ice_main.c

// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018, Intel Corporation. */

/* Intel(R) Ethernet Connection E800 Series Linux Driver */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include "ice.h"
#include "ice_base.h"
#include "ice_lib.h"
#include "ice_dcb_lib.h"
#include "ice_dcb_nl.h"

#define DRV_VERSION_MAJOR 0
#define DRV_VERSION_MINOR 8
#define DRV_VERSION_BUILD 1

#define DRV_VERSION	__stringify(DRV_VERSION_MAJOR) "." \
			__stringify(DRV_VERSION_MINOR) "." \
			__stringify(DRV_VERSION_BUILD) "-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;
static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";

/* DDP Package file located in firmware search paths (e.g. /lib/firmware/) */
#define ICE_DDP_PKG_PATH	"intel/ice/ddp/"
#define ICE_DDP_PKG_FILE	ICE_DDP_PKG_PATH "ice.pkg"

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION(DRV_SUMMARY);
MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
MODULE_FIRMWARE(ICE_DDP_PKG_FILE);

static int debug = -1;
module_param(debug, int, 0644);
#ifndef CONFIG_DYNAMIC_DEBUG
MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXXXXX)");
#else
MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
#endif /* !CONFIG_DYNAMIC_DEBUG */

static struct workqueue_struct *ice_wq;
static const struct net_device_ops ice_netdev_safe_mode_ops;
static const struct net_device_ops ice_netdev_ops;
static int ice_vsi_open(struct ice_vsi *vsi);

static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type);

static void ice_vsi_release_all(struct ice_pf *pf);

/**
 * ice_get_tx_pending - returns number of Tx descriptors not processed
 * @ring: the ring of descriptors
 */
static u16 ice_get_tx_pending(struct ice_ring *ring)
{
	u16 head, tail;

	head = ring->next_to_clean;
	tail = ring->next_to_use;

	if (head != tail)
		return (head < tail) ?
			tail - head : (tail + ring->count - head);
	return 0;
}

/**
 * ice_check_for_hang_subtask - check for and recover hung queues
 * @pf: pointer to PF struct
 */
static void ice_check_for_hang_subtask(struct ice_pf *pf)
{
	struct ice_vsi *vsi = NULL;
	struct ice_hw *hw;
	unsigned int i;
	int packets;
	u32 v;

	ice_for_each_vsi(pf, v)
		if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) {
			vsi = pf->vsi[v];
			break;
		}

	if (!vsi || test_bit(__ICE_DOWN, vsi->state))
		return;

	if (!(vsi->netdev && netif_carrier_ok(vsi->netdev)))
		return;

	hw = &vsi->back->hw;

	for (i = 0; i < vsi->num_txq; i++) {
		struct ice_ring *tx_ring = vsi->tx_rings[i];

		if (tx_ring && tx_ring->desc) {
			/* If packet counter has not changed the queue is
			 * likely stalled, so force an interrupt for this
			 * queue.
			 *
			 * prev_pkt would be negative if there was no
			 * pending work.
			 */
			packets = tx_ring->stats.pkts & INT_MAX;
			if (tx_ring->tx_stats.prev_pkt == packets) {
				/* Trigger sw interrupt to revive the queue */
				ice_trigger_sw_intr(hw, tx_ring->q_vector);
				continue;
			}

			/* Memory barrier between read of packet count and call
			 * to ice_get_tx_pending()
			 */
			smp_rmb();
			tx_ring->tx_stats.prev_pkt =
			    ice_get_tx_pending(tx_ring) ? packets : -1;
		}
	}
}

/**
 * ice_init_mac_fltr - Set initial MAC filters
 * @pf: board private structure
 *
 * Set initial set of MAC filters for PF VSI; configure filters for permanent
 * address and broadcast address. If an error is encountered, netdevice will be
 * unregistered.
 */
static int ice_init_mac_fltr(struct ice_pf *pf)
{
	enum ice_status status;
	u8 broadcast[ETH_ALEN];
	struct ice_vsi *vsi;

	vsi = ice_get_main_vsi(pf);
	if (!vsi)
		return -EINVAL;

	/* To add a MAC filter, first add the MAC to a list and then
	 * pass the list to ice_add_mac.
	 */

	 /* Add a unicast MAC filter so the VSI can get its packets */
	status = ice_vsi_cfg_mac_fltr(vsi, vsi->port_info->mac.perm_addr, true);
	if (status)
		goto unregister;

	/* VSI needs to receive broadcast traffic, so add the broadcast
	 * MAC address to the list as well.
	 */
	eth_broadcast_addr(broadcast);
	status = ice_vsi_cfg_mac_fltr(vsi, broadcast, true);
	if (status)
		goto unregister;

	return 0;
unregister:
	/* We aren't useful with no MAC filters, so unregister if we
	 * had an error
	 */
	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
		dev_err(ice_pf_to_dev(pf),
			"Could not add MAC filters error %d. Unregistering device\n",
			status);
		unregister_netdev(vsi->netdev);
		free_netdev(vsi->netdev);
		vsi->netdev = NULL;
	}

	return -EIO;
}

/**
 * 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
 *
 * 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.
 */
static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;

	if (ice_add_mac_to_list(vsi, &vsi->tmp_sync_list, addr))
		return -EINVAL;

	return 0;
}

/**
 * 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
 *
 * 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.
 */
static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;

	if (ice_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr))
		return -EINVAL;

	return 0;
}

/**
 * ice_vsi_fltr_changed - check if filter state changed
 * @vsi: VSI to be checked
 *
 * returns true if filter state has changed, false otherwise.
 */
static bool ice_vsi_fltr_changed(struct ice_vsi *vsi)
{
	return test_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags) ||
	       test_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags) ||
	       test_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
}

/**
 * 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
 *
 * Push any outstanding VSI filter changes through the AdminQ.
 */
static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
{
	struct device *dev = &vsi->back->pdev->dev;
	struct net_device *netdev = vsi->netdev;
	bool promisc_forced_on = false;
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	enum ice_status status = 0;
	u32 changed_flags = 0;
	u8 promisc_m;
	int err = 0;

	if (!vsi->netdev)
		return -EINVAL;

	while (test_and_set_bit(__ICE_CFG_BUSY, vsi->state))
		usleep_range(1000, 2000);

	changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags;
	vsi->current_netdev_flags = vsi->netdev->flags;

	INIT_LIST_HEAD(&vsi->tmp_sync_list);
	INIT_LIST_HEAD(&vsi->tmp_unsync_list);

	if (ice_vsi_fltr_changed(vsi)) {
		clear_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
		clear_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
		clear_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);

		/* grab the netdev's addr_list_lock */
		netif_addr_lock_bh(netdev);
		__dev_uc_sync(netdev, ice_add_mac_to_sync_list,
			      ice_add_mac_to_unsync_list);
		__dev_mc_sync(netdev, ice_add_mac_to_sync_list,
			      ice_add_mac_to_unsync_list);
		/* our temp lists are populated. release lock */
		netif_addr_unlock_bh(netdev);
	}

	/* 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) {
		netdev_err(netdev, "Failed to delete MAC filters\n");
		/* if we failed because of alloc failures, just bail */
		if (status == ICE_ERR_NO_MEMORY) {
			err = -ENOMEM;
			goto out;
		}
	}

	/* 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 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
		 * should go into promiscuous mode. There should be some
		 * space reserved for promiscuous filters.
		 */
		if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC &&
		    !test_and_set_bit(__ICE_FLTR_OVERFLOW_PROMISC,
				      vsi->state)) {
			promisc_forced_on = true;
			netdev_warn(netdev,
				    "Reached MAC filter limit, forcing promisc mode on VSI %d\n",
				    vsi->vsi_num);
		} else {
			err = -EIO;
			goto out;
		}
	}
	/* check for changes in promiscuous modes */
	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 Rx filter rule to get traffic from wire */
			if (!ice_is_dflt_vsi_in_use(pf->first_sw)) {
				err = ice_set_dflt_vsi(pf->first_sw, vsi);
				if (err && err != -EEXIST) {
					netdev_err(netdev,
						   "Error %d setting default VSI %i Rx rule\n",
						   err, vsi->vsi_num);
					vsi->current_netdev_flags &=
						~IFF_PROMISC;
					goto out_promisc;
				}
			}
		} else {
			/* Clear Rx filter to remove traffic from wire */
			if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) {
				err = ice_clear_dflt_vsi(pf->first_sw);
				if (err) {
					netdev_err(netdev,
						   "Error %d clearing default VSI %i Rx rule\n",
						   err, vsi->vsi_num);
					vsi->current_netdev_flags |=
						IFF_PROMISC;
					goto out_promisc;
				}
			}
		}
	}
	goto exit;

out_promisc:
	set_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
	goto exit;
out:
	/* if something went wrong then set the changed flag so we try again */
	set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
	set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
exit:
	clear_bit(__ICE_CFG_BUSY, vsi->state);
	return err;
}

/**
 * ice_sync_fltr_subtask - Sync the VSI filter list with HW
 * @pf: board private structure
 */
static void ice_sync_fltr_subtask(struct ice_pf *pf)
{
	int v;

	if (!pf || !(test_bit(ICE_FLAG_FLTR_SYNC, pf->flags)))
		return;

	clear_bit(ICE_FLAG_FLTR_SYNC, pf->flags);

	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 */
			set_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
			break;
		}
}

/**
 * ice_pf_dis_all_vsi - Pause all VSIs on a PF
 * @pf: the PF
 * @locked: is the rtnl_lock already held
 */
static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
{
	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
 *
 * Inform or close all dependent features in prep for reset.
 */
static void
ice_prepare_for_reset(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;
	int i;

	/* 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 VFs until reset is completed */
	ice_for_each_vf(pf, i)
		ice_set_vf_state_qs_dis(&pf->vf[i]);

	/* clear SW filtering DB */
	ice_clear_hw_tbls(hw);
	/* disable the VSIs and their queues that are not already DOWN */
	ice_pf_dis_all_vsi(pf, false);

	if (hw->port_info)
		ice_sched_clear_port(hw->port_info);

	ice_shutdown_all_ctrlq(hw);

	set_bit(__ICE_PREPARED_FOR_RESET, pf->state);
}

/**
 * ice_do_reset - Initiate one of many types of resets
 * @pf: board private structure
 * @reset_type: reset type requested
 * before this function was called.
 */
static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;

	dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
	WARN_ON(in_interrupt());

	ice_prepare_for_reset(pf);

	/* trigger the reset */
	if (ice_reset(hw, reset_type)) {
		dev_err(dev, "reset %d failed\n", reset_type);
		set_bit(__ICE_RESET_FAILED, pf->state);
		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);
		return;
	}

	/* PFR is a bit of a special case because it doesn't result in an OICR
	 * interrupt. So for PFR, rebuild after the reset and clear the reset-
	 * associated state bits.
	 */
	if (reset_type == ICE_RESET_PFR) {
		pf->pfr_count++;
		ice_rebuild(pf, reset_type);
		clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
		clear_bit(__ICE_PFR_REQ, pf->state);
		ice_reset_all_vfs(pf, true);
	}
}

/**
 * ice_reset_subtask - Set up for resetting the device and driver
 * @pf: board private structure
 */
static void ice_reset_subtask(struct ice_pf *pf)
{
	enum ice_reset_req reset_type = ICE_RESET_INVAL;

	/* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an
	 * OICR interrupt. The OICR handler (ice_misc_intr) determines what type
	 * of reset is pending and sets bits in pf->state indicating the reset
	 * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set
	 * prepare for pending reset if not already (for PF software-initiated
	 * global resets the software should already be prepared for it as
	 * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated
	 * by firmware or software on other PFs, that bit is not set so prepare
	 * for the reset now), poll for reset done, rebuild and return.
	 */
	if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) {
		/* 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;
		if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state))
			reset_type = ICE_RESET_EMPR;
		/* 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)) {
			set_bit(__ICE_RESET_FAILED, pf->state);
		} else {
			/* done with reset. start rebuild */
			pf->hw.reset_ongoing = false;
			ice_rebuild(pf, reset_type);
			/* clear bit to resume normal operations, but
			 * 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;
	}

	/* No pending resets to finish processing. Check for new resets */
	if (test_bit(__ICE_PFR_REQ, pf->state))
		reset_type = ICE_RESET_PFR;
	if (test_bit(__ICE_CORER_REQ, pf->state))
		reset_type = ICE_RESET_CORER;
	if (test_bit(__ICE_GLOBR_REQ, pf->state))
		reset_type = ICE_RESET_GLOBR;
	/* If no valid reset type requested just return */
	if (reset_type == ICE_RESET_INVAL)
		return;

	/* reset if not already down or busy */
	if (!test_bit(__ICE_DOWN, pf->state) &&
	    !test_bit(__ICE_CFG_BUSY, pf->state)) {
		ice_do_reset(pf, reset_type);
	}
}

/**
 * ice_print_topo_conflict - print topology conflict message
 * @vsi: the VSI whose topology status is being checked
 */
static void ice_print_topo_conflict(struct ice_vsi *vsi)
{
	switch (vsi->port_info->phy.link_info.topo_media_conflict) {
	case ICE_AQ_LINK_TOPO_CONFLICT:
	case ICE_AQ_LINK_MEDIA_CONFLICT:
	case ICE_AQ_LINK_TOPO_UNREACH_PRT:
	case ICE_AQ_LINK_TOPO_UNDRUTIL_PRT:
	case ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA:
		netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n");
		break;
	case ICE_AQ_LINK_TOPO_UNSUPP_MEDIA:
		netdev_info(vsi->netdev, "Rx/Tx is disabled on this device because an unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
		break;
	default:
		break;
	}
}

/**
 * ice_print_link_msg - print link up or down message
 * @vsi: the VSI whose link status is being queried
 * @isup: boolean for if the link is now up or down
 */
void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
{
	struct ice_aqc_get_phy_caps_data *caps;
	enum ice_status status;
	const char *fec_req;
	const char *speed;
	const char *fec;
	const char *fc;
	const char *an;

	if (!vsi)
		return;

	if (vsi->current_isup == isup)
		return;

	vsi->current_isup = isup;

	if (!isup) {
		netdev_info(vsi->netdev, "NIC Link is Down\n");
		return;
	}

	switch (vsi->port_info->phy.link_info.link_speed) {
	case ICE_AQ_LINK_SPEED_100GB:
		speed = "100 G";
		break;
	case ICE_AQ_LINK_SPEED_50GB:
		speed = "50 G";
		break;
	case ICE_AQ_LINK_SPEED_40GB:
		speed = "40 G";
		break;
	case ICE_AQ_LINK_SPEED_25GB:
		speed = "25 G";
		break;
	case ICE_AQ_LINK_SPEED_20GB:
		speed = "20 G";
		break;
	case ICE_AQ_LINK_SPEED_10GB:
		speed = "10 G";
		break;
	case ICE_AQ_LINK_SPEED_5GB:
		speed = "5 G";
		break;
	case ICE_AQ_LINK_SPEED_2500MB:
		speed = "2.5 G";
		break;
	case ICE_AQ_LINK_SPEED_1000MB:
		speed = "1 G";
		break;
	case ICE_AQ_LINK_SPEED_100MB:
		speed = "100 M";
		break;
	default:
		speed = "Unknown";
		break;
	}

	switch (vsi->port_info->fc.current_mode) {
	case ICE_FC_FULL:
		fc = "Rx/Tx";
		break;
	case ICE_FC_TX_PAUSE:
		fc = "Tx";
		break;
	case ICE_FC_RX_PAUSE:
		fc = "Rx";
		break;
	case ICE_FC_NONE:
		fc = "None";
		break;
	default:
		fc = "Unknown";
		break;
	}

	/* Get FEC mode based on negotiated link info */
	switch (vsi->port_info->phy.link_info.fec_info) {
	case ICE_AQ_LINK_25G_RS_528_FEC_EN:
		/* fall through */
	case ICE_AQ_LINK_25G_RS_544_FEC_EN:
		fec = "RS-FEC";
		break;
	case ICE_AQ_LINK_25G_KR_FEC_EN:
		fec = "FC-FEC/BASE-R";
		break;
	default:
		fec = "NONE";
		break;
	}

	/* check if autoneg completed, might be false due to not supported */
	if (vsi->port_info->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)
		an = "True";
	else
		an = "False";

	/* Get FEC mode requested based on PHY caps last SW configuration */
	caps = kzalloc(sizeof(*caps), GFP_KERNEL);
	if (!caps) {
		fec_req = "Unknown";
		goto done;
	}

	status = ice_aq_get_phy_caps(vsi->port_info, false,
				     ICE_AQC_REPORT_SW_CFG, caps, NULL);
	if (status)
		netdev_info(vsi->netdev, "Get phy capability failed.\n");

	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ)
		fec_req = "RS-FEC";
	else if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
		 caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
		fec_req = "FC-FEC/BASE-R";
	else
		fec_req = "NONE";

	kfree(caps);

done:
	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n",
		    speed, fec_req, fec, an, fc);
	ice_print_topo_conflict(vsi);
}

