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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 555 insertions, 269 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 47cc3f905b7f..7843abf4d44d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -7,8 +7,9 @@
 
 #include "ice.h"
 #include "ice_lib.h"
+#include "ice_dcb_lib.h"
 
-#define DRV_VERSION	"0.7.2-k"
+#define DRV_VERSION	"0.7.4-k"
 #define DRV_SUMMARY	"Intel(R) Ethernet Connection E800 Series Linux Driver"
 const char ice_drv_ver[] = DRV_VERSION;
 static const char ice_driver_string[] = DRV_SUMMARY;
@@ -30,7 +31,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 static struct workqueue_struct *ice_wq;
 static const struct net_device_ops ice_netdev_ops;
 
-static void ice_pf_dis_all_vsi(struct ice_pf *pf);
 static void ice_rebuild(struct ice_pf *pf);
 
 static void ice_vsi_release_all(struct ice_pf *pf);
@@ -113,14 +113,14 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 }
 
 /**
- * ice_add_mac_to_sync_list - creates list of mac addresses to be synced
+ * ice_add_mac_to_sync_list - creates list of MAC addresses to be synced
  * @netdev: the net device on which the sync is happening
- * @addr: mac address to sync
+ * @addr: MAC address to sync
  *
  * This is a callback function which is called by the in kernel device sync
  * functions (like __dev_uc_sync, __dev_mc_sync, etc). This function only
  * populates the tmp_sync_list, which is later used by ice_add_mac to add the
- * mac filters from the hardware.
+ * MAC filters from the hardware.
  */
 static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
 {
@@ -134,14 +134,14 @@ static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
 }
 
 /**
- * ice_add_mac_to_unsync_list - creates list of mac addresses to be unsynced
+ * ice_add_mac_to_unsync_list - creates list of MAC addresses to be unsynced
  * @netdev: the net device on which the unsync is happening
- * @addr: mac address to unsync
+ * @addr: MAC address to unsync
  *
  * This is a callback function which is called by the in kernel device unsync
  * functions (like __dev_uc_unsync, __dev_mc_unsync, etc). This function only
  * populates the tmp_unsync_list, which is later used by ice_remove_mac to
- * delete the mac filters from the hardware.
+ * delete the MAC filters from the hardware.
  */
 static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
 {
@@ -168,6 +168,39 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_cfg_promisc - Enable or disable promiscuous mode for a given PF
+ * @vsi: the VSI being configured
+ * @promisc_m: mask of promiscuous config bits
+ * @set_promisc: enable or disable promisc flag request
+ *
+ */
+static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	enum ice_status status = 0;
+
+	if (vsi->type != ICE_VSI_PF)
+		return 0;
+
+	if (vsi->vlan_ena) {
+		status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
+						  set_promisc);
+	} else {
+		if (set_promisc)
+			status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+						     0);
+		else
+			status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+						       0);
+	}
+
+	if (status)
+		return -EIO;
+
+	return 0;
+}
+
+/**
  * ice_vsi_sync_fltr - Update the VSI filter list to the HW
  * @vsi: ptr to the VSI
  *
@@ -182,6 +215,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status status = 0;
 	u32 changed_flags = 0;
+	u8 promisc_m;
 	int err = 0;
 
 	if (!vsi->netdev)
@@ -211,7 +245,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		netif_addr_unlock_bh(netdev);
 	}
 
-	/* Remove mac addresses in the unsync list */
+	/* Remove MAC addresses in the unsync list */
 	status = ice_remove_mac(hw, &vsi->tmp_unsync_list);
 	ice_free_fltr_list(dev, &vsi->tmp_unsync_list);
 	if (status) {
@@ -223,12 +257,16 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		}
 	}
 
-	/* Add mac addresses in the sync list */
+	/* Add MAC addresses in the sync list */
 	status = ice_add_mac(hw, &vsi->tmp_sync_list);
 	ice_free_fltr_list(dev, &vsi->tmp_sync_list);
-	if (status) {
+	/* If filter is added successfully or already exists, do not go into
+	 * 'if' condition and report it as error. Instead continue processing
+	 * rest of the function.
+	 */
+	if (status && status != ICE_ERR_ALREADY_EXISTS) {
 		netdev_err(netdev, "Failed to add MAC filters\n");
-		/* If there is no more space for new umac filters, vsi
+		/* If there is no more space for new umac filters, VSI
 		 * should go into promiscuous mode. There should be some
 		 * space reserved for promiscuous filters.
 		 */
@@ -245,49 +283,56 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		}
 	}
 	/* check for changes in promiscuous modes */
-	if (changed_flags & IFF_ALLMULTI)
-		netdev_warn(netdev, "Unsupported configuration\n");
+	if (changed_flags & IFF_ALLMULTI) {
+		if (vsi->current_netdev_flags & IFF_ALLMULTI) {
+			if (vsi->vlan_ena)
+				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_MCAST_PROMISC_BITS;
+
+			err = ice_cfg_promisc(vsi, promisc_m, true);
+			if (err) {
+				netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n",
+					   vsi->vsi_num);
+				vsi->current_netdev_flags &= ~IFF_ALLMULTI;
+				goto out_promisc;
+			}
+		} else if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) {
+			if (vsi->vlan_ena)
+				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_MCAST_PROMISC_BITS;
+
+			err = ice_cfg_promisc(vsi, promisc_m, false);
+			if (err) {
+				netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n",
+					   vsi->vsi_num);
+				vsi->current_netdev_flags |= IFF_ALLMULTI;
+				goto out_promisc;
+			}
+		}
+	}
 
