Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

20 files changed, 16382 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile
new file mode 100644
index 000000000..26a9746cc
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/Makefile
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2013 - 2018 Intel Corporation.
+
+#
+# Makefile for the Intel(R) Ethernet Switch Host Interface Driver
+#
+
+obj-$(CONFIG_FM10K) += fm10k.o
+
+fm10k-y := fm10k_main.o \
+	   fm10k_common.o \
+	   fm10k_pci.o \
+	   fm10k_netdev.o \
+	   fm10k_ethtool.o \
+	   fm10k_pf.o \
+	   fm10k_vf.o \
+	   fm10k_mbx.o \
+	   fm10k_iov.o \
+	   fm10k_tlv.o
+
+fm10k-$(CONFIG_DEBUG_FS) += fm10k_debugfs.o
+fm10k-$(CONFIG_DCB) += fm10k_dcbnl.o
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
new file mode 100644
index 000000000..6119a4108
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -0,0 +1,565 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#ifndef _FM10K_H_
+#define _FM10K_H_
+
+#include <linux/types.h>
+#include <linux/etherdevice.h>
+#include <linux/cpumask.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+
+#include "fm10k_pf.h"
+#include "fm10k_vf.h"
+
+#define FM10K_MAX_JUMBO_FRAME_SIZE	15342	/* Maximum supported size 15K */
+
+#define MAX_QUEUES	FM10K_MAX_QUEUES_PF
+
+#define FM10K_MIN_RXD		 128
+#define FM10K_MAX_RXD		4096
+#define FM10K_DEFAULT_RXD	 256
+
+#define FM10K_MIN_TXD		 128
+#define FM10K_MAX_TXD		4096
+#define FM10K_DEFAULT_TXD	 256
+#define FM10K_DEFAULT_TX_WORK	 256
+
+#define FM10K_RXBUFFER_256	  256
+#define FM10K_RX_HDR_LEN	FM10K_RXBUFFER_256
+#define FM10K_RXBUFFER_2048	 2048
+#define FM10K_RX_BUFSZ		FM10K_RXBUFFER_2048
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define FM10K_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+
+#define FM10K_MAX_STATIONS	63
+struct fm10k_l2_accel {
+	int size;
+	u16 count;
+	u16 dglort;
+	struct rcu_head rcu;
+	struct net_device *macvlan[];
+};
+
+enum fm10k_ring_state_t {
+	__FM10K_TX_DETECT_HANG,
+	__FM10K_HANG_CHECK_ARMED,
+	__FM10K_TX_XPS_INIT_DONE,
+	/* This must be last and is used to calculate BITMAP size */
+	__FM10K_TX_STATE_SIZE__,
+};
+
+#define check_for_tx_hang(ring) \
+	test_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
+#define set_check_for_tx_hang(ring) \
+	set_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
+#define clear_check_for_tx_hang(ring) \
+	clear_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
+
+struct fm10k_tx_buffer {
+	struct fm10k_tx_desc *next_to_watch;
+	struct sk_buff *skb;
+	unsigned int bytecount;
+	u16 gso_segs;
+	u16 tx_flags;
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+};
+
+struct fm10k_rx_buffer {
+	dma_addr_t dma;
+	struct page *page;
+	u32 page_offset;
+};
+
+struct fm10k_queue_stats {
+	u64 packets;
+	u64 bytes;
+};
+
+struct fm10k_tx_queue_stats {
+	u64 restart_queue;
+	u64 csum_err;
+	u64 tx_busy;
+	u64 tx_done_old;
+	u64 csum_good;
+};
+
+struct fm10k_rx_queue_stats {
+	u64 alloc_failed;
+	u64 csum_err;
+	u64 errors;
+	u64 csum_good;
+	u64 switch_errors;
+	u64 drops;
+	u64 pp_errors;
+	u64 link_errors;
+	u64 length_errors;
+};
+
+struct fm10k_ring {
+	struct fm10k_q_vector *q_vector;/* backpointer to host q_vector */
+	struct net_device *netdev;	/* netdev ring belongs to */
+	struct device *dev;		/* device for DMA mapping */
+	struct fm10k_l2_accel __rcu *l2_accel;	/* L2 acceleration list */
+	void *desc;			/* descriptor ring memory */
+	union {
+		struct fm10k_tx_buffer *tx_buffer;
+		struct fm10k_rx_buffer *rx_buffer;
+	};
+	u32 __iomem *tail;
+	DECLARE_BITMAP(state, __FM10K_TX_STATE_SIZE__);
+	dma_addr_t dma;			/* phys. address of descriptor ring */
+	unsigned int size;		/* length in bytes */
+
+	u8 queue_index;			/* needed for queue management */
+	u8 reg_idx;			/* holds the special value that gets
+					 * the hardware register offset
+					 * associated with this ring, which is
+					 * different for DCB and RSS modes
+					 */
+	u8 qos_pc;			/* priority class of queue */
+	u16 vid;			/* default VLAN ID of queue */
+	u16 count;			/* amount of descriptors */
+
+	u16 next_to_alloc;
+	u16 next_to_use;
+	u16 next_to_clean;
+
+	struct fm10k_queue_stats stats;
+	struct u64_stats_sync syncp;
+	union {
+		/* Tx */
+		struct fm10k_tx_queue_stats tx_stats;
+		/* Rx */
+		struct {
+			struct fm10k_rx_queue_stats rx_stats;
+			struct sk_buff *skb;
+		};
+	};
+} ____cacheline_internodealigned_in_smp;
+
+struct fm10k_ring_container {
+	struct fm10k_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 */
+	u16 itr;			/* interrupt throttle rate value */
+	u8 itr_scale;			/* ITR adjustment based on PCI speed */
+	u8 count;			/* total number of rings in vector */
+};
+
+#define FM10K_ITR_MAX		0x0FFF	/* maximum value for ITR */
+#define FM10K_ITR_10K		100	/* 100us */
+#define FM10K_ITR_20K		50	/* 50us */
+#define FM10K_ITR_40K		25	/* 25us */
+#define FM10K_ITR_ADAPTIVE	0x8000	/* adaptive interrupt moderation flag */
+
+#define ITR_IS_ADAPTIVE(itr) (!!(itr & FM10K_ITR_ADAPTIVE))
+
+#define FM10K_TX_ITR_DEFAULT	FM10K_ITR_40K
+#define FM10K_RX_ITR_DEFAULT	FM10K_ITR_20K
+#define FM10K_ITR_ENABLE	(FM10K_ITR_AUTOMASK | FM10K_ITR_MASK_CLEAR)
+
+static inline struct netdev_queue *txring_txq(const struct fm10k_ring *ring)
+{
+	return &ring->netdev->_tx[ring->queue_index];
+}
+
+/* iterator for handling rings in ring container */
+#define fm10k_for_each_ring(pos, head) \
+	for (pos = &(head).ring[(head).count]; (--pos) >= (head).ring;)
+
+#define MAX_Q_VECTORS 256
+#define MIN_Q_VECTORS	1
+enum fm10k_non_q_vectors {
+	FM10K_MBX_VECTOR,
+	NON_Q_VECTORS
+};
+
+#define MIN_MSIX_COUNT(hw)	(MIN_Q_VECTORS + NON_Q_VECTORS)
+
+struct fm10k_q_vector {
+	struct fm10k_intfc *interface;
+	u32 __iomem *itr;	/* pointer to ITR register for this vector */
+	u16 v_idx;		/* index of q_vector within interface array */
+	struct fm10k_ring_container rx, tx;
+
+	struct napi_struct napi;
+	cpumask_t affinity_mask;
+	char name[IFNAMSIZ + 9];
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dbg_q_vector;
+#endif /* CONFIG_DEBUG_FS */
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+
+	/* for dynamic allocation of rings associated with this q_vector */
+	struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp;
+};
+
+enum fm10k_ring_f_enum {
+	RING_F_RSS,
+	RING_F_QOS,
+	RING_F_ARRAY_SIZE  /* must be last in enum set */
+};
+
+struct fm10k_ring_feature {
+	u16 limit;	/* upper limit on feature indices */
+	u16 indices;	/* current value of indices */
+	u16 mask;	/* Mask used for feature to ring mapping */
+	u16 offset;	/* offset to start of feature */
+};
+
+struct fm10k_iov_data {
+	unsigned int		num_vfs;
+	unsigned int		next_vf_mbx;
+	struct rcu_head		rcu;
+	struct fm10k_vf_info	vf_info[];
+};
+
+enum fm10k_macvlan_request_type {
+	FM10K_UC_MAC_REQUEST,
+	FM10K_MC_MAC_REQUEST,
+	FM10K_VLAN_REQUEST
+};
+
+struct fm10k_macvlan_request {
+	enum fm10k_macvlan_request_type type;
+	struct list_head list;
+	union {
+		struct fm10k_mac_request {
+			u8 addr[ETH_ALEN];
+			u16 glort;
+			u16 vid;
+		} mac;
+		struct fm10k_vlan_request {
+			u32 vid;
+			u8 vsi;
+		} vlan;
+	};
+	bool set;
+};
+
+/* one work queue for entire driver */
+extern struct workqueue_struct *fm10k_workqueue;
+
+/* The following enumeration contains flags which indicate or enable modified
+ * driver behaviors. To avoid race conditions, the flags are stored in
+ * a BITMAP in the fm10k_intfc structure. The BITMAP should be accessed using
+ * atomic *_bit() operations.
+ */
+enum fm10k_flags_t {
+	FM10K_FLAG_RESET_REQUESTED,
+	FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+	FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+	FM10K_FLAG_SWPRI_CONFIG,
+	/* __FM10K_FLAGS_SIZE__ is used to calculate the size of
+	 * interface->flags and must be the last value in this
+	 * enumeration.
+	 */
+	__FM10K_FLAGS_SIZE__
+};
+
+enum fm10k_state_t {
+	__FM10K_RESETTING,
+	__FM10K_RESET_DETACHED,
+	__FM10K_RESET_SUSPENDED,
+	__FM10K_DOWN,
+	__FM10K_SERVICE_SCHED,
+	__FM10K_SERVICE_REQUEST,
+	__FM10K_SERVICE_DISABLE,
+	__FM10K_MACVLAN_SCHED,
+	__FM10K_MACVLAN_REQUEST,
+	__FM10K_MACVLAN_DISABLE,
+	__FM10K_LINK_DOWN,
+	__FM10K_UPDATING_STATS,
+	/* This value must be last and determines the BITMAP size */
+	__FM10K_STATE_SIZE__,
+};
+
+struct fm10k_intfc {
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	struct net_device *netdev;
+	struct fm10k_l2_accel *l2_accel; /* pointer to L2 acceleration list */
+	struct pci_dev *pdev;
+	DECLARE_BITMAP(state, __FM10K_STATE_SIZE__);
+
+	/* Access flag values using atomic *_bit() operations */
+	DECLARE_BITMAP(flags, __FM10K_FLAGS_SIZE__);
+
+	int xcast_mode;
+
+	/* Tx fast path data */
+	int num_tx_queues;
+	u16 tx_itr;
+
+	/* Rx fast path data */
+	int num_rx_queues;
+	u16 rx_itr;
+
+	/* TX */
+	struct fm10k_ring *tx_ring[MAX_QUEUES] ____cacheline_aligned_in_smp;
+
+	u64 restart_queue;
+	u64 tx_busy;
+	u64 tx_csum_errors;
+	u64 alloc_failed;
+	u64 rx_csum_errors;
+
+	u64 tx_bytes_nic;
+	u64 tx_packets_nic;
+	u64 rx_bytes_nic;
+	u64 rx_packets_nic;
+	u64 rx_drops_nic;
+	u64 rx_overrun_pf;
+	u64 rx_overrun_vf;
+
+	/* Debug Statistics */
+	u64 hw_sm_mbx_full;
+	u64 hw_csum_tx_good;
+	u64 hw_csum_rx_good;
+	u64 rx_switch_errors;
+	u64 rx_drops;
+	u64 rx_pp_errors;
+	u64 rx_link_errors;
+	u64 rx_length_errors;
+
+	u32 tx_timeout_count;
+
+	/* RX */
+	struct fm10k_ring *rx_ring[MAX_QUEUES];
+
+	/* Queueing vectors */
+	struct fm10k_q_vector *q_vector[MAX_Q_VECTORS];
+	struct msix_entry *msix_entries;
+	int num_q_vectors;	/* current number of q_vectors for device */
+	struct fm10k_ring_feature ring_feature[RING_F_ARRAY_SIZE];
+
+	/* SR-IOV information management structure */
+	struct fm10k_iov_data *iov_data;
+
+	struct fm10k_hw_stats stats;
+	struct fm10k_hw hw;
+	/* Mailbox lock */
+	spinlock_t mbx_lock;
+	u32 __iomem *uc_addr;
+	u32 __iomem *sw_addr;
+	u16 msg_enable;
+	u16 tx_ring_count;
+	u16 rx_ring_count;
+	struct timer_list service_timer;
+	struct work_struct service_task;
+	unsigned long next_stats_update;
+	unsigned long next_tx_hang_check;
+	unsigned long last_reset;
+	unsigned long link_down_event;
+	bool host_ready;
+	bool lport_map_failed;
+
+	u32 reta[FM10K_RETA_SIZE];
+	u32 rssrk[FM10K_RSSRK_SIZE];
+
+	/* UDP encapsulation port tracking information */
+	__be16 vxlan_port;
+	__be16 geneve_port;
+
+	/* MAC/VLAN update queue */
+	struct list_head macvlan_requests;
+	struct delayed_work macvlan_task;
+	/* MAC/VLAN update queue lock */
+	spinlock_t macvlan_lock;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dbg_intfc;
+#endif /* CONFIG_DEBUG_FS */
+
+#ifdef CONFIG_DCB
+	u8 pfc_en;
+#endif
+	u8 rx_pause;
+
+	/* GLORT resources in use by PF */
+	u16 glort;
+	u16 glort_count;
+
+	/* VLAN ID for updating multicast/unicast lists */
+	u16 vid;
+};
+
+static inline void fm10k_mbx_lock(struct fm10k_intfc *interface)
+{
+	spin_lock(&interface->mbx_lock);
+}
+
+static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface)
+{
+	spin_unlock(&interface->mbx_lock);
+}
+
+static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface)
+{
+	return spin_trylock(&interface->mbx_lock);
+}
+
+/* fm10k_test_staterr - test bits in Rx descriptor status and error fields */
+static inline __le32 fm10k_test_staterr(union fm10k_rx_desc *rx_desc,
+					const u32 stat_err_bits)
+{
+	return rx_desc->d.staterr & cpu_to_le32(stat_err_bits);
+}
+
+/* fm10k_desc_unused - calculate if we have unused descriptors */
+static inline u16 fm10k_desc_unused(struct fm10k_ring *ring)
+{
+	s16 unused = ring->next_to_clean - ring->next_to_use - 1;
+
+	return likely(unused < 0) ? unused + ring->count : unused;
+}
+
+#define FM10K_TX_DESC(R, i)	\
+	(&(((struct fm10k_tx_desc *)((R)->desc))[i]))
+#define FM10K_RX_DESC(R, i)	\
+	 (&(((union fm10k_rx_desc *)((R)->desc))[i]))
+
+#define FM10K_MAX_TXD_PWR	14
+#define FM10K_MAX_DATA_PER_TXD	(1u << FM10K_MAX_TXD_PWR)
+
+/* Tx Descriptors needed, worst case */
+#define TXD_USE_COUNT(S)	DIV_ROUND_UP((S), FM10K_MAX_DATA_PER_TXD)
+#define DESC_NEEDED	(MAX_SKB_FRAGS + 4)
+
+enum fm10k_tx_flags {
+	/* Tx offload flags */
+	FM10K_TX_FLAGS_CSUM	= 0x01,
+};
+
+/* This structure is stored as little endian values as that is the native
+ * format of the Rx descriptor.  The ordering of these fields is reversed
+ * from the actual ftag header to allow for a single bswap to take care
+ * of placing all of the values in network order
+ */
+union fm10k_ftag_info {
+	__le64 ftag;
+	struct {
+		/* dglort and sglort combined into a single 32bit desc read */
+		__le32 glort;
+		/* upper 16 bits of VLAN are reserved 0 for swpri_type_user */
+		__le32 vlan;
+	} d;
+	struct {
+		__le16 dglort;
+		__le16 sglort;
+		__le16 vlan;
+		__le16 swpri_type_user;
+	} w;
+};
+
+struct fm10k_cb {
+	union {
+		__le64 tstamp;
+		unsigned long ts_tx_timeout;
+	};
+	union fm10k_ftag_info fi;
+};
+
+#define FM10K_CB(skb) ((struct fm10k_cb *)(skb)->cb)
+
+/* main */
+extern char fm10k_driver_name[];
+int fm10k_init_queueing_scheme(struct fm10k_intfc *interface);
+void fm10k_clear_queueing_scheme(struct fm10k_intfc *interface);
+__be16 fm10k_tx_encap_offload(struct sk_buff *skb);
+netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb,
+				  struct fm10k_ring *tx_ring);
+void fm10k_tx_timeout_reset(struct fm10k_intfc *interface);
+u64 fm10k_get_tx_pending(struct fm10k_ring *ring, bool in_sw);
+bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring);
+void fm10k_alloc_rx_buffers(struct fm10k_ring *rx_ring, u16 cleaned_count);
+
+/* PCI */
+void fm10k_mbx_free_irq(struct fm10k_intfc *);
+int fm10k_mbx_request_irq(struct fm10k_intfc *);
+void fm10k_qv_free_irq(struct fm10k_intfc *interface);
+int fm10k_qv_request_irq(struct fm10k_intfc *interface);
+int fm10k_register_pci_driver(void);
+void fm10k_unregister_pci_driver(void);
+void fm10k_up(struct fm10k_intfc *interface);
+void fm10k_down(struct fm10k_intfc *interface);
+void fm10k_update_stats(struct fm10k_intfc *interface);
+void fm10k_service_event_schedule(struct fm10k_intfc *interface);
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface);
+void fm10k_update_rx_drop_en(struct fm10k_intfc *interface);
+
+/* Netdev */
+struct net_device *fm10k_alloc_netdev(const struct fm10k_info *info);
+int fm10k_setup_rx_resources(struct fm10k_ring *);
+int fm10k_setup_tx_resources(struct fm10k_ring *);
+void fm10k_free_rx_resources(struct fm10k_ring *);
+void fm10k_free_tx_resources(struct fm10k_ring *);
+void fm10k_clean_all_rx_rings(struct fm10k_intfc *);
+void fm10k_clean_all_tx_rings(struct fm10k_intfc *);
+void fm10k_unmap_and_free_tx_resource(struct fm10k_ring *,
+				      struct fm10k_tx_buffer *);
+void fm10k_restore_rx_state(struct fm10k_intfc *);
+void fm10k_reset_rx_state(struct fm10k_intfc *);
+int fm10k_setup_tc(struct net_device *dev, u8 tc);
+int fm10k_open(struct net_device *netdev);
+int fm10k_close(struct net_device *netdev);
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface, u32 vid,
+			     u8 vsi, bool set);
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+			    const unsigned char *addr, u16 vid, bool set);
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+			       u16 glort, bool vlans);
+
+/* Ethtool */
+void fm10k_set_ethtool_ops(struct net_device *dev);
+void fm10k_write_reta(struct fm10k_intfc *interface, const u32 *indir);
+
+/* IOV */
+s32 fm10k_iov_event(struct fm10k_intfc *interface);
+s32 fm10k_iov_mbx(struct fm10k_intfc *interface);
+void fm10k_iov_suspend(struct pci_dev *pdev);
+int fm10k_iov_resume(struct pci_dev *pdev);
+void fm10k_iov_disable(struct pci_dev *pdev);
+int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs);
+void fm10k_iov_update_stats(struct fm10k_intfc *interface);
+s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid);
+int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac);
+int fm10k_ndo_set_vf_vlan(struct net_device *netdev,
+			  int vf_idx, u16 vid, u8 qos, __be16 vlan_proto);
+int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
+			int __always_unused min_rate, int max_rate);
+int fm10k_ndo_get_vf_config(struct net_device *netdev,
+			    int vf_idx, struct ifla_vf_info *ivi);
+int fm10k_ndo_get_vf_stats(struct net_device *netdev,
+			   int vf_idx, struct ifla_vf_stats *stats);
+
+/* DebugFS */
+#ifdef CONFIG_DEBUG_FS
+void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector);
+void fm10k_dbg_q_vector_exit(struct fm10k_q_vector *q_vector);
+void fm10k_dbg_intfc_init(struct fm10k_intfc *interface);
+void fm10k_dbg_intfc_exit(struct fm10k_intfc *interface);
+void fm10k_dbg_init(void);
+void fm10k_dbg_exit(void);
+#else
+static inline void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) {}
+static inline void fm10k_dbg_q_vector_exit(struct fm10k_q_vector *q_vector) {}
+static inline void fm10k_dbg_intfc_init(struct fm10k_intfc *interface) {}
+static inline void fm10k_dbg_intfc_exit(struct fm10k_intfc *interface) {}
+static inline void fm10k_dbg_init(void) {}
+static inline void fm10k_dbg_exit(void) {}
+#endif /* CONFIG_DEBUG_FS */
+
+/* DCB */
+#ifdef CONFIG_DCB
+void fm10k_dcbnl_set_ops(struct net_device *dev);
+#else
+static inline void fm10k_dcbnl_set_ops(struct net_device *dev) {}
+#endif
+#endif /* _FM10K_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
new file mode 100644
index 000000000..f51a63fca
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
@@ -0,0 +1,524 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "fm10k_common.h"
+
+/**
+ *  fm10k_get_bus_info_generic - Generic set PCI bus info
+ *  @hw: pointer to hardware structure
+ *
+ *  Gets the PCI bus info (speed, width, type) then calls helper function to
+ *  store this data within the fm10k_hw structure.
+ **/
+s32 fm10k_get_bus_info_generic(struct fm10k_hw *hw)
+{
+	u16 link_cap, link_status, device_cap, device_control;
+
+	/* Get the maximum link width and speed from PCIe config space */
+	link_cap = fm10k_read_pci_cfg_word(hw, FM10K_PCIE_LINK_CAP);
+
+	switch (link_cap & FM10K_PCIE_LINK_WIDTH) {
+	case FM10K_PCIE_LINK_WIDTH_1:
+		hw->bus_caps.width = fm10k_bus_width_pcie_x1;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_2:
+		hw->bus_caps.width = fm10k_bus_width_pcie_x2;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_4:
+		hw->bus_caps.width = fm10k_bus_width_pcie_x4;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_8:
+		hw->bus_caps.width = fm10k_bus_width_pcie_x8;
+		break;
+	default:
+		hw->bus_caps.width = fm10k_bus_width_unknown;
+		break;
+	}
+
+	switch (link_cap & FM10K_PCIE_LINK_SPEED) {
+	case FM10K_PCIE_LINK_SPEED_2500:
+		hw->bus_caps.speed = fm10k_bus_speed_2500;
+		break;
+	case FM10K_PCIE_LINK_SPEED_5000:
+		hw->bus_caps.speed = fm10k_bus_speed_5000;
+		break;
+	case FM10K_PCIE_LINK_SPEED_8000:
+		hw->bus_caps.speed = fm10k_bus_speed_8000;
+		break;
+	default:
+		hw->bus_caps.speed = fm10k_bus_speed_unknown;
+		break;
+	}
+
+	/* Get the PCIe maximum payload size for the PCIe function */
+	device_cap = fm10k_read_pci_cfg_word(hw, FM10K_PCIE_DEV_CAP);
+
+	switch (device_cap & FM10K_PCIE_DEV_CAP_PAYLOAD) {
+	case FM10K_PCIE_DEV_CAP_PAYLOAD_128:
+		hw->bus_caps.payload = fm10k_bus_payload_128;
+		break;
+	case FM10K_PCIE_DEV_CAP_PAYLOAD_256:
+		hw->bus_caps.payload = fm10k_bus_payload_256;
+		break;
+	case FM10K_PCIE_DEV_CAP_PAYLOAD_512:
+		hw->bus_caps.payload = fm10k_bus_payload_512;
+		break;
+	default:
+		hw->bus_caps.payload = fm10k_bus_payload_unknown;
+		break;
+	}
+
+	/* Get the negotiated link width and speed from PCIe config space */
+	link_status = fm10k_read_pci_cfg_word(hw, FM10K_PCIE_LINK_STATUS);
+
+	switch (link_status & FM10K_PCIE_LINK_WIDTH) {
+	case FM10K_PCIE_LINK_WIDTH_1:
+		hw->bus.width = fm10k_bus_width_pcie_x1;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_2:
+		hw->bus.width = fm10k_bus_width_pcie_x2;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_4:
+		hw->bus.width = fm10k_bus_width_pcie_x4;
+		break;
+	case FM10K_PCIE_LINK_WIDTH_8:
+		hw->bus.width = fm10k_bus_width_pcie_x8;
+		break;
+	default:
+		hw->bus.width = fm10k_bus_width_unknown;
+		break;
+	}
+
+	switch (link_status & FM10K_PCIE_LINK_SPEED) {
+	case FM10K_PCIE_LINK_SPEED_2500:
+		hw->bus.speed = fm10k_bus_speed_2500;
+		break;
+	case FM10K_PCIE_LINK_SPEED_5000:
+		hw->bus.speed = fm10k_bus_speed_5000;
+		break;
+	case FM10K_PCIE_LINK_SPEED_8000:
+		hw->bus.speed = fm10k_bus_speed_8000;
+		break;
+	default:
+		hw->bus.speed = fm10k_bus_speed_unknown;
+		break;
+	}
+
+	/* Get the negotiated PCIe maximum payload size for the PCIe function */
+	device_control = fm10k_read_pci_cfg_word(hw, FM10K_PCIE_DEV_CTRL);
+
+	switch (device_control & FM10K_PCIE_DEV_CTRL_PAYLOAD) {
+	case FM10K_PCIE_DEV_CTRL_PAYLOAD_128:
+		hw->bus.payload = fm10k_bus_payload_128;
+		break;
+	case FM10K_PCIE_DEV_CTRL_PAYLOAD_256:
+		hw->bus.payload = fm10k_bus_payload_256;
+		break;
+	case FM10K_PCIE_DEV_CTRL_PAYLOAD_512:
+		hw->bus.payload = fm10k_bus_payload_512;
+		break;
+	default:
+		hw->bus.payload = fm10k_bus_payload_unknown;
+		break;
+	}
+
+	return 0;
+}
+
+static u16 fm10k_get_pcie_msix_count_generic(struct fm10k_hw *hw)
+{
+	u16 msix_count;
+
+	/* read in value from MSI-X capability register */
+	msix_count = fm10k_read_pci_cfg_word(hw, FM10K_PCI_MSIX_MSG_CTRL);
+	msix_count &= FM10K_PCI_MSIX_MSG_CTRL_TBL_SZ_MASK;
+
+	/* MSI-X count is zero-based in HW */
+	msix_count++;
+
+	if (msix_count > FM10K_MAX_MSIX_VECTORS)
+		msix_count = FM10K_MAX_MSIX_VECTORS;
+
+	return msix_count;
+}
+
+/**
+ *  fm10k_get_invariants_generic - Inits constant values
+ *  @hw: pointer to the hardware structure
+ *
+ *  Initialize the common invariants for the device.
+ **/
+s32 fm10k_get_invariants_generic(struct fm10k_hw *hw)
+{
+	struct fm10k_mac_info *mac = &hw->mac;
+
+	/* initialize GLORT state to avoid any false hits */
+	mac->dglort_map = FM10K_DGLORTMAP_NONE;
+
+	/* record maximum number of MSI-X vectors */
+	mac->max_msix_vectors = fm10k_get_pcie_msix_count_generic(hw);
+
+	return 0;
+}
+
+/**
+ *  fm10k_start_hw_generic - Prepare hardware for Tx/Rx
+ *  @hw: pointer to hardware structure
+ *
+ *  This function sets the Tx ready flag to indicate that the Tx path has
+ *  been initialized.