/**
 * 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)
		return;

	if (test_bit(__ICE_DOWN, vsi->state) || !vsi->netdev)
		return;

	if (vsi->type == ICE_VSI_PF) {
		if (link_up == netif_carrier_ok(vsi->netdev))
			return;

		if (link_up) {
			netif_carrier_on(vsi->netdev);
			netif_tx_wake_all_queues(vsi->netdev);
		} else {
			netif_carrier_off(vsi->netdev);
			netif_tx_stop_all_queues(vsi->netdev);
		}
	}
}

/**
 * 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 0 on success and negative on failure
 */
static int
ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
	       u16 link_speed)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_phy_info *phy_info;
	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;

	old_link = !!(phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
	old_link_speed = phy_info->link_info_old.link_speed;

	/* 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(dev,
			"Failed to update link status and re-enable link events for port %d\n",
			pi->lport);

	/* 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;

	vsi = ice_get_main_vsi(pf);
	if (!vsi || !vsi->port_info)
		return -EINVAL;

	/* turn off PHY if media was removed */
	if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) &&
	    !(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) {
		set_bit(ICE_FLAG_NO_MEDIA, pf->flags);

		result = ice_aq_set_link_restart_an(pi, false, NULL);
		if (result) {
			dev_dbg(dev,
				"Failed to set link down, VSI %d error %d\n",
				vsi->vsi_num, result);
			return result;
		}
	}

	ice_vsi_link_event(vsi, link_up);
	ice_print_link_msg(vsi, link_up);

	if (pf->num_alloc_vfs)
		ice_vc_notify_link_state(pf);

	return result;
}

/**
 * ice_watchdog_subtask - periodic tasks not using event driven scheduling
 * @pf: board private structure
 */
static void ice_watchdog_subtask(struct ice_pf *pf)
{
	int i;

	/* if interface is down do nothing */
	if (test_bit(__ICE_DOWN, pf->state) ||
	    test_bit(__ICE_CFG_BUSY, pf->state))
		return;

	/* make sure we don't do these things too often */
	if (time_before(jiffies,
			pf->serv_tmr_prev + pf->serv_tmr_period))
		return;

	pf->serv_tmr_prev = jiffies;

	/* Update the stats for active netdevs so the network stack
	 * can look at updated numbers whenever it cares to
	 */
	ice_update_pf_stats(pf);
	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(ice_pf_to_dev(pf),
			"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
 */
static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_rq_event_info event;
	struct ice_hw *hw = &pf->hw;
	struct ice_ctl_q_info *cq;
	u16 pending, i = 0;
	const char *qtype;
	u32 oldval, val;

	/* Do not clean control queue if/when PF reset fails */
	if (test_bit(__ICE_RESET_FAILED, pf->state))
		return 0;

	switch (q_type) {
	case ICE_CTL_Q_ADMIN:
		cq = &hw->adminq;
		qtype = "Admin";
		break;
	case ICE_CTL_Q_MAILBOX:
		cq = &hw->mailboxq;
		qtype = "Mailbox";
		break;
	default:
		dev_warn(dev, "Unknown control queue type 0x%x\n", q_type);
		return 0;
	}

	/* check for error indications - PF_xx_AxQLEN register layout for
	 * FW/MBX/SB are identical so just use defines for PF_FW_AxQLEN.
	 */
	val = rd32(hw, cq->rq.len);
	if (val & (PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
		   PF_FW_ARQLEN_ARQCRIT_M)) {
		oldval = val;
		if (val & PF_FW_ARQLEN_ARQVFE_M)
			dev_dbg(dev, "%s Receive Queue VF Error detected\n",
				qtype);
		if (val & PF_FW_ARQLEN_ARQOVFL_M) {
			dev_dbg(dev,
				"%s Receive Queue Overflow Error detected\n",
				qtype);
		}
		if (val & PF_FW_ARQLEN_ARQCRIT_M)
			dev_dbg(dev,
				"%s Receive Queue Critical Error detected\n",
				qtype);
		val &= ~(PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
			 PF_FW_ARQLEN_ARQCRIT_M);
		if (oldval != val)
			wr32(hw, cq->rq.len, val);
	}

	val = rd32(hw, cq->sq.len);
	if (val & (PF_FW_ATQLEN_ATQVFE_M | PF_FW_ATQLEN_ATQOVFL_M |
		   PF_FW_ATQLEN_ATQCRIT_M)) {
		oldval = val;
		if (val & PF_FW_ATQLEN_ATQVFE_M)
			dev_dbg(dev,
				"%s Send Queue VF Error detected\n", qtype);
		if (val & PF_FW_ATQLEN_ATQOVFL_M) {
			dev_dbg(dev, "%s Send Queue Overflow Error detected\n",
				qtype);
		}
		if (val & PF_FW_ATQLEN_ATQCRIT_M)
			dev_dbg(dev, "%s Send Queue Critical Error detected\n",
				qtype);
		val &= ~(PF_FW_ATQLEN_ATQVFE_M | PF_FW_ATQLEN_ATQOVFL_M |
			 PF_FW_ATQLEN_ATQCRIT_M);
		if (oldval != val)
			wr32(hw, cq->sq.len, val);
	}

	event.buf_len = cq->rq_buf_size;
	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
	if (!event.msg_buf)
		return 0;

	do {
		enum ice_status ret;
		u16 opcode;

		ret = ice_clean_rq_elem(hw, cq, &event, &pending);
		if (ret == ICE_ERR_AQ_NO_WORK)
			break;
		if (ret) {
			dev_err(dev, "%s Receive Queue event error %d\n", qtype,
				ret);
			break;
		}

		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(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(dev,
				"%s Receive Queue unknown event 0x%04x ignored\n",
				qtype, opcode);
			break;
		}
	} while (pending && (i++ < ICE_DFLT_IRQ_WORK));

	kfree(event.msg_buf);

	return pending && (i == ICE_DFLT_IRQ_WORK);
}

/**
 * ice_ctrlq_pending - check if there is a difference between ntc and ntu
 * @hw: pointer to hardware info
 * @cq: control queue information
 *
 * returns true if there are pending messages in a queue, false if there aren't
 */
static bool ice_ctrlq_pending(struct ice_hw *hw, struct ice_ctl_q_info *cq)
{
	u16 ntu;

	ntu = (u16)(rd32(hw, cq->rq.head) & cq->rq.head_mask);
	return cq->rq.next_to_clean != ntu;
}

/**
 * ice_clean_adminq_subtask - clean the AdminQ rings
 * @pf: board private structure
 */
static void ice_clean_adminq_subtask(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;

	if (!test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state))
		return;

	if (__ice_clean_ctrlq(pf, ICE_CTL_Q_ADMIN))
		return;

	clear_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);

	/* There might be a situation where new messages arrive to a control
	 * queue between processing the last message and clearing the
	 * EVENT_PENDING bit. So before exiting, check queue head again (using
	 * ice_ctrlq_pending) and process new messages if any.
	 */
	if (ice_ctrlq_pending(hw, &hw->adminq))
		__ice_clean_ctrlq(pf, ICE_CTL_Q_ADMIN);

	ice_flush(hw);
}

/**
 * ice_clean_mailboxq_subtask - clean the MailboxQ rings
 * @pf: board private structure
 */
static void ice_clean_mailboxq_subtask(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;

	if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state))
		return;

	if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX))
		return;

	clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state);

	if (ice_ctrlq_pending(hw, &hw->mailboxq))
		__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX);

	ice_flush(hw);
}

/**
 * ice_service_task_schedule - schedule the service task to wake up
 * @pf: board private structure
 *
 * If not already scheduled, this puts the task into the work queue.
 */
static void ice_service_task_schedule(struct ice_pf *pf)
{
	if (!test_bit(__ICE_SERVICE_DIS, pf->state) &&
	    !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) &&
	    !test_bit(__ICE_NEEDS_RESTART, pf->state))
		queue_work(ice_wq, &pf->serv_task);
}

/**
 * ice_service_task_complete - finish up the service task
 * @pf: board private structure
 */
static void ice_service_task_complete(struct ice_pf *pf)
{
	WARN_ON(!test_bit(__ICE_SERVICE_SCHED, pf->state));

	/* force memory (pf->state) to sync before next service task */
	smp_mb__before_atomic();
	clear_bit(__ICE_SERVICE_SCHED, pf->state);
}

/**
 * ice_service_task_stop - stop service task and cancel works
 * @pf: board private structure
 */
static void ice_service_task_stop(struct ice_pf *pf)
{
	set_bit(__ICE_SERVICE_DIS, pf->state);

	if (pf->serv_tmr.function)
		del_timer_sync(&pf->serv_tmr);
	if (pf->serv_task.func)
		cancel_work_sync(&pf->serv_task);

	clear_bit(__ICE_SERVICE_SCHED, pf->state);
}

/**
 * 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
 */
static void ice_service_timer(struct timer_list *t)
{
	struct ice_pf *pf = from_timer(pf, t, serv_tmr);

	mod_timer(&pf->serv_tmr, round_jiffies(pf->serv_tmr_period + jiffies));
	ice_service_task_schedule(pf);
}

/**
 * ice_handle_mdd_event - handle malicious driver detect event
 * @pf: pointer to the PF structure
 *
 * Called from service task. OICR interrupt handler indicates MDD event
 */
static void ice_handle_mdd_event(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;
	bool mdd_detected = false;
	u32 reg;
	int i;

	if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state))
		return;

	/* find what triggered the MDD event */
	reg = rd32(hw, GL_MDET_TX_PQM);
	if (reg & GL_MDET_TX_PQM_VALID_M) {
		u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >>
				GL_MDET_TX_PQM_PF_NUM_S;
		u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >>
				GL_MDET_TX_PQM_VF_NUM_S;
		u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >>
				GL_MDET_TX_PQM_MAL_TYPE_S;
		u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >>
				GL_MDET_TX_PQM_QNUM_S);

		if (netif_msg_tx_err(pf))
			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
				 event, queue, pf_num, vf_num);
		wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
		mdd_detected = true;
	}

	reg = rd32(hw, GL_MDET_TX_TCLAN);
	if (reg & GL_MDET_TX_TCLAN_VALID_M) {
		u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
				GL_MDET_TX_TCLAN_PF_NUM_S;
		u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >>
				GL_MDET_TX_TCLAN_VF_NUM_S;
		u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >>
				GL_MDET_TX_TCLAN_MAL_TYPE_S;
		u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
				GL_MDET_TX_TCLAN_QNUM_S);

		if (netif_msg_rx_err(pf))
			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
				 event, queue, pf_num, vf_num);
		wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
		mdd_detected = true;
	}

	reg = rd32(hw, GL_MDET_RX);
	if (reg & GL_MDET_RX_VALID_M) {
		u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >>
				GL_MDET_RX_PF_NUM_S;
		u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >>
				GL_MDET_RX_VF_NUM_S;
		u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >>
				GL_MDET_RX_MAL_TYPE_S;
		u16 queue = ((reg & GL_MDET_RX_QNUM_M) >>
				GL_MDET_RX_QNUM_S);

		if (netif_msg_rx_err(pf))
			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
				 event, queue, pf_num, vf_num);
		wr32(hw, GL_MDET_RX, 0xffffffff);
		mdd_detected = true;
	}

	if (mdd_detected) {
		bool pf_mdd_detected = false;

		reg = rd32(hw, PF_MDET_TX_PQM);
		if (reg & PF_MDET_TX_PQM_VALID_M) {
			wr32(hw, PF_MDET_TX_PQM, 0xFFFF);
			dev_info(dev, "TX driver issue detected, PF reset issued\n");
			pf_mdd_detected = true;
		}

		reg = rd32(hw, PF_MDET_TX_TCLAN);
		if (reg & PF_MDET_TX_TCLAN_VALID_M) {
			wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF);
			dev_info(dev, "TX driver issue detected, PF reset issued\n");
			pf_mdd_detected = true;
		}

		reg = rd32(hw, PF_MDET_RX);
		if (reg & PF_MDET_RX_VALID_M) {
			wr32(hw, PF_MDET_RX, 0xFFFF);
			dev_info(dev, "RX driver issue detected, PF reset issued\n");
			pf_mdd_detected = true;
		}
		/* Queue belongs to the PF initiate a reset */
		if (pf_mdd_detected) {
			set_bit(__ICE_NEEDS_RESTART, pf->state);
			ice_service_task_schedule(pf);
		}
	}

	/* check to see if one of the VFs caused the MDD */
	ice_for_each_vf(pf, i) {
		struct ice_vf *vf = &pf->vf[i];

		bool vf_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_mdd_detected = true;
			dev_info(dev, "TX driver issue detected on VF %d\n",
				 i);
		}

		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_mdd_detected = true;
			dev_info(dev, "TX driver issue detected on VF %d\n",
				 i);
		}

		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_mdd_detected = true;
			dev_info(dev, "TX driver issue detected on VF %d\n",
				 i);
		}

		reg = rd32(hw, VP_MDET_RX(i));
		if (reg & VP_MDET_RX_VALID_M) {
			wr32(hw, VP_MDET_RX(i), 0xFFFF);
			vf_mdd_detected = true;
			dev_info(dev, "RX driver issue detected on VF %d\n",
				 i);
		}

		if (vf_mdd_detected) {
			vf->num_mdd_events++;
			if (vf->num_mdd_events &&
			    vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD)
				dev_info(dev,
					 "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n",
					 i, vf->num_mdd_events);
		}
	}
}

/**
 * ice_force_phys_link_state - Force the physical link state
 * @vsi: VSI to force the physical link state to up/down
 * @link_up: true/false indicates to set the physical link to up/down
 *
 * Force the physical link state by getting the current PHY capabilities from
 * hardware and setting the PHY config based on the determined capabilities. If
 * link changes a link event will be triggered because both the Enable Automatic
 * Link Update and LESM Enable bits are set when setting the PHY capabilities.
 *
 * Returns 0 on success, negative on failure
 */
static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
{
	struct ice_aqc_get_phy_caps_data *pcaps;
	struct ice_aqc_set_phy_cfg_data *cfg;
	struct ice_port_info *pi;
	struct device *dev;
	int retcode;

	if (!vsi || !vsi->port_info || !vsi->back)
		return -EINVAL;
	if (vsi->type != ICE_VSI_PF)
		return 0;

	dev = &vsi->back->pdev->dev;

	pi = vsi->port_info;

	pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL);
	if (!pcaps)
		return -ENOMEM;

	retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
				      NULL);
	if (retcode) {
		dev_err(dev,
			"Failed to get phy capabilities, VSI %d error %d\n",
			vsi->vsi_num, retcode);
		retcode = -EIO;
		goto out;
	}

	/* No change in link */
	if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) &&
	    link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
		goto out;

	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
	if (!cfg) {
		retcode = -ENOMEM;
		goto out;
	}

	cfg->phy_type_low = pcaps->phy_type_low;
	cfg->phy_type_high = pcaps->phy_type_high;
	cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
	cfg->low_power_ctrl = pcaps->low_power_ctrl;
	cfg->eee_cap = pcaps->eee_cap;
	cfg->eeer_value = pcaps->eeer_value;
	cfg->link_fec_opt = pcaps->link_fec_options;
	if (link_up)
		cfg->caps |= ICE_AQ_PHY_ENA_LINK;
	else
		cfg->caps &= ~ICE_AQ_PHY_ENA_LINK;

	retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL);
	if (retcode) {
		dev_err(dev, "Failed to set phy config, VSI %d error %d\n",
			vsi->vsi_num, retcode);
		retcode = -EIO;
	}

	kfree(cfg);
out:
	kfree(pcaps);
	return retcode;
}

/**
 * ice_check_media_subtask - Check for media; bring link up if detected.
 * @pf: pointer to PF struct
 */
static void ice_check_media_subtask(struct ice_pf *pf)
{
	struct ice_port_info *pi;
	struct ice_vsi *vsi;
	int err;

	vsi = ice_get_main_vsi(pf);
	if (!vsi)
		return;

	/* No need to check for media if it's already present or the interface
	 * is down
	 */
	if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) ||
	    test_bit(__ICE_DOWN, vsi->state))
		return;

	/* Refresh link info and check if media is present */
	pi = vsi->port_info;
	err = ice_update_link_info(pi);
	if (err)
		return;

	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
		err = ice_force_phys_link_state(vsi, true);
		if (err)
			return;
		clear_bit(ICE_FLAG_NO_MEDIA, pf->flags);

		/* A Link Status Event will be generated; the event handler
		 * will complete bringing the interface up
		 */
	}
}

/**
 * ice_service_task - manage and run subtasks
 * @work: pointer to work_struct contained by the PF struct
 */
static void ice_service_task(struct work_struct *work)
{
	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
	unsigned long start_time = jiffies;

	/* subtasks */

	/* process reset requests first */
	ice_reset_subtask(pf);

	/* bail if a reset/recovery cycle is pending or rebuild failed */
	if (ice_is_reset_in_progress(pf->state) ||
	    test_bit(__ICE_SUSPENDED, pf->state) ||
	    test_bit(__ICE_NEEDS_RESTART, pf->state)) {
		ice_service_task_complete(pf);
		return;
	}

	ice_clean_adminq_subtask(pf);
	ice_check_media_subtask(pf);
	ice_check_for_hang_subtask(pf);
	ice_sync_fltr_subtask(pf);
	ice_handle_mdd_event(pf);
	ice_watchdog_subtask(pf);

	if (ice_is_safe_mode(pf)) {
		ice_service_task_complete(pf);
		return;
	}

	ice_process_vflr_event(pf);
	ice_clean_mailboxq_subtask(pf);

