diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 33c35d3b7420fa9ae545aea4ebd5160036914718..aca9cef50d81a521f21aa74a93ebaebd0a27d793 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -182,6 +182,7 @@ struct i40e_lump_tracking {
 enum i40e_fd_stat_idx {
 	I40E_FD_STAT_ATR,
 	I40E_FD_STAT_SB,
+	I40E_FD_STAT_ATR_TUNNEL,
 	I40E_FD_STAT_PF_COUNT
 };
 #define I40E_FD_STAT_PF_IDX(pf_id) ((pf_id) * I40E_FD_STAT_PF_COUNT)
@@ -189,6 +190,8 @@ enum i40e_fd_stat_idx {
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR)
 #define I40E_FD_SB_STAT_IDX(pf_id)  \
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_SB)
+#define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
+			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
 
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
@@ -263,8 +266,6 @@ struct i40e_pf {
 
 	struct hlist_head fdir_filter_list;
 	u16 fdir_pf_active_filters;
-	u16 fd_sb_cnt_idx;
-	u16 fd_atr_cnt_idx;
 	unsigned long fd_flush_timestamp;
 	u32 fd_flush_cnt;
 	u32 fd_add_err;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 4cbaaeb902c47737274010d2070d6fb95c5637ce..9a68c65b17ea03bd00642aab5fe3b2e5a5066765 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -147,6 +147,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	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),
+	I40E_PF_STAT("fdir_atr_tunnel_match", stats.fd_atr_tunnel_match),
 	I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match),
 
 	/* LPI stats */
@@ -1548,6 +1549,17 @@ static int i40e_loopback_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
+static inline bool i40e_active_vfs(struct i40e_pf *pf)
+{
+	struct i40e_vf *vfs = pf->vf;
+	int i;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++)
+		if (vfs[i].vf_states & I40E_VF_STAT_ACTIVE)
+			return true;
+	return false;
+}
+
 static void i40e_diag_test(struct net_device *netdev,
 			   struct ethtool_test *eth_test, u64 *data)
 {
@@ -1560,6 +1572,20 @@ static void i40e_diag_test(struct net_device *netdev,
 		netif_info(pf, drv, netdev, "offline testing starting\n");
 
 		set_bit(__I40E_TESTING, &pf->state);
+
+		if (i40e_active_vfs(pf)) {
+			dev_warn(&pf->pdev->dev,
+				 "Please take active VFS offline and restart the adapter before running NIC diagnostics\n");
+			data[I40E_ETH_TEST_REG]		= 1;
+			data[I40E_ETH_TEST_EEPROM]	= 1;
+			data[I40E_ETH_TEST_INTR]	= 1;
+			data[I40E_ETH_TEST_LOOPBACK]	= 1;
+			data[I40E_ETH_TEST_LINK]	= 1;
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+			clear_bit(__I40E_TESTING, &pf->state);
+			goto skip_ol_tests;
+		}
+
 		/* If the device is online then take it offline */
 		if (if_running)
 			/* indicate we're in test mode */
@@ -1605,6 +1631,8 @@ static void i40e_diag_test(struct net_device *netdev,
 		data[I40E_ETH_TEST_LOOPBACK] = 0;
 	}
 
+skip_ol_tests:
+
 	netif_info(pf, drv, netdev, "testing finished\n");
 }
 
@@ -2265,7 +2293,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	input->pctype = 0;
 	input->dest_vsi = vsi->id;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
-	input->cnt_index  = pf->fd_sb_cnt_idx;
+	input->cnt_index  = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 	input->flow_type = fsp->flow_type;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 1803afeef23ede81ed906b5400e9f3164234a4de..c8b621e0e7cda622c5a0fa9e795a898e53886cf5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -118,7 +118,7 @@ static inline int i40e_fcoe_fc_eof(struct sk_buff *skb, u8 *eof)
  *
  * The FC EOF is converted to the value understood by HW for descriptor
  * programming. Never call this w/o calling i40e_fcoe_eof_is_supported()
- * first.
+ * first and that already checks for all supported valid eof values.
  **/
 static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 {
@@ -132,9 +132,12 @@ static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 	case FC_EOF_A:
 		return I40E_TX_DESC_CMD_L4T_EOFT_EOF_A;
 	default:
-		/* FIXME: still returns 0 */
-		pr_err("Unrecognized EOF %x\n", eof);
-		return 0;
+		/* Supported valid eof shall be already checked by
+		 * calling i40e_fcoe_eof_is_supported() first,
+		 * therefore this default case shall never hit.
+		 */
+		WARN_ON(1);
+		return -EINVAL;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a54c14491e3b6a4dbc168980dd44d399b6766487..0a3e928a2b0014b62ecbbd4d27efd1b7607816dd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_BUILD 4
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -772,9 +772,8 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
 