 	if (((changed_flags & IFF_PROMISC) || promisc_forced_on) ||
 	    test_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags)) {
 		clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
 		if (vsi->current_netdev_flags & IFF_PROMISC) {
-			/* Apply TX filter rule to get traffic from VMs */
-			status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
-						  ICE_FLTR_TX);
-			if (status) {
-				netdev_err(netdev, "Error setting default VSI %i tx rule\n",
-					   vsi->vsi_num);
-				vsi->current_netdev_flags &= ~IFF_PROMISC;
-				err = -EIO;
-				goto out_promisc;
-			}
-			/* Apply RX filter rule to get traffic from wire */
+			/* Apply Rx filter rule to get traffic from wire */
 			status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
 						  ICE_FLTR_RX);
 			if (status) {
-				netdev_err(netdev, "Error setting default VSI %i rx rule\n",
+				netdev_err(netdev, "Error setting default VSI %i Rx rule\n",
 					   vsi->vsi_num);
 				vsi->current_netdev_flags &= ~IFF_PROMISC;
 				err = -EIO;
 				goto out_promisc;
 			}
 		} else {
-			/* Clear TX filter rule to stop traffic from VMs */
-			status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
-						  ICE_FLTR_TX);
-			if (status) {
-				netdev_err(netdev, "Error clearing default VSI %i tx rule\n",
-					   vsi->vsi_num);
-				vsi->current_netdev_flags |= IFF_PROMISC;
-				err = -EIO;
-				goto out_promisc;
-			}
-			/* Clear RX filter to remove traffic from wire */
+			/* Clear Rx filter to remove traffic from wire */
 			status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
 						  ICE_FLTR_RX);
 			if (status) {
-				netdev_err(netdev, "Error clearing default VSI %i rx rule\n",
+				netdev_err(netdev, "Error clearing default VSI %i Rx rule\n",
 					   vsi->vsi_num);
 				vsi->current_netdev_flags |= IFF_PROMISC;
 				err = -EIO;
@@ -322,7 +367,7 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
 
 	clear_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
 
-	for (v = 0; v < pf->num_alloc_vsi; v++)
+	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v] && ice_vsi_fltr_changed(pf->vsi[v]) &&
 		    ice_vsi_sync_fltr(pf->vsi[v])) {
 			/* come back and try again later */
@@ -332,6 +377,51 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
 }
 
 /**
+ * ice_dis_vsi - pause a VSI
+ * @vsi: the VSI being paused
+ * @locked: is the rtnl_lock already held
+ */
+static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+{
+	if (test_bit(__ICE_DOWN, vsi->state))
+		return;
+
+	set_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
+		if (netif_running(vsi->netdev)) {
+			if (!locked) {
+				rtnl_lock();
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				rtnl_unlock();
+			} else {
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+			}
+		} else {
+			ice_vsi_close(vsi);
+		}
+	}
+}
+
+/**
+ * ice_pf_dis_all_vsi - Pause all VSIs on a PF
+ * @pf: the PF
+ * @locked: is the rtnl_lock already held
+ */
+#ifdef CONFIG_DCB
+void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#else
+static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#endif /* CONFIG_DCB */
+{
+	int v;
+
+	ice_for_each_vsi(pf, v)
+		if (pf->vsi[v])
+			ice_dis_vsi(pf->vsi[v], locked);
+}
+
+/**
  * ice_prepare_for_reset - prep for the core to reset
  * @pf: board private structure
  *
@@ -342,12 +432,16 @@ ice_prepare_for_reset(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 
+	/* already prepared for reset */
+	if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
+		return;
+
 	/* Notify VFs of impending reset */
 	if (ice_check_sq_alive(hw, &hw->mailboxq))
 		ice_vc_notify_reset(pf);
 
 	/* disable the VSIs and their queues that are not already DOWN */
-	ice_pf_dis_all_vsi(pf);
+	ice_pf_dis_all_vsi(pf, false);
 
 	if (hw->port_info)
 		ice_sched_clear_port(hw->port_info);
@@ -394,6 +488,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_rebuild(pf);
 		clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
 		clear_bit(__ICE_PFR_REQ, pf->state);
+		ice_reset_all_vfs(pf, true);
 	}
 }
 
@@ -416,10 +511,15 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	 * for the reset now), poll for reset done, rebuild and return.
 	 */
 	if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) {
-		clear_bit(__ICE_GLOBR_RECV, pf->state);
-		clear_bit(__ICE_CORER_RECV, pf->state);
-		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
-			ice_prepare_for_reset(pf);
+		/* Perform the largest reset requested */
+		if (test_and_clear_bit(__ICE_CORER_RECV, pf->state))
+			reset_type = ICE_RESET_CORER;
+		if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state))
+			reset_type = ICE_RESET_GLOBR;
+		/* return if no valid reset type requested */
+		if (reset_type == ICE_RESET_INVAL)
+			return;
+		ice_prepare_for_reset(pf);
 
 		/* make sure we are ready to rebuild */
 		if (ice_check_reset(&pf->hw)) {
@@ -429,13 +529,14 @@ static void ice_reset_subtask(struct ice_pf *pf)
 			pf->hw.reset_ongoing = false;
 			ice_rebuild(pf);
 			/* clear bit to resume normal operations, but
-			 * ICE_NEEDS_RESTART bit is set incase rebuild failed
+			 * ICE_NEEDS_RESTART bit is set in case rebuild failed
 			 */
 			clear_bit(__ICE_RESET_OICR_RECV, pf->state);
 			clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
 			clear_bit(__ICE_PFR_REQ, pf->state);
 			clear_bit(__ICE_CORER_REQ, pf->state);
 			clear_bit(__ICE_GLOBR_REQ, pf->state);
+			ice_reset_all_vfs(pf, true);
 		}
 
 		return;
@@ -469,6 +570,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	const char *speed;
 	const char *fc;
 
+	if (!vsi)
+		return;
+
 	if (vsi->current_isup == isup)
 		return;
 
@@ -519,6 +623,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	case ICE_FC_RX_PAUSE:
 		fc = "RX";
 		break;
+	case ICE_FC_NONE:
+		fc = "None";
+		break;
 	default:
 		fc = "Unknown";
 		break;
@@ -529,21 +636,22 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 }
 
