Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2017-06-20

This series contains updates to i40e and i40evf only.

Björn adds additional XDP support for i40e, by adding pass and drop actions
and XDP_TX action support.

Jake fixes a possible NULL pointer dereference in
i40evf_get_ethtool_stats() which could occur if the VF fails to recover
from a reset, and then a user requests statistics.  Changed the use of
dev_info() to dev_dbg() for vf_capability client routine so that the
standard log is not spammed with this information which "might" cause
administrators to worry.  Also added more code comments to help explain
why udp_port has be in host byte order and to avoid future changes which
may cause this to break.  Fixed the holding of the RTNL lock for the
entire reset routine, reduced the scope so that the reset function will
handle its own lock, so that we do not have to wrap every reference
to i40e_do_reset() with RTNL lock/unlock.

Alice updates flags related to firmware interactions for WoL and admin
queue command address with the correct value.

Sudheer makes a fix to ensure that the array is not accessed past the
size of the array.

Greg fixes the parsing of firmware 4.33 admin queue commmand "Get CEE
DCBX PER CFG" because the firmware now creates the oper_prio_tc nibbles
reversed from those in the CDD Priority Group sub-TLV.

Carolyn adds a check and message to let users know that when in MFP mode,
changing RSS hash input set is not supported.

Shannon makes the partition bandwidth control more generic since it is not
in just one form of multi-function partitioning (MFP).  Also fixes a bug
which was causing the firmware confusion in some reset sequences, when
we were disabling interrupts and we were clearing the whole register.
Instead we should only be clearing the CAUSE_ENA bit when disabling
interrupts.

Filip adds support for OEM firmware version, so that if a OEM specific
adapter is detected, ethtool reports the OEM product version in the
firmware version string instead of etrack id.

Alan fixes a bug where the driver was not correctly exiting overflow
promiscuous mode, which can happen if "too many" MAC filters are added,
putting the driver into overflow promiscuous mode, and the filters are
then removed.  The bug occurs because the conditional for toggling
promiscuous mode was only be executed when enabled and not when it was
disabled.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e.h

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -103,6 +103,12 @@
 	(I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW | \
 	I40E_AQ_PHY_DEBUG_DISABLE_ALL_LINK_FW)
 
+#define I40E_OEM_EETRACK_ID		0xffffffff
+#define I40E_OEM_GEN_SHIFT		24
+#define I40E_OEM_SNAP_MASK		0x00ff0000
+#define I40E_OEM_SNAP_SHIFT		16
+#define I40E_OEM_RELEASE_MASK		0x0000ffff
+
 /* The values in here are decimal coded as hex as is the case in the NVM map*/
 #define I40E_CURRENT_NVM_VERSION_HI	0x2
 #define I40E_CURRENT_NVM_VERSION_LO	0x40
@@ -516,9 +522,8 @@ struct i40e_pf {
 	bool ptp_tx;
 	bool ptp_rx;
 	u16 rss_table_size; /* HW RSS table size */
-	/* These are only valid in NPAR modes */
-	u32 npar_max_bw;
-	u32 npar_min_bw;
+	u32 max_bw;
+	u32 min_bw;
 
 	u32 ioremap_len;
 	u32 fd_inv;
@@ -629,6 +634,7 @@ struct i40e_vsi {
 	/* These are containers of ring pointers, allocated at run-time */
 	struct i40e_ring **rx_rings;
 	struct i40e_ring **tx_rings;
+	struct i40e_ring **xdp_rings; /* XDP Tx rings */
 
 	u32  active_filters;
 	u32  promisc_threshold;
@@ -645,6 +651,8 @@ struct i40e_vsi {
 	u16 max_frame;
 	u16 rx_buf_len;
 
+	struct bpf_prog *xdp_prog;
+
 	/* List of q_vectors allocated to this VSI */
 	struct i40e_q_vector **q_vectors;
 	int num_q_vectors;
@@ -732,22 +740,36 @@ static inline char *i40e_nvm_version_str(struct i40e_hw *hw)
 {
 	static char buf[32];
 	u32 full_ver;
-	u8 ver, patch;
-	u16 build;
 
 	full_ver = hw->nvm.oem_ver;
-	ver = (u8)(full_ver >> I40E_OEM_VER_SHIFT);
-	build = (u16)((full_ver >> I40E_OEM_VER_BUILD_SHIFT) &
-		 I40E_OEM_VER_BUILD_MASK);
-	patch = (u8)(full_ver & I40E_OEM_VER_PATCH_MASK);
-
-	snprintf(buf, sizeof(buf),
-		 "%x.%02x 0x%x %d.%d.%d",
-		 (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >>
-			I40E_NVM_VERSION_HI_SHIFT,
-		 (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >>
-			I40E_NVM_VERSION_LO_SHIFT,
-		 hw->nvm.eetrack, ver, build, patch);
+
+	if (hw->nvm.eetrack == I40E_OEM_EETRACK_ID) {
+		u8 gen, snap;
+		u16 release;
+
+		gen = (u8)(full_ver >> I40E_OEM_GEN_SHIFT);
+		snap = (u8)((full_ver & I40E_OEM_SNAP_MASK) >>
+			I40E_OEM_SNAP_SHIFT);
+		release = (u16)(full_ver & I40E_OEM_RELEASE_MASK);
+
+		snprintf(buf, sizeof(buf), "%x.%x.%x", gen, snap, release);
+	} else {
+		u8 ver, patch;
+		u16 build;
+
+		ver = (u8)(full_ver >> I40E_OEM_VER_SHIFT);
+		build = (u16)((full_ver >> I40E_OEM_VER_BUILD_SHIFT) &
+			 I40E_OEM_VER_BUILD_MASK);
+		patch = (u8)(full_ver & I40E_OEM_VER_PATCH_MASK);
+
+		snprintf(buf, sizeof(buf),
+			 "%x.%02x 0x%x %d.%d.%d",
+			 (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >>
+				I40E_NVM_VERSION_HI_SHIFT,
+			 (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >>
+				I40E_NVM_VERSION_LO_SHIFT,
+			 hw->nvm.eetrack, ver, build, patch);
+	}
 
 	return buf;
 }
@@ -968,8 +990,13 @@ int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
 void i40e_ptp_init(struct i40e_pf *pf);
 void i40e_ptp_stop(struct i40e_pf *pf);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
-i40e_status i40e_get_npar_bw_setting(struct i40e_pf *pf);
-i40e_status i40e_set_npar_bw_setting(struct i40e_pf *pf);
-i40e_status i40e_commit_npar_bw_setting(struct i40e_pf *pf);
+i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf);
+i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
+i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
+
+static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
+{
+	return !!vsi->xdp_prog;
+}
 #endif /* _I40E_H_ */

drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -531,7 +531,7 @@ struct i40e_aqc_mac_address_read {
 #define I40E_AQC_PORT_ADDR_VALID	0x40
 #define I40E_AQC_WOL_ADDR_VALID		0x80
 #define I40E_AQC_MC_MAG_EN_VALID	0x100
-#define I40E_AQC_ADDR_VALID_MASK	0x1F0
+#define I40E_AQC_ADDR_VALID_MASK	0x3F0
 	u8	reserved[6];
 	__le32	addr_high;
 	__le32	addr_low;

drivers/net/ethernet/intel/i40e/i40e_client.c

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -273,8 +273,8 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id)
 	if (!cdev || !cdev->client)
 		goto out;
 	if (!cdev->client->ops || !cdev->client->ops->vf_capable) {
-		dev_info(&pf->pdev->dev,
-			 "Cannot locate client instance VF capability routine\n");
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance VF capability routine\n");
 		goto out;
 	}
 	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state))