 	dcb_cfg = &hw->local_dcbx_config;
 
-	/* See if DCB enabled with PFC TC */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED) ||
-	    !(dcb_cfg->pfc.pfcenable)) {
+	/* Collect Link XOFF stats when PFC is disabled */
+	if (!dcb_cfg->pfc.pfcenable) {
 		i40e_update_link_xoff_rx(pf);
 		return;
 	}
@@ -1097,12 +1096,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_jabber, &nsd->rx_jabber);
 
 	/* FDIR stats */
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_atr_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_atr_match, &nsd->fd_atr_match);
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_sb_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_sb_match, &nsd->fd_sb_match);
+	i40e_stat_update32(hw,
+		      I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)),
+		      pf->stat_offsets_loaded,
+		      &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match);
 
 	val = rd32(hw, I40E_PRTPM_EEE_STAT);
 	nsd->tx_lpi_status =
@@ -4739,7 +4744,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 		pf->fd_add_err = pf->fd_atr_cnt = 0;
 		if (pf->fd_tcp_rule > 0) {
 			pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
 			pf->fd_tcp_rule = 0;
 		}
 		i40e_fdir_filter_restore(vsi);
@@ -5428,7 +5434,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
-			dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 		}
 	}
 	/* Wait for some more space to be available to turn on ATR */
@@ -5436,7 +5443,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
 		}
 	}
 }
@@ -5469,7 +5477,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 
 		if (!(time_after(jiffies, min_flush_time)) &&
 		    (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) {
-			dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
 			disable_atr = true;
 		}
 
@@ -5496,7 +5505,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 			if (!disable_atr)
 				pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 			clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
-			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 		}
 	}
 }
@@ -7676,12 +7686,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 		pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
-		/* Setup a counter for fd_atr per PF */
-		pf->fd_atr_cnt_idx = I40E_FD_ATR_STAT_IDX(pf->hw.pf_id);
 		if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
 			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-			/* Setup a counter for fd_sb per PF */
-			pf->fd_sb_cnt_idx = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 		} else {
 			dev_info(&pf->pdev->dev,
 				 "Flow Director Sideband mode Disabled in MFP mode\n");
@@ -7771,7 +7777,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
 		pf->fdir_pf_active_filters = 0;
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-		dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
+		if (I40E_DEBUG_FD & pf->hw.debug_mask)
+			dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		/* if ATR was auto disabled it can be re-enabled. */
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0b4a7be2c7d2b21f2286732218c0cbb2f2bb61b2..cc82a7ffacb06326f259ff3e8c1f0fc4ec6e9838 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -165,9 +165,6 @@ int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
 	tx_desc->cmd_type_offset_bsz =
 		build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_SIZE, 0);
 
-	/* set the timestamp */
-	tx_buf->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.
 	 */
@@ -283,7 +280,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	if (add) {
 		pf->fd_tcp_rule++;
 		if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) {
-			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
 			pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 		}
 	} else {
@@ -291,7 +289,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				  (pf->fd_tcp_rule - 1) : 0;
 		if (pf->fd_tcp_rule == 0) {
 			pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
 		}
 	}
 
@@ -501,7 +500,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 			    !(pf->auto_disable_flags &
 				     I40E_FLAG_FD_SB_ENABLED)) {
-				dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
+				if (I40E_DEBUG_FD & pf->hw.debug_mask)
+					dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
 				pf->auto_disable_flags |=
 							I40E_FLAG_FD_SB_ENABLED;
 			}
@@ -807,10 +807,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 			 tx_ring->vsi->seid,
 			 tx_ring->queue_index,
 			 tx_ring->next_to_use, i);
-		dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n"
-			 "  time_stamp           <%lx>\n"
-			 "  jiffies              <%lx>\n",
-			 tx_ring->tx_bi[i].time_stamp, jiffies);
 