 /**
- * ice_vsi_link_event - update the vsi's netdev
- * @vsi: the vsi on which the link event occurred
- * @link_up: whether or not the vsi needs to be set up or down
+ * ice_vsi_link_event - update the VSI's netdev
+ * @vsi: the VSI on which the link event occurred
+ * @link_up: whether or not the VSI needs to be set up or down
  */
 static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
 {
-	if (!vsi || test_bit(__ICE_DOWN, vsi->state))
+	if (!vsi)
+		return;
+
+	if (test_bit(__ICE_DOWN, vsi->state) || !vsi->netdev)
 		return;
 
 	if (vsi->type == ICE_VSI_PF) {
-		if (!vsi->netdev) {
-			dev_dbg(&vsi->back->pdev->dev,
-				"vsi->netdev is not initialized!\n");
+		if (link_up == netif_carrier_ok(vsi->netdev))
 			return;
-		}
+
 		if (link_up) {
 			netif_carrier_on(vsi->netdev);
 			netif_tx_wake_all_queues(vsi->netdev);
@@ -558,61 +666,51 @@ static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
  * ice_link_event - process the link event
  * @pf: pf that the link event is associated with
  * @pi: port_info for the port that the link event is associated with
+ * @link_up: true if the physical link is up and false if it is down
+ * @link_speed: current link speed received from the link event
  *
- * Returns -EIO if ice_get_link_status() fails
- * Returns 0 on success
+ * Returns 0 on success and negative on failure
  */
 static int
-ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
+ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
+	       u16 link_speed)
 {
-	u8 new_link_speed, old_link_speed;
 	struct ice_phy_info *phy_info;
-	bool new_link_same_as_old;
-	bool new_link, old_link;
-	u8 lport;
-	u16 v;
+	struct ice_vsi *vsi;
+	u16 old_link_speed;
+	bool old_link;
+	int result;
 
 	phy_info = &pi->phy;
 	phy_info->link_info_old = phy_info->link_info;
-	/* Force ice_get_link_status() to update link info */
-	phy_info->get_link_info = true;
 
-	old_link = (phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
+	old_link = !!(phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
 	old_link_speed = phy_info->link_info_old.link_speed;
 
-	lport = pi->lport;
-	if (ice_get_link_status(pi, &new_link)) {
+	/* update the link info structures and re-enable link events,
+	 * don't bail on failure due to other book keeping needed
+	 */
+	result = ice_update_link_info(pi);
+	if (result)
 		dev_dbg(&pf->pdev->dev,
-			"Could not get link status for port %d\n", lport);
-		return -EIO;
-	}
-
-	new_link_speed = phy_info->link_info.link_speed;
+			"Failed to update link status and re-enable link events for port %d\n",
+			pi->lport);
 
-	new_link_same_as_old = (new_link == old_link &&
-				new_link_speed == old_link_speed);
-
-	ice_for_each_vsi(pf, v) {
-		struct ice_vsi *vsi = pf->vsi[v];
-
-		if (!vsi || !vsi->port_info)
-			continue;
+	/* if the old link up/down and speed is the same as the new */
+	if (link_up == old_link && link_speed == old_link_speed)
+		return result;
 
-		if (new_link_same_as_old &&
-		    (test_bit(__ICE_DOWN, vsi->state) ||
-		    new_link == netif_carrier_ok(vsi->netdev)))
-			continue;
+	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	if (!vsi || !vsi->port_info)
+		return -EINVAL;
 
-		if (vsi->port_info->lport == lport) {
-			ice_print_link_msg(vsi, new_link);
-			ice_vsi_link_event(vsi, new_link);
-		}
-	}
+	ice_vsi_link_event(vsi, link_up);
+	ice_print_link_msg(vsi, link_up);
 
-	if (!new_link_same_as_old && pf->num_alloc_vfs)
+	if (pf->num_alloc_vfs)
 		ice_vc_notify_link_state(pf);
 
-	return 0;
+	return result;
 }
 
 /**
@@ -635,19 +733,73 @@ static void ice_watchdog_subtask(struct ice_pf *pf)
 
 	pf->serv_tmr_prev = jiffies;
 
-	if (ice_link_event(pf, pf->hw.port_info))
-		dev_dbg(&pf->pdev->dev, "ice_link_event failed\n");
-
 	/* Update the stats for active netdevs so the network stack
 	 * can look at updated numbers whenever it cares to
 	 */
 	ice_update_pf_stats(pf);
-	for (i = 0; i < pf->num_alloc_vsi; i++)
+	ice_for_each_vsi(pf, i)
 		if (pf->vsi[i] && pf->vsi[i]->netdev)
 			ice_update_vsi_stats(pf->vsi[i]);
 }
 
 /**
+ * ice_init_link_events - enable/initialize link events
+ * @pi: pointer to the port_info instance
+ *
+ * Returns -EIO on failure, 0 on success
+ */
+static int ice_init_link_events(struct ice_port_info *pi)
+{
+	u16 mask;
+
+	mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA |
+		       ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL));
+
+	if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) {
+		dev_dbg(ice_hw_to_dev(pi->hw),
+			"Failed to set link event mask for port %d\n",
+			pi->lport);
+		return -EIO;
+	}
+
+	if (ice_aq_get_link_info(pi, true, NULL, NULL)) {
+		dev_dbg(ice_hw_to_dev(pi->hw),
+			"Failed to enable link events for port %d\n",
+			pi->lport);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_handle_link_event - handle link event via ARQ
+ * @pf: pf that the link event is associated with
+ * @event: event structure containing link status info
+ */
+static int
+ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	struct ice_aqc_get_link_status_data *link_data;
+	struct ice_port_info *port_info;
+	int status;
+
+	link_data = (struct ice_aqc_get_link_status_data *)event->msg_buf;
+	port_info = pf->hw.port_info;
+	if (!port_info)
+		return -EINVAL;
+
+	status = ice_link_event(pf, port_info,
+				!!(link_data->link_info & ICE_AQ_LINK_UP),
+				le16_to_cpu(link_data->link_speed));
+	if (status)
+		dev_dbg(&pf->pdev->dev,
+			"Could not process link event, error %d\n", status);
+
+	return status;
+}
+
+/**
  * __ice_clean_ctrlq - helper function to clean controlq rings
  * @pf: ptr to struct ice_pf
  * @q_type: specific Control queue type
@@ -750,12 +902,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		opcode = le16_to_cpu(event.desc.opcode);
 
 		switch (opcode) {
+		case ice_aqc_opc_get_link_status:
+			if (ice_handle_link_event(pf, &event))
+				dev_err(&pf->pdev->dev,
+					"Could not handle link event\n");
+			break;
 		case ice_mbx_opc_send_msg_to_pf:
 			ice_vc_process_vf_msg(pf, &event);
 			break;
 		case ice_aqc_opc_fw_logging:
 			ice_output_fw_log(hw, &event.desc, event.msg_buf);
 			break;
+		case ice_aqc_opc_lldp_set_mib_change:
+			ice_dcb_process_lldp_set_mib_change(pf, &event);
+			break;
 		default:
 			dev_dbg(&pf->pdev->dev,
 				"%s Receive Queue unknown event 0x%04x ignored\n",
@@ -877,6 +1037,18 @@ static void ice_service_task_stop(struct ice_pf *pf)
 }
 