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -3614,11 +3614,15 @@ i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 /**
  * i40e_aq_add_udp_tunnel
  * @hw: pointer to the hw struct
- * @udp_port: the UDP port to add
+ * @udp_port: the UDP port to add in Host byte order
  * @header_len: length of the tunneling header length in DWords
  * @protocol_index: protocol index type
  * @filter_index: pointer to filter index
  * @cmd_details: pointer to command details structure or NULL
+ *
+ * Note: Firmware expects the udp_port value to be in Little Endian format,
+ * and this function will call cpu_to_le16 to convert from Host byte order to
+ * Little Endian order.
  **/
 i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
 				u16 udp_port, u8 protocol_index,

drivers/net/ethernet/intel/i40e/i40e_dcb.c

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -390,6 +390,8 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv,
 
 	if (!dcbcfg->numapps)
 		return;
+	if (dcbcfg->numapps > I40E_DCBX_MAX_APPS)
+		dcbcfg->numapps = I40E_DCBX_MAX_APPS;
 
 	for (i = 0; i < dcbcfg->numapps; i++) {
 		u8 up, selector;
@@ -618,14 +620,17 @@ static void i40e_cee_to_dcb_v1_config(
 	/* CEE PG data to ETS config */
 	dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
 
+	/* Note that the FW creates the oper_prio_tc nibbles reversed
+	 * from those in the CEE Priority Group sub-TLV.
+	 */
 	for (i = 0; i < 4; i++) {
-		tc = (u8)((cee_cfg->oper_prio_tc[i] &
-			 I40E_CEE_PGID_PRIO_1_MASK) >>
-			 I40E_CEE_PGID_PRIO_1_SHIFT);
-		dcbcfg->etscfg.prioritytable[i*2] =  tc;
 		tc = (u8)((cee_cfg->oper_prio_tc[i] &
 			 I40E_CEE_PGID_PRIO_0_MASK) >>
 			 I40E_CEE_PGID_PRIO_0_SHIFT);
+		dcbcfg->etscfg.prioritytable[i * 2] =  tc;
+		tc = (u8)((cee_cfg->oper_prio_tc[i] &
+			 I40E_CEE_PGID_PRIO_1_MASK) >>
+			 I40E_CEE_PGID_PRIO_1_SHIFT);
 		dcbcfg->etscfg.prioritytable[i*2 + 1] = tc;
 	}
 

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1299,6 +1299,17 @@ static void i40e_get_ringparam(struct net_device *netdev,
 	ring->rx_jumbo_pending = 0;
 }
 
+static bool i40e_active_tx_ring_index(struct i40e_vsi *vsi, u16 index)
+{
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		return index < vsi->num_queue_pairs ||
+			(index >= vsi->alloc_queue_pairs &&
+			 index < vsi->alloc_queue_pairs + vsi->num_queue_pairs);
+	}
+
+	return index < vsi->num_queue_pairs;
+}
+
 static int i40e_set_ringparam(struct net_device *netdev,
 			      struct ethtool_ringparam *ring)
 {
@@ -1308,6 +1319,7 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	u32 new_rx_count, new_tx_count;
+	u16 tx_alloc_queue_pairs;
 	int timeout = 50;
 	int i, err = 0;
 
@@ -1345,6 +1357,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			vsi->tx_rings[i]->count = new_tx_count;
 			vsi->rx_rings[i]->count = new_rx_count;
+			if (i40e_enabled_xdp_vsi(vsi))
+				vsi->xdp_rings[i]->count = new_tx_count;
 		}
 		goto done;
 	}
@@ -1354,20 +1368,24 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	 * to the Tx and Rx ring structs.
 	 */
 
-	/* alloc updated Tx resources */
+	/* alloc updated Tx and XDP Tx resources */
+	tx_alloc_queue_pairs = vsi->alloc_queue_pairs *
+			       (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
 	if (new_tx_count != vsi->tx_rings[0]->count) {
 		netdev_info(netdev,
 			    "Changing Tx descriptor count from %d to %d.\n",
 			    vsi->tx_rings[0]->count, new_tx_count);
-		tx_rings = kcalloc(vsi->alloc_queue_pairs,
+		tx_rings = kcalloc(tx_alloc_queue_pairs,
 				   sizeof(struct i40e_ring), GFP_KERNEL);
 		if (!tx_rings) {
 			err = -ENOMEM;
 			goto done;
 		}
 
-		for (i = 0; i < vsi->num_queue_pairs; i++) {
-			/* clone ring and setup updated count */
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (!i40e_active_tx_ring_index(vsi, i))
+				continue;
+
 			tx_rings[i] = *vsi->tx_rings[i];
 			tx_rings[i].count = new_tx_count;
 			/* the desc and bi pointers will be reallocated in the
@@ -1379,6 +1397,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			if (err) {
 				while (i) {
 					i--;
+					if (!i40e_active_tx_ring_index(vsi, i))
+						continue;
 					i40e_free_tx_resources(&tx_rings[i]);
 				}
 				kfree(tx_rings);
@@ -1446,9 +1466,11 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	i40e_down(vsi);
 
 	if (tx_rings) {
-		for (i = 0; i < vsi->num_queue_pairs; i++) {
-			i40e_free_tx_resources(vsi->tx_rings[i]);
-			*vsi->tx_rings[i] = tx_rings[i];
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (i40e_active_tx_ring_index(vsi, i)) {
+				i40e_free_tx_resources(vsi->tx_rings[i]);
+				*vsi->tx_rings[i] = tx_rings[i];
+			}
 		}
 		kfree(tx_rings);
 		tx_rings = NULL;
@@ -1479,8 +1501,10 @@ static int i40e_set_ringparam(struct net_device *netdev,
 free_tx:
 	/* error cleanup if the Rx allocations failed after getting Tx */
 	if (tx_rings) {
-		for (i = 0; i < vsi->num_queue_pairs; i++)
-			i40e_free_tx_resources(&tx_rings[i]);
+		for (i = 0; i < tx_alloc_queue_pairs; i++) {
+			if (i40e_active_tx_ring_index(vsi, i))
+				i40e_free_tx_resources(vsi->tx_rings[i]);
+		}
 		kfree(tx_rings);
 		tx_rings = NULL;
 	}
@@ -2687,6 +2711,12 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	u8 flow_pctype = 0;
 	u64 i_set, i_setc;
 
+	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+		dev_err(&pf->pdev->dev,
+			"Change of RSS hash input set is not supported when MFP mode is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
 	/* RSS does not support anything other than hashing
 	 * to queues on src and dst IPs and ports
 	 */

drivers/net/ethernet/intel/i40e/i40e_main.c

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -27,6 +27,7 @@
 #include <linux/etherdevice.h>
 #include <linux/of_net.h>
 #include <linux/pci.h>
+#include <linux/bpf.h>
 
 /* Local includes */
 #include "i40e.h"
@@ -406,6 +407,27 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
 	return &vsi->net_stats;
 }
 