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
@@ -1653,9 +1649,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
-			/* TODO: shouldn't we increment a counter indicating the
-			 * drop?
-			 */
 			continue;
 		}
 
@@ -1923,11 +1916,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
  * i40e_atr - Add a Flow Director ATR filter
  * @tx_ring:  ring to add programming descriptor to
  * @skb:      send buffer
- * @flags:    send flags
+ * @tx_flags: send tx flags
  * @protocol: wire protocol
  **/
 static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		     u32 flags, __be16 protocol)
+		     u32 tx_flags, __be16 protocol)
 {
 	struct i40e_filter_program_desc *fdir_desc;
 	struct i40e_pf *pf = tx_ring->vsi->back;
@@ -1952,25 +1945,38 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!tx_ring->atr_sample_rate)
 		return;
 
-	/* snag network header to get L4 type and address */
-	hdr.network = skb_network_header(skb);
+	if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6)))
+		return;
 
-	/* Currently only IPv4/IPv6 with TCP is supported */
-	if (protocol == htons(ETH_P_IP)) {
-		if (hdr.ipv4->protocol != IPPROTO_TCP)
-			return;
+	if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) {
+		/* snag network header to get L4 type and address */
+		hdr.network = skb_network_header(skb);
 
-		/* access ihl as a u8 to avoid unaligned access on ia64 */
-		hlen = (hdr.network[0] & 0x0F) << 2;
-	} else if (protocol == htons(ETH_P_IPV6)) {
-		if (hdr.ipv6->nexthdr != IPPROTO_TCP)
+		/* 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;
-
-		hlen = sizeof(struct ipv6hdr);
 	} else {
-		return;
+		hdr.network = skb_inner_network_header(skb);
+		hlen = skb_inner_network_header_len(skb);
 	}
 
+	/* 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))
+		return;
+
 	th = (struct tcphdr *)(hdr.network + hlen);
 
 	/* Due to lack of space, no more new filters can be programmed */
@@ -2020,9 +2026,16 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		     I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT;
 
 	dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
-	dtype_cmd |=
-		((u32)pf->fd_atr_cnt_idx << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
-		I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+	if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL))
+		dtype_cmd |=
+			((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) <<
+			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
+			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+	else
+		dtype_cmd |=
+			((u32)I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id) <<
+			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
+			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
 	fdir_desc->rsvd = cpu_to_le32(0);
@@ -2043,13 +2056,13 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
 #ifdef I40E_FCOE
-int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring,
-			       u32 *flags)
-#else
-static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
+inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring,
 				      u32 *flags)
+#else
+static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
+					     struct i40e_ring *tx_ring,
+					     u32 *flags)
 #endif
 {
 	__be16 protocol = skb->protocol;
@@ -2117,16 +2130,14 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
  * i40e_tso - set up the tso context descriptor
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
- * @tx_flags: the collected send information
- * @protocol: the send protocol
  * @hdr_len:  ptr to the size of the packet header
  * @cd_tunneling: ptr to context descriptor bits
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
  **/
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		    u32 tx_flags, __be16 protocol, u8 *hdr_len,
-		    u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling)
+		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss,
+		    u32 *cd_tunneling)
 {
 	u32 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
@@ -2218,12 +2229,12 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
 /**
  * i40e_tx_enable_csum - Enable Tx checksum offloads
  * @skb: send buffer
- * @tx_flags: Tx flags currently set
+ * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
+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)
@@ -2239,6 +2250,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
 			return;
@@ -2248,18 +2260,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		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) {
+		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) {
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (tx_flags & I40E_TX_FLAGS_TSO)
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
 		}
 
@@ -2271,8 +2282,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					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;
+			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
@@ -2282,12 +2293,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 	}
 