	/* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */
	ice_service_task_complete(pf);

	/* If the tasks have taken longer than one service timer period
	 * or there is more work to be done, reset the service timer to
	 * schedule the service task now.
	 */
	if (time_after(jiffies, (start_time + pf->serv_tmr_period)) ||
	    test_bit(__ICE_MDD_EVENT_PENDING, pf->state) ||
	    test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
	    test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) ||
	    test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state))
		mod_timer(&pf->serv_tmr, jiffies);
}

/**
 * ice_set_ctrlq_len - helper function to set controlq length
 * @hw: pointer to the HW instance
 */
static void ice_set_ctrlq_len(struct ice_hw *hw)
{
	hw->adminq.num_rq_entries = ICE_AQ_LEN;
	hw->adminq.num_sq_entries = ICE_AQ_LEN;
	hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN;
	hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN;
	hw->mailboxq.num_rq_entries = ICE_MBXRQ_LEN;
	hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN;
	hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
	hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
}

/**
 * ice_schedule_reset - schedule a reset
 * @pf: board private structure
 * @reset: reset being requested
 */
int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
{
	struct device *dev = ice_pf_to_dev(pf);

	/* bail out if earlier reset has failed */
	if (test_bit(__ICE_RESET_FAILED, pf->state)) {
		dev_dbg(dev, "earlier reset has failed\n");
		return -EIO;
	}
	/* bail if reset/recovery already in progress */
	if (ice_is_reset_in_progress(pf->state)) {
		dev_dbg(dev, "Reset already in progress\n");
		return -EBUSY;
	}

	switch (reset) {
	case ICE_RESET_PFR:
		set_bit(__ICE_PFR_REQ, pf->state);
		break;
	case ICE_RESET_CORER:
		set_bit(__ICE_CORER_REQ, pf->state);
		break;
	case ICE_RESET_GLOBR:
		set_bit(__ICE_GLOBR_REQ, pf->state);
		break;
	default:
		return -EINVAL;
	}

	ice_service_task_schedule(pf);
	return 0;
}

/**
 * ice_irq_affinity_notify - Callback for affinity changes
 * @notify: context as to what irq was changed
 * @mask: the new affinity mask
 *
 * 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)
{
	struct ice_q_vector *q_vector =
		container_of(notify, struct ice_q_vector, affinity_notify);

	cpumask_copy(&q_vector->affinity_mask, mask);
}

/**
 * ice_irq_affinity_release - Callback for affinity notifier release
 * @ref: internal core kernel usage
 *
 * This is a callback function used by the irq_set_affinity_notifier function
 * to inform the current notification subscriber that they will no longer
 * receive notifications.
 */
static void ice_irq_affinity_release(struct kref __always_unused *ref) {}

/**
 * ice_vsi_ena_irq - Enable IRQ for the given VSI
 * @vsi: the VSI being configured
 */
static int ice_vsi_ena_irq(struct ice_vsi *vsi)
{
	struct ice_hw *hw = &vsi->back->hw;
	int i;

	ice_for_each_q_vector(vsi, i)
		ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);

	ice_flush(hw);
	return 0;
}

/**
 * ice_vsi_req_irq_msix - get MSI-X vectors from the OS for the VSI
 * @vsi: the VSI being configured
 * @basename: name for the vector
 */
static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
{
	int q_vectors = vsi->num_q_vectors;
	struct ice_pf *pf = vsi->back;
	int base = vsi->base_vector;
	struct device *dev;
	int rx_int_idx = 0;
	int tx_int_idx = 0;
	int vector, err;
	int irq_num;

	dev = ice_pf_to_dev(pf);
	for (vector = 0; vector < q_vectors; vector++) {
		struct ice_q_vector *q_vector = vsi->q_vectors[vector];

		irq_num = pf->msix_entries[base + vector].vector;

		if (q_vector->tx.ring && q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", basename, "TxRx", rx_int_idx++);
			tx_int_idx++;
		} else if (q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", basename, "rx", rx_int_idx++);
		} else if (q_vector->tx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", basename, "tx", tx_int_idx++);
		} else {
			/* skip this unused q_vector */
			continue;
		}
		err = devm_request_irq(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);
			goto free_q_irqs;
		}

		/* register for affinity change notifications */
		q_vector->affinity_notify.notify = ice_irq_affinity_notify;
		q_vector->affinity_notify.release = ice_irq_affinity_release;
		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);

		/* assign the mask for this irq */
		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
	}

	vsi->irqs_ready = true;
	return 0;

free_q_irqs:
	while (vector) {
		vector--;
		irq_num = pf->msix_entries[base + vector].vector,
		irq_set_affinity_notifier(irq_num, NULL);
		irq_set_affinity_hint(irq_num, NULL);
		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
	}
	return err;
}

/**
 * ice_xdp_alloc_setup_rings - Allocate and setup Tx rings for XDP
 * @vsi: VSI to setup Tx rings used by XDP
 *
 * Return 0 on success and negative value on error
 */
static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
{
	struct device *dev = &vsi->back->pdev->dev;
	int i;

	for (i = 0; i < vsi->num_xdp_txq; i++) {
		u16 xdp_q_idx = vsi->alloc_txq + i;
		struct ice_ring *xdp_ring;

		xdp_ring = kzalloc(sizeof(*xdp_ring), GFP_KERNEL);

		if (!xdp_ring)
			goto free_xdp_rings;

		xdp_ring->q_index = xdp_q_idx;
		xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx];
		xdp_ring->ring_active = false;
		xdp_ring->vsi = vsi;
		xdp_ring->netdev = NULL;
		xdp_ring->dev = dev;
		xdp_ring->count = vsi->num_tx_desc;
		vsi->xdp_rings[i] = xdp_ring;
		if (ice_setup_tx_ring(xdp_ring))
			goto free_xdp_rings;
		ice_set_ring_xdp(xdp_ring);
		xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring);
	}

	return 0;

free_xdp_rings:
	for (; i >= 0; i--)
		if (vsi->xdp_rings[i] && vsi->xdp_rings[i]->desc)
			ice_free_tx_ring(vsi->xdp_rings[i]);
	return -ENOMEM;
}

/**
 * ice_vsi_assign_bpf_prog - set or clear bpf prog pointer on VSI
 * @vsi: VSI to set the bpf prog on
 * @prog: the bpf prog pointer
 */
static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
{
	struct bpf_prog *old_prog;
	int i;

	old_prog = xchg(&vsi->xdp_prog, prog);
	if (old_prog)
		bpf_prog_put(old_prog);

	ice_for_each_rxq(vsi, i)
		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
}

/**
 * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
 * @vsi: VSI to bring up Tx rings used by XDP
 * @prog: bpf program that will be assigned to VSI
 *
 * Return 0 on success and negative value on error
 */
int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
{
	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
	int xdp_rings_rem = vsi->num_xdp_txq;
	struct ice_pf *pf = vsi->back;
	struct ice_qs_cfg xdp_qs_cfg = {
		.qs_mutex = &pf->avail_q_mutex,
		.pf_map = pf->avail_txqs,
		.pf_map_size = pf->max_pf_txqs,
		.q_count = vsi->num_xdp_txq,
		.scatter_count = ICE_MAX_SCATTER_TXQS,
		.vsi_map = vsi->txq_map,
		.vsi_map_offset = vsi->alloc_txq,
		.mapping_mode = ICE_VSI_MAP_CONTIG
	};
	enum ice_status status;
	struct device *dev;
	int i, v_idx;

	dev = ice_pf_to_dev(pf);
	vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq,
				      sizeof(*vsi->xdp_rings), GFP_KERNEL);
	if (!vsi->xdp_rings)
		return -ENOMEM;

	vsi->xdp_mapping_mode = xdp_qs_cfg.mapping_mode;
	if (__ice_vsi_get_qs(&xdp_qs_cfg))
		goto err_map_xdp;

	if (ice_xdp_alloc_setup_rings(vsi))
		goto clear_xdp_rings;

	/* follow the logic from ice_vsi_map_rings_to_vectors */
	ice_for_each_q_vector(vsi, v_idx) {
		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
		int xdp_rings_per_v, q_id, q_base;

		xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
					       vsi->num_q_vectors - v_idx);
		q_base = vsi->num_xdp_txq - xdp_rings_rem;

		for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
			struct ice_ring *xdp_ring = vsi->xdp_rings[q_id];

			xdp_ring->q_vector = q_vector;
			xdp_ring->next = q_vector->tx.ring;
			q_vector->tx.ring = xdp_ring;
		}
		xdp_rings_rem -= xdp_rings_per_v;
	}

	/* omit the scheduler update if in reset path; XDP queues will be
	 * taken into account at the end of ice_vsi_rebuild, where
	 * ice_cfg_vsi_lan is being called
	 */
	if (ice_is_reset_in_progress(pf->state))
		return 0;

	/* tell the Tx scheduler that right now we have
	 * additional queues
	 */
	for (i = 0; i < vsi->tc_cfg.numtc; i++)
		max_txqs[i] = vsi->num_txq + vsi->num_xdp_txq;

	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
				 max_txqs);
	if (status) {
		dev_err(dev, "Failed VSI LAN queue config for XDP, error:%d\n",
			status);
		goto clear_xdp_rings;
	}
	ice_vsi_assign_bpf_prog(vsi, prog);

	return 0;
clear_xdp_rings:
	for (i = 0; i < vsi->num_xdp_txq; i++)
		if (vsi->xdp_rings[i]) {
			kfree_rcu(vsi->xdp_rings[i], rcu);
			vsi->xdp_rings[i] = NULL;
		}

err_map_xdp:
	mutex_lock(&pf->avail_q_mutex);
	for (i = 0; i < vsi->num_xdp_txq; i++) {
		clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs);
		vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX;
	}
	mutex_unlock(&pf->avail_q_mutex);

	devm_kfree(dev, vsi->xdp_rings);
	return -ENOMEM;
}

/**
 * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings
 * @vsi: VSI to remove XDP rings
 *
 * Detach XDP rings from irq vectors, clean up the PF bitmap and free
 * resources
 */
int ice_destroy_xdp_rings(struct ice_vsi *vsi)
{
	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
	struct ice_pf *pf = vsi->back;
	int i, v_idx;

	/* q_vectors are freed in reset path so there's no point in detaching
	 * rings; in case of rebuild being triggered not from reset reset bits
	 * in pf->state won't be set, so additionally check first q_vector
	 * against NULL
	 */
	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
		goto free_qmap;

	ice_for_each_q_vector(vsi, v_idx) {
		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
		struct ice_ring *ring;

		ice_for_each_ring(ring, q_vector->tx)
			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
				break;

		/* restore the value of last node prior to XDP setup */
		q_vector->tx.ring = ring;
	}

free_qmap:
	mutex_lock(&pf->avail_q_mutex);
	for (i = 0; i < vsi->num_xdp_txq; i++) {
		clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs);
		vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX;
	}
	mutex_unlock(&pf->avail_q_mutex);

	for (i = 0; i < vsi->num_xdp_txq; i++)
		if (vsi->xdp_rings[i]) {
			if (vsi->xdp_rings[i]->desc)
				ice_free_tx_ring(vsi->xdp_rings[i]);
			kfree_rcu(vsi->xdp_rings[i], rcu);
			vsi->xdp_rings[i] = NULL;
		}

	devm_kfree(ice_pf_to_dev(pf), vsi->xdp_rings);
	vsi->xdp_rings = NULL;

	if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
		return 0;

	ice_vsi_assign_bpf_prog(vsi, NULL);

	/* notify Tx scheduler that we destroyed XDP queues and bring
	 * back the old number of child nodes
	 */
	for (i = 0; i < vsi->tc_cfg.numtc; i++)
		max_txqs[i] = vsi->num_txq;

	return ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
			       max_txqs);
}

/**
 * ice_xdp_setup_prog - Add or remove XDP eBPF program
 * @vsi: VSI to setup XDP for
 * @prog: XDP program
 * @extack: netlink extended ack
 */
static int
ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
		   struct netlink_ext_ack *extack)
{
	int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
	bool if_running = netif_running(vsi->netdev);
	int ret = 0, xdp_ring_err = 0;

	if (frame_size > vsi->rx_buf_len) {
		NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP");
		return -EOPNOTSUPP;
	}

	/* need to stop netdev while setting up the program for Rx rings */
	if (if_running && !test_and_set_bit(__ICE_DOWN, vsi->state)) {
		ret = ice_down(vsi);
		if (ret) {
			NL_SET_ERR_MSG_MOD(extack,
					   "Preparing device for XDP attach failed");
			return ret;
		}
	}

	if (!ice_is_xdp_ena_vsi(vsi) && prog) {
		vsi->num_xdp_txq = vsi->alloc_txq;
		xdp_ring_err = ice_prepare_xdp_rings(vsi, prog);
		if (xdp_ring_err)
			NL_SET_ERR_MSG_MOD(extack,
					   "Setting up XDP Tx resources failed");
	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
		xdp_ring_err = ice_destroy_xdp_rings(vsi);
		if (xdp_ring_err)
			NL_SET_ERR_MSG_MOD(extack,
					   "Freeing XDP Tx resources failed");
	} else {
		ice_vsi_assign_bpf_prog(vsi, prog);
	}

	if (if_running)
		ret = ice_up(vsi);

	if (!ret && prog && vsi->xsk_umems) {
		int i;

		ice_for_each_rxq(vsi, i) {
			struct ice_ring *rx_ring = vsi->rx_rings[i];

			if (rx_ring->xsk_umem)
				napi_schedule(&rx_ring->q_vector->napi);
		}
	}

	return (ret || xdp_ring_err) ? -ENOMEM : 0;
}

/**
 * ice_xdp - implements XDP handler
 * @dev: netdevice
 * @xdp: XDP command
 */
static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
	struct ice_netdev_priv *np = netdev_priv(dev);
	struct ice_vsi *vsi = np->vsi;

	if (vsi->type != ICE_VSI_PF) {
		NL_SET_ERR_MSG_MOD(xdp->extack,
				   "XDP can be loaded only on PF VSI");
		return -EINVAL;
	}

	switch (xdp->command) {
	case XDP_SETUP_PROG:
		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
	case XDP_QUERY_PROG:
		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
		return 0;
	case XDP_SETUP_XSK_UMEM:
		return ice_xsk_umem_setup(vsi, xdp->xsk.umem,
					  xdp->xsk.queue_id);
	default:
		return -EINVAL;
	}
}

/**
 * ice_ena_misc_vector - enable the non-queue interrupts
 * @pf: board private structure
 */
static void ice_ena_misc_vector(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;
	u32 val;

	/* clear things first */
	wr32(hw, PFINT_OICR_ENA, 0);	/* disable all */
	rd32(hw, PFINT_OICR);		/* read to clear */

	val = (PFINT_OICR_ECC_ERR_M |
	       PFINT_OICR_MAL_DETECT_M |
	       PFINT_OICR_GRST_M |
	       PFINT_OICR_PCI_EXCEPTION_M |
	       PFINT_OICR_VFLR_M |
	       PFINT_OICR_HMC_ERR_M |
	       PFINT_OICR_PE_CRITERR_M);

	wr32(hw, PFINT_OICR_ENA, val);

	/* SW_ITR_IDX = 0, but don't change INTENA */
	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
}

/**
 * ice_misc_intr - misc interrupt handler
 * @irq: interrupt number
 * @data: pointer to a q_vector
 */
static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
{
	struct ice_pf *pf = (struct ice_pf *)data;
	struct ice_hw *hw = &pf->hw;
	irqreturn_t ret = IRQ_NONE;
	struct device *dev;
	u32 oicr, ena_mask;

	dev = ice_pf_to_dev(pf);
	set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);
	set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state);

	oicr = rd32(hw, PFINT_OICR);
	ena_mask = rd32(hw, PFINT_OICR_ENA);

	if (oicr & PFINT_OICR_SWINT_M) {
		ena_mask &= ~PFINT_OICR_SWINT_M;
		pf->sw_int_count++;
	}

	if (oicr & PFINT_OICR_MAL_DETECT_M) {
		ena_mask &= ~PFINT_OICR_MAL_DETECT_M;
		set_bit(__ICE_MDD_EVENT_PENDING, pf->state);
	}
	if (oicr & PFINT_OICR_VFLR_M) {
		ena_mask &= ~PFINT_OICR_VFLR_M;
		set_bit(__ICE_VFLR_EVENT_PENDING, pf->state);
	}

	if (oicr & PFINT_OICR_GRST_M) {
		u32 reset;

		/* we have a reset warning */
		ena_mask &= ~PFINT_OICR_GRST_M;
		reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
			GLGEN_RSTAT_RESET_TYPE_S;

		if (reset == ICE_RESET_CORER)
			pf->corer_count++;
		else if (reset == ICE_RESET_GLOBR)
			pf->globr_count++;
		else if (reset == ICE_RESET_EMPR)
			pf->empr_count++;
		else
			dev_dbg(dev, "Invalid reset type %d\n", reset);

