7 files changed, 311 insertions, 112 deletions
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
index 6c31bf22c2c3..60f04e96a80e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
@@ -148,7 +148,7 @@ static inline int i40e_aq_rc_to_posix(u32 aq_ret, u16 aq_rc)
 
 /* general information */
 #define I40E_AQ_LARGE_BUF	512
-#define I40E_ASQ_CMD_TIMEOUT	100  /* msecs */
+#define I40E_ASQ_CMD_TIMEOUT	250  /* msecs */
 
 void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
 				       u16 opcode);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index ff1b16370da9..e715bccfb5d2 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -268,6 +268,8 @@ enum i40e_admin_queue_opc {
 	/* OEM commands */
 	i40e_aqc_opc_oem_parameter_change	= 0xFE00,
 	i40e_aqc_opc_oem_device_status_change	= 0xFE01,
+	i40e_aqc_opc_oem_ocsd_initialize	= 0xFE02,
+	i40e_aqc_opc_oem_ocbb_initialize	= 0xFE03,
 
 	/* debug commands */
 	i40e_aqc_opc_debug_get_deviceid		= 0xFF00,
@@ -276,7 +278,6 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_debug_write_reg		= 0xFF04,
 	i40e_aqc_opc_debug_modify_reg		= 0xFF07,
 	i40e_aqc_opc_debug_dump_internals	= 0xFF08,
-	i40e_aqc_opc_debug_modify_internals	= 0xFF09,
 };
 
 /* command structures and indirect data structures */
@@ -410,6 +411,7 @@ struct i40e_aqc_list_capabilities_element_resp {
 #define I40E_AQ_CAP_ID_VSI		0x0017
 #define I40E_AQ_CAP_ID_DCB		0x0018
 #define I40E_AQ_CAP_ID_FCOE		0x0021
+#define I40E_AQ_CAP_ID_ISCSI		0x0022
 #define I40E_AQ_CAP_ID_RSS		0x0040
 #define I40E_AQ_CAP_ID_RXQ		0x0041
 #define I40E_AQ_CAP_ID_TXQ		0x0042
@@ -454,8 +456,11 @@ struct i40e_aqc_arp_proxy_data {
 	__le32	pfpm_proxyfc;
 	__le32	ip_addr;
 	u8	mac_addr[6];
+	u8	reserved[2];
 };
 
+I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data);
+
 /* Set NS Proxy Table Entry Command (indirect 0x0105) */
 struct i40e_aqc_ns_proxy_data {
 	__le16	table_idx_mac_addr_0;
@@ -481,6 +486,8 @@ struct i40e_aqc_ns_proxy_data {
 	u8	ipv6_addr_1[16];
 };
 
+I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data);
+
 /* Manage LAA Command (0x0106) - obsolete */
 struct i40e_aqc_mng_laa {
 	__le16	command_flags;
@@ -491,6 +498,8 @@ struct i40e_aqc_mng_laa {
 	u8	reserved2[6];
 };
 
+I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa);
+
 /* Manage MAC Address Read Command (indirect 0x0107) */
 struct i40e_aqc_mac_address_read {
 	__le16	command_flags;
@@ -562,6 +571,8 @@ struct i40e_aqc_get_switch_config_header_resp {
 	u8	reserved[12];
 };
 
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp);
+
 struct i40e_aqc_switch_config_element_resp {
 	u8	element_type;
 #define I40E_AQ_SW_ELEM_TYPE_MAC	1
@@ -587,6 +598,8 @@ struct i40e_aqc_switch_config_element_resp {
 	__le16	element_info;
 };
 
+I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp);
+
 /* Get Switch Configuration (indirect 0x0200)
  *    an array of elements are returned in the response buffer
  *    the first in the array is the header, remainder are elements
@@ -596,6 +609,8 @@ struct i40e_aqc_get_switch_config_resp {
 	struct i40e_aqc_switch_config_element_resp	element[1];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp);
+
 /* Add Statistics (direct 0x0201)
  * Remove Statistics (direct 0x0202)
  */
@@ -661,6 +676,8 @@ struct i40e_aqc_switch_resource_alloc_element_resp {
 	u8	reserved2[6];
 };
 
+I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
+
 /* Add VSI (indirect 0x0210)
  *    this indirect command uses struct i40e_aqc_vsi_properties_data
  *    as the indirect buffer (128 bytes)
@@ -1092,6 +1109,8 @@ struct i40e_aqc_remove_tag {
 	u8	reserved[12];
 };
 