+/**
+ * i40e_get_netdev_stats_struct_tx - populate stats from a Tx ring
+ * @ring: Tx ring to get statistics from
+ * @stats: statistics entry to be updated
+ **/
+static void i40e_get_netdev_stats_struct_tx(struct i40e_ring *ring,
+					    struct rtnl_link_stats64 *stats)
+{
+	u64 bytes, packets;
+	unsigned int start;
+
+	do {
+		start = u64_stats_fetch_begin_irq(&ring->syncp);
+		packets = ring->stats.packets;
+		bytes   = ring->stats.bytes;
+	} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
+
+	stats->tx_packets += packets;
+	stats->tx_bytes   += bytes;
+}
+
 /**
  * i40e_get_netdev_stats_struct - Get statistics for netdev interface
  * @netdev: network interface device structure
@@ -436,15 +458,8 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 		tx_ring = ACCESS_ONCE(vsi->tx_rings[i]);
 		if (!tx_ring)
 			continue;
+		i40e_get_netdev_stats_struct_tx(tx_ring, stats);
 
-		do {
-			start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
-			packets = tx_ring->stats.packets;
-			bytes   = tx_ring->stats.bytes;
-		} while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
-
-		stats->tx_packets += packets;
-		stats->tx_bytes   += bytes;
 		rx_ring = &tx_ring[1];
 
 		do {
@@ -455,6 +470,9 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 
 		stats->rx_packets += packets;
 		stats->rx_bytes   += bytes;
+
+		if (i40e_enabled_xdp_vsi(vsi))
+			i40e_get_netdev_stats_struct_tx(&rx_ring[1], stats);
 	}
 	rcu_read_unlock();
 
@@ -2263,9 +2281,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				 i40e_aq_str(hw, hw->aq.asq_last_status));
 		}
 	}
-	if ((changed_flags & IFF_PROMISC) ||
-	    (promisc_changed &&
-	     test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))) {
+
+	if ((changed_flags & IFF_PROMISC) || promisc_changed) {
 		bool cur_promisc;
 
 		cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
@@ -2395,6 +2412,18 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 	}
 }
 
+/**
+ * i40e_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @vsi: the vsi
+ **/
+static int i40e_max_xdp_frame_size(struct i40e_vsi *vsi)
+{
+	if (PAGE_SIZE >= 8192 || (vsi->back->flags & I40E_FLAG_LEGACY_RX))
+		return I40E_RXBUFFER_2048;
+	else
+		return I40E_RXBUFFER_3072;
+}
+
 /**
  * i40e_change_mtu - NDO callback to change the Maximum Transfer Unit
  * @netdev: network interface device structure
@@ -2408,6 +2437,13 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+
+		if (frame_size > i40e_max_xdp_frame_size(vsi))
+			return -EINVAL;
+	}
+
 	netdev_info(netdev, "changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
@@ -2794,6 +2830,12 @@ static int i40e_vsi_setup_tx_resources(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_setup_tx_descriptors(vsi->tx_rings[i]);
 
+	if (!i40e_enabled_xdp_vsi(vsi))
+		return err;
+
+	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
+		err = i40e_setup_tx_descriptors(vsi->xdp_rings[i]);
+
 	return err;
 }
 
@@ -2807,12 +2849,17 @@ static void i40e_vsi_free_tx_resources(struct i40e_vsi *vsi)
 {
 	int i;
 
-	if (!vsi->tx_rings)
-		return;
+	if (vsi->tx_rings) {
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+				i40e_free_tx_resources(vsi->tx_rings[i]);
+	}
 
-	for (i = 0; i < vsi->num_queue_pairs; i++)
-		if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
-			i40e_free_tx_resources(vsi->tx_rings[i]);
+	if (vsi->xdp_rings) {
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			if (vsi->xdp_rings[i] && vsi->xdp_rings[i]->desc)
+				i40e_free_tx_resources(vsi->xdp_rings[i]);
+	}
 }
 
 /**
@@ -3073,6 +3120,12 @@ static int i40e_vsi_configure_tx(struct i40e_vsi *vsi)
 	for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
 		err = i40e_configure_tx_ring(vsi->tx_rings[i]);
 
+	if (!i40e_enabled_xdp_vsi(vsi))
+		return err;
+
+	for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
+		err = i40e_configure_tx_ring(vsi->xdp_rings[i]);
+
 	return err;
 }
 
@@ -3217,6 +3270,7 @@ static int i40e_vsi_configure(struct i40e_vsi *vsi)
  **/
 static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 {
+	bool has_xdp = i40e_enabled_xdp_vsi(vsi);
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	u16 vector;
@@ -3247,28 +3301,40 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 		/* Linked list for the queuepairs assigned to this vector */
 		wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp);
 		for (q = 0; q < q_vector->num_ringpairs; q++) {
+			u32 nextqp = has_xdp ? qp + vsi->alloc_queue_pairs : qp;
 			u32 val;
 
 			val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
-			      (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT)  |
-			      (vector      << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) |
-			      (qp          << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)|
-			      (I40E_QUEUE_TYPE_TX
-				      << I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT);
+			      (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
+			      (vector << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) |
+			      (nextqp << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT) |
+			      (I40E_QUEUE_TYPE_TX <<
+			       I40E_QINT_RQCTL_NEXTQ_TYPE_SHIFT);
 
 			wr32(hw, I40E_QINT_RQCTL(qp), val);
 
+			if (has_xdp) {
+				val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
+				      (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) |
+				      (vector << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) |
+				      (qp << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT) |
+				      (I40E_QUEUE_TYPE_TX <<
+				       I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
+
+				wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+			}
+
 			val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
-			      (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT)  |
-			      (vector      << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) |
-			      ((qp+1)      << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT)|
-			      (I40E_QUEUE_TYPE_RX
-				      << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
+			      (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) |
+			      (vector << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) |
+			      ((qp + 1) << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT) |
+			      (I40E_QUEUE_TYPE_RX <<
+			       I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
 
 			/* Terminate the linked list */
 			if (q == (q_vector->num_ringpairs - 1))
-				val |= (I40E_QUEUE_END_OF_LIST
-					   << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT);
+				val |= (I40E_QUEUE_END_OF_LIST <<
+					I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT);
 
 			wr32(hw, I40E_QINT_TQCTL(qp), val);
 			qp++;
@@ -3322,6 +3388,7 @@ static void i40e_enable_misc_int_causes(struct i40e_pf *pf)
  **/
 static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 {
+	u32 nextqp = i40e_enabled_xdp_vsi(vsi) ? vsi->alloc_queue_pairs : 0;
 	struct i40e_q_vector *q_vector = vsi->q_vectors[0];
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
@@ -3342,12 +3409,22 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 	wr32(hw, I40E_PFINT_LNKLST0, 0);
 
 	/* Associate the queue pair to the vector and enable the queue int */
-	val = I40E_QINT_RQCTL_CAUSE_ENA_MASK		      |
-	      (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
+	val = I40E_QINT_RQCTL_CAUSE_ENA_MASK		       |
+	      (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT)  |
+	      (nextqp	   << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)|
 	      (I40E_QUEUE_TYPE_TX << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
 
 	wr32(hw, I40E_QINT_RQCTL(0), val);
 
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		val = I40E_QINT_TQCTL_CAUSE_ENA_MASK		     |
+		      (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT)|
+		      (I40E_QUEUE_TYPE_TX
+		       << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
+
+	       wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+	}
+
 	val = I40E_QINT_TQCTL_CAUSE_ENA_MASK		      |
 	      (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) |
 	      (I40E_QUEUE_END_OF_LIST << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT);
@@ -3511,11 +3588,24 @@ static void i40e_vsi_disable_irq(struct i40e_vsi *vsi)
 	int base = vsi->base_vector;
 	int i;
 
