTBIT takes effect after a write with 0. */
-		outl(0, regaddr(dev, interruptControl));
-		ret = IRQ_HANDLED;
-	} else if (int_flags & MIPSNET_INTCTL_TXDONE) {
-		/* Only one packet at a time, we are done. */
-		dev->stats.tx_packets++;
-		netif_wake_queue(dev);
-		outl(MIPSNET_INTCTL_TXDONE,
-		     regaddr(dev, interruptControl));
-		ret = IRQ_HANDLED;
-	} else if (int_flags & MIPSNET_INTCTL_RXDONE) {
-		mipsnet_get_fromdev(dev, inl(regaddr(dev, rxDataCount)));
-		outl(MIPSNET_INTCTL_RXDONE, regaddr(dev, interruptControl));
-		ret = IRQ_HANDLED;
-	}
-	return ret;
-
-out_badirq:
-	printk(KERN_INFO "%s: %s(): irq %d for unknown device\n",
-	       dev->name, __func__, irq);
-	return ret;
-}
-
-static int mipsnet_open(struct net_device *dev)
-{
-	int err;
-
-	err = request_irq(dev->irq, mipsnet_interrupt,
-			  IRQF_SHARED, dev->name, (void *) dev);
-	if (err) {
-		release_region(dev->base_addr, sizeof(struct mipsnet_regs));
-		return err;
-	}
-
-	netif_start_queue(dev);
-
-	/* test interrupt handler */
-	outl(MIPSNET_INTCTL_TESTBIT, regaddr(dev, interruptControl));
-
-	return 0;
-}
-
-static int mipsnet_close(struct net_device *dev)
-{
-	netif_stop_queue(dev);
-	free_irq(dev->irq, dev);
-	return 0;
-}
-
-static void mipsnet_set_mclist(struct net_device *dev)
-{
-}
-
-static const struct net_device_ops mipsnet_netdev_ops = {
-	.ndo_open		= mipsnet_open,
-	.ndo_stop		= mipsnet_close,
-	.ndo_start_xmit		= mipsnet_xmit,
-	.ndo_set_rx_mode	= mipsnet_set_mclist,
-	.ndo_change_mtu		= eth_change_mtu,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address	= eth_mac_addr,
-};
-
-static int __devinit mipsnet_probe(struct platform_device *dev)
-{
-	struct net_device *netdev;
-	int err;
-
-	netdev = alloc_etherdev(0);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	platform_set_drvdata(dev, netdev);
-
-	netdev->netdev_ops = &mipsnet_netdev_ops;
-
-	/*
-	 * TODO: probe for these or load them from PARAM
-	 */
-	netdev->base_addr = 0x4200;
-	netdev->irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB0 +
-		      inl(regaddr(netdev, interruptInfo));
-
-	/* Get the io region now, get irq on open() */
-	if (!request_region(netdev->base_addr, sizeof(struct mipsnet_regs),
-			    "mipsnet")) {
-		err = -EBUSY;
-		goto out_free_netdev;
-	}
-
-	/*
-	 * Lacking any better mechanism to allocate a MAC address we use a
-	 * random one ...
-	 */
-	eth_hw_addr_random(netdev);
-
-	err = register_netdev(netdev);
-	if (err) {
-		printk(KERN_ERR "MIPSNet: failed to register netdev.\n");
-		goto out_free_region;
-	}
-
-	return 0;
-
-out_free_region:
-	release_region(netdev->base_addr, sizeof(struct mipsnet_regs));
-
-out_free_netdev:
-	free_netdev(netdev);
-
-out:
-	return err;
-}
-
-static int __devexit mipsnet_device_remove(struct platform_device *device)
-{
-	struct net_device *dev = platform_get_drvdata(device);
-
-	unregister_netdev(dev);
-	release_region(dev->base_addr, sizeof(struct mipsnet_regs));
-	free_netdev(dev);
-	platform_set_drvdata(device, NULL);
-
-	return 0;
-}
-
-static struct platform_driver mipsnet_driver = {
-	.driver = {
-		.name		= mipsnet_string,
-		.owner		= THIS_MODULE,
-	},
-	.probe		= mipsnet_probe,
-	.remove		= __devexit_p(mipsnet_device_remove),
-};
-
-static int __init mipsnet_init_module(void)
-{
-	int err;
-
-	printk(KERN_INFO "MIPSNet Ethernet driver. Version: %s. "
-	       "(c)2005 MIPS Technologies, Inc.\n", MIPSNET_VERSION);
-
-	err = platform_driver_register(&mipsnet_driver);
-	if (err)
-		printk(KERN_ERR "Driver registration failed\n");
-
-	return err;
-}
-
-static void __exit mipsnet_exit_module(void)
-{
-	platform_driver_unregister(&mipsnet_driver);
-}
-
-module_init(mipsnet_init_module);
-module_exit(mipsnet_exit_module);
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index f45def01a98e..876beceaf2d7 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -3409,7 +3409,7 @@ set_speed:
 
 	pause_flags = 0;
 	/* setup pause frame */
-	if (np->duplex != 0) {
+	if (netif_running(dev) && (np->duplex != 0)) {
 		if (np->autoneg && np->pause_flags & NV_PAUSEFRAME_AUTONEG) {
 			adv_pause = adv & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM);
 			lpa_pause = lpa & (LPA_PAUSE_CAP | LPA_PAUSE_ASYM);
@@ -4435,7 +4435,7 @@ static void nv_get_regs(struct net_device *dev, struct ethtool_regs *regs, void
 
 	regs->version = FORCEDETH_REGS_VER;
 	spin_lock_irq(&np->lock);
-	for (i = 0; i <= np->register_size/sizeof(u32); i++)
+	for (i = 0; i < np->register_size/sizeof(u32); i++)
 		rbuf[i] = readl(base + i*sizeof(u32));
 	spin_unlock_irq(&np->lock);
 }
@@ -5455,6 +5455,7 @@ static int nv_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 	spin_lock_irq(&np->lock);
+	nv_update_pause(dev, 0); /* otherwise stop_tx bricks NIC */
 	nv_stop_rxtx(dev);
 	nv_txrx_reset(dev);
 
@@ -5904,11 +5905,19 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
 		goto out_error;
 	}
 
+	netif_carrier_off(dev);
+
+	/* Some NICs freeze when TX pause is enabled while NIC is
+	 * down, and this stays across warm reboots. The sequence
+	 * below should be enough to recover from that state.
+	 */
+	nv_update_pause(dev, 0);
+	nv_start_tx(dev);
+	nv_stop_tx(dev);
+
 	if (id->driver_data & DEV_HAS_VLAN)
 		nv_vlan_mode(dev, dev->features);
 
-	netif_carrier_off(dev);
-
 	dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n",
 		 dev->name, np->phy_oui, np->phyaddr, dev->dev_addr);
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a7cc56007b33..e7ff886e8047 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -77,7 +77,7 @@
 static const int multicast_filter_limit = 32;
 
 #define MAX_READ_REQUEST_SHIFT	12
-#define TX_DMA_BURST	6	/* Maximum PCI burst, '6' is 1024 */
+#define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define SafeMtu		0x1c20	/* ... actually life sucks beyond ~7k */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
 
@@ -287,6 +287,8 @@ static DEFINE_PCI_DEVICE_TABLE(rtl8169_pci_tbl) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
+	{ PCI_VENDOR_ID_DLINK,			0x4300,
+		PCI_VENDOR_ID_DLINK, 0x4b10,		 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4300), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4302), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AT,		0xc107), 0, 0, RTL_CFG_0 },
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index fb3cbc27063c..25906c1d1b15 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -34,3 +34,10 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
+config SFC_PTP
+	bool "Solarflare SFC9000-family PTP support"
+	depends on SFC && PTP_1588_CLOCK && !(SFC=y && PTP_1588_CLOCK=m)
+	default y
+	---help---
+	  This enables support for the Precision Time Protocol (PTP)
+	  on SFC9000-family NICs
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index ea1f8db57318..e11f2ecf69d9 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -5,5 +5,6 @@ sfc-y			+= efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \
 			   mcdi.o mcdi_phy.o mcdi_mon.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o
+sfc-$(CONFIG_SFC_PTP)	+= ptp.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h
index b26a954c27fc..5400a33f254f 100644
--- a/drivers/net/ethernet/sfc/bitfield.h
+++ b/drivers/net/ethernet/sfc/bitfield.h
@@ -120,10 +120,10 @@ typedef union efx_oword {
  * [0,high-low), with garbage in bits [high-low+1,...).
  */
 #define EFX_EXTRACT_NATIVE(native_element, min, max, low, high)		\
-	(((low > max) || (high < min)) ? 0 :				\
-	 ((low > min) ?							\
-	  ((native_element) >> (low - min)) :				\
-	  ((native_element) << (min - low))))
+	((low) > (max) || (high) < (min) ? 0 :				\
+	 (low) > (min) ?						\
+	 (native_element) >> ((low) - (min)) :				\
+	 (native_element) << ((min) - (low)))
 
 /*
  * Extract bit field portion [low,high) from the 64-bit little-endian
@@ -142,27 +142,27 @@ typedef union efx_oword {
 #define EFX_EXTRACT_OWORD64(oword, low, high)				\
 	((EFX_EXTRACT64((oword).u64[0], 0, 63, low, high) |		\
 	  EFX_EXTRACT64((oword).u64[1], 64, 127, low, high)) &		\
-	 EFX_MASK64(high + 1 - low))
+	 EFX_MASK64((high) + 1 - (low)))
 
 #define EFX_EXTRACT_QWORD64(qword, low, high)				\
 	(EFX_EXTRACT64((qword).u64[0], 0, 63, low, high) &		\
-	 EFX_MASK64(high + 1 - low))
+	 EFX_MASK64((high) + 1 - (low)))
 
 #define EFX_EXTRACT_OWORD32(oword, low, high)				\
 	((EFX_EXTRACT32((oword).u32[0], 0, 31, low, high) |		\
 	  EFX_EXTRACT32((oword).u32[1], 32, 63, low, high) |		\
 	  EFX_EXTRACT32((oword).u32[2], 64, 95, low, high) |		\
 	  EFX_EXTRACT32((oword).u32[3], 96, 127, low, high)) &		\
-	 EFX_MASK32(high + 1 - low))
+	 EFX_MASK32((high) + 1 - (low)))
 
 #define EFX_EXTRACT_QWORD32(qword, low, high)				\
 	((EFX_EXTRACT32((qword).u32[0], 0, 31, low, high) |		\
 	  EFX_EXTRACT32((qword).u32[1], 32, 63, low, high)) &		\
-	 EFX_MASK32(high + 1 - low))
+	 EFX_MASK32((high) + 1 - (low)))
 
 #define EFX_EXTRACT_DWORD(dword, low, high)			\
 	(EFX_EXTRACT32((dword).u32[0], 0, 31, low, high) &	\
-	 EFX_MASK32(high + 1 - low))
+	 EFX_MASK32((high) + 1 - (low)))
 
 #define EFX_OWORD_FIELD64(oword, field)				\
 	EFX_EXTRACT_OWORD64(oword, EFX_LOW_BIT(field),		\
@@ -442,10 +442,10 @@ typedef union efx_oword {
 	cpu_to_le32(EFX_INSERT_NATIVE(min, max, low, high, value))
 
 #define EFX_INPLACE_MASK64(min, max, low, high)				\
-	EFX_INSERT64(min, max, low, high, EFX_MASK64(high + 1 - low))
+	EFX_INSERT64(min, max, low, high, EFX_MASK64((high) + 1 - (low)))
 
 #define EFX_INPLACE_MASK32(min, max, low, high)				\
-	EFX_INSERT32(min, max, low, high, EFX_MASK32(high + 1 - low))
+	EFX_INSERT32(min, max, low, high, EFX_MASK32((high) + 1 - (low)))
 
 #define EFX_SET_OWORD64(oword, low, high, value) do {			\
 	(oword).u64[0] = (((oword).u64[0]				\
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 65a8d49106a4..96bd980e828d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -202,11 +202,21 @@ static void efx_stop_all(struct efx_nic *efx);
 
 #define EFX_ASSERT_RESET_SERIALISED(efx)		\
 	do {						\
-		if ((efx->state == STATE_RUNNING) ||	\
+		if ((efx->state == STATE_READY) ||	\
 		    (efx->state == STATE_DISABLED))	\
 			ASSERT_RTNL();			\
 	} while (0)
 
+static int efx_check_disabled(struct efx_nic *efx)
+{
+	if (efx->state == STATE_DISABLED) {
+		netif_err(efx, drv, efx->net_dev,
+			  "device is disabled due to earlier errors\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 /**************************************************************************
  *
  * Event queue processing
@@ -630,6 +640,16 @@ static void efx_start_datapath(struct efx_nic *efx)
 	efx->rx_buffer_order = get_order(efx->rx_buffer_len +
 					 sizeof(struct efx_rx_page_state));
 
+	/* We must keep at least one descriptor in a TX ring empty.
+	 * We could avoid this when the queue size does not exactly
+	 * match the hardware ring size, but it's not that important.
+	 * Therefore we stop the queue when one more skb might fill
+	 * the ring completely.  We wake it when half way back to
+	 * empty.
+	 */
+	efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx);
+	efx->txq_wake_thresh = efx->txq_stop_thresh / 2;
+
 	/* Initialise the channels */
 	efx_for_each_channel(channel, efx) {
 		efx_for_each_channel_tx_queue(tx_queue, channel)
@@ -714,6 +734,7 @@ static void efx_remove_channel(struct efx_channel *channel)
 	efx_for_each_possible_channel_tx_queue(tx_queue, channel)
 		efx_remove_tx_queue(tx_queue);
 	efx_remove_eventq(channel);
+	channel->type->post_remove(channel);
 }
 
 static void efx_remove_channels(struct efx_nic *efx)
@@ -730,7 +751,11 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 	struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
 	u32 old_rxq_entries, old_txq_entries;
 	unsigned i, next_buffer_table = 0;
-	int rc = 0;
+	int rc;
+
+	rc = efx_check_disabled(efx);
+	if (rc)
+		return rc;
 
 	/* Not all channels should be reallocated. We must avoid
 	 * reallocating their buffer table entries.
@@ -828,6 +853,7 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
 
 static const struct efx_channel_type efx_default_channel_type = {
 	.pre_probe		= efx_channel_dummy_op_int,
+	.post_remove		= efx_channel_dummy_op_void,
 	.get_name		= efx_get_channel_name,
 	.copy			= efx_copy_channel,
 	.keep_eventq		= false,
@@ -838,6 +864,10 @@ int efx_channel_dummy_op_int(struct efx_channel *channel)
 	return 0;
 }
 
+void efx_channel_dummy_op_void(struct efx_channel *channel)
+{
+}
+
 /**************************************************************************
  *
  * Port handling
@@ -1365,6 +1395,8 @@ static void efx_start_interrupts(struct efx_nic *efx, bool may_keep_eventq)
 {
 	struct efx_channel *channel;
 
+	BUG_ON(efx->state == STATE_DISABLED);
+
 	if (efx->legacy_irq)
 		efx->legacy_irq_enabled = true;
 	efx_nic_enable_interrupts(efx);
@@ -1382,6 +1414,9 @@ static void efx_stop_interrupts(struct efx_nic *efx, bool may_keep_eventq)
 {
 	struct efx_channel *channel;
 
+	if (efx->state == STATE_DISABLED)
+		return;
+
 	efx_mcdi_mode_poll(efx);
 
 	efx_nic_disable_interrupts(efx);
@@ -1422,10 +1457,16 @@ static void efx_set_channels(struct efx_nic *efx)
 	efx->tx_channel_offset =
 		separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0;
 
-	/* We need to adjust the TX queue numbers if we have separate
+	/* We need to mark which channels really have RX and TX
+	 * queues, and adjust the TX queue numbers if we have separate
 	 * RX-only and TX-only channels.
 	 */
 	efx_for_each_channel(channel, efx) {
+		if (channel->channel < efx->n_rx_channels)
+			channel->rx_queue.core_index = channel->channel;
+		else
+			channel->rx_queue.core_index = -1;
+
 		efx_for_each_channel_tx_queue(tx_queue, channel)
 			tx_queue->queue -= (efx->tx_channel_offset *
 					    EFX_TXQ_TYPES);
@@ -1533,22 +1574,21 @@ static int efx_probe_all(struct efx_nic *efx)
 	return rc;
 }
 
-/* Called after previous invocation(s) of efx_stop_all, restarts the port,
- * kernel transmit queues and NAPI processing, and ensures that the port is
- * scheduled to be reconfigured. This function is safe to call multiple
- * times when the NIC is in any state.
+/* If the interface is supposed to be running but is not, start
+ * the hardware and software data path, regular activity for the port
+ * (MAC statistics, link polling, etc.) and schedule the port to be
+ * reconfigured.  Interrupts must already be enabled.  This function
+ * is safe to call multiple times, so long as the NIC is not disabled.
+ * Requires the RTNL lock.
  */
 static void efx_start_all(struct efx_nic *efx)
 {
 	EFX_ASSERT_RESET_SERIALISED(efx);
+	BUG_ON(efx->state == STATE_DISABLED);
 
 	/* Check that it is appropriate to restart the interface. All
 	 * of these flags are safe to read under just the rtnl lock */
-	if (efx->port_enabled)
-		return;
-	if ((efx->state != STATE_RUNNING) && (efx->state != STATE_INIT))
-		return;
-	if (!netif_running(efx->net_dev))
+	if (efx->port_enabled || !netif_running(efx->net_dev))
 		return;
 
 	efx_start_port(efx);
@@ -1582,11 +1622,11 @@ static void efx_flush_all(struct efx_nic *efx)
 	cancel_work_sync(&efx->mac_work);
 }
 
-/* Quiesce hardware and software without bringing the link down.
- * Safe to call multiple times, when the nic and interface is in any
- * state. The caller is guaranteed to subsequently be in a position
- * to modify any hardware and software state they see fit without
- * taking locks. */
+/* Quiesce the hardware and software data path, and regular activity
+ * for the port without bringing the link down.  Safe to call multiple
+ * times with the NIC in almost any state, but interrupts should be
+ * enabled.  Requires the RTNL lock.
+ */
 static void efx_stop_all(struct efx_nic *efx)
 {
 	EFX_ASSERT_RESET_SERIALISED(efx);
@@ -1739,7 +1779,8 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct mii_ioctl_data *data = if_mii(ifr);
 
-	EFX_ASSERT_RESET_SERIALISED(efx);
+	if (cmd == SIOCSHWTSTAMP)
+		return efx_ptp_ioctl(efx, ifr, cmd);
 
 	/* Convert phy_id from older PRTAD/DEVAD format */
 	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
@@ -1820,13 +1861,14 @@ static void efx_netpoll(struct net_device *net_dev)
 static int efx_net_open(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	EFX_ASSERT_RESET_SERIALISED(efx);
+	int rc;
 
 	netif_dbg(efx, ifup, efx->net_dev, "opening device on CPU %d\n",
 		  raw_smp_processor_id());
 
-	if (efx->state == STATE_DISABLED)
-		return -EIO;
+	rc = efx_check_disabled(efx);
+	if (rc)
+		return rc;
 	if (efx->phy_mode & PHY_MODE_SPECIAL)
 		return -EBUSY;
 	if (efx_mcdi_poll_reboot(efx) && efx_reset(efx, RESET_TYPE_ALL))
@@ -1852,10 +1894,8 @@ static int efx_net_stop(struct net_device *net_dev)
 	netif_dbg(efx, ifdown, efx->net_dev, "closing on CPU %d\n",
 		  raw_smp_processor_id());
 
-	if (efx->state != STATE_DISABLED) {
-		/* Stop the device and flush all the channels */
-		efx_stop_all(efx);
-	}
+	/* Stop the device and flush all the channels */
+	efx_stop_all(efx);
 
 	return 0;
 }
@@ -1915,9 +1955,11 @@ static void efx_watchdog(struct net_device *net_dev)
 static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	int rc;
 
-	EFX_ASSERT_RESET_SERIALISED(efx);
-
+	rc = efx_check_disabled(efx);
+	if (rc)
+		return rc;
 	if (new_mtu > EFX_MAX_MTU)
 		return -EINVAL;
 
@@ -1926,8 +1968,6 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 	netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
 
 	mutex_lock(&efx->mac_lock);
-	/* Reconfigure the MAC before enabling the dma queues so that
-	 * the RX buffers don't overflow */
 	net_dev->mtu = new_mtu;
 	efx->type->reconfigure_mac(efx);
 	mutex_unlock(&efx->mac_lock);
@@ -1942,8 +1982,6 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
 	struct sockaddr *addr = data;
 	char *new_addr = addr->sa_data;
 
-	EFX_ASSERT_RESET_SERIALISED(efx);
-
 	if (!is_valid_ether_addr(new_addr)) {
 		netif_err(efx, drv, efx->net_dev,
 			  "invalid ethernet MAC address requested: %pM\n",
@@ -2079,11 +2117,27 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 	rtnl_lock();
 
+	/* Enable resets to be scheduled and check whether any were
+	 * already requested.  If so, the NIC is probably hosed so we
+	 * abort.
+	 */
+	efx->state = STATE_READY;
+	smp_mb(); /* ensure we change state before checking reset_pending */
+	if (efx->reset_pending) {
+		netif_err(efx, probe, efx->net_dev,
+			  "aborting probe due to scheduled reset\n");
+		rc = -EIO;
+		goto fail_locked;
+	}
+
 	rc = dev_alloc_name(net_dev, net_dev->name);
 	if (rc < 0)
 		goto fail_locked;
 	efx_update_name(efx);
 
+	/* Always start with carrier off; PHY events will detect the link */
+	netif_carrier_off(net_dev);
+
 	rc = register_netdevice(net_dev);
 	if (rc)
 		goto fail_locked;
@@ -2094,9 +2148,6 @@ static int efx_register_netdev(struct efx_nic *efx)
 			efx_init_tx_queue_core_txq(tx_queue);
 	}
 
-	/* Always start with carrier off; PHY events will detect the link */
-	netif_carrier_off(net_dev);
-
 	rtnl_unlock();
 
 	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type);
@@ -2108,14 +2159,14 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 	return 0;
 