+I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag);
+
 /* Add multicast E-Tag (direct 0x0257)
  * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields
  * and no external data
@@ -1207,7 +1226,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 	} ipaddr;
 	__le16	flags;
 #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT			0
-#define I40E_AQC_ADD_CLOUD_FILTER_MASK			(0x3F << \
+#define I40E_AQC_ADD_CLOUD_FILTER_MASK	(0x3F << \
 					I40E_AQC_ADD_CLOUD_FILTER_SHIFT)
 /* 0x0000 reserved */
 #define I40E_AQC_ADD_CLOUD_FILTER_OIP			0x0001
@@ -1240,7 +1259,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data {
 	u8	reserved[4];
 	__le16	queue_number;
 #define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT		0
-#define I40E_AQC_ADD_CLOUD_QUEUE_MASK		(0x3F << \
+#define I40E_AQC_ADD_CLOUD_QUEUE_MASK		(0x7FF << \
 						 I40E_AQC_ADD_CLOUD_QUEUE_SHIFT)
 	u8	reserved2[14];
 	/* response section */
@@ -1359,6 +1378,8 @@ struct i40e_aqc_configure_vsi_ets_sla_bw_data {
 	u8	reserved1[28];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data);
+
 /* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407)
  *    responds with i40e_aqc_qs_handles_resp
  */
@@ -1370,6 +1391,8 @@ struct i40e_aqc_configure_vsi_tc_bw_data {
 	__le16	qs_handles[8];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data);
+
 /* Query vsi bw configuration (indirect 0x0408) */
 struct i40e_aqc_query_vsi_bw_config_resp {
 	u8	tc_valid_bits;
@@ -1383,6 +1406,8 @@ struct i40e_aqc_query_vsi_bw_config_resp {
 	u8	reserved3[23];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp);
+
 /* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */
 struct i40e_aqc_query_vsi_ets_sla_config_resp {
 	u8	tc_valid_bits;
@@ -1394,6 +1419,8 @@ struct i40e_aqc_query_vsi_ets_sla_config_resp {
 	__le16	tc_bw_max[2];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp);
+
 /* Configure Switching Component Bandwidth Limit (direct 0x0410) */
 struct i40e_aqc_configure_switching_comp_bw_limit {
 	__le16	seid;
@@ -1421,6 +1448,8 @@ struct i40e_aqc_configure_switching_comp_ets_data {
 	u8	reserved2[96];
 };
 
+I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data);
+
 /* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */
 struct i40e_aqc_configure_switching_comp_ets_bw_limit_data {
 	u8	tc_valid_bits;
@@ -1432,6 +1461,9 @@ struct i40e_aqc_configure_switching_comp_ets_bw_limit_data {
 	u8	reserved1[28];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40,
+		      i40e_aqc_configure_switching_comp_ets_bw_limit_data);
+
 /* Configure Switching Component Bandwidth Allocation per Tc
  * (indirect 0x0417)
  */
@@ -1443,6 +1475,8 @@ struct i40e_aqc_configure_switching_comp_bw_config_data {
 	u8	reserved1[20];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data);
+
 /* Query Switching Component Configuration (indirect 0x0418) */
 struct i40e_aqc_query_switching_comp_ets_config_resp {
 	u8	tc_valid_bits;
@@ -1453,6 +1487,8 @@ struct i40e_aqc_query_switching_comp_ets_config_resp {
 	u8	reserved2[23];
 };
 
+I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp);
+
 /* Query PhysicalPort ETS Configuration (indirect 0x0419) */
 struct i40e_aqc_query_port_ets_config_resp {
 	u8	reserved[4];
@@ -1468,6 +1504,8 @@ struct i40e_aqc_query_port_ets_config_resp {
 	u8	reserved3[32];
 };
 
+I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp);
+
 /* Query Switching Component Bandwidth Allocation per Traffic Type
  * (indirect 0x041A)
  */
@@ -1482,6 +1520,8 @@ struct i40e_aqc_query_switching_comp_bw_config_resp {
 	__le16	tc_bw_max[2];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp);
+
 /* Suspend/resume port TX traffic
  * (direct 0x041B and 0x041C) uses the generic SEID struct
  */
@@ -1495,6 +1535,8 @@ struct i40e_aqc_configure_partition_bw_data {
 	u8	max_bw[16];      /* bandwidth limit */
 };
 