+	/* disable interrupt causation from each queue */
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		wr32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i]->reg_idx), 0);
-		wr32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i]->reg_idx), 0);
+		u32 val;
+
+		val = rd32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i]->reg_idx));
+		val &= ~I40E_QINT_TQCTL_CAUSE_ENA_MASK;
+		wr32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val);
+
+		val = rd32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i]->reg_idx));
+		val &= ~I40E_QINT_RQCTL_CAUSE_ENA_MASK;
+		wr32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i]->reg_idx), val);
+
+		if (!i40e_enabled_xdp_vsi(vsi))
+			continue;
+		wr32(hw, I40E_QINT_TQCTL(vsi->xdp_rings[i]->reg_idx), 0);
 	}
 
+	/* disable each interrupt */
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
 		for (i = vsi->base_vector;
 		     i < (vsi->num_q_vectors + vsi->base_vector); i++)
@@ -3594,10 +3684,10 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		pf->sw_int_count++;
 
 	if ((pf->flags & I40E_FLAG_IWARP_ENABLED) &&
-	    (ena_mask & I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK)) {
+	    (icr0 & I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK)) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK;
-		icr0 &= ~I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK;
 		dev_dbg(&pf->pdev->dev, "cleared PE_CRITERR\n");
+		set_bit(__I40E_CORE_RESET_REQUESTED, pf->state);
 	}
 
 	/* only q0 is used in MSI/Legacy mode, and none are used in MSIX */
@@ -3816,6 +3906,16 @@ static void i40e_map_vector_to_qp(struct i40e_vsi *vsi, int v_idx, int qp_idx)
 	q_vector->tx.ring = tx_ring;
 	q_vector->tx.count++;
 
+	/* Place XDP Tx ring in the same q_vector ring list as regular Tx */
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		struct i40e_ring *xdp_ring = vsi->xdp_rings[qp_idx];
+
+		xdp_ring->q_vector = q_vector;
+		xdp_ring->next = q_vector->tx.ring;
+		q_vector->tx.ring = xdp_ring;
+		q_vector->tx.count++;
+	}
+
 	rx_ring->q_vector = q_vector;
 	rx_ring->next = q_vector->rx.ring;
 	q_vector->rx.ring = rx_ring;
@@ -3994,6 +4094,33 @@ static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable)
 	wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
 }
 
+/**
+ * i40e_control_wait_tx_q - Start/stop Tx queue and wait for completion
+ * @seid: VSI SEID
+ * @pf: the PF structure
+ * @pf_q: the PF queue to configure
+ * @is_xdp: true if the queue is used for XDP
+ * @enable: start or stop the queue
+ **/
+static int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q,
+				  bool is_xdp, bool enable)
+{
+	int ret;
+
+	i40e_control_tx_q(pf, pf_q, enable);
+
+	/* wait for the change to finish */
+	ret = i40e_pf_txq_wait(pf, pf_q, enable);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "VSI seid %d %sTx ring %d %sable timeout\n",
+			 seid, (is_xdp ? "XDP " : ""), pf_q,
+			 (enable ? "en" : "dis"));
+	}
+
+	return ret;
+}
+
 /**
  * i40e_vsi_control_tx - Start or stop a VSI's rings
  * @vsi: the VSI being configured
@@ -4006,16 +4133,20 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		i40e_control_tx_q(pf, pf_q, enable);
+		ret = i40e_control_wait_tx_q(vsi->seid, pf,
+					     pf_q,
+					     false /*is xdp*/, enable);
+		if (ret)
+			break;
 
-		/* wait for the change to finish */
-		ret = i40e_pf_txq_wait(pf, pf_q, enable);
-		if (ret) {
-			dev_info(&pf->pdev->dev,
-				 "VSI seid %d Tx ring %d %sable timeout\n",
-				 vsi->seid, pf_q, (enable ? "en" : "dis"));
+		if (!i40e_enabled_xdp_vsi(vsi))
+			continue;
+
+		ret = i40e_control_wait_tx_q(vsi->seid, pf,
+					     pf_q + vsi->alloc_queue_pairs,
+					     true /*is xdp*/, enable);
+		if (ret)
 			break;
-		}
 	}
 
 	return ret;
@@ -4527,7 +4658,21 @@ int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 				 vsi->seid, pf_q);
 			return ret;
 		}
-		/* Check and wait for the Tx queue */
+
+		if (!i40e_enabled_xdp_vsi(vsi))
+			goto wait_rx;
+
+		/* Check and wait for the XDP Tx queue */
+		ret = i40e_pf_txq_wait(pf, pf_q + vsi->alloc_queue_pairs,
+				       false);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "VSI seid %d XDP Tx ring %d disable timeout\n",
+				 vsi->seid, pf_q);
+			return ret;
+		}
+wait_rx:
+		/* Check and wait for the Rx queue */
 		ret = i40e_pf_rxq_wait(pf, pf_q, false);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
@@ -5446,6 +5591,8 @@ void i40e_down(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
+		if (i40e_enabled_xdp_vsi(vsi))
+			i40e_clean_tx_ring(vsi->xdp_rings[i]);
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
@@ -6419,9 +6566,7 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
 	if (reset_flags &&
 	    !test_bit(__I40E_DOWN, pf->state) &&
 	    !test_bit(__I40E_CONFIG_BUSY, pf->state)) {
-		rtnl_lock();
-		i40e_do_reset(pf, reset_flags, true);
-		rtnl_unlock();
+		i40e_do_reset(pf, reset_flags, false);
 	}
 }
 
@@ -6969,6 +7114,51 @@ static void i40e_send_version(struct i40e_pf *pf)
 	i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
 }
 
+/**
+ * i40e_get_oem_version - get OEM specific version information
+ * @hw: pointer to the hardware structure
+ **/
+static void i40e_get_oem_version(struct i40e_hw *hw)
+{
+	u16 block_offset = 0xffff;
+	u16 block_length = 0;
+	u16 capabilities = 0;
+	u16 gen_snap = 0;
+	u16 release = 0;
+
+#define I40E_SR_NVM_OEM_VERSION_PTR		0x1B
+#define I40E_NVM_OEM_LENGTH_OFFSET		0x00
+#define I40E_NVM_OEM_CAPABILITIES_OFFSET	0x01
+#define I40E_NVM_OEM_GEN_OFFSET			0x02
+#define I40E_NVM_OEM_RELEASE_OFFSET		0x03
+#define I40E_NVM_OEM_CAPABILITIES_MASK		0x000F
+#define I40E_NVM_OEM_LENGTH			3
+
+	/* Check if pointer to OEM version block is valid. */
+	i40e_read_nvm_word(hw, I40E_SR_NVM_OEM_VERSION_PTR, &block_offset);
+	if (block_offset == 0xffff)
+		return;
+
+	/* Check if OEM version block has correct length. */
+	i40e_read_nvm_word(hw, block_offset + I40E_NVM_OEM_LENGTH_OFFSET,
+			   &block_length);
+	if (block_length < I40E_NVM_OEM_LENGTH)
+		return;
+
+	/* Check if OEM version format is as expected. */
+	i40e_read_nvm_word(hw, block_offset + I40E_NVM_OEM_CAPABILITIES_OFFSET,
+			   &capabilities);
+	if ((capabilities & I40E_NVM_OEM_CAPABILITIES_MASK) != 0)
+		return;
+
+	i40e_read_nvm_word(hw, block_offset + I40E_NVM_OEM_GEN_OFFSET,
+			   &gen_snap);
+	i40e_read_nvm_word(hw, block_offset + I40E_NVM_OEM_RELEASE_OFFSET,
+			   &release);
+	hw->nvm.oem_ver = (gen_snap << I40E_OEM_SNAP_SHIFT) | release;
+	hw->nvm.eetrack = I40E_OEM_EETRACK_ID;
+}
+
 /**
  * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen
  * @pf: board private structure
@@ -7016,6 +7206,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 		goto clear_recovery;
 	}
+	i40e_get_oem_version(&pf->hw);
 
