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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 640 insertions, 712 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 82a95cc2c8ee..d5c9c9e06ff5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -32,6 +32,12 @@
 #include "i40e.h"
 #include "i40e_diag.h"
 #include <net/udp_tunnel.h>
+/* All i40e tracepoints are defined by the include below, which
+ * must be included exactly once across the whole kernel with
+ * CREATE_TRACE_POINTS defined
+ */
+#define CREATE_TRACE_POINTS
+#include "i40e_trace.h"
 
 const char i40e_driver_name[] = "i40e";
 static const char i40e_driver_string[] =
@@ -39,9 +45,9 @@ static const char i40e_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 14
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -50,13 +56,16 @@ static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporatio
 
 /* a bit of forward declarations */
 static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
-static void i40e_handle_reset_warning(struct i40e_pf *pf);
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired);
 static int i40e_add_vsi(struct i40e_vsi *vsi);
 static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi);
 static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit);
 static int i40e_setup_misc_vector(struct i40e_pf *pf);
 static void i40e_determine_queue_usage(struct i40e_pf *pf);
 static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
+static int i40e_reset(struct i40e_pf *pf);
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf);
 static int i40e_veb_get_bw_info(struct i40e_veb *veb);
 
@@ -286,8 +295,8 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
  **/
 void i40e_service_event_schedule(struct i40e_pf *pf)
 {
-	if (!test_bit(__I40E_DOWN, &pf->state) &&
-	    !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+	if (!test_bit(__I40E_VSI_DOWN, pf->state) &&
+	    !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		queue_work(i40e_wq, &pf->service_task);
 }
 
@@ -299,11 +308,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf)
  * device is munged, not just the one netdev port, so go for the full
  * reset.
  **/
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev)
-#else
 static void i40e_tx_timeout(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -372,13 +377,13 @@ static void i40e_tx_timeout(struct net_device *netdev)
 
 	switch (pf->tx_timeout_recovery_level) {
 	case 1:
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		break;
 	case 2:
-		set_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_CORE_RESET_REQUESTED, pf->state);
 		break;
 	case 3:
-		set_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 		break;
 	default:
 		netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
@@ -408,10 +413,7 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
  * Returns the address of the device statistics structure.
  * The statistics are actually updated from the service task.
  **/
-#ifndef I40E_FCOE
-static
-#endif
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
+static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 				  struct rtnl_link_stats64 *stats)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
@@ -420,7 +422,7 @@ void i40e_get_netdev_stats_struct(struct net_device *netdev,
 	struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi);
 	int i;
 
-	if (test_bit(__I40E_DOWN, &vsi->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	if (!vsi->tx_rings)
@@ -723,55 +725,6 @@ static void i40e_update_veb_stats(struct i40e_veb *veb)
 	veb->stat_offsets_loaded = true;
 }
 
-#ifdef I40E_FCOE
-/**
- * i40e_update_fcoe_stats - Update FCoE-specific ethernet statistics counters.
- * @vsi: the VSI that is capable of doing FCoE
- **/
-static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	struct i40e_fcoe_stats *ofs;
-	struct i40e_fcoe_stats *fs;     /* device's eth stats */
-	int idx;
-
-	if (vsi->type != I40E_VSI_FCOE)
-		return;
-
-	idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET;
-	fs = &vsi->fcoe_stats;
-	ofs = &vsi->fcoe_stats_offsets;
-
-	i40e_stat_update32(hw, I40E_GL_FCOEPRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_packets, &fs->rx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWRCH(idx), I40E_GL_FCOEDWRCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dwords, &fs->rx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOERPDC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dropped, &fs->rx_fcoe_dropped);
-	i40e_stat_update32(hw, I40E_GL_FCOEPTC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_packets, &fs->tx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWTCH(idx), I40E_GL_FCOEDWTCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_dwords, &fs->tx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOECRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_bad_fccrc, &fs->fcoe_bad_fccrc);
-	i40e_stat_update32(hw, I40E_GL_FCOELAST(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_last_error, &fs->fcoe_last_error);
-	i40e_stat_update32(hw, I40E_GL_FCOEDDPC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_ddp_count, &fs->fcoe_ddp_count);
-
-	vsi->fcoe_stat_offsets_loaded = true;
-}
-
-#endif
 /**
  * i40e_update_vsi_stats - Update the vsi statistics counters.
  * @vsi: the VSI to be updated
@@ -790,7 +743,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	struct i40e_eth_stats *oes;
 	struct i40e_eth_stats *es;     /* device's eth stats */
 	u32 tx_restart, tx_busy;
-	u64 tx_lost_interrupt;
 	struct i40e_ring *p;
 	u32 rx_page, rx_buf;
 	u64 bytes, packets;
@@ -801,8 +753,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	u64 tx_p, tx_b;
 	u16 q;
 
-	if (test_bit(__I40E_DOWN, &vsi->state) ||
-	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state) ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
 	ns = i40e_get_vsi_stats_struct(vsi);
@@ -816,7 +768,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	rx_b = rx_p = 0;
 	tx_b = tx_p = 0;
 	tx_restart = tx_busy = tx_linearize = tx_force_wb = 0;
-	tx_lost_interrupt = 0;
 	rx_page = 0;
 	rx_buf = 0;
 	rcu_read_lock();
@@ -835,7 +786,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 		tx_busy += p->tx_stats.tx_busy;
 		tx_linearize += p->tx_stats.tx_linearize;
 		tx_force_wb += p->tx_stats.tx_force_wb;
-		tx_lost_interrupt += p->tx_stats.tx_lost_interrupt;
 
 		/* Rx queue is part of the same block as Tx queue */
 		p = &p[1];
@@ -854,7 +804,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	vsi->tx_busy = tx_busy;
 	vsi->tx_linearize = tx_linearize;
 	vsi->tx_force_wb = tx_force_wb;
-	vsi->tx_lost_interrupt = tx_lost_interrupt;
 	vsi->rx_page_failed = rx_page;
 	vsi->rx_buf_failed = rx_buf;
 
@@ -1101,13 +1050,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_lpi_count, &nsd->rx_lpi_count);
 
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED))
+	    !(pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED))
 		nsd->fd_sb_status = true;
 	else
 		nsd->fd_sb_status = false;
 
 	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	    !(pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED))
 		nsd->fd_atr_status = true;
 	else
 		nsd->fd_atr_status = false;
@@ -1129,9 +1078,6 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 		i40e_update_pf_stats(pf);
 
 	i40e_update_vsi_stats(vsi);
-#ifdef I40E_FCOE
-	i40e_update_fcoe_stats(vsi);
-#endif
 }
 
 /**
@@ -1400,7 +1346,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 		 * to failed, so we don't bother to try sending the filter
 		 * to the hardware.
 		 */
-		if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))
+		if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))
 			f->state = I40E_FILTER_FAILED;
 		else
 			f->state = I40E_FILTER_NEW;
@@ -1562,11 +1508,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
  *
  * Returns 0 on success, negative on failure
  **/
-#ifdef I40E_FCOE
-int i40e_set_mac(struct net_device *netdev, void *p)
-#else
 static int i40e_set_mac(struct net_device *netdev, void *p)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1583,8 +1525,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		return 0;
 	}
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
+	    test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
 		return -EADDRNOTAVAIL;
 
 	if (ether_addr_equal(hw->mac.addr, addr->sa_data))
@@ -1626,17 +1568,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
  *
  * Setup VSI queue mapping for enabled traffic classes.
  **/
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
-			      struct i40e_vsi_context *ctxt,
-			      u8 enabled_tc,
-			      bool is_add)
-#else
 static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				     struct i40e_vsi_context *ctxt,
 				     u8 enabled_tc,
 				     bool is_add)
-#endif
 {
 	struct i40e_pf *pf = vsi->back;
 	u16 sections = 0;
@@ -1686,11 +1621,6 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				qcount = min_t(int, pf->alloc_rss_size,
 					       num_tc_qps);
 				break;
-#ifdef I40E_FCOE
-			case I40E_VSI_FCOE:
-				qcount = num_tc_qps;
-				break;
-#endif
 			case I40E_VSI_FDIR:
 			case I40E_VSI_SRIOV:
 			case I40E_VSI_VMDQ2:
@@ -1800,11 +1730,7 @@ static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr)
  * i40e_set_rx_mode - NDO callback to set the netdev filters
  * @netdev: network interface device structure
  **/
-#ifdef I40E_FCOE
-void i40e_set_rx_mode(struct net_device *netdev)
-#else
 static void i40e_set_rx_mode(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1883,19 +1809,12 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi,
 static
 struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next)
 {
-	while (next) {
-		next = hlist_entry(next->hlist.next,
-				   typeof(struct i40e_new_mac_filter),
-				   hlist);
-
-		/* keep going if we found a broadcast filter */
-		if (next && is_broadcast_ether_addr(next->f->macaddr))
-			continue;
-
-		break;
+	hlist_for_each_entry_continue(next, hlist) {
+		if (!is_broadcast_ether_addr(next->f->macaddr))
+			return next;
 	}
 
-	return next;
+	return NULL;
 }
 
 /**
@@ -2001,7 +1920,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 
 	if (fcnt != num_add) {
 		*promisc_changed = true;
-		set_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		dev_warn(&vsi->back->pdev->dev,
 			 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
 			 i40e_aq_str(hw, aq_err),
@@ -2084,7 +2003,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	struct i40e_aqc_add_macvlan_element_data *add_list;
 	struct i40e_aqc_remove_macvlan_element_data *del_list;
 
-	while (test_and_set_bit(__I40E_CONFIG_BUSY, &vsi->state))
+	while (test_and_set_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state))
 		usleep_range(1000, 2000);
 	pf = vsi->back;
 