+I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data);
+
 /* Get and set the active HMC resource profile and status.
  * (direct 0x0500) and (direct 0x0501)
  */
@@ -1577,6 +1619,8 @@ struct i40e_aqc_module_desc {
 	u8 reserved2[8];
 };
 
+I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc);
+
 struct i40e_aq_get_phy_abilities_resp {
 	__le32	phy_type;       /* bitmap using the above enum for offsets */
 	u8	link_speed;     /* bitmap using the above enum bit patterns */
@@ -1605,6 +1649,8 @@ struct i40e_aq_get_phy_abilities_resp {
 	struct i40e_aqc_module_desc	qualified_module[I40E_AQ_PHY_MAX_QMS];
 };
 
+I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp);
+
 /* Set PHY Config (direct 0x0601) */
 struct i40e_aq_set_phy_config { /* same bits as above in all */
 	__le32	phy_type;
@@ -1788,12 +1834,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
 /* NVM Config Read (indirect 0x0704) */
 struct i40e_aqc_nvm_config_read {
 	__le16	cmd_flags;
-#define ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK	1
-#define ANVM_READ_SINGLE_FEATURE		0
-#define ANVM_READ_MULTIPLE_FEATURES		1
+#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK	1
+#define I40E_AQ_ANVM_READ_SINGLE_FEATURE		0
+#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES		1
 	__le16	element_count;
-	__le16	element_id; /* Feature/field ID */
-	u8	reserved[2];
+	__le16	element_id;	/* Feature/field ID */
+	__le16	element_id_msw;	/* MSWord of field ID */
 	__le32	address_high;
 	__le32	address_low;
 };
@@ -1811,21 +1857,32 @@ struct i40e_aqc_nvm_config_write {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write);
 
+/* Used for 0x0704 as well as for 0x0705 commands */
+#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT		1
+#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \
+				(1 << I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT)
+#define I40E_AQ_ANVM_FEATURE		0
+#define I40E_AQ_ANVM_IMMEDIATE_FIELD	(1 << FEATURE_OR_IMMEDIATE_SHIFT)
 struct i40e_aqc_nvm_config_data_feature {
 	__le16 feature_id;
-	__le16 instance_id;
+#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY		0x01
+#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP		0x08
+#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR		0x10
 	__le16 feature_options;
 	__le16 feature_selection;
 };
 
+I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature);
+
 struct i40e_aqc_nvm_config_data_immediate_field {
-#define ANVM_FEATURE_OR_IMMEDIATE_MASK	0x2
-	__le16 field_id;
-	__le16 instance_id;
+	__le32 field_id;
+	__le32 field_value;
 	__le16 field_options;
-	__le16 field_value;
+	__le16 reserved;
 };
 
+I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field);
+
 /* 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)
@@ -2082,7 +2139,8 @@ struct i40e_aqc_oem_param_change {
 #define I40E_AQ_OEM_PARAM_TYPE_BW_CTL	1
 #define I40E_AQ_OEM_PARAM_MAC		2
 	__le32	param_value1;
-	u8	param_value2[8];
+	__le16	param_value2;
+	u8	reserved[6];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change);
@@ -2096,6 +2154,28 @@ struct i40e_aqc_oem_state_change {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change);
 
+/* Initialize OCSD (0xFE02, direct) */
+struct i40e_aqc_opc_oem_ocsd_initialize {
+	u8 type_status;
+	u8 reserved1[3];
+	__le32 ocsd_memory_block_addr_high;
+	__le32 ocsd_memory_block_addr_low;
+	__le32 requested_update_interval;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize);
+
+/* Initialize OCBB  (0xFE03, direct) */
+struct i40e_aqc_opc_oem_ocbb_initialize {
+	u8 type_status;
+	u8 reserved1[3];
+	__le32 ocbb_memory_block_addr_high;
+	__le32 ocbb_memory_block_addr_low;
+	u8 reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize);
+
 /* debug commands */
 
 /* get device id (0xFF00) uses the generic structure */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 04c7c1557a0c..708891571dae 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -126,6 +126,20 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring)
 }
 