+fail_registered:
+	rtnl_lock();
+	unregister_netdevice(net_dev);
 fail_locked:
+	efx->state = STATE_UNINIT;
 	rtnl_unlock();
 	netif_err(efx, drv, efx->net_dev, "could not register net dev\n");
 	return rc;
-
-fail_registered:
-	unregister_netdev(net_dev);
-	return rc;
 }
 
 static void efx_unregister_netdev(struct efx_nic *efx)
@@ -2138,7 +2189,11 @@ static void efx_unregister_netdev(struct efx_nic *efx)
 
 	strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
 	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
-	unregister_netdev(efx->net_dev);
+
+	rtnl_lock();
+	unregister_netdevice(efx->net_dev);
+	efx->state = STATE_UNINIT;
+	rtnl_unlock();
 }
 
 /**************************************************************************
@@ -2154,9 +2209,9 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
 	efx_stop_all(efx);
-	mutex_lock(&efx->mac_lock);
-
 	efx_stop_interrupts(efx, false);
+
+	mutex_lock(&efx->mac_lock);
 	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE)
 		efx->phy_op->fini(efx);
 	efx->type->fini(efx);
@@ -2276,16 +2331,15 @@ static void efx_reset_work(struct work_struct *data)
 	if (!pending)
 		return;
 
-	/* If we're not RUNNING then don't reset. Leave the reset_pending
-	 * flags set so that efx_pci_probe_main will be retried */
-	if (efx->state != STATE_RUNNING) {
-		netif_info(efx, drv, efx->net_dev,
-			   "scheduled reset quenched. NIC not RUNNING\n");
-		return;
-	}
-
 	rtnl_lock();
-	(void)efx_reset(efx, fls(pending) - 1);
+
+	/* We checked the state in efx_schedule_reset() but it may
+	 * have changed by now.  Now that we have the RTNL lock,
+	 * it cannot change again.
+	 */
+	if (efx->state == STATE_READY)
+		(void)efx_reset(efx, fls(pending) - 1);
+
 	rtnl_unlock();
 }
 
@@ -2311,6 +2365,13 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
 	}
 
 	set_bit(method, &efx->reset_pending);
+	smp_mb(); /* ensure we change reset_pending before checking state */
+
+	/* If we're not READY then just leave the flags set as the cue
+	 * to abort probing or reschedule the reset later.
+	 */
+	if (ACCESS_ONCE(efx->state) != STATE_READY)
+		return;
 
 	/* efx_process_channel() will no longer read events once a
 	 * reset is scheduled. So switch back to poll'd MCDI completions. */
@@ -2376,13 +2437,12 @@ static const struct efx_phy_operations efx_dummy_phy_operations = {
 /* This zeroes out and then fills in the invariants in a struct
  * efx_nic (including all sub-structures).
  */
-static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
+static int efx_init_struct(struct efx_nic *efx,
 			   struct pci_dev *pci_dev, struct net_device *net_dev)
 {
 	int i;
 
 	/* Initialise common structures */
-	memset(efx, 0, sizeof(*efx));
 	spin_lock_init(&efx->biu_lock);
 #ifdef CONFIG_SFC_MTD
 	INIT_LIST_HEAD(&efx->mtd_list);
@@ -2392,7 +2452,7 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
 	INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
 	efx->pci_dev = pci_dev;
 	efx->msg_enable = debug;
-	efx->state = STATE_INIT;
+	efx->state = STATE_UNINIT;
 	strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name));
 
 	efx->net_dev = net_dev;
@@ -2409,8 +2469,6 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
 			goto fail;
 	}
 
-	efx->type = type;
-
 	EFX_BUG_ON_PARANOID(efx->type->phys_addr_channels > EFX_MAX_CHANNELS);
 
 	/* Higher numbered interrupt modes are less capable! */
@@ -2455,6 +2513,12 @@ static void efx_fini_struct(struct efx_nic *efx)
  */
 static void efx_pci_remove_main(struct efx_nic *efx)
 {
+	/* Flush reset_work. It can no longer be scheduled since we
+	 * are not READY.
+	 */
+	BUG_ON(efx->state == STATE_READY);
+	cancel_work_sync(&efx->reset_work);
+
 #ifdef CONFIG_RFS_ACCEL
 	free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
 	efx->net_dev->rx_cpu_rmap = NULL;
@@ -2480,24 +2544,15 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 
 	/* Mark the NIC as fini, then stop the interface */
 	rtnl_lock();
-	efx->state = STATE_FINI;
 	dev_close(efx->net_dev);
-
-	/* Allow any queued efx_resets() to complete */
+	efx_stop_interrupts(efx, false);
 	rtnl_unlock();
 
-	efx_stop_interrupts(efx, false);
 	efx_sriov_fini(efx);
 	efx_unregister_netdev(efx);
 
 	efx_mtd_remove(efx);
 
-	/* Wait for any scheduled resets to complete. No more will be
-	 * scheduled from this point because efx_stop_all() has been
-	 * called, we are no longer registered with driverlink, and
-	 * the net_device's have been removed. */
-	cancel_work_sync(&efx->reset_work);
-
 	efx_pci_remove_main(efx);
 
 	efx_fini_io(efx);
@@ -2617,7 +2672,6 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 				   const struct pci_device_id *entry)
 {
-	const struct efx_nic_type *type = (const struct efx_nic_type *) entry->driver_data;
 	struct net_device *net_dev;
 	struct efx_nic *efx;
 	int rc;
@@ -2627,10 +2681,12 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 				     EFX_MAX_RX_QUEUES);
 	if (!net_dev)
 		return -ENOMEM;
-	net_dev->features |= (type->offload_features | NETIF_F_SG |
+	efx = netdev_priv(net_dev);
+	efx->type = (const struct efx_nic_type *) entry->driver_data;
+	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
 			      NETIF_F_HIGHDMA | NETIF_F_TSO |
 			      NETIF_F_RXCSUM);
-	if (type->offload_features & NETIF_F_V6_CSUM)
+	if (efx->type->offload_features & NETIF_F_V6_CSUM)
 		net_dev->features |= NETIF_F_TSO6;
 	/* Mask for features that also apply to VLAN devices */
 	net_dev->vlan_features |= (NETIF_F_ALL_CSUM | NETIF_F_SG |
@@ -2638,10 +2694,9 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 				   NETIF_F_RXCSUM);
 	/* All offloads can be toggled */
 	net_dev->hw_features = net_dev->features & ~NETIF_F_HIGHDMA;
-	efx = netdev_priv(net_dev);
 	pci_set_drvdata(pci_dev, efx);
 	SET_NETDEV_DEV(net_dev, &pci_dev->dev);
-	rc = efx_init_struct(efx, type, pci_dev, net_dev);
+	rc = efx_init_struct(efx, pci_dev, net_dev);
 	if (rc)
 		goto fail1;
 
@@ -2656,28 +2711,9 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 		goto fail2;
 
 	rc = efx_pci_probe_main(efx);
-
-	/* Serialise against efx_reset(). No more resets will be
-	 * scheduled since efx_stop_all() has been called, and we have
-	 * not and never have been registered.
-	 */
-	cancel_work_sync(&efx->reset_work);
-
 	if (rc)
 		goto fail3;
 
-	/* If there was a scheduled reset during probe, the NIC is
-	 * probably hosed anyway.
-	 */
-	if (efx->reset_pending) {
-		rc = -EIO;
-		goto fail4;
-	}
-
-	/* Switch to the running state before we expose the device to the OS,
-	 * so that dev_open()|efx_start_all() will actually start the device */
-	efx->state = STATE_RUNNING;
-
 	rc = efx_register_netdev(efx);
 	if (rc)
 		goto fail4;
@@ -2717,12 +2753,18 @@ static int efx_pm_freeze(struct device *dev)
 {
 	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
 
-	efx->state = STATE_FINI;
+	rtnl_lock();
 
-	netif_device_detach(efx->net_dev);
+	if (efx->state != STATE_DISABLED) {
+		efx->state = STATE_UNINIT;
 
-	efx_stop_all(efx);
-	efx_stop_interrupts(efx, false);
+		netif_device_detach(efx->net_dev);
+
+		efx_stop_all(efx);
+		efx_stop_interrupts(efx, false);
+	}
+
+	rtnl_unlock();
 
 	return 0;
 }
@@ -2731,21 +2773,25 @@ static int efx_pm_thaw(struct device *dev)
 {
 	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
 
-	efx->state = STATE_INIT;
+	rtnl_lock();
 
-	efx_start_interrupts(efx, false);
+	if (efx->state != STATE_DISABLED) {
+		efx_start_interrupts(efx, false);
 
-	mutex_lock(&efx->mac_lock);
-	efx->phy_op->reconfigure(efx);
-	mutex_unlock(&efx->mac_lock);
+		mutex_lock(&efx->mac_lock);
+		efx->phy_op->reconfigure(efx);
+		mutex_unlock(&efx->mac_lock);
 
-	efx_start_all(efx);
+		efx_start_all(efx);
 
-	netif_device_attach(efx->net_dev);
+		netif_device_attach(efx->net_dev);
 
-	efx->state = STATE_RUNNING;
+		efx->state = STATE_READY;
 
-	efx->type->resume_wol(efx);
+		efx->type->resume_wol(efx);
+	}
+
+	rtnl_unlock();
 
 	/* Reschedule any quenched resets scheduled during efx_pm_freeze() */
 	queue_work(reset_workqueue, &efx->reset_work);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 70755c97251a..f11170bc48bf 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -102,6 +102,7 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel) {}
 
 /* Channels */
 extern int efx_channel_dummy_op_int(struct efx_channel *channel);
+extern void efx_channel_dummy_op_void(struct efx_channel *channel);
 extern void efx_process_channel_now(struct efx_channel *channel);
 extern int
 efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 5faedd855b77..90f078eff8e6 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -337,7 +337,8 @@ static int efx_fill_loopback_test(struct efx_nic *efx,
 				  unsigned int test_index,
 				  struct ethtool_string *strings, u64 *data)
 {
-	struct efx_channel *channel = efx_get_channel(efx, 0);
+	struct efx_channel *channel =
+		efx_get_channel(efx, efx->tx_channel_offset);
 	struct efx_tx_queue *tx_queue;
 
 	efx_for_each_channel_tx_queue(tx_queue, channel) {
@@ -529,9 +530,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
 	if (!efx_tests)
 		goto fail;
 
-
-	ASSERT_RTNL();
-	if (efx->state != STATE_RUNNING) {
+	if (efx->state != STATE_READY) {
 		rc = -EIO;
 		goto fail1;
 	}
@@ -962,9 +961,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 	int rc;
 
 	/* Check that user wants us to choose the location */
-	if (rule->location != RX_CLS_LOC_ANY &&
-	    rule->location != RX_CLS_LOC_FIRST &&
-	    rule->location != RX_CLS_LOC_LAST)
+	if (rule->location != RX_CLS_LOC_ANY)
 		return -EINVAL;
 
 	/* Range-check ring_cookie */
@@ -978,9 +975,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 	     rule->m_ext.data[1]))
 		return -EINVAL;
 
-	efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL,
-			   (rule->location == RX_CLS_LOC_FIRST) ?
-			   EFX_FILTER_FLAG_RX_OVERRIDE_IP : 0,
+	efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL, 0,
 			   (rule->ring_cookie == RX_CLS_FLOW_DISC) ?
 			   0xfff : rule->ring_cookie);
 
@@ -1176,6 +1171,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_indir		= efx_ethtool_get_rxfh_indir,
 	.set_rxfh_indir		= efx_ethtool_set_rxfh_indir,
+	.get_ts_info		= efx_ptp_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
 };
diff --git a/drivers/net/ethernet/sfc/falcon_boards.c b/drivers/net/ethernet/sfc/falcon_boards.c
index 8687a6c3db0d..ec1e99d0dcad 100644
--- a/drivers/net/ethernet/sfc/falcon_boards.c
+++ b/drivers/net/ethernet/sfc/falcon_boards.c
@@ -380,7 +380,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev,
 		new_mode = PHY_MODE_SPECIAL;
 	if (!((old_mode ^ new_mode) & PHY_MODE_SPECIAL)) {
 		err = 0;
-	} else if (efx->state != STATE_RUNNING || netif_running(efx->net_dev)) {
+	} else if (efx->state != STATE_READY || netif_running(efx->net_dev)) {
 		err = -EBUSY;
 	} else {
 		/* Reset the PHY, reconfigure the MAC and enable/disable
diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
index c3fd61f0a95c..8af42cd1feda 100644
--- a/drivers/net/ethernet/sfc/filter.c
+++ b/drivers/net/ethernet/sfc/filter.c
@@ -162,20 +162,12 @@ static void efx_filter_push_rx_config(struct efx_nic *efx)
 			!!(table->spec[EFX_FILTER_INDEX_UC_DEF].flags &
 			   EFX_FILTER_FLAG_RX_RSS));
 		EFX_SET_OWORD_FIELD(
-			filter_ctl, FRF_CZ_UNICAST_NOMATCH_IP_OVERRIDE,
-			!!(table->spec[EFX_FILTER_INDEX_UC_DEF].flags &
-			   EFX_FILTER_FLAG_RX_OVERRIDE_IP));
-		EFX_SET_OWORD_FIELD(
 			filter_ctl, FRF_CZ_MULTICAST_NOMATCH_Q_ID,
 			table->spec[EFX_FILTER_INDEX_MC_DEF].dmaq_id);
 		EFX_SET_OWORD_FIELD(
 			filter_ctl, FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED,
 			!!(table->spec[EFX_FILTER_INDEX_MC_DEF].flags &
 			   EFX_FILTER_FLAG_RX_RSS));
-		EFX_SET_OWORD_FIELD(
-			filter_ctl, FRF_CZ_MULTICAST_NOMATCH_IP_OVERRIDE,
-			!!(table->spec[EFX_FILTER_INDEX_MC_DEF].flags &
-			   EFX_FILTER_FLAG_RX_OVERRIDE_IP));
 	}
 
 	efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
@@ -480,14 +472,12 @@ static u32 efx_filter_build(efx_oword_t *filter, struct efx_filter_spec *spec)
 
 	case EFX_FILTER_TABLE_RX_MAC: {
 		bool is_wild = spec->type == EFX_FILTER_MAC_WILD;
-		EFX_POPULATE_OWORD_8(
+		EFX_POPULATE_OWORD_7(
 			*filter,
 			FRF_CZ_RMFT_RSS_EN,
 			!!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
 			FRF_CZ_RMFT_SCATTER_EN,
 			!!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
-			FRF_CZ_RMFT_IP_OVERRIDE,
-			!!(spec->flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP),
 			FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id,
 			FRF_CZ_RMFT_WILDCARD_MATCH, is_wild,
 			FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2],
@@ -567,49 +557,62 @@ static int efx_filter_search(struct efx_filter_table *table,
 }
 
 /*
- * Construct/deconstruct external filter IDs.  These must be ordered
- * by matching priority, for RX NFC semantics.
+ * Construct/deconstruct external filter IDs.  At least the RX filter
+ * IDs must be ordered by matching priority, for RX NFC semantics.
  *
- * Each RX MAC filter entry has a flag for whether it can override an
- * RX IP filter that also matches.  So we assign locations for MAC
- * filters with overriding behaviour, then for IP filters, then for
- * MAC filters without overriding behaviour.
+ * Deconstruction needs to be robust against invalid IDs so that
+ * efx_filter_remove_id_safe() and efx_filter_get_filter_safe() can
+ * accept user-provided IDs.
  */
 
-#define EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP	0
-#define EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP	1
-#define EFX_FILTER_MATCH_PRI_NORMAL_BASE	2
+#define EFX_FILTER_MATCH_PRI_COUNT	5
+
+static const u8 efx_filter_type_match_pri[EFX_FILTER_TYPE_COUNT] = {
+	[EFX_FILTER_TCP_FULL]	= 0,
+	[EFX_FILTER_UDP_FULL]	= 0,
+	[EFX_FILTER_TCP_WILD]	= 1,
+	[EFX_FILTER_UDP_WILD]	= 1,
+	[EFX_FILTER_MAC_FULL]	= 2,
+	[EFX_FILTER_MAC_WILD]	= 3,
+	[EFX_FILTER_UC_DEF]	= 4,
+	[EFX_FILTER_MC_DEF]	= 4,
+};
+
+static const enum efx_filter_table_id efx_filter_range_table[] = {
+	EFX_FILTER_TABLE_RX_IP,		/* RX match pri 0 */
+	EFX_FILTER_TABLE_RX_IP,
+	EFX_FILTER_TABLE_RX_MAC,
+	EFX_FILTER_TABLE_RX_MAC,
+	EFX_FILTER_TABLE_RX_DEF,	/* RX match pri 4 */
+	EFX_FILTER_TABLE_COUNT,		/* TX match pri 0; invalid */
+	EFX_FILTER_TABLE_COUNT,		/* invalid */
+	EFX_FILTER_TABLE_TX_MAC,
+	EFX_FILTER_TABLE_TX_MAC,	/* TX match pri 3 */
+};
 
 #define EFX_FILTER_INDEX_WIDTH	13
 #define EFX_FILTER_INDEX_MASK	((1 << EFX_FILTER_INDEX_WIDTH) - 1)
 
-static inline u32 efx_filter_make_id(enum efx_filter_table_id table_id,
-				     unsigned int index, u8 flags)
+static inline u32
+efx_filter_make_id(const struct efx_filter_spec *spec, unsigned int index)
 {
-	unsigned int match_pri = EFX_FILTER_MATCH_PRI_NORMAL_BASE + table_id;
+	unsigned int range;
 
-	if (flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP) {
-		if (table_id == EFX_FILTER_TABLE_RX_MAC)
-			match_pri = EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP;
-		else if (table_id == EFX_FILTER_TABLE_RX_DEF)
-			match_pri = EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP;
-	}
+	range = efx_filter_type_match_pri[spec->type];
+	if (!(spec->flags & EFX_FILTER_FLAG_RX))
+		range += EFX_FILTER_MATCH_PRI_COUNT;
 
-	return match_pri << EFX_FILTER_INDEX_WIDTH | index;
+	return range << EFX_FILTER_INDEX_WIDTH | index;
 }
 
 static inline enum efx_filter_table_id efx_filter_id_table_id(u32 id)
 {
-	unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH;
+	unsigned int range = id >> EFX_FILTER_INDEX_WIDTH;
 
-	switch (match_pri) {
-	case EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP:
-		return EFX_FILTER_TABLE_RX_MAC;
-	case EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP:
-		return EFX_FILTER_TABLE_RX_DEF;
-	default:
-		return match_pri - EFX_FILTER_MATCH_PRI_NORMAL_BASE;
-	}
+	if (range < ARRAY_SIZE(efx_filter_range_table))
+		return efx_filter_range_table[range];
+	else
+		return EFX_FILTER_TABLE_COUNT; /* invalid */
 }
 
 static inline unsigned int efx_filter_id_index(u32 id)
@@ -619,12 +622,9 @@ static inline unsigned int efx_filter_id_index(u32 id)
 
 static inline u8 efx_filter_id_flags(u32 id)
 {
-	unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH;
+	unsigned int range = id >> EFX_FILTER_INDEX_WIDTH;
 
-	if (match_pri < EFX_FILTER_MATCH_PRI_NORMAL_BASE)
-		return EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_OVERRIDE_IP;
-	else if (match_pri <=
-		 EFX_FILTER_MATCH_PRI_NORMAL_BASE + EFX_FILTER_TABLE_RX_DEF)
+	if (range < EFX_FILTER_MATCH_PRI_COUNT)
 		return EFX_FILTER_FLAG_RX;
 	else
 		return EFX_FILTER_FLAG_TX;
@@ -633,14 +633,15 @@ static inline u8 efx_filter_id_flags(u32 id)
 u32 efx_filter_get_rx_id_limit(struct efx_nic *efx)
 {
 	struct efx_filter_state *state = efx->filter_state;
-	unsigned int table_id = EFX_FILTER_TABLE_RX_DEF;
+	unsigned int range = EFX_FILTER_MATCH_PRI_COUNT - 1;
+	enum efx_filter_table_id table_id;
 
 	do {
+		table_id = efx_filter_range_table[range];
 		if (state->table[table_id].size != 0)
-			return ((EFX_FILTER_MATCH_PRI_NORMAL_BASE + table_id)
-				<< EFX_FILTER_INDEX_WIDTH) +
+			return range << EFX_FILTER_INDEX_WIDTH |
 				state->table[table_id].size;
-	} while (table_id--);
+	} while (range--);
 
 	return 0;
 }
@@ -718,7 +719,7 @@ s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
 	netif_vdbg(efx, hw, efx->net_dev,
 		   "%s: filter type %d index %d rxq %u set",
 		   __func__, spec->type, filter_idx, spec->dmaq_id);
-	rc = efx_filter_make_id(table->id, filter_idx, spec->flags);
+	rc = efx_filter_make_id(spec, filter_idx);
 
 out:
 	spin_unlock_bh(&state->lock);
@@ -781,8 +782,7 @@ int efx_filter_remove_id_safe(struct efx_nic *efx,
 	spin_lock_bh(&state->lock);
 
 	if (test_bit(filter_idx, table->used_bitmap) &&
-	    spec->priority == priority &&
-	    !((spec->flags ^ filter_flags) & EFX_FILTER_FLAG_RX_OVERRIDE_IP)) {
+	    spec->priority == priority) {
 		efx_filter_table_clear_entry(efx, table, filter_idx);
 		if (table->used == 0)
 			efx_filter_table_reset_search_depth(table);
@@ -833,8 +833,7 @@ int efx_filter_get_filter_safe(struct efx_nic *efx,
 	spin_lock_bh(&state->lock);
 
 	if (test_bit(filter_idx, table->used_bitmap) &&
-	    spec->priority == priority &&
-	    !((spec->flags ^ filter_flags) & EFX_FILTER_FLAG_RX_OVERRIDE_IP)) {
+	    spec->priority == priority) {
 		*spec_buf = *spec;
 		rc = 0;
 	} else {
@@ -927,8 +926,7 @@ s32 efx_filter_get_rx_ids(struct efx_nic *efx,
 					goto out;
 				}
 				buf[count++] = efx_filter_make_id(
-					table_id, filter_idx,
-					table->spec[filter_idx].flags);
+					&table->spec[filter_idx], filter_idx);
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h
index 3c77802aed6c..5cb54723b824 100644
--- a/drivers/net/ethernet/sfc/filter.h
+++ b/drivers/net/ethernet/sfc/filter.h
@@ -61,16 +61,12 @@ enum efx_filter_priority {
  *	according to the indirection table.
  * @EFX_FILTER_FLAG_RX_SCATTER: Enable DMA scatter on the receiving
  *	queue.
- * @EFX_FILTER_FLAG_RX_OVERRIDE_IP: Enables a MAC filter to override
- *	any IP filter that matches the same packet.  By default, IP
- *	filters take precedence.
  * @EFX_FILTER_FLAG_RX: Filter is for RX
  * @EFX_FILTER_FLAG_TX: Filter is for TX
  */
 enum efx_filter_flags {
 	EFX_FILTER_FLAG_RX_RSS = 0x01,
 	EFX_FILTER_FLAG_RX_SCATTER = 0x02,
-	EFX_FILTER_FLAG_RX_OVERRIDE_IP = 0x04,
 	EFX_FILTER_FLAG_RX = 0x08,
 	EFX_FILTER_FLAG_TX = 0x10,
 };
@@ -88,8 +84,7 @@ enum efx_filter_flags {
  *
  * The @priority field is used by software to determine whether a new
  * filter may replace an old one.  The hardware priority of a filter
- * depends on the filter type and %EFX_FILTER_FLAG_RX_OVERRIDE_IP
- * flag.
+ * depends on the filter type.
  */
 struct efx_filter_spec {
 	u8	type:4;
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index fc5e7bbcbc9e..aea43cbd0520 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -320,14 +320,20 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
 		efx_mcdi_complete(mcdi);
 }
 