 /**
+ * ice_service_task_restart - restart service task and schedule works
+ * @pf: board private structure
+ *
+ * This function is needed for suspend and resume works (e.g WoL scenario)
+ */
+static void ice_service_task_restart(struct ice_pf *pf)
+{
+	clear_bit(__ICE_SERVICE_DIS, pf->state);
+	ice_service_task_schedule(pf);
+}
+
+/**
  * ice_service_timer - timer callback to schedule service task
  * @t: pointer to timer_list
  */
@@ -901,7 +1073,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state))
+	if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state))
 		return;
 
 	/* find what triggered the MDD event */
@@ -993,10 +1165,12 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
 		struct ice_vf *vf = &pf->vf[i];
 
+		mdd_detected = false;
+
 		reg = rd32(hw, VP_MDET_TX_PQM(i));
 		if (reg & VP_MDET_TX_PQM_VALID_M) {
 			wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF);
-			vf->num_mdd_events++;
+			mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1004,7 +1178,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_TX_TCLAN(i));
 		if (reg & VP_MDET_TX_TCLAN_VALID_M) {
 			wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF);
-			vf->num_mdd_events++;
+			mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1012,7 +1186,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_TX_TDPU(i));
 		if (reg & VP_MDET_TX_TDPU_VALID_M) {
 			wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF);
-			vf->num_mdd_events++;
+			mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1020,26 +1194,19 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_RX(i));
 		if (reg & VP_MDET_RX_VALID_M) {
 			wr32(hw, VP_MDET_RX(i), 0xFFFF);
-			vf->num_mdd_events++;
+			mdd_detected = true;
 			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
 				 i);
 		}
 
-		if (vf->num_mdd_events > ICE_DFLT_NUM_MDD_EVENTS_ALLOWED) {
-			dev_info(&pf->pdev->dev,
-				 "Too many MDD events on VF %d, disabled\n", i);
+		if (mdd_detected) {
+			vf->num_mdd_events++;
 			dev_info(&pf->pdev->dev,
 				 "Use PF Control I/F to re-enable the VF\n");
 			set_bit(ICE_VF_STATE_DIS, vf->vf_states);
 		}
 	}
 
-	/* re-enable MDD interrupt cause */
-	clear_bit(__ICE_MDD_EVENT_PENDING, pf->state);
-	reg = rd32(hw, PFINT_OICR_ENA);
-	reg |= PFINT_OICR_MAL_DETECT_M;
-	wr32(hw, PFINT_OICR_ENA, reg);
-	ice_flush(hw);
 }
 
 /**
@@ -1089,7 +1256,7 @@ static void ice_service_task(struct work_struct *work)
 
 /**
  * ice_set_ctrlq_len - helper function to set controlq length
- * @hw: pointer to the hw instance
+ * @hw: pointer to the HW instance
  */
 static void ice_set_ctrlq_len(struct ice_hw *hw)
 {
@@ -1111,8 +1278,9 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
  * This is a callback function used by the irq_set_affinity_notifier function
  * so that we may register to receive changes to the irq affinity masks.
  */
-static void ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-				    const cpumask_t *mask)
+static void
+ice_irq_affinity_notify(struct irq_affinity_notify *notify,
+			const cpumask_t *mask)
 {
 	struct ice_q_vector *q_vector =
 		container_of(notify, struct ice_q_vector, affinity_notify);
@@ -1142,7 +1310,7 @@ static int ice_vsi_ena_irq(struct ice_vsi *vsi)
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
 		int i;
 
-		for (i = 0; i < vsi->num_q_vectors; i++)
+		ice_for_each_q_vector(vsi, i)
 			ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
 	}
 
@@ -1184,10 +1352,9 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 			/* skip this unused q_vector */
 			continue;
 		}
-		err = devm_request_irq(&pf->pdev->dev,
-				       pf->msix_entries[base + vector].vector,
-				       vsi->irq_handler, 0, q_vector->name,
-				       q_vector);
+		err = devm_request_irq(&pf->pdev->dev, irq_num,
+				       vsi->irq_handler, 0,
+				       q_vector->name, q_vector);
 		if (err) {
 			netdev_err(vsi->netdev,
 				   "MSIX request_irq failed, error: %d\n", err);
@@ -1328,7 +1495,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			rd32(hw, PFHMC_ERRORDATA));
 	}
 
-	/* Report and mask off any remaining unexpected interrupts */
+	/* Report any remaining unexpected interrupts */
 	oicr &= ena_mask;
 	if (oicr) {
 		dev_dbg(&pf->pdev->dev, "unhandled interrupt oicr=0x%08x\n",
@@ -1342,12 +1509,9 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			set_bit(__ICE_PFR_REQ, pf->state);
 			ice_service_task_schedule(pf);
 		}
-		ena_mask &= ~oicr;
 	}
 	ret = IRQ_HANDLED;
 
-	/* re-enable interrupt causes that are not handled during this pass */
-	wr32(hw, PFINT_OICR_ENA, ena_mask);
 	if (!test_bit(__ICE_DOWN, pf->state)) {
 		ice_service_task_schedule(pf);
 		ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1406,23 +1570,23 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 /**
  * ice_ena_ctrlq_interrupts - enable control queue interrupts
  * @hw: pointer to HW structure
- * @v_idx: HW vector index to associate the control queue interrupts with
+ * @reg_idx: HW vector index to associate the control queue interrupts with
  */
-static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 v_idx)
+static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
 {
 	u32 val;
 