 	/* Enable IP checksum offloads */
-	if (tx_flags & I40E_TX_FLAGS_IPV4) {
+	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 		l4_hdr = this_ip_hdr->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) {
+		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
 			this_ip_hdr->check = 0;
 		} else {
@@ -2296,7 +2307,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		/* Now set the td_offset for IP header length */
 		*td_offset = (network_hdr_len >> 2) <<
 			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+	} 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 */
@@ -2394,9 +2405,9 @@ static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
  * Returns 0 if stop is not needed
  **/
 #ifdef I40E_FCOE
-int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 #else
-static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 #endif
 {
 	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
@@ -2476,13 +2487,13 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
  * @td_offset: offset for checksum or crc
  **/
 #ifdef I40E_FCOE
-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)
-#else
-static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
+inline 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)
+#else
+static inline 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)
 #endif
 {
 	unsigned int data_len = skb->data_len;
@@ -2588,9 +2599,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 						 tx_ring->queue_index),
 			     first->bytecount);
 
-	/* set the timestamp */
-	first->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -2643,11 +2651,11 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * one descriptor.
  **/
 #ifdef I40E_FCOE
-int i40e_xmit_descriptor_count(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring)
-#else
-static int i40e_xmit_descriptor_count(struct sk_buff *skb,
+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;
@@ -2709,7 +2717,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len,
+	tso = i40e_tso(tx_ring, skb, &hdr_len,
 		       &cd_type_cmd_tso_mss, &cd_tunneling);
 
 	if (tso < 0)
@@ -2735,7 +2743,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		tx_flags |= I40E_TX_FLAGS_CSUM;
 
-		i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
+		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
 				    tx_ring, &cd_tunneling);
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 4b0b8102cdc39c2529f49c18d6b1cbc61c48c341..0dc48dc9ca61922a4b11bd0b7624f07c153c603a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -139,6 +139,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_TSYN		(u32)(1 << 8)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -146,7 +147,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 568e855da0f3e16b29a81702766070974dd3da91..9a5a75b1e2bc053b50bec13adde2fd3aa4848595 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1133,6 +1133,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 78d1c4ff565e8853473b70c3827e6a727ff3ce1c..4653b6e653c9470da76e9b35be2bd3767da7bf5b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -980,6 +980,13 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	int pre_existing_vfs = pci_num_vf(pdev);
 	int err = 0;
 
+	if (pf->state & __I40E_TESTING) {
+		dev_warn(&pdev->dev,
+			 "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n");
+		err = -EPERM;
+		goto err_out;
+	}
+
 	dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
 	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
 		i40e_free_vfs(pf);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 3ef23091439f72d90879acd3f820f15c71206127..ec7e220757db1e283cb385f58f0b5955f50e2b25 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -322,10 +322,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 			 tx_ring->vsi->seid,
 			 tx_ring->queue_index,
 			 tx_ring->next_to_use, i);
-		dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n"
-			 "  time_stamp           <%lx>\n"
-			 "  jiffies              <%lx>\n",
-			 tx_ring->tx_bi[i].time_stamp, jiffies);
 
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
@@ -1128,9 +1124,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
-			/* TODO: shouldn't we increment a counter indicating the
-			 * drop?
-			 */
 			continue;
 		}
 
@@ -1350,7 +1343,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 }
 
 /**
- * i40e_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
  * @flags:   the tx flags to be set
@@ -1361,9 +1354,9 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
  * Returns error code indicate the frame should be dropped upon error and the
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
-static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring,
-				      u32 *flags)
+static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb,
+					       struct i40e_ring *tx_ring,
+					       u32 *flags)
 {
 	__be16 protocol = skb->protocol;
 	u32  tx_flags = 0;
@@ -1406,16 +1399,14 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
  * i40e_tso - set up the tso context descriptor
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
- * @tx_flags: the collected send information
- * @protocol: the send protocol
  * @hdr_len:  ptr to the size of the packet header
  * @cd_tunneling: ptr to context descriptor bits
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
  **/
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		    u32 tx_flags, __be16 protocol, u8 *hdr_len,
-		    u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling)
+		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss,
+		    u32 *cd_tunneling)
 {
 	u32 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
@@ -1466,12 +1457,12 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 /**
  * i40e_tx_enable_csum - Enable Tx checksum offloads
  * @skb: send buffer
- * @tx_flags: Tx flags currently set
+ * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
+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)
@@ -1487,6 +1478,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
 			return;
@@ -1496,18 +1488,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		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) {
+		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) {
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (tx_flags & I40E_TX_FLAGS_TSO)
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
 		}
 