 /**
+ * i40e_get_head - Retrieve head from head writeback
+ * @tx_ring:  tx ring to fetch head of
+ *
+ * Returns value of Tx ring head based on value stored
+ * in head write-back location
+ **/
+static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
+{
+	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
+
+	return le32_to_cpu(*(volatile __le32 *)head);
+}
+
+/**
  * i40e_get_tx_pending - how many tx descriptors not processed
  * @tx_ring: the ring of descriptors
  *
@@ -134,10 +148,16 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring)
  **/
 static u32 i40e_get_tx_pending(struct i40e_ring *ring)
 {
-	u32 ntu = ((ring->next_to_clean <= ring->next_to_use)
-			? ring->next_to_use
-			: ring->next_to_use + ring->count);
-	return ntu - ring->next_to_clean;
+	u32 head, tail;
+
+	head = i40e_get_head(ring);
+	tail = readl(ring->tail);
+
+	if (head != tail)
+		return (head < tail) ?
+			tail - head : (tail + ring->count - head);
+
+	return 0;
 }
 
 /**
@@ -146,6 +166,8 @@ static u32 i40e_get_tx_pending(struct i40e_ring *ring)
  **/
 static bool i40e_check_tx_hang(struct i40e_ring *tx_ring)
 {
+	u32 tx_done = tx_ring->stats.packets;
+	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
 	u32 tx_pending = i40e_get_tx_pending(tx_ring);
 	bool ret = false;
 
@@ -162,35 +184,21 @@ static bool i40e_check_tx_hang(struct i40e_ring *tx_ring)
 	 * run the check_tx_hang logic with a transmit completion
 	 * pending but without time to complete it yet.
 	 */
-	if ((tx_ring->tx_stats.tx_done_old == tx_ring->stats.packets) &&
-	    (tx_pending >= I40E_MIN_DESC_PENDING)) {
+	if ((tx_done_old == tx_done) && tx_pending) {
 		/* make sure it is true for two checks in a row */
 		ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED,
 				       &tx_ring->state);
-	} else if (!(tx_ring->tx_stats.tx_done_old == tx_ring->stats.packets) ||
-		   !(tx_pending < I40E_MIN_DESC_PENDING) ||
-		   !(tx_pending > 0)) {
+	} else if (tx_done_old == tx_done &&
+		   (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) {
 		/* update completed stats and disarm the hang check */
-		tx_ring->tx_stats.tx_done_old = tx_ring->stats.packets;
+		tx_ring->tx_stats.tx_done_old = tx_done;
 		clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state);
 	}
 
 	return ret;
 }
 
-/**
- * i40e_get_head - Retrieve head from head writeback
- * @tx_ring:  tx ring to fetch head of
- *
- * Returns value of Tx ring head based on value stored
- * in head write-back location
- **/
-static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
-{
-	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
-
-	return le32_to_cpu(*(volatile __le32 *)head);
-}
+#define WB_STRIDE 0x3
 
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
@@ -293,6 +301,14 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
+	if (budget &&
+	    !((i & WB_STRIDE) == WB_STRIDE) &&
+	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+		tx_ring->arm_wb = true;
+	else
+		tx_ring->arm_wb = false;
+
 	if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -344,6 +360,24 @@ 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
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+	u32 val = I40E_VFINT_DYN_CTLN_INTENA_MASK |
+		  I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK |
+		  I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK;
+		  /* allow 00 to be written to the index */
+
+	wr32(&vsi->back->hw,
+	     I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1),
+	     val);
+}
+
+/**
  * i40e_set_new_dynamic_itr - Find new ITR level
  * @rc: structure containing ring performance data
  *
@@ -568,6 +602,8 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	if (!rx_ring->rx_bi)
 		goto err;
 
+	u64_stats_init(&rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = ring_is_16byte_desc_enabled(rx_ring)
 		? rx_ring->count * sizeof(union i40e_16byte_rx_desc)
@@ -1065,6 +1101,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	struct i40e_vsi *vsi = q_vector->vsi;
 	struct i40e_ring *ring;
 	bool clean_complete = true;
+	bool arm_wb = false;
 	int budget_per_ring;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
@@ -1075,8 +1112,10 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
-	i40e_for_each_ring(ring, q_vector->tx)
+	i40e_for_each_ring(ring, q_vector->tx) {
 		clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+		arm_wb |= ring->arm_wb;
+	}
 