-/* Issue the given command by writing the data into the shared memory PDU,
- * ring the doorbell and wait for completion. Copyout the result. */
 int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
 		 const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen,
 		 size_t *outlen_actual)
 {
+	efx_mcdi_rpc_start(efx, cmd, inbuf, inlen);
+	return efx_mcdi_rpc_finish(efx, cmd, inlen,
+				   outbuf, outlen, outlen_actual);
+}
+
+void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, const u8 *inbuf,
+			size_t inlen)
+{
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	int rc;
+
 	BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
 
 	efx_mcdi_acquire(mcdi);
@@ -338,6 +344,15 @@ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
 	spin_unlock_bh(&mcdi->iface_lock);
 
 	efx_mcdi_copyin(efx, cmd, inbuf, inlen);
+}
+
+int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+			u8 *outbuf, size_t outlen, size_t *outlen_actual)
+{
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+	int rc;
+
+	BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
 
 	if (mcdi->mode == MCDI_MODE_POLL)
 		rc = efx_mcdi_poll(efx);
@@ -563,6 +578,11 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 	case MCDI_EVENT_CODE_FLR:
 		efx_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));
 		break;
+	case MCDI_EVENT_CODE_PTP_RX:
+	case MCDI_EVENT_CODE_PTP_FAULT:
+	case MCDI_EVENT_CODE_PTP_PPS:
+		efx_ptp_event(efx, event);
+		break;
 
 	default:
 		netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n",
@@ -641,9 +661,8 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 			   u16 *fw_subtype_list, u32 *capabilities)
 {
 	uint8_t outbuf[MC_CMD_GET_BOARD_CFG_OUT_LENMIN];
-	size_t outlen;
+	size_t outlen, offset, i;
 	int port_num = efx_port_num(efx);
-	int offset;
 	int rc;
 
 	BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0);
@@ -663,11 +682,18 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 		: MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST;
 	if (mac_address)
 		memcpy(mac_address, outbuf + offset, ETH_ALEN);
-	if (fw_subtype_list)
-		memcpy(fw_subtype_list,
-		       outbuf + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST,
-		       MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM *
-		       sizeof(fw_subtype_list[0]));
+	if (fw_subtype_list) {
+		/* Byte-swap and truncate or zero-pad as necessary */
+		offset = MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST;
+		for (i = 0;
+		     i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM;
+		     i++) {
+			fw_subtype_list[i] =
+				(offset + 2 <= outlen) ?
+				le16_to_cpup((__le16 *)(outbuf + offset)) : 0;
+			offset += 2;
+		}
+	}
 	if (capabilities) {
 		if (port_num)
 			*capabilities = MCDI_DWORD(outbuf,
@@ -1169,6 +1195,9 @@ int efx_mcdi_flush_rxqs(struct efx_nic *efx)
 	__le32 *qid;
 	int rc, count;
 
+	BUILD_BUG_ON(EFX_MAX_CHANNELS >
+		     MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
+
 	qid = kmalloc(EFX_MAX_CHANNELS * sizeof(*qid), GFP_KERNEL);
 	if (qid == NULL)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 0bdf3e331832..3ba2e5b5a9cc 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -71,6 +71,12 @@ extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf,
 			size_t inlen, u8 *outbuf, size_t outlen,
 			size_t *outlen_actual);
 
+extern void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd,
+			       const u8 *inbuf, size_t inlen);
+extern int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+			       u8 *outbuf, size_t outlen,
+			       size_t *outlen_actual);
+
 extern int efx_mcdi_poll_reboot(struct efx_nic *efx);
 extern void efx_mcdi_mode_poll(struct efx_nic *efx);
 extern void efx_mcdi_mode_event(struct efx_nic *efx);
@@ -107,11 +113,13 @@ extern void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
 #define MCDI_EVENT_FIELD(_ev, _field)			\
 	EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field)
 #define MCDI_ARRAY_FIELD(_buf, _field1, _type, _index, _field2)		\
-	EFX_DWORD_FIELD(						\
+	EFX_EXTRACT_DWORD(						\
 		*((efx_dword_t *)					\
 		  (MCDI_ARRAY_PTR(_buf, _field1, _type, _index) +	\
 		   (MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _OFST & ~3))), \
-		MC_CMD_ ## _type ## _TYPEDEF_ ## _field2)
+		MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _LBN & 0x1f, \
+		(MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _LBN & 0x1f) + \
+		MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _WIDTH - 1)
 
 extern void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len);
 extern int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index db4beed97669..9d426d0457bd 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -289,6 +289,7 @@
 #define          MCDI_EVENT_CODE_TX_FLUSH  0xc /* enum */
 #define          MCDI_EVENT_CODE_PTP_RX  0xd /* enum */
 #define          MCDI_EVENT_CODE_PTP_FAULT  0xe /* enum */
+#define          MCDI_EVENT_CODE_PTP_PPS  0xf /* enum */
 #define       MCDI_EVENT_CMDDONE_DATA_OFST 0
 #define       MCDI_EVENT_CMDDONE_DATA_LBN 0
 #define       MCDI_EVENT_CMDDONE_DATA_WIDTH 32
@@ -491,12 +492,12 @@
 
 /* MC_CMD_GET_FPGAREG_OUT msgresponse */
 #define    MC_CMD_GET_FPGAREG_OUT_LENMIN 1
-#define    MC_CMD_GET_FPGAREG_OUT_LENMAX 255
+#define    MC_CMD_GET_FPGAREG_OUT_LENMAX 252
 #define    MC_CMD_GET_FPGAREG_OUT_LEN(num) (0+1*(num))
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_OFST 0
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_LEN 1
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 255
+#define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 252
 
 
 /***********************************/
@@ -507,13 +508,13 @@
 
 /* MC_CMD_PUT_FPGAREG_IN msgrequest */
 #define    MC_CMD_PUT_FPGAREG_IN_LENMIN 5
-#define    MC_CMD_PUT_FPGAREG_IN_LENMAX 255
+#define    MC_CMD_PUT_FPGAREG_IN_LENMAX 252
 #define    MC_CMD_PUT_FPGAREG_IN_LEN(num) (4+1*(num))
 #define       MC_CMD_PUT_FPGAREG_IN_ADDR_OFST 0
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_OFST 4
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_LEN 1
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MINNUM 1
-#define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 251
+#define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 248
 
 /* MC_CMD_PUT_FPGAREG_OUT msgresponse */
 #define    MC_CMD_PUT_FPGAREG_OUT_LEN 0
@@ -560,7 +561,7 @@
 
 /* MC_CMD_PTP_IN_TRANSMIT msgrequest */
 #define    MC_CMD_PTP_IN_TRANSMIT_LENMIN 13
-#define    MC_CMD_PTP_IN_TRANSMIT_LENMAX 255
+#define    MC_CMD_PTP_IN_TRANSMIT_LENMAX 252
 #define    MC_CMD_PTP_IN_TRANSMIT_LEN(num) (12+1*(num))
 /*            MC_CMD_PTP_IN_CMD_OFST 0 */
 /*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
@@ -568,7 +569,7 @@
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST 12
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_LEN 1
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MINNUM 1
-#define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 243
+#define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 240
 
 /* MC_CMD_PTP_IN_READ_NIC_TIME msgrequest */
 #define    MC_CMD_PTP_IN_READ_NIC_TIME_LEN 8
@@ -1145,7 +1146,7 @@
 
 /* MC_CMD_PUTS_IN msgrequest */
 #define    MC_CMD_PUTS_IN_LENMIN 13
-#define    MC_CMD_PUTS_IN_LENMAX 255
+#define    MC_CMD_PUTS_IN_LENMAX 252
 #define    MC_CMD_PUTS_IN_LEN(num) (12+1*(num))
 #define       MC_CMD_PUTS_IN_DEST_OFST 0
 #define        MC_CMD_PUTS_IN_UART_LBN 0
@@ -1157,7 +1158,7 @@
 #define       MC_CMD_PUTS_IN_STRING_OFST 12
 #define       MC_CMD_PUTS_IN_STRING_LEN 1
 #define       MC_CMD_PUTS_IN_STRING_MINNUM 1
-#define       MC_CMD_PUTS_IN_STRING_MAXNUM 243
+#define       MC_CMD_PUTS_IN_STRING_MAXNUM 240
 
 /* MC_CMD_PUTS_OUT msgresponse */
 #define    MC_CMD_PUTS_OUT_LEN 0
@@ -1947,12 +1948,12 @@
 
 /* MC_CMD_NVRAM_READ_OUT msgresponse */
 #define    MC_CMD_NVRAM_READ_OUT_LENMIN 1
-#define    MC_CMD_NVRAM_READ_OUT_LENMAX 255
+#define    MC_CMD_NVRAM_READ_OUT_LENMAX 252
 #define    MC_CMD_NVRAM_READ_OUT_LEN(num) (0+1*(num))
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_LEN 1
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 255
+#define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 252
 
 
 /***********************************/
@@ -1963,7 +1964,7 @@
 
 /* MC_CMD_NVRAM_WRITE_IN msgrequest */
 #define    MC_CMD_NVRAM_WRITE_IN_LENMIN 13
-#define    MC_CMD_NVRAM_WRITE_IN_LENMAX 255
+#define    MC_CMD_NVRAM_WRITE_IN_LENMAX 252
 #define    MC_CMD_NVRAM_WRITE_IN_LEN(num) (12+1*(num))
 #define       MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0
 /*            Enum values, see field(s): */
@@ -1973,7 +1974,7 @@
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN 1
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 243
+#define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 240
 
 /* MC_CMD_NVRAM_WRITE_OUT msgresponse */
 #define    MC_CMD_NVRAM_WRITE_OUT_LEN 0
@@ -2305,13 +2306,13 @@
 
 /* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5
-#define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 255
+#define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LEN(num) (4+1*(num))
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATALEN_OFST 0
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST 4
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_LEN 1
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MINNUM 1
-#define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 251
+#define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 248
 
 
 /***********************************/
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index 758148379b0e..08f825b71ac8 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -585,6 +585,7 @@ static const struct siena_nvram_type_info siena_nvram_types[] = {
 	[MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1]	= { 1, "sfc_exp_rom_cfg" },
 	[MC_CMD_NVRAM_TYPE_PHY_PORT0]		= { 0, "sfc_phy_fw" },
 	[MC_CMD_NVRAM_TYPE_PHY_PORT1]		= { 1, "sfc_phy_fw" },
+	[MC_CMD_NVRAM_TYPE_FPGA]		= { 0, "sfc_fpga" },
 };
 
 static int siena_mtd_probe_partition(struct efx_nic *efx,
@@ -598,7 +599,8 @@ static int siena_mtd_probe_partition(struct efx_nic *efx,
 	bool protected;
 	int rc;
 
-	if (type >= ARRAY_SIZE(siena_nvram_types))
+	if (type >= ARRAY_SIZE(siena_nvram_types) ||
+	    siena_nvram_types[type].name == NULL)
 		return -ENODEV;
 
 	info = &siena_nvram_types[type];
@@ -627,7 +629,8 @@ static int siena_mtd_get_fw_subtypes(struct efx_nic *efx,
 				     struct efx_mtd *efx_mtd)
 {
 	struct efx_mtd_partition *part;
-	uint16_t fw_subtype_list[MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM];
+	uint16_t fw_subtype_list[
+		MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM];
 	int rc;
 
 	rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list, NULL);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index cd9c0a989692..c1a010cda89b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -37,7 +37,7 @@
  *
  **************************************************************************/
 
-#define EFX_DRIVER_VERSION	"3.1"
+#define EFX_DRIVER_VERSION	"3.2"
 
 #ifdef DEBUG
 #define EFX_BUG_ON_PARANOID(x) BUG_ON(x)
@@ -56,7 +56,8 @@
 #define EFX_MAX_CHANNELS 32U
 #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
 #define EFX_EXTRA_CHANNEL_IOV	0
-#define EFX_MAX_EXTRA_CHANNELS	1U
+#define EFX_EXTRA_CHANNEL_PTP	1
+#define EFX_MAX_EXTRA_CHANNELS	2U
 
 /* Checksum generation is a per-queue option in hardware, so each
  * queue visible to the networking core is backed by two hardware TX
@@ -68,6 +69,9 @@
 #define EFX_TXQ_TYPES		4
 #define EFX_MAX_TX_QUEUES	(EFX_TXQ_TYPES * EFX_MAX_CHANNELS)
 
+/* Forward declare Precision Time Protocol (PTP) support structure. */
+struct efx_ptp_data;
+
 struct efx_self_tests;
 
 /**
@@ -91,29 +95,31 @@ struct efx_special_buffer {
 };
 
 /**
- * struct efx_tx_buffer - An Efx TX buffer
- * @skb: The associated socket buffer.
- *	Set only on the final fragment of a packet; %NULL for all other
- *	fragments.  When this fragment completes, then we can free this
- *	skb.
- * @tsoh: The associated TSO header structure, or %NULL if this
- *	buffer is not a TSO header.
+ * struct efx_tx_buffer - buffer state for a TX descriptor
+ * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be
+ *	freed when descriptor completes
+ * @heap_buf: When @flags & %EFX_TX_BUF_HEAP, the associated heap buffer to be
+ *	freed when descriptor completes.
  * @dma_addr: DMA address of the fragment.
+ * @flags: Flags for allocation and DMA mapping type
  * @len: Length of this fragment.
  *	This field is zero when the queue slot is empty.
- * @continuation: True if this fragment is not the end of a packet.
- * @unmap_single: True if dma_unmap_single should be used.
  * @unmap_len: Length of this fragment to unmap
  */
 struct efx_tx_buffer {
-	const struct sk_buff *skb;
-	struct efx_tso_header *tsoh;
+	union {
+		const struct sk_buff *skb;
+		void *heap_buf;
+	};
 	dma_addr_t dma_addr;
+	unsigned short flags;
 	unsigned short len;
-	bool continuation;
-	bool unmap_single;
 	unsigned short unmap_len;
 };
+#define EFX_TX_BUF_CONT		1	/* not last descriptor of packet */
+#define EFX_TX_BUF_SKB		2	/* buffer is last part of skb */
+#define EFX_TX_BUF_HEAP		4	/* buffer was allocated with kmalloc() */
+#define EFX_TX_BUF_MAP_SINGLE	8	/* buffer was mapped with dma_map_single() */
 
 /**
  * struct efx_tx_queue - An Efx TX queue
@@ -133,6 +139,7 @@ struct efx_tx_buffer {
  * @channel: The associated channel
  * @core_txq: The networking core TX queue structure
  * @buffer: The software buffer ring
+ * @tsoh_page: Array of pages of TSO header buffers
  * @txd: The hardware descriptor ring
  * @ptr_mask: The size of the ring minus 1.
  * @initialised: Has hardware queue been initialised?
@@ -156,9 +163,6 @@ struct efx_tx_buffer {
  *	variable indicates that the queue is full.  This is to
  *	avoid cache-line ping-pong between the xmit path and the
  *	completion path.
- * @tso_headers_free: A list of TSO headers allocated for this TX queue
- *	that are not in use, and so available for new TSO sends. The list
- *	is protected by the TX queue lock.
  * @tso_bursts: Number of times TSO xmit invoked by kernel
  * @tso_long_headers: Number of packets with headers too long for standard
  *	blocks
@@ -175,6 +179,7 @@ struct efx_tx_queue {
 	struct efx_channel *channel;
 	struct netdev_queue *core_txq;
 	struct efx_tx_buffer *buffer;
+	struct efx_buffer *tsoh_page;
 	struct efx_special_buffer txd;
 	unsigned int ptr_mask;
 	bool initialised;
@@ -187,7 +192,6 @@ struct efx_tx_queue {
 	unsigned int insert_count ____cacheline_aligned_in_smp;
 	unsigned int write_count;
 	unsigned int old_read_count;
-	struct efx_tso_header *tso_headers_free;
 	unsigned int tso_bursts;
 	unsigned int tso_long_headers;
 	unsigned int tso_packets;
@@ -242,6 +246,8 @@ struct efx_rx_page_state {
 /**
  * struct efx_rx_queue - An Efx RX queue
  * @efx: The associated Efx NIC
+ * @core_index:  Index of network core RX queue.  Will be >= 0 iff this
+ *	is associated with a real RX queue.
  * @buffer: The software buffer ring
  * @rxd: The hardware descriptor ring
  * @ptr_mask: The size of the ring minus 1.
@@ -263,6 +269,7 @@ struct efx_rx_page_state {
  */
 struct efx_rx_queue {
 	struct efx_nic *efx;
+	int core_index;
 	struct efx_rx_buffer *buffer;
 	struct efx_special_buffer rxd;
 	unsigned int ptr_mask;
@@ -390,14 +397,17 @@ struct efx_channel {
  * @get_name: Generate the channel's name (used for its IRQ handler)
  * @copy: Copy the channel state prior to reallocation.  May be %NULL if
  *	reallocation is not supported.
+ * @receive_skb: Handle an skb ready to be passed to netif_receive_skb()
  * @keep_eventq: Flag for whether event queue should be kept initialised
  *	while the device is stopped
  */
 struct efx_channel_type {
 	void (*handle_no_channel)(struct efx_nic *);
 	int (*pre_probe)(struct efx_channel *);
+	void (*post_remove)(struct efx_channel *);
 	void (*get_name)(struct efx_channel *, char *buf, size_t len);
 	struct efx_channel *(*copy)(const struct efx_channel *);
+	void (*receive_skb)(struct efx_channel *, struct sk_buff *);
 	bool keep_eventq;
 };
 
@@ -430,11 +440,9 @@ enum efx_int_mode {
 #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI)
 
 enum nic_state {
-	STATE_INIT = 0,
-	STATE_RUNNING = 1,
-	STATE_FINI = 2,
-	STATE_DISABLED = 3,
-	STATE_MAX,
+	STATE_UNINIT = 0,	/* device being probed/removed or is frozen */
+	STATE_READY = 1,	/* hardware ready and netdev registered */
+	STATE_DISABLED = 2,	/* device disabled due to hardware errors */
 };
 
 /*
@@ -654,7 +662,7 @@ struct vfdi_status;
  * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues
  * @irq_rx_moderation: IRQ moderation time for RX event queues
  * @msg_enable: Log message enable flags
- * @state: Device state flag. Serialised by the rtnl_lock.
+ * @state: Device state number (%STATE_*). Serialised by the rtnl_lock.
  * @reset_pending: Bitmask for pending resets
  * @tx_queue: TX DMA queues
  * @rx_queue: RX DMA queues
@@ -664,6 +672,8 @@ struct vfdi_status;
  *	should be allocated for this NIC
  * @rxq_entries: Size of receive queues requested by user.
  * @txq_entries: Size of transmit queues requested by user.
+ * @txq_stop_thresh: TX queue fill level at or above which we stop it.
+ * @txq_wake_thresh: TX queue fill level at or below which we wake it.
  * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches
  * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches
  * @sram_lim_qw: Qword address limit of SRAM
@@ -730,6 +740,7 @@ struct vfdi_status;
  *	%local_addr_list. Protected by %local_lock.
  * @local_lock: Mutex protecting %local_addr_list and %local_page_list.
  * @peer_work: Work item to broadcast peer addresses to VMs.
+ * @ptp_data: PTP state data
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -774,6 +785,9 @@ struct efx_nic {
 
 	unsigned rxq_entries;
 	unsigned txq_entries;
+	unsigned int txq_stop_thresh;
+	unsigned int txq_wake_thresh;
+
 	unsigned tx_dc_base;
 	unsigned rx_dc_base;
 	unsigned sram_lim_qw;
@@ -854,6 +868,10 @@ struct efx_nic {
 	struct work_struct peer_work;
 #endif
 
+#ifdef CONFIG_SFC_PTP
+	struct efx_ptp_data *ptp_data;
+#endif
+
 	/* The following fields may be written more often */
 
 	struct delayed_work monitor_work ____cacheline_aligned_in_smp;
@@ -1044,7 +1062,7 @@ static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue)
 
 static inline bool efx_channel_has_rx_queue(struct efx_channel *channel)
 {
-	return channel->channel < channel->efx->n_rx_channels;
+	return channel->rx_queue.core_index >= 0;
 }
 
 static inline struct efx_rx_queue *
@@ -1116,5 +1134,13 @@ static inline void clear_bit_le(unsigned nr, unsigned char *addr)
 #define EFX_MAX_FRAME_LEN(mtu) \
 	((((mtu) + ETH_HLEN + VLAN_HLEN + 4/* FCS */ + 7) & ~7) + 16)
 