		/* If a reset cycle isn't already in progress, we set a bit in
		 * pf->state so that the service task can start a reset/rebuild.
		 * We also make note of which reset happened so that peer
		 * devices/drivers can be informed.
		 */
		if (!test_and_set_bit(__ICE_RESET_OICR_RECV, pf->state)) {
			if (reset == ICE_RESET_CORER)
				set_bit(__ICE_CORER_RECV, pf->state);
			else if (reset == ICE_RESET_GLOBR)
				set_bit(__ICE_GLOBR_RECV, pf->state);
			else
				set_bit(__ICE_EMPR_RECV, pf->state);

			/* There are couple of different bits at play here.
			 * hw->reset_ongoing indicates whether the hardware is
			 * in reset. This is set to true when a reset interrupt
			 * is received and set back to false after the driver
			 * has determined that the hardware is out of reset.
			 *
			 * __ICE_RESET_OICR_RECV in pf->state indicates
			 * that a post reset rebuild is required before the
			 * driver is operational again. This is set above.
			 *
			 * As this is the start of the reset/rebuild cycle, set
			 * both to indicate that.
			 */
			hw->reset_ongoing = true;
		}
	}

	if (oicr & PFINT_OICR_HMC_ERR_M) {
		ena_mask &= ~PFINT_OICR_HMC_ERR_M;
		dev_dbg(dev, "HMC Error interrupt - info 0x%x, data 0x%x\n",
			rd32(hw, PFHMC_ERRORINFO),
			rd32(hw, PFHMC_ERRORDATA));
	}

	/* Report any remaining unexpected interrupts */
	oicr &= ena_mask;
	if (oicr) {
		dev_dbg(dev, "unhandled interrupt oicr=0x%08x\n", oicr);
		/* If a critical error is pending there is no choice but to
		 * reset the device.
		 */
		if (oicr & (PFINT_OICR_PE_CRITERR_M |
			    PFINT_OICR_PCI_EXCEPTION_M |
			    PFINT_OICR_ECC_ERR_M)) {
			set_bit(__ICE_PFR_REQ, pf->state);
			ice_service_task_schedule(pf);
		}
	}
	ret = IRQ_HANDLED;

	if (!test_bit(__ICE_DOWN, pf->state)) {
		ice_service_task_schedule(pf);
		ice_irq_dynamic_ena(hw, NULL, NULL);
	}

	return ret;
}

/**
 * ice_dis_ctrlq_interrupts - disable control queue interrupts
 * @hw: pointer to HW structure
 */
static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
{
	/* disable Admin queue Interrupt causes */
	wr32(hw, PFINT_FW_CTL,
	     rd32(hw, PFINT_FW_CTL) & ~PFINT_FW_CTL_CAUSE_ENA_M);

	/* disable Mailbox queue Interrupt causes */
	wr32(hw, PFINT_MBX_CTL,
	     rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M);

	/* disable Control queue Interrupt causes */
	wr32(hw, PFINT_OICR_CTL,
	     rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M);

	ice_flush(hw);
}

/**
 * ice_free_irq_msix_misc - Unroll misc vector setup
 * @pf: board private structure
 */
static void ice_free_irq_msix_misc(struct ice_pf *pf)
{
	struct ice_hw *hw = &pf->hw;

	ice_dis_ctrlq_interrupts(hw);

	/* disable OICR interrupt */
	wr32(hw, PFINT_OICR_ENA, 0);
	ice_flush(hw);

	if (pf->msix_entries) {
		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
		devm_free_irq(ice_pf_to_dev(pf),
			      pf->msix_entries[pf->oicr_idx].vector, pf);
	}

	pf->num_avail_sw_msix += 1;
	ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
}

/**
 * ice_ena_ctrlq_interrupts - enable control queue interrupts
 * @hw: pointer to HW structure
 * @reg_idx: HW vector index to associate the control queue interrupts with
 */
static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
{
	u32 val;

	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 = ((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 = ((reg_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
	       PFINT_MBX_CTL_CAUSE_ENA_M);
	wr32(hw, PFINT_MBX_CTL, val);

	ice_flush(hw);
}

/**
 * ice_req_irq_msix_misc - Setup the misc vector to handle non queue events
 * @pf: board private structure
 *
 * This sets up the handler for MSIX 0, which is used to manage the
 * non-queue interrupts, e.g. AdminQ and errors. This is not used
 * when in MSI or Legacy interrupt mode.
 */
static int ice_req_irq_msix_misc(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;
	int oicr_idx, err = 0;

	if (!pf->int_name[0])
		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
			 dev_driver_string(dev), dev_name(dev));

	/* Do not request IRQ but do enable OICR interrupt since settings are
	 * lost during reset. Note that this function is called only during
	 * rebuild path and not while reset is in progress.
	 */
	if (ice_is_reset_in_progress(pf->state))
		goto skip_req_irq;

	/* reserve one vector in irq_tracker for misc interrupts */
	oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
	if (oicr_idx < 0)
		return oicr_idx;

	pf->num_avail_sw_msix -= 1;
	pf->oicr_idx = oicr_idx;

	err = devm_request_irq(dev, pf->msix_entries[pf->oicr_idx].vector,
			       ice_misc_intr, 0, pf->int_name, pf);
	if (err) {
		dev_err(dev, "devm_request_irq for %s failed: %d\n",
			pf->int_name, err);
		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
		pf->num_avail_sw_msix += 1;
		return err;
	}

skip_req_irq:
	ice_ena_misc_vector(pf);

	ice_ena_ctrlq_interrupts(hw, pf->oicr_idx);
	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);

	ice_flush(hw);
	ice_irq_dynamic_ena(hw, NULL, NULL);

	return 0;
}

/**
 * ice_napi_add - register NAPI handler for the VSI
 * @vsi: VSI for which NAPI handler is to be registered
 *
 * This function is only called in the driver's load path. Registering the NAPI
 * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume,
 * reset/rebuild, etc.)
 */
static void ice_napi_add(struct ice_vsi *vsi)
{
	int v_idx;

	if (!vsi->netdev)
		return;

	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);
}

/**
 * ice_set_ops - set netdev and ethtools ops for the given netdev
 * @netdev: netdev instance
 */
static void ice_set_ops(struct net_device *netdev)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);

	if (ice_is_safe_mode(pf)) {
		netdev->netdev_ops = &ice_netdev_safe_mode_ops;
		ice_set_ethtool_safe_mode_ops(netdev);
		return;
	}

	netdev->netdev_ops = &ice_netdev_ops;
	ice_set_ethtool_ops(netdev);
}

/**
 * ice_set_netdev_features - set features for the given netdev
 * @netdev: netdev instance
 */
static void ice_set_netdev_features(struct net_device *netdev)
{
	struct ice_pf *pf = ice_netdev_to_pf(netdev);
	netdev_features_t csumo_features;
	netdev_features_t vlano_features;
	netdev_features_t dflt_features;
	netdev_features_t tso_features;

	if (ice_is_safe_mode(pf)) {
		/* safe mode */
		netdev->features = NETIF_F_SG | NETIF_F_HIGHDMA;
		netdev->hw_features = netdev->features;
		return;
	}

	dflt_features = NETIF_F_SG	|
			NETIF_F_HIGHDMA	|
			NETIF_F_RXHASH;

	csumo_features = NETIF_F_RXCSUM	  |
			 NETIF_F_IP_CSUM  |
			 NETIF_F_SCTP_CRC |
			 NETIF_F_IPV6_CSUM;

	vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
			 NETIF_F_HW_VLAN_CTAG_TX     |
			 NETIF_F_HW_VLAN_CTAG_RX;

	tso_features = NETIF_F_TSO		|
		       NETIF_F_GSO_UDP_L4;

	/* set features that user can change */
	netdev->hw_features = dflt_features | csumo_features |
			      vlano_features | tso_features;

	/* enable features */
	netdev->features |= netdev->hw_features;
	/* encap and VLAN devices inherit default, csumo and tso features */
	netdev->hw_enc_features |= dflt_features | csumo_features |
				   tso_features;
	netdev->vlan_features |= dflt_features | csumo_features |
				 tso_features;
}

/**
 * ice_cfg_netdev - Allocate, configure and register a netdev
 * @vsi: the VSI associated with the new netdev
 *
 * Returns 0 on success, negative value on failure
 */
static int ice_cfg_netdev(struct ice_vsi *vsi)
{
	struct ice_pf *pf = vsi->back;
	struct ice_netdev_priv *np;
	struct net_device *netdev;
	u8 mac_addr[ETH_ALEN];
	int err;

	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
				    vsi->alloc_rxq);
	if (!netdev)
		return -ENOMEM;

	vsi->netdev = netdev;
	np = netdev_priv(netdev);
	np->vsi = vsi;

	ice_set_netdev_features(netdev);

	ice_set_ops(netdev);

	if (vsi->type == ICE_VSI_PF) {
		SET_NETDEV_DEV(netdev, ice_pf_to_dev(pf));
		ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
		ether_addr_copy(netdev->dev_addr, mac_addr);
		ether_addr_copy(netdev->perm_addr, mac_addr);
	}

	netdev->priv_flags |= IFF_UNICAST_FLT;

	/* Setup netdev TC information */
	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);

	/* setup watchdog timeout value to be 5 second */
	netdev->watchdog_timeo = 5 * HZ;

	netdev->min_mtu = ETH_MIN_MTU;
	netdev->max_mtu = ICE_MAX_MTU;

	err = register_netdev(vsi->netdev);
	if (err)
		return err;

	netif_carrier_off(vsi->netdev);

	/* make sure transmit queues start off as stopped */
	netif_tx_stop_all_queues(vsi->netdev);

	return 0;
}

/**
 * ice_fill_rss_lut - Fill the RSS lookup table with default values
 * @lut: Lookup table
 * @rss_table_size: Lookup table size
 * @rss_size: Range of queue number for hashing
 */
void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size)
{
	u16 i;

	for (i = 0; i < rss_table_size; i++)
		lut[i] = i % rss_size;
}

/**
 * ice_pf_vsi_setup - Set up a PF VSI
 * @pf: board private structure
 * @pi: pointer to the port_info instance
 *
 * Returns pointer to the successfully allocated VSI software struct
 * on success, otherwise returns NULL on failure.
 */
static struct ice_vsi *
ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
{
	return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID);
}

/**
 * ice_lb_vsi_setup - Set up a loopback VSI
 * @pf: board private structure
 * @pi: pointer to the port_info instance
 *
 * Returns pointer to the successfully allocated VSI software struct
 * on success, otherwise returns NULL on failure.
 */
struct ice_vsi *
ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
{
	return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID);
}

/**
 * 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
 *
 * 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)
{
	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",
			   vid, VLAN_N_VID);
		return -EINVAL;
	}

	if (vsi->info.pvid)
		return -EINVAL;

	/* Enable VLAN pruning when VLAN 0 is added */
	if (unlikely(!vid)) {
		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
	 * needed to continue allowing all untagged packets since VLAN prune
	 * list is applied to all packets by the switch
	 */
	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
 * @netdev: network interface to be adjusted
 * @proto: unused protocol
 * @vid: VLAN ID to be removed
 *
 * 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)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	int ret;

	if (vsi->info.pvid)
		return -EINVAL;

	/* Make sure ice_vsi_kill_vlan is successful before updating VLAN
	 * information
	 */
	ret = ice_vsi_kill_vlan(vsi, vid);
	if (ret)
		return ret;

	/* Disable VLAN pruning when VLAN 0 is removed */
	if (unlikely(!vid))
		ret = ice_cfg_vlan_pruning(vsi, false, false);

	vsi->vlan_ena = false;
	set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
	return ret;
}

/**
 * ice_setup_pf_sw - Setup the HW switch on startup or after reset
 * @pf: board private structure
 *
 * Returns 0 on success, negative value on failure
 */
static int ice_setup_pf_sw(struct ice_pf *pf)
{
	struct ice_vsi *vsi;
	int status = 0;

	if (ice_is_reset_in_progress(pf->state))
		return -EBUSY;

	vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
	if (!vsi) {
		status = -ENOMEM;
		goto unroll_vsi_setup;
	}

	status = ice_cfg_netdev(vsi);
	if (status) {
		status = -ENODEV;
		goto unroll_vsi_setup;
	}
	/* netdev has to be configured before setting frame size */
	ice_vsi_cfg_frame_size(vsi);

	/* Setup DCB netlink interface */
	ice_dcbnl_setup(vsi);

	/* registering the NAPI handler requires both the queues and
	 * netdev to be created, which are done in ice_pf_vsi_setup()
	 * and ice_cfg_netdev() respectively
	 */
	ice_napi_add(vsi);

	status = ice_init_mac_fltr(pf);
	if (status)
		goto unroll_napi_add;

	return status;

unroll_napi_add:
	if (vsi) {
		ice_napi_del(vsi);
		if (vsi->netdev) {
			if (vsi->netdev->reg_state == NETREG_REGISTERED)
				unregister_netdev(vsi->netdev);
			free_netdev(vsi->netdev);
			vsi->netdev = NULL;
		}
	}

unroll_vsi_setup:
	if (vsi) {
		ice_vsi_free_q_vectors(vsi);
		ice_vsi_delete(vsi);
		ice_vsi_put_qs(vsi);
		ice_vsi_clear(vsi);
	}
	return status;
}

/**
 * ice_get_avail_q_count - Get count of queues in use
 * @pf_qmap: bitmap to get queue use count from
 * @lock: pointer to a mutex that protects access to pf_qmap
 * @size: size of the bitmap
 */
static u16
ice_get_avail_q_count(unsigned long *pf_qmap, struct mutex *lock, u16 size)
{
	u16 count = 0, bit;

	mutex_lock(lock);
	for_each_clear_bit(bit, pf_qmap, size)
		count++;
	mutex_unlock(lock);

	return count;
}

/**
 * ice_get_avail_txq_count - Get count of Tx queues in use
 * @pf: pointer to an ice_pf instance
 */
u16 ice_get_avail_txq_count(struct ice_pf *pf)
{
	return ice_get_avail_q_count(pf->avail_txqs, &pf->avail_q_mutex,
				     pf->max_pf_txqs);
}

/**
 * ice_get_avail_rxq_count - Get count of Rx queues in use
 * @pf: pointer to an ice_pf instance
 */
u16 ice_get_avail_rxq_count(struct ice_pf *pf)
{
	return ice_get_avail_q_count(pf->avail_rxqs, &pf->avail_q_mutex,
				     pf->max_pf_rxqs);
}

/**
 * ice_deinit_pf - Unrolls initialziations done by ice_init_pf
 * @pf: board private structure to initialize
 */
static void ice_deinit_pf(struct ice_pf *pf)
{
	ice_service_task_stop(pf);
	mutex_destroy(&pf->sw_mutex);
	mutex_destroy(&pf->tc_mutex);
	mutex_destroy(&pf->avail_q_mutex);

	if (pf->avail_txqs) {
		bitmap_free(pf->avail_txqs);
		pf->avail_txqs = NULL;
	}

	if (pf->avail_rxqs) {
		bitmap_free(pf->avail_rxqs);
		pf->avail_rxqs = NULL;
	}
}

/**
 * ice_set_pf_caps - set PFs capability flags
 * @pf: pointer to the PF instance
 */
static void ice_set_pf_caps(struct ice_pf *pf)
{
	struct ice_hw_func_caps *func_caps = &pf->hw.func_caps;

	clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
	if (func_caps->common_cap.dcb)
		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
#ifdef CONFIG_PCI_IOV
	clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
	if (func_caps->common_cap.sr_iov_1_1) {
		set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
		pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs,
					      ICE_MAX_VF_COUNT);
	}
#endif /* CONFIG_PCI_IOV */
	clear_bit(ICE_FLAG_RSS_ENA, pf->flags);
	if (func_caps->common_cap.rss_table_size)
		set_bit(ICE_FLAG_RSS_ENA, pf->flags);

	pf->max_pf_txqs = func_caps->common_cap.num_txq;
	pf->max_pf_rxqs = func_caps->common_cap.num_rxq;
}

/**
 * ice_init_pf - Initialize general software structures (struct ice_pf)
 * @pf: board private structure to initialize
 */
static int ice_init_pf(struct ice_pf *pf)
{
	ice_set_pf_caps(pf);

	mutex_init(&pf->sw_mutex);
	mutex_init(&pf->tc_mutex);

	/* setup service timer and periodic service task */
	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
	pf->serv_tmr_period = HZ;
	INIT_WORK(&pf->serv_task, ice_service_task);
	clear_bit(__ICE_SERVICE_SCHED, pf->state);

	mutex_init(&pf->avail_q_mutex);
	pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL);
	if (!pf->avail_txqs)
		return -ENOMEM;

	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
	if (!pf->avail_rxqs) {
		devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs);
		pf->avail_txqs = NULL;
		return -ENOMEM;
	}

	return 0;
}

/**
 * ice_ena_msix_range - Request a range of MSIX vectors from the OS
 * @pf: board private structure
 *
 * compute the number of MSIX vectors required (v_budget) and request from
 * the OS. Return the number of vectors reserved or negative on failure
 */
static int ice_ena_msix_range(struct ice_pf *pf)
{
	struct device *dev = ice_pf_to_dev(pf);
	int v_left, v_actual, v_budget = 0;
	int needed, err, i;

	v_left = pf->hw.func_caps.common_cap.num_msix_vectors;