-	val = ((v_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+	val = ((reg_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
 	       PFINT_OICR_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_OICR_CTL, val);
 
 	/* enable Admin queue Interrupt causes */
-	val = ((v_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+	val = ((reg_idx & PFINT_FW_CTL_MSIX_INDX_M) |
 	       PFINT_FW_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_FW_CTL, val);
 
 	/* enable Mailbox queue Interrupt causes */
-	val = ((v_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
+	val = ((reg_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
 	       PFINT_MBX_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_MBX_CTL, val);
 
@@ -1510,7 +1674,7 @@ void ice_napi_del(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
+	ice_for_each_q_vector(vsi, v_idx)
 		netif_napi_del(&vsi->q_vectors[v_idx]->napi);
 }
 
@@ -1529,7 +1693,7 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
+	ice_for_each_q_vector(vsi, v_idx)
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll, NAPI_POLL_WEIGHT);
 }
@@ -1649,18 +1813,20 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 }
 
 /**
- * ice_vlan_rx_add_vid - Add a vlan id filter to HW offload
+ * ice_vlan_rx_add_vid - Add a VLAN ID filter to HW offload
  * @netdev: network interface to be adjusted
  * @proto: unused protocol
- * @vid: vlan id to be added
+ * @vid: VLAN ID to be added
  *
- * net_device_ops implementation for adding vlan ids
+ * net_device_ops implementation for adding VLAN IDs
  */
-static int ice_vlan_rx_add_vid(struct net_device *netdev,
-			       __always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto,
+		    u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	int ret;
 
 	if (vid >= VLAN_N_VID) {
 		netdev_err(netdev, "VLAN id requested %d is out of range %d\n",
@@ -1673,33 +1839,39 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev,
 
 	/* Enable VLAN pruning when VLAN 0 is added */
 	if (unlikely(!vid)) {
-		int ret = ice_cfg_vlan_pruning(vsi, true);
-
+		ret = ice_cfg_vlan_pruning(vsi, true, false);
 		if (ret)
 			return ret;
 	}
 
-	/* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is
+	/* Add all VLAN IDs including 0 to the switch filter. VLAN ID 0 is
 	 * needed to continue allowing all untagged packets since VLAN prune
 	 * list is applied to all packets by the switch
 	 */
-	return ice_vsi_add_vlan(vsi, vid);
+	ret = ice_vsi_add_vlan(vsi, vid);
+	if (!ret) {
+		vsi->vlan_ena = true;
+		set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+	}
+
+	return ret;
 }
 
 /**
- * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
+ * ice_vlan_rx_kill_vid - Remove a VLAN ID filter from HW offload
  * @netdev: network interface to be adjusted
  * @proto: unused protocol
- * @vid: vlan id to be removed
+ * @vid: VLAN ID to be removed
  *
- * net_device_ops implementation for removing vlan ids
+ * net_device_ops implementation for removing VLAN IDs
  */
-static int ice_vlan_rx_kill_vid(struct net_device *netdev,
-				__always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto,
+		     u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
-	int status;
+	int ret;
 
 	if (vsi->info.pvid)
 		return -EINVAL;
@@ -1707,15 +1879,17 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev,
 	/* Make sure ice_vsi_kill_vlan is successful before updating VLAN
 	 * information
 	 */
-	status = ice_vsi_kill_vlan(vsi, vid);
-	if (status)
-		return status;
+	ret = ice_vsi_kill_vlan(vsi, vid);
+	if (ret)
+		return ret;
 
 	/* Disable VLAN pruning when VLAN 0 is removed */
 	if (unlikely(!vid))
-		status = ice_cfg_vlan_pruning(vsi, false);
+		ret = ice_cfg_vlan_pruning(vsi, false, false);
 
-	return status;
+	vsi->vlan_ena = false;
+	set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+	return ret;
 }
 
 /**
@@ -2033,23 +2207,6 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 }
 
 /**
- * ice_verify_itr_gran - verify driver's assumption of ITR granularity
- * @pf: pointer to the PF structure
- *
- * There is no error returned here because the driver will be able to handle a
- * different ITR granularity, but interrupt moderation will not be accurate if
- * the driver's assumptions are not verified. This assumption is made so we can
- * use constants in the hot path instead of accessing structure members.
- */
-static void ice_verify_itr_gran(struct ice_pf *pf)
-{
-	if (pf->hw.itr_gran != (ICE_ITR_GRAN_S << 1))
-		dev_warn(&pf->pdev->dev,
-			 "%d ITR granularity assumption is invalid, actual ITR granularity is %d. Interrupt moderation will be inaccurate!\n",
-			 (ICE_ITR_GRAN_S << 1), pf->hw.itr_gran);
-}
-
-/**
  * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
  * @pf: pointer to the PF structure
  *
@@ -2072,9 +2229,10 @@ static void ice_verify_cacheline_size(struct ice_pf *pf)
  *
  * Returns 0 on success, negative on failure
  */
-static int ice_probe(struct pci_dev *pdev,
-		     const struct pci_device_id __always_unused *ent)
+static int
+ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 {
+	struct device *dev = &pdev->dev;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	int err;
@@ -2086,20 +2244,20 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev));
 	if (err) {
-		dev_err(&pdev->dev, "BAR0 I/O map error %d\n", err);
+		dev_err(dev, "BAR0 I/O map error %d\n", err);
 		return err;
 	}
 
-	pf = devm_kzalloc(&pdev->dev, sizeof(*pf), GFP_KERNEL);
+	pf = devm_kzalloc(dev, sizeof(*pf), GFP_KERNEL);
 	if (!pf)
 		return -ENOMEM;
 
 	/* set up for high or low dma */
-	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err)
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (err) {
-		dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err);
+		dev_err(dev, "DMA configuration failed: 0x%x\n", err);
 		return err;
 	}
 
