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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

18 files changed, 2074 insertions, 1073 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 68f2204..2f6210a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -64,9 +64,6 @@
 #include "i40e_dcb.h"
 
 /* Useful i40e defaults */
-#define I40E_BASE_PF_SEID     16
-#define I40E_BASE_VSI_SEID    512
-#define I40E_BASE_VEB_SEID    288
 #define I40E_MAX_VEB          16
 
 #define I40E_MAX_NUM_DESCRIPTORS      4096
@@ -104,6 +101,7 @@
 #define I40E_PRIV_FLAGS_FD_ATR		BIT(2)
 #define I40E_PRIV_FLAGS_VEB_STATS	BIT(3)
 #define I40E_PRIV_FLAGS_PS		BIT(4)
+#define I40E_PRIV_FLAGS_HW_ATR_EVICT	BIT(5)
 
 #define I40E_NVM_VERSION_LO_SHIFT  0
 #define I40E_NVM_VERSION_LO_MASK   (0xff << I40E_NVM_VERSION_LO_SHIFT)
@@ -113,6 +111,7 @@
 #define I40E_OEM_VER_PATCH_MASK    0xff
 #define I40E_OEM_VER_BUILD_SHIFT   8
 #define I40E_OEM_VER_SHIFT         24
+#define I40E_PHY_DEBUG_PORT        BIT(4)
 
 /* The values in here are decimal coded as hex as is the case in the NVM map*/
 #define I40E_CURRENT_NVM_VERSION_HI 0x2
@@ -137,6 +136,19 @@
 /* default to trying for four seconds */
 #define I40E_TRY_LINK_TIMEOUT (4 * HZ)
 
+/**
+ * i40e_is_mac_710 - Return true if MAC is X710/XL710
+ * @hw: ptr to the hardware info
+ **/
+static inline bool i40e_is_mac_710(struct i40e_hw *hw)
+{
+	if ((hw->mac.type == I40E_MAC_X710) ||
+	    (hw->mac.type == I40E_MAC_XL710))
+		return true;
+
+	return false;
+}
+
 /* driver state flags */
 enum i40e_state_t {
 	__I40E_TESTING,
@@ -339,6 +351,12 @@ struct i40e_pf {
 #define I40E_FLAG_VEB_MODE_ENABLED		BIT_ULL(40)
 #define I40E_FLAG_GENEVE_OFFLOAD_CAPABLE	BIT_ULL(41)
 #define I40E_FLAG_NO_PCI_LINK_CHECK		BIT_ULL(42)
+#define I40E_FLAG_100M_SGMII_CAPABLE		BIT_ULL(43)
+#define I40E_FLAG_RESTART_AUTONEG		BIT_ULL(44)
+#define I40E_FLAG_NO_DCB_SUPPORT		BIT_ULL(45)
+#define I40E_FLAG_USE_SET_LLDP_MIB		BIT_ULL(46)
+#define I40E_FLAG_STOP_FW_LLDP			BIT_ULL(47)
+#define I40E_FLAG_HAVE_10GBASET_PHY		BIT_ULL(48)
 #define I40E_FLAG_PF_MAC			BIT_ULL(50)
 
 	/* tracks features that get auto disabled by errors */
@@ -391,6 +409,7 @@ struct i40e_pf {
 	struct i40e_vf *vf;
 	int num_alloc_vfs;	/* actual number of VFs allocated */
 	u32 vf_aq_requests;
+	u32 arq_overflows;	/* Not fatal, possibly indicative of problems */
 
 	/* DCBx/DCBNL capability for PF that indicates
 	 * whether DCBx is managed by firmware or host
@@ -423,6 +442,7 @@ struct i40e_pf {
 
 	u32 ioremap_len;
 	u32 fd_inv;
+	u16 phy_led_val;
 };
 
 struct i40e_mac_filter {
@@ -492,6 +512,7 @@ struct i40e_vsi {
 	u32 tx_busy;
 	u64 tx_linearize;
 	u64 tx_force_wb;
+	u64 tx_lost_interrupt;
 	u32 rx_buf_failed;
 	u32 rx_page_failed;
 
@@ -500,13 +521,6 @@ struct i40e_vsi {
 	struct i40e_ring **tx_rings;
 
 	u16 work_limit;
-	/* high bit set means dynamic, use accessor routines to read/write.
-	 * hardware only supports 2us resolution for the ITR registers.
-	 * these values always store the USER setting, and must be converted
-	 * before programming to a register.
-	 */
-	u16 rx_itr_setting;
-	u16 tx_itr_setting;
 	u16 int_rate_limit;  /* value in usecs */
 
 	u16 rss_table_size; /* HW RSS table size */
@@ -747,6 +761,9 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
+	/* definitely clear the PBA here, as this function is meant to
+	 * clean out all previous interrupts AND enable the interrupt
+	 */
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
@@ -754,9 +771,8 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 	/* skip the flush */
 }
 
-void i40e_irq_dynamic_disable(struct i40e_vsi *vsi, int vector);
 void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf);
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
 #ifdef I40E_FCOE
 struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
 					     struct net_device *netdev,
@@ -786,7 +802,8 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
 				      bool is_vf, bool is_netdev);
 #ifdef I40E_FCOE
 int i40e_close(struct net_device *netdev);
-int i40e_setup_tc(struct net_device *netdev, u8 tc);
+int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
+		    struct tc_to_netdev *tc);
 void i40e_netpoll(struct net_device *netdev);
 int i40e_fcoe_enable(struct net_device *netdev);
 int i40e_fcoe_disable(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 1fd5ea8..df8e2fd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -953,6 +953,9 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 	u16 flags;
 	u16 ntu;
 
+	/* pre-clean the event info */
+	memset(&e->desc, 0, sizeof(e->desc));
+
 	/* take the lock before we start messing with the ring */
 	mutex_lock(&hw->aq.arq_mutex);
 
@@ -1020,14 +1023,6 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 	hw->aq.arq.next_to_clean = ntc;
 	hw->aq.arq.next_to_use = ntu;
 
-clean_arq_element_out:
-	/* Set pending if needed, unlock and return */
-	if (pending != NULL)
-		*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
-
-clean_arq_element_err:
-	mutex_unlock(&hw->aq.arq_mutex);
-
 	if (i40e_is_nvm_update_op(&e->desc)) {
 		if (hw->aq.nvm_release_on_done) {
 			i40e_release_nvm(hw);
@@ -1048,6 +1043,13 @@ clean_arq_element_err:
 		}
 	}
 
+clean_arq_element_out:
+	/* Set pending if needed, unlock and return */
+	if (pending)
+		*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+clean_arq_element_err:
+	mutex_unlock(&hw->aq.arq_mutex);
+
 	return ret_code;
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index b22012a..8d5c65a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -34,7 +34,7 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR	0x0004
+#define I40E_FW_API_VERSION_MINOR	0x0005
 
 struct i40e_aq_desc {
 	__le16 flags;
@@ -145,6 +145,9 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_statistics		= 0x0202,
 	i40e_aqc_opc_set_port_parameters	= 0x0203,
 	i40e_aqc_opc_get_switch_resource_alloc	= 0x0204,
+	i40e_aqc_opc_set_switch_config		= 0x0205,
+	i40e_aqc_opc_rx_ctl_reg_read		= 0x0206,
+	i40e_aqc_opc_rx_ctl_reg_write		= 0x0207,
 
 	i40e_aqc_opc_add_vsi			= 0x0210,
 	i40e_aqc_opc_update_vsi_parameters	= 0x0211,
@@ -220,6 +223,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_phy_wol_caps		= 0x0621,
 	i40e_aqc_opc_set_phy_debug		= 0x0622,
 	i40e_aqc_opc_upload_ext_phy_fm		= 0x0625,
+	i40e_aqc_opc_run_phy_activity		= 0x0626,
 
 	/* NVM commands */
 	i40e_aqc_opc_nvm_read			= 0x0701,
@@ -228,6 +232,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_nvm_config_read		= 0x0704,
 	i40e_aqc_opc_nvm_config_write		= 0x0705,
 	i40e_aqc_opc_oem_post_update		= 0x0720,
+	i40e_aqc_opc_thermal_sensor		= 0x0721,
 
 	/* virtualization commands */
 	i40e_aqc_opc_send_msg_to_pf		= 0x0801,
@@ -402,6 +407,7 @@ struct i40e_aqc_list_capabilities_element_resp {
 #define I40E_AQ_CAP_ID_OS2BMC_CAP	0x0004
 #define I40E_AQ_CAP_ID_FUNCTIONS_VALID	0x0005
 #define I40E_AQ_CAP_ID_ALTERNATE_RAM	0x0006
+#define I40E_AQ_CAP_ID_WOL_AND_PROXY	0x0008
 #define I40E_AQ_CAP_ID_SRIOV		0x0012
 #define I40E_AQ_CAP_ID_VF		0x0013
 #define I40E_AQ_CAP_ID_VMDQ		0x0014
@@ -422,6 +428,7 @@ struct i40e_aqc_list_capabilities_element_resp {
 #define I40E_AQ_CAP_ID_LED		0x0061
 #define I40E_AQ_CAP_ID_SDP		0x0062
 #define I40E_AQ_CAP_ID_MDIO		0x0063
+#define I40E_AQ_CAP_ID_WSR_PROT		0x0064
 #define I40E_AQ_CAP_ID_FLEX10		0x00F1
 #define I40E_AQ_CAP_ID_CEM		0x00F2
 
@@ -680,6 +687,31 @@ struct i40e_aqc_switch_resource_alloc_element_resp {
 
 I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 
+/* Set Switch Configuration (direct 0x0205) */
+struct i40e_aqc_set_switch_config {
+	__le16	flags;
+#define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
+#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
+	__le16	valid_flags;
+	u8	reserved[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
+
+/* Read Receive control registers  (direct 0x0206)
+ * Write Receive control registers (direct 0x0207)
+ *     used for accessing Rx control registers that can be
+ *     slow and need special handling when under high Rx load
+ */
+struct i40e_aqc_rx_ctl_reg_read_write {
+	__le32 reserved1;
+	__le32 address;
+	__le32 reserved2;
+	__le32 value;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_rx_ctl_reg_read_write);
+
 /* Add VSI (indirect 0x0210)
  *    this indirect command uses struct i40e_aqc_vsi_properties_data
  *    as the indirect buffer (128 bytes)
@@ -906,7 +938,8 @@ struct i40e_aqc_add_veb {
 					I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT)
 #define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT	0x2
 #define I40E_AQC_ADD_VEB_PORT_TYPE_DATA		0x4
-#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER	0x8
+#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER	0x8     /* deprecated */
+#define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS	0x10
 	u8	enable_tcs;
 	u8	reserved[9];
 };
@@ -973,6 +1006,7 @@ struct i40e_aqc_add_macvlan_element_data {
 #define I40E_AQC_MACVLAN_ADD_HASH_MATCH		0x0002
 #define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN	0x0004
 #define I40E_AQC_MACVLAN_ADD_TO_QUEUE		0x0008
+#define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC	0x0010
 	__le16	queue_number;
 #define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT	0
 #define I40E_AQC_MACVLAN_CMD_QUEUE_MASK		(0x7FF << \
@@ -1069,6 +1103,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes {
 #define I40E_AQC_SET_VSI_PROMISC_BROADCAST	0x04
 #define I40E_AQC_SET_VSI_DEFAULT		0x08
 #define I40E_AQC_SET_VSI_PROMISC_VLAN		0x10
+#define I40E_AQC_SET_VSI_PROMISC_TX		0x8000
 	__le16	seid;
 #define I40E_AQC_VSI_PROM_CMD_SEID_MASK		0x3FF
 	__le16	vlan_tag;
@@ -1257,10 +1292,16 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT		9
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK		0x1E00
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_XVLAN		0
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN		0
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC		1
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE			2
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE		2
 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP			3
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED		4
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE		5
+
+#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC	0x2000
+#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC	0x4000
+#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP	0x8000
 
 	__le32	tenant_id;
 	u8	reserved[4];
@@ -1755,7 +1796,12 @@ struct i40e_aqc_get_link_status {
 	u8	config;
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	reserved[5];
+	u8	external_power_ability;
+#define I40E_AQ_LINK_POWER_CLASS_1	0x00
+#define I40E_AQ_LINK_POWER_CLASS_2	0x01
+#define I40E_AQ_LINK_POWER_CLASS_3	0x02
+#define I40E_AQ_LINK_POWER_CLASS_4	0x03
+	u8	reserved[4];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
@@ -1823,6 +1869,18 @@ enum i40e_aq_phy_reg_type {
 	I40E_AQC_PHY_REG_EXERNAL_MODULE	= 0x3
 };
 
+/* Run PHY Activity (0x0626) */
+struct i40e_aqc_run_phy_activity {
+	__le16  activity_id;
+	u8      flags;
+	u8      reserved1;
+	__le32  control;
+	__le32  data;
+	u8      reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
@@ -1912,6 +1970,22 @@ struct i40e_aqc_nvm_oem_post_update_buffer {
 
 I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer);
 
+/* Thermal Sensor (indirect 0x0721)
+ *     read or set thermal sensor configs and values
+ *     takes a sensor and command specific data buffer, not detailed here
+ */
+struct i40e_aqc_thermal_sensor {
+	u8 sensor_action;
+#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG	0
+#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG	1
+#define I40E_AQ_THERMAL_SENSOR_READ_TEMP	2
+	u8 reserved[7];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_thermal_sensor);
+
 /* Send to PF command (indirect 0x0801) id is only used by PF
  * Send to VF command (indirect 0x0802) id is only used by PF
  * Send to Peer PF command (indirect 0x0803)
@@ -2191,6 +2265,7 @@ struct i40e_aqc_add_udp_tunnel {
 #define I40E_AQC_TUNNEL_TYPE_VXLAN	0x00
 #define I40E_AQC_TUNNEL_TYPE_NGE	0x01
 #define I40E_AQC_TUNNEL_TYPE_TEREDO	0x10
+#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE	0x11
 	u8	reserved1[10];
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 6a034dd..4596294 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -55,19 +55,13 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
 		case I40E_DEV_ID_20G_KR2_A:
 			hw->mac.type = I40E_MAC_XL710;
 			break;
+		case I40E_DEV_ID_KX_X722:
+		case I40E_DEV_ID_QSFP_X722:
 		case I40E_DEV_ID_SFP_X722:
 		case I40E_DEV_ID_1G_BASE_T_X722:
 		case I40E_DEV_ID_10G_BASE_T_X722:
 			hw->mac.type = I40E_MAC_X722;
 			break;
-		case I40E_DEV_ID_X722_VF:
-		case I40E_DEV_ID_X722_VF_HV:
-			hw->mac.type = I40E_MAC_X722_VF;
-			break;
-		case I40E_DEV_ID_VF:
-		case I40E_DEV_ID_VF_HV:
-			hw->mac.type = I40E_MAC_VF;
-			break;
 		default:
 			hw->mac.type = I40E_MAC_GENERIC;
 			break;
@@ -1245,7 +1239,13 @@ i40e_status i40e_pf_reset(struct i40e_hw *hw)
 	grst_del = (rd32(hw, I40E_GLGEN_RSTCTL) &
 		    I40E_GLGEN_RSTCTL_GRSTDEL_MASK) >>
 		    I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT;
-	for (cnt = 0; cnt < grst_del + 10; cnt++) {
+
+	/* It can take upto 15 secs for GRST steady state.
+	 * Bump it to 16 secs max to be safe.
+	 */
+	grst_del = grst_del * 20;
+
+	for (cnt = 0; cnt < grst_del; cnt++) {
 		reg = rd32(hw, I40E_GLGEN_RSTAT);
 		if (!(reg & I40E_GLGEN_RSTAT_DEVSTATE_MASK))
 			break;
@@ -1894,6 +1894,32 @@ i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw,
 }
 
 /**
+ * i40e_aq_set_phy_debug
+ * @hw: pointer to the hw struct
+ * @cmd_flags: debug command flags
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Reset the external PHY.
+ **/
+enum i40e_status_code i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
+					struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_set_phy_debug *cmd =
+		(struct i40e_aqc_set_phy_debug *)&desc.params.raw;
+	enum i40e_status_code status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_set_phy_debug);
+
+	cmd->command_flags = cmd_flags;
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
  * i40e_aq_add_vsi
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -1958,12 +1984,19 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
-	if (set)
+	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
+		if (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) ||
+		    (hw->aq.api_maj_ver > 1))
+			flags |= I40E_AQC_SET_VSI_PROMISC_TX;
+	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
+	if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) ||
+	    (hw->aq.api_maj_ver > 1))
+		cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX);
 
 	cmd->seid = cpu_to_le16(seid);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2039,6 +2072,37 @@ i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
 }
 
 /**
+ * i40e_aq_set_vsi_vlan_promisc - control the VLAN promiscuous setting
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
+				       u16 seid, bool enable,
+				       struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	i40e_status status;
+	u16 flags = 0;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					i40e_aqc_opc_set_vsi_promiscuous_modes);
+	if (enable)
+		flags |= I40E_AQC_SET_VSI_PROMISC_VLAN;
+
+	cmd->promiscuous_flags = cpu_to_le16(flags);
+	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_VLAN);
+	cmd->seid = cpu_to_le16(seid);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
  * i40e_get_vsi_params - get VSI configuration info
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -2283,8 +2347,8 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw)
  * @downlink_seid: the VSI SEID
  * @enabled_tc: bitmap of TCs to be enabled
  * @default_port: true for default port VSI, false for control port
- * @enable_l2_filtering: true to add L2 filter table rules to regular forwarding rules for cloud support
  * @veb_seid: pointer to where to put the resulting VEB SEID
+ * @enable_stats: true to turn on VEB stats
  * @cmd_details: pointer to command details structure or NULL
  *
  * This asks the FW to add a VEB between the uplink and downlink
@@ -2292,8 +2356,8 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw)
  **/
 i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 				u16 downlink_seid, u8 enabled_tc,
-				bool default_port, bool enable_l2_filtering,
-				u16 *veb_seid,
+				bool default_port, u16 *veb_seid,
+				bool enable_stats,
 				struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aq_desc desc;
@@ -2320,8 +2384,9 @@ i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 	else
 		veb_flags |= I40E_AQC_ADD_VEB_PORT_TYPE_DATA;
 
-	if (enable_l2_filtering)
-		veb_flags |= I40E_AQC_ADD_VEB_ENABLE_L2_FILTER;
+	/* reverse logic here: set the bitflag to disable the stats */
+	if (!enable_stats)
+		veb_flags |= I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS;
 
 	cmd->veb_flags = cpu_to_le16(veb_flags);
 
@@ -2410,6 +2475,7 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
 		(struct i40e_aqc_macvlan *)&desc.params.raw;
 	i40e_status status;
 	u16 buf_size;
+	int i;
 
 	if (count == 0 || !mv_list || !hw)
 		return I40E_ERR_PARAM;
@@ -2423,12 +2489,17 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
 	cmd->seid[1] = 0;
 	cmd->seid[2] = 0;
 
+	for (i = 0; i < count; i++)
+		if (is_multicast_ether_addr(mv_list[i].mac_addr))
+			mv_list[i].flags |=
+			       cpu_to_le16(I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC);
+
 	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
 		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, mv_list, buf_size,
-				    cmd_details);
+				       cmd_details);
 
 	return status;
 }
@@ -2476,6 +2547,137 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 }
 
 /**
+ * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule
+ * @hw: pointer to the hw struct
+ * @opcode: AQ opcode for add or delete mirror rule
+ * @sw_seid: Switch SEID (to which rule refers)
+ * @rule_type: Rule Type (ingress/egress/VLAN)
+ * @id: Destination VSI SEID or Rule ID
+ * @count: length of the list
+ * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
+ * @cmd_details: pointer to command details structure or NULL
+ * @rule_id: Rule ID returned from FW
+ * @rule_used: Number of rules used in internal switch
+ * @rule_free: Number of rules free in internal switch
+ *
+ * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for
+ * VEBs/VEPA elements only
+ **/
+static i40e_status i40e_mirrorrule_op(struct i40e_hw *hw,
+				u16 opcode, u16 sw_seid, u16 rule_type, u16 id,
+				u16 count, __le16 *mr_list,
+				struct i40e_asq_cmd_details *cmd_details,
+				u16 *rule_id, u16 *rules_used, u16 *rules_free)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_add_delete_mirror_rule *cmd =
+		(struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw;
+	struct i40e_aqc_add_delete_mirror_rule_completion *resp =
+	(struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw;
+	i40e_status status;
+	u16 buf_size;
+
+	buf_size = count * sizeof(*mr_list);
+
+	/* prep the rest of the request */
+	i40e_fill_default_direct_cmd_desc(&desc, opcode);
+	cmd->seid = cpu_to_le16(sw_seid);
+	cmd->rule_type = cpu_to_le16(rule_type &
+				     I40E_AQC_MIRROR_RULE_TYPE_MASK);
+	cmd->num_entries = cpu_to_le16(count);
+	/* Dest VSI for add, rule_id for delete */
+	cmd->destination = cpu_to_le16(id);
+	if (mr_list) {
+		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
+						I40E_AQ_FLAG_RD));
+		if (buf_size > I40E_AQ_LARGE_BUF)
+			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+	}
+
+	status = i40e_asq_send_command(hw, &desc, mr_list, buf_size,
+				       cmd_details);
+	if (!status ||
+	    hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) {
+		if (rule_id)
+			*rule_id = le16_to_cpu(resp->rule_id);
+		if (rules_used)
+			*rules_used = le16_to_cpu(resp->mirror_rules_used);
+		if (rules_free)
+			*rules_free = le16_to_cpu(resp->mirror_rules_free);
+	}
+	return status;
+}
+
+/**
+ * i40e_aq_add_mirrorrule - add a mirror rule
+ * @hw: pointer to the hw struct
+ * @sw_seid: Switch SEID (to which rule refers)
+ * @rule_type: Rule Type (ingress/egress/VLAN)
+ * @dest_vsi: SEID of VSI to which packets will be mirrored
+ * @count: length of the list
+ * @mr_list: list of mirrored VSI SEIDs or VLAN IDs
+ * @cmd_details: pointer to command details structure or NULL
+ * @rule_id: Rule ID returned from FW
+ * @rule_used: Number of rules used in internal switch
+ * @rule_free: Number of rules free in internal switch
+ *
+ * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only
+ **/
+i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
+			u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list,
+			struct i40e_asq_cmd_details *cmd_details,
+			u16 *rule_id, u16 *rules_used, u16 *rules_free)
+{
+	if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS ||
+	    rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) {
+		if (count == 0 || !mr_list)
+			return I40E_ERR_PARAM;
+	}
+
+	return i40e_mirrorrule_op(hw, i40e_aqc_opc_add_mirror_rule, sw_seid,
+				  rule_type, dest_vsi, count, mr_list,
+				  cmd_details, rule_id, rules_used, rules_free);
+}
+
+/**
+ * i40e_aq_delete_mirrorrule - delete a mirror rule
+ * @hw: pointer to the hw struct
+ * @sw_seid: Switch SEID (to which rule refers)
+ * @rule_type: Rule Type (ingress/egress/VLAN)
+ * @count: length of the list
+ * @rule_id: Rule ID that is returned in the receive desc as part of
+ *		add_mirrorrule.
+ * @mr_list: list of mirrored VLAN IDs to be removed
+ * @cmd_details: pointer to command details structure or NULL
+ * @rule_used: Number of rules used in internal switch
+ * @rule_free: Number of rules free in internal switch
+ *
+ * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only
+ **/
+i40e_status i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
+			u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list,
+			struct i40e_asq_cmd_details *cmd_details,
+			u16 *rules_used, u16 *rules_free)
+{
+	/* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */
+	if (rule_type != I40E_AQC_MIRROR_RULE_TYPE_VLAN) {
+		if (!rule_id)
+			return I40E_ERR_PARAM;
+	} else {
+		/* count and mr_list shall be valid for rule_type INGRESS VLAN
+		 * mirroring. For other rule_type, count and rule_type should
+		 * not matter.
+		 */
+		if (count == 0 || !mr_list)
+			return I40E_ERR_PARAM;
+	}
+
+	return i40e_mirrorrule_op(hw, i40e_aqc_opc_delete_mirror_rule, sw_seid,
+				  rule_type, rule_id, count, mr_list,
+				  cmd_details, NULL, rules_used, rules_free);
+}
+
+/**
  * i40e_aq_send_msg_to_vf
  * @hw: pointer to the hardware structure
  * @vfid: VF id to send msg
@@ -2765,35 +2967,6 @@ i40e_aq_erase_nvm_exit:
 	return status;
 }
 
