ixgbe_main.c

// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 1999 - 2018 Intel Corporation. */

#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
#include <linux/pkt_sched.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/if_macvlan.h>
#include <linux/if_bridge.h>
#include <linux/prefetch.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/atomic.h>
#include <linux/numa.h>
#include <scsi/fc/fc_fcoe.h>
#include <net/udp_tunnel.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
#include <net/vxlan.h>
#include <net/mpls.h>
#include <net/xdp_sock.h>
#include <net/xfrm.h>

#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
#include "ixgbe_phy.h"
#include "ixgbe_sriov.h"
#include "ixgbe_model.h"
#include "ixgbe_txrx_common.h"

char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
			      "Intel(R) 10 Gigabit PCI Express Network Driver";
#ifdef IXGBE_FCOE
char ixgbe_default_device_descr[] =
			      "Intel(R) 10 Gigabit Network Connection";
#else
static char ixgbe_default_device_descr[] =
			      "Intel(R) 10 Gigabit Network Connection";
#endif
#define DRV_VERSION "5.1.0-k"
const char ixgbe_driver_version[] = DRV_VERSION;
static const char ixgbe_copyright[] =
				"Copyright (c) 1999-2016 Intel Corporation.";

static const char ixgbe_overheat_msg[] = "Network adapter has been stopped because it has over heated. Restart the computer. If the problem persists, power off the system and replace the adapter";

static const struct ixgbe_info *ixgbe_info_tbl[] = {
	[board_82598]		= &ixgbe_82598_info,
	[board_82599]		= &ixgbe_82599_info,
	[board_X540]		= &ixgbe_X540_info,
	[board_X550]		= &ixgbe_X550_info,
	[board_X550EM_x]	= &ixgbe_X550EM_x_info,
	[board_x550em_x_fw]	= &ixgbe_x550em_x_fw_info,
	[board_x550em_a]	= &ixgbe_x550em_a_info,
	[board_x550em_a_fw]	= &ixgbe_x550em_a_fw_info,
};

/* ixgbe_pci_tbl - PCI Device ID Table
 *
 * Wildcard entries (PCI_ANY_ID) should come last
 * Last entry must be all 0s
 *
 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
 *   Class, Class Mask, private data (not used) }
 */
static const struct pci_device_id ixgbe_pci_tbl[] = {
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII_L), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_10G_T), board_x550em_a},
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw },
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw },
	/* required last entry */
	{0, }
};
MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl);

#ifdef CONFIG_IXGBE_DCA
static int ixgbe_notify_dca(struct notifier_block *, unsigned long event,
			    void *p);
static struct notifier_block dca_notifier = {
	.notifier_call = ixgbe_notify_dca,
	.next          = NULL,
	.priority      = 0
};
#endif

#ifdef CONFIG_PCI_IOV
static unsigned int max_vfs;
module_param(max_vfs, uint, 0);
MODULE_PARM_DESC(max_vfs,
		 "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)");
#endif /* CONFIG_PCI_IOV */

static unsigned int allow_unsupported_sfp;
module_param(allow_unsupported_sfp, uint, 0);
MODULE_PARM_DESC(allow_unsupported_sfp,
		 "Allow unsupported and untested SFP+ modules on 82599-based adapters");

#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
static int debug = -1;
module_param(debug, int, 0);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);

static struct workqueue_struct *ixgbe_wq;

static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev);
static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *);

static const struct net_device_ops ixgbe_netdev_ops;

static bool netif_is_ixgbe(struct net_device *dev)
{
	return dev && (dev->netdev_ops == &ixgbe_netdev_ops);
}

static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
					  u32 reg, u16 *value)
{
	struct pci_dev *parent_dev;
	struct pci_bus *parent_bus;

	parent_bus = adapter->pdev->bus->parent;
	if (!parent_bus)
		return -1;

	parent_dev = parent_bus->self;
	if (!parent_dev)
		return -1;

	if (!pci_is_pcie(parent_dev))
		return -1;

	pcie_capability_read_word(parent_dev, reg, value);
	if (*value == IXGBE_FAILED_READ_CFG_WORD &&
	    ixgbe_check_cfg_remove(&adapter->hw, parent_dev))
		return -1;
	return 0;
}

static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u16 link_status = 0;
	int err;

	hw->bus.type = ixgbe_bus_type_pci_express;