@@ -2133,17 +2291,26 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_init_hw(hw);
 	if (err) {
-		dev_err(&pdev->dev, "ice_init_hw failed: %d\n", err);
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
 		err = -EIO;
 		goto err_exit_unroll;
 	}
 
-	dev_info(&pdev->dev, "firmware %d.%d.%05d api %d.%d\n",
+	dev_info(dev, "firmware %d.%d.%05d api %d.%d\n",
 		 hw->fw_maj_ver, hw->fw_min_ver, hw->fw_build,
 		 hw->api_maj_ver, hw->api_min_ver);
 
 	ice_init_pf(pf);
 
+	err = ice_init_pf_dcb(pf);
+	if (err) {
+		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+
+		/* do not fail overall init if DCB init fails */
+		err = 0;
+	}
+
 	ice_determine_q_usage(pf);
 
 	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
@@ -2152,8 +2319,8 @@ static int ice_probe(struct pci_dev *pdev,
 		goto err_init_pf_unroll;
 	}
 
-	pf->vsi = devm_kcalloc(&pdev->dev, pf->num_alloc_vsi,
-			       sizeof(*pf->vsi), GFP_KERNEL);
+	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
+			       GFP_KERNEL);
 	if (!pf->vsi) {
 		err = -ENOMEM;
 		goto err_init_pf_unroll;
@@ -2161,8 +2328,7 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_init_interrupt_scheme(pf);
 	if (err) {
-		dev_err(&pdev->dev,
-			"ice_init_interrupt_scheme failed: %d\n", err);
+		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
 		goto err_init_interrupt_unroll;
 	}
@@ -2178,15 +2344,13 @@ static int ice_probe(struct pci_dev *pdev,
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
 		err = ice_req_irq_msix_misc(pf);
 		if (err) {
-			dev_err(&pdev->dev,
-				"setup of misc vector failed: %d\n", err);
+			dev_err(dev, "setup of misc vector failed: %d\n", err);
 			goto err_init_interrupt_unroll;
 		}
 	}
 
 	/* create switch struct for the switch element created by FW on boot */
-	pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(*pf->first_sw),
-				    GFP_KERNEL);
+	pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL);
 	if (!pf->first_sw) {
 		err = -ENOMEM;
 		goto err_msix_misc_unroll;
@@ -2204,8 +2368,7 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_setup_pf_sw(pf);
 	if (err) {
-		dev_err(&pdev->dev,
-			"probe failed due to setup pf switch:%d\n", err);
+		dev_err(dev, "probe failed due to setup pf switch:%d\n", err);
 		goto err_alloc_sw_unroll;
 	}
 
@@ -2214,8 +2377,13 @@ static int ice_probe(struct pci_dev *pdev,
 	/* since everything is good, start the service timer */
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
+	err = ice_init_link_events(pf->hw.port_info);
+	if (err) {
+		dev_err(dev, "ice_init_link_events failed: %d\n", err);
+		goto err_alloc_sw_unroll;
+	}
+
 	ice_verify_cacheline_size(pf);
-	ice_verify_itr_gran(pf);
 
 	return 0;
 
@@ -2227,7 +2395,7 @@ err_msix_misc_unroll:
 	ice_free_irq_msix_misc(pf);
 err_init_interrupt_unroll:
 	ice_clear_interrupt_scheme(pf);
-	devm_kfree(&pdev->dev, pf->vsi);
+	devm_kfree(dev, pf->vsi);
 err_init_pf_unroll:
 	ice_deinit_pf(pf);
 	ice_deinit_hw(hw);
@@ -2272,6 +2440,136 @@ static void ice_remove(struct pci_dev *pdev)
 	pci_disable_pcie_error_reporting(pdev);
 }
 
+/**
+ * ice_pci_err_detected - warning that PCI error has been detected
+ * @pdev: PCI device information struct
+ * @err: the type of PCI error
+ *
+ * Called to warn that something happened on the PCI bus and the error handling
+ * is in progress.  Allows the driver to gracefully prepare/handle PCI errors.
+ */
+static pci_ers_result_t
+ice_pci_err_detected(struct pci_dev *pdev, enum pci_channel_state err)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!pf) {
+		dev_err(&pdev->dev, "%s: unrecoverable device error %d\n",
+			__func__, err);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+		ice_service_task_stop(pf);
+
+		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+			set_bit(__ICE_PFR_REQ, pf->state);
+			ice_prepare_for_reset(pf);
+		}
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * ice_pci_err_slot_reset - a PCI slot reset has just happened
+ * @pdev: PCI device information struct
+ *
+ * Called to determine if the driver can recover from the PCI slot reset by
+ * using a register read to determine if the device is recoverable.
+ */
+static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+	pci_ers_result_t result;
+	int err;
+	u32 reg;
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Cannot re-enable PCI device after reset, error %d\n",
+			err);
+		result = PCI_ERS_RESULT_DISCONNECT;
+	} else {
+		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
+		pci_wake_from_d3(pdev, false);
+
+		/* Check for life */
+		reg = rd32(&pf->hw, GLGEN_RTRIG);
+		if (!reg)
+			result = PCI_ERS_RESULT_RECOVERED;
+		else
+			result = PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	err = pci_cleanup_aer_uncorrect_error_status(pdev);
+	if (err)
+		dev_dbg(&pdev->dev,
+			"pci_cleanup_aer_uncorrect_error_status failed, error %d\n",
+			err);
+		/* non-fatal, continue */
+
+	return result;
+}
+
+/**
+ * ice_pci_err_resume - restart operations after PCI error recovery
+ * @pdev: PCI device information struct
+ *
+ * Called to allow the driver to bring things back up after PCI error and/or
+ * reset recovery have finished
+ */
+static void ice_pci_err_resume(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!pf) {
+		dev_err(&pdev->dev,
+			"%s failed, device is unrecoverable\n", __func__);
+		return;
+	}
+
+	if (test_bit(__ICE_SUSPENDED, pf->state)) {
+		dev_dbg(&pdev->dev, "%s failed to resume normal operations!\n",
+			__func__);
+		return;
+	}
+
+	ice_do_reset(pf, ICE_RESET_PFR);
+	ice_service_task_restart(pf);
+	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
+}
+
+/**
+ * ice_pci_err_reset_prepare - prepare device driver for PCI reset
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_prepare(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+		ice_service_task_stop(pf);
+
+		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+			set_bit(__ICE_PFR_REQ, pf->state);
+			ice_prepare_for_reset(pf);
+		}
+	}
+}
+
+/**
+ * ice_pci_err_reset_done - PCI reset done, device driver reset can begin
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_done(struct pci_dev *pdev)
+{
+	ice_pci_err_resume(pdev);
+}
+
 /* ice_pci_tbl - PCI Device ID Table
  *
  * Wildcard entries (PCI_ANY_ID) should come last
@@ -2289,12 +2587,21 @@ static const struct pci_device_id ice_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, ice_pci_tbl);
 