+ **/
+s32 fm10k_start_hw_generic(struct fm10k_hw *hw)
+{
+	/* set flag indicating we are beginning Tx */
+	hw->mac.tx_ready = true;
+
+	return 0;
+}
+
+/**
+ *  fm10k_disable_queues_generic - Stop Tx/Rx queues
+ *  @hw: pointer to hardware structure
+ *  @q_cnt: number of queues to be disabled
+ *
+ **/
+s32 fm10k_disable_queues_generic(struct fm10k_hw *hw, u16 q_cnt)
+{
+	u32 reg;
+	u16 i, time;
+
+	/* clear tx_ready to prevent any false hits for reset */
+	hw->mac.tx_ready = false;
+
+	if (FM10K_REMOVED(hw->hw_addr))
+		return 0;
+
+	/* clear the enable bit for all rings */
+	for (i = 0; i < q_cnt; i++) {
+		reg = fm10k_read_reg(hw, FM10K_TXDCTL(i));
+		fm10k_write_reg(hw, FM10K_TXDCTL(i),
+				reg & ~FM10K_TXDCTL_ENABLE);
+		reg = fm10k_read_reg(hw, FM10K_RXQCTL(i));
+		fm10k_write_reg(hw, FM10K_RXQCTL(i),
+				reg & ~FM10K_RXQCTL_ENABLE);
+	}
+
+	fm10k_write_flush(hw);
+	udelay(1);
+
+	/* loop through all queues to verify that they are all disabled */
+	for (i = 0, time = FM10K_QUEUE_DISABLE_TIMEOUT; time;) {
+		/* if we are at end of rings all rings are disabled */
+		if (i == q_cnt)
+			return 0;
+
+		/* if queue enables cleared, then move to next ring pair */
+		reg = fm10k_read_reg(hw, FM10K_TXDCTL(i));
+		if (!~reg || !(reg & FM10K_TXDCTL_ENABLE)) {
+			reg = fm10k_read_reg(hw, FM10K_RXQCTL(i));
+			if (!~reg || !(reg & FM10K_RXQCTL_ENABLE)) {
+				i++;
+				continue;
+			}
+		}
+
+		/* decrement time and wait 1 usec */
+		time--;
+		if (time)
+			udelay(1);
+	}
+
+	return FM10K_ERR_REQUESTS_PENDING;
+}
+
+/**
+ *  fm10k_stop_hw_generic - Stop Tx/Rx units
+ *  @hw: pointer to hardware structure
+ *
+ **/
+s32 fm10k_stop_hw_generic(struct fm10k_hw *hw)
+{
+	return fm10k_disable_queues_generic(hw, hw->mac.max_queues);
+}
+
+/**
+ *  fm10k_read_hw_stats_32b - Reads value of 32-bit registers
+ *  @hw: pointer to the hardware structure
+ *  @addr: address of register containing a 32-bit value
+ *  @stat: pointer to structure holding hw stat information
+ *
+ *  Function reads the content of the register and returns the delta
+ *  between the base and the current value.
+ *  **/
+u32 fm10k_read_hw_stats_32b(struct fm10k_hw *hw, u32 addr,
+			    struct fm10k_hw_stat *stat)
+{
+	u32 delta = fm10k_read_reg(hw, addr) - stat->base_l;
+
+	if (FM10K_REMOVED(hw->hw_addr))
+		stat->base_h = 0;
+
+	return delta;
+}
+
+/**
+ *  fm10k_read_hw_stats_48b - Reads value of 48-bit registers
+ *  @hw: pointer to the hardware structure
+ *  @addr: address of register containing the lower 32-bit value
+ *  @stat: pointer to structure holding hw stat information
+ *
+ *  Function reads the content of 2 registers, combined to represent a 48-bit
+ *  statistical value. Extra processing is required to handle overflowing.
+ *  Finally, a delta value is returned representing the difference between the
+ *  values stored in registers and values stored in the statistic counters.
+ *  **/
+static u64 fm10k_read_hw_stats_48b(struct fm10k_hw *hw, u32 addr,
+				   struct fm10k_hw_stat *stat)
+{
+	u32 count_l;
+	u32 count_h;
+	u32 count_tmp;
+	u64 delta;
+
+	count_h = fm10k_read_reg(hw, addr + 1);
+
+	/* Check for overflow */
+	do {
+		count_tmp = count_h;
+		count_l = fm10k_read_reg(hw, addr);
+		count_h = fm10k_read_reg(hw, addr + 1);
+	} while (count_h != count_tmp);
+
+	delta = ((u64)(count_h - stat->base_h) << 32) + count_l;
+	delta -= stat->base_l;
+
+	return delta & FM10K_48_BIT_MASK;
+}
+
+/**
+ *  fm10k_update_hw_base_48b - Updates 48-bit statistic base value
+ *  @stat: pointer to the hardware statistic structure
+ *  @delta: value to be updated into the hardware statistic structure
+ *
+ *  Function receives a value and determines if an update is required based on
+ *  a delta calculation. Only the base value will be updated.
+ **/
+static void fm10k_update_hw_base_48b(struct fm10k_hw_stat *stat, u64 delta)
+{
+	if (!delta)
+		return;
+
+	/* update lower 32 bits */
+	delta += stat->base_l;
+	stat->base_l = (u32)delta;
+
+	/* update upper 32 bits */
+	stat->base_h += (u32)(delta >> 32);
+}
+
+/**
+ *  fm10k_update_hw_stats_tx_q - Updates TX queue statistics counters
+ *  @hw: pointer to the hardware structure
+ *  @q: pointer to the ring of hardware statistics queue
+ *  @idx: index pointing to the start of the ring iteration
+ *
+ *  Function updates the TX queue statistics counters that are related to the
+ *  hardware.
+ **/
+static void fm10k_update_hw_stats_tx_q(struct fm10k_hw *hw,
+				       struct fm10k_hw_stats_q *q,
+				       u32 idx)
+{
+	u32 id_tx, id_tx_prev, tx_packets;
+	u64 tx_bytes = 0;
+
+	/* Retrieve TX Owner Data */
+	id_tx = fm10k_read_reg(hw, FM10K_TXQCTL(idx));
+
+	/* Process TX Ring */
+	do {
+		tx_packets = fm10k_read_hw_stats_32b(hw, FM10K_QPTC(idx),
+						     &q->tx_packets);
+
+		if (tx_packets)
+			tx_bytes = fm10k_read_hw_stats_48b(hw,
+							   FM10K_QBTC_L(idx),
+							   &q->tx_bytes);
+
+		/* Re-Check Owner Data */
+		id_tx_prev = id_tx;
+		id_tx = fm10k_read_reg(hw, FM10K_TXQCTL(idx));
+	} while ((id_tx ^ id_tx_prev) & FM10K_TXQCTL_ID_MASK);
+
+	/* drop non-ID bits and set VALID ID bit */
+	id_tx &= FM10K_TXQCTL_ID_MASK;
+	id_tx |= FM10K_STAT_VALID;
+
+	/* update packet counts */
+	if (q->tx_stats_idx == id_tx) {
+		q->tx_packets.count += tx_packets;
+		q->tx_bytes.count += tx_bytes;
+	}
+
+	/* update bases and record ID */
+	fm10k_update_hw_base_32b(&q->tx_packets, tx_packets);
+	fm10k_update_hw_base_48b(&q->tx_bytes, tx_bytes);
+
+	q->tx_stats_idx = id_tx;
+}
+
+/**
+ *  fm10k_update_hw_stats_rx_q - Updates RX queue statistics counters
+ *  @hw: pointer to the hardware structure
+ *  @q: pointer to the ring of hardware statistics queue
+ *  @idx: index pointing to the start of the ring iteration
+ *
+ *  Function updates the RX queue statistics counters that are related to the
+ *  hardware.
+ **/
+static void fm10k_update_hw_stats_rx_q(struct fm10k_hw *hw,
+				       struct fm10k_hw_stats_q *q,
+				       u32 idx)
+{
+	u32 id_rx, id_rx_prev, rx_packets, rx_drops;
+	u64 rx_bytes = 0;
+
+	/* Retrieve RX Owner Data */
+	id_rx = fm10k_read_reg(hw, FM10K_RXQCTL(idx));
+
+	/* Process RX Ring */
+	do {
+		rx_drops = fm10k_read_hw_stats_32b(hw, FM10K_QPRDC(idx),
+						   &q->rx_drops);
+
+		rx_packets = fm10k_read_hw_stats_32b(hw, FM10K_QPRC(idx),
+						     &q->rx_packets);
+
+		if (rx_packets)
+			rx_bytes = fm10k_read_hw_stats_48b(hw,
+							   FM10K_QBRC_L(idx),
+							   &q->rx_bytes);
+
+		/* Re-Check Owner Data */
+		id_rx_prev = id_rx;
+		id_rx = fm10k_read_reg(hw, FM10K_RXQCTL(idx));
+	} while ((id_rx ^ id_rx_prev) & FM10K_RXQCTL_ID_MASK);
+
+	/* drop non-ID bits and set VALID ID bit */
+	id_rx &= FM10K_RXQCTL_ID_MASK;
+	id_rx |= FM10K_STAT_VALID;
+
+	/* update packet counts */
+	if (q->rx_stats_idx == id_rx) {
+		q->rx_drops.count += rx_drops;
+		q->rx_packets.count += rx_packets;
+		q->rx_bytes.count += rx_bytes;
+	}
+
+	/* update bases and record ID */
+	fm10k_update_hw_base_32b(&q->rx_drops, rx_drops);
+	fm10k_update_hw_base_32b(&q->rx_packets, rx_packets);
+	fm10k_update_hw_base_48b(&q->rx_bytes, rx_bytes);
+
+	q->rx_stats_idx = id_rx;
+}
+
+/**
+ *  fm10k_update_hw_stats_q - Updates queue statistics counters
+ *  @hw: pointer to the hardware structure
+ *  @q: pointer to the ring of hardware statistics queue
+ *  @idx: index pointing to the start of the ring iteration
+ *  @count: number of queues to iterate over
+ *
+ *  Function updates the queue statistics counters that are related to the
+ *  hardware.
+ **/
+void fm10k_update_hw_stats_q(struct fm10k_hw *hw, struct fm10k_hw_stats_q *q,
+			     u32 idx, u32 count)
+{
+	u32 i;
+
+	for (i = 0; i < count; i++, idx++, q++) {
+		fm10k_update_hw_stats_tx_q(hw, q, idx);
+		fm10k_update_hw_stats_rx_q(hw, q, idx);
+	}
+}
+
+/**
+ *  fm10k_unbind_hw_stats_q - Unbind the queue counters from their queues
+ *  @q: pointer to the ring of hardware statistics queue
+ *  @idx: index pointing to the start of the ring iteration
+ *  @count: number of queues to iterate over
+ *
+ *  Function invalidates the index values for the queues so any updates that
+ *  may have happened are ignored and the base for the queue stats is reset.
+ **/
+void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 idx, u32 count)
+{
+	u32 i;
+
+	for (i = 0; i < count; i++, idx++, q++) {
+		q->rx_stats_idx = 0;
+		q->tx_stats_idx = 0;
+	}
+}
+
+/**
+ *  fm10k_get_host_state_generic - Returns the state of the host
+ *  @hw: pointer to hardware structure
+ *  @host_ready: pointer to boolean value that will record host state
+ *
+ *  This function will check the health of the mailbox and Tx queue 0
+ *  in order to determine if we should report that the link is up or not.
+ **/
+s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	struct fm10k_mac_info *mac = &hw->mac;
+	s32 ret_val = 0;
+	u32 txdctl = fm10k_read_reg(hw, FM10K_TXDCTL(0));
+
+	/* process upstream mailbox in case interrupts were disabled */
+	mbx->ops.process(hw, mbx);
+
+	/* If Tx is no longer enabled link should come down */
+	if (!(~txdctl) || !(txdctl & FM10K_TXDCTL_ENABLE))
+		mac->get_host_state = true;
+
+	/* exit if not checking for link, or link cannot be changed */
+	if (!mac->get_host_state || !(~txdctl))
+		goto out;
+
+	/* if we somehow dropped the Tx enable we should reset */
+	if (mac->tx_ready && !(txdctl & FM10K_TXDCTL_ENABLE)) {
+		ret_val = FM10K_ERR_RESET_REQUESTED;
+		goto out;
+	}
+
+	/* if Mailbox timed out we should request reset */
+	if (!mbx->timeout) {
+		ret_val = FM10K_ERR_RESET_REQUESTED;
+		goto out;
+	}
+
+	/* verify Mailbox is still open */
+	if (mbx->state != FM10K_STATE_OPEN)
+		goto out;
+
+	/* interface cannot receive traffic without logical ports */
+	if (mac->dglort_map == FM10K_DGLORTMAP_NONE) {
+		if (mac->ops.request_lport_map)
+			ret_val = mac->ops.request_lport_map(hw);
+
+		goto out;
+	}
+
+	/* if we passed all the tests above then the switch is ready and we no
+	 * longer need to check for link
+	 */
+	mac->get_host_state = false;
+
+out:
+	*host_ready = !mac->get_host_state;
+	return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.h b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
new file mode 100644
index 000000000..4c48fb73b
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _FM10K_COMMON_H_
+#define _FM10K_COMMON_H_
+
+#include "fm10k_type.h"
+
+#define FM10K_REMOVED(hw_addr) unlikely(!(hw_addr))
+
+/* PCI configuration read */
+u16 fm10k_read_pci_cfg_word(struct fm10k_hw *hw, u32 reg);
+
+/* read operations, indexed using DWORDS */
+u32 fm10k_read_reg(struct fm10k_hw *hw, int reg);
+
+/* write operations, indexed using DWORDS */
+#define fm10k_write_reg(hw, reg, val) \
+do { \
+	u32 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
+	if (!FM10K_REMOVED(hw_addr)) \
+		writel((val), &hw_addr[(reg)]); \
+} while (0)
+
+/* Switch register write operations, index using DWORDS */
+#define fm10k_write_sw_reg(hw, reg, val) \
+do { \
+	u32 __iomem *sw_addr = READ_ONCE((hw)->sw_addr); \
+	if (!FM10K_REMOVED(sw_addr)) \
+		writel((val), &sw_addr[(reg)]); \
+} while (0)
+
+/* read ctrl register which has no clear on read fields as PCIe flush */
+#define fm10k_write_flush(hw) fm10k_read_reg((hw), FM10K_CTRL)
+s32 fm10k_get_bus_info_generic(struct fm10k_hw *hw);
+s32 fm10k_get_invariants_generic(struct fm10k_hw *hw);
+s32 fm10k_disable_queues_generic(struct fm10k_hw *hw, u16 q_cnt);
+s32 fm10k_start_hw_generic(struct fm10k_hw *hw);
+s32 fm10k_stop_hw_generic(struct fm10k_hw *hw);
+u32 fm10k_read_hw_stats_32b(struct fm10k_hw *hw, u32 addr,
+			    struct fm10k_hw_stat *stat);
+#define fm10k_update_hw_base_32b(stat, delta) ((stat)->base_l += (delta))
+void fm10k_update_hw_stats_q(struct fm10k_hw *hw, struct fm10k_hw_stats_q *q,
+			     u32 idx, u32 count);
+#define fm10k_unbind_hw_stats_32b(s) ((s)->base_h = 0)
+void fm10k_unbind_hw_stats_q(struct fm10k_hw_stats_q *q, u32 idx, u32 count);
+s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready);
+#endif /* _FM10K_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
new file mode 100644
index 000000000..86397c564
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k.h"
+
+/**
+ * fm10k_dcbnl_ieee_getets - get the ETS configuration for the device
+ * @dev: netdev interface for the device
+ * @ets: ETS structure to push configuration to
+ **/
+static int fm10k_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
+{
+	int i;
+
+	/* we support 8 TCs in all modes */
+	ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
+	ets->cbs = 0;
+
+	/* we only support strict priority and cannot do traffic shaping */
+	memset(ets->tc_tx_bw, 0, sizeof(ets->tc_tx_bw));
+	memset(ets->tc_rx_bw, 0, sizeof(ets->tc_rx_bw));
+	memset(ets->tc_tsa, IEEE_8021QAZ_TSA_STRICT, sizeof(ets->tc_tsa));
+
+	/* populate the prio map based on the netdev */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		ets->prio_tc[i] = netdev_get_prio_tc_map(dev, i);
+
+	return 0;
+}
+
+/**
+ * fm10k_dcbnl_ieee_setets - set the ETS configuration for the device
+ * @dev: netdev interface for the device
+ * @ets: ETS structure to pull configuration from
+ **/
+static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
+{
+	u8 num_tc = 0;
+	int i;
+
+	/* verify type and determine num_tcs needed */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (ets->tc_tx_bw[i] || ets->tc_rx_bw[i])
+			return -EINVAL;
+		if (ets->tc_tsa[i] != IEEE_8021QAZ_TSA_STRICT)
+			return -EINVAL;
+		if (ets->prio_tc[i] > num_tc)
+			num_tc = ets->prio_tc[i];
+	}
+
+	/* if requested TC is greater than 0 then num_tcs is max + 1 */
+	if (num_tc)
+		num_tc++;
+
+	if (num_tc > IEEE_8021QAZ_MAX_TCS)
+		return -EINVAL;
+
+	/* update TC hardware mapping if necessary */
+	if (num_tc != netdev_get_num_tc(dev)) {
+		int err = fm10k_setup_tc(dev, num_tc);
+		if (err)
+			return err;
+	}
+
+	/* update priority mapping */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		netdev_set_prio_tc_map(dev, i, ets->prio_tc[i]);
+
+	return 0;
+}
+
+/**
+ * fm10k_dcbnl_ieee_getpfc - get the PFC configuration for the device
+ * @dev: netdev interface for the device
+ * @pfc: PFC structure to push configuration to
+ **/
+static int fm10k_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	/* record flow control max count and state of TCs */
+	pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc->pfc_en = interface->pfc_en;
+
+	return 0;
+}
+
+/**
+ * fm10k_dcbnl_ieee_setpfc - set the PFC configuration for the device
+ * @dev: netdev interface for the device
+ * @pfc: PFC structure to pull configuration from
+ **/
+static int fm10k_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	/* record PFC configuration to interface */
+	interface->pfc_en = pfc->pfc_en;
+
+	/* if we are running update the drop_en state for all queues */
+	if (netif_running(dev))
+		fm10k_update_rx_drop_en(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_dcbnl_getdcbx - get the DCBX configuration for the device
+ * @dev: netdev interface for the device
+ *
+ * Returns that we support only IEEE DCB for this interface
+ **/
+static u8 fm10k_dcbnl_getdcbx(struct net_device __always_unused *dev)
+{
+	return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+}
+
+/**
+ * fm10k_dcbnl_setdcbx - get the DCBX configuration for the device
+ * @dev: netdev interface for the device
+ * @mode: new mode for this device
+ *
+ * Returns error on attempt to enable anything but IEEE DCB for this interface
+ **/
+static u8 fm10k_dcbnl_setdcbx(struct net_device __always_unused *dev, u8 mode)
+{
+	return (mode != (DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE)) ? 1 : 0;
+}
+
+static const struct dcbnl_rtnl_ops fm10k_dcbnl_ops = {
+	.ieee_getets	= fm10k_dcbnl_ieee_getets,
+	.ieee_setets	= fm10k_dcbnl_ieee_setets,
+	.ieee_getpfc	= fm10k_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= fm10k_dcbnl_ieee_setpfc,
+
+	.getdcbx	= fm10k_dcbnl_getdcbx,
+	.setdcbx	= fm10k_dcbnl_setdcbx,
+};
+
+/**
+ * fm10k_dcbnl_set_ops - Configures dcbnl ops pointer for netdev
+ * @dev: netdev interface for the device
+ *
+ * Enables PF for DCB by assigning DCBNL ops pointer.
+ **/
+void fm10k_dcbnl_set_ops(struct net_device *dev)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+
+	if (hw->mac.type == fm10k_mac_pf)
+		dev->dcbnl_ops = &fm10k_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
new file mode 100644
index 000000000..5c77054d6
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "fm10k.h"
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static struct dentry *dbg_root;
+
+/* Descriptor Seq Functions */
+
+static void *fm10k_dbg_desc_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct fm10k_ring *ring = s->private;
+
+	return (*pos < ring->count) ? pos : NULL;
+}
+
+static void *fm10k_dbg_desc_seq_next(struct seq_file *s,
+				     void __always_unused *v,
+				     loff_t *pos)
+{
+	struct fm10k_ring *ring = s->private;
+
+	return (++(*pos) < ring->count) ? pos : NULL;
+}
+
+static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s,
+				    void __always_unused *v)
+{
+	/* Do nothing. */
+}
+
+static void fm10k_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static int fm10k_dbg_tx_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fm10k_ring *ring = s->private;
+	int i = *(loff_t *)v;
+	static const char tx_desc_hdr[] =
+		"DES BUFFER_ADDRESS     LENGTH VLAN   MSS    HDRLEN FLAGS\n";
+
+	/* Generate header */
+	if (!i) {
+		seq_printf(s, tx_desc_hdr);
+		fm10k_dbg_desc_break(s, sizeof(tx_desc_hdr) - 1);
+	}
+
+	/* Validate descriptor allocation */
+	if (!ring->desc) {
+		seq_printf(s, "%03X Descriptor ring not allocated.\n", i);
+	} else {
+		struct fm10k_tx_desc *txd = FM10K_TX_DESC(ring, i);
+
+		seq_printf(s, "%03X %#018llx %#06x %#06x %#06x %#06x %#04x\n",
+			   i, txd->buffer_addr, txd->buflen, txd->vlan,
+			   txd->mss, txd->hdrlen, txd->flags);
+	}
+
+	return 0;
+}
+
+static int fm10k_dbg_rx_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fm10k_ring *ring = s->private;
+	int i = *(loff_t *)v;
+	static const char rx_desc_hdr[] =
+	"DES DATA       RSS        STATERR    LENGTH VLAN   DGLORT SGLORT TIMESTAMP\n";
+
+	/* Generate header */
+	if (!i) {
+		seq_printf(s, rx_desc_hdr);
+		fm10k_dbg_desc_break(s, sizeof(rx_desc_hdr) - 1);
+	}
+
+	/* Validate descriptor allocation */
+	if (!ring->desc) {
+		seq_printf(s, "%03X Descriptor ring not allocated.\n", i);
+	} else {
+		union fm10k_rx_desc *rxd = FM10K_RX_DESC(ring, i);
+
+		seq_printf(s,
+			   "%03X %#010x %#010x %#010x %#06x %#06x %#06x %#06x %#018llx\n",
+			   i, rxd->d.data, rxd->d.rss, rxd->d.staterr,
+			   rxd->w.length, rxd->w.vlan, rxd->w.dglort,
+			   rxd->w.sglort, rxd->q.timestamp);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations fm10k_dbg_tx_desc_seq_ops = {
+	.start = fm10k_dbg_desc_seq_start,
+	.next  = fm10k_dbg_desc_seq_next,
+	.stop  = fm10k_dbg_desc_seq_stop,
+	.show  = fm10k_dbg_tx_desc_seq_show,
+};
+
+static const struct seq_operations fm10k_dbg_rx_desc_seq_ops = {
+	.start = fm10k_dbg_desc_seq_start,
+	.next  = fm10k_dbg_desc_seq_next,
+	.stop  = fm10k_dbg_desc_seq_stop,
+	.show  = fm10k_dbg_rx_desc_seq_show,
+};
+
+static int fm10k_dbg_desc_open(struct inode *inode, struct file *filep)
+{
+	struct fm10k_ring *ring = inode->i_private;
+	struct fm10k_q_vector *q_vector = ring->q_vector;
+	const struct seq_operations *desc_seq_ops;
+	int err;
+
+	if (ring < q_vector->rx.ring)
+		desc_seq_ops = &fm10k_dbg_tx_desc_seq_ops;
+	else
+		desc_seq_ops = &fm10k_dbg_rx_desc_seq_ops;
+
+	err = seq_open(filep, desc_seq_ops);
+	if (err)
+		return err;
+
+	((struct seq_file *)filep->private_data)->private = ring;
+
+	return 0;
+}
+
+static const struct file_operations fm10k_dbg_desc_fops = {
+	.owner   = THIS_MODULE,
+	.open    = fm10k_dbg_desc_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+/**
+ * fm10k_dbg_q_vector_init - setup debugfs for the q_vectors
+ * @q_vector: q_vector to allocate directories for
+ *
+ * A folder is created for each q_vector found. In each q_vector
+ * folder, a debugfs file is created for each tx and rx ring
+ * allocated to the q_vector.
+ **/
+void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector)
+{
+	struct fm10k_intfc *interface = q_vector->interface;
+	char name[16];
+	int i;
+
+	if (!interface->dbg_intfc)
+		return;
+
+	/* Generate a folder for each q_vector */
+	snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx);
+
+	q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc);
+
+	/* Generate a file for each rx ring in the q_vector */
+	for (i = 0; i < q_vector->tx.count; i++) {
+		struct fm10k_ring *ring = &q_vector->tx.ring[i];
+
+		snprintf(name, sizeof(name), "tx_ring.%03d", ring->queue_index);
+
+		debugfs_create_file(name, 0600,
+				    q_vector->dbg_q_vector, ring,
+				    &fm10k_dbg_desc_fops);
+	}
+
+	/* Generate a file for each rx ring in the q_vector */
+	for (i = 0; i < q_vector->rx.count; i++) {
+		struct fm10k_ring *ring = &q_vector->rx.ring[i];
+
+		snprintf(name, sizeof(name), "rx_ring.%03d", ring->queue_index);
+
+		debugfs_create_file(name, 0600,
+				    q_vector->dbg_q_vector, ring,
+				    &fm10k_dbg_desc_fops);
+	}
+}
+
+/**
+ * fm10k_dbg_q_vector_exit - setup debugfs for the q_vectors
+ * @q_vector: q_vector to allocate directories for
+ **/
+void fm10k_dbg_q_vector_exit(struct fm10k_q_vector *q_vector)
+{
+	struct fm10k_intfc *interface = q_vector->interface;
+
+	if (interface->dbg_intfc)
+		debugfs_remove_recursive(q_vector->dbg_q_vector);
+	q_vector->dbg_q_vector = NULL;
+}
+
+/**
+ * fm10k_dbg_intfc_init - setup the debugfs directory for the intferface
+ * @interface: the interface that is starting up
+ **/
+
+void fm10k_dbg_intfc_init(struct fm10k_intfc *interface)
+{
+	const char *name = pci_name(interface->pdev);
+
+	if (dbg_root)
+		interface->dbg_intfc = debugfs_create_dir(name, dbg_root);
+}
+
+/**
+ * fm10k_dbg_intfc_exit - clean out the interface's debugfs entries
+ * @interface: the interface that is stopping
+ **/
+void fm10k_dbg_intfc_exit(struct fm10k_intfc *interface)
+{
+	if (dbg_root)
+		debugfs_remove_recursive(interface->dbg_intfc);
+	interface->dbg_intfc = NULL;
+}
+
+/**
+ * fm10k_dbg_init - start up debugfs for the driver
+ **/
+void fm10k_dbg_init(void)
+{
+	dbg_root = debugfs_create_dir(fm10k_driver_name, NULL);
+}
+
+/**
+ * fm10k_dbg_exit - clean out the driver's debugfs entries
+ **/
+void fm10k_dbg_exit(void)
+{
+	debugfs_remove_recursive(dbg_root);
+	dbg_root = NULL;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
new file mode 100644
index 000000000..d53369e30
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -0,0 +1,1195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include <linux/ethtool.h>
+#include <linux/vmalloc.h>
+
+#include "fm10k.h"
+
+struct fm10k_stats {
+	/* The stat_string is expected to be a format string formatted using
+	 * vsnprintf by fm10k_add_stat_strings. Every member of a stats array
+	 * should use the same format specifiers as they will be formatted
+	 * using the same variadic arguments.