@@ -1519,8 +1510,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					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;
+			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
 
 
@@ -1532,12 +1523,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 	}
 
 	/* Enable IP checksum offloads */
-	if (tx_flags & I40E_TX_FLAGS_IPV4) {
+	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 		l4_hdr = this_ip_hdr->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) {
+		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
 			this_ip_hdr->check = 0;
 		} else {
@@ -1546,7 +1537,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		/* Now set the td_offset for IP header length */
 		*td_offset = (network_hdr_len >> 2) <<
 			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+	} 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 */
@@ -1675,7 +1666,44 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
 }
 
 /**
- * i40e_tx_map - Build the Tx descriptor
+ * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size:    the size buffer we want to assure is available
+ *
+ * Returns -EBUSY if a stop is needed, else 0
+ **/
+static inline int __i40evf_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 */
+	smp_mb();
+
+	/* Check again in a case another CPU has just made room available. */
+	if (likely(I40E_DESC_UNUSED(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	++tx_ring->tx_stats.restart_queue;
+	return 0;
+}
+
+/**
+ * i40evf_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 i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
+		return 0;
+	return __i40evf_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * i40evf_tx_map - Build the Tx descriptor
  * @tx_ring:  ring to send buffer on
  * @skb:      send buffer
  * @first:    first buffer info buffer to use
@@ -1684,9 +1712,9 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
  * @td_cmd:   the command field in the descriptor
  * @td_offset: offset for checksum or crc
  **/
-static 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)
+static inline void i40evf_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)
 {
 	unsigned int data_len = skb->data_len;
 	unsigned int size = skb_headlen(skb);
@@ -1792,9 +1820,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 						 tx_ring->queue_index),
 			     first->bytecount);
 
-	/* set the timestamp */
-	first->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -1811,8 +1836,12 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	tx_ring->next_to_use = i;
 
+	i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED);
 	/* notify HW of packet */
-	writel(i, tx_ring->tail);
+	if (!skb->xmit_more ||
+	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						   tx_ring->queue_index)))
+		writel(i, tx_ring->tail);
 
 	return;
 
@@ -1834,44 +1863,7 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 }
 
 /**
- * __i40e_maybe_stop_tx - 2nd level check for tx stop conditions
- * @tx_ring: the ring to be checked
- * @size:    the size buffer we want to assure is available
- *
- * Returns -EBUSY if a stop is needed, else 0
- **/
-static inline 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 */
-	smp_mb();
-
-	/* Check again in a case another CPU has just made room available. */
-	if (likely(I40E_DESC_UNUSED(tx_ring) < size))
-		return -EBUSY;
-
-	/* A reprieve! - use start_queue because it doesn't call schedule */
-	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	++tx_ring->tx_stats.restart_queue;
-	return 0;
-}
-
-/**
- * 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 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_xmit_descriptor_count - calculate number of tx descriptors needed
+ * i40evf_xmit_descriptor_count - calculate number of tx descriptors needed
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
  *
@@ -1879,8 +1871,8 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
  * there is not enough descriptors available in this ring since we need at least
  * one descriptor.
  **/
-static int i40e_xmit_descriptor_count(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring)
+static inline int i40evf_xmit_descriptor_count(struct sk_buff *skb,
+					       struct i40e_ring *tx_ring)
 {
 	unsigned int f;
 	int count = 0;
@@ -1895,7 +1887,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 		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)) {
+	if (i40evf_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;
 		return 0;
 	}
@@ -1921,11 +1913,11 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	u32 td_cmd = 0;
 	u8 hdr_len = 0;
 	int tso;
-	if (0 == i40e_xmit_descriptor_count(skb, tx_ring))
+	if (0 == i40evf_xmit_descriptor_count(skb, tx_ring))
 		return NETDEV_TX_BUSY;
 