-#define I40E_DEV_FUNC_CAP_SWITCH_MODE	0x01
-#define I40E_DEV_FUNC_CAP_MGMT_MODE	0x02
-#define I40E_DEV_FUNC_CAP_NPAR		0x03
-#define I40E_DEV_FUNC_CAP_OS2BMC	0x04
-#define I40E_DEV_FUNC_CAP_VALID_FUNC	0x05
-#define I40E_DEV_FUNC_CAP_SRIOV_1_1	0x12
-#define I40E_DEV_FUNC_CAP_VF		0x13
-#define I40E_DEV_FUNC_CAP_VMDQ		0x14
-#define I40E_DEV_FUNC_CAP_802_1_QBG	0x15
-#define I40E_DEV_FUNC_CAP_802_1_QBH	0x16
-#define I40E_DEV_FUNC_CAP_VSI		0x17
-#define I40E_DEV_FUNC_CAP_DCB		0x18
-#define I40E_DEV_FUNC_CAP_FCOE		0x21
-#define I40E_DEV_FUNC_CAP_ISCSI		0x22
-#define I40E_DEV_FUNC_CAP_RSS		0x40
-#define I40E_DEV_FUNC_CAP_RX_QUEUES	0x41
-#define I40E_DEV_FUNC_CAP_TX_QUEUES	0x42
-#define I40E_DEV_FUNC_CAP_MSIX		0x43
-#define I40E_DEV_FUNC_CAP_MSIX_VF	0x44
-#define I40E_DEV_FUNC_CAP_FLOW_DIRECTOR	0x45
-#define I40E_DEV_FUNC_CAP_IEEE_1588	0x46
-#define I40E_DEV_FUNC_CAP_FLEX10	0xF1
-#define I40E_DEV_FUNC_CAP_CEM		0xF2
-#define I40E_DEV_FUNC_CAP_IWARP		0x51
-#define I40E_DEV_FUNC_CAP_LED		0x61
-#define I40E_DEV_FUNC_CAP_SDP		0x62
-#define I40E_DEV_FUNC_CAP_MDIO		0x63
-#define I40E_DEV_FUNC_CAP_WR_CSR_PROT	0x64
-
 /**
  * i40e_parse_discover_capabilities
  * @hw: pointer to the hw struct
@@ -2832,79 +3005,79 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 		major_rev = cap->major_rev;
 
 		switch (id) {
-		case I40E_DEV_FUNC_CAP_SWITCH_MODE:
+		case I40E_AQ_CAP_ID_SWITCH_MODE:
 			p->switch_mode = number;
 			break;
-		case I40E_DEV_FUNC_CAP_MGMT_MODE:
+		case I40E_AQ_CAP_ID_MNG_MODE:
 			p->management_mode = number;
 			break;
-		case I40E_DEV_FUNC_CAP_NPAR:
+		case I40E_AQ_CAP_ID_NPAR_ACTIVE:
 			p->npar_enable = number;
 			break;
-		case I40E_DEV_FUNC_CAP_OS2BMC:
+		case I40E_AQ_CAP_ID_OS2BMC_CAP:
 			p->os2bmc = number;
 			break;
-		case I40E_DEV_FUNC_CAP_VALID_FUNC:
+		case I40E_AQ_CAP_ID_FUNCTIONS_VALID:
 			p->valid_functions = number;
 			break;
-		case I40E_DEV_FUNC_CAP_SRIOV_1_1:
+		case I40E_AQ_CAP_ID_SRIOV:
 			if (number == 1)
 				p->sr_iov_1_1 = true;
 			break;
-		case I40E_DEV_FUNC_CAP_VF:
+		case I40E_AQ_CAP_ID_VF:
 			p->num_vfs = number;
 			p->vf_base_id = logical_id;
 			break;
-		case I40E_DEV_FUNC_CAP_VMDQ:
+		case I40E_AQ_CAP_ID_VMDQ:
 			if (number == 1)
 				p->vmdq = true;
 			break;
-		case I40E_DEV_FUNC_CAP_802_1_QBG:
+		case I40E_AQ_CAP_ID_8021QBG:
 			if (number == 1)
 				p->evb_802_1_qbg = true;
 			break;
-		case I40E_DEV_FUNC_CAP_802_1_QBH:
+		case I40E_AQ_CAP_ID_8021QBR:
 			if (number == 1)
 				p->evb_802_1_qbh = true;
 			break;
-		case I40E_DEV_FUNC_CAP_VSI:
+		case I40E_AQ_CAP_ID_VSI:
 			p->num_vsis = number;
 			break;
-		case I40E_DEV_FUNC_CAP_DCB:
+		case I40E_AQ_CAP_ID_DCB:
 			if (number == 1) {
 				p->dcb = true;
 				p->enabled_tcmap = logical_id;
 				p->maxtc = phys_id;
 			}
 			break;
-		case I40E_DEV_FUNC_CAP_FCOE:
+		case I40E_AQ_CAP_ID_FCOE:
 			if (number == 1)
 				p->fcoe = true;
 			break;
-		case I40E_DEV_FUNC_CAP_ISCSI:
+		case I40E_AQ_CAP_ID_ISCSI:
 			if (number == 1)
 				p->iscsi = true;
 			break;
-		case I40E_DEV_FUNC_CAP_RSS:
+		case I40E_AQ_CAP_ID_RSS:
 			p->rss = true;
 			p->rss_table_size = number;
 			p->rss_table_entry_width = logical_id;
 			break;
-		case I40E_DEV_FUNC_CAP_RX_QUEUES:
+		case I40E_AQ_CAP_ID_RXQ:
 			p->num_rx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_DEV_FUNC_CAP_TX_QUEUES:
+		case I40E_AQ_CAP_ID_TXQ:
 			p->num_tx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_DEV_FUNC_CAP_MSIX:
+		case I40E_AQ_CAP_ID_MSIX:
 			p->num_msix_vectors = number;
 			break;
-		case I40E_DEV_FUNC_CAP_MSIX_VF:
+		case I40E_AQ_CAP_ID_VF_MSIX:
 			p->num_msix_vectors_vf = number;
 			break;
-		case I40E_DEV_FUNC_CAP_FLEX10:
+		case I40E_AQ_CAP_ID_FLEX10:
 			if (major_rev == 1) {
 				if (number == 1) {
 					p->flex10_enable = true;
@@ -2920,38 +3093,38 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 			p->flex10_mode = logical_id;
 			p->flex10_status = phys_id;
 			break;
-		case I40E_DEV_FUNC_CAP_CEM:
+		case I40E_AQ_CAP_ID_CEM:
 			if (number == 1)
 				p->mgmt_cem = true;
 			break;
-		case I40E_DEV_FUNC_CAP_IWARP:
+		case I40E_AQ_CAP_ID_IWARP:
 			if (number == 1)
 				p->iwarp = true;
 			break;
-		case I40E_DEV_FUNC_CAP_LED:
+		case I40E_AQ_CAP_ID_LED:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->led[phys_id] = true;
 			break;
-		case I40E_DEV_FUNC_CAP_SDP:
+		case I40E_AQ_CAP_ID_SDP:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->sdp[phys_id] = true;
 			break;
-		case I40E_DEV_FUNC_CAP_MDIO:
+		case I40E_AQ_CAP_ID_MDIO:
 			if (number == 1) {
 				p->mdio_port_num = phys_id;
 				p->mdio_port_mode = logical_id;
 			}
 			break;
-		case I40E_DEV_FUNC_CAP_IEEE_1588:
+		case I40E_AQ_CAP_ID_1588:
 			if (number == 1)
 				p->ieee_1588 = true;
 			break;
-		case I40E_DEV_FUNC_CAP_FLOW_DIRECTOR:
+		case I40E_AQ_CAP_ID_FLOW_DIRECTOR:
 			p->fd = true;
 			p->fd_filters_guaranteed = number;
 			p->fd_filters_best_effort = logical_id;
 			break;
-		case I40E_DEV_FUNC_CAP_WR_CSR_PROT:
+		case I40E_AQ_CAP_ID_WSR_PROT:
 			p->wr_csr_prot = (u64)number;
 			p->wr_csr_prot |= (u64)logical_id << 32;
 			break;
@@ -3709,7 +3882,7 @@ i40e_status i40e_set_filter_control(struct i40e_hw *hw,
 		return ret;
 
 	/* Read the PF Queue Filter control register */
-	val = rd32(hw, I40E_PFQF_CTL_0);
+	val = i40e_read_rx_ctl(hw, I40E_PFQF_CTL_0);
 
 	/* Program required PE hash buckets for the PF */
 	val &= ~I40E_PFQF_CTL_0_PEHSIZE_MASK;
@@ -3746,7 +3919,7 @@ i40e_status i40e_set_filter_control(struct i40e_hw *hw,
 	if (settings->enable_macvlan)
 		val |= I40E_PFQF_CTL_0_MACVLAN_ENA_MASK;
 
-	wr32(hw, I40E_PFQF_CTL_0, val);
+	i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, val);
 
 	return 0;
 }
@@ -4073,3 +4246,454 @@ i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw,
 
 	return status;
 }
+
+/**
+ * i40e_read_phy_register
+ * @hw: pointer to the HW structure
+ * @page: registers page number
+ * @reg: register address in the page
+ * @phy_adr: PHY address on MDIO interface
+ * @value: PHY register value
+ *
+ * Reads specified PHY register value
+ **/
+i40e_status i40e_read_phy_register(struct i40e_hw *hw,
+				   u8 page, u16 reg, u8 phy_addr,
+				   u16 *value)
+{
+	i40e_status status = I40E_ERR_TIMEOUT;
+	u32 command = 0;
+	u16 retry = 1000;
+	u8 port_num = hw->func_caps.mdio_port_num;
+
+	command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) |
+		  (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) |
+		  (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) |
+		  (I40E_MDIO_OPCODE_ADDRESS) |
+		  (I40E_MDIO_STCODE) |
+		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
+		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
+	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
+	do {
+		command = rd32(hw, I40E_GLGEN_MSCA(port_num));
+		if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) {
+			status = 0;
+			break;
+		}
+		usleep_range(10, 20);
+		retry--;
+	} while (retry);
+
+	if (status) {
+		i40e_debug(hw, I40E_DEBUG_PHY,
+			   "PHY: Can't write command to external PHY.\n");
+		goto phy_read_end;
+	}
+
+	command = (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) |
+		  (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) |
+		  (I40E_MDIO_OPCODE_READ) |
+		  (I40E_MDIO_STCODE) |
+		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
+		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
+	status = I40E_ERR_TIMEOUT;
+	retry = 1000;
+	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
+	do {
+		command = rd32(hw, I40E_GLGEN_MSCA(port_num));
+		if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) {
+			status = 0;
+			break;
+		}
+		usleep_range(10, 20);
+		retry--;
+	} while (retry);
+
+	if (!status) {
+		command = rd32(hw, I40E_GLGEN_MSRWD(port_num));
+		*value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >>
+			 I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT;
+	} else {
+		i40e_debug(hw, I40E_DEBUG_PHY,
+			   "PHY: Can't read register value from external PHY.\n");
+	}
+
+phy_read_end:
+	return status;
+}
+
+/**
+ * i40e_write_phy_register
+ * @hw: pointer to the HW structure
+ * @page: registers page number
+ * @reg: register address in the page
+ * @phy_adr: PHY address on MDIO interface
+ * @value: PHY register value
+ *
+ * Writes value to specified PHY register
+ **/
+i40e_status i40e_write_phy_register(struct i40e_hw *hw,
+				    u8 page, u16 reg, u8 phy_addr,
+				    u16 value)
+{
+	i40e_status status = I40E_ERR_TIMEOUT;
+	u32 command = 0;
+	u16 retry = 1000;
+	u8 port_num = hw->func_caps.mdio_port_num;
+
+	command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) |
+		  (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) |
+		  (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) |
+		  (I40E_MDIO_OPCODE_ADDRESS) |
+		  (I40E_MDIO_STCODE) |
+		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
+		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
+	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
+	do {
+		command = rd32(hw, I40E_GLGEN_MSCA(port_num));
+		if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) {
+			status = 0;
+			break;
+		}
+		usleep_range(10, 20);
+		retry--;
+	} while (retry);
+	if (status) {
+		i40e_debug(hw, I40E_DEBUG_PHY,
+			   "PHY: Can't write command to external PHY.\n");
+		goto phy_write_end;
+	}
+
+	command = value << I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT;
+	wr32(hw, I40E_GLGEN_MSRWD(port_num), command);
+
+	command = (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) |
+		  (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) |
+		  (I40E_MDIO_OPCODE_WRITE) |
+		  (I40E_MDIO_STCODE) |
+		  (I40E_GLGEN_MSCA_MDICMD_MASK) |
+		  (I40E_GLGEN_MSCA_MDIINPROGEN_MASK);
+	status = I40E_ERR_TIMEOUT;
+	retry = 1000;
+	wr32(hw, I40E_GLGEN_MSCA(port_num), command);
+	do {
+		command = rd32(hw, I40E_GLGEN_MSCA(port_num));
+		if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) {
+			status = 0;
+			break;
+		}
+		usleep_range(10, 20);
+		retry--;
+	} while (retry);
+
+phy_write_end:
+	return status;
+}
+
+/**
+ * i40e_get_phy_address
+ * @hw: pointer to the HW structure
+ * @dev_num: PHY port num that address we want
+ * @phy_addr: Returned PHY address
+ *
+ * Gets PHY address for current port
+ **/
+u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num)
+{
+	u8 port_num = hw->func_caps.mdio_port_num;
+	u32 reg_val = rd32(hw, I40E_GLGEN_MDIO_I2C_SEL(port_num));
+
+	return (u8)(reg_val >> ((dev_num + 1) * 5)) & 0x1f;
+}
+
+/**
+ * i40e_blink_phy_led
+ * @hw: pointer to the HW structure
+ * @time: time how long led will blinks in secs
+ * @interval: gap between LED on and off in msecs
+ *
+ * Blinks PHY link LED
+ **/
+i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
+				    u32 time, u32 interval)
+{
+	i40e_status status = 0;
+	u32 i;
+	u16 led_ctl;
+	u16 gpio_led_port;
+	u16 led_reg;
+	u16 led_addr = I40E_PHY_LED_PROV_REG_1;
+	u8 phy_addr = 0;
+	u8 port_num;
+
+	i = rd32(hw, I40E_PFGEN_PORTNUM);
+	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+	phy_addr = i40e_get_phy_address(hw, port_num);
+
+	for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++,
+	     led_addr++) {
+		status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE,
+						led_addr, phy_addr, &led_reg);
+		if (status)
+			goto phy_blinking_end;
+		led_ctl = led_reg;
+		if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
+			led_reg = 0;
+			status = i40e_write_phy_register(hw,
+							 I40E_PHY_COM_REG_PAGE,
+							 led_addr, phy_addr,
+							 led_reg);
+			if (status)
+				goto phy_blinking_end;
+			break;
+		}
+	}
+
+	if (time > 0 && interval > 0) {
+		for (i = 0; i < time * 1000; i += interval) {
+			status = i40e_read_phy_register(hw,
+							I40E_PHY_COM_REG_PAGE,
+							led_addr, phy_addr,
+							&led_reg);
+			if (status)
+				goto restore_config;
+			if (led_reg & I40E_PHY_LED_MANUAL_ON)
+				led_reg = 0;
+			else
+				led_reg = I40E_PHY_LED_MANUAL_ON;
+			status = i40e_write_phy_register(hw,
+							 I40E_PHY_COM_REG_PAGE,
+							 led_addr, phy_addr,
+							 led_reg);
+			if (status)
+				goto restore_config;
+			msleep(interval);
+		}
+	}
+
+restore_config:
+	status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr,
+					 phy_addr, led_ctl);
+
+phy_blinking_end:
+	return status;
+}
+
+/**
+ * i40e_led_get_phy - return current on/off mode
+ * @hw: pointer to the hw struct
+ * @led_addr: address of led register to use
+ * @val: original value of register to use
+ *
+ **/
+i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
+			     u16 *val)
+{
+	i40e_status status = 0;
+	u16 gpio_led_port;
+	u8 phy_addr = 0;
+	u16 reg_val;
+	u16 temp_addr;
+	u8 port_num;
+	u32 i;
+
+	temp_addr = I40E_PHY_LED_PROV_REG_1;
+	i = rd32(hw, I40E_PFGEN_PORTNUM);
+	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+	phy_addr = i40e_get_phy_address(hw, port_num);
+
+	for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++,
+	     temp_addr++) {
+		status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE,
+						temp_addr, phy_addr, &reg_val);
+		if (status)
+			return status;
+		*val = reg_val;
+		if (reg_val & I40E_PHY_LED_LINK_MODE_MASK) {
+			*led_addr = temp_addr;
+			break;
+		}
+	}
+	return status;
+}
+
+/**
+ * i40e_led_set_phy
+ * @hw: pointer to the HW structure
+ * @on: true or false
+ * @mode: original val plus bit for set or ignore
+ * Set led's on or off when controlled by the PHY
+ *
+ **/
+i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on,
+			     u16 led_addr, u32 mode)
+{
+	i40e_status status = 0;
+	u16 led_ctl = 0;
+	u16 led_reg = 0;
+	u8 phy_addr = 0;
+	u8 port_num;
+	u32 i;
+
+	i = rd32(hw, I40E_PFGEN_PORTNUM);
+	port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+	phy_addr = i40e_get_phy_address(hw, port_num);
+
+	status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr,
+					phy_addr, &led_reg);
+	if (status)
+		return status;
+	led_ctl = led_reg;
+	if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
+		led_reg = 0;
+		status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE,
+						 led_addr, phy_addr, led_reg);
+		if (status)
+			return status;
+	}
+	status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE,
+					led_addr, phy_addr, &led_reg);
+	if (status)
+		goto restore_config;
+	if (on)
+		led_reg = I40E_PHY_LED_MANUAL_ON;
+	else
+		led_reg = 0;
+	status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE,
+					 led_addr, phy_addr, led_reg);
+	if (status)
+		goto restore_config;
+	if (mode & I40E_PHY_LED_MODE_ORIG) {
+		led_ctl = (mode & I40E_PHY_LED_MODE_MASK);
+		status = i40e_write_phy_register(hw,
+						 I40E_PHY_COM_REG_PAGE,
+						 led_addr, phy_addr, led_ctl);
+	}
+	return status;
+restore_config:
+	status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr,
+					 phy_addr, led_ctl);
+	return status;
+}
+
+/**
+ * i40e_aq_rx_ctl_read_register - use FW to read from an Rx control register
+ * @hw: pointer to the hw struct
+ * @reg_addr: register address
+ * @reg_val: ptr to register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Use the firmware to read the Rx control register,
+ * especially useful if the Rx unit is under heavy pressure
+ **/
+i40e_status i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
+				u32 reg_addr, u32 *reg_val,
+				struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp =
+		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	i40e_status status;
+
+	if (!reg_val)
+		return I40E_ERR_PARAM;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_read);
+
+	cmd_resp->address = cpu_to_le32(reg_addr);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	if (status == 0)
+		*reg_val = le32_to_cpu(cmd_resp->value);
+
+	return status;
+}
+
+/**
+ * i40e_read_rx_ctl - read from an Rx control register
+ * @hw: pointer to the hw struct
+ * @reg_addr: register address
+ **/
+u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
+{
+	i40e_status status = 0;
+	bool use_register;
+	int retry = 5;
+	u32 val = 0;
+
+	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	if (!use_register) {
+do_retry:
+		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
+		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+			usleep_range(1000, 2000);
+			retry--;
+			goto do_retry;
+		}
+	}
+
+	/* if the AQ access failed, try the old-fashioned way */
+	if (status || use_register)
+		val = rd32(hw, reg_addr);
+
+	return val;
+}
+
+/**
+ * i40e_aq_rx_ctl_write_register
+ * @hw: pointer to the hw struct
+ * @reg_addr: register address
+ * @reg_val: register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Use the firmware to write to an Rx control register,
+ * especially useful if the Rx unit is under heavy pressure
+ **/
+i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
+				u32 reg_addr, u32 reg_val,
+				struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd =
+		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_write);
+
+	cmd->address = cpu_to_le32(reg_addr);
+	cmd->value = cpu_to_le32(reg_val);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40e_write_rx_ctl - write to an Rx control register
+ * @hw: pointer to the hw struct
+ * @reg_addr: register address
+ * @reg_val: register value
+ **/
+void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
+{
+	i40e_status status = 0;
+	bool use_register;
+	int retry = 5;
+
+	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	if (!use_register) {
+do_retry:
+		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
+						       reg_val, NULL);
+		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+			usleep_range(1000, 2000);
+			retry--;
+			goto do_retry;
+		}
+	}
+
+	/* if the AQ access failed, try the old-fashioned way */
+	if (status || use_register)
+		wr32(hw, reg_addr, reg_val);
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 2691277..0fab3a9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -380,17 +380,20 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv,
 {
 	u16 length, typelength, offset = 0;
 	struct i40e_cee_app_prio *app;
-	u8 i, up, selector;
+	u8 i;
 
 	typelength = ntohs(tlv->hdr.typelen);
 	length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
 		       I40E_LLDP_TLV_LEN_SHIFT);
 
 	dcbcfg->numapps = length / sizeof(*app);
+
 	if (!dcbcfg->numapps)
 		return;
 
 	for (i = 0; i < dcbcfg->numapps; i++) {
+		u8 up, selector;
+
 		app = (struct i40e_cee_app_prio *)(tlv->tlvinfo + offset);
 		for (up = 0; up < I40E_MAX_USER_PRIORITY; up++) {
 			if (app->prio_map & BIT(up))
@@ -400,13 +403,17 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv,
 