	/* Get the negotiated link width and speed from PCI config space of the
	 * parent, as this device is behind a switch
	 */
	err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status);

	/* assume caller will handle error case */
	if (err)
		return err;

	hw->bus.width = ixgbe_convert_bus_width(link_status);
	hw->bus.speed = ixgbe_convert_bus_speed(link_status);

	return 0;
}

/**
 * ixgbe_check_from_parent - Determine whether PCIe info should come from parent
 * @hw: hw specific details
 *
 * This function is used by probe to determine whether a device's PCI-Express
 * bandwidth details should be gathered from the parent bus instead of from the
 * device. Used to ensure that various locations all have the correct device ID
 * checks.
 */
static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw)
{
	switch (hw->device_id) {
	case IXGBE_DEV_ID_82599_SFP_SF_QP:
	case IXGBE_DEV_ID_82599_QSFP_SF_QP:
		return true;
	default:
		return false;
	}
}

static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter,
				     int expected_gts)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct pci_dev *pdev;

	/* Some devices are not connected over PCIe and thus do not negotiate
	 * speed. These devices do not have valid bus info, and thus any report
	 * we generate may not be correct.
	 */
	if (hw->bus.type == ixgbe_bus_type_internal)
		return;

	/* determine whether to use the parent device */
	if (ixgbe_pcie_from_parent(&adapter->hw))
		pdev = adapter->pdev->bus->parent->self;
	else
		pdev = adapter->pdev;

	pcie_print_link_status(pdev);
}

static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter)
{
	if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
	    !test_bit(__IXGBE_REMOVING, &adapter->state) &&
	    !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state))
		queue_work(ixgbe_wq, &adapter->service_task);
}

static void ixgbe_remove_adapter(struct ixgbe_hw *hw)
{
	struct ixgbe_adapter *adapter = hw->back;

	if (!hw->hw_addr)
		return;
	hw->hw_addr = NULL;
	e_dev_err("Adapter removed\n");
	if (test_bit(__IXGBE_SERVICE_INITED, &adapter->state))
		ixgbe_service_event_schedule(adapter);
}

static u32 ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
{
	u8 __iomem *reg_addr;
	u32 value;
	int i;

	reg_addr = READ_ONCE(hw->hw_addr);
	if (ixgbe_removed(reg_addr))
		return IXGBE_FAILED_READ_REG;

	/* Register read of 0xFFFFFFF can indicate the adapter has been removed,
	 * so perform several status register reads to determine if the adapter
	 * has been removed.
	 */
	for (i = 0; i < IXGBE_FAILED_READ_RETRIES; i++) {
		value = readl(reg_addr + IXGBE_STATUS);
		if (value != IXGBE_FAILED_READ_REG)
			break;
		mdelay(3);
	}

	if (value == IXGBE_FAILED_READ_REG)
		ixgbe_remove_adapter(hw);
	else
		value = readl(reg_addr + reg);
	return value;
}

/**
 * ixgbe_read_reg - Read from device register
 * @hw: hw specific details
 * @reg: offset of register to read
 *
 * Returns : value read or IXGBE_FAILED_READ_REG if removed
 *
 * This function is used to read device registers. It checks for device
 * removal by confirming any read that returns all ones by checking the
 * status register value for all ones. This function avoids reading from
 * the hardware if a removal was previously detected in which case it
 * returns IXGBE_FAILED_READ_REG (all ones).
 */
u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg)
{
	u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr);
	u32 value;

	if (ixgbe_removed(reg_addr))
		return IXGBE_FAILED_READ_REG;
	if (unlikely(hw->phy.nw_mng_if_sel &
		     IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE)) {
		struct ixgbe_adapter *adapter;
		int i;