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
@@ -1087,8 +1126,11 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 		clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		if (arm_wb)
+			i40e_force_wb(vsi, q_vector);
 		return budget;
+	}
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete(napi);
@@ -1122,8 +1164,8 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 	u32  tx_flags = 0;
 
 	/* if we have a HW VLAN tag being added, default to the HW one */
-	if (vlan_tx_tag_present(skb)) {
-		tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= I40E_TX_FLAGS_HW_VLAN;
 	/* else if it is a SW VLAN, check the next protocol and store the tag */
 	} else if (protocol == htons(ETH_P_8021Q)) {
@@ -1170,17 +1212,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (protocol == htons(ETH_P_IP)) {
-		iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	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 (skb_is_gso_v6(skb)) {
-
-		ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb)
-					   : ipv6_hdr(skb);
+	} 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,
@@ -1238,13 +1279,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			if (tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -1254,6 +1291,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 				   ((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;
+			tx_flags |= I40E_TX_FLAGS_IPV6;
+		}
+
 
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
@@ -1344,6 +1386,67 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
 	context_desc->type_cmd_tso_mss = cpu_to_le64(cd_type_cmd_tso_mss);
 }
 
+ /**
+ * i40e_chk_linearize - Check if there are more than 8 fragments per packet
+ * @skb:      send buffer
+ * @tx_flags: collected send information
+ * @hdr_len:  size of the packet header
+ *
+ * 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,
+			       const u8 hdr_len)
+{
+	struct skb_frag_struct *frag;
+	bool linearize = false;
+	unsigned int size = 0;
+	u16 num_frags;
+	u16 gso_segs;
+
+	num_frags = skb_shinfo(skb)->nr_frags;
+	gso_segs = skb_shinfo(skb)->gso_segs;
+
+	if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
+		u16 j = 1;
+
+		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];
+		size = hdr_len;
+		/* we might still have more fragments per segment */
+		do {
+			size += skb_frag_size(frag);
+			frag++; j++;
+			if (j == I40E_MAX_BUFFER_TXD) {
+				if (size < skb_shinfo(skb)->gso_size) {
+					linearize = true;
+					break;
+				}
+				j = 1;
+				size -= skb_shinfo(skb)->gso_size;
+				if (size)
+					j++;
+				size += hdr_len;
+			}
+			num_frags--;
+		} while (num_frags);
+	} else {
+		if (num_frags >= I40E_MAX_BUFFER_TXD)
+			linearize = true;
+	}
+
+linearize_chk_done:
+	return linearize;
+}
+
 /**
  * i40e_tx_map - Build the Tx descriptor
  * @tx_ring:  ring to send buffer on
@@ -1618,6 +1721,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (tso)
 		tx_flags |= I40E_TX_FLAGS_TSO;
 
+	if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+		if (skb_linearize(skb))
+			goto out_drop;
+
 	skb_tx_timestamp(skb);
 
 	/* always enable CRC insertion offload */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index c7f29626eada..c950a038237c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -112,6 +112,7 @@ enum i40e_dyn_idx_t {
 
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_MAX_BUFFER_TXD	8
 #define I40E_MIN_TX_LEN		17
 #define I40E_MAX_DATA_PER_TXD	8192
 
@@ -238,6 +239,7 @@ struct i40e_ring {
 	u8 atr_count;
 
 	bool ring_active;		/* is ring online or not */
+	bool arm_wb;		/* do something to arm write back */
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 68aec11f6523..3d0fdaab5cc8 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -211,6 +211,7 @@ struct i40e_hw_capabilities {
 	bool evb_802_1_qbh; /* Bridge Port Extension */
 	bool dcb;
 	bool fcoe;
+	bool iscsi; /* Indicates iSCSI enabled */
 	bool mfp_mode_1;
 	bool mgmt_cem;
 	bool ieee_1588;
@@ -425,7 +426,7 @@ struct i40e_hw {
 	u8 __iomem *hw_addr;
 	void *back;
 
-	/* function pointer structs */
+	/* subsystem structs */
 	struct i40e_phy_info phy;
 	struct i40e_mac_info mac;
 	struct i40e_bus_info bus;
@@ -452,6 +453,11 @@ struct i40e_hw {
 	u8  pf_id;
 	u16 main_vsi_seid;
 