 		/* Get Selector from lower 2 bits, and convert to IEEE */
 		selector = (app->upper_oui_sel & I40E_CEE_APP_SELECTOR_MASK);
-		if (selector == I40E_CEE_APP_SEL_ETHTYPE)
+		switch (selector) {
+		case I40E_CEE_APP_SEL_ETHTYPE:
 			dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE;
-		else if (selector == I40E_CEE_APP_SEL_TCPIP)
+			break;
+		case I40E_CEE_APP_SEL_TCPIP:
 			dcbcfg->app[i].selector = I40E_APP_SEL_TCPIP;
-		else
+			break;
+		default:
 			/* Keep selector as it is for unknown types */
 			dcbcfg->app[i].selector = selector;
+		}
 
 		dcbcfg->app[i].protocolid = ntohs(app->protocol);
 		/* Move to next app */
@@ -814,13 +821,15 @@ i40e_status i40e_get_dcb_config(struct i40e_hw *hw)
 	struct i40e_aqc_get_cee_dcb_cfg_resp cee_cfg;
 	struct i40e_aqc_get_cee_dcb_cfg_v1_resp cee_v1_cfg;
 
-	/* If Firmware version < v4.33 IEEE only */
-	if (((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver < 33)) ||
-	    (hw->aq.fw_maj_ver < 4))
+	/* If Firmware version < v4.33 on X710/XL710, IEEE only */
+	if ((hw->mac.type == I40E_MAC_XL710) &&
+	    (((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver < 33)) ||
+	      (hw->aq.fw_maj_ver < 4)))
 		return i40e_get_ieee_dcb_config(hw);
 
-	/* If Firmware version == v4.33 use old CEE struct */
-	if ((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver == 33)) {
+	/* If Firmware version == v4.33 on X710/XL710, use old CEE struct */
+	if ((hw->mac.type == I40E_MAC_XL710) &&
+	    ((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver == 33))) {
 		ret = i40e_aq_get_cee_dcb_config(hw, &cee_v1_cfg,
 						 sizeof(cee_v1_cfg), NULL);
 		if (!ret) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 10744a6..0c97733 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -61,257 +61,13 @@ static struct i40e_veb *i40e_dbg_find_veb(struct i40e_pf *pf, int seid)
 {
 	int i;
 
-	if ((seid < I40E_BASE_VEB_SEID) ||
-	    (seid > (I40E_BASE_VEB_SEID + I40E_MAX_VEB)))
-		dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
-	else
-		for (i = 0; i < I40E_MAX_VEB; i++)
-			if (pf->veb[i] && pf->veb[i]->seid == seid)
-				return pf->veb[i];
+	for (i = 0; i < I40E_MAX_VEB; i++)
+		if (pf->veb[i] && pf->veb[i]->seid == seid)
+			return pf->veb[i];
 	return NULL;
 }
 
 /**************************************************************
- * dump
- * The dump entry in debugfs is for getting a data snapshow of
- * the driver's current configuration and runtime details.
- * When the filesystem entry is written, a snapshot is taken.
- * When the entry is read, the most recent snapshot data is dumped.
- **************************************************************/
-static char *i40e_dbg_dump_buf;
-static ssize_t i40e_dbg_dump_data_len;
-static ssize_t i40e_dbg_dump_buffer_len;
-
-/**
- * i40e_dbg_dump_read - read the dump data
- * @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 i40e_dbg_dump_read(struct file *filp, char __user *buffer,
-				  size_t count, loff_t *ppos)
-{
-	int bytes_not_copied;
-	int len;
-
-	/* is *ppos bigger than the available data? */
-	if (*ppos >= i40e_dbg_dump_data_len || !i40e_dbg_dump_buf)
-		return 0;
-
-	/* be sure to not read beyond the end of available data */
-	len = min_t(int, count, (i40e_dbg_dump_data_len - *ppos));
-
-	bytes_not_copied = copy_to_user(buffer, &i40e_dbg_dump_buf[*ppos], len);
-	if (bytes_not_copied)
-		return -EFAULT;
-
-	*ppos += len;
-	return len;
-}
-
-/**
- * i40e_dbg_prep_dump_buf
- * @pf: the PF we're working with
- * @buflen: the desired buffer length
- *
- * Return positive if success, 0 if failed
- **/
-static int i40e_dbg_prep_dump_buf(struct i40e_pf *pf, int buflen)
-{
-	/* if not already big enough, prep for re alloc */
-	if (i40e_dbg_dump_buffer_len && i40e_dbg_dump_buffer_len < buflen) {
-		kfree(i40e_dbg_dump_buf);
-		i40e_dbg_dump_buffer_len = 0;
-		i40e_dbg_dump_buf = NULL;
-	}
-
-	/* get a new buffer if needed */
-	if (!i40e_dbg_dump_buf) {
-		i40e_dbg_dump_buf = kzalloc(buflen, GFP_KERNEL);
-		if (i40e_dbg_dump_buf != NULL)
-			i40e_dbg_dump_buffer_len = buflen;
-	}
-
-	return i40e_dbg_dump_buffer_len;
-}
-
-/**
- * i40e_dbg_dump_write - trigger a datadump snapshot
- * @filp: the opened file
- * @buffer: where to find the user's data
- * @count: the length of the user's data
- * @ppos: file position offset
- *
- * Any write clears the stats
- **/
-static ssize_t i40e_dbg_dump_write(struct file *filp,
-				   const char __user *buffer,
-				   size_t count, loff_t *ppos)
-{
-	struct i40e_pf *pf = filp->private_data;
-	bool seid_found = false;
-	long seid = -1;
-	int buflen = 0;
-	int i, ret;
-	int len;
-	u8 *p;
-
-	/* don't allow partial writes */
-	if (*ppos != 0)
-		return 0;
-
-	/* decode the SEID given to be dumped */
-	ret = kstrtol_from_user(buffer, count, 0, &seid);
-
-	if (ret) {
-		dev_info(&pf->pdev->dev, "bad seid value\n");
-	} else if (seid == 0) {
-		seid_found = true;
-
-		kfree(i40e_dbg_dump_buf);
-		i40e_dbg_dump_buffer_len = 0;
-		i40e_dbg_dump_data_len = 0;
-		i40e_dbg_dump_buf = NULL;
-		dev_info(&pf->pdev->dev, "debug buffer freed\n");
-
-	} else if (seid == pf->pf_seid || seid == 1) {
-		seid_found = true;
-
-		buflen = sizeof(struct i40e_pf);
-		buflen += (sizeof(struct i40e_aq_desc)
-		     * (pf->hw.aq.num_arq_entries + pf->hw.aq.num_asq_entries));
-
-		if (i40e_dbg_prep_dump_buf(pf, buflen)) {
-			p = i40e_dbg_dump_buf;
-
-			len = sizeof(struct i40e_pf);
-			memcpy(p, pf, len);
-			p += len;
-
-			len = (sizeof(struct i40e_aq_desc)
-					* pf->hw.aq.num_asq_entries);
-			memcpy(p, pf->hw.aq.asq.desc_buf.va, len);
-			p += len;
-
-			len = (sizeof(struct i40e_aq_desc)
-					* pf->hw.aq.num_arq_entries);
-			memcpy(p, pf->hw.aq.arq.desc_buf.va, len);
-			p += len;
-
-			i40e_dbg_dump_data_len = buflen;
-			dev_info(&pf->pdev->dev,
-				 "PF seid %ld dumped %d bytes\n",
-				 seid, (int)i40e_dbg_dump_data_len);
-		}
-	} else if (seid >= I40E_BASE_VSI_SEID) {
-		struct i40e_vsi *vsi = NULL;
-		struct i40e_mac_filter *f;
-		int filter_count = 0;
-
-		mutex_lock(&pf->switch_mutex);
-		vsi = i40e_dbg_find_vsi(pf, seid);
-		if (!vsi) {
-			mutex_unlock(&pf->switch_mutex);
-			goto write_exit;
-		}
-
-		buflen = sizeof(struct i40e_vsi);
-		buflen += sizeof(struct i40e_q_vector) * vsi->num_q_vectors;
-		buflen += sizeof(struct i40e_ring) * 2 * vsi->num_queue_pairs;
-		buflen += sizeof(struct i40e_tx_buffer) * vsi->num_queue_pairs;
-		buflen += sizeof(struct i40e_rx_buffer) * vsi->num_queue_pairs;
-		list_for_each_entry(f, &vsi->mac_filter_list, list)
-			filter_count++;
-		buflen += sizeof(struct i40e_mac_filter) * filter_count;
-
-		if (i40e_dbg_prep_dump_buf(pf, buflen)) {
-			p = i40e_dbg_dump_buf;
-			seid_found = true;
-
-			len = sizeof(struct i40e_vsi);
-			memcpy(p, vsi, len);
-			p += len;
-
-			if (vsi->num_q_vectors) {
-				len = (sizeof(struct i40e_q_vector)
-					* vsi->num_q_vectors);
-				memcpy(p, vsi->q_vectors, len);
-				p += len;
-			}
-
-			if (vsi->num_queue_pairs) {
-				len = (sizeof(struct i40e_ring) *
-				      vsi->num_queue_pairs);
-				memcpy(p, vsi->tx_rings, len);
-				p += len;
-				memcpy(p, vsi->rx_rings, len);
-				p += len;
-			}
-
-			if (vsi->tx_rings[0]) {
-				len = sizeof(struct i40e_tx_buffer);
-				for (i = 0; i < vsi->num_queue_pairs; i++) {
-					memcpy(p, vsi->tx_rings[i]->tx_bi, len);
-					p += len;
-				}
-				len = sizeof(struct i40e_rx_buffer);
-				for (i = 0; i < vsi->num_queue_pairs; i++) {
-					memcpy(p, vsi->rx_rings[i]->rx_bi, len);
-					p += len;
-				}
-			}
-
-			/* macvlan filter list */
-			len = sizeof(struct i40e_mac_filter);
-			list_for_each_entry(f, &vsi->mac_filter_list, list) {
-				memcpy(p, f, len);
-				p += len;
-			}
-
-			i40e_dbg_dump_data_len = buflen;
-			dev_info(&pf->pdev->dev,
-				 "VSI seid %ld dumped %d bytes\n",
-				 seid, (int)i40e_dbg_dump_data_len);
-		}
-		mutex_unlock(&pf->switch_mutex);
-	} else if (seid >= I40E_BASE_VEB_SEID) {
-		struct i40e_veb *veb = NULL;
-
-		mutex_lock(&pf->switch_mutex);
-		veb = i40e_dbg_find_veb(pf, seid);
-		if (!veb) {
-			mutex_unlock(&pf->switch_mutex);
-			goto write_exit;
-		}
-
-		buflen = sizeof(struct i40e_veb);
-		if (i40e_dbg_prep_dump_buf(pf, buflen)) {
-			seid_found = true;
-			memcpy(i40e_dbg_dump_buf, veb, buflen);
-			i40e_dbg_dump_data_len = buflen;
-			dev_info(&pf->pdev->dev,
-				 "VEB seid %ld dumped %d bytes\n",
-				 seid, (int)i40e_dbg_dump_data_len);
-		}
-		mutex_unlock(&pf->switch_mutex);
-	}
-
-write_exit:
-	if (!seid_found)
-		dev_info(&pf->pdev->dev, "unknown seid %ld\n", seid);
-
-	return count;
-}
-
-static const struct file_operations i40e_dbg_dump_fops = {
-	.owner = THIS_MODULE,
-	.open =  simple_open,
-	.read =  i40e_dbg_dump_read,
-	.write = i40e_dbg_dump_write,
-};
-
-/**************************************************************
  * command
  * The command entry in debugfs is for giving the driver commands
  * to be executed - these may be for changing the internal switch
@@ -379,19 +135,27 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 		return;
 	}
 	dev_info(&pf->pdev->dev, "vsi seid %d\n", seid);
-	if (vsi->netdev)
-		dev_info(&pf->pdev->dev,
-			 "    netdev: name = %s\n",
-			 vsi->netdev->name);
+	if (vsi->netdev) {
+		struct net_device *nd = vsi->netdev;
+
+		dev_info(&pf->pdev->dev, "    netdev: name = %s, state = %lu, flags = 0x%08x\n",
+			 nd->name, nd->state, nd->flags);
+		dev_info(&pf->pdev->dev, "        features      = 0x%08lx\n",
+			 (unsigned long int)nd->features);
+		dev_info(&pf->pdev->dev, "        hw_features   = 0x%08lx\n",
+			 (unsigned long int)nd->hw_features);
+		dev_info(&pf->pdev->dev, "        vlan_features = 0x%08lx\n",
+			 (unsigned long int)nd->vlan_features);
+	}
 	if (vsi->active_vlans)
 		dev_info(&pf->pdev->dev,
 			 "    vlgrp: & = %p\n", vsi->active_vlans);
 	dev_info(&pf->pdev->dev,
-		 "    netdev_registered = %i, current_netdev_flags = 0x%04x, state = %li flags = 0x%08lx\n",
-		 vsi->netdev_registered,
-		 vsi->current_netdev_flags, vsi->state, vsi->flags);
+		 "    state = %li flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n",
+		 vsi->state, vsi->flags,
+		 vsi->netdev_registered, vsi->current_netdev_flags);
 	if (vsi == pf->vsi[pf->lan_vsi])
-		dev_info(&pf->pdev->dev, "MAC address: %pM SAN MAC: %pM Port MAC: %pM\n",
+		dev_info(&pf->pdev->dev, "    MAC address: %pM SAN MAC: %pM Port MAC: %pM\n",
 			 pf->hw.mac.addr,
 			 pf->hw.mac.san_addr,
 			 pf->hw.mac.port_addr);
@@ -511,7 +275,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 rx_ring->dtype);
 		dev_info(&pf->pdev->dev,
 			 "    rx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
-			 i, rx_ring->hsplit,
+			 i, ring_is_ps_enabled(rx_ring),
 			 rx_ring->next_to_use,
 			 rx_ring->next_to_clean,
 			 rx_ring->ring_active);
@@ -526,6 +290,11 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 rx_ring->rx_stats.alloc_page_failed,
 			 rx_ring->rx_stats.alloc_buff_failed);
 		dev_info(&pf->pdev->dev,
+			 "    rx_rings[%i]: rx_stats: realloc_count = %lld, page_reuse_count = %lld\n",
+			 i,
+			 rx_ring->rx_stats.realloc_count,
+			 rx_ring->rx_stats.page_reuse_count);
+		dev_info(&pf->pdev->dev,
 			 "    rx_rings[%i]: size = %i, dma = 0x%08lx\n",
 			 i, rx_ring->size,
 			 (unsigned long int)rx_ring->dma);
@@ -533,6 +302,10 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 "    rx_rings[%i]: vsi = %p, q_vector = %p\n",
 			 i, rx_ring->vsi,
 			 rx_ring->q_vector);
+		dev_info(&pf->pdev->dev,
+			 "    rx_rings[%i]: rx_itr_setting = %d (%s)\n",
+			 i, rx_ring->rx_itr_setting,
+			 ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed");
 	}
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[i]);
@@ -557,8 +330,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 "    tx_rings[%i]: dtype = %d\n",
 			 i, tx_ring->dtype);
 		dev_info(&pf->pdev->dev,
-			 "    tx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
-			 i, tx_ring->hsplit,
+			 "    tx_rings[%i]: next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
+			 i,
 			 tx_ring->next_to_use,
 			 tx_ring->next_to_clean,
 			 tx_ring->ring_active);
@@ -583,14 +356,15 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 		dev_info(&pf->pdev->dev,
 			 "    tx_rings[%i]: DCB tc = %d\n",
 			 i, tx_ring->dcb_tc);
+		dev_info(&pf->pdev->dev,
+			 "    tx_rings[%i]: tx_itr_setting = %d (%s)\n",
+			 i, tx_ring->tx_itr_setting,
+			 ITR_IS_DYNAMIC(tx_ring->tx_itr_setting) ? "dynamic" : "fixed");
 	}
 	rcu_read_unlock();
 	dev_info(&pf->pdev->dev,
-		 "    work_limit = %d, rx_itr_setting = %d (%s), tx_itr_setting = %d (%s)\n",
-		 vsi->work_limit, vsi->rx_itr_setting,
-		 ITR_IS_DYNAMIC(vsi->rx_itr_setting) ? "dynamic" : "fixed",
-		 vsi->tx_itr_setting,
-		 ITR_IS_DYNAMIC(vsi->tx_itr_setting) ? "dynamic" : "fixed");
+		 "    work_limit = %d\n",
+		 vsi->work_limit);
 	dev_info(&pf->pdev->dev,
 		 "    max_frame = %d, rx_hdr_len = %d, rx_buf_len = %d dtype = %d\n",
 		 vsi->max_frame, vsi->rx_hdr_len, vsi->rx_buf_len, vsi->dtype);
@@ -815,20 +589,20 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
 			if (!is_rx_ring) {
 				txd = I40E_TX_DESC(ring, i);
 				dev_info(&pf->pdev->dev,
-					 "   d[%03i] = 0x%016llx 0x%016llx\n",
+					 "   d[%03x] = 0x%016llx 0x%016llx\n",
 					 i, txd->buffer_addr,
 					 txd->cmd_type_offset_bsz);
 			} else if (sizeof(union i40e_rx_desc) ==
 				   sizeof(union i40e_16byte_rx_desc)) {
 				rxd = I40E_RX_DESC(ring, i);
 				dev_info(&pf->pdev->dev,
-					 "   d[%03i] = 0x%016llx 0x%016llx\n",
+					 "   d[%03x] = 0x%016llx 0x%016llx\n",
 					 i, rxd->read.pkt_addr,
 					 rxd->read.hdr_addr);
 			} else {
 				rxd = I40E_RX_DESC(ring, i);
 				dev_info(&pf->pdev->dev,
-					 "   d[%03i] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
+					 "   d[%03x] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
 					 i, rxd->read.pkt_addr,
 					 rxd->read.hdr_addr,
 					 rxd->read.rsvd1, rxd->read.rsvd2);
@@ -843,20 +617,20 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
 		if (!is_rx_ring) {
 			txd = I40E_TX_DESC(ring, desc_n);
 			dev_info(&pf->pdev->dev,
-				 "vsi = %02i tx ring = %02i d[%03i] = 0x%016llx 0x%016llx\n",
+				 "vsi = %02i tx ring = %02i d[%03x] = 0x%016llx 0x%016llx\n",
 				 vsi_seid, ring_id, desc_n,
 				 txd->buffer_addr, txd->cmd_type_offset_bsz);
 		} else if (sizeof(union i40e_rx_desc) ==
 			   sizeof(union i40e_16byte_rx_desc)) {
 			rxd = I40E_RX_DESC(ring, desc_n);
 			dev_info(&pf->pdev->dev,
-				 "vsi = %02i rx ring = %02i d[%03i] = 0x%016llx 0x%016llx\n",
+				 "vsi = %02i rx ring = %02i d[%03x] = 0x%016llx 0x%016llx\n",
 				 vsi_seid, ring_id, desc_n,
 				 rxd->read.pkt_addr, rxd->read.hdr_addr);
 		} else {
 			rxd = I40E_RX_DESC(ring, desc_n);
 			dev_info(&pf->pdev->dev,
-				 "vsi = %02i rx ring = %02i d[%03i] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
+				 "vsi = %02i rx ring = %02i d[%03x] = 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
 				 vsi_seid, ring_id, desc_n,
 				 rxd->read.pkt_addr, rxd->read.hdr_addr,
 				 rxd->read.rsvd1, rxd->read.rsvd2);
@@ -918,12 +692,6 @@ static void i40e_dbg_dump_veb_seid(struct i40e_pf *pf, int seid)
 {
 	struct i40e_veb *veb;
 
-	if ((seid < I40E_BASE_VEB_SEID) ||
-	    (seid >= (I40E_MAX_VEB + I40E_BASE_VEB_SEID))) {
-		dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
-		return;
-	}
-
 	veb = i40e_dbg_find_veb(pf, seid);
 	if (!veb) {
 		dev_info(&pf->pdev->dev, "can't find veb %d\n", seid);
@@ -2202,11 +1970,6 @@ void i40e_dbg_pf_init(struct i40e_pf *pf)
 	if (!pfile)
 		goto create_failed;
 
-	pfile = debugfs_create_file("dump", 0600, pf->i40e_dbg_pf, pf,
-				    &i40e_dbg_dump_fops);
-	if (!pfile)
-		goto create_failed;
-
 	pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf,
 				    &i40e_dbg_netdev_ops_fops);
 	if (!pfile)
@@ -2227,9 +1990,6 @@ void i40e_dbg_pf_exit(struct i40e_pf *pf)
 {
 	debugfs_remove_recursive(pf->i40e_dbg_pf);
 	pf->i40e_dbg_pf = NULL;
-
-	kfree(i40e_dbg_dump_buf);
-	i40e_dbg_dump_buf = NULL;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h
index 448ef4c..99257fc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h
@@ -39,13 +39,11 @@
 #define I40E_DEV_ID_20G_KR2		0x1587
 #define I40E_DEV_ID_20G_KR2_A		0x1588
 #define I40E_DEV_ID_10G_BASE_T4		0x1589
-#define I40E_DEV_ID_VF			0x154C
-#define I40E_DEV_ID_VF_HV		0x1571
+#define I40E_DEV_ID_KX_X722		0x37CE
+#define I40E_DEV_ID_QSFP_X722		0x37CF
 #define I40E_DEV_ID_SFP_X722		0x37D0
 #define I40E_DEV_ID_1G_BASE_T_X722	0x37D1
 #define I40E_DEV_ID_10G_BASE_T_X722	0x37D2
-#define I40E_DEV_ID_X722_VF		0x37CD
-#define I40E_DEV_ID_X722_VF_HV		0x37D9
 
 #define i40e_is_40G_device(d)		((d) == I40E_DEV_ID_QSFP_A  || \
 					 (d) == I40E_DEV_ID_QSFP_B  || \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 29d5833..784b165 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -89,6 +89,9 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = {
 	I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
 	I40E_VSI_STAT("tx_linearize", tx_linearize),
 	I40E_VSI_STAT("tx_force_wb", tx_force_wb),
+	I40E_VSI_STAT("tx_lost_interrupt", tx_lost_interrupt),
+	I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed),
+	I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
 };
 