+static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP;
+}
+static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb)
+{
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
 
 #endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 326d799762d6..cdff40b65729 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -298,7 +298,7 @@ efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
 /**************************************************************************
  *
  * Generic buffer handling
- * These buffers are used for interrupt status and MAC stats
+ * These buffers are used for interrupt status, MAC stats, etc.
  *
  **************************************************************************/
 
@@ -401,8 +401,10 @@ void efx_nic_push_buffers(struct efx_tx_queue *tx_queue)
 		++tx_queue->write_count;
 
 		/* Create TX descriptor ring entry */
+		BUILD_BUG_ON(EFX_TX_BUF_CONT != 1);
 		EFX_POPULATE_QWORD_4(*txd,
-				     FSF_AZ_TX_KER_CONT, buffer->continuation,
+				     FSF_AZ_TX_KER_CONT,
+				     buffer->flags & EFX_TX_BUF_CONT,
 				     FSF_AZ_TX_KER_BYTE_COUNT, buffer->len,
 				     FSF_AZ_TX_KER_BUF_REGION, 0,
 				     FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr);
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index bab5cd9f5740..438cef11f727 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -11,6 +11,7 @@
 #ifndef EFX_NIC_H
 #define EFX_NIC_H
 
+#include <linux/net_tstamp.h>
 #include <linux/i2c-algo-bit.h>
 #include "net_driver.h"
 #include "efx.h"
@@ -250,6 +251,41 @@ extern int efx_sriov_get_vf_config(struct net_device *dev, int vf,
 extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
 				     bool spoofchk);
 