 	/* prepare the xmit flags */
-	if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
+	if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
 		goto out_drop;
 
 	/* obtain protocol of skb */
@@ -1940,7 +1932,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len,
+	tso = i40e_tso(tx_ring, skb, &hdr_len,
 		       &cd_type_cmd_tso_mss, &cd_tunneling);
 
 	if (tso < 0)
@@ -1961,17 +1953,15 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		tx_flags |= I40E_TX_FLAGS_CSUM;
 
-		i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
+		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);
 
-	i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
-		    td_cmd, td_offset);
-
-	i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+	i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
+		      td_cmd, td_offset);
 
 	return NETDEV_TX_OK;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 1e49bb1fbac1f0de59444626cc9645b72aeac0da..e7a34f899f2cbb8150495a31e0690a95e90efc1a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -138,6 +138,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FCCRC		(u32)(1 << 6)
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -145,7 +146,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index ec9d83a9337944f20f934cf6217467ee61ec7303..c463ec41579c708ffbe606ea0b31ca0485ea4c58 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -1108,6 +1108,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 9f6fb19062a00c43005d39e03c8037bf58f93488..9a1d0f142b091c3cecb06ce65ffac1d3c8e6bf1a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2594,18 +2594,35 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fdir_filter *input;
 	union ixgbe_atr_input mask;
+	u8 queue;
 	int err;
 
 	if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
 		return -EOPNOTSUPP;
 
-	/*
-	 * Don't allow programming if the action is a queue greater than
-	 * the number of online Rx queues.
+	/* ring_cookie is a masked into a set of queues and ixgbe pools or
+	 * we use the drop index.
 	 */
-	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
-	    (fsp->ring_cookie >= adapter->num_rx_queues))
-		return -EINVAL;
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		queue = IXGBE_FDIR_DROP_QUEUE;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (!vf && (ring >= adapter->num_rx_queues))
+			return -EINVAL;
+		else if (vf &&
+			 ((vf > adapter->num_vfs) ||
+			   ring >= adapter->num_rx_queues_per_pool))
+			return -EINVAL;
+
+		/* Map the ring onto the absolute queue index */
+		if (!vf)
+			queue = adapter->rx_ring[ring]->reg_idx;
+		else
+			queue = ((vf - 1) *
+				adapter->num_rx_queues_per_pool) + ring;
+	}
 
 	/* Don't allow indexes to exist outside of available space */
 	if (fsp->location >= ((1024 << adapter->fdir_pballoc) - 2)) {
@@ -2683,10 +2700,7 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 
 	/* program filters to filter memory */
 	err = ixgbe_fdir_write_perfect_filter_82599(hw,
-				&input->filter, input->sw_idx,
-				(input->action == IXGBE_FDIR_DROP_QUEUE) ?
-				IXGBE_FDIR_DROP_QUEUE :
-				adapter->rx_ring[input->action]->reg_idx);
+				&input->filter, input->sw_idx, queue);
 	if (err)
 		goto err_out_w_lock;
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index ae832b45b44c01fe149547eb07734865dabcd478..0594933cdf55c715965db2ff46c88e272ca8114f 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -796,6 +796,31 @@ struct ethtool_rx_flow_spec {
 	__u32		location;
 };
 
+/* How rings are layed out when accessing virtual functions or
+ * offloaded queues is device specific. To allow users to do flow
+ * steering and specify these queues the ring cookie is partitioned
+ * into a 32bit queue index with an 8 bit virtual function id.
+ * This also leaves the 3bytes for further specifiers. It is possible
+ * future devices may support more than 256 virtual functions if
+ * devices start supporting PCIe w/ARI. However at the moment I
+ * do not know of any devices that support this so I do not reserve
+ * space for this at this time. If a future patch consumes the next
+ * byte it should be aware of this possiblity.
+ */
+#define ETHTOOL_RX_FLOW_SPEC_RING	0x00000000FFFFFFFFLL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF	0x000000FF00000000LL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32
+static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie)
+{
+	return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie;
+};
+
+static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
+{
+	return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >>
+				ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+};
+
 /**
  * struct ethtool_rxnfc - command to get or set RX flow classification rules
  * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH,