// 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_lib.h"
#include "ice_dcb_lib.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 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(&pf->pdev->dev,
                        "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 */
                        status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
                                                  ICE_FLTR_RX);
                        if (status) {
                                netdev_err(netdev, "Error setting default VSI %i Rx rule\n",
                                           vsi->vsi_num);
                                vsi->current_netdev_flags &= ~IFF_PROMISC;
                                err = -EIO;
                                goto out_promisc;
                        }
                } else {
                        /* Clear Rx filter to remove traffic from wire */
                        status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
                                                  ICE_FLTR_RX);
                        if (status) {
                                netdev_err(netdev, "Error clearing default VSI %i Rx rule\n",
                                           vsi->vsi_num);
                                vsi->current_netdev_flags |= IFF_PROMISC;
                                err = -EIO;
                                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_dis_vsi - pause a VSI
 * @vsi: the VSI being paused
 * @locked: is the rtnl_lock already held
 */
static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
{
        if (test_bit(__ICE_DOWN, vsi->state))
                return;

        set_bit(__ICE_NEEDS_RESTART, vsi->state);

        if (vsi->type == ICE_VSI_PF && vsi->netdev) {
                if (netif_running(vsi->netdev)) {
                        if (!locked)
                                rtnl_lock();

                        ice_stop(vsi->netdev);

                        if (!locked)
                                rtnl_unlock();
                } else {
                        ice_vsi_close(vsi);
                }
        }
}

/**
 * ice_pf_dis_all_vsi - Pause all VSIs on a PF
 * @pf: the PF
 * @locked: is the rtnl_lock already held
 */
#ifdef CONFIG_DCB
void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
#else
static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
#endif /* CONFIG_DCB */
{
        int v;

        ice_for_each_vsi(pf, v)
                if (pf->vsi[v])
                        ice_dis_vsi(pf->vsi[v], locked);
}

/**
 * ice_prepare_for_reset - prep for the core to reset
 * @pf: board private structure
 *
 * 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 */
        for (i = 0; i < pf->num_alloc_vfs; 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 = &pf->pdev->dev;
        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:
                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;
        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 = devm_kzalloc(&vsi->back->pdev->dev, 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";

        devm_kfree(&vsi->back->pdev->dev, 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 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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->dev,
                        "Could not process link event, error %d\n", status);

        return status;
}

/**
 * __ice_clean_ctrlq - helper function to clean controlq rings
 * @pf: ptr to struct ice_pf
 * @q_type: specific Control queue type
 */
static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
{
        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(&pf->pdev->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(&pf->pdev->dev,
                                "%s Receive Queue VF Error detected\n", qtype);
                if (val & PF_FW_ARQLEN_ARQOVFL_M) {
                        dev_dbg(&pf->pdev->dev,

                                "%s Receive Queue Overflow Error detected\n",
                                qtype);
                }
                if (val & PF_FW_ARQLEN_ARQCRIT_M)
                        dev_dbg(&pf->pdev->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(&pf->pdev->dev,
                                "%s Send Queue VF Error detected\n", qtype);
                if (val & PF_FW_ATQLEN_ATQOVFL_M) {
                        dev_dbg(&pf->pdev->dev,
                                "%s Send Queue Overflow Error detected\n",
                                qtype);
                }
                if (val & PF_FW_ATQLEN_ATQCRIT_M)
                        dev_dbg(&pf->pdev->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 = devm_kzalloc(&pf->pdev->dev, 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(&pf->pdev->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(&pf->pdev->dev,
                                        "Could not handle link event\n");
                        break;
                case ice_mbx_opc_send_msg_to_pf:
                        ice_vc_process_vf_msg(pf, &event);
                        break;
                case ice_aqc_opc_fw_logging:
                        ice_output_fw_log(hw, &event.desc, event.msg_buf);
                        break;
                case ice_aqc_opc_lldp_set_mib_change:
                        ice_dcb_process_lldp_set_mib_change(pf, &event);
                        break;
                default:
                        dev_dbg(&pf->pdev->dev,
                                "%s Receive Queue unknown event 0x%04x ignored\n",
                                qtype, opcode);
                        break;
                }
        } while (pending && (i++ < ICE_DFLT_IRQ_WORK));

        devm_kfree(&pf->pdev->dev, 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 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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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 */
        for (i = 0; i < pf->num_alloc_vfs; 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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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 = devm_kzalloc(dev, 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 = devm_kzalloc(dev, 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;
        }

        devm_kfree(dev, cfg);
out:
        devm_kfree(dev, 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_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;
        int rx_int_idx = 0;
        int tx_int_idx = 0;
        int vector, err;
        int irq_num;

        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(&pf->pdev->dev, irq_num,
                                       vsi->irq_handler, 0,
                                       q_vector->name, q_vector);
                if (err) {
                        netdev_err(vsi->netdev,
                                   "MSIX request_irq failed, error: %d\n", err);
                        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(&pf->pdev->dev, irq_num, &vsi->q_vectors[vector]);
        }
        return err;
}

/**
 * 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;
        u32 oicr, ena_mask;

        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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->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(&pf->pdev->dev,
                              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 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(&pf->pdev->dev),
                         dev_name(&pf->pdev->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(&pf->pdev->dev,
                               pf->msix_entries[pf->oicr_idx].vector,
                               ice_misc_intr, 0, pf->int_name, pf);
        if (err) {
                dev_err(&pf->pdev->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;

        /* 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, &pf->pdev->dev);
                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;
        }

        /* 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->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);

        /* 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(&pf->pdev->dev, 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)
{
        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(&pf->pdev->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(&pf->pdev->dev, "unable to reserve MSI-X vectors\n");
                err = v_actual;
                goto msix_err;
        }

        if (v_actual < v_budget) {
                dev_warn(&pf->pdev->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(&pf->pdev->dev, pf->msix_entries);
        goto exit_err;

no_hw_vecs_left_err:
        dev_err(&pf->pdev->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(&pf->pdev->dev, 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(&pf->pdev->dev, 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(&pf->pdev->dev, 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_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 = &pf->pdev->dev;

        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->adminq.sq_last_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 = &pf->pdev->dev;
        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(&pf->pdev->dev,
                         "%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 = &pf->pdev->dev;
        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];
        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);
        }

        return 0;

err_alloc_sw_unroll:
        set_bit(__ICE_SERVICE_DIS, pf->state);
        set_bit(__ICE_DOWN, pf->state);
        devm_kfree(&pf->pdev->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