Merge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
1GbE Intel Wired LAN Driver Updates 2018-10-17

This series adds support for the new igc driver.

The igc driver is the new client driver supporting the Intel I225
Ethernet Controller, which supports 2.5GbE speeds. The reason for
creating a new client driver, instead of adding support for the new
device in e1000e, is that the silicon behaves more like devices
supported in igb driver. It also did not make sense to add a client
part, to the igb driver which supports only 1GbE server parts.

This initial set of patches is designed for basic support (i.e. link and
pass traffic). Follow-on patch series will add more advanced support
like VLAN, Wake-on-LAN, etc..
====================

Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/intel/Kconfig

···
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
 
+config IGC
+	tristate "Intel(R) Ethernet Controller I225-LM/I225-V support"
+	default n
+	depends on PCI
+	---help---
+	  This driver supports Intel(R) Ethernet Controller I225-LM/I225-V
+	  family of adapters.
+
+	  For more information on how to identify your adapter, go
+	  to the Adapter & Driver ID Guide that can be located at:
+
+	  <http://support.intel.com>
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called igc.
+
 endif # NET_VENDOR_INTEL

drivers/net/ethernet/intel/Makefile

···
 obj-$(CONFIG_E1000) += e1000/
 obj-$(CONFIG_E1000E) += e1000e/
 obj-$(CONFIG_IGB) += igb/
+obj-$(CONFIG_IGC) += igc/
 obj-$(CONFIG_IGBVF) += igbvf/
 obj-$(CONFIG_IXGBE) += ixgbe/
 obj-$(CONFIG_IXGBEVF) += ixgbevf/

drivers/net/ethernet/intel/igc/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c)  2018 Intel Corporation
+
+#
+# Intel(R) I225-LM/I225-V 2.5G Ethernet Controller
+#
+
+obj-$(CONFIG_IGC) += igc.o
+
+igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o

drivers/net/ethernet/intel/igc/igc.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_H_
+#define _IGC_H_
+
+#include <linux/kobject.h>
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+
+#include <linux/ethtool.h>
+
+#include <linux/sctp.h>
+
+#define IGC_ERR(args...) pr_err("igc: " args)
+
+#define PFX "igc: "
+
+#include <linux/timecounter.h>
+#include <linux/net_tstamp.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "igc_hw.h"
+
+/* main */
+extern char igc_driver_name[];
+extern char igc_driver_version[];
+
+/* Interrupt defines */
+#define IGC_START_ITR			648 /* ~6000 ints/sec */
+#define IGC_FLAG_HAS_MSI		BIT(0)
+#define IGC_FLAG_QUEUE_PAIRS		BIT(4)
+#define IGC_FLAG_NEED_LINK_UPDATE	BIT(9)
+#define IGC_FLAG_MEDIA_RESET		BIT(10)
+#define IGC_FLAG_MAS_ENABLE		BIT(12)
+#define IGC_FLAG_HAS_MSIX		BIT(13)
+#define IGC_FLAG_VLAN_PROMISC		BIT(15)
+
+#define IGC_START_ITR			648 /* ~6000 ints/sec */
+#define IGC_4K_ITR			980
+#define IGC_20K_ITR			196
+#define IGC_70K_ITR			56
+
+#define IGC_DEFAULT_ITR		3 /* dynamic */
+#define IGC_MAX_ITR_USECS	10000
+#define IGC_MIN_ITR_USECS	10
+#define NON_Q_VECTORS		1
+#define MAX_MSIX_ENTRIES	10
+
+/* TX/RX descriptor defines */
+#define IGC_DEFAULT_TXD		256
+#define IGC_DEFAULT_TX_WORK	128
+#define IGC_MIN_TXD		80
+#define IGC_MAX_TXD		4096
+
+#define IGC_DEFAULT_RXD		256
+#define IGC_MIN_RXD		80
+#define IGC_MAX_RXD		4096
+
+/* Transmit and receive queues */
+#define IGC_MAX_RX_QUEUES		4
+#define IGC_MAX_TX_QUEUES		4
+
+#define MAX_Q_VECTORS			8
+#define MAX_STD_JUMBO_FRAME_SIZE	9216
+
+/* Supported Rx Buffer Sizes */
+#define IGC_RXBUFFER_256		256
+#define IGC_RXBUFFER_2048		2048
+#define IGC_RXBUFFER_3072		3072
+
+#define IGC_RX_HDR_LEN			IGC_RXBUFFER_256
+
+/* RX and TX descriptor control thresholds.
+ * PTHRESH - MAC will consider prefetch if it has fewer than this number of
+ *           descriptors available in its onboard memory.
+ *           Setting this to 0 disables RX descriptor prefetch.
+ * HTHRESH - MAC will only prefetch if there are at least this many descriptors
+ *           available in host memory.
+ *           If PTHRESH is 0, this should also be 0.
+ * WTHRESH - RX descriptor writeback threshold - MAC will delay writing back
+ *           descriptors until either it has this many to write back, or the
+ *           ITR timer expires.
+ */
+#define IGC_RX_PTHRESH			8
+#define IGC_RX_HTHRESH			8
+#define IGC_TX_PTHRESH			8
+#define IGC_TX_HTHRESH			1
+#define IGC_RX_WTHRESH			4
+#define IGC_TX_WTHRESH			16
+
+#define IGC_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+#define IGC_TS_HDR_LEN			16
+
+#define IGC_SKB_PAD			(NET_SKB_PAD + NET_IP_ALIGN)
+
+#if (PAGE_SIZE < 8192)
+#define IGC_MAX_FRAME_BUILD_SKB \
+	(SKB_WITH_OVERHEAD(IGC_RXBUFFER_2048) - IGC_SKB_PAD - IGC_TS_HDR_LEN)
+#else
+#define IGC_MAX_FRAME_BUILD_SKB (IGC_RXBUFFER_2048 - IGC_TS_HDR_LEN)
+#endif
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IGC_RX_BUFFER_WRITE	16 /* Must be power of 2 */
+
+/* igc_test_staterr - tests bits within Rx descriptor status and error fields */
+static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc,
+				      const u32 stat_err_bits)
+{
+	return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits);
+}
+
+enum igc_state_t {
+	__IGC_TESTING,
+	__IGC_RESETTING,
+	__IGC_DOWN,
+	__IGC_PTP_TX_IN_PROGRESS,
+};
+
+enum igc_tx_flags {
+	/* cmd_type flags */
+	IGC_TX_FLAGS_VLAN	= 0x01,
+	IGC_TX_FLAGS_TSO	= 0x02,
+	IGC_TX_FLAGS_TSTAMP	= 0x04,
+
+	/* olinfo flags */
+	IGC_TX_FLAGS_IPV4	= 0x10,
+	IGC_TX_FLAGS_CSUM	= 0x20,
+};
+
+enum igc_boards {
+	board_base,
+};
+
+/* The largest size we can write to the descriptor is 65535.  In order to
+ * maintain a power of two alignment we have to limit ourselves to 32K.
+ */
+#define IGC_MAX_TXD_PWR		15
+#define IGC_MAX_DATA_PER_TXD	BIT(IGC_MAX_TXD_PWR)
+
+/* Tx Descriptors needed, worst case */
+#define TXD_USE_COUNT(S)	DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD)
+#define DESC_NEEDED	(MAX_SKB_FRAGS + 4)
+
+/* wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct igc_tx_buffer {
+	union igc_adv_tx_desc *next_to_watch;
+	unsigned long time_stamp;
+	struct sk_buff *skb;
+	unsigned int bytecount;
+	u16 gso_segs;
+	__be16 protocol;
+
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+	u32 tx_flags;
+};
+
+struct igc_rx_buffer {
+	dma_addr_t dma;
+	struct page *page;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
+};
+
+struct igc_tx_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 restart_queue;
+	u64 restart_queue2;
+};
+
+struct igc_rx_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 drops;
+	u64 csum_err;
+	u64 alloc_failed;
+};
+
+struct igc_rx_packet_stats {
+	u64 ipv4_packets;      /* IPv4 headers processed */
+	u64 ipv4e_packets;     /* IPv4E headers with extensions processed */
+	u64 ipv6_packets;      /* IPv6 headers processed */
+	u64 ipv6e_packets;     /* IPv6E headers with extensions processed */
+	u64 tcp_packets;       /* TCP headers processed */
+	u64 udp_packets;       /* UDP headers processed */
+	u64 sctp_packets;      /* SCTP headers processed */
+	u64 nfs_packets;       /* NFS headers processe */
+	u64 other_packets;
+};
+
+struct igc_ring_container {
+	struct igc_ring *ring;          /* pointer to linked list of rings */
+	unsigned int total_bytes;       /* total bytes processed this int */
+	unsigned int total_packets;     /* total packets processed this int */
+	u16 work_limit;                 /* total work allowed per interrupt */
+	u8 count;                       /* total number of rings in vector */
+	u8 itr;                         /* current ITR setting for ring */
+};
+
+struct igc_ring {
+	struct igc_q_vector *q_vector;  /* backlink to q_vector */
+	struct net_device *netdev;      /* back pointer to net_device */
+	struct device *dev;             /* device for dma mapping */
+	union {                         /* array of buffer info structs */
+		struct igc_tx_buffer *tx_buffer_info;
+		struct igc_rx_buffer *rx_buffer_info;
+	};
+	void *desc;                     /* descriptor ring memory */
+	unsigned long flags;            /* ring specific flags */
+	void __iomem *tail;             /* pointer to ring tail register */
+	dma_addr_t dma;                 /* phys address of the ring */
+	unsigned int size;              /* length of desc. ring in bytes */
+
+	u16 count;                      /* number of desc. in the ring */
+	u8 queue_index;                 /* logical index of the ring*/
+	u8 reg_idx;                     /* physical index of the ring */
+
+	/* everything past this point are written often */
+	u16 next_to_clean;
+	u16 next_to_use;
+	u16 next_to_alloc;
+
+	union {
+		/* TX */
+		struct {
+			struct igc_tx_queue_stats tx_stats;
+			struct u64_stats_sync tx_syncp;
+			struct u64_stats_sync tx_syncp2;
+		};
+		/* RX */
+		struct {
+			struct igc_rx_queue_stats rx_stats;
+			struct igc_rx_packet_stats pkt_stats;
+			struct u64_stats_sync rx_syncp;
+			struct sk_buff *skb;
+		};
+	};
+} ____cacheline_internodealigned_in_smp;
+
+struct igc_q_vector {
+	struct igc_adapter *adapter;    /* backlink */
+	void __iomem *itr_register;
+	u32 eims_value;                 /* EIMS mask value */
+
+	u16 itr_val;
+	u8 set_itr;
+
+	struct igc_ring_container rx, tx;
+
+	struct napi_struct napi;
+
+	struct rcu_head rcu;    /* to avoid race with update stats on free */
+	char name[IFNAMSIZ + 9];
+	struct net_device poll_dev;
+
+	/* for dynamic allocation of rings associated with this q_vector */
+	struct igc_ring ring[0] ____cacheline_internodealigned_in_smp;
+};
+
+struct igc_mac_addr {
+	u8 addr[ETH_ALEN];
+	u8 queue;
+	u8 state; /* bitmask */
+};
+
+#define IGC_MAC_STATE_DEFAULT	0x1
+#define IGC_MAC_STATE_MODIFIED	0x2
+#define IGC_MAC_STATE_IN_USE	0x4
+
+/* Board specific private data structure */
+struct igc_adapter {
+	struct net_device *netdev;
+
+	unsigned long state;
+	unsigned int flags;
+	unsigned int num_q_vectors;
+
+	struct msix_entry *msix_entries;
+
+	/* TX */
+	u16 tx_work_limit;
+	u32 tx_timeout_count;
+	int num_tx_queues;
+	struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES];
+
+	/* RX */
+	int num_rx_queues;
+	struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES];
+
+	struct timer_list watchdog_timer;
+	struct timer_list dma_err_timer;
+	struct timer_list phy_info_timer;
+
+	u16 link_speed;
+	u16 link_duplex;
+
+	u8 port_num;
+
+	u8 __iomem *io_addr;
+	/* Interrupt Throttle Rate */
+	u32 rx_itr_setting;
+	u32 tx_itr_setting;
+
+	struct work_struct reset_task;
+	struct work_struct watchdog_task;
+	struct work_struct dma_err_task;
+	bool fc_autoneg;
+
+	u8 tx_timeout_factor;
+
+	int msg_enable;
+	u32 max_frame_size;
+	u32 min_frame_size;
+
+	/* OS defined structs */
+	struct pci_dev *pdev;
+	/* lock for statistics */
+	spinlock_t stats64_lock;
+	struct rtnl_link_stats64 stats64;
+
+	/* structs defined in igc_hw.h */
+	struct igc_hw hw;
+	struct igc_hw_stats stats;
+
+	struct igc_q_vector *q_vector[MAX_Q_VECTORS];
+	u32 eims_enable_mask;
+	u32 eims_other;
+
+	u16 tx_ring_count;
+	u16 rx_ring_count;
+
+	u32 *shadow_vfta;
+
+	u32 rss_queues;
+
+	/* lock for RX network flow classification filter */
+	spinlock_t nfc_lock;
+
+	struct igc_mac_addr *mac_table;
+
+	unsigned long link_check_timeout;
+	struct igc_info ei;
+};
+
+/* igc_desc_unused - calculate if we have unused descriptors */
+static inline u16 igc_desc_unused(const struct igc_ring *ring)
+{
+	u16 ntc = ring->next_to_clean;
+	u16 ntu = ring->next_to_use;
+
+	return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1;
+}
+
+static inline s32 igc_get_phy_info(struct igc_hw *hw)
+{
+	if (hw->phy.ops.get_phy_info)
+		return hw->phy.ops.get_phy_info(hw);
+
+	return 0;
+}
+
+static inline s32 igc_reset_phy(struct igc_hw *hw)
+{
+	if (hw->phy.ops.reset)
+		return hw->phy.ops.reset(hw);
+
+	return 0;
+}
+
+static inline struct netdev_queue *txring_txq(const struct igc_ring *tx_ring)
+{
+	return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
+}
+
+enum igc_ring_flags_t {
+	IGC_RING_FLAG_RX_3K_BUFFER,
+	IGC_RING_FLAG_RX_BUILD_SKB_ENABLED,
+	IGC_RING_FLAG_RX_SCTP_CSUM,
+	IGC_RING_FLAG_RX_LB_VLAN_BSWAP,
+	IGC_RING_FLAG_TX_CTX_IDX,
+	IGC_RING_FLAG_TX_DETECT_HANG
+};
+
+#define ring_uses_large_buffer(ring) \
+	test_bit(IGC_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+
+#define ring_uses_build_skb(ring) \
+	test_bit(IGC_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
+static inline unsigned int igc_rx_bufsz(struct igc_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return IGC_RXBUFFER_3072;
+
+	if (ring_uses_build_skb(ring))
+		return IGC_MAX_FRAME_BUILD_SKB + IGC_TS_HDR_LEN;
+#endif
+	return IGC_RXBUFFER_2048;
+}
+
+static inline unsigned int igc_rx_pg_order(struct igc_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return 1;
+#endif
+	return 0;
+}
+
+static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
+{
+	if (hw->phy.ops.read_reg)
+		return hw->phy.ops.read_reg(hw, offset, data);
+
+	return 0;
+}
+
+#define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
+
+#define IGC_TXD_DCMD	(IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS)
+
+#define IGC_RX_DESC(R, i)       \
+	(&(((union igc_adv_rx_desc *)((R)->desc))[i]))
+#define IGC_TX_DESC(R, i)       \
+	(&(((union igc_adv_tx_desc *)((R)->desc))[i]))
+#define IGC_TX_CTXTDESC(R, i)   \
+	(&(((struct igc_adv_tx_context_desc *)((R)->desc))[i]))
+
+#endif /* _IGC_H_ */

drivers/net/ethernet/intel/igc/igc_base.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include <linux/delay.h>
+
+#include "igc_hw.h"
+#include "igc_i225.h"
+#include "igc_mac.h"
+#include "igc_base.h"
+#include "igc.h"
+
+/**
+ * igc_set_pcie_completion_timeout - set pci-e completion timeout
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_set_pcie_completion_timeout(struct igc_hw *hw)
+{
+	u32 gcr = rd32(IGC_GCR);
+	u16 pcie_devctl2;
+	s32 ret_val = 0;
+
+	/* only take action if timeout value is defaulted to 0 */
+	if (gcr & IGC_GCR_CMPL_TMOUT_MASK)
+		goto out;
+
+	/* if capabilities version is type 1 we can write the
+	 * timeout of 10ms to 200ms through the GCR register
+	 */
+	if (!(gcr & IGC_GCR_CAP_VER2)) {
+		gcr |= IGC_GCR_CMPL_TMOUT_10ms;
+		goto out;
+	}
+
+	/* for version 2 capabilities we need to write the config space
+	 * directly in order to set the completion timeout value for
+	 * 16ms to 55ms
+	 */
+	ret_val = igc_read_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
+					&pcie_devctl2);
+	if (ret_val)
+		goto out;
+
+	pcie_devctl2 |= PCIE_DEVICE_CONTROL2_16ms;
+
+	ret_val = igc_write_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
+					 &pcie_devctl2);
+out:
+	/* disable completion timeout resend */
+	gcr &= ~IGC_GCR_CMPL_TMOUT_RESEND;
+
+	wr32(IGC_GCR, gcr);
+
+	return ret_val;
+}
+
+/**
+ * igc_check_for_link_base - Check for link
+ * @hw: pointer to the HW structure
+ *
+ * If sgmii is enabled, then use the pcs register to determine link, otherwise
+ * use the generic interface for determining link.
+ */
+static s32 igc_check_for_link_base(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+
+	ret_val = igc_check_for_copper_link(hw);
+
+	return ret_val;
+}
+
+/**
+ * igc_reset_hw_base - Reset hardware
+ * @hw: pointer to the HW structure
+ *
+ * This resets the hardware into a known state.  This is a
+ * function pointer entry point called by the api module.
+ */
+static s32 igc_reset_hw_base(struct igc_hw *hw)
+{
+	s32 ret_val;
+	u32 ctrl;
+
+	/* Prevent the PCI-E bus from sticking if there is no TLP connection
+	 * on the last TLP read/write transaction when MAC is reset.
+	 */
+	ret_val = igc_disable_pcie_master(hw);
+	if (ret_val)
+		hw_dbg("PCI-E Master disable polling has failed.\n");
+
+	/* set the completion timeout for interface */
+	ret_val = igc_set_pcie_completion_timeout(hw);
+	if (ret_val)
+		hw_dbg("PCI-E Set completion timeout has failed.\n");
+
+	hw_dbg("Masking off all interrupts\n");
+	wr32(IGC_IMC, 0xffffffff);
+
+	wr32(IGC_RCTL, 0);
+	wr32(IGC_TCTL, IGC_TCTL_PSP);
+	wrfl();
+
+	usleep_range(10000, 20000);
+
+	ctrl = rd32(IGC_CTRL);
+
+	hw_dbg("Issuing a global reset to MAC\n");
+	wr32(IGC_CTRL, ctrl | IGC_CTRL_RST);
+
+	ret_val = igc_get_auto_rd_done(hw);
+	if (ret_val) {
+		/* When auto config read does not complete, do not
+		 * return with an error. This can happen in situations
+		 * where there is no eeprom and prevents getting link.
+		 */
+		hw_dbg("Auto Read Done did not complete\n");
+	}
+
+	/* Clear any pending interrupt events. */
+	wr32(IGC_IMC, 0xffffffff);
+	rd32(IGC_ICR);
+
+	return ret_val;
+}
+
+/**
+ * igc_get_phy_id_base - Retrieve PHY addr and id
+ * @hw: pointer to the HW structure
+ *
+ * Retrieves the PHY address and ID for both PHY's which do and do not use
+ * sgmi interface.
+ */
+static s32 igc_get_phy_id_base(struct igc_hw *hw)
+{
+	s32  ret_val = 0;
+
+	ret_val = igc_get_phy_id(hw);
+
+	return ret_val;
+}
+
+/**
+ * igc_init_nvm_params_base - Init NVM func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_nvm_params_base(struct igc_hw *hw)
+{
+	struct igc_nvm_info *nvm = &hw->nvm;
+	u32 eecd = rd32(IGC_EECD);
+	u16 size;
+
+	size = (u16)((eecd & IGC_EECD_SIZE_EX_MASK) >>
+		     IGC_EECD_SIZE_EX_SHIFT);
+
+	/* Added to a constant, "size" becomes the left-shift value
+	 * for setting word_size.
+	 */
+	size += NVM_WORD_SIZE_BASE_SHIFT;
+
+	/* Just in case size is out of range, cap it to the largest
+	 * EEPROM size supported
+	 */
+	if (size > 15)
+		size = 15;
+
+	nvm->word_size = BIT(size);
+	nvm->opcode_bits = 8;
+	nvm->delay_usec = 1;
+
+	nvm->page_size = eecd & IGC_EECD_ADDR_BITS ? 32 : 8;
+	nvm->address_bits = eecd & IGC_EECD_ADDR_BITS ?
+			    16 : 8;
+
+	if (nvm->word_size == BIT(15))
+		nvm->page_size = 128;
+
+	return 0;
+}
+
+/**
+ * igc_setup_copper_link_base - Configure copper link settings
+ * @hw: pointer to the HW structure
+ *
+ * Configures the link for auto-neg or forced speed and duplex.  Then we check
+ * for link, once link is established calls to configure collision distance
+ * and flow control are called.
+ */
+static s32 igc_setup_copper_link_base(struct igc_hw *hw)
+{
+	s32  ret_val = 0;
+	u32 ctrl;
+
+	ctrl = rd32(IGC_CTRL);
+	ctrl |= IGC_CTRL_SLU;
+	ctrl &= ~(IGC_CTRL_FRCSPD | IGC_CTRL_FRCDPX);
+	wr32(IGC_CTRL, ctrl);
+
+	ret_val = igc_setup_copper_link(hw);
+
+	return ret_val;
+}
+
+/**
+ * igc_init_mac_params_base - Init MAC func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_mac_params_base(struct igc_hw *hw)
+{
+	struct igc_dev_spec_base *dev_spec = &hw->dev_spec._base;
+	struct igc_mac_info *mac = &hw->mac;
+
+	/* Set mta register count */
+	mac->mta_reg_count = 128;
+	mac->rar_entry_count = IGC_RAR_ENTRIES;
+
+	/* reset */
+	mac->ops.reset_hw = igc_reset_hw_base;
+
+	mac->ops.acquire_swfw_sync = igc_acquire_swfw_sync_i225;
+	mac->ops.release_swfw_sync = igc_release_swfw_sync_i225;
+
+	/* Allow a single clear of the SW semaphore on I225 */
+	if (mac->type == igc_i225)
+		dev_spec->clear_semaphore_once = true;
+
+	/* physical interface link setup */
+	mac->ops.setup_physical_interface = igc_setup_copper_link_base;
+
+	return 0;
+}
+
+/**
+ * igc_init_phy_params_base - Init PHY func ptrs.
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_init_phy_params_base(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	s32 ret_val = 0;
+	u32 ctrl_ext;
+
+	if (hw->phy.media_type != igc_media_type_copper) {
+		phy->type = igc_phy_none;
+		goto out;
+	}
+
+	phy->autoneg_mask	= AUTONEG_ADVERTISE_SPEED_DEFAULT_2500;
+	phy->reset_delay_us	= 100;
+
+	ctrl_ext = rd32(IGC_CTRL_EXT);
+
+	/* set lan id */
+	hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >>
+			IGC_STATUS_FUNC_SHIFT;
+
+	/* Make sure the PHY is in a good state. Several people have reported
+	 * firmware leaving the PHY's page select register set to something
+	 * other than the default of zero, which causes the PHY ID read to
+	 * access something other than the intended register.
+	 */
+	ret_val = hw->phy.ops.reset(hw);
+	if (ret_val) {
+		hw_dbg("Error resetting the PHY.\n");
+		goto out;
+	}
+
+	ret_val = igc_get_phy_id_base(hw);
+	if (ret_val)
+		return ret_val;
+
+	igc_check_for_link_base(hw);
+
+	/* Verify phy id and set remaining function pointers */
+	switch (phy->id) {
+	case I225_I_PHY_ID:
+		phy->type	= igc_phy_i225;
+		break;
+	default:
+		ret_val = -IGC_ERR_PHY;
+		goto out;
+	}
+
+out:
+	return ret_val;
+}
+
+static s32 igc_get_invariants_base(struct igc_hw *hw)
+{
+	struct igc_mac_info *mac = &hw->mac;
+	u32 link_mode = 0;
+	u32 ctrl_ext = 0;
+	s32 ret_val = 0;
+
+	switch (hw->device_id) {
+	case IGC_DEV_ID_I225_LM:
+	case IGC_DEV_ID_I225_V:
+		mac->type = igc_i225;
+		break;
+	default:
+		return -IGC_ERR_MAC_INIT;
+	}
+
+	hw->phy.media_type = igc_media_type_copper;
+
+	ctrl_ext = rd32(IGC_CTRL_EXT);
+	link_mode = ctrl_ext & IGC_CTRL_EXT_LINK_MODE_MASK;
+
+	/* mac initialization and operations */
+	ret_val = igc_init_mac_params_base(hw);
+	if (ret_val)
+		goto out;
+
+	/* NVM initialization */
+	ret_val = igc_init_nvm_params_base(hw);
+	switch (hw->mac.type) {
+	case igc_i225:
+		ret_val = igc_init_nvm_params_i225(hw);
+		break;
+	default:
+		break;
+	}
+
+	/* setup PHY parameters */
+	ret_val = igc_init_phy_params_base(hw);
+	if (ret_val)
+		goto out;
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_acquire_phy_base - Acquire rights to access PHY
+ * @hw: pointer to the HW structure
+ *
+ * Acquire access rights to the correct PHY.  This is a
+ * function pointer entry point called by the api module.
+ */
+static s32 igc_acquire_phy_base(struct igc_hw *hw)
+{
+	u16 mask = IGC_SWFW_PHY0_SM;
+
+	return hw->mac.ops.acquire_swfw_sync(hw, mask);
+}
+
+/**
+ * igc_release_phy_base - Release rights to access PHY
+ * @hw: pointer to the HW structure
+ *
+ * A wrapper to release access rights to the correct PHY.  This is a
+ * function pointer entry point called by the api module.
+ */
+static void igc_release_phy_base(struct igc_hw *hw)
+{
+	u16 mask = IGC_SWFW_PHY0_SM;
+
+	hw->mac.ops.release_swfw_sync(hw, mask);
+}
+
+/**
+ * igc_get_link_up_info_base - Get link speed/duplex info
+ * @hw: pointer to the HW structure
+ * @speed: stores the current speed
+ * @duplex: stores the current duplex
+ *
+ * This is a wrapper function, if using the serial gigabit media independent
+ * interface, use PCS to retrieve the link speed and duplex information.
+ * Otherwise, use the generic function to get the link speed and duplex info.
+ */
+static s32 igc_get_link_up_info_base(struct igc_hw *hw, u16 *speed,
+				     u16 *duplex)
+{
+	s32 ret_val;
+
+	ret_val = igc_get_speed_and_duplex_copper(hw, speed, duplex);
+
+	return ret_val;
+}
+
+/**
+ * igc_init_hw_base - Initialize hardware
+ * @hw: pointer to the HW structure
+ *
+ * This inits the hardware readying it for operation.
+ */
+static s32 igc_init_hw_base(struct igc_hw *hw)
+{
+	struct igc_mac_info *mac = &hw->mac;
+	u16 i, rar_count = mac->rar_entry_count;
+	s32 ret_val = 0;
+
+	/* Setup the receive address */
+	igc_init_rx_addrs(hw, rar_count);
+
+	/* Zero out the Multicast HASH table */
+	hw_dbg("Zeroing the MTA\n");
+	for (i = 0; i < mac->mta_reg_count; i++)
+		array_wr32(IGC_MTA, i, 0);
+
+	/* Zero out the Unicast HASH table */
+	hw_dbg("Zeroing the UTA\n");
+	for (i = 0; i < mac->uta_reg_count; i++)
+		array_wr32(IGC_UTA, i, 0);
+
+	/* Setup link and flow control */
+	ret_val = igc_setup_link(hw);
+
+	/* Clear all of the statistics registers (clear on read).  It is
+	 * important that we do this after we have tried to establish link
+	 * because the symbol error count will increment wildly if there
+	 * is no link.
+	 */
+	igc_clear_hw_cntrs_base(hw);
+
+	return ret_val;
+}
+
+/**
+ * igc_read_mac_addr_base - Read device MAC address
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_read_mac_addr_base(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+
+	ret_val = igc_read_mac_addr(hw);
+
+	return ret_val;
+}
+
+/**
+ * igc_power_down_phy_copper_base - Remove link during PHY power down
+ * @hw: pointer to the HW structure
+ *
+ * In the case of a PHY power down to save power, or to turn off link during a
+ * driver unload, or wake on lan is not enabled, remove the link.
+ */
+void igc_power_down_phy_copper_base(struct igc_hw *hw)
+{
+	/* If the management interface is not enabled, then power down */
+	if (!(igc_enable_mng_pass_thru(hw) || igc_check_reset_block(hw)))
+		igc_power_down_phy_copper(hw);
+}
+
+/**
+ * igc_rx_fifo_flush_base - Clean rx fifo after Rx enable
+ * @hw: pointer to the HW structure
+ *
+ * After Rx enable, if manageability is enabled then there is likely some
+ * bad data at the start of the fifo and possibly in the DMA fifo.  This
+ * function clears the fifos and flushes any packets that came in as rx was
+ * being enabled.
+ */
+void igc_rx_fifo_flush_base(struct igc_hw *hw)
+{
+	u32 rctl, rlpml, rxdctl[4], rfctl, temp_rctl, rx_enabled;
+	int i, ms_wait;
+
+	/* disable IPv6 options as per hardware errata */
+	rfctl = rd32(IGC_RFCTL);
+	rfctl |= IGC_RFCTL_IPV6_EX_DIS;
+	wr32(IGC_RFCTL, rfctl);
+
+	if (!(rd32(IGC_MANC) & IGC_MANC_RCV_TCO_EN))
+		return;
+
+	/* Disable all Rx queues */
+	for (i = 0; i < 4; i++) {
+		rxdctl[i] = rd32(IGC_RXDCTL(i));
+		wr32(IGC_RXDCTL(i),
+		     rxdctl[i] & ~IGC_RXDCTL_QUEUE_ENABLE);
+	}
+	/* Poll all queues to verify they have shut down */
+	for (ms_wait = 0; ms_wait < 10; ms_wait++) {
+		usleep_range(1000, 2000);
+		rx_enabled = 0;
+		for (i = 0; i < 4; i++)
+			rx_enabled |= rd32(IGC_RXDCTL(i));
+		if (!(rx_enabled & IGC_RXDCTL_QUEUE_ENABLE))
+			break;
+	}
+
+	if (ms_wait == 10)
+		pr_debug("Queue disable timed out after 10ms\n");
+
+	/* Clear RLPML, RCTL.SBP, RFCTL.LEF, and set RCTL.LPE so that all
+	 * incoming packets are rejected.  Set enable and wait 2ms so that
+	 * any packet that was coming in as RCTL.EN was set is flushed
+	 */
+	wr32(IGC_RFCTL, rfctl & ~IGC_RFCTL_LEF);
+
+	rlpml = rd32(IGC_RLPML);
+	wr32(IGC_RLPML, 0);
+
+	rctl = rd32(IGC_RCTL);
+	temp_rctl = rctl & ~(IGC_RCTL_EN | IGC_RCTL_SBP);
+	temp_rctl |= IGC_RCTL_LPE;
+
+	wr32(IGC_RCTL, temp_rctl);
+	wr32(IGC_RCTL, temp_rctl | IGC_RCTL_EN);
+	wrfl();
+	usleep_range(2000, 3000);
+
+	/* Enable Rx queues that were previously enabled and restore our
+	 * previous state
+	 */
+	for (i = 0; i < 4; i++)
+		wr32(IGC_RXDCTL(i), rxdctl[i]);
+	wr32(IGC_RCTL, rctl);
+	wrfl();
+
+	wr32(IGC_RLPML, rlpml);
+	wr32(IGC_RFCTL, rfctl);
+
+	/* Flush receive errors generated by workaround */
+	rd32(IGC_ROC);
+	rd32(IGC_RNBC);
+	rd32(IGC_MPC);
+}
+
+static struct igc_mac_operations igc_mac_ops_base = {
+	.init_hw		= igc_init_hw_base,
+	.check_for_link		= igc_check_for_link_base,
+	.rar_set		= igc_rar_set,
+	.read_mac_addr		= igc_read_mac_addr_base,
+	.get_speed_and_duplex	= igc_get_link_up_info_base,
+};
+
+static const struct igc_phy_operations igc_phy_ops_base = {
+	.acquire		= igc_acquire_phy_base,
+	.release		= igc_release_phy_base,
+	.reset			= igc_phy_hw_reset,
+	.read_reg		= igc_read_phy_reg_gpy,
+	.write_reg		= igc_write_phy_reg_gpy,
+};
+
+const struct igc_info igc_base_info = {
+	.get_invariants		= igc_get_invariants_base,
+	.mac_ops		= &igc_mac_ops_base,
+	.phy_ops		= &igc_phy_ops_base,
+};