 	/* re-verify the eeprom if we just had an EMP reset */
 	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
@@ -7515,15 +7706,22 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
  **/
 static int i40e_vsi_alloc_arrays(struct i40e_vsi *vsi, bool alloc_qvectors)
 {
+	struct i40e_ring **next_rings;
 	int size;
 	int ret = 0;
 
-	/* allocate memory for both Tx and Rx ring pointers */
-	size = sizeof(struct i40e_ring *) * vsi->alloc_queue_pairs * 2;
+	/* allocate memory for both Tx, XDP Tx and Rx ring pointers */
+	size = sizeof(struct i40e_ring *) * vsi->alloc_queue_pairs *
+	       (i40e_enabled_xdp_vsi(vsi) ? 3 : 2);
 	vsi->tx_rings = kzalloc(size, GFP_KERNEL);
 	if (!vsi->tx_rings)
 		return -ENOMEM;
-	vsi->rx_rings = &vsi->tx_rings[vsi->alloc_queue_pairs];
+	next_rings = vsi->tx_rings + vsi->alloc_queue_pairs;
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		vsi->xdp_rings = next_rings;
+		next_rings += vsi->alloc_queue_pairs;
+	}
+	vsi->rx_rings = next_rings;
 
 	if (alloc_qvectors) {
 		/* allocate memory for q_vector pointers */
@@ -7643,6 +7841,7 @@ static void i40e_vsi_free_arrays(struct i40e_vsi *vsi, bool free_qvectors)
 	kfree(vsi->tx_rings);
 	vsi->tx_rings = NULL;
 	vsi->rx_rings = NULL;
+	vsi->xdp_rings = NULL;
 }
 
 /**
@@ -7726,6 +7925,8 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
 			kfree_rcu(vsi->tx_rings[i], rcu);
 			vsi->tx_rings[i] = NULL;
 			vsi->rx_rings[i] = NULL;
+			if (vsi->xdp_rings)
+				vsi->xdp_rings[i] = NULL;
 		}
 	}
 }
@@ -7736,43 +7937,61 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
  **/
 static int i40e_alloc_rings(struct i40e_vsi *vsi)
 {
-	struct i40e_ring *tx_ring, *rx_ring;
+	int i, qpv = i40e_enabled_xdp_vsi(vsi) ? 3 : 2;
 	struct i40e_pf *pf = vsi->back;
-	int i;
+	struct i40e_ring *ring;
 
 	/* Set basic values in the rings to be used later during open() */
 	for (i = 0; i < vsi->alloc_queue_pairs; i++) {
 		/* allocate space for both Tx and Rx in one shot */
-		tx_ring = kzalloc(sizeof(struct i40e_ring) * 2, GFP_KERNEL);
-		if (!tx_ring)
+		ring = kcalloc(qpv, sizeof(struct i40e_ring), GFP_KERNEL);
+		if (!ring)
 			goto err_out;
 
-		tx_ring->queue_index = i;
-		tx_ring->reg_idx = vsi->base_queue + i;
-		tx_ring->ring_active = false;
-		tx_ring->vsi = vsi;
-		tx_ring->netdev = vsi->netdev;
-		tx_ring->dev = &pf->pdev->dev;
-		tx_ring->count = vsi->num_desc;
-		tx_ring->size = 0;
-		tx_ring->dcb_tc = 0;
+		ring->queue_index = i;
+		ring->reg_idx = vsi->base_queue + i;
+		ring->ring_active = false;
+		ring->vsi = vsi;
+		ring->netdev = vsi->netdev;
+		ring->dev = &pf->pdev->dev;
+		ring->count = vsi->num_desc;
+		ring->size = 0;
+		ring->dcb_tc = 0;
 		if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
-			tx_ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
-		tx_ring->tx_itr_setting = pf->tx_itr_default;
-		vsi->tx_rings[i] = tx_ring;
-
-		rx_ring = &tx_ring[1];
-		rx_ring->queue_index = i;
-		rx_ring->reg_idx = vsi->base_queue + i;
-		rx_ring->ring_active = false;
-		rx_ring->vsi = vsi;
-		rx_ring->netdev = vsi->netdev;
-		rx_ring->dev = &pf->pdev->dev;
-		rx_ring->count = vsi->num_desc;
-		rx_ring->size = 0;
-		rx_ring->dcb_tc = 0;
-		rx_ring->rx_itr_setting = pf->rx_itr_default;
-		vsi->rx_rings[i] = rx_ring;
+			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
+		ring->tx_itr_setting = pf->tx_itr_default;
+		vsi->tx_rings[i] = ring++;
+
+		if (!i40e_enabled_xdp_vsi(vsi))
+			goto setup_rx;
+
+		ring->queue_index = vsi->alloc_queue_pairs + i;
+		ring->reg_idx = vsi->base_queue + ring->queue_index;
+		ring->ring_active = false;
+		ring->vsi = vsi;
+		ring->netdev = NULL;
+		ring->dev = &pf->pdev->dev;
+		ring->count = vsi->num_desc;
+		ring->size = 0;
+		ring->dcb_tc = 0;
+		if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
+			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
+		set_ring_xdp(ring);
+		ring->tx_itr_setting = pf->tx_itr_default;
+		vsi->xdp_rings[i] = ring++;
+
+setup_rx:
+		ring->queue_index = i;
+		ring->reg_idx = vsi->base_queue + i;
+		ring->ring_active = false;
+		ring->vsi = vsi;
+		ring->netdev = vsi->netdev;
+		ring->dev = &pf->pdev->dev;
+		ring->count = vsi->num_desc;
+		ring->size = 0;
+		ring->dcb_tc = 0;
+		ring->rx_itr_setting = pf->rx_itr_default;
+		vsi->rx_rings[i] = ring;
 	}
 
 	return 0;
@@ -8574,10 +8793,10 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 }
 
 /**
- * i40e_get_npar_bw_setting - Retrieve BW settings for this PF partition
+ * i40e_get_partition_bw_setting - Retrieve BW settings for this PF partition
  * @pf: board private structure
  **/
-i40e_status i40e_get_npar_bw_setting(struct i40e_pf *pf)
+i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf)
 {
 	i40e_status status;
 	bool min_valid, max_valid;
@@ -8588,27 +8807,27 @@ i40e_status i40e_get_npar_bw_setting(struct i40e_pf *pf)
 
 	if (!status) {
 		if (min_valid)
-			pf->npar_min_bw = min_bw;
+			pf->min_bw = min_bw;
 		if (max_valid)
-			pf->npar_max_bw = max_bw;
+			pf->max_bw = max_bw;
 	}
 
 	return status;
 }
 
 /**
- * i40e_set_npar_bw_setting - Set BW settings for this PF partition
+ * i40e_set_partition_bw_setting - Set BW settings for this PF partition
  * @pf: board private structure
  **/
-i40e_status i40e_set_npar_bw_setting(struct i40e_pf *pf)
+i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf)
 {
 	struct i40e_aqc_configure_partition_bw_data bw_data;
 	i40e_status status;
 