+struct ethtool_ts_info;
+#ifdef CONFIG_SFC_PTP
+extern void efx_ptp_probe(struct efx_nic *efx);
+extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd);
+extern int efx_ptp_get_ts_info(struct net_device *net_dev,
+			       struct ethtool_ts_info *ts_info);
+extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
+#else
+static inline void efx_ptp_probe(struct efx_nic *efx) {}
+static inline int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
+{
+	return -EOPNOTSUPP;
+}
+static inline int efx_ptp_get_ts_info(struct net_device *net_dev,
+				      struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = (SOF_TIMESTAMPING_SOFTWARE |
+				    SOF_TIMESTAMPING_RX_SOFTWARE);
+	ts_info->phc_index = -1;
+
+	return 0;
+}
+static inline bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	return false;
+}
+static inline int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	return NETDEV_TX_OK;
+}
+static inline void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) {}
+#endif
+
 extern const struct efx_nic_type falcon_a1_nic_type;
 extern const struct efx_nic_type falcon_b0_nic_type;
 extern const struct efx_nic_type siena_a0_nic_type;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
new file mode 100644
index 000000000000..5b3dd028ce85
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -0,0 +1,1484 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2011 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+/* Theory of operation:
+ *
+ * PTP support is assisted by firmware running on the MC, which provides
+ * the hardware timestamping capabilities.  Both transmitted and received
+ * PTP event packets are queued onto internal queues for subsequent processing;
+ * this is because the MC operations are relatively long and would block
+ * block NAPI/interrupt operation.
+ *
+ * Receive event processing:
+ *	The event contains the packet's UUID and sequence number, together
+ *	with the hardware timestamp.  The PTP receive packet queue is searched
+ *	for this UUID/sequence number and, if found, put on a pending queue.
+ *	Packets not matching are delivered without timestamps (MCDI events will
+ *	always arrive after the actual packet).
+ *	It is important for the operation of the PTP protocol that the ordering
+ *	of packets between the event and general port is maintained.
+ *
+ * Work queue processing:
+ *	If work waiting, synchronise host/hardware time
+ *
+ *	Transmit: send packet through MC, which returns the transmission time
+ *	that is converted to an appropriate timestamp.
+ *
+ *	Receive: the packet's reception time is converted to an appropriate
+ *	timestamp.
+ */
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/pps_kernel.h>
+#include <linux/ptp_clock_kernel.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+#include "io.h"
+#include "regs.h"
+#include "nic.h"
+
+/* Maximum number of events expected to make up a PTP event */
+#define	MAX_EVENT_FRAGS			3
+
+/* Maximum delay, ms, to begin synchronisation */
+#define	MAX_SYNCHRONISE_WAIT_MS		2
+
+/* How long, at most, to spend synchronising */
+#define	SYNCHRONISE_PERIOD_NS		250000
+
+/* How often to update the shared memory time */
+#define	SYNCHRONISATION_GRANULARITY_NS	200
+
+/* Minimum permitted length of a (corrected) synchronisation time */
+#define	MIN_SYNCHRONISATION_NS		120
+
+/* Maximum permitted length of a (corrected) synchronisation time */
+#define	MAX_SYNCHRONISATION_NS		1000
+
+/* How many (MC) receive events that can be queued */
+#define	MAX_RECEIVE_EVENTS		8
+
+/* Length of (modified) moving average. */
+#define	AVERAGE_LENGTH			16
+
+/* How long an unmatched event or packet can be held */
+#define PKT_EVENT_LIFETIME_MS		10
+
+/* Offsets into PTP packet for identification.  These offsets are from the
+ * start of the IP header, not the MAC header.  Note that neither PTP V1 nor
+ * PTP V2 permit the use of IPV4 options.
+ */
+#define PTP_DPORT_OFFSET	22
+
+#define PTP_V1_VERSION_LENGTH	2
+#define PTP_V1_VERSION_OFFSET	28
+
+#define PTP_V1_UUID_LENGTH	6
+#define PTP_V1_UUID_OFFSET	50
+
+#define PTP_V1_SEQUENCE_LENGTH	2
+#define PTP_V1_SEQUENCE_OFFSET	58
+
+/* The minimum length of a PTP V1 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define	PTP_V1_MIN_LENGTH	64
+
+#define PTP_V2_VERSION_LENGTH	1
+#define PTP_V2_VERSION_OFFSET	29
+
+/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2),
+ * the MC only captures the last six bytes of the clock identity. These values
+ * reflect those, not the ones used in the standard.  The standard permits
+ * mapping of V1 UUIDs to V2 UUIDs with these same values.
+ */
+#define PTP_V2_MC_UUID_LENGTH	6
+#define PTP_V2_MC_UUID_OFFSET	50
+
+#define PTP_V2_SEQUENCE_LENGTH	2
+#define PTP_V2_SEQUENCE_OFFSET	58
+
+/* The minimum length of a PTP V2 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define	PTP_V2_MIN_LENGTH	63
+
+#define	PTP_MIN_LENGTH		63
+
+#define PTP_ADDRESS		0xe0000181	/* 224.0.1.129 */
+#define PTP_EVENT_PORT		319
+#define PTP_GENERAL_PORT	320
+
+/* Annoyingly the format of the version numbers are different between
+ * versions 1 and 2 so it isn't possible to simply look for 1 or 2.
+ */
+#define	PTP_VERSION_V1		1
+
+#define	PTP_VERSION_V2		2
+#define	PTP_VERSION_V2_MASK	0x0f
+
+enum ptp_packet_state {
+	PTP_PACKET_STATE_UNMATCHED = 0,
+	PTP_PACKET_STATE_MATCHED,
+	PTP_PACKET_STATE_TIMED_OUT,
+	PTP_PACKET_STATE_MATCH_UNWANTED
+};
+
+/* NIC synchronised with single word of time only comprising
+ * partial seconds and full nanoseconds: 10^9 ~ 2^30 so 2 bits for seconds.
+ */
+#define	MC_NANOSECOND_BITS	30
+#define	MC_NANOSECOND_MASK	((1 << MC_NANOSECOND_BITS) - 1)
+#define	MC_SECOND_MASK		((1 << (32 - MC_NANOSECOND_BITS)) - 1)
+
+/* Maximum parts-per-billion adjustment that is acceptable */
+#define MAX_PPB			1000000
+
+/* Number of bits required to hold the above */
+#define	MAX_PPB_BITS		20
+
+/* Number of extra bits allowed when calculating fractional ns.
+ * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should
+ * be less than 63.
+ */
+#define	PPB_EXTRA_BITS		2
+
+/* Precalculate scale word to avoid long long division at runtime */
+#define	PPB_SCALE_WORD	((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\
+			MAX_PPB_BITS)) / 1000000000LL)
+
+#define PTP_SYNC_ATTEMPTS	4
+
+/**
+ * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area.
+ * @words: UUID and (partial) sequence number
+ * @expiry: Time after which the packet should be delivered irrespective of
+ *            event arrival.
+ * @state: The state of the packet - whether it is ready for processing or
+ *         whether that is of no interest.
+ */
+struct efx_ptp_match {
+	u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)];
+	unsigned long expiry;
+	enum ptp_packet_state state;
+};
+
+/**
+ * struct efx_ptp_event_rx - A PTP receive event (from MC)
+ * @seq0: First part of (PTP) UUID
+ * @seq1: Second part of (PTP) UUID and sequence number
+ * @hwtimestamp: Event timestamp
+ */
+struct efx_ptp_event_rx {
+	struct list_head link;
+	u32 seq0;
+	u32 seq1;
+	ktime_t hwtimestamp;
+	unsigned long expiry;
+};
+
+/**
+ * struct efx_ptp_timeset - Synchronisation between host and MC
+ * @host_start: Host time immediately before hardware timestamp taken
+ * @seconds: Hardware timestamp, seconds
+ * @nanoseconds: Hardware timestamp, nanoseconds
+ * @host_end: Host time immediately after hardware timestamp taken
+ * @waitns: Number of nanoseconds between hardware timestamp being read and
+ *          host end time being seen
+ * @window: Difference of host_end and host_start
+ * @valid: Whether this timeset is valid
+ */
+struct efx_ptp_timeset {
+	u32 host_start;
+	u32 seconds;
+	u32 nanoseconds;
+	u32 host_end;
+	u32 waitns;
+	u32 window;	/* Derived: end - start, allowing for wrap */
+};
+
+/**
+ * struct efx_ptp_data - Precision Time Protocol (PTP) state
+ * @channel: The PTP channel
+ * @rxq: Receive queue (awaiting timestamps)
+ * @txq: Transmit queue
+ * @evt_list: List of MC receive events awaiting packets
+ * @evt_free_list: List of free events
+ * @evt_lock: Lock for manipulating evt_list and evt_free_list
+ * @rx_evts: Instantiated events (on evt_list and evt_free_list)
+ * @workwq: Work queue for processing pending PTP operations
+ * @work: Work task
+ * @reset_required: A serious error has occurred and the PTP task needs to be
+ *                  reset (disable, enable).
+ * @rxfilter_event: Receive filter when operating
+ * @rxfilter_general: Receive filter when operating
+ * @config: Current timestamp configuration
+ * @enabled: PTP operation enabled
+ * @mode: Mode in which PTP operating (PTP version)
+ * @evt_frags: Partly assembled PTP events
+ * @evt_frag_idx: Current fragment number
+ * @evt_code: Last event code
+ * @start: Address at which MC indicates ready for synchronisation
+ * @host_time_pps: Host time at last PPS
+ * @last_sync_ns: Last number of nanoseconds between readings when synchronising
+ * @base_sync_ns: Number of nanoseconds for last synchronisation.
+ * @base_sync_valid: Whether base_sync_time is valid.
+ * @current_adjfreq: Current ppb adjustment.
+ * @phc_clock: Pointer to registered phc device
+ * @phc_clock_info: Registration structure for phc device
+ * @pps_work: pps work task for handling pps events
+ * @pps_workwq: pps work queue
+ * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled
+ * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids
+ *         allocations in main data path).
+ * @debug_ptp_dir: PTP debugfs directory
+ * @missed_rx_sync: Number of packets received without syncrhonisation.
+ * @good_syncs: Number of successful synchronisations.
+ * @no_time_syncs: Number of synchronisations with no good times.
+ * @bad_sync_durations: Number of synchronisations with bad durations.
+ * @bad_syncs: Number of failed synchronisations.
+ * @last_sync_time: Number of nanoseconds for last synchronisation.
+ * @sync_timeouts: Number of synchronisation timeouts
+ * @fast_syncs: Number of synchronisations requiring short delay
+ * @min_sync_delta: Minimum time between event and synchronisation
+ * @max_sync_delta: Maximum time between event and synchronisation
+ * @average_sync_delta: Average time between event and synchronisation.
+ *                      Modified moving average.
+ * @last_sync_delta: Last time between event and synchronisation
+ * @mc_stats: Context value for MC statistics
+ * @timeset: Last set of synchronisation statistics.
+ */
+struct efx_ptp_data {
+	struct efx_channel *channel;
+	struct sk_buff_head rxq;
+	struct sk_buff_head txq;
+	struct list_head evt_list;
+	struct list_head evt_free_list;
+	spinlock_t evt_lock;
+	struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
+	struct workqueue_struct *workwq;
+	struct work_struct work;
+	bool reset_required;
+	u32 rxfilter_event;
+	u32 rxfilter_general;
+	bool rxfilter_installed;
+	struct hwtstamp_config config;
+	bool enabled;
+	unsigned int mode;
+	efx_qword_t evt_frags[MAX_EVENT_FRAGS];
+	int evt_frag_idx;
+	int evt_code;
+	struct efx_buffer start;
+	struct pps_event_time host_time_pps;
+	unsigned last_sync_ns;
+	unsigned base_sync_ns;
+	bool base_sync_valid;
+	s64 current_adjfreq;
+	struct ptp_clock *phc_clock;
+	struct ptp_clock_info phc_clock_info;
+	struct work_struct pps_work;
+	struct workqueue_struct *pps_workwq;
+	bool nic_ts_enabled;
+	u8 txbuf[ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN(
+			       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM), 4)];
+	struct efx_ptp_timeset
+	timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM];
+};
+
+static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta);
+static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta);
+static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts);
+static int efx_phc_settime(struct ptp_clock_info *ptp,
+			   const struct timespec *e_ts);
+static int efx_phc_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *request, int on);
+
+/* Enable MCDI PTP support. */
+static int efx_ptp_enable(struct efx_nic *efx)
+{
+	u8 inbuf[MC_CMD_PTP_IN_ENABLE_LEN];
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE,
+		       efx->ptp_data->channel->channel);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode);
+
+	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+/* Disable MCDI PTP support.
+ *
+ * Note that this function should never rely on the presence of ptp_data -
+ * may be called before that exists.
+ */
+static int efx_ptp_disable(struct efx_nic *efx)
+{
+	u8 inbuf[MC_CMD_PTP_IN_DISABLE_LEN];
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE);
+	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(q))) {
+		local_bh_disable();
+		netif_receive_skb(skb);
+		local_bh_enable();
+	}
+}
+
+static void efx_ptp_handle_no_channel(struct efx_nic *efx)
+{
+	netif_err(efx, drv, efx->net_dev,
+		  "ERROR: PTP requires MSI-X and 1 additional interrupt"
+		  "vector. PTP disabled\n");
+}
+
+/* Repeatedly send the host time to the MC which will capture the hardware
+ * time.
+ */
+static void efx_ptp_send_times(struct efx_nic *efx,
+			       struct pps_event_time *last_time)
+{
+	struct pps_event_time now;
+	struct timespec limit;
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct timespec start;
+	int *mc_running = ptp->start.addr;
+
+	pps_get_ts(&now);
+	start = now.ts_real;
+	limit = now.ts_real;
+	timespec_add_ns(&limit, SYNCHRONISE_PERIOD_NS);
+
+	/* Write host time for specified period or until MC is done */
+	while ((timespec_compare(&now.ts_real, &limit) < 0) &&
+	       ACCESS_ONCE(*mc_running)) {
+		struct timespec update_time;
+		unsigned int host_time;
+
+		/* Don't update continuously to avoid saturating the PCIe bus */
+		update_time = now.ts_real;
+		timespec_add_ns(&update_time, SYNCHRONISATION_GRANULARITY_NS);
+		do {
+			pps_get_ts(&now);
+		} while ((timespec_compare(&now.ts_real, &update_time) < 0) &&
+			 ACCESS_ONCE(*mc_running));
+
+		/* Synchronise NIC with single word of time only */
+		host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS |
+			     now.ts_real.tv_nsec);
+		/* Update host time in NIC memory */
+		_efx_writed(efx, cpu_to_le32(host_time),
+			    FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST);
+	}
+	*last_time = now;
+}
+
+/* Read a timeset from the MC's results and partial process. */
+static void efx_ptp_read_timeset(u8 *data, struct efx_ptp_timeset *timeset)
+{
+	unsigned start_ns, end_ns;
+
+	timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
+	timeset->seconds = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_SECONDS);
+	timeset->nanoseconds = MCDI_DWORD(data,
+					 PTP_OUT_SYNCHRONIZE_NANOSECONDS);
+	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
+	timeset->waitns = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);
+
+	/* Ignore seconds */
+	start_ns = timeset->host_start & MC_NANOSECOND_MASK;
+	end_ns = timeset->host_end & MC_NANOSECOND_MASK;
+	/* Allow for rollover */
+	if (end_ns < start_ns)
+		end_ns += NSEC_PER_SEC;
+	/* Determine duration of operation */
+	timeset->window = end_ns - start_ns;
+}
+
+/* Process times received from MC.
+ *
+ * Extract times from returned results, and establish the minimum value
+ * seen.  The minimum value represents the "best" possible time and events
+ * too much greater than this are rejected - the machine is, perhaps, too
+ * busy. A number of readings are taken so that, hopefully, at least one good
+ * synchronisation will be seen in the results.
+ */
+static int efx_ptp_process_times(struct efx_nic *efx, u8 *synch_buf,
+				 size_t response_length,
+				 const struct pps_event_time *last_time)
+{
+	unsigned number_readings = (response_length /
+			       MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN);
+	unsigned i;
+	unsigned min;
+	unsigned min_set = 0;
+	unsigned total;
+	unsigned ngood = 0;
+	unsigned last_good = 0;
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool min_valid = false;
+	u32 last_sec;
+	u32 start_sec;
+	struct timespec delta;
+
+	if (number_readings == 0)
+		return -EAGAIN;
+
+	/* Find minimum value in this set of results, discarding clearly
+	 * erroneous results.
+	 */
+	for (i = 0; i < number_readings; i++) {
+		efx_ptp_read_timeset(synch_buf, &ptp->timeset[i]);
+		synch_buf += MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN;
+		if (ptp->timeset[i].window > SYNCHRONISATION_GRANULARITY_NS) {
+			if (min_valid) {
+				if (ptp->timeset[i].window < min_set)
+					min_set = ptp->timeset[i].window;
+			} else {
+				min_valid = true;
+				min_set = ptp->timeset[i].window;
+			}
+		}
+	}
+
+	if (min_valid) {
+		if (ptp->base_sync_valid && (min_set > ptp->base_sync_ns))
+			min = ptp->base_sync_ns;
+		else
+			min = min_set;
+	} else {
+		min = SYNCHRONISATION_GRANULARITY_NS;
+	}
+
+	/* Discard excessively long synchronise durations.  The MC times
+	 * when it finishes reading the host time so the corrected window
+	 * time should be fairly constant for a given platform.
+	 */
+	total = 0;
+	for (i = 0; i < number_readings; i++)
+		if (ptp->timeset[i].window > ptp->timeset[i].waitns) {
+			unsigned win;
+
+			win = ptp->timeset[i].window - ptp->timeset[i].waitns;
+			if (win >= MIN_SYNCHRONISATION_NS &&
+			    win < MAX_SYNCHRONISATION_NS) {
+				total += ptp->timeset[i].window;
+				ngood++;
+				last_good = i;
+			}
+		}
+
+	if (ngood == 0) {
+		netif_warn(efx, drv, efx->net_dev,
+			   "PTP no suitable synchronisations %dns %dns\n",
+			   ptp->base_sync_ns, min_set);
+		return -EAGAIN;
+	}
+
+	/* Average minimum this synchronisation */
+	ptp->last_sync_ns = DIV_ROUND_UP(total, ngood);
+	if (!ptp->base_sync_valid || (ptp->last_sync_ns < ptp->base_sync_ns)) {
+		ptp->base_sync_valid = true;
+		ptp->base_sync_ns = ptp->last_sync_ns;
+	}
+
+	/* Calculate delay from actual PPS to last_time */
+	delta.tv_nsec =
+		ptp->timeset[last_good].nanoseconds +
+		last_time->ts_real.tv_nsec -
+		(ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);
+
+	/* It is possible that the seconds rolled over between taking
+	 * the start reading and the last value written by the host.  The
+	 * timescales are such that a gap of more than one second is never
+	 * expected.
+	 */
+	start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
+	last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
+	if (start_sec != last_sec) {
+		if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
+			netif_warn(efx, hw, efx->net_dev,
+				   "PTP bad synchronisation seconds\n");
+			return -EAGAIN;
+		} else {
+			delta.tv_sec = 1;
+		}
+	} else {
+		delta.tv_sec = 0;
+	}
+
+	ptp->host_time_pps = *last_time;
+	pps_sub_ts(&ptp->host_time_pps, delta);
+
+	return 0;
+}
+
+/* Synchronize times between the host and the MC */
+static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	u8 synch_buf[MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX];
+	size_t response_length;
+	int rc;
+	unsigned long timeout;
+	struct pps_event_time last_time = {};
+	unsigned int loops = 0;
+	int *start = ptp->start.addr;
+
+	MCDI_SET_DWORD(synch_buf, PTP_IN_OP, MC_CMD_PTP_OP_SYNCHRONIZE);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_NUMTIMESETS,
+		       num_readings);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_LO,
+		       (u32)ptp->start.dma_addr);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_HI,
+		       (u32)((u64)ptp->start.dma_addr >> 32));
+
+	/* Clear flag that signals MC ready */
+	ACCESS_ONCE(*start) = 0;
+	efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf,
+			   MC_CMD_PTP_IN_SYNCHRONIZE_LEN);
+
+	/* Wait for start from MCDI (or timeout) */
+	timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS);
+	while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) {
+		udelay(20);	/* Usually start MCDI execution quickly */
+		loops++;
+	}
+
+	if (ACCESS_ONCE(*start))
+		efx_ptp_send_times(efx, &last_time);
+
+	/* Collect results */
+	rc = efx_mcdi_rpc_finish(efx, MC_CMD_PTP,
+				 MC_CMD_PTP_IN_SYNCHRONIZE_LEN,
+				 synch_buf, sizeof(synch_buf),
+				 &response_length);
+	if (rc == 0)
+		rc = efx_ptp_process_times(efx, synch_buf, response_length,
+					   &last_time);
+
+	return rc;
+}
+
+/* Transmit a PTP packet, via the MCDI interface, to the wire. */
+static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb)
+{
+	u8 *txbuf = efx->ptp_data->txbuf;
+	struct skb_shared_hwtstamps timestamps;
+	int rc = -EIO;
+	/* MCDI driver requires word aligned lengths */
+	size_t len = ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN(skb->len), 4);
+	u8 txtime[MC_CMD_PTP_OUT_TRANSMIT_LEN];
+
+	MCDI_SET_DWORD(txbuf, PTP_IN_OP, MC_CMD_PTP_OP_TRANSMIT);
+	MCDI_SET_DWORD(txbuf, PTP_IN_TRANSMIT_LENGTH, skb->len);
+	if (skb_shinfo(skb)->nr_frags != 0) {
+		rc = skb_linearize(skb);
+		if (rc != 0)
+			goto fail;
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		rc = skb_checksum_help(skb);
+		if (rc != 0)
+			goto fail;
+	}
+	skb_copy_from_linear_data(skb,
+				  &txbuf[MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST],
+				  len);
+	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, txbuf, len, txtime,
+			  sizeof(txtime), &len);
+	if (rc != 0)
+		goto fail;
+
+	memset(&timestamps, 0, sizeof(timestamps));
+	timestamps.hwtstamp = ktime_set(
+		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_SECONDS),
+		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_NANOSECONDS));
+
+	skb_tstamp_tx(skb, &timestamps);
+
+	rc = 0;
+
+fail:
+	dev_kfree_skb(skb);
+
+	return rc;
+}
+
+static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct list_head *cursor;
+	struct list_head *next;
+
+	/* Drop time-expired events */
+	spin_lock_bh(&ptp->evt_lock);
+	if (!list_empty(&ptp->evt_list)) {
+		list_for_each_safe(cursor, next, &ptp->evt_list) {
+			struct efx_ptp_event_rx *evt;
+
+			evt = list_entry(cursor, struct efx_ptp_event_rx,
+					 link);
+			if (time_after(jiffies, evt->expiry)) {
+				list_del(&evt->link);
+				list_add(&evt->link, &ptp->evt_free_list);
+				netif_warn(efx, hw, efx->net_dev,
+					   "PTP rx event dropped\n");
+			}
+		}
+	}
+	spin_unlock_bh(&ptp->evt_lock);
+}
+
+static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
+					      struct sk_buff *skb)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool evts_waiting;
+	struct list_head *cursor;
+	struct list_head *next;
+	struct efx_ptp_match *match;
+	enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED;
+
+	spin_lock_bh(&ptp->evt_lock);
+	evts_waiting = !list_empty(&ptp->evt_list);
+	spin_unlock_bh(&ptp->evt_lock);
+
+	if (!evts_waiting)
+		return PTP_PACKET_STATE_UNMATCHED;
+
+	match = (struct efx_ptp_match *)skb->cb;
+	/* Look for a matching timestamp in the event queue */
+	spin_lock_bh(&ptp->evt_lock);
+	list_for_each_safe(cursor, next, &ptp->evt_list) {
+		struct efx_ptp_event_rx *evt;
+
+		evt = list_entry(cursor, struct efx_ptp_event_rx, link);
+		if ((evt->seq0 == match->words[0]) &&
+		    (evt->seq1 == match->words[1])) {
+			struct skb_shared_hwtstamps *timestamps;
+
+			/* Match - add in hardware timestamp */
+			timestamps = skb_hwtstamps(skb);
+			timestamps->hwtstamp = evt->hwtimestamp;
+
+			match->state = PTP_PACKET_STATE_MATCHED;
+			rc = PTP_PACKET_STATE_MATCHED;
+			list_del(&evt->link);
+			list_add(&evt->link, &ptp->evt_free_list);
+			break;
+		}
+	}
+	spin_unlock_bh(&ptp->evt_lock);
+
+	return rc;
+}
+
+/* Process any queued receive events and corresponding packets
+ *
+ * q is returned with all the packets that are ready for delivery.
+ * true is returned if at least one of those packets requires
+ * synchronisation.
+ */
+static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool rc = false;
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&ptp->rxq))) {
+		struct efx_ptp_match *match;
+
+		match = (struct efx_ptp_match *)skb->cb;
+		if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) {
+			__skb_queue_tail(q, skb);
+		} else if (efx_ptp_match_rx(efx, skb) ==
+			   PTP_PACKET_STATE_MATCHED) {
+			rc = true;
+			__skb_queue_tail(q, skb);
+		} else if (time_after(jiffies, match->expiry)) {
+			match->state = PTP_PACKET_STATE_TIMED_OUT;
+			netif_warn(efx, rx_err, efx->net_dev,
+				   "PTP packet - no timestamp seen\n");
+			__skb_queue_tail(q, skb);
+		} else {
+			/* Replace unprocessed entry and stop */
+			skb_queue_head(&ptp->rxq, skb);
+			break;
+		}
+	}
+
+	return rc;
+}
+
+/* Complete processing of a received packet */
+static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	local_bh_disable();
+	netif_receive_skb(skb);
+	local_bh_enable();
+}
+
+static int efx_ptp_start(struct efx_nic *efx)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct efx_filter_spec rxfilter;
+	int rc;
+
+	ptp->reset_required = false;
+
+	/* Must filter on both event and general ports to ensure
+	 * that there is no packet re-ordering.
+	 */
+	efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
+			   efx_rx_queue_index(
+				   efx_channel_get_rx_queue(ptp->channel)));
+	rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
+				       htonl(PTP_ADDRESS),
+				       htons(PTP_EVENT_PORT));
+	if (rc != 0)
+		return rc;
+
+	rc = efx_filter_insert_filter(efx, &rxfilter, true);
+	if (rc < 0)
+		return rc;
+	ptp->rxfilter_event = rc;
+
+	efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
+			   efx_rx_queue_index(
+				   efx_channel_get_rx_queue(ptp->channel)));
+	rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
+				       htonl(PTP_ADDRESS),
+				       htons(PTP_GENERAL_PORT));
+	if (rc != 0)
+		goto fail;
+
+	rc = efx_filter_insert_filter(efx, &rxfilter, true);
+	if (rc < 0)
+		goto fail;
+	ptp->rxfilter_general = rc;
+
+	rc = efx_ptp_enable(efx);
+	if (rc != 0)
+		goto fail2;
+
+	ptp->evt_frag_idx = 0;
+	ptp->current_adjfreq = 0;
+	ptp->rxfilter_installed = true;
+
+	return 0;
+
+fail2:
+	efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+				  ptp->rxfilter_general);
+fail:
+	efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+				  ptp->rxfilter_event);
+
+	return rc;
+}
+
+static int efx_ptp_stop(struct efx_nic *efx)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	int rc = efx_ptp_disable(efx);
+	struct list_head *cursor;
+	struct list_head *next;
+
+	if (ptp->rxfilter_installed) {
+		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+					  ptp->rxfilter_general);
+		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+					  ptp->rxfilter_event);
+		ptp->rxfilter_installed = false;
+	}
+
+	/* Make sure RX packets are really delivered */
+	efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq);
+	skb_queue_purge(&efx->ptp_data->txq);
+
+	/* Drop any pending receive events */
+	spin_lock_bh(&efx->ptp_data->evt_lock);
+	list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
+		list_del(cursor);
+		list_add(cursor, &efx->ptp_data->evt_free_list);
+	}
+	spin_unlock_bh(&efx->ptp_data->evt_lock);
+
+	return rc;
+}
+
+static void efx_ptp_pps_worker(struct work_struct *work)
+{
+	struct efx_ptp_data *ptp =
+		container_of(work, struct efx_ptp_data, pps_work);
+	struct efx_nic *efx = ptp->channel->efx;
+	struct ptp_clock_event ptp_evt;
+
+	if (efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS))
+		return;
+
+	ptp_evt.type = PTP_CLOCK_PPSUSR;
+	ptp_evt.pps_times = ptp->host_time_pps;
+	ptp_clock_event(ptp->phc_clock, &ptp_evt);
+}
+
+/* Process any pending transmissions and timestamp any received packets.
+ */
+static void efx_ptp_worker(struct work_struct *work)
+{
+	struct efx_ptp_data *ptp_data =
+		container_of(work, struct efx_ptp_data, work);
+	struct efx_nic *efx = ptp_data->channel->efx;
+	struct sk_buff *skb;
+	struct sk_buff_head tempq;
+
+	if (ptp_data->reset_required) {
+		efx_ptp_stop(efx);
+		efx_ptp_start(efx);
+		return;
+	}
+
+	efx_ptp_drop_time_expired_events(efx);
+
+	__skb_queue_head_init(&tempq);
+	if (efx_ptp_process_events(efx, &tempq) ||
+	    !skb_queue_empty(&ptp_data->txq)) {
+
+		while ((skb = skb_dequeue(&ptp_data->txq)))
+			efx_ptp_xmit_skb(efx, skb);
+	}
+
+	while ((skb = __skb_dequeue(&tempq)))
+		efx_ptp_process_rx(efx, skb);
+}
+
+/* Initialise PTP channel and state.
+ *
+ * Setting core_index to zero causes the queue to be initialised and doesn't
+ * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue.
+ */
+static int efx_ptp_probe_channel(struct efx_channel *channel)
+{
+	struct efx_nic *efx = channel->efx;
+	struct efx_ptp_data *ptp;
+	int rc = 0;
+	unsigned int pos;
+
+	channel->irq_moderation = 0;
+	channel->rx_queue.core_index = 0;
+
+	ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL);
+	efx->ptp_data = ptp;
+	if (!efx->ptp_data)
+		return -ENOMEM;
+
+	rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int));
+	if (rc != 0)
+		goto fail1;
+
+	ptp->channel = channel;
+	skb_queue_head_init(&ptp->rxq);
+	skb_queue_head_init(&ptp->txq);
+	ptp->workwq = create_singlethread_workqueue("sfc_ptp");
+	if (!ptp->workwq) {
+		rc = -ENOMEM;
+		goto fail2;
+	}
+
+	INIT_WORK(&ptp->work, efx_ptp_worker);
+	ptp->config.flags = 0;
+	ptp->config.tx_type = HWTSTAMP_TX_OFF;
+	ptp->config.rx_filter = HWTSTAMP_FILTER_NONE;
+	INIT_LIST_HEAD(&ptp->evt_list);
+	INIT_LIST_HEAD(&ptp->evt_free_list);
+	spin_lock_init(&ptp->evt_lock);
+	for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
+		list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
+
+	ptp->phc_clock_info.owner = THIS_MODULE;
+	snprintf(ptp->phc_clock_info.name,
+		 sizeof(ptp->phc_clock_info.name),
+		 "%pm", efx->net_dev->perm_addr);
+	ptp->phc_clock_info.max_adj = MAX_PPB;
+	ptp->phc_clock_info.n_alarm = 0;
+	ptp->phc_clock_info.n_ext_ts = 0;
+	ptp->phc_clock_info.n_per_out = 0;
+	ptp->phc_clock_info.pps = 1;
+	ptp->phc_clock_info.adjfreq = efx_phc_adjfreq;
+	ptp->phc_clock_info.adjtime = efx_phc_adjtime;
+	ptp->phc_clock_info.gettime = efx_phc_gettime;
+	ptp->phc_clock_info.settime = efx_phc_settime;
+	ptp->phc_clock_info.enable = efx_phc_enable;
+
+	ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info,
+					    &efx->pci_dev->dev);
+	if (!ptp->phc_clock)
+		goto fail3;
+
+	INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker);
+	ptp->pps_workwq = create_singlethread_workqueue("sfc_pps");
+	if (!ptp->pps_workwq) {
+		rc = -ENOMEM;
+		goto fail4;
+	}
+	ptp->nic_ts_enabled = false;
+
+	return 0;
+fail4:
+	ptp_clock_unregister(efx->ptp_data->phc_clock);
+
+fail3:
+	destroy_workqueue(efx->ptp_data->workwq);
+
+fail2:
+	efx_nic_free_buffer(efx, &ptp->start);
+
+fail1:
+	kfree(efx->ptp_data);
+	efx->ptp_data = NULL;
+
+	return rc;
+}
+
+static void efx_ptp_remove_channel(struct efx_channel *channel)
+{
+	struct efx_nic *efx = channel->efx;
+
+	if (!efx->ptp_data)
+		return;
+
+	(void)efx_ptp_disable(channel->efx);
+
+	cancel_work_sync(&efx->ptp_data->work);
+	cancel_work_sync(&efx->ptp_data->pps_work);
+
+	skb_queue_purge(&efx->ptp_data->rxq);
+	skb_queue_purge(&efx->ptp_data->txq);
+
+	ptp_clock_unregister(efx->ptp_data->phc_clock);
+
+	destroy_workqueue(efx->ptp_data->workwq);
+	destroy_workqueue(efx->ptp_data->pps_workwq);
+
+	efx_nic_free_buffer(efx, &efx->ptp_data->start);
+	kfree(efx->ptp_data);
+}
+
+static void efx_ptp_get_channel_name(struct efx_channel *channel,
+				     char *buf, size_t len)
+{
+	snprintf(buf, len, "%s-ptp", channel->efx->name);
+}
+
+/* Determine whether this packet should be processed by the PTP module
+ * or transmitted conventionally.
+ */
+bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	return efx->ptp_data &&
+		efx->ptp_data->enabled &&
+		skb->len >= PTP_MIN_LENGTH &&
+		skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM &&
+		likely(skb->protocol == htons(ETH_P_IP)) &&
+		ip_hdr(skb)->protocol == IPPROTO_UDP &&
+		udp_hdr(skb)->dest == htons(PTP_EVENT_PORT);
+}
+
+/* Receive a PTP packet.  Packets are queued until the arrival of
+ * the receive timestamp from the MC - this will probably occur after the
+ * packet arrival because of the processing in the MC.
+ */
+static void efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
+{
+	struct efx_nic *efx = channel->efx;
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb;
+	u8 *data;
+	unsigned int version;
+
+	match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
+
+	/* Correct version? */
+	if (ptp->mode == MC_CMD_PTP_MODE_V1) {
+		if (skb->len < PTP_V1_MIN_LENGTH) {
+			netif_receive_skb(skb);
+			return;
+		}
+		version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]);
+		if (version != PTP_VERSION_V1) {
+			netif_receive_skb(skb);
+			return;
+		}
+	} else {
+		if (skb->len < PTP_V2_MIN_LENGTH) {
+			netif_receive_skb(skb);
+			return;
+		}
+		version = skb->data[PTP_V2_VERSION_OFFSET];
+
+		BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2);
+		BUILD_BUG_ON(PTP_V1_UUID_OFFSET != PTP_V2_MC_UUID_OFFSET);
+		BUILD_BUG_ON(PTP_V1_UUID_LENGTH != PTP_V2_MC_UUID_LENGTH);
+		BUILD_BUG_ON(PTP_V1_SEQUENCE_OFFSET != PTP_V2_SEQUENCE_OFFSET);
+		BUILD_BUG_ON(PTP_V1_SEQUENCE_LENGTH != PTP_V2_SEQUENCE_LENGTH);
+
+		if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) {
+			netif_receive_skb(skb);
+			return;
+		}
+	}
+
+	/* Does this packet require timestamping? */
+	if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) {
+		struct skb_shared_hwtstamps *timestamps;
+
+		match->state = PTP_PACKET_STATE_UNMATCHED;
+
+		/* Clear all timestamps held: filled in later */
+		timestamps = skb_hwtstamps(skb);
+		memset(timestamps, 0, sizeof(*timestamps));
+
+		/* Extract UUID/Sequence information */
+		data = skb->data + PTP_V1_UUID_OFFSET;
+		match->words[0] = (data[0]         |
+				   (data[1] << 8)  |
+				   (data[2] << 16) |
+				   (data[3] << 24));
+		match->words[1] = (data[4]         |
+				   (data[5] << 8)  |
+				   (skb->data[PTP_V1_SEQUENCE_OFFSET +
+					      PTP_V1_SEQUENCE_LENGTH - 1] <<
+				    16));
+	} else {
+		match->state = PTP_PACKET_STATE_MATCH_UNWANTED;
+	}
+
+	skb_queue_tail(&ptp->rxq, skb);
+	queue_work(ptp->workwq, &ptp->work);
+}
+
+/* Transmit a PTP packet.  This has to be transmitted by the MC
+ * itself, through an MCDI call.  MCDI calls aren't permitted
+ * in the transmit path so defer the actual transmission to a suitable worker.
+ */
+int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+
+	skb_queue_tail(&ptp->txq, skb);
+
+	if ((udp_hdr(skb)->dest == htons(PTP_EVENT_PORT)) &&
+	    (skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM))
+		efx_xmit_hwtstamp_pending(skb);
+	queue_work(ptp->workwq, &ptp->work);
+
+	return NETDEV_TX_OK;
+}
+
+static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
+			       unsigned int new_mode)
+{
+	if ((enable_wanted != efx->ptp_data->enabled) ||
+	    (enable_wanted && (efx->ptp_data->mode != new_mode))) {
+		int rc;
+
+		if (enable_wanted) {
+			/* Change of mode requires disable */
+			if (efx->ptp_data->enabled &&
+			    (efx->ptp_data->mode != new_mode)) {
+				efx->ptp_data->enabled = false;
+				rc = efx_ptp_stop(efx);
+				if (rc != 0)
+					return rc;
+			}
+
+			/* Set new operating mode and establish
+			 * baseline synchronisation, which must
+			 * succeed.
+			 */
+			efx->ptp_data->mode = new_mode;
+			rc = efx_ptp_start(efx);
+			if (rc == 0) {
+				rc = efx_ptp_synchronize(efx,
+							 PTP_SYNC_ATTEMPTS * 2);
+				if (rc != 0)
+					efx_ptp_stop(efx);
+			}
+		} else {
+			rc = efx_ptp_stop(efx);
+		}
+
+		if (rc != 0)
+			return rc;
+
+		efx->ptp_data->enabled = enable_wanted;
+	}
+
+	return 0;
+}
+
+static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
+{
+	bool enable_wanted = false;
+	unsigned int new_mode;
+	int rc;
+
+	if (init->flags)
+		return -EINVAL;
+
+	if ((init->tx_type != HWTSTAMP_TX_OFF) &&
+	    (init->tx_type != HWTSTAMP_TX_ON))
+		return -ERANGE;
+
+	new_mode = efx->ptp_data->mode;
+	/* Determine whether any PTP HW operations are required */
+	switch (init->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		new_mode = MC_CMD_PTP_MODE_V1;
+		enable_wanted = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	/* Although these three are accepted only IPV4 packets will be
+	 * timestamped
+	 */
+		init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		new_mode = MC_CMD_PTP_MODE_V2;
+		enable_wanted = true;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		/* Non-IP + IPv6 timestamping not supported */
+		return -ERANGE;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (init->tx_type != HWTSTAMP_TX_OFF)
+		enable_wanted = true;
+
+	rc = efx_ptp_change_mode(efx, enable_wanted, new_mode);
+	if (rc != 0)
+		return rc;
+
+	efx->ptp_data->config = *init;
+
+	return 0;
+}
+
+int
+efx_ptp_get_ts_info(struct net_device *net_dev, struct ethtool_ts_info *ts_info)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	struct efx_ptp_data *ptp = efx->ptp_data;
+
+	if (!ptp)
+		return -EOPNOTSUPP;
+
+	ts_info->so_timestamping = (SOF_TIMESTAMPING_TX_HARDWARE |
+				    SOF_TIMESTAMPING_RX_HARDWARE |
+				    SOF_TIMESTAMPING_RAW_HARDWARE);
+	ts_info->phc_index = ptp_clock_index(ptp->phc_clock);
+	ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON;
+	ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE |
+			       1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT |
+			       1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC |
+			       1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ |
+			       1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT |
+			       1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC |
+			       1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ);
+	return 0;
+}
+
+int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
+{
+	struct hwtstamp_config config;
+	int rc;
+
+	/* Not a PTP enabled port */
+	if (!efx->ptp_data)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	rc = efx_ptp_ts_init(efx, &config);
+	if (rc != 0)
+		return rc;
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config))
+		? -EFAULT : 0;
+}
+
+static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+
+	netif_err(efx, hw, efx->net_dev,
+		"PTP unexpected event length: got %d expected %d\n",
+		ptp->evt_frag_idx, expected_frag_len);
+	ptp->reset_required = true;
+	queue_work(ptp->workwq, &ptp->work);
+}
+
+/* Process a completed receive event.  Put it on the event queue and
+ * start worker thread.  This is required because event and their
+ * correspoding packets may come in either order.
+ */
+static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+	struct efx_ptp_event_rx *evt = NULL;
+
+	if (ptp->evt_frag_idx != 3) {
+		ptp_event_failure(efx, 3);
+		return;
+	}
+
+	spin_lock_bh(&ptp->evt_lock);
+	if (!list_empty(&ptp->evt_free_list)) {
+		evt = list_first_entry(&ptp->evt_free_list,
+				       struct efx_ptp_event_rx, link);
+		list_del(&evt->link);
+
+		evt->seq0 = EFX_QWORD_FIELD(ptp->evt_frags[2], MCDI_EVENT_DATA);
+		evt->seq1 = (EFX_QWORD_FIELD(ptp->evt_frags[2],
+					     MCDI_EVENT_SRC)        |
+			     (EFX_QWORD_FIELD(ptp->evt_frags[1],
+					      MCDI_EVENT_SRC) << 8) |
+			     (EFX_QWORD_FIELD(ptp->evt_frags[0],
+					      MCDI_EVENT_SRC) << 16));
+		evt->hwtimestamp = ktime_set(
+			EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA),
+			EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA));
+		evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
+		list_add_tail(&evt->link, &ptp->evt_list);
+
+		queue_work(ptp->workwq, &ptp->work);
+	} else {
+		netif_err(efx, rx_err, efx->net_dev, "No free PTP event");
+	}
+	spin_unlock_bh(&ptp->evt_lock);
+}
+
+static void ptp_event_fault(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+	int code = EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA);
+	if (ptp->evt_frag_idx != 1) {
+		ptp_event_failure(efx, 1);
+		return;
+	}
+
+	netif_err(efx, hw, efx->net_dev, "PTP error %d\n", code);
+}
+
+static void ptp_event_pps(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+	if (ptp->nic_ts_enabled)
+		queue_work(ptp->pps_workwq, &ptp->pps_work);
+}
+
+void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
+
+	if (!ptp->enabled)
+		return;
+
+	if (ptp->evt_frag_idx == 0) {
+		ptp->evt_code = code;
+	} else if (ptp->evt_code != code) {
+		netif_err(efx, hw, efx->net_dev,
+			  "PTP out of sequence event %d\n", code);
+		ptp->evt_frag_idx = 0;
+	}
+
+	ptp->evt_frags[ptp->evt_frag_idx++] = *ev;
+	if (!MCDI_EVENT_FIELD(*ev, CONT)) {
+		/* Process resulting event */
+		switch (code) {
+		case MCDI_EVENT_CODE_PTP_RX:
+			ptp_event_rx(efx, ptp);
+			break;
+		case MCDI_EVENT_CODE_PTP_FAULT:
+			ptp_event_fault(efx, ptp);
+			break;
+		case MCDI_EVENT_CODE_PTP_PPS:
+			ptp_event_pps(efx, ptp);
+			break;
+		default:
+			netif_err(efx, hw, efx->net_dev,
+				  "PTP unknown event %d\n", code);
+			break;
+		}
+		ptp->evt_frag_idx = 0;
+	} else if (MAX_EVENT_FRAGS == ptp->evt_frag_idx) {
+		netif_err(efx, hw, efx->net_dev,
+			  "PTP too many event fragments\n");
+		ptp->evt_frag_idx = 0;
+	}
+}
+
+static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+	struct efx_ptp_data *ptp_data = container_of(ptp,
+						     struct efx_ptp_data,
+						     phc_clock_info);
+	struct efx_nic *efx = ptp_data->channel->efx;
+	u8 inadj[MC_CMD_PTP_IN_ADJUST_LEN];
+	s64 adjustment_ns;
+	int rc;
+
+	if (delta > MAX_PPB)
+		delta = MAX_PPB;
+	else if (delta < -MAX_PPB)
+		delta = -MAX_PPB;
+
+	/* Convert ppb to fixed point ns. */
+	adjustment_ns = (((s64)delta * PPB_SCALE_WORD) >>
+			 (PPB_EXTRA_BITS + MAX_PPB_BITS));
+
+	MCDI_SET_DWORD(inadj, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
+	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_FREQ_LO, (u32)adjustment_ns);
+	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_FREQ_HI,
+		       (u32)(adjustment_ns >> 32));
+	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_SECONDS, 0);
+	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_NANOSECONDS, 0);
+	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inadj, sizeof(inadj),
+			  NULL, 0, NULL);
+	if (rc != 0)
+		return rc;
+
+	ptp_data->current_adjfreq = delta;
+	return 0;
+}
+
+static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct efx_ptp_data *ptp_data = container_of(ptp,
+						     struct efx_ptp_data,
+						     phc_clock_info);
+	struct efx_nic *efx = ptp_data->channel->efx;
+	struct timespec delta_ts = ns_to_timespec(delta);
+	u8 inbuf[MC_CMD_PTP_IN_ADJUST_LEN];
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_FREQ_LO, 0);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_FREQ_HI, 0);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_SECONDS, (u32)delta_ts.tv_sec);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_NANOSECONDS, (u32)delta_ts.tv_nsec);
+	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+	struct efx_ptp_data *ptp_data = container_of(ptp,
+						     struct efx_ptp_data,
+						     phc_clock_info);
+	struct efx_nic *efx = ptp_data->channel->efx;
+	u8 inbuf[MC_CMD_PTP_IN_READ_NIC_TIME_LEN];
+	u8 outbuf[MC_CMD_PTP_OUT_READ_NIC_TIME_LEN];
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_READ_NIC_TIME);
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			  outbuf, sizeof(outbuf), NULL);
+	if (rc != 0)
+		return rc;
+
+	ts->tv_sec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_SECONDS);
+	ts->tv_nsec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_NANOSECONDS);
+	return 0;
+}
+
+static int efx_phc_settime(struct ptp_clock_info *ptp,
+			   const struct timespec *e_ts)
+{
+	/* Get the current NIC time, efx_phc_gettime.
+	 * Subtract from the desired time to get the offset
+	 * call efx_phc_adjtime with the offset
+	 */
+	int rc;
+	struct timespec time_now;
+	struct timespec delta;
+
+	rc = efx_phc_gettime(ptp, &time_now);
+	if (rc != 0)
+		return rc;
+
+	delta = timespec_sub(*e_ts, time_now);
+
+	efx_phc_adjtime(ptp, timespec_to_ns(&delta));
+	if (rc != 0)
+		return rc;
+
+	return 0;
+}
+
+static int efx_phc_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *request,
+			  int enable)
+{
+	struct efx_ptp_data *ptp_data = container_of(ptp,
+						     struct efx_ptp_data,
+						     phc_clock_info);
+	if (request->type != PTP_CLK_REQ_PPS)
+		return -EOPNOTSUPP;
+
+	ptp_data->nic_ts_enabled = !!enable;
+	return 0;
+}
+
+static const struct efx_channel_type efx_ptp_channel_type = {
+	.handle_no_channel	= efx_ptp_handle_no_channel,
+	.pre_probe		= efx_ptp_probe_channel,
+	.post_remove		= efx_ptp_remove_channel,
+	.get_name		= efx_ptp_get_channel_name,
+	/* no copy operation; there is no need to reallocate this channel */
+	.receive_skb		= efx_ptp_rx,
+	.keep_eventq		= false,
+};
+
+void efx_ptp_probe(struct efx_nic *efx)
+{
+	/* Check whether PTP is implemented on this NIC.  The DISABLE
+	 * operation will succeed if and only if it is implemented.
+	 */
+	if (efx_ptp_disable(efx) == 0)
+		efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] =
+			&efx_ptp_channel_type;
+}
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 719319b89d7a..9e0ad1b75c33 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -479,7 +479,7 @@ static void efx_rx_packet_gro(struct efx_channel *channel,
 		skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ?
 				  CHECKSUM_UNNECESSARY : CHECKSUM_NONE);
 