drivers/net/ethernet/intel/igc/igc_base.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_BASE_H
+#define _IGC_BASE_H
+
+/* forward declaration */
+void igc_rx_fifo_flush_base(struct igc_hw *hw);
+void igc_power_down_phy_copper_base(struct igc_hw *hw);
+
+/* Transmit Descriptor - Advanced */
+union igc_adv_tx_desc {
+	struct {
+		__le64 buffer_addr;    /* Address of descriptor's data buf */
+		__le32 cmd_type_len;
+		__le32 olinfo_status;
+	} read;
+	struct {
+		__le64 rsvd;       /* Reserved */
+		__le32 nxtseq_seed;
+		__le32 status;
+	} wb;
+};
+
+/* Adv Transmit Descriptor Config Masks */
+#define IGC_ADVTXD_MAC_TSTAMP	0x00080000 /* IEEE1588 Timestamp packet */
+#define IGC_ADVTXD_DTYP_CTXT	0x00200000 /* Advanced Context Descriptor */
+#define IGC_ADVTXD_DTYP_DATA	0x00300000 /* Advanced Data Descriptor */
+#define IGC_ADVTXD_DCMD_EOP	0x01000000 /* End of Packet */
+#define IGC_ADVTXD_DCMD_IFCS	0x02000000 /* Insert FCS (Ethernet CRC) */
+#define IGC_ADVTXD_DCMD_RS	0x08000000 /* Report Status */
+#define IGC_ADVTXD_DCMD_DEXT	0x20000000 /* Descriptor extension (1=Adv) */
+#define IGC_ADVTXD_DCMD_VLE	0x40000000 /* VLAN pkt enable */
+#define IGC_ADVTXD_DCMD_TSE	0x80000000 /* TCP Seg enable */
+#define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
+
+#define IGC_RAR_ENTRIES		16
+
+struct igc_adv_data_desc {
+	__le64 buffer_addr;    /* Address of the descriptor's data buffer */
+	union {
+		u32 data;
+		struct {
+			u32 datalen:16; /* Data buffer length */
+			u32 rsvd:4;
+			u32 dtyp:4;  /* Descriptor type */
+			u32 dcmd:8;  /* Descriptor command */
+		} config;
+	} lower;
+	union {
+		u32 data;
+		struct {
+			u32 status:4;  /* Descriptor status */
+			u32 idx:4;
+			u32 popts:6;  /* Packet Options */
+			u32 paylen:18; /* Payload length */
+		} options;
+	} upper;
+};
+
+/* Receive Descriptor - Advanced */
+union igc_adv_rx_desc {
+	struct {
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
+	} read;
+	struct {
+		struct {
+			union {
+				__le32 data;
+				struct {
+					__le16 pkt_info; /*RSS type, Pkt type*/
+					/* Split Header, header buffer len */
+					__le16 hdr_info;
+				} hs_rss;
+			} lo_dword;
+			union {
+				__le32 rss; /* RSS Hash */
+				struct {
+					__le16 ip_id; /* IP id */
+					__le16 csum; /* Packet Checksum */
+				} csum_ip;
+			} hi_dword;
+		} lower;
+		struct {
+			__le32 status_error; /* ext status/error */
+			__le16 length; /* Packet length */
+			__le16 vlan; /* VLAN tag */
+		} upper;
+	} wb;  /* writeback */
+};
+
+/* Adv Transmit Descriptor Config Masks */
+#define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
+
+/* Additional Transmit Descriptor Control definitions */
+#define IGC_TXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Tx Queue */
+
+/* Additional Receive Descriptor Control definitions */
+#define IGC_RXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Rx Queue */
+
+/* SRRCTL bit definitions */
+#define IGC_SRRCTL_BSIZEPKT_SHIFT		10 /* Shift _right_ */
+#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT		2  /* Shift _left_ */
+#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF	0x02000000
+
+#endif /* _IGC_BASE_H */

drivers/net/ethernet/intel/igc/igc_defines.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_DEFINES_H_
+#define _IGC_DEFINES_H_
+
+#define IGC_CTRL_EXT_DRV_LOAD	0x10000000 /* Drv loaded bit for FW */
+
+/* PCI Bus Info */
+#define PCIE_DEVICE_CONTROL2		0x28
+#define PCIE_DEVICE_CONTROL2_16ms	0x0005
+
+/* Physical Func Reset Done Indication */
+#define IGC_CTRL_EXT_LINK_MODE_MASK	0x00C00000
+
+/* Loop limit on how long we wait for auto-negotiation to complete */
+#define COPPER_LINK_UP_LIMIT		10
+#define PHY_AUTO_NEG_LIMIT		45
+#define PHY_FORCE_LIMIT			20
+
+/* Number of 100 microseconds we wait for PCI Express master disable */
+#define MASTER_DISABLE_TIMEOUT		800
+/*Blocks new Master requests */
+#define IGC_CTRL_GIO_MASTER_DISABLE	0x00000004
+/* Status of Master requests. */
+#define IGC_STATUS_GIO_MASTER_ENABLE	0x00080000
+
+/* PCI Express Control */
+#define IGC_GCR_CMPL_TMOUT_MASK		0x0000F000
+#define IGC_GCR_CMPL_TMOUT_10ms		0x00001000
+#define IGC_GCR_CMPL_TMOUT_RESEND	0x00010000
+#define IGC_GCR_CAP_VER2		0x00040000
+
+/* Receive Address
+ * Number of high/low register pairs in the RAR. The RAR (Receive Address
+ * Registers) holds the directed and multicast addresses that we monitor.
+ * Technically, we have 16 spots.  However, we reserve one of these spots
+ * (RAR[15]) for our directed address used by controllers with
+ * manageability enabled, allowing us room for 15 multicast addresses.
+ */
+#define IGC_RAH_AV		0x80000000 /* Receive descriptor valid */
+#define IGC_RAH_POOL_1		0x00040000
+#define IGC_RAL_MAC_ADDR_LEN	4
+#define IGC_RAH_MAC_ADDR_LEN	2
+
+/* Error Codes */
+#define IGC_SUCCESS			0
+#define IGC_ERR_NVM			1
+#define IGC_ERR_PHY			2
+#define IGC_ERR_CONFIG			3
+#define IGC_ERR_PARAM			4
+#define IGC_ERR_MAC_INIT		5
+#define IGC_ERR_RESET			9
+#define IGC_ERR_MASTER_REQUESTS_PENDING	10
+#define IGC_ERR_BLK_PHY_RESET		12
+#define IGC_ERR_SWFW_SYNC		13
+
+/* Device Control */
+#define IGC_CTRL_RST		0x04000000  /* Global reset */
+
+#define IGC_CTRL_PHY_RST	0x80000000  /* PHY Reset */
+#define IGC_CTRL_SLU		0x00000040  /* Set link up (Force Link) */
+#define IGC_CTRL_FRCSPD		0x00000800  /* Force Speed */
+#define IGC_CTRL_FRCDPX		0x00001000  /* Force Duplex */
+
+#define IGC_CTRL_RFCE		0x08000000  /* Receive Flow Control enable */
+#define IGC_CTRL_TFCE		0x10000000  /* Transmit flow control enable */
+
+#define IGC_CONNSW_AUTOSENSE_EN	0x1
+
+/* PBA constants */
+#define IGC_PBA_34K		0x0022
+
+/* SW Semaphore Register */
+#define IGC_SWSM_SMBI		0x00000001 /* Driver Semaphore bit */
+#define IGC_SWSM_SWESMBI	0x00000002 /* FW Semaphore bit */
+
+/* SWFW_SYNC Definitions */
+#define IGC_SWFW_EEP_SM		0x1
+#define IGC_SWFW_PHY0_SM	0x2
+
+/* Autoneg Advertisement Register */
+#define NWAY_AR_10T_HD_CAPS	0x0020   /* 10T   Half Duplex Capable */
+#define NWAY_AR_10T_FD_CAPS	0x0040   /* 10T   Full Duplex Capable */
+#define NWAY_AR_100TX_HD_CAPS	0x0080   /* 100TX Half Duplex Capable */
+#define NWAY_AR_100TX_FD_CAPS	0x0100   /* 100TX Full Duplex Capable */
+#define NWAY_AR_PAUSE		0x0400   /* Pause operation desired */
+#define NWAY_AR_ASM_DIR		0x0800   /* Asymmetric Pause Direction bit */
+
+/* Link Partner Ability Register (Base Page) */
+#define NWAY_LPAR_PAUSE		0x0400 /* LP Pause operation desired */
+#define NWAY_LPAR_ASM_DIR	0x0800 /* LP Asymmetric Pause Direction bit */
+
+/* 1000BASE-T Control Register */
+#define CR_1000T_ASYM_PAUSE	0x0080 /* Advertise asymmetric pause bit */
+#define CR_1000T_HD_CAPS	0x0100 /* Advertise 1000T HD capability */
+#define CR_1000T_FD_CAPS	0x0200 /* Advertise 1000T FD capability  */
+
+/* 1000BASE-T Status Register */
+#define SR_1000T_REMOTE_RX_STATUS	0x1000 /* Remote receiver OK */
+#define SR_1000T_LOCAL_RX_STATUS	0x2000 /* Local receiver OK */
+
+/* PHY GPY 211 registers */
+#define STANDARD_AN_REG_MASK	0x0007 /* MMD */
+#define ANEG_MULTIGBT_AN_CTRL	0x0020 /* MULTI GBT AN Control Register */
+#define MMD_DEVADDR_SHIFT	16     /* Shift MMD to higher bits */
+#define CR_2500T_FD_CAPS	0x0080 /* Advertise 2500T FD capability */
+
+/* NVM Control */
+/* Number of milliseconds for NVM auto read done after MAC reset. */
+#define AUTO_READ_DONE_TIMEOUT		10
+#define IGC_EECD_AUTO_RD		0x00000200  /* NVM Auto Read done */
+#define IGC_EECD_REQ		0x00000040 /* NVM Access Request */
+#define IGC_EECD_GNT		0x00000080 /* NVM Access Grant */
+/* NVM Addressing bits based on type 0=small, 1=large */
+#define IGC_EECD_ADDR_BITS		0x00000400
+#define IGC_NVM_GRANT_ATTEMPTS		1000 /* NVM # attempts to gain grant */
+#define IGC_EECD_SIZE_EX_MASK		0x00007800  /* NVM Size */
+#define IGC_EECD_SIZE_EX_SHIFT		11
+#define IGC_EECD_FLUPD_I225		0x00800000 /* Update FLASH */
+#define IGC_EECD_FLUDONE_I225		0x04000000 /* Update FLASH done*/
+#define IGC_EECD_FLASH_DETECTED_I225	0x00080000 /* FLASH detected */
+#define IGC_FLUDONE_ATTEMPTS		20000
+#define IGC_EERD_EEWR_MAX_COUNT		512 /* buffered EEPROM words rw */
+
+/* Offset to data in NVM read/write registers */
+#define IGC_NVM_RW_REG_DATA	16
+#define IGC_NVM_RW_REG_DONE	2    /* Offset to READ/WRITE done bit */
+#define IGC_NVM_RW_REG_START	1    /* Start operation */
+#define IGC_NVM_RW_ADDR_SHIFT	2    /* Shift to the address bits */
+#define IGC_NVM_POLL_READ	0    /* Flag for polling for read complete */
+
+/* NVM Word Offsets */
+#define NVM_CHECKSUM_REG		0x003F
+
+/* For checksumming, the sum of all words in the NVM should equal 0xBABA. */
+#define NVM_SUM				0xBABA
+
+#define NVM_PBA_OFFSET_0		8
+#define NVM_PBA_OFFSET_1		9
+#define NVM_RESERVED_WORD		0xFFFF
+#define NVM_PBA_PTR_GUARD		0xFAFA
+#define NVM_WORD_SIZE_BASE_SHIFT	6
+
+/* Collision related configuration parameters */
+#define IGC_COLLISION_THRESHOLD		15
+#define IGC_CT_SHIFT			4
+#define IGC_COLLISION_DISTANCE		63
+#define IGC_COLD_SHIFT			12
+
+/* Device Status */
+#define IGC_STATUS_FD		0x00000001      /* Full duplex.0=half,1=full */
+#define IGC_STATUS_LU		0x00000002      /* Link up.0=no,1=link */
+#define IGC_STATUS_FUNC_MASK	0x0000000C      /* PCI Function Mask */
+#define IGC_STATUS_FUNC_SHIFT	2
+#define IGC_STATUS_FUNC_1	0x00000004      /* Function 1 */
+#define IGC_STATUS_TXOFF	0x00000010      /* transmission paused */
+#define IGC_STATUS_SPEED_100	0x00000040      /* Speed 100Mb/s */
+#define IGC_STATUS_SPEED_1000	0x00000080      /* Speed 1000Mb/s */
+#define IGC_STATUS_SPEED_2500	0x00400000	/* Speed 2.5Gb/s */
+
+#define SPEED_10		10
+#define SPEED_100		100
+#define SPEED_1000		1000
+#define SPEED_2500		2500
+#define HALF_DUPLEX		1
+#define FULL_DUPLEX		2
+
+/* 1Gbps and 2.5Gbps half duplex is not supported, nor spec-compliant. */
+#define ADVERTISE_10_HALF		0x0001
+#define ADVERTISE_10_FULL		0x0002
+#define ADVERTISE_100_HALF		0x0004
+#define ADVERTISE_100_FULL		0x0008
+#define ADVERTISE_1000_HALF		0x0010 /* Not used, just FYI */
+#define ADVERTISE_1000_FULL		0x0020
+#define ADVERTISE_2500_HALF		0x0040 /* Not used, just FYI */
+#define ADVERTISE_2500_FULL		0x0080
+
+#define IGC_ALL_SPEED_DUPLEX_2500 ( \
+	ADVERTISE_10_HALF | ADVERTISE_10_FULL | ADVERTISE_100_HALF | \
+	ADVERTISE_100_FULL | ADVERTISE_1000_FULL | ADVERTISE_2500_FULL)
+
+#define AUTONEG_ADVERTISE_SPEED_DEFAULT_2500	IGC_ALL_SPEED_DUPLEX_2500
+
+/* Interrupt Cause Read */
+#define IGC_ICR_TXDW		BIT(0)	/* Transmit desc written back */
+#define IGC_ICR_TXQE		BIT(1)	/* Transmit Queue empty */
+#define IGC_ICR_LSC		BIT(2)	/* Link Status Change */
+#define IGC_ICR_RXSEQ		BIT(3)	/* Rx sequence error */
+#define IGC_ICR_RXDMT0		BIT(4)	/* Rx desc min. threshold (0) */
+#define IGC_ICR_RXO		BIT(6)	/* Rx overrun */
+#define IGC_ICR_RXT0		BIT(7)	/* Rx timer intr (ring 0) */
+#define IGC_ICR_DRSTA		BIT(30)	/* Device Reset Asserted */
+
+/* If this bit asserted, the driver should claim the interrupt */
+#define IGC_ICR_INT_ASSERTED	BIT(31)
+
+#define IGC_ICS_RXT0		IGC_ICR_RXT0 /* Rx timer intr */
+
+#define IMS_ENABLE_MASK ( \
+	IGC_IMS_RXT0   |    \
+	IGC_IMS_TXDW   |    \
+	IGC_IMS_RXDMT0 |    \
+	IGC_IMS_RXSEQ  |    \
+	IGC_IMS_LSC)
+
+/* Interrupt Mask Set */
+#define IGC_IMS_TXDW		IGC_ICR_TXDW	/* Tx desc written back */
+#define IGC_IMS_RXSEQ		IGC_ICR_RXSEQ	/* Rx sequence error */
+#define IGC_IMS_LSC		IGC_ICR_LSC	/* Link Status Change */
+#define IGC_IMS_DOUTSYNC	IGC_ICR_DOUTSYNC /* NIC DMA out of sync */
+#define IGC_IMS_DRSTA		IGC_ICR_DRSTA	/* Device Reset Asserted */
+#define IGC_IMS_RXT0		IGC_ICR_RXT0	/* Rx timer intr */
+#define IGC_IMS_RXDMT0		IGC_ICR_RXDMT0	/* Rx desc min. threshold */
+
+#define IGC_QVECTOR_MASK	0x7FFC		/* Q-vector mask */
+#define IGC_ITR_VAL_MASK	0x04		/* ITR value mask */
+
+/* Interrupt Cause Set */
+#define IGC_ICS_LSC		IGC_ICR_LSC       /* Link Status Change */
+#define IGC_ICS_RXDMT0		IGC_ICR_RXDMT0    /* rx desc min. threshold */
+#define IGC_ICS_DRSTA		IGC_ICR_DRSTA     /* Device Reset Aserted */
+
+#define IGC_ICR_DOUTSYNC	0x10000000 /* NIC DMA out of sync */
+#define IGC_EITR_CNT_IGNR	0x80000000 /* Don't reset counters on write */
+#define IGC_IVAR_VALID		0x80
+#define IGC_GPIE_NSICR		0x00000001
+#define IGC_GPIE_MSIX_MODE	0x00000010
+#define IGC_GPIE_EIAME		0x40000000
+#define IGC_GPIE_PBA		0x80000000
+
+/* Transmit Descriptor bit definitions */
+#define IGC_TXD_DTYP_D		0x00100000 /* Data Descriptor */
+#define IGC_TXD_DTYP_C		0x00000000 /* Context Descriptor */
+#define IGC_TXD_POPTS_IXSM	0x01       /* Insert IP checksum */
+#define IGC_TXD_POPTS_TXSM	0x02       /* Insert TCP/UDP checksum */
+#define IGC_TXD_CMD_EOP		0x01000000 /* End of Packet */
+#define IGC_TXD_CMD_IFCS	0x02000000 /* Insert FCS (Ethernet CRC) */
+#define IGC_TXD_CMD_IC		0x04000000 /* Insert Checksum */
+#define IGC_TXD_CMD_RS		0x08000000 /* Report Status */
+#define IGC_TXD_CMD_RPS		0x10000000 /* Report Packet Sent */
+#define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
+#define IGC_TXD_CMD_VLE		0x40000000 /* Add VLAN tag */
+#define IGC_TXD_CMD_IDE		0x80000000 /* Enable Tidv register */
+#define IGC_TXD_STAT_DD		0x00000001 /* Descriptor Done */
+#define IGC_TXD_STAT_EC		0x00000002 /* Excess Collisions */
+#define IGC_TXD_STAT_LC		0x00000004 /* Late Collisions */
+#define IGC_TXD_STAT_TU		0x00000008 /* Transmit underrun */
+#define IGC_TXD_CMD_TCP		0x01000000 /* TCP packet */
+#define IGC_TXD_CMD_IP		0x02000000 /* IP packet */
+#define IGC_TXD_CMD_TSE		0x04000000 /* TCP Seg enable */
+#define IGC_TXD_STAT_TC		0x00000004 /* Tx Underrun */
+#define IGC_TXD_EXTCMD_TSTAMP	0x00000010 /* IEEE1588 Timestamp packet */
+
+/* Transmit Control */
+#define IGC_TCTL_EN		0x00000002 /* enable Tx */
+#define IGC_TCTL_PSP		0x00000008 /* pad short packets */
+#define IGC_TCTL_CT		0x00000ff0 /* collision threshold */
+#define IGC_TCTL_COLD		0x003ff000 /* collision distance */
+#define IGC_TCTL_RTLC		0x01000000 /* Re-transmit on late collision */
+#define IGC_TCTL_MULR		0x10000000 /* Multiple request support */
+
+#define IGC_CT_SHIFT			4
+#define IGC_COLLISION_THRESHOLD		15
+
+/* Flow Control Constants */
+#define FLOW_CONTROL_ADDRESS_LOW	0x00C28001
+#define FLOW_CONTROL_ADDRESS_HIGH	0x00000100
+#define FLOW_CONTROL_TYPE		0x8808
+/* Enable XON frame transmission */
+#define IGC_FCRTL_XONE			0x80000000
+
+/* Management Control */
+#define IGC_MANC_RCV_TCO_EN	0x00020000 /* Receive TCO Packets Enabled */
+#define IGC_MANC_BLK_PHY_RST_ON_IDE	0x00040000 /* Block phy resets */
+
+/* Receive Control */
+#define IGC_RCTL_RST		0x00000001 /* Software reset */
+#define IGC_RCTL_EN		0x00000002 /* enable */
+#define IGC_RCTL_SBP		0x00000004 /* store bad packet */
+#define IGC_RCTL_UPE		0x00000008 /* unicast promisc enable */
+#define IGC_RCTL_MPE		0x00000010 /* multicast promisc enable */
+#define IGC_RCTL_LPE		0x00000020 /* long packet enable */
+#define IGC_RCTL_LBM_MAC	0x00000040 /* MAC loopback mode */
+#define IGC_RCTL_LBM_TCVR	0x000000C0 /* tcvr loopback mode */
+
+#define IGC_RCTL_RDMTS_HALF	0x00000000 /* Rx desc min thresh size */
+#define IGC_RCTL_BAM		0x00008000 /* broadcast enable */
+
+/* Receive Descriptor bit definitions */
+#define IGC_RXD_STAT_EOP	0x02    /* End of Packet */
+
+#define IGC_RXDEXT_STATERR_CE		0x01000000
+#define IGC_RXDEXT_STATERR_SE		0x02000000
+#define IGC_RXDEXT_STATERR_SEQ		0x04000000
+#define IGC_RXDEXT_STATERR_CXE		0x10000000
+#define IGC_RXDEXT_STATERR_TCPE		0x20000000
+#define IGC_RXDEXT_STATERR_IPE		0x40000000
+#define IGC_RXDEXT_STATERR_RXE		0x80000000
+
+/* Same mask, but for extended and packet split descriptors */
+#define IGC_RXDEXT_ERR_FRAME_ERR_MASK ( \
+	IGC_RXDEXT_STATERR_CE  |	\
+	IGC_RXDEXT_STATERR_SE  |	\
+	IGC_RXDEXT_STATERR_SEQ |	\
+	IGC_RXDEXT_STATERR_CXE |	\
+	IGC_RXDEXT_STATERR_RXE)
+
+/* Header split receive */
+#define IGC_RFCTL_IPV6_EX_DIS	0x00010000
+#define IGC_RFCTL_LEF		0x00040000
+
+#define IGC_RCTL_SZ_256		0x00030000 /* Rx buffer size 256 */
+
+#define IGC_RCTL_MO_SHIFT	12 /* multicast offset shift */
+#define IGC_RCTL_CFIEN		0x00080000 /* canonical form enable */
+#define IGC_RCTL_DPF		0x00400000 /* discard pause frames */
+#define IGC_RCTL_PMCF		0x00800000 /* pass MAC control frames */
+#define IGC_RCTL_SECRC		0x04000000 /* Strip Ethernet CRC */
+
+#define I225_RXPBSIZE_DEFAULT	0x000000A2 /* RXPBSIZE default */
+#define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
+
+/* GPY211 - I225 defines */
+#define GPY_MMD_MASK		0xFFFF0000
+#define GPY_MMD_SHIFT		16
+#define GPY_REG_MASK		0x0000FFFF
+
+#define IGC_MMDAC_FUNC_DATA	0x4000 /* Data, no post increment */
+
+/* MAC definitions */
+#define IGC_FACTPS_MNGCG	0x20000000
+#define IGC_FWSM_MODE_MASK	0xE
+#define IGC_FWSM_MODE_SHIFT	1
+
+/* Management Control */
+#define IGC_MANC_SMBUS_EN	0x00000001 /* SMBus Enabled - RO */
+#define IGC_MANC_ASF_EN		0x00000002 /* ASF Enabled - RO */
+
+/* PHY */
+#define PHY_REVISION_MASK	0xFFFFFFF0
+#define MAX_PHY_REG_ADDRESS	0x1F  /* 5 bit address bus (0-0x1F) */
+#define IGC_GEN_POLL_TIMEOUT	1920
+
+/* PHY Control Register */
+#define MII_CR_FULL_DUPLEX	0x0100  /* FDX =1, half duplex =0 */
+#define MII_CR_RESTART_AUTO_NEG	0x0200  /* Restart auto negotiation */
+#define MII_CR_POWER_DOWN	0x0800  /* Power down */
+#define MII_CR_AUTO_NEG_EN	0x1000  /* Auto Neg Enable */
+#define MII_CR_LOOPBACK		0x4000  /* 0 = normal, 1 = loopback */
+#define MII_CR_RESET		0x8000  /* 0 = normal, 1 = PHY reset */
+#define MII_CR_SPEED_1000	0x0040
+#define MII_CR_SPEED_100	0x2000
+#define MII_CR_SPEED_10		0x0000
+
+/* PHY Status Register */
+#define MII_SR_LINK_STATUS	0x0004 /* Link Status 1 = link */
+#define MII_SR_AUTONEG_COMPLETE	0x0020 /* Auto Neg Complete */
+
+/* PHY 1000 MII Register/Bit Definitions */
+/* PHY Registers defined by IEEE */
+#define PHY_CONTROL		0x00 /* Control Register */
+#define PHY_STATUS		0x01 /* Status Register */
+#define PHY_ID1			0x02 /* Phy Id Reg (word 1) */
+#define PHY_ID2			0x03 /* Phy Id Reg (word 2) */
+#define PHY_AUTONEG_ADV		0x04 /* Autoneg Advertisement */
+#define PHY_LP_ABILITY		0x05 /* Link Partner Ability (Base Page) */
+#define PHY_1000T_CTRL		0x09 /* 1000Base-T Control Reg */
+#define PHY_1000T_STATUS	0x0A /* 1000Base-T Status Reg */
+
+/* Bit definitions for valid PHY IDs. I = Integrated E = External */
+#define I225_I_PHY_ID		0x67C9DC00
+
+/* MDI Control */
+#define IGC_MDIC_DATA_MASK	0x0000FFFF
+#define IGC_MDIC_REG_MASK	0x001F0000
+#define IGC_MDIC_REG_SHIFT	16
+#define IGC_MDIC_PHY_MASK	0x03E00000
+#define IGC_MDIC_PHY_SHIFT	21
+#define IGC_MDIC_OP_WRITE	0x04000000
+#define IGC_MDIC_OP_READ	0x08000000
+#define IGC_MDIC_READY		0x10000000
+#define IGC_MDIC_INT_EN		0x20000000
+#define IGC_MDIC_ERROR		0x40000000
+#define IGC_MDIC_DEST		0x80000000
+
+#define IGC_N0_QUEUE -1
+
+#endif /* _IGC_DEFINES_H_ */

drivers/net/ethernet/intel/igc/igc_hw.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_HW_H_
+#define _IGC_HW_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+
+#include "igc_regs.h"
+#include "igc_defines.h"
+#include "igc_mac.h"
+#include "igc_phy.h"
+#include "igc_nvm.h"
+#include "igc_i225.h"
+#include "igc_base.h"
+
+#define IGC_DEV_ID_I225_LM			0x15F2
+#define IGC_DEV_ID_I225_V			0x15F3
+
+#define IGC_FUNC_0				0
+
+/* Function pointers for the MAC. */
+struct igc_mac_operations {
+	s32 (*check_for_link)(struct igc_hw *hw);
+	s32 (*reset_hw)(struct igc_hw *hw);
+	s32 (*init_hw)(struct igc_hw *hw);
+	s32 (*setup_physical_interface)(struct igc_hw *hw);
+	void (*rar_set)(struct igc_hw *hw, u8 *address, u32 index);
+	s32 (*read_mac_addr)(struct igc_hw *hw);
+	s32 (*get_speed_and_duplex)(struct igc_hw *hw, u16 *speed,
+				    u16 *duplex);
+	s32 (*acquire_swfw_sync)(struct igc_hw *hw, u16 mask);
+	void (*release_swfw_sync)(struct igc_hw *hw, u16 mask);
+};
+
+enum igc_mac_type {
+	igc_undefined = 0,
+	igc_i225,
+	igc_num_macs  /* List is 1-based, so subtract 1 for true count. */
+};
+
+enum igc_phy_type {
+	igc_phy_unknown = 0,
+	igc_phy_none,
+	igc_phy_i225,
+};
+
+enum igc_media_type {
+	igc_media_type_unknown = 0,
+	igc_media_type_copper = 1,
+	igc_num_media_types
+};
+
+enum igc_nvm_type {
+	igc_nvm_unknown = 0,
+	igc_nvm_flash_hw,
+	igc_nvm_invm,
+};
+
+struct igc_info {
+	s32 (*get_invariants)(struct igc_hw *hw);
+	struct igc_mac_operations *mac_ops;
+	const struct igc_phy_operations *phy_ops;
+	struct igc_nvm_operations *nvm_ops;
+};
+
+extern const struct igc_info igc_base_info;
+
+struct igc_mac_info {
+	struct igc_mac_operations ops;
+
+	u8 addr[ETH_ALEN];
+	u8 perm_addr[ETH_ALEN];
+
+	enum igc_mac_type type;
+
+	u32 collision_delta;
+	u32 ledctl_default;
+	u32 ledctl_mode1;
+	u32 ledctl_mode2;
+	u32 mc_filter_type;
+	u32 tx_packet_delta;
+	u32 txcw;
+
+	u16 mta_reg_count;
+	u16 uta_reg_count;
+
+	u16 rar_entry_count;
+
+	u8 forced_speed_duplex;
+
+	bool adaptive_ifs;
+	bool has_fwsm;
+	bool asf_firmware_present;
+	bool arc_subsystem_valid;
+
+	bool autoneg;
+	bool autoneg_failed;
+	bool get_link_status;
+};
+
+struct igc_nvm_operations {
+	s32 (*acquire)(struct igc_hw *hw);
+	s32 (*read)(struct igc_hw *hw, u16 offset, u16 i, u16 *data);
+	void (*release)(struct igc_hw *hw);
+	s32 (*write)(struct igc_hw *hw, u16 offset, u16 i, u16 *data);
+	s32 (*update)(struct igc_hw *hw);
+	s32 (*validate)(struct igc_hw *hw);
+	s32 (*valid_led_default)(struct igc_hw *hw, u16 *data);
+};
+
+struct igc_phy_operations {
+	s32 (*acquire)(struct igc_hw *hw);
+	s32 (*check_polarity)(struct igc_hw *hw);
+	s32 (*check_reset_block)(struct igc_hw *hw);
+	s32 (*force_speed_duplex)(struct igc_hw *hw);
+	s32 (*get_cfg_done)(struct igc_hw *hw);
+	s32 (*get_cable_length)(struct igc_hw *hw);
+	s32 (*get_phy_info)(struct igc_hw *hw);
+	s32 (*read_reg)(struct igc_hw *hw, u32 address, u16 *data);
+	void (*release)(struct igc_hw *hw);
+	s32 (*reset)(struct igc_hw *hw);
+	s32 (*write_reg)(struct igc_hw *hw, u32 address, u16 data);
+};
+
+struct igc_nvm_info {
+	struct igc_nvm_operations ops;
+	enum igc_nvm_type type;
+
+	u32 flash_bank_size;
+	u32 flash_base_addr;
+
+	u16 word_size;
+	u16 delay_usec;
+	u16 address_bits;
+	u16 opcode_bits;
+	u16 page_size;
+};
+
+struct igc_phy_info {
+	struct igc_phy_operations ops;
+
+	enum igc_phy_type type;
+
+	u32 addr;
+	u32 id;
+	u32 reset_delay_us; /* in usec */
+	u32 revision;
+
+	enum igc_media_type media_type;
+
+	u16 autoneg_advertised;
+	u16 autoneg_mask;
+	u16 cable_length;
+	u16 max_cable_length;
+	u16 min_cable_length;
+	u16 pair_length[4];
+
+	u8 mdix;
+
+	bool disable_polarity_correction;
+	bool is_mdix;
+	bool polarity_correction;
+	bool reset_disable;
+	bool speed_downgraded;
+	bool autoneg_wait_to_complete;
+};
+
+struct igc_bus_info {
+	u16 func;
+	u16 pci_cmd_word;
+};
+
+enum igc_fc_mode {
+	igc_fc_none = 0,
+	igc_fc_rx_pause,
+	igc_fc_tx_pause,
+	igc_fc_full,
+	igc_fc_default = 0xFF
+};
+
+struct igc_fc_info {
+	u32 high_water;     /* Flow control high-water mark */
+	u32 low_water;      /* Flow control low-water mark */
+	u16 pause_time;     /* Flow control pause timer */
+	bool send_xon;      /* Flow control send XON */
+	bool strict_ieee;   /* Strict IEEE mode */
+	enum igc_fc_mode current_mode; /* Type of flow control */
+	enum igc_fc_mode requested_mode;
+};
+
+struct igc_dev_spec_base {
+	bool global_device_reset;
+	bool eee_disable;
+	bool clear_semaphore_once;
+	bool module_plugged;
+	u8 media_port;
+	bool mas_capable;
+};
+
+struct igc_hw {
+	void *back;
+
+	u8 __iomem *hw_addr;
+	unsigned long io_base;
+
+	struct igc_mac_info  mac;
+	struct igc_fc_info   fc;
+	struct igc_nvm_info  nvm;
+	struct igc_phy_info  phy;
+
+	struct igc_bus_info bus;
+
+	union {
+		struct igc_dev_spec_base	_base;
+	} dev_spec;
+
+	u16 device_id;
+	u16 subsystem_vendor_id;
+	u16 subsystem_device_id;
+	u16 vendor_id;
+
+	u8 revision_id;
+};
+
+/* Statistics counters collected by the MAC */
+struct igc_hw_stats {
+	u64 crcerrs;
+	u64 algnerrc;
+	u64 symerrs;
+	u64 rxerrc;
+	u64 mpc;
+	u64 scc;
+	u64 ecol;
+	u64 mcc;
+	u64 latecol;
+	u64 colc;
+	u64 dc;
+	u64 tncrs;
+	u64 sec;
+	u64 cexterr;
+	u64 rlec;
+	u64 xonrxc;
+	u64 xontxc;
+	u64 xoffrxc;
+	u64 xofftxc;
+	u64 fcruc;
+	u64 prc64;
+	u64 prc127;
+	u64 prc255;
+	u64 prc511;
+	u64 prc1023;
+	u64 prc1522;
+	u64 gprc;
+	u64 bprc;
+	u64 mprc;
+	u64 gptc;
+	u64 gorc;
+	u64 gotc;
+	u64 rnbc;
+	u64 ruc;
+	u64 rfc;
+	u64 roc;
+	u64 rjc;
+	u64 mgprc;
+	u64 mgpdc;
+	u64 mgptc;
+	u64 tor;
+	u64 tot;
+	u64 tpr;
+	u64 tpt;
+	u64 ptc64;
+	u64 ptc127;
+	u64 ptc255;
+	u64 ptc511;
+	u64 ptc1023;
+	u64 ptc1522;
+	u64 mptc;
+	u64 bptc;
+	u64 tsctc;
+	u64 tsctfc;
+	u64 iac;
+	u64 icrxptc;
+	u64 icrxatc;
+	u64 ictxptc;
+	u64 ictxatc;
+	u64 ictxqec;
+	u64 ictxqmtc;
+	u64 icrxdmtc;
+	u64 icrxoc;
+	u64 cbtmpc;
+	u64 htdpmc;
+	u64 cbrdpc;
+	u64 cbrmpc;
+	u64 rpthc;
+	u64 hgptc;
+	u64 htcbdpc;
+	u64 hgorc;
+	u64 hgotc;
+	u64 lenerrs;
+	u64 scvpc;
+	u64 hrmpc;
+	u64 doosync;
+	u64 o2bgptc;
+	u64 o2bspc;
+	u64 b2ospc;
+	u64 b2ogprc;
+};
+
+struct net_device *igc_get_hw_dev(struct igc_hw *hw);
+#define hw_dbg(format, arg...) \
+	netdev_dbg(igc_get_hw_dev(hw), format, ##arg)
+
+s32  igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
+s32  igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value);
+void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
+void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value);
+
+#endif /* _IGC_HW_H_ */