 	/* Set the valid bit for this PF */
 	bw_data.pf_valid_bits = cpu_to_le16(BIT(pf->hw.pf_id));
-	bw_data.max_bw[pf->hw.pf_id] = pf->npar_max_bw & I40E_ALT_BW_VALUE_MASK;
-	bw_data.min_bw[pf->hw.pf_id] = pf->npar_min_bw & I40E_ALT_BW_VALUE_MASK;
+	bw_data.max_bw[pf->hw.pf_id] = pf->max_bw & I40E_ALT_BW_VALUE_MASK;
+	bw_data.min_bw[pf->hw.pf_id] = pf->min_bw & I40E_ALT_BW_VALUE_MASK;
 
 	/* Set the new bandwidths */
 	status = i40e_aq_configure_partition_bw(&pf->hw, &bw_data, NULL);
@@ -8617,10 +8836,10 @@ i40e_status i40e_set_npar_bw_setting(struct i40e_pf *pf)
 }
 
 /**
- * i40e_commit_npar_bw_setting - Commit BW settings for this PF partition
+ * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition
  * @pf: board private structure
  **/
-i40e_status i40e_commit_npar_bw_setting(struct i40e_pf *pf)
+i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf)
 {
 	/* Commit temporary BW setting to permanent NVM image */
 	enum i40e_admin_queue_err last_aq_status;
@@ -8739,16 +8958,19 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	if (pf->hw.func_caps.npar_enable || pf->hw.func_caps.flex10_enable) {
 		pf->flags |= I40E_FLAG_MFP_ENABLED;
 		dev_info(&pf->pdev->dev, "MFP mode Enabled\n");
-		if (i40e_get_npar_bw_setting(pf))
+		if (i40e_get_partition_bw_setting(pf)) {
 			dev_warn(&pf->pdev->dev,
-				 "Could not get NPAR bw settings\n");
-		else
+				 "Could not get partition bw settings\n");
+		} else {
 			dev_info(&pf->pdev->dev,
-				 "Min BW = %8.8x, Max BW = %8.8x\n",
-				 pf->npar_min_bw, pf->npar_max_bw);
+				 "Partition BW Min = %8.8x, Max = %8.8x\n",
+				 pf->min_bw, pf->max_bw);
+
+			/* nudge the Tx scheduler */
+			i40e_set_partition_bw_setting(pf);
+		}
 	}
 
-	/* FW/NVM is not yet fixed in this regard */
 	if ((pf->hw.func_caps.fd_filters_guaranteed > 0) ||
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
@@ -8851,10 +9073,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 
 	mutex_init(&pf->switch_mutex);
 
-	/* If NPAR is enabled nudge the Tx scheduler */
-	if (pf->hw.func_caps.npar_enable && (!i40e_get_npar_bw_setting(pf)))
-		i40e_set_npar_bw_setting(pf);
-
 sw_init_done:
 	return err;
 }
@@ -9311,6 +9529,72 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb,
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
+/**
+ * i40e_xdp_setup - add/remove an XDP program
+ * @vsi: VSI to changed
+ * @prog: XDP program
+ **/
+static int i40e_xdp_setup(struct i40e_vsi *vsi,
+			  struct bpf_prog *prog)
+{
+	int frame_size = vsi->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	struct i40e_pf *pf = vsi->back;
+	struct bpf_prog *old_prog;
+	bool need_reset;
+	int i;
+
+	/* Don't allow frames that span over multiple buffers */
+	if (frame_size > vsi->rx_buf_len)
+		return -EINVAL;
+
+	if (!i40e_enabled_xdp_vsi(vsi) && !prog)
+		return 0;
+
+	/* When turning XDP on->off/off->on we reset and rebuild the rings. */
+	need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog);
+
+	if (need_reset)
+		i40e_prep_for_reset(pf, true);
+
+	old_prog = xchg(&vsi->xdp_prog, prog);
+
+	if (need_reset)
+		i40e_reset_and_rebuild(pf, true, true);
+
+	for (i = 0; i < vsi->num_queue_pairs; i++)
+		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	return 0;
+}
+
+/**
+ * i40e_xdp - implements ndo_xdp for i40e
+ * @dev: netdevice
+ * @xdp: XDP command
+ **/
+static int i40e_xdp(struct net_device *dev,
+		    struct netdev_xdp *xdp)
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	struct i40e_vsi *vsi = np->vsi;
+
+	if (vsi->type != I40E_VSI_MAIN)
+		return -EINVAL;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return i40e_xdp_setup(vsi, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_open		= i40e_open,
 	.ndo_stop		= i40e_close,
@@ -9343,6 +9627,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_features_check	= i40e_features_check,
 	.ndo_bridge_getlink	= i40e_ndo_bridge_getlink,
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
+	.ndo_xdp		= i40e_xdp,
 };
 
 /**
@@ -9911,6 +10196,7 @@ static int i40e_vsi_setup_vectors(struct i40e_vsi *vsi)
  **/
 static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 {
+	u16 alloc_queue_pairs;
 	struct i40e_pf *pf;
 	u8 enabled_tc;
 	int ret;
@@ -9929,11 +10215,14 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 	if (ret)
 		goto err_vsi;
 
-	ret = i40e_get_lump(pf, pf->qp_pile, vsi->alloc_queue_pairs, vsi->idx);
+	alloc_queue_pairs = vsi->alloc_queue_pairs *
+			    (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
+
+	ret = i40e_get_lump(pf, pf->qp_pile, alloc_queue_pairs, vsi->idx);
 	if (ret < 0) {
 		dev_info(&pf->pdev->dev,
 			 "failed to get tracking for %d queues for VSI %d err %d\n",
-			 vsi->alloc_queue_pairs, vsi->seid, ret);
+			 alloc_queue_pairs, vsi->seid, ret);
 		goto err_vsi;
 	}
 	vsi->base_queue = ret;
@@ -9989,6 +10278,7 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 {
 	struct i40e_vsi *vsi = NULL;
 	struct i40e_veb *veb = NULL;
+	u16 alloc_queue_pairs;
 	int ret, i;
 	int v_idx;
 
@@ -10076,12 +10366,14 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 	else if (type == I40E_VSI_SRIOV)
 		vsi->vf_id = param1;
 	/* assign it some queues */
-	ret = i40e_get_lump(pf, pf->qp_pile, vsi->alloc_queue_pairs,
-				vsi->idx);
+	alloc_queue_pairs = vsi->alloc_queue_pairs *
+			    (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
+
+	ret = i40e_get_lump(pf, pf->qp_pile, alloc_queue_pairs, vsi->idx);
 	if (ret < 0) {
 		dev_info(&pf->pdev->dev,
 			 "failed to get tracking for %d queues for VSI %d err=%d\n",
-			 vsi->alloc_queue_pairs, vsi->seid, ret);
+			 alloc_queue_pairs, vsi->seid, ret);
 		goto err_vsi;
 	}
 	vsi->base_queue = ret;
@@ -11099,6 +11391,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		goto err_pf_reset;
 	}
+	i40e_get_oem_version(hw);
 
 	/* provide nvm, fw, api versions */
 	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
@@ -11611,11 +11904,8 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 	}
 
 	/* shutdown all operations */
-	if (!test_bit(__I40E_SUSPENDED, pf->state)) {
-		rtnl_lock();
-		i40e_prep_for_reset(pf, true);
-		rtnl_unlock();
-	}
+	if (!test_bit(__I40E_SUSPENDED, pf->state))
+		i40e_prep_for_reset(pf, false);
 
 	/* Request a slot reset */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -11681,9 +11971,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	if (test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
-	rtnl_lock();
-	i40e_handle_reset_warning(pf, true);
-	rtnl_unlock();
+	i40e_handle_reset_warning(pf, false);
 }
 