-		skb_record_rx_queue(skb, channel->channel);
+		skb_record_rx_queue(skb, channel->rx_queue.core_index);
 
 		gro_result = napi_gro_frags(napi);
 	} else {
@@ -571,8 +571,14 @@ static void efx_rx_deliver(struct efx_channel *channel,
 	/* Set the SKB flags */
 	skb_checksum_none_assert(skb);
 
+	/* Record the rx_queue */
+	skb_record_rx_queue(skb, channel->rx_queue.core_index);
+
 	/* Pass the packet up */
-	netif_receive_skb(skb);
+	if (channel->type->receive_skb)
+		channel->type->receive_skb(channel, skb);
+	else
+		netif_receive_skb(skb);
 
 	/* Update allocation strategy method */
 	channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
@@ -608,13 +614,14 @@ void __efx_rx_packet(struct efx_channel *channel, struct efx_rx_buffer *rx_buf)
 		 * at the ethernet header */
 		skb->protocol = eth_type_trans(skb, efx->net_dev);
 
-		skb_record_rx_queue(skb, channel->channel);
+		skb_record_rx_queue(skb, channel->rx_queue.core_index);
 	}
 
 	if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM)))
 		rx_buf->flags &= ~EFX_RX_PKT_CSUMMED;
 
-	if (likely(rx_buf->flags & (EFX_RX_BUF_PAGE | EFX_RX_PKT_CSUMMED)))
+	if (likely(rx_buf->flags & (EFX_RX_BUF_PAGE | EFX_RX_PKT_CSUMMED)) &&
+	    !channel->type->receive_skb)
 		efx_rx_packet_gro(channel, rx_buf, eh);
 	else
 		efx_rx_deliver(channel, rx_buf);
@@ -624,6 +631,11 @@ void efx_rx_strategy(struct efx_channel *channel)
 {
 	enum efx_rx_alloc_method method = rx_alloc_method;
 
+	if (channel->type->receive_skb) {
+		channel->rx_alloc_push_pages = false;
+		return;
+	}
+
 	/* Only makes sense to use page based allocation if GRO is enabled */
 	if (!(channel->efx->net_dev->features & NETIF_F_GRO)) {
 		method = RX_ALLOC_METHOD_SKB;
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 96068d15b601..ce72ae4f399f 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -614,7 +614,8 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests,
 {
 	enum efx_loopback_mode mode;
 	struct efx_loopback_state *state;
-	struct efx_channel *channel = efx_get_channel(efx, 0);
+	struct efx_channel *channel =
+		efx_get_channel(efx, efx->tx_channel_offset);
 	struct efx_tx_queue *tx_queue;
 	int rc = 0;
 
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 6bafd216e55e..84b41bf08a38 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -335,6 +335,7 @@ static int siena_probe_nic(struct efx_nic *efx)
 		goto fail5;
 
 	efx_sriov_probe(efx);
+	efx_ptp_probe(efx);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index 9cb3b84ecae9..d49b53dc2a50 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -21,6 +21,9 @@
 /* Number of longs required to track all the VIs in a VF */
 #define VI_MASK_LENGTH BITS_TO_LONGS(1 << EFX_VI_SCALE_MAX)
 
+/* Maximum number of RX queues supported */
+#define VF_MAX_RX_QUEUES 63
+
 /**
  * enum efx_vf_tx_filter_mode - TX MAC filtering behaviour
  * @VF_TX_FILTER_OFF: Disabled
@@ -578,6 +581,7 @@ static int efx_vfdi_init_rxq(struct efx_vf *vf)
 	efx_oword_t reg;
 
 	if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_rxq) ||
+	    vf_rxq >= VF_MAX_RX_QUEUES ||
 	    bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) {
 		if (net_ratelimit())
 			netif_err(efx, hw, efx->net_dev,
@@ -683,6 +687,9 @@ static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
 	__le32 *rxqs;
 	int rc;
 
+	BUILD_BUG_ON(VF_MAX_RX_QUEUES >
+		     MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
+
 	rxqs = kmalloc(count * sizeof(*rxqs), GFP_KERNEL);
 	if (rxqs == NULL)
 		return VFDI_RC_ENOMEM;
@@ -1028,6 +1035,7 @@ efx_sriov_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
 static const struct efx_channel_type efx_sriov_channel_type = {
 	.handle_no_channel	= efx_sriov_handle_no_channel,
 	.pre_probe		= efx_sriov_probe_channel,
+	.post_remove		= efx_channel_dummy_op_void,
 	.get_name		= efx_sriov_get_channel_name,
 	/* no copy operation; channel must not be reallocated */
 	.keep_eventq		= true,
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 18713436b443..5e090e54298e 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -22,14 +22,6 @@
 #include "nic.h"
 #include "workarounds.h"
 
-/*
- * TX descriptor ring full threshold
- *
- * The tx_queue descriptor ring fill-level must fall below this value
- * before we restart the netif queue
- */
-#define EFX_TXQ_THRESHOLD(_efx) ((_efx)->txq_entries / 2u)
-
 static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 			       struct efx_tx_buffer *buffer,
 			       unsigned int *pkts_compl,
@@ -39,67 +31,32 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 		struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
 		dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len -
 					 buffer->unmap_len);
-		if (buffer->unmap_single)
+		if (buffer->flags & EFX_TX_BUF_MAP_SINGLE)
 			dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
 					 DMA_TO_DEVICE);
 		else
 			dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
 				       DMA_TO_DEVICE);
 		buffer->unmap_len = 0;
-		buffer->unmap_single = false;
 	}
 
-	if (buffer->skb) {
+	if (buffer->flags & EFX_TX_BUF_SKB) {
 		(*pkts_compl)++;
 		(*bytes_compl) += buffer->skb->len;
 		dev_kfree_skb_any((struct sk_buff *) buffer->skb);
-		buffer->skb = NULL;
 		netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
 			   "TX queue %d transmission id %x complete\n",
 			   tx_queue->queue, tx_queue->read_count);
+	} else if (buffer->flags & EFX_TX_BUF_HEAP) {
+		kfree(buffer->heap_buf);
 	}
-}
 
-/**
- * struct efx_tso_header - a DMA mapped buffer for packet headers
- * @next: Linked list of free ones.
- *	The list is protected by the TX queue lock.
- * @dma_unmap_len: Length to unmap for an oversize buffer, or 0.
- * @dma_addr: The DMA address of the header below.
- *
- * This controls the memory used for a TSO header.  Use TSOH_DATA()
- * to find the packet header data.  Use TSOH_SIZE() to calculate the
- * total size required for a given packet header length.  TSO headers
- * in the free list are exactly %TSOH_STD_SIZE bytes in size.
- */
-struct efx_tso_header {
-	union {
-		struct efx_tso_header *next;
-		size_t unmap_len;
-	};
-	dma_addr_t dma_addr;
-};
+	buffer->len = 0;
+	buffer->flags = 0;
+}
 
 static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 			       struct sk_buff *skb);
-static void efx_fini_tso(struct efx_tx_queue *tx_queue);
-static void efx_tsoh_heap_free(struct efx_tx_queue *tx_queue,
-			       struct efx_tso_header *tsoh);
-
-static void efx_tsoh_free(struct efx_tx_queue *tx_queue,
-			  struct efx_tx_buffer *buffer)
-{
-	if (buffer->tsoh) {
-		if (likely(!buffer->tsoh->unmap_len)) {
-			buffer->tsoh->next = tx_queue->tso_headers_free;
-			tx_queue->tso_headers_free = buffer->tsoh;
-		} else {
-			efx_tsoh_heap_free(tx_queue, buffer->tsoh);
-		}
-		buffer->tsoh = NULL;
-	}
-}
-
 
 static inline unsigned
 efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
@@ -138,6 +95,56 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
 	return max_descs;
 }
 
+/* Get partner of a TX queue, seen as part of the same net core queue */
+static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue)
+{
+	if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
+		return tx_queue - EFX_TXQ_TYPE_OFFLOAD;
+	else
+		return tx_queue + EFX_TXQ_TYPE_OFFLOAD;
+}
+
+static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
+{
+	/* We need to consider both queues that the net core sees as one */
+	struct efx_tx_queue *txq2 = efx_tx_queue_partner(txq1);
+	struct efx_nic *efx = txq1->efx;
+	unsigned int fill_level;
+
+	fill_level = max(txq1->insert_count - txq1->old_read_count,
+			 txq2->insert_count - txq2->old_read_count);
+	if (likely(fill_level < efx->txq_stop_thresh))
+		return;
+
+	/* We used the stale old_read_count above, which gives us a
+	 * pessimistic estimate of the fill level (which may even
+	 * validly be >= efx->txq_entries).  Now try again using
+	 * read_count (more likely to be a cache miss).
+	 *
+	 * If we read read_count and then conditionally stop the
+	 * queue, it is possible for the completion path to race with
+	 * us and complete all outstanding descriptors in the middle,
+	 * after which there will be no more completions to wake it.
+	 * Therefore we stop the queue first, then read read_count
+	 * (with a memory barrier to ensure the ordering), then
+	 * restart the queue if the fill level turns out to be low
+	 * enough.
+	 */
+	netif_tx_stop_queue(txq1->core_txq);
+	smp_mb();
+	txq1->old_read_count = ACCESS_ONCE(txq1->read_count);
+	txq2->old_read_count = ACCESS_ONCE(txq2->read_count);
+
+	fill_level = max(txq1->insert_count - txq1->old_read_count,
+			 txq2->insert_count - txq2->old_read_count);
+	EFX_BUG_ON_PARANOID(fill_level >= efx->txq_entries);
+	if (likely(fill_level < efx->txq_stop_thresh)) {
+		smp_mb();
+		if (likely(!efx->loopback_selftest))
+			netif_tx_start_queue(txq1->core_txq);
+	}
+}
+
 /*
  * Add a socket buffer to a TX queue
  *
@@ -151,7 +158,7 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
  * This function is split out from efx_hard_start_xmit to allow the
  * loopback test to direct packets via specific TX queues.
  *
- * Returns NETDEV_TX_OK or NETDEV_TX_BUSY
+ * Returns NETDEV_TX_OK.
  * You must hold netif_tx_lock() to call this function.
  */
 netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
@@ -160,12 +167,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	struct device *dma_dev = &efx->pci_dev->dev;
 	struct efx_tx_buffer *buffer;
 	skb_frag_t *fragment;
-	unsigned int len, unmap_len = 0, fill_level, insert_ptr;
+	unsigned int len, unmap_len = 0, insert_ptr;
 	dma_addr_t dma_addr, unmap_addr = 0;
 	unsigned int dma_len;
-	bool unmap_single;
-	int q_space, i = 0;
-	netdev_tx_t rc = NETDEV_TX_OK;
+	unsigned short dma_flags;
+	int i = 0;
 
 	EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
 
@@ -183,14 +189,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 			return NETDEV_TX_OK;
 	}
 
-	fill_level = tx_queue->insert_count - tx_queue->old_read_count;
-	q_space = efx->txq_entries - 1 - fill_level;
-
 	/* Map for DMA.  Use dma_map_single rather than dma_map_page
 	 * since this is more efficient on machines with sparse
 	 * memory.
 	 */
-	unmap_single = true;
+	dma_flags = EFX_TX_BUF_MAP_SINGLE;
 	dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE);
 
 	/* Process all fragments */
@@ -205,39 +208,10 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 		/* Add to TX queue, splitting across DMA boundaries */
 		do {
-			if (unlikely(q_space-- <= 0)) {
-				/* It might be that completions have
-				 * happened since the xmit path last
-				 * checked.  Update the xmit path's
-				 * copy of read_count.
-				 */
-				netif_tx_stop_queue(tx_queue->core_txq);
-				/* This memory barrier protects the
-				 * change of queue state from the access
-				 * of read_count. */
-				smp_mb();
-				tx_queue->old_read_count =
-					ACCESS_ONCE(tx_queue->read_count);
-				fill_level = (tx_queue->insert_count
-					      - tx_queue->old_read_count);
-				q_space = efx->txq_entries - 1 - fill_level;
-				if (unlikely(q_space-- <= 0)) {
-					rc = NETDEV_TX_BUSY;
-					goto unwind;
-				}
-				smp_mb();
-				if (likely(!efx->loopback_selftest))
-					netif_tx_start_queue(
-						tx_queue->core_txq);
-			}
-
 			insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
 			buffer = &tx_queue->buffer[insert_ptr];
-			efx_tsoh_free(tx_queue, buffer);
-			EFX_BUG_ON_PARANOID(buffer->tsoh);
-			EFX_BUG_ON_PARANOID(buffer->skb);
+			EFX_BUG_ON_PARANOID(buffer->flags);
 			EFX_BUG_ON_PARANOID(buffer->len);
-			EFX_BUG_ON_PARANOID(!buffer->continuation);
 			EFX_BUG_ON_PARANOID(buffer->unmap_len);
 
 			dma_len = efx_max_tx_len(efx, dma_addr);
@@ -247,13 +221,14 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 			/* Fill out per descriptor fields */
 			buffer->len = dma_len;
 			buffer->dma_addr = dma_addr;
+			buffer->flags = EFX_TX_BUF_CONT;
 			len -= dma_len;
 			dma_addr += dma_len;
 			++tx_queue->insert_count;
 		} while (len);
 
 		/* Transfer ownership of the unmapping to the final buffer */
-		buffer->unmap_single = unmap_single;
+		buffer->flags = EFX_TX_BUF_CONT | dma_flags;
 		buffer->unmap_len = unmap_len;
 		unmap_len = 0;
 
@@ -264,20 +239,22 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		len = skb_frag_size(fragment);
 		i++;
 		/* Map for DMA */
-		unmap_single = false;
+		dma_flags = 0;
 		dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
 					    DMA_TO_DEVICE);
 	}
 
 	/* Transfer ownership of the skb to the final buffer */
 	buffer->skb = skb;
-	buffer->continuation = false;
+	buffer->flags = EFX_TX_BUF_SKB | dma_flags;
 
 	netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
 
 	/* Pass off to hardware */
 	efx_nic_push_buffers(tx_queue);
 
+	efx_tx_maybe_stop_queue(tx_queue);
+
 	return NETDEV_TX_OK;
 
  dma_err:
@@ -289,7 +266,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	/* Mark the packet as transmitted, and free the SKB ourselves */
 	dev_kfree_skb_any(skb);
 
- unwind:
 	/* Work backwards until we hit the original insert pointer value */
 	while (tx_queue->insert_count != tx_queue->write_count) {
 		unsigned int pkts_compl = 0, bytes_compl = 0;
@@ -297,12 +273,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
 		buffer = &tx_queue->buffer[insert_ptr];
 		efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
-		buffer->len = 0;
 	}
 
 	/* Free the fragment we were mid-way through pushing */
 	if (unmap_len) {
-		if (unmap_single)
+		if (dma_flags & EFX_TX_BUF_MAP_SINGLE)
 			dma_unmap_single(dma_dev, unmap_addr, unmap_len,
 					 DMA_TO_DEVICE);
 		else
@@ -310,7 +285,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 				       DMA_TO_DEVICE);
 	}
 
-	return rc;
+	return NETDEV_TX_OK;
 }
 
 /* Remove packets from the TX queue
@@ -340,8 +315,6 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
 		}
 
 		efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
-		buffer->continuation = true;
-		buffer->len = 0;
 
 		++tx_queue->read_count;
 		read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
@@ -366,6 +339,12 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
 
 	EFX_WARN_ON_PARANOID(!netif_device_present(net_dev));
 