drivers/net/ethernet/intel/igc/igc_i225.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include <linux/delay.h>
+
+#include "igc_hw.h"
+
+/**
+ * igc_get_hw_semaphore_i225 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the necessary semaphores for exclusive access to the EEPROM.
+ * Set the EEPROM access request bit and wait for EEPROM access grant bit.
+ * Return successful if access grant bit set, else clear the request for
+ * EEPROM access and return -IGC_ERR_NVM (-1).
+ */
+static s32 igc_acquire_nvm_i225(struct igc_hw *hw)
+{
+	return igc_acquire_swfw_sync_i225(hw, IGC_SWFW_EEP_SM);
+}
+
+/**
+ * igc_release_nvm_i225 - Release exclusive access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Stop any current commands to the EEPROM and clear the EEPROM request bit,
+ * then release the semaphores acquired.
+ */
+static void igc_release_nvm_i225(struct igc_hw *hw)
+{
+	igc_release_swfw_sync_i225(hw, IGC_SWFW_EEP_SM);
+}
+
+/**
+ * igc_get_hw_semaphore_i225 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the HW semaphore to access the PHY or NVM
+ */
+static s32 igc_get_hw_semaphore_i225(struct igc_hw *hw)
+{
+	s32 timeout = hw->nvm.word_size + 1;
+	s32 i = 0;
+	u32 swsm;
+
+	/* Get the SW semaphore */
+	while (i < timeout) {
+		swsm = rd32(IGC_SWSM);
+		if (!(swsm & IGC_SWSM_SMBI))
+			break;
+
+		usleep_range(500, 600);
+		i++;
+	}
+
+	if (i == timeout) {
+		/* In rare circumstances, the SW semaphore may already be held
+		 * unintentionally. Clear the semaphore once before giving up.
+		 */
+		if (hw->dev_spec._base.clear_semaphore_once) {
+			hw->dev_spec._base.clear_semaphore_once = false;
+			igc_put_hw_semaphore(hw);
+			for (i = 0; i < timeout; i++) {
+				swsm = rd32(IGC_SWSM);
+				if (!(swsm & IGC_SWSM_SMBI))
+					break;
+
+				usleep_range(500, 600);
+			}
+		}
+
+		/* If we do not have the semaphore here, we have to give up. */
+		if (i == timeout) {
+			hw_dbg("Driver can't access device - SMBI bit is set.\n");
+			return -IGC_ERR_NVM;
+		}
+	}
+
+	/* Get the FW semaphore. */
+	for (i = 0; i < timeout; i++) {
+		swsm = rd32(IGC_SWSM);
+		wr32(IGC_SWSM, swsm | IGC_SWSM_SWESMBI);
+
+		/* Semaphore acquired if bit latched */
+		if (rd32(IGC_SWSM) & IGC_SWSM_SWESMBI)
+			break;
+
+		usleep_range(500, 600);
+	}
+
+	if (i == timeout) {
+		/* Release semaphores */
+		igc_put_hw_semaphore(hw);
+		hw_dbg("Driver can't access the NVM\n");
+		return -IGC_ERR_NVM;
+	}
+
+	return 0;
+}
+
+/**
+ * igc_acquire_swfw_sync_i225 - Acquire SW/FW semaphore
+ * @hw: pointer to the HW structure
+ * @mask: specifies which semaphore to acquire
+ *
+ * Acquire the SW/FW semaphore to access the PHY or NVM.  The mask
+ * will also specify which port we're acquiring the lock for.
+ */
+s32 igc_acquire_swfw_sync_i225(struct igc_hw *hw, u16 mask)
+{
+	s32 i = 0, timeout = 200;
+	u32 fwmask = mask << 16;
+	u32 swmask = mask;
+	s32 ret_val = 0;
+	u32 swfw_sync;
+
+	while (i < timeout) {
+		if (igc_get_hw_semaphore_i225(hw)) {
+			ret_val = -IGC_ERR_SWFW_SYNC;
+			goto out;
+		}
+
+		swfw_sync = rd32(IGC_SW_FW_SYNC);
+		if (!(swfw_sync & (fwmask | swmask)))
+			break;
+
+		/* Firmware currently using resource (fwmask) */
+		igc_put_hw_semaphore(hw);
+		mdelay(5);
+		i++;
+	}
+
+	if (i == timeout) {
+		hw_dbg("Driver can't access resource, SW_FW_SYNC timeout.\n");
+		ret_val = -IGC_ERR_SWFW_SYNC;
+		goto out;
+	}
+
+	swfw_sync |= swmask;
+	wr32(IGC_SW_FW_SYNC, swfw_sync);
+
+	igc_put_hw_semaphore(hw);
+out:
+	return ret_val;
+}
+
+/**
+ * igc_release_swfw_sync_i225 - Release SW/FW semaphore
+ * @hw: pointer to the HW structure
+ * @mask: specifies which semaphore to acquire
+ *
+ * Release the SW/FW semaphore used to access the PHY or NVM.  The mask
+ * will also specify which port we're releasing the lock for.
+ */
+void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask)
+{
+	u32 swfw_sync;
+
+	while (igc_get_hw_semaphore_i225(hw))
+		; /* Empty */
+
+	swfw_sync = rd32(IGC_SW_FW_SYNC);
+	swfw_sync &= ~mask;
+	wr32(IGC_SW_FW_SYNC, swfw_sync);
+
+	igc_put_hw_semaphore(hw);
+}
+
+/**
+ * igc_read_nvm_srrd_i225 - Reads Shadow Ram using EERD register
+ * @hw: pointer to the HW structure
+ * @offset: offset of word in the Shadow Ram to read
+ * @words: number of words to read
+ * @data: word read from the Shadow Ram
+ *
+ * Reads a 16 bit word from the Shadow Ram using the EERD register.
+ * Uses necessary synchronization semaphores.
+ */
+static s32 igc_read_nvm_srrd_i225(struct igc_hw *hw, u16 offset, u16 words,
+				  u16 *data)
+{
+	s32 status = 0;
+	u16 i, count;
+
+	/* We cannot hold synchronization semaphores for too long,
+	 * because of forceful takeover procedure. However it is more efficient
+	 * to read in bursts than synchronizing access for each word.
+	 */
+	for (i = 0; i < words; i += IGC_EERD_EEWR_MAX_COUNT) {
+		count = (words - i) / IGC_EERD_EEWR_MAX_COUNT > 0 ?
+			IGC_EERD_EEWR_MAX_COUNT : (words - i);
+
+		status = hw->nvm.ops.acquire(hw);
+		if (status)
+			break;
+
+		status = igc_read_nvm_eerd(hw, offset, count, data + i);
+		hw->nvm.ops.release(hw);
+		if (status)
+			break;
+	}
+
+	return status;
+}
+
+/**
+ * igc_write_nvm_srwr - Write to Shadow Ram using EEWR
+ * @hw: pointer to the HW structure
+ * @offset: offset within the Shadow Ram to be written to
+ * @words: number of words to write
+ * @data: 16 bit word(s) to be written to the Shadow Ram
+ *
+ * Writes data to Shadow Ram at offset using EEWR register.
+ *
+ * If igc_update_nvm_checksum is not called after this function , the
+ * Shadow Ram will most likely contain an invalid checksum.
+ */
+static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words,
+			      u16 *data)
+{
+	struct igc_nvm_info *nvm = &hw->nvm;
+	u32 attempts = 100000;
+	u32 i, k, eewr = 0;
+	s32 ret_val = 0;
+
+	/* A check for invalid values:  offset too large, too many words,
+	 * too many words for the offset, and not enough words.
+	 */
+	if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) ||
+	    words == 0) {
+		hw_dbg("nvm parameter(s) out of bounds\n");
+		ret_val = -IGC_ERR_NVM;
+		goto out;
+	}
+
+	for (i = 0; i < words; i++) {
+		eewr = ((offset + i) << IGC_NVM_RW_ADDR_SHIFT) |
+			(data[i] << IGC_NVM_RW_REG_DATA) |
+			IGC_NVM_RW_REG_START;
+
+		wr32(IGC_SRWR, eewr);
+
+		for (k = 0; k < attempts; k++) {
+			if (IGC_NVM_RW_REG_DONE &
+			    rd32(IGC_SRWR)) {
+				ret_val = 0;
+				break;
+			}
+			udelay(5);
+		}
+
+		if (ret_val) {
+			hw_dbg("Shadow RAM write EEWR timed out\n");
+			break;
+		}
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_write_nvm_srwr_i225 - Write to Shadow RAM using EEWR
+ * @hw: pointer to the HW structure
+ * @offset: offset within the Shadow RAM to be written to
+ * @words: number of words to write
+ * @data: 16 bit word(s) to be written to the Shadow RAM
+ *
+ * Writes data to Shadow RAM at offset using EEWR register.
+ *
+ * If igc_update_nvm_checksum is not called after this function , the
+ * data will not be committed to FLASH and also Shadow RAM will most likely
+ * contain an invalid checksum.
+ *
+ * If error code is returned, data and Shadow RAM may be inconsistent - buffer
+ * partially written.
+ */
+static s32 igc_write_nvm_srwr_i225(struct igc_hw *hw, u16 offset, u16 words,
+				   u16 *data)
+{
+	s32 status = 0;
+	u16 i, count;
+
+	/* We cannot hold synchronization semaphores for too long,
+	 * because of forceful takeover procedure. However it is more efficient
+	 * to write in bursts than synchronizing access for each word.
+	 */
+	for (i = 0; i < words; i += IGC_EERD_EEWR_MAX_COUNT) {
+		count = (words - i) / IGC_EERD_EEWR_MAX_COUNT > 0 ?
+			IGC_EERD_EEWR_MAX_COUNT : (words - i);
+
+		status = hw->nvm.ops.acquire(hw);
+		if (status)
+			break;
+
+		status = igc_write_nvm_srwr(hw, offset, count, data + i);
+		hw->nvm.ops.release(hw);
+		if (status)
+			break;
+	}
+
+	return status;
+}
+
+/**
+ * igc_validate_nvm_checksum_i225 - Validate EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Calculates the EEPROM checksum by reading/adding each word of the EEPROM
+ * and then verifies that the sum of the EEPROM is equal to 0xBABA.
+ */
+static s32 igc_validate_nvm_checksum_i225(struct igc_hw *hw)
+{
+	s32 (*read_op_ptr)(struct igc_hw *hw, u16 offset, u16 count,
+			   u16 *data);
+	s32 status = 0;
+
+	status = hw->nvm.ops.acquire(hw);
+	if (status)
+		goto out;
+
+	/* Replace the read function with semaphore grabbing with
+	 * the one that skips this for a while.
+	 * We have semaphore taken already here.
+	 */
+	read_op_ptr = hw->nvm.ops.read;
+	hw->nvm.ops.read = igc_read_nvm_eerd;
+
+	status = igc_validate_nvm_checksum(hw);
+
+	/* Revert original read operation. */
+	hw->nvm.ops.read = read_op_ptr;
+
+	hw->nvm.ops.release(hw);
+
+out:
+	return status;
+}
+
+/**
+ * igc_pool_flash_update_done_i225 - Pool FLUDONE status
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_pool_flash_update_done_i225(struct igc_hw *hw)
+{
+	s32 ret_val = -IGC_ERR_NVM;
+	u32 i, reg;
+
+	for (i = 0; i < IGC_FLUDONE_ATTEMPTS; i++) {
+		reg = rd32(IGC_EECD);
+		if (reg & IGC_EECD_FLUDONE_I225) {
+			ret_val = 0;
+			break;
+		}
+		udelay(5);
+	}
+
+	return ret_val;
+}
+
+/**
+ * igc_update_flash_i225 - Commit EEPROM to the flash
+ * @hw: pointer to the HW structure
+ */
+static s32 igc_update_flash_i225(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+	u32 flup;
+
+	ret_val = igc_pool_flash_update_done_i225(hw);
+	if (ret_val == -IGC_ERR_NVM) {
+		hw_dbg("Flash update time out\n");
+		goto out;
+	}
+
+	flup = rd32(IGC_EECD) | IGC_EECD_FLUPD_I225;
+	wr32(IGC_EECD, flup);
+
+	ret_val = igc_pool_flash_update_done_i225(hw);
+	if (ret_val)
+		hw_dbg("Flash update time out\n");
+	else
+		hw_dbg("Flash update complete\n");
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_update_nvm_checksum_i225 - Update EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Updates the EEPROM checksum by reading/adding each word of the EEPROM
+ * up to the checksum.  Then calculates the EEPROM checksum and writes the
+ * value to the EEPROM. Next commit EEPROM data onto the Flash.
+ */
+static s32 igc_update_nvm_checksum_i225(struct igc_hw *hw)
+{
+	u16 checksum = 0;
+	s32 ret_val = 0;
+	u16 i, nvm_data;
+
+	/* Read the first word from the EEPROM. If this times out or fails, do
+	 * not continue or we could be in for a very long wait while every
+	 * EEPROM read fails
+	 */
+	ret_val = igc_read_nvm_eerd(hw, 0, 1, &nvm_data);
+	if (ret_val) {
+		hw_dbg("EEPROM read failed\n");
+		goto out;
+	}
+
+	ret_val = hw->nvm.ops.acquire(hw);
+	if (ret_val)
+		goto out;
+
+	/* Do not use hw->nvm.ops.write, hw->nvm.ops.read
+	 * because we do not want to take the synchronization
+	 * semaphores twice here.
+	 */
+
+	for (i = 0; i < NVM_CHECKSUM_REG; i++) {
+		ret_val = igc_read_nvm_eerd(hw, i, 1, &nvm_data);
+		if (ret_val) {
+			hw->nvm.ops.release(hw);
+			hw_dbg("NVM Read Error while updating checksum.\n");
+			goto out;
+		}
+		checksum += nvm_data;
+	}
+	checksum = (u16)NVM_SUM - checksum;
+	ret_val = igc_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1,
+				     &checksum);
+	if (ret_val) {
+		hw->nvm.ops.release(hw);
+		hw_dbg("NVM Write Error while updating checksum.\n");
+		goto out;
+	}
+
+	hw->nvm.ops.release(hw);
+
+	ret_val = igc_update_flash_i225(hw);
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_get_flash_presence_i225 - Check if flash device is detected
+ * @hw: pointer to the HW structure
+ */
+bool igc_get_flash_presence_i225(struct igc_hw *hw)
+{
+	bool ret_val = false;
+	u32 eec = 0;
+
+	eec = rd32(IGC_EECD);
+	if (eec & IGC_EECD_FLASH_DETECTED_I225)
+		ret_val = true;
+
+	return ret_val;
+}
+
+/**
+ * igc_init_nvm_params_i225 - Init NVM func ptrs.
+ * @hw: pointer to the HW structure
+ */
+s32 igc_init_nvm_params_i225(struct igc_hw *hw)
+{
+	struct igc_nvm_info *nvm = &hw->nvm;
+
+	nvm->ops.acquire = igc_acquire_nvm_i225;
+	nvm->ops.release = igc_release_nvm_i225;
+
+	/* NVM Function Pointers */
+	if (igc_get_flash_presence_i225(hw)) {
+		hw->nvm.type = igc_nvm_flash_hw;
+		nvm->ops.read = igc_read_nvm_srrd_i225;
+		nvm->ops.write = igc_write_nvm_srwr_i225;
+		nvm->ops.validate = igc_validate_nvm_checksum_i225;
+		nvm->ops.update = igc_update_nvm_checksum_i225;
+	} else {
+		hw->nvm.type = igc_nvm_invm;
+		nvm->ops.read = igc_read_nvm_eerd;
+		nvm->ops.write = NULL;
+		nvm->ops.validate = NULL;
+		nvm->ops.update = NULL;
+	}
+	return 0;
+}

drivers/net/ethernet/intel/igc/igc_i225.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_I225_H_
+#define _IGC_I225_H_
+
+s32 igc_acquire_swfw_sync_i225(struct igc_hw *hw, u16 mask);
+void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask);
+
+s32 igc_init_nvm_params_i225(struct igc_hw *hw);
+bool igc_get_flash_presence_i225(struct igc_hw *hw);
+
+#endif

drivers/net/ethernet/intel/igc/igc_mac.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include <linux/pci.h>
+#include <linux/delay.h>
+
+#include "igc_mac.h"
+#include "igc_hw.h"
+
+/* forward declaration */
+static s32 igc_set_default_fc(struct igc_hw *hw);
+static s32 igc_set_fc_watermarks(struct igc_hw *hw);
+
+/**
+ * igc_disable_pcie_master - Disables PCI-express master access
+ * @hw: pointer to the HW structure
+ *
+ * Returns 0 (0) if successful, else returns -10
+ * (-IGC_ERR_MASTER_REQUESTS_PENDING) if master disable bit has not caused
+ * the master requests to be disabled.
+ *
+ * Disables PCI-Express master access and verifies there are no pending
+ * requests.
+ */
+s32 igc_disable_pcie_master(struct igc_hw *hw)
+{
+	s32 timeout = MASTER_DISABLE_TIMEOUT;
+	s32 ret_val = 0;
+	u32 ctrl;
+
+	ctrl = rd32(IGC_CTRL);
+	ctrl |= IGC_CTRL_GIO_MASTER_DISABLE;
+	wr32(IGC_CTRL, ctrl);
+
+	while (timeout) {
+		if (!(rd32(IGC_STATUS) &
+		    IGC_STATUS_GIO_MASTER_ENABLE))
+			break;
+		usleep_range(2000, 3000);
+		timeout--;
+	}
+
+	if (!timeout) {
+		hw_dbg("Master requests are pending.\n");
+		ret_val = -IGC_ERR_MASTER_REQUESTS_PENDING;
+		goto out;
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_init_rx_addrs - Initialize receive addresses
+ * @hw: pointer to the HW structure
+ * @rar_count: receive address registers
+ *
+ * Setup the receive address registers by setting the base receive address
+ * register to the devices MAC address and clearing all the other receive
+ * address registers to 0.
+ */
+void igc_init_rx_addrs(struct igc_hw *hw, u16 rar_count)
+{
+	u8 mac_addr[ETH_ALEN] = {0};
+	u32 i;
+
+	/* Setup the receive address */
+	hw_dbg("Programming MAC Address into RAR[0]\n");
+
+	hw->mac.ops.rar_set(hw, hw->mac.addr, 0);
+
+	/* Zero out the other (rar_entry_count - 1) receive addresses */
+	hw_dbg("Clearing RAR[1-%u]\n", rar_count - 1);
+	for (i = 1; i < rar_count; i++)
+		hw->mac.ops.rar_set(hw, mac_addr, i);
+}
+
+/**
+ * igc_setup_link - Setup flow control and link settings
+ * @hw: pointer to the HW structure
+ *
+ * Determines which flow control settings to use, then configures flow
+ * control.  Calls the appropriate media-specific link configuration
+ * function.  Assuming the adapter has a valid link partner, a valid link
+ * should be established.  Assumes the hardware has previously been reset
+ * and the transmitter and receiver are not enabled.
+ */
+s32 igc_setup_link(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+
+	/* In the case of the phy reset being blocked, we already have a link.
+	 * We do not need to set it up again.
+	 */
+	if (igc_check_reset_block(hw))
+		goto out;
+
+	/* If requested flow control is set to default, set flow control
+	 * based on the EEPROM flow control settings.
+	 */
+	if (hw->fc.requested_mode == igc_fc_default) {
+		ret_val = igc_set_default_fc(hw);
+		if (ret_val)
+			goto out;
+	}
+
+	/* We want to save off the original Flow Control configuration just
+	 * in case we get disconnected and then reconnected into a different
+	 * hub or switch with different Flow Control capabilities.
+	 */
+	hw->fc.current_mode = hw->fc.requested_mode;
+
+	hw_dbg("After fix-ups FlowControl is now = %x\n", hw->fc.current_mode);
+
+	/* Call the necessary media_type subroutine to configure the link. */
+	ret_val = hw->mac.ops.setup_physical_interface(hw);
+	if (ret_val)
+		goto out;
+
+	/* Initialize the flow control address, type, and PAUSE timer
+	 * registers to their default values.  This is done even if flow
+	 * control is disabled, because it does not hurt anything to
+	 * initialize these registers.
+	 */
+	hw_dbg("Initializing the Flow Control address, type and timer regs\n");
+	wr32(IGC_FCT, FLOW_CONTROL_TYPE);
+	wr32(IGC_FCAH, FLOW_CONTROL_ADDRESS_HIGH);
+	wr32(IGC_FCAL, FLOW_CONTROL_ADDRESS_LOW);
+
+	wr32(IGC_FCTTV, hw->fc.pause_time);
+
+	ret_val = igc_set_fc_watermarks(hw);
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_set_default_fc - Set flow control default values
+ * @hw: pointer to the HW structure
+ *
+ * Read the EEPROM for the default values for flow control and store the
+ * values.
+ */
+static s32 igc_set_default_fc(struct igc_hw *hw)
+{
+	hw->fc.requested_mode = igc_fc_full;
+	return 0;
+}
+
+/**
+ * igc_force_mac_fc - Force the MAC's flow control settings
+ * @hw: pointer to the HW structure
+ *
+ * Force the MAC's flow control settings.  Sets the TFCE and RFCE bits in the
+ * device control register to reflect the adapter settings.  TFCE and RFCE
+ * need to be explicitly set by software when a copper PHY is used because
+ * autonegotiation is managed by the PHY rather than the MAC.  Software must
+ * also configure these bits when link is forced on a fiber connection.
+ */
+s32 igc_force_mac_fc(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+	u32 ctrl;
+
+	ctrl = rd32(IGC_CTRL);
+
+	/* Because we didn't get link via the internal auto-negotiation
+	 * mechanism (we either forced link or we got link via PHY
+	 * auto-neg), we have to manually enable/disable transmit an
+	 * receive flow control.
+	 *
+	 * The "Case" statement below enables/disable flow control
+	 * according to the "hw->fc.current_mode" parameter.
+	 *
+	 * The possible values of the "fc" parameter are:
+	 *      0:  Flow control is completely disabled
+	 *      1:  Rx flow control is enabled (we can receive pause
+	 *          frames but not send pause frames).
+	 *      2:  Tx flow control is enabled (we can send pause frames
+	 *          frames but we do not receive pause frames).
+	 *      3:  Both Rx and TX flow control (symmetric) is enabled.
+	 *  other:  No other values should be possible at this point.
+	 */
+	hw_dbg("hw->fc.current_mode = %u\n", hw->fc.current_mode);
+
+	switch (hw->fc.current_mode) {
+	case igc_fc_none:
+		ctrl &= (~(IGC_CTRL_TFCE | IGC_CTRL_RFCE));
+		break;
+	case igc_fc_rx_pause:
+		ctrl &= (~IGC_CTRL_TFCE);
+		ctrl |= IGC_CTRL_RFCE;
+		break;
+	case igc_fc_tx_pause:
+		ctrl &= (~IGC_CTRL_RFCE);
+		ctrl |= IGC_CTRL_TFCE;
+		break;
+	case igc_fc_full:
+		ctrl |= (IGC_CTRL_TFCE | IGC_CTRL_RFCE);
+		break;
+	default:
+		hw_dbg("Flow control param set incorrectly\n");
+		ret_val = -IGC_ERR_CONFIG;
+		goto out;
+	}
+
+	wr32(IGC_CTRL, ctrl);
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_set_fc_watermarks - Set flow control high/low watermarks
+ * @hw: pointer to the HW structure
+ *
+ * Sets the flow control high/low threshold (watermark) registers.  If
+ * flow control XON frame transmission is enabled, then set XON frame
+ * transmission as well.
+ */
+static s32 igc_set_fc_watermarks(struct igc_hw *hw)
+{
+	u32 fcrtl = 0, fcrth = 0;
+
+	/* Set the flow control receive threshold registers.  Normally,
+	 * these registers will be set to a default threshold that may be
+	 * adjusted later by the driver's runtime code.  However, if the
+	 * ability to transmit pause frames is not enabled, then these
+	 * registers will be set to 0.
+	 */
+	if (hw->fc.current_mode & igc_fc_tx_pause) {
+		/* We need to set up the Receive Threshold high and low water
+		 * marks as well as (optionally) enabling the transmission of
+		 * XON frames.
+		 */
+		fcrtl = hw->fc.low_water;
+		if (hw->fc.send_xon)
+			fcrtl |= IGC_FCRTL_XONE;
+
+		fcrth = hw->fc.high_water;
+	}
+	wr32(IGC_FCRTL, fcrtl);
+	wr32(IGC_FCRTH, fcrth);
+
+	return 0;
+}
+
+/**
+ * igc_clear_hw_cntrs_base - Clear base hardware counters
+ * @hw: pointer to the HW structure
+ *
+ * Clears the base hardware counters by reading the counter registers.
+ */
+void igc_clear_hw_cntrs_base(struct igc_hw *hw)
+{
+	rd32(IGC_CRCERRS);
+	rd32(IGC_SYMERRS);
+	rd32(IGC_MPC);
+	rd32(IGC_SCC);
+	rd32(IGC_ECOL);
+	rd32(IGC_MCC);
+	rd32(IGC_LATECOL);
+	rd32(IGC_COLC);
+	rd32(IGC_DC);
+	rd32(IGC_SEC);
+	rd32(IGC_RLEC);
+	rd32(IGC_XONRXC);
+	rd32(IGC_XONTXC);
+	rd32(IGC_XOFFRXC);
+	rd32(IGC_XOFFTXC);
+	rd32(IGC_FCRUC);
+	rd32(IGC_GPRC);
+	rd32(IGC_BPRC);
+	rd32(IGC_MPRC);
+	rd32(IGC_GPTC);
+	rd32(IGC_GORCL);
+	rd32(IGC_GORCH);
+	rd32(IGC_GOTCL);
+	rd32(IGC_GOTCH);
+	rd32(IGC_RNBC);
+	rd32(IGC_RUC);
+	rd32(IGC_RFC);
+	rd32(IGC_ROC);
+	rd32(IGC_RJC);
+	rd32(IGC_TORL);
+	rd32(IGC_TORH);
+	rd32(IGC_TOTL);
+	rd32(IGC_TOTH);
+	rd32(IGC_TPR);
+	rd32(IGC_TPT);
+	rd32(IGC_MPTC);
+	rd32(IGC_BPTC);
+
+	rd32(IGC_PRC64);
+	rd32(IGC_PRC127);
+	rd32(IGC_PRC255);
+	rd32(IGC_PRC511);
+	rd32(IGC_PRC1023);
+	rd32(IGC_PRC1522);
+	rd32(IGC_PTC64);
+	rd32(IGC_PTC127);
+	rd32(IGC_PTC255);
+	rd32(IGC_PTC511);
+	rd32(IGC_PTC1023);
+	rd32(IGC_PTC1522);
+
+	rd32(IGC_ALGNERRC);
+	rd32(IGC_RXERRC);
+	rd32(IGC_TNCRS);
+	rd32(IGC_CEXTERR);
+	rd32(IGC_TSCTC);
+	rd32(IGC_TSCTFC);
+
+	rd32(IGC_MGTPRC);
+	rd32(IGC_MGTPDC);
+	rd32(IGC_MGTPTC);
+
+	rd32(IGC_IAC);
+	rd32(IGC_ICRXOC);
+
+	rd32(IGC_ICRXPTC);
+	rd32(IGC_ICRXATC);
+	rd32(IGC_ICTXPTC);
+	rd32(IGC_ICTXATC);
+	rd32(IGC_ICTXQEC);
+	rd32(IGC_ICTXQMTC);
+	rd32(IGC_ICRXDMTC);
+
+	rd32(IGC_CBTMPC);
+	rd32(IGC_HTDPMC);
+	rd32(IGC_CBRMPC);
+	rd32(IGC_RPTHC);
+	rd32(IGC_HGPTC);
+	rd32(IGC_HTCBDPC);
+	rd32(IGC_HGORCL);
+	rd32(IGC_HGORCH);
+	rd32(IGC_HGOTCL);
+	rd32(IGC_HGOTCH);
+	rd32(IGC_LENERRS);
+}
+
+/**
+ * igc_rar_set - Set receive address register
+ * @hw: pointer to the HW structure
+ * @addr: pointer to the receive address
+ * @index: receive address array register
+ *
+ * Sets the receive address array register at index to the address passed
+ * in by addr.
+ */
+void igc_rar_set(struct igc_hw *hw, u8 *addr, u32 index)
+{
+	u32 rar_low, rar_high;
+
+	/* HW expects these in little endian so we reverse the byte order
+	 * from network order (big endian) to little endian
+	 */
+	rar_low = ((u32)addr[0] |
+		   ((u32)addr[1] << 8) |
+		   ((u32)addr[2] << 16) | ((u32)addr[3] << 24));
+
+	rar_high = ((u32)addr[4] | ((u32)addr[5] << 8));
+
+	/* If MAC address zero, no need to set the AV bit */
+	if (rar_low || rar_high)
+		rar_high |= IGC_RAH_AV;
+
+	/* Some bridges will combine consecutive 32-bit writes into
+	 * a single burst write, which will malfunction on some parts.
+	 * The flushes avoid this.
+	 */
+	wr32(IGC_RAL(index), rar_low);
+	wrfl();
+	wr32(IGC_RAH(index), rar_high);
+	wrfl();
+}
+
+/**
+ * igc_check_for_copper_link - Check for link (Copper)
+ * @hw: pointer to the HW structure
+ *
+ * Checks to see of the link status of the hardware has changed.  If a
+ * change in link status has been detected, then we read the PHY registers
+ * to get the current speed/duplex if link exists.
+ */
+s32 igc_check_for_copper_link(struct igc_hw *hw)
+{
+	struct igc_mac_info *mac = &hw->mac;
+	s32 ret_val;
+	bool link;
+
+	/* We only want to go out to the PHY registers to see if Auto-Neg
+	 * has completed and/or if our link status has changed.  The
+	 * get_link_status flag is set upon receiving a Link Status
+	 * Change or Rx Sequence Error interrupt.
+	 */
+	if (!mac->get_link_status) {
+		ret_val = 0;
+		goto out;
+	}
+
+	/* First we want to see if the MII Status Register reports
+	 * link.  If so, then we want to get the current speed/duplex
+	 * of the PHY.
+	 */
+	ret_val = igc_phy_has_link(hw, 1, 0, &link);
+	if (ret_val)
+		goto out;
+
+	if (!link)
+		goto out; /* No link detected */
+
+	mac->get_link_status = false;
+
+	/* Check if there was DownShift, must be checked
+	 * immediately after link-up
+	 */
+	igc_check_downshift(hw);
+
+	/* If we are forcing speed/duplex, then we simply return since
+	 * we have already determined whether we have link or not.
+	 */
+	if (!mac->autoneg) {
+		ret_val = -IGC_ERR_CONFIG;
+		goto out;
+	}
+
+	/* Auto-Neg is enabled.  Auto Speed Detection takes care
+	 * of MAC speed/duplex configuration.  So we only need to
+	 * configure Collision Distance in the MAC.
+	 */
+	igc_config_collision_dist(hw);
+
+	/* Configure Flow Control now that Auto-Neg has completed.
+	 * First, we need to restore the desired flow control
+	 * settings because we may have had to re-autoneg with a
+	 * different link partner.
+	 */
+	ret_val = igc_config_fc_after_link_up(hw);
+	if (ret_val)
+		hw_dbg("Error configuring flow control\n");
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_config_collision_dist - Configure collision distance
+ * @hw: pointer to the HW structure
+ *
+ * Configures the collision distance to the default value and is used
+ * during link setup. Currently no func pointer exists and all
+ * implementations are handled in the generic version of this function.
+ */
+void igc_config_collision_dist(struct igc_hw *hw)
+{
+	u32 tctl;
+
+	tctl = rd32(IGC_TCTL);
+
+	tctl &= ~IGC_TCTL_COLD;
+	tctl |= IGC_COLLISION_DISTANCE << IGC_COLD_SHIFT;
+
+	wr32(IGC_TCTL, tctl);
+	wrfl();
+}
+
+/**
+ * igc_config_fc_after_link_up - Configures flow control after link
+ * @hw: pointer to the HW structure
+ *
+ * Checks the status of auto-negotiation after link up to ensure that the
+ * speed and duplex were not forced.  If the link needed to be forced, then
+ * flow control needs to be forced also.  If auto-negotiation is enabled
+ * and did not fail, then we configure flow control based on our link
+ * partner.
+ */
+s32 igc_config_fc_after_link_up(struct igc_hw *hw)
+{
+	u16 mii_status_reg, mii_nway_adv_reg, mii_nway_lp_ability_reg;
+	struct igc_mac_info *mac = &hw->mac;
+	u16 speed, duplex;
+	s32 ret_val = 0;
+
+	/* Check for the case where we have fiber media and auto-neg failed
+	 * so we had to force link.  In this case, we need to force the
+	 * configuration of the MAC to match the "fc" parameter.
+	 */
+	if (mac->autoneg_failed) {
+		if (hw->phy.media_type == igc_media_type_copper)
+			ret_val = igc_force_mac_fc(hw);
+	}
+
+	if (ret_val) {
+		hw_dbg("Error forcing flow control settings\n");
+		goto out;
+	}
+
+	/* Check for the case where we have copper media and auto-neg is
+	 * enabled.  In this case, we need to check and see if Auto-Neg
+	 * has completed, and if so, how the PHY and link partner has
+	 * flow control configured.
+	 */
+	if (hw->phy.media_type == igc_media_type_copper && mac->autoneg) {
+		/* Read the MII Status Register and check to see if AutoNeg
+		 * has completed.  We read this twice because this reg has
+		 * some "sticky" (latched) bits.
+		 */
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
+					       &mii_status_reg);
+		if (ret_val)
+			goto out;
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS,
+					       &mii_status_reg);
+		if (ret_val)
+			goto out;
+
+		if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) {
+			hw_dbg("Copper PHY and Auto Neg has not completed.\n");
+			goto out;
+		}
+
+		/* The AutoNeg process has completed, so we now need to
+		 * read both the Auto Negotiation Advertisement
+		 * Register (Address 4) and the Auto_Negotiation Base
+		 * Page Ability Register (Address 5) to determine how
+		 * flow control was negotiated.
+		 */
+		ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV,
+					       &mii_nway_adv_reg);
+		if (ret_val)
+			goto out;
+		ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY,
+					       &mii_nway_lp_ability_reg);
+		if (ret_val)
+			goto out;
+		/* Two bits in the Auto Negotiation Advertisement Register
+		 * (Address 4) and two bits in the Auto Negotiation Base
+		 * Page Ability Register (Address 5) determine flow control
+		 * for both the PHY and the link partner.  The following
+		 * table, taken out of the IEEE 802.3ab/D6.0 dated March 25,
+		 * 1999, describes these PAUSE resolution bits and how flow
+		 * control is determined based upon these settings.
+		 * NOTE:  DC = Don't Care
+		 *
+		 *   LOCAL DEVICE  |   LINK PARTNER
+		 * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution
+		 *-------|---------|-------|---------|--------------------
+		 *   0   |    0    |  DC   |   DC    | igc_fc_none
+		 *   0   |    1    |   0   |   DC    | igc_fc_none
+		 *   0   |    1    |   1   |    0    | igc_fc_none
+		 *   0   |    1    |   1   |    1    | igc_fc_tx_pause
+		 *   1   |    0    |   0   |   DC    | igc_fc_none
+		 *   1   |   DC    |   1   |   DC    | igc_fc_full
+		 *   1   |    1    |   0   |    0    | igc_fc_none
+		 *   1   |    1    |   0   |    1    | igc_fc_rx_pause
+		 *
+		 * Are both PAUSE bits set to 1?  If so, this implies
+		 * Symmetric Flow Control is enabled at both ends.  The
+		 * ASM_DIR bits are irrelevant per the spec.
+		 *
+		 * For Symmetric Flow Control:
+		 *
+		 *   LOCAL DEVICE  |   LINK PARTNER
+		 * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+		 *-------|---------|-------|---------|--------------------
+		 *   1   |   DC    |   1   |   DC    | IGC_fc_full
+		 *
+		 */
+		if ((mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+		    (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) {
+			/* Now we need to check if the user selected RX ONLY
+			 * of pause frames.  In this case, we had to advertise
+			 * FULL flow control because we could not advertise RX
+			 * ONLY. Hence, we must now check to see if we need to
+			 * turn OFF  the TRANSMISSION of PAUSE frames.
+			 */
+			if (hw->fc.requested_mode == igc_fc_full) {
+				hw->fc.current_mode = igc_fc_full;
+				hw_dbg("Flow Control = FULL.\n");
+			} else {
+				hw->fc.current_mode = igc_fc_rx_pause;
+				hw_dbg("Flow Control = RX PAUSE frames only.\n");
+			}
+		}
+
+		/* For receiving PAUSE frames ONLY.
+		 *
+		 *   LOCAL DEVICE  |   LINK PARTNER
+		 * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+		 *-------|---------|-------|---------|--------------------
+		 *   0   |    1    |   1   |    1    | igc_fc_tx_pause
+		 */
+		else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+			 (mii_nway_adv_reg & NWAY_AR_ASM_DIR) &&
+			 (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) &&
+			 (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) {
+			hw->fc.current_mode = igc_fc_tx_pause;
+			hw_dbg("Flow Control = TX PAUSE frames only.\n");
+		}
+		/* For transmitting PAUSE frames ONLY.
+		 *
+		 *   LOCAL DEVICE  |   LINK PARTNER
+		 * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result
+		 *-------|---------|-------|---------|--------------------
+		 *   1   |    1    |   0   |    1    | igc_fc_rx_pause
+		 */
+		else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) &&
+			 (mii_nway_adv_reg & NWAY_AR_ASM_DIR) &&
+			 !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) &&
+			 (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) {
+			hw->fc.current_mode = igc_fc_rx_pause;
+			hw_dbg("Flow Control = RX PAUSE frames only.\n");
+		}
+		/* Per the IEEE spec, at this point flow control should be
+		 * disabled.  However, we want to consider that we could
+		 * be connected to a legacy switch that doesn't advertise
+		 * desired flow control, but can be forced on the link
+		 * partner.  So if we advertised no flow control, that is
+		 * what we will resolve to.  If we advertised some kind of
+		 * receive capability (Rx Pause Only or Full Flow Control)
+		 * and the link partner advertised none, we will configure
+		 * ourselves to enable Rx Flow Control only.  We can do
+		 * this safely for two reasons:  If the link partner really
+		 * didn't want flow control enabled, and we enable Rx, no
+		 * harm done since we won't be receiving any PAUSE frames
+		 * anyway.  If the intent on the link partner was to have
+		 * flow control enabled, then by us enabling RX only, we
+		 * can at least receive pause frames and process them.
+		 * This is a good idea because in most cases, since we are
+		 * predominantly a server NIC, more times than not we will
+		 * be asked to delay transmission of packets than asking
+		 * our link partner to pause transmission of frames.
+		 */
+		else if ((hw->fc.requested_mode == igc_fc_none) ||
+			 (hw->fc.requested_mode == igc_fc_tx_pause) ||
+			 (hw->fc.strict_ieee)) {
+			hw->fc.current_mode = igc_fc_none;
+			hw_dbg("Flow Control = NONE.\n");
+		} else {
+			hw->fc.current_mode = igc_fc_rx_pause;
+			hw_dbg("Flow Control = RX PAUSE frames only.\n");
+		}
+
+		/* Now we need to do one last check...  If we auto-
+		 * negotiated to HALF DUPLEX, flow control should not be
+		 * enabled per IEEE 802.3 spec.
+		 */
+		ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex);
+		if (ret_val) {
+			hw_dbg("Error getting link speed and duplex\n");
+			goto out;
+		}
+
+		if (duplex == HALF_DUPLEX)
+			hw->fc.current_mode = igc_fc_none;
+
+		/* Now we call a subroutine to actually force the MAC
+		 * controller to use the correct flow control settings.
+		 */
+		ret_val = igc_force_mac_fc(hw);
+		if (ret_val) {
+			hw_dbg("Error forcing flow control settings\n");
+			goto out;
+		}
+	}
+
+out:
+	return 0;
+}
+
+/**
+ * igc_get_auto_rd_done - Check for auto read completion
+ * @hw: pointer to the HW structure
+ *
+ * Check EEPROM for Auto Read done bit.
+ */
+s32 igc_get_auto_rd_done(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+	s32 i = 0;
+
+	while (i < AUTO_READ_DONE_TIMEOUT) {
+		if (rd32(IGC_EECD) & IGC_EECD_AUTO_RD)
+			break;
+		usleep_range(1000, 2000);
+		i++;
+	}
+
+	if (i == AUTO_READ_DONE_TIMEOUT) {
+		hw_dbg("Auto read by HW from NVM has not completed.\n");
+		ret_val = -IGC_ERR_RESET;
+		goto out;
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_get_speed_and_duplex_copper - Retrieve current speed/duplex
+ * @hw: pointer to the HW structure
+ * @speed: stores the current speed
+ * @duplex: stores the current duplex
+ *
+ * Read the status register for the current speed/duplex and store the current
+ * speed and duplex for copper connections.
+ */
+s32 igc_get_speed_and_duplex_copper(struct igc_hw *hw, u16 *speed,
+				    u16 *duplex)
+{
+	u32 status;
+
+	status = rd32(IGC_STATUS);
+	if (status & IGC_STATUS_SPEED_1000) {
+		/* For I225, STATUS will indicate 1G speed in both 1 Gbps
+		 * and 2.5 Gbps link modes. An additional bit is used
+		 * to differentiate between 1 Gbps and 2.5 Gbps.
+		 */
+		if (hw->mac.type == igc_i225 &&
+		    (status & IGC_STATUS_SPEED_2500)) {
+			*speed = SPEED_2500;
+			hw_dbg("2500 Mbs, ");
+		} else {
+			*speed = SPEED_1000;
+			hw_dbg("1000 Mbs, ");
+		}
+	} else if (status & IGC_STATUS_SPEED_100) {
+		*speed = SPEED_100;
+		hw_dbg("100 Mbs, ");
+	} else {
+		*speed = SPEED_10;
+		hw_dbg("10 Mbs, ");
+	}
+
+	if (status & IGC_STATUS_FD) {
+		*duplex = FULL_DUPLEX;
+		hw_dbg("Full Duplex\n");
+	} else {
+		*duplex = HALF_DUPLEX;
+		hw_dbg("Half Duplex\n");
+	}
+
+	return 0;
+}
+
+/**
+ * igc_put_hw_semaphore - Release hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Release hardware semaphore used to access the PHY or NVM
+ */
+void igc_put_hw_semaphore(struct igc_hw *hw)
+{
+	u32 swsm;
+
+	swsm = rd32(IGC_SWSM);
+
+	swsm &= ~(IGC_SWSM_SMBI | IGC_SWSM_SWESMBI);
+
+	wr32(IGC_SWSM, swsm);
+}
+
+/**
+ * igc_enable_mng_pass_thru - Enable processing of ARP's
+ * @hw: pointer to the HW structure
+ *
+ * Verifies the hardware needs to leave interface enabled so that frames can
+ * be directed to and from the management interface.
+ */
+bool igc_enable_mng_pass_thru(struct igc_hw *hw)
+{
+	bool ret_val = false;
+	u32 fwsm, factps;
+	u32 manc;
+
+	if (!hw->mac.asf_firmware_present)
+		goto out;
+
+	manc = rd32(IGC_MANC);
+
+	if (!(manc & IGC_MANC_RCV_TCO_EN))
+		goto out;
+
+	if (hw->mac.arc_subsystem_valid) {
+		fwsm = rd32(IGC_FWSM);
+		factps = rd32(IGC_FACTPS);
+
+		if (!(factps & IGC_FACTPS_MNGCG) &&
+		    ((fwsm & IGC_FWSM_MODE_MASK) ==
+		    (igc_mng_mode_pt << IGC_FWSM_MODE_SHIFT))) {
+			ret_val = true;
+			goto out;
+		}
+	} else {
+		if ((manc & IGC_MANC_SMBUS_EN) &&
+		    !(manc & IGC_MANC_ASF_EN)) {
+			ret_val = true;
+			goto out;
+		}
+	}
+
+out:
+	return ret_val;
+}