		for (i = 0; i < 200; ++i) {
			value = readl(reg_addr + IXGBE_MAC_SGMII_BUSY);
			if (likely(!value))
				goto writes_completed;
			if (value == IXGBE_FAILED_READ_REG) {
				ixgbe_remove_adapter(hw);
				return IXGBE_FAILED_READ_REG;
			}
			udelay(5);
		}

		adapter = hw->back;
		e_warn(hw, "register writes incomplete %08x\n", value);
	}

writes_completed:
	value = readl(reg_addr + reg);
	if (unlikely(value == IXGBE_FAILED_READ_REG))
		value = ixgbe_check_remove(hw, reg);
	return value;
}

static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev)
{
	u16 value;

	pci_read_config_word(pdev, PCI_VENDOR_ID, &value);
	if (value == IXGBE_FAILED_READ_CFG_WORD) {
		ixgbe_remove_adapter(hw);
		return true;
	}
	return false;
}

u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg)
{
	struct ixgbe_adapter *adapter = hw->back;
	u16 value;

	if (ixgbe_removed(hw->hw_addr))
		return IXGBE_FAILED_READ_CFG_WORD;
	pci_read_config_word(adapter->pdev, reg, &value);
	if (value == IXGBE_FAILED_READ_CFG_WORD &&
	    ixgbe_check_cfg_remove(hw, adapter->pdev))
		return IXGBE_FAILED_READ_CFG_WORD;
	return value;
}

#ifdef CONFIG_PCI_IOV
static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg)
{
	struct ixgbe_adapter *adapter = hw->back;
	u32 value;

	if (ixgbe_removed(hw->hw_addr))
		return IXGBE_FAILED_READ_CFG_DWORD;
	pci_read_config_dword(adapter->pdev, reg, &value);
	if (value == IXGBE_FAILED_READ_CFG_DWORD &&
	    ixgbe_check_cfg_remove(hw, adapter->pdev))
		return IXGBE_FAILED_READ_CFG_DWORD;
	return value;
}
#endif /* CONFIG_PCI_IOV */

void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value)
{
	struct ixgbe_adapter *adapter = hw->back;

	if (ixgbe_removed(hw->hw_addr))
		return;
	pci_write_config_word(adapter->pdev, reg, value);
}

static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
{
	BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));

	/* flush memory to make sure state is correct before next watchdog */
	smp_mb__before_atomic();
	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
}

struct ixgbe_reg_info {
	u32 ofs;
	char *name;
};

static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {

	/* General Registers */
	{IXGBE_CTRL, "CTRL"},
	{IXGBE_STATUS, "STATUS"},
	{IXGBE_CTRL_EXT, "CTRL_EXT"},

	/* Interrupt Registers */
	{IXGBE_EICR, "EICR"},

	/* RX Registers */
	{IXGBE_SRRCTL(0), "SRRCTL"},
	{IXGBE_DCA_RXCTRL(0), "DRXCTL"},
	{IXGBE_RDLEN(0), "RDLEN"},
	{IXGBE_RDH(0), "RDH"},
	{IXGBE_RDT(0), "RDT"},
	{IXGBE_RXDCTL(0), "RXDCTL"},
	{IXGBE_RDBAL(0), "RDBAL"},
	{IXGBE_RDBAH(0), "RDBAH"},

	/* TX Registers */
	{IXGBE_TDBAL(0), "TDBAL"},
	{IXGBE_TDBAH(0), "TDBAH"},
	{IXGBE_TDLEN(0), "TDLEN"},
	{IXGBE_TDH(0), "TDH"},
	{IXGBE_TDT(0), "TDT"},
	{IXGBE_TXDCTL(0), "TXDCTL"},

	/* List Terminator */
	{ .name = NULL }
};