 /* These PF_STATs might look like duplicates of some NETDEV_STATs,
@@ -143,6 +146,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_oversize", stats.rx_oversize),
 	I40E_PF_STAT("rx_jabber", stats.rx_jabber),
 	I40E_PF_STAT("VF_admin_queue_requests", vf_aq_requests),
+	I40E_PF_STAT("arq_overflows", arq_overflows),
 	I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 	I40E_PF_STAT("fdir_flush_cnt", fd_flush_cnt),
 	I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match),
@@ -232,6 +236,7 @@ static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = {
 	"flow-director-atr",
 	"veb-stats",
 	"packet-split",
+	"hw-atr-eviction",
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings)
@@ -340,7 +345,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 				  SUPPORTED_1000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
 			ecmd->advertising |= ADVERTISED_1000baseT_Full;
-		if (pf->hw.mac.type == I40E_MAC_X722) {
+		if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
 			ecmd->supported |= SUPPORTED_100baseT_Full;
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_100MB)
@@ -411,6 +416,10 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw,
 		if (pf->hw.mac.type == I40E_MAC_X722) {
 			ecmd->supported |= SUPPORTED_100baseT_Full;
 			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
+				ecmd->supported |= SUPPORTED_100baseT_Full;
+				ecmd->advertising |= ADVERTISED_100baseT_Full;
+			}
 		}
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_XAUI ||
@@ -996,16 +1005,19 @@ static int i40e_get_eeprom(struct net_device *netdev,
 	/* check for NVMUpdate access method */
 	magic = hw->vendor_id | (hw->device_id << 16);
 	if (eeprom->magic && eeprom->magic != magic) {
-		struct i40e_nvm_access *cmd;
-		int errno;
+		struct i40e_nvm_access *cmd = (struct i40e_nvm_access *)eeprom;
+		int errno = 0;
 
 		/* make sure it is the right magic for NVMUpdate */
 		if ((eeprom->magic >> 16) != hw->device_id)
-			return -EINVAL;
+			errno = -EINVAL;
+		else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
+			 test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+			errno = -EBUSY;
+		else
+			ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
 
-		cmd = (struct i40e_nvm_access *)eeprom;
-		ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
-		if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM))
+		if ((errno || ret_val) && (hw->debug_mask & I40E_DEBUG_NVM))
 			dev_info(&pf->pdev->dev,
 				 "NVMUpdate read failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n",
 				 ret_val, hw->aq.asq_last_status, errno,
@@ -1089,27 +1101,25 @@ static int i40e_set_eeprom(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_hw *hw = &np->vsi->back->hw;
 	struct i40e_pf *pf = np->vsi->back;
-	struct i40e_nvm_access *cmd;
+	struct i40e_nvm_access *cmd = (struct i40e_nvm_access *)eeprom;
 	int ret_val = 0;
-	int errno;
+	int errno = 0;
 	u32 magic;
 
 	/* normal ethtool set_eeprom is not supported */
 	magic = hw->vendor_id | (hw->device_id << 16);
 	if (eeprom->magic == magic)
-		return -EOPNOTSUPP;
-
+		errno = -EOPNOTSUPP;
 	/* check for NVMUpdate access method */
-	if (!eeprom->magic || (eeprom->magic >> 16) != hw->device_id)
-		return -EINVAL;
-
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
-	    test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
-		return -EBUSY;
+	else if (!eeprom->magic || (eeprom->magic >> 16) != hw->device_id)
+		errno = -EINVAL;
+	else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
+		 test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state))
+		errno = -EBUSY;
+	else
+		ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
 
-	cmd = (struct i40e_nvm_access *)eeprom;
-	ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
-	if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM))
+	if ((errno || ret_val) && (hw->debug_mask & I40E_DEBUG_NVM))
 		dev_info(&pf->pdev->dev,
 			 "NVMUpdate write failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n",
 			 ret_val, hw->aq.asq_last_status, errno,
@@ -1816,28 +1826,52 @@ static int i40e_set_phys_id(struct net_device *netdev,
 			    enum ethtool_phys_id_state state)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	i40e_status ret = 0;
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	int blink_freq = 2;
+	u16 temp_status;
 
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
-		pf->led_status = i40e_led_get(hw);
+		if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) {
+			pf->led_status = i40e_led_get(hw);
+		} else {
+			i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_PORT, NULL);
+			ret = i40e_led_get_phy(hw, &temp_status,
+					       &pf->phy_led_val);
+			pf->led_status = temp_status;
+		}
 		return blink_freq;
 	case ETHTOOL_ID_ON:
-		i40e_led_set(hw, 0xF, false);
+		if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY))
+			i40e_led_set(hw, 0xf, false);
+		else
+			ret = i40e_led_set_phy(hw, true, pf->led_status, 0);
 		break;
 	case ETHTOOL_ID_OFF:
-		i40e_led_set(hw, 0x0, false);
+		if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY))
+			i40e_led_set(hw, 0x0, false);
+		else
+			ret = i40e_led_set_phy(hw, false, pf->led_status, 0);
 		break;
 	case ETHTOOL_ID_INACTIVE:
-		i40e_led_set(hw, pf->led_status, false);
+		if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) {
+			i40e_led_set(hw, false, pf->led_status);
+		} else {
+			ret = i40e_led_set_phy(hw, false, pf->led_status,
+					       (pf->phy_led_val |
+					       I40E_PHY_LED_MODE_ORIG));
+			i40e_aq_set_phy_debug(hw, 0, NULL);
+		}
 		break;
 	default:
 		break;
 	}
-
-	return 0;
+		if (ret)
+			return -ENOENT;
+		else
+			return 0;
 }
 
 /* NOTE: i40e hardware uses a conversion factor of 2 for Interrupt
@@ -1845,8 +1879,9 @@ static int i40e_set_phys_id(struct net_device *netdev,
  * 125us (8000 interrupts per second) == ITR(62)
  */
 
-static int i40e_get_coalesce(struct net_device *netdev,
-			     struct ethtool_coalesce *ec)
+static int __i40e_get_coalesce(struct net_device *netdev,
+			       struct ethtool_coalesce *ec,
+			       int queue)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1854,14 +1889,24 @@ static int i40e_get_coalesce(struct net_device *netdev,
 	ec->tx_max_coalesced_frames_irq = vsi->work_limit;
 	ec->rx_max_coalesced_frames_irq = vsi->work_limit;
 
-	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting))
+	/* rx and tx usecs has per queue value. If user doesn't specify the queue,
+	 * return queue 0's value to represent.
+	 */
+	if (queue < 0) {
+		queue = 0;
+	} else if (queue >= vsi->num_queue_pairs) {
+		return -EINVAL;
+	}
+
+	if (ITR_IS_DYNAMIC(vsi->rx_rings[queue]->rx_itr_setting))
 		ec->use_adaptive_rx_coalesce = 1;
 
-	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting))
+	if (ITR_IS_DYNAMIC(vsi->tx_rings[queue]->tx_itr_setting))
 		ec->use_adaptive_tx_coalesce = 1;
 
-	ec->rx_coalesce_usecs = vsi->rx_itr_setting & ~I40E_ITR_DYNAMIC;
-	ec->tx_coalesce_usecs = vsi->tx_itr_setting & ~I40E_ITR_DYNAMIC;
+	ec->rx_coalesce_usecs = vsi->rx_rings[queue]->rx_itr_setting & ~I40E_ITR_DYNAMIC;
+	ec->tx_coalesce_usecs = vsi->tx_rings[queue]->tx_itr_setting & ~I40E_ITR_DYNAMIC;
+
 	/* we use the _usecs_high to store/set the interrupt rate limit
 	 * that the hardware supports, that almost but not quite
 	 * fits the original intent of the ethtool variable,
@@ -1874,15 +1919,63 @@ static int i40e_get_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static int i40e_set_coalesce(struct net_device *netdev,
+static int i40e_get_coalesce(struct net_device *netdev,
 			     struct ethtool_coalesce *ec)
 {
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	return __i40e_get_coalesce(netdev, ec, -1);
+}
+
+static int i40e_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
+				       struct ethtool_coalesce *ec)
+{
+	return __i40e_get_coalesce(netdev, ec, queue);
+}
+
+static void i40e_set_itr_per_queue(struct i40e_vsi *vsi,
+				   struct ethtool_coalesce *ec,
+				   int queue)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
 	struct i40e_q_vector *q_vector;
+	u16 vector, intrl;
+
+	intrl = INTRL_USEC_TO_REG(vsi->int_rate_limit);
+
+	vsi->rx_rings[queue]->rx_itr_setting = ec->rx_coalesce_usecs;
+	vsi->tx_rings[queue]->tx_itr_setting = ec->tx_coalesce_usecs;
+
+	if (ec->use_adaptive_rx_coalesce)
+		vsi->rx_rings[queue]->rx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->rx_rings[queue]->rx_itr_setting &= ~I40E_ITR_DYNAMIC;
+
+	if (ec->use_adaptive_tx_coalesce)
+		vsi->tx_rings[queue]->tx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->tx_rings[queue]->tx_itr_setting &= ~I40E_ITR_DYNAMIC;
+
+	q_vector = vsi->rx_rings[queue]->q_vector;
+	q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[queue]->rx_itr_setting);
+	vector = vsi->base_vector + q_vector->v_idx;
+	wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr);
+
+	q_vector = vsi->tx_rings[queue]->q_vector;
+	q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[queue]->tx_itr_setting);
+	vector = vsi->base_vector + q_vector->v_idx;
+	wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr);
+
+	wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl);
+	i40e_flush(hw);
+}
+
+static int __i40e_set_coalesce(struct net_device *netdev,
+			       struct ethtool_coalesce *ec,
+			       int queue)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	u16 vector;
 	int i;
 
 	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
@@ -1899,57 +1992,53 @@ static int i40e_set_coalesce(struct net_device *netdev,
 		return -EINVAL;
 	}
 
-	vector = vsi->base_vector;
-	if ((ec->rx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
-	    (ec->rx_coalesce_usecs <= (I40E_MAX_ITR << 1))) {
-		vsi->rx_itr_setting = ec->rx_coalesce_usecs;
-	} else if (ec->rx_coalesce_usecs == 0) {
-		vsi->rx_itr_setting = ec->rx_coalesce_usecs;
+	if (ec->rx_coalesce_usecs == 0) {
 		if (ec->use_adaptive_rx_coalesce)
 			netif_info(pf, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n");
-	} else {
-		netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
-		return -EINVAL;
+	} else if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
+		   (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1))) {
+			netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
+			return -EINVAL;
 	}
 
 	vsi->int_rate_limit = ec->rx_coalesce_usecs_high;
 
-	if ((ec->tx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
-	    (ec->tx_coalesce_usecs <= (I40E_MAX_ITR << 1))) {
-		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
-	} else if (ec->tx_coalesce_usecs == 0) {
-		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
+	if (ec->tx_coalesce_usecs == 0) {
 		if (ec->use_adaptive_tx_coalesce)
 			netif_info(pf, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n");
+	} else if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
+		   (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1))) {
+			netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n");
+			return -EINVAL;
+	}
+
+	/* rx and tx usecs has per queue value. If user doesn't specify the queue,
+	 * apply to all queues.
+	 */
+	if (queue < 0) {
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			i40e_set_itr_per_queue(vsi, ec, i);
+	} else if (queue < vsi->num_queue_pairs) {
+		i40e_set_itr_per_queue(vsi, ec, queue);
 	} else {
-		netif_info(pf, drv, netdev,
-			   "Invalid value, tx-usecs range is 0-8160\n");
+		netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n",
+			   vsi->num_queue_pairs - 1);
 		return -EINVAL;
 	}
 
-	if (ec->use_adaptive_rx_coalesce)
-		vsi->rx_itr_setting |= I40E_ITR_DYNAMIC;
-	else
-		vsi->rx_itr_setting &= ~I40E_ITR_DYNAMIC;
-
-	if (ec->use_adaptive_tx_coalesce)
-		vsi->tx_itr_setting |= I40E_ITR_DYNAMIC;
-	else
-		vsi->tx_itr_setting &= ~I40E_ITR_DYNAMIC;
-
-	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
-		u16 intrl = INTRL_USEC_TO_REG(vsi->int_rate_limit);
+	return 0;
+}
 
-		q_vector = vsi->q_vectors[i];
-		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
-		wr32(hw, I40E_PFINT_ITRN(0, vector - 1), q_vector->rx.itr);
-		q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
-		wr32(hw, I40E_PFINT_ITRN(1, vector - 1), q_vector->tx.itr);
-		wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl);
-		i40e_flush(hw);
-	}
+static int i40e_set_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *ec)
+{
+	return __i40e_set_coalesce(netdev, ec, -1);
+}
 
-	return 0;
+static int i40e_set_per_queue_coalesce(struct net_device *netdev, u32 queue,
+				       struct ethtool_coalesce *ec)
+{
+	return __i40e_set_coalesce(netdev, ec, queue);
 }
 
 /**
@@ -2147,8 +2236,8 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 {
 	struct i40e_hw *hw = &pf->hw;
-	u64 hena = (u64)rd32(hw, I40E_PFQF_HENA(0)) |
-		   ((u64)rd32(hw, I40E_PFQF_HENA(1)) << 32);
+	u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
+		   ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
 
 	/* RSS does not support anything other than hashing
 	 * to queues on src and dst IPs and ports
@@ -2166,9 +2255,12 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+				hena |=
+			   BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
 			break;
 		default:
@@ -2178,9 +2270,12 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+				hena |=
+			   BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK);
+
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
 			break;
 		default:
@@ -2190,10 +2285,13 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+				hena |=
+			    BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+			    BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP);
+
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
 			break;
@@ -2204,10 +2302,13 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+				hena |=
+			    BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+			    BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP);
+
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
 			break;
@@ -2245,8 +2346,8 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		return -EINVAL;
 	}
 
-	wr32(hw, I40E_PFQF_HENA(0), (u32)hena);
-	wr32(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
 	i40e_flush(hw);
 
 	/* Save setting for future output/update */
@@ -2712,6 +2813,8 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 		I40E_PRIV_FLAGS_VEB_STATS : 0;
 	ret_flags |= pf->flags & I40E_FLAG_RX_PS_ENABLED ?
 		I40E_PRIV_FLAGS_PS : 0;
+	ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
+		0 : I40E_PRIV_FLAGS_HW_ATR_EVICT;
 
 	return ret_flags;
 }
@@ -2763,10 +2866,21 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
 	}
 
-	if (flags & I40E_PRIV_FLAGS_VEB_STATS)
+	if ((flags & I40E_PRIV_FLAGS_VEB_STATS) &&
+	    !(pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
 		pf->flags |= I40E_FLAG_VEB_STATS_ENABLED;
-	else
+		reset_required = true;
+	} else if (!(flags & I40E_PRIV_FLAGS_VEB_STATS) &&
+		   (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
 		pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
+		reset_required = true;
+	}
+
+	if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) &&
+	    (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))
+		pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+	else
+		pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 
 	/* if needed, issue reset to cause things to take effect */
 	if (reset_required)
@@ -2812,6 +2926,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.get_ts_info		= i40e_get_ts_info,
 	.get_priv_flags		= i40e_get_priv_flags,
 	.set_priv_flags		= i40e_set_priv_flags,
+	.get_per_queue_coalesce	= i40e_get_per_queue_coalesce,
+	.set_per_queue_coalesce	= i40e_set_per_queue_coalesce,
 };
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 579a46c..8ad162c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -295,11 +295,11 @@ void i40e_init_pf_fcoe(struct i40e_pf *pf)
 	}
 
 	/* enable FCoE hash filter */
-	val = rd32(hw, I40E_PFQF_HENA(1));
+	val = i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1));
 	val |= BIT(I40E_FILTER_PCTYPE_FCOE_OX - 32);
 	val |= BIT(I40E_FILTER_PCTYPE_FCOE_RX - 32);
 	val &= I40E_PFQF_HENA_PTYPE_ENA_MASK;
-	wr32(hw, I40E_PFQF_HENA(1), val);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), val);
 
 	/* enable flag */
 	pf->flags |= I40E_FLAG_FCOE_ENABLED;
@@ -317,11 +317,11 @@ void i40e_init_pf_fcoe(struct i40e_pf *pf)
 	pf->filter_settings.fcoe_cntx_num = I40E_DMA_CNTX_SIZE_4K;
 
 	/* Setup max frame with FCoE_MTU plus L2 overheads */
-	val = rd32(hw, I40E_GLFCOE_RCTL);
+	val = i40e_read_rx_ctl(hw, I40E_GLFCOE_RCTL);
 	val &= ~I40E_GLFCOE_RCTL_MAX_SIZE_MASK;
 	val |= ((FCOE_MTU + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 		 << I40E_GLFCOE_RCTL_MAX_SIZE_SHIFT);
-	wr32(hw, I40E_GLFCOE_RCTL, val);
+	i40e_write_rx_ctl(hw, I40E_GLFCOE_RCTL, val);
 
 	dev_info(&pf->pdev->dev, "FCoE is supported.\n");
 }
@@ -1359,16 +1359,32 @@ static netdev_tx_t i40e_fcoe_xmit_frame(struct sk_buff *skb,
 	struct i40e_ring *tx_ring = vsi->tx_rings[skb->queue_mapping];
 	struct i40e_tx_buffer *first;
 	u32 tx_flags = 0;
+	int fso, count;
 	u8 hdr_len = 0;
 	u8 sof = 0;
 	u8 eof = 0;
-	int fso;
 
 	if (i40e_fcoe_set_skb_header(skb))
 		goto out_drop;
 
-	if (!i40e_xmit_descriptor_count(skb, tx_ring))
+	count = i40e_xmit_descriptor_count(skb);
+	if (i40e_chk_linearize(skb, count)) {
+		if (__skb_linearize(skb))
+			goto out_drop;
+		count = TXD_USE_COUNT(skb->len);
+		tx_ring->tx_stats.tx_linearize++;
+	}
+
+	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
+	 *       + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
+	 *       + 4 desc gap to avoid the cache line where head is,
+	 *       + 1 desc for context descriptor,
+	 * otherwise try next time
+	 */
+	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+		tx_ring->tx_stats.tx_busy++;
 		return NETDEV_TX_BUSY;
+	}
 
 	/* prepare the xmit flags */
 	if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
@@ -1457,7 +1473,7 @@ static const struct net_device_ops i40e_fcoe_netdev_ops = {
 	.ndo_tx_timeout		= i40e_tx_timeout,
 	.ndo_vlan_rx_add_vid	= i40e_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= i40e_vlan_rx_kill_vid,
-	.ndo_setup_tc		= i40e_setup_tc,
+	.ndo_setup_tc		= __i40e_setup_tc,
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= i40e_netpoll,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 8f3b53e..70d9605 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -28,11 +28,6 @@
 #include <linux/of_net.h>
 #include <linux/pci.h>
 
-#ifdef CONFIG_SPARC
-#include <asm/idprom.h>
-#include <asm/prom.h>
-#endif
-
 /* Local includes */
 #include "i40e.h"
 #include "i40e_diag.h"
@@ -51,7 +46,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 4
-#define DRV_VERSION_BUILD 8
+#define DRV_VERSION_BUILD 25
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -90,6 +85,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0},
@@ -110,6 +107,8 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
+static struct workqueue_struct *i40e_wq;
+
 /**
  * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code
  * @hw:   pointer to the HW structure
@@ -295,7 +294,7 @@ static void i40e_service_event_schedule(struct i40e_pf *pf)
 	if (!test_bit(__I40E_DOWN, &pf->state) &&
 	    !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) &&
 	    !test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
-		schedule_work(&pf->service_task);
+		queue_work(i40e_wq, &pf->service_task);
 }
 
 /**
@@ -769,7 +768,7 @@ static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
 	if (vsi->type != I40E_VSI_FCOE)
 		return;
 
-	idx = (pf->pf_seid - I40E_BASE_PF_SEID) + I40E_FCOE_PF_STAT_OFFSET;
+	idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET;
 	fs = &vsi->fcoe_stats;
 	ofs = &vsi->fcoe_stats_offsets;
 
@@ -820,6 +819,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	struct i40e_eth_stats *oes;
 	struct i40e_eth_stats *es;     /* device's eth stats */
 	u32 tx_restart, tx_busy;
+	u64 tx_lost_interrupt;
 	struct i40e_ring *p;
 	u32 rx_page, rx_buf;
 	u64 bytes, packets;
@@ -845,6 +845,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	rx_b = rx_p = 0;
 	tx_b = tx_p = 0;
 	tx_restart = tx_busy = tx_linearize = tx_force_wb = 0;
+	tx_lost_interrupt = 0;
 	rx_page = 0;
 	rx_buf = 0;
 	rcu_read_lock();
@@ -863,6 +864,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 		tx_busy += p->tx_stats.tx_busy;
 		tx_linearize += p->tx_stats.tx_linearize;
 		tx_force_wb += p->tx_stats.tx_force_wb;
+		tx_lost_interrupt += p->tx_stats.tx_lost_interrupt;
 
 		/* Rx queue is part of the same block as Tx queue */
 		p = &p[1];
@@ -881,6 +883,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	vsi->tx_busy = tx_busy;
 	vsi->tx_linearize = tx_linearize;
 	vsi->tx_force_wb = tx_force_wb;
+	vsi->tx_lost_interrupt = tx_lost_interrupt;
 	vsi->rx_page_failed = rx_page;
 	vsi->rx_buf_failed = rx_buf;
 
@@ -1368,7 +1371,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 		f->changed = true;
 
 		INIT_LIST_HEAD(&f->list);
-		list_add(&f->list, &vsi->mac_filter_list);
+		list_add_tail(&f->list, &vsi->mac_filter_list);
 	}
 
 	/* increment counter and add a new flag if needed */
@@ -1538,7 +1541,11 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 
 	ether_addr_copy(netdev->dev_addr, addr->sa_data);
 
-	return i40e_sync_vsi_filters(vsi);
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
+	return 0;
 }
 
 /**
@@ -1762,6 +1769,11 @@ bottom_of_search_loop:
 		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
 		vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
 	}
+
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
 }
 
 /**
@@ -1933,7 +1945,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
 		del_list_size = filter_list_len *
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
-		del_list = kzalloc(del_list_size, GFP_KERNEL);
+		del_list = kzalloc(del_list_size, GFP_ATOMIC);
 		if (!del_list) {
 			i40e_cleanup_add_list(&tmp_add_list);
 
@@ -2011,7 +2023,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			       sizeof(struct i40e_aqc_add_macvlan_element_data),
 		add_list_size = filter_list_len *
 			       sizeof(struct i40e_aqc_add_macvlan_element_data);
-		add_list = kzalloc(add_list_size, GFP_KERNEL);
+		add_list = kzalloc(add_list_size, GFP_ATOMIC);
 		if (!add_list) {
 			/* Purge element from temporary lists */
 			i40e_cleanup_add_list(&tmp_add_list);
@@ -2110,7 +2122,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
 			       test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
 					&vsi->state));
-		if (vsi->type == I40E_VSI_MAIN && pf->lan_veb != I40E_NO_VEB) {
+		if ((vsi->type == I40E_VSI_MAIN) &&
+		    (pf->lan_veb != I40E_NO_VEB) &&
+		    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
 			/* set defport ON for Main VSI instead of true promisc
 			 * this way we will get all unicast/multicast and VLAN
 			 * promisc behavior but will not get VF or VMDq traffic
@@ -2160,6 +2174,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 	}
 out:
+	/* if something went wrong then set the changed flag so we try again */
+	if (retval)
+		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+
 	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
 	return retval;
 }
@@ -3106,11 +3124,11 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 		struct i40e_q_vector *q_vector = vsi->q_vectors[i];
 
 		q_vector->itr_countdown = ITR_COUNTDOWN_START;
-		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+		q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[i]->rx_itr_setting);
 		q_vector->rx.latency_range = I40E_LOW_LATENCY;
 		wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
 		     q_vector->rx.itr);
-		q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+		q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[i]->tx_itr_setting);
 		q_vector->tx.latency_range = I40E_LOW_LATENCY;
 		wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1),
 		     q_vector->tx.itr);
@@ -3202,10 +3220,10 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 
 	/* set the ITR configuration */
 	q_vector->itr_countdown = ITR_COUNTDOWN_START;
-	q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+	q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[0]->rx_itr_setting);
 	q_vector->rx.latency_range = I40E_LOW_LATENCY;
 	wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr);
-	q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+	q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[0]->tx_itr_setting);
 	q_vector->tx.latency_range = I40E_LOW_LATENCY;
 	wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr);
 