+	/* for multi-function MACs */
+	u16 partition_id;
+	u16 num_partitions;
+	u16 num_ports;
+
 	/* Closest numa node to the device */
 	u16 numa_node;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index cabaf599f562..8d8c201c63c1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -36,7 +36,7 @@ char i40evf_driver_name[] = "i40evf";
 static const char i40evf_driver_string[] =
 	"Intel(R) XL710/X710 Virtual Function Network Driver";
 
-#define DRV_VERSION "1.0.6"
+#define DRV_VERSION "1.2.0"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2014 Intel Corporation.";
@@ -313,10 +313,6 @@ static irqreturn_t i40evf_msix_aq(int irq, void *data)
 	val = val | I40E_PFINT_DYN_CTL0_CLEARPBA_MASK;
 	wr32(hw, I40E_VFINT_DYN_CTL01, val);
 
-	/* re-enable interrupt causes */
-	wr32(hw, I40E_VFINT_ICR0_ENA1, ena_mask);
-	wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK);
-
 	/* schedule work on the private workqueue */
 	schedule_work(&adapter->adminq_task);
 
@@ -947,30 +943,6 @@ static int i40evf_up_complete(struct i40evf_adapter *adapter)
 }
 
 /**
- * i40evf_clean_all_rx_rings - Free Rx Buffers for all queues
- * @adapter: board private structure
- **/
-static void i40evf_clean_all_rx_rings(struct i40evf_adapter *adapter)
-{
-	int i;
-
-	for (i = 0; i < adapter->num_active_queues; i++)
-		i40evf_clean_rx_ring(adapter->rx_rings[i]);
-}
-
-/**
- * i40evf_clean_all_tx_rings - Free Tx Buffers for all queues
- * @adapter: board private structure
- **/
-static void i40evf_clean_all_tx_rings(struct i40evf_adapter *adapter)
-{
-	int i;
-
-	for (i = 0; i < adapter->num_active_queues; i++)
-		i40evf_clean_tx_ring(adapter->tx_rings[i]);
-}
-
-/**
  * i40e_down - Shutdown the connection processing
  * @adapter: board private structure
  **/
@@ -982,6 +954,12 @@ void i40evf_down(struct i40evf_adapter *adapter)
 	if (adapter->state == __I40EVF_DOWN)
 		return;
 
+	while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
+				&adapter->crit_section))
+		usleep_range(500, 1000);
+
+	i40evf_irq_disable(adapter);
+
 	/* remove all MAC filters */
 	list_for_each_entry(f, &adapter->mac_filter_list, list) {
 		f->remove = true;
@@ -992,25 +970,27 @@ void i40evf_down(struct i40evf_adapter *adapter)
 	}
 	if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) &&
 	    adapter->state != __I40EVF_RESETTING) {
-		adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+		/* cancel any current operation */
+		adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
+		adapter->aq_pending = 0;
+		/* Schedule operations to close down the HW. Don't wait
+		 * here for this to complete. The watchdog is still running
+		 * and it will take care of this.
+		 */
+		adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER;
 		adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
-		/* disable receives */
 		adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES;
-		mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
-		msleep(20);
 	}
 	netif_tx_disable(netdev);
 
 	netif_tx_stop_all_queues(netdev);
 
-	i40evf_irq_disable(adapter);
-
 	i40evf_napi_disable_all(adapter);
 
-	netif_carrier_off(netdev);
+	msleep(20);
 
-	i40evf_clean_all_tx_rings(adapter);
-	i40evf_clean_all_rx_rings(adapter);
+	netif_carrier_off(netdev);
+	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
 }
 
 /**
@@ -1356,8 +1336,13 @@ static void i40evf_watchdog_task(struct work_struct *work)
 	/* Process admin queue tasks. After init, everything gets done
 	 * here so we don't race on the admin queue.
 	 */
-	if (adapter->aq_pending)
+	if (adapter->aq_pending) {
+		if (!i40evf_asq_done(hw)) {
+			dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n");
+			i40evf_send_api_ver(adapter);
+		}
 		goto watchdog_done;
+	}
 
 	if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) {
 		i40evf_map_queues(adapter);
@@ -1401,11 +1386,14 @@ static void i40evf_watchdog_task(struct work_struct *work)
 