+	 */
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define FM10K_STAT_FIELDS(_type, _name, _stat) { \
+	.stat_string = _name, \
+	.sizeof_stat = sizeof_field(_type, _stat), \
+	.stat_offset = offsetof(_type, _stat) \
+}
+
+/* netdevice statistics */
+#define FM10K_NETDEV_STAT(_net_stat) \
+	FM10K_STAT_FIELDS(struct net_device_stats, __stringify(_net_stat), \
+			  _net_stat)
+
+static const struct fm10k_stats fm10k_gstrings_net_stats[] = {
+	FM10K_NETDEV_STAT(tx_packets),
+	FM10K_NETDEV_STAT(tx_bytes),
+	FM10K_NETDEV_STAT(tx_errors),
+	FM10K_NETDEV_STAT(rx_packets),
+	FM10K_NETDEV_STAT(rx_bytes),
+	FM10K_NETDEV_STAT(rx_errors),
+	FM10K_NETDEV_STAT(rx_dropped),
+
+	/* detailed Rx errors */
+	FM10K_NETDEV_STAT(rx_length_errors),
+	FM10K_NETDEV_STAT(rx_crc_errors),
+	FM10K_NETDEV_STAT(rx_fifo_errors),
+};
+
+#define FM10K_NETDEV_STATS_LEN	ARRAY_SIZE(fm10k_gstrings_net_stats)
+
+/* General interface statistics */
+#define FM10K_STAT(_name, _stat) \
+	FM10K_STAT_FIELDS(struct fm10k_intfc, _name, _stat)
+
+static const struct fm10k_stats fm10k_gstrings_global_stats[] = {
+	FM10K_STAT("tx_restart_queue", restart_queue),
+	FM10K_STAT("tx_busy", tx_busy),
+	FM10K_STAT("tx_csum_errors", tx_csum_errors),
+	FM10K_STAT("rx_alloc_failed", alloc_failed),
+	FM10K_STAT("rx_csum_errors", rx_csum_errors),
+
+	FM10K_STAT("tx_packets_nic", tx_packets_nic),
+	FM10K_STAT("tx_bytes_nic", tx_bytes_nic),
+	FM10K_STAT("rx_packets_nic", rx_packets_nic),
+	FM10K_STAT("rx_bytes_nic", rx_bytes_nic),
+	FM10K_STAT("rx_drops_nic", rx_drops_nic),
+	FM10K_STAT("rx_overrun_pf", rx_overrun_pf),
+	FM10K_STAT("rx_overrun_vf", rx_overrun_vf),
+
+	FM10K_STAT("swapi_status", hw.swapi.status),
+	FM10K_STAT("mac_rules_used", hw.swapi.mac.used),
+	FM10K_STAT("mac_rules_avail", hw.swapi.mac.avail),
+
+	FM10K_STAT("reset_while_pending", hw.mac.reset_while_pending),
+
+	FM10K_STAT("tx_hang_count", tx_timeout_count),
+};
+
+static const struct fm10k_stats fm10k_gstrings_pf_stats[] = {
+	FM10K_STAT("timeout", stats.timeout.count),
+	FM10K_STAT("ur", stats.ur.count),
+	FM10K_STAT("ca", stats.ca.count),
+	FM10K_STAT("um", stats.um.count),
+	FM10K_STAT("xec", stats.xec.count),
+	FM10K_STAT("vlan_drop", stats.vlan_drop.count),
+	FM10K_STAT("loopback_drop", stats.loopback_drop.count),
+	FM10K_STAT("nodesc_drop", stats.nodesc_drop.count),
+};
+
+/* mailbox statistics */
+#define FM10K_MBX_STAT(_name, _stat) \
+	FM10K_STAT_FIELDS(struct fm10k_mbx_info, _name, _stat)
+
+static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = {
+	FM10K_MBX_STAT("mbx_tx_busy", tx_busy),
+	FM10K_MBX_STAT("mbx_tx_dropped", tx_dropped),
+	FM10K_MBX_STAT("mbx_tx_messages", tx_messages),
+	FM10K_MBX_STAT("mbx_tx_dwords", tx_dwords),
+	FM10K_MBX_STAT("mbx_tx_mbmem_pulled", tx_mbmem_pulled),
+	FM10K_MBX_STAT("mbx_rx_messages", rx_messages),
+	FM10K_MBX_STAT("mbx_rx_dwords", rx_dwords),
+	FM10K_MBX_STAT("mbx_rx_parse_err", rx_parse_err),
+	FM10K_MBX_STAT("mbx_rx_mbmem_pushed", rx_mbmem_pushed),
+};
+
+/* per-queue ring statistics */
+#define FM10K_QUEUE_STAT(_name, _stat) \
+	FM10K_STAT_FIELDS(struct fm10k_ring, _name, _stat)
+
+static const struct fm10k_stats fm10k_gstrings_queue_stats[] = {
+	FM10K_QUEUE_STAT("%s_queue_%u_packets", stats.packets),
+	FM10K_QUEUE_STAT("%s_queue_%u_bytes", stats.bytes),
+};
+
+#define FM10K_GLOBAL_STATS_LEN ARRAY_SIZE(fm10k_gstrings_global_stats)
+#define FM10K_PF_STATS_LEN ARRAY_SIZE(fm10k_gstrings_pf_stats)
+#define FM10K_MBX_STATS_LEN ARRAY_SIZE(fm10k_gstrings_mbx_stats)
+#define FM10K_QUEUE_STATS_LEN ARRAY_SIZE(fm10k_gstrings_queue_stats)
+
+#define FM10K_STATIC_STATS_LEN (FM10K_GLOBAL_STATS_LEN + \
+				FM10K_NETDEV_STATS_LEN + \
+				FM10K_MBX_STATS_LEN)
+
+static const char fm10k_gstrings_test[][ETH_GSTRING_LEN] = {
+	"Mailbox test (on/offline)"
+};
+
+#define FM10K_TEST_LEN (sizeof(fm10k_gstrings_test) / ETH_GSTRING_LEN)
+
+enum fm10k_self_test_types {
+	FM10K_TEST_MBX,
+	FM10K_TEST_MAX = FM10K_TEST_LEN
+};
+
+enum {
+	FM10K_PRV_FLAG_LEN,
+};
+
+static const char fm10k_prv_flags[FM10K_PRV_FLAG_LEN][ETH_GSTRING_LEN] = {
+};
+
+static void __fm10k_add_stat_strings(u8 **p, const struct fm10k_stats stats[],
+				     const unsigned int size, ...)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++) {
+		va_list args;
+
+		va_start(args, size);
+		vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
+		*p += ETH_GSTRING_LEN;
+		va_end(args);
+	}
+}
+
+#define fm10k_add_stat_strings(p, stats, ...) \
+	__fm10k_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
+
+static void fm10k_get_stat_strings(struct net_device *dev, u8 *data)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	unsigned int i;
+
+	fm10k_add_stat_strings(&data, fm10k_gstrings_net_stats);
+
+	fm10k_add_stat_strings(&data, fm10k_gstrings_global_stats);
+
+	fm10k_add_stat_strings(&data, fm10k_gstrings_mbx_stats);
+
+	if (interface->hw.mac.type != fm10k_mac_vf)
+		fm10k_add_stat_strings(&data, fm10k_gstrings_pf_stats);
+
+	for (i = 0; i < interface->hw.mac.max_queues; i++) {
+		fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats,
+				       "tx", i);
+
+		fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats,
+				       "rx", i);
+	}
+}
+
+static void fm10k_get_strings(struct net_device *dev,
+			      u32 stringset, u8 *data)
+{
+	switch (stringset) {
+	case ETH_SS_TEST:
+		memcpy(data, fm10k_gstrings_test,
+		       FM10K_TEST_LEN * ETH_GSTRING_LEN);
+		break;
+	case ETH_SS_STATS:
+		fm10k_get_stat_strings(dev, data);
+		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, fm10k_prv_flags,
+		       FM10K_PRV_FLAG_LEN * ETH_GSTRING_LEN);
+		break;
+	}
+}
+
+static int fm10k_get_sset_count(struct net_device *dev, int sset)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+	int stats_len = FM10K_STATIC_STATS_LEN;
+
+	switch (sset) {
+	case ETH_SS_TEST:
+		return FM10K_TEST_LEN;
+	case ETH_SS_STATS:
+		stats_len += hw->mac.max_queues * 2 * FM10K_QUEUE_STATS_LEN;
+
+		if (hw->mac.type != fm10k_mac_vf)
+			stats_len += FM10K_PF_STATS_LEN;
+
+		return stats_len;
+	case ETH_SS_PRIV_FLAGS:
+		return FM10K_PRV_FLAG_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void __fm10k_add_ethtool_stats(u64 **data, void *pointer,
+				      const struct fm10k_stats stats[],
+				      const unsigned int size)
+{
+	unsigned int i;
+
+	if (!pointer) {
+		/* memory is not zero allocated so we have to clear it */
+		for (i = 0; i < size; i++)
+			*((*data)++) = 0;
+		return;
+	}
+
+	for (i = 0; i < size; i++) {
+		char *p = (char *)pointer + stats[i].stat_offset;
+
+		switch (stats[i].sizeof_stat) {
+		case sizeof(u64):
+			*((*data)++) = *(u64 *)p;
+			break;
+		case sizeof(u32):
+			*((*data)++) = *(u32 *)p;
+			break;
+		case sizeof(u16):
+			*((*data)++) = *(u16 *)p;
+			break;
+		case sizeof(u8):
+			*((*data)++) = *(u8 *)p;
+			break;
+		default:
+			WARN_ONCE(1, "unexpected stat size for %s",
+				  stats[i].stat_string);
+			*((*data)++) = 0;
+		}
+	}
+}
+
+#define fm10k_add_ethtool_stats(data, pointer, stats) \
+	__fm10k_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
+static void fm10k_get_ethtool_stats(struct net_device *netdev,
+				    struct ethtool_stats __always_unused *stats,
+				    u64 *data)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct net_device_stats *net_stats = &netdev->stats;
+	int i;
+
+	fm10k_update_stats(interface);
+
+	fm10k_add_ethtool_stats(&data, net_stats, fm10k_gstrings_net_stats);
+
+	fm10k_add_ethtool_stats(&data, interface, fm10k_gstrings_global_stats);
+
+	fm10k_add_ethtool_stats(&data, &interface->hw.mbx,
+				fm10k_gstrings_mbx_stats);
+
+	if (interface->hw.mac.type != fm10k_mac_vf) {
+		fm10k_add_ethtool_stats(&data, interface,
+					fm10k_gstrings_pf_stats);
+	}
+
+	for (i = 0; i < interface->hw.mac.max_queues; i++) {
+		struct fm10k_ring *ring;
+
+		ring = interface->tx_ring[i];
+		fm10k_add_ethtool_stats(&data, ring,
+					fm10k_gstrings_queue_stats);
+
+		ring = interface->rx_ring[i];
+		fm10k_add_ethtool_stats(&data, ring,
+					fm10k_gstrings_queue_stats);
+	}
+}
+
+/* If function below adds more registers this define needs to be updated */
+#define FM10K_REGS_LEN_Q 29
+
+static void fm10k_get_reg_q(struct fm10k_hw *hw, u32 *buff, int i)
+{
+	int idx = 0;
+
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RDBAL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RDBAH(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RDLEN(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TPH_RXCTRL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RDH(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RDT(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RXQCTL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RXDCTL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_RXINT(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_SRRCTL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QPRC(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QPRDC(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QBRC_L(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QBRC_H(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TDBAL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TDBAH(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TDLEN(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TPH_TXCTRL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TDH(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TDT(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TXDCTL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TXQCTL(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TXINT(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QPTC(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QBTC_L(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_QBTC_H(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TQDLOC(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_TX_SGLORT(i));
+	buff[idx++] = fm10k_read_reg(hw, FM10K_PFVTCTL(i));
+
+	BUG_ON(idx != FM10K_REGS_LEN_Q);
+}
+
+/* If function above adds more registers this define needs to be updated */
+#define FM10K_REGS_LEN_VSI 43
+
+static void fm10k_get_reg_vsi(struct fm10k_hw *hw, u32 *buff, int i)
+{
+	int idx = 0, j;
+
+	buff[idx++] = fm10k_read_reg(hw, FM10K_MRQC(i));
+	for (j = 0; j < 10; j++)
+		buff[idx++] = fm10k_read_reg(hw, FM10K_RSSRK(i, j));
+	for (j = 0; j < 32; j++)
+		buff[idx++] = fm10k_read_reg(hw, FM10K_RETA(i, j));
+
+	BUG_ON(idx != FM10K_REGS_LEN_VSI);
+}
+
+static void fm10k_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *p)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_hw *hw = &interface->hw;
+	u32 *buff = p;
+	u16 i;
+
+	regs->version = BIT(24) | (hw->revision_id << 16) | hw->device_id;
+
+	switch (hw->mac.type) {
+	case fm10k_mac_pf:
+		/* General PF Registers */
+		*(buff++) = fm10k_read_reg(hw, FM10K_CTRL);
+		*(buff++) = fm10k_read_reg(hw, FM10K_CTRL_EXT);
+		*(buff++) = fm10k_read_reg(hw, FM10K_GCR);
+		*(buff++) = fm10k_read_reg(hw, FM10K_GCR_EXT);
+
+		for (i = 0; i < 8; i++) {
+			*(buff++) = fm10k_read_reg(hw, FM10K_DGLORTMAP(i));
+			*(buff++) = fm10k_read_reg(hw, FM10K_DGLORTDEC(i));
+		}
+
+		for (i = 0; i < 65; i++) {
+			fm10k_get_reg_vsi(hw, buff, i);
+			buff += FM10K_REGS_LEN_VSI;
+		}
+
+		*(buff++) = fm10k_read_reg(hw, FM10K_DMA_CTRL);
+		*(buff++) = fm10k_read_reg(hw, FM10K_DMA_CTRL2);
+
+		for (i = 0; i < FM10K_MAX_QUEUES_PF; i++) {
+			fm10k_get_reg_q(hw, buff, i);
+			buff += FM10K_REGS_LEN_Q;
+		}
+
+		*(buff++) = fm10k_read_reg(hw, FM10K_TPH_CTRL);
+
+		for (i = 0; i < 8; i++)
+			*(buff++) = fm10k_read_reg(hw, FM10K_INT_MAP(i));
+
+		/* Interrupt Throttling Registers */
+		for (i = 0; i < 130; i++)
+			*(buff++) = fm10k_read_reg(hw, FM10K_ITR(i));
+
+		break;
+	case fm10k_mac_vf:
+		/* General VF registers */
+		*(buff++) = fm10k_read_reg(hw, FM10K_VFCTRL);
+		*(buff++) = fm10k_read_reg(hw, FM10K_VFINT_MAP);
+		*(buff++) = fm10k_read_reg(hw, FM10K_VFSYSTIME);
+
+		/* Interrupt Throttling Registers */
+		for (i = 0; i < 8; i++)
+			*(buff++) = fm10k_read_reg(hw, FM10K_VFITR(i));
+
+		fm10k_get_reg_vsi(hw, buff, 0);
+		buff += FM10K_REGS_LEN_VSI;
+
+		for (i = 0; i < FM10K_MAX_QUEUES_POOL; i++) {
+			if (i < hw->mac.max_queues)
+				fm10k_get_reg_q(hw, buff, i);
+			else
+				memset(buff, 0, sizeof(u32) * FM10K_REGS_LEN_Q);
+			buff += FM10K_REGS_LEN_Q;
+		}
+
+		break;
+	default:
+		return;
+	}
+}
+
+/* If function above adds more registers these define need to be updated */
+#define FM10K_REGS_LEN_PF \
+(162 + (65 * FM10K_REGS_LEN_VSI) + (FM10K_MAX_QUEUES_PF * FM10K_REGS_LEN_Q))
+#define FM10K_REGS_LEN_VF \
+(11 + FM10K_REGS_LEN_VSI + (FM10K_MAX_QUEUES_POOL * FM10K_REGS_LEN_Q))
+
+static int fm10k_get_regs_len(struct net_device *netdev)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_hw *hw = &interface->hw;
+
+	switch (hw->mac.type) {
+	case fm10k_mac_pf:
+		return FM10K_REGS_LEN_PF * sizeof(u32);
+	case fm10k_mac_vf:
+		return FM10K_REGS_LEN_VF * sizeof(u32);
+	default:
+		return 0;
+	}
+}
+
+static void fm10k_get_drvinfo(struct net_device *dev,
+			      struct ethtool_drvinfo *info)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	strncpy(info->driver, fm10k_driver_name,
+		sizeof(info->driver) - 1);
+	strncpy(info->bus_info, pci_name(interface->pdev),
+		sizeof(info->bus_info) - 1);
+}
+
+static void fm10k_get_pauseparam(struct net_device *dev,
+				 struct ethtool_pauseparam *pause)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	/* record fixed values for autoneg and tx pause */
+	pause->autoneg = 0;
+	pause->tx_pause = 1;
+
+	pause->rx_pause = interface->rx_pause ? 1 : 0;
+}
+
+static int fm10k_set_pauseparam(struct net_device *dev,
+				struct ethtool_pauseparam *pause)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+
+	if (pause->autoneg || !pause->tx_pause)
+		return -EINVAL;
+
+	/* we can only support pause on the PF to avoid head-of-line blocking */
+	if (hw->mac.type == fm10k_mac_pf)
+		interface->rx_pause = pause->rx_pause ? ~0 : 0;
+	else if (pause->rx_pause)
+		return -EINVAL;
+
+	if (netif_running(dev))
+		fm10k_update_rx_drop_en(interface);
+
+	return 0;
+}
+
+static u32 fm10k_get_msglevel(struct net_device *netdev)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+
+	return interface->msg_enable;
+}
+
+static void fm10k_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+
+	interface->msg_enable = data;
+}
+
+static void fm10k_get_ringparam(struct net_device *netdev,
+				struct ethtool_ringparam *ring,
+				struct kernel_ethtool_ringparam *kernel_ring,
+				struct netlink_ext_ack *extack)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+
+	ring->rx_max_pending = FM10K_MAX_RXD;
+	ring->tx_max_pending = FM10K_MAX_TXD;
+	ring->rx_mini_max_pending = 0;
+	ring->rx_jumbo_max_pending = 0;
+	ring->rx_pending = interface->rx_ring_count;
+	ring->tx_pending = interface->tx_ring_count;
+	ring->rx_mini_pending = 0;
+	ring->rx_jumbo_pending = 0;
+}
+
+static int fm10k_set_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_ring *temp_ring;
+	int i, err = 0;
+	u32 new_rx_count, new_tx_count;
+
+	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
+		return -EINVAL;
+
+	new_tx_count = clamp_t(u32, ring->tx_pending,
+			       FM10K_MIN_TXD, FM10K_MAX_TXD);
+	new_tx_count = ALIGN(new_tx_count, FM10K_REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	new_rx_count = clamp_t(u32, ring->rx_pending,
+			       FM10K_MIN_RXD, FM10K_MAX_RXD);
+	new_rx_count = ALIGN(new_rx_count, FM10K_REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	if ((new_tx_count == interface->tx_ring_count) &&
+	    (new_rx_count == interface->rx_ring_count)) {
+		/* nothing to do */
+		return 0;
+	}
+
+	while (test_and_set_bit(__FM10K_RESETTING, interface->state))
+		usleep_range(1000, 2000);
+
+	if (!netif_running(interface->netdev)) {
+		for (i = 0; i < interface->num_tx_queues; i++)
+			interface->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < interface->num_rx_queues; i++)
+			interface->rx_ring[i]->count = new_rx_count;
+		interface->tx_ring_count = new_tx_count;
+		interface->rx_ring_count = new_rx_count;
+		goto clear_reset;
+	}
+
+	/* allocate temporary buffer to store rings in */
+	i = max_t(int, interface->num_tx_queues, interface->num_rx_queues);
+	temp_ring = vmalloc(array_size(i, sizeof(struct fm10k_ring)));
+
+	if (!temp_ring) {
+		err = -ENOMEM;
+		goto clear_reset;
+	}
+
+	fm10k_down(interface);
+
+	/* Setup new Tx resources and free the old Tx resources in that order.
+	 * We can then assign the new resources to the rings via a memcpy.
+	 * The advantage to this approach is that we are guaranteed to still
+	 * have resources even in the case of an allocation failure.
+	 */
+	if (new_tx_count != interface->tx_ring_count) {
+		for (i = 0; i < interface->num_tx_queues; i++) {
+			memcpy(&temp_ring[i], interface->tx_ring[i],
+			       sizeof(struct fm10k_ring));
+
+			temp_ring[i].count = new_tx_count;
+			err = fm10k_setup_tx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					fm10k_free_tx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < interface->num_tx_queues; i++) {
+			fm10k_free_tx_resources(interface->tx_ring[i]);
+
+			memcpy(interface->tx_ring[i], &temp_ring[i],
+			       sizeof(struct fm10k_ring));
+		}
+
+		interface->tx_ring_count = new_tx_count;
+	}
+
+	/* Repeat the process for the Rx rings if needed */
+	if (new_rx_count != interface->rx_ring_count) {
+		for (i = 0; i < interface->num_rx_queues; i++) {
+			memcpy(&temp_ring[i], interface->rx_ring[i],
+			       sizeof(struct fm10k_ring));
+
+			temp_ring[i].count = new_rx_count;
+			err = fm10k_setup_rx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					fm10k_free_rx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < interface->num_rx_queues; i++) {
+			fm10k_free_rx_resources(interface->rx_ring[i]);
+
+			memcpy(interface->rx_ring[i], &temp_ring[i],
+			       sizeof(struct fm10k_ring));
+		}
+
+		interface->rx_ring_count = new_rx_count;
+	}
+
+err_setup:
+	fm10k_up(interface);
+	vfree(temp_ring);
+clear_reset:
+	clear_bit(__FM10K_RESETTING, interface->state);
+	return err;
+}
+
+static int fm10k_get_coalesce(struct net_device *dev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	ec->use_adaptive_tx_coalesce = ITR_IS_ADAPTIVE(interface->tx_itr);
+	ec->tx_coalesce_usecs = interface->tx_itr & ~FM10K_ITR_ADAPTIVE;
+
+	ec->use_adaptive_rx_coalesce = ITR_IS_ADAPTIVE(interface->rx_itr);
+	ec->rx_coalesce_usecs = interface->rx_itr & ~FM10K_ITR_ADAPTIVE;
+
+	return 0;
+}
+
+static int fm10k_set_coalesce(struct net_device *dev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	u16 tx_itr, rx_itr;
+	int i;
+
+	/* verify limits */
+	if ((ec->rx_coalesce_usecs > FM10K_ITR_MAX) ||
+	    (ec->tx_coalesce_usecs > FM10K_ITR_MAX))
+		return -EINVAL;
+
+	/* record settings */
+	tx_itr = ec->tx_coalesce_usecs;
+	rx_itr = ec->rx_coalesce_usecs;
+
+	/* set initial values for adaptive ITR */
+	if (ec->use_adaptive_tx_coalesce)
+		tx_itr = FM10K_ITR_ADAPTIVE | FM10K_TX_ITR_DEFAULT;
+
+	if (ec->use_adaptive_rx_coalesce)
+		rx_itr = FM10K_ITR_ADAPTIVE | FM10K_RX_ITR_DEFAULT;
+
+	/* update interface */
+	interface->tx_itr = tx_itr;
+	interface->rx_itr = rx_itr;
+
+	/* update q_vectors */
+	for (i = 0; i < interface->num_q_vectors; i++) {
+		struct fm10k_q_vector *qv = interface->q_vector[i];
+
+		qv->tx.itr = tx_itr;
+		qv->rx.itr = rx_itr;
+	}
+
+	return 0;
+}
+
+static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
+				   struct ethtool_rxnfc *cmd)
+{
+	cmd->data = 0;
+
+	/* Report default options for RSS on fm10k */
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case UDP_V4_FLOW:
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+			     interface->flags))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		fallthrough;
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V4_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V4_FLOW:
+	case ESP_V6_FLOW:
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case UDP_V6_FLOW:
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+			     interface->flags))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			   u32 __always_unused *rule_locs)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = interface->num_rx_queues;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXFH:
+		ret = fm10k_get_rss_hash_opts(interface, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
+				  struct ethtool_rxnfc *nfc)
+{
+	int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				    interface->flags);
+	int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				    interface->flags);
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    !(nfc->data & RXH_L4_B_0_1) ||
+		    !(nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	case UDP_V4_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			clear_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				  interface->flags);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			set_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				interface->flags);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			clear_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				  interface->flags);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			set_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				interface->flags);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    (nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* If something changed we need to update the MRQC register. Note that
+	 * test_bit() is guaranteed to return strictly 0 or 1, so testing for
+	 * equality is safe.
+	 */
+	if ((rss_ipv4_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+				      interface->flags)) ||
+	    (rss_ipv6_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+				      interface->flags))) {
+		struct fm10k_hw *hw = &interface->hw;
+		bool warn = false;
+		u32 mrqc;
+
+		/* Perform hash on these packet types */
+		mrqc = FM10K_MRQC_IPV4 |
+		       FM10K_MRQC_TCP_IPV4 |
+		       FM10K_MRQC_IPV6 |
+		       FM10K_MRQC_TCP_IPV6;
+
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+			     interface->flags)) {
+			mrqc |= FM10K_MRQC_UDP_IPV4;
+			warn = true;
+		}
+		if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+			     interface->flags)) {
+			mrqc |= FM10K_MRQC_UDP_IPV6;
+			warn = true;
+		}
+
+		/* If we enable UDP RSS display a warning that this may cause
+		 * fragmented UDP packets to arrive out of order.
+		 */
+		if (warn)
+			netif_warn(interface, drv, interface->netdev,
+				   "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
+
+		fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
+	}
+
+	return 0;
+}
+
+static int fm10k_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = fm10k_set_rss_hash_opt(interface, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int fm10k_mbx_test(struct fm10k_intfc *interface, u64 *data)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 attr_flag, test_msg[6];
+	unsigned long timeout;
+	int err = -EINVAL;
+
+	/* For now this is a VF only feature */
+	if (hw->mac.type != fm10k_mac_vf)
+		return 0;
+
+	/* loop through both nested and unnested attribute types */
+	for (attr_flag = BIT(FM10K_TEST_MSG_UNSET);
+	     attr_flag < BIT(2 * FM10K_TEST_MSG_NESTED);
+	     attr_flag += attr_flag) {
+		/* generate message to be tested */
+		fm10k_tlv_msg_test_create(test_msg, attr_flag);
+
+		fm10k_mbx_lock(interface);
+		mbx->test_result = FM10K_NOT_IMPLEMENTED;
+		err = mbx->ops.enqueue_tx(hw, mbx, test_msg);
+		fm10k_mbx_unlock(interface);
+
+		/* wait up to 1 second for response */
+		timeout = jiffies + HZ;
+		do {
+			if (err < 0)
+				goto err_out;
+
+			usleep_range(500, 1000);
+
+			fm10k_mbx_lock(interface);
+			mbx->ops.process(hw, mbx);
+			fm10k_mbx_unlock(interface);
+
+			err = mbx->test_result;
+			if (!err)
+				break;
+		} while (time_is_after_jiffies(timeout));
+
+		/* reporting errors */
+		if (err)
+			goto err_out;
+	}
+
+err_out:
+	*data = err < 0 ? (attr_flag) : (err > 0);
+	return err;
+}
+
+static void fm10k_self_test(struct net_device *dev,
+			    struct ethtool_test *eth_test, u64 *data)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+
+	memset(data, 0, sizeof(*data) * FM10K_TEST_LEN);
+
+	if (FM10K_REMOVED(hw->hw_addr)) {
+		netif_err(interface, drv, dev,
+			  "Interface removed - test blocked\n");
+		eth_test->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
+	if (fm10k_mbx_test(interface, &data[FM10K_TEST_MBX]))
+		eth_test->flags |= ETH_TEST_FL_FAILED;
+}
+
+static u32 fm10k_get_priv_flags(struct net_device *netdev)
+{
+	return 0;
+}
+
+static int fm10k_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	if (priv_flags >= BIT(FM10K_PRV_FLAG_LEN))
+		return -EINVAL;
+
+	return 0;
+}
+
+static u32 fm10k_get_reta_size(struct net_device __always_unused *netdev)
+{
+	return FM10K_RETA_SIZE * FM10K_RETA_ENTRIES_PER_REG;
+}
+
+void fm10k_write_reta(struct fm10k_intfc *interface, const u32 *indir)
+{
+	u16 rss_i = interface->ring_feature[RING_F_RSS].indices;
+	struct fm10k_hw *hw = &interface->hw;
+	u32 table[4];
+	int i, j;
+
+	/* record entries to reta table */
+	for (i = 0; i < FM10K_RETA_SIZE; i++) {
+		u32 reta, n;
+
+		/* generate a new table if we weren't given one */
+		for (j = 0; j < 4; j++) {
+			if (indir)
+				n = indir[4 * i + j];
+			else
+				n = ethtool_rxfh_indir_default(4 * i + j,
+							       rss_i);
+
+			table[j] = n;
+		}
+
+		reta = table[0] |
+			(table[1] << 8) |
+			(table[2] << 16) |
+			(table[3] << 24);
+
+		if (interface->reta[i] == reta)
+			continue;
+
+		interface->reta[i] = reta;
+		fm10k_write_reg(hw, FM10K_RETA(0, i), reta);
+	}
+}
+
+static int fm10k_get_reta(struct net_device *netdev, u32 *indir)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	int i;
+
+	if (!indir)
+		return 0;
+
+	for (i = 0; i < FM10K_RETA_SIZE; i++, indir += 4) {
+		u32 reta = interface->reta[i];
+
+		indir[0] = (reta << 24) >> 24;
+		indir[1] = (reta << 16) >> 24;
+		indir[2] = (reta <<  8) >> 24;
+		indir[3] = (reta) >> 24;
+	}
+
+	return 0;
+}
+
+static int fm10k_set_reta(struct net_device *netdev, const u32 *indir)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	int i;
+	u16 rss_i;
+
+	if (!indir)
+		return 0;
+
+	/* Verify user input. */
+	rss_i = interface->ring_feature[RING_F_RSS].indices;
+	for (i = fm10k_get_reta_size(netdev); i--;) {
+		if (indir[i] < rss_i)
+			continue;
+		return -EINVAL;
+	}
+
+	fm10k_write_reta(interface, indir);
+
+	return 0;
+}
+
+static u32 fm10k_get_rssrk_size(struct net_device __always_unused *netdev)
+{
+	return FM10K_RSSRK_SIZE * FM10K_RSSRK_ENTRIES_PER_REG;
+}
+
+static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
+			  u8 *hfunc)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	int i, err;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
+	err = fm10k_get_reta(netdev, indir);
+	if (err || !key)
+		return err;
+
+	for (i = 0; i < FM10K_RSSRK_SIZE; i++, key += 4)
+		*(__le32 *)key = cpu_to_le32(interface->rssrk[i]);
+
+	return 0;
+}
+
+static int fm10k_set_rssh(struct net_device *netdev, const u32 *indir,
+			  const u8 *key, const u8 hfunc)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_hw *hw = &interface->hw;
+	int i, err;
+
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	err = fm10k_set_reta(netdev, indir);
+	if (err || !key)
+		return err;
+
+	for (i = 0; i < FM10K_RSSRK_SIZE; i++, key += 4) {
+		u32 rssrk = le32_to_cpu(*(__le32 *)key);
+
+		if (interface->rssrk[i] == rssrk)
+			continue;
+
+		interface->rssrk[i] = rssrk;
+		fm10k_write_reg(hw, FM10K_RSSRK(0, i), rssrk);
+	}
+
+	return 0;
+}
+
+static unsigned int fm10k_max_channels(struct net_device *dev)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	unsigned int max_combined = interface->hw.mac.max_queues;
+	u8 tcs = netdev_get_num_tc(dev);
+
+	/* For QoS report channels per traffic class */
+	if (tcs > 1)
+		max_combined = BIT((fls(max_combined / tcs) - 1));
+
+	return max_combined;
+}
+
+static void fm10k_get_channels(struct net_device *dev,
+			       struct ethtool_channels *ch)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+
+	/* report maximum channels */
+	ch->max_combined = fm10k_max_channels(dev);
+
+	/* report info for other vector */
+	ch->max_other = NON_Q_VECTORS;
+	ch->other_count = ch->max_other;
+
+	/* record RSS queues */
+	ch->combined_count = interface->ring_feature[RING_F_RSS].indices;
+}
+
+static int fm10k_set_channels(struct net_device *dev,
+			      struct ethtool_channels *ch)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	unsigned int count = ch->combined_count;
+
+	/* verify they are not requesting separate vectors */
+	if (!count || ch->rx_count || ch->tx_count)
+		return -EINVAL;
+
+	/* verify other_count has not changed */
+	if (ch->other_count != NON_Q_VECTORS)
+		return -EINVAL;
+
+	/* verify the number of channels does not exceed hardware limits */
+	if (count > fm10k_max_channels(dev))
+		return -EINVAL;
+
+	interface->ring_feature[RING_F_RSS].limit = count;
+
+	/* use setup TC to update any traffic class queue mapping */
+	return fm10k_setup_tc(dev, netdev_get_num_tc(dev));
+}
+
+static const struct ethtool_ops fm10k_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE,
+	.get_strings		= fm10k_get_strings,
+	.get_sset_count		= fm10k_get_sset_count,
+	.get_ethtool_stats      = fm10k_get_ethtool_stats,
+	.get_drvinfo		= fm10k_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_pauseparam		= fm10k_get_pauseparam,
+	.set_pauseparam		= fm10k_set_pauseparam,
+	.get_msglevel		= fm10k_get_msglevel,
+	.set_msglevel		= fm10k_set_msglevel,
+	.get_ringparam		= fm10k_get_ringparam,
+	.set_ringparam		= fm10k_set_ringparam,
+	.get_coalesce		= fm10k_get_coalesce,
+	.set_coalesce		= fm10k_set_coalesce,
+	.get_rxnfc		= fm10k_get_rxnfc,
+	.set_rxnfc		= fm10k_set_rxnfc,
+	.get_regs               = fm10k_get_regs,
+	.get_regs_len           = fm10k_get_regs_len,
+	.self_test		= fm10k_self_test,
+	.get_priv_flags		= fm10k_get_priv_flags,
+	.set_priv_flags		= fm10k_set_priv_flags,
+	.get_rxfh_indir_size	= fm10k_get_reta_size,
+	.get_rxfh_key_size	= fm10k_get_rssrk_size,
+	.get_rxfh		= fm10k_get_rssh,
+	.set_rxfh		= fm10k_set_rssh,
+	.get_channels		= fm10k_get_channels,
+	.set_channels		= fm10k_set_channels,
+	.get_ts_info		= ethtool_op_get_ts_info,
+};
+
+void fm10k_set_ethtool_ops(struct net_device *dev)
+{
+	dev->ethtool_ops = &fm10k_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
new file mode 100644
index 000000000..8c50a128d
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -0,0 +1,700 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k.h"
+#include "fm10k_vf.h"
+#include "fm10k_pf.h"
+
+static s32 fm10k_iov_msg_error(struct fm10k_hw *hw, u32 **results,
+			       struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	struct fm10k_intfc *interface = hw->back;
+	struct pci_dev *pdev = interface->pdev;
+
+	dev_err(&pdev->dev, "Unknown message ID %u on VF %d\n",
+		**results & FM10K_TLV_ID_MASK, vf_info->vf_idx);
+
+	return fm10k_tlv_msg_error(hw, results, mbx);
+}
+
+/**
+ *  fm10k_iov_msg_queue_mac_vlan - Message handler for MAC/VLAN request from VF
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function is a custom handler for MAC/VLAN requests from the VF. The
+ *  assumption is that it is acceptable to directly hand off the message from
+ *  the VF to the PF's switch manager. However, we use a MAC/VLAN message
+ *  queue to avoid overloading the mailbox when a large number of requests
+ *  come in.