/*
 * ixgbe_regdump - register printout routine
 */
static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
{
	int i;
	char rname[16];
	u32 regs[64];

	switch (reginfo->ofs) {
	case IXGBE_SRRCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i));
		break;
	case IXGBE_DCA_RXCTRL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
		break;
	case IXGBE_RDLEN(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i));
		break;
	case IXGBE_RDH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i));
		break;
	case IXGBE_RDT(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i));
		break;
	case IXGBE_RXDCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i));
		break;
	case IXGBE_RDBAL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i));
		break;
	case IXGBE_RDBAH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i));
		break;
	case IXGBE_TDBAL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i));
		break;
	case IXGBE_TDBAH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i));
		break;
	case IXGBE_TDLEN(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i));
		break;
	case IXGBE_TDH(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i));
		break;
	case IXGBE_TDT(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i));
		break;
	case IXGBE_TXDCTL(0):
		for (i = 0; i < 64; i++)
			regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
		break;
	default:
		pr_info("%-15s %08x\n",
			reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs));
		return;
	}

	i = 0;
	while (i < 64) {
		int j;
		char buf[9 * 8 + 1];
		char *p = buf;

		snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7);
		for (j = 0; j < 8; j++)
			p += sprintf(p, " %08x", regs[i++]);
		pr_err("%-15s%s\n", rname, buf);
	}

}

static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n)
{
	struct ixgbe_tx_buffer *tx_buffer;

	tx_buffer = &ring->tx_buffer_info[ring->next_to_clean];
	pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n",
		n, ring->next_to_use, ring->next_to_clean,
		(u64)dma_unmap_addr(tx_buffer, dma),
		dma_unmap_len(tx_buffer, len),
		tx_buffer->next_to_watch,
		(u64)tx_buffer->time_stamp);
}

/*
 * ixgbe_dump - Print registers, tx-rings and rx-rings
 */
static void ixgbe_dump(struct ixgbe_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_reg_info *reginfo;
	int n = 0;
	struct ixgbe_ring *ring;
	struct ixgbe_tx_buffer *tx_buffer;
	union ixgbe_adv_tx_desc *tx_desc;
	struct my_u0 { u64 a; u64 b; } *u0;
	struct ixgbe_ring *rx_ring;
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbe_rx_buffer *rx_buffer_info;
	int i = 0;

	if (!netif_msg_hw(adapter))
		return;

	/* Print netdevice Info */
	if (netdev) {
		dev_info(&adapter->pdev->dev, "Net device Info\n");
		pr_info("Device Name     state            "
			"trans_start\n");
		pr_info("%-15s %016lX %016lX\n",
			netdev->name,
			netdev->state,
			dev_trans_start(netdev));
	}

	/* Print Registers */
	dev_info(&adapter->pdev->dev, "Register Dump\n");
	pr_info(" Register Name   Value\n");
	for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl;
	     reginfo->name; reginfo++) {
		ixgbe_regdump(hw, reginfo);
	}

	/* Print TX Ring Summary */
	if (!netdev || !netif_running(netdev))
		return;

	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
	pr_info(" %s     %s              %s        %s\n",
		"Queue [NTU] [NTC] [bi(ntc)->dma  ]",
		"leng", "ntw", "timestamp");
	for (n = 0; n < adapter->num_tx_queues; n++) {
		ring = adapter->tx_ring[n];
		ixgbe_print_buffer(ring, n);
	}

	for (n = 0; n < adapter->num_xdp_queues; n++) {
		ring = adapter->xdp_ring[n];
		ixgbe_print_buffer(ring, n);
	}

	/* Print TX Rings */
	if (!netif_msg_tx_done(adapter))
		goto rx_ring_summary;

	dev_info(&adapter->pdev->dev, "TX Rings Dump\n");