@@ -2220,8 +2139,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 		num_add = 0;
 		hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) {
-			if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
-				     &vsi->state)) {
+			if (test_bit(__I40E_VSI_OVERFLOW_PROMISC,
+				     vsi->state)) {
 				new->state = I40E_FILTER_FAILED;
 				continue;
 			}
@@ -2308,20 +2227,20 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	 * safely exit if we didn't just enter, we no longer have any failed
 	 * filters, and we have reduced filters below the threshold value.
 	 */
-	if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) &&
+	if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) &&
 	    !promisc_changed && !failed_filters &&
 	    (vsi->active_filters < vsi->promisc_threshold)) {
 		dev_info(&pf->pdev->dev,
 			 "filter logjam cleared on %s, leaving overflow promiscuous mode\n",
 			 vsi_name);
-		clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		promisc_changed = true;
 		vsi->promisc_threshold = 0;
 	}
 
 	/* if the VF is not trusted do not do promisc */
 	if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) {
-		clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 		goto out;
 	}
 
@@ -2346,12 +2265,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	}
 	if ((changed_flags & IFF_PROMISC) ||
 	    (promisc_changed &&
-	     test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))) {
+	     test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))) {
 		bool cur_promisc;
 
 		cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
-			       test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
-					&vsi->state));
+			       test_bit(__I40E_VSI_OVERFLOW_PROMISC,
+					vsi->state));
 		if ((vsi->type == I40E_VSI_MAIN) &&
 		    (pf->lan_veb != I40E_NO_VEB) &&
 		    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
@@ -2434,7 +2353,7 @@ out:
 	if (retval)
 		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
 
-	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+	clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state);
 	return retval;
 
 err_no_memory:
@@ -2446,7 +2365,7 @@ err_no_memory_locked:
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
 
 	vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
-	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+	clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state);
 	return -ENOMEM;
 }
 
@@ -2487,13 +2406,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 
 	netdev_info(netdev, "changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 	if (netif_running(netdev))
 		i40e_vsi_reinit_locked(vsi);
-	i40e_notify_client_of_l2_param_changes(vsi);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	return 0;
 }
 
@@ -2707,13 +2628,8 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid)
  *
  * net_device_ops implementation for adding vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
-			 __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_add_vid(struct net_device *netdev,
 				__always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2744,13 +2660,8 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev,
  *
  * net_device_ops implementation for removing vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
-			  __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
 				 __always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2920,9 +2831,6 @@ static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_setup_rx_descriptors(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_setup_ddp_resources(vsi);
-#endif
 	return err;
 }
 
@@ -2942,9 +2850,6 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_queue_pairs; i++)
 		if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
 			i40e_free_rx_resources(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_free_ddp_resources(vsi);
-#endif
 }
 
 /**
@@ -3015,9 +2920,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	tx_ctx.qlen = ring->count;
 	tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
 					       I40E_FLAG_FD_ATR_ENABLED));
-#ifdef I40E_FCOE
-	tx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
 	/* FDIR VSI tx ring can still use RS bit and writebacks */
 	if (vsi->type != I40E_VSI_FDIR)
@@ -3098,7 +3000,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->rx_buf_len = vsi->rx_buf_len;
 
-	rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT;
+	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
+				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
 
 	rx_ctx.base = (ring->dma / 128);
 	rx_ctx.qlen = ring->count;
@@ -3120,9 +3023,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	rx_ctx.l2tsel = 1;
 	/* this controls whether VLAN is stripped from inner headers */
 	rx_ctx.showiv = 0;
-#ifdef I40E_FCOE
-	rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	/* set the prefena field to 1 because the manual says to */
 	rx_ctx.prefena = 1;
 
@@ -3144,6 +3044,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		return -ENOMEM;
 	}
 
+	/* configure Rx buffer alignment */
+	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX))
+		clear_ring_build_skb_enabled(ring);
+	else
+		set_ring_build_skb_enabled(ring);
+
 	/* cache tail for quicker writes, and clear the reg before use */
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
@@ -3181,27 +3087,21 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
 	int err = 0;
 	u16 i;
 
-	if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN))
-		vsi->max_frame = vsi->netdev->mtu + ETH_HLEN
-			       + ETH_FCS_LEN + VLAN_HLEN;
-	else
-		vsi->max_frame = I40E_RXBUFFER_2048;
-
-	vsi->rx_buf_len = I40E_RXBUFFER_2048;
-
-#ifdef I40E_FCOE
-	/* setup rx buffer for FCoE */
-	if ((vsi->type == I40E_VSI_FCOE) &&
-	    (vsi->back->flags & I40E_FLAG_FCOE_ENABLED)) {
-		vsi->rx_buf_len = I40E_RXBUFFER_3072;
-		vsi->max_frame = I40E_RXBUFFER_3072;
+	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = I40E_RXBUFFER_2048;
+#if (PAGE_SIZE < 8192)
+	} else if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
+		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
+		vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+		vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+#endif
+	} else {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = (PAGE_SIZE < 8192) ? I40E_RXBUFFER_3072 :
+						       I40E_RXBUFFER_2048;
 	}
 
-#endif /* I40E_FCOE */
-	/* round up for the chip's needs */
-	vsi->rx_buf_len = ALIGN(vsi->rx_buf_len,
-				BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
-
 	/* set up individual rings */
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_configure_rx_ring(vsi->rx_rings[i]);
@@ -3281,6 +3181,12 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return;
 
+	/* Reset FDir counters as we're replaying all existing filters */
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
 	hlist_for_each_entry_safe(filter, node,
 				  &pf->fdir_filter_list, fdir_node) {
 		i40e_add_del_fdir(vsi, filter, true);
@@ -3705,29 +3611,29 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		 * this is not a performance path and napi_schedule()
 		 * can deal with rescheduling.
 		 */
-		if (!test_bit(__I40E_DOWN, &pf->state))
+		if (!test_bit(__I40E_VSI_DOWN, pf->state))
 			napi_schedule_irqoff(&q_vector->napi);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
-		set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state);
 		i40e_debug(&pf->hw, I40E_DEBUG_NVM, "AdminQ event\n");
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
-		set_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) {
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK;
-		set_bit(__I40E_VFLR_EVENT_PENDING, &pf->state);
+		set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_GRST_MASK) {
-		if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
-			set_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
+		if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+			set_bit(__I40E_RESET_INTR_RECEIVED, pf->state);
 		ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK;
 		val = rd32(hw, I40E_GLGEN_RSTAT);
 		val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK)
@@ -3738,7 +3644,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 			pf->globr_count++;
 		} else if (val == I40E_RESET_EMPR) {
 			pf->empr_count++;
-			set_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state);
+			set_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state);
 		}
 	}
 
@@ -3771,7 +3677,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		    (icr0_remaining & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK) ||
 		    (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK)) {
 			dev_info(&pf->pdev->dev, "device will be reset\n");
-			set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 			i40e_service_event_schedule(pf);
 		}
 		ena_mask &= ~icr0_remaining;
@@ -3781,7 +3687,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 enable_intr:
 	/* re-enable interrupt causes */
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
-	if (!test_bit(__I40E_DOWN, &pf->state)) {
+	if (!test_bit(__I40E_VSI_DOWN, pf->state)) {
 		i40e_service_event_schedule(pf);
 		i40e_irq_dynamic_enable_icr0(pf, false);
 	}
@@ -3993,11 +3899,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
  * This is used by netconsole to send skbs without having to re-enable
  * interrupts.  It's not called while the normal interrupt routine is executing.
  **/
-#ifdef I40E_FCOE
-void i40e_netpoll(struct net_device *netdev)
-#else
 static void i40e_netpoll(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -4005,7 +3907,7 @@ static void i40e_netpoll(struct net_device *netdev)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &vsi->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
@@ -4017,6 +3919,8 @@ static void i40e_netpoll(struct net_device *netdev)
 }
 #endif
 
+#define I40E_QTX_ENA_WAIT_COUNT 50
+
 /**
  * i40e_pf_txq_wait - Wait for a PF's Tx queue to be enabled or disabled
  * @pf: the PF being configured
@@ -4047,6 +3951,50 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 }
 
 /**
+ * i40e_control_tx_q - Start or stop a particular Tx queue
+ * @pf: the PF structure
+ * @pf_q: the PF queue to configure
+ * @enable: start or stop the queue
+ *
+ * This function enables or disables a single queue. Note that any delay
+ * required after the operation is expected to be handled by the caller of
+ * this function.
+ **/
+static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u32 tx_reg;
+	int i;
+
+	/* warn the TX unit of coming changes */
+	i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable);
+	if (!enable)
+		usleep_range(10, 20);
+
+	for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) {
+		tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
+		if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
+		    ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1))
+			break;
+		usleep_range(1000, 2000);
+	}
+
+	/* Skip if the queue is already in the requested state */
+	if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+		return;
+
+	/* turn on/off the queue */
+	if (enable) {
+		wr32(hw, I40E_QTX_HEAD(pf_q), 0);
+		tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK;
+	} else {
+		tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
+	}
+
+	wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
+}
+
+/**
  * i40e_vsi_control_tx - Start or stop a VSI's rings
  * @vsi: the VSI being configured
  * @enable: start or stop the rings
@@ -4054,41 +4002,11 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	int i, j, pf_q, ret = 0;
-	u32 tx_reg;
+	int i, pf_q, ret = 0;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-
-		/* warn the TX unit of coming changes */
-		i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable);
-		if (!enable)
-			usleep_range(10, 20);
-
-		for (j = 0; j < 50; j++) {
-			tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
-			if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
-			    ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1))
-				break;
-			usleep_range(1000, 2000);
-		}
-		/* Skip if the queue is already in the requested state */
-		if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
-			continue;
-
-		/* turn on/off the queue */
-		if (enable) {
-			wr32(hw, I40E_QTX_HEAD(pf_q), 0);
-			tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK;
-		} else {
-			tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
-		}
-
-		wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
-		/* No waiting for the Tx queue to disable */
-		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
-			continue;
+		i40e_control_tx_q(pf, pf_q, enable);
 