+static const struct pci_error_handlers ice_pci_err_handler = {
+	.error_detected = ice_pci_err_detected,
+	.slot_reset = ice_pci_err_slot_reset,
+	.reset_prepare = ice_pci_err_reset_prepare,
+	.reset_done = ice_pci_err_reset_done,
+	.resume = ice_pci_err_resume
+};
+
 static struct pci_driver ice_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = ice_pci_tbl,
 	.probe = ice_probe,
 	.remove = ice_remove,
 	.sriov_configure = ice_sriov_configure,
+	.err_handler = &ice_pci_err_handler
 };
 
 /**
@@ -2341,7 +2648,7 @@ static void __exit ice_module_exit(void)
 module_exit(ice_module_exit);
 
 /**
- * ice_set_mac_address - NDO callback to set mac address
+ * ice_set_mac_address - NDO callback to set MAC address
  * @netdev: network interface device structure
  * @pi: pointer to an address structure
  *
@@ -2378,14 +2685,14 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 		return -EBUSY;
 	}
 
-	/* When we change the mac address we also have to change the mac address
-	 * based filter rules that were created previously for the old mac
+	/* When we change the MAC address we also have to change the MAC address
+	 * based filter rules that were created previously for the old MAC
 	 * address. So first, we remove the old filter rule using ice_remove_mac
 	 * and then create a new filter rule using ice_add_mac. Note that for
-	 * both these operations, we first need to form a "list" of mac
-	 * addresses (even though in this case, we have only 1 mac address to be
+	 * both these operations, we first need to form a "list" of MAC
+	 * addresses (even though in this case, we have only 1 MAC address to be
 	 * added/removed) and this done using ice_add_mac_to_list. Depending on
-	 * the ensuing operation this "list" of mac addresses is either to be
+	 * the ensuing operation this "list" of MAC addresses is either to be
 	 * added or removed from the filter.
 	 */
 	err = ice_add_mac_to_list(vsi, &r_mac_list, netdev->dev_addr);
@@ -2423,12 +2730,12 @@ free_lists:
 		return err;
 	}
 
-	/* change the netdev's mac address */
+	/* change the netdev's MAC address */
 	memcpy(netdev->dev_addr, mac, netdev->addr_len);
 	netdev_dbg(vsi->netdev, "updated mac address to %pM\n",
 		   netdev->dev_addr);
 
-	/* write new mac address to the firmware */
+	/* write new MAC address to the firmware */
 	flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
 	status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
 	if (status) {
@@ -2470,7 +2777,7 @@ static void ice_set_rx_mode(struct net_device *netdev)
  * @tb: pointer to array of nladdr (unused)
  * @dev: the net device pointer
  * @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
  * @flags: instructions from stack about fdb operation
  * @extack: netlink extended ack
  */
@@ -2510,11 +2817,12 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
  * @tb: pointer to array of nladdr (unused)
  * @dev: the net device pointer
  * @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
  */
-static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
-		       struct net_device *dev, const unsigned char *addr,
-		       __always_unused u16 vid)
+static int
+ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
+	    struct net_device *dev, const unsigned char *addr,
+	    __always_unused u16 vid)
 {
 	int err;
 
@@ -2538,13 +2846,16 @@ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
  * @netdev: ptr to the netdev being adjusted
  * @features: the feature set that the stack is suggesting
  */
-static int ice_set_features(struct net_device *netdev,
-			    netdev_features_t features)
+static int
+ice_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 	int ret = 0;
 
+	/* Multiple features can be changed in one call so keep features in
+	 * separate if/else statements to guarantee each feature is checked
+	 */
 	if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH))
 		ret = ice_vsi_manage_rss_lut(vsi, true);
 	else if (!(features & NETIF_F_RXHASH) &&
@@ -2557,8 +2868,9 @@ static int ice_set_features(struct net_device *netdev,
 	else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) &&
 		 (netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
 		ret = ice_vsi_manage_vlan_stripping(vsi, false);
-	else if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
-		 !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
+	    !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
 		ret = ice_vsi_manage_vlan_insertion(vsi);
 	else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) &&
 		 (netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
@@ -2568,8 +2880,8 @@ static int ice_set_features(struct net_device *netdev,
 }
 
 /**
- * ice_vsi_vlan_setup - Setup vlan offload properties on a VSI
- * @vsi: VSI to setup vlan properties for
+ * ice_vsi_vlan_setup - Setup VLAN offload properties on a VSI
+ * @vsi: VSI to setup VLAN properties for
  */
 static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
 {
@@ -2601,6 +2913,7 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 		if (err)
 			return err;
 	}
+	ice_vsi_cfg_dcb_rings(vsi);
 
 	err = ice_vsi_cfg_lan_txqs(vsi);
 	if (!err)
@@ -2620,7 +2933,7 @@ static void ice_napi_enable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+	ice_for_each_q_vector(vsi, q_idx)  {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
 		if (q_vector->rx.ring || q_vector->tx.ring)
@@ -2666,7 +2979,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 
 	ice_service_task_schedule(pf);
 