@@ -3245,14 +3263,15 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf)
 /**
  * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0
  * @pf: board private structure
+ * @clearpba: true when all pending interrupt events should be cleared
  **/
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf)
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTL0_INTENA_MASK   |
-	      I40E_PFINT_DYN_CTL0_CLEARPBA_MASK |
+	      (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT);
 
 	wr32(hw, I40E_PFINT_DYN_CTL0, val);
@@ -3260,22 +3279,6 @@ void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf)
 }
 
 /**
- * i40e_irq_dynamic_disable - Disable default interrupt generation settings
- * @vsi: pointer to a vsi
- * @vector: disable a particular Hw Interrupt vector
- **/
-void i40e_irq_dynamic_disable(struct i40e_vsi *vsi, int vector)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	u32 val;
-
-	val = I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT;
-	wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val);
-	i40e_flush(hw);
-}
-
-/**
  * i40e_msix_clean_rings - MSIX mode Interrupt Handler
  * @irq: interrupt number
  * @data: pointer to a q_vector
@@ -3400,7 +3403,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_irq_dynamic_enable(vsi, i);
 	} else {
-		i40e_irq_dynamic_enable_icr0(pf);
+		i40e_irq_dynamic_enable_icr0(pf, true);
 	}
 
 	i40e_flush(&pf->hw);
@@ -3459,16 +3462,12 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 		struct i40e_q_vector *q_vector = vsi->q_vectors[0];
 
-		/* temporarily disable queue cause for NAPI processing */
-		u32 qval = rd32(hw, I40E_QINT_RQCTL(0));
-
-		qval &= ~I40E_QINT_RQCTL_CAUSE_ENA_MASK;
-		wr32(hw, I40E_QINT_RQCTL(0), qval);
-
-		qval = rd32(hw, I40E_QINT_TQCTL(0));
-		qval &= ~I40E_QINT_TQCTL_CAUSE_ENA_MASK;
-		wr32(hw, I40E_QINT_TQCTL(0), qval);
-
+		/* We do not have a way to disarm Queue causes while leaving
+		 * interrupt enabled for all other causes, ideally
+		 * interrupt should be disabled while we are in NAPI but
+		 * this is not a performance path and napi_schedule()
+		 * can deal with rescheduling.
+		 */
 		if (!test_bit(__I40E_DOWN, &pf->state))
 			napi_schedule_irqoff(&q_vector->napi);
 	}
@@ -3476,6 +3475,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 	if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
 		set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+		i40e_debug(&pf->hw, I40E_DEBUG_NVM, "AdminQ event\n");
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
@@ -3546,7 +3546,7 @@ enable_intr:
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
 	if (!test_bit(__I40E_DOWN, &pf->state)) {
 		i40e_service_event_schedule(pf);
-		i40e_irq_dynamic_enable_icr0(pf);
+		i40e_irq_dynamic_enable_icr0(pf, false);
 	}
 
 	return ret;
@@ -3750,7 +3750,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /**
- * i40e_netpoll - A Polling 'interrupt'handler
+ * i40e_netpoll - A Polling 'interrupt' handler
  * @netdev: network interface device structure
  *
  * This is used by netconsole to send skbs without having to re-enable
@@ -3929,6 +3929,9 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 		else
 			rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
 		wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
+		/* No waiting for the Tx queue to disable */
+		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
+			continue;
 
 		/* wait for the change to finish */
 		ret = i40e_pf_rxq_wait(pf, pf_q, enable);
@@ -4287,12 +4290,12 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
 
 #ifdef CONFIG_I40E_DCB
 /**
- * i40e_vsi_wait_txq_disabled - Wait for VSI's queues to be disabled
+ * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled
  * @vsi: the VSI being configured
  *
- * This function waits for the given VSI's Tx queues to be disabled.
+ * This function waits for the given VSI's queues to be disabled.
  **/
-static int i40e_vsi_wait_txq_disabled(struct i40e_vsi *vsi)
+static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
 	int i, pf_q, ret;
@@ -4309,24 +4312,36 @@ static int i40e_vsi_wait_txq_disabled(struct i40e_vsi *vsi)
 		}
 	}
 
+	pf_q = vsi->base_queue;
+	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+		/* Check and wait for the disable status of the queue */
+		ret = i40e_pf_rxq_wait(pf, pf_q, false);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "VSI seid %d Rx ring %d disable timeout\n",
+				 vsi->seid, pf_q);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
 /**
- * i40e_pf_wait_txq_disabled - Wait for all queues of PF VSIs to be disabled
+ * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled
  * @pf: the PF
  *
- * This function waits for the Tx queues to be in disabled state for all the
+ * This function waits for the queues to be in disabled state for all the
  * VSIs that are managed by this PF.
  **/
-static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf)
+static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 {
 	int v, ret = 0;
 
 	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
 		/* No need to wait for FCoE VSI queues */
 		if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
-			ret = i40e_vsi_wait_txq_disabled(pf->vsi[v]);
+			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
 				break;
 		}
@@ -4352,7 +4367,7 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 {
 	struct i40e_ring *tx_ring = NULL;
 	struct i40e_pf	*pf;
-	u32 head, val, tx_pending;
+	u32 head, val, tx_pending_hw;
 	int i;
 
 	pf = vsi->back;
@@ -4378,16 +4393,9 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 	else
 		val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
 
-	/* Bail out if interrupts are disabled because napi_poll
-	 * execution in-progress or will get scheduled soon.
-	 * napi_poll cleans TX and RX queues and updates 'next_to_clean'.
-	 */
-	if (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))
-		return;
-
 	head = i40e_get_head(tx_ring);
 
-	tx_pending = i40e_get_tx_pending(tx_ring);
+	tx_pending_hw = i40e_get_tx_pending(tx_ring, false);
 
 	/* HW is done executing descriptors, updated HEAD write back,
 	 * but SW hasn't processed those descriptors. If interrupt is
@@ -4395,12 +4403,12 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 	 * dev_watchdog detecting timeout on those netdev_queue,
 	 * hence proactively trigger SW interrupt.
 	 */
-	if (tx_pending) {
+	if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
 		/* NAPI Poll didn't run and clear since it was set */
 		if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT,
 				       &tx_ring->q_vector->hung_detected)) {
-			netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
-				    vsi->seid, q_idx, tx_pending,
+			netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
+				    vsi->seid, q_idx, tx_pending_hw,
 				    tx_ring->next_to_clean, head,
 				    tx_ring->next_to_use,
 				    readl(tx_ring->tail));
@@ -4413,6 +4421,17 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 				&tx_ring->q_vector->hung_detected);
 		}
 	}
+
+	/* This is the case where we have interrupts missing,
+	 * so the tx_pending in HW will most likely be 0, but we
+	 * will have tx_pending in SW since the WB happened but the
+	 * interrupt got lost.
+	 */
+	if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) &&
+	    (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
+		if (napi_reschedule(&tx_ring->q_vector->napi))
+			tx_ring->tx_stats.tx_lost_interrupt++;
+	}
 }
 
 /**
@@ -5016,8 +5035,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 	int err = 0;
 
 	/* Do not enable DCB for SW1 and SW2 images even if the FW is capable */
-	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
-	    (pf->hw.aq.fw_maj_ver < 4))
+	if (pf->flags & I40E_FLAG_NO_DCB_SUPPORT)
 		goto out;
 
 	/* Get the initial DCB configuration */
@@ -5249,11 +5267,7 @@ void i40e_down(struct i40e_vsi *vsi)
  * @netdev: net device to configure
  * @tc: number of traffic classes to enable
  **/
-#ifdef I40E_FCOE
-int i40e_setup_tc(struct net_device *netdev, u8 tc)
-#else
 static int i40e_setup_tc(struct net_device *netdev, u8 tc)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -5306,6 +5320,19 @@ exit:
 	return ret;
 }
 
+#ifdef I40E_FCOE
+int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
+		    struct tc_to_netdev *tc)
+#else
+static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
+			   struct tc_to_netdev *tc)
+#endif
+{
+	if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)
+		return -EINVAL;
+	return i40e_setup_tc(netdev, tc->tc);
+}
+
 /**
  * i40e_open - Called when a network interface is made active
  * @netdev: network interface device structure
@@ -5348,7 +5375,8 @@ int i40e_open(struct net_device *netdev)
 	vxlan_get_rx_port(netdev);
 #endif
 #ifdef CONFIG_I40E_GENEVE
-	geneve_get_rx_port(netdev);
+	if (pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)
+		geneve_get_rx_port(netdev);
 #endif
 
 	return 0;
@@ -5713,8 +5741,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	if (ret)
 		goto exit;
 
-	/* Wait for the PF's Tx queues to be disabled */
-	ret = i40e_pf_wait_txq_disabled(pf);
+	/* Wait for the PF's queues to be disabled */
+	ret = i40e_pf_wait_queues_disabled(pf);
 	if (ret) {
 		/* Schedule PF reset to recover */
 		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
@@ -6244,6 +6272,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 		if (hw->debug_mask & I40E_DEBUG_AQ)
 			dev_info(&pf->pdev->dev, "ARQ Overflow Error detected\n");
 		val &= ~I40E_PF_ARQLEN_ARQOVFL_MASK;
+		pf->arq_overflows++;
 	}
 	if (val & I40E_PF_ARQLEN_ARQCRIT_MASK) {
 		if (hw->debug_mask & I40E_DEBUG_AQ)
@@ -6319,7 +6348,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 		case i40e_aqc_opc_nvm_erase:
 		case i40e_aqc_opc_nvm_update:
 		case i40e_aqc_opc_oem_post_update:
-			i40e_debug(&pf->hw, I40E_DEBUG_NVM, "ARQ NVM operation completed\n");
+			i40e_debug(&pf->hw, I40E_DEBUG_NVM,
+				   "ARQ NVM operation 0x%04x completed\n",
+				   opcode);
 			break;
 		default:
 			dev_info(&pf->pdev->dev,
@@ -6803,12 +6834,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	if (ret)
 		goto end_core_reset;
 
-	/* driver is only interested in link up/down and module qualification
-	 * reports from firmware
+	/* The driver only wants link up/down and module qualification
+	 * reports from firmware.  Note the negative logic.
 	 */
 	ret = i40e_aq_set_phy_int_mask(&pf->hw,
-				       I40E_AQ_EVENT_LINK_UPDOWN |
-				       I40E_AQ_EVENT_MODULE_QUAL_FAIL, NULL);
+				       ~(I40E_AQ_EVENT_LINK_UPDOWN |
+					 I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL);
 	if (ret)
 		dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n",
 			 i40e_stat_str(&pf->hw, ret),
@@ -6889,8 +6920,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		wr32(hw, I40E_REG_MSS, val);
 	}
 
-	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
-	    (pf->hw.aq.fw_maj_ver < 4)) {
+	if (pf->flags & I40E_FLAG_RESTART_AUTONEG) {
 		msleep(75);
 		ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
 		if (ret)
@@ -7079,12 +7109,13 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 				ret = i40e_aq_del_udp_tunnel(hw, i, NULL);
 
 			if (ret) {
-				dev_info(&pf->pdev->dev,
-					 "%s vxlan port %d, index %d failed, err %s aq_err %s\n",
-					 port ? "add" : "delete",
-					 ntohs(port), i,
-					 i40e_stat_str(&pf->hw, ret),
-					 i40e_aq_str(&pf->hw,
+				dev_dbg(&pf->pdev->dev,
+					"%s %s port %d, index %d failed, err %s aq_err %s\n",
+					pf->udp_ports[i].type ? "vxlan" : "geneve",
+					port ? "add" : "delete",
+					ntohs(port), i,
+					i40e_stat_str(&pf->hw, ret),
+					i40e_aq_str(&pf->hw,
 						    pf->hw.aq.asq_last_status));
 				pf->udp_ports[i].index = 0;
 			}
@@ -7111,6 +7142,7 @@ static void i40e_service_task(struct work_struct *work)
 	}
 
 	i40e_detect_recover_hung(pf);
+	i40e_sync_filters_subtask(pf);
 	i40e_reset_subtask(pf);
 	i40e_handle_mdd_event(pf);
 	i40e_vc_process_vflr_event(pf);
@@ -7290,8 +7322,6 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	set_bit(__I40E_DOWN, &vsi->state);
 	vsi->flags = 0;
 	vsi->idx = vsi_idx;
-	vsi->rx_itr_setting = pf->rx_itr_default;
-	vsi->tx_itr_setting = pf->tx_itr_default;
 	vsi->int_rate_limit = 0;
 	vsi->rss_table_size = (vsi->type == I40E_VSI_MAIN) ?
 				pf->rss_table_size : 64;
@@ -7458,8 +7488,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		tx_ring->dcb_tc = 0;
 		if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
-		if (vsi->back->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)
-			tx_ring->flags |= I40E_TXR_FLAGS_OUTER_UDP_CSUM;
+		tx_ring->tx_itr_setting = pf->tx_itr_default;
 		vsi->tx_rings[i] = tx_ring;
 
 		rx_ring = &tx_ring[1];
@@ -7476,6 +7505,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 			set_ring_16byte_desc_enabled(rx_ring);
 		else
 			clear_ring_16byte_desc_enabled(rx_ring);
+		rx_ring->rx_itr_setting = pf->rx_itr_default;
 		vsi->rx_rings[i] = rx_ring;
 	}
 
@@ -7852,7 +7882,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 
 	i40e_flush(hw);
 
-	i40e_irq_dynamic_enable_icr0(pf);
+	i40e_irq_dynamic_enable_icr0(pf, true);
 
 	return err;
 }
@@ -7936,6 +7966,52 @@ static int i40e_vsi_config_rss(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands
+ * @vsi: Pointer to vsi structure
+ * @seed: Buffter to store the hash keys
+ * @lut: Buffer to store the lookup table entries
+ * @lut_size: Size of buffer to store the lookup table entries
+ *
+ * Return 0 on success, negative on failure
+ */
+static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
+			   u8 *lut, u16 lut_size)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	int ret = 0;
+
+	if (seed) {
+		ret = i40e_aq_get_rss_key(hw, vsi->id,
+			(struct i40e_aqc_get_set_rss_key_data *)seed);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "Cannot get RSS key, err %s aq_err %s\n",
+				 i40e_stat_str(&pf->hw, ret),
+				 i40e_aq_str(&pf->hw,
+					     pf->hw.aq.asq_last_status));
+			return ret;
+		}
+	}
+
+	if (lut) {
+		bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+
+		ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "Cannot get RSS lut, err %s aq_err %s\n",
+				 i40e_stat_str(&pf->hw, ret),
+				 i40e_aq_str(&pf->hw,
+					     pf->hw.aq.asq_last_status));
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+/**
  * i40e_config_rss_reg - Configure RSS keys and lut by writing registers
  * @vsi: Pointer to vsi structure
  * @seed: RSS hash seed
@@ -7956,7 +8032,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 		u32 *seed_dw = (u32 *)seed;
 
 		for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
-			wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
+			i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
 	}
 
 	if (lut) {
@@ -7993,7 +8069,7 @@ static int i40e_get_rss_reg(struct i40e_vsi *vsi, u8 *seed,
 		u32 *seed_dw = (u32 *)seed;
 
 		for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
-			seed_dw[i] = rd32(hw, I40E_PFQF_HKEY(i));
+			seed_dw[i] = i40e_read_rx_ctl(hw, I40E_PFQF_HKEY(i));
 	}
 	if (lut) {
 		u32 *lut_dw = (u32 *)lut;
@@ -8037,7 +8113,12 @@ int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
  */
 int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 {
-	return i40e_get_rss_reg(vsi, seed, lut, lut_size);
+	struct i40e_pf *pf = vsi->back;
+
+	if (pf->flags & I40E_FLAG_RSS_AQ_CAPABLE)
+		return i40e_get_rss_aq(vsi, seed, lut, lut_size);
+	else
+		return i40e_get_rss_reg(vsi, seed, lut, lut_size);
 }
 
 /**
@@ -8071,19 +8152,19 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	int ret;
 
 	/* By default we enable TCP/UDP with IPv4/IPv6 ptypes */
-	hena = (u64)rd32(hw, I40E_PFQF_HENA(0)) |
-		((u64)rd32(hw, I40E_PFQF_HENA(1)) << 32);
+	hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
+		((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
 	hena |= i40e_pf_get_default_rss_hena(pf);
 
-	wr32(hw, I40E_PFQF_HENA(0), (u32)hena);
-	wr32(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
 
 	/* Determine the RSS table size based on the hardware capabilities */
-	reg_val = rd32(hw, I40E_PFQF_CTL_0);
+	reg_val = i40e_read_rx_ctl(hw, I40E_PFQF_CTL_0);
 	reg_val = (pf->rss_table_size == 512) ?
 			(reg_val | I40E_PFQF_CTL_0_HASHLUTSIZE_512) :
 			(reg_val & ~I40E_PFQF_CTL_0_HASHLUTSIZE_512);
-	wr32(hw, I40E_PFQF_CTL_0, reg_val);
+	i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val);
 
 	/* Determine the RSS size of the VSI */
 	if (!vsi->rss_size)
@@ -8367,6 +8448,26 @@ static int i40e_sw_init(struct i40e_pf *pf)
 				 pf->hw.func_caps.fd_filters_best_effort;
 	}
 
+	if (i40e_is_mac_710(&pf->hw) &&
+	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
+	    (pf->hw.aq.fw_maj_ver < 4))) {
+		pf->flags |= I40E_FLAG_RESTART_AUTONEG;
+		/* No DCB support  for FW < v4.33 */
+		pf->flags |= I40E_FLAG_NO_DCB_SUPPORT;
+	}
+
+	/* Disable FW LLDP if FW < v4.3 */
+	if (i40e_is_mac_710(&pf->hw) &&
+	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) ||
+	    (pf->hw.aq.fw_maj_ver < 4)))
+		pf->flags |= I40E_FLAG_STOP_FW_LLDP;
+
+	/* Use the FW Set LLDP MIB API if FW > v4.40 */
+	if (i40e_is_mac_710(&pf->hw) &&
+	    (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver >= 40)) ||
+	    (pf->hw.aq.fw_maj_ver >= 5)))
+		pf->flags |= I40E_FLAG_USE_SET_LLDP_MIB;
+
 	if (pf->hw.func_caps.vmdq) {
 		pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
 		pf->flags |= I40E_FLAG_VMDQ_ENABLED;
@@ -8393,8 +8494,19 @@ static int i40e_sw_init(struct i40e_pf *pf)
 			     I40E_FLAG_OUTER_UDP_CSUM_CAPABLE |
 			     I40E_FLAG_WB_ON_ITR_CAPABLE |
 			     I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE |
+			     I40E_FLAG_100M_SGMII_CAPABLE |
+			     I40E_FLAG_USE_SET_LLDP_MIB |
 			     I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
+	} else if ((pf->hw.aq.api_maj_ver > 1) ||
+		   ((pf->hw.aq.api_maj_ver == 1) &&
+		    (pf->hw.aq.api_min_ver > 4))) {
+		/* Supported in FW API version higher than 1.4 */
+		pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
+		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+	} else {
+		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	}
+
 	pf->eeprom_version = 0xDEAD;
 	pf->lan_veb = I40E_NO_VEB;
 	pf->lan_vsi = I40E_NO_VSI;
@@ -8530,9 +8642,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
 	u8 next_idx;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
@@ -8572,9 +8681,6 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
 	struct i40e_pf *pf = vsi->back;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
@@ -8608,7 +8714,7 @@ static void i40e_add_geneve_port(struct net_device *netdev,
 	u8 next_idx;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
+	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
 		return;
 
 	idx = i40e_get_udp_port_idx(pf, port);
@@ -8652,7 +8758,7 @@ static void i40e_del_geneve_port(struct net_device *netdev,
 	struct i40e_pf *pf = vsi->back;
 	u8 idx;
 
-	if (sa_family == AF_INET6)
+	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
 		return;
 
 	idx = i40e_get_udp_port_idx(pf, port);
@@ -8890,7 +8996,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= i40e_netpoll,
 #endif
-	.ndo_setup_tc		= i40e_setup_tc,
+	.ndo_setup_tc		= __i40e_setup_tc,
 #ifdef I40E_FCOE
 	.ndo_fcoe_enable	= i40e_fcoe_enable,
 	.ndo_fcoe_disable	= i40e_fcoe_disable,
@@ -8942,11 +9048,15 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	np = netdev_priv(netdev);
 	np->vsi = vsi;
 
-	netdev->hw_enc_features |= NETIF_F_IP_CSUM	 |
-				  NETIF_F_RXCSUM	 |
-				  NETIF_F_GSO_UDP_TUNNEL |
-				  NETIF_F_GSO_GRE	 |
-				  NETIF_F_TSO;
+	netdev->hw_enc_features |= NETIF_F_IP_CSUM	       |
+				   NETIF_F_IPV6_CSUM	       |
+				   NETIF_F_TSO		       |
+				   NETIF_F_TSO6		       |
+				   NETIF_F_TSO_ECN	       |
+				   NETIF_F_GSO_GRE	       |
+				   NETIF_F_GSO_UDP_TUNNEL      |
+				   NETIF_F_GSO_UDP_TUNNEL_CSUM |
+				   0;
 
 	netdev->features = NETIF_F_SG		       |
 			   NETIF_F_IP_CSUM	       |
@@ -8967,6 +9077,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
 		netdev->features |= NETIF_F_NTUPLE;
+	if (pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)
+		netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
@@ -9471,10 +9583,15 @@ vector_setup_out:
  **/
 static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 {
-	struct i40e_pf *pf = vsi->back;
+	struct i40e_pf *pf;
 	u8 enabled_tc;
 	int ret;
 
+	if (!vsi)
+		return NULL;
+
+	pf = vsi->back;
+
 	i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
 	i40e_vsi_clear_rings(vsi);
 
@@ -9975,13 +10092,13 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = veb->pf;
 	bool is_default = veb->pf->cur_promisc;
-	bool is_cloud = false;
+	bool enable_stats = !!(pf->flags & I40E_FLAG_VEB_STATS_ENABLED);
 	int ret;
 