	/* Transmit Descriptor Formats
	 *
	 * 82598 Advanced Transmit Descriptor
	 *   +--------------------------------------------------------------+
	 * 0 |         Buffer Address [63:0]                                |
	 *   +--------------------------------------------------------------+
	 * 8 |  PAYLEN  | POPTS  | IDX | STA | DCMD  |DTYP |  RSV |  DTALEN |
	 *   +--------------------------------------------------------------+
	 *   63       46 45    40 39 36 35 32 31   24 23 20 19              0
	 *
	 * 82598 Advanced Transmit Descriptor (Write-Back Format)
	 *   +--------------------------------------------------------------+
	 * 0 |                          RSV [63:0]                          |
	 *   +--------------------------------------------------------------+
	 * 8 |            RSV           |  STA  |          NXTSEQ           |
	 *   +--------------------------------------------------------------+
	 *   63                       36 35   32 31                         0
	 *
	 * 82599+ Advanced Transmit Descriptor
	 *   +--------------------------------------------------------------+
	 * 0 |         Buffer Address [63:0]                                |
	 *   +--------------------------------------------------------------+
	 * 8 |PAYLEN  |POPTS|CC|IDX  |STA  |DCMD  |DTYP |MAC  |RSV  |DTALEN |
	 *   +--------------------------------------------------------------+
	 *   63     46 45 40 39 38 36 35 32 31  24 23 20 19 18 17 16 15     0
	 *
	 * 82599+ Advanced Transmit Descriptor (Write-Back Format)
	 *   +--------------------------------------------------------------+
	 * 0 |                          RSV [63:0]                          |
	 *   +--------------------------------------------------------------+
	 * 8 |            RSV           |  STA  |           RSV             |
	 *   +--------------------------------------------------------------+
	 *   63                       36 35   32 31                         0
	 */

	for (n = 0; n < adapter->num_tx_queues; n++) {
		ring = adapter->tx_ring[n];
		pr_info("------------------------------------\n");
		pr_info("TX QUEUE INDEX = %d\n", ring->queue_index);
		pr_info("------------------------------------\n");
		pr_info("%s%s    %s              %s        %s          %s\n",
			"T [desc]     [address 63:0  ] ",
			"[PlPOIdStDDt Ln] [bi->dma       ] ",
			"leng", "ntw", "timestamp", "bi->skb");

		for (i = 0; ring->desc && (i < ring->count); i++) {
			tx_desc = IXGBE_TX_DESC(ring, i);
			tx_buffer = &ring->tx_buffer_info[i];
			u0 = (struct my_u0 *)tx_desc;
			if (dma_unmap_len(tx_buffer, len) > 0) {
				const char *ring_desc;

				if (i == ring->next_to_use &&
				    i == ring->next_to_clean)
					ring_desc = " NTC/U";
				else if (i == ring->next_to_use)
					ring_desc = " NTU";
				else if (i == ring->next_to_clean)
					ring_desc = " NTC";
				else
					ring_desc = "";
				pr_info("T [0x%03X]    %016llX %016llX %016llX %08X %p %016llX %p%s",
					i,
					le64_to_cpu((__force __le64)u0->a),
					le64_to_cpu((__force __le64)u0->b),
					(u64)dma_unmap_addr(tx_buffer, dma),
					dma_unmap_len(tx_buffer, len),
					tx_buffer->next_to_watch,
					(u64)tx_buffer->time_stamp,
					tx_buffer->skb,
					ring_desc);

				if (netif_msg_pktdata(adapter) &&
				    tx_buffer->skb)
					print_hex_dump(KERN_INFO, "",
						DUMP_PREFIX_ADDRESS, 16, 1,
						tx_buffer->skb->data,
						dma_unmap_len(tx_buffer, len),
						true);
			}
		}
	}

	/* Print RX Rings Summary */
rx_ring_summary:
	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
	pr_info("Queue [NTU] [NTC]\n");
	for (n = 0; n < adapter->num_rx_queues; n++) {
		rx_ring = adapter->rx_ring[n];
		pr_info("%5d %5X %5X\n",
			n, rx_ring->next_to_use, rx_ring->next_to_clean);
	}

	/* Print RX Rings */
	if (!netif_msg_rx_status(adapter))
		return;

	dev_info(&adapter->pdev->dev, "RX Rings Dump\n");