 /**
@@ -11763,9 +12051,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
 		i40e_enable_mc_magic_wake(pf);
 
-	rtnl_lock();
-	i40e_prep_for_reset(pf, true);
-	rtnl_unlock();
+	i40e_prep_for_reset(pf, false);
 
 	wr32(hw, I40E_PFPM_APM,
 	     (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11797,9 +12083,7 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 	if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
 		i40e_enable_mc_magic_wake(pf);
 
-	rtnl_lock();
-	i40e_prep_for_reset(pf, true);
-	rtnl_unlock();
+	i40e_prep_for_reset(pf, false);
 
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
 	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
@@ -11845,9 +12129,7 @@ static int i40e_resume(struct pci_dev *pdev)
 	/* handling the reset will rebuild the device state */
 	if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
 		clear_bit(__I40E_DOWN, pf->state);
-		rtnl_lock();
-		i40e_reset_and_rebuild(pf, false, true);
-		rtnl_unlock();
+		i40e_reset_and_rebuild(pf, false, false);
 	}
 
 	return 0;

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -26,6 +26,7 @@
 
 #include <linux/prefetch.h>
 #include <net/busy_poll.h>
+#include <linux/bpf_trace.h>
 #include "i40e.h"
 #include "i40e_trace.h"
 #include "i40e_prototype.h"
@@ -629,6 +630,8 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 	if (tx_buffer->skb) {
 		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
 			kfree(tx_buffer->raw_buf);
+		else if (ring_is_xdp(ring))
+			page_frag_free(tx_buffer->raw_buf);
 		else
 			dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
@@ -770,8 +773,11 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		total_bytes += tx_buf->bytecount;
 		total_packets += tx_buf->gso_segs;
 
-		/* free the skb */
-		napi_consume_skb(tx_buf->skb, napi_budget);
+		/* free the skb/XDP data */
+		if (ring_is_xdp(tx_ring))
+			page_frag_free(tx_buf->raw_buf);
+		else
+			napi_consume_skb(tx_buf->skb, napi_budget);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -847,6 +853,9 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 			tx_ring->arm_wb = true;
 	}
 
+	if (ring_is_xdp(tx_ring))
+		return !!budget;
+
 	/* notify netdev of completed buffers */
 	netdev_tx_completed_queue(txring_txq(tx_ring),
 				  total_packets, total_bytes);
@@ -1195,6 +1204,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 {
 	i40e_clean_rx_ring(rx_ring);
+	rx_ring->xdp_prog = NULL;
 	kfree(rx_ring->rx_bi);
 	rx_ring->rx_bi = NULL;
 
@@ -1241,6 +1251,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 
+	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
+
 	return 0;
 err:
 	kfree(rx_ring->rx_bi);
@@ -1593,6 +1605,7 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
  * i40e_cleanup_headers - Correct empty headers
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @skb: pointer to current skb being fixed
+ * @rx_desc: pointer to the EOP Rx descriptor
  *
  * Also address the case where we are pulling data in on pages only
  * and as such no data is present in the skb header.
@@ -1602,8 +1615,25 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
  *
  * Returns true if an error was encountered and skb was freed.
  **/
-static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb)
+static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb,
+				 union i40e_rx_desc *rx_desc)
+
 {
+	/* XDP packets use error pointer so abort at this point */
+	if (IS_ERR(skb))
+		return true;
+
+	/* ERR_MASK will only have valid bits if EOP set, and
+	 * what we are doing here is actually checking
+	 * I40E_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
+	 * the error field
+	 */
+	if (unlikely(i40e_test_staterr(rx_desc,
+				       BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
+		dev_kfree_skb_any(skb);
+		return true;
+	}
+
 	/* if eth_skb_pad returns an error the skb was freed */
 	if (eth_skb_pad(skb))
 		return true;
@@ -1776,7 +1806,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
  * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: rx buffer to pull data from
- * @size: size of buffer to add to skb
+ * @xdp: xdp_buff pointing to the data
  *
  * This function allocates an skb.  It then populates it with the page
  * data from the current receive descriptor, taking care to set up the
@@ -1784,9 +1814,9 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
  */
 static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 					  struct i40e_rx_buffer *rx_buffer,
-					  unsigned int size)
+					  struct xdp_buff *xdp)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+	unsigned int size = xdp->data_end - xdp->data;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
@@ -1796,9 +1826,9 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
+	prefetch(xdp->data);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
 
 	/* allocate a skb to store the frags */
@@ -1811,10 +1841,11 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > I40E_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+		headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+	memcpy(__skb_put(skb, headlen), xdp->data,
+	       ALIGN(headlen, sizeof(long)));
 
 	/* update all of the pointers */
 	size -= headlen;
@@ -1841,16 +1872,16 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
  * i40e_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_buffer: Rx buffer to pull data from
- * @size: size of buffer to add to skb
+ * @xdp: xdp_buff pointing to the data
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
 static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 				      struct i40e_rx_buffer *rx_buffer,
-				      unsigned int size)
+				      struct xdp_buff *xdp)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+	unsigned int size = xdp->data_end - xdp->data;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
@@ -1860,12 +1891,12 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
+	prefetch(xdp->data);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
 	/* build an skb around the page buffer */
-	skb = build_skb(va - I40E_SKB_PAD, truesize);
+	skb = build_skb(xdp->data_hard_start, truesize);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -1944,6 +1975,75 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 	return true;
 }
 
+#define I40E_XDP_PASS 0
+#define I40E_XDP_CONSUMED 1
+#define I40E_XDP_TX 2
+
+static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+			      struct i40e_ring *xdp_ring);
+
+/**
+ * i40e_run_xdp - run an XDP program
+ * @rx_ring: Rx ring being processed
+ * @xdp: XDP buffer containing the frame
+ **/
+static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
+				    struct xdp_buff *xdp)
+{
+	int result = I40E_XDP_PASS;
+	struct i40e_ring *xdp_ring;
+	struct bpf_prog *xdp_prog;
+	u32 act;
+
+	rcu_read_lock();
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+	if (!xdp_prog)
+		goto xdp_out;
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+		result = i40e_xmit_xdp_ring(xdp, xdp_ring);
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+		/* fallthrough -- handle aborts by dropping packet */
+	case XDP_DROP:
+		result = I40E_XDP_CONSUMED;
+		break;
+	}
+xdp_out:
+	rcu_read_unlock();
+	return ERR_PTR(-result);
+}
+
+/**
+ * i40e_rx_buffer_flip - adjusted rx_buffer to point to an unused region
+ * @rx_ring: Rx ring
+ * @rx_buffer: Rx buffer to adjust
+ * @size: Size of adjustment
+ **/
+static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring,
+				struct i40e_rx_buffer *rx_buffer,
+				unsigned int size)
+{
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+
+	rx_buffer->page_offset ^= truesize;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(i40e_rx_offset(rx_ring) + size);
+
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
 /**
  * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
@@ -1961,11 +2061,12 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	bool failure = false;
+	bool failure = false, xdp_xmit = false;
 
 	while (likely(total_rx_packets < budget)) {
 		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		struct xdp_buff xdp;
 		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
@@ -2006,12 +2107,32 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
 