+ **/
+static s32 fm10k_iov_msg_queue_mac_vlan(struct fm10k_hw *hw, u32 **results,
+					struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	struct fm10k_intfc *interface = hw->back;
+	u8 mac[ETH_ALEN];
+	u32 *result;
+	int err = 0;
+	bool set;
+	u16 vlan;
+	u32 vid;
+
+	/* we shouldn't be updating rules on a disabled interface */
+	if (!FM10K_VF_FLAG_ENABLED(vf_info))
+		err = FM10K_ERR_PARAM;
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
+		result = results[FM10K_MAC_VLAN_MSG_VLAN];
+
+		/* record VLAN id requested */
+		err = fm10k_tlv_attr_get_u32(result, &vid);
+		if (err)
+			return err;
+
+		set = !(vid & FM10K_VLAN_CLEAR);
+		vid &= ~FM10K_VLAN_CLEAR;
+
+		/* if the length field has been set, this is a multi-bit
+		 * update request. For multi-bit requests, simply disallow
+		 * them when the pf_vid has been set. In this case, the PF
+		 * should have already cleared the VLAN_TABLE, and if we
+		 * allowed them, it could allow a rogue VF to receive traffic
+		 * on a VLAN it was not assigned. In the single-bit case, we
+		 * need to modify requests for VLAN 0 to use the default PF or
+		 * SW vid when assigned.
+		 */
+
+		if (vid >> 16) {
+			/* prevent multi-bit requests when PF has
+			 * administratively set the VLAN for this VF
+			 */
+			if (vf_info->pf_vid)
+				return FM10K_ERR_PARAM;
+		} else {
+			err = fm10k_iov_select_vid(vf_info, (u16)vid);
+			if (err < 0)
+				return err;
+
+			vid = err;
+		}
+
+		/* update VSI info for VF in regards to VLAN table */
+		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
+		result = results[FM10K_MAC_VLAN_MSG_MAC];
+
+		/* record unicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* block attempts to set MAC for a locked device */
+		if (is_valid_ether_addr(vf_info->mac) &&
+		    !ether_addr_equal(mac, vf_info->mac))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* Add this request to the MAC/VLAN queue */
+		err = fm10k_queue_mac_request(interface, vf_info->glort,
+					      mac, vlan, set);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
+		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
+
+		/* record multicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* verify that the VF is allowed to request multicast */
+		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* Add this request to the MAC/VLAN queue */
+		err = fm10k_queue_mac_request(interface, vf_info->glort,
+					      mac, vlan, set);
+	}
+
+	return err;
+}
+
+static const struct fm10k_msg_data iov_mbx_data[] = {
+	FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test),
+	FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf),
+	FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_queue_mac_vlan),
+	FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf),
+	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_iov_msg_error),
+};
+
+s32 fm10k_iov_event(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_iov_data *iov_data;
+	s64 vflre;
+	int i;
+
+	/* if there is no iov_data then there is no mailbox to process */
+	if (!READ_ONCE(interface->iov_data))
+		return 0;
+
+	rcu_read_lock();
+
+	iov_data = interface->iov_data;
+
+	/* check again now that we are in the RCU block */
+	if (!iov_data)
+		goto read_unlock;
+
+	if (!(fm10k_read_reg(hw, FM10K_EICR) & FM10K_EICR_VFLR))
+		goto read_unlock;
+
+	/* read VFLRE to determine if any VFs have been reset */
+	vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1));
+	vflre <<= 32;
+	vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0));
+
+	i = iov_data->num_vfs;
+
+	for (vflre <<= 64 - i; vflre && i--; vflre += vflre) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+
+		if (vflre >= 0)
+			continue;
+
+		hw->iov.ops.reset_resources(hw, vf_info);
+		vf_info->mbx.ops.connect(hw, &vf_info->mbx);
+	}
+
+read_unlock:
+	rcu_read_unlock();
+
+	return 0;
+}
+
+s32 fm10k_iov_mbx(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_iov_data *iov_data;
+	int i;
+
+	/* if there is no iov_data then there is no mailbox to process */
+	if (!READ_ONCE(interface->iov_data))
+		return 0;
+
+	rcu_read_lock();
+
+	iov_data = interface->iov_data;
+
+	/* check again now that we are in the RCU block */
+	if (!iov_data)
+		goto read_unlock;
+
+	/* lock the mailbox for transmit and receive */
+	fm10k_mbx_lock(interface);
+
+	/* Most VF messages sent to the PF cause the PF to respond by
+	 * requesting from the SM mailbox. This means that too many VF
+	 * messages processed at once could cause a mailbox timeout on the PF.
+	 * To prevent this, store a pointer to the next VF mbx to process. Use
+	 * that as the start of the loop so that we don't starve whichever VF
+	 * got ignored on the previous run.
+	 */
+process_mbx:
+	for (i = iov_data->next_vf_mbx ? : iov_data->num_vfs; i--;) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+		struct fm10k_mbx_info *mbx = &vf_info->mbx;
+		u16 glort = vf_info->glort;
+
+		/* process the SM mailbox first to drain outgoing messages */
+		hw->mbx.ops.process(hw, &hw->mbx);
+
+		/* verify port mapping is valid, if not reset port */
+		if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) {
+			hw->iov.ops.reset_lport(hw, vf_info);
+			fm10k_clear_macvlan_queue(interface, glort, false);
+		}
+
+		/* reset VFs that have mailbox timed out */
+		if (!mbx->timeout) {
+			hw->iov.ops.reset_resources(hw, vf_info);
+			mbx->ops.connect(hw, mbx);
+		}
+
+		/* guarantee we have free space in the SM mailbox */
+		if (hw->mbx.state == FM10K_STATE_OPEN &&
+		    !hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) {
+			/* keep track of how many times this occurs */
+			interface->hw_sm_mbx_full++;
+
+			/* make sure we try again momentarily */
+			fm10k_service_event_schedule(interface);
+
+			break;
+		}
+
+		/* cleanup mailbox and process received messages */
+		mbx->ops.process(hw, mbx);
+	}
+
+	/* if we stopped processing mailboxes early, update next_vf_mbx.
+	 * Otherwise, reset next_vf_mbx, and restart loop so that we process
+	 * the remaining mailboxes we skipped at the start.
+	 */
+	if (i >= 0) {
+		iov_data->next_vf_mbx = i + 1;
+	} else if (iov_data->next_vf_mbx) {
+		iov_data->next_vf_mbx = 0;
+		goto process_mbx;
+	}
+
+	/* free the lock */
+	fm10k_mbx_unlock(interface);
+
+read_unlock:
+	rcu_read_unlock();
+
+	return 0;
+}
+
+void fm10k_iov_suspend(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	int num_vfs, i;
+
+	/* pull out num_vfs from iov_data */
+	num_vfs = iov_data ? iov_data->num_vfs : 0;
+
+	/* shut down queue mapping for VFs */
+	fm10k_write_reg(hw, FM10K_DGLORTMAP(fm10k_dglort_vf_rss),
+			FM10K_DGLORTMAP_NONE);
+
+	/* Stop any active VFs and reset their resources */
+	for (i = 0; i < num_vfs; i++) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+
+		hw->iov.ops.reset_resources(hw, vf_info);
+		hw->iov.ops.reset_lport(hw, vf_info);
+		fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
+	}
+}
+
+static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev)
+{
+	u32 err_mask;
+	int pos;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return;
+
+	/* Mask the completion abort bit in the ERR_UNCOR_MASK register,
+	 * preventing the device from reporting these errors to the upstream
+	 * PCIe root device. This avoids bringing down platforms which upgrade
+	 * non-fatal completer aborts into machine check exceptions. Completer
+	 * aborts can occur whenever a VF reads a queue it doesn't own.
+	 */
+	pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask);
+	err_mask |= PCI_ERR_UNC_COMP_ABORT;
+	pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask);
+}
+
+int fm10k_iov_resume(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_dglort_cfg dglort = { 0 };
+	struct fm10k_hw *hw = &interface->hw;
+	int num_vfs, i;
+
+	/* pull out num_vfs from iov_data */
+	num_vfs = iov_data ? iov_data->num_vfs : 0;
+
+	/* return error if iov_data is not already populated */
+	if (!iov_data)
+		return -ENOMEM;
+
+	/* Lower severity of completer abort error reporting as
+	 * the VFs can trigger this any time they read a queue
+	 * that they don't own.
+	 */
+	fm10k_mask_aer_comp_abort(pdev);
+
+	/* allocate hardware resources for the VFs */
+	hw->iov.ops.assign_resources(hw, num_vfs, num_vfs);
+
+	/* configure DGLORT mapping for RSS */
+	dglort.glort = hw->mac.dglort_map & FM10K_DGLORTMAP_NONE;
+	dglort.idx = fm10k_dglort_vf_rss;
+	dglort.inner_rss = 1;
+	dglort.rss_l = fls(fm10k_queues_per_pool(hw) - 1);
+	dglort.queue_b = fm10k_vf_queue_index(hw, 0);
+	dglort.vsi_l = fls(hw->iov.total_vfs - 1);
+	dglort.vsi_b = 1;
+
+	hw->mac.ops.configure_dglort_map(hw, &dglort);
+
+	/* assign resources to the device */
+	for (i = 0; i < num_vfs; i++) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+
+		/* allocate all but the last GLORT to the VFs */
+		if (i == (~hw->mac.dglort_map >> FM10K_DGLORTMAP_MASK_SHIFT))
+			break;
+
+		/* assign GLORT to VF, and restrict it to multicast */
+		hw->iov.ops.set_lport(hw, vf_info, i,
+				      FM10K_VF_FLAG_MULTI_CAPABLE);
+
+		/* mailbox is disconnected so we don't send a message */
+		hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
+
+		/* now we are ready so we can connect */
+		vf_info->mbx.ops.connect(hw, &vf_info->mbx);
+	}
+
+	return 0;
+}
+
+s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid)
+{
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_vf_info *vf_info;
+	u16 vf_idx = (glort - hw->mac.dglort_map) & FM10K_DGLORTMAP_NONE;
+
+	/* no IOV support, not our message to process */
+	if (!iov_data)
+		return FM10K_ERR_PARAM;
+
+	/* glort outside our range, not our message to process */
+	if (vf_idx >= iov_data->num_vfs)
+		return FM10K_ERR_PARAM;
+
+	/* determine if an update has occurred and if so notify the VF */
+	vf_info = &iov_data->vf_info[vf_idx];
+	if (vf_info->sw_vid != pvid) {
+		vf_info->sw_vid = pvid;
+		hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
+	}
+
+	return 0;
+}
+
+static void fm10k_iov_free_data(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+
+	if (!interface->iov_data)
+		return;
+
+	/* reclaim hardware resources */
+	fm10k_iov_suspend(pdev);
+
+	/* drop iov_data from interface */
+	kfree_rcu(interface->iov_data, rcu);
+	interface->iov_data = NULL;
+}
+
+static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	size_t size;
+	int i;
+
+	/* return error if iov_data is already populated */
+	if (iov_data)
+		return -EBUSY;
+
+	/* The PF should always be able to assign resources */
+	if (!hw->iov.ops.assign_resources)
+		return -ENODEV;
+
+	/* nothing to do if no VFs are requested */
+	if (!num_vfs)
+		return 0;
+
+	/* allocate memory for VF storage */
+	size = offsetof(struct fm10k_iov_data, vf_info[num_vfs]);
+	iov_data = kzalloc(size, GFP_KERNEL);
+	if (!iov_data)
+		return -ENOMEM;
+
+	/* record number of VFs */
+	iov_data->num_vfs = num_vfs;
+
+	/* loop through vf_info structures initializing each entry */
+	for (i = 0; i < num_vfs; i++) {
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+		int err;
+
+		/* Record VF VSI value */
+		vf_info->vsi = i + 1;
+		vf_info->vf_idx = i;
+
+		/* initialize mailbox memory */
+		err = fm10k_pfvf_mbx_init(hw, &vf_info->mbx, iov_mbx_data, i);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Unable to initialize SR-IOV mailbox\n");
+			kfree(iov_data);
+			return err;
+		}
+	}
+
+	/* assign iov_data to interface */
+	interface->iov_data = iov_data;
+
+	/* allocate hardware resources for the VFs */
+	fm10k_iov_resume(pdev);
+
+	return 0;
+}
+
+void fm10k_iov_disable(struct pci_dev *pdev)
+{
+	if (pci_num_vf(pdev) && pci_vfs_assigned(pdev))
+		dev_err(&pdev->dev,
+			"Cannot disable SR-IOV while VFs are assigned\n");
+	else
+		pci_disable_sriov(pdev);
+
+	fm10k_iov_free_data(pdev);
+}
+
+int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	int current_vfs = pci_num_vf(pdev);
+	int err = 0;
+
+	if (current_vfs && pci_vfs_assigned(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot modify SR-IOV while VFs are assigned\n");
+		num_vfs = current_vfs;
+	} else {
+		pci_disable_sriov(pdev);
+		fm10k_iov_free_data(pdev);
+	}
+
+	/* allocate resources for the VFs */
+	err = fm10k_iov_alloc_data(pdev, num_vfs);
+	if (err)
+		return err;
+
+	/* allocate VFs if not already allocated */
+	if (num_vfs && num_vfs != current_vfs) {
+		err = pci_enable_sriov(pdev, num_vfs);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Enable PCI SR-IOV failed: %d\n", err);
+			return err;
+		}
+	}
+
+	return num_vfs;
+}
+
+/**
+ * fm10k_iov_update_stats - Update stats for all VFs
+ * @interface: device private structure
+ *
+ * Updates the VF statistics for all enabled VFs. Expects to be called by
+ * fm10k_update_stats and assumes that locking via the __FM10K_UPDATING_STATS
+ * bit is already handled.
+ */
+void fm10k_iov_update_stats(struct fm10k_intfc *interface)
+{
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	int i;
+
+	if (!iov_data)
+		return;
+
+	for (i = 0; i < iov_data->num_vfs; i++)
+		hw->iov.ops.update_stats(hw, iov_data->vf_info[i].stats, i);
+}
+
+static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface,
+				       struct fm10k_vf_info *vf_info)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* assigning the MAC address will send a mailbox message */
+	fm10k_mbx_lock(interface);
+
+	/* disable LPORT for this VF which clears switch rules */
+	hw->iov.ops.reset_lport(hw, vf_info);
+
+	fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
+
+	/* assign new MAC+VLAN for this VF */
+	hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
+
+	/* re-enable the LPORT for this VF */
+	hw->iov.ops.set_lport(hw, vf_info, vf_info->vf_idx,
+			      FM10K_VF_FLAG_MULTI_CAPABLE);
+
+	fm10k_mbx_unlock(interface);
+}
+
+int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_vf_info *vf_info;
+
+	/* verify SR-IOV is active and that vf idx is valid */
+	if (!iov_data || vf_idx >= iov_data->num_vfs)
+		return -EINVAL;
+
+	/* verify MAC addr is valid */
+	if (!is_zero_ether_addr(mac) && !is_valid_ether_addr(mac))
+		return -EINVAL;
+
+	/* record new MAC address */
+	vf_info = &iov_data->vf_info[vf_idx];
+	ether_addr_copy(vf_info->mac, mac);
+
+	fm10k_reset_vf_info(interface, vf_info);
+
+	return 0;
+}
+
+int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid,
+			  u8 qos, __be16 vlan_proto)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_vf_info *vf_info;
+
+	/* verify SR-IOV is active and that vf idx is valid */
+	if (!iov_data || vf_idx >= iov_data->num_vfs)
+		return -EINVAL;
+
+	/* QOS is unsupported and VLAN IDs accepted range 0-4094 */
+	if (qos || (vid > (VLAN_VID_MASK - 1)))
+		return -EINVAL;
+
+	/* VF VLAN Protocol part to default is unsupported */
+	if (vlan_proto != htons(ETH_P_8021Q))
+		return -EPROTONOSUPPORT;
+
+	vf_info = &iov_data->vf_info[vf_idx];
+
+	/* exit if there is nothing to do */
+	if (vf_info->pf_vid == vid)
+		return 0;
+
+	/* record default VLAN ID for VF */
+	vf_info->pf_vid = vid;
+
+	/* Clear the VLAN table for the VF */
+	hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, vf_info->vsi, false);
+
+	fm10k_reset_vf_info(interface, vf_info);
+
+	return 0;
+}
+
+int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
+			int __always_unused min_rate, int max_rate)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* verify SR-IOV is active and that vf idx is valid */
+	if (!iov_data || vf_idx >= iov_data->num_vfs)
+		return -EINVAL;
+
+	/* rate limit cannot be less than 10Mbs or greater than link speed */
+	if (max_rate &&
+	    (max_rate < FM10K_VF_TC_MIN || max_rate > FM10K_VF_TC_MAX))
+		return -EINVAL;
+
+	/* store values */
+	iov_data->vf_info[vf_idx].rate = max_rate;
+
+	/* update hardware configuration */
+	hw->iov.ops.configure_tc(hw, vf_idx, max_rate);
+
+	return 0;
+}
+
+int fm10k_ndo_get_vf_config(struct net_device *netdev,
+			    int vf_idx, struct ifla_vf_info *ivi)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_vf_info *vf_info;
+
+	/* verify SR-IOV is active and that vf idx is valid */
+	if (!iov_data || vf_idx >= iov_data->num_vfs)
+		return -EINVAL;
+
+	vf_info = &iov_data->vf_info[vf_idx];
+
+	ivi->vf = vf_idx;
+	ivi->max_tx_rate = vf_info->rate;
+	ivi->min_tx_rate = 0;
+	ether_addr_copy(ivi->mac, vf_info->mac);
+	ivi->vlan = vf_info->pf_vid;
+	ivi->qos = 0;
+
+	return 0;
+}
+
+int fm10k_ndo_get_vf_stats(struct net_device *netdev,
+			   int vf_idx, struct ifla_vf_stats *stats)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_hw_stats_q *hw_stats;
+	u32 idx, qpp;
+
+	/* verify SR-IOV is active and that vf idx is valid */
+	if (!iov_data || vf_idx >= iov_data->num_vfs)
+		return -EINVAL;
+
+	qpp = fm10k_queues_per_pool(hw);
+	hw_stats = iov_data->vf_info[vf_idx].stats;
+
+	for (idx = 0; idx < qpp; idx++) {
+		stats->rx_packets += hw_stats[idx].rx_packets.count;
+		stats->tx_packets += hw_stats[idx].tx_packets.count;
+		stats->rx_bytes += hw_stats[idx].rx_bytes.count;
+		stats->tx_bytes += hw_stats[idx].tx_bytes.count;
+		stats->rx_dropped += hw_stats[idx].rx_drops.count;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
new file mode 100644
index 000000000..fc373472e
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -0,0 +1,2009 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <linux/if_macvlan.h>
+#include <linux/prefetch.h>
+
+#include "fm10k.h"
+
+#define DRV_SUMMARY	"Intel(R) Ethernet Switch Host Interface Driver"
+char fm10k_driver_name[] = "fm10k";
+static const char fm10k_driver_string[] = DRV_SUMMARY;
+static const char fm10k_copyright[] =
+	"Copyright(c) 2013 - 2019 Intel Corporation.";
+
+MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
+MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_LICENSE("GPL v2");
+
+/* single workqueue for entire fm10k driver */
+struct workqueue_struct *fm10k_workqueue;
+
+/**
+ * fm10k_init_module - Driver Registration Routine
+ *
+ * fm10k_init_module is the first routine called when the driver is
+ * loaded.  All it does is register with the PCI subsystem.
+ **/
+static int __init fm10k_init_module(void)
+{
+	int ret;
+
+	pr_info("%s\n", fm10k_driver_string);
+	pr_info("%s\n", fm10k_copyright);
+
+	/* create driver workqueue */
+	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+					  fm10k_driver_name);
+	if (!fm10k_workqueue)
+		return -ENOMEM;
+
+	fm10k_dbg_init();
+
+	ret = fm10k_register_pci_driver();
+	if (ret) {
+		fm10k_dbg_exit();
+		destroy_workqueue(fm10k_workqueue);
+	}
+
+	return ret;
+}
+module_init(fm10k_init_module);
+
+/**
+ * fm10k_exit_module - Driver Exit Cleanup Routine
+ *
+ * fm10k_exit_module is called just before the driver is removed
+ * from memory.
+ **/
+static void __exit fm10k_exit_module(void)
+{
+	fm10k_unregister_pci_driver();
+
+	fm10k_dbg_exit();
+
+	/* destroy driver workqueue */
+	destroy_workqueue(fm10k_workqueue);
+}
+module_exit(fm10k_exit_module);
+
+static bool fm10k_alloc_mapped_page(struct fm10k_ring *rx_ring,
+				    struct fm10k_rx_buffer *bi)
+{
+	struct page *page = bi->page;
+	dma_addr_t dma;
+
+	/* Only page will be NULL if buffer was consumed */
+	if (likely(page))
+		return true;
+
+	/* alloc new page for storage */
+	page = dev_alloc_page();
+	if (unlikely(!page)) {
+		rx_ring->rx_stats.alloc_failed++;
+		return false;
+	}
+
+	/* map page for use */
+	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* 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 = 0;
+
+	return true;
+}
+
+/**
+ * fm10k_alloc_rx_buffers - Replace used receive buffers
+ * @rx_ring: ring to place buffers on
+ * @cleaned_count: number of buffers to replace
+ **/
+void fm10k_alloc_rx_buffers(struct fm10k_ring *rx_ring, u16 cleaned_count)
+{
+	union fm10k_rx_desc *rx_desc;
+	struct fm10k_rx_buffer *bi;
+	u16 i = rx_ring->next_to_use;
+
+	/* nothing to do */
+	if (!cleaned_count)
+		return;
+
+	rx_desc = FM10K_RX_DESC(rx_ring, i);
+	bi = &rx_ring->rx_buffer[i];
+	i -= rx_ring->count;
+
+	do {
+		if (!fm10k_alloc_mapped_page(rx_ring, bi))
+			break;
+
+		/* Refresh the desc even if buffer_addrs didn't change
+		 * because each write-back erases this info.
+		 */
+		rx_desc->q.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+
+		rx_desc++;
+		bi++;
+		i++;
+		if (unlikely(!i)) {
+			rx_desc = FM10K_RX_DESC(rx_ring, 0);
+			bi = rx_ring->rx_buffer;
+			i -= rx_ring->count;
+		}
+
+		/* clear the status bits for the next_to_use descriptor */
+		rx_desc->d.staterr = 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();
+
+		/* notify hardware of new descriptors */
+		writel(i, rx_ring->tail);
+	}
+}
+
+/**
+ * fm10k_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 interface
+ **/
+static void fm10k_reuse_rx_page(struct fm10k_ring *rx_ring,
+				struct fm10k_rx_buffer *old_buff)
+{
+	struct fm10k_rx_buffer *new_buff;
+	u16 nta = rx_ring->next_to_alloc;
+
+	new_buff = &rx_ring->rx_buffer[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 */
+	*new_buff = *old_buff;
+
+	/* sync the buffer for use by the device */
+	dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma,
+					 old_buff->page_offset,
+					 FM10K_RX_BUFSZ,
+					 DMA_FROM_DEVICE);
+}
+
+static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
+				    struct page *page,
+				    unsigned int __maybe_unused truesize)
+{
+	/* avoid re-using remote and pfmemalloc pages */
+	if (!dev_page_is_reusable(page))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* flip page offset to other buffer */
+	rx_buffer->page_offset ^= FM10K_RX_BUFSZ;
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > (PAGE_SIZE - FM10K_RX_BUFSZ))
+		return false;
+#endif
+
+	/* Even if we own the page, we are not allowed to use atomic_set()
+	 * This would break get_page_unless_zero() users.