	/* Receive Descriptor Formats
	 *
	 * 82598 Advanced Receive Descriptor (Read) Format
	 *    63                                           1        0
	 *    +-----------------------------------------------------+
	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
	 *    +----------------------------------------------+------+
	 *  8 |       Header Buffer Address [63:1]           |  DD  |
	 *    +-----------------------------------------------------+
	 *
	 *
	 * 82598 Advanced Receive Descriptor (Write-Back) Format
	 *
	 *   63       48 47    32 31  30      21 20 16 15   4 3     0
	 *   +------------------------------------------------------+
	 * 0 |       RSS Hash /  |SPH| HDR_LEN  | RSV |Packet|  RSS |
	 *   | Packet   | IP     |   |          |     | Type | Type |
	 *   | Checksum | Ident  |   |          |     |      |      |
	 *   +------------------------------------------------------+
	 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
	 *   +------------------------------------------------------+
	 *   63       48 47    32 31            20 19               0
	 *
	 * 82599+ Advanced Receive Descriptor (Read) Format
	 *    63                                           1        0
	 *    +-----------------------------------------------------+
	 *  0 |       Packet Buffer Address [63:1]           |A0/NSE|
	 *    +----------------------------------------------+------+
	 *  8 |       Header Buffer Address [63:1]           |  DD  |
	 *    +-----------------------------------------------------+
	 *
	 *
	 * 82599+ Advanced Receive Descriptor (Write-Back) Format
	 *
	 *   63       48 47    32 31  30      21 20 17 16   4 3     0
	 *   +------------------------------------------------------+
	 * 0 |RSS / Frag Checksum|SPH| HDR_LEN  |RSC- |Packet|  RSS |
	 *   |/ RTT / PCoE_PARAM |   |          | CNT | Type | Type |
	 *   |/ Flow Dir Flt ID  |   |          |     |      |      |
	 *   +------------------------------------------------------+
	 * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP |
	 *   +------------------------------------------------------+
	 *   63       48 47    32 31          20 19                 0
	 */

	for (n = 0; n < adapter->num_rx_queues; n++) {
		rx_ring = adapter->rx_ring[n];
		pr_info("------------------------------------\n");
		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
		pr_info("------------------------------------\n");
		pr_info("%s%s%s\n",
			"R  [desc]      [ PktBuf     A0] ",
			"[  HeadBuf   DD] [bi->dma       ] [bi->skb       ] ",
			"<-- Adv Rx Read format");
		pr_info("%s%s%s\n",
			"RWB[desc]      [PcsmIpSHl PtRs] ",
			"[vl er S cks ln] ---------------- [bi->skb       ] ",
			"<-- Adv Rx Write-Back format");

		for (i = 0; i < rx_ring->count; i++) {
			const char *ring_desc;

			if (i == rx_ring->next_to_use)
				ring_desc = " NTU";
			else if (i == rx_ring->next_to_clean)
				ring_desc = " NTC";
			else
				ring_desc = "";

			rx_buffer_info = &rx_ring->rx_buffer_info[i];
			rx_desc = IXGBE_RX_DESC(rx_ring, i);
			u0 = (struct my_u0 *)rx_desc;
			if (rx_desc->wb.upper.length) {
				/* Descriptor Done */
				pr_info("RWB[0x%03X]     %016llX %016llX ---------------- %p%s\n",
					i,
					le64_to_cpu((__force __le64)u0->a),
					le64_to_cpu((__force __le64)u0->b),
					rx_buffer_info->skb,
					ring_desc);
			} else {
				pr_info("R  [0x%03X]     %016llX %016llX %016llX %p%s\n",
					i,
					le64_to_cpu((__force __le64)u0->a),
					le64_to_cpu((__force __le64)u0->b),
					(u64)rx_buffer_info->dma,
					rx_buffer_info->skb,
					ring_desc);

				if (netif_msg_pktdata(adapter) &&
				    rx_buffer_info->dma) {
					print_hex_dump(KERN_INFO, "",
					   DUMP_PREFIX_ADDRESS, 16, 1,
					   page_address(rx_buffer_info->page) +
						    rx_buffer_info->page_offset,
					   ixgbe_rx_bufsz(rx_ring), true);
				}
			}
		}
	}
}

static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
{
	u32 ctrl_ext;

	/* Let firmware take over control of h/w */
	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
			ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD);
}

static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter)
{
	u32 ctrl_ext;

	/* Let firmware know the driver has taken over */
	ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
	IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
			ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD);
}