 	/* get a VEB from the hardware */
 	ret = i40e_aq_add_veb(&pf->hw, veb->uplink_seid, vsi->seid,
 			      veb->enabled_tc, is_default,
-			      is_cloud, &veb->seid, NULL);
+			      &veb->seid, enable_stats, NULL);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't add VEB, err %s aq_err %s\n",
@@ -10538,21 +10655,9 @@ static void i40e_print_features(struct i40e_pf *pf)
  **/
 static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 {
-	struct device_node *dp = pci_device_to_OF_node(pdev);
-	const unsigned char *addr;
-	u8 *mac_addr = pf->hw.mac.addr;
-
 	pf->flags &= ~I40E_FLAG_PF_MAC;
-	addr = of_get_mac_address(dp);
-	if (addr) {
-		ether_addr_copy(mac_addr, addr);
+	if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
 		pf->flags |= I40E_FLAG_PF_MAC;
-#ifdef CONFIG_SPARC
-	} else {
-		ether_addr_copy(mac_addr, idprom->id_ethaddr);
-		pf->flags |= I40E_FLAG_PF_MAC;
-#endif /* CONFIG_SPARC */
-	}
 }
 
 /**
@@ -10575,7 +10680,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	u16 wol_nvm_bits;
 	u16 link_status;
 	int err;
-	u32 len;
 	u32 val;
 	u32 i;
 	u8 set_fc_aq_fail;
@@ -10758,8 +10862,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * Ignore error return codes because if it was already disabled via
 	 * hardware settings this will fail
 	 */
-	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) ||
-	    (pf->hw.aq.fw_maj_ver < 4)) {
+	if (pf->flags & I40E_FLAG_STOP_FW_LLDP) {
 		dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
 		i40e_aq_stop_lldp(hw, true, NULL);
 	}
@@ -10834,8 +10937,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
 
 	/* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */
-	len = sizeof(struct i40e_vsi *) * pf->num_alloc_vsi;
-	pf->vsi = kzalloc(len, GFP_KERNEL);
+	pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
+			  GFP_KERNEL);
 	if (!pf->vsi) {
 		err = -ENOMEM;
 		goto err_switch_setup;
@@ -10882,12 +10985,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	/* driver is only interested in link up/down and module qualification
-	 * reports from firmware
+	/* The driver only wants link up/down and module qualification
+	 * reports from firmware.  Note the negative logic.
 	 */
 	err = i40e_aq_set_phy_int_mask(&pf->hw,
-				       I40E_AQ_EVENT_LINK_UPDOWN |
-				       I40E_AQ_EVENT_MODULE_QUAL_FAIL, NULL);
+				       ~(I40E_AQ_EVENT_LINK_UPDOWN |
+					 I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL);
 	if (err)
 		dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n",
 			 i40e_stat_str(&pf->hw, err),
@@ -10904,8 +11007,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		wr32(hw, I40E_REG_MSS, val);
 	}
 
-	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
-	    (pf->hw.aq.fw_maj_ver < 4)) {
+	if (pf->flags & I40E_FLAG_RESTART_AUTONEG) {
 		msleep(75);
 		err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
 		if (err)
@@ -10939,8 +11041,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
 	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
-		u32 val;
-
 		/* disable link interrupts for VFs */
 		val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM);
 		val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK;
@@ -11051,6 +11151,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i40e_add_filter_to_drop_tx_flow_control_frames(&pf->hw,
 						       pf->main_vsi_seid);
 
+	if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) ||
+	    (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4))
+		pf->flags |= I40E_FLAG_HAVE_10GBASET_PHY;
+
 	/* print a string summarizing features */
 	i40e_print_features(pf);
 
@@ -11107,10 +11211,11 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_ptp_stop(pf);
 
 	/* Disable RSS in hw */
-	wr32(hw, I40E_PFQF_HENA(0), 0);
-	wr32(hw, I40E_PFQF_HENA(1), 0);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
 	/* no more scheduling of any task */
+	set_bit(__I40E_SUSPENDED, &pf->state);
 	set_bit(__I40E_DOWN, &pf->state);
 	del_timer_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
@@ -11141,8 +11246,8 @@ static void i40e_remove(struct pci_dev *pdev)
 		i40e_vsi_release(pf->vsi[pf->lan_vsi]);
 
 	/* shutdown and destroy the HMC */
-	if (pf->hw.hmc.hmc_obj) {
-		ret_code = i40e_shutdown_lan_hmc(&pf->hw);
+	if (hw->hmc.hmc_obj) {
+		ret_code = i40e_shutdown_lan_hmc(hw);
 		if (ret_code)
 			dev_warn(&pdev->dev,
 				 "Failed to destroy the HMC resources: %d\n",
@@ -11150,7 +11255,7 @@ static void i40e_remove(struct pci_dev *pdev)
 	}
 
 	/* shutdown the adminq */
-	ret_code = i40e_shutdown_adminq(&pf->hw);
+	ret_code = i40e_shutdown_adminq(hw);
 	if (ret_code)
 		dev_warn(&pdev->dev,
 			 "Failed to destroy the Admin Queue resources: %d\n",
@@ -11178,7 +11283,7 @@ static void i40e_remove(struct pci_dev *pdev)
 	kfree(pf->qp_pile);
 	kfree(pf->vsi);
 
-	iounmap(pf->hw.hw_addr);
+	iounmap(hw->hw_addr);
 	kfree(pf);
 	pci_release_selected_regions(pdev,
 				     pci_select_bars(pdev, IORESOURCE_MEM));
@@ -11413,6 +11518,16 @@ static int __init i40e_init_module(void)
 		i40e_driver_string, i40e_driver_version_str);
 	pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);
 
+	/* we will see if single thread per module is enough for now,
+	 * it can't be any worse than using the system workqueue which
+	 * was already single threaded
+	 */
+	i40e_wq = create_singlethread_workqueue(i40e_driver_name);
+	if (!i40e_wq) {
+		pr_err("%s: Failed to create workqueue\n", i40e_driver_name);
+		return -ENOMEM;
+	}
+
 	i40e_dbg_init();
 	return pci_register_driver(&i40e_driver);
 }
@@ -11427,6 +11542,7 @@ module_init(i40e_init_module);
 static void __exit i40e_exit_module(void)
 {
 	pci_unregister_driver(&i40e_driver);
+	destroy_workqueue(i40e_wq);
 	i40e_dbg_exit();
 }
 module_exit(i40e_exit_module);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 6100cdd..5730f80 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -693,10 +693,11 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw,
 	/* early check for status command and debug msgs */
 	upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno);
 
-	i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d\n",
+	i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d cmd 0x%08x config 0x%08x offset 0x%08x data_size 0x%08x\n",
 		   i40e_nvm_update_state_str[upd_cmd],
 		   hw->nvmupd_state,
-		   hw->aq.nvm_release_on_done);
+		   hw->aq.nvm_release_on_done,
+		   cmd->command, cmd->config, cmd->offset, cmd->data_size);
 
 	if (upd_cmd == I40E_NVMUPD_INVALID) {
 		*perrno = -EFAULT;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index bb9d583..d51eee5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -74,6 +74,12 @@ i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw,
 
 u32 i40e_led_get(struct i40e_hw *hw);
 void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink);
+i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on,
+			     u16 led_addr, u32 mode);
+i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
+			     u16 *val);
+i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
+				    u32 time, u32 interval);
 
 /* admin send queue commands */
 
@@ -127,6 +133,9 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 		u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw,
 		u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw,
+				u16 seid, bool enable,
+				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw,
 				struct i40e_vsi_context *vsi_ctx,
 				struct i40e_asq_cmd_details *cmd_details);
@@ -135,8 +144,8 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 				u16 downlink_seid, u8 enabled_tc,
-				bool default_port, bool enable_l2_filtering,
-				u16 *pveb_seid,
+				bool default_port, u16 *pveb_seid,
+				bool enable_stats,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw,
 				u16 veb_seid, u16 *switch_id, bool *floating,
@@ -149,6 +158,15 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id,
 i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id,
 			struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			u16 count, struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
+			u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list,
+			struct i40e_asq_cmd_details *cmd_details,
+			u16 *rule_id, u16 *rules_used, u16 *rules_free);
+i40e_status i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid,
+			u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list,
+			struct i40e_asq_cmd_details *cmd_details,
+			u16 *rules_used, u16 *rules_free);
+
 i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 				u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
 				struct i40e_asq_cmd_details *cmd_details);
@@ -324,4 +342,19 @@ i40e_status i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 			       struct i40e_asq_cmd_details *cmd_details);
 void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
 						    u16 vsi_seid);
+i40e_status i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
+				u32 reg_addr, u32 *reg_val,
+				struct i40e_asq_cmd_details *cmd_details);
+u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr);
+i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
+				u32 reg_addr, u32 reg_val,
+				struct i40e_asq_cmd_details *cmd_details);
+void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
+i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page,
+				   u16 reg, u8 phy_addr, u16 *value);
+i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page,
+				    u16 reg, u8 phy_addr, u16 value);
+u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
+i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
+				    u32 time, u32 interval);
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index dc0402f..86ca27f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -2045,6 +2045,14 @@
 #define I40E_PRTPM_TLPIC 0x001E43C0 /* Reset: GLOBR */
 #define I40E_PRTPM_TLPIC_ETLPIC_SHIFT 0
 #define I40E_PRTPM_TLPIC_ETLPIC_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTPM_TLPIC_ETLPIC_SHIFT)
+#define I40E_GL_PRS_FVBM(_i) (0x00269760 + ((_i) * 4)) /* _i=0...3 */ /* Reset: CORER */
+#define I40E_GL_PRS_FVBM_MAX_INDEX 3
+#define I40E_GL_PRS_FVBM_FV_BYTE_INDX_SHIFT 0
+#define I40E_GL_PRS_FVBM_FV_BYTE_INDX_MASK I40E_MASK(0x7F, I40E_GL_PRS_FVBM_FV_BYTE_INDX_SHIFT)
+#define I40E_GL_PRS_FVBM_RULE_BUS_INDX_SHIFT 8
+#define I40E_GL_PRS_FVBM_RULE_BUS_INDX_MASK I40E_MASK(0x3F, I40E_GL_PRS_FVBM_RULE_BUS_INDX_SHIFT)
+#define I40E_GL_PRS_FVBM_MSK_ENA_SHIFT 31
+#define I40E_GL_PRS_FVBM_MSK_ENA_MASK I40E_MASK(0x1, I40E_GL_PRS_FVBM_MSK_ENA_SHIFT)
 #define I40E_GLRPB_DPSS 0x000AC828 /* Reset: CORER */
 #define I40E_GLRPB_DPSS_DPS_TCN_SHIFT 0
 #define I40E_GLRPB_DPSS_DPS_TCN_MASK I40E_MASK(0xFFFFF, I40E_GLRPB_DPSS_DPS_TCN_SHIFT)
@@ -2216,6 +2224,14 @@
 #define I40E_PRTQF_FD_FLXINSET_MAX_INDEX 63
 #define I40E_PRTQF_FD_FLXINSET_INSET_SHIFT 0
 #define I40E_PRTQF_FD_FLXINSET_INSET_MASK I40E_MASK(0xFF, I40E_PRTQF_FD_FLXINSET_INSET_SHIFT)
+#define I40E_PRTQF_FD_INSET(_i, _j) (0x00250000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */ /* Reset: CORER */
+#define I40E_PRTQF_FD_INSET_MAX_INDEX 63
+#define I40E_PRTQF_FD_INSET_INSET_SHIFT 0
+#define I40E_PRTQF_FD_INSET_INSET_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTQF_FD_INSET_INSET_SHIFT)
+#define I40E_PRTQF_FD_INSET(_i, _j) (0x00250000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */ /* Reset: CORER */
+#define I40E_PRTQF_FD_INSET_MAX_INDEX 63
+#define I40E_PRTQF_FD_INSET_INSET_SHIFT 0
+#define I40E_PRTQF_FD_INSET_INSET_MASK I40E_MASK(0xFFFFFFFF, I40E_PRTQF_FD_INSET_INSET_SHIFT)
 #define I40E_PRTQF_FD_MSK(_i, _j) (0x00252000 + ((_i) * 64 + (_j) * 32)) /* _i=0...63, _j=0...1 */ /* Reset: CORER */
 #define I40E_PRTQF_FD_MSK_MAX_INDEX 63
 #define I40E_PRTQF_FD_MSK_MASK_SHIFT 0
@@ -5155,6 +5171,38 @@
 #define I40E_GLQF_FD_PCTYPES_MAX_INDEX 63
 #define I40E_GLQF_FD_PCTYPES_FD_PCTYPE_SHIFT 0
 #define I40E_GLQF_FD_PCTYPES_FD_PCTYPE_MASK I40E_MASK(0x3F, I40E_GLQF_FD_PCTYPES_FD_PCTYPE_SHIFT)
+#define I40E_GLQF_FD_MSK(_i, _j) (0x00267200 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
+#define I40E_GLQF_FD_MSK_MAX_INDEX 1
+#define I40E_GLQF_FD_MSK_MASK_SHIFT 0
+#define I40E_GLQF_FD_MSK_MASK_MASK I40E_MASK(0xFFFF, I40E_GLQF_FD_MSK_MASK_SHIFT)
+#define I40E_GLQF_FD_MSK_OFFSET_SHIFT 16
+#define I40E_GLQF_FD_MSK_OFFSET_MASK I40E_MASK(0x3F, I40E_GLQF_FD_MSK_OFFSET_SHIFT)
+#define I40E_GLQF_HASH_INSET(_i, _j) (0x00267600 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
+#define I40E_GLQF_HASH_INSET_MAX_INDEX 1
+#define I40E_GLQF_HASH_INSET_INSET_SHIFT 0
+#define I40E_GLQF_HASH_INSET_INSET_MASK I40E_MASK(0xFFFFFFFF, I40E_GLQF_HASH_INSET_INSET_SHIFT)
+#define I40E_GLQF_HASH_MSK(_i, _j) (0x00267A00 + ((_i) * 4 + (_j) * 8)) /* _i=0...1, _j=0...63 */ /* Reset: CORER */
+#define I40E_GLQF_HASH_MSK_MAX_INDEX 1
+#define I40E_GLQF_HASH_MSK_MASK_SHIFT 0
+#define I40E_GLQF_HASH_MSK_MASK_MASK I40E_MASK(0xFFFF, I40E_GLQF_HASH_MSK_MASK_SHIFT)
+#define I40E_GLQF_HASH_MSK_OFFSET_SHIFT 16
+#define I40E_GLQF_HASH_MSK_OFFSET_MASK I40E_MASK(0x3F, I40E_GLQF_HASH_MSK_OFFSET_SHIFT)
+#define I40E_GLQF_ORT(_i) (0x00268900 + ((_i) * 4)) /* _i=0...63 */ /* Reset: CORER */
+#define I40E_GLQF_ORT_MAX_INDEX 63
+#define I40E_GLQF_ORT_PIT_INDX_SHIFT 0
+#define I40E_GLQF_ORT_PIT_INDX_MASK I40E_MASK(0x1F, I40E_GLQF_ORT_PIT_INDX_SHIFT)
+#define I40E_GLQF_ORT_FIELD_CNT_SHIFT 5
+#define I40E_GLQF_ORT_FIELD_CNT_MASK I40E_MASK(0x3, I40E_GLQF_ORT_FIELD_CNT_SHIFT)
+#define I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT 7
+#define I40E_GLQF_ORT_FLX_PAYLOAD_MASK I40E_MASK(0x1, I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT)
+#define I40E_GLQF_PIT(_i) (0x00268C80 + ((_i) * 4)) /* _i=0...23 */ /* Reset: CORER */
+#define I40E_GLQF_PIT_MAX_INDEX 23
+#define I40E_GLQF_PIT_SOURCE_OFF_SHIFT 0
+#define I40E_GLQF_PIT_SOURCE_OFF_MASK I40E_MASK(0x1F, I40E_GLQF_PIT_SOURCE_OFF_SHIFT)
+#define I40E_GLQF_PIT_FSIZE_SHIFT 5
+#define I40E_GLQF_PIT_FSIZE_MASK I40E_MASK(0x1F, I40E_GLQF_PIT_FSIZE_SHIFT)
+#define I40E_GLQF_PIT_DEST_OFF_SHIFT 10
+#define I40E_GLQF_PIT_DEST_OFF_MASK I40E_MASK(0x3F, I40E_GLQF_PIT_DEST_OFF_SHIFT)
 #define I40E_GLQF_FDEVICTENA(_i) (0x00270384 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */
 #define I40E_GLQF_FDEVICTENA_MAX_INDEX 1
 #define I40E_GLQF_FDEVICTENA_GLQF_FDEVICTENA_SHIFT 0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 47bd8b3..084d0ab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -610,15 +610,19 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring)
 /**
  * i40e_get_tx_pending - how many tx descriptors not processed
  * @tx_ring: the ring of descriptors
+ * @in_sw: is tx_pending being checked in SW or HW
  *
  * Since there is no access to the ring head register
  * in XL710, we need to use our local copies
  **/
-u32 i40e_get_tx_pending(struct i40e_ring *ring)
+u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 {
 	u32 head, tail;
 
-	head = i40e_get_head(ring);
+	if (!in_sw)
+		head = i40e_get_head(ring);
+	else
+		head = ring->next_to_clean;
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -741,7 +745,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		 * them to be written back in case we stay in NAPI.
 		 * In this mode on X722 we do not enable Interrupt.
 		 */
-		j = i40e_get_tx_pending(tx_ring);
+		j = i40e_get_tx_pending(tx_ring, false);
 
 		if (budget &&
 		    ((j / (WB_STRIDE + 1)) == 0) && (j != 0) &&
@@ -774,29 +778,48 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 }
 
 /**
- * i40e_force_wb - Arm hardware to do a wb on noncache aligned descriptors
+ * i40e_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled
  * @vsi: the VSI we care about
- * @q_vector: the vector  on which to force writeback
+ * @q_vector: the vector on which to enable writeback
  *
  **/
-void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi,
+				  struct i40e_q_vector *q_vector)
 {
 	u16 flags = q_vector->tx.ring[0].flags;
+	u32 val;
 
-	if (flags & I40E_TXR_FLAGS_WB_ON_ITR) {
-		u32 val;
+	if (!(flags & I40E_TXR_FLAGS_WB_ON_ITR))
+		return;
 
-		if (q_vector->arm_wb_state)
-			return;
+	if (q_vector->arm_wb_state)
+		return;
 
-		val = I40E_PFINT_DYN_CTLN_WB_ON_ITR_MASK;
+	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
+		val = I40E_PFINT_DYN_CTLN_WB_ON_ITR_MASK |
+		      I40E_PFINT_DYN_CTLN_ITR_INDX_MASK; /* set noitr */
 
 		wr32(&vsi->back->hw,
-		     I40E_PFINT_DYN_CTLN(q_vector->v_idx +
-					 vsi->base_vector - 1),
+		     I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1),
 		     val);
-		q_vector->arm_wb_state = true;
-	} else if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
+	} else {
+		val = I40E_PFINT_DYN_CTL0_WB_ON_ITR_MASK |
+		      I40E_PFINT_DYN_CTL0_ITR_INDX_MASK; /* set noitr */
+
+		wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0, val);
+	}
+	q_vector->arm_wb_state = true;
+}
+
+/**
+ * i40e_force_wb - Issue SW Interrupt so HW does a wb
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
 		u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 			  I40E_PFINT_DYN_CTLN_ITR_INDX_MASK | /* set noitr */
 			  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
@@ -1041,7 +1064,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 			if (rx_bi->page_dma) {
 				dma_unmap_page(dev,
 					       rx_bi->page_dma,
-					       PAGE_SIZE / 2,
+					       PAGE_SIZE,
 					       DMA_FROM_DEVICE);
 				rx_bi->page_dma = 0;
 			}
@@ -1176,16 +1199,19 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
  * i40e_alloc_rx_buffers_ps - Replace used receive buffers; packet split
  * @rx_ring: ring to place buffers on
  * @cleaned_count: number of buffers to replace
+ *
+ * Returns true if any errors on allocation
  **/
-void i40e_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count)
+bool i40e_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count)
 {
 	u16 i = rx_ring->next_to_use;
 	union i40e_rx_desc *rx_desc;
 	struct i40e_rx_buffer *bi;
+	const int current_node = numa_node_id();
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
-		return;
+		return false;
 
 	while (cleaned_count--) {
 		rx_desc = I40E_RX_DESC(rx_ring, i);
@@ -1193,56 +1219,79 @@ void i40e_alloc_rx_buffers_ps(struct i40e_ring *rx_ring, u16 cleaned_count)
 
 		if (bi->skb) /* desc is in use */
 			goto no_buffers;
+
+	/* If we've been moved to a different NUMA node, release the
+	 * page so we can get a new one on the current node.
+	 */
+		if (bi->page &&  page_to_nid(bi->page) != current_node) {
+			dma_unmap_page(rx_ring->dev,
+				       bi->page_dma,
+				       PAGE_SIZE,
+				       DMA_FROM_DEVICE);
+			__free_page(bi->page);
+			bi->page = NULL;
+			bi->page_dma = 0;
+			rx_ring->rx_stats.realloc_count++;
+		} else if (bi->page) {
+			rx_ring->rx_stats.page_reuse_count++;
+		}
+
 		if (!bi->page) {
 			bi->page = alloc_page(GFP_ATOMIC);
 			if (!bi->page) {
 				rx_ring->rx_stats.alloc_page_failed++;
 				goto no_buffers;
 			}
-		}
-
-		if (!bi->page_dma) {
-			/* use a half page if we're re-using */
-			bi->page_offset ^= PAGE_SIZE / 2;
 			bi->page_dma = dma_map_page(rx_ring->dev,
 						    bi->page,
-						    bi->page_offset,
-						    PAGE_SIZE / 2,
+						    0,
+						    PAGE_SIZE,
 						    DMA_FROM_DEVICE);
-			if (dma_mapping_error(rx_ring->dev,
-					      bi->page_dma)) {
+			if (dma_mapping_error(rx_ring->dev, bi->page_dma)) {
 				rx_ring->rx_stats.alloc_page_failed++;
+				__free_page(bi->page);
+				bi->page = NULL;
 				bi->page_dma = 0;
+				bi->page_offset = 0;
 				goto no_buffers;
 			}
+			bi->page_offset = 0;
 		}
 
-		dma_sync_single_range_for_device(rx_ring->dev,
-						 bi->dma,
-						 0,
-						 rx_ring->rx_hdr_len,
-						 DMA_FROM_DEVICE);
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
+		rx_desc->read.pkt_addr =
+				cpu_to_le64(bi->page_dma + bi->page_offset);
 		rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
 		i++;
 		if (i == rx_ring->count)
 			i = 0;
 	}
 
+	if (rx_ring->next_to_use != i)
+		i40e_release_rx_desc(rx_ring, i);
+
+	return false;
+
 no_buffers:
 	if (rx_ring->next_to_use != i)
 		i40e_release_rx_desc(rx_ring, i);
+
+	/* make sure to come back via polling to try again after
+	 * allocation failure
+	 */
+	return true;
 }
 