+	 */
+	page_ref_inc(page);
+
+	return true;
+}
+
+/**
+ * fm10k_add_rx_frag - Add contents of Rx buffer to sk_buff
+ * @rx_buffer: buffer containing page to add
+ * @size: packet size from rx_desc
+ * @rx_desc: descriptor containing length of buffer written by hardware
+ * @skb: sk_buff to place the data into
+ *
+ * This function will add the data contained in rx_buffer->page to the skb.
+ * This is done either through a direct copy if the data in the buffer is
+ * less than the skb header size, otherwise it will just attach the page as
+ * a frag to the skb.
+ *
+ * The function will then update the page offset if necessary and return
+ * true if the buffer can be reused by the interface.
+ **/
+static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
+			      unsigned int size,
+			      union fm10k_rx_desc *rx_desc,
+			      struct sk_buff *skb)
+{
+	struct page *page = rx_buffer->page;
+	unsigned char *va = page_address(page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = FM10K_RX_BUFSZ;
+#else
+	unsigned int truesize = ALIGN(size, 512);
+#endif
+	unsigned int pull_len;
+
+	if (unlikely(skb_is_nonlinear(skb)))
+		goto add_tail_frag;
+
+	if (likely(size <= FM10K_RX_HDR_LEN)) {
+		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+
+		/* page is reusable, we can reuse buffer as-is */
+		if (dev_page_is_reusable(page))
+			return true;
+
+		/* this page cannot be reused so discard it */
+		__free_page(page);
+		return false;
+	}
+
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	va += pull_len;
+	size -= pull_len;
+
+add_tail_frag:
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			(unsigned long)va & ~PAGE_MASK, size, truesize);
+
+	return fm10k_can_reuse_rx_page(rx_buffer, page, truesize);
+}
+
+static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring,
+					     union fm10k_rx_desc *rx_desc,
+					     struct sk_buff *skb)
+{
+	unsigned int size = le16_to_cpu(rx_desc->w.length);
+	struct fm10k_rx_buffer *rx_buffer;
+	struct page *page;
+
+	rx_buffer = &rx_ring->rx_buffer[rx_ring->next_to_clean];
+	page = rx_buffer->page;
+	prefetchw(page);
+
+	if (likely(!skb)) {
+		void *page_addr = page_address(page) +
+				  rx_buffer->page_offset;
+
+		/* prefetch first cache line of first page */
+		net_prefetch(page_addr);
+
+		/* allocate a skb to store the frags */
+		skb = napi_alloc_skb(&rx_ring->q_vector->napi,
+				     FM10K_RX_HDR_LEN);
+		if (unlikely(!skb)) {
+			rx_ring->rx_stats.alloc_failed++;
+			return NULL;
+		}
+
+		/* we will be copying header into skb->data in
+		 * pskb_may_pull so it is in our interest to prefetch
+		 * it now to avoid a possible cache miss
+		 */
+		prefetchw(skb->data);
+	}
+
+	/* 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);
+
+	/* pull page into skb */
+	if (fm10k_add_rx_frag(rx_buffer, size, rx_desc, skb)) {
+		/* hand second half of page back to the ring */
+		fm10k_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* we are not reusing the buffer so unmap it */
+		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	/* clear contents of rx_buffer */
+	rx_buffer->page = NULL;
+
+	return skb;
+}
+
+static inline void fm10k_rx_checksum(struct fm10k_ring *ring,
+				     union fm10k_rx_desc *rx_desc,
+				     struct sk_buff *skb)
+{
+	skb_checksum_none_assert(skb);
+
+	/* Rx checksum disabled via ethtool */
+	if (!(ring->netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	/* TCP/UDP checksum error bit is set */
+	if (fm10k_test_staterr(rx_desc,
+			       FM10K_RXD_STATUS_L4E |
+			       FM10K_RXD_STATUS_L4E2 |
+			       FM10K_RXD_STATUS_IPE |
+			       FM10K_RXD_STATUS_IPE2)) {
+		ring->rx_stats.csum_err++;
+		return;
+	}
+
+	/* It must be a TCP or UDP packet with a valid checksum */
+	if (fm10k_test_staterr(rx_desc, FM10K_RXD_STATUS_L4CS2))
+		skb->encapsulation = true;
+	else if (!fm10k_test_staterr(rx_desc, FM10K_RXD_STATUS_L4CS))
+		return;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	ring->rx_stats.csum_good++;
+}
+
+#define FM10K_RSS_L4_TYPES_MASK \
+	(BIT(FM10K_RSSTYPE_IPV4_TCP) | \
+	 BIT(FM10K_RSSTYPE_IPV4_UDP) | \
+	 BIT(FM10K_RSSTYPE_IPV6_TCP) | \
+	 BIT(FM10K_RSSTYPE_IPV6_UDP))
+
+static inline void fm10k_rx_hash(struct fm10k_ring *ring,
+				 union fm10k_rx_desc *rx_desc,
+				 struct sk_buff *skb)
+{
+	u16 rss_type;
+
+	if (!(ring->netdev->features & NETIF_F_RXHASH))
+		return;
+
+	rss_type = le16_to_cpu(rx_desc->w.pkt_info) & FM10K_RXD_RSSTYPE_MASK;
+	if (!rss_type)
+		return;
+
+	skb_set_hash(skb, le32_to_cpu(rx_desc->d.rss),
+		     (BIT(rss_type) & FM10K_RSS_L4_TYPES_MASK) ?
+		     PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
+}
+
+static void fm10k_type_trans(struct fm10k_ring *rx_ring,
+			     union fm10k_rx_desc __maybe_unused *rx_desc,
+			     struct sk_buff *skb)
+{
+	struct net_device *dev = rx_ring->netdev;
+	struct fm10k_l2_accel *l2_accel = rcu_dereference_bh(rx_ring->l2_accel);
+
+	/* check to see if DGLORT belongs to a MACVLAN */
+	if (l2_accel) {
+		u16 idx = le16_to_cpu(FM10K_CB(skb)->fi.w.dglort) - 1;
+
+		idx -= l2_accel->dglort;
+		if (idx < l2_accel->size && l2_accel->macvlan[idx])
+			dev = l2_accel->macvlan[idx];
+		else
+			l2_accel = NULL;
+	}
+
+	/* Record Rx queue, or update macvlan statistics */
+	if (!l2_accel)
+		skb_record_rx_queue(skb, rx_ring->queue_index);
+	else
+		macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true,
+				 false);
+
+	skb->protocol = eth_type_trans(skb, dev);
+}
+
+/**
+ * fm10k_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 unsigned int fm10k_process_skb_fields(struct fm10k_ring *rx_ring,
+					     union fm10k_rx_desc *rx_desc,
+					     struct sk_buff *skb)
+{
+	unsigned int len = skb->len;
+
+	fm10k_rx_hash(rx_ring, rx_desc, skb);
+
+	fm10k_rx_checksum(rx_ring, rx_desc, skb);
+
+	FM10K_CB(skb)->tstamp = rx_desc->q.timestamp;
+
+	FM10K_CB(skb)->fi.w.vlan = rx_desc->w.vlan;
+
+	FM10K_CB(skb)->fi.d.glort = rx_desc->d.glort;
+
+	if (rx_desc->w.vlan) {
+		u16 vid = le16_to_cpu(rx_desc->w.vlan);
+
+		if ((vid & VLAN_VID_MASK) != rx_ring->vid)
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+		else if (vid & VLAN_PRIO_MASK)
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       vid & VLAN_PRIO_MASK);
+	}
+
+	fm10k_type_trans(rx_ring, rx_desc, skb);
+
+	return len;
+}
+
+/**
+ * fm10k_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ *
+ * 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 fm10k_is_non_eop(struct fm10k_ring *rx_ring,
+			     union fm10k_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(FM10K_RX_DESC(rx_ring, ntc));
+
+	if (likely(fm10k_test_staterr(rx_desc, FM10K_RXD_STATUS_EOP)))
+		return false;
+
+	return true;
+}
+
+/**
+ * fm10k_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 fm10k_cleanup_headers(struct fm10k_ring *rx_ring,
+				  union fm10k_rx_desc *rx_desc,
+				  struct sk_buff *skb)
+{
+	if (unlikely((fm10k_test_staterr(rx_desc,
+					 FM10K_RXD_STATUS_RXE)))) {
+#define FM10K_TEST_RXD_BIT(rxd, bit) \
+	((rxd)->w.csum_err & cpu_to_le16(bit))
+		if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_SWITCH_ERROR))
+			rx_ring->rx_stats.switch_errors++;
+		if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_NO_DESCRIPTOR))
+			rx_ring->rx_stats.drops++;
+		if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_PP_ERROR))
+			rx_ring->rx_stats.pp_errors++;
+		if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_SWITCH_READY))
+			rx_ring->rx_stats.link_errors++;
+		if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_TOO_BIG))
+			rx_ring->rx_stats.length_errors++;
+		dev_kfree_skb_any(skb);
+		rx_ring->rx_stats.errors++;
+		return true;
+	}
+
+	/* if eth_skb_pad returns an error the skb was freed */
+	if (eth_skb_pad(skb))
+		return true;
+
+	return false;
+}
+
+/**
+ * fm10k_receive_skb - helper function to handle rx indications
+ * @q_vector: structure containing interrupt and ring information
+ * @skb: packet to send up
+ **/
+static void fm10k_receive_skb(struct fm10k_q_vector *q_vector,
+			      struct sk_buff *skb)
+{
+	napi_gro_receive(&q_vector->napi, skb);
+}
+
+static int fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
+			      struct fm10k_ring *rx_ring,
+			      int budget)
+{
+	struct sk_buff *skb = rx_ring->skb;
+	unsigned int total_bytes = 0, total_packets = 0;
+	u16 cleaned_count = fm10k_desc_unused(rx_ring);
+
+	while (likely(total_packets < budget)) {
+		union fm10k_rx_desc *rx_desc;
+
+		/* return some buffers to hardware, one at a time is too slow */
+		if (cleaned_count >= FM10K_RX_BUFFER_WRITE) {
+			fm10k_alloc_rx_buffers(rx_ring, cleaned_count);
+			cleaned_count = 0;
+		}
+
+		rx_desc = FM10K_RX_DESC(rx_ring, rx_ring->next_to_clean);
+
+		if (!rx_desc->d.staterr)
+			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();
+
+		/* retrieve a buffer from the ring */
+		skb = fm10k_fetch_rx_buffer(rx_ring, rx_desc, skb);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb)
+			break;
+
+		cleaned_count++;
+
+		/* fetch next buffer in frame if non-eop */
+		if (fm10k_is_non_eop(rx_ring, rx_desc))
+			continue;
+
+		/* verify the packet layout is correct */
+		if (fm10k_cleanup_headers(rx_ring, rx_desc, skb)) {
+			skb = NULL;
+			continue;
+		}
+
+		/* populate checksum, timestamp, VLAN, and protocol */
+		total_bytes += fm10k_process_skb_fields(rx_ring, rx_desc, skb);
+
+		fm10k_receive_skb(q_vector, 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->syncp);
+	rx_ring->stats.packets += total_packets;
+	rx_ring->stats.bytes += total_bytes;
+	u64_stats_update_end(&rx_ring->syncp);
+	q_vector->rx.total_packets += total_packets;
+	q_vector->rx.total_bytes += total_bytes;
+
+	return total_packets;
+}
+
+#define VXLAN_HLEN (sizeof(struct udphdr) + 8)
+static struct ethhdr *fm10k_port_is_vxlan(struct sk_buff *skb)
+{
+	struct fm10k_intfc *interface = netdev_priv(skb->dev);
+
+	if (interface->vxlan_port != udp_hdr(skb)->dest)
+		return NULL;
+
+	/* return offset of udp_hdr plus 8 bytes for VXLAN header */
+	return (struct ethhdr *)(skb_transport_header(skb) + VXLAN_HLEN);
+}
+
+#define FM10K_NVGRE_RESERVED0_FLAGS htons(0x9FFF)
+#define NVGRE_TNI htons(0x2000)
+struct fm10k_nvgre_hdr {
+	__be16 flags;
+	__be16 proto;
+	__be32 tni;
+};
+
+static struct ethhdr *fm10k_gre_is_nvgre(struct sk_buff *skb)
+{
+	struct fm10k_nvgre_hdr *nvgre_hdr;
+	int hlen = ip_hdrlen(skb);
+
+	/* currently only IPv4 is supported due to hlen above */
+	if (vlan_get_protocol(skb) != htons(ETH_P_IP))
+		return NULL;
+
+	/* our transport header should be NVGRE */
+	nvgre_hdr = (struct fm10k_nvgre_hdr *)(skb_network_header(skb) + hlen);
+
+	/* verify all reserved flags are 0 */
+	if (nvgre_hdr->flags & FM10K_NVGRE_RESERVED0_FLAGS)
+		return NULL;
+
+	/* report start of ethernet header */
+	if (nvgre_hdr->flags & NVGRE_TNI)
+		return (struct ethhdr *)(nvgre_hdr + 1);
+
+	return (struct ethhdr *)(&nvgre_hdr->tni);
+}
+
+__be16 fm10k_tx_encap_offload(struct sk_buff *skb)
+{
+	u8 l4_hdr = 0, inner_l4_hdr = 0, inner_l4_hlen;
+	struct ethhdr *eth_hdr;
+
+	if (skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
+	    skb->inner_protocol != htons(ETH_P_TEB))
+		return 0;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IP):
+		l4_hdr = ip_hdr(skb)->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		l4_hdr = ipv6_hdr(skb)->nexthdr;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (l4_hdr) {
+	case IPPROTO_UDP:
+		eth_hdr = fm10k_port_is_vxlan(skb);
+		break;
+	case IPPROTO_GRE:
+		eth_hdr = fm10k_gre_is_nvgre(skb);
+		break;
+	default:
+		return 0;
+	}
+
+	if (!eth_hdr)
+		return 0;
+
+	switch (eth_hdr->h_proto) {
+	case htons(ETH_P_IP):
+		inner_l4_hdr = inner_ip_hdr(skb)->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		inner_l4_hdr = inner_ipv6_hdr(skb)->nexthdr;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (inner_l4_hdr) {
+	case IPPROTO_TCP:
+		inner_l4_hlen = inner_tcp_hdrlen(skb);
+		break;
+	case IPPROTO_UDP:
+		inner_l4_hlen = 8;
+		break;
+	default:
+		return 0;
+	}
+
+	/* The hardware allows tunnel offloads only if the combined inner and
+	 * outer header is 184 bytes or less
+	 */
+	if (skb_inner_transport_header(skb) + inner_l4_hlen -
+	    skb_mac_header(skb) > FM10K_TUNNEL_HEADER_LENGTH)
+		return 0;
+
+	return eth_hdr->h_proto;
+}
+
+static int fm10k_tso(struct fm10k_ring *tx_ring,
+		     struct fm10k_tx_buffer *first)
+{
+	struct sk_buff *skb = first->skb;
+	struct fm10k_tx_desc *tx_desc;
+	unsigned char *th;
+	u8 hdrlen;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	/* compute header lengths */
+	if (skb->encapsulation) {
+		if (!fm10k_tx_encap_offload(skb))
+			goto err_vxlan;
+		th = skb_inner_transport_header(skb);
+	} else {
+		th = skb_transport_header(skb);
+	}
+
+	/* compute offset from SOF to transport header and add header len */
+	hdrlen = (th - skb->data) + (((struct tcphdr *)th)->doff << 2);
+
+	first->tx_flags |= FM10K_TX_FLAGS_CSUM;
+
+	/* update gso size and bytecount with header size */
+	first->gso_segs = skb_shinfo(skb)->gso_segs;
+	first->bytecount += (first->gso_segs - 1) * hdrlen;
+
+	/* populate Tx descriptor header size and mss */
+	tx_desc = FM10K_TX_DESC(tx_ring, tx_ring->next_to_use);
+	tx_desc->hdrlen = hdrlen;
+	tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
+
+	return 1;
+
+err_vxlan:
+	tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL;
+	if (net_ratelimit())
+		netdev_err(tx_ring->netdev,
+			   "TSO requested for unsupported tunnel, disabling offload\n");
+	return -1;
+}
+
+static void fm10k_tx_csum(struct fm10k_ring *tx_ring,
+			  struct fm10k_tx_buffer *first)
+{
+	struct sk_buff *skb = first->skb;
+	struct fm10k_tx_desc *tx_desc;
+	union {
+		struct iphdr *ipv4;
+		struct ipv6hdr *ipv6;
+		u8 *raw;
+	} network_hdr;
+	u8 *transport_hdr;
+	__be16 frag_off;
+	__be16 protocol;
+	u8 l4_hdr = 0;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		goto no_csum;
+
+	if (skb->encapsulation) {
+		protocol = fm10k_tx_encap_offload(skb);
+		if (!protocol) {
+			if (skb_checksum_help(skb)) {
+				dev_warn(tx_ring->dev,
+					 "failed to offload encap csum!\n");
+				tx_ring->tx_stats.csum_err++;
+			}
+			goto no_csum;
+		}
+		network_hdr.raw = skb_inner_network_header(skb);
+		transport_hdr = skb_inner_transport_header(skb);
+	} else {
+		protocol = vlan_get_protocol(skb);
+		network_hdr.raw = skb_network_header(skb);
+		transport_hdr = skb_transport_header(skb);
+	}
+
+	switch (protocol) {
+	case htons(ETH_P_IP):
+		l4_hdr = network_hdr.ipv4->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		l4_hdr = network_hdr.ipv6->nexthdr;
+		if (likely((transport_hdr - network_hdr.raw) ==
+			   sizeof(struct ipv6hdr)))
+			break;
+		ipv6_skip_exthdr(skb, network_hdr.raw - skb->data +
+				      sizeof(struct ipv6hdr),
+				 &l4_hdr, &frag_off);
+		if (unlikely(frag_off))
+			l4_hdr = NEXTHDR_FRAGMENT;
+		break;
+	default:
+		break;
+	}
+
+	switch (l4_hdr) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		break;
+	case IPPROTO_GRE:
+		if (skb->encapsulation)
+			break;
+		fallthrough;
+	default:
+		if (unlikely(net_ratelimit())) {
+			dev_warn(tx_ring->dev,
+				 "partial checksum, version=%d l4 proto=%x\n",
+				 protocol, l4_hdr);
+		}
+		skb_checksum_help(skb);
+		tx_ring->tx_stats.csum_err++;
+		goto no_csum;
+	}
+
+	/* update TX checksum flag */
+	first->tx_flags |= FM10K_TX_FLAGS_CSUM;
+	tx_ring->tx_stats.csum_good++;
+
+no_csum:
+	/* populate Tx descriptor header size and mss */
+	tx_desc = FM10K_TX_DESC(tx_ring, tx_ring->next_to_use);
+	tx_desc->hdrlen = 0;
+	tx_desc->mss = 0;
+}
+
+#define FM10K_SET_FLAG(_input, _flag, _result) \
+	((_flag <= _result) ? \
+	 ((u32)(_input & _flag) * (_result / _flag)) : \
+	 ((u32)(_input & _flag) / (_flag / _result)))
+
+static u8 fm10k_tx_desc_flags(struct sk_buff *skb, u32 tx_flags)
+{
+	/* set type for advanced descriptor with frame checksum insertion */
+	u32 desc_flags = 0;
+
+	/* set checksum offload bits */
+	desc_flags |= FM10K_SET_FLAG(tx_flags, FM10K_TX_FLAGS_CSUM,
+				     FM10K_TXD_FLAG_CSUM);
+
+	return desc_flags;
+}
+
+static bool fm10k_tx_desc_push(struct fm10k_ring *tx_ring,
+			       struct fm10k_tx_desc *tx_desc, u16 i,
+			       dma_addr_t dma, unsigned int size, u8 desc_flags)
+{
+	/* set RS and INT for last frame in a cache line */
+	if ((++i & (FM10K_TXD_WB_FIFO_SIZE - 1)) == 0)
+		desc_flags |= FM10K_TXD_FLAG_RS | FM10K_TXD_FLAG_INT;
+
+	/* record values to descriptor */
+	tx_desc->buffer_addr = cpu_to_le64(dma);
+	tx_desc->flags = desc_flags;
+	tx_desc->buflen = cpu_to_le16(size);
+
+	/* return true if we just wrapped the ring */
+	return i == tx_ring->count;
+}
+
+static int __fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
+{
+	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+	/* Memory barrier before checking head and tail */
+	smp_mb();
+
+	/* Check again in a case another CPU has just made room available */
+	if (likely(fm10k_desc_unused(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	++tx_ring->tx_stats.restart_queue;
+	return 0;
+}
+
+static inline int fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
+{
+	if (likely(fm10k_desc_unused(tx_ring) >= size))
+		return 0;
+	return __fm10k_maybe_stop_tx(tx_ring, size);
+}
+
+static void fm10k_tx_map(struct fm10k_ring *tx_ring,
+			 struct fm10k_tx_buffer *first)
+{
+	struct sk_buff *skb = first->skb;
+	struct fm10k_tx_buffer *tx_buffer;
+	struct fm10k_tx_desc *tx_desc;
+	skb_frag_t *frag;
+	unsigned char *data;
+	dma_addr_t dma;
+	unsigned int data_len, size;
+	u32 tx_flags = first->tx_flags;
+	u16 i = tx_ring->next_to_use;
+	u8 flags = fm10k_tx_desc_flags(skb, tx_flags);
+
+	tx_desc = FM10K_TX_DESC(tx_ring, i);
+
+	/* add HW VLAN tag */
+	if (skb_vlan_tag_present(skb))
+		tx_desc->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
+	else
+		tx_desc->vlan = 0;
+
+	size = skb_headlen(skb);
+	data = skb->data;
+
+	dma = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE);
+
+	data_len = skb->data_len;
+	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);
+
+		while (unlikely(size > FM10K_MAX_DATA_PER_TXD)) {
+			if (fm10k_tx_desc_push(tx_ring, tx_desc++, i++, dma,
+					       FM10K_MAX_DATA_PER_TXD, flags)) {
+				tx_desc = FM10K_TX_DESC(tx_ring, 0);
+				i = 0;
+			}
+
+			dma += FM10K_MAX_DATA_PER_TXD;
+			size -= FM10K_MAX_DATA_PER_TXD;
+		}
+
+		if (likely(!data_len))
+			break;
+
+		if (fm10k_tx_desc_push(tx_ring, tx_desc++, i++,
+				       dma, size, flags)) {
+			tx_desc = FM10K_TX_DESC(tx_ring, 0);
+			i = 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[i];
+	}
+
+	/* write last descriptor with LAST bit set */
+	flags |= FM10K_TXD_FLAG_LAST;
+
+	if (fm10k_tx_desc_push(tx_ring, tx_desc, i++, dma, size, flags))
+		i = 0;
+
+	/* record bytecount for BQL */
+	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
+
+	/* record SW timestamp if HW timestamp is not available */
+	skb_tx_timestamp(first->skb);
+
+	/* 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;
+
+	tx_ring->next_to_use = i;
+
+	/* Make sure there is space in the ring for the next send. */
+	fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	/* notify HW of packet */
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
+		writel(i, tx_ring->tail);
+	}
+
+	return;
+dma_error:
+	dev_err(tx_ring->dev, "TX DMA map failed\n");
+
+	/* clear dma mappings for failed tx_buffer map */
+	for (;;) {
+		tx_buffer = &tx_ring->tx_buffer[i];
+		fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+		if (tx_buffer == first)
+			break;
+		if (i == 0)
+			i = tx_ring->count;
+		i--;
+	}
+
+	tx_ring->next_to_use = i;
+}
+
+netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb,
+				  struct fm10k_ring *tx_ring)
+{
+	u16 count = TXD_USE_COUNT(skb_headlen(skb));
+	struct fm10k_tx_buffer *first;
+	unsigned short f;
+	u32 tx_flags = 0;
+	int tso;
+
+	/* need: 1 descriptor per page * PAGE_SIZE/FM10K_MAX_DATA_PER_TXD,
+	 *       + 1 desc for skb_headlen/FM10K_MAX_DATA_PER_TXD,
+	 *       + 2 desc gap to keep tail from touching head
+	 * otherwise try next time
+	 */
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+
+		count += TXD_USE_COUNT(skb_frag_size(frag));
+	}
+
+	if (fm10k_maybe_stop_tx(tx_ring, count + 3)) {
+		tx_ring->tx_stats.tx_busy++;
+		return NETDEV_TX_BUSY;
+	}
+
+	/* record the location of the first descriptor for this packet */
+	first = &tx_ring->tx_buffer[tx_ring->next_to_use];
+	first->skb = skb;
+	first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
+	first->gso_segs = 1;
+
+	/* record initial flags and protocol */
+	first->tx_flags = tx_flags;
+
+	tso = fm10k_tso(tx_ring, first);
+	if (tso < 0)
+		goto out_drop;
+	else if (!tso)
+		fm10k_tx_csum(tx_ring, first);
+
+	fm10k_tx_map(tx_ring, first);
+
+	return NETDEV_TX_OK;
+
+out_drop:
+	dev_kfree_skb_any(first->skb);
+	first->skb = NULL;
+
+	return NETDEV_TX_OK;
+}
+
+static u64 fm10k_get_tx_completed(struct fm10k_ring *ring)
+{
+	return ring->stats.packets;
+}
+
+/**
+ * fm10k_get_tx_pending - how many Tx descriptors not processed
+ * @ring: the ring structure
+ * @in_sw: is tx_pending being checked in SW or in HW?
+ */
+u64 fm10k_get_tx_pending(struct fm10k_ring *ring, bool in_sw)
+{
+	struct fm10k_intfc *interface = ring->q_vector->interface;
+	struct fm10k_hw *hw = &interface->hw;
+	u32 head, tail;
+
+	if (likely(in_sw)) {
+		head = ring->next_to_clean;
+		tail = ring->next_to_use;
+	} else {
+		head = fm10k_read_reg(hw, FM10K_TDH(ring->reg_idx));
+		tail = fm10k_read_reg(hw, FM10K_TDT(ring->reg_idx));
+	}
+
+	return ((head <= tail) ? tail : tail + ring->count) - head;
+}
+
+bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring)
+{
+	u32 tx_done = fm10k_get_tx_completed(tx_ring);
+	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
+	u32 tx_pending = fm10k_get_tx_pending(tx_ring, true);
+
+	clear_check_for_tx_hang(tx_ring);
+
+	/* Check for a hung queue, but be thorough. This verifies
+	 * that a transmit has been completed since the previous
+	 * check AND there is at least one packet pending. By
+	 * requiring this to fail twice we avoid races with
+	 * clearing the ARMED bit and conditions where we
+	 * run the check_tx_hang logic with a transmit completion
+	 * pending but without time to complete it yet.