 	if (adapter->state == __I40EVF_RUNNING)
 		i40evf_request_stats(adapter);
-
-	i40evf_irq_enable(adapter, true);
-	i40evf_fire_sw_int(adapter, 0xFF);
-
 watchdog_done:
+	if (adapter->state == __I40EVF_RUNNING) {
+		i40evf_irq_enable_queues(adapter, ~0);
+		i40evf_fire_sw_int(adapter, 0xFF);
+	} else {
+		i40evf_fire_sw_int(adapter, 0x1);
+	}
+
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
 restart_watchdog:
 	if (adapter->state == __I40EVF_REMOVE)
@@ -1633,17 +1621,17 @@ static void i40evf_adminq_task(struct work_struct *work)
 	u16 pending;
 
 	if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
-		return;
+		goto out;
 
 	event.buf_len = I40EVF_MAX_AQ_BUF_SIZE;
 	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf)
-		return;
+		goto out;
 
 	v_msg = (struct i40e_virtchnl_msg *)&event.desc;
 	do {
 		ret = i40evf_clean_arq_element(hw, &event, &pending);
-		if (ret)
+		if (ret || !v_msg->v_opcode)
 			break; /* No event to process or error cleaning ARQ */
 
 		i40evf_virtchnl_completion(adapter, v_msg->v_opcode,
@@ -1688,10 +1676,10 @@ static void i40evf_adminq_task(struct work_struct *work)
 	if (oldval != val)
 		wr32(hw, hw->aq.asq.len, val);
 
+	kfree(event.msg_buf);
+out:
 	/* re-enable Admin queue interrupt cause */
 	i40evf_misc_irq_enable(adapter);
-
-	kfree(event.msg_buf);
 }
 
 /**
@@ -2053,12 +2041,8 @@ static void i40evf_init_task(struct work_struct *work)
 		/* aq msg sent, awaiting reply */
 		err = i40evf_verify_api_ver(adapter);
 		if (err) {
-			dev_info(&pdev->dev, "Unable to verify API version (%d), retrying\n",
-				 err);
-			if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) {
-				dev_info(&pdev->dev, "Resending request\n");
+			if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK)
 				err = i40evf_send_api_ver(adapter);
-			}
 			goto err;
 		}
 		err = i40evf_send_vf_config_msg(adapter);
@@ -2081,7 +2065,6 @@ static void i40evf_init_task(struct work_struct *work)
 		}
 		err = i40evf_get_vf_config(adapter);
 		if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) {
-			dev_info(&pdev->dev, "Resending VF config request\n");
 			err = i40evf_send_vf_config_msg(adapter);
 			goto err;
 		}
@@ -2230,12 +2213,18 @@ err:
 static void i40evf_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev))
 		i40evf_close(netdev);
 
+	/* Prevent the watchdog from running. */
+	adapter->state = __I40EVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->aq_pending = 0;
+
 #ifdef CONFIG_PM
 	pci_save_state(pdev);
 
@@ -2448,7 +2437,18 @@ static void i40evf_remove(struct pci_dev *pdev)
 		unregister_netdev(netdev);
 		adapter->netdev_registered = false;
 	}
+
+	/* Shut down all the garbage mashers on the detention level */
 	adapter->state = __I40EVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->aq_pending = 0;
+	i40evf_request_reset(adapter);
+	msleep(20);
+	/* If the FW isn't responding, kick it once, but only once. */
+	if (!i40evf_asq_done(hw)) {
+		i40evf_request_reset(adapter);
+		msleep(20);
+	}
 
 	if (adapter->msix_entries) {
 		i40evf_misc_irq_disable(adapter);
@@ -2477,6 +2477,10 @@ static void i40evf_remove(struct pci_dev *pdev)
 		list_del(&f->list);
 		kfree(f);
 	}
+	list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) {
+		list_del(&f->list);
+		kfree(f);
+	}
 
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index 5fde5a7f4591..3f0c85ecbca6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -715,14 +715,14 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		}
 		return;
 	}
-	if (v_opcode != adapter->current_op)
-		dev_info(&adapter->pdev->dev, "Pending op is %d, received %d\n",
-			 adapter->current_op, v_opcode);
 	if (v_retval) {
 		dev_err(&adapter->pdev->dev, "%s: PF returned error %d to our request %d\n",
 			__func__, v_retval, v_opcode);
 	}
 	switch (v_opcode) {
+	case I40E_VIRTCHNL_OP_VERSION:
+		/* no action, but also not an error */
+		break;
 	case I40E_VIRTCHNL_OP_GET_STATS: {
 		struct i40e_eth_stats *stats =
 			(struct i40e_eth_stats *)msg;