+	/* PTP "event" packet */
+	if (unlikely(efx_xmit_with_hwtstamp(skb)) &&
+	    unlikely(efx_ptp_is_ptp_tx(efx, skb))) {
+		return efx_ptp_tx(efx, skb);
+	}
+
 	index = skb_get_queue_mapping(skb);
 	type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0;
 	if (index >= efx->n_tx_channels) {
@@ -450,6 +429,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
 {
 	unsigned fill_level;
 	struct efx_nic *efx = tx_queue->efx;
+	struct efx_tx_queue *txq2;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 
 	EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask);
@@ -457,15 +437,18 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
 	efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
 	netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
 
-	/* See if we need to restart the netif queue.  This barrier
-	 * separates the update of read_count from the test of the
-	 * queue state. */
+	/* See if we need to restart the netif queue.  This memory
+	 * barrier ensures that we write read_count (inside
+	 * efx_dequeue_buffers()) before reading the queue status.
+	 */
 	smp_mb();
 	if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) &&
 	    likely(efx->port_enabled) &&
 	    likely(netif_device_present(efx->net_dev))) {
-		fill_level = tx_queue->insert_count - tx_queue->read_count;
-		if (fill_level < EFX_TXQ_THRESHOLD(efx))
+		txq2 = efx_tx_queue_partner(tx_queue);
+		fill_level = max(tx_queue->insert_count - tx_queue->read_count,
+				 txq2->insert_count - txq2->read_count);
+		if (fill_level <= efx->txq_wake_thresh)
 			netif_tx_wake_queue(tx_queue->core_txq);
 	}
 
@@ -480,11 +463,26 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
 	}
 }
 
+/* Size of page-based TSO header buffers.  Larger blocks must be
+ * allocated from the heap.
+ */
+#define TSOH_STD_SIZE	128
+#define TSOH_PER_PAGE	(PAGE_SIZE / TSOH_STD_SIZE)
+
+/* At most half the descriptors in the queue at any time will refer to
+ * a TSO header buffer, since they must always be followed by a
+ * payload descriptor referring to an skb.
+ */
+static unsigned int efx_tsoh_page_count(struct efx_tx_queue *tx_queue)
+{
+	return DIV_ROUND_UP(tx_queue->ptr_mask + 1, 2 * TSOH_PER_PAGE);
+}
+
 int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
 {
 	struct efx_nic *efx = tx_queue->efx;
 	unsigned int entries;
-	int i, rc;
+	int rc;
 
 	/* Create the smallest power-of-two aligned ring */
 	entries = max(roundup_pow_of_two(efx->txq_entries), EFX_MIN_DMAQ_SIZE);
@@ -500,17 +498,28 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
 				   GFP_KERNEL);
 	if (!tx_queue->buffer)
 		return -ENOMEM;
-	for (i = 0; i <= tx_queue->ptr_mask; ++i)
-		tx_queue->buffer[i].continuation = true;
+
+	if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD) {
+		tx_queue->tsoh_page =
+			kcalloc(efx_tsoh_page_count(tx_queue),
+				sizeof(tx_queue->tsoh_page[0]), GFP_KERNEL);
+		if (!tx_queue->tsoh_page) {
+			rc = -ENOMEM;
+			goto fail1;
+		}
+	}
 
 	/* Allocate hardware ring */
 	rc = efx_nic_probe_tx(tx_queue);
 	if (rc)
-		goto fail;
+		goto fail2;
 
 	return 0;
 
- fail:
+fail2:
+	kfree(tx_queue->tsoh_page);
+	tx_queue->tsoh_page = NULL;
+fail1:
 	kfree(tx_queue->buffer);
 	tx_queue->buffer = NULL;
 	return rc;
@@ -546,8 +555,6 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue)
 		unsigned int pkts_compl = 0, bytes_compl = 0;
 		buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
 		efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
-		buffer->continuation = true;
-		buffer->len = 0;
 
 		++tx_queue->read_count;
 	}
@@ -568,13 +575,12 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 	efx_nic_fini_tx(tx_queue);
 
 	efx_release_tx_buffers(tx_queue);
-
-	/* Free up TSO header cache */
-	efx_fini_tso(tx_queue);
 }
 
 void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
 {
+	int i;
+
 	if (!tx_queue->buffer)
 		return;
 
@@ -582,6 +588,14 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
 		  "destroying TX queue %d\n", tx_queue->queue);
 	efx_nic_remove_tx(tx_queue);
 
+	if (tx_queue->tsoh_page) {
+		for (i = 0; i < efx_tsoh_page_count(tx_queue); i++)
+			efx_nic_free_buffer(tx_queue->efx,
+					    &tx_queue->tsoh_page[i]);
+		kfree(tx_queue->tsoh_page);
+		tx_queue->tsoh_page = NULL;
+	}
+
 	kfree(tx_queue->buffer);
 	tx_queue->buffer = NULL;
 }
@@ -604,22 +618,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
 #define TSOH_OFFSET	NET_IP_ALIGN
 #endif
 
-#define TSOH_BUFFER(tsoh)	((u8 *)(tsoh + 1) + TSOH_OFFSET)
-
-/* Total size of struct efx_tso_header, buffer and padding */
-#define TSOH_SIZE(hdr_len)					\
-	(sizeof(struct efx_tso_header) + TSOH_OFFSET + hdr_len)
-
-/* Size of blocks on free list.  Larger blocks must be allocated from
- * the heap.
- */
-#define TSOH_STD_SIZE		128
-
 #define PTR_DIFF(p1, p2)  ((u8 *)(p1) - (u8 *)(p2))
-#define ETH_HDR_LEN(skb)  (skb_network_header(skb) - (skb)->data)
-#define SKB_TCP_OFF(skb)  PTR_DIFF(tcp_hdr(skb), (skb)->data)
-#define SKB_IPV4_OFF(skb) PTR_DIFF(ip_hdr(skb), (skb)->data)
-#define SKB_IPV6_OFF(skb) PTR_DIFF(ipv6_hdr(skb), (skb)->data)
 
 /**
  * struct tso_state - TSO state for an SKB
@@ -631,10 +630,12 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
  * @in_len: Remaining length in current SKB fragment
  * @unmap_len: Length of SKB fragment
  * @unmap_addr: DMA address of SKB fragment
- * @unmap_single: DMA single vs page mapping flag
+ * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0
  * @protocol: Network protocol (after any VLAN header)
+ * @ip_off: Offset of IP header
+ * @tcp_off: Offset of TCP header
  * @header_len: Number of bytes of header
- * @full_packet_size: Number of bytes to put in each outgoing segment
+ * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload
  *
  * The state used during segmentation.  It is put into this data structure
  * just to make it easy to pass into inline functions.
@@ -651,11 +652,13 @@ struct tso_state {
 	unsigned in_len;
 	unsigned unmap_len;
 	dma_addr_t unmap_addr;
-	bool unmap_single;
+	unsigned short dma_flags;
 
 	__be16 protocol;
+	unsigned int ip_off;
+	unsigned int tcp_off;
 	unsigned header_len;
-	int full_packet_size;
+	unsigned int ip_base_len;
 };
 
 
@@ -687,91 +690,43 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
 	return protocol;
 }
 
-
-/*
- * Allocate a page worth of efx_tso_header structures, and string them
- * into the tx_queue->tso_headers_free linked list. Return 0 or -ENOMEM.
- */
-static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
+static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue,
+			       struct efx_tx_buffer *buffer, unsigned int len)
 {
-	struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
-	struct efx_tso_header *tsoh;
-	dma_addr_t dma_addr;
-	u8 *base_kva, *kva;
+	u8 *result;
 
-	base_kva = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, GFP_ATOMIC);
-	if (base_kva == NULL) {
-		netif_err(tx_queue->efx, tx_err, tx_queue->efx->net_dev,
-			  "Unable to allocate page for TSO headers\n");
-		return -ENOMEM;
-	}
-
-	/* dma_alloc_coherent() allocates pages. */
-	EFX_BUG_ON_PARANOID(dma_addr & (PAGE_SIZE - 1u));
-
-	for (kva = base_kva; kva < base_kva + PAGE_SIZE; kva += TSOH_STD_SIZE) {
-		tsoh = (struct efx_tso_header *)kva;
-		tsoh->dma_addr = dma_addr + (TSOH_BUFFER(tsoh) - base_kva);
-		tsoh->next = tx_queue->tso_headers_free;
-		tx_queue->tso_headers_free = tsoh;
-	}
-
-	return 0;
-}
-
-
-/* Free up a TSO header, and all others in the same page. */
-static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
-				struct efx_tso_header *tsoh,
-				struct device *dma_dev)
-{
-	struct efx_tso_header **p;
-	unsigned long base_kva;
-	dma_addr_t base_dma;
-
-	base_kva = (unsigned long)tsoh & PAGE_MASK;
-	base_dma = tsoh->dma_addr & PAGE_MASK;
-
-	p = &tx_queue->tso_headers_free;
-	while (*p != NULL) {
-		if (((unsigned long)*p & PAGE_MASK) == base_kva)
-			*p = (*p)->next;
-		else
-			p = &(*p)->next;
-	}
+	EFX_BUG_ON_PARANOID(buffer->len);
+	EFX_BUG_ON_PARANOID(buffer->flags);
+	EFX_BUG_ON_PARANOID(buffer->unmap_len);
 
-	dma_free_coherent(dma_dev, PAGE_SIZE, (void *)base_kva, base_dma);
-}
+	if (likely(len <= TSOH_STD_SIZE - TSOH_OFFSET)) {
+		unsigned index =
+			(tx_queue->insert_count & tx_queue->ptr_mask) / 2;
+		struct efx_buffer *page_buf =
+			&tx_queue->tsoh_page[index / TSOH_PER_PAGE];
+		unsigned offset =
+			TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + TSOH_OFFSET;
+
+		if (unlikely(!page_buf->addr) &&
+		    efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE))
+			return NULL;
+
+		result = (u8 *)page_buf->addr + offset;
+		buffer->dma_addr = page_buf->dma_addr + offset;
+		buffer->flags = EFX_TX_BUF_CONT;
+	} else {
+		tx_queue->tso_long_headers++;
 
-static struct efx_tso_header *
-efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
-{
-	struct efx_tso_header *tsoh;
-
-	tsoh = kmalloc(TSOH_SIZE(header_len), GFP_ATOMIC | GFP_DMA);
-	if (unlikely(!tsoh))
-		return NULL;
-
-	tsoh->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
-					TSOH_BUFFER(tsoh), header_len,
-					DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
-				       tsoh->dma_addr))) {
-		kfree(tsoh);
-		return NULL;
+		buffer->heap_buf = kmalloc(TSOH_OFFSET + len, GFP_ATOMIC);
+		if (unlikely(!buffer->heap_buf))
+			return NULL;
+		result = (u8 *)buffer->heap_buf + TSOH_OFFSET;
+		buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP;
 	}
 
-	tsoh->unmap_len = header_len;
-	return tsoh;
-}
+	buffer->len = len;
 
-static void
-efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
-{
-	dma_unmap_single(&tx_queue->efx->pci_dev->dev,
-			 tsoh->dma_addr, tsoh->unmap_len,
-			 DMA_TO_DEVICE);
-	kfree(tsoh);
+	return result;
 }
 
 /**
@@ -781,47 +736,19 @@ efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
  * @len:		Length of fragment
  * @final_buffer:	The final buffer inserted into the queue
  *
- * Push descriptors onto the TX queue.  Return 0 on success or 1 if
- * @tx_queue full.
+ * Push descriptors onto the TX queue.
  */
-static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
-			       dma_addr_t dma_addr, unsigned len,
-			       struct efx_tx_buffer **final_buffer)
+static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
+				dma_addr_t dma_addr, unsigned len,
+				struct efx_tx_buffer **final_buffer)
 {
 	struct efx_tx_buffer *buffer;
 	struct efx_nic *efx = tx_queue->efx;
-	unsigned dma_len, fill_level, insert_ptr;
-	int q_space;
+	unsigned dma_len, insert_ptr;
 
 	EFX_BUG_ON_PARANOID(len <= 0);
 
-	fill_level = tx_queue->insert_count - tx_queue->old_read_count;
-	/* -1 as there is no way to represent all descriptors used */
-	q_space = efx->txq_entries - 1 - fill_level;
-
 	while (1) {
-		if (unlikely(q_space-- <= 0)) {
-			/* It might be that completions have happened
-			 * since the xmit path last checked.  Update
-			 * the xmit path's copy of read_count.
-			 */
-			netif_tx_stop_queue(tx_queue->core_txq);
-			/* This memory barrier protects the change of
-			 * queue state from the access of read_count. */
-			smp_mb();
-			tx_queue->old_read_count =
-				ACCESS_ONCE(tx_queue->read_count);
-			fill_level = (tx_queue->insert_count
-				      - tx_queue->old_read_count);
-			q_space = efx->txq_entries - 1 - fill_level;
-			if (unlikely(q_space-- <= 0)) {
-				*final_buffer = NULL;
-				return 1;
-			}
-			smp_mb();
-			netif_tx_start_queue(tx_queue->core_txq);
-		}
-
 		insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
 		buffer = &tx_queue->buffer[insert_ptr];
 		++tx_queue->insert_count;
@@ -830,12 +757,9 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
 				    tx_queue->read_count >=
 				    efx->txq_entries);
 
-		efx_tsoh_free(tx_queue, buffer);
 		EFX_BUG_ON_PARANOID(buffer->len);
 		EFX_BUG_ON_PARANOID(buffer->unmap_len);
-		EFX_BUG_ON_PARANOID(buffer->skb);
-		EFX_BUG_ON_PARANOID(!buffer->continuation);
-		EFX_BUG_ON_PARANOID(buffer->tsoh);
+		EFX_BUG_ON_PARANOID(buffer->flags);
 
 		buffer->dma_addr = dma_addr;
 
@@ -845,7 +769,8 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
 		if (dma_len >= len)
 			break;
 
-		buffer->len = dma_len; /* Don't set the other members */
+		buffer->len = dma_len;
+		buffer->flags = EFX_TX_BUF_CONT;
 		dma_addr += dma_len;
 		len -= dma_len;
 	}
@@ -853,7 +778,6 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
 	EFX_BUG_ON_PARANOID(!len);
 	buffer->len = len;
 	*final_buffer = buffer;
-	return 0;
 }
 
 
@@ -864,54 +788,42 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
  * a single fragment, and we know it doesn't cross a page boundary.  It
  * also allows us to not worry about end-of-packet etc.
  */
-static void efx_tso_put_header(struct efx_tx_queue *tx_queue,
-			       struct efx_tso_header *tsoh, unsigned len)
+static int efx_tso_put_header(struct efx_tx_queue *tx_queue,
+			      struct efx_tx_buffer *buffer, u8 *header)
 {
-	struct efx_tx_buffer *buffer;
-
-	buffer = &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask];
-	efx_tsoh_free(tx_queue, buffer);
-	EFX_BUG_ON_PARANOID(buffer->len);
-	EFX_BUG_ON_PARANOID(buffer->unmap_len);
-	EFX_BUG_ON_PARANOID(buffer->skb);
-	EFX_BUG_ON_PARANOID(!buffer->continuation);
-	EFX_BUG_ON_PARANOID(buffer->tsoh);
-	buffer->len = len;
-	buffer->dma_addr = tsoh->dma_addr;
-	buffer->tsoh = tsoh;
+	if (unlikely(buffer->flags & EFX_TX_BUF_HEAP)) {
+		buffer->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
+						  header, buffer->len,
+						  DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
+					       buffer->dma_addr))) {
+			kfree(buffer->heap_buf);
+			buffer->len = 0;
+			buffer->flags = 0;
+			return -ENOMEM;
+		}
+		buffer->unmap_len = buffer->len;
+		buffer->flags |= EFX_TX_BUF_MAP_SINGLE;
+	}
 
 	++tx_queue->insert_count;
+	return 0;
 }
 
 
-/* Remove descriptors put into a tx_queue. */
+/* Remove buffers put into a tx_queue.  None of the buffers must have
+ * an skb attached.
+ */
 static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
 {
 	struct efx_tx_buffer *buffer;
-	dma_addr_t unmap_addr;
 
 	/* Work backwards until we hit the original insert pointer value */
 	while (tx_queue->insert_count != tx_queue->write_count) {
 		--tx_queue->insert_count;
 		buffer = &tx_queue->buffer[tx_queue->insert_count &
 					   tx_queue->ptr_mask];
-		efx_tsoh_free(tx_queue, buffer);
-		EFX_BUG_ON_PARANOID(buffer->skb);
-		if (buffer->unmap_len) {
-			unmap_addr = (buffer->dma_addr + buffer->len -
-				      buffer->unmap_len);
-			if (buffer->unmap_single)
-				dma_unmap_single(&tx_queue->efx->pci_dev->dev,
-						 unmap_addr, buffer->unmap_len,
-						 DMA_TO_DEVICE);
-			else
-				dma_unmap_page(&tx_queue->efx->pci_dev->dev,
-					       unmap_addr, buffer->unmap_len,
-					       DMA_TO_DEVICE);
-			buffer->unmap_len = 0;
-		}
-		buffer->len = 0;
-		buffer->continuation = true;
+		efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
 	}
 }
 
@@ -919,17 +831,16 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
 /* Parse the SKB header and initialise state. */
 static void tso_start(struct tso_state *st, const struct sk_buff *skb)
 {
-	/* All ethernet/IP/TCP headers combined size is TCP header size
-	 * plus offset of TCP header relative to start of packet.
-	 */
-	st->header_len = ((tcp_hdr(skb)->doff << 2u)
-			  + PTR_DIFF(tcp_hdr(skb), skb->data));
-	st->full_packet_size = st->header_len + skb_shinfo(skb)->gso_size;
-
-	if (st->protocol == htons(ETH_P_IP))
+	st->ip_off = skb_network_header(skb) - skb->data;
+	st->tcp_off = skb_transport_header(skb) - skb->data;
+	st->header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
+	if (st->protocol == htons(ETH_P_IP)) {
+		st->ip_base_len = st->header_len - st->ip_off;
 		st->ipv4_id = ntohs(ip_hdr(skb)->id);
-	else
+	} else {
+		st->ip_base_len = st->header_len - st->tcp_off;
 		st->ipv4_id = 0;
+	}
 	st->seqnum = ntohl(tcp_hdr(skb)->seq);
 
 	EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg);
@@ -938,7 +849,7 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb)
 
 	st->out_len = skb->len - st->header_len;
 	st->unmap_len = 0;
-	st->unmap_single = false;
+	st->dma_flags = 0;
 }
 
 static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
@@ -947,7 +858,7 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
 	st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0,
 					  skb_frag_size(frag), DMA_TO_DEVICE);
 	if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
-		st->unmap_single = false;
+		st->dma_flags = 0;
 		st->unmap_len = skb_frag_size(frag);
 		st->in_len = skb_frag_size(frag);
 		st->dma_addr = st->unmap_addr;
@@ -965,7 +876,7 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
 	st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl,
 					len, DMA_TO_DEVICE);
 	if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
-		st->unmap_single = true;
+		st->dma_flags = EFX_TX_BUF_MAP_SINGLE;
 		st->unmap_len = len;
 		st->in_len = len;
 		st->dma_addr = st->unmap_addr;
@@ -982,20 +893,19 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
  * @st:			TSO state
  *
  * Form descriptors for the current fragment, until we reach the end
- * of fragment or end-of-packet.  Return 0 on success, 1 if not enough
- * space in @tx_queue.
+ * of fragment or end-of-packet.
  */
-static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
-					 const struct sk_buff *skb,
-					 struct tso_state *st)
+static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
+					  const struct sk_buff *skb,
+					  struct tso_state *st)
 {
 	struct efx_tx_buffer *buffer;
-	int n, end_of_packet, rc;
+	int n;
 
 	if (st->in_len == 0)
-		return 0;
+		return;
 	if (st->packet_space == 0)
-		return 0;
+		return;
 
 	EFX_BUG_ON_PARANOID(st->in_len <= 0);
 	EFX_BUG_ON_PARANOID(st->packet_space <= 0);
@@ -1006,25 +916,24 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
 	st->out_len -= n;
 	st->in_len -= n;
 
-	rc = efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
-	if (likely(rc == 0)) {
-		if (st->out_len == 0)
-			/* Transfer ownership of the skb */
-			buffer->skb = skb;
+	efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
 
-		end_of_packet = st->out_len == 0 || st->packet_space == 0;
-		buffer->continuation = !end_of_packet;
+	if (st->out_len == 0) {
+		/* Transfer ownership of the skb */
+		buffer->skb = skb;
+		buffer->flags = EFX_TX_BUF_SKB;
+	} else if (st->packet_space != 0) {
+		buffer->flags = EFX_TX_BUF_CONT;
+	}
 
-		if (st->in_len == 0) {
-			/* Transfer ownership of the DMA mapping */
-			buffer->unmap_len = st->unmap_len;
-			buffer->unmap_single = st->unmap_single;
-			st->unmap_len = 0;
-		}
+	if (st->in_len == 0) {
+		/* Transfer ownership of the DMA mapping */
+		buffer->unmap_len = st->unmap_len;
+		buffer->flags |= st->dma_flags;
+		st->unmap_len = 0;
 	}
 
 	st->dma_addr += n;
-	return rc;
 }
 
 
@@ -1035,36 +944,25 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
  * @st:			TSO state
  *
  * Generate a new header and prepare for the new packet.  Return 0 on
- * success, or -1 if failed to alloc header.
+ * success, or -%ENOMEM if failed to alloc header.
  */
 static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
 				const struct sk_buff *skb,
 				struct tso_state *st)
 {
-	struct efx_tso_header *tsoh;
+	struct efx_tx_buffer *buffer =
+		&tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask];
 	struct tcphdr *tsoh_th;
 	unsigned ip_length;
 	u8 *header;
+	int rc;
 
-	/* Allocate a DMA-mapped header buffer. */
-	if (likely(TSOH_SIZE(st->header_len) <= TSOH_STD_SIZE)) {
-		if (tx_queue->tso_headers_free == NULL) {
-			if (efx_tsoh_block_alloc(tx_queue))
-				return -1;
-		}
-		EFX_BUG_ON_PARANOID(!tx_queue->tso_headers_free);
-		tsoh = tx_queue->tso_headers_free;
-		tx_queue->tso_headers_free = tsoh->next;
-		tsoh->unmap_len = 0;
-	} else {
-		tx_queue->tso_long_headers++;
-		tsoh = efx_tsoh_heap_alloc(tx_queue, st->header_len);
-		if (unlikely(!tsoh))
-			return -1;
-	}
+	/* Allocate and insert a DMA-mapped header buffer. */
+	header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len);
+	if (!header)
+		return -ENOMEM;
 