/**
 * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
 * @adapter: pointer to adapter struct
 * @direction: 0 for Rx, 1 for Tx, -1 for other causes
 * @queue: queue to map the corresponding interrupt to
 * @msix_vector: the vector to map to the corresponding queue
 *
 */
static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
			   u8 queue, u8 msix_vector)
{
	u32 ivar, index;
	struct ixgbe_hw *hw = &adapter->hw;
	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
		if (direction == -1)
			direction = 0;
		index = (((direction * 64) + queue) >> 2) & 0x1F;
		ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
		ivar &= ~(0xFF << (8 * (queue & 0x3)));
		ivar |= (msix_vector << (8 * (queue & 0x3)));
		IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
	case ixgbe_mac_X550:
	case ixgbe_mac_X550EM_x:
	case ixgbe_mac_x550em_a:
		if (direction == -1) {
			/* other causes */
			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
			index = ((queue & 1) * 8);
			ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC);
			ivar &= ~(0xFF << index);
			ivar |= (msix_vector << index);
			IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar);
			break;
		} else {
			/* tx or rx causes */
			msix_vector |= IXGBE_IVAR_ALLOC_VAL;
			index = ((16 * (queue & 1)) + (8 * direction));
			ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1));
			ivar &= ~(0xFF << index);
			ivar |= (msix_vector << index);
			IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar);
			break;
		}
	default:
		break;
	}
}

void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
			    u64 qmask)
{
	u32 mask;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82598EB:
		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
	case ixgbe_mac_X550:
	case ixgbe_mac_X550EM_x:
	case ixgbe_mac_x550em_a:
		mask = (qmask & 0xFFFFFFFF);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
		mask = (qmask >> 32);
		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
		break;
	default:
		break;
	}
}

static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_hw_stats *hwstats = &adapter->stats;
	int i;
	u32 data;

	if ((hw->fc.current_mode != ixgbe_fc_full) &&
	    (hw->fc.current_mode != ixgbe_fc_rx_pause))
		return;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
		break;
	default:
		data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
	}
	hwstats->lxoffrxc += data;

	/* refill credits (no tx hang) if we received xoff */
	if (!data)
		return;

	for (i = 0; i < adapter->num_tx_queues; i++)
		clear_bit(__IXGBE_HANG_CHECK_ARMED,
			  &adapter->tx_ring[i]->state);

	for (i = 0; i < adapter->num_xdp_queues; i++)
		clear_bit(__IXGBE_HANG_CHECK_ARMED,
			  &adapter->xdp_ring[i]->state);
}

static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbe_hw_stats *hwstats = &adapter->stats;
	u32 xoff[8] = {0};
	u8 tc;
	int i;
	bool pfc_en = adapter->dcb_cfg.pfc_mode_enable;

	if (adapter->ixgbe_ieee_pfc)
		pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en);

	if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) {
		ixgbe_update_xoff_rx_lfc(adapter);
		return;
	}

	/* update stats for each tc, only valid with PFC enabled */
	for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
		u32 pxoffrxc;

		switch (hw->mac.type) {
		case ixgbe_mac_82598EB:
			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
			break;
		default:
			pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
		}
		hwstats->pxoffrxc[i] += pxoffrxc;
		/* Get the TC for given UP */
		tc = netdev_get_prio_tc_map(adapter->netdev, i);
		xoff[tc] += pxoffrxc;
	}

	/* disarm tx queues that have received xoff frames */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];

		tc = tx_ring->dcb_tc;
		if (xoff[tc])
			clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
	}

	for (i = 0; i < adapter->num_xdp_queues; i++) {
		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];

		tc = xdp_ring->dcb_tc;
		if (xoff[tc])
			clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state);
	}
}

static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
{
	return ring->stats.packets;
}

static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
{
	unsigned int head, tail;

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

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

static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
{
	u32 tx_done = ixgbe_get_tx_completed(tx_ring);
	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
	u32 tx_pending = ixgbe_get_tx_pending(tx_ring);

	clear_check_for_tx_hang(tx_ring);