 		/* wait for the change to finish */
 		ret = i40e_pf_txq_wait(pf, pf_q, enable);
@@ -4100,8 +4018,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
-	if (hw->revision_id == 0)
-		mdelay(50);
 	return ret;
 }
 
@@ -4135,6 +4051,43 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 }
 
 /**
+ * i40e_control_rx_q - Start or stop a particular Rx queue
+ * @pf: the PF structure
+ * @pf_q: the PF queue to configure
+ * @enable: start or stop the queue
+ *
+ * This function enables or disables a single queue. Note that any delay
+ * required after the operation is expected to be handled by the caller of
+ * this function.
+ **/
+static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u32 rx_reg;
+	int i;
+
+	for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) {
+		rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
+		if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) ==
+		    ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1))
+			break;
+		usleep_range(1000, 2000);
+	}
+
+	/* Skip if the queue is already in the requested state */
+	if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+		return;
+
+	/* turn on/off the queue */
+	if (enable)
+		rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK;
+	else
+		rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
+
+	wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
+}
+
+/**
  * i40e_vsi_control_rx - Start or stop a VSI's rings
  * @vsi: the VSI being configured
  * @enable: start or stop the rings
@@ -4142,33 +4095,11 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable)
 static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	int i, j, pf_q, ret = 0;
-	u32 rx_reg;
+	int i, pf_q, ret = 0;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		for (j = 0; j < 50; j++) {
-			rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
-			if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) ==
-			    ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1))
-				break;
-			usleep_range(1000, 2000);
-		}
-
-		/* Skip if the queue is already in the requested state */
-		if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-			continue;
-
-		/* turn on/off the queue */
-		if (enable)
-			rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK;
-		else
-			rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
-		wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
-		/* No waiting for the Tx queue to disable */
-		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
-			continue;
+		i40e_control_rx_q(pf, pf_q, enable);
 
 		/* wait for the change to finish */
 		ret = i40e_pf_rxq_wait(pf, pf_q, enable);
@@ -4180,6 +4111,12 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
+	/* Due to HW errata, on Rx disable only, the register can indicate done
+	 * before it really is. Needs 50ms to be sure
+	 */
+	if (!enable)
+		mdelay(50);
+
 	return ret;
 }
 
@@ -4206,6 +4143,10 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
  **/
 void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 {
+	/* When port TX is suspended, don't wait */
+	if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
+		return i40e_vsi_stop_rings_no_wait(vsi);
+
 	/* do rx first for enable and last for disable
 	 * Ignore return value, we need to shutdown whatever we can
 	 */
@@ -4214,6 +4155,29 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_vsi_stop_rings_no_wait - Stop a VSI's rings and do not delay
+ * @vsi: the VSI being shutdown
+ *
+ * This function stops all the rings for a VSI but does not delay to verify
+ * that rings have been disabled. It is expected that the caller is shutting
+ * down multiple VSIs at once and will delay together for all the VSIs after
+ * initiating the shutdown. This is particularly useful for shutting down lots
+ * of VFs together. Otherwise, a large delay can be incurred while configuring
+ * each VSI in serial.
+ **/
+void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+	int i, pf_q;
+
+	pf_q = vsi->base_queue;
+	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+		i40e_control_tx_q(pf, pf_q, false);
+		i40e_control_rx_q(pf, pf_q, false);
+	}
+}
+
+/**
  * i40e_vsi_free_irq - Free the irq association with the OS
  * @vsi: the VSI being configured
  **/
@@ -4471,17 +4435,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
  **/
 static void i40e_vsi_close(struct i40e_vsi *vsi)
 {
-	bool reset = false;
-
-	if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
+	struct i40e_pf *pf = vsi->back;
+	if (!test_and_set_bit(__I40E_VSI_DOWN, vsi->state))
 		i40e_down(vsi);
 	i40e_vsi_free_irq(vsi);
 	i40e_vsi_free_tx_resources(vsi);
 	i40e_vsi_free_rx_resources(vsi);
 	vsi->current_netdev_flags = 0;
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		reset = true;
-	i40e_notify_client_of_netdev_close(vsi, reset);
+	pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+		pf->flags |=  I40E_FLAG_CLIENT_RESET;
 }
 
 /**
@@ -4490,18 +4453,10 @@ static void i40e_vsi_close(struct i40e_vsi *vsi)
  **/
 static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
 {
-	if (test_bit(__I40E_DOWN, &vsi->state))
-		return;
-
-	/* No need to disable FCoE VSI when Tx suspended */
-	if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
-	    vsi->type == I40E_VSI_FCOE) {
-		dev_dbg(&vsi->back->pdev->dev,
-			 "VSI seid %d skipping FCoE VSI disable\n", vsi->seid);
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
-	}
 
-	set_bit(__I40E_NEEDS_RESTART, &vsi->state);
+	set_bit(__I40E_VSI_NEEDS_RESTART, vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
 	else
@@ -4514,10 +4469,9 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
  **/
 static void i40e_unquiesce_vsi(struct i40e_vsi *vsi)
 {
-	if (!test_bit(__I40E_NEEDS_RESTART, &vsi->state))
+	if (!test_and_clear_bit(__I40E_VSI_NEEDS_RESTART, vsi->state))
 		return;
 
-	clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
 	else
@@ -4552,21 +4506,20 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
 	}
 }
 
-#ifdef CONFIG_I40E_DCB
 /**
  * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled
  * @vsi: the VSI being configured
  *
- * This function waits for the given VSI's queues to be disabled.
+ * Wait until all queues on a given VSI have been disabled.
  **/
-static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
+int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
 	int i, pf_q, ret;
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		/* Check and wait for the disable status of the queue */
+		/* Check and wait for the Tx queue */
 		ret = i40e_pf_txq_wait(pf, pf_q, false);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
@@ -4574,11 +4527,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 				 vsi->seid, pf_q);
 			return ret;
 		}
-	}
-
-	pf_q = vsi->base_queue;
-	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
-		/* Check and wait for the disable status of the queue */
+		/* Check and wait for the Tx queue */
 		ret = i40e_pf_rxq_wait(pf, pf_q, false);
 		if (ret) {
 			dev_info(&pf->pdev->dev,
@@ -4591,6 +4540,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
 	return 0;
 }
 
+#ifdef CONFIG_I40E_DCB
 /**
  * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled
  * @pf: the PF
@@ -4603,8 +4553,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 	int v, ret = 0;
 
 	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
-		/* No need to wait for FCoE VSI queues */
-		if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
+		if (pf->vsi[v]) {
 			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
 				break;
@@ -4622,16 +4571,15 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
  * @vsi: Pointer to VSI struct
  *
  * This function checks specified queue for given VSI. Detects hung condition.
- * Sets hung bit since it is two step process. Before next run of service task
- * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not,
- * hung condition remain unchanged and during subsequent run, this function
- * issues SW interrupt to recover from hung condition.
+ * We proactively detect hung TX queues by checking if interrupts are disabled
+ * but there are pending descriptors.  If it appears hung, attempt to recover
+ * by triggering a SW interrupt.
  **/
 static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 {
 	struct i40e_ring *tx_ring = NULL;
 	struct i40e_pf	*pf;
-	u32 head, val, tx_pending_hw;
+	u32 val, tx_pending;
 	int i;
 
 	pf = vsi->back;
@@ -4657,47 +4605,15 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 	else
 		val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
 
-	head = i40e_get_head(tx_ring);
-
-	tx_pending_hw = i40e_get_tx_pending(tx_ring, false);
-
-	/* HW is done executing descriptors, updated HEAD write back,
-	 * but SW hasn't processed those descriptors. If interrupt is
-	 * not generated from this point ON, it could result into
-	 * dev_watchdog detecting timeout on those netdev_queue,
-	 * hence proactively trigger SW interrupt.
-	 */
-	if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
-		/* NAPI Poll didn't run and clear since it was set */
-		if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT,
-				       &tx_ring->q_vector->hung_detected)) {
-			netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
-				    vsi->seid, q_idx, tx_pending_hw,
-				    tx_ring->next_to_clean, head,
-				    tx_ring->next_to_use,
-				    readl(tx_ring->tail));
-			netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n",
-				    vsi->seid, q_idx, val);
-			i40e_force_wb(vsi, tx_ring->q_vector);
-		} else {
-			/* First Chance - detected possible hung */
-			set_bit(I40E_Q_VECTOR_HUNG_DETECT,
-				&tx_ring->q_vector->hung_detected);
-		}
-	}
+	tx_pending = i40e_get_tx_pending(tx_ring);
 
-	/* This is the case where we have interrupts missing,
-	 * so the tx_pending in HW will most likely be 0, but we
-	 * will have tx_pending in SW since the WB happened but the
-	 * interrupt got lost.
+	/* Interrupts are disabled and TX pending is non-zero,
+	 * trigger the SW interrupt (don't wait). Worst case
+	 * there will be one extra interrupt which may result
+	 * into not cleaning any queues because queues are cleaned.
 	 */
-	if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) &&
-	    (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
-		local_bh_disable();
-		if (napi_reschedule(&tx_ring->q_vector->napi))
-			tx_ring->tx_stats.tx_lost_interrupt++;
-		local_bh_enable();
-	}
+	if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
+		i40e_force_wb(vsi, tx_ring->q_vector);
 }
 
 /**
@@ -4721,8 +4637,8 @@ static void i40e_detect_recover_hung(struct i40e_pf *pf)
 		return;
 
 	/* Make sure, VSI state is not DOWN/RECOVERY_PENDING */
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
+	if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
+	    test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
 		return;
 
 	/* Make sure type is MAIN VSI */
@@ -5228,20 +5144,12 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 			continue;
 