	/* reserve one vector for miscellaneous handler */
	needed = 1;
	if (v_left < needed)
		goto no_hw_vecs_left_err;
	v_budget += needed;
	v_left -= needed;

	/* reserve vectors for LAN traffic */
	needed = min_t(int, num_online_cpus(), v_left);
	if (v_left < needed)
		goto no_hw_vecs_left_err;
	pf->num_lan_msix = needed;
	v_budget += needed;
	v_left -= needed;

	pf->msix_entries = devm_kcalloc(dev, v_budget,
					sizeof(*pf->msix_entries), GFP_KERNEL);

	if (!pf->msix_entries) {
		err = -ENOMEM;
		goto exit_err;
	}

	for (i = 0; i < v_budget; i++)
		pf->msix_entries[i].entry = i;

	/* actually reserve the vectors */
	v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries,
					 ICE_MIN_MSIX, v_budget);

	if (v_actual < 0) {
		dev_err(dev, "unable to reserve MSI-X vectors\n");
		err = v_actual;
		goto msix_err;
	}

	if (v_actual < v_budget) {
		dev_warn(dev,
			 "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
			 v_budget, v_actual);
/* 2 vectors for LAN (traffic + OICR) */
#define ICE_MIN_LAN_VECS 2

		if (v_actual < ICE_MIN_LAN_VECS) {
			/* error if we can't get minimum vectors */
			pci_disable_msix(pf->pdev);
			err = -ERANGE;
			goto msix_err;
		} else {
			pf->num_lan_msix = ICE_MIN_LAN_VECS;
		}
	}

	return v_actual;

msix_err:
	devm_kfree(dev, pf->msix_entries);
	goto exit_err;

no_hw_vecs_left_err:
	dev_err(dev,
		"not enough device MSI-X vectors. requested = %d, available = %d\n",
		needed, v_left);
	err = -ERANGE;
exit_err:
	pf->num_lan_msix = 0;
	return err;
}

/**
 * ice_dis_msix - Disable MSI-X interrupt setup in OS
 * @pf: board private structure
 */
static void ice_dis_msix(struct ice_pf *pf)
{
	pci_disable_msix(pf->pdev);
	devm_kfree(ice_pf_to_dev(pf), pf->msix_entries);
	pf->msix_entries = NULL;
}

/**
 * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme
 * @pf: board private structure
 */
static void ice_clear_interrupt_scheme(struct ice_pf *pf)
{
	ice_dis_msix(pf);

	if (pf->irq_tracker) {
		devm_kfree(ice_pf_to_dev(pf), pf->irq_tracker);
		pf->irq_tracker = NULL;
	}
}

/**
 * ice_init_interrupt_scheme - Determine proper interrupt scheme
 * @pf: board private structure to initialize
 */
static int ice_init_interrupt_scheme(struct ice_pf *pf)
{
	int vectors;

	vectors = ice_ena_msix_range(pf);

	if (vectors < 0)
		return vectors;

	/* set up vector assignment tracking */
	pf->irq_tracker =
		devm_kzalloc(ice_pf_to_dev(pf), sizeof(*pf->irq_tracker) +
			     (sizeof(u16) * vectors), GFP_KERNEL);
	if (!pf->irq_tracker) {
		ice_dis_msix(pf);
		return -ENOMEM;
	}

	/* populate SW interrupts pool with number of OS granted IRQs. */
	pf->num_avail_sw_msix = vectors;
	pf->irq_tracker->num_entries = vectors;
	pf->irq_tracker->end = pf->irq_tracker->num_entries;

	return 0;
}

/**
 * ice_vsi_recfg_qs - Change the number of queues on a VSI
 * @vsi: VSI being changed
 * @new_rx: new number of Rx queues
 * @new_tx: new number of Tx queues
 *
 * Only change the number of queues if new_tx, or new_rx is non-0.
 *
 * Returns 0 on success.
 */
int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx)
{
	struct ice_pf *pf = vsi->back;
	int err = 0, timeout = 50;

	if (!new_rx && !new_tx)
		return -EINVAL;

	while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
		timeout--;
		if (!timeout)
			return -EBUSY;
		usleep_range(1000, 2000);
	}

	if (new_tx)
		vsi->req_txq = new_tx;
	if (new_rx)
		vsi->req_rxq = new_rx;

	/* set for the next time the netdev is started */
	if (!netif_running(vsi->netdev)) {
		ice_vsi_rebuild(vsi, false);
		dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
		goto done;
	}

	ice_vsi_close(vsi);
	ice_vsi_rebuild(vsi, false);
	ice_pf_dcb_recfg(pf);
	ice_vsi_open(vsi);
done:
	clear_bit(__ICE_CFG_BUSY, pf->state);
	return err;
}

/**
 * ice_log_pkg_init - log result of DDP package load
 * @hw: pointer to hardware info
 * @status: status of package load
 */
static void
ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
{
	struct ice_pf *pf = (struct ice_pf *)hw->back;
	struct device *dev = ice_pf_to_dev(pf);

	switch (*status) {
	case ICE_SUCCESS:
		/* The package download AdminQ command returned success because
		 * this download succeeded or ICE_ERR_AQ_NO_WORK since there is
		 * already a package loaded on the device.
		 */
		if (hw->pkg_ver.major == hw->active_pkg_ver.major &&
		    hw->pkg_ver.minor == hw->active_pkg_ver.minor &&
		    hw->pkg_ver.update == hw->active_pkg_ver.update &&
		    hw->pkg_ver.draft == hw->active_pkg_ver.draft &&
		    !memcmp(hw->pkg_name, hw->active_pkg_name,
			    sizeof(hw->pkg_name))) {
			if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST)
				dev_info(dev,
					 "DDP package already present on device: %s version %d.%d.%d.%d\n",
					 hw->active_pkg_name,
					 hw->active_pkg_ver.major,
					 hw->active_pkg_ver.minor,
					 hw->active_pkg_ver.update,
					 hw->active_pkg_ver.draft);
			else
				dev_info(dev,
					 "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n",
					 hw->active_pkg_name,
					 hw->active_pkg_ver.major,
					 hw->active_pkg_ver.minor,
					 hw->active_pkg_ver.update,
					 hw->active_pkg_ver.draft);
		} else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ ||
			   hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) {
			dev_err(dev,
				"The device has a DDP package that is not supported by the driver.  The device has package '%s' version %d.%d.x.x.  The driver requires version %d.%d.x.x.  Entering Safe Mode.\n",
				hw->active_pkg_name,
				hw->active_pkg_ver.major,
				hw->active_pkg_ver.minor,
				ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
			*status = ICE_ERR_NOT_SUPPORTED;
		} else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
			   hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) {
			dev_info(dev,
				 "The driver could not load the DDP package file because a compatible DDP package is already present on the device.  The device has package '%s' version %d.%d.%d.%d.  The package file found by the driver: '%s' version %d.%d.%d.%d.\n",
				 hw->active_pkg_name,
				 hw->active_pkg_ver.major,
				 hw->active_pkg_ver.minor,
				 hw->active_pkg_ver.update,
				 hw->active_pkg_ver.draft,
				 hw->pkg_name,
				 hw->pkg_ver.major,
				 hw->pkg_ver.minor,
				 hw->pkg_ver.update,
				 hw->pkg_ver.draft);
		} else {
			dev_err(dev,
				"An unknown error occurred when loading the DDP package, please reboot the system.  If the problem persists, update the NVM.  Entering Safe Mode.\n");
			*status = ICE_ERR_NOT_SUPPORTED;
		}
		break;
	case ICE_ERR_BUF_TOO_SHORT:
		/* fall-through */
	case ICE_ERR_CFG:
		dev_err(dev,
			"The DDP package file is invalid. Entering Safe Mode.\n");
		break;
	case ICE_ERR_NOT_SUPPORTED:
		/* Package File version not supported */
		if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ ||
		    (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
		     hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR))
			dev_err(dev,
				"The DDP package file version is higher than the driver supports.  Please use an updated driver.  Entering Safe Mode.\n");
		else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ ||
			 (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
			  hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR))
			dev_err(dev,
				"The DDP package file version is lower than the driver supports.  The driver requires version %d.%d.x.x.  Please use an updated DDP Package file.  Entering Safe Mode.\n",
				ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
		break;
	case ICE_ERR_AQ_ERROR:
		switch (hw->pkg_dwnld_status) {
		case ICE_AQ_RC_ENOSEC:
		case ICE_AQ_RC_EBADSIG:
			dev_err(dev,
				"The DDP package could not be loaded because its signature is not valid.  Please use a valid DDP Package.  Entering Safe Mode.\n");
			return;
		case ICE_AQ_RC_ESVN:
			dev_err(dev,
				"The DDP Package could not be loaded because its security revision is too low.  Please use an updated DDP Package.  Entering Safe Mode.\n");
			return;
		case ICE_AQ_RC_EBADMAN:
		case ICE_AQ_RC_EBADBUF:
			dev_err(dev,
				"An error occurred on the device while loading the DDP package.  The device will be reset.\n");
			return;
		default:
			break;
		}
		/* fall-through */
	default:
		dev_err(dev,
			"An unknown error (%d) occurred when loading the DDP package.  Entering Safe Mode.\n",
			*status);
		break;
	}
}

/**
 * ice_load_pkg - load/reload the DDP Package file
 * @firmware: firmware structure when firmware requested or NULL for reload
 * @pf: pointer to the PF instance
 *
 * Called on probe and post CORER/GLOBR rebuild to load DDP Package and
 * initialize HW tables.
 */
static void
ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf)
{
	enum ice_status status = ICE_ERR_PARAM;
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;

	/* Load DDP Package */
	if (firmware && !hw->pkg_copy) {
		status = ice_copy_and_init_pkg(hw, firmware->data,
					       firmware->size);
		ice_log_pkg_init(hw, &status);
	} else if (!firmware && hw->pkg_copy) {
		/* Reload package during rebuild after CORER/GLOBR reset */
		status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size);
		ice_log_pkg_init(hw, &status);
	} else {
		dev_err(dev,
			"The DDP package file failed to load. Entering Safe Mode.\n");
	}

	if (status) {
		/* Safe Mode */
		clear_bit(ICE_FLAG_ADV_FEATURES, pf->flags);
		return;
	}

	/* Successful download package is the precondition for advanced
	 * features, hence setting the ICE_FLAG_ADV_FEATURES flag
	 */
	set_bit(ICE_FLAG_ADV_FEATURES, pf->flags);
}

/**
 * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
 * @pf: pointer to the PF structure
 *
 * There is no error returned here because the driver should be able to handle
 * 128 Byte cache lines, so we only print a warning in case issues are seen,
 * specifically with Tx.
 */
static void ice_verify_cacheline_size(struct ice_pf *pf)
{
	if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M)
		dev_warn(ice_pf_to_dev(pf),
			 "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
			 ICE_CACHE_LINE_BYTES);
}

/**
 * ice_send_version - update firmware with driver version
 * @pf: PF struct
 *
 * Returns ICE_SUCCESS on success, else error code
 */
static enum ice_status ice_send_version(struct ice_pf *pf)
{
	struct ice_driver_ver dv;

	dv.major_ver = DRV_VERSION_MAJOR;
	dv.minor_ver = DRV_VERSION_MINOR;
	dv.build_ver = DRV_VERSION_BUILD;
	dv.subbuild_ver = 0;
	strscpy((char *)dv.driver_string, DRV_VERSION,
		sizeof(dv.driver_string));
	return ice_aq_send_driver_ver(&pf->hw, &dv, NULL);
}

/**
 * ice_get_opt_fw_name - return optional firmware file name or NULL
 * @pf: pointer to the PF instance
 */
static char *ice_get_opt_fw_name(struct ice_pf *pf)
{
	/* Optional firmware name same as default with additional dash
	 * followed by a EUI-64 identifier (PCIe Device Serial Number)
	 */
	struct pci_dev *pdev = pf->pdev;
	char *opt_fw_filename = NULL;
	u32 dword;
	u8 dsn[8];
	int pos;

	/* Determine the name of the optional file using the DSN (two
	 * dwords following the start of the DSN Capability).
	 */
	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
	if (pos) {
		opt_fw_filename = kzalloc(NAME_MAX, GFP_KERNEL);
		if (!opt_fw_filename)
			return NULL;

		pci_read_config_dword(pdev, pos + 4, &dword);
		put_unaligned_le32(dword, &dsn[0]);
		pci_read_config_dword(pdev, pos + 8, &dword);
		put_unaligned_le32(dword, &dsn[4]);
		snprintf(opt_fw_filename, NAME_MAX,
			 "%sice-%02x%02x%02x%02x%02x%02x%02x%02x.pkg",
			 ICE_DDP_PKG_PATH,
			 dsn[7], dsn[6], dsn[5], dsn[4],
			 dsn[3], dsn[2], dsn[1], dsn[0]);
	}

	return opt_fw_filename;
}

/**
 * ice_request_fw - Device initialization routine
 * @pf: pointer to the PF instance
 */
static void ice_request_fw(struct ice_pf *pf)
{
	char *opt_fw_filename = ice_get_opt_fw_name(pf);
	const struct firmware *firmware = NULL;
	struct device *dev = ice_pf_to_dev(pf);
	int err = 0;

	/* optional device-specific DDP (if present) overrides the default DDP
	 * package file. kernel logs a debug message if the file doesn't exist,
	 * and warning messages for other errors.
	 */
	if (opt_fw_filename) {
		err = firmware_request_nowarn(&firmware, opt_fw_filename, dev);
		if (err) {
			kfree(opt_fw_filename);
			goto dflt_pkg_load;
		}

		/* request for firmware was successful. Download to device */
		ice_load_pkg(firmware, pf);
		kfree(opt_fw_filename);
		release_firmware(firmware);
		return;
	}

dflt_pkg_load:
	err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
	if (err) {
		dev_err(dev,
			"The DDP package file was not found or could not be read. Entering Safe Mode\n");
		return;
	}

	/* request for firmware was successful. Download to device */
	ice_load_pkg(firmware, pf);
	release_firmware(firmware);
}

/**
 * ice_probe - Device initialization routine
 * @pdev: PCI device information struct
 * @ent: entry in ice_pci_tbl
 *
 * Returns 0 on success, negative on failure
 */
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;

	/* this driver uses devres, see Documentation/driver-api/driver-model/devres.rst */
	err = pcim_enable_device(pdev);
	if (err)
		return err;

	err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev));
	if (err) {
		dev_err(dev, "BAR0 I/O map error %d\n", err);
		return err;
	}

	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(dev, DMA_BIT_MASK(64));
	if (err)
		err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
	if (err) {
		dev_err(dev, "DMA configuration failed: 0x%x\n", err);
		return err;
	}

	pci_enable_pcie_error_reporting(pdev);
	pci_set_master(pdev);

	pf->pdev = pdev;
	pci_set_drvdata(pdev, pf);
	set_bit(__ICE_DOWN, pf->state);
	/* Disable service task until DOWN bit is cleared */
	set_bit(__ICE_SERVICE_DIS, pf->state);

	hw = &pf->hw;
	hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0];
	pci_save_state(pdev);

	hw->back = pf;
	hw->vendor_id = pdev->vendor;
	hw->device_id = pdev->device;
	pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
	hw->subsystem_vendor_id = pdev->subsystem_vendor;
	hw->subsystem_device_id = pdev->subsystem_device;
	hw->bus.device = PCI_SLOT(pdev->devfn);
	hw->bus.func = PCI_FUNC(pdev->devfn);
	ice_set_ctrlq_len(hw);

	pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M);

#ifndef CONFIG_DYNAMIC_DEBUG
	if (debug < -1)
		hw->debug_mask = debug;
#endif

	err = ice_init_hw(hw);
	if (err) {
		dev_err(dev, "ice_init_hw failed: %d\n", err);
		err = -EIO;
		goto err_exit_unroll;
	}

	dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n",
		 hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch,
		 hw->api_maj_ver, hw->api_min_ver, hw->api_patch,
		 ice_nvm_version_str(hw), hw->fw_build);

	ice_request_fw(pf);

	/* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
	 * set in pf->state, which will cause ice_is_safe_mode to return
	 * true
	 */
	if (ice_is_safe_mode(pf)) {
		dev_err(dev,
			"Package download failed. Advanced features disabled - Device now in Safe Mode\n");
		/* we already got function/device capabilities but these don't
		 * reflect what the driver needs to do in safe mode. Instead of
		 * adding conditional logic everywhere to ignore these
		 * device/function capabilities, override them.
		 */
		ice_set_safe_mode_caps(hw);
	}

	err = ice_init_pf(pf);
	if (err) {
		dev_err(dev, "ice_init_pf failed: %d\n", err);
		goto err_init_pf_unroll;
	}

	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
	if (!pf->num_alloc_vsi) {
		err = -EIO;
		goto err_init_pf_unroll;
	}