drivers/net/ethernet/intel/igc/igc_mac.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_MAC_H_
+#define _IGC_MAC_H_
+
+#include "igc_hw.h"
+#include "igc_phy.h"
+#include "igc_defines.h"
+
+#ifndef IGC_REMOVED
+#define IGC_REMOVED(a) (0)
+#endif /* IGC_REMOVED */
+
+/* forward declaration */
+s32 igc_disable_pcie_master(struct igc_hw *hw);
+s32 igc_check_for_copper_link(struct igc_hw *hw);
+s32 igc_config_fc_after_link_up(struct igc_hw *hw);
+s32 igc_force_mac_fc(struct igc_hw *hw);
+void igc_init_rx_addrs(struct igc_hw *hw, u16 rar_count);
+s32 igc_setup_link(struct igc_hw *hw);
+void igc_clear_hw_cntrs_base(struct igc_hw *hw);
+s32 igc_get_auto_rd_done(struct igc_hw *hw);
+void igc_put_hw_semaphore(struct igc_hw *hw);
+void igc_rar_set(struct igc_hw *hw, u8 *addr, u32 index);
+void igc_config_collision_dist(struct igc_hw *hw);
+
+s32 igc_get_speed_and_duplex_copper(struct igc_hw *hw, u16 *speed,
+				    u16 *duplex);
+
+bool igc_enable_mng_pass_thru(struct igc_hw *hw);
+
+enum igc_mng_mode {
+	igc_mng_mode_none = 0,
+	igc_mng_mode_asf,
+	igc_mng_mode_pt,
+	igc_mng_mode_ipmi,
+	igc_mng_mode_host_if_only
+};
+
+#endif