 		/* - Enable all TCs for the LAN VSI
-#ifdef I40E_FCOE
-		 * - For FCoE VSI only enable the TC configured
-		 *   as per the APP TLV
-#endif
 		 * - For all others keep them at TC0 for now
 		 */
 		if (v == pf->lan_vsi)
 			tc_map = i40e_pf_get_tc_map(pf);
 		else
 			tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
-#ifdef I40E_FCOE
-		if (pf->vsi[v]->type == I40E_VSI_FCOE)
-			tc_map = i40e_get_fcoe_tc_map(pf);
-#endif /* #ifdef I40E_FCOE */
 
 		ret = i40e_vsi_config_tc(pf->vsi[v], tc_map);
 		if (ret) {
@@ -5277,7 +5185,7 @@ static int i40e_resume_port_tx(struct i40e_pf *pf)
 			  i40e_stat_str(&pf->hw, ret),
 			  i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 		/* Schedule PF reset to recover */
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
 	}
 
@@ -5308,10 +5216,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		    (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED)) {
 			dev_info(&pf->pdev->dev,
 				 "DCBX offload is not supported or is disabled for this PF.\n");
-
-			if (pf->flags & I40E_FLAG_MFP_ENABLED)
-				goto out;
-
 		} else {
 			/* When status is not DISABLED then DCBX in FW */
 			pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
@@ -5449,7 +5353,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	if (err)
 		return err;
 
-	clear_bit(__I40E_DOWN, &vsi->state);
+	clear_bit(__I40E_VSI_DOWN, vsi->state);
 	i40e_napi_enable_all(vsi);
 	i40e_vsi_enable_irq(vsi);
 
@@ -5472,13 +5376,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	/* replay FDIR SB filters */
 	if (vsi->type == I40E_VSI_FDIR) {
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = 0;
-		if (pf->fd_tcp_rule > 0) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
-			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;
-		}
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		i40e_fdir_filter_restore(vsi);
 	}
 
@@ -5503,12 +5402,12 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 
 	WARN_ON(in_interrupt());
-	while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
+	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state))
 		usleep_range(1000, 2000);
 	i40e_down(vsi);
 
 	i40e_up(vsi);
-	clear_bit(__I40E_CONFIG_BUSY, &pf->state);
+	clear_bit(__I40E_CONFIG_BUSY, pf->state);
 }
 
 /**
@@ -5535,7 +5434,7 @@ void i40e_down(struct i40e_vsi *vsi)
 	int i;
 
 	/* It is assumed that the caller of this function
-	 * sets the vsi->state __I40E_DOWN bit.
+	 * sets the vsi->state __I40E_VSI_DOWN bit.
 	 */
 	if (vsi->netdev) {
 		netif_carrier_off(vsi->netdev);
@@ -5550,8 +5449,6 @@ void i40e_down(struct i40e_vsi *vsi)
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
-	i40e_notify_client_of_netdev_close(vsi, false);
-
 }
 
 /**
@@ -5612,17 +5509,15 @@ exit:
 	return ret;
 }
 
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
-		    struct tc_to_netdev *tc)
-#else
 static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 			   struct tc_to_netdev *tc)
-#endif
 {
-	if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)
+	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
-	return i40e_setup_tc(netdev, tc->tc);
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return i40e_setup_tc(netdev, tc->mqprio->num_tc);
 }
 
 /**
@@ -5645,8 +5540,8 @@ int i40e_open(struct net_device *netdev)
 	int err;
 
 	/* disallow open during test or if eeprom is broken */
-	if (test_bit(__I40E_TESTING, &pf->state) ||
-	    test_bit(__I40E_BAD_EEPROM, &pf->state))
+	if (test_bit(__I40E_TESTING, pf->state) ||
+	    test_bit(__I40E_BAD_EEPROM, pf->state))
 		return -EBUSY;
 
 	netif_carrier_off(netdev);
@@ -5675,6 +5570,8 @@ int i40e_open(struct net_device *netdev)
  * Finish initialization of the VSI.
  *
  * Returns 0 on success, negative value on failure
+ *
+ * Note: expects to be called while under rtnl_lock()
  **/
 int i40e_vsi_open(struct i40e_vsi *vsi)
 {
@@ -5738,7 +5635,7 @@ err_setup_rx:
 err_setup_tx:
 	i40e_vsi_free_tx_resources(vsi);
 	if (vsi == pf->vsi[pf->lan_vsi])
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
 
 	return err;
 }
@@ -5753,6 +5650,7 @@ err_setup_tx:
 static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 {
 	struct i40e_fdir_filter *filter;
+	struct i40e_flex_pit *pit_entry, *tmp;
 	struct hlist_node *node2;
 
 	hlist_for_each_entry_safe(filter, node2,
@@ -5760,7 +5658,43 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 		hlist_del(&filter->fdir_node);
 		kfree(filter);
 	}
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l3_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l4_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	pf->fdir_pf_active_filters = 0;
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
+	/* Reprogram the default input set for TCP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for UDP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for SCTP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for Other/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
 /**
@@ -5787,12 +5721,14 @@ int i40e_close(struct net_device *netdev)
  * i40e_do_reset - Start a PF or Core Reset sequence
  * @pf: board private structure
  * @reset_flags: which reset is requested
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  *
  * The essential difference in resets is that the PF Reset
  * doesn't clear the packet buffers, doesn't reset the PE
  * firmware, and doesn't bother the other PFs on the chip.
  **/
-void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 {
 	u32 val;
 
@@ -5838,7 +5774,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 		 * for the Core Reset.
 		 */
 		dev_dbg(&pf->pdev->dev, "PFR requested\n");
-		i40e_handle_reset_warning(pf);
+		i40e_handle_reset_warning(pf, lock_acquired);
 
 	} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
 		int v;
@@ -5850,10 +5786,9 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 			struct i40e_vsi *vsi = pf->vsi[v];
 
 			if (vsi != NULL &&
-			    test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) {
+			    test_and_clear_bit(__I40E_VSI_REINIT_REQUESTED,
+					       vsi->state))
 				i40e_vsi_reinit_locked(pf->vsi[v]);
-				clear_bit(__I40E_REINIT_REQUESTED, &vsi->state);
-			}
 		}
 	} else if (reset_flags & BIT_ULL(__I40E_DOWN_REQUESTED)) {
 		int v;
@@ -5864,10 +5799,10 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 			struct i40e_vsi *vsi = pf->vsi[v];
 
 			if (vsi != NULL &&
-			    test_bit(__I40E_DOWN_REQUESTED, &vsi->state)) {
-				set_bit(__I40E_DOWN, &vsi->state);
+			    test_and_clear_bit(__I40E_VSI_DOWN_REQUESTED,
+					       vsi->state)) {
+				set_bit(__I40E_VSI_DOWN, vsi->state);
 				i40e_down(vsi);
-				clear_bit(__I40E_DOWN_REQUESTED, &vsi->state);
 			}
 		}
 	} else {
@@ -6007,7 +5942,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	else
 		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
 
-	set_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
+	set_bit(__I40E_PORT_SUSPENDED, pf->state);
 	/* Reconfiguration needed quiesce all VSIs */
 	i40e_pf_quiesce_all_vsi(pf);
 
@@ -6016,7 +5951,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 
 	ret = i40e_resume_port_tx(pf);
 
-	clear_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
+	clear_bit(__I40E_PORT_SUSPENDED, pf->state);
 	/* In case of error no point in resuming VSIs */
 	if (ret)
 		goto exit;
@@ -6025,12 +5960,12 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	ret = i40e_pf_wait_queues_disabled(pf);
 	if (ret) {
 		/* Schedule PF reset to recover */
-		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
-		/* Notify the client for the DCB changes */
-		i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	}
 
 exit:
@@ -6047,7 +5982,7 @@ exit:
 void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags)
 {
 	rtnl_lock();
-	i40e_do_reset(pf, reset_flags);
+	i40e_do_reset(pf, reset_flags, true);
 	rtnl_unlock();
 }
 
@@ -6140,34 +6075,33 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 	u32 fcnt_prog, fcnt_avail;
 	struct hlist_node *node;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		return;
 
-	/* Check if, FD SB or ATR was auto disabled and if there is enough room
-	 * to re-enable
-	 */
+	/* Check if we have enough room to re-enable FDir SB capability. */
 	fcnt_prog = i40e_get_global_fd_count(pf);
 	fcnt_avail = pf->fdir_pf_filter_count;
 	if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM)) ||
 	    (pf->fd_add_err == 0) ||
 	    (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) {
-		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;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+		if (pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_SB_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
+			    (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. We also
-	 * must check that no existing ntuple rules for TCP are in effect
+	/* We should wait for even more space before re-enabling ATR.
+	 * Additionally, we cannot enable ATR as long as we still have TCP SB
+	 * rules active.
 	 */
-	if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) {
-		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->fd_tcp_rule == 0)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+	if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) &&
+	    (pf->fd_tcp4_filter_cnt == 0)) {
+		if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n");
 		}
 	}
@@ -6218,7 +6152,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	}
 
 	pf->fd_flush_timestamp = jiffies;
-	pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+	pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED;
 	/* flush all filters */
 	wr32(&pf->hw, I40E_PFQF_CTL_1,
 	     I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
@@ -6237,9 +6171,9 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	} else {
 		/* replay sideband filters */
 		i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
-		if (!disable_atr)
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
+		if (!disable_atr && !pf->fd_tcp4_filter_cnt)
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+		clear_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 	}
@@ -6269,10 +6203,10 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf)
 {
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, pf->state))
 		return;
 
-	if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
+	if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
 		i40e_fdir_flush_and_replay(pf);
 
 	i40e_fdir_check_and_reenable(pf);
@@ -6286,14 +6220,11 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf)
  **/
 static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
 {
-	if (!vsi || test_bit(__I40E_DOWN, &vsi->state))
+	if (!vsi || test_bit(__I40E_VSI_DOWN, vsi->state))
 		return;
 
 	switch (vsi->type) {
 	case I40E_VSI_MAIN:
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-#endif
 		if (!vsi->netdev || !vsi->netdev_registered)
 			break;
 