-	return err;
+	return 0;
 }
 
 /**
@@ -2693,8 +3006,8 @@ int ice_up(struct ice_vsi *vsi)
  * This function fetches stats from the ring considering the atomic operations
  * that needs to be performed to read u64 values in 32 bit machine.
  */
-static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts,
-					 u64 *bytes)
+static void
+ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes)
 {
 	unsigned int start;
 	*pkts = 0;
@@ -2911,6 +3224,8 @@ static void ice_update_pf_stats(struct ice_pf *pf)
 	ice_stat_update32(hw, GLPRT_LXOFFTXC(pf_id), pf->stat_prev_loaded,
 			  &prev_ps->link_xoff_tx, &cur_ps->link_xoff_tx);
 
+	ice_update_dcb_stats(pf);
+
 	ice_stat_update32(hw, GLPRT_CRCERRS(pf_id), pf->stat_prev_loaded,
 			  &prev_ps->crc_errors, &cur_ps->crc_errors);
 
@@ -2992,7 +3307,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
 		if (q_vector->rx.ring || q_vector->tx.ring)
@@ -3276,7 +3591,7 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 	if (!pf->vsi)
 		return;
 
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		if (!pf->vsi[i])
 			continue;
 
@@ -3289,47 +3604,31 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 }
 
 /**
- * ice_dis_vsi - pause a VSI
- * @vsi: the VSI being paused
+ * ice_ena_vsi - resume a VSI
+ * @vsi: the VSI being resume
  * @locked: is the rtnl_lock already held
  */
-static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+static int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
 {
-	if (test_bit(__ICE_DOWN, vsi->state))
-		return;
+	int err = 0;
 
-	set_bit(__ICE_NEEDS_RESTART, vsi->state);
+	if (!test_bit(__ICE_NEEDS_RESTART, vsi->state))
+		return err;
+
+	clear_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+		struct net_device *netd = vsi->netdev;
 
-	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
 		if (netif_running(vsi->netdev)) {
-			if (!locked) {
+			if (locked) {
+				err = netd->netdev_ops->ndo_open(netd);
+			} else {
 				rtnl_lock();
-				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				err = netd->netdev_ops->ndo_open(netd);
 				rtnl_unlock();
-			} else {
-				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
 			}
 		} else {
-			ice_vsi_close(vsi);
-		}
-	}
-}
-
-/**
- * ice_ena_vsi - resume a VSI
- * @vsi: the VSI being resume
- */
-static int ice_ena_vsi(struct ice_vsi *vsi)
-{
-	int err = 0;
-
-	if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state) &&
-	    vsi->netdev) {
-		if (netif_running(vsi->netdev)) {
-			rtnl_lock();
-			err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
-			rtnl_unlock();
-		} else {
 			err = ice_vsi_open(vsi);
 		}
 	}
@@ -3338,29 +3637,21 @@ static int ice_ena_vsi(struct ice_vsi *vsi)
 }
 
 /**
- * ice_pf_dis_all_vsi - Pause all VSIs on a PF
- * @pf: the PF
- */
-static void ice_pf_dis_all_vsi(struct ice_pf *pf)
-{
-	int v;
-
-	ice_for_each_vsi(pf, v)
-		if (pf->vsi[v])
-			ice_dis_vsi(pf->vsi[v], false);
-}
-
-/**
  * ice_pf_ena_all_vsi - Resume all VSIs on a PF
  * @pf: the PF
+ * @locked: is the rtnl_lock already held
  */
-static int ice_pf_ena_all_vsi(struct ice_pf *pf)
+#ifdef CONFIG_DCB
+int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
+#else
+static int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
+#endif /* CONFIG_DCB */
 {
 	int v;
 
 	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v])
-			if (ice_ena_vsi(pf->vsi[v]))
+			if (ice_ena_vsi(pf->vsi[v], locked))
 				return -EIO;
 
 	return 0;
@@ -3375,16 +3666,12 @@ static int ice_vsi_rebuild_all(struct ice_pf *pf)
 	int i;
 
 	/* loop through pf->vsi array and reinit the VSI if found */
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		int err;
 
 		if (!pf->vsi[i])
 			continue;
 
-		/* VF VSI rebuild isn't supported yet */
-		if (pf->vsi[i]->type == ICE_VSI_VF)
-			continue;
-
 		err = ice_vsi_rebuild(pf->vsi[i]);
 		if (err) {
 			dev_err(&pf->pdev->dev,
@@ -3412,7 +3699,7 @@ static int ice_vsi_replay_all(struct ice_pf *pf)
 	int i;
 
 	/* loop through pf->vsi array and replay the VSI if found */
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		if (!pf->vsi[i])
 			continue;
 
@@ -3479,6 +3766,8 @@ static void ice_rebuild(struct ice_pf *pf)
 	if (err)
 		goto err_sched_init_port;
 
+	ice_dcb_rebuild(pf);
+
 	/* reset search_hint of irq_trackers to 0 since interrupts are
 	 * reclaimed and could be allocated from beginning during VSI rebuild
 	 */
@@ -3512,7 +3801,7 @@ static void ice_rebuild(struct ice_pf *pf)
 	}
 
 	/* restart the VSIs that were rebuilt and running before the reset */
-	err = ice_pf_ena_all_vsi(pf);
+	err = ice_pf_ena_all_vsi(pf, false);
 	if (err) {
 		dev_err(&pf->pdev->dev, "error enabling VSIs\n");
 		/* no need to disable VSIs in tear down path in ice_rebuild()
@@ -3521,9 +3810,7 @@ static void ice_rebuild(struct ice_pf *pf)
 		goto err_vsi_rebuild;
 	}
 
-	ice_reset_all_vfs(pf, true);
-
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		bool link_up;
 
 		if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF)
@@ -3710,7 +3997,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 /**
  * ice_bridge_getlink - Get the hardware bridge mode
  * @skb: skb buff
- * @pid: process id
+ * @pid: process ID
  * @seq: RTNL message seq
  * @dev: the netdev being configured
  * @filter_mask: filter mask passed in
@@ -3909,8 +4196,7 @@ static void ice_tx_timeout(struct net_device *netdev)
 		/* Read interrupt register */
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 			val = rd32(hw,
-				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
-						 tx_ring->vsi->hw_base_vector));
+				   GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,