 /**
  * i40e_alloc_rx_buffers_1buf - Replace used receive buffers; single buffer
  * @rx_ring: ring to place buffers on
  * @cleaned_count: number of buffers to replace
+ *
+ * Returns true if any errors on allocation
  **/
-void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
+bool i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
 {
 	u16 i = rx_ring->next_to_use;
 	union i40e_rx_desc *rx_desc;
@@ -1251,7 +1300,7 @@ void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
-		return;
+		return false;
 
 	while (cleaned_count--) {
 		rx_desc = I40E_RX_DESC(rx_ring, i);
@@ -1259,8 +1308,10 @@ void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
 		skb = bi->skb;
 
 		if (!skb) {
-			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-							rx_ring->rx_buf_len);
+			skb = __netdev_alloc_skb_ip_align(rx_ring->netdev,
+							  rx_ring->rx_buf_len,
+							  GFP_ATOMIC |
+							  __GFP_NOWARN);
 			if (!skb) {
 				rx_ring->rx_stats.alloc_buff_failed++;
 				goto no_buffers;
@@ -1278,6 +1329,8 @@ void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
 			if (dma_mapping_error(rx_ring->dev, bi->dma)) {
 				rx_ring->rx_stats.alloc_buff_failed++;
 				bi->dma = 0;
+				dev_kfree_skb(bi->skb);
+				bi->skb = NULL;
 				goto no_buffers;
 			}
 		}
@@ -1289,9 +1342,19 @@ void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rx_ring, u16 cleaned_count)
 			i = 0;
 	}
 
+	if (rx_ring->next_to_use != i)
+		i40e_release_rx_desc(rx_ring, i);
+
+	return false;
+
 no_buffers:
 	if (rx_ring->next_to_use != i)
 		i40e_release_rx_desc(rx_ring, i);
+
+	/* make sure to come back via polling to try again after
+	 * allocation failure
+	 */
+	return true;
 }
 
 /**
@@ -1326,16 +1389,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    u16 rx_ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
-	bool ipv4 = false, ipv6 = false;
-	bool ipv4_tunnel, ipv6_tunnel;
-	__wsum rx_udp_csum;
-	struct iphdr *iph;
-	__sum16 csum;
-
-	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
-	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
-		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
+	bool ipv4, ipv6, ipv4_tunnel, ipv6_tunnel;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
@@ -1351,12 +1405,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (!(decoded.known && decoded.outer_ip))
 		return;
 
-	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-	    decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4)
-		ipv4 = true;
-	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-		 decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6)
-		ipv6 = true;
+	ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4);
+	ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
+	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6);
 
 	if (ipv4 &&
 	    (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
@@ -1380,37 +1432,17 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* If VXLAN/GENEVE traffic has an outer UDPv4 checksum we need to check
-	 * it in the driver, hardware does not do it for us.
-	 * Since L3L4P bit was set we assume a valid IHL value (>=5)
-	 * so the total length of IPv4 header is IHL*4 bytes
-	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
+	/* The hardware supported by this driver does not validate outer
+	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
+	 * with it but the specification states that you "MAY validate", it
+	 * doesn't make it a hard requirement so if we have validated the
+	 * inner checksum report CHECKSUM_UNNECESSARY.
 	 */
-	if (!(vsi->back->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) &&
-	    (ipv4_tunnel)) {
-		skb->transport_header = skb->mac_header +
-					sizeof(struct ethhdr) +
-					(ip_hdr(skb)->ihl * 4);
-
-		/* Add 4 bytes for VLAN tagged packets */
-		skb->transport_header += (skb->protocol == htons(ETH_P_8021Q) ||
-					  skb->protocol == htons(ETH_P_8021AD))
-					  ? VLAN_HLEN : 0;
-
-		if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
-		    (udp_hdr(skb)->check != 0)) {
-			rx_udp_csum = udp_csum(skb);
-			iph = ip_hdr(skb);
-			csum = csum_tcpudp_magic(
-					iph->saddr, iph->daddr,
-					(skb->len - skb_transport_offset(skb)),
-					IPPROTO_UDP, rx_udp_csum);
-
-			if (udp_hdr(skb)->check != csum)
-				goto checksum_fail;
-
-		} /* else its GRE and so no outer UDP header */
-	}
+
+	ipv4_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
+	ipv6_tunnel = (rx_ptype >= I40E_RX_PTYPE_GRENAT6_MAC_PAY3) &&
+		     (rx_ptype <= I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4);
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->csum_level = ipv4_tunnel || ipv6_tunnel;
@@ -1475,18 +1507,19 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  **/
-static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
+static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, const int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	const int current_node = numa_mem_id();
 	struct i40e_vsi *vsi = rx_ring->vsi;
 	u16 i = rx_ring->next_to_clean;
 	union i40e_rx_desc *rx_desc;
 	u32 rx_error, rx_status;
+	bool failure = false;
 	u8 rx_ptype;
 	u64 qword;
+	u32 copysize;
 
 	if (budget <= 0)
 		return 0;
@@ -1497,7 +1530,9 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		u16 vlan_tag;
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
-			i40e_alloc_rx_buffers_ps(rx_ring, cleaned_count);
+			failure = failure ||
+				  i40e_alloc_rx_buffers_ps(rx_ring,
+							   cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -1515,6 +1550,12 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		 * DD bit is set.
 		 */
 		dma_rmb();
+		/* sync header buffer for reading */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_ring->rx_bi[0].dma,
+					      i * rx_ring->rx_hdr_len,
+					      rx_ring->rx_hdr_len,
+					      DMA_FROM_DEVICE);
 		if (i40e_rx_is_programming_status(qword)) {
 			i40e_clean_programming_status(rx_ring, rx_desc);
 			I40E_RX_INCREMENT(rx_ring, i);
@@ -1523,10 +1564,13 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		rx_bi = &rx_ring->rx_bi[i];
 		skb = rx_bi->skb;
 		if (likely(!skb)) {
-			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-							rx_ring->rx_hdr_len);
+			skb = __netdev_alloc_skb_ip_align(rx_ring->netdev,
+							  rx_ring->rx_hdr_len,
+							  GFP_ATOMIC |
+							  __GFP_NOWARN);
 			if (!skb) {
 				rx_ring->rx_stats.alloc_buff_failed++;
+				failure = true;
 				break;
 			}
 
@@ -1534,8 +1578,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			skb_record_rx_queue(skb, rx_ring->queue_index);
 			/* we are reusing so sync this buffer for CPU use */
 			dma_sync_single_range_for_cpu(rx_ring->dev,
-						      rx_bi->dma,
-						      0,
+						      rx_ring->rx_bi[0].dma,
+						      i * rx_ring->rx_hdr_len,
 						      rx_ring->rx_hdr_len,
 						      DMA_FROM_DEVICE);
 		}
@@ -1553,9 +1597,16 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 
 		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
 			   I40E_RXD_QW1_PTYPE_SHIFT;
-		prefetch(rx_bi->page);
+		/* sync half-page for reading */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->page_dma,
+					      rx_bi->page_offset,
+					      PAGE_SIZE / 2,
+					      DMA_FROM_DEVICE);
+		prefetch(page_address(rx_bi->page) + rx_bi->page_offset);
 		rx_bi->skb = NULL;
 		cleaned_count++;
+		copysize = 0;
 		if (rx_hbo || rx_sph) {
 			int len;
 
@@ -1566,38 +1617,50 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			memcpy(__skb_put(skb, len), rx_bi->hdr_buf, len);
 		} else if (skb->len == 0) {
 			int len;
+			unsigned char *va = page_address(rx_bi->page) +
+					    rx_bi->page_offset;
 
-			len = (rx_packet_len > skb_headlen(skb) ?
-				skb_headlen(skb) : rx_packet_len);
-			memcpy(__skb_put(skb, len),
-			       rx_bi->page + rx_bi->page_offset,
-			       len);
-			rx_bi->page_offset += len;
+			len = min(rx_packet_len, rx_ring->rx_hdr_len);
+			memcpy(__skb_put(skb, len), va, len);
+			copysize = len;
 			rx_packet_len -= len;
 		}
-
 		/* Get the rest of the data if this was a header split */
 		if (rx_packet_len) {
-			skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
-					   rx_bi->page,
-					   rx_bi->page_offset,
-					   rx_packet_len);
-
-			skb->len += rx_packet_len;
-			skb->data_len += rx_packet_len;
-			skb->truesize += rx_packet_len;
-
-			if ((page_count(rx_bi->page) == 1) &&
-			    (page_to_nid(rx_bi->page) == current_node))
-				get_page(rx_bi->page);
-			else
+			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+					rx_bi->page,
+					rx_bi->page_offset + copysize,
+					rx_packet_len, I40E_RXBUFFER_2048);
+
+			/* If the page count is more than 2, then both halves
+			 * of the page are used and we need to free it. Do it
+			 * here instead of in the alloc code. Otherwise one
+			 * of the half-pages might be released between now and
+			 * then, and we wouldn't know which one to use.
+			 * Don't call get_page and free_page since those are
+			 * both expensive atomic operations that just change
+			 * the refcount in opposite directions. Just give the
+			 * page to the stack; he can have our refcount.
+			 */
+			if (page_count(rx_bi->page) > 2) {
+				dma_unmap_page(rx_ring->dev,
+					       rx_bi->page_dma,
+					       PAGE_SIZE,
+					       DMA_FROM_DEVICE);
 				rx_bi->page = NULL;
+				rx_bi->page_dma = 0;
+				rx_ring->rx_stats.realloc_count++;
+			} else {
+				get_page(rx_bi->page);
+				/* switch to the other half-page here; the
+				 * allocation code programs the right addr
+				 * into HW. If we haven't used this half-page,
+				 * the address won't be changed, and HW can
+				 * just use it next time through.
+				 */
+				rx_bi->page_offset ^= PAGE_SIZE / 2;
+			}
 
-			dma_unmap_page(rx_ring->dev,
-				       rx_bi->page_dma,
-				       PAGE_SIZE / 2,
-				       DMA_FROM_DEVICE);
-			rx_bi->page_dma = 0;
 		}
 		I40E_RX_INCREMENT(rx_ring, i);
 
@@ -1656,7 +1719,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 	rx_ring->q_vector->rx.total_packets += total_rx_packets;
 	rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
 
-	return total_rx_packets;
+	return failure ? budget : total_rx_packets;
 }
 
 /**
@@ -1674,6 +1737,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 	union i40e_rx_desc *rx_desc;
 	u32 rx_error, rx_status;
 	u16 rx_packet_len;
+	bool failure = false;
 	u8 rx_ptype;
 	u64 qword;
 	u16 i;
@@ -1684,7 +1748,9 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 		u16 vlan_tag;
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
-			i40e_alloc_rx_buffers_1buf(rx_ring, cleaned_count);
+			failure = failure ||
+				  i40e_alloc_rx_buffers_1buf(rx_ring,
+							     cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -1783,7 +1849,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 	rx_ring->q_vector->rx.total_packets += total_rx_packets;
 	rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
 
-	return total_rx_packets;
+	return failure ? budget : total_rx_packets;
 }
 
 static u32 i40e_buildreg_itr(const int type, const u16 itr)
@@ -1791,7 +1857,9 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
+	      /* Don't clear PBA because that can cause lost interrupts that
+	       * came in while we were cleaning/polling
+	       */
 	      (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
 	      (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
 
@@ -1814,6 +1882,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	bool rx = false, tx = false;
 	u32 rxval, txval;
 	int vector;
+	int idx = q_vector->v_idx;
 
 	vector = (q_vector->v_idx + vsi->base_vector);
 
@@ -1823,17 +1892,17 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
 
 	if (q_vector->itr_countdown > 0 ||
-	    (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) &&
-	     !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) {
+	    (!ITR_IS_DYNAMIC(vsi->rx_rings[idx]->rx_itr_setting) &&
+	     !ITR_IS_DYNAMIC(vsi->tx_rings[idx]->tx_itr_setting))) {
 		goto enable_int;
 	}
 
-	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
+	if (ITR_IS_DYNAMIC(vsi->rx_rings[idx]->rx_itr_setting)) {
 		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
 		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
 	}
 
-	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) {
+	if (ITR_IS_DYNAMIC(vsi->tx_rings[idx]->tx_itr_setting)) {
 		tx = i40e_set_new_dynamic_itr(&q_vector->tx);
 		txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr);
 	}
@@ -1906,7 +1975,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	i40e_for_each_ring(ring, q_vector->tx) {
-		clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+		clean_complete = clean_complete &&
+				 i40e_clean_tx_irq(ring, vsi->work_limit);
 		arm_wb = arm_wb || ring->arm_wb;
 		ring->arm_wb = false;
 	}
@@ -1930,7 +2000,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 
 		work_done += cleaned;
 		/* if we didn't clean as many as budgeted, we must be done */
-		clean_complete &= (budget_per_ring != cleaned);
+		clean_complete = clean_complete && (budget_per_ring > cleaned);
 	}
 
 	/* If work not completed, return budget and polling will return */
@@ -1938,7 +2008,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 tx_only:
 		if (arm_wb) {
 			q_vector->tx.ring[0].tx_stats.tx_force_wb++;
-			i40e_force_wb(vsi, q_vector);
+			i40e_enable_wb_on_itr(vsi, q_vector);
 		}
 		return budget;
 	}
@@ -1951,20 +2021,7 @@ tx_only:
 	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
 		i40e_update_enable_itr(vsi, q_vector);
 	} else { /* Legacy mode */
-		struct i40e_hw *hw = &vsi->back->hw;
-		/* We re-enable the queue 0 cause, but
-		 * don't worry about dynamic_enable
-		 * because we left it on for the other
-		 * possible interrupts during napi
-		 */
-		u32 qval = rd32(hw, I40E_QINT_RQCTL(0)) |
-			   I40E_QINT_RQCTL_CAUSE_ENA_MASK;
-
-		wr32(hw, I40E_QINT_RQCTL(0), qval);
-		qval = rd32(hw, I40E_QINT_TQCTL(0)) |
-		       I40E_QINT_TQCTL_CAUSE_ENA_MASK;
-		wr32(hw, I40E_QINT_TQCTL(0), qval);
-		i40e_irq_dynamic_enable_icr0(vsi->back);
+		i40e_irq_dynamic_enable_icr0(vsi->back, false);
 	}
 	return 0;
 }
@@ -1974,10 +2031,9 @@ tx_only:
  * @tx_ring:  ring to add programming descriptor to
  * @skb:      send buffer
  * @tx_flags: send tx flags
- * @protocol: wire protocol
  **/
 static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		     u32 tx_flags, __be16 protocol)
+		     u32 tx_flags)
 {
 	struct i40e_filter_program_desc *fdir_desc;
 	struct i40e_pf *pf = tx_ring->vsi->back;
@@ -1989,6 +2045,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	struct tcphdr *th;
 	unsigned int hlen;
 	u32 flex_ptype, dtype_cmd;
+	int l4_proto;
 	u16 i;
 
 	/* make sure ATR is enabled */
@@ -2002,36 +2059,28 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!tx_ring->atr_sample_rate)
 		return;
 
+	/* Currently only IPv4/IPv6 with TCP is supported */
 	if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6)))
 		return;
 
-	if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL)) {
-		/* snag network header to get L4 type and address */
-		hdr.network = skb_network_header(skb);
+	/* snag network header to get L4 type and address */
+	hdr.network = (tx_flags & I40E_TX_FLAGS_UDP_TUNNEL) ?
+		      skb_inner_network_header(skb) : skb_network_header(skb);
 
-		/* Currently only IPv4/IPv6 with TCP is supported
-		 * access ihl as u8 to avoid unaligned access on ia64
-		 */
-		if (tx_flags & I40E_TX_FLAGS_IPV4)
-			hlen = (hdr.network[0] & 0x0F) << 2;
-		else if (protocol == htons(ETH_P_IPV6))
-			hlen = sizeof(struct ipv6hdr);
-		else
-			return;
+	/* Note: tx_flags gets modified to reflect inner protocols in
+	 * tx_enable_csum function if encap is enabled.
+	 */
+	if (tx_flags & I40E_TX_FLAGS_IPV4) {
+		/* access ihl as u8 to avoid unaligned access on ia64 */
+		hlen = (hdr.network[0] & 0x0F) << 2;
+		l4_proto = hdr.ipv4->protocol;
 	} else {
-		hdr.network = skb_inner_network_header(skb);
-		hlen = skb_inner_network_header_len(skb);
+		hlen = hdr.network - skb->data;
+		l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL);
+		hlen -= hdr.network - skb->data;
 	}
 
-	/* Currently only IPv4/IPv6 with TCP is supported
-	 * Note: tx_flags gets modified to reflect inner protocols in
-	 * tx_enable_csum function if encap is enabled.
-	 */
-	if ((tx_flags & I40E_TX_FLAGS_IPV4) &&
-	    (hdr.ipv4->protocol != IPPROTO_TCP))
-		return;
-	else if ((tx_flags & I40E_TX_FLAGS_IPV6) &&
-		 (hdr.ipv6->nexthdr != IPPROTO_TCP))
+	if (l4_proto != IPPROTO_TCP)
 		return;
 
 	th = (struct tcphdr *)(hdr.network + hlen);
@@ -2039,7 +2088,8 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* Due to lack of space, no more new filters can be programmed */
 	if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
-	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) {
+	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
+	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2067,7 +2117,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) &
 		      I40E_TXD_FLTR_QW0_QINDEX_MASK;
-	flex_ptype |= (protocol == htons(ETH_P_IP)) ?
+	flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ?
 		      (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
 		      (I40E_FILTER_PCTYPE_NONF_IPV6_TCP <<
@@ -2101,7 +2151,8 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
 			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
-	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
+	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
+	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -2206,13 +2257,23 @@ out:
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
-	u32 cd_cmd, cd_tso_len, cd_mss;
-	struct ipv6hdr *ipv6h;
-	struct tcphdr *tcph;
-	struct iphdr *iph;
-	u32 l4len;
+	u64 cd_cmd, cd_tso_len, cd_mss;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		struct udphdr *udp;
+		unsigned char *hdr;
+	} l4;
+	u32 paylen, l4_offset;
 	int err;
 
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
 	if (!skb_is_gso(skb))
 		return 0;
 
@@ -2220,35 +2281,60 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
-	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
-
-	if (iph->version == 4) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
-		iph->tot_len = 0;
-		iph->check = 0;
-		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-						 0, IPPROTO_TCP, 0);
-	} else if (ipv6h->version == 6) {
-		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
-		ipv6h->payload_len = 0;
-		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-					       0, IPPROTO_TCP, 0);
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
+
+	/* initialize outer IP header fields */
+	if (ip.v4->version == 4) {
+		ip.v4->tot_len = 0;
+		ip.v4->check = 0;
+	} else {
+		ip.v6->payload_len = 0;
 	}
 
-	l4len = skb->encapsulation ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb);
-	*hdr_len = (skb->encapsulation
-		    ? (skb_inner_transport_header(skb) - skb->data)
-		    : skb_transport_offset(skb)) + l4len;
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			/* determine offset of outer transport header */
+			l4_offset = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = (__force u16)l4.udp->check;
+			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+		}
+
+		/* reset pointers to inner headers */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+
+		/* initialize inner IP header fields */
+		if (ip.v4->version == 4) {
+			ip.v4->tot_len = 0;
+			ip.v4->check = 0;
+		} else {
+			ip.v6->payload_len = 0;
+		}
+	}
+
+	/* determine offset of inner transport header */
+	l4_offset = l4.hdr - skb->data;
+
+	/* remove payload length from inner checksum */
+	paylen = (__force u16)l4.tcp->check;
+	paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+	l4.tcp->check = ~csum_fold((__force __wsum)paylen);
+
+	/* compute length of segmentation header */
+	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
 
 	/* find the field values */
 	cd_cmd = I40E_TX_CTX_DESC_TSO;
 	cd_tso_len = skb->len - *hdr_len;
 	cd_mss = skb_shinfo(skb)->gso_size;
-	*cd_type_cmd_tso_mss |= ((u64)cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
-				((u64)cd_tso_len <<
-				 I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
-				((u64)cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
+	*cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
+				(cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) |
+				(cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT);
 	return 1;
 }
 
@@ -2303,129 +2389,154 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * @tx_ring: Tx descriptor ring
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
-				u32 *td_cmd, u32 *td_offset,
-				struct i40e_ring *tx_ring,
-				u32 *cd_tunneling)
+static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
+			       u32 *td_cmd, u32 *td_offset,
+			       struct i40e_ring *tx_ring,
+			       u32 *cd_tunneling)
 {
-	struct ipv6hdr *this_ipv6_hdr;
-	unsigned int this_tcp_hdrlen;
-	struct iphdr *this_ip_hdr;
-	u32 network_hdr_len;
-	u8 l4_hdr = 0;
-	struct udphdr *oudph = NULL;
-	struct iphdr *oiph = NULL;
-	u32 l4_tunnel = 0;
+	union {
+		struct iphdr *v4;
+		struct ipv6hdr *v6;
+		unsigned char *hdr;
+	} ip;
+	union {
+		struct tcphdr *tcp;
+		struct udphdr *udp;
+		unsigned char *hdr;
+	} l4;
+	unsigned char *exthdr;
+	u32 offset, cmd = 0, tunnel = 0;
+	__be16 frag_off;
+	u8 l4_proto = 0;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	ip.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
+
+	/* compute outer L2 header size */
+	offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
 
 	if (skb->encapsulation) {
-		switch (ip_hdr(skb)->protocol) {
+		/* define outer network header type */
+		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+			tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+				  I40E_TX_CTX_EXT_IP_IPV4 :
+				  I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
+
+			l4_proto = ip.v4->protocol;
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
+			tunnel |= I40E_TX_CTX_EXT_IP_IPV6;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		}
+
+		/* compute outer L3 header size */
+		tunnel |= ((l4.hdr - ip.hdr) / 4) <<
+			  I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT;
+
+		/* switch IP header pointer from outer to inner header */
+		ip.hdr = skb_inner_network_header(skb);
+
+		/* define outer transport */
+		switch (l4_proto) {
 		case IPPROTO_UDP:
-			oudph = udp_hdr(skb);
-			oiph = ip_hdr(skb);
-			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			tunnel |= I40E_TXD_CTX_UDP_TUNNELING;
 			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		case IPPROTO_GRE:
-			l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING;
+			tunnel |= I40E_TXD_CTX_GRE_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_UDP_TUNNEL;
 			break;
 		default:
-			return;
-		}
-		network_hdr_len = skb_inner_network_header_len(skb);
-		this_ip_hdr = inner_ip_hdr(skb);
-		this_ipv6_hdr = inner_ipv6_hdr(skb);
-		this_tcp_hdrlen = inner_tcp_hdrlen(skb);
-
-		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-			if (*tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
-				ip_hdr(skb)->check = 0;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
-		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
 			if (*tx_flags & I40E_TX_FLAGS_TSO)
-				ip_hdr(skb)->check = 0;
+				return -1;
+
+			skb_checksum_help(skb);
+			return 0;
 		}
 