@@ -6382,11 +6313,11 @@ static void i40e_link_event(struct i40e_pf *pf)
 
 	if (new_link == old_link &&
 	    new_link_speed == old_link_speed &&
-	    (test_bit(__I40E_DOWN, &vsi->state) ||
+	    (test_bit(__I40E_VSI_DOWN, vsi->state) ||
 	     new_link == netif_carrier_ok(vsi->netdev)))
 		return;
 
-	if (!test_bit(__I40E_DOWN, &vsi->state))
+	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
 		i40e_print_link_message(vsi, new_link);
 
 	/* Notify the base of the switch tree connected to
@@ -6413,8 +6344,8 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf)
 	int i;
 
 	/* if interface is down do nothing */
-	if (test_bit(__I40E_DOWN, &pf->state) ||
-	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, pf->state) ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
 	/* make sure we don't do these things too often */
@@ -6452,44 +6383,44 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
 {
 	u32 reset_flags = 0;
 
-	rtnl_lock();
-	if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_REINIT_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_REINIT_REQUESTED);
-		clear_bit(__I40E_REINIT_REQUESTED, &pf->state);
+		clear_bit(__I40E_REINIT_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_PF_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_PF_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_PF_RESET_REQUESTED);
-		clear_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_CORE_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_CORE_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_CORE_RESET_REQUESTED);
-		clear_bit(__I40E_CORE_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_CORE_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state)) {
+	if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state)) {
 		reset_flags |= BIT(__I40E_GLOBAL_RESET_REQUESTED);
-		clear_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state);
+		clear_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 	}
-	if (test_bit(__I40E_DOWN_REQUESTED, &pf->state)) {
-		reset_flags |= BIT(__I40E_DOWN_REQUESTED);
-		clear_bit(__I40E_DOWN_REQUESTED, &pf->state);
+	if (test_bit(__I40E_VSI_DOWN_REQUESTED, pf->state)) {
+		reset_flags |= BIT(__I40E_VSI_DOWN_REQUESTED);
+		clear_bit(__I40E_VSI_DOWN_REQUESTED, pf->state);
 	}
 
 	/* If there's a recovery already waiting, it takes
 	 * precedence before starting a new reset sequence.
 	 */
-	if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) {
-		i40e_handle_reset_warning(pf);
-		goto unlock;
+	if (test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) {
+		i40e_prep_for_reset(pf, false);
+		i40e_reset(pf);
+		i40e_rebuild(pf, false, false);
 	}
 
 	/* If we're already down or resetting, just bail */
 	if (reset_flags &&
-	    !test_bit(__I40E_DOWN, &pf->state) &&
-	    !test_bit(__I40E_CONFIG_BUSY, &pf->state))
-		i40e_do_reset(pf, reset_flags);
-
-unlock:
-	rtnl_unlock();
+	    !test_bit(__I40E_VSI_DOWN, pf->state) &&
+	    !test_bit(__I40E_CONFIG_BUSY, pf->state)) {
+		rtnl_lock();
+		i40e_do_reset(pf, reset_flags, true);
+		rtnl_unlock();
+	}
 }
 
 /**
@@ -6534,7 +6465,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 	u32 val;
 
 	/* Do not run clean AQ when PF reset fails */
-	if (test_bit(__I40E_RESET_FAILED, &pf->state))
+	if (test_bit(__I40E_RESET_FAILED, pf->state))
 		return;
 
 	/* check for error indications */
@@ -6635,9 +6566,11 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 				 opcode);
 			break;
 		}
-	} while (pending && (i++ < pf->adminq_work_limit));
+	} while (i++ < pf->adminq_work_limit);
+
+	if (i < pf->adminq_work_limit)
+		clear_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state);
 
-	clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
 	/* re-enable Admin queue interrupt cause */
 	val = rd32(hw, I40E_PFINT_ICR0_ENA);
 	val |=  I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
@@ -6662,13 +6595,13 @@ static void i40e_verify_eeprom(struct i40e_pf *pf)
 		if (err) {
 			dev_info(&pf->pdev->dev, "eeprom check failed (%d), Tx/Rx traffic disabled\n",
 				 err);
-			set_bit(__I40E_BAD_EEPROM, &pf->state);
+			set_bit(__I40E_BAD_EEPROM, pf->state);
 		}
 	}
 
-	if (!err && test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	if (!err && test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		dev_info(&pf->pdev->dev, "eeprom check passed, Tx/Rx traffic enabled\n");
-		clear_bit(__I40E_BAD_EEPROM, &pf->state);
+		clear_bit(__I40E_BAD_EEPROM, pf->state);
 	}
 }
 
@@ -6975,17 +6908,19 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
 /**
  * i40e_prep_for_reset - prep for the core to reset
  * @pf: board private structure
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  *
  * Close up the VFs and other things in prep for PF Reset.
   **/
-static void i40e_prep_for_reset(struct i40e_pf *pf)
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired)
 {
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret = 0;
 	u32 v;
 
-	clear_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
-	if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+	clear_bit(__I40E_RESET_INTR_RECEIVED, pf->state);
+	if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		return;
 	if (i40e_check_asq_alive(&pf->hw))
 		i40e_vc_notify_reset(pf);
@@ -6993,7 +6928,12 @@ static void i40e_prep_for_reset(struct i40e_pf *pf)
 	dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
 
 	/* quiesce the VSIs and their queues that are not already DOWN */
+	/* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */
+	if (!lock_acquired)
+		rtnl_lock();
 	i40e_pf_quiesce_all_vsi(pf);
+	if (!lock_acquired)
+		rtnl_unlock();
 
 	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v])
@@ -7028,31 +6968,41 @@ static void i40e_send_version(struct i40e_pf *pf)
 }
 
 /**
- * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen
  * @pf: board private structure
- * @reinit: if the Main VSI needs to re-initialized.
  **/
-static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
+static int i40e_reset(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
-	u8 set_fc_aq_fail = 0;
 	i40e_status ret;
-	u32 val;
-	u32 v;
 
-	/* Now we wait for GRST to settle out.
-	 * We don't have to delete the VEBs or VSIs from the hw switch
-	 * because the reset will make them disappear.
-	 */
 	ret = i40e_pf_reset(hw);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
-		set_bit(__I40E_RESET_FAILED, &pf->state);
-		goto clear_recovery;
+		set_bit(__I40E_RESET_FAILED, pf->state);
+		clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+	} else {
+		pf->pfr_count++;
 	}
-	pf->pfr_count++;
+	return ret;
+}
+
+/**
+ * i40e_rebuild - rebuild using a saved config
+ * @pf: board private structure
+ * @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
+ **/
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u8 set_fc_aq_fail = 0;
+	i40e_status ret;
+	u32 val;
+	int v;
 
-	if (test_bit(__I40E_DOWN, &pf->state))
+	if (test_bit(__I40E_VSI_DOWN, pf->state))
 		goto clear_recovery;
 	dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -7066,7 +7016,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	}
 
 	/* re-verify the eeprom if we just had an EMP reset */
-	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state))
+	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
 		i40e_verify_eeprom(pf);
 
 	i40e_clear_pxe_mode(hw);
@@ -7075,8 +7025,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		goto end_core_reset;
 
 	ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret);
 		goto end_core_reset;
@@ -7095,14 +7044,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif
 	/* do basic switch setup */
+	if (!lock_acquired)
+		rtnl_lock();
 	ret = i40e_setup_pf_switch(pf, reinit);
 	if (ret)
-		goto end_core_reset;
+		goto end_unlock;
 
 	/* The driver only wants link up/down and module qualification
 	 * reports from firmware.  Note the negative logic.
@@ -7173,7 +7120,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "rebuild of Main VSI failed: %d\n", ret);
-			goto end_core_reset;
+			goto end_unlock;
 		}
 	}
 
@@ -7216,18 +7163,45 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	/* restart the VSIs that were rebuilt and running before the reset */
 	i40e_pf_unquiesce_all_vsi(pf);
 
-	if (pf->num_alloc_vfs) {
-		for (v = 0; v < pf->num_alloc_vfs; v++)
-			i40e_reset_vf(&pf->vf[v], true);
-	}
+	/* Release the RTNL lock before we start resetting VFs */
+	if (!lock_acquired)
+		rtnl_unlock();
+
+	i40e_reset_all_vfs(pf, true);
 
 	/* tell the firmware that we're starting */
 	i40e_send_version(pf);
 
+	/* We've already released the lock, so don't do it again */
+	goto end_core_reset;
+
+end_unlock:
+	if (!lock_acquired)
+		rtnl_unlock();
 end_core_reset:
-	clear_bit(__I40E_RESET_FAILED, &pf->state);
+	clear_bit(__I40E_RESET_FAILED, pf->state);
 clear_recovery:
-	clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+	clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+}
+
+/**
+ * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * @pf: board private structure
+ * @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
+ **/
+static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
+				   bool lock_acquired)
+{
+	int ret;
+	/* Now we wait for GRST to settle out.
+	 * We don't have to delete the VEBs or VSIs from the hw switch
+	 * because the reset will make them disappear.
+	 */
+	ret = i40e_reset(pf);
+	if (!ret)
+		i40e_rebuild(pf, reinit, lock_acquired);
 }
 
 /**
@@ -7236,11 +7210,13 @@ clear_recovery:
  *
  * Close up the VFs and other things in prep for a Core Reset,
  * then get ready to rebuild the world.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
  **/
-static void i40e_handle_reset_warning(struct i40e_pf *pf)
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
 {
-	i40e_prep_for_reset(pf);
-	i40e_reset_and_rebuild(pf, false);
+	i40e_prep_for_reset(pf, lock_acquired);
+	i40e_reset_and_rebuild(pf, false, lock_acquired);
 }
 
 /**
@@ -7258,7 +7234,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__I40E_MDD_EVENT_PENDING, &pf->state))
+	if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state))
 		return;
 
 	/* find what triggered the MDD event */
@@ -7310,7 +7286,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 		}
 		/* Queue belongs to the PF, initiate a reset */
 		if (pf_mdd_detected) {
-			set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
 			i40e_service_event_schedule(pf);
 		}
 	}
@@ -7339,12 +7315,12 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 				 "Too many MDD events on VF %d, disabled\n", i);
 			dev_info(&pf->pdev->dev,
 				 "Use PF Control I/F to re-enable the VF\n");
-			set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states);
+			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		}
 	}
 