	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
			       GFP_KERNEL);
	if (!pf->vsi) {
		err = -ENOMEM;
		goto err_init_pf_unroll;
	}

	err = ice_init_interrupt_scheme(pf);
	if (err) {
		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
		err = -EIO;
		goto err_init_interrupt_unroll;
	}

	/* Driver is mostly up */
	clear_bit(__ICE_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
	 * the misc functionality and queue processing is combined in
	 * the same vector and that gets setup at open.
	 */
	err = ice_req_irq_msix_misc(pf);
	if (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(dev, sizeof(*pf->first_sw), GFP_KERNEL);
	if (!pf->first_sw) {
		err = -ENOMEM;
		goto err_msix_misc_unroll;
	}

	if (hw->evb_veb)
		pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
	else
		pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA;

	pf->first_sw->pf = pf;

	/* record the sw_id available for later use */
	pf->first_sw->sw_id = hw->port_info->sw_id;

	err = ice_setup_pf_sw(pf);
	if (err) {
		dev_err(dev, "probe failed due to setup PF switch: %d\n", err);
		goto err_alloc_sw_unroll;
	}

	clear_bit(__ICE_SERVICE_DIS, pf->state);

	/* tell the firmware we are up */
	err = ice_send_version(pf);
	if (err) {
		dev_err(dev,
			"probe failed sending driver version %s. error: %d\n",
			ice_drv_ver, err);
		goto err_alloc_sw_unroll;
	}

	/* 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);

	/* If no DDP driven features have to be setup, return here */
	if (ice_is_safe_mode(pf))
		return 0;

	/* initialize DDP driven features */

	/* Note: DCB init failure is non-fatal to load */
	if (ice_init_pf_dcb(pf, false)) {
		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
	} else {
		ice_cfg_lldp_mib_change(&pf->hw, true);
	}

	/* print PCI link speed and width */
	pcie_print_link_status(pf->pdev);

	return 0;

err_alloc_sw_unroll:
	set_bit(__ICE_SERVICE_DIS, pf->state);
	set_bit(__ICE_DOWN, pf->state);
	devm_kfree(dev, pf->first_sw);
err_msix_misc_unroll:
	ice_free_irq_msix_misc(pf);
err_init_interrupt_unroll:
	ice_clear_interrupt_scheme(pf);
	devm_kfree(dev, pf->vsi);
err_init_pf_unroll:
	ice_deinit_pf(pf);
	ice_deinit_hw(hw);
err_exit_unroll:
	pci_disable_pcie_error_reporting(pdev);
	return err;
}

/**
 * ice_remove - Device removal routine
 * @pdev: PCI device information struct
 */
static void ice_remove(struct pci_dev *pdev)
{
	struct ice_pf *pf = pci_get_drvdata(pdev);
	int i;

	if (!pf)
		return;

	for (i = 0; i < ICE_MAX_RESET_WAIT; i++) {
		if (!ice_is_reset_in_progress(pf->state))
			break;
		msleep(100);
	}

	set_bit(__ICE_DOWN, pf->state);
	ice_service_task_stop(pf);

	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags))
		ice_free_vfs(pf);
	ice_vsi_release_all(pf);
	ice_free_irq_msix_misc(pf);
	ice_for_each_vsi(pf, i) {
		if (!pf->vsi[i])
			continue;
		ice_vsi_free_q_vectors(pf->vsi[i]);
	}
	ice_deinit_pf(pf);
	ice_deinit_hw(&pf->hw);
	/* Issue a PFR as part of the prescribed driver unload flow.  Do not
	 * do it via ice_schedule_reset() since there is no need to rebuild
	 * and the service task is already stopped.
	 */
	ice_reset(&pf->hw, ICE_RESET_PFR);
	pci_wait_for_pending_transaction(pdev);
	ice_clear_interrupt_scheme(pf);
	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
 * Last entry must be all 0s
 *
 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
 *   Class, Class Mask, private data (not used) }
 */
static const struct pci_device_id ice_pci_tbl[] = {
	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
	/* required last entry */
	{ 0, }
};
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
};

/**
 * ice_module_init - Driver registration routine
 *
 * ice_module_init is the first routine called when the driver is
 * loaded. All it does is register with the PCI subsystem.
 */
static int __init ice_module_init(void)
{
	int status;

	pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver);
	pr_info("%s\n", ice_copyright);

	ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME);
	if (!ice_wq) {
		pr_err("Failed to create workqueue\n");
		return -ENOMEM;
	}

	status = pci_register_driver(&ice_driver);
	if (status) {
		pr_err("failed to register PCI driver, err %d\n", status);
		destroy_workqueue(ice_wq);
	}

	return status;
}
module_init(ice_module_init);

/**
 * ice_module_exit - Driver exit cleanup routine
 *
 * ice_module_exit is called just before the driver is removed
 * from memory.
 */
static void __exit ice_module_exit(void)
{
	pci_unregister_driver(&ice_driver);
	destroy_workqueue(ice_wq);
	pr_info("module unloaded\n");
}
module_exit(ice_module_exit);

/**
 * ice_set_mac_address - NDO callback to set MAC address
 * @netdev: network interface device structure
 * @pi: pointer to an address structure
 *
 * Returns 0 on success, negative on failure
 */
static int ice_set_mac_address(struct net_device *netdev, void *pi)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	struct sockaddr *addr = pi;
	enum ice_status status;
	u8 flags = 0;
	int err = 0;
	u8 *mac;

	mac = (u8 *)addr->sa_data;

	if (!is_valid_ether_addr(mac))
		return -EADDRNOTAVAIL;

	if (ether_addr_equal(netdev->dev_addr, mac)) {
		netdev_warn(netdev, "already using mac %pM\n", mac);
		return 0;
	}

	if (test_bit(__ICE_DOWN, pf->state) ||
	    ice_is_reset_in_progress(pf->state)) {
		netdev_err(netdev, "can't set mac %pM. device not ready\n",
			   mac);
		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
	 * address. So first, we remove the old filter rule using ice_remove_mac
	 * and then create a new filter rule using ice_add_mac via
	 * ice_vsi_cfg_mac_fltr function call for both add and/or remove
	 * filters.
	 */
	status = ice_vsi_cfg_mac_fltr(vsi, netdev->dev_addr, false);
	if (status) {
		err = -EADDRNOTAVAIL;
		goto err_update_filters;
	}

	status = ice_vsi_cfg_mac_fltr(vsi, mac, true);
	if (status) {
		err = -EADDRNOTAVAIL;
		goto err_update_filters;
	}

err_update_filters:
	if (err) {
		netdev_err(netdev, "can't set MAC %pM. filter update failed\n",
			   mac);
		return err;
	}

	/* 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 */
	flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
	status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
	if (status) {
		netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %d\n",
			   mac, status);
	}
	return 0;
}

/**
 * ice_set_rx_mode - NDO callback to set the netdev filters
 * @netdev: network interface device structure
 */
static void ice_set_rx_mode(struct net_device *netdev)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;

	if (!vsi)
		return;

	/* Set the flags to synchronize filters
	 * ndo_set_rx_mode may be triggered even without a change in netdev
	 * flags
	 */
	set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags);
	set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags);
	set_bit(ICE_FLAG_FLTR_SYNC, vsi->back->flags);

	/* schedule our worker thread which will take care of
	 * applying the new filter changes
	 */
	ice_service_task_schedule(vsi->back);
}

/**
 * ice_set_tx_maxrate - NDO callback to set the maximum per-queue bitrate
 * @netdev: network interface device structure
 * @queue_index: Queue ID
 * @maxrate: maximum bandwidth in Mbps
 */
static int
ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	enum ice_status status;
	u16 q_handle;
	u8 tc;

	/* Validate maxrate requested is within permitted range */
	if (maxrate && (maxrate > (ICE_SCHED_MAX_BW / 1000))) {
		netdev_err(netdev,
			   "Invalid max rate %d specified for the queue %d\n",
			   maxrate, queue_index);
		return -EINVAL;
	}

	q_handle = vsi->tx_rings[queue_index]->q_handle;
	tc = ice_dcb_get_tc(vsi, queue_index);

	/* Set BW back to default, when user set maxrate to 0 */
	if (!maxrate)
		status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc,
					       q_handle, ICE_MAX_BW);
	else
		status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc,
					  q_handle, ICE_MAX_BW, maxrate * 1000);
	if (status) {
		netdev_err(netdev,
			   "Unable to set Tx max rate, error %d\n", status);
		return -EIO;
	}

	return 0;
}

/**
 * ice_fdb_add - add an entry to the hardware database
 * @ndm: the input from the stack
 * @tb: pointer to array of nladdr (unused)
 * @dev: the net device pointer
 * @addr: the MAC address entry being added
 * @vid: VLAN ID
 * @flags: instructions from stack about fdb operation
 * @extack: netlink extended ack
 */
static int
ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
	    struct net_device *dev, const unsigned char *addr, u16 vid,
	    u16 flags, struct netlink_ext_ack __always_unused *extack)
{
	int err;

	if (vid) {
		netdev_err(dev, "VLANs aren't supported yet for dev_uc|mc_add()\n");
		return -EINVAL;
	}
	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
		netdev_err(dev, "FDB only supports static addresses\n");
		return -EINVAL;
	}

	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
		err = dev_uc_add_excl(dev, addr);
	else if (is_multicast_ether_addr(addr))
		err = dev_mc_add_excl(dev, addr);
	else
		err = -EINVAL;

	/* Only return duplicate errors if NLM_F_EXCL is set */
	if (err == -EEXIST && !(flags & NLM_F_EXCL))
		err = 0;

	return err;
}

/**
 * ice_fdb_del - delete an entry from the hardware database
 * @ndm: the input from the stack
 * @tb: pointer to array of nladdr (unused)
 * @dev: the net device pointer
 * @addr: the MAC address entry being added
 * @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)
{
	int err;

	if (ndm->ndm_state & NUD_PERMANENT) {
		netdev_err(dev, "FDB only supports static addresses\n");
		return -EINVAL;
	}

	if (is_unicast_ether_addr(addr))
		err = dev_uc_del(dev, addr);
	else if (is_multicast_ether_addr(addr))
		err = dev_mc_del(dev, addr);
	else
		err = -EINVAL;

	return err;
}

/**
 * ice_set_features - set the netdev feature flags
 * @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)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_pf *pf = vsi->back;
	int ret = 0;

	/* Don't set any netdev advanced features with device in Safe Mode */
	if (ice_is_safe_mode(vsi->back)) {
		dev_err(&vsi->back->pdev->dev,
			"Device is in Safe Mode - not enabling advanced netdev features\n");
		return ret;
	}

	/* Do not change setting during reset */
	if (ice_is_reset_in_progress(pf->state)) {
		dev_err(&vsi->back->pdev->dev,
			"Device is resetting, changing advanced netdev features temporarily unavailable.\n");
		return -EBUSY;
	}

	/* 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) &&
		 netdev->features & NETIF_F_RXHASH)
		ret = ice_vsi_manage_rss_lut(vsi, false);

	if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
	    !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
		ret = ice_vsi_manage_vlan_stripping(vsi, true);
	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);

	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))
		ret = ice_vsi_manage_vlan_insertion(vsi);

	if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
	    !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
		ret = ice_cfg_vlan_pruning(vsi, true, false);
	else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
		 (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
		ret = ice_cfg_vlan_pruning(vsi, false, false);

	return ret;
}

/**
 * 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)
{
	int ret = 0;

	if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
		ret = ice_vsi_manage_vlan_stripping(vsi, true);
	if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)
		ret = ice_vsi_manage_vlan_insertion(vsi);

	return ret;
}

/**
 * ice_vsi_cfg - Setup the VSI
 * @vsi: the VSI being configured
 *
 * Return 0 on success and negative value on error
 */
int ice_vsi_cfg(struct ice_vsi *vsi)
{
	int err;

	if (vsi->netdev) {
		ice_set_rx_mode(vsi->netdev);

		err = ice_vsi_vlan_setup(vsi);

		if (err)
			return err;
	}
	ice_vsi_cfg_dcb_rings(vsi);

	err = ice_vsi_cfg_lan_txqs(vsi);
	if (!err && ice_is_xdp_ena_vsi(vsi))
		err = ice_vsi_cfg_xdp_txqs(vsi);
	if (!err)
		err = ice_vsi_cfg_rxqs(vsi);

	return err;
}

/**
 * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI
 * @vsi: the VSI being configured
 */
static void ice_napi_enable_all(struct ice_vsi *vsi)
{
	int q_idx;

	if (!vsi->netdev)
		return;

	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)
			napi_enable(&q_vector->napi);
	}
}

/**
 * ice_up_complete - Finish the last steps of bringing up a connection
 * @vsi: The VSI being configured
 *
 * Return 0 on success and negative value on error
 */
static int ice_up_complete(struct ice_vsi *vsi)
{
	struct ice_pf *pf = vsi->back;
	int err;

	ice_vsi_cfg_msix(vsi);

	/* Enable only Rx rings, Tx rings were enabled by the FW when the
	 * Tx queue group list was configured and the context bits were
	 * programmed using ice_vsi_cfg_txqs
	 */
	err = ice_vsi_start_rx_rings(vsi);
	if (err)
		return err;

	clear_bit(__ICE_DOWN, vsi->state);
	ice_napi_enable_all(vsi);
	ice_vsi_ena_irq(vsi);

	if (vsi->port_info &&
	    (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) &&
	    vsi->netdev) {
		ice_print_link_msg(vsi, true);
		netif_tx_start_all_queues(vsi->netdev);
		netif_carrier_on(vsi->netdev);
	}

	ice_service_task_schedule(pf);

	return 0;
}

/**
 * ice_up - Bring the connection back up after being down
 * @vsi: VSI being configured
 */
int ice_up(struct ice_vsi *vsi)
{
	int err;

	err = ice_vsi_cfg(vsi);
	if (!err)
		err = ice_up_complete(vsi);

	return err;
}

/**
 * ice_fetch_u64_stats_per_ring - get packets and bytes stats per ring
 * @ring: Tx or Rx ring to read stats from
 * @pkts: packets stats counter
 * @bytes: bytes stats counter
 *
 * 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)
{
	unsigned int start;
	*pkts = 0;
	*bytes = 0;

	if (!ring)
		return;
	do {
		start = u64_stats_fetch_begin_irq(&ring->syncp);
		*pkts = ring->stats.pkts;
		*bytes = ring->stats.bytes;
	} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
}

/**
 * ice_update_vsi_ring_stats - Update VSI stats counters
 * @vsi: the VSI to be updated
 */
static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
{
	struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
	struct ice_ring *ring;
	u64 pkts, bytes;
	int i;

	/* reset netdev stats */
	vsi_stats->tx_packets = 0;
	vsi_stats->tx_bytes = 0;
	vsi_stats->rx_packets = 0;
	vsi_stats->rx_bytes = 0;

	/* reset non-netdev (extended) stats */
	vsi->tx_restart = 0;
	vsi->tx_busy = 0;
	vsi->tx_linearize = 0;
	vsi->rx_buf_failed = 0;
	vsi->rx_page_failed = 0;

	rcu_read_lock();

	/* update Tx rings counters */
	ice_for_each_txq(vsi, i) {
		ring = READ_ONCE(vsi->tx_rings[i]);
		ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
		vsi_stats->tx_packets += pkts;
		vsi_stats->tx_bytes += bytes;
		vsi->tx_restart += ring->tx_stats.restart_q;
		vsi->tx_busy += ring->tx_stats.tx_busy;
		vsi->tx_linearize += ring->tx_stats.tx_linearize;
	}

	/* update Rx rings counters */
	ice_for_each_rxq(vsi, i) {
		ring = READ_ONCE(vsi->rx_rings[i]);
		ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
		vsi_stats->rx_packets += pkts;
		vsi_stats->rx_bytes += bytes;
		vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed;
		vsi->rx_page_failed += ring->rx_stats.alloc_page_failed;
	}

	rcu_read_unlock();
}

/**
 * ice_update_vsi_stats - Update VSI stats counters
 * @vsi: the VSI to be updated
 */
void ice_update_vsi_stats(struct ice_vsi *vsi)
{
	struct rtnl_link_stats64 *cur_ns = &vsi->net_stats;
	struct ice_eth_stats *cur_es = &vsi->eth_stats;
	struct ice_pf *pf = vsi->back;

	if (test_bit(__ICE_DOWN, vsi->state) ||
	    test_bit(__ICE_CFG_BUSY, pf->state))
		return;

	/* get stats as recorded by Tx/Rx rings */
	ice_update_vsi_ring_stats(vsi);

	/* get VSI stats as recorded by the hardware */
	ice_update_eth_stats(vsi);

	cur_ns->tx_errors = cur_es->tx_errors;
	cur_ns->rx_dropped = cur_es->rx_discards;
	cur_ns->tx_dropped = cur_es->tx_discards;
	cur_ns->multicast = cur_es->rx_multicast;

	/* update some more netdev stats if this is main VSI */
	if (vsi->type == ICE_VSI_PF) {
		cur_ns->rx_crc_errors = pf->stats.crc_errors;
		cur_ns->rx_errors = pf->stats.crc_errors +
				    pf->stats.illegal_bytes;
		cur_ns->rx_length_errors = pf->stats.rx_len_errors;
		/* record drops from the port level */
		cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
	}
}