drivers/net/ethernet/intel/igc/igc_main.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/if_vlan.h>
+#include <linux/aer.h>
+
+#include "igc.h"
+#include "igc_hw.h"
+
+#define DRV_VERSION	"0.0.1-k"
+#define DRV_SUMMARY	"Intel(R) 2.5G Ethernet Linux Driver"
+
+static int debug = -1;
+
+MODULE_AUTHOR("Intel Corporation, <[e-mail]>");
+MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
+char igc_driver_name[] = "igc";
+char igc_driver_version[] = DRV_VERSION;
+static const char igc_driver_string[] = DRV_SUMMARY;
+static const char igc_copyright[] =
+	"Copyright(c) 2018 Intel Corporation.";
+
+static const struct igc_info *igc_info_tbl[] = {
+	[board_base] = &igc_base_info,
+};
+
+static const struct pci_device_id igc_pci_tbl[] = {
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LM), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_V), board_base },
+	/* required last entry */
+	{0, }
+};
+
+MODULE_DEVICE_TABLE(pci, igc_pci_tbl);
+
+/* forward declaration */
+static void igc_clean_tx_ring(struct igc_ring *tx_ring);
+static int igc_sw_init(struct igc_adapter *);
+static void igc_configure(struct igc_adapter *adapter);
+static void igc_power_down_link(struct igc_adapter *adapter);
+static void igc_set_default_mac_filter(struct igc_adapter *adapter);
+static void igc_set_rx_mode(struct net_device *netdev);
+static void igc_write_itr(struct igc_q_vector *q_vector);
+static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector);
+static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx);
+static void igc_set_interrupt_capability(struct igc_adapter *adapter,
+					 bool msix);
+static void igc_free_q_vectors(struct igc_adapter *adapter);
+static void igc_irq_disable(struct igc_adapter *adapter);
+static void igc_irq_enable(struct igc_adapter *adapter);
+static void igc_configure_msix(struct igc_adapter *adapter);
+static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
+				  struct igc_rx_buffer *bi);
+
+enum latency_range {
+	lowest_latency = 0,
+	low_latency = 1,
+	bulk_latency = 2,
+	latency_invalid = 255
+};
+
+static void igc_reset(struct igc_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct igc_hw *hw = &adapter->hw;
+
+	hw->mac.ops.reset_hw(hw);
+
+	if (hw->mac.ops.init_hw(hw))
+		dev_err(&pdev->dev, "Hardware Error\n");
+
+	if (!netif_running(adapter->netdev))
+		igc_power_down_link(adapter);
+
+	igc_get_phy_info(hw);
+}
+
+/**
+ * igc_power_up_link - Power up the phy/serdes link
+ * @adapter: address of board private structure
+ */
+static void igc_power_up_link(struct igc_adapter *adapter)
+{
+	igc_reset_phy(&adapter->hw);
+
+	if (adapter->hw.phy.media_type == igc_media_type_copper)
+		igc_power_up_phy_copper(&adapter->hw);
+
+	igc_setup_link(&adapter->hw);
+}
+
+/**
+ * igc_power_down_link - Power down the phy/serdes link
+ * @adapter: address of board private structure
+ */
+static void igc_power_down_link(struct igc_adapter *adapter)
+{
+	if (adapter->hw.phy.media_type == igc_media_type_copper)
+		igc_power_down_phy_copper_base(&adapter->hw);
+}
+
+/**
+ * igc_release_hw_control - release control of the h/w to f/w
+ * @adapter: address of board private structure
+ *
+ * igc_release_hw_control resets CTRL_EXT:DRV_LOAD bit.
+ * For ASF and Pass Through versions of f/w this means that the
+ * driver is no longer loaded.
+ */
+static void igc_release_hw_control(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 ctrl_ext;
+
+	/* Let firmware take over control of h/w */
+	ctrl_ext = rd32(IGC_CTRL_EXT);
+	wr32(IGC_CTRL_EXT,
+	     ctrl_ext & ~IGC_CTRL_EXT_DRV_LOAD);
+}
+
+/**
+ * igc_get_hw_control - get control of the h/w from f/w
+ * @adapter: address of board private structure
+ *
+ * igc_get_hw_control sets CTRL_EXT:DRV_LOAD bit.
+ * For ASF and Pass Through versions of f/w this means that
+ * the driver is loaded.
+ */
+static void igc_get_hw_control(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 ctrl_ext;
+
+	/* Let firmware know the driver has taken over */
+	ctrl_ext = rd32(IGC_CTRL_EXT);
+	wr32(IGC_CTRL_EXT,
+	     ctrl_ext | IGC_CTRL_EXT_DRV_LOAD);
+}
+
+/**
+ * igc_free_tx_resources - Free Tx Resources per Queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ */
+static void igc_free_tx_resources(struct igc_ring *tx_ring)
+{
+	igc_clean_tx_ring(tx_ring);
+
+	vfree(tx_ring->tx_buffer_info);
+	tx_ring->tx_buffer_info = NULL;
+
+	/* if not set, then don't free */
+	if (!tx_ring->desc)
+		return;
+
+	dma_free_coherent(tx_ring->dev, tx_ring->size,
+			  tx_ring->desc, tx_ring->dma);
+
+	tx_ring->desc = NULL;
+}
+
+/**
+ * igc_free_all_tx_resources - Free Tx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all transmit software resources
+ */
+static void igc_free_all_tx_resources(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		igc_free_tx_resources(adapter->tx_ring[i]);
+}
+
+/**
+ * igc_clean_tx_ring - Free Tx Buffers
+ * @tx_ring: ring to be cleaned
+ */
+static void igc_clean_tx_ring(struct igc_ring *tx_ring)
+{
+	u16 i = tx_ring->next_to_clean;
+	struct igc_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+
+	while (i != tx_ring->next_to_use) {
+		union igc_adv_tx_desc *eop_desc, *tx_desc;
+
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer->skb);
+
+		/* 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);
+
+		/* check for eop_desc to determine the end of the packet */
+		eop_desc = tx_buffer->next_to_watch;
+		tx_desc = IGC_TX_DESC(tx_ring, i);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
+			tx_buffer++;
+			tx_desc++;
+			i++;
+			if (unlikely(i == tx_ring->count)) {
+				i = 0;
+				tx_buffer = tx_ring->tx_buffer_info;
+				tx_desc = IGC_TX_DESC(tx_ring, 0);
+			}
+
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len))
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+		}
+
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		i++;
+		if (unlikely(i == tx_ring->count)) {
+			i = 0;
+			tx_buffer = tx_ring->tx_buffer_info;
+		}
+	}
+
+	/* reset BQL for queue */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	/* reset next_to_use and next_to_clean */
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+}
+
+/**
+ * igc_clean_all_tx_rings - Free Tx Buffers for all queues
+ * @adapter: board private structure
+ */
+static void igc_clean_all_tx_rings(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		if (adapter->tx_ring[i])
+			igc_clean_tx_ring(adapter->tx_ring[i]);
+}
+
+/**
+ * igc_setup_tx_resources - allocate Tx resources (Descriptors)
+ * @tx_ring: tx descriptor ring (for a specific queue) to setup
+ *
+ * Return 0 on success, negative on failure
+ */
+static int igc_setup_tx_resources(struct igc_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int size = 0;
+
+	size = sizeof(struct igc_tx_buffer) * tx_ring->count;
+	tx_ring->tx_buffer_info = vzalloc(size);
+	if (!tx_ring->tx_buffer_info)
+		goto err;
+
+	/* round up to nearest 4K */
+	tx_ring->size = tx_ring->count * sizeof(union igc_adv_tx_desc);
+	tx_ring->size = ALIGN(tx_ring->size, 4096);
+
+	tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
+					   &tx_ring->dma, GFP_KERNEL);
+
+	if (!tx_ring->desc)
+		goto err;
+
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+
+	return 0;
+
+err:
+	vfree(tx_ring->tx_buffer_info);
+	dev_err(dev,
+		"Unable to allocate memory for the transmit descriptor ring\n");
+	return -ENOMEM;
+}
+
+/**
+ * igc_setup_all_tx_resources - wrapper to allocate Tx resources for all queues
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ */
+static int igc_setup_all_tx_resources(struct igc_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		err = igc_setup_tx_resources(adapter->tx_ring[i]);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Allocation for Tx Queue %u failed\n", i);
+			for (i--; i >= 0; i--)
+				igc_free_tx_resources(adapter->tx_ring[i]);
+			break;
+		}
+	}
+
+	return err;
+}
+
+/**
+ * igc_clean_rx_ring - Free Rx Buffers per Queue
+ * @rx_ring: ring to free buffers from
+ */
+static void igc_clean_rx_ring(struct igc_ring *rx_ring)
+{
+	u16 i = rx_ring->next_to_clean;
+
+	if (rx_ring->skb)
+		dev_kfree_skb(rx_ring->skb);
+	rx_ring->skb = NULL;
+
+	/* Free all the Rx ring sk_buffs */
+	while (i != rx_ring->next_to_alloc) {
+		struct igc_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
+
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      buffer_info->dma,
+					      buffer_info->page_offset,
+					      igc_rx_bufsz(rx_ring),
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev,
+				     buffer_info->dma,
+				     igc_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     IGC_RX_DMA_ATTR);
+		__page_frag_cache_drain(buffer_info->page,
+					buffer_info->pagecnt_bias);
+
+		i++;
+		if (i == rx_ring->count)
+			i = 0;
+	}
+
+	rx_ring->next_to_alloc = 0;
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+}
+
+/**
+ * igc_clean_all_rx_rings - Free Rx Buffers for all queues
+ * @adapter: board private structure
+ */
+static void igc_clean_all_rx_rings(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		if (adapter->rx_ring[i])
+			igc_clean_rx_ring(adapter->rx_ring[i]);
+}
+
+/**
+ * igc_free_rx_resources - Free Rx Resources
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ */
+static void igc_free_rx_resources(struct igc_ring *rx_ring)
+{
+	igc_clean_rx_ring(rx_ring);
+
+	vfree(rx_ring->rx_buffer_info);
+	rx_ring->rx_buffer_info = NULL;
+
+	/* if not set, then don't free */
+	if (!rx_ring->desc)
+		return;
+
+	dma_free_coherent(rx_ring->dev, rx_ring->size,
+			  rx_ring->desc, rx_ring->dma);
+
+	rx_ring->desc = NULL;
+}
+
+/**
+ * igc_free_all_rx_resources - Free Rx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all receive software resources
+ */
+static void igc_free_all_rx_resources(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		igc_free_rx_resources(adapter->rx_ring[i]);
+}
+
+/**
+ * igc_setup_rx_resources - allocate Rx resources (Descriptors)
+ * @rx_ring:    rx descriptor ring (for a specific queue) to setup
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int igc_setup_rx_resources(struct igc_ring *rx_ring)
+{
+	struct device *dev = rx_ring->dev;
+	int size, desc_len;
+
+	size = sizeof(struct igc_rx_buffer) * rx_ring->count;
+	rx_ring->rx_buffer_info = vzalloc(size);
+	if (!rx_ring->rx_buffer_info)
+		goto err;
+
+	desc_len = sizeof(union igc_adv_rx_desc);
+
+	/* Round up to nearest 4K */
+	rx_ring->size = rx_ring->count * desc_len;
+	rx_ring->size = ALIGN(rx_ring->size, 4096);
+
+	rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
+					   &rx_ring->dma, GFP_KERNEL);
+
+	if (!rx_ring->desc)
+		goto err;
+
+	rx_ring->next_to_alloc = 0;
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+
+	return 0;
+
+err:
+	vfree(rx_ring->rx_buffer_info);
+	rx_ring->rx_buffer_info = NULL;
+	dev_err(dev,
+		"Unable to allocate memory for the receive descriptor ring\n");
+	return -ENOMEM;
+}
+
+/**
+ * igc_setup_all_rx_resources - wrapper to allocate Rx resources
+ *                                (Descriptors) for all queues
+ * @adapter: board private structure
+ *
+ * Return 0 on success, negative on failure
+ */
+static int igc_setup_all_rx_resources(struct igc_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		err = igc_setup_rx_resources(adapter->rx_ring[i]);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Allocation for Rx Queue %u failed\n", i);
+			for (i--; i >= 0; i--)
+				igc_free_rx_resources(adapter->rx_ring[i]);
+			break;
+		}
+	}
+
+	return err;
+}
+
+/**
+ * igc_configure_rx_ring - Configure a receive ring after Reset
+ * @adapter: board private structure
+ * @ring: receive ring to be configured
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ */
+static void igc_configure_rx_ring(struct igc_adapter *adapter,
+				  struct igc_ring *ring)
+{
+	struct igc_hw *hw = &adapter->hw;
+	union igc_adv_rx_desc *rx_desc;
+	int reg_idx = ring->reg_idx;
+	u32 srrctl = 0, rxdctl = 0;
+	u64 rdba = ring->dma;
+
+	/* disable the queue */
+	wr32(IGC_RXDCTL(reg_idx), 0);
+
+	/* Set DMA base address registers */
+	wr32(IGC_RDBAL(reg_idx),
+	     rdba & 0x00000000ffffffffULL);
+	wr32(IGC_RDBAH(reg_idx), rdba >> 32);
+	wr32(IGC_RDLEN(reg_idx),
+	     ring->count * sizeof(union igc_adv_rx_desc));
+
+	/* initialize head and tail */
+	ring->tail = adapter->io_addr + IGC_RDT(reg_idx);
+	wr32(IGC_RDH(reg_idx), 0);
+	writel(0, ring->tail);
+
+	/* reset next-to- use/clean to place SW in sync with hardware */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
+
+	/* set descriptor configuration */
+	srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	if (ring_uses_large_buffer(ring))
+		srrctl |= IGC_RXBUFFER_3072 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+	else
+		srrctl |= IGC_RXBUFFER_2048 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+	srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF;
+
+	wr32(IGC_SRRCTL(reg_idx), srrctl);
+
+	rxdctl |= IGC_RX_PTHRESH;
+	rxdctl |= IGC_RX_HTHRESH << 8;
+	rxdctl |= IGC_RX_WTHRESH << 16;
+
+	/* initialize rx_buffer_info */
+	memset(ring->rx_buffer_info, 0,
+	       sizeof(struct igc_rx_buffer) * ring->count);
+
+	/* initialize Rx descriptor 0 */
+	rx_desc = IGC_RX_DESC(ring, 0);
+	rx_desc->wb.upper.length = 0;
+
+	/* enable receive descriptor fetching */
+	rxdctl |= IGC_RXDCTL_QUEUE_ENABLE;
+
+	wr32(IGC_RXDCTL(reg_idx), rxdctl);
+}
+
+/**
+ * igc_configure_rx - Configure receive Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ */
+static void igc_configure_rx(struct igc_adapter *adapter)
+{
+	int i;
+
+	/* Setup the HW Rx Head and Tail Descriptor Pointers and
+	 * the Base and Length of the Rx Descriptor Ring
+	 */
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		igc_configure_rx_ring(adapter, adapter->rx_ring[i]);
+}
+
+/**
+ * igc_configure_tx_ring - Configure transmit ring after Reset
+ * @adapter: board private structure
+ * @ring: tx ring to configure
+ *
+ * Configure a transmit ring after a reset.
+ */
+static void igc_configure_tx_ring(struct igc_adapter *adapter,
+				  struct igc_ring *ring)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int reg_idx = ring->reg_idx;
+	u64 tdba = ring->dma;
+	u32 txdctl = 0;
+
+	/* disable the queue */
+	wr32(IGC_TXDCTL(reg_idx), 0);
+	wrfl();
+	mdelay(10);
+
+	wr32(IGC_TDLEN(reg_idx),
+	     ring->count * sizeof(union igc_adv_tx_desc));
+	wr32(IGC_TDBAL(reg_idx),
+	     tdba & 0x00000000ffffffffULL);
+	wr32(IGC_TDBAH(reg_idx), tdba >> 32);
+
+	ring->tail = adapter->io_addr + IGC_TDT(reg_idx);
+	wr32(IGC_TDH(reg_idx), 0);
+	writel(0, ring->tail);
+
+	txdctl |= IGC_TX_PTHRESH;
+	txdctl |= IGC_TX_HTHRESH << 8;
+	txdctl |= IGC_TX_WTHRESH << 16;
+
+	txdctl |= IGC_TXDCTL_QUEUE_ENABLE;
+	wr32(IGC_TXDCTL(reg_idx), txdctl);
+}
+
+/**
+ * igc_configure_tx - Configure transmit Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Tx unit of the MAC after a reset.
+ */
+static void igc_configure_tx(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		igc_configure_tx_ring(adapter, adapter->tx_ring[i]);
+}
+
+/**
+ * igc_setup_mrqc - configure the multiple receive queue control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_mrqc(struct igc_adapter *adapter)
+{
+}
+
+/**
+ * igc_setup_rctl - configure the receive control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_rctl(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 rctl;
+
+	rctl = rd32(IGC_RCTL);
+
+	rctl &= ~(3 << IGC_RCTL_MO_SHIFT);
+	rctl &= ~(IGC_RCTL_LBM_TCVR | IGC_RCTL_LBM_MAC);
+
+	rctl |= IGC_RCTL_EN | IGC_RCTL_BAM | IGC_RCTL_RDMTS_HALF |
+		(hw->mac.mc_filter_type << IGC_RCTL_MO_SHIFT);
+
+	/* enable stripping of CRC. Newer features require
+	 * that the HW strips the CRC.
+	 */
+	rctl |= IGC_RCTL_SECRC;
+
+	/* disable store bad packets and clear size bits. */
+	rctl &= ~(IGC_RCTL_SBP | IGC_RCTL_SZ_256);
+
+	/* enable LPE to allow for reception of jumbo frames */
+	rctl |= IGC_RCTL_LPE;
+
+	/* disable queue 0 to prevent tail write w/o re-config */
+	wr32(IGC_RXDCTL(0), 0);
+
+	/* This is useful for sniffing bad packets. */
+	if (adapter->netdev->features & NETIF_F_RXALL) {
+		/* UPE and MPE will be handled by normal PROMISC logic
+		 * in set_rx_mode
+		 */
+		rctl |= (IGC_RCTL_SBP | /* Receive bad packets */
+			 IGC_RCTL_BAM | /* RX All Bcast Pkts */
+			 IGC_RCTL_PMCF); /* RX All MAC Ctrl Pkts */
+
+		rctl &= ~(IGC_RCTL_DPF | /* Allow filtered pause */
+			  IGC_RCTL_CFIEN); /* Disable VLAN CFIEN Filter */
+	}
+
+	wr32(IGC_RCTL, rctl);
+}
+
+/**
+ * igc_setup_tctl - configure the transmit control registers
+ * @adapter: Board private structure
+ */
+static void igc_setup_tctl(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 tctl;
+
+	/* disable queue 0 which icould be enabled by default */
+	wr32(IGC_TXDCTL(0), 0);
+
+	/* Program the Transmit Control Register */
+	tctl = rd32(IGC_TCTL);
+	tctl &= ~IGC_TCTL_CT;
+	tctl |= IGC_TCTL_PSP | IGC_TCTL_RTLC |
+		(IGC_COLLISION_THRESHOLD << IGC_CT_SHIFT);
+
+	/* Enable transmits */
+	tctl |= IGC_TCTL_EN;
+
+	wr32(IGC_TCTL, tctl);
+}
+
+/**
+ * igc_set_mac - Change the Ethernet Address of the NIC
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int igc_set_mac(struct net_device *netdev, void *p)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
+
+	/* set the correct pool for the new PF MAC address in entry 0 */
+	igc_set_default_mac_filter(adapter);
+
+	return 0;
+}
+
+static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first)
+{
+}
+
+static int __igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
+{
+	struct net_device *netdev = tx_ring->netdev;
+
+	netif_stop_subqueue(netdev, tx_ring->queue_index);
+
+	/* memory barriier comment */
+	smp_mb();
+
+	/* We need to check again in a case another CPU has just
+	 * made room available.
+	 */
+	if (igc_desc_unused(tx_ring) < size)
+		return -EBUSY;
+
+	/* A reprieve! */
+	netif_wake_subqueue(netdev, tx_ring->queue_index);
+
+	u64_stats_update_begin(&tx_ring->tx_syncp2);
+	tx_ring->tx_stats.restart_queue2++;
+	u64_stats_update_end(&tx_ring->tx_syncp2);
+
+	return 0;
+}
+
+static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
+{
+	if (igc_desc_unused(tx_ring) >= size)
+		return 0;
+	return __igc_maybe_stop_tx(tx_ring, size);
+}
+
+static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
+{
+	/* set type for advanced descriptor with frame checksum insertion */
+	u32 cmd_type = IGC_ADVTXD_DTYP_DATA |
+		       IGC_ADVTXD_DCMD_DEXT |
+		       IGC_ADVTXD_DCMD_IFCS;
+
+	return cmd_type;
+}
+
+static void igc_tx_olinfo_status(struct igc_ring *tx_ring,
+				 union igc_adv_tx_desc *tx_desc,
+				 u32 tx_flags, unsigned int paylen)
+{
+	u32 olinfo_status = paylen << IGC_ADVTXD_PAYLEN_SHIFT;
+
+	/* insert L4 checksum */
+	olinfo_status |= (tx_flags & IGC_TX_FLAGS_CSUM) *
+			  ((IGC_TXD_POPTS_TXSM << 8) /
+			  IGC_TX_FLAGS_CSUM);
+
+	/* insert IPv4 checksum */
+	olinfo_status |= (tx_flags & IGC_TX_FLAGS_IPV4) *
+			  (((IGC_TXD_POPTS_IXSM << 8)) /
+			  IGC_TX_FLAGS_IPV4);
+
+	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+}
+
+static int igc_tx_map(struct igc_ring *tx_ring,
+		      struct igc_tx_buffer *first,
+		      const u8 hdr_len)
+{
+	struct sk_buff *skb = first->skb;
+	struct igc_tx_buffer *tx_buffer;
+	union igc_adv_tx_desc *tx_desc;
+	u32 tx_flags = first->tx_flags;
+	struct skb_frag_struct *frag;
+	u16 i = tx_ring->next_to_use;
+	unsigned int data_len, size;
+	dma_addr_t dma;
+	u32 cmd_type = igc_tx_cmd_type(skb, tx_flags);
+
+	tx_desc = IGC_TX_DESC(tx_ring, i);
+
+	igc_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len);
+
+	size = skb_headlen(skb);
+	data_len = skb->data_len;
+
+	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
+
+	tx_buffer = first;
+
+	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+		if (dma_mapping_error(tx_ring->dev, dma))
+			goto dma_error;
+
+		/* record length, and DMA address */
+		dma_unmap_len_set(tx_buffer, len, size);
+		dma_unmap_addr_set(tx_buffer, dma, dma);
+
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+		while (unlikely(size > IGC_MAX_DATA_PER_TXD)) {
+			tx_desc->read.cmd_type_len =
+				cpu_to_le32(cmd_type ^ IGC_MAX_DATA_PER_TXD);
+
+			i++;
+			tx_desc++;
+			if (i == tx_ring->count) {
+				tx_desc = IGC_TX_DESC(tx_ring, 0);
+				i = 0;
+			}
+			tx_desc->read.olinfo_status = 0;
+
+			dma += IGC_MAX_DATA_PER_TXD;
+			size -= IGC_MAX_DATA_PER_TXD;
+
+			tx_desc->read.buffer_addr = cpu_to_le64(dma);
+		}
+
+		if (likely(!data_len))
+			break;
+
+		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size);
+
+		i++;
+		tx_desc++;
+		if (i == tx_ring->count) {
+			tx_desc = IGC_TX_DESC(tx_ring, 0);
+			i = 0;
+		}
+		tx_desc->read.olinfo_status = 0;
+
+		size = skb_frag_size(frag);
+		data_len -= size;
+
+		dma = skb_frag_dma_map(tx_ring->dev, frag, 0,
+				       size, DMA_TO_DEVICE);
+
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+	}
+
+	/* write last descriptor with RS and EOP bits */
+	cmd_type |= size | IGC_TXD_DCMD;
+	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+
+	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
+
+	/* set the timestamp */
+	first->time_stamp = jiffies;
+
+	/* Force memory writes to complete before letting h/w know there
+	 * are new descriptors to fetch.  (Only applicable for weak-ordered
+	 * memory model archs, such as IA-64).
+	 *
+	 * We also need this memory barrier to make certain all of the
+	 * status bits have been updated before next_to_watch is written.
+	 */
+	wmb();
+
+	/* set next_to_watch value indicating a packet is present */
+	first->next_to_watch = tx_desc;
+
+	i++;
+	if (i == tx_ring->count)
+		i = 0;
+
+	tx_ring->next_to_use = i;
+
+	/* Make sure there is space in the ring for the next send. */
+	igc_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+		writel(i, tx_ring->tail);
+
+		/* we need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
+	}
+
+	return 0;
+dma_error:
+	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	tx_buffer = &tx_ring->tx_buffer_info[i];
+
+	/* clear dma mappings for failed tx_buffer_info map */
+	while (tx_buffer != first) {
+		if (dma_unmap_len(tx_buffer, len))
+			dma_unmap_page(tx_ring->dev,
+				       dma_unmap_addr(tx_buffer, dma),
+				       dma_unmap_len(tx_buffer, len),
+				       DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		if (i-- == 0)
+			i += tx_ring->count;
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+	}
+
+	if (dma_unmap_len(tx_buffer, len))
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buffer, len, 0);
+
+	dev_kfree_skb_any(tx_buffer->skb);
+	tx_buffer->skb = NULL;
+
+	tx_ring->next_to_use = i;
+
+	return -1;
+}
+
+static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
+				       struct igc_ring *tx_ring)
+{
+	u16 count = TXD_USE_COUNT(skb_headlen(skb));
+	__be16 protocol = vlan_get_protocol(skb);
+	struct igc_tx_buffer *first;
+	u32 tx_flags = 0;
+	unsigned short f;
+	u8 hdr_len = 0;
+
+	/* need: 1 descriptor per page * PAGE_SIZE/IGC_MAX_DATA_PER_TXD,
+	 *	+ 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
+	 *	+ 2 desc gap to keep tail from touching head,
+	 *	+ 1 desc for context descriptor,
+	 * otherwise try next time
+	 */
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+
+	if (igc_maybe_stop_tx(tx_ring, count + 3)) {
+		/* this is a hard error */
+		return NETDEV_TX_BUSY;
+	}
+
+	/* record the location of the first descriptor for this packet */
+	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	first->skb = skb;
+	first->bytecount = skb->len;
+	first->gso_segs = 1;
+
+	skb_tx_timestamp(skb);
+
+	/* record initial flags and protocol */
+	first->tx_flags = tx_flags;
+	first->protocol = protocol;
+
+	igc_tx_csum(tx_ring, first);
+
+	igc_tx_map(tx_ring, first, hdr_len);
+
+	return NETDEV_TX_OK;
+}
+
+static inline struct igc_ring *igc_tx_queue_mapping(struct igc_adapter *adapter,
+						    struct sk_buff *skb)
+{
+	unsigned int r_idx = skb->queue_mapping;
+
+	if (r_idx >= adapter->num_tx_queues)
+		r_idx = r_idx % adapter->num_tx_queues;
+
+	return adapter->tx_ring[r_idx];
+}
+
+static netdev_tx_t igc_xmit_frame(struct sk_buff *skb,
+				  struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	/* The minimum packet size with TCTL.PSP set is 17 so pad the skb
+	 * in order to meet this minimum size requirement.
+	 */
+	if (skb->len < 17) {
+		if (skb_padto(skb, 17))
+			return NETDEV_TX_OK;
+		skb->len = 17;
+	}
+
+	return igc_xmit_frame_ring(skb, igc_tx_queue_mapping(adapter, skb));
+}
+
+static inline void igc_rx_hash(struct igc_ring *ring,
+			       union igc_adv_rx_desc *rx_desc,
+			       struct sk_buff *skb)
+{
+	if (ring->netdev->features & NETIF_F_RXHASH)
+		skb_set_hash(skb,
+			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
+			     PKT_HASH_TYPE_L3);
+}
+
+/**
+ * igc_process_skb_fields - Populate skb header fields from Rx descriptor
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being populated
+ *
+ * This function checks the ring, descriptor, and packet information in
+ * order to populate the hash, checksum, VLAN, timestamp, protocol, and
+ * other fields within the skb.
+ */
+static void igc_process_skb_fields(struct igc_ring *rx_ring,
+				   union igc_adv_rx_desc *rx_desc,
+				   struct sk_buff *skb)
+{
+	igc_rx_hash(rx_ring, rx_desc, skb);
+
+	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+}
+
+static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring,
+					       const unsigned int size)
+{
+	struct igc_rx_buffer *rx_buffer;
+
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
+
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
+
+	rx_buffer->pagecnt_bias--;
+
+	return rx_buffer;
+}
+
+/**
+ * igc_add_rx_frag - Add contents of Rx buffer to sk_buff
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: buffer containing page to add
+ * @skb: sk_buff to place the data into
+ * @size: size of buffer to be added
+ *
+ * This function will add the data contained in rx_buffer->page to the skb.
+ */
+static void igc_add_rx_frag(struct igc_ring *rx_ring,
+			    struct igc_rx_buffer *rx_buffer,
+			    struct sk_buff *skb,
+			    unsigned int size)
+{
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
+	rx_buffer->page_offset ^= truesize;
+#else
+	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+				SKB_DATA_ALIGN(IGC_SKB_PAD + size) :
+				SKB_DATA_ALIGN(size);
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
+static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
+				     struct igc_rx_buffer *rx_buffer,
+				     union igc_adv_rx_desc *rx_desc,
+				     unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(IGC_SKB_PAD + size);
+#endif
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* build an skb around the page buffer */
+	skb = build_skb(va - IGC_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, IGC_SKB_PAD);
+	 __skb_put(skb, size);
+
+	/* update buffer offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+
+	return skb;
+}
+
+static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
+					 struct igc_rx_buffer *rx_buffer,
+					 union igc_adv_rx_desc *rx_desc,
+					 unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igc_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGC_RX_HDR_LEN);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > IGC_RX_HDR_LEN)
+		headlen = eth_get_headlen(va, IGC_RX_HDR_LEN);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				(va + headlen) - page_address(rx_buffer->page),
+				size, truesize);
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		rx_buffer->pagecnt_bias++;
+	}
+
+	return skb;
+}
+
+/**
+ * igc_reuse_rx_page - page flip buffer and store it back on the ring
+ * @rx_ring: rx descriptor ring to store buffers on
+ * @old_buff: donor buffer to have page reused
+ *
+ * Synchronizes page for reuse by the adapter
+ */
+static void igc_reuse_rx_page(struct igc_ring *rx_ring,
+			      struct igc_rx_buffer *old_buff)
+{
+	u16 nta = rx_ring->next_to_alloc;
+	struct igc_rx_buffer *new_buff;
+
+	new_buff = &rx_ring->rx_buffer_info[nta];
+
+	/* update, and store next to alloc */
+	nta++;
+	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+	/* Transfer page from old buffer to new buffer.
+	 * Move each member individually to avoid possible store
+	 * forwarding stalls.
+	 */
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
+}
+
+static inline bool igc_page_is_reserved(struct page *page)
+{
+	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
+}
+
+static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer)
+{
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
+
+	/* avoid re-using remote pages */
+	if (unlikely(igc_page_is_reserved(page)))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+		return false;
+#else
+#define IGC_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IGC_RXBUFFER_2048)
+
+	if (rx_buffer->page_offset > IGC_LAST_OFFSET)
+		return false;
+#endif
+
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
+
+	return true;
+}
+
+/**
+ * igc_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ * @skb: current socket buffer containing buffer in progress
+ *
+ * This function updates next to clean.  If the buffer is an EOP buffer
+ * this function exits returning false, otherwise it will place the
+ * sk_buff in the next buffer to be chained and return true indicating
+ * that this is in fact a non-EOP buffer.
+ */
+static bool igc_is_non_eop(struct igc_ring *rx_ring,
+			   union igc_adv_rx_desc *rx_desc)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	/* fetch, update, and store next to clean */
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+
+	prefetch(IGC_RX_DESC(rx_ring, ntc));
+
+	if (likely(igc_test_staterr(rx_desc, IGC_RXD_STAT_EOP)))
+		return false;
+
+	return true;
+}
+
+/**
+ * igc_cleanup_headers - Correct corrupted or empty headers
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being fixed
+ *
+ * Address the case where we are pulling data in on pages only
+ * and as such no data is present in the skb header.
+ *
+ * In addition if skb is not at least 60 bytes we need to pad it so that
+ * it is large enough to qualify as a valid Ethernet frame.
+ *
+ * Returns true if an error was encountered and skb was freed.
+ */
+static bool igc_cleanup_headers(struct igc_ring *rx_ring,
+				union igc_adv_rx_desc *rx_desc,
+				struct sk_buff *skb)
+{
+	if (unlikely((igc_test_staterr(rx_desc,
+				       IGC_RXDEXT_ERR_FRAME_ERR_MASK)))) {
+		struct net_device *netdev = rx_ring->netdev;
+
+		if (!(netdev->features & NETIF_F_RXALL)) {
+			dev_kfree_skb_any(skb);
+			return true;
+		}
+	}
+
+	/* if eth_skb_pad returns an error the skb was freed */
+	if (eth_skb_pad(skb))
+		return true;
+
+	return false;
+}
+
+static void igc_put_rx_buffer(struct igc_ring *rx_ring,
+			      struct igc_rx_buffer *rx_buffer)
+{
+	if (igc_can_reuse_rx_page(rx_buffer)) {
+		/* hand second half of page back to the ring */
+		igc_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* We are not reusing the buffer so unmap it and free
+		 * any references we are holding to it
+		 */
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     igc_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
+				     IGC_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
+	}
+
+	/* clear contents of rx_buffer */
+	rx_buffer->page = NULL;
+}
+
+/**
+ * igc_alloc_rx_buffers - Replace used receive buffers; packet split
+ * @adapter: address of board private structure
+ */
+static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count)
+{
+	union igc_adv_rx_desc *rx_desc;
+	u16 i = rx_ring->next_to_use;
+	struct igc_rx_buffer *bi;
+	u16 bufsz;
+
+	/* nothing to do */
+	if (!cleaned_count)
+		return;
+
+	rx_desc = IGC_RX_DESC(rx_ring, i);
+	bi = &rx_ring->rx_buffer_info[i];
+	i -= rx_ring->count;
+
+	bufsz = igc_rx_bufsz(rx_ring);
+
+	do {
+		if (!igc_alloc_mapped_page(rx_ring, bi))
+			break;
+
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset, bufsz,
+						 DMA_FROM_DEVICE);
+
+		/* Refresh the desc even if buffer_addrs didn't change
+		 * because each write-back erases this info.
+		 */
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+
+		rx_desc++;
+		bi++;
+		i++;
+		if (unlikely(!i)) {
+			rx_desc = IGC_RX_DESC(rx_ring, 0);
+			bi = rx_ring->rx_buffer_info;
+			i -= rx_ring->count;
+		}
+
+		/* clear the length for the next_to_use descriptor */
+		rx_desc->wb.upper.length = 0;
+
+		cleaned_count--;
+	} while (cleaned_count);
+
+	i += rx_ring->count;
+
+	if (rx_ring->next_to_use != i) {
+		/* record the next descriptor to use */
+		rx_ring->next_to_use = i;
+
+		/* update next to alloc since we have filled the ring */
+		rx_ring->next_to_alloc = i;
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(i, rx_ring->tail);
+	}
+}
+
+static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
+{
+	unsigned int total_bytes = 0, total_packets = 0;
+	struct igc_ring *rx_ring = q_vector->rx.ring;
+	struct sk_buff *skb = rx_ring->skb;
+	u16 cleaned_count = igc_desc_unused(rx_ring);
+
+	while (likely(total_packets < budget)) {
+		union igc_adv_rx_desc *rx_desc;
+		struct igc_rx_buffer *rx_buffer;
+		unsigned int size;
+
+		/* return some buffers to hardware, one at a time is too slow */
+		if (cleaned_count >= IGC_RX_BUFFER_WRITE) {
+			igc_alloc_rx_buffers(rx_ring, cleaned_count);
+			cleaned_count = 0;
+		}
+
+		rx_desc = IGC_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
+			break;
+
+		/* This memory barrier is needed to keep us from reading
+		 * any other fields out of the rx_desc until we know the
+		 * descriptor has been written back
+		 */
+		dma_rmb();
+
+		rx_buffer = igc_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			igc_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = igc_build_skb(rx_ring, rx_buffer, rx_desc, size);
+		else
+			skb = igc_construct_skb(rx_ring, rx_buffer,
+						rx_desc, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_failed++;
+			rx_buffer->pagecnt_bias++;
+			break;
+		}
+
+		igc_put_rx_buffer(rx_ring, rx_buffer);
+		cleaned_count++;
+
+		/* fetch next buffer in frame if non-eop */
+		if (igc_is_non_eop(rx_ring, rx_desc))
+			continue;
+
+		/* verify the packet layout is correct */
+		if (igc_cleanup_headers(rx_ring, rx_desc, skb)) {
+			skb = NULL;
+			continue;
+		}
+
+		/* probably a little skewed due to removing CRC */
+		total_bytes += skb->len;
+
+		/* populate checksum, timestamp, VLAN, and protocol */
+		igc_process_skb_fields(rx_ring, rx_desc, skb);
+
+		napi_gro_receive(&q_vector->napi, skb);
+
+		/* reset skb pointer */
+		skb = NULL;
+
+		/* update budget accounting */
+		total_packets++;
+	}
+
+	/* place incomplete frames back on ring for completion */
+	rx_ring->skb = skb;
+
+	u64_stats_update_begin(&rx_ring->rx_syncp);
+	rx_ring->rx_stats.packets += total_packets;
+	rx_ring->rx_stats.bytes += total_bytes;
+	u64_stats_update_end(&rx_ring->rx_syncp);
+	q_vector->rx.total_packets += total_packets;
+	q_vector->rx.total_bytes += total_bytes;
+
+	if (cleaned_count)
+		igc_alloc_rx_buffers(rx_ring, cleaned_count);
+
+	return total_packets;
+}
+
+static inline unsigned int igc_rx_offset(struct igc_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? IGC_SKB_PAD : 0;
+}
+
+static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
+				  struct igc_rx_buffer *bi)
+{
+	struct page *page = bi->page;
+	dma_addr_t dma;
+
+	/* since we are recycling buffers we should seldom need to alloc */
+	if (likely(page))
+		return true;
+
+	/* alloc new page for storage */
+	page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
+	if (unlikely(!page)) {
+		rx_ring->rx_stats.alloc_failed++;
+		return false;
+	}
+
+	/* map page for use */
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 igc_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 IGC_RX_DMA_ATTR);
+
+	/* if mapping failed free memory back to system since
+	 * there isn't much point in holding memory we can't use
+	 */
+	if (dma_mapping_error(rx_ring->dev, dma)) {
+		__free_page(page);
+
+		rx_ring->rx_stats.alloc_failed++;
+		return false;
+	}
+
+	bi->dma = dma;
+	bi->page = page;
+	bi->page_offset = igc_rx_offset(rx_ring);
+	bi->pagecnt_bias = 1;
+
+	return true;
+}
+
+/**
+ * igc_clean_tx_irq - Reclaim resources after transmit completes
+ * @q_vector: pointer to q_vector containing needed info
+ * @napi_budget: Used to determine if we are in netpoll
+ *
+ * returns true if ring is completely cleaned
+ */
+static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	unsigned int total_bytes = 0, total_packets = 0;
+	unsigned int budget = q_vector->tx.work_limit;
+	struct igc_ring *tx_ring = q_vector->tx.ring;
+	unsigned int i = tx_ring->next_to_clean;
+	struct igc_tx_buffer *tx_buffer;
+	union igc_adv_tx_desc *tx_desc;
+
+	if (test_bit(__IGC_DOWN, &adapter->state))
+		return true;
+
+	tx_buffer = &tx_ring->tx_buffer_info[i];
+	tx_desc = IGC_TX_DESC(tx_ring, i);
+	i -= tx_ring->count;
+
+	do {
+		union igc_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(IGC_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;
+
+		/* free the skb */
+		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);
+
+		/* clear last DMA location and 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 = IGC_TX_DESC(tx_ring, 0);
+			}
+
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len)) {
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+				dma_unmap_len_set(tx_buffer, len, 0);
+			}
+		}
+
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		tx_desc++;
+		i++;
+		if (unlikely(!i)) {
+			i -= tx_ring->count;
+			tx_buffer = tx_ring->tx_buffer_info;
+			tx_desc = IGC_TX_DESC(tx_ring, 0);
+		}
+
+		/* issue prefetch for next Tx descriptor */
+		prefetch(tx_desc);
+
+		/* update budget accounting */
+		budget--;
+	} while (likely(budget));
+
+	netdev_tx_completed_queue(txring_txq(tx_ring),
+				  total_packets, total_bytes);
+
+	i += tx_ring->count;
+	tx_ring->next_to_clean = i;
+	u64_stats_update_begin(&tx_ring->tx_syncp);
+	tx_ring->tx_stats.bytes += total_bytes;
+	tx_ring->tx_stats.packets += total_packets;
+	u64_stats_update_end(&tx_ring->tx_syncp);
+	q_vector->tx.total_bytes += total_bytes;
+	q_vector->tx.total_packets += total_packets;
+
+	if (test_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
+		struct igc_hw *hw = &adapter->hw;
+
+		/* Detect a transmit hang in hardware, this serializes the
+		 * check with the clearing of time_stamp and movement of i
+		 */
+		clear_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags);
+		if (tx_buffer->next_to_watch &&
+		    time_after(jiffies, tx_buffer->time_stamp +
+		    (adapter->tx_timeout_factor * HZ)) &&
+		    !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) {
+			/* detected Tx unit hang */
+			dev_err(tx_ring->dev,
+				"Detected Tx Unit Hang\n"
+				"  Tx Queue             <%d>\n"
+				"  TDH                  <%x>\n"
+				"  TDT                  <%x>\n"
+				"  next_to_use          <%x>\n"
+				"  next_to_clean        <%x>\n"
+				"buffer_info[next_to_clean]\n"
+				"  time_stamp           <%lx>\n"
+				"  next_to_watch        <%p>\n"
+				"  jiffies              <%lx>\n"
+				"  desc.status          <%x>\n",
+				tx_ring->queue_index,
+				rd32(IGC_TDH(tx_ring->reg_idx)),
+				readl(tx_ring->tail),
+				tx_ring->next_to_use,
+				tx_ring->next_to_clean,
+				tx_buffer->time_stamp,
+				tx_buffer->next_to_watch,
+				jiffies,
+				tx_buffer->next_to_watch->wb.status);
+				netif_stop_subqueue(tx_ring->netdev,
+						    tx_ring->queue_index);
+
+			/* we are about to reset, no point in enabling stuff */
+			return true;
+		}
+	}
+
+#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
+	if (unlikely(total_packets &&
+		     netif_carrier_ok(tx_ring->netdev) &&
+		     igc_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) {
+		/* Make sure that anybody stopping the queue after this
+		 * sees the new next_to_clean.
+		 */
+		smp_mb();
+		if (__netif_subqueue_stopped(tx_ring->netdev,
+					     tx_ring->queue_index) &&
+		    !(test_bit(__IGC_DOWN, &adapter->state))) {
+			netif_wake_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
+
+			u64_stats_update_begin(&tx_ring->tx_syncp);
+			tx_ring->tx_stats.restart_queue++;
+			u64_stats_update_end(&tx_ring->tx_syncp);
+		}
+	}
+
+	return !!budget;
+}
+
+/**
+ * igc_ioctl - I/O control method
+ * @netdev: network interface device structure
+ * @ifreq: frequency
+ * @cmd: command
+ */
+static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	switch (cmd) {
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * igc_up - Open the interface and prepare it to handle traffic
+ * @adapter: board private structure
+ */
+static void igc_up(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int i = 0;
+
+	/* hardware has been reset, we need to reload some things */
+	igc_configure(adapter);
+
+	clear_bit(__IGC_DOWN, &adapter->state);
+
+	for (i = 0; i < adapter->num_q_vectors; i++)
+		napi_enable(&adapter->q_vector[i]->napi);
+
+	if (adapter->msix_entries)
+		igc_configure_msix(adapter);
+	else
+		igc_assign_vector(adapter->q_vector[0], 0);
+
+	/* Clear any pending interrupts. */
+	rd32(IGC_ICR);
+	igc_irq_enable(adapter);
+
+	netif_tx_start_all_queues(adapter->netdev);
+
+	/* start the watchdog. */
+	hw->mac.get_link_status = 1;
+	schedule_work(&adapter->watchdog_task);
+}
+
+/**
+ * igc_update_stats - Update the board statistics counters
+ * @adapter: board private structure
+ */
+static void igc_update_stats(struct igc_adapter *adapter)
+{
+}
+
+static void igc_nfc_filter_exit(struct igc_adapter *adapter)
+{
+}
+
+/**
+ * igc_down - Close the interface
+ * @adapter: board private structure
+ */
+static void igc_down(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct igc_hw *hw = &adapter->hw;
+	u32 tctl, rctl;
+	int i = 0;
+
+	set_bit(__IGC_DOWN, &adapter->state);
+
+	/* disable receives in the hardware */
+	rctl = rd32(IGC_RCTL);
+	wr32(IGC_RCTL, rctl & ~IGC_RCTL_EN);
+	/* flush and sleep below */
+
+	igc_nfc_filter_exit(adapter);
+
+	/* set trans_start so we don't get spurious watchdogs during reset */
+	netif_trans_update(netdev);
+
+	netif_carrier_off(netdev);
+	netif_tx_stop_all_queues(netdev);
+
+	/* disable transmits in the hardware */
+	tctl = rd32(IGC_TCTL);
+	tctl &= ~IGC_TCTL_EN;
+	wr32(IGC_TCTL, tctl);
+	/* flush both disables and wait for them to finish */
+	wrfl();
+	usleep_range(10000, 20000);
+
+	igc_irq_disable(adapter);
+
+	adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		if (adapter->q_vector[i]) {
+			napi_synchronize(&adapter->q_vector[i]->napi);
+			napi_disable(&adapter->q_vector[i]->napi);
+		}
+	}
+
+	del_timer_sync(&adapter->watchdog_timer);
+	del_timer_sync(&adapter->phy_info_timer);
+
+	/* record the stats before reset*/
+	spin_lock(&adapter->stats64_lock);
+	igc_update_stats(adapter);
+	spin_unlock(&adapter->stats64_lock);
+
+	adapter->link_speed = 0;
+	adapter->link_duplex = 0;
+
+	if (!pci_channel_offline(adapter->pdev))
+		igc_reset(adapter);
+
+	/* clear VLAN promisc flag so VFTA will be updated if necessary */
+	adapter->flags &= ~IGC_FLAG_VLAN_PROMISC;
+
+	igc_clean_all_tx_rings(adapter);
+	igc_clean_all_rx_rings(adapter);
+}
+
+static void igc_reinit_locked(struct igc_adapter *adapter)
+{
+	WARN_ON(in_interrupt());
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+	igc_down(adapter);
+	igc_up(adapter);
+	clear_bit(__IGC_RESETTING, &adapter->state);
+}
+
+static void igc_reset_task(struct work_struct *work)
+{
+	struct igc_adapter *adapter;
+
+	adapter = container_of(work, struct igc_adapter, reset_task);
+
+	netdev_err(adapter->netdev, "Reset adapter\n");
+	igc_reinit_locked(adapter);
+}
+
+/**
+ * igc_change_mtu - Change the Maximum Transfer Unit
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int igc_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct pci_dev *pdev = adapter->pdev;
+
+	/* adjust max frame to be at least the size of a standard frame */
+	if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
+		max_frame = ETH_FRAME_LEN + ETH_FCS_LEN;
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	/* igc_down has a dependency on max_frame_size */
+	adapter->max_frame_size = max_frame;
+
+	if (netif_running(netdev))
+		igc_down(adapter);
+
+	dev_info(&pdev->dev, "changing MTU from %d to %d\n",
+		 netdev->mtu, new_mtu);
+	netdev->mtu = new_mtu;
+
+	if (netif_running(netdev))
+		igc_up(adapter);
+	else
+		igc_reset(adapter);
+
+	clear_bit(__IGC_RESETTING, &adapter->state);
+
+	return 0;
+}
+
+/**
+ * igc_get_stats - Get System Network Statistics
+ * @netdev: network interface device structure
+ *
+ * Returns the address of the device statistics structure.
+ * The statistics are updated here and also from the timer callback.
+ */
+static struct net_device_stats *igc_get_stats(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (!test_bit(__IGC_RESETTING, &adapter->state))
+		igc_update_stats(adapter);
+
+	/* only return the current stats */
+	return &netdev->stats;
+}
+
+/**
+ * igc_configure - configure the hardware for RX and TX
+ * @adapter: private board structure
+ */
+static void igc_configure(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int i = 0;
+
+	igc_get_hw_control(adapter);
+	igc_set_rx_mode(netdev);
+
+	igc_setup_tctl(adapter);
+	igc_setup_mrqc(adapter);
+	igc_setup_rctl(adapter);
+
+	igc_configure_tx(adapter);
+	igc_configure_rx(adapter);
+
+	igc_rx_fifo_flush_base(&adapter->hw);
+
+	/* call igc_desc_unused which always leaves
+	 * at least 1 descriptor unused to make sure
+	 * next_to_use != next_to_clean
+	 */
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igc_ring *ring = adapter->rx_ring[i];
+
+		igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
+	}
+}
+
+/**
+ * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
+ * @adapter: Pointer to adapter structure
+ * @index: Index of the RAR entry which need to be synced with MAC table
+ */
+static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
+{
+	u8 *addr = adapter->mac_table[index].addr;
+	struct igc_hw *hw = &adapter->hw;
+	u32 rar_low, rar_high;
+
+	/* HW expects these to be in network order when they are plugged
+	 * into the registers which are little endian.  In order to guarantee
+	 * that ordering we need to do an leXX_to_cpup here in order to be
+	 * ready for the byteswap that occurs with writel
+	 */
+	rar_low = le32_to_cpup((__le32 *)(addr));
+	rar_high = le16_to_cpup((__le16 *)(addr + 4));
+
+	/* Indicate to hardware the Address is Valid. */
+	if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
+		if (is_valid_ether_addr(addr))
+			rar_high |= IGC_RAH_AV;
+
+		rar_high |= IGC_RAH_POOL_1 <<
+			adapter->mac_table[index].queue;
+	}
+
+	wr32(IGC_RAL(index), rar_low);
+	wrfl();
+	wr32(IGC_RAH(index), rar_high);
+	wrfl();
+}
+
+/* Set default MAC address for the PF in the first RAR entry */
+static void igc_set_default_mac_filter(struct igc_adapter *adapter)
+{
+	struct igc_mac_addr *mac_table = &adapter->mac_table[0];
+
+	ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
+	mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+
+	igc_rar_set_index(adapter, 0);
+}
+
+/**
+ * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
+ * @netdev: network interface device structure
+ *
+ * The set_rx_mode entry point is called whenever the unicast or multicast
+ * address lists or the network interface flags are updated.  This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
+ * promiscuous mode, and all-multi behavior.
+ */
+static void igc_set_rx_mode(struct net_device *netdev)
+{
+}
+
+/**
+ * igc_msix_other - msix other interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t igc_msix_other(int irq, void *data)
+{
+	struct igc_adapter *adapter = data;
+	struct igc_hw *hw = &adapter->hw;
+	u32 icr = rd32(IGC_ICR);
+
+	/* reading ICR causes bit 31 of EICR to be cleared */
+	if (icr & IGC_ICR_DRSTA)
+		schedule_work(&adapter->reset_task);
+
+	if (icr & IGC_ICR_DOUTSYNC) {
+		/* HW is reporting DMA is out of sync */
+		adapter->stats.doosync++;
+	}
+
+	if (icr & IGC_ICR_LSC) {
+		hw->mac.get_link_status = 1;
+		/* guard against interrupt when we're going down */
+		if (!test_bit(__IGC_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
+
+	wr32(IGC_EIMS, adapter->eims_other);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * igc_write_ivar - configure ivar for given MSI-X vector
+ * @hw: pointer to the HW structure
+ * @msix_vector: vector number we are allocating to a given ring
+ * @index: row index of IVAR register to write within IVAR table
+ * @offset: column offset of in IVAR, should be multiple of 8
+ *
+ * The IVAR table consists of 2 columns,
+ * each containing an cause allocation for an Rx and Tx ring, and a
+ * variable number of rows depending on the number of queues supported.
+ */
+static void igc_write_ivar(struct igc_hw *hw, int msix_vector,
+			   int index, int offset)
+{