 	/* re-enable mdd interrupt cause */
-	clear_bit(__I40E_MDD_EVENT_PENDING, &pf->state);
+	clear_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |=  I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
@@ -7352,6 +7328,23 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters
+ * @pf: board private structure
+ **/
+static void i40e_sync_udp_filters(struct i40e_pf *pf)
+{
+	int i;
+
+	/* loop through and set pending bit for all active UDP filters */
+	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
+		if (pf->udp_ports[i].port)
+			pf->pending_udp_bitmap |= BIT_ULL(i);
+	}
+
+	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
+}
+
+/**
  * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW
  * @pf: board private structure
  **/
@@ -7359,7 +7352,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
-	__be16 port;
+	u16 port;
 	int i;
 
 	if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC))
@@ -7370,7 +7363,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
 		if (pf->pending_udp_bitmap & BIT_ULL(i)) {
 			pf->pending_udp_bitmap &= ~BIT_ULL(i);
-			port = pf->udp_ports[i].index;
+			port = pf->udp_ports[i].port;
 			if (port)
 				ret = i40e_aq_add_udp_tunnel(hw, port,
 							pf->udp_ports[i].type,
@@ -7383,11 +7376,11 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 					"%s %s port %d, index %d failed, err %s aq_err %s\n",
 					pf->udp_ports[i].type ? "vxlan" : "geneve",
 					port ? "add" : "delete",
-					ntohs(port), i,
+					port, i,
 					i40e_stat_str(&pf->hw, ret),
 					i40e_aq_str(&pf->hw,
 						    pf->hw.aq.asq_last_status));
-				pf->udp_ports[i].index = 0;
+				pf->udp_ports[i].port = 0;
 			}
 		}
 	}
@@ -7405,11 +7398,10 @@ static void i40e_service_task(struct work_struct *work)
 	unsigned long start_time = jiffies;
 
 	/* don't bother with service tasks if a reset is in progress */
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
 		return;
-	}
 
-	if (test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
+	if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
 		return;
 
 	i40e_detect_recover_hung(pf);
@@ -7419,23 +7411,34 @@ static void i40e_service_task(struct work_struct *work)
 	i40e_vc_process_vflr_event(pf);
 	i40e_watchdog_subtask(pf);
 	i40e_fdir_reinit_subtask(pf);
-	i40e_client_subtask(pf);
+	if (pf->flags & I40E_FLAG_CLIENT_RESET) {
+		/* Client subtask will reopen next time through. */
+		i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+		pf->flags &= ~I40E_FLAG_CLIENT_RESET;
+	} else {
+		i40e_client_subtask(pf);
+		if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) {
+			i40e_notify_client_of_l2_param_changes(
+							pf->vsi[pf->lan_vsi]);
+			pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE;
+		}
+	}
 	i40e_sync_filters_subtask(pf);
 	i40e_sync_udp_filters_subtask(pf);
 	i40e_clean_adminq_subtask(pf);
 
 	/* flush memory to make sure state is correct before next watchdog */
 	smp_mb__before_atomic();
-	clear_bit(__I40E_SERVICE_SCHED, &pf->state);
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
 
 	/* If the tasks have taken longer than one timer cycle or there
 	 * is more work to be done, reschedule the service task now
 	 * rather than wait for the timer to tick again.
 	 */
 	if (time_after(jiffies, (start_time + pf->service_timer_period)) ||
-	    test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state)		 ||
-	    test_bit(__I40E_MDD_EVENT_PENDING, &pf->state)		 ||
-	    test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state))
+	    test_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state)		 ||
+	    test_bit(__I40E_MDD_EVENT_PENDING, pf->state)		 ||
+	    test_bit(__I40E_VFLR_EVENT_PENDING, pf->state))
 		i40e_service_event_schedule(pf);
 }
 
@@ -7492,15 +7495,6 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 				      I40E_REQ_DESCRIPTOR_MULTIPLE);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		vsi->alloc_queue_pairs = pf->num_fcoe_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
-		vsi->num_q_vectors = pf->num_fcoe_msix;
-		break;
-
-#endif /* I40E_FCOE */
 	default:
 		WARN_ON(1);
 		return -ENODATA;
@@ -7593,7 +7587,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	}
 	vsi->type = type;
 	vsi->back = pf;
-	set_bit(__I40E_DOWN, &vsi->state);
+	set_bit(__I40E_VSI_DOWN, vsi->state);
 	vsi->flags = 0;
 	vsi->idx = vsi_idx;
 	vsi->int_rate_limit = 0;
@@ -7817,6 +7811,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
 static int i40e_init_msix(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
+	int cpus, extra_vectors;
 	int vectors_left;
 	int v_budget, i;
 	int v_actual;
@@ -7835,9 +7830,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	 *	- assumes symmetric Tx/Rx pairing
 	 *   - The number of VMDq pairs
 	 *   - The CPU count within the NUMA node if iWARP is enabled
-#ifdef I40E_FCOE
-	 *   - The number of FCOE qps.
-#endif
 	 * Once we count this up, try the request.
 	 *
 	 * If we can't get what we want, we'll simplify to nearly nothing
@@ -7852,10 +7844,16 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		vectors_left--;
 	}
 
-	/* reserve vectors for the main PF traffic queues */
-	pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left);
+	/* reserve some vectors for the main PF traffic queues. Initially we
+	 * only reserve at most 50% of the available vectors, in the case that
+	 * the number of online CPUs is large. This ensures that we can enable
+	 * extra features as well. Once we've enabled the other features, we
+	 * will use any remaining vectors to reach as close as we can to the
+	 * number of online CPUs.
+	 */
+	cpus = num_online_cpus();
+	pf->num_lan_msix = min_t(int, cpus, vectors_left / 2);
 	vectors_left -= pf->num_lan_msix;
-	v_budget += pf->num_lan_msix;
 
 	/* reserve one vector for sideband flow director */
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -7868,20 +7866,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
-#ifdef I40E_FCOE
-	/* can we reserve enough for FCoE? */
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (!vectors_left)
-			pf->num_fcoe_msix = 0;
-		else if (vectors_left >= pf->num_fcoe_qps)
-			pf->num_fcoe_msix = pf->num_fcoe_qps;
-		else
-			pf->num_fcoe_msix = 1;
-		v_budget += pf->num_fcoe_msix;
-		vectors_left -= pf->num_fcoe_msix;
-	}
-
-#endif
 	/* can we reserve enough for iWARP? */
 	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
 		iwarp_requested = pf->num_iwarp_msix;
@@ -7918,6 +7902,23 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
+	/* On systems with a large number of SMP cores, we previously limited
+	 * the number of vectors for num_lan_msix to be at most 50% of the
+	 * available vectors, to allow for other features. Now, we add back
+	 * the remaining vectors. However, we ensure that the total
+	 * num_lan_msix will not exceed num_online_cpus(). To do this, we
+	 * calculate the number of vectors we can add without going over the
+	 * cap of CPUs. For systems with a small number of CPUs this will be
+	 * zero.
+	 */
+	extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left);
+	pf->num_lan_msix += extra_vectors;
+	vectors_left -= extra_vectors;
+
+	WARN(vectors_left < 0,
+	     "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n");
+
+	v_budget += pf->num_lan_msix;
 	pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
 				   GFP_KERNEL);
 	if (!pf->msix_entries)
@@ -7958,10 +7959,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		pf->num_vmdq_msix = 1;    /* force VMDqs to only one vector */
 		pf->num_vmdq_vsis = 1;
 		pf->num_vmdq_qps = 1;
-#ifdef I40E_FCOE
-		pf->num_fcoe_qps = 0;
-		pf->num_fcoe_msix = 0;
-#endif
 
 		/* partition out the remaining vectors */
 		switch (vec) {
@@ -7975,13 +7972,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			} else {
 				pf->num_lan_msix = 2;
 			}
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_lan_msix = 1;
-				pf->num_fcoe_msix = 1;
-			}
-#endif
 			break;
 		default:
 			if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
@@ -8001,13 +7991,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			       (vec - (pf->num_iwarp_msix + pf->num_vmdq_vsis)),
 							      pf->num_lan_msix);
 			pf->num_lan_qps = pf->num_lan_msix;
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_fcoe_msix = 1;
-				vec--;
-			}
-#endif
 			break;
 		}
 	}
@@ -8028,13 +8011,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n");
 		pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
 	}
-#ifdef I40E_FCOE
-
-	if ((pf->flags & I40E_FLAG_FCOE_ENABLED) && (pf->num_fcoe_msix == 0)) {
-		dev_info(&pf->pdev->dev, "FCOE disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-	}
-#endif
 	i40e_debug(&pf->hw, I40E_DEBUG_INIT,
 		   "MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n",
 		   pf->num_lan_msix,
@@ -8133,9 +8109,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 		if (vectors < 0) {
 			pf->flags &= ~(I40E_FLAG_MSIX_ENABLED	|
 				       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-				       I40E_FLAG_FCOE_ENABLED	|
-#endif
 				       I40E_FLAG_RSS_ENABLED	|
 				       I40E_FLAG_DCB_CAPABLE	|
 				       I40E_FLAG_DCB_ENABLED	|
@@ -8196,7 +8169,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 	/* Only request the irq if this is the first time through, and
 	 * not when we're rebuilding after a Reset
 	 */
-	if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
+	if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) {
 		err = request_irq(pf->msix_entries[0].vector,
 				  i40e_intr, 0, pf->int_name, pf);
 		if (err) {
@@ -8368,13 +8341,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 
 		if (vsi->type == I40E_VSI_MAIN) {
 			for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i),
-						  seed_dw[i]);
+				wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
 		} else if (vsi->type == I40E_VSI_SRIOV) {
 			for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HKEY1(i, vf_id),
-						  seed_dw[i]);
+				wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n");
 		}
@@ -8392,9 +8362,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 			if (lut_size != I40E_VF_HLUT_ARRAY_SIZE)
 				return -EINVAL;
 			for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HLUT1(i, vf_id),
-						  lut_dw[i]);
+				wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n");
 		}
@@ -8522,9 +8490,12 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val);
 