-	header = TSOH_BUFFER(tsoh);
-	tsoh_th = (struct tcphdr *)(header + SKB_TCP_OFF(skb));
+	tsoh_th = (struct tcphdr *)(header + st->tcp_off);
 
 	/* Copy and update the headers. */
 	memcpy(header, skb->data, st->header_len);
@@ -1073,19 +971,19 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
 	st->seqnum += skb_shinfo(skb)->gso_size;
 	if (st->out_len > skb_shinfo(skb)->gso_size) {
 		/* This packet will not finish the TSO burst. */
-		ip_length = st->full_packet_size - ETH_HDR_LEN(skb);
+		st->packet_space = skb_shinfo(skb)->gso_size;
 		tsoh_th->fin = 0;
 		tsoh_th->psh = 0;
 	} else {
 		/* This packet will be the last in the TSO burst. */
-		ip_length = st->header_len - ETH_HDR_LEN(skb) + st->out_len;
+		st->packet_space = st->out_len;
 		tsoh_th->fin = tcp_hdr(skb)->fin;
 		tsoh_th->psh = tcp_hdr(skb)->psh;
 	}
+	ip_length = st->ip_base_len + st->packet_space;
 
 	if (st->protocol == htons(ETH_P_IP)) {
-		struct iphdr *tsoh_iph =
-			(struct iphdr *)(header + SKB_IPV4_OFF(skb));
+		struct iphdr *tsoh_iph = (struct iphdr *)(header + st->ip_off);
 
 		tsoh_iph->tot_len = htons(ip_length);
 
@@ -1094,16 +992,16 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
 		st->ipv4_id++;
 	} else {
 		struct ipv6hdr *tsoh_iph =
-			(struct ipv6hdr *)(header + SKB_IPV6_OFF(skb));
+			(struct ipv6hdr *)(header + st->ip_off);
 
-		tsoh_iph->payload_len = htons(ip_length - sizeof(*tsoh_iph));
+		tsoh_iph->payload_len = htons(ip_length);
 	}
 
-	st->packet_space = skb_shinfo(skb)->gso_size;
-	++tx_queue->tso_packets;
+	rc = efx_tso_put_header(tx_queue, buffer, header);
+	if (unlikely(rc))
+		return rc;
 
-	/* Form a descriptor for this header. */
-	efx_tso_put_header(tx_queue, tsoh, st->header_len);
+	++tx_queue->tso_packets;
 
 	return 0;
 }
@@ -1118,13 +1016,13 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
  *
  * Add socket buffer @skb to @tx_queue, doing TSO or return != 0 if
  * @skb was not enqueued.  In all cases @skb is consumed.  Return
- * %NETDEV_TX_OK or %NETDEV_TX_BUSY.
+ * %NETDEV_TX_OK.
  */
 static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 			       struct sk_buff *skb)
 {
 	struct efx_nic *efx = tx_queue->efx;
-	int frag_i, rc, rc2 = NETDEV_TX_OK;
+	int frag_i, rc;
 	struct tso_state state;
 
 	/* Find the packet protocol and sanity-check it */
@@ -1156,11 +1054,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 		goto mem_err;
 
 	while (1) {
-		rc = tso_fill_packet_with_fragment(tx_queue, skb, &state);
-		if (unlikely(rc)) {
-			rc2 = NETDEV_TX_BUSY;
-			goto unwind;
-		}
+		tso_fill_packet_with_fragment(tx_queue, skb, &state);
 
 		/* Move onto the next fragment? */
 		if (state.in_len == 0) {
@@ -1184,6 +1078,8 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	/* Pass off to hardware */
 	efx_nic_push_buffers(tx_queue);
 
+	efx_tx_maybe_stop_queue(tx_queue);
+
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
 
@@ -1192,10 +1088,9 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 		  "Out of memory for TSO headers, or DMA mapping error\n");
 	dev_kfree_skb_any(skb);
 
- unwind:
 	/* Free the DMA mapping we were in the process of writing out */
 	if (state.unmap_len) {
-		if (state.unmap_single)
+		if (state.dma_flags & EFX_TX_BUF_MAP_SINGLE)
 			dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr,
 					 state.unmap_len, DMA_TO_DEVICE);
 		else
@@ -1204,25 +1099,5 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	}
 
 	efx_enqueue_unwind(tx_queue);
-	return rc2;
-}
-
-
-/*
- * Free up all TSO datastructures associated with tx_queue. This
- * routine should be called only once the tx_queue is both empty and
- * will no longer be used.
- */
-static void efx_fini_tso(struct efx_tx_queue *tx_queue)
-{
-	unsigned i;
-
-	if (tx_queue->buffer) {
-		for (i = 0; i <= tx_queue->ptr_mask; ++i)
-			efx_tsoh_free(tx_queue, &tx_queue->buffer[i]);
-	}
-
-	while (tx_queue->tso_headers_free != NULL)
-		efx_tsoh_block_free(tx_queue, tx_queue->tso_headers_free,
-				    &tx_queue->efx->pci_dev->dev);
+	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index ade108232048..0376a5e6b2bf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -177,7 +177,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 	new_bus->write = &stmmac_mdio_write;
 	new_bus->reset = &stmmac_mdio_reset;
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x",
-		new_bus->name, mdio_bus_data->bus_id);
+		new_bus->name, priv->plat->bus_id);
 	new_bus->priv = ndev;
 	new_bus->irq = irqlist;
 	new_bus->phy_mask = mdio_bus_data->phy_mask;
@@ -213,12 +213,10 @@ int stmmac_mdio_register(struct net_device *ndev)
 			 * and no PHY number was provided to the MAC,
 			 * use the one probed here.
 			 */
-			if ((priv->plat->bus_id == mdio_bus_data->bus_id) &&
-			    (priv->plat->phy_addr == -1))
+			if (priv->plat->phy_addr == -1)
 				priv->plat->phy_addr = addr;
 
-			act = (priv->plat->bus_id == mdio_bus_data->bus_id) &&
-				(priv->plat->phy_addr == addr);
+			act = (priv->plat->phy_addr == addr);
 			switch (phydev->irq) {
 			case PHY_POLL:
 				irq_str = "POLL";
@@ -258,6 +256,9 @@ int stmmac_mdio_unregister(struct net_device *ndev)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
 
+	if (!priv->mii)
+		return 0;
+
 	mdiobus_unregister(priv->mii);
 	priv->mii->priv = NULL;
 	mdiobus_free(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 13afb8edfadc..1f069b0f6af5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -40,7 +40,6 @@ static void stmmac_default_data(void)
 	plat_dat.has_gmac = 1;
 	plat_dat.force_sf_dma_mode = 1;
 
-	mdio_data.bus_id = 1;
 	mdio_data.phy_reset = NULL;
 	mdio_data.phy_mask = 0;
 	plat_dat.mdio_bus_data = &mdio_data;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index b93245c11995..ed112b55ae7f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -78,6 +78,7 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 {
 	int ret = 0;
 	struct resource *res;
+	struct device *dev = &pdev->dev;
 	void __iomem *addr = NULL;
 	struct stmmac_priv *priv = NULL;
 	struct plat_stmmacenet_data *plat_dat = NULL;
@@ -87,18 +88,10 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 	if (!res)
 		return -ENODEV;
 
-	if (!request_mem_region(res->start, resource_size(res), pdev->name)) {
-		pr_err("%s: ERROR: memory allocation failed"
-		       "cannot get the I/O addr 0x%x\n",
-		       __func__, (unsigned int)res->start);
-		return -EBUSY;
-	}
-
-	addr = ioremap(res->start, resource_size(res));
+	addr = devm_request_and_ioremap(dev, res);
 	if (!addr) {
 		pr_err("%s: ERROR: memory mapping failed", __func__);
-		ret = -ENOMEM;
-		goto out_release_region;
+		return -ENOMEM;
 	}
 
 	if (pdev->dev.of_node) {
@@ -107,14 +100,13 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 					GFP_KERNEL);
 		if (!plat_dat) {
 			pr_err("%s: ERROR: no memory", __func__);
-			ret = -ENOMEM;
-			goto out_unmap;
+			return  -ENOMEM;
 		}
 
 		ret = stmmac_probe_config_dt(pdev, plat_dat, &mac);
 		if (ret) {
 			pr_err("%s: main dt probe failed", __func__);
-			goto out_unmap;
+			return ret;
 		}
 	} else {
 		plat_dat = pdev->dev.platform_data;
@@ -124,13 +116,13 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 	if (plat_dat->init) {
 		ret = plat_dat->init(pdev);
 		if (unlikely(ret))
-			goto out_unmap;
+			return ret;
 	}
 
 	priv = stmmac_dvr_probe(&(pdev->dev), plat_dat, addr);
 	if (!priv) {
 		pr_err("%s: main driver probe failed", __func__);
-		goto out_unmap;
+		return -ENODEV;
 	}
 
 	/* Get MAC address if available (DT) */
@@ -142,8 +134,7 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 	if (priv->dev->irq == -ENXIO) {
 		pr_err("%s: ERROR: MAC IRQ configuration "
 		       "information not found\n", __func__);
-		ret = -ENXIO;
-		goto out_unmap;
+		return -ENXIO;
 	}
 
 	/*
@@ -165,15 +156,6 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev)
 	pr_debug("STMMAC platform driver registration completed");
 
 	return 0;
-
-out_unmap:
-	iounmap(addr);
-	platform_set_drvdata(pdev, NULL);
-
-out_release_region:
-	release_mem_region(res->start, resource_size(res));
-
-	return ret;
 }
 
 /**
@@ -186,7 +168,6 @@ static int stmmac_pltfr_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct resource *res;
 	int ret = stmmac_dvr_remove(ndev);
 
 	if (priv->plat->exit)
@@ -194,10 +175,6 @@ static int stmmac_pltfr_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	iounmap((void __force __iomem *)priv->ioaddr);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
-
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 967fe8cb476e..c9c977bf02ac 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -212,7 +212,6 @@ static void bigmac_clean_rings(struct bigmac *bp)
 static void bigmac_init_rings(struct bigmac *bp, int from_irq)
 {
 	struct bmac_init_block *bb = bp->bmac_block;
-	struct net_device *dev = bp->dev;
 	int i;
 	gfp_t gfp_flags = GFP_KERNEL;
 
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 1b173a6145d6..b26cbda5efa9 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -32,7 +32,7 @@ config TI_DAVINCI_EMAC
 
 config TI_DAVINCI_MDIO
 	tristate "TI DaVinci MDIO Support"
-	depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 )
+	depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 || SOC_AM33XX )
 	select PHYLIB
 	---help---
 	  This driver supports TI's DaVinci MDIO module.
@@ -42,7 +42,7 @@ config TI_DAVINCI_MDIO
 
 config TI_DAVINCI_CPDMA
 	tristate "TI DaVinci CPDMA Support"
-	depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 )
+	depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 || SOC_AM33XX )
 	---help---
 	  This driver supports TI's DaVinci CPDMA dma engine.
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 1e5d85b06e71..df55e2403746 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -28,6 +28,9 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_device.h>
 
 #include <linux/platform_data/cpsw.h>
 
@@ -383,6 +386,11 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 			mac_control |= BIT(7);	/* GIGABITEN	*/
 		if (phy->duplex)
 			mac_control |= BIT(0);	/* FULLDUPLEXEN	*/
+
+		/* set speed_in input in case RMII mode is used in 100Mbps */
+		if (phy->speed == 100)
+			mac_control |= BIT(15);
+
 		*link = true;
 	} else {
 		mac_control = 0;
@@ -709,6 +717,158 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	slave->sliver	= regs + data->sliver_reg_ofs;
 }
 
+static int cpsw_probe_dt(struct cpsw_platform_data *data,
+			 struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *slave_node;
+	int i = 0, ret;
+	u32 prop;
+
+	if (!node)
+		return -EINVAL;
+
+	if (of_property_read_u32(node, "slaves", &prop)) {
+		pr_err("Missing slaves property in the DT.\n");
+		return -EINVAL;
+	}
+	data->slaves = prop;
+
+	data->slave_data = kzalloc(sizeof(struct cpsw_slave_data) *
+				   data->slaves, GFP_KERNEL);
+	if (!data->slave_data) {
+		pr_err("Could not allocate slave memory.\n");
+		return -EINVAL;
+	}
+
+	data->no_bd_ram = of_property_read_bool(node, "no_bd_ram");
+
+	if (of_property_read_u32(node, "cpdma_channels", &prop)) {
+		pr_err("Missing cpdma_channels property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->channels = prop;
+
+	if (of_property_read_u32(node, "host_port_no", &prop)) {
+		pr_err("Missing host_port_no property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->host_port_num = prop;
+
+	if (of_property_read_u32(node, "cpdma_reg_ofs", &prop)) {
+		pr_err("Missing cpdma_reg_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpdma_reg_ofs = prop;
+
+	if (of_property_read_u32(node, "cpdma_sram_ofs", &prop)) {
+		pr_err("Missing cpdma_sram_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpdma_sram_ofs = prop;
+
+	if (of_property_read_u32(node, "ale_reg_ofs", &prop)) {
+		pr_err("Missing ale_reg_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->ale_reg_ofs = prop;
+
+	if (of_property_read_u32(node, "ale_entries", &prop)) {
+		pr_err("Missing ale_entries property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->ale_entries = prop;
+
+	if (of_property_read_u32(node, "host_port_reg_ofs", &prop)) {
+		pr_err("Missing host_port_reg_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->host_port_reg_ofs = prop;
+
+	if (of_property_read_u32(node, "hw_stats_reg_ofs", &prop)) {
+		pr_err("Missing hw_stats_reg_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->hw_stats_reg_ofs = prop;
+
+	if (of_property_read_u32(node, "bd_ram_ofs", &prop)) {
+		pr_err("Missing bd_ram_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->bd_ram_ofs = prop;
+
+	if (of_property_read_u32(node, "bd_ram_size", &prop)) {
+		pr_err("Missing bd_ram_size property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->bd_ram_size = prop;
+
+	if (of_property_read_u32(node, "rx_descs", &prop)) {
+		pr_err("Missing rx_descs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->rx_descs = prop;
+
+	if (of_property_read_u32(node, "mac_control", &prop)) {
+		pr_err("Missing mac_control property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->mac_control = prop;
+
+	for_each_child_of_node(node, slave_node) {
+		struct cpsw_slave_data *slave_data = data->slave_data + i;
+		const char *phy_id = NULL;
+		const void *mac_addr = NULL;
+
+		if (of_property_read_string(slave_node, "phy_id", &phy_id)) {
+			pr_err("Missing slave[%d] phy_id property\n", i);
+			ret = -EINVAL;
+			goto error_ret;
+		}
+		slave_data->phy_id = phy_id;
+
+		if (of_property_read_u32(slave_node, "slave_reg_ofs", &prop)) {
+			pr_err("Missing slave[%d] slave_reg_ofs property\n", i);
+			ret = -EINVAL;
+			goto error_ret;
+		}
+		slave_data->slave_reg_ofs = prop;
+
+		if (of_property_read_u32(slave_node, "sliver_reg_ofs",
+					 &prop)) {
+			pr_err("Missing slave[%d] sliver_reg_ofs property\n",
+				i);
+			ret = -EINVAL;
+			goto error_ret;
+		}
+		slave_data->sliver_reg_ofs = prop;
+
+		mac_addr = of_get_mac_address(slave_node);
+		if (mac_addr)
+			memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);
+
+		i++;
+	}
+
+	return 0;
+
+error_ret:
+	kfree(data->slave_data);
+	return ret;
+}
+
 static int __devinit cpsw_probe(struct platform_device *pdev)
 {
 	struct cpsw_platform_data	*data = pdev->dev.platform_data;
@@ -720,11 +880,6 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 	struct resource			*res;
 	int ret = 0, i, k = 0;
 
-	if (!data) {
-		pr_err("platform data missing\n");
-		return -ENODEV;
-	}
-
 	ndev = alloc_etherdev(sizeof(struct cpsw_priv));
 	if (!ndev) {
 		pr_err("error allocating net_device\n");
@@ -734,13 +889,19 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ndev);
 	priv = netdev_priv(ndev);
 	spin_lock_init(&priv->lock);
-	priv->data = *data;
 	priv->pdev = pdev;
 	priv->ndev = ndev;
 	priv->dev  = &ndev->dev;
 	priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG);
 	priv->rx_packet_max = max(rx_packet_max, 128);
 
+	if (cpsw_probe_dt(&priv->data, pdev)) {
+		pr_err("cpsw: platform data missing\n");
+		ret = -ENODEV;
+		goto clean_ndev_ret;
+	}
+	data = &priv->data;
+
 	if (is_valid_ether_addr(data->slave_data[0].mac_addr)) {
 		memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN);
 		pr_info("Detected MACID = %pM", priv->mac_addr);
@@ -996,11 +1157,17 @@ static const struct dev_pm_ops cpsw_pm_ops = {
 	.resume		= cpsw_resume,
 };
 
+static const struct of_device_id cpsw_of_mtable[] = {
+	{ .compatible = "ti,cpsw", },
+	{ /* sentinel */ },
+};
+
 static struct platform_driver cpsw_driver = {
 	.driver = {
 		.name	 = "cpsw",
 		.owner	 = THIS_MODULE,
 		.pm	 = &cpsw_pm_ops,
+		.of_match_table = of_match_ptr(cpsw_of_mtable),
 	},
 	.probe = cpsw_probe,
 	.remove = __devexit_p(cpsw_remove),
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index a9ca4a03d31b..51a96dbee9ac 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -36,6 +36,8 @@
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
 #include <linux/davinci_emac.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 /*
  * This timeout definition is a worst-case ultra defensive measure against
@@ -289,6 +291,25 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id,
 	return 0;
 }
 
+static int davinci_mdio_probe_dt(struct mdio_platform_data *data,
+			 struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	u32 prop;
+
+	if (!node)
+		return -EINVAL;
+
+	if (of_property_read_u32(node, "bus_freq", &prop)) {
+		pr_err("Missing bus_freq property in the DT.\n");
+		return -EINVAL;
+	}
+	data->bus_freq = prop;
+
+	return 0;
+}
+
+
 static int __devinit davinci_mdio_probe(struct platform_device *pdev)
 {
 	struct mdio_platform_data *pdata = pdev->dev.platform_data;
@@ -304,8 +325,6 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	data->pdata = pdata ? (*pdata) : default_pdata;
-
 	data->bus = mdiobus_alloc();
 	if (!data->bus) {
 		dev_err(dev, "failed to alloc mii bus\n");
@@ -313,14 +332,22 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev)
 		goto bail_out;
 	}
 
+	if (dev->of_node) {
+		if (davinci_mdio_probe_dt(&data->pdata, pdev))
+			data->pdata = default_pdata;
+		snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s", pdev->name);
+	} else {
+		data->pdata = pdata ? (*pdata) : default_pdata;
+		snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x",
+			 pdev->name, pdev->id);
+	}
+
 	data->bus->name		= dev_name(dev);
 	data->bus->read		= davinci_mdio_read,
 	data->bus->write	= davinci_mdio_write,
 	data->bus->reset	= davinci_mdio_reset,
 	data->bus->parent	= dev;
 	data->bus->priv		= data;
-	snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x",
-		pdev->name, pdev->id);
 
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
@@ -456,11 +483,17 @@ static const struct dev_pm_ops davinci_mdio_pm_ops = {
 	.resume		= davinci_mdio_resume,
 };
 
+static const struct of_device_id davinci_mdio_of_mtable[] = {
+	{ .compatible = "ti,davinci_mdio", },
+	{ /* sentinel */ },
+};
+
 static struct platform_driver davinci_mdio_driver = {
 	.driver = {
 		.name	 = "davinci_mdio",
 		.owner	 = THIS_MODULE,
 		.pm	 = &davinci_mdio_pm_ops,
+		.of_match_table = of_match_ptr(davinci_mdio_of_mtable),
 	},
 	.probe = davinci_mdio_probe,
 	.remove = __devexit_p(davinci_mdio_remove),
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index 277c93e9ff4d..8fa947a2d929 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1359,7 +1359,6 @@ static int tsi108_open(struct net_device *dev)
 		}
 
 		data->rxskbs[i] = skb;
-		data->rxskbs[i] = skb;
 		data->rxring[i].buf0 = virt_to_phys(data->rxskbs[i]->data);
 		data->rxring[i].misc = TSI108_RX_OWN | TSI108_RX_INT;
 	}
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index a5826a3111a6..2c08bf6e7bf3 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -637,8 +637,7 @@ static int __devinit w5100_hw_probe(struct platform_device *pdev)
 	if (data && is_valid_ether_addr(data->mac_addr)) {
 		memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN);
 	} else {
-		eth_random_addr(ndev->dev_addr);
-		ndev->addr_assign_type |= NET_ADDR_RANDOM;
+		eth_hw_addr_random(ndev);
 	}
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index bdd8891c215a..88943d90c765 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -557,8 +557,7 @@ static int __devinit w5300_hw_probe(struct platform_device *pdev)
 	if (data && is_valid_ether_addr(data->mac_addr)) {
 		memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN);
 	} else {
-		eth_random_addr(ndev->dev_addr);
-		ndev->addr_assign_type |= NET_ADDR_RANDOM;
+		eth_hw_addr_random(ndev);
 	}
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
author	Linus Torvalds <torvalds@linux-foundation.org>	2012-10-03 00:38:27 +0400
committer	Linus Torvalds <torvalds@linux-foundation.org>	2012-10-03 00:38:27 +0400
commit	aecdc33e111b2c447b622e287c6003726daa1426 (patch)
tree	3e7657eae4b785e1a1fb5dfb225dbae0b2f0cfc6 /drivers/net/ethernet
parent	a20acf99f75e49271381d65db097c9763060a1e8 (diff)
parent	a3a6cab5ea10cca64d036851fe0d932448f2fe4f (diff)
download	linux-aecdc33e111b2c447b622e287c6003726daa1426.tar.xz