+	u32 ivar = array_rd32(IGC_IVAR0, index);
+
+	/* clear any bits that are currently set */
+	ivar &= ~((u32)0xFF << offset);
+
+	/* write vector and valid bit */
+	ivar |= (msix_vector | IGC_IVAR_VALID) << offset;
+
+	array_wr32(IGC_IVAR0, index, ivar);
+}
+
+static void igc_assign_vector(struct igc_q_vector *q_vector, int msix_vector)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	struct igc_hw *hw = &adapter->hw;
+	int rx_queue = IGC_N0_QUEUE;
+	int tx_queue = IGC_N0_QUEUE;
+
+	if (q_vector->rx.ring)
+		rx_queue = q_vector->rx.ring->reg_idx;
+	if (q_vector->tx.ring)
+		tx_queue = q_vector->tx.ring->reg_idx;
+
+	switch (hw->mac.type) {
+	case igc_i225:
+		if (rx_queue > IGC_N0_QUEUE)
+			igc_write_ivar(hw, msix_vector,
+				       rx_queue >> 1,
+				       (rx_queue & 0x1) << 4);
+		if (tx_queue > IGC_N0_QUEUE)
+			igc_write_ivar(hw, msix_vector,
+				       tx_queue >> 1,
+				       ((tx_queue & 0x1) << 4) + 8);
+		q_vector->eims_value = BIT(msix_vector);
+		break;
+	default:
+		WARN_ONCE(hw->mac.type != igc_i225, "Wrong MAC type\n");
+		break;
+	}
+
+	/* add q_vector eims value to global eims_enable_mask */
+	adapter->eims_enable_mask |= q_vector->eims_value;
+
+	/* configure q_vector to set itr on first interrupt */
+	q_vector->set_itr = 1;
+}
+
+/**
+ * igc_configure_msix - Configure MSI-X hardware
+ * @adapter: Pointer to adapter structure
+ *
+ * igc_configure_msix sets up the hardware to properly
+ * generate MSI-X interrupts.
+ */
+static void igc_configure_msix(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int i, vector = 0;
+	u32 tmp;
+
+	adapter->eims_enable_mask = 0;
+
+	/* set vector for other causes, i.e. link changes */
+	switch (hw->mac.type) {
+	case igc_i225:
+		/* Turn on MSI-X capability first, or our settings
+		 * won't stick.  And it will take days to debug.
+		 */
+		wr32(IGC_GPIE, IGC_GPIE_MSIX_MODE |
+		     IGC_GPIE_PBA | IGC_GPIE_EIAME |
+		     IGC_GPIE_NSICR);
+
+		/* enable msix_other interrupt */
+		adapter->eims_other = BIT(vector);
+		tmp = (vector++ | IGC_IVAR_VALID) << 8;
+
+		wr32(IGC_IVAR_MISC, tmp);
+		break;
+	default:
+		/* do nothing, since nothing else supports MSI-X */
+		break;
+	} /* switch (hw->mac.type) */
+
+	adapter->eims_enable_mask |= adapter->eims_other;
+
+	for (i = 0; i < adapter->num_q_vectors; i++)
+		igc_assign_vector(adapter->q_vector[i], vector++);
+
+	wrfl();
+}
+
+static irqreturn_t igc_msix_ring(int irq, void *data)
+{
+	struct igc_q_vector *q_vector = data;
+
+	/* Write the ITR value calculated from the previous interrupt. */
+	igc_write_itr(q_vector);
+
+	napi_schedule(&q_vector->napi);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * igc_request_msix - Initialize MSI-X interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * igc_request_msix allocates MSI-X vectors and requests interrupts from the
+ * kernel.
+ */
+static int igc_request_msix(struct igc_adapter *adapter)
+{
+	int i = 0, err = 0, vector = 0, free_vector = 0;
+	struct net_device *netdev = adapter->netdev;
+
+	err = request_irq(adapter->msix_entries[vector].vector,
+			  &igc_msix_other, 0, netdev->name, adapter);
+	if (err)
+		goto err_out;
+
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		struct igc_q_vector *q_vector = adapter->q_vector[i];
+
+		vector++;
+
+		q_vector->itr_register = adapter->io_addr + IGC_EITR(vector);
+
+		if (q_vector->rx.ring && q_vector->tx.ring)
+			sprintf(q_vector->name, "%s-TxRx-%u", netdev->name,
+				q_vector->rx.ring->queue_index);
+		else if (q_vector->tx.ring)
+			sprintf(q_vector->name, "%s-tx-%u", netdev->name,
+				q_vector->tx.ring->queue_index);
+		else if (q_vector->rx.ring)
+			sprintf(q_vector->name, "%s-rx-%u", netdev->name,
+				q_vector->rx.ring->queue_index);
+		else
+			sprintf(q_vector->name, "%s-unused", netdev->name);
+
+		err = request_irq(adapter->msix_entries[vector].vector,
+				  igc_msix_ring, 0, q_vector->name,
+				  q_vector);
+		if (err)
+			goto err_free;
+	}
+
+	igc_configure_msix(adapter);
+	return 0;
+
+err_free:
+	/* free already assigned IRQs */
+	free_irq(adapter->msix_entries[free_vector++].vector, adapter);
+
+	vector--;
+	for (i = 0; i < vector; i++) {
+		free_irq(adapter->msix_entries[free_vector++].vector,
+			 adapter->q_vector[i]);
+	}
+err_out:
+	return err;
+}
+
+/**
+ * igc_reset_q_vector - Reset config for interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be reset
+ *
+ * If NAPI is enabled it will delete any references to the
+ * NAPI struct. This is preparation for igc_free_q_vector.
+ */
+static void igc_reset_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+	/* if we're coming from igc_set_interrupt_capability, the vectors are
+	 * not yet allocated
+	 */
+	if (!q_vector)
+		return;
+
+	if (q_vector->tx.ring)
+		adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
+
+	if (q_vector->rx.ring)
+		adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
+
+	netif_napi_del(&q_vector->napi);
+}
+
+static void igc_reset_interrupt_capability(struct igc_adapter *adapter)
+{
+	int v_idx = adapter->num_q_vectors;
+
+	if (adapter->msix_entries) {
+		pci_disable_msix(adapter->pdev);
+		kfree(adapter->msix_entries);
+		adapter->msix_entries = NULL;
+	} else if (adapter->flags & IGC_FLAG_HAS_MSI) {
+		pci_disable_msi(adapter->pdev);
+	}
+
+	while (v_idx--)
+		igc_reset_q_vector(adapter, v_idx);
+}
+
+/**
+ * igc_clear_interrupt_scheme - reset the device to a state of no interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * This function resets the device so that it has 0 rx queues, tx queues, and
+ * MSI-X interrupts allocated.
+ */
+static void igc_clear_interrupt_scheme(struct igc_adapter *adapter)
+{
+	igc_free_q_vectors(adapter);
+	igc_reset_interrupt_capability(adapter);
+}
+
+/**
+ * igc_free_q_vectors - Free memory allocated for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function frees the memory allocated to the q_vectors.  In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ */
+static void igc_free_q_vectors(struct igc_adapter *adapter)
+{
+	int v_idx = adapter->num_q_vectors;
+
+	adapter->num_tx_queues = 0;
+	adapter->num_rx_queues = 0;
+	adapter->num_q_vectors = 0;
+
+	while (v_idx--) {
+		igc_reset_q_vector(adapter, v_idx);
+		igc_free_q_vector(adapter, v_idx);
+	}
+}
+
+/**
+ * igc_free_q_vector - Free memory allocated for specific interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_idx: Index of vector to be freed
+ *
+ * This function frees the memory allocated to the q_vector.
+ */
+static void igc_free_q_vector(struct igc_adapter *adapter, int v_idx)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[v_idx];
+
+	adapter->q_vector[v_idx] = NULL;
+
+	/* igc_get_stats64() might access the rings on this vector,
+	 * we must wait a grace period before freeing it.
+	 */
+	if (q_vector)
+		kfree_rcu(q_vector, rcu);
+}
+
+/* Need to wait a few seconds after link up to get diagnostic information from
+ * the phy
+ */
+static void igc_update_phy_info(struct timer_list *t)
+{
+	struct igc_adapter *adapter = from_timer(adapter, t, phy_info_timer);
+
+	igc_get_phy_info(&adapter->hw);
+}
+
+/**
+ * igc_has_link - check shared code for link and determine up/down
+ * @adapter: pointer to driver private info
+ */
+static bool igc_has_link(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	bool link_active = false;
+
+	/* get_link_status is set on LSC (link status) interrupt or
+	 * rx sequence error interrupt.  get_link_status will stay
+	 * false until the igc_check_for_link establishes link
+	 * for copper adapters ONLY
+	 */
+	switch (hw->phy.media_type) {
+	case igc_media_type_copper:
+		if (!hw->mac.get_link_status)
+			return true;
+		hw->mac.ops.check_for_link(hw);
+		link_active = !hw->mac.get_link_status;
+		break;
+	default:
+	case igc_media_type_unknown:
+		break;
+	}
+
+	if (hw->mac.type == igc_i225 &&
+	    hw->phy.id == I225_I_PHY_ID) {
+		if (!netif_carrier_ok(adapter->netdev)) {
+			adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+		} else if (!(adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)) {
+			adapter->flags |= IGC_FLAG_NEED_LINK_UPDATE;
+			adapter->link_check_timeout = jiffies;
+		}
+	}
+
+	return link_active;
+}
+
+/**
+ * igc_watchdog - Timer Call-back
+ * @data: pointer to adapter cast into an unsigned long
+ */
+static void igc_watchdog(struct timer_list *t)
+{
+	struct igc_adapter *adapter = from_timer(adapter, t, watchdog_timer);
+	/* Do the rest outside of interrupt context */
+	schedule_work(&adapter->watchdog_task);
+}
+
+static void igc_watchdog_task(struct work_struct *work)
+{
+	struct igc_adapter *adapter = container_of(work,
+						   struct igc_adapter,
+						   watchdog_task);
+	struct net_device *netdev = adapter->netdev;
+	struct igc_hw *hw = &adapter->hw;
+	struct igc_phy_info *phy = &hw->phy;
+	u16 phy_data, retry_count = 20;
+	u32 connsw;
+	u32 link;
+	int i;
+
+	link = igc_has_link(adapter);
+
+	if (adapter->flags & IGC_FLAG_NEED_LINK_UPDATE) {
+		if (time_after(jiffies, (adapter->link_check_timeout + HZ)))
+			adapter->flags &= ~IGC_FLAG_NEED_LINK_UPDATE;
+		else
+			link = false;
+	}
+
+	/* Force link down if we have fiber to swap to */
+	if (adapter->flags & IGC_FLAG_MAS_ENABLE) {
+		if (hw->phy.media_type == igc_media_type_copper) {
+			connsw = rd32(IGC_CONNSW);
+			if (!(connsw & IGC_CONNSW_AUTOSENSE_EN))
+				link = 0;
+		}
+	}
+	if (link) {
+		if (!netif_carrier_ok(netdev)) {
+			u32 ctrl;
+
+			hw->mac.ops.get_speed_and_duplex(hw,
+							 &adapter->link_speed,
+							 &adapter->link_duplex);
+
+			ctrl = rd32(IGC_CTRL);
+			/* Link status message must follow this format */
+			netdev_info(netdev,
+				    "igc: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
+				    netdev->name,
+				    adapter->link_speed,
+				    adapter->link_duplex == FULL_DUPLEX ?
+				    "Full" : "Half",
+				    (ctrl & IGC_CTRL_TFCE) &&
+				    (ctrl & IGC_CTRL_RFCE) ? "RX/TX" :
+				    (ctrl & IGC_CTRL_RFCE) ?  "RX" :
+				    (ctrl & IGC_CTRL_TFCE) ?  "TX" : "None");
+
+			/* check if SmartSpeed worked */
+			igc_check_downshift(hw);
+			if (phy->speed_downgraded)
+				netdev_warn(netdev, "Link Speed was downgraded by SmartSpeed\n");
+
+			/* adjust timeout factor according to speed/duplex */
+			adapter->tx_timeout_factor = 1;
+			switch (adapter->link_speed) {
+			case SPEED_10:
+				adapter->tx_timeout_factor = 14;
+				break;
+			case SPEED_100:
+				/* maybe add some timeout factor ? */
+				break;
+			}
+
+			if (adapter->link_speed != SPEED_1000)
+				goto no_wait;
+
+			/* wait for Remote receiver status OK */
+retry_read_status:
+			if (!igc_read_phy_reg(hw, PHY_1000T_STATUS,
+					      &phy_data)) {
+				if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) &&
+				    retry_count) {
+					msleep(100);
+					retry_count--;
+					goto retry_read_status;
+				} else if (!retry_count) {
+					dev_err(&adapter->pdev->dev, "exceed max 2 second\n");
+				}
+			} else {
+				dev_err(&adapter->pdev->dev, "read 1000Base-T Status Reg\n");
+			}
+no_wait:
+			netif_carrier_on(netdev);
+
+			/* link state has changed, schedule phy info update */
+			if (!test_bit(__IGC_DOWN, &adapter->state))
+				mod_timer(&adapter->phy_info_timer,
+					  round_jiffies(jiffies + 2 * HZ));
+		}
+	} else {
+		if (netif_carrier_ok(netdev)) {
+			adapter->link_speed = 0;
+			adapter->link_duplex = 0;
+
+			/* Links status message must follow this format */
+			netdev_info(netdev, "igc: %s NIC Link is Down\n",
+				    netdev->name);
+			netif_carrier_off(netdev);
+
+			/* link state has changed, schedule phy info update */
+			if (!test_bit(__IGC_DOWN, &adapter->state))
+				mod_timer(&adapter->phy_info_timer,
+					  round_jiffies(jiffies + 2 * HZ));
+
+			/* link is down, time to check for alternate media */
+			if (adapter->flags & IGC_FLAG_MAS_ENABLE) {
+				if (adapter->flags & IGC_FLAG_MEDIA_RESET) {
+					schedule_work(&adapter->reset_task);
+					/* return immediately */
+					return;
+				}
+			}
+
+		/* also check for alternate media here */
+		} else if (!netif_carrier_ok(netdev) &&
+			   (adapter->flags & IGC_FLAG_MAS_ENABLE)) {
+			if (adapter->flags & IGC_FLAG_MEDIA_RESET) {
+				schedule_work(&adapter->reset_task);
+				/* return immediately */
+				return;
+			}
+		}
+	}
+
+	spin_lock(&adapter->stats64_lock);
+	igc_update_stats(adapter);
+	spin_unlock(&adapter->stats64_lock);
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		if (!netif_carrier_ok(netdev)) {
+			/* We've lost link, so the controller stops DMA,
+			 * but we've got queued Tx work that's never going
+			 * to get done, so reset controller to flush Tx.
+			 * (Do the reset outside of interrupt context).
+			 */
+			if (igc_desc_unused(tx_ring) + 1 < tx_ring->count) {
+				adapter->tx_timeout_count++;
+				schedule_work(&adapter->reset_task);
+				/* return immediately since reset is imminent */
+				return;
+			}
+		}
+
+		/* Force detection of hung controller every watchdog period */
+		set_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags);
+	}
+
+	/* Cause software interrupt to ensure Rx ring is cleaned */
+	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+		u32 eics = 0;
+
+		for (i = 0; i < adapter->num_q_vectors; i++)
+			eics |= adapter->q_vector[i]->eims_value;
+		wr32(IGC_EICS, eics);
+	} else {
+		wr32(IGC_ICS, IGC_ICS_RXDMT0);
+	}
+
+	/* Reset the timer */
+	if (!test_bit(__IGC_DOWN, &adapter->state)) {
+		if (adapter->flags & IGC_FLAG_NEED_LINK_UPDATE)
+			mod_timer(&adapter->watchdog_timer,
+				  round_jiffies(jiffies +  HZ));
+		else
+			mod_timer(&adapter->watchdog_timer,
+				  round_jiffies(jiffies + 2 * HZ));
+	}
+}
+
+/**
+ * igc_update_ring_itr - update the dynamic ITR value based on packet size
+ * @q_vector: pointer to q_vector
+ *
+ * Stores a new ITR value based on strictly on packet size.  This
+ * algorithm is less sophisticated than that used in igc_update_itr,
+ * due to the difficulty of synchronizing statistics across multiple
+ * receive rings.  The divisors and thresholds used by this function
+ * were determined based on theoretical maximum wire speed and testing
+ * data, in order to minimize response time while increasing bulk
+ * throughput.
+ * NOTE: This function is called only when operating in a multiqueue
+ * receive environment.
+ */
+static void igc_update_ring_itr(struct igc_q_vector *q_vector)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	int new_val = q_vector->itr_val;
+	int avg_wire_size = 0;
+	unsigned int packets;
+
+	/* For non-gigabit speeds, just fix the interrupt rate at 4000
+	 * ints/sec - ITR timer value of 120 ticks.
+	 */
+	switch (adapter->link_speed) {
+	case SPEED_10:
+	case SPEED_100:
+		new_val = IGC_4K_ITR;
+		goto set_itr_val;
+	default:
+		break;
+	}
+
+	packets = q_vector->rx.total_packets;
+	if (packets)
+		avg_wire_size = q_vector->rx.total_bytes / packets;
+
+	packets = q_vector->tx.total_packets;
+	if (packets)
+		avg_wire_size = max_t(u32, avg_wire_size,
+				      q_vector->tx.total_bytes / packets);
+
+	/* if avg_wire_size isn't set no work was done */
+	if (!avg_wire_size)
+		goto clear_counts;
+
+	/* Add 24 bytes to size to account for CRC, preamble, and gap */
+	avg_wire_size += 24;
+
+	/* Don't starve jumbo frames */
+	avg_wire_size = min(avg_wire_size, 3000);
+
+	/* Give a little boost to mid-size frames */
+	if (avg_wire_size > 300 && avg_wire_size < 1200)
+		new_val = avg_wire_size / 3;
+	else
+		new_val = avg_wire_size / 2;
+
+	/* conservative mode (itr 3) eliminates the lowest_latency setting */
+	if (new_val < IGC_20K_ITR &&
+	    ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+	    (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+		new_val = IGC_20K_ITR;
+
+set_itr_val:
+	if (new_val != q_vector->itr_val) {
+		q_vector->itr_val = new_val;
+		q_vector->set_itr = 1;
+	}
+clear_counts:
+	q_vector->rx.total_bytes = 0;
+	q_vector->rx.total_packets = 0;
+	q_vector->tx.total_bytes = 0;
+	q_vector->tx.total_packets = 0;
+}
+
+/**
+ * igc_update_itr - update the dynamic ITR value based on statistics
+ * @q_vector: pointer to q_vector
+ * @ring_container: ring info to update the itr for
+ *
+ * Stores a new ITR value based on packets and byte
+ * counts during the last interrupt.  The advantage of per interrupt
+ * computation is faster updates and more accurate ITR for the current
+ * traffic pattern.  Constants in this function were computed
+ * based on theoretical maximum wire speed and thresholds were set based
+ * on testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ * NOTE: These calculations are only valid when operating in a single-
+ * queue environment.
+ */
+static void igc_update_itr(struct igc_q_vector *q_vector,
+			   struct igc_ring_container *ring_container)
+{
+	unsigned int packets = ring_container->total_packets;
+	unsigned int bytes = ring_container->total_bytes;
+	u8 itrval = ring_container->itr;
+
+	/* no packets, exit with status unchanged */
+	if (packets == 0)
+		return;
+
+	switch (itrval) {
+	case lowest_latency:
+		/* handle TSO and jumbo frames */
+		if (bytes / packets > 8000)
+			itrval = bulk_latency;
+		else if ((packets < 5) && (bytes > 512))
+			itrval = low_latency;
+		break;
+	case low_latency:  /* 50 usec aka 20000 ints/s */
+		if (bytes > 10000) {
+			/* this if handles the TSO accounting */
+			if (bytes / packets > 8000)
+				itrval = bulk_latency;
+			else if ((packets < 10) || ((bytes / packets) > 1200))
+				itrval = bulk_latency;
+			else if ((packets > 35))
+				itrval = lowest_latency;
+		} else if (bytes / packets > 2000) {
+			itrval = bulk_latency;
+		} else if (packets <= 2 && bytes < 512) {
+			itrval = lowest_latency;
+		}
+		break;
+	case bulk_latency: /* 250 usec aka 4000 ints/s */
+		if (bytes > 25000) {
+			if (packets > 35)
+				itrval = low_latency;
+		} else if (bytes < 1500) {
+			itrval = low_latency;
+		}
+		break;
+	}
+
+	/* clear work counters since we have the values we need */
+	ring_container->total_bytes = 0;
+	ring_container->total_packets = 0;
+
+	/* write updated itr to ring container */
+	ring_container->itr = itrval;
+}
+
+/**
+ * igc_intr_msi - Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a network interface device structure
+ */
+static irqreturn_t igc_intr_msi(int irq, void *data)
+{
+	struct igc_adapter *adapter = data;
+	struct igc_q_vector *q_vector = adapter->q_vector[0];
+	struct igc_hw *hw = &adapter->hw;
+	/* read ICR disables interrupts using IAM */
+	u32 icr = rd32(IGC_ICR);
+
+	igc_write_itr(q_vector);
+
+	if (icr & IGC_ICR_DRSTA)
+		schedule_work(&adapter->reset_task);
+
+	if (icr & IGC_ICR_DOUTSYNC) {
+		/* HW is reporting DMA is out of sync */
+		adapter->stats.doosync++;
+	}
+
+	if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) {
+		hw->mac.get_link_status = 1;
+		if (!test_bit(__IGC_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
+
+	napi_schedule(&q_vector->napi);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * igc_intr - Legacy Interrupt Handler
+ * @irq: interrupt number
+ * @data: pointer to a network interface device structure
+ */
+static irqreturn_t igc_intr(int irq, void *data)
+{
+	struct igc_adapter *adapter = data;
+	struct igc_q_vector *q_vector = adapter->q_vector[0];
+	struct igc_hw *hw = &adapter->hw;
+	/* Interrupt Auto-Mask...upon reading ICR, interrupts are masked.  No
+	 * need for the IMC write
+	 */
+	u32 icr = rd32(IGC_ICR);
+
+	/* IMS will not auto-mask if INT_ASSERTED is not set, and if it is
+	 * not set, then the adapter didn't send an interrupt
+	 */
+	if (!(icr & IGC_ICR_INT_ASSERTED))
+		return IRQ_NONE;
+
+	igc_write_itr(q_vector);
+
+	if (icr & IGC_ICR_DRSTA)
+		schedule_work(&adapter->reset_task);
+
+	if (icr & IGC_ICR_DOUTSYNC) {
+		/* HW is reporting DMA is out of sync */
+		adapter->stats.doosync++;
+	}
+
+	if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) {
+		hw->mac.get_link_status = 1;
+		/* guard against interrupt when we're going down */
+		if (!test_bit(__IGC_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
+
+	napi_schedule(&q_vector->napi);
+
+	return IRQ_HANDLED;
+}
+
+static void igc_set_itr(struct igc_q_vector *q_vector)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	u32 new_itr = q_vector->itr_val;
+	u8 current_itr = 0;
+
+	/* for non-gigabit speeds, just fix the interrupt rate at 4000 */
+	switch (adapter->link_speed) {
+	case SPEED_10:
+	case SPEED_100:
+		current_itr = 0;
+		new_itr = IGC_4K_ITR;
+		goto set_itr_now;
+	default:
+		break;
+	}
+
+	igc_update_itr(q_vector, &q_vector->tx);
+	igc_update_itr(q_vector, &q_vector->rx);
+
+	current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
+
+	/* conservative mode (itr 3) eliminates the lowest_latency setting */
+	if (current_itr == lowest_latency &&
+	    ((q_vector->rx.ring && adapter->rx_itr_setting == 3) ||
+	    (!q_vector->rx.ring && adapter->tx_itr_setting == 3)))
+		current_itr = low_latency;
+
+	switch (current_itr) {
+	/* counts and packets in update_itr are dependent on these numbers */
+	case lowest_latency:
+		new_itr = IGC_70K_ITR; /* 70,000 ints/sec */
+		break;
+	case low_latency:
+		new_itr = IGC_20K_ITR; /* 20,000 ints/sec */
+		break;
+	case bulk_latency:
+		new_itr = IGC_4K_ITR;  /* 4,000 ints/sec */
+		break;
+	default:
+		break;
+	}
+
+set_itr_now:
+	if (new_itr != q_vector->itr_val) {
+		/* this attempts to bias the interrupt rate towards Bulk
+		 * by adding intermediate steps when interrupt rate is
+		 * increasing
+		 */
+		new_itr = new_itr > q_vector->itr_val ?
+			  max((new_itr * q_vector->itr_val) /
+			  (new_itr + (q_vector->itr_val >> 2)),
+			  new_itr) : new_itr;
+		/* Don't write the value here; it resets the adapter's
+		 * internal timer, and causes us to delay far longer than
+		 * we should between interrupts.  Instead, we write the ITR
+		 * value at the beginning of the next interrupt so the timing
+		 * ends up being correct.
+		 */
+		q_vector->itr_val = new_itr;
+		q_vector->set_itr = 1;
+	}
+}
+
+static void igc_ring_irq_enable(struct igc_q_vector *q_vector)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	struct igc_hw *hw = &adapter->hw;
+
+	if ((q_vector->rx.ring && (adapter->rx_itr_setting & 3)) ||
+	    (!q_vector->rx.ring && (adapter->tx_itr_setting & 3))) {
+		if (adapter->num_q_vectors == 1)
+			igc_set_itr(q_vector);
+		else
+			igc_update_ring_itr(q_vector);
+	}
+
+	if (!test_bit(__IGC_DOWN, &adapter->state)) {
+		if (adapter->msix_entries)
+			wr32(IGC_EIMS, q_vector->eims_value);
+		else
+			igc_irq_enable(adapter);
+	}
+}
+
+/**
+ * igc_poll - NAPI Rx polling callback
+ * @napi: napi polling structure
+ * @budget: count of how many packets we should handle
+ */
+static int igc_poll(struct napi_struct *napi, int budget)
+{
+	struct igc_q_vector *q_vector = container_of(napi,
+						     struct igc_q_vector,
+						     napi);
+	bool clean_complete = true;
+	int work_done = 0;
+
+	if (q_vector->tx.ring)
+		clean_complete = igc_clean_tx_irq(q_vector, budget);
+
+	if (q_vector->rx.ring) {
+		int cleaned = igc_clean_rx_irq(q_vector, budget);
+
+		work_done += cleaned;
+		if (cleaned >= budget)
+			clean_complete = false;
+	}
+
+	/* If all work not completed, return budget and keep polling */
+	if (!clean_complete)
+		return budget;
+
+	/* If not enough Rx work done, exit the polling mode */
+	napi_complete_done(napi, work_done);
+	igc_ring_irq_enable(q_vector);
+
+	return 0;
+}
+
+/**
+ * igc_set_interrupt_capability - set MSI or MSI-X if supported
+ * @adapter: Pointer to adapter structure
+ *
+ * Attempt to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ */
+static void igc_set_interrupt_capability(struct igc_adapter *adapter,
+					 bool msix)
+{
+	int numvecs, i;
+	int err;
+
+	if (!msix)
+		goto msi_only;
+	adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+	/* Number of supported queues. */
+	adapter->num_rx_queues = adapter->rss_queues;
+
+	adapter->num_tx_queues = adapter->rss_queues;
+
+	/* start with one vector for every Rx queue */
+	numvecs = adapter->num_rx_queues;
+
+	/* if Tx handler is separate add 1 for every Tx queue */
+	if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS))
+		numvecs += adapter->num_tx_queues;
+
+	/* store the number of vectors reserved for queues */
+	adapter->num_q_vectors = numvecs;
+
+	/* add 1 vector for link status interrupts */
+	numvecs++;
+
+	adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry),
+					GFP_KERNEL);
+
+	if (!adapter->msix_entries)
+		return;
+
+	/* populate entry values */
+	for (i = 0; i < numvecs; i++)
+		adapter->msix_entries[i].entry = i;
+
+	err = pci_enable_msix_range(adapter->pdev,
+				    adapter->msix_entries,
+				    numvecs,
+				    numvecs);
+	if (err > 0)
+		return;
+
+	kfree(adapter->msix_entries);
+	adapter->msix_entries = NULL;
+
+	igc_reset_interrupt_capability(adapter);
+
+msi_only:
+	adapter->flags &= ~IGC_FLAG_HAS_MSIX;
+
+	adapter->rss_queues = 1;
+	adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+	adapter->num_rx_queues = 1;
+	adapter->num_tx_queues = 1;
+	adapter->num_q_vectors = 1;
+	if (!pci_enable_msi(adapter->pdev))
+		adapter->flags |= IGC_FLAG_HAS_MSI;
+}
+
+static void igc_add_ring(struct igc_ring *ring,
+			 struct igc_ring_container *head)
+{
+	head->ring = ring;
+	head->count++;
+}
+
+/**
+ * igc_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @adapter: board private structure to initialize
+ * @v_count: q_vectors allocated on adapter, used for ring interleaving
+ * @v_idx: index of vector in adapter struct
+ * @txr_count: total number of Tx rings to allocate
+ * @txr_idx: index of first Tx ring to allocate
+ * @rxr_count: total number of Rx rings to allocate
+ * @rxr_idx: index of first Rx ring to allocate
+ *
+ * We allocate one q_vector.  If allocation fails we return -ENOMEM.
+ */
+static int igc_alloc_q_vector(struct igc_adapter *adapter,
+			      unsigned int v_count, unsigned int v_idx,
+			      unsigned int txr_count, unsigned int txr_idx,
+			      unsigned int rxr_count, unsigned int rxr_idx)
+{
+	struct igc_q_vector *q_vector;
+	struct igc_ring *ring;
+	int ring_count, size;
+
+	/* igc only supports 1 Tx and/or 1 Rx queue per vector */
+	if (txr_count > 1 || rxr_count > 1)
+		return -ENOMEM;
+
+	ring_count = txr_count + rxr_count;
+	size = sizeof(struct igc_q_vector) +
+		(sizeof(struct igc_ring) * ring_count);
+
+	/* allocate q_vector and rings */
+	q_vector = adapter->q_vector[v_idx];
+	if (!q_vector)
+		q_vector = kzalloc(size, GFP_KERNEL);
+	else
+		memset(q_vector, 0, size);
+	if (!q_vector)
+		return -ENOMEM;
+
+	/* initialize NAPI */
+	netif_napi_add(adapter->netdev, &q_vector->napi,
+		       igc_poll, 64);
+
+	/* tie q_vector and adapter together */
+	adapter->q_vector[v_idx] = q_vector;
+	q_vector->adapter = adapter;
+
+	/* initialize work limits */
+	q_vector->tx.work_limit = adapter->tx_work_limit;
+
+	/* initialize ITR configuration */
+	q_vector->itr_register = adapter->io_addr + IGC_EITR(0);
+	q_vector->itr_val = IGC_START_ITR;
+
+	/* initialize pointer to rings */
+	ring = q_vector->ring;
+
+	/* initialize ITR */
+	if (rxr_count) {
+		/* rx or rx/tx vector */
+		if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3)
+			q_vector->itr_val = adapter->rx_itr_setting;
+	} else {
+		/* tx only vector */
+		if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3)
+			q_vector->itr_val = adapter->tx_itr_setting;
+	}
+
+	if (txr_count) {
+		/* assign generic ring traits */
+		ring->dev = &adapter->pdev->dev;
+		ring->netdev = adapter->netdev;
+
+		/* configure backlink on ring */
+		ring->q_vector = q_vector;
+
+		/* update q_vector Tx values */
+		igc_add_ring(ring, &q_vector->tx);
+
+		/* apply Tx specific ring traits */
+		ring->count = adapter->tx_ring_count;
+		ring->queue_index = txr_idx;
+
+		/* assign ring to adapter */
+		adapter->tx_ring[txr_idx] = ring;
+
+		/* push pointer to next ring */
+		ring++;
+	}
+
+	if (rxr_count) {
+		/* assign generic ring traits */
+		ring->dev = &adapter->pdev->dev;
+		ring->netdev = adapter->netdev;
+
+		/* configure backlink on ring */
+		ring->q_vector = q_vector;
+
+		/* update q_vector Rx values */
+		igc_add_ring(ring, &q_vector->rx);
+
+		/* apply Rx specific ring traits */
+		ring->count = adapter->rx_ring_count;
+		ring->queue_index = rxr_idx;
+
+		/* assign ring to adapter */
+		adapter->rx_ring[rxr_idx] = ring;
+	}
+
+	return 0;
+}
+
+/**
+ * igc_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt.  If allocation fails we
+ * return -ENOMEM.
+ */
+static int igc_alloc_q_vectors(struct igc_adapter *adapter)
+{
+	int rxr_remaining = adapter->num_rx_queues;
+	int txr_remaining = adapter->num_tx_queues;
+	int rxr_idx = 0, txr_idx = 0, v_idx = 0;
+	int q_vectors = adapter->num_q_vectors;
+	int err;
+
+	if (q_vectors >= (rxr_remaining + txr_remaining)) {
+		for (; rxr_remaining; v_idx++) {
+			err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+						 0, 0, 1, rxr_idx);
+
+			if (err)
+				goto err_out;
+
+			/* update counts and index */
+			rxr_remaining--;
+			rxr_idx++;
+		}
+	}
+
+	for (; v_idx < q_vectors; v_idx++) {
+		int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
+		int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+
+		err = igc_alloc_q_vector(adapter, q_vectors, v_idx,
+					 tqpv, txr_idx, rqpv, rxr_idx);
+
+		if (err)
+			goto err_out;
+
+		/* update counts and index */
+		rxr_remaining -= rqpv;
+		txr_remaining -= tqpv;
+		rxr_idx++;
+		txr_idx++;
+	}
+
+	return 0;
+
+err_out:
+	adapter->num_tx_queues = 0;
+	adapter->num_rx_queues = 0;
+	adapter->num_q_vectors = 0;
+
+	while (v_idx--)
+		igc_free_q_vector(adapter, v_idx);
+
+	return -ENOMEM;
+}
+
+/**
+ * igc_cache_ring_register - Descriptor ring to register mapping
+ * @adapter: board private structure to initialize
+ *
+ * Once we know the feature-set enabled for the device, we'll cache
+ * the register offset the descriptor ring is assigned to.
+ */
+static void igc_cache_ring_register(struct igc_adapter *adapter)
+{
+	int i = 0, j = 0;
+
+	switch (adapter->hw.mac.type) {
+	case igc_i225:
+	/* Fall through */
+	default:
+		for (; i < adapter->num_rx_queues; i++)
+			adapter->rx_ring[i]->reg_idx = i;
+		for (; j < adapter->num_tx_queues; j++)
+			adapter->tx_ring[j]->reg_idx = j;
+		break;
+	}
+}
+
+/**
+ * igc_init_interrupt_scheme - initialize interrupts, allocate queues/vectors
+ * @adapter: Pointer to adapter structure
+ *
+ * This function initializes the interrupts and allocates all of the queues.
+ */
+static int igc_init_interrupt_scheme(struct igc_adapter *adapter, bool msix)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	int err = 0;
+
+	igc_set_interrupt_capability(adapter, msix);
+
+	err = igc_alloc_q_vectors(adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Unable to allocate memory for vectors\n");
+		goto err_alloc_q_vectors;
+	}
+
+	igc_cache_ring_register(adapter);
+
+	return 0;
+
+err_alloc_q_vectors:
+	igc_reset_interrupt_capability(adapter);
+	return err;
+}
+
+static void igc_free_irq(struct igc_adapter *adapter)
+{
+	if (adapter->msix_entries) {
+		int vector = 0, i;
+
+		free_irq(adapter->msix_entries[vector++].vector, adapter);
+
+		for (i = 0; i < adapter->num_q_vectors; i++)
+			free_irq(adapter->msix_entries[vector++].vector,
+				 adapter->q_vector[i]);
+	} else {
+		free_irq(adapter->pdev->irq, adapter);
+	}
+}
+
+/**
+ * igc_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ */
+static void igc_irq_disable(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+
+	if (adapter->msix_entries) {
+		u32 regval = rd32(IGC_EIAM);
+
+		wr32(IGC_EIAM, regval & ~adapter->eims_enable_mask);
+		wr32(IGC_EIMC, adapter->eims_enable_mask);
+		regval = rd32(IGC_EIAC);
+		wr32(IGC_EIAC, regval & ~adapter->eims_enable_mask);
+	}
+
+	wr32(IGC_IAM, 0);
+	wr32(IGC_IMC, ~0);
+	wrfl();
+
+	if (adapter->msix_entries) {
+		int vector = 0, i;
+
+		synchronize_irq(adapter->msix_entries[vector++].vector);
+
+		for (i = 0; i < adapter->num_q_vectors; i++)
+			synchronize_irq(adapter->msix_entries[vector++].vector);
+	} else {
+		synchronize_irq(adapter->pdev->irq);
+	}
+}
+
+/**
+ * igc_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ */
+static void igc_irq_enable(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+
+	if (adapter->msix_entries) {
+		u32 ims = IGC_IMS_LSC | IGC_IMS_DOUTSYNC | IGC_IMS_DRSTA;
+		u32 regval = rd32(IGC_EIAC);
+
+		wr32(IGC_EIAC, regval | adapter->eims_enable_mask);
+		regval = rd32(IGC_EIAM);
+		wr32(IGC_EIAM, regval | adapter->eims_enable_mask);
+		wr32(IGC_EIMS, adapter->eims_enable_mask);
+		wr32(IGC_IMS, ims);
+	} else {
+		wr32(IGC_IMS, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+		wr32(IGC_IAM, IMS_ENABLE_MASK | IGC_IMS_DRSTA);
+	}
+}
+
+/**
+ * igc_request_irq - initialize interrupts
+ * @adapter: Pointer to adapter structure
+ *
+ * Attempts to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ */
+static int igc_request_irq(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	int err = 0;
+
+	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+		err = igc_request_msix(adapter);
+		if (!err)
+			goto request_done;
+		/* fall back to MSI */
+		igc_free_all_tx_resources(adapter);
+		igc_free_all_rx_resources(adapter);
+
+		igc_clear_interrupt_scheme(adapter);
+		err = igc_init_interrupt_scheme(adapter, false);
+		if (err)
+			goto request_done;
+		igc_setup_all_tx_resources(adapter);
+		igc_setup_all_rx_resources(adapter);
+		igc_configure(adapter);
+	}
+
+	igc_assign_vector(adapter->q_vector[0], 0);
+
+	if (adapter->flags & IGC_FLAG_HAS_MSI) {
+		err = request_irq(pdev->irq, &igc_intr_msi, 0,
+				  netdev->name, adapter);
+		if (!err)
+			goto request_done;
+
+		/* fall back to legacy interrupts */
+		igc_reset_interrupt_capability(adapter);
+		adapter->flags &= ~IGC_FLAG_HAS_MSI;
+	}
+
+	err = request_irq(pdev->irq, &igc_intr, IRQF_SHARED,
+			  netdev->name, adapter);
+
+	if (err)
+		dev_err(&pdev->dev, "Error %d getting interrupt\n",
+			err);
+
+request_done:
+	return err;
+}
+
+static void igc_write_itr(struct igc_q_vector *q_vector)
+{
+	u32 itr_val = q_vector->itr_val & IGC_QVECTOR_MASK;
+
+	if (!q_vector->set_itr)
+		return;
+
+	if (!itr_val)
+		itr_val = IGC_ITR_VAL_MASK;
+
+	itr_val |= IGC_EITR_CNT_IGNR;
+
+	writel(itr_val, q_vector->itr_register);
+	q_vector->set_itr = 0;
+}
+
+/**
+ * igc_open - Called when a network interface is made active
+ * @netdev: network interface device structure
+ *
+ * Returns 0 on success, negative value on failure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP).  At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the watchdog timer is started,
+ * and the stack is notified that the interface is ready.
+ */
+static int __igc_open(struct net_device *netdev, bool resuming)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int err = 0;
+	int i = 0;
+
+	/* disallow open during test */
+
+	if (test_bit(__IGC_TESTING, &adapter->state)) {
+		WARN_ON(resuming);
+		return -EBUSY;
+	}
+
+	netif_carrier_off(netdev);
+
+	/* allocate transmit descriptors */
+	err = igc_setup_all_tx_resources(adapter);
+	if (err)
+		goto err_setup_tx;
+
+	/* allocate receive descriptors */
+	err = igc_setup_all_rx_resources(adapter);
+	if (err)
+		goto err_setup_rx;
+
+	igc_power_up_link(adapter);
+
+	igc_configure(adapter);
+
+	err = igc_request_irq(adapter);
+	if (err)
+		goto err_req_irq;
+
+	/* Notify the stack of the actual queue counts. */
+	netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
+	if (err)
+		goto err_set_queues;
+
+	err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues);
+	if (err)
+		goto err_set_queues;
+
+	clear_bit(__IGC_DOWN, &adapter->state);
+
+	for (i = 0; i < adapter->num_q_vectors; i++)
+		napi_enable(&adapter->q_vector[i]->napi);
+
+	/* Clear any pending interrupts. */
+	rd32(IGC_ICR);
+	igc_irq_enable(adapter);
+
+	netif_tx_start_all_queues(netdev);
+
+	/* start the watchdog. */
+	hw->mac.get_link_status = 1;
+	schedule_work(&adapter->watchdog_task);
+
+	return IGC_SUCCESS;
+
+err_set_queues:
+	igc_free_irq(adapter);
+err_req_irq:
+	igc_release_hw_control(adapter);
+	igc_power_down_link(adapter);
+	igc_free_all_rx_resources(adapter);
+err_setup_rx:
+	igc_free_all_tx_resources(adapter);
+err_setup_tx:
+	igc_reset(adapter);
+
+	return err;
+}
+
+static int igc_open(struct net_device *netdev)
+{
+	return __igc_open(netdev, false);
+}
+
+/**
+ * igc_close - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * Returns 0, this is not allowed to fail
+ *
+ * The close entry point is called when an interface is de-activated
+ * by the OS.  The hardware is still under the driver's control, but
+ * needs to be disabled.  A global MAC reset is issued to stop the
+ * hardware, and all transmit and receive resources are freed.
+ */
+static int __igc_close(struct net_device *netdev, bool suspending)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	WARN_ON(test_bit(__IGC_RESETTING, &adapter->state));
+
+	igc_down(adapter);
+
+	igc_release_hw_control(adapter);
+
+	igc_free_irq(adapter);
+
+	igc_free_all_tx_resources(adapter);
+	igc_free_all_rx_resources(adapter);
+
+	return 0;
+}
+
+static int igc_close(struct net_device *netdev)
+{
+	if (netif_device_present(netdev) || netdev->dismantle)
+		return __igc_close(netdev, false);
+	return 0;
+}
+
+static const struct net_device_ops igc_netdev_ops = {
+	.ndo_open		= igc_open,
+	.ndo_stop		= igc_close,
+	.ndo_start_xmit		= igc_xmit_frame,
+	.ndo_set_mac_address	= igc_set_mac,
+	.ndo_change_mtu		= igc_change_mtu,
+	.ndo_get_stats		= igc_get_stats,
+	.ndo_do_ioctl		= igc_ioctl,
+};
+
+/* PCIe configuration access */
+void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+	struct igc_adapter *adapter = hw->back;
+
+	pci_read_config_word(adapter->pdev, reg, value);
+}
+
+void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+	struct igc_adapter *adapter = hw->back;
+
+	pci_write_config_word(adapter->pdev, reg, *value);
+}
+
+s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+	struct igc_adapter *adapter = hw->back;
+	u16 cap_offset;
+
+	cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
+	if (!cap_offset)
+		return -IGC_ERR_CONFIG;
+
+	pci_read_config_word(adapter->pdev, cap_offset + reg, value);
+
+	return IGC_SUCCESS;
+}
+
+s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
+{
+	struct igc_adapter *adapter = hw->back;
+	u16 cap_offset;
+
+	cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
+	if (!cap_offset)
+		return -IGC_ERR_CONFIG;
+
+	pci_write_config_word(adapter->pdev, cap_offset + reg, *value);
+
+	return IGC_SUCCESS;
+}
+
+u32 igc_rd32(struct igc_hw *hw, u32 reg)
+{
+	struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw);
+	u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
+	u32 value = 0;
+
+	if (IGC_REMOVED(hw_addr))
+		return ~value;
+
+	value = readl(&hw_addr[reg]);
+
+	/* reads should not return all F's */
+	if (!(~value) && (!reg || !(~readl(hw_addr)))) {
+		struct net_device *netdev = igc->netdev;
+
+		hw->hw_addr = NULL;
+		netif_device_detach(netdev);
+		netdev_err(netdev, "PCIe link lost, device now detached\n");
+	}
+
+	return value;
+}
+
+/**
+ * igc_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in igc_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * igc_probe initializes an adapter identified by a pci_dev structure.
+ * The OS initialization, configuring the adapter private structure,
+ * and a hardware reset occur.
+ */
+static int igc_probe(struct pci_dev *pdev,
+		     const struct pci_device_id *ent)
+{
+	struct igc_adapter *adapter;
+	struct net_device *netdev;
+	struct igc_hw *hw;
+	const struct igc_info *ei = igc_info_tbl[ent->driver_data];
+	int err, pci_using_dac;
+
+	err = pci_enable_device_mem(pdev);
+	if (err)
+		return err;
+
+	pci_using_dac = 0;
+	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (!err) {
+		err = dma_set_coherent_mask(&pdev->dev,
+					    DMA_BIT_MASK(64));
+		if (!err)
+			pci_using_dac = 1;
+	} else {
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			err = dma_set_coherent_mask(&pdev->dev,
+						    DMA_BIT_MASK(32));
+			if (err) {
+				IGC_ERR("Wrong DMA configuration, aborting\n");
+				goto err_dma;
+			}
+		}
+	}
+
+	err = pci_request_selected_regions(pdev,
+					   pci_select_bars(pdev,
+							   IORESOURCE_MEM),
+					   igc_driver_name);
+	if (err)
+		goto err_pci_reg;
+
+	pci_enable_pcie_error_reporting(pdev);
+
+	pci_set_master(pdev);
+
+	err = -ENOMEM;
+	netdev = alloc_etherdev_mq(sizeof(struct igc_adapter),
+				   IGC_MAX_TX_QUEUES);
+
+	if (!netdev)
+		goto err_alloc_etherdev;
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+
+	pci_set_drvdata(pdev, netdev);
+	adapter = netdev_priv(netdev);
+	adapter->netdev = netdev;
+	adapter->pdev = pdev;
+	hw = &adapter->hw;
+	hw->back = adapter;
+	adapter->port_num = hw->bus.func;
+	adapter->msg_enable = GENMASK(debug - 1, 0);
+
+	err = pci_save_state(pdev);
+	if (err)
+		goto err_ioremap;
+
+	err = -EIO;
+	adapter->io_addr = ioremap(pci_resource_start(pdev, 0),
+				   pci_resource_len(pdev, 0));
+	if (!adapter->io_addr)
+		goto err_ioremap;
+
+	/* hw->hw_addr can be zeroed, so use adapter->io_addr for unmap */
+	hw->hw_addr = adapter->io_addr;
+
+	netdev->netdev_ops = &igc_netdev_ops;
+
+	netdev->watchdog_timeo = 5 * HZ;
+
+	netdev->mem_start = pci_resource_start(pdev, 0);
+	netdev->mem_end = pci_resource_end(pdev, 0);
+
+	/* PCI config space info */
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	hw->revision_id = pdev->revision;
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+
+	/* Copy the default MAC and PHY function pointers */
+	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
+	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
+
+	/* Initialize skew-specific constants */
+	err = ei->get_invariants(hw);
+	if (err)
+		goto err_sw_init;
+
+	/* setup the private structure */
+	err = igc_sw_init(adapter);
+	if (err)
+		goto err_sw_init;
+
+	/* MTU range: 68 - 9216 */
+	netdev->min_mtu = ETH_MIN_MTU;
+	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
+
+	/* before reading the NVM, reset the controller to put the device in a
+	 * known good starting state
+	 */
+	hw->mac.ops.reset_hw(hw);
+
+	if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) {
+		/* copy the MAC address out of the NVM */
+		if (hw->mac.ops.read_mac_addr(hw))
+			dev_err(&pdev->dev, "NVM Read Error\n");
+	}
+
+	memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len);
+
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
+		dev_err(&pdev->dev, "Invalid MAC Address\n");
+		err = -EIO;
+		goto err_eeprom;
+	}
+
+	/* configure RXPBSIZE and TXPBSIZE */
+	wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT);
+	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+
+	timer_setup(&adapter->watchdog_timer, igc_watchdog, 0);
+	timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0);
+
+	INIT_WORK(&adapter->reset_task, igc_reset_task);
+	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
+
+	/* Initialize link properties that are user-changeable */
+	adapter->fc_autoneg = true;
+	hw->mac.autoneg = true;
+	hw->phy.autoneg_advertised = 0xaf;
+
+	hw->fc.requested_mode = igc_fc_default;
+	hw->fc.current_mode = igc_fc_default;
+
+	/* reset the hardware with the new settings */
+	igc_reset(adapter);
+
+	/* let the f/w know that the h/w is now under the control of the
+	 * driver.
+	 */
+	igc_get_hw_control(adapter);
+
+	strncpy(netdev->name, "eth%d", IFNAMSIZ);
+	err = register_netdev(netdev);
+	if (err)
+		goto err_register;
+
+	 /* carrier off reporting is important to ethtool even BEFORE open */
+	netif_carrier_off(netdev);
+
+	/* Check if Media Autosense is enabled */
+	adapter->ei = *ei;
+
+	/* print pcie link status and MAC address */
+	pcie_print_link_status(pdev);
+	netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr);
+
+	return 0;
+
+err_register:
+	igc_release_hw_control(adapter);
+err_eeprom:
+	if (!igc_check_reset_block(hw))
+		igc_reset_phy(hw);
+err_sw_init:
+	igc_clear_interrupt_scheme(adapter);
+	iounmap(adapter->io_addr);
+err_ioremap:
+	free_netdev(netdev);
+err_alloc_etherdev:
+	pci_release_selected_regions(pdev,
+				     pci_select_bars(pdev, IORESOURCE_MEM));
+err_pci_reg:
+err_dma:
+	pci_disable_device(pdev);
+	return err;
+}
+
+/**
+ * igc_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * igc_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.  This could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ */
+static void igc_remove(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	set_bit(__IGC_DOWN, &adapter->state);
+
+	del_timer_sync(&adapter->watchdog_timer);
+	del_timer_sync(&adapter->phy_info_timer);
+
+	cancel_work_sync(&adapter->reset_task);
+	cancel_work_sync(&adapter->watchdog_task);
+
+	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
+	 * would have already happened in close and is redundant.
+	 */
+	igc_release_hw_control(adapter);
+	unregister_netdev(netdev);
+
+	igc_clear_interrupt_scheme(adapter);
+	pci_iounmap(pdev, adapter->io_addr);
+	pci_release_mem_regions(pdev);
+
+	kfree(adapter->mac_table);
+	kfree(adapter->shadow_vfta);
+	free_netdev(netdev);
+
+	pci_disable_pcie_error_reporting(pdev);
+
+	pci_disable_device(pdev);
+}
+
+static struct pci_driver igc_driver = {
+	.name     = igc_driver_name,
+	.id_table = igc_pci_tbl,
+	.probe    = igc_probe,
+	.remove   = igc_remove,
+};
+
+static void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+				     const u32 max_rss_queues)
+{
+	/* Determine if we need to pair queues. */
+	/* If rss_queues > half of max_rss_queues, pair the queues in
+	 * order to conserve interrupts due to limited supply.
+	 */
+	if (adapter->rss_queues > (max_rss_queues / 2))
+		adapter->flags |= IGC_FLAG_QUEUE_PAIRS;
+	else
+		adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
+}
+
+static unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
+{
+	unsigned int max_rss_queues;
+
+	/* Determine the maximum number of RSS queues supported. */
+	max_rss_queues = IGC_MAX_RX_QUEUES;
+
+	return max_rss_queues;
+}
+
+static void igc_init_queue_configuration(struct igc_adapter *adapter)
+{
+	u32 max_rss_queues;
+
+	max_rss_queues = igc_get_max_rss_queues(adapter);
+	adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
+
+	igc_set_flag_queue_pairs(adapter, max_rss_queues);
+}
+
+/**
+ * igc_sw_init - Initialize general software structures (struct igc_adapter)
+ * @adapter: board private structure to initialize
+ *
+ * igc_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ */
+static int igc_sw_init(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	struct igc_hw *hw = &adapter->hw;
+
+	int size = sizeof(struct igc_mac_addr) * hw->mac.rar_entry_count;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
+
+	/* set default ring sizes */
+	adapter->tx_ring_count = IGC_DEFAULT_TXD;
+	adapter->rx_ring_count = IGC_DEFAULT_RXD;
+
+	/* set default ITR values */
+	adapter->rx_itr_setting = IGC_DEFAULT_ITR;
+	adapter->tx_itr_setting = IGC_DEFAULT_ITR;
+
+	/* set default work limits */
+	adapter->tx_work_limit = IGC_DEFAULT_TX_WORK;
+
+	/* adjust max frame to be at least the size of a standard frame */
+	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
+				VLAN_HLEN;
+	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+
+	spin_lock_init(&adapter->nfc_lock);
+	spin_lock_init(&adapter->stats64_lock);
+	/* Assume MSI-X interrupts, will be checked during IRQ allocation */
+	adapter->flags |= IGC_FLAG_HAS_MSIX;
+
+	adapter->mac_table = kzalloc(size, GFP_ATOMIC);
+	if (!adapter->mac_table)
+		return -ENOMEM;
+
+	igc_init_queue_configuration(adapter);
+
+	/* This call may decrease the number of queues */
+	if (igc_init_interrupt_scheme(adapter, true)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		return -ENOMEM;
+	}
+
+	/* Explicitly disable IRQ since the NIC can be in any state. */
+	igc_irq_disable(adapter);
+
+	set_bit(__IGC_DOWN, &adapter->state);
+
+	return 0;
+}
+
+/**
+ * igc_get_hw_dev - return device
+ * @hw: pointer to hardware structure
+ *
+ * used by hardware layer to print debugging information
+ */
+struct net_device *igc_get_hw_dev(struct igc_hw *hw)
+{
+	struct igc_adapter *adapter = hw->back;
+
+	return adapter->netdev;
+}
+
+/**
+ * igc_init_module - Driver Registration Routine
+ *
+ * igc_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ */
+static int __init igc_init_module(void)
+{
+	int ret;
+
+	pr_info("%s - version %s\n",
+		igc_driver_string, igc_driver_version);
+
+	pr_info("%s\n", igc_copyright);
+
+	ret = pci_register_driver(&igc_driver);
+	return ret;
+}
+
+module_init(igc_init_module);
+
+/**
+ * igc_exit_module - Driver Exit Cleanup Routine
+ *
+ * igc_exit_module is called just before the driver is removed
+ * from memory.
+ */
+static void __exit igc_exit_module(void)
+{
+	pci_unregister_driver(&igc_driver);
+}
+
+module_exit(igc_exit_module);
+/* igc_main.c */