 	/* Determine the RSS size of the VSI */
-	if (!vsi->rss_size)
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+	if (!vsi->rss_size) {
+		u16 qcount;
+
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
+	}
 	if (!vsi->rss_size)
 		return -EINVAL;
 
@@ -8558,6 +8529,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
  *
  * returns 0 if rss is not enabled, if enabled returns the final rss queue
  * count which may be different from the requested queue count.
+ * Note: expects to be called while under rtnl_lock()
  **/
 int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 {
@@ -8570,12 +8542,14 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	new_rss_size = min_t(int, queue_count, pf->rss_size_max);
 
 	if (queue_count != vsi->num_queue_pairs) {
+		u16 qcount;
+
 		vsi->req_queue_pairs = queue_count;
-		i40e_prep_for_reset(pf);
+		i40e_prep_for_reset(pf, true);
 
 		pf->alloc_rss_size = new_rss_size;
 
-		i40e_reset_and_rebuild(pf, true);
+		i40e_reset_and_rebuild(pf, true, true);
 
 		/* Discard the user configured hash keys and lut, if less
 		 * queues are enabled.
@@ -8587,8 +8561,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 		}
 
 		/* Reset vsi->rss_size, as number of enabled queues changed */
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
 
 		i40e_pf_config_rss(pf);
 	}
@@ -8821,10 +8795,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
 
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif /* I40E_FCOE */
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
 		pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
@@ -8851,9 +8821,9 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    (pf->hw.aq.api_min_ver > 4))) {
 		/* Supported in FW API version higher than 1.4 */
 		pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	} else {
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	}
 
 	pf->eeprom_version = 0xDEAD;
@@ -8913,16 +8883,16 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 			need_reset = true;
 			i40e_fdir_filter_exit(pf);
 		}
-		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-		pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED |
+			       I40E_FLAG_FD_SB_AUTO_DISABLED);
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
-		pf->fdir_pf_active_filters = 0;
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		/* 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)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+		if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) {
+			pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED;
+			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+			    (I40E_DEBUG_FD & pf->hw.debug_mask))
 				dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		}
 	}
@@ -8955,6 +8925,7 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi)
  * i40e_set_features - set the netdev feature flags
  * @netdev: ptr to the netdev being adjusted
  * @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
  **/
 static int i40e_set_features(struct net_device *netdev,
 			     netdev_features_t features)
@@ -8978,7 +8949,7 @@ static int i40e_set_features(struct net_device *netdev,
 	need_reset = i40e_set_ntuple(pf, features);
 
 	if (need_reset)
-		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
 
 	return 0;
 }
@@ -8990,12 +8961,12 @@ static int i40e_set_features(struct net_device *netdev,
  *
  * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
  **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port)
+static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
 {
 	u8 i;
 
 	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->udp_ports[i].index == port)
+		if (pf->udp_ports[i].port == port)
 			return i;
 	}
 
@@ -9013,7 +8984,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 next_idx;
 	u8 idx;
 
@@ -9021,8 +8992,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	/* Check if port already exists */
 	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "port %d already offloaded\n",
-			    ntohs(port));
+		netdev_info(netdev, "port %d already offloaded\n", port);
 		return;
 	}
 
@@ -9031,7 +9001,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
 		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
-			    ntohs(port));
+			    port);
 		return;
 	}
 
@@ -9049,7 +9019,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 	}
 
 	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].index = port;
+	pf->udp_ports[next_idx].port = port;
 	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 }
@@ -9065,7 +9035,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 idx;
 
 	idx = i40e_get_udp_port_idx(pf, port);
@@ -9090,14 +9060,14 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	/* if port exists, set it to 0 (mark for deletion)
 	 * and make it pending
 	 */
-	pf->udp_ports[idx].index = 0;
+	pf->udp_ports[idx].port = 0;
 	pf->pending_udp_bitmap |= BIT_ULL(idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 
 	return;
 not_found:
 	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
-		    ntohs(port));
+		    port);
 }
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -9174,6 +9144,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  * is to change the mode then that requires a PF reset to
  * allow rebuild of the components with required hardware
  * bridge mode enabled.
+ *
+ * Note: expects to be called while under rtnl_lock()
  **/
 static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				   struct nlmsghdr *nlh,
@@ -9229,7 +9201,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 			else
 				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED),
+				      true);
 			break;
 		}
 	}
@@ -9352,10 +9325,6 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_poll_controller	= i40e_netpoll,
 #endif
 	.ndo_setup_tc		= __i40e_setup_tc,
-#ifdef I40E_FCOE
-	.ndo_fcoe_enable	= i40e_fcoe_enable,
-	.ndo_fcoe_disable	= i40e_fcoe_disable,
-#endif
 	.ndo_set_features	= i40e_set_features,
 	.ndo_set_vf_mac		= i40e_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= i40e_ndo_set_vf_port_vlan,
@@ -9388,6 +9357,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	u8 broadcast[ETH_ALEN];
 	u8 mac_addr[ETH_ALEN];
 	int etherdev_size;
+	netdev_features_t hw_enc_features;
+	netdev_features_t hw_features;
 
 	etherdev_size = sizeof(struct i40e_netdev_priv);
 	netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs);
@@ -9398,52 +9369,57 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	np = netdev_priv(netdev);
 	np->vsi = vsi;
 
-	netdev->hw_enc_features |= NETIF_F_SG			|
-				   NETIF_F_IP_CSUM		|
-				   NETIF_F_IPV6_CSUM		|
-				   NETIF_F_HIGHDMA		|
-				   NETIF_F_SOFT_FEATURES	|
-				   NETIF_F_TSO			|
-				   NETIF_F_TSO_ECN		|
-				   NETIF_F_TSO6			|
-				   NETIF_F_GSO_GRE		|
-				   NETIF_F_GSO_GRE_CSUM		|
-				   NETIF_F_GSO_IPXIP4		|
-				   NETIF_F_GSO_IPXIP6		|
-				   NETIF_F_GSO_UDP_TUNNEL	|
-				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-				   NETIF_F_GSO_PARTIAL		|
-				   NETIF_F_SCTP_CRC		|
-				   NETIF_F_RXHASH		|
-				   NETIF_F_RXCSUM		|
-				   0;
+	hw_enc_features = NETIF_F_SG			|
+			  NETIF_F_IP_CSUM		|
+			  NETIF_F_IPV6_CSUM		|
+			  NETIF_F_HIGHDMA		|
+			  NETIF_F_SOFT_FEATURES		|
+			  NETIF_F_TSO			|
+			  NETIF_F_TSO_ECN		|
+			  NETIF_F_TSO6			|
+			  NETIF_F_GSO_GRE		|
+			  NETIF_F_GSO_GRE_CSUM		|
+			  NETIF_F_GSO_PARTIAL		|
+			  NETIF_F_GSO_UDP_TUNNEL	|
+			  NETIF_F_GSO_UDP_TUNNEL_CSUM	|
+			  NETIF_F_SCTP_CRC		|
+			  NETIF_F_RXHASH		|
+			  NETIF_F_RXCSUM		|
+			  0;
 
 	if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE))
 		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
+	netdev->hw_enc_features |= hw_enc_features;
+
 	/* record features VLANs can make use of */
-	netdev->vlan_features |= netdev->hw_enc_features |
-				 NETIF_F_TSO_MANGLEID;
+	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
 		netdev->hw_features |= NETIF_F_NTUPLE;
+	hw_features = hw_enc_features		|
+		      NETIF_F_HW_VLAN_CTAG_TX	|
+		      NETIF_F_HW_VLAN_CTAG_RX;
 
-	netdev->hw_features |= netdev->hw_enc_features	|
-			       NETIF_F_HW_VLAN_CTAG_TX	|
-			       NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features |= hw_features;
 
-	netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
 
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
 		ether_addr_copy(mac_addr, hw->mac.perm_addr);
-		/* The following steps are necessary to prevent reception
-		 * of tagged packets - some older NVM configurations load a
-		 * default a MAC-VLAN filter that accepts any tagged packet
-		 * which must be replaced by a normal filter.
+		/* The following steps are necessary for two reasons. First,
+		 * some older NVM configurations load a default MAC-VLAN
+		 * filter that will accept any tagged packet, and we want to
+		 * replace this with a normal filter. Additionally, it is
+		 * possible our MAC address was provided by the platform using
+		 * Open Firmware or similar.
+		 *
+		 * Thus, we need to remove the default filter and install one
+		 * specific to the MAC address.
 		 */
 		i40e_rm_default_mac_filter(vsi, mac_addr);
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -9489,9 +9465,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	netdev->netdev_ops = &i40e_netdev_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 	i40e_set_ethtool_ops(netdev);
-#ifdef I40E_FCOE
-	i40e_fcoe_config_netdev(netdev, vsi);
-#endif
 
 	/* MTU range: 68 - 9706 */
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -9715,16 +9688,6 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		ret = i40e_fcoe_vsi_init(vsi, &ctxt);
-		if (ret) {
-			dev_info(&pf->pdev->dev, "failed to initialize FCoE VSI\n");
-			return ret;
-		}
-		break;
-
-#endif /* I40E_FCOE */
 	case I40E_VSI_IWARP:
 		/* send down message to iWARP */
 		break;
@@ -9751,7 +9714,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 	}
 
 	vsi->active_filters = 0;
-	clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+	clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 	/* If macvlan filters already exist, force them to get loaded */
 	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
@@ -9804,7 +9767,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		return -ENODEV;
 	}
 	if (vsi == pf->vsi[pf->lan_vsi] &&
-	    !test_bit(__I40E_DOWN, &pf->state)) {
+	    !test_bit(__I40E_VSI_DOWN, pf->state)) {
 		dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
 		return -ENODEV;
 	}
@@ -10141,7 +10104,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 			}
 		}
 	case I40E_VSI_VMDQ2:
-	case I40E_VSI_FCOE:
 		ret = i40e_config_netdev(vsi);
 		if (ret)
 			goto err_netdev;
@@ -10789,6 +10751,9 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 
 	i40e_ptp_init(pf);
 