	/*
	 * Check for a hung queue, but be thorough. This verifies
	 * that a transmit has been completed since the previous
	 * check AND there is at least one packet pending. The
	 * ARMED bit is set to indicate a potential hang. The
	 * bit is cleared if a pause frame is received to remove
	 * false hang detection due to PFC or 802.3x frames. By
	 * requiring this to fail twice we avoid races with
	 * pfc clearing the ARMED bit and conditions where we
	 * run the check_tx_hang logic with a transmit completion
	 * pending but without time to complete it yet.
	 */
	if (tx_done_old == tx_done && tx_pending)
		/* make sure it is true for two checks in a row */
		return test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
					&tx_ring->state);
	/* update completed stats and continue */
	tx_ring->tx_stats.tx_done_old = tx_done;
	/* reset the countdown */
	clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);

	return false;
}

/**
 * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout
 * @adapter: driver private struct
 **/
static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
{

	/* Do the reset outside of interrupt context */
	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
		set_bit(__IXGBE_RESET_REQUESTED, &adapter->state);
		e_warn(drv, "initiating reset due to tx timeout\n");
		ixgbe_service_event_schedule(adapter);
	}
}

/**
 * ixgbe_tx_maxrate - callback to set the maximum per-queue bitrate
 * @netdev: network interface device structure
 * @queue_index: Tx queue to set
 * @maxrate: desired maximum transmit bitrate
 **/
static int ixgbe_tx_maxrate(struct net_device *netdev,
			    int queue_index, u32 maxrate)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	u32 bcnrc_val = ixgbe_link_mbps(adapter);

	if (!maxrate)
		return 0;

	/* Calculate the rate factor values to set */
	bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
	bcnrc_val /= maxrate;

	/* clear everything but the rate factor */
	bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK |
	IXGBE_RTTBCNRC_RF_DEC_MASK;

	/* enable the rate scheduler */
	bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;

	IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, queue_index);
	IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);

	return 0;
}

/**
 * ixgbe_clean_tx_irq - Reclaim resources after transmit completes
 * @q_vector: structure containing interrupt and ring information
 * @tx_ring: tx ring to clean
 * @napi_budget: Used to determine if we are in netpoll
 **/
static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
			       struct ixgbe_ring *tx_ring, int napi_budget)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_tx_buffer *tx_buffer;
	union ixgbe_adv_tx_desc *tx_desc;
	unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0;
	unsigned int budget = q_vector->tx.work_limit;
	unsigned int i = tx_ring->next_to_clean;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return true;

	tx_buffer = &tx_ring->tx_buffer_info[i];
	tx_desc = IXGBE_TX_DESC(tx_ring, i);
	i -= tx_ring->count;

	do {
		union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;

		/* if next_to_watch is not set then there is no work pending */
		if (!eop_desc)
			break;

		/* prevent any other reads prior to eop_desc */
		smp_rmb();

		/* if DD is not set pending work has not been completed */
		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
			break;

		/* clear next_to_watch to prevent false hangs */
		tx_buffer->next_to_watch = NULL;

		/* update the statistics for this packet */
		total_bytes += tx_buffer->bytecount;
		total_packets += tx_buffer->gso_segs;
		if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC)
			total_ipsec++;

		/* free the skb */
		if (ring_is_xdp(tx_ring))
			xdp_return_frame(tx_buffer->xdpf);
		else
			napi_consume_skb(tx_buffer->skb, napi_budget);

		/* unmap skb header data */
		dma_unmap_single(tx_ring->dev,
				 dma_unmap_addr(tx_buffer, dma),
				 dma_unmap_len(tx_buffer, len),
				 DMA_TO_DEVICE);

		/* clear tx_buffer data */
		dma_unmap_len_set(tx_buffer, len, 0);

		/* unmap remaining buffers */
		while (tx_desc != eop_desc) {
			tx_buffer++;
			tx_desc++;
			i++;
			if (unlikely(!i)) {
				i -= tx_ring->count;
				tx_buffer = tx_ring->tx_buffer_info;
				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
			}