drivers/net/ethernet/intel/igc/igc_nvm.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include "igc_mac.h"
+#include "igc_nvm.h"
+
+/**
+ * igc_poll_eerd_eewr_done - Poll for EEPROM read/write completion
+ * @hw: pointer to the HW structure
+ * @ee_reg: EEPROM flag for polling
+ *
+ * Polls the EEPROM status bit for either read or write completion based
+ * upon the value of 'ee_reg'.
+ */
+static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg)
+{
+	s32 ret_val = -IGC_ERR_NVM;
+	u32 attempts = 100000;
+	u32 i, reg = 0;
+
+	for (i = 0; i < attempts; i++) {
+		if (ee_reg == IGC_NVM_POLL_READ)
+			reg = rd32(IGC_EERD);
+		else
+			reg = rd32(IGC_EEWR);
+
+		if (reg & IGC_NVM_RW_REG_DONE) {
+			ret_val = 0;
+			break;
+		}
+
+		udelay(5);
+	}
+
+	return ret_val;
+}
+
+/**
+ * igc_acquire_nvm - Generic request for access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Set the EEPROM access request bit and wait for EEPROM access grant bit.
+ * Return successful if access grant bit set, else clear the request for
+ * EEPROM access and return -IGC_ERR_NVM (-1).
+ */
+s32 igc_acquire_nvm(struct igc_hw *hw)
+{
+	s32 timeout = IGC_NVM_GRANT_ATTEMPTS;
+	u32 eecd = rd32(IGC_EECD);
+	s32 ret_val = 0;
+
+	wr32(IGC_EECD, eecd | IGC_EECD_REQ);
+	eecd = rd32(IGC_EECD);
+
+	while (timeout) {
+		if (eecd & IGC_EECD_GNT)
+			break;
+		udelay(5);
+		eecd = rd32(IGC_EECD);
+		timeout--;
+	}
+
+	if (!timeout) {
+		eecd &= ~IGC_EECD_REQ;
+		wr32(IGC_EECD, eecd);
+		hw_dbg("Could not acquire NVM grant\n");
+		ret_val = -IGC_ERR_NVM;
+	}
+
+	return ret_val;
+}
+
+/**
+ * igc_release_nvm - Release exclusive access to EEPROM
+ * @hw: pointer to the HW structure
+ *
+ * Stop any current commands to the EEPROM and clear the EEPROM request bit.
+ */
+void igc_release_nvm(struct igc_hw *hw)
+{
+	u32 eecd;
+
+	eecd = rd32(IGC_EECD);
+	eecd &= ~IGC_EECD_REQ;
+	wr32(IGC_EECD, eecd);
+}
+
+/**
+ * igc_read_nvm_eerd - Reads EEPROM using EERD register
+ * @hw: pointer to the HW structure
+ * @offset: offset of word in the EEPROM to read
+ * @words: number of words to read
+ * @data: word read from the EEPROM
+ *
+ * Reads a 16 bit word from the EEPROM using the EERD register.
+ */
+s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data)
+{
+	struct igc_nvm_info *nvm = &hw->nvm;
+	u32 i, eerd = 0;
+	s32 ret_val = 0;
+
+	/* A check for invalid values:  offset too large, too many words,
+	 * and not enough words.
+	 */
+	if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) ||
+	    words == 0) {
+		hw_dbg("nvm parameter(s) out of bounds\n");
+		ret_val = -IGC_ERR_NVM;
+		goto out;
+	}
+
+	for (i = 0; i < words; i++) {
+		eerd = ((offset + i) << IGC_NVM_RW_ADDR_SHIFT) +
+			IGC_NVM_RW_REG_START;
+
+		wr32(IGC_EERD, eerd);
+		ret_val = igc_poll_eerd_eewr_done(hw, IGC_NVM_POLL_READ);
+		if (ret_val)
+			break;
+
+		data[i] = (rd32(IGC_EERD) >> IGC_NVM_RW_REG_DATA);
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_read_mac_addr - Read device MAC address
+ * @hw: pointer to the HW structure
+ */
+s32 igc_read_mac_addr(struct igc_hw *hw)
+{
+	u32 rar_high;
+	u32 rar_low;
+	u16 i;
+
+	rar_high = rd32(IGC_RAH(0));
+	rar_low = rd32(IGC_RAL(0));
+
+	for (i = 0; i < IGC_RAL_MAC_ADDR_LEN; i++)
+		hw->mac.perm_addr[i] = (u8)(rar_low >> (i * 8));
+
+	for (i = 0; i < IGC_RAH_MAC_ADDR_LEN; i++)
+		hw->mac.perm_addr[i + 4] = (u8)(rar_high >> (i * 8));
+
+	for (i = 0; i < ETH_ALEN; i++)
+		hw->mac.addr[i] = hw->mac.perm_addr[i];
+
+	return 0;
+}
+
+/**
+ * igc_validate_nvm_checksum - Validate EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Calculates the EEPROM checksum by reading/adding each word of the EEPROM
+ * and then verifies that the sum of the EEPROM is equal to 0xBABA.
+ */
+s32 igc_validate_nvm_checksum(struct igc_hw *hw)
+{
+	u16 checksum = 0;
+	u16 i, nvm_data;
+	s32 ret_val = 0;
+
+	for (i = 0; i < (NVM_CHECKSUM_REG + 1); i++) {
+		ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
+		if (ret_val) {
+			hw_dbg("NVM Read Error\n");
+			goto out;
+		}
+		checksum += nvm_data;
+	}
+
+	if (checksum != (u16)NVM_SUM) {
+		hw_dbg("NVM Checksum Invalid\n");
+		ret_val = -IGC_ERR_NVM;
+		goto out;
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_update_nvm_checksum - Update EEPROM checksum
+ * @hw: pointer to the HW structure
+ *
+ * Updates the EEPROM checksum by reading/adding each word of the EEPROM
+ * up to the checksum.  Then calculates the EEPROM checksum and writes the
+ * value to the EEPROM.
+ */
+s32 igc_update_nvm_checksum(struct igc_hw *hw)
+{
+	u16 checksum = 0;
+	u16 i, nvm_data;
+	s32  ret_val;
+
+	for (i = 0; i < NVM_CHECKSUM_REG; i++) {
+		ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
+		if (ret_val) {
+			hw_dbg("NVM Read Error while updating checksum.\n");
+			goto out;
+		}
+		checksum += nvm_data;
+	}
+	checksum = (u16)NVM_SUM - checksum;
+	ret_val = hw->nvm.ops.write(hw, NVM_CHECKSUM_REG, 1, &checksum);
+	if (ret_val)
+		hw_dbg("NVM Write Error while updating checksum.\n");
+
+out:
+	return ret_val;
+}