+	/* repopulate tunnel port filters */
+	i40e_sync_udp_filters(pf);
+
 	return ret;
 }
 
@@ -10801,9 +10766,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	int queues_left;
 
 	pf->num_lan_qps = 0;
-#ifdef I40E_FCOE
-	pf->num_fcoe_qps = 0;
-#endif
 
 	/* Find the max queues to be put into basic use.  We'll always be
 	 * using TC0, whether or not DCB is running, and TC0 will get the
@@ -10820,9 +10782,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		/* make sure all the fancies are disabled */
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_CAPABLE	|
@@ -10839,9 +10798,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_ENABLED	|
@@ -10862,22 +10818,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		queues_left -= pf->num_lan_qps;
 	}
 
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (I40E_DEFAULT_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_DEFAULT_FCOE;
-		} else if (I40E_MINIMUM_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_MINIMUM_FCOE;
-		} else {
-			pf->num_fcoe_qps = 0;
-			pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-			dev_info(&pf->pdev->dev, "not enough queues for FCoE. FCoE feature will be disabled\n");
-		}
-
-		queues_left -= pf->num_fcoe_qps;
-	}
-
-#endif
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
 		if (queues_left > 1) {
 			queues_left -= 1; /* save 1 queue for FD */
@@ -10909,9 +10849,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs,
 		pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps,
 		queues_left);
-#ifdef I40E_FCOE
-	dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
-#endif
 }
 
 /**
@@ -10978,10 +10915,6 @@ static void i40e_print_features(struct i40e_pf *pf)
 	i += snprintf(&buf[i], REMAIN(i), " Geneve");
 	if (pf->flags & I40E_FLAG_PTP)
 		i += snprintf(&buf[i], REMAIN(i), " PTP");
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " FCOE");
-#endif
 	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
 		i += snprintf(&buf[i], REMAIN(i), " VEB");
 	else
@@ -10994,20 +10927,18 @@ static void i40e_print_features(struct i40e_pf *pf)
 
 /**
  * i40e_get_platform_mac_addr - get platform-specific MAC address
- *
  * @pdev: PCI device information struct
  * @pf: board private structure
  *
- * Look up the MAC address in Open Firmware  on systems that support it,
- * and use IDPROM on SPARC if no OF address is found. On return, the
- * I40E_FLAG_PF_MAC will be wset in pf->flags if a platform-specific value
- * has been selected.
+ * Look up the MAC address for the device. First we'll try
+ * eth_platform_get_mac_address, which will check Open Firmware, or arch
+ * specific fallback. Otherwise, we'll default to the stored value in
+ * firmware.
  **/
 static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 {
-	pf->flags &= ~I40E_FLAG_PF_MAC;
-	if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
-		pf->flags |= I40E_FLAG_PF_MAC;
+	if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
+		i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr);
 }
 
 /**
@@ -11072,7 +11003,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	pf->next_vsi = 0;
 	pf->pdev = pdev;
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 
 	hw = &pf->hw;
 	hw->back = pf;
@@ -11098,6 +11029,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.bus_id = pdev->bus->number;
 	pf->instance = pfs_found;
 
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
 	 */
@@ -11196,8 +11130,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (err) {
 		dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err);
 		goto err_init_lan_hmc;
@@ -11219,9 +11152,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		i40e_aq_stop_lldp(hw, true, NULL);
 	}
 
-	i40e_get_mac_addr(hw, hw->mac.addr);
 	/* allow a platform config to override the HW addr */
 	i40e_get_platform_mac_addr(pdev, pf);
+
 	if (!is_valid_ether_addr(hw->mac.addr)) {
 		dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr);
 		err = -EIO;
@@ -11232,18 +11165,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i40e_get_port_mac_addr(hw, hw->mac.port_addr);
 	if (is_valid_ether_addr(hw->mac.port_addr))
 		pf->flags |= I40E_FLAG_PORT_ID_VALID;
-#ifdef I40E_FCOE
-	err = i40e_get_san_mac_addr(hw, hw->mac.san_addr);
-	if (err)
-		dev_info(&pdev->dev,
-			 "(non-fatal) SAN MAC retrieval failed: %d\n", err);
-	if (!is_valid_ether_addr(hw->mac.san_addr)) {
-		dev_warn(&pdev->dev, "invalid SAN MAC address %pM, falling back to LAN MAC\n",
-			 hw->mac.san_addr);
-		ether_addr_copy(hw->mac.san_addr, hw->mac.addr);
-	}
-	dev_info(&pf->pdev->dev, "SAN MAC: %pM\n", hw->mac.san_addr);
-#endif /* I40E_FCOE */
 
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
@@ -11261,8 +11182,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pf->service_timer_period = HZ;
 
 	INIT_WORK(&pf->service_task, i40e_service_task);
-	clear_bit(__I40E_SERVICE_SCHED, &pf->state);
-	pf->flags |= I40E_FLAG_NEED_LINK_UPDATE;
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
 
 	/* NVM bit on means WoL disabled for the port */
 	i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits);
@@ -11300,7 +11220,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* prep for VF support */
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
-	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		if (pci_num_vf(pdev))
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 	}
@@ -11373,7 +11293,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * before setting up the misc vector or we get a race and the vector
 	 * ends up disabled forever.
 	 */
-	clear_bit(__I40E_DOWN, &pf->state);
+	clear_bit(__I40E_VSI_DOWN, pf->state);
 
 	/* In case of MSIX we are going to setup the misc vector right here
 	 * to handle admin queue events etc. In case of legacy and MSI
@@ -11393,7 +11313,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* prep for VF support */
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
-	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+	    !test_bit(__I40E_BAD_EEPROM, pf->state)) {
 		/* disable link interrupts for VFs */
 		val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM);
 		val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK;
@@ -11434,16 +11354,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		  round_jiffies(jiffies + pf->service_timer_period));
 
 	/* add this PF to client device list and launch a client service task */
-	err = i40e_lan_add_device(pf);
-	if (err)
-		dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
-			 err);
-
-#ifdef I40E_FCOE
-	/* create FCoE interface */
-	i40e_fcoe_vsi_setup(pf);
+	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+		err = i40e_lan_add_device(pf);
+		if (err)
+			dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
+				 err);
+	}
 
-#endif
 #define PCI_SPEED_SIZE 8
 #define PCI_WIDTH_SIZE 8
 	/* Devices on the IOSF bus do not have this information
@@ -11531,7 +11448,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Unwind what we've done if something failed in the setup */
 err_vsis:
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	i40e_clear_interrupt_scheme(pf);
 	kfree(pf->vsi);
 err_switch_setup:
@@ -11582,13 +11499,18 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
 	/* no more scheduling of any task */
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	if (pf->service_timer.data)
 		del_timer_sync(&pf->service_timer);
 	if (pf->service_task.func)
 		cancel_work_sync(&pf->service_task);
 
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
 	if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
 		i40e_free_vfs(pf);
 		pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
@@ -11615,10 +11537,11 @@ static void i40e_remove(struct pci_dev *pdev)
 		i40e_vsi_release(pf->vsi[pf->lan_vsi]);
 
 	/* remove attached clients */
-	ret_code = i40e_lan_del_device(pf);
-	if (ret_code) {
-		dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
-			 ret_code);
+	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+		ret_code = i40e_lan_del_device(pf);
+		if (ret_code)
+			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+				 ret_code);
 	}
 
 	/* shutdown and destroy the HMC */
@@ -11685,9 +11608,9 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 	}
 
 	/* shutdown all operations */
-	if (!test_bit(__I40E_SUSPENDED, &pf->state)) {
+	if (!test_bit(__I40E_SUSPENDED, pf->state)) {
 		rtnl_lock();
-		i40e_prep_for_reset(pf);
+		i40e_prep_for_reset(pf, true);
 		rtnl_unlock();
 	}
 
@@ -11752,11 +11675,11 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
-	if (test_bit(__I40E_SUSPENDED, &pf->state))
+	if (test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
 	rtnl_lock();
-	i40e_handle_reset_warning(pf);
+	i40e_handle_reset_warning(pf, true);
 	rtnl_unlock();
 }
 
@@ -11816,10 +11739,10 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
 
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->state);
 	rtnl_lock();
-	i40e_prep_for_reset(pf);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11829,11 +11752,16 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	cancel_work_sync(&pf->service_task);
 	i40e_fdir_teardown(pf);
 
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
 	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);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM,
@@ -11860,14 +11788,14 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct i40e_hw *hw = &pf->hw;
 	int retval = 0;
 
-	set_bit(__I40E_SUSPENDED, &pf->state);
-	set_bit(__I40E_DOWN, &pf->state);
+	set_bit(__I40E_SUSPENDED, pf->state);
+	set_bit(__I40E_VSI_DOWN, pf->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);
+	i40e_prep_for_reset(pf, true);
 	rtnl_unlock();
 
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11912,10 +11840,10 @@ static int i40e_resume(struct pci_dev *pdev)
 	pci_wake_from_d3(pdev, false);
 
 	/* handling the reset will rebuild the device state */
-	if (test_and_clear_bit(__I40E_SUSPENDED, &pf->state)) {
-		clear_bit(__I40E_DOWN, &pf->state);
+	if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
+		clear_bit(__I40E_VSI_DOWN, pf->state);
 		rtnl_lock();
-		i40e_reset_and_rebuild(pf, false);
+		i40e_reset_and_rebuild(pf, false, true);
 		rtnl_unlock();
 	}