+	 */
+	if (!tx_pending || (tx_done_old != tx_done)) {
+		/* update completed stats and continue */
+		tx_ring->tx_stats.tx_done_old = tx_done;
+		/* reset the countdown */
+		clear_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
+
+		return false;
+	}
+
+	/* make sure it is true for two checks in a row */
+	return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
+}
+
+/**
+ * fm10k_tx_timeout_reset - initiate reset due to Tx timeout
+ * @interface: driver private struct
+ **/
+void fm10k_tx_timeout_reset(struct fm10k_intfc *interface)
+{
+	/* Do the reset outside of interrupt context */
+	if (!test_bit(__FM10K_DOWN, interface->state)) {
+		interface->tx_timeout_count++;
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+		fm10k_service_event_schedule(interface);
+	}
+}
+
+/**
+ * fm10k_clean_tx_irq - Reclaim resources after transmit completes
+ * @q_vector: structure containing interrupt and ring information
+ * @tx_ring: tx ring to clean
+ * @napi_budget: Used to determine if we are in netpoll
+ **/
+static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
+			       struct fm10k_ring *tx_ring, int napi_budget)
+{
+	struct fm10k_intfc *interface = q_vector->interface;
+	struct fm10k_tx_buffer *tx_buffer;
+	struct fm10k_tx_desc *tx_desc;
+	unsigned int total_bytes = 0, total_packets = 0;
+	unsigned int budget = q_vector->tx.work_limit;
+	unsigned int i = tx_ring->next_to_clean;
+
+	if (test_bit(__FM10K_DOWN, interface->state))
+		return true;
+
+	tx_buffer = &tx_ring->tx_buffer[i];
+	tx_desc = FM10K_TX_DESC(tx_ring, i);
+	i -= tx_ring->count;
+
+	do {
+		struct fm10k_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->flags & FM10K_TXD_FLAG_DONE))
+			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 */
+		tx_buffer->skb = NULL;
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
+			tx_buffer++;
+			tx_desc++;
+			i++;
+			if (unlikely(!i)) {
+				i -= tx_ring->count;
+				tx_buffer = tx_ring->tx_buffer;
+				tx_desc = FM10K_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;
+			tx_desc = FM10K_TX_DESC(tx_ring, 0);
+		}
+
+		/* issue prefetch for next Tx descriptor */
+		prefetch(tx_desc);
+
+		/* update budget accounting */
+		budget--;
+	} while (likely(budget));
+
+	i += tx_ring->count;
+	tx_ring->next_to_clean = i;
+	u64_stats_update_begin(&tx_ring->syncp);
+	tx_ring->stats.bytes += total_bytes;
+	tx_ring->stats.packets += total_packets;
+	u64_stats_update_end(&tx_ring->syncp);
+	q_vector->tx.total_bytes += total_bytes;
+	q_vector->tx.total_packets += total_packets;
+
+	if (check_for_tx_hang(tx_ring) && fm10k_check_tx_hang(tx_ring)) {
+		/* schedule immediate reset if we believe we hung */
+		struct fm10k_hw *hw = &interface->hw;
+
+		netif_err(interface, drv, tx_ring->netdev,
+			  "Detected Tx Unit Hang\n"
+			  "  Tx Queue             <%d>\n"
+			  "  TDH, TDT             <%x>, <%x>\n"
+			  "  next_to_use          <%x>\n"
+			  "  next_to_clean        <%x>\n",
+			  tx_ring->queue_index,
+			  fm10k_read_reg(hw, FM10K_TDH(tx_ring->reg_idx)),
+			  fm10k_read_reg(hw, FM10K_TDT(tx_ring->reg_idx)),
+			  tx_ring->next_to_use, i);
+
+		netif_stop_subqueue(tx_ring->netdev,
+				    tx_ring->queue_index);
+
+		netif_info(interface, probe, tx_ring->netdev,
+			   "tx hang %d detected on queue %d, resetting interface\n",
+			   interface->tx_timeout_count + 1,
+			   tx_ring->queue_index);
+
+		fm10k_tx_timeout_reset(interface);
+
+		/* the netdev is about to reset, no point in enabling stuff */
+		return true;
+	}
+
+	/* notify netdev of completed buffers */
+	netdev_tx_completed_queue(txring_txq(tx_ring),
+				  total_packets, total_bytes);
+
+#define TX_WAKE_THRESHOLD min_t(u16, FM10K_MIN_TXD - 1, DESC_NEEDED * 2)
+	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
+		     (fm10k_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(__FM10K_DOWN, interface->state)) {
+			netif_wake_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
+			++tx_ring->tx_stats.restart_queue;
+		}
+	}
+
+	return !!budget;
+}
+
+/**
+ * fm10k_update_itr - update the dynamic ITR value based on packet size
+ *
+ *      Stores a new ITR value based on strictly on packet size.  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.
+ *
+ * @ring_container: Container for rings to have ITR updated
+ **/
+static void fm10k_update_itr(struct fm10k_ring_container *ring_container)
+{
+	unsigned int avg_wire_size, packets, itr_round;
+
+	/* Only update ITR if we are using adaptive setting */
+	if (!ITR_IS_ADAPTIVE(ring_container->itr))
+		goto clear_counts;
+
+	packets = ring_container->total_packets;
+	if (!packets)
+		goto clear_counts;
+
+	avg_wire_size = ring_container->total_bytes / packets;
+
+	/* The following is a crude approximation of:
+	 *  wmem_default / (size + overhead) = desired_pkts_per_int
+	 *  rate / bits_per_byte / (size + ethernet overhead) = pkt_rate
+	 *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
+	 *
+	 * Assuming wmem_default is 212992 and overhead is 640 bytes per
+	 * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
+	 * formula down to
+	 *
+	 *  (34 * (size + 24)) / (size + 640) = ITR
+	 *
+	 * We first do some math on the packet size and then finally bitshift
+	 * by 8 after rounding up. We also have to account for PCIe link speed
+	 * difference as ITR scales based on this.
+	 */
+	if (avg_wire_size <= 360) {
+		/* Start at 250K ints/sec and gradually drop to 77K ints/sec */
+		avg_wire_size *= 8;
+		avg_wire_size += 376;
+	} else if (avg_wire_size <= 1152) {
+		/* 77K ints/sec to 45K ints/sec */
+		avg_wire_size *= 3;
+		avg_wire_size += 2176;
+	} else if (avg_wire_size <= 1920) {
+		/* 45K ints/sec to 38K ints/sec */
+		avg_wire_size += 4480;
+	} else {
+		/* plateau at a limit of 38K ints/sec */
+		avg_wire_size = 6656;
+	}
+
+	/* Perform final bitshift for division after rounding up to ensure
+	 * that the calculation will never get below a 1. The bit shift
+	 * accounts for changes in the ITR due to PCIe link speed.
+	 */
+	itr_round = READ_ONCE(ring_container->itr_scale) + 8;
+	avg_wire_size += BIT(itr_round) - 1;
+	avg_wire_size >>= itr_round;
+
+	/* write back value and retain adaptive flag */
+	ring_container->itr = avg_wire_size | FM10K_ITR_ADAPTIVE;
+
+clear_counts:
+	ring_container->total_bytes = 0;
+	ring_container->total_packets = 0;
+}
+
+static void fm10k_qv_enable(struct fm10k_q_vector *q_vector)
+{
+	/* Enable auto-mask and clear the current mask */
+	u32 itr = FM10K_ITR_ENABLE;
+
+	/* Update Tx ITR */
+	fm10k_update_itr(&q_vector->tx);
+
+	/* Update Rx ITR */
+	fm10k_update_itr(&q_vector->rx);
+
+	/* Store Tx itr in timer slot 0 */
+	itr |= (q_vector->tx.itr & FM10K_ITR_MAX);
+
+	/* Shift Rx itr to timer slot 1 */
+	itr |= (q_vector->rx.itr & FM10K_ITR_MAX) << FM10K_ITR_INTERVAL1_SHIFT;
+
+	/* Write the final value to the ITR register */
+	writel(itr, q_vector->itr);
+}
+
+static int fm10k_poll(struct napi_struct *napi, int budget)
+{
+	struct fm10k_q_vector *q_vector =
+			       container_of(napi, struct fm10k_q_vector, napi);
+	struct fm10k_ring *ring;
+	int per_ring_budget, work_done = 0;
+	bool clean_complete = true;
+
+	fm10k_for_each_ring(ring, q_vector->tx) {
+		if (!fm10k_clean_tx_irq(q_vector, ring, budget))
+			clean_complete = false;
+	}
+
+	/* Handle case where we are called by netpoll with a budget of 0 */
+	if (budget <= 0)
+		return budget;
+
+	/* attempt to distribute budget to each queue fairly, but don't
+	 * allow the budget to go below 1 because we'll exit polling
+	 */
+	if (q_vector->rx.count > 1)
+		per_ring_budget = max(budget / q_vector->rx.count, 1);
+	else
+		per_ring_budget = budget;
+
+	fm10k_for_each_ring(ring, q_vector->rx) {
+		int work = fm10k_clean_rx_irq(q_vector, ring, per_ring_budget);
+
+		work_done += work;
+		if (work >= per_ring_budget)
+			clean_complete = false;
+	}
+
+	/* If all work not completed, return budget and keep polling */
+	if (!clean_complete)
+		return budget;
+
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		fm10k_qv_enable(q_vector);
+
+	return min(work_done, budget - 1);
+}
+
+/**
+ * fm10k_set_qos_queues: Allocate queues for a QOS-enabled device
+ * @interface: board private structure to initialize
+ *
+ * When QoS (Quality of Service) is enabled, allocate queues for
+ * each traffic class.  If multiqueue isn't available,then abort QoS
+ * initialization.
+ *
+ * This function handles all combinations of Qos and RSS.
+ *
+ **/
+static bool fm10k_set_qos_queues(struct fm10k_intfc *interface)
+{
+	struct net_device *dev = interface->netdev;
+	struct fm10k_ring_feature *f;
+	int rss_i, i;
+	int pcs;
+
+	/* Map queue offset and counts onto allocated tx queues */
+	pcs = netdev_get_num_tc(dev);
+
+	if (pcs <= 1)
+		return false;
+
+	/* set QoS mask and indices */
+	f = &interface->ring_feature[RING_F_QOS];
+	f->indices = pcs;
+	f->mask = BIT(fls(pcs - 1)) - 1;
+
+	/* determine the upper limit for our current DCB mode */
+	rss_i = interface->hw.mac.max_queues / pcs;
+	rss_i = BIT(fls(rss_i) - 1);
+
+	/* set RSS mask and indices */
+	f = &interface->ring_feature[RING_F_RSS];
+	rss_i = min_t(u16, rss_i, f->limit);
+	f->indices = rss_i;
+	f->mask = BIT(fls(rss_i - 1)) - 1;
+
+	/* configure pause class to queue mapping */
+	for (i = 0; i < pcs; i++)
+		netdev_set_tc_queue(dev, i, rss_i, rss_i * i);
+
+	interface->num_rx_queues = rss_i * pcs;
+	interface->num_tx_queues = rss_i * pcs;
+
+	return true;
+}
+
+/**
+ * fm10k_set_rss_queues: Allocate queues for RSS
+ * @interface: board private structure to initialize
+ *
+ * This is our "base" multiqueue mode.  RSS (Receive Side Scaling) will try
+ * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU.
+ *
+ **/
+static bool fm10k_set_rss_queues(struct fm10k_intfc *interface)
+{
+	struct fm10k_ring_feature *f;
+	u16 rss_i;
+
+	f = &interface->ring_feature[RING_F_RSS];
+	rss_i = min_t(u16, interface->hw.mac.max_queues, f->limit);
+
+	/* record indices and power of 2 mask for RSS */
+	f->indices = rss_i;
+	f->mask = BIT(fls(rss_i - 1)) - 1;
+
+	interface->num_rx_queues = rss_i;
+	interface->num_tx_queues = rss_i;
+
+	return true;
+}
+
+/**
+ * fm10k_set_num_queues: Allocate queues for device, feature dependent
+ * @interface: board private structure to initialize
+ *
+ * This is the top level queue allocation routine.  The order here is very
+ * important, starting with the "most" number of features turned on at once,
+ * and ending with the smallest set of features.  This way large combinations
+ * can be allocated if they're turned on, and smaller combinations are the
+ * fall through conditions.
+ *
+ **/
+static void fm10k_set_num_queues(struct fm10k_intfc *interface)
+{
+	/* Attempt to setup QoS and RSS first */
+	if (fm10k_set_qos_queues(interface))
+		return;
+
+	/* If we don't have QoS, just fallback to only RSS. */
+	fm10k_set_rss_queues(interface);
+}
+
+/**
+ * fm10k_reset_num_queues - Reset the number of queues to zero
+ * @interface: board private structure
+ *
+ * This function should be called whenever we need to reset the number of
+ * queues after an error condition.
+ */
+static void fm10k_reset_num_queues(struct fm10k_intfc *interface)
+{
+	interface->num_tx_queues = 0;
+	interface->num_rx_queues = 0;
+	interface->num_q_vectors = 0;
+}
+
+/**
+ * fm10k_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @interface: board private structure to initialize
+ * @v_count: q_vectors allocated on interface, used for ring interleaving
+ * @v_idx: index of vector in interface 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 fm10k_alloc_q_vector(struct fm10k_intfc *interface,
+				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 fm10k_q_vector *q_vector;
+	struct fm10k_ring *ring;
+	int ring_count;
+
+	ring_count = txr_count + rxr_count;
+
+	/* allocate q_vector and rings */
+	q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL);
+	if (!q_vector)
+		return -ENOMEM;
+
+	/* initialize NAPI */
+	netif_napi_add(interface->netdev, &q_vector->napi, fm10k_poll);
+
+	/* tie q_vector and interface together */
+	interface->q_vector[v_idx] = q_vector;
+	q_vector->interface = interface;
+	q_vector->v_idx = v_idx;
+
+	/* initialize pointer to rings */
+	ring = q_vector->ring;
+
+	/* save Tx ring container info */
+	q_vector->tx.ring = ring;
+	q_vector->tx.work_limit = FM10K_DEFAULT_TX_WORK;
+	q_vector->tx.itr = interface->tx_itr;
+	q_vector->tx.itr_scale = interface->hw.mac.itr_scale;
+	q_vector->tx.count = txr_count;
+
+	while (txr_count) {
+		/* assign generic ring traits */
+		ring->dev = &interface->pdev->dev;
+		ring->netdev = interface->netdev;
+
+		/* configure backlink on ring */
+		ring->q_vector = q_vector;
+
+		/* apply Tx specific ring traits */
+		ring->count = interface->tx_ring_count;
+		ring->queue_index = txr_idx;
+
+		/* assign ring to interface */
+		interface->tx_ring[txr_idx] = ring;
+
+		/* update count and index */
+		txr_count--;
+		txr_idx += v_count;
+
+		/* push pointer to next ring */
+		ring++;
+	}
+
+	/* save Rx ring container info */
+	q_vector->rx.ring = ring;
+	q_vector->rx.itr = interface->rx_itr;
+	q_vector->rx.itr_scale = interface->hw.mac.itr_scale;
+	q_vector->rx.count = rxr_count;
+
+	while (rxr_count) {
+		/* assign generic ring traits */
+		ring->dev = &interface->pdev->dev;
+		ring->netdev = interface->netdev;
+		rcu_assign_pointer(ring->l2_accel, interface->l2_accel);
+
+		/* configure backlink on ring */
+		ring->q_vector = q_vector;
+
+		/* apply Rx specific ring traits */
+		ring->count = interface->rx_ring_count;
+		ring->queue_index = rxr_idx;
+
+		/* assign ring to interface */
+		interface->rx_ring[rxr_idx] = ring;
+
+		/* update count and index */
+		rxr_count--;
+		rxr_idx += v_count;
+
+		/* push pointer to next ring */
+		ring++;
+	}
+
+	fm10k_dbg_q_vector_init(q_vector);
+
+	return 0;
+}
+
+/**
+ * fm10k_free_q_vector - Free memory allocated for specific interrupt vector
+ * @interface: board private structure to initialize
+ * @v_idx: Index of vector to be freed
+ *
+ * This function frees the memory allocated to the q_vector.  In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ **/
+static void fm10k_free_q_vector(struct fm10k_intfc *interface, int v_idx)
+{
+	struct fm10k_q_vector *q_vector = interface->q_vector[v_idx];
+	struct fm10k_ring *ring;
+
+	fm10k_dbg_q_vector_exit(q_vector);
+
+	fm10k_for_each_ring(ring, q_vector->tx)
+		interface->tx_ring[ring->queue_index] = NULL;
+
+	fm10k_for_each_ring(ring, q_vector->rx)
+		interface->rx_ring[ring->queue_index] = NULL;
+
+	interface->q_vector[v_idx] = NULL;
+	netif_napi_del(&q_vector->napi);
+	kfree_rcu(q_vector, rcu);
+}
+
+/**
+ * fm10k_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @interface: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt.  If allocation fails we
+ * return -ENOMEM.
+ **/
+static int fm10k_alloc_q_vectors(struct fm10k_intfc *interface)
+{
+	unsigned int q_vectors = interface->num_q_vectors;
+	unsigned int rxr_remaining = interface->num_rx_queues;
+	unsigned int txr_remaining = interface->num_tx_queues;
+	unsigned int rxr_idx = 0, txr_idx = 0, v_idx = 0;
+	int err;
+
+	if (q_vectors >= (rxr_remaining + txr_remaining)) {
+		for (; rxr_remaining; v_idx++) {
+			err = fm10k_alloc_q_vector(interface, 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 = fm10k_alloc_q_vector(interface, 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:
+	fm10k_reset_num_queues(interface);
+
+	while (v_idx--)
+		fm10k_free_q_vector(interface, v_idx);
+
+	return -ENOMEM;
+}
+
+/**
+ * fm10k_free_q_vectors - Free memory allocated for interrupt vectors
+ * @interface: 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 fm10k_free_q_vectors(struct fm10k_intfc *interface)
+{
+	int v_idx = interface->num_q_vectors;
+
+	fm10k_reset_num_queues(interface);
+
+	while (v_idx--)
+		fm10k_free_q_vector(interface, v_idx);
+}
+
+/**
+ * fm10k_reset_msix_capability - reset MSI-X capability
+ * @interface: board private structure to initialize
+ *
+ * Reset the MSI-X capability back to its starting state
+ **/
+static void fm10k_reset_msix_capability(struct fm10k_intfc *interface)
+{
+	pci_disable_msix(interface->pdev);
+	kfree(interface->msix_entries);
+	interface->msix_entries = NULL;
+}
+
+/**
+ * fm10k_init_msix_capability - configure MSI-X capability
+ * @interface: board private structure to initialize
+ *
+ * Attempt to configure the interrupts using the best available
+ * capabilities of the hardware and the kernel.
+ **/
+static int fm10k_init_msix_capability(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	int v_budget, vector;
+
+	/* It's easy to be greedy for MSI-X vectors, but it really
+	 * doesn't do us much good if we have a lot more vectors
+	 * than CPU's.  So let's be conservative and only ask for
+	 * (roughly) the same number of vectors as there are CPU's.
+	 * the default is to use pairs of vectors
+	 */
+	v_budget = max(interface->num_rx_queues, interface->num_tx_queues);
+	v_budget = min_t(u16, v_budget, num_online_cpus());
+
+	/* account for vectors not related to queues */
+	v_budget += NON_Q_VECTORS;
+
+	/* At the same time, hardware can only support a maximum of
+	 * hw.mac->max_msix_vectors vectors.  With features
+	 * such as RSS and VMDq, we can easily surpass the number of Rx and Tx
+	 * descriptor queues supported by our device.  Thus, we cap it off in
+	 * those rare cases where the cpu count also exceeds our vector limit.
+	 */
+	v_budget = min_t(int, v_budget, hw->mac.max_msix_vectors);
+
+	/* A failure in MSI-X entry allocation is fatal. */
+	interface->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
+					  GFP_KERNEL);
+	if (!interface->msix_entries)
+		return -ENOMEM;
+
+	/* populate entry values */
+	for (vector = 0; vector < v_budget; vector++)
+		interface->msix_entries[vector].entry = vector;
+
+	/* Attempt to enable MSI-X with requested value */
+	v_budget = pci_enable_msix_range(interface->pdev,
+					 interface->msix_entries,
+					 MIN_MSIX_COUNT(hw),
+					 v_budget);
+	if (v_budget < 0) {
+		kfree(interface->msix_entries);
+		interface->msix_entries = NULL;
+		return v_budget;
+	}
+
+	/* record the number of queues available for q_vectors */
+	interface->num_q_vectors = v_budget - NON_Q_VECTORS;
+
+	return 0;
+}
+
+/**
+ * fm10k_cache_ring_qos - Descriptor ring to register mapping for QoS
+ * @interface: Interface structure continaining rings and devices
+ *
+ * Cache the descriptor ring offsets for Qos
+ **/
+static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface)
+{
+	struct net_device *dev = interface->netdev;
+	int pc, offset, rss_i, i;
+	u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1;
+	u8 num_pcs = netdev_get_num_tc(dev);
+
+	if (num_pcs <= 1)
+		return false;
+
+	rss_i = interface->ring_feature[RING_F_RSS].indices;
+
+	for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) {
+		int q_idx = pc;
+
+		for (i = 0; i < rss_i; i++) {
+			interface->tx_ring[offset + i]->reg_idx = q_idx;
+			interface->tx_ring[offset + i]->qos_pc = pc;
+			interface->rx_ring[offset + i]->reg_idx = q_idx;
+			interface->rx_ring[offset + i]->qos_pc = pc;
+			q_idx += pc_stride;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * fm10k_cache_ring_rss - Descriptor ring to register mapping for RSS
+ * @interface: Interface structure continaining rings and devices
+ *
+ * Cache the descriptor ring offsets for RSS
+ **/
+static void fm10k_cache_ring_rss(struct fm10k_intfc *interface)
+{
+	int i;
+
+	for (i = 0; i < interface->num_rx_queues; i++)
+		interface->rx_ring[i]->reg_idx = i;
+
+	for (i = 0; i < interface->num_tx_queues; i++)
+		interface->tx_ring[i]->reg_idx = i;
+}
+
+/**
+ * fm10k_assign_rings - Map rings to network devices
+ * @interface: Interface structure containing rings and devices
+ *
+ * This function is meant to go though and configure both the network
+ * devices so that they contain rings, and configure the rings so that
+ * they function with their network devices.
+ **/
+static void fm10k_assign_rings(struct fm10k_intfc *interface)
+{
+	if (fm10k_cache_ring_qos(interface))
+		return;
+
+	fm10k_cache_ring_rss(interface);
+}
+
+static void fm10k_init_reta(struct fm10k_intfc *interface)
+{
+	u16 i, rss_i = interface->ring_feature[RING_F_RSS].indices;
+	u32 reta;
+
+	/* If the Rx flow indirection table has been configured manually, we
+	 * need to maintain it when possible.
+	 */
+	if (netif_is_rxfh_configured(interface->netdev)) {
+		for (i = FM10K_RETA_SIZE; i--;) {
+			reta = interface->reta[i];
+			if ((((reta << 24) >> 24) < rss_i) &&
+			    (((reta << 16) >> 24) < rss_i) &&
+			    (((reta <<  8) >> 24) < rss_i) &&
+			    (((reta)       >> 24) < rss_i))
+				continue;
+
+			/* this should never happen */
+			dev_err(&interface->pdev->dev,
+				"RSS indirection table assigned flows out of queue bounds. Reconfiguring.\n");
+			goto repopulate_reta;
+		}
+
+		/* do nothing if all of the elements are in bounds */
+		return;
+	}
+
+repopulate_reta:
+	fm10k_write_reta(interface, NULL);
+}
+
+/**
+ * fm10k_init_queueing_scheme - Determine proper queueing scheme
+ * @interface: board private structure to initialize
+ *
+ * We determine which queueing scheme to use based on...
+ * - Hardware queue count (num_*_queues)
+ *   - defined by miscellaneous hardware support/features (RSS, etc.)
+ **/
+int fm10k_init_queueing_scheme(struct fm10k_intfc *interface)
+{
+	int err;
+
+	/* Number of supported queues */
+	fm10k_set_num_queues(interface);
+
+	/* Configure MSI-X capability */
+	err = fm10k_init_msix_capability(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev,
+			"Unable to initialize MSI-X capability\n");
+		goto err_init_msix;
+	}
+
+	/* Allocate memory for queues */
+	err = fm10k_alloc_q_vectors(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev,
+			"Unable to allocate queue vectors\n");
+		goto err_alloc_q_vectors;
+	}
+
+	/* Map rings to devices, and map devices to physical queues */
+	fm10k_assign_rings(interface);
+
+	/* Initialize RSS redirection table */
+	fm10k_init_reta(interface);
+
+	return 0;
+
+err_alloc_q_vectors:
+	fm10k_reset_msix_capability(interface);
+err_init_msix:
+	fm10k_reset_num_queues(interface);
+	return err;
+}
+
+/**
+ * fm10k_clear_queueing_scheme - Clear the current queueing scheme settings
+ * @interface: board private structure to clear queueing scheme on
+ *
+ * We go through and clear queueing specific resources and reset the structure
+ * to pre-load conditions
+ **/
+void fm10k_clear_queueing_scheme(struct fm10k_intfc *interface)
+{
+	fm10k_free_q_vectors(interface);
+	fm10k_reset_msix_capability(interface);
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
new file mode 100644
index 000000000..87fa5874f
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -0,0 +1,2182 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k_common.h"
+
+/**
+ *  fm10k_fifo_init - Initialize a message FIFO
+ *  @fifo: pointer to FIFO
+ *  @buffer: pointer to memory to be used to store FIFO
+ *  @size: maximum message size to store in FIFO, must be 2^n - 1
+ **/
+static void fm10k_fifo_init(struct fm10k_mbx_fifo *fifo, u32 *buffer, u16 size)
+{
+	fifo->buffer = buffer;
+	fifo->size = size;
+	fifo->head = 0;
+	fifo->tail = 0;
+}
+
+/**
+ *  fm10k_fifo_used - Retrieve used space in FIFO
+ *  @fifo: pointer to FIFO
+ *
+ *  This function returns the number of DWORDs used in the FIFO
+ **/
+static u16 fm10k_fifo_used(struct fm10k_mbx_fifo *fifo)
+{
+	return fifo->tail - fifo->head;
+}
+
+/**
+ *  fm10k_fifo_unused - Retrieve unused space in FIFO
+ *  @fifo: pointer to FIFO
+ *
+ *  This function returns the number of unused DWORDs in the FIFO
+ **/
+static u16 fm10k_fifo_unused(struct fm10k_mbx_fifo *fifo)
+{
+	return fifo->size + fifo->head - fifo->tail;
+}
+
+/**
+ *  fm10k_fifo_empty - Test to verify if FIFO is empty
+ *  @fifo: pointer to FIFO
+ *
+ *  This function returns true if the FIFO is empty, else false
+ **/
+static bool fm10k_fifo_empty(struct fm10k_mbx_fifo *fifo)
+{
+	return fifo->head == fifo->tail;
+}
+
+/**
+ *  fm10k_fifo_head_offset - returns indices of head with given offset
+ *  @fifo: pointer to FIFO
+ *  @offset: offset to add to head
+ *
+ *  This function returns the indices into the FIFO based on head + offset
+ **/
+static u16 fm10k_fifo_head_offset(struct fm10k_mbx_fifo *fifo, u16 offset)
+{
+	return (fifo->head + offset) & (fifo->size - 1);
+}
+
+/**
+ *  fm10k_fifo_tail_offset - returns indices of tail with given offset
+ *  @fifo: pointer to FIFO
+ *  @offset: offset to add to tail
+ *
+ *  This function returns the indices into the FIFO based on tail + offset
+ **/
+static u16 fm10k_fifo_tail_offset(struct fm10k_mbx_fifo *fifo, u16 offset)
+{
+	return (fifo->tail + offset) & (fifo->size - 1);
+}
+
+/**
+ *  fm10k_fifo_head_len - Retrieve length of first message in FIFO
+ *  @fifo: pointer to FIFO
+ *
+ *  This function returns the size of the first message in the FIFO
+ **/
+static u16 fm10k_fifo_head_len(struct fm10k_mbx_fifo *fifo)
+{
+	u32 *head = fifo->buffer + fm10k_fifo_head_offset(fifo, 0);
+
+	/* verify there is at least 1 DWORD in the fifo so *head is valid */
+	if (fm10k_fifo_empty(fifo))
+		return 0;
+
+	/* retieve the message length */
+	return FM10K_TLV_DWORD_LEN(*head);
+}
+
+/**
+ *  fm10k_fifo_head_drop - Drop the first message in FIFO
+ *  @fifo: pointer to FIFO
+ *
+ *  This function returns the size of the message dropped from the FIFO
+ **/
+static u16 fm10k_fifo_head_drop(struct fm10k_mbx_fifo *fifo)
+{
+	u16 len = fm10k_fifo_head_len(fifo);
+
+	/* update head so it is at the start of next frame */
+	fifo->head += len;
+
+	return len;
+}
+
+/**
+ *  fm10k_fifo_drop_all - Drop all messages in FIFO
+ *  @fifo: pointer to FIFO
+ *
+ *  This function resets the head pointer to drop all messages in the FIFO and
+ *  ensure the FIFO is empty.
+ **/
+static void fm10k_fifo_drop_all(struct fm10k_mbx_fifo *fifo)
+{
+	fifo->head = fifo->tail;
+}
+
+/**
+ *  fm10k_mbx_index_len - Convert a head/tail index into a length value
+ *  @mbx: pointer to mailbox
+ *  @head: head index
+ *  @tail: head index
+ *
+ *  This function takes the head and tail index and determines the length
+ *  of the data indicated by this pair.
+ **/
+static u16 fm10k_mbx_index_len(struct fm10k_mbx_info *mbx, u16 head, u16 tail)
+{
+	u16 len = tail - head;
+
+	/* we wrapped so subtract 2, one for index 0, one for all 1s index */
+	if (len > tail)
+		len -= 2;
+
+	return len & ((mbx->mbmem_len << 1) - 1);
+}
+
+/**
+ *  fm10k_mbx_tail_add - Determine new tail value with added offset
+ *  @mbx: pointer to mailbox
+ *  @offset: length to add to tail offset
+ *
+ *  This function takes the local tail index and recomputes it for
+ *  a given length added as an offset.
+ **/
+static u16 fm10k_mbx_tail_add(struct fm10k_mbx_info *mbx, u16 offset)
+{
+	u16 tail = (mbx->tail + offset + 1) & ((mbx->mbmem_len << 1) - 1);
+
+	/* add/sub 1 because we cannot have offset 0 or all 1s */
+	return (tail > mbx->tail) ? --tail : ++tail;
+}
+
+/**
+ *  fm10k_mbx_tail_sub - Determine new tail value with subtracted offset
+ *  @mbx: pointer to mailbox
+ *  @offset: length to add to tail offset
+ *
+ *  This function takes the local tail index and recomputes it for
+ *  a given length added as an offset.