/**
 * ice_update_pf_stats - Update PF port stats counters
 * @pf: PF whose stats needs to be updated
 */
void ice_update_pf_stats(struct ice_pf *pf)
{
	struct ice_hw_port_stats *prev_ps, *cur_ps;
	struct ice_hw *hw = &pf->hw;
	u8 port;

	port = hw->port_info->lport;
	prev_ps = &pf->stats_prev;
	cur_ps = &pf->stats;

	ice_stat_update40(hw, GLPRT_GORCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.rx_bytes,
			  &cur_ps->eth.rx_bytes);

	ice_stat_update40(hw, GLPRT_UPRCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.rx_unicast,
			  &cur_ps->eth.rx_unicast);

	ice_stat_update40(hw, GLPRT_MPRCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.rx_multicast,
			  &cur_ps->eth.rx_multicast);

	ice_stat_update40(hw, GLPRT_BPRCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.rx_broadcast,
			  &cur_ps->eth.rx_broadcast);

	ice_stat_update32(hw, PRTRPB_RDPC, pf->stat_prev_loaded,
			  &prev_ps->eth.rx_discards,
			  &cur_ps->eth.rx_discards);

	ice_stat_update40(hw, GLPRT_GOTCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.tx_bytes,
			  &cur_ps->eth.tx_bytes);

	ice_stat_update40(hw, GLPRT_UPTCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.tx_unicast,
			  &cur_ps->eth.tx_unicast);

	ice_stat_update40(hw, GLPRT_MPTCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.tx_multicast,
			  &cur_ps->eth.tx_multicast);

	ice_stat_update40(hw, GLPRT_BPTCL(port), pf->stat_prev_loaded,
			  &prev_ps->eth.tx_broadcast,
			  &cur_ps->eth.tx_broadcast);

	ice_stat_update32(hw, GLPRT_TDOLD(port), pf->stat_prev_loaded,
			  &prev_ps->tx_dropped_link_down,
			  &cur_ps->tx_dropped_link_down);

	ice_stat_update40(hw, GLPRT_PRC64L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_64, &cur_ps->rx_size_64);

	ice_stat_update40(hw, GLPRT_PRC127L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_127, &cur_ps->rx_size_127);

	ice_stat_update40(hw, GLPRT_PRC255L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_255, &cur_ps->rx_size_255);

	ice_stat_update40(hw, GLPRT_PRC511L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_511, &cur_ps->rx_size_511);

	ice_stat_update40(hw, GLPRT_PRC1023L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_1023, &cur_ps->rx_size_1023);

	ice_stat_update40(hw, GLPRT_PRC1522L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_1522, &cur_ps->rx_size_1522);

	ice_stat_update40(hw, GLPRT_PRC9522L(port), pf->stat_prev_loaded,
			  &prev_ps->rx_size_big, &cur_ps->rx_size_big);

	ice_stat_update40(hw, GLPRT_PTC64L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_64, &cur_ps->tx_size_64);

	ice_stat_update40(hw, GLPRT_PTC127L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_127, &cur_ps->tx_size_127);

	ice_stat_update40(hw, GLPRT_PTC255L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_255, &cur_ps->tx_size_255);

	ice_stat_update40(hw, GLPRT_PTC511L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_511, &cur_ps->tx_size_511);

	ice_stat_update40(hw, GLPRT_PTC1023L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_1023, &cur_ps->tx_size_1023);

	ice_stat_update40(hw, GLPRT_PTC1522L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_1522, &cur_ps->tx_size_1522);

	ice_stat_update40(hw, GLPRT_PTC9522L(port), pf->stat_prev_loaded,
			  &prev_ps->tx_size_big, &cur_ps->tx_size_big);

	ice_stat_update32(hw, GLPRT_LXONRXC(port), pf->stat_prev_loaded,
			  &prev_ps->link_xon_rx, &cur_ps->link_xon_rx);

	ice_stat_update32(hw, GLPRT_LXOFFRXC(port), pf->stat_prev_loaded,
			  &prev_ps->link_xoff_rx, &cur_ps->link_xoff_rx);

	ice_stat_update32(hw, GLPRT_LXONTXC(port), pf->stat_prev_loaded,
			  &prev_ps->link_xon_tx, &cur_ps->link_xon_tx);

	ice_stat_update32(hw, GLPRT_LXOFFTXC(port), 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(port), pf->stat_prev_loaded,
			  &prev_ps->crc_errors, &cur_ps->crc_errors);

	ice_stat_update32(hw, GLPRT_ILLERRC(port), pf->stat_prev_loaded,
			  &prev_ps->illegal_bytes, &cur_ps->illegal_bytes);

	ice_stat_update32(hw, GLPRT_MLFC(port), pf->stat_prev_loaded,
			  &prev_ps->mac_local_faults,
			  &cur_ps->mac_local_faults);

	ice_stat_update32(hw, GLPRT_MRFC(port), pf->stat_prev_loaded,
			  &prev_ps->mac_remote_faults,
			  &cur_ps->mac_remote_faults);

	ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
			  &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);

	ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
			  &prev_ps->rx_undersize, &cur_ps->rx_undersize);

	ice_stat_update32(hw, GLPRT_RFC(port), pf->stat_prev_loaded,
			  &prev_ps->rx_fragments, &cur_ps->rx_fragments);

	ice_stat_update32(hw, GLPRT_ROC(port), pf->stat_prev_loaded,
			  &prev_ps->rx_oversize, &cur_ps->rx_oversize);

	ice_stat_update32(hw, GLPRT_RJC(port), pf->stat_prev_loaded,
			  &prev_ps->rx_jabber, &cur_ps->rx_jabber);

	pf->stat_prev_loaded = true;
}

/**
 * ice_get_stats64 - get statistics for network device structure
 * @netdev: network interface device structure
 * @stats: main device statistics structure
 */
static
void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct rtnl_link_stats64 *vsi_stats;
	struct ice_vsi *vsi = np->vsi;

	vsi_stats = &vsi->net_stats;

	if (!vsi->num_txq || !vsi->num_rxq)
		return;

	/* netdev packet/byte stats come from ring counter. These are obtained
	 * by summing up ring counters (done by ice_update_vsi_ring_stats).
	 * But, only call the update routine and read the registers if VSI is
	 * not down.
	 */
	if (!test_bit(__ICE_DOWN, vsi->state))
		ice_update_vsi_ring_stats(vsi);
	stats->tx_packets = vsi_stats->tx_packets;
	stats->tx_bytes = vsi_stats->tx_bytes;
	stats->rx_packets = vsi_stats->rx_packets;
	stats->rx_bytes = vsi_stats->rx_bytes;

	/* The rest of the stats can be read from the hardware but instead we
	 * just return values that the watchdog task has already obtained from
	 * the hardware.
	 */
	stats->multicast = vsi_stats->multicast;
	stats->tx_errors = vsi_stats->tx_errors;
	stats->tx_dropped = vsi_stats->tx_dropped;
	stats->rx_errors = vsi_stats->rx_errors;
	stats->rx_dropped = vsi_stats->rx_dropped;
	stats->rx_crc_errors = vsi_stats->rx_crc_errors;
	stats->rx_length_errors = vsi_stats->rx_length_errors;
}

/**
 * ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
 * @vsi: VSI having NAPI disabled
 */
static void ice_napi_disable_all(struct ice_vsi *vsi)
{
	int q_idx;

	if (!vsi->netdev)
		return;

	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)
			napi_disable(&q_vector->napi);
	}
}

/**
 * ice_down - Shutdown the connection
 * @vsi: The VSI being stopped
 */
int ice_down(struct ice_vsi *vsi)
{
	int i, tx_err, rx_err, link_err = 0;

	/* Caller of this function is expected to set the
	 * vsi->state __ICE_DOWN bit
	 */
	if (vsi->netdev) {
		netif_carrier_off(vsi->netdev);
		netif_tx_disable(vsi->netdev);
	}

	ice_vsi_dis_irq(vsi);

	tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
	if (tx_err)
		netdev_err(vsi->netdev,
			   "Failed stop Tx rings, VSI %d error %d\n",
			   vsi->vsi_num, tx_err);
	if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
		tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
		if (tx_err)
			netdev_err(vsi->netdev,
				   "Failed stop XDP rings, VSI %d error %d\n",
				   vsi->vsi_num, tx_err);
	}

	rx_err = ice_vsi_stop_rx_rings(vsi);
	if (rx_err)
		netdev_err(vsi->netdev,
			   "Failed stop Rx rings, VSI %d error %d\n",
			   vsi->vsi_num, rx_err);

	ice_napi_disable_all(vsi);

	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
		link_err = ice_force_phys_link_state(vsi, false);
		if (link_err)
			netdev_err(vsi->netdev,
				   "Failed to set physical link down, VSI %d error %d\n",
				   vsi->vsi_num, link_err);
	}

	ice_for_each_txq(vsi, i)
		ice_clean_tx_ring(vsi->tx_rings[i]);

	ice_for_each_rxq(vsi, i)
		ice_clean_rx_ring(vsi->rx_rings[i]);

	if (tx_err || rx_err || link_err) {
		netdev_err(vsi->netdev,
			   "Failed to close VSI 0x%04X on switch 0x%04X\n",
			   vsi->vsi_num, vsi->vsw->sw_id);
		return -EIO;
	}

	return 0;
}

/**
 * ice_vsi_setup_tx_rings - Allocate VSI Tx queue resources
 * @vsi: VSI having resources allocated
 *
 * Return 0 on success, negative on failure
 */
int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
{
	int i, err = 0;

	if (!vsi->num_txq) {
		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n",
			vsi->vsi_num);
		return -EINVAL;
	}

	ice_for_each_txq(vsi, i) {
		struct ice_ring *ring = vsi->tx_rings[i];

		if (!ring)
			return -EINVAL;

		ring->netdev = vsi->netdev;
		err = ice_setup_tx_ring(ring);
		if (err)
			break;
	}

	return err;
}

/**
 * ice_vsi_setup_rx_rings - Allocate VSI Rx queue resources
 * @vsi: VSI having resources allocated
 *
 * Return 0 on success, negative on failure
 */
int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
{
	int i, err = 0;

	if (!vsi->num_rxq) {
		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n",
			vsi->vsi_num);
		return -EINVAL;
	}

	ice_for_each_rxq(vsi, i) {
		struct ice_ring *ring = vsi->rx_rings[i];

		if (!ring)
			return -EINVAL;

		ring->netdev = vsi->netdev;
		err = ice_setup_rx_ring(ring);
		if (err)
			break;
	}

	return err;
}

/**
 * ice_vsi_open - Called when a network interface is made active
 * @vsi: the VSI to open
 *
 * Initialization of the VSI
 *
 * Returns 0 on success, negative value on error
 */
static int ice_vsi_open(struct ice_vsi *vsi)
{
	char int_name[ICE_INT_NAME_STR_LEN];
	struct ice_pf *pf = vsi->back;
	int err;

	/* allocate descriptors */
	err = ice_vsi_setup_tx_rings(vsi);
	if (err)
		goto err_setup_tx;

	err = ice_vsi_setup_rx_rings(vsi);
	if (err)
		goto err_setup_rx;

	err = ice_vsi_cfg(vsi);
	if (err)
		goto err_setup_rx;

	snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
		 dev_driver_string(ice_pf_to_dev(pf)), vsi->netdev->name);
	err = ice_vsi_req_irq_msix(vsi, int_name);
	if (err)
		goto err_setup_rx;

	/* Notify the stack of the actual queue counts. */
	err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq);
	if (err)
		goto err_set_qs;

	err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
	if (err)
		goto err_set_qs;

	err = ice_up_complete(vsi);
	if (err)
		goto err_up_complete;

	return 0;

err_up_complete:
	ice_down(vsi);
err_set_qs:
	ice_vsi_free_irq(vsi);
err_setup_rx:
	ice_vsi_free_rx_rings(vsi);
err_setup_tx:
	ice_vsi_free_tx_rings(vsi);

	return err;
}

/**
 * ice_vsi_release_all - Delete all VSIs
 * @pf: PF from which all VSIs are being removed
 */
static void ice_vsi_release_all(struct ice_pf *pf)
{
	int err, i;

	if (!pf->vsi)
		return;

	ice_for_each_vsi(pf, i) {
		if (!pf->vsi[i])
			continue;

		err = ice_vsi_release(pf->vsi[i]);
		if (err)
			dev_dbg(ice_pf_to_dev(pf),
				"Failed to release pf->vsi[%d], err %d, vsi_num = %d\n",
				i, err, pf->vsi[i]->vsi_num);
	}
}

/**
 * ice_vsi_rebuild_by_type - Rebuild VSI of a given type
 * @pf: pointer to the PF instance
 * @type: VSI type to rebuild
 *
 * Iterates through the pf->vsi array and rebuilds VSIs of the requested type
 */
static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
{
	struct device *dev = ice_pf_to_dev(pf);
	enum ice_status status;
	int i, err;

	ice_for_each_vsi(pf, i) {
		struct ice_vsi *vsi = pf->vsi[i];

		if (!vsi || vsi->type != type)
			continue;

		/* rebuild the VSI */
		err = ice_vsi_rebuild(vsi, true);
		if (err) {
			dev_err(dev,
				"rebuild VSI failed, err %d, VSI index %d, type %s\n",
				err, vsi->idx, ice_vsi_type_str(type));
			return err;
		}

		/* replay filters for the VSI */
		status = ice_replay_vsi(&pf->hw, vsi->idx);
		if (status) {
			dev_err(dev,
				"replay VSI failed, status %d, VSI index %d, type %s\n",
				status, vsi->idx, ice_vsi_type_str(type));
			return -EIO;
		}

		/* Re-map HW VSI number, using VSI handle that has been
		 * previously validated in ice_replay_vsi() call above
		 */
		vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx);

		/* enable the VSI */
		err = ice_ena_vsi(vsi, false);
		if (err) {
			dev_err(dev,
				"enable VSI failed, err %d, VSI index %d, type %s\n",
				err, vsi->idx, ice_vsi_type_str(type));
			return err;
		}

		dev_info(dev, "VSI rebuilt. VSI index %d, type %s\n", vsi->idx,
			 ice_vsi_type_str(type));
	}

	return 0;
}

/**
 * ice_update_pf_netdev_link - Update PF netdev link status
 * @pf: pointer to the PF instance
 */
static void ice_update_pf_netdev_link(struct ice_pf *pf)
{
	bool link_up;
	int i;

	ice_for_each_vsi(pf, i) {
		struct ice_vsi *vsi = pf->vsi[i];

		if (!vsi || vsi->type != ICE_VSI_PF)
			return;

		ice_get_link_status(pf->vsi[i]->port_info, &link_up);
		if (link_up) {
			netif_carrier_on(pf->vsi[i]->netdev);
			netif_tx_wake_all_queues(pf->vsi[i]->netdev);
		} else {
			netif_carrier_off(pf->vsi[i]->netdev);
			netif_tx_stop_all_queues(pf->vsi[i]->netdev);
		}
	}
}

/**
 * ice_rebuild - rebuild after reset
 * @pf: PF to rebuild
 * @reset_type: type of reset
 */
static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
{
	struct device *dev = ice_pf_to_dev(pf);
	struct ice_hw *hw = &pf->hw;
	enum ice_status ret;
	int err;

	if (test_bit(__ICE_DOWN, pf->state))
		goto clear_recovery;

	dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type);

	ret = ice_init_all_ctrlq(hw);
	if (ret) {
		dev_err(dev, "control queues init failed %d\n", ret);
		goto err_init_ctrlq;
	}

	/* if DDP was previously loaded successfully */
	if (!ice_is_safe_mode(pf)) {
		/* reload the SW DB of filter tables */
		if (reset_type == ICE_RESET_PFR)
			ice_fill_blk_tbls(hw);
		else
			/* Reload DDP Package after CORER/GLOBR reset */
			ice_load_pkg(NULL, pf);
	}

	ret = ice_clear_pf_cfg(hw);
	if (ret) {
		dev_err(dev, "clear PF configuration failed %d\n", ret);
		goto err_init_ctrlq;
	}

	if (pf->first_sw->dflt_vsi_ena)
		dev_info(dev,
			 "Clearing default VSI, re-enable after reset completes\n");
	/* clear the default VSI configuration if it exists */
	pf->first_sw->dflt_vsi = NULL;
	pf->first_sw->dflt_vsi_ena = false;

	ice_clear_pxe_mode(hw);

	ret = ice_get_caps(hw);
	if (ret) {
		dev_err(dev, "ice_get_caps failed %d\n", ret);
		goto err_init_ctrlq;
	}

	err = ice_sched_init_port(hw->port_info);
	if (err)
		goto err_sched_init_port;

	err = ice_update_link_info(hw->port_info);
	if (err)
		dev_err(dev, "Get link status error %d\n", err);

	/* start misc vector */
	err = ice_req_irq_msix_misc(pf);
	if (err) {
		dev_err(dev, "misc vector setup failed: %d\n", err);
		goto err_sched_init_port;
	}

	if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
		ice_dcb_rebuild(pf);