drivers/net/ethernet/intel/igc/igc_nvm.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_NVM_H_
+#define _IGC_NVM_H_
+
+s32 igc_acquire_nvm(struct igc_hw *hw);
+void igc_release_nvm(struct igc_hw *hw);
+s32 igc_read_mac_addr(struct igc_hw *hw);
+s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data);
+s32 igc_validate_nvm_checksum(struct igc_hw *hw);
+s32 igc_update_nvm_checksum(struct igc_hw *hw);
+
+#endif

drivers/net/ethernet/intel/igc/igc_phy.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+#include "igc_phy.h"
+
+/* forward declaration */
+static s32 igc_phy_setup_autoneg(struct igc_hw *hw);
+static s32 igc_wait_autoneg(struct igc_hw *hw);
+
+/**
+ * igc_check_reset_block - Check if PHY reset is blocked
+ * @hw: pointer to the HW structure
+ *
+ * Read the PHY management control register and check whether a PHY reset
+ * is blocked.  If a reset is not blocked return 0, otherwise
+ * return IGC_ERR_BLK_PHY_RESET (12).
+ */
+s32 igc_check_reset_block(struct igc_hw *hw)
+{
+	u32 manc;
+
+	manc = rd32(IGC_MANC);
+
+	return (manc & IGC_MANC_BLK_PHY_RST_ON_IDE) ?
+		IGC_ERR_BLK_PHY_RESET : 0;
+}
+
+/**
+ * igc_get_phy_id - Retrieve the PHY ID and revision
+ * @hw: pointer to the HW structure
+ *
+ * Reads the PHY registers and stores the PHY ID and possibly the PHY
+ * revision in the hardware structure.
+ */
+s32 igc_get_phy_id(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	s32 ret_val = 0;
+	u16 phy_id;
+
+	ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id);
+	if (ret_val)
+		goto out;
+
+	phy->id = (u32)(phy_id << 16);
+	usleep_range(200, 500);
+	ret_val = phy->ops.read_reg(hw, PHY_ID2, &phy_id);
+	if (ret_val)
+		goto out;
+
+	phy->id |= (u32)(phy_id & PHY_REVISION_MASK);
+	phy->revision = (u32)(phy_id & ~PHY_REVISION_MASK);
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_phy_has_link - Polls PHY for link
+ * @hw: pointer to the HW structure
+ * @iterations: number of times to poll for link
+ * @usec_interval: delay between polling attempts
+ * @success: pointer to whether polling was successful or not
+ *
+ * Polls the PHY status register for link, 'iterations' number of times.
+ */
+s32 igc_phy_has_link(struct igc_hw *hw, u32 iterations,
+		     u32 usec_interval, bool *success)
+{
+	u16 i, phy_status;
+	s32 ret_val = 0;
+
+	for (i = 0; i < iterations; i++) {
+		/* Some PHYs require the PHY_STATUS register to be read
+		 * twice due to the link bit being sticky.  No harm doing
+		 * it across the board.
+		 */
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+		if (ret_val && usec_interval > 0) {
+			/* If the first read fails, another entity may have
+			 * ownership of the resources, wait and try again to
+			 * see if they have relinquished the resources yet.
+			 */
+			if (usec_interval >= 1000)
+				mdelay(usec_interval / 1000);
+			else
+				udelay(usec_interval);
+		}
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+		if (ret_val)
+			break;
+		if (phy_status & MII_SR_LINK_STATUS)
+			break;
+		if (usec_interval >= 1000)
+			mdelay(usec_interval / 1000);
+		else
+			udelay(usec_interval);
+	}
+
+	*success = (i < iterations) ? true : false;
+
+	return ret_val;
+}
+
+/**
+ * igc_power_up_phy_copper - Restore copper link in case of PHY power down
+ * @hw: pointer to the HW structure
+ *
+ * In the case of a PHY power down to save power, or to turn off link during a
+ * driver unload, restore the link to previous settings.
+ */
+void igc_power_up_phy_copper(struct igc_hw *hw)
+{
+	u16 mii_reg = 0;
+
+	/* The PHY will retain its settings across a power down/up cycle */
+	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
+	mii_reg &= ~MII_CR_POWER_DOWN;
+	hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
+}
+
+/**
+ * igc_power_down_phy_copper - Power down copper PHY
+ * @hw: pointer to the HW structure
+ *
+ * Power down PHY to save power when interface is down and wake on lan
+ * is not enabled.
+ */
+void igc_power_down_phy_copper(struct igc_hw *hw)
+{
+	u16 mii_reg = 0;
+
+	/* The PHY will retain its settings across a power down/up cycle */
+	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
+	mii_reg |= MII_CR_POWER_DOWN;
+
+	/* Temporary workaround - should be removed when PHY will implement
+	 * IEEE registers as properly
+	 */
+	/* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/
+	usleep_range(1000, 2000);
+}
+
+/**
+ * igc_check_downshift - Checks whether a downshift in speed occurred
+ * @hw: pointer to the HW structure
+ *
+ * Success returns 0, Failure returns 1
+ *
+ * A downshift is detected by querying the PHY link health.
+ */
+s32 igc_check_downshift(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u16 phy_data, offset, mask;
+	s32 ret_val;
+
+	switch (phy->type) {
+	case igc_phy_i225:
+	default:
+		/* speed downshift not supported */
+		phy->speed_downgraded = false;
+		ret_val = 0;
+		goto out;
+	}
+
+	ret_val = phy->ops.read_reg(hw, offset, &phy_data);
+
+	if (!ret_val)
+		phy->speed_downgraded = (phy_data & mask) ? true : false;
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_phy_hw_reset - PHY hardware reset
+ * @hw: pointer to the HW structure
+ *
+ * Verify the reset block is not blocking us from resetting.  Acquire
+ * semaphore (if necessary) and read/set/write the device control reset
+ * bit in the PHY.  Wait the appropriate delay time for the device to
+ * reset and release the semaphore (if necessary).
+ */
+s32 igc_phy_hw_reset(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	s32  ret_val;
+	u32 ctrl;
+
+	ret_val = igc_check_reset_block(hw);
+	if (ret_val) {
+		ret_val = 0;
+		goto out;
+	}
+
+	ret_val = phy->ops.acquire(hw);
+	if (ret_val)
+		goto out;
+
+	ctrl = rd32(IGC_CTRL);
+	wr32(IGC_CTRL, ctrl | IGC_CTRL_PHY_RST);
+	wrfl();
+
+	udelay(phy->reset_delay_us);
+
+	wr32(IGC_CTRL, ctrl);
+	wrfl();
+
+	usleep_range(1500, 2000);
+
+	phy->ops.release(hw);
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_copper_link_autoneg - Setup/Enable autoneg for copper link
+ * @hw: pointer to the HW structure
+ *
+ * Performs initial bounds checking on autoneg advertisement parameter, then
+ * configure to advertise the full capability.  Setup the PHY to autoneg
+ * and restart the negotiation process between the link partner.  If
+ * autoneg_wait_to_complete, then wait for autoneg to complete before exiting.
+ */
+static s32 igc_copper_link_autoneg(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u16 phy_ctrl;
+	s32 ret_val;
+
+	/* Perform some bounds checking on the autoneg advertisement
+	 * parameter.
+	 */
+	phy->autoneg_advertised &= phy->autoneg_mask;
+
+	/* If autoneg_advertised is zero, we assume it was not defaulted
+	 * by the calling code so we set to advertise full capability.
+	 */
+	if (phy->autoneg_advertised == 0)
+		phy->autoneg_advertised = phy->autoneg_mask;
+
+	hw_dbg("Reconfiguring auto-neg advertisement params\n");
+	ret_val = igc_phy_setup_autoneg(hw);
+	if (ret_val) {
+		hw_dbg("Error Setting up Auto-Negotiation\n");
+		goto out;
+	}
+	hw_dbg("Restarting Auto-Neg\n");
+
+	/* Restart auto-negotiation by setting the Auto Neg Enable bit and
+	 * the Auto Neg Restart bit in the PHY control register.
+	 */
+	ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl);
+	if (ret_val)
+		goto out;
+
+	phy_ctrl |= (MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG);
+	ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl);
+	if (ret_val)
+		goto out;
+
+	/* Does the user want to wait for Auto-Neg to complete here, or
+	 * check at a later time (for example, callback routine).
+	 */
+	if (phy->autoneg_wait_to_complete) {
+		ret_val = igc_wait_autoneg(hw);
+		if (ret_val) {
+			hw_dbg("Error while waiting for autoneg to complete\n");
+			goto out;
+		}
+	}
+
+	hw->mac.get_link_status = true;
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_wait_autoneg - Wait for auto-neg completion
+ * @hw: pointer to the HW structure
+ *
+ * Waits for auto-negotiation to complete or for the auto-negotiation time
+ * limit to expire, which ever happens first.
+ */
+static s32 igc_wait_autoneg(struct igc_hw *hw)
+{
+	u16 i, phy_status;
+	s32 ret_val = 0;
+
+	/* Break after autoneg completes or PHY_AUTO_NEG_LIMIT expires. */
+	for (i = PHY_AUTO_NEG_LIMIT; i > 0; i--) {
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+		if (ret_val)
+			break;
+		ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
+		if (ret_val)
+			break;
+		if (phy_status & MII_SR_AUTONEG_COMPLETE)
+			break;
+		msleep(100);
+	}
+
+	/* PHY_AUTO_NEG_TIME expiration doesn't guarantee auto-negotiation
+	 * has completed.
+	 */
+	return ret_val;
+}
+
+/**
+ * igc_phy_setup_autoneg - Configure PHY for auto-negotiation
+ * @hw: pointer to the HW structure
+ *
+ * Reads the MII auto-neg advertisement register and/or the 1000T control
+ * register and if the PHY is already setup for auto-negotiation, then
+ * return successful.  Otherwise, setup advertisement and flow control to
+ * the appropriate values for the wanted auto-negotiation.
+ */
+static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u16 aneg_multigbt_an_ctrl = 0;
+	u16 mii_1000t_ctrl_reg = 0;
+	u16 mii_autoneg_adv_reg;
+	s32 ret_val;
+
+	phy->autoneg_advertised &= phy->autoneg_mask;
+
+	/* Read the MII Auto-Neg Advertisement Register (Address 4). */
+	ret_val = phy->ops.read_reg(hw, PHY_AUTONEG_ADV, &mii_autoneg_adv_reg);
+	if (ret_val)
+		return ret_val;
+
+	if (phy->autoneg_mask & ADVERTISE_1000_FULL) {
+		/* Read the MII 1000Base-T Control Register (Address 9). */
+		ret_val = phy->ops.read_reg(hw, PHY_1000T_CTRL,
+					    &mii_1000t_ctrl_reg);
+		if (ret_val)
+			return ret_val;
+	}
+
+	if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
+	    hw->phy.id == I225_I_PHY_ID) {
+		/* Read the MULTI GBT AN Control Register - reg 7.32 */
+		ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+					    MMD_DEVADDR_SHIFT) |
+					    ANEG_MULTIGBT_AN_CTRL,
+					    &aneg_multigbt_an_ctrl);
+
+		if (ret_val)
+			return ret_val;
+	}
+
+	/* Need to parse both autoneg_advertised and fc and set up
+	 * the appropriate PHY registers.  First we will parse for
+	 * autoneg_advertised software override.  Since we can advertise
+	 * a plethora of combinations, we need to check each bit
+	 * individually.
+	 */
+
+	/* First we clear all the 10/100 mb speed bits in the Auto-Neg
+	 * Advertisement Register (Address 4) and the 1000 mb speed bits in
+	 * the  1000Base-T Control Register (Address 9).
+	 */
+	mii_autoneg_adv_reg &= ~(NWAY_AR_100TX_FD_CAPS |
+				 NWAY_AR_100TX_HD_CAPS |
+				 NWAY_AR_10T_FD_CAPS   |
+				 NWAY_AR_10T_HD_CAPS);
+	mii_1000t_ctrl_reg &= ~(CR_1000T_HD_CAPS | CR_1000T_FD_CAPS);
+
+	hw_dbg("autoneg_advertised %x\n", phy->autoneg_advertised);
+
+	/* Do we want to advertise 10 Mb Half Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_10_HALF) {
+		hw_dbg("Advertise 10mb Half duplex\n");
+		mii_autoneg_adv_reg |= NWAY_AR_10T_HD_CAPS;
+	}
+
+	/* Do we want to advertise 10 Mb Full Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_10_FULL) {
+		hw_dbg("Advertise 10mb Full duplex\n");
+		mii_autoneg_adv_reg |= NWAY_AR_10T_FD_CAPS;
+	}
+
+	/* Do we want to advertise 100 Mb Half Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_100_HALF) {
+		hw_dbg("Advertise 100mb Half duplex\n");
+		mii_autoneg_adv_reg |= NWAY_AR_100TX_HD_CAPS;
+	}
+
+	/* Do we want to advertise 100 Mb Full Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_100_FULL) {
+		hw_dbg("Advertise 100mb Full duplex\n");
+		mii_autoneg_adv_reg |= NWAY_AR_100TX_FD_CAPS;
+	}
+
+	/* We do not allow the Phy to advertise 1000 Mb Half Duplex */
+	if (phy->autoneg_advertised & ADVERTISE_1000_HALF)
+		hw_dbg("Advertise 1000mb Half duplex request denied!\n");
+
+	/* Do we want to advertise 1000 Mb Full Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_1000_FULL) {
+		hw_dbg("Advertise 1000mb Full duplex\n");
+		mii_1000t_ctrl_reg |= CR_1000T_FD_CAPS;
+	}
+
+	/* We do not allow the Phy to advertise 2500 Mb Half Duplex */
+	if (phy->autoneg_advertised & ADVERTISE_2500_HALF)
+		hw_dbg("Advertise 2500mb Half duplex request denied!\n");
+
+	/* Do we want to advertise 2500 Mb Full Duplex? */
+	if (phy->autoneg_advertised & ADVERTISE_2500_FULL) {
+		hw_dbg("Advertise 2500mb Full duplex\n");
+		aneg_multigbt_an_ctrl |= CR_2500T_FD_CAPS;
+	} else {
+		aneg_multigbt_an_ctrl &= ~CR_2500T_FD_CAPS;
+	}
+
+	/* Check for a software override of the flow control settings, and
+	 * setup the PHY advertisement registers accordingly.  If
+	 * auto-negotiation is enabled, then software will have to set the
+	 * "PAUSE" bits to the correct value in the Auto-Negotiation
+	 * Advertisement Register (PHY_AUTONEG_ADV) and re-start auto-
+	 * negotiation.
+	 *
+	 * The possible values of the "fc" parameter are:
+	 *      0:  Flow control is completely disabled
+	 *      1:  Rx flow control is enabled (we can receive pause frames
+	 *          but not send pause frames).
+	 *      2:  Tx flow control is enabled (we can send pause frames
+	 *          but we do not support receiving pause frames).
+	 *      3:  Both Rx and Tx flow control (symmetric) are enabled.
+	 *  other:  No software override.  The flow control configuration
+	 *          in the EEPROM is used.
+	 */
+	switch (hw->fc.current_mode) {
+	case igc_fc_none:
+		/* Flow control (Rx & Tx) is completely disabled by a
+		 * software over-ride.
+		 */
+		mii_autoneg_adv_reg &= ~(NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+		break;
+	case igc_fc_rx_pause:
+		/* Rx Flow control is enabled, and Tx Flow control is
+		 * disabled, by a software over-ride.
+		 *
+		 * Since there really isn't a way to advertise that we are
+		 * capable of Rx Pause ONLY, we will advertise that we
+		 * support both symmetric and asymmetric Rx PAUSE.  Later
+		 * (in igc_config_fc_after_link_up) we will disable the
+		 * hw's ability to send PAUSE frames.
+		 */
+		mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+		break;
+	case igc_fc_tx_pause:
+		/* Tx Flow control is enabled, and Rx Flow control is
+		 * disabled, by a software over-ride.
+		 */
+		mii_autoneg_adv_reg |= NWAY_AR_ASM_DIR;
+		mii_autoneg_adv_reg &= ~NWAY_AR_PAUSE;
+		break;
+	case igc_fc_full:
+		/* Flow control (both Rx and Tx) is enabled by a software
+		 * over-ride.
+		 */
+		mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE);
+		break;
+	default:
+		hw_dbg("Flow control param set incorrectly\n");
+		return -IGC_ERR_CONFIG;
+	}
+
+	ret_val = phy->ops.write_reg(hw, PHY_AUTONEG_ADV, mii_autoneg_adv_reg);
+	if (ret_val)
+		return ret_val;
+
+	hw_dbg("Auto-Neg Advertising %x\n", mii_autoneg_adv_reg);
+
+	if (phy->autoneg_mask & ADVERTISE_1000_FULL)
+		ret_val = phy->ops.write_reg(hw, PHY_1000T_CTRL,
+					     mii_1000t_ctrl_reg);
+
+	if ((phy->autoneg_mask & ADVERTISE_2500_FULL) &&
+	    hw->phy.id == I225_I_PHY_ID)
+		ret_val = phy->ops.write_reg(hw,
+					     (STANDARD_AN_REG_MASK <<
+					     MMD_DEVADDR_SHIFT) |
+					     ANEG_MULTIGBT_AN_CTRL,
+					     aneg_multigbt_an_ctrl);
+
+	return ret_val;
+}
+
+/**
+ * igc_setup_copper_link - Configure copper link settings
+ * @hw: pointer to the HW structure
+ *
+ * Calls the appropriate function to configure the link for auto-neg or forced
+ * speed and duplex.  Then we check for link, once link is established calls
+ * to configure collision distance and flow control are called.  If link is
+ * not established, we return -IGC_ERR_PHY (-2).
+ */
+s32 igc_setup_copper_link(struct igc_hw *hw)
+{
+	s32 ret_val = 0;
+	bool link;
+
+	if (hw->mac.autoneg) {
+		/* Setup autoneg and flow control advertisement and perform
+		 * autonegotiation.
+		 */
+		ret_val = igc_copper_link_autoneg(hw);
+		if (ret_val)
+			goto out;
+	} else {
+		/* PHY will be set to 10H, 10F, 100H or 100F
+		 * depending on user settings.
+		 */
+		hw_dbg("Forcing Speed and Duplex\n");
+		ret_val = hw->phy.ops.force_speed_duplex(hw);
+		if (ret_val) {
+			hw_dbg("Error Forcing Speed and Duplex\n");
+			goto out;
+		}
+	}
+
+	/* Check link status. Wait up to 100 microseconds for link to become
+	 * valid.
+	 */
+	ret_val = igc_phy_has_link(hw, COPPER_LINK_UP_LIMIT, 10, &link);
+	if (ret_val)
+		goto out;
+
+	if (link) {
+		hw_dbg("Valid link established!!!\n");
+		igc_config_collision_dist(hw);
+		ret_val = igc_config_fc_after_link_up(hw);
+	} else {
+		hw_dbg("Unable to establish link!!!\n");
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_read_phy_reg_mdic - Read MDI control register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to be read
+ * @data: pointer to the read data
+ *
+ * Reads the MDI control register in the PHY at offset and stores the
+ * information read to data.
+ */
+static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u32 i, mdic = 0;
+	s32 ret_val = 0;
+
+	if (offset > MAX_PHY_REG_ADDRESS) {
+		hw_dbg("PHY Address %d is out of range\n", offset);
+		ret_val = -IGC_ERR_PARAM;
+		goto out;
+	}
+
+	/* Set up Op-code, Phy Address, and register offset in the MDI
+	 * Control register.  The MAC will take care of interfacing with the
+	 * PHY to retrieve the desired data.
+	 */
+	mdic = ((offset << IGC_MDIC_REG_SHIFT) |
+		(phy->addr << IGC_MDIC_PHY_SHIFT) |
+		(IGC_MDIC_OP_READ));
+
+	wr32(IGC_MDIC, mdic);
+
+	/* Poll the ready bit to see if the MDI read completed
+	 * Increasing the time out as testing showed failures with
+	 * the lower time out
+	 */
+	for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
+		usleep_range(500, 1000);
+		mdic = rd32(IGC_MDIC);
+		if (mdic & IGC_MDIC_READY)
+			break;
+	}
+	if (!(mdic & IGC_MDIC_READY)) {
+		hw_dbg("MDI Read did not complete\n");
+		ret_val = -IGC_ERR_PHY;
+		goto out;
+	}
+	if (mdic & IGC_MDIC_ERROR) {
+		hw_dbg("MDI Error\n");
+		ret_val = -IGC_ERR_PHY;
+		goto out;
+	}
+	*data = (u16)mdic;
+
+out:
+	return ret_val;
+}
+
+/**
+ * igc_write_phy_reg_mdic - Write MDI control register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to write to
+ * @data: data to write to register at offset
+ *
+ * Writes data to MDI control register in the PHY at offset.
+ */
+static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data)
+{
+	struct igc_phy_info *phy = &hw->phy;
+	u32 i, mdic = 0;
+	s32 ret_val = 0;
+
+	if (offset > MAX_PHY_REG_ADDRESS) {
+		hw_dbg("PHY Address %d is out of range\n", offset);
+		ret_val = -IGC_ERR_PARAM;
+		goto out;
+	}
+
+	/* Set up Op-code, Phy Address, and register offset in the MDI
+	 * Control register.  The MAC will take care of interfacing with the
+	 * PHY to write the desired data.
+	 */
+	mdic = (((u32)data) |
+		(offset << IGC_MDIC_REG_SHIFT) |
+		(phy->addr << IGC_MDIC_PHY_SHIFT) |
+		(IGC_MDIC_OP_WRITE));
+
+	wr32(IGC_MDIC, mdic);
+
+	/* Poll the ready bit to see if the MDI read completed
+	 * Increasing the time out as testing showed failures with
+	 * the lower time out
+	 */
+	for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) {
+		usleep_range(500, 1000);
+		mdic = rd32(IGC_MDIC);
+		if (mdic & IGC_MDIC_READY)
+			break;
+	}
+	if (!(mdic & IGC_MDIC_READY)) {
+		hw_dbg("MDI Write did not complete\n");
+		ret_val = -IGC_ERR_PHY;
+		goto out;
+	}
+	if (mdic & IGC_MDIC_ERROR) {
+		hw_dbg("MDI Error\n");
+		ret_val = -IGC_ERR_PHY;
+		goto out;
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ * __igc_access_xmdio_reg - Read/write XMDIO register
+ * @hw: pointer to the HW structure
+ * @address: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: pointer to value to read/write from/to the XMDIO address
+ * @read: boolean flag to indicate read or write
+ */
+static s32 __igc_access_xmdio_reg(struct igc_hw *hw, u16 address,
+				  u8 dev_addr, u16 *data, bool read)
+{
+	s32 ret_val;
+
+	ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, dev_addr);
+	if (ret_val)
+		return ret_val;
+
+	ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAAD, address);
+	if (ret_val)
+		return ret_val;
+
+	ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, IGC_MMDAC_FUNC_DATA |
+					dev_addr);
+	if (ret_val)
+		return ret_val;
+
+	if (read)
+		ret_val = hw->phy.ops.read_reg(hw, IGC_MMDAAD, data);
+	else
+		ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAAD, *data);
+	if (ret_val)
+		return ret_val;
+
+	/* Recalibrate the device back to 0 */
+	ret_val = hw->phy.ops.write_reg(hw, IGC_MMDAC, 0);
+	if (ret_val)
+		return ret_val;
+
+	return ret_val;
+}
+
+/**
+ * igc_read_xmdio_reg - Read XMDIO register
+ * @hw: pointer to the HW structure
+ * @addr: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: value to be read from the EMI address
+ */
+static s32 igc_read_xmdio_reg(struct igc_hw *hw, u16 addr,
+			      u8 dev_addr, u16 *data)
+{
+	return __igc_access_xmdio_reg(hw, addr, dev_addr, data, true);
+}
+
+/**
+ * igc_write_xmdio_reg - Write XMDIO register
+ * @hw: pointer to the HW structure
+ * @addr: XMDIO address to program
+ * @dev_addr: device address to program
+ * @data: value to be written to the XMDIO address
+ */
+static s32 igc_write_xmdio_reg(struct igc_hw *hw, u16 addr,
+			       u8 dev_addr, u16 data)
+{
+	return __igc_access_xmdio_reg(hw, addr, dev_addr, &data, false);
+}
+
+/**
+ * igc_write_phy_reg_gpy - Write GPY PHY register
+ * @hw: pointer to the HW structure
+ * @offset: register offset to write to
+ * @data: data to write at register offset
+ *
+ * Acquires semaphore, if necessary, then writes the data to PHY register
+ * at the offset. Release any acquired semaphores before exiting.
+ */
+s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data)
+{
+	u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+	s32 ret_val;
+
+	offset = offset & GPY_REG_MASK;
+
+	if (!dev_addr) {
+		ret_val = hw->phy.ops.acquire(hw);
+		if (ret_val)
+			return ret_val;
+		ret_val = igc_write_phy_reg_mdic(hw, offset, data);
+		if (ret_val)
+			return ret_val;
+		hw->phy.ops.release(hw);
+	} else {
+		ret_val = igc_write_xmdio_reg(hw, (u16)offset, dev_addr,
+					      data);
+	}
+
+	return ret_val;
+}
+
+/**
+ * igc_read_phy_reg_gpy - Read GPY PHY register
+ * @hw: pointer to the HW structure
+ * @offset: lower half is register offset to read to
+ * upper half is MMD to use.
+ * @data: data to read at register offset
+ *
+ * Acquires semaphore, if necessary, then reads the data in the PHY register
+ * at the offset. Release any acquired semaphores before exiting.
+ */
+s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data)
+{
+	u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT;
+	s32 ret_val;
+
+	offset = offset & GPY_REG_MASK;
+
+	if (!dev_addr) {
+		ret_val = hw->phy.ops.acquire(hw);
+		if (ret_val)
+			return ret_val;
+		ret_val = igc_read_phy_reg_mdic(hw, offset, data);
+		if (ret_val)
+			return ret_val;
+		hw->phy.ops.release(hw);
+	} else {
+		ret_val = igc_read_xmdio_reg(hw, (u16)offset, dev_addr,
+					     data);
+	}
+
+	return ret_val;
+}

drivers/net/ethernet/intel/igc/igc_phy.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_PHY_H_
+#define _IGC_PHY_H_
+
+#include "igc_mac.h"
+
+s32 igc_check_reset_block(struct igc_hw *hw);
+s32 igc_phy_hw_reset(struct igc_hw *hw);
+s32 igc_get_phy_id(struct igc_hw *hw);
+s32 igc_phy_has_link(struct igc_hw *hw, u32 iterations,
+		     u32 usec_interval, bool *success);
+s32 igc_check_downshift(struct igc_hw *hw);
+s32 igc_setup_copper_link(struct igc_hw *hw);
+void igc_power_up_phy_copper(struct igc_hw *hw);
+void igc_power_down_phy_copper(struct igc_hw *hw);
+s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data);
+s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data);
+
+#endif

drivers/net/ethernet/intel/igc/igc_regs.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2018 Intel Corporation */
+
+#ifndef _IGC_REGS_H_
+#define _IGC_REGS_H_
+
+/* General Register Descriptions */
+#define IGC_CTRL		0x00000  /* Device Control - RW */
+#define IGC_STATUS		0x00008  /* Device Status - RO */
+#define IGC_EECD		0x00010  /* EEPROM/Flash Control - RW */
+#define IGC_CTRL_EXT		0x00018  /* Extended Device Control - RW */
+#define IGC_MDIC		0x00020  /* MDI Control - RW */
+#define IGC_MDICNFG		0x00E04  /* MDC/MDIO Configuration - RW */
+#define IGC_CONNSW		0x00034  /* Copper/Fiber switch control - RW */
+
+/* Internal Packet Buffer Size Registers */
+#define IGC_RXPBS		0x02404  /* Rx Packet Buffer Size - RW */
+#define IGC_TXPBS		0x03404  /* Tx Packet Buffer Size - RW */
+
+/* NVM  Register Descriptions */
+#define IGC_EERD		0x12014  /* EEprom mode read - RW */
+#define IGC_EEWR		0x12018  /* EEprom mode write - RW */
+
+/* Flow Control Register Descriptions */
+#define IGC_FCAL		0x00028  /* FC Address Low - RW */
+#define IGC_FCAH		0x0002C  /* FC Address High - RW */
+#define IGC_FCT			0x00030  /* FC Type - RW */
+#define IGC_FCTTV		0x00170  /* FC Transmit Timer - RW */
+#define IGC_FCRTL		0x02160  /* FC Receive Threshold Low - RW */
+#define IGC_FCRTH		0x02168  /* FC Receive Threshold High - RW */
+#define IGC_FCRTV		0x02460  /* FC Refresh Timer Value - RW */
+#define IGC_FCSTS		0x02464  /* FC Status - RO */
+
+/* PCIe Register Description */
+#define IGC_GCR			0x05B00  /* PCIe control- RW */
+
+/* Semaphore registers */
+#define IGC_SW_FW_SYNC		0x05B5C  /* SW-FW Synchronization - RW */
+#define IGC_SWSM		0x05B50  /* SW Semaphore */
+#define IGC_FWSM		0x05B54  /* FW Semaphore */
+
+/* Function Active and Power State to MNG */
+#define IGC_FACTPS		0x05B30
+
+/* Interrupt Register Description */
+#define IGC_EICS		0x01520  /* Ext. Interrupt Cause Set - W0 */
+#define IGC_EIMS		0x01524  /* Ext. Interrupt Mask Set/Read - RW */
+#define IGC_EIMC		0x01528  /* Ext. Interrupt Mask Clear - WO */
+#define IGC_EIAC		0x0152C  /* Ext. Interrupt Auto Clear - RW */
+#define IGC_EIAM		0x01530  /* Ext. Interrupt Auto Mask - RW */
+#define IGC_ICR			0x01500  /* Intr Cause Read - RC/W1C */
+#define IGC_ICS			0x01504  /* Intr Cause Set - WO */
+#define IGC_IMS			0x01508  /* Intr Mask Set/Read - RW */
+#define IGC_IMC			0x0150C  /* Intr Mask Clear - WO */
+#define IGC_IAM			0x01510  /* Intr Ack Auto Mask- RW */
+/* Intr Throttle - RW */
+#define IGC_EITR(_n)		(0x01680 + (0x4 * (_n)))
+/* Interrupt Vector Allocation - RW */
+#define IGC_IVAR0		0x01700
+#define IGC_IVAR_MISC		0x01740  /* IVAR for "other" causes - RW */
+#define IGC_GPIE		0x01514  /* General Purpose Intr Enable - RW */
+
+/* Interrupt Cause */
+#define IGC_ICRXPTC		0x04104  /* Rx Packet Timer Expire Count */
+#define IGC_ICRXATC		0x04108  /* Rx Absolute Timer Expire Count */
+#define IGC_ICTXPTC		0x0410C  /* Tx Packet Timer Expire Count */
+#define IGC_ICTXATC		0x04110  /* Tx Absolute Timer Expire Count */
+#define IGC_ICTXQEC		0x04118  /* Tx Queue Empty Count */
+#define IGC_ICTXQMTC		0x0411C  /* Tx Queue Min Threshold Count */
+#define IGC_ICRXDMTC		0x04120  /* Rx Descriptor Min Threshold Count */
+#define IGC_ICRXOC		0x04124  /* Receiver Overrun Count */
+
+#define IGC_CBTMPC		0x0402C  /* Circuit Breaker TX Packet Count */
+#define IGC_HTDPMC		0x0403C  /* Host Transmit Discarded Packets */
+#define IGC_CBRMPC		0x040FC  /* Circuit Breaker RX Packet Count */
+#define IGC_RPTHC		0x04104  /* Rx Packets To Host */
+#define IGC_HGPTC		0x04118  /* Host Good Packets TX Count */
+#define IGC_HTCBDPC		0x04124  /* Host TX Circ.Breaker Drop Count */
+
+/* MSI-X Table Register Descriptions */
+#define IGC_PBACL		0x05B68  /* MSIx PBA Clear - R/W 1 to clear */
+
+/* Receive Register Descriptions */
+#define IGC_RCTL		0x00100  /* Rx Control - RW */
+#define IGC_SRRCTL(_n)		(0x0C00C + ((_n) * 0x40))
+#define IGC_PSRTYPE(_i)		(0x05480 + ((_i) * 4))
+#define IGC_RDBAL(_n)		(0x0C000 + ((_n) * 0x40))
+#define IGC_RDBAH(_n)		(0x0C004 + ((_n) * 0x40))
+#define IGC_RDLEN(_n)		(0x0C008 + ((_n) * 0x40))
+#define IGC_RDH(_n)		(0x0C010 + ((_n) * 0x40))
+#define IGC_RDT(_n)		(0x0C018 + ((_n) * 0x40))
+#define IGC_RXDCTL(_n)		(0x0C028 + ((_n) * 0x40))
+#define IGC_RQDPC(_n)		(0x0C030 + ((_n) * 0x40))
+#define IGC_RXCSUM		0x05000  /* Rx Checksum Control - RW */
+#define IGC_RLPML		0x05004  /* Rx Long Packet Max Length */
+#define IGC_RFCTL		0x05008  /* Receive Filter Control*/
+#define IGC_MTA			0x05200  /* Multicast Table Array - RW Array */
+#define IGC_UTA			0x0A000  /* Unicast Table Array - RW */
+#define IGC_RAL(_n)		(0x05400 + ((_n) * 0x08))
+#define IGC_RAH(_n)		(0x05404 + ((_n) * 0x08))
+
+/* Transmit Register Descriptions */
+#define IGC_TCTL		0x00400  /* Tx Control - RW */
+#define IGC_TIPG		0x00410  /* Tx Inter-packet gap - RW */
+#define IGC_TDBAL(_n)		(0x0E000 + ((_n) * 0x40))
+#define IGC_TDBAH(_n)		(0x0E004 + ((_n) * 0x40))
+#define IGC_TDLEN(_n)		(0x0E008 + ((_n) * 0x40))
+#define IGC_TDH(_n)		(0x0E010 + ((_n) * 0x40))
+#define IGC_TDT(_n)		(0x0E018 + ((_n) * 0x40))
+#define IGC_TXDCTL(_n)		(0x0E028 + ((_n) * 0x40))
+
+/* MMD Register Descriptions */
+#define IGC_MMDAC		13 /* MMD Access Control */
+#define IGC_MMDAAD		14 /* MMD Access Address/Data */
+
+/* Good transmitted packets counter registers */
+#define IGC_PQGPTC(_n)		(0x010014 + (0x100 * (_n)))
+
+/* Statistics Register Descriptions */
+#define IGC_CRCERRS	0x04000  /* CRC Error Count - R/clr */
+#define IGC_ALGNERRC	0x04004  /* Alignment Error Count - R/clr */
+#define IGC_SYMERRS	0x04008  /* Symbol Error Count - R/clr */
+#define IGC_RXERRC	0x0400C  /* Receive Error Count - R/clr */
+#define IGC_MPC		0x04010  /* Missed Packet Count - R/clr */
+#define IGC_SCC		0x04014  /* Single Collision Count - R/clr */
+#define IGC_ECOL	0x04018  /* Excessive Collision Count - R/clr */
+#define IGC_MCC		0x0401C  /* Multiple Collision Count - R/clr */
+#define IGC_LATECOL	0x04020  /* Late Collision Count - R/clr */
+#define IGC_COLC	0x04028  /* Collision Count - R/clr */
+#define IGC_DC		0x04030  /* Defer Count - R/clr */
+#define IGC_TNCRS	0x04034  /* Tx-No CRS - R/clr */
+#define IGC_SEC		0x04038  /* Sequence Error Count - R/clr */
+#define IGC_CEXTERR	0x0403C  /* Carrier Extension Error Count - R/clr */
+#define IGC_RLEC	0x04040  /* Receive Length Error Count - R/clr */
+#define IGC_XONRXC	0x04048  /* XON Rx Count - R/clr */
+#define IGC_XONTXC	0x0404C  /* XON Tx Count - R/clr */
+#define IGC_XOFFRXC	0x04050  /* XOFF Rx Count - R/clr */
+#define IGC_XOFFTXC	0x04054  /* XOFF Tx Count - R/clr */
+#define IGC_FCRUC	0x04058  /* Flow Control Rx Unsupported Count- R/clr */
+#define IGC_PRC64	0x0405C  /* Packets Rx (64 bytes) - R/clr */
+#define IGC_PRC127	0x04060  /* Packets Rx (65-127 bytes) - R/clr */
+#define IGC_PRC255	0x04064  /* Packets Rx (128-255 bytes) - R/clr */
+#define IGC_PRC511	0x04068  /* Packets Rx (255-511 bytes) - R/clr */
+#define IGC_PRC1023	0x0406C  /* Packets Rx (512-1023 bytes) - R/clr */
+#define IGC_PRC1522	0x04070  /* Packets Rx (1024-1522 bytes) - R/clr */
+#define IGC_GPRC	0x04074  /* Good Packets Rx Count - R/clr */
+#define IGC_BPRC	0x04078  /* Broadcast Packets Rx Count - R/clr */
+#define IGC_MPRC	0x0407C  /* Multicast Packets Rx Count - R/clr */
+#define IGC_GPTC	0x04080  /* Good Packets Tx Count - R/clr */
+#define IGC_GORCL	0x04088  /* Good Octets Rx Count Low - R/clr */
+#define IGC_GORCH	0x0408C  /* Good Octets Rx Count High - R/clr */
+#define IGC_GOTCL	0x04090  /* Good Octets Tx Count Low - R/clr */
+#define IGC_GOTCH	0x04094  /* Good Octets Tx Count High - R/clr */
+#define IGC_RNBC	0x040A0  /* Rx No Buffers Count - R/clr */
+#define IGC_RUC		0x040A4  /* Rx Undersize Count - R/clr */
+#define IGC_RFC		0x040A8  /* Rx Fragment Count - R/clr */
+#define IGC_ROC		0x040AC  /* Rx Oversize Count - R/clr */
+#define IGC_RJC		0x040B0  /* Rx Jabber Count - R/clr */
+#define IGC_MGTPRC	0x040B4  /* Management Packets Rx Count - R/clr */
+#define IGC_MGTPDC	0x040B8  /* Management Packets Dropped Count - R/clr */
+#define IGC_MGTPTC	0x040BC  /* Management Packets Tx Count - R/clr */
+#define IGC_TORL	0x040C0  /* Total Octets Rx Low - R/clr */
+#define IGC_TORH	0x040C4  /* Total Octets Rx High - R/clr */
+#define IGC_TOTL	0x040C8  /* Total Octets Tx Low - R/clr */
+#define IGC_TOTH	0x040CC  /* Total Octets Tx High - R/clr */
+#define IGC_TPR		0x040D0  /* Total Packets Rx - R/clr */
+#define IGC_TPT		0x040D4  /* Total Packets Tx - R/clr */
+#define IGC_PTC64	0x040D8  /* Packets Tx (64 bytes) - R/clr */
+#define IGC_PTC127	0x040DC  /* Packets Tx (65-127 bytes) - R/clr */
+#define IGC_PTC255	0x040E0  /* Packets Tx (128-255 bytes) - R/clr */
+#define IGC_PTC511	0x040E4  /* Packets Tx (256-511 bytes) - R/clr */
+#define IGC_PTC1023	0x040E8  /* Packets Tx (512-1023 bytes) - R/clr */
+#define IGC_PTC1522	0x040EC  /* Packets Tx (1024-1522 Bytes) - R/clr */
+#define IGC_MPTC	0x040F0  /* Multicast Packets Tx Count - R/clr */
+#define IGC_BPTC	0x040F4  /* Broadcast Packets Tx Count - R/clr */
+#define IGC_TSCTC	0x040F8  /* TCP Segmentation Context Tx - R/clr */
+#define IGC_TSCTFC	0x040FC  /* TCP Segmentation Context Tx Fail - R/clr */
+#define IGC_IAC		0x04100  /* Interrupt Assertion Count */
+#define IGC_ICTXPTC	0x0410C  /* Interrupt Cause Tx Pkt Timer Expire Count */
+#define IGC_ICTXATC	0x04110  /* Interrupt Cause Tx Abs Timer Expire Count */
+#define IGC_ICTXQEC	0x04118  /* Interrupt Cause Tx Queue Empty Count */
+#define IGC_ICTXQMTC	0x0411C  /* Interrupt Cause Tx Queue Min Thresh Count */
+#define IGC_RPTHC	0x04104  /* Rx Packets To Host */
+#define IGC_HGPTC	0x04118  /* Host Good Packets Tx Count */
+#define IGC_RXDMTC	0x04120  /* Rx Descriptor Minimum Threshold Count */
+#define IGC_HGORCL	0x04128  /* Host Good Octets Received Count Low */
+#define IGC_HGORCH	0x0412C  /* Host Good Octets Received Count High */
+#define IGC_HGOTCL	0x04130  /* Host Good Octets Transmit Count Low */
+#define IGC_HGOTCH	0x04134  /* Host Good Octets Transmit Count High */
+#define IGC_LENERRS	0x04138  /* Length Errors Count */
+#define IGC_SCVPC	0x04228  /* SerDes/SGMII Code Violation Pkt Count */
+#define IGC_HRMPC	0x0A018  /* Header Redirection Missed Packet Count */
+
+/* Management registers */
+#define IGC_MANC	0x05820  /* Management Control - RW */
+
+/* Shadow Ram Write Register - RW */
+#define IGC_SRWR	0x12018
+
+/* forward declaration */
+struct igc_hw;
+u32 igc_rd32(struct igc_hw *hw, u32 reg);
+
+/* write operations, indexed using DWORDS */
+#define wr32(reg, val) \
+do { \
+	u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
+	if (!IGC_REMOVED(hw_addr)) \
+		writel((val), &hw_addr[(reg)]); \
+} while (0)
+
+#define rd32(reg) (igc_rd32(hw, reg))
+
+#define wrfl() ((void)rd32(IGC_STATUS))
+
+#define array_wr32(reg, offset, value) \
+	wr32((reg) + ((offset) << 2), (value))
+
+#define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2)))
+
+#endif