+ **/
+static u16 fm10k_mbx_tail_sub(struct fm10k_mbx_info *mbx, u16 offset)
+{
+	u16 tail = (mbx->tail - offset - 1) & ((mbx->mbmem_len << 1) - 1);
+
+	/* sub/add 1 because we cannot have offset 0 or all 1s */
+	return (tail < mbx->tail) ? ++tail : --tail;
+}
+
+/**
+ *  fm10k_mbx_head_add - Determine new head value with added offset
+ *  @mbx: pointer to mailbox
+ *  @offset: length to add to head offset
+ *
+ *  This function takes the local head index and recomputes it for
+ *  a given length added as an offset.
+ **/
+static u16 fm10k_mbx_head_add(struct fm10k_mbx_info *mbx, u16 offset)
+{
+	u16 head = (mbx->head + offset + 1) & ((mbx->mbmem_len << 1) - 1);
+
+	/* add/sub 1 because we cannot have offset 0 or all 1s */
+	return (head > mbx->head) ? --head : ++head;
+}
+
+/**
+ *  fm10k_mbx_head_sub - Determine new head value with subtracted offset
+ *  @mbx: pointer to mailbox
+ *  @offset: length to add to head offset
+ *
+ *  This function takes the local head index and recomputes it for
+ *  a given length added as an offset.
+ **/
+static u16 fm10k_mbx_head_sub(struct fm10k_mbx_info *mbx, u16 offset)
+{
+	u16 head = (mbx->head - offset - 1) & ((mbx->mbmem_len << 1) - 1);
+
+	/* sub/add 1 because we cannot have offset 0 or all 1s */
+	return (head < mbx->head) ? ++head : --head;
+}
+
+/**
+ *  fm10k_mbx_pushed_tail_len - Retrieve the length of message being pushed
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will return the length of the message currently being
+ *  pushed onto the tail of the Rx queue.
+ **/
+static u16 fm10k_mbx_pushed_tail_len(struct fm10k_mbx_info *mbx)
+{
+	u32 *tail = mbx->rx.buffer + fm10k_fifo_tail_offset(&mbx->rx, 0);
+
+	/* pushed tail is only valid if pushed is set */
+	if (!mbx->pushed)
+		return 0;
+
+	return FM10K_TLV_DWORD_LEN(*tail);
+}
+
+/**
+ *  fm10k_fifo_write_copy - pulls data off of msg and places it in FIFO
+ *  @fifo: pointer to FIFO
+ *  @msg: message array to populate
+ *  @tail_offset: additional offset to add to tail pointer
+ *  @len: length of FIFO to copy into message header
+ *
+ *  This function will take a message and copy it into a section of the
+ *  FIFO.  In order to get something into a location other than just
+ *  the tail you can use tail_offset to adjust the pointer.
+ **/
+static void fm10k_fifo_write_copy(struct fm10k_mbx_fifo *fifo,
+				  const u32 *msg, u16 tail_offset, u16 len)
+{
+	u16 end = fm10k_fifo_tail_offset(fifo, tail_offset);
+	u32 *tail = fifo->buffer + end;
+
+	/* track when we should cross the end of the FIFO */
+	end = fifo->size - end;
+
+	/* copy end of message before start of message */
+	if (end < len)
+		memcpy(fifo->buffer, msg + end, (len - end) << 2);
+	else
+		end = len;
+
+	/* Copy remaining message into Tx FIFO */
+	memcpy(tail, msg, end << 2);
+}
+
+/**
+ *  fm10k_fifo_enqueue - Enqueues the message to the tail of the FIFO
+ *  @fifo: pointer to FIFO
+ *  @msg: message array to read
+ *
+ *  This function enqueues a message up to the size specified by the length
+ *  contained in the first DWORD of the message and will place at the tail
+ *  of the FIFO.  It will return 0 on success, or a negative value on error.
+ **/
+static s32 fm10k_fifo_enqueue(struct fm10k_mbx_fifo *fifo, const u32 *msg)
+{
+	u16 len = FM10K_TLV_DWORD_LEN(*msg);
+
+	/* verify parameters */
+	if (len > fifo->size)
+		return FM10K_MBX_ERR_SIZE;
+
+	/* verify there is room for the message */
+	if (len > fm10k_fifo_unused(fifo))
+		return FM10K_MBX_ERR_NO_SPACE;
+
+	/* Copy message into FIFO */
+	fm10k_fifo_write_copy(fifo, msg, 0, len);
+
+	/* memory barrier to guarantee FIFO is written before tail update */
+	wmb();
+
+	/* Update Tx FIFO tail */
+	fifo->tail += len;
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_validate_msg_size - Validate incoming message based on size
+ *  @mbx: pointer to mailbox
+ *  @len: length of data pushed onto buffer
+ *
+ *  This function analyzes the frame and will return a non-zero value when
+ *  the start of a message larger than the mailbox is detected.
+ **/
+static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->rx;
+	u16 total_len = 0, msg_len;
+
+	/* length should include previous amounts pushed */
+	len += mbx->pushed;
+
+	/* offset in message is based off of current message size */
+	do {
+		u32 *msg;
+
+		msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len);
+		msg_len = FM10K_TLV_DWORD_LEN(*msg);
+		total_len += msg_len;
+	} while (total_len < len);
+
+	/* message extends out of pushed section, but fits in FIFO */
+	if ((len < total_len) && (msg_len <= mbx->max_size))
+		return 0;
+
+	/* return length of invalid section */
+	return (len < total_len) ? len : (len - total_len);
+}
+
+/**
+ *  fm10k_mbx_write_copy - pulls data off of Tx FIFO and places it in mbmem
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will take a section of the Tx FIFO and copy it into the
+ *  mailbox memory.  The offset in mbmem is based on the lower bits of the
+ *  tail and len determines the length to copy.
+ **/
+static void fm10k_mbx_write_copy(struct fm10k_hw *hw,
+				 struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->tx;
+	u32 mbmem = mbx->mbmem_reg;
+	u32 *head = fifo->buffer;
+	u16 end, len, tail, mask;
+
+	if (!mbx->tail_len)
+		return;
+
+	/* determine data length and mbmem tail index */
+	mask = mbx->mbmem_len - 1;
+	len = mbx->tail_len;
+	tail = fm10k_mbx_tail_sub(mbx, len);
+	if (tail > mask)
+		tail++;
+
+	/* determine offset in the ring */
+	end = fm10k_fifo_head_offset(fifo, mbx->pulled);
+	head += end;
+
+	/* memory barrier to guarantee data is ready to be read */
+	rmb();
+
+	/* Copy message from Tx FIFO */
+	for (end = fifo->size - end; len; head = fifo->buffer) {
+		do {
+			/* adjust tail to match offset for FIFO */
+			tail &= mask;
+			if (!tail)
+				tail++;
+
+			mbx->tx_mbmem_pulled++;
+
+			/* write message to hardware FIFO */
+			fm10k_write_reg(hw, mbmem + tail++, *(head++));
+		} while (--len && --end);
+	}
+}
+
+/**
+ *  fm10k_mbx_pull_head - Pulls data off of head of Tx FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @head: acknowledgement number last received
+ *
+ *  This function will push the tail index forward based on the remote
+ *  head index.  It will then pull up to mbmem_len DWORDs off of the
+ *  head of the FIFO and will place it in the MBMEM registers
+ *  associated with the mailbox.
+ **/
+static void fm10k_mbx_pull_head(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx, u16 head)
+{
+	u16 mbmem_len, len, ack = fm10k_mbx_index_len(mbx, head, mbx->tail);
+	struct fm10k_mbx_fifo *fifo = &mbx->tx;
+
+	/* update number of bytes pulled and update bytes in transit */
+	mbx->pulled += mbx->tail_len - ack;
+
+	/* determine length of data to pull, reserve space for mbmem header */
+	mbmem_len = mbx->mbmem_len - 1;
+	len = fm10k_fifo_used(fifo) - mbx->pulled;
+	if (len > mbmem_len)
+		len = mbmem_len;
+
+	/* update tail and record number of bytes in transit */
+	mbx->tail = fm10k_mbx_tail_add(mbx, len - ack);
+	mbx->tail_len = len;
+
+	/* drop pulled messages from the FIFO */
+	for (len = fm10k_fifo_head_len(fifo);
+	     len && (mbx->pulled >= len);
+	     len = fm10k_fifo_head_len(fifo)) {
+		mbx->pulled -= fm10k_fifo_head_drop(fifo);
+		mbx->tx_messages++;
+		mbx->tx_dwords += len;
+	}
+
+	/* Copy message out from the Tx FIFO */
+	fm10k_mbx_write_copy(hw, mbx);
+}
+
+/**
+ *  fm10k_mbx_read_copy - pulls data off of mbmem and places it in Rx FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will take a section of the mailbox memory and copy it
+ *  into the Rx FIFO.  The offset is based on the lower bits of the
+ *  head and len determines the length to copy.
+ **/
+static void fm10k_mbx_read_copy(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->rx;
+	u32 mbmem = mbx->mbmem_reg ^ mbx->mbmem_len;
+	u32 *tail = fifo->buffer;
+	u16 end, len, head;
+
+	/* determine data length and mbmem head index */
+	len = mbx->head_len;
+	head = fm10k_mbx_head_sub(mbx, len);
+	if (head >= mbx->mbmem_len)
+		head++;
+
+	/* determine offset in the ring */
+	end = fm10k_fifo_tail_offset(fifo, mbx->pushed);
+	tail += end;
+
+	/* Copy message into Rx FIFO */
+	for (end = fifo->size - end; len; tail = fifo->buffer) {
+		do {
+			/* adjust head to match offset for FIFO */
+			head &= mbx->mbmem_len - 1;
+			if (!head)
+				head++;
+
+			mbx->rx_mbmem_pushed++;
+
+			/* read message from hardware FIFO */
+			*(tail++) = fm10k_read_reg(hw, mbmem + head++);
+		} while (--len && --end);
+	}
+
+	/* memory barrier to guarantee FIFO is written before tail update */
+	wmb();
+}
+
+/**
+ *  fm10k_mbx_push_tail - Pushes up to 15 DWORDs on to tail of FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @tail: tail index of message
+ *
+ *  This function will first validate the tail index and size for the
+ *  incoming message.  It then updates the acknowledgment number and
+ *  copies the data into the FIFO.  It will return the number of messages
+ *  dequeued on success and a negative value on error.
+ **/
+static s32 fm10k_mbx_push_tail(struct fm10k_hw *hw,
+			       struct fm10k_mbx_info *mbx,
+			       u16 tail)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->rx;
+	u16 len, seq = fm10k_mbx_index_len(mbx, mbx->head, tail);
+
+	/* determine length of data to push */
+	len = fm10k_fifo_unused(fifo) - mbx->pushed;
+	if (len > seq)
+		len = seq;
+
+	/* update head and record bytes received */
+	mbx->head = fm10k_mbx_head_add(mbx, len);
+	mbx->head_len = len;
+
+	/* nothing to do if there is no data */
+	if (!len)
+		return 0;
+
+	/* Copy msg into Rx FIFO */
+	fm10k_mbx_read_copy(hw, mbx);
+
+	/* determine if there are any invalid lengths in message */
+	if (fm10k_mbx_validate_msg_size(mbx, len))
+		return FM10K_MBX_ERR_SIZE;
+
+	/* Update pushed */
+	mbx->pushed += len;
+
+	/* flush any completed messages */
+	for (len = fm10k_mbx_pushed_tail_len(mbx);
+	     len && (mbx->pushed >= len);
+	     len = fm10k_mbx_pushed_tail_len(mbx)) {
+		fifo->tail += len;
+		mbx->pushed -= len;
+		mbx->rx_messages++;
+		mbx->rx_dwords += len;
+	}
+
+	return 0;
+}
+
+/* pre-generated data for generating the CRC based on the poly 0xAC9A. */
+static const u16 fm10k_crc_16b_table[256] = {
+	0x0000, 0x7956, 0xF2AC, 0x8BFA, 0xBC6D, 0xC53B, 0x4EC1, 0x3797,
+	0x21EF, 0x58B9, 0xD343, 0xAA15, 0x9D82, 0xE4D4, 0x6F2E, 0x1678,
+	0x43DE, 0x3A88, 0xB172, 0xC824, 0xFFB3, 0x86E5, 0x0D1F, 0x7449,
+	0x6231, 0x1B67, 0x909D, 0xE9CB, 0xDE5C, 0xA70A, 0x2CF0, 0x55A6,
+	0x87BC, 0xFEEA, 0x7510, 0x0C46, 0x3BD1, 0x4287, 0xC97D, 0xB02B,
+	0xA653, 0xDF05, 0x54FF, 0x2DA9, 0x1A3E, 0x6368, 0xE892, 0x91C4,
+	0xC462, 0xBD34, 0x36CE, 0x4F98, 0x780F, 0x0159, 0x8AA3, 0xF3F5,
+	0xE58D, 0x9CDB, 0x1721, 0x6E77, 0x59E0, 0x20B6, 0xAB4C, 0xD21A,
+	0x564D, 0x2F1B, 0xA4E1, 0xDDB7, 0xEA20, 0x9376, 0x188C, 0x61DA,
+	0x77A2, 0x0EF4, 0x850E, 0xFC58, 0xCBCF, 0xB299, 0x3963, 0x4035,
+	0x1593, 0x6CC5, 0xE73F, 0x9E69, 0xA9FE, 0xD0A8, 0x5B52, 0x2204,
+	0x347C, 0x4D2A, 0xC6D0, 0xBF86, 0x8811, 0xF147, 0x7ABD, 0x03EB,
+	0xD1F1, 0xA8A7, 0x235D, 0x5A0B, 0x6D9C, 0x14CA, 0x9F30, 0xE666,
+	0xF01E, 0x8948, 0x02B2, 0x7BE4, 0x4C73, 0x3525, 0xBEDF, 0xC789,
+	0x922F, 0xEB79, 0x6083, 0x19D5, 0x2E42, 0x5714, 0xDCEE, 0xA5B8,
+	0xB3C0, 0xCA96, 0x416C, 0x383A, 0x0FAD, 0x76FB, 0xFD01, 0x8457,
+	0xAC9A, 0xD5CC, 0x5E36, 0x2760, 0x10F7, 0x69A1, 0xE25B, 0x9B0D,
+	0x8D75, 0xF423, 0x7FD9, 0x068F, 0x3118, 0x484E, 0xC3B4, 0xBAE2,
+	0xEF44, 0x9612, 0x1DE8, 0x64BE, 0x5329, 0x2A7F, 0xA185, 0xD8D3,
+	0xCEAB, 0xB7FD, 0x3C07, 0x4551, 0x72C6, 0x0B90, 0x806A, 0xF93C,
+	0x2B26, 0x5270, 0xD98A, 0xA0DC, 0x974B, 0xEE1D, 0x65E7, 0x1CB1,
+	0x0AC9, 0x739F, 0xF865, 0x8133, 0xB6A4, 0xCFF2, 0x4408, 0x3D5E,
+	0x68F8, 0x11AE, 0x9A54, 0xE302, 0xD495, 0xADC3, 0x2639, 0x5F6F,
+	0x4917, 0x3041, 0xBBBB, 0xC2ED, 0xF57A, 0x8C2C, 0x07D6, 0x7E80,
+	0xFAD7, 0x8381, 0x087B, 0x712D, 0x46BA, 0x3FEC, 0xB416, 0xCD40,
+	0xDB38, 0xA26E, 0x2994, 0x50C2, 0x6755, 0x1E03, 0x95F9, 0xECAF,
+	0xB909, 0xC05F, 0x4BA5, 0x32F3, 0x0564, 0x7C32, 0xF7C8, 0x8E9E,
+	0x98E6, 0xE1B0, 0x6A4A, 0x131C, 0x248B, 0x5DDD, 0xD627, 0xAF71,
+	0x7D6B, 0x043D, 0x8FC7, 0xF691, 0xC106, 0xB850, 0x33AA, 0x4AFC,
+	0x5C84, 0x25D2, 0xAE28, 0xD77E, 0xE0E9, 0x99BF, 0x1245, 0x6B13,
+	0x3EB5, 0x47E3, 0xCC19, 0xB54F, 0x82D8, 0xFB8E, 0x7074, 0x0922,
+	0x1F5A, 0x660C, 0xEDF6, 0x94A0, 0xA337, 0xDA61, 0x519B, 0x28CD };
+
+/**
+ *  fm10k_crc_16b - Generate a 16 bit CRC for a region of 16 bit data
+ *  @data: pointer to data to process
+ *  @seed: seed value for CRC
+ *  @len: length measured in 16 bits words
+ *
+ *  This function will generate a CRC based on the polynomial 0xAC9A and
+ *  whatever value is stored in the seed variable.  Note that this
+ *  value inverts the local seed and the result in order to capture all
+ *  leading and trailing zeros.
+ */
+static u16 fm10k_crc_16b(const u32 *data, u16 seed, u16 len)
+{
+	u32 result = seed;
+
+	while (len--) {
+		result ^= *(data++);
+		result = (result >> 8) ^ fm10k_crc_16b_table[result & 0xFF];
+		result = (result >> 8) ^ fm10k_crc_16b_table[result & 0xFF];
+
+		if (!(len--))
+			break;
+
+		result = (result >> 8) ^ fm10k_crc_16b_table[result & 0xFF];
+		result = (result >> 8) ^ fm10k_crc_16b_table[result & 0xFF];
+	}
+
+	return (u16)result;
+}
+
+/**
+ *  fm10k_fifo_crc - generate a CRC based off of FIFO data
+ *  @fifo: pointer to FIFO
+ *  @offset: offset point for start of FIFO
+ *  @len: number of DWORDS words to process
+ *  @seed: seed value for CRC
+ *
+ *  This function generates a CRC for some region of the FIFO
+ **/
+static u16 fm10k_fifo_crc(struct fm10k_mbx_fifo *fifo, u16 offset,
+			  u16 len, u16 seed)
+{
+	u32 *data = fifo->buffer + offset;
+
+	/* track when we should cross the end of the FIFO */
+	offset = fifo->size - offset;
+
+	/* if we are in 2 blocks process the end of the FIFO first */
+	if (offset < len) {
+		seed = fm10k_crc_16b(data, seed, offset * 2);
+		data = fifo->buffer;
+		len -= offset;
+	}
+
+	/* process any remaining bits */
+	return fm10k_crc_16b(data, seed, len * 2);
+}
+
+/**
+ *  fm10k_mbx_update_local_crc - Update the local CRC for outgoing data
+ *  @mbx: pointer to mailbox
+ *  @head: head index provided by remote mailbox
+ *
+ *  This function will generate the CRC for all data from the end of the
+ *  last head update to the current one.  It uses the result of the
+ *  previous CRC as the seed for this update.  The result is stored in
+ *  mbx->local.
+ **/
+static void fm10k_mbx_update_local_crc(struct fm10k_mbx_info *mbx, u16 head)
+{
+	u16 len = mbx->tail_len - fm10k_mbx_index_len(mbx, head, mbx->tail);
+
+	/* determine the offset for the start of the region to be pulled */
+	head = fm10k_fifo_head_offset(&mbx->tx, mbx->pulled);
+
+	/* update local CRC to include all of the pulled data */
+	mbx->local = fm10k_fifo_crc(&mbx->tx, head, len, mbx->local);
+}
+
+/**
+ *  fm10k_mbx_verify_remote_crc - Verify the CRC is correct for current data
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will take all data that has been provided from the remote
+ *  end and generate a CRC for it.  This is stored in mbx->remote.  The
+ *  CRC for the header is then computed and if the result is non-zero this
+ *  is an error and we signal an error dropping all data and resetting the
+ *  connection.
+ */
+static s32 fm10k_mbx_verify_remote_crc(struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->rx;
+	u16 len = mbx->head_len;
+	u16 offset = fm10k_fifo_tail_offset(fifo, mbx->pushed) - len;
+	u16 crc;
+
+	/* update the remote CRC if new data has been received */
+	if (len)
+		mbx->remote = fm10k_fifo_crc(fifo, offset, len, mbx->remote);
+
+	/* process the full header as we have to validate the CRC */
+	crc = fm10k_crc_16b(&mbx->mbx_hdr, mbx->remote, 1);
+
+	/* notify other end if we have a problem */
+	return crc ? FM10K_MBX_ERR_CRC : 0;
+}
+
+/**
+ *  fm10k_mbx_rx_ready - Indicates that a message is ready in the Rx FIFO
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns true if there is a message in the Rx FIFO to dequeue.
+ **/
+static bool fm10k_mbx_rx_ready(struct fm10k_mbx_info *mbx)
+{
+	u16 msg_size = fm10k_fifo_head_len(&mbx->rx);
+
+	return msg_size && (fm10k_fifo_used(&mbx->rx) >= msg_size);
+}
+
+/**
+ *  fm10k_mbx_tx_ready - Indicates that the mailbox is in state ready for Tx
+ *  @mbx: pointer to mailbox
+ *  @len: verify free space is >= this value
+ *
+ *  This function returns true if the mailbox is in a state ready to transmit.
+ **/
+static bool fm10k_mbx_tx_ready(struct fm10k_mbx_info *mbx, u16 len)
+{
+	u16 fifo_unused = fm10k_fifo_unused(&mbx->tx);
+
+	return (mbx->state == FM10K_STATE_OPEN) && (fifo_unused >= len);
+}
+
+/**
+ *  fm10k_mbx_tx_complete - Indicates that the Tx FIFO has been emptied
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns true if the Tx FIFO is empty.
+ **/
+static bool fm10k_mbx_tx_complete(struct fm10k_mbx_info *mbx)
+{
+	return fm10k_fifo_empty(&mbx->tx);
+}
+
+/**
+ *  fm10k_mbx_dequeue_rx - Dequeues the message from the head in the Rx FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function dequeues messages and hands them off to the TLV parser.
+ *  It will return the number of messages processed when called.
+ **/
+static u16 fm10k_mbx_dequeue_rx(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->rx;
+	s32 err;
+	u16 cnt;
+
+	/* parse Rx messages out of the Rx FIFO to empty it */
+	for (cnt = 0; !fm10k_fifo_empty(fifo); cnt++) {
+		err = fm10k_tlv_msg_parse(hw, fifo->buffer + fifo->head,
+					  mbx, mbx->msg_data);
+		if (err < 0)
+			mbx->rx_parse_err++;
+
+		fm10k_fifo_head_drop(fifo);
+	}
+
+	/* shift remaining bytes back to start of FIFO */
+	memmove(fifo->buffer, fifo->buffer + fifo->tail, mbx->pushed << 2);
+
+	/* shift head and tail based on the memory we moved */
+	fifo->tail -= fifo->head;
+	fifo->head = 0;
+
+	return cnt;
+}
+
+/**
+ *  fm10k_mbx_enqueue_tx - Enqueues the message to the tail of the Tx FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @msg: message array to read
+ *
+ *  This function enqueues a message up to the size specified by the length
+ *  contained in the first DWORD of the message and will place at the tail
+ *  of the FIFO.  It will return 0 on success, or a negative value on error.
+ **/
+static s32 fm10k_mbx_enqueue_tx(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx, const u32 *msg)
+{
+	u32 countdown = mbx->timeout;
+	s32 err;
+
+	switch (mbx->state) {
+	case FM10K_STATE_CLOSED:
+	case FM10K_STATE_DISCONNECT:
+		return FM10K_MBX_ERR_NO_MBX;
+	default:
+		break;
+	}
+
+	/* enqueue the message on the Tx FIFO */
+	err = fm10k_fifo_enqueue(&mbx->tx, msg);
+
+	/* if it failed give the FIFO a chance to drain */
+	while (err && countdown) {
+		countdown--;
+		udelay(mbx->udelay);
+		mbx->ops.process(hw, mbx);
+		err = fm10k_fifo_enqueue(&mbx->tx, msg);
+	}
+
+	/* if we failed treat the error */
+	if (err) {
+		mbx->timeout = 0;
+		mbx->tx_busy++;
+	}
+
+	/* begin processing message, ignore errors as this is just meant
+	 * to start the mailbox flow so we are not concerned if there
+	 * is a bad error, or the mailbox is already busy with a request
+	 */
+	if (!mbx->tail_len)
+		mbx->ops.process(hw, mbx);
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_read - Copies the mbmem to local message buffer
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function copies the message from the mbmem to the message array
+ **/
+static s32 fm10k_mbx_read(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+	/* only allow one reader in here at a time */
+	if (mbx->mbx_hdr)
+		return FM10K_MBX_ERR_BUSY;
+
+	/* read to capture initial interrupt bits */
+	if (fm10k_read_reg(hw, mbx->mbx_reg) & FM10K_MBX_REQ_INTERRUPT)
+		mbx->mbx_lock = FM10K_MBX_ACK;
+
+	/* write back interrupt bits to clear */
+	fm10k_write_reg(hw, mbx->mbx_reg,
+			FM10K_MBX_REQ_INTERRUPT | FM10K_MBX_ACK_INTERRUPT);
+
+	/* read remote header */
+	mbx->mbx_hdr = fm10k_read_reg(hw, mbx->mbmem_reg ^ mbx->mbmem_len);
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_write - Copies the local message buffer to mbmem
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function copies the message from the message array to mbmem
+ **/
+static void fm10k_mbx_write(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+	u32 mbmem = mbx->mbmem_reg;
+
+	/* write new msg header to notify recipient of change */
+	fm10k_write_reg(hw, mbmem, mbx->mbx_hdr);
+
+	/* write mailbox to send interrupt */
+	if (mbx->mbx_lock)
+		fm10k_write_reg(hw, mbx->mbx_reg, mbx->mbx_lock);
+
+	/* we no longer are using the header so free it */
+	mbx->mbx_hdr = 0;
+	mbx->mbx_lock = 0;
+}
+
+/**
+ *  fm10k_mbx_create_connect_hdr - Generate a connect mailbox header
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns a connection mailbox header
+ **/
+static void fm10k_mbx_create_connect_hdr(struct fm10k_mbx_info *mbx)
+{
+	mbx->mbx_lock |= FM10K_MBX_REQ;
+
+	mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_CONNECT, TYPE) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->head, HEAD) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->rx.size - 1, CONNECT_SIZE);
+}
+
+/**
+ *  fm10k_mbx_create_data_hdr - Generate a data mailbox header
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns a data mailbox header
+ **/
+static void fm10k_mbx_create_data_hdr(struct fm10k_mbx_info *mbx)
+{
+	u32 hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_DATA, TYPE) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->tail, TAIL) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->head, HEAD);
+	struct fm10k_mbx_fifo *fifo = &mbx->tx;
+	u16 crc;
+
+	if (mbx->tail_len)
+		mbx->mbx_lock |= FM10K_MBX_REQ;
+
+	/* generate CRC for data in flight and header */
+	crc = fm10k_fifo_crc(fifo, fm10k_fifo_head_offset(fifo, mbx->pulled),
+			     mbx->tail_len, mbx->local);
+	crc = fm10k_crc_16b(&hdr, crc, 1);
+
+	/* load header to memory to be written */
+	mbx->mbx_hdr = hdr | FM10K_MSG_HDR_FIELD_SET(crc, CRC);
+}
+
+/**
+ *  fm10k_mbx_create_disconnect_hdr - Generate a disconnect mailbox header
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns a disconnect mailbox header
+ **/
+static void fm10k_mbx_create_disconnect_hdr(struct fm10k_mbx_info *mbx)
+{
+	u32 hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_DISCONNECT, TYPE) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->tail, TAIL) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->head, HEAD);
+	u16 crc = fm10k_crc_16b(&hdr, mbx->local, 1);
+
+	mbx->mbx_lock |= FM10K_MBX_ACK;
+
+	/* load header to memory to be written */
+	mbx->mbx_hdr = hdr | FM10K_MSG_HDR_FIELD_SET(crc, CRC);
+}
+
+/**
+ *  fm10k_mbx_create_fake_disconnect_hdr - Generate a false disconnect mbox hdr
+ *  @mbx: pointer to mailbox
+ *
+ *  This function creates a fake disconnect header for loading into remote
+ *  mailbox header. The primary purpose is to prevent errors on immediate
+ *  start up after mbx->connect.
+ **/
+static void fm10k_mbx_create_fake_disconnect_hdr(struct fm10k_mbx_info *mbx)
+{
+	u32 hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_DISCONNECT, TYPE) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->head, TAIL) |
+		  FM10K_MSG_HDR_FIELD_SET(mbx->tail, HEAD);
+	u16 crc = fm10k_crc_16b(&hdr, mbx->local, 1);
+
+	mbx->mbx_lock |= FM10K_MBX_ACK;
+
+	/* load header to memory to be written */
+	mbx->mbx_hdr = hdr | FM10K_MSG_HDR_FIELD_SET(crc, CRC);
+}
+
+/**
+ *  fm10k_mbx_create_error_msg - Generate an error message
+ *  @mbx: pointer to mailbox
+ *  @err: local error encountered
+ *
+ *  This function will interpret the error provided by err, and based on
+ *  that it may shift the message by 1 DWORD and then place an error header
+ *  at the start of the message.