 		/* retrieve a buffer from the ring */
-		if (skb)
+		if (!skb) {
+			xdp.data = page_address(rx_buffer->page) +
+				   rx_buffer->page_offset;
+			xdp.data_hard_start = xdp.data -
+					      i40e_rx_offset(rx_ring);
+			xdp.data_end = xdp.data + size;
+
+			skb = i40e_run_xdp(rx_ring, &xdp);
+		}
+
+		if (IS_ERR(skb)) {
+			if (PTR_ERR(skb) == -I40E_XDP_TX) {
+				xdp_xmit = true;
+				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
+			} else {
+				rx_buffer->pagecnt_bias++;
+			}
+			total_rx_bytes += size;
+			total_rx_packets++;
+		} else if (skb) {
 			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
-		else if (ring_uses_build_skb(rx_ring))
-			skb = i40e_build_skb(rx_ring, rx_buffer, size);
-		else
-			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+		} else if (ring_uses_build_skb(rx_ring)) {
+			skb = i40e_build_skb(rx_ring, rx_buffer, &xdp);
+		} else {
+			skb = i40e_construct_skb(rx_ring, rx_buffer, &xdp);
+		}
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -2026,18 +2147,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
 			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set, and
-		 * what we are doing here is actually checking
-		 * I40E_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
-		 * the error field
-		 */
-		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
-			dev_kfree_skb_any(skb);
-			skb = NULL;
-			continue;
-		}
-
-		if (i40e_cleanup_headers(rx_ring, skb)) {
+		if (i40e_cleanup_headers(rx_ring, skb, rx_desc)) {
 			skb = NULL;
 			continue;
 		}
@@ -2063,6 +2173,19 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
+	if (xdp_xmit) {
+		struct i40e_ring *xdp_ring;
+
+		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.
+		 */
+		wmb();
+
+		writel(xdp_ring->next_to_use, xdp_ring->tail);
+	}
+
 	rx_ring->skb = skb;
 
 	u64_stats_update_begin(&rx_ring->syncp);
@@ -3119,6 +3242,59 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	return -1;
 }
 
+/**
+ * i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring
+ * @xdp: data to transmit
+ * @xdp_ring: XDP Tx ring
+ **/
+static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+			      struct i40e_ring *xdp_ring)
+{
+	u32 size = xdp->data_end - xdp->data;
+	u16 i = xdp_ring->next_to_use;
+	struct i40e_tx_buffer *tx_bi;
+	struct i40e_tx_desc *tx_desc;
+	dma_addr_t dma;
+
+	if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
+		xdp_ring->tx_stats.tx_busy++;
+		return I40E_XDP_CONSUMED;
+	}
+
+	dma = dma_map_single(xdp_ring->dev, xdp->data, size, DMA_TO_DEVICE);
+	if (dma_mapping_error(xdp_ring->dev, dma))
+		return I40E_XDP_CONSUMED;
+
+	tx_bi = &xdp_ring->tx_bi[i];
+	tx_bi->bytecount = size;
+	tx_bi->gso_segs = 1;
+	tx_bi->raw_buf = xdp->data;
+
+	/* record length, and DMA address */
+	dma_unmap_len_set(tx_bi, len, size);
+	dma_unmap_addr_set(tx_bi, dma, dma);
+
+	tx_desc = I40E_TX_DESC(xdp_ring, i);
+	tx_desc->buffer_addr = cpu_to_le64(dma);
+	tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC
+						  | I40E_TXD_CMD,
+						  0, size, 0);
+
+	/* Make certain all of the status bits have been updated
+	 * before next_to_watch is written.
+	 */
+	smp_wmb();
+
+	i++;
+	if (i == xdp_ring->count)
+		i = 0;
+
+	tx_bi->next_to_watch = tx_desc;
+	xdp_ring->next_to_use = i;
+
+	return I40E_XDP_TX;
+}
+
 /**
  * i40e_xmit_frame_ring - Sends buffer on Tx ring
  * @skb:     send buffer

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -360,6 +360,7 @@ struct i40e_ring {
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
+	struct bpf_prog *xdp_prog;
 	union {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
@@ -395,6 +396,7 @@ struct i40e_ring {
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR		BIT(0)
 #define I40E_RXR_FLAGS_BUILD_SKB_ENABLED	BIT(1)
+#define I40E_TXR_FLAGS_XDP			BIT(2)
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
@@ -437,6 +439,16 @@ static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
 	ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
 }
 
+static inline bool ring_is_xdp(struct i40e_ring *ring)
+{
+	return !!(ring->flags & I40E_TXR_FLAGS_XDP);
+}
+
+static inline void set_ring_xdp(struct i40e_ring *ring)
+{
+	ring->flags |= I40E_TXR_FLAGS_XDP;
+}
+
 enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,

drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h

 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 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,
@@ -528,7 +528,7 @@ struct i40e_aqc_mac_address_read {
 #define I40E_AQC_PORT_ADDR_VALID	0x40
 #define I40E_AQC_WOL_ADDR_VALID		0x80
 #define I40E_AQC_MC_MAG_EN_VALID	0x100
-#define I40E_AQC_ADDR_VALID_MASK	0x1F0
+#define I40E_AQC_ADDR_VALID_MASK	0x3F0
 	u8	reserved[6];
 	__le32	addr_high;
 	__le32	addr_low;
@@ -586,6 +586,7 @@ struct i40e_aqc_set_wol_filter {
 	__le16 cmd_flags;
 #define I40E_AQC_SET_WOL_FILTER				0x8000
 #define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_WOL_PRESERVE_ON_PFR	0x2000
 #define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
 #define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
 	__le16 valid_flags;

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -1198,6 +1198,7 @@ static void i40evf_free_queues(struct i40evf_adapter *adapter)
 {
 	if (!adapter->vsi_res)
 		return;
+	adapter->num_active_queues = 0;
 	kfree(adapter->tx_rings);
 	adapter->tx_rings = NULL;
 	kfree(adapter->rx_rings);
@@ -1214,18 +1215,22 @@ static void i40evf_free_queues(struct i40evf_adapter *adapter)
  **/
 static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 {
-	int i;
+	int i, num_active_queues;
+
+	num_active_queues = min_t(int,
+				  adapter->vsi_res->num_queue_pairs,
+				  (int)(num_online_cpus()));
 
-	adapter->tx_rings = kcalloc(adapter->num_active_queues,
+	adapter->tx_rings = kcalloc(num_active_queues,
 				    sizeof(struct i40e_ring), GFP_KERNEL);
 	if (!adapter->tx_rings)
 		goto err_out;
-	adapter->rx_rings = kcalloc(adapter->num_active_queues,
+	adapter->rx_rings = kcalloc(num_active_queues,
 				    sizeof(struct i40e_ring), GFP_KERNEL);
 	if (!adapter->rx_rings)
 		goto err_out;
 
-	for (i = 0; i < adapter->num_active_queues; i++) {
+	for (i = 0; i < num_active_queues; i++) {
 		struct i40e_ring *tx_ring;
 		struct i40e_ring *rx_ring;
 
@@ -1247,6 +1252,8 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF);
 	}
 
+	adapter->num_active_queues = num_active_queues;
+
 	return 0;
 
 err_out:
@@ -2636,9 +2643,6 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->watchdog_timer.data = (unsigned long)adapter;
 	mod_timer(&adapter->watchdog_timer, jiffies + 1);
 
-	adapter->num_active_queues = min_t(int,
-					   adapter->vsi_res->num_queue_pairs,
-					   (int)(num_online_cpus()));
 	adapter->tx_desc_count = I40EVF_DEFAULT_TXD;
 	adapter->rx_desc_count = I40EVF_DEFAULT_RXD;
 	err = i40evf_init_interrupt_scheme(adapter);