	/* rebuild PF VSI */
	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF);
	if (err) {
		dev_err(dev, "PF VSI rebuild failed: %d\n", err);
		goto err_vsi_rebuild;
	}

	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
		err = ice_vsi_rebuild_by_type(pf, ICE_VSI_VF);
		if (err) {
			dev_err(dev, "VF VSI rebuild failed: %d\n", err);
			goto err_vsi_rebuild;
		}
	}

	ice_update_pf_netdev_link(pf);

	/* tell the firmware we are up */
	ret = ice_send_version(pf);
	if (ret) {
		dev_err(dev,
			"Rebuild failed due to error sending driver version: %d\n",
			ret);
		goto err_vsi_rebuild;
	}

	ice_replay_post(hw);

	/* if we get here, reset flow is successful */
	clear_bit(__ICE_RESET_FAILED, pf->state);
	return;

err_vsi_rebuild:
err_sched_init_port:
	ice_sched_cleanup_all(hw);
err_init_ctrlq:
	ice_shutdown_all_ctrlq(hw);
	set_bit(__ICE_RESET_FAILED, pf->state);
clear_recovery:
	/* set this bit in PF state to control service task scheduling */
	set_bit(__ICE_NEEDS_RESTART, pf->state);
	dev_err(dev, "Rebuild failed, unload and reload driver\n");
}

/**
 * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP
 * @vsi: Pointer to VSI structure
 */
static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
{
	if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
		return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM;
	else
		return ICE_RXBUF_3072;
}

/**
 * ice_change_mtu - NDO callback to change the MTU
 * @netdev: network interface device structure
 * @new_mtu: new value for maximum frame size
 *
 * Returns 0 on success, negative on failure
 */
static int ice_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_pf *pf = vsi->back;
	u8 count = 0;

	if (new_mtu == netdev->mtu) {
		netdev_warn(netdev, "MTU is already %u\n", netdev->mtu);
		return 0;
	}

	if (ice_is_xdp_ena_vsi(vsi)) {
		int frame_size = ice_max_xdp_frame_size(vsi);

		if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) {
			netdev_err(netdev, "max MTU for XDP usage is %d\n",
				   frame_size - ICE_ETH_PKT_HDR_PAD);
			return -EINVAL;
		}
	}

	if (new_mtu < netdev->min_mtu) {
		netdev_err(netdev, "new MTU invalid. min_mtu is %d\n",
			   netdev->min_mtu);
		return -EINVAL;
	} else if (new_mtu > netdev->max_mtu) {
		netdev_err(netdev, "new MTU invalid. max_mtu is %d\n",
			   netdev->min_mtu);
		return -EINVAL;
	}
	/* if a reset is in progress, wait for some time for it to complete */
	do {
		if (ice_is_reset_in_progress(pf->state)) {
			count++;
			usleep_range(1000, 2000);
		} else {
			break;
		}

	} while (count < 100);

	if (count == 100) {
		netdev_err(netdev, "can't change MTU. Device is busy\n");
		return -EBUSY;
	}

	netdev->mtu = new_mtu;

	/* if VSI is up, bring it down and then back up */
	if (!test_and_set_bit(__ICE_DOWN, vsi->state)) {
		int err;

		err = ice_down(vsi);
		if (err) {
			netdev_err(netdev, "change MTU if_up err %d\n", err);
			return err;
		}

		err = ice_up(vsi);
		if (err) {
			netdev_err(netdev, "change MTU if_up err %d\n", err);
			return err;
		}
	}

	netdev_info(netdev, "changed MTU to %d\n", new_mtu);
	return 0;
}

/**
 * ice_set_rss - Set RSS keys and lut
 * @vsi: Pointer to VSI structure
 * @seed: RSS hash seed
 * @lut: Lookup table
 * @lut_size: Lookup table size
 *
 * Returns 0 on success, negative on failure
 */
int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
{
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	enum ice_status status;
	struct device *dev;

	dev = ice_pf_to_dev(pf);
	if (seed) {
		struct ice_aqc_get_set_rss_keys *buf =
				  (struct ice_aqc_get_set_rss_keys *)seed;

		status = ice_aq_set_rss_key(hw, vsi->idx, buf);

		if (status) {
			dev_err(dev, "Cannot set RSS key, err %d aq_err %d\n",
				status, hw->adminq.rq_last_status);
			return -EIO;
		}
	}

	if (lut) {
		status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
					    lut, lut_size);
		if (status) {
			dev_err(dev, "Cannot set RSS lut, err %d aq_err %d\n",
				status, hw->adminq.rq_last_status);
			return -EIO;
		}
	}

	return 0;
}

/**
 * ice_get_rss - Get RSS keys and lut
 * @vsi: Pointer to VSI structure
 * @seed: Buffer to store the keys
 * @lut: Buffer to store the lookup table entries
 * @lut_size: Size of buffer to store the lookup table entries
 *
 * Returns 0 on success, negative on failure
 */
int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
{
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	enum ice_status status;
	struct device *dev;

	dev = ice_pf_to_dev(pf);
	if (seed) {
		struct ice_aqc_get_set_rss_keys *buf =
				  (struct ice_aqc_get_set_rss_keys *)seed;

		status = ice_aq_get_rss_key(hw, vsi->idx, buf);
		if (status) {
			dev_err(dev, "Cannot get RSS key, err %d aq_err %d\n",
				status, hw->adminq.rq_last_status);
			return -EIO;
		}
	}

	if (lut) {
		status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
					    lut, lut_size);
		if (status) {
			dev_err(dev, "Cannot get RSS lut, err %d aq_err %d\n",
				status, hw->adminq.rq_last_status);
			return -EIO;
		}
	}

	return 0;
}

/**
 * ice_bridge_getlink - Get the hardware bridge mode
 * @skb: skb buff
 * @pid: process ID
 * @seq: RTNL message seq
 * @dev: the netdev being configured
 * @filter_mask: filter mask passed in
 * @nlflags: netlink flags passed in
 *
 * Return the bridge mode (VEB/VEPA)
 */
static int
ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
		   struct net_device *dev, u32 filter_mask, int nlflags)
{
	struct ice_netdev_priv *np = netdev_priv(dev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_pf *pf = vsi->back;
	u16 bmode;

	bmode = pf->first_sw->bridge_mode;

	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bmode, 0, 0, nlflags,
				       filter_mask, NULL);
}

/**
 * ice_vsi_update_bridge_mode - Update VSI for switching bridge mode (VEB/VEPA)
 * @vsi: Pointer to VSI structure
 * @bmode: Hardware bridge mode (VEB/VEPA)
 *
 * Returns 0 on success, negative on failure
 */
static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
{
	struct ice_aqc_vsi_props *vsi_props;
	struct ice_hw *hw = &vsi->back->hw;
	struct ice_vsi_ctx *ctxt;
	enum ice_status status;
	int ret = 0;

	vsi_props = &vsi->info;

	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
	if (!ctxt)
		return -ENOMEM;

	ctxt->info = vsi->info;

	if (bmode == BRIDGE_MODE_VEB)
		/* change from VEPA to VEB mode */
		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
	else
		/* change from VEB to VEPA mode */
		ctxt->info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);

	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
	if (status) {
		dev_err(&vsi->back->pdev->dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
			bmode, status, hw->adminq.sq_last_status);
		ret = -EIO;
		goto out;
	}
	/* Update sw flags for book keeping */
	vsi_props->sw_flags = ctxt->info.sw_flags;

out:
	kfree(ctxt);
	return ret;
}

/**
 * ice_bridge_setlink - Set the hardware bridge mode
 * @dev: the netdev being configured
 * @nlh: RTNL message
 * @flags: bridge setlink flags
 * @extack: netlink extended ack
 *
 * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is
 * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if
 * not already set for all VSIs connected to this switch. And also update the
 * unicast switch filter rules for the corresponding switch of the netdev.
 */
static int
ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
		   u16 __always_unused flags,
		   struct netlink_ext_ack __always_unused *extack)
{
	struct ice_netdev_priv *np = netdev_priv(dev);
	struct ice_pf *pf = np->vsi->back;
	struct nlattr *attr, *br_spec;
	struct ice_hw *hw = &pf->hw;
	enum ice_status status;
	struct ice_sw *pf_sw;
	int rem, v, err = 0;

	pf_sw = pf->first_sw;
	/* find the attribute in the netlink message */
	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);

	nla_for_each_nested(attr, br_spec, rem) {
		__u16 mode;

		if (nla_type(attr) != IFLA_BRIDGE_MODE)
			continue;
		mode = nla_get_u16(attr);
		if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB)
			return -EINVAL;
		/* Continue  if bridge mode is not being flipped */
		if (mode == pf_sw->bridge_mode)
			continue;
		/* Iterates through the PF VSI list and update the loopback
		 * mode of the VSI
		 */
		ice_for_each_vsi(pf, v) {
			if (!pf->vsi[v])
				continue;
			err = ice_vsi_update_bridge_mode(pf->vsi[v], mode);
			if (err)
				return err;
		}

		hw->evb_veb = (mode == BRIDGE_MODE_VEB);
		/* Update the unicast switch filter rules for the corresponding
		 * switch of the netdev
		 */
		status = ice_update_sw_rule_bridge_mode(hw);
		if (status) {
			netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n",
				   mode, status, hw->adminq.sq_last_status);
			/* revert hw->evb_veb */
			hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
			return -EIO;
		}

		pf_sw->bridge_mode = mode;
	}

	return 0;
}

/**
 * ice_tx_timeout - Respond to a Tx Hang
 * @netdev: network interface device structure
 */
static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_ring *tx_ring = NULL;
	struct ice_vsi *vsi = np->vsi;
	struct ice_pf *pf = vsi->back;
	int hung_queue = -1;
	u32 i;

	pf->tx_timeout_count++;

	/* find the stopped queue the same way dev_watchdog() does */
	for (i = 0; i < netdev->num_tx_queues; i++) {
		unsigned long trans_start;
		struct netdev_queue *q;

		q = netdev_get_tx_queue(netdev, i);
		trans_start = q->trans_start;
		if (netif_xmit_stopped(q) &&
		    time_after(jiffies,
			       trans_start + netdev->watchdog_timeo)) {
			hung_queue = i;
			break;
		}
	}

	if (i == netdev->num_tx_queues)
		netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
	else
		/* now that we have an index, find the tx_ring struct */
		for (i = 0; i < vsi->num_txq; i++)
			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
				if (hung_queue == vsi->tx_rings[i]->q_index) {
					tx_ring = vsi->tx_rings[i];
					break;
				}

	/* Reset recovery level if enough time has elapsed after last timeout.
	 * Also ensure no new reset action happens before next timeout period.
	 */
	if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ * 20)))
		pf->tx_timeout_recovery_level = 1;
	else if (time_before(jiffies, (pf->tx_timeout_last_recovery +
				       netdev->watchdog_timeo)))
		return;

	if (tx_ring) {
		struct ice_hw *hw = &pf->hw;
		u32 head, val = 0;

		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
		/* Read interrupt register */
		val = rd32(hw, 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,
			    head, tx_ring->next_to_use, val);
	}

	pf->tx_timeout_last_recovery = jiffies;
	netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
		    pf->tx_timeout_recovery_level, hung_queue);

	switch (pf->tx_timeout_recovery_level) {
	case 1:
		set_bit(__ICE_PFR_REQ, pf->state);
		break;
	case 2:
		set_bit(__ICE_CORER_REQ, pf->state);
		break;
	case 3:
		set_bit(__ICE_GLOBR_REQ, pf->state);
		break;
	default:
		netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n");
		set_bit(__ICE_DOWN, pf->state);
		set_bit(__ICE_NEEDS_RESTART, vsi->state);
		set_bit(__ICE_SERVICE_DIS, pf->state);
		break;
	}

	ice_service_task_schedule(pf);
	pf->tx_timeout_recovery_level++;
}

/**
 * ice_open - Called when a network interface becomes active
 * @netdev: network interface device structure
 *
 * The open entry point is called when a network interface is made
 * active by the system (IFF_UP). At this point all resources needed
 * for transmit and receive operations are allocated, the interrupt
 * handler is registered with the OS, the netdev watchdog is enabled,
 * and the stack is notified that the interface is ready.
 *
 * Returns 0 on success, negative value on failure
 */
int ice_open(struct net_device *netdev)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_port_info *pi;
	int err;

	if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) {
		netdev_err(netdev, "driver needs to be unloaded and reloaded\n");
		return -EIO;
	}

	netif_carrier_off(netdev);

	pi = vsi->port_info;
	err = ice_update_link_info(pi);
	if (err) {
		netdev_err(netdev, "Failed to get link info, error %d\n",
			   err);
		return err;
	}

	/* Set PHY if there is media, otherwise, turn off PHY */
	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
		err = ice_force_phys_link_state(vsi, true);
		if (err) {
			netdev_err(netdev,
				   "Failed to set physical link up, error %d\n",
				   err);
			return err;
		}
	} else {
		err = ice_aq_set_link_restart_an(pi, false, NULL);
		if (err) {
			netdev_err(netdev, "Failed to set PHY state, VSI %d error %d\n",
				   vsi->vsi_num, err);
			return err;
		}
		set_bit(ICE_FLAG_NO_MEDIA, vsi->back->flags);
	}

	err = ice_vsi_open(vsi);
	if (err)
		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
			   vsi->vsi_num, vsi->vsw->sw_id);
	return err;
}

/**
 * ice_stop - Disables a network interface
 * @netdev: network interface device structure
 *
 * The stop entry point is called when an interface is de-activated by the OS,
 * and the netdevice enters the DOWN state. The hardware is still under the
 * driver's control, but the netdev interface is disabled.
 *
 * Returns success only - not allowed to fail
 */
int ice_stop(struct net_device *netdev)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;

	ice_vsi_close(vsi);

	return 0;
}

/**
 * ice_features_check - Validate encapsulated packet conforms to limits
 * @skb: skb buffer
 * @netdev: This port's netdev
 * @features: Offload features that the stack believes apply
 */
static netdev_features_t
ice_features_check(struct sk_buff *skb,
		   struct net_device __always_unused *netdev,
		   netdev_features_t features)
{
	size_t len;

	/* No point in doing any of this if neither checksum nor GSO are
	 * being requested for this frame. We can rule out both by just
	 * checking for CHECKSUM_PARTIAL
	 */
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return features;

	/* We cannot support GSO if the MSS is going to be less than
	 * 64 bytes. If it is then we need to drop support for GSO.
	 */
	if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
		features &= ~NETIF_F_GSO_MASK;

	len = skb_network_header(skb) - skb->data;
	if (len & ~(ICE_TXD_MACLEN_MAX))
		goto out_rm_features;

	len = skb_transport_header(skb) - skb_network_header(skb);
	if (len & ~(ICE_TXD_IPLEN_MAX))
		goto out_rm_features;

	if (skb->encapsulation) {
		len = skb_inner_network_header(skb) - skb_transport_header(skb);
		if (len & ~(ICE_TXD_L4LEN_MAX))
			goto out_rm_features;

		len = skb_inner_transport_header(skb) -
		      skb_inner_network_header(skb);
		if (len & ~(ICE_TXD_IPLEN_MAX))
			goto out_rm_features;
	}

	return features;
out_rm_features:
	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}

static const struct net_device_ops ice_netdev_safe_mode_ops = {
	.ndo_open = ice_open,
	.ndo_stop = ice_stop,
	.ndo_start_xmit = ice_start_xmit,
	.ndo_set_mac_address = ice_set_mac_address,
	.ndo_validate_addr = eth_validate_addr,
	.ndo_change_mtu = ice_change_mtu,
	.ndo_get_stats64 = ice_get_stats64,
	.ndo_tx_timeout = ice_tx_timeout,
};

static const struct net_device_ops ice_netdev_ops = {
	.ndo_open = ice_open,
	.ndo_stop = ice_stop,
	.ndo_start_xmit = ice_start_xmit,
	.ndo_features_check = ice_features_check,
	.ndo_set_rx_mode = ice_set_rx_mode,
	.ndo_set_mac_address = ice_set_mac_address,
	.ndo_validate_addr = eth_validate_addr,
	.ndo_change_mtu = ice_change_mtu,
	.ndo_get_stats64 = ice_get_stats64,
	.ndo_set_tx_maxrate = ice_set_tx_maxrate,
	.ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
	.ndo_set_vf_mac = ice_set_vf_mac,
	.ndo_get_vf_config = ice_get_vf_cfg,
	.ndo_set_vf_trust = ice_set_vf_trust,
	.ndo_set_vf_vlan = ice_set_vf_port_vlan,
	.ndo_set_vf_link_state = ice_set_vf_link_state,
	.ndo_get_vf_stats = ice_get_vf_stats,
	.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
	.ndo_set_features = ice_set_features,
	.ndo_bridge_getlink = ice_bridge_getlink,
	.ndo_bridge_setlink = ice_bridge_setlink,
	.ndo_fdb_add = ice_fdb_add,
	.ndo_fdb_del = ice_fdb_del,
	.ndo_tx_timeout = ice_tx_timeout,
	.ndo_bpf = ice_xdp,
	.ndo_xdp_xmit = ice_xdp_xmit,
	.ndo_xsk_wakeup = ice_xsk_wakeup,
};