-		/* Now set the ctx descriptor fields */
-		*cd_tunneling |= (skb_network_header_len(skb) >> 2) <<
-				   I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT      |
-				   l4_tunnel                             |
-				   ((skb_inner_network_offset(skb) -
-					skb_transport_offset(skb)) >> 1) <<
-				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-		if (this_ip_hdr->version == 6) {
-			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+		/* compute tunnel header size */
+		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
+			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+
+		/* indicate if we need to offload outer UDP header */
+		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+
+		/* record tunnel offload values */
+		*cd_tunneling |= tunnel;
+
+		/* switch L4 header pointer from outer to inner */
+		l4.hdr = skb_inner_transport_header(skb);
+		l4_proto = 0;
+
+		/* reset type as we transition from outer to inner headers */
+		*tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6);
+		if (ip.v4->version == 4)
+			*tx_flags |= I40E_TX_FLAGS_IPV4;
+		if (ip.v6->version == 6)
 			*tx_flags |= I40E_TX_FLAGS_IPV6;
-		}
-		if ((tx_ring->flags & I40E_TXR_FLAGS_OUTER_UDP_CSUM) &&
-		    (l4_tunnel == I40E_TXD_CTX_UDP_TUNNELING)        &&
-		    (*cd_tunneling & I40E_TXD_CTX_QW0_EXT_IP_MASK)) {
-			oudph->check = ~csum_tcpudp_magic(oiph->saddr,
-					oiph->daddr,
-					(skb->len - skb_transport_offset(skb)),
-					IPPROTO_UDP, 0);
-			*cd_tunneling |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
-		}
-	} else {
-		network_hdr_len = skb_network_header_len(skb);
-		this_ip_hdr = ip_hdr(skb);
-		this_ipv6_hdr = ipv6_hdr(skb);
-		this_tcp_hdrlen = tcp_hdrlen(skb);
 	}
 
 	/* Enable IP checksum offloads */
 	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
-		l4_hdr = this_ip_hdr->protocol;
+		l4_proto = ip.v4->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
-		if (*tx_flags & I40E_TX_FLAGS_TSO) {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
-			this_ip_hdr->check = 0;
-		} else {
-			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4;
-		}
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
+		cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
+		       I40E_TX_DESC_CMD_IIPT_IPV4_CSUM :
+		       I40E_TX_DESC_CMD_IIPT_IPV4;
 	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
-		l4_hdr = this_ipv6_hdr->nexthdr;
-		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
-		/* Now set the td_offset for IP header length */
-		*td_offset = (network_hdr_len >> 2) <<
-			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
+
+		exthdr = ip.hdr + sizeof(*ip.v6);
+		l4_proto = ip.v6->nexthdr;
+		if (l4.hdr != exthdr)
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 &l4_proto, &frag_off);
 	}
-	/* words in MACLEN + dwords in IPLEN + dwords in L4Len */
-	*td_offset |= (skb_network_offset(skb) >> 1) <<
-		       I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
+
+	/* compute inner L3 header size */
+	offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
 
 	/* Enable L4 checksum offloads */
-	switch (l4_hdr) {
+	switch (l4_proto) {
 	case IPPROTO_TCP:
 		/* enable checksum offloads */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
-		*td_offset |= (this_tcp_hdrlen >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP;
+		offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_SCTP:
 		/* enable SCTP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
-		*td_offset |= (sizeof(struct sctphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP;
+		offset |= (sizeof(struct sctphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	case IPPROTO_UDP:
 		/* enable UDP checksum offload */
-		*td_cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
-		*td_offset |= (sizeof(struct udphdr) >> 2) <<
-			       I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
+		cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP;
+		offset |= (sizeof(struct udphdr) >> 2) <<
+			  I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT;
 		break;
 	default:
-		break;
+		if (*tx_flags & I40E_TX_FLAGS_TSO)
+			return -1;
+		skb_checksum_help(skb);
+		return 0;
 	}
+
+	*td_cmd |= cmd;
+	*td_offset |= offset;
+
+	return 1;
 }
 
 /**
@@ -2466,7 +2577,7 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
  *
  * Returns -EBUSY if a stop is needed, else 0
  **/
-static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 {
 	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 	/* Memory barrier before checking head and tail */
@@ -2483,77 +2594,71 @@ static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 }
 
 /**
- * i40e_maybe_stop_tx - 1st level check for tx stop conditions
- * @tx_ring: the ring to be checked
- * @size:    the size buffer we want to assure is available
- *
- * Returns 0 if stop is not needed
- **/
-#ifdef I40E_FCOE
-inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
-#else
-static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
-#endif
-{
-	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
-		return 0;
-	return __i40e_maybe_stop_tx(tx_ring, size);
-}
-
-/**
- * i40e_chk_linearize - Check if there are more than 8 fragments per packet
+ * __i40e_chk_linearize - Check if there are more than 8 fragments per packet
  * @skb:      send buffer
- * @tx_flags: collected send information
  *
  * Note: Our HW can't scatter-gather more than 8 fragments to build
  * a packet on the wire and so we need to figure out the cases where we
  * need to linearize the skb.
  **/
-static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags)
+bool __i40e_chk_linearize(struct sk_buff *skb)
 {
-	struct skb_frag_struct *frag;
-	bool linearize = false;
-	unsigned int size = 0;
-	u16 num_frags;
-	u16 gso_segs;
+	const struct skb_frag_struct *frag, *stale;
+	int gso_size, nr_frags, sum;
 
-	num_frags = skb_shinfo(skb)->nr_frags;
-	gso_segs = skb_shinfo(skb)->gso_segs;
+	/* check to see if TSO is enabled, if so we may get a repreive */
+	gso_size = skb_shinfo(skb)->gso_size;
+	if (unlikely(!gso_size))
+		return true;
 
-	if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
-		u16 j = 0;
+	/* no need to check if number of frags is less than 8 */
+	nr_frags = skb_shinfo(skb)->nr_frags;
+	if (nr_frags < I40E_MAX_BUFFER_TXD)
+		return false;
 
-		if (num_frags < (I40E_MAX_BUFFER_TXD))
-			goto linearize_chk_done;
-		/* try the simple math, if we have too many frags per segment */
-		if (DIV_ROUND_UP((num_frags + gso_segs), gso_segs) >
-		    I40E_MAX_BUFFER_TXD) {
-			linearize = true;
-			goto linearize_chk_done;
-		}
-		frag = &skb_shinfo(skb)->frags[0];
-		/* we might still have more fragments per segment */
-		do {
-			size += skb_frag_size(frag);
-			frag++; j++;
-			if ((size >= skb_shinfo(skb)->gso_size) &&
-			    (j < I40E_MAX_BUFFER_TXD)) {
-				size = (size % skb_shinfo(skb)->gso_size);
-				j = (size) ? 1 : 0;
-			}
-			if (j == I40E_MAX_BUFFER_TXD) {
-				linearize = true;
-				break;
-			}
-			num_frags--;
-		} while (num_frags);
-	} else {
-		if (num_frags >= I40E_MAX_BUFFER_TXD)
-			linearize = true;
+	/* We need to walk through the list and validate that each group
+	 * of 6 fragments totals at least gso_size.  However we don't need
+	 * to perform such validation on the first or last 6 since the first
+	 * 6 cannot inherit any data from a descriptor before them, and the
+	 * last 6 cannot inherit any data from a descriptor after them.
+	 */
+	nr_frags -= I40E_MAX_BUFFER_TXD - 1;
+	frag = &skb_shinfo(skb)->frags[0];
+
+	/* Initialize size to the negative value of gso_size minus 1.  We
+	 * use this as the worst case scenerio in which the frag ahead
+	 * of us only provides one byte which is why we are limited to 6
+	 * descriptors for a single transmit as the header and previous
+	 * fragment are already consuming 2 descriptors.
+	 */
+	sum = 1 - gso_size;
+
+	/* Add size of frags 1 through 5 to create our initial sum */
+	sum += skb_frag_size(++frag);
+	sum += skb_frag_size(++frag);
+	sum += skb_frag_size(++frag);
+	sum += skb_frag_size(++frag);
+	sum += skb_frag_size(++frag);
+
+	/* Walk through fragments adding latest fragment, testing it, and
+	 * then removing stale fragments from the sum.
+	 */
+	stale = &skb_shinfo(skb)->frags[0];
+	for (;;) {
+		sum += skb_frag_size(++frag);
+
+		/* if sum is negative we failed to make sufficient progress */
+		if (sum < 0)
+			return true;
+
+		/* use pre-decrement to avoid processing last fragment */
+		if (!--nr_frags)
+			break;
+
+		sum -= skb_frag_size(++stale);
 	}
 
-linearize_chk_done:
-	return linearize;
+	return false;
 }
 
 /**
@@ -2760,43 +2865,6 @@ dma_error:
 }
 
 /**
- * i40e_xmit_descriptor_count - calculate number of tx descriptors needed
- * @skb:     send buffer
- * @tx_ring: ring to send buffer on
- *
- * Returns number of data descriptors needed for this skb. Returns 0 to indicate
- * there is not enough descriptors available in this ring since we need at least
- * one descriptor.
- **/
-#ifdef I40E_FCOE
-inline int i40e_xmit_descriptor_count(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring)
-#else
-static inline int i40e_xmit_descriptor_count(struct sk_buff *skb,
-					     struct i40e_ring *tx_ring)
-#endif
-{
-	unsigned int f;
-	int count = 0;
-
-	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
-	 *       + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
-	 *       + 4 desc gap to avoid the cache line where head is,
-	 *       + 1 desc for context descriptor,
-	 * otherwise try next time
-	 */
-	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
-		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-
-	count += TXD_USE_COUNT(skb_headlen(skb));
-	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
-		tx_ring->tx_stats.tx_busy++;
-		return 0;
-	}
-	return count;
-}
-
-/**
  * i40e_xmit_frame_ring - Sends buffer on Tx ring
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
@@ -2814,14 +2882,30 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	__be16 protocol;
 	u32 td_cmd = 0;
 	u8 hdr_len = 0;
+	int tso, count;
 	int tsyn;
-	int tso;
 
 	/* prefetch the data, we'll need it later */
 	prefetch(skb->data);
 
-	if (0 == i40e_xmit_descriptor_count(skb, tx_ring))
+	count = i40e_xmit_descriptor_count(skb);
+	if (i40e_chk_linearize(skb, count)) {
+		if (__skb_linearize(skb))
+			goto out_drop;
+		count = TXD_USE_COUNT(skb->len);
+		tx_ring->tx_stats.tx_linearize++;
+	}
+
+	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
+	 *       + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
+	 *       + 4 desc gap to avoid the cache line where head is,
+	 *       + 1 desc for context descriptor,
+	 * otherwise try next time
+	 */
+	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+		tx_ring->tx_stats.tx_busy++;
 		return NETDEV_TX_BUSY;
+	}
 
 	/* prepare the xmit flags */
 	if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
@@ -2846,29 +2930,22 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (tso)
 		tx_flags |= I40E_TX_FLAGS_TSO;
 
+	/* Always offload the checksum, since it's in the data descriptor */
+	tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
+				  tx_ring, &cd_tunneling);
+	if (tso < 0)
+		goto out_drop;
+
 	tsyn = i40e_tsyn(tx_ring, skb, tx_flags, &cd_type_cmd_tso_mss);
 
 	if (tsyn)
 		tx_flags |= I40E_TX_FLAGS_TSYN;
 
-	if (i40e_chk_linearize(skb, tx_flags)) {
-		if (skb_linearize(skb))
-			goto out_drop;
-		tx_ring->tx_stats.tx_linearize++;
-	}
 	skb_tx_timestamp(skb);
 
 	/* always enable CRC insertion offload */
 	td_cmd |= I40E_TX_DESC_CMD_ICRC;
 
-	/* Always offload the checksum, since it's in the data descriptor */
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		tx_flags |= I40E_TX_FLAGS_CSUM;
-
-		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
-				    tx_ring, &cd_tunneling);
-	}
-
 	i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
 			   cd_tunneling, cd_l2tag2);
 
@@ -2876,7 +2953,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	 *
 	 * NOTE: this must always be directly before the data descriptor.
 	 */
-	i40e_atr(tx_ring, skb, tx_flags, protocol);
+	i40e_atr(tx_ring, skb, tx_flags);
 
 	i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
 		    td_cmd, td_offset);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 3f081e2..cdd5dc0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -153,7 +153,6 @@ enum i40e_dyn_idx_t {
 #define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 #define I40E_MIN_DESC_PENDING	4
 
-#define I40E_TX_FLAGS_CSUM		BIT(0)
 #define I40E_TX_FLAGS_HW_VLAN		BIT(1)
 #define I40E_TX_FLAGS_SW_VLAN		BIT(2)
 #define I40E_TX_FLAGS_TSO		BIT(3)
@@ -203,12 +202,15 @@ struct i40e_tx_queue_stats {
 	u64 tx_done_old;
 	u64 tx_linearize;
 	u64 tx_force_wb;
+	u64 tx_lost_interrupt;
 };
 
 struct i40e_rx_queue_stats {
 	u64 non_eop_descs;
 	u64 alloc_page_failed;
 	u64 alloc_buff_failed;
+	u64 page_reuse_count;
+	u64 realloc_count;
 };
 
 enum i40e_ring_state_t {
@@ -246,6 +248,14 @@ struct i40e_ring {
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
 
+	/* high bit set means dynamic, use accessor routines to read/write.
+	 * hardware only supports 2us resolution for the ITR registers.
+	 * these values always store the USER setting, and must be converted
+	 * before programming to a register.
+	 */
+	u16 rx_itr_setting;
+	u16 tx_itr_setting;
+
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 rx_hdr_len;
@@ -254,7 +264,6 @@ struct i40e_ring {
 #define I40E_RX_DTYPE_NO_SPLIT      0
 #define I40E_RX_DTYPE_HEADER_SPLIT  1
 #define I40E_RX_DTYPE_SPLIT_ALWAYS  2
-	u8  hsplit;
 #define I40E_RX_SPLIT_L2      0x1
 #define I40E_RX_SPLIT_IP      0x2
 #define I40E_RX_SPLIT_TCP_UDP 0x4
@@ -275,7 +284,6 @@ struct i40e_ring {
 
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
-#define I40E_TXR_FLAGS_OUTER_UDP_CSUM	BIT(1)
 #define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
 
 	/* stats structs */
@@ -316,8 +324,8 @@ struct i40e_ring_container {
 #define i40e_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
-void i40e_alloc_rx_buffers_ps(struct i40e_ring *rxr, u16 cleaned_count);
-void i40e_alloc_rx_buffers_1buf(struct i40e_ring *rxr, u16 cleaned_count);
+bool i40e_alloc_rx_buffers_ps(struct i40e_ring *rxr, u16 cleaned_count);
+bool i40e_alloc_rx_buffers_1buf(struct i40e_ring *rxr, u16 cleaned_count);
 void i40e_alloc_rx_headers(struct i40e_ring *rxr);
 netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
@@ -331,13 +339,13 @@ int i40e_napi_poll(struct napi_struct *napi, int budget);
 void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		 struct i40e_tx_buffer *first, u32 tx_flags,
 		 const u8 hdr_len, u32 td_cmd, u32 td_offset);
-int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
-int i40e_xmit_descriptor_count(struct sk_buff *skb, struct i40e_ring *tx_ring);
 int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 			       struct i40e_ring *tx_ring, u32 *flags);
 #endif
 void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
-u32 i40e_get_tx_pending(struct i40e_ring *ring);
+u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
+int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
+bool __i40e_chk_linearize(struct sk_buff *skb);
 
 /**
  * i40e_get_head - Retrieve head from head writeback
@@ -352,4 +360,63 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
 
 	return le32_to_cpu(*(volatile __le32 *)head);
 }
+
+/**
+ * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
+ * @skb:     send buffer
+ * @tx_ring: ring to send buffer on
+ *
+ * Returns number of data descriptors needed for this skb. Returns 0 to indicate
+ * there is not enough descriptors available in this ring since we need at least
+ * one descriptor.
+ **/
+static inline int i40e_xmit_descriptor_count(struct sk_buff *skb)
+{
+	const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+	int count = 0, size = skb_headlen(skb);
+
+	for (;;) {
+		count += TXD_USE_COUNT(size);
+
+		if (!nr_frags--)
+			break;
+
+		size = skb_frag_size(frag++);
+	}
+
+	return count;
+}
+
+/**
+ * i40e_maybe_stop_tx - 1st level check for Tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size:    the size buffer we want to assure is available
+ *
+ * Returns 0 if stop is not needed
+ **/
+static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
+		return 0;
+	return __i40e_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * i40e_chk_linearize - Check if there are more than 8 fragments per packet
+ * @skb:      send buffer
+ * @count:    number of buffers used
+ *
+ * Note: Our HW can't scatter-gather more than 8 fragments to build
+ * a packet on the wire and so we need to figure out the cases where we
+ * need to linearize the skb.
+ **/
+static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
+{
+	/* we can only support up to 8 data buffers for a single send */
+	if (likely(count <= I40E_MAX_BUFFER_TXD))
+		return false;
+
+	return __i40e_chk_linearize(skb);
+}
 #endif /* _I40E_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index dd2da35..0a0baf7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -90,6 +90,22 @@ enum i40e_debug_mask {
 	I40E_DEBUG_ALL			= 0xFFFFFFFF
 };
 
+#define I40E_MDIO_STCODE                0
+#define I40E_MDIO_OPCODE_ADDRESS        0
+#define I40E_MDIO_OPCODE_WRITE          I40E_MASK(1, \
+						  I40E_GLGEN_MSCA_OPCODE_SHIFT)
+#define I40E_MDIO_OPCODE_READ_INC_ADDR  I40E_MASK(2, \
+						  I40E_GLGEN_MSCA_OPCODE_SHIFT)
+#define I40E_MDIO_OPCODE_READ           I40E_MASK(3, \
+						  I40E_GLGEN_MSCA_OPCODE_SHIFT)
+
+#define I40E_PHY_COM_REG_PAGE                   0x1E
+#define I40E_PHY_LED_LINK_MODE_MASK             0xF0
+#define I40E_PHY_LED_MANUAL_ON                  0x100
+#define I40E_PHY_LED_PROV_REG_1                 0xC430
+#define I40E_PHY_LED_MODE_MASK                  0xFFFF
+#define I40E_PHY_LED_MODE_ORIG                  0x80000000
+
 /* These are structs for managing the hardware information and the operations.
  * The structures of function pointers are filled out at init time when we
  * know for sure exactly which hardware we're working with.  This gives us the
@@ -1098,6 +1114,10 @@ enum i40e_filter_program_desc_pcmd {
 					 I40E_TXD_FLTR_QW1_CMD_SHIFT)
 #define I40E_TXD_FLTR_QW1_ATR_MASK	BIT_ULL(I40E_TXD_FLTR_QW1_ATR_SHIFT)
 
+#define I40E_TXD_FLTR_QW1_ATR_SHIFT	(0xEULL + \
+					 I40E_TXD_FLTR_QW1_CMD_SHIFT)
+#define I40E_TXD_FLTR_QW1_ATR_MASK	BIT_ULL(I40E_TXD_FLTR_QW1_ATR_SHIFT)
+
 #define I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT 20
 #define I40E_TXD_FLTR_QW1_CNTINDEX_MASK	(0x1FFUL << \
 					 I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 63e62f9..acd2693 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2016 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,
@@ -461,7 +461,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 		rx_ctx.hbuff = info->hdr_size >> I40E_RXQ_CTX_HBUFF_SHIFT;
 
 		/* set splitalways mode 10b */
-		rx_ctx.dtype = 0x2;
+		rx_ctx.dtype = I40E_RX_DTYPE_HEADER_SPLIT;
 	}
 
 	/* databuffer length validation */
@@ -602,8 +602,8 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf)
 	 * that VF queues be mapped using this method, even when they are
 	 * contiguous in real life
 	 */
-	wr32(hw, I40E_VSILAN_QBASE(vf->lan_vsi_id),
-	     I40E_VSILAN_QBASE_VSIQTABLE_ENA_MASK);
+	i40e_write_rx_ctl(hw, I40E_VSILAN_QBASE(vf->lan_vsi_id),
+			  I40E_VSILAN_QBASE_VSIQTABLE_ENA_MASK);
 
 	/* enable VF vplan_qtable mappings */
 	reg = I40E_VPLAN_MAPENA_TXRX_ENA_MASK;
@@ -630,7 +630,8 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf)
 						      (j * 2) + 1);
 			reg |= qid << 16;
 		}
-		wr32(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id), reg);
+		i40e_write_rx_ctl(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id),
+				  reg);
 	}
 
 	i40e_flush(hw);
@@ -980,7 +981,7 @@ err_alloc:
 		i40e_free_vfs(pf);
 err_iov:
 	/* Re-enable interrupt 0. */
-	i40e_irq_dynamic_enable_icr0(pf);
+	i40e_irq_dynamic_enable_icr0(pf, false);
 	return ret;
 }
 
@@ -1213,9 +1214,21 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG;
 	}
 
+	if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+		if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+			vfres->vf_offload_flags |=
+				I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
+	}
+
 	if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING)
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING;
 
+	if (pf->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) {
+		if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+			vfres->vf_offload_flags |=
+					I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
+	}
+
 	vfres->num_vsis = num_vsis;
 	vfres->num_queue_pairs = vf->num_queue_pairs;
 	vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
@@ -2025,7 +2038,11 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 	if (!test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
 		return 0;
 
-	/* re-enable vflr interrupt cause */
+	/* Re-enable the VFLR interrupt cause here, before looking for which
+	 * VF got reset. Otherwise, if another VF gets a reset while the
+	 * first one is being processed, that interrupt will be lost, and
+	 * that VF will be stuck in reset forever.
+	 */
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |= I40E_PFINT_ICR0_ENA_VFLR_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
@@ -2186,6 +2203,8 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 		 * and then reloading the VF driver.
 		 */
 		i40e_vc_disable_vf(pf, vf);
+		/* During reset the VF got a new VSI, so refresh the pointer. */
+		vsi = pf->vsi[vf->lan_vsi_idx];
 	}
 
 	/* Check for condition where there was already a port VLAN ID
@@ -2294,6 +2313,9 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 	case I40E_LINK_SPEED_40GB:
 		speed = 40000;
 		break;
+	case I40E_LINK_SPEED_20GB:
+		speed = 20000;
+		break;
 	case I40E_LINK_SPEED_10GB:
 		speed = 10000;
 		break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index da44995..e74642a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -91,8 +91,8 @@ struct i40e_vf {
 	 * When assigned, these will be non-zero, because VSI 0 is always
 	 * the main LAN VSI for the PF.
 	 */
-	u8 lan_vsi_idx;	        /* index into PF struct */
-	u8 lan_vsi_id;		/* ID as used by firmware */
+	u16 lan_vsi_idx;	/* index into PF struct */
+	u16 lan_vsi_id;		/* ID as used by firmware */
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
 	u64 num_mdd_events;	/* num of mdd events detected */