+ **/
+static void fm10k_mbx_create_error_msg(struct fm10k_mbx_info *mbx, s32 err)
+{
+	/* only generate an error message for these types */
+	switch (err) {
+	case FM10K_MBX_ERR_TAIL:
+	case FM10K_MBX_ERR_HEAD:
+	case FM10K_MBX_ERR_TYPE:
+	case FM10K_MBX_ERR_SIZE:
+	case FM10K_MBX_ERR_RSVD0:
+	case FM10K_MBX_ERR_CRC:
+		break;
+	default:
+		return;
+	}
+
+	mbx->mbx_lock |= FM10K_MBX_REQ;
+
+	mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_ERROR, TYPE) |
+		       FM10K_MSG_HDR_FIELD_SET(err, ERR_NO) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->head, HEAD);
+}
+
+/**
+ *  fm10k_mbx_validate_msg_hdr - Validate common fields in the message header
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will parse up the fields in the mailbox header and return
+ *  an error if the header contains any of a number of invalid configurations
+ *  including unrecognized type, invalid route, or a malformed message.
+ **/
+static s32 fm10k_mbx_validate_msg_hdr(struct fm10k_mbx_info *mbx)
+{
+	u16 type, rsvd0, head, tail, size;
+	const u32 *hdr = &mbx->mbx_hdr;
+
+	type = FM10K_MSG_HDR_FIELD_GET(*hdr, TYPE);
+	rsvd0 = FM10K_MSG_HDR_FIELD_GET(*hdr, RSVD0);
+	tail = FM10K_MSG_HDR_FIELD_GET(*hdr, TAIL);
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
+	size = FM10K_MSG_HDR_FIELD_GET(*hdr, CONNECT_SIZE);
+
+	if (rsvd0)
+		return FM10K_MBX_ERR_RSVD0;
+
+	switch (type) {
+	case FM10K_MSG_DISCONNECT:
+		/* validate that all data has been received */
+		if (tail != mbx->head)
+			return FM10K_MBX_ERR_TAIL;
+
+		fallthrough;
+	case FM10K_MSG_DATA:
+		/* validate that head is moving correctly */
+		if (!head || (head == FM10K_MSG_HDR_MASK(HEAD)))
+			return FM10K_MBX_ERR_HEAD;
+		if (fm10k_mbx_index_len(mbx, head, mbx->tail) > mbx->tail_len)
+			return FM10K_MBX_ERR_HEAD;
+
+		/* validate that tail is moving correctly */
+		if (!tail || (tail == FM10K_MSG_HDR_MASK(TAIL)))
+			return FM10K_MBX_ERR_TAIL;
+		if (fm10k_mbx_index_len(mbx, mbx->head, tail) < mbx->mbmem_len)
+			break;
+
+		return FM10K_MBX_ERR_TAIL;
+	case FM10K_MSG_CONNECT:
+		/* validate size is in range and is power of 2 mask */
+		if ((size < FM10K_VFMBX_MSG_MTU) || (size & (size + 1)))
+			return FM10K_MBX_ERR_SIZE;
+
+		fallthrough;
+	case FM10K_MSG_ERROR:
+		if (!head || (head == FM10K_MSG_HDR_MASK(HEAD)))
+			return FM10K_MBX_ERR_HEAD;
+		/* neither create nor error include a tail offset */
+		if (tail)
+			return FM10K_MBX_ERR_TAIL;
+
+		break;
+	default:
+		return FM10K_MBX_ERR_TYPE;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_create_reply - Generate reply based on state and remote head
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @head: acknowledgement number
+ *
+ *  This function will generate an outgoing message based on the current
+ *  mailbox state and the remote FIFO head.  It will return the length
+ *  of the outgoing message excluding header on success, and a negative value
+ *  on error.
+ **/
+static s32 fm10k_mbx_create_reply(struct fm10k_hw *hw,
+				  struct fm10k_mbx_info *mbx, u16 head)
+{
+	switch (mbx->state) {
+	case FM10K_STATE_OPEN:
+	case FM10K_STATE_DISCONNECT:
+		/* update our checksum for the outgoing data */
+		fm10k_mbx_update_local_crc(mbx, head);
+
+		/* as long as other end recognizes us keep sending data */
+		fm10k_mbx_pull_head(hw, mbx, head);
+
+		/* generate new header based on data */
+		if (mbx->tail_len || (mbx->state == FM10K_STATE_OPEN))
+			fm10k_mbx_create_data_hdr(mbx);
+		else
+			fm10k_mbx_create_disconnect_hdr(mbx);
+		break;
+	case FM10K_STATE_CONNECT:
+		/* send disconnect even if we aren't connected */
+		fm10k_mbx_create_connect_hdr(mbx);
+		break;
+	case FM10K_STATE_CLOSED:
+		/* generate new header based on data */
+		fm10k_mbx_create_disconnect_hdr(mbx);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_reset_work- Reset internal pointers for any pending work
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will reset all internal pointers so any work in progress
+ *  is dropped.  This call should occur every time we transition from the
+ *  open state to the connect state.
+ **/
+static void fm10k_mbx_reset_work(struct fm10k_mbx_info *mbx)
+{
+	u16 len, head, ack;
+
+	/* reset our outgoing max size back to Rx limits */
+	mbx->max_size = mbx->rx.size - 1;
+
+	/* update mbx->pulled to account for tail_len and ack */
+	head = FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, HEAD);
+	ack = fm10k_mbx_index_len(mbx, head, mbx->tail);
+	mbx->pulled += mbx->tail_len - ack;
+
+	/* now drop any messages which have started or finished transmitting */
+	while (fm10k_fifo_head_len(&mbx->tx) && mbx->pulled) {
+		len = fm10k_fifo_head_drop(&mbx->tx);
+		mbx->tx_dropped++;
+		if (mbx->pulled >= len)
+			mbx->pulled -= len;
+		else
+			mbx->pulled = 0;
+	}
+
+	/* just do a quick resysnc to start of message */
+	mbx->pushed = 0;
+	mbx->pulled = 0;
+	mbx->tail_len = 0;
+	mbx->head_len = 0;
+	mbx->rx.tail = 0;
+	mbx->rx.head = 0;
+}
+
+/**
+ *  fm10k_mbx_update_max_size - Update the max_size and drop any large messages
+ *  @mbx: pointer to mailbox
+ *  @size: new value for max_size
+ *
+ *  This function updates the max_size value and drops any outgoing messages
+ *  at the head of the Tx FIFO if they are larger than max_size. It does not
+ *  drop all messages, as this is too difficult to parse and remove them from
+ *  the FIFO. Instead, rely on the checking to ensure that messages larger
+ *  than max_size aren't pushed into the memory buffer.
+ **/
+static void fm10k_mbx_update_max_size(struct fm10k_mbx_info *mbx, u16 size)
+{
+	u16 len;
+
+	mbx->max_size = size;
+
+	/* flush any oversized messages from the queue */
+	for (len = fm10k_fifo_head_len(&mbx->tx);
+	     len > size;
+	     len = fm10k_fifo_head_len(&mbx->tx)) {
+		fm10k_fifo_head_drop(&mbx->tx);
+		mbx->tx_dropped++;
+	}
+}
+
+/**
+ *  fm10k_mbx_connect_reset - Reset following request for reset
+ *  @mbx: pointer to mailbox
+ *
+ *  This function resets the mailbox to either a disconnected state
+ *  or a connect state depending on the current mailbox state
+ **/
+static void fm10k_mbx_connect_reset(struct fm10k_mbx_info *mbx)
+{
+	/* just do a quick resysnc to start of frame */
+	fm10k_mbx_reset_work(mbx);
+
+	/* reset CRC seeds */
+	mbx->local = FM10K_MBX_CRC_SEED;
+	mbx->remote = FM10K_MBX_CRC_SEED;
+
+	/* we cannot exit connect until the size is good */
+	if (mbx->state == FM10K_STATE_OPEN)
+		mbx->state = FM10K_STATE_CONNECT;
+	else
+		mbx->state = FM10K_STATE_CLOSED;
+}
+
+/**
+ *  fm10k_mbx_process_connect - Process connect header
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will read an incoming connect header and reply with the
+ *  appropriate message.  It will return a value indicating the number of
+ *  data DWORDs on success, or will return a negative value on failure.
+ **/
+static s32 fm10k_mbx_process_connect(struct fm10k_hw *hw,
+				     struct fm10k_mbx_info *mbx)
+{
+	const enum fm10k_mbx_state state = mbx->state;
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 size, head;
+
+	/* we will need to pull all of the fields for verification */
+	size = FM10K_MSG_HDR_FIELD_GET(*hdr, CONNECT_SIZE);
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
+
+	switch (state) {
+	case FM10K_STATE_DISCONNECT:
+	case FM10K_STATE_OPEN:
+		/* reset any in-progress work */
+		fm10k_mbx_connect_reset(mbx);
+		break;
+	case FM10K_STATE_CONNECT:
+		/* we cannot exit connect until the size is good */
+		if (size > mbx->rx.size) {
+			mbx->max_size = mbx->rx.size - 1;
+		} else {
+			/* record the remote system requesting connection */
+			mbx->state = FM10K_STATE_OPEN;
+
+			fm10k_mbx_update_max_size(mbx, size);
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* align our tail index to remote head index */
+	mbx->tail = head;
+
+	return fm10k_mbx_create_reply(hw, mbx, head);
+}
+
+/**
+ *  fm10k_mbx_process_data - Process data header
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will read an incoming data header and reply with the
+ *  appropriate message.  It will return a value indicating the number of
+ *  data DWORDs on success, or will return a negative value on failure.
+ **/
+static s32 fm10k_mbx_process_data(struct fm10k_hw *hw,
+				  struct fm10k_mbx_info *mbx)
+{
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 head, tail;
+	s32 err;
+
+	/* we will need to pull all of the fields for verification */
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
+	tail = FM10K_MSG_HDR_FIELD_GET(*hdr, TAIL);
+
+	/* if we are in connect just update our data and go */
+	if (mbx->state == FM10K_STATE_CONNECT) {
+		mbx->tail = head;
+		mbx->state = FM10K_STATE_OPEN;
+	}
+
+	/* abort on message size errors */
+	err = fm10k_mbx_push_tail(hw, mbx, tail);
+	if (err < 0)
+		return err;
+
+	/* verify the checksum on the incoming data */
+	err = fm10k_mbx_verify_remote_crc(mbx);
+	if (err)
+		return err;
+
+	/* process messages if we have received any */
+	fm10k_mbx_dequeue_rx(hw, mbx);
+
+	return fm10k_mbx_create_reply(hw, mbx, head);
+}
+
+/**
+ *  fm10k_mbx_process_disconnect - Process disconnect header
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will read an incoming disconnect header and reply with the
+ *  appropriate message.  It will return a value indicating the number of
+ *  data DWORDs on success, or will return a negative value on failure.
+ **/
+static s32 fm10k_mbx_process_disconnect(struct fm10k_hw *hw,
+					struct fm10k_mbx_info *mbx)
+{
+	const enum fm10k_mbx_state state = mbx->state;
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 head;
+	s32 err;
+
+	/* we will need to pull the header field for verification */
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
+
+	/* We should not be receiving disconnect if Rx is incomplete */
+	if (mbx->pushed)
+		return FM10K_MBX_ERR_TAIL;
+
+	/* we have already verified mbx->head == tail so we know this is 0 */
+	mbx->head_len = 0;
+
+	/* verify the checksum on the incoming header is correct */
+	err = fm10k_mbx_verify_remote_crc(mbx);
+	if (err)
+		return err;
+
+	switch (state) {
+	case FM10K_STATE_DISCONNECT:
+	case FM10K_STATE_OPEN:
+		/* state doesn't change if we still have work to do */
+		if (!fm10k_mbx_tx_complete(mbx))
+			break;
+
+		/* verify the head indicates we completed all transmits */
+		if (head != mbx->tail)
+			return FM10K_MBX_ERR_HEAD;
+
+		/* reset any in-progress work */
+		fm10k_mbx_connect_reset(mbx);
+		break;
+	default:
+		break;
+	}
+
+	return fm10k_mbx_create_reply(hw, mbx, head);
+}
+
+/**
+ *  fm10k_mbx_process_error - Process error header
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will read an incoming error header and reply with the
+ *  appropriate message.  It will return a value indicating the number of
+ *  data DWORDs on success, or will return a negative value on failure.
+ **/
+static s32 fm10k_mbx_process_error(struct fm10k_hw *hw,
+				   struct fm10k_mbx_info *mbx)
+{
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 head;
+
+	/* we will need to pull all of the fields for verification */
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
+
+	switch (mbx->state) {
+	case FM10K_STATE_OPEN:
+	case FM10K_STATE_DISCONNECT:
+		/* flush any uncompleted work */
+		fm10k_mbx_reset_work(mbx);
+
+		/* reset CRC seeds */
+		mbx->local = FM10K_MBX_CRC_SEED;
+		mbx->remote = FM10K_MBX_CRC_SEED;
+
+		/* reset tail index and size to prepare for reconnect */
+		mbx->tail = head;
+
+		/* if open then reset max_size and go back to connect */
+		if (mbx->state == FM10K_STATE_OPEN) {
+			mbx->state = FM10K_STATE_CONNECT;
+			break;
+		}
+
+		/* send a connect message to get data flowing again */
+		fm10k_mbx_create_connect_hdr(mbx);
+		return 0;
+	default:
+		break;
+	}
+
+	return fm10k_mbx_create_reply(hw, mbx, mbx->tail);
+}
+
+/**
+ *  fm10k_mbx_process - Process mailbox interrupt
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will process incoming mailbox events and generate mailbox
+ *  replies.  It will return a value indicating the number of DWORDs
+ *  transmitted excluding header on success or a negative value on error.
+ **/
+static s32 fm10k_mbx_process(struct fm10k_hw *hw,
+			     struct fm10k_mbx_info *mbx)
+{
+	s32 err;
+
+	/* we do not read mailbox if closed */
+	if (mbx->state == FM10K_STATE_CLOSED)
+		return 0;
+
+	/* copy data from mailbox */
+	err = fm10k_mbx_read(hw, mbx);
+	if (err)
+		return err;
+
+	/* validate type, source, and destination */
+	err = fm10k_mbx_validate_msg_hdr(mbx);
+	if (err < 0)
+		goto msg_err;
+
+	switch (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, TYPE)) {
+	case FM10K_MSG_CONNECT:
+		err = fm10k_mbx_process_connect(hw, mbx);
+		break;
+	case FM10K_MSG_DATA:
+		err = fm10k_mbx_process_data(hw, mbx);
+		break;
+	case FM10K_MSG_DISCONNECT:
+		err = fm10k_mbx_process_disconnect(hw, mbx);
+		break;
+	case FM10K_MSG_ERROR:
+		err = fm10k_mbx_process_error(hw, mbx);
+		break;
+	default:
+		err = FM10K_MBX_ERR_TYPE;
+		break;
+	}
+
+msg_err:
+	/* notify partner of errors on our end */
+	if (err < 0)
+		fm10k_mbx_create_error_msg(mbx, err);
+
+	/* copy data from mailbox */
+	fm10k_mbx_write(hw, mbx);
+
+	return err;
+}
+
+/**
+ *  fm10k_mbx_disconnect - Shutdown mailbox connection
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will shut down the mailbox.  It places the mailbox first
+ *  in the disconnect state, it then allows up to a predefined timeout for
+ *  the mailbox to transition to close on its own.  If this does not occur
+ *  then the mailbox will be forced into the closed state.
+ *
+ *  Any mailbox transactions not completed before calling this function
+ *  are not guaranteed to complete and may be dropped.
+ **/
+static void fm10k_mbx_disconnect(struct fm10k_hw *hw,
+				 struct fm10k_mbx_info *mbx)
+{
+	int timeout = mbx->timeout ? FM10K_MBX_DISCONNECT_TIMEOUT : 0;
+
+	/* Place mbx in ready to disconnect state */
+	mbx->state = FM10K_STATE_DISCONNECT;
+
+	/* trigger interrupt to start shutdown process */
+	fm10k_write_reg(hw, mbx->mbx_reg, FM10K_MBX_REQ |
+					  FM10K_MBX_INTERRUPT_DISABLE);
+	do {
+		udelay(FM10K_MBX_POLL_DELAY);
+		mbx->ops.process(hw, mbx);
+		timeout -= FM10K_MBX_POLL_DELAY;
+	} while ((timeout > 0) && (mbx->state != FM10K_STATE_CLOSED));
+
+	/* in case we didn't close, just force the mailbox into shutdown and
+	 * drop all left over messages in the FIFO.
+	 */
+	fm10k_mbx_connect_reset(mbx);
+	fm10k_fifo_drop_all(&mbx->tx);
+
+	fm10k_write_reg(hw, mbx->mbmem_reg, 0);
+}
+
+/**
+ *  fm10k_mbx_connect - Start mailbox connection
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will initiate a mailbox connection.  It will populate the
+ *  mailbox with a broadcast connect message and then initialize the lock.
+ *  This is safe since the connect message is a single DWORD so the mailbox
+ *  transaction is guaranteed to be atomic.
+ *
+ *  This function will return an error if the mailbox has not been initiated
+ *  or is currently in use.
+ **/
+static s32 fm10k_mbx_connect(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+	/* we cannot connect an uninitialized mailbox */
+	if (!mbx->rx.buffer)
+		return FM10K_MBX_ERR_NO_SPACE;
+
+	/* we cannot connect an already connected mailbox */
+	if (mbx->state != FM10K_STATE_CLOSED)
+		return FM10K_MBX_ERR_BUSY;
+
+	/* mailbox timeout can now become active */
+	mbx->timeout = FM10K_MBX_INIT_TIMEOUT;
+
+	/* Place mbx in ready to connect state */
+	mbx->state = FM10K_STATE_CONNECT;
+
+	fm10k_mbx_reset_work(mbx);
+
+	/* initialize header of remote mailbox */
+	fm10k_mbx_create_fake_disconnect_hdr(mbx);
+	fm10k_write_reg(hw, mbx->mbmem_reg ^ mbx->mbmem_len, mbx->mbx_hdr);
+
+	/* enable interrupt and notify other party of new message */
+	mbx->mbx_lock = FM10K_MBX_REQ_INTERRUPT | FM10K_MBX_ACK_INTERRUPT |
+			FM10K_MBX_INTERRUPT_ENABLE;
+
+	/* generate and load connect header into mailbox */
+	fm10k_mbx_create_connect_hdr(mbx);
+	fm10k_mbx_write(hw, mbx);
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_validate_handlers - Validate layout of message parsing data
+ *  @msg_data: handlers for mailbox events
+ *
+ *  This function validates the layout of the message parsing data.  This
+ *  should be mostly static, but it is important to catch any errors that
+ *  are made when constructing the parsers.
+ **/
+static s32 fm10k_mbx_validate_handlers(const struct fm10k_msg_data *msg_data)
+{
+	const struct fm10k_tlv_attr *attr;
+	unsigned int id;
+
+	/* Allow NULL mailboxes that transmit but don't receive */
+	if (!msg_data)
+		return 0;
+
+	while (msg_data->id != FM10K_TLV_ERROR) {
+		/* all messages should have a function handler */
+		if (!msg_data->func)
+			return FM10K_ERR_PARAM;
+
+		/* parser is optional */
+		attr = msg_data->attr;
+		if (attr) {
+			while (attr->id != FM10K_TLV_ERROR) {
+				id = attr->id;
+				attr++;
+				/* ID should always be increasing */
+				if (id >= attr->id)
+					return FM10K_ERR_PARAM;
+				/* ID should fit in results array */
+				if (id >= FM10K_TLV_RESULTS_MAX)
+					return FM10K_ERR_PARAM;
+			}
+
+			/* verify terminator is in the list */
+			if (attr->id != FM10K_TLV_ERROR)
+				return FM10K_ERR_PARAM;
+		}
+
+		id = msg_data->id;
+		msg_data++;
+		/* ID should always be increasing */
+		if (id >= msg_data->id)
+			return FM10K_ERR_PARAM;
+	}
+
+	/* verify terminator is in the list */
+	if ((msg_data->id != FM10K_TLV_ERROR) || !msg_data->func)
+		return FM10K_ERR_PARAM;
+
+	return 0;
+}
+
+/**
+ *  fm10k_mbx_register_handlers - Register a set of handler ops for mailbox
+ *  @mbx: pointer to mailbox
+ *  @msg_data: handlers for mailbox events
+ *
+ *  This function associates a set of message handling ops with a mailbox.
+ **/
+static s32 fm10k_mbx_register_handlers(struct fm10k_mbx_info *mbx,
+				       const struct fm10k_msg_data *msg_data)
+{
+	/* validate layout of handlers before assigning them */
+	if (fm10k_mbx_validate_handlers(msg_data))
+		return FM10K_ERR_PARAM;
+
+	/* initialize the message handlers */
+	mbx->msg_data = msg_data;
+
+	return 0;
+}
+
+/**
+ *  fm10k_pfvf_mbx_init - Initialize mailbox memory for PF/VF mailbox
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @msg_data: handlers for mailbox events
+ *  @id: ID reference for PF as it supports up to 64 PF/VF mailboxes
+ *
+ *  This function initializes the mailbox for use.  It will split the
+ *  buffer provided and use that to populate both the Tx and Rx FIFO by
+ *  evenly splitting it.  In order to allow for easy masking of head/tail
+ *  the value reported in size must be a power of 2 and is reported in
+ *  DWORDs, not bytes.  Any invalid values will cause the mailbox to return
+ *  error.
+ **/
+s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx,
+			const struct fm10k_msg_data *msg_data, u8 id)
+{
+	/* initialize registers */
+	switch (hw->mac.type) {
+	case fm10k_mac_vf:
+		mbx->mbx_reg = FM10K_VFMBX;
+		mbx->mbmem_reg = FM10K_VFMBMEM(FM10K_VFMBMEM_VF_XOR);
+		break;
+	case fm10k_mac_pf:
+		/* there are only 64 VF <-> PF mailboxes */
+		if (id < 64) {
+			mbx->mbx_reg = FM10K_MBX(id);
+			mbx->mbmem_reg = FM10K_MBMEM_VF(id, 0);
+			break;
+		}
+		fallthrough;
+	default:
+		return FM10K_MBX_ERR_NO_MBX;
+	}
+
+	/* start out in closed state */
+	mbx->state = FM10K_STATE_CLOSED;
+
+	/* validate layout of handlers before assigning them */
+	if (fm10k_mbx_validate_handlers(msg_data))
+		return FM10K_ERR_PARAM;
+
+	/* initialize the message handlers */
+	mbx->msg_data = msg_data;
+
+	/* start mailbox as timed out and let the reset_hw call
+	 * set the timeout value to begin communications
+	 */
+	mbx->timeout = 0;
+	mbx->udelay = FM10K_MBX_INIT_DELAY;
+
+	/* initialize tail and head */
+	mbx->tail = 1;
+	mbx->head = 1;
+
+	/* initialize CRC seeds */
+	mbx->local = FM10K_MBX_CRC_SEED;
+	mbx->remote = FM10K_MBX_CRC_SEED;
+
+	/* Split buffer for use by Tx/Rx FIFOs */
+	mbx->max_size = FM10K_MBX_MSG_MAX_SIZE;
+	mbx->mbmem_len = FM10K_VFMBMEM_VF_XOR;
+
+	/* initialize the FIFOs, sizes are in 4 byte increments */
+	fm10k_fifo_init(&mbx->tx, mbx->buffer, FM10K_MBX_TX_BUFFER_SIZE);
+	fm10k_fifo_init(&mbx->rx, &mbx->buffer[FM10K_MBX_TX_BUFFER_SIZE],
+			FM10K_MBX_RX_BUFFER_SIZE);
+
+	/* initialize function pointers */
+	mbx->ops.connect = fm10k_mbx_connect;
+	mbx->ops.disconnect = fm10k_mbx_disconnect;
+	mbx->ops.rx_ready = fm10k_mbx_rx_ready;
+	mbx->ops.tx_ready = fm10k_mbx_tx_ready;
+	mbx->ops.tx_complete = fm10k_mbx_tx_complete;
+	mbx->ops.enqueue_tx = fm10k_mbx_enqueue_tx;
+	mbx->ops.process = fm10k_mbx_process;
+	mbx->ops.register_handlers = fm10k_mbx_register_handlers;
+
+	return 0;
+}
+
+/**
+ *  fm10k_sm_mbx_create_data_hdr - Generate a mailbox header for local FIFO
+ *  @mbx: pointer to mailbox
+ *
+ *  This function returns a data mailbox header
+ **/
+static void fm10k_sm_mbx_create_data_hdr(struct fm10k_mbx_info *mbx)
+{
+	if (mbx->tail_len)
+		mbx->mbx_lock |= FM10K_MBX_REQ;
+
+	mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(mbx->tail, SM_TAIL) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->remote, SM_VER) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->head, SM_HEAD);
+}
+
+/**
+ *  fm10k_sm_mbx_create_connect_hdr - Generate a mailbox header for local FIFO
+ *  @mbx: pointer to mailbox
+ *  @err: error flags to report if any
+ *
+ *  This function returns a connection mailbox header
+ **/
+static void fm10k_sm_mbx_create_connect_hdr(struct fm10k_mbx_info *mbx, u8 err)
+{
+	if (mbx->local)
+		mbx->mbx_lock |= FM10K_MBX_REQ;
+
+	mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(mbx->tail, SM_TAIL) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->remote, SM_VER) |
+		       FM10K_MSG_HDR_FIELD_SET(mbx->head, SM_HEAD) |
+		       FM10K_MSG_HDR_FIELD_SET(err, SM_ERR);
+}
+
+/**
+ *  fm10k_sm_mbx_connect_reset - Reset following request for reset
+ *  @mbx: pointer to mailbox
+ *
+ *  This function resets the mailbox to a just connected state
+ **/
+static void fm10k_sm_mbx_connect_reset(struct fm10k_mbx_info *mbx)
+{
+	/* flush any uncompleted work */
+	fm10k_mbx_reset_work(mbx);
+
+	/* set local version to max and remote version to 0 */
+	mbx->local = FM10K_SM_MBX_VERSION;
+	mbx->remote = 0;
+
+	/* initialize tail and head */
+	mbx->tail = 1;
+	mbx->head = 1;
+
+	/* reset state back to connect */
+	mbx->state = FM10K_STATE_CONNECT;
+}
+
+/**
+ *  fm10k_sm_mbx_connect - Start switch manager mailbox connection
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will initiate a mailbox connection with the switch
+ *  manager.  To do this it will first disconnect the mailbox, and then
+ *  reconnect it in order to complete a reset of the mailbox.
+ *
+ *  This function will return an error if the mailbox has not been initiated
+ *  or is currently in use.
+ **/
+static s32 fm10k_sm_mbx_connect(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+	/* we cannot connect an uninitialized mailbox */
+	if (!mbx->rx.buffer)
+		return FM10K_MBX_ERR_NO_SPACE;
+
+	/* we cannot connect an already connected mailbox */
+	if (mbx->state != FM10K_STATE_CLOSED)
+		return FM10K_MBX_ERR_BUSY;
+
+	/* mailbox timeout can now become active */
+	mbx->timeout = FM10K_MBX_INIT_TIMEOUT;
+
+	/* Place mbx in ready to connect state */
+	mbx->state = FM10K_STATE_CONNECT;
+	mbx->max_size = FM10K_MBX_MSG_MAX_SIZE;
+
+	/* reset interface back to connect */
+	fm10k_sm_mbx_connect_reset(mbx);
+
+	/* enable interrupt and notify other party of new message */
+	mbx->mbx_lock = FM10K_MBX_REQ_INTERRUPT | FM10K_MBX_ACK_INTERRUPT |
+			FM10K_MBX_INTERRUPT_ENABLE;
+
+	/* generate and load connect header into mailbox */
+	fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+	fm10k_mbx_write(hw, mbx);
+
+	return 0;
+}
+
+/**
+ *  fm10k_sm_mbx_disconnect - Shutdown mailbox connection
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will shut down the mailbox.  It places the mailbox first
+ *  in the disconnect state, it then allows up to a predefined timeout for
+ *  the mailbox to transition to close on its own.  If this does not occur
+ *  then the mailbox will be forced into the closed state.
+ *
+ *  Any mailbox transactions not completed before calling this function
+ *  are not guaranteed to complete and may be dropped.
+ **/
+static void fm10k_sm_mbx_disconnect(struct fm10k_hw *hw,
+				    struct fm10k_mbx_info *mbx)
+{
+	int timeout = mbx->timeout ? FM10K_MBX_DISCONNECT_TIMEOUT : 0;
+
+	/* Place mbx in ready to disconnect state */
+	mbx->state = FM10K_STATE_DISCONNECT;
+
+	/* trigger interrupt to start shutdown process */
+	fm10k_write_reg(hw, mbx->mbx_reg, FM10K_MBX_REQ |
+					  FM10K_MBX_INTERRUPT_DISABLE);
+	do {
+		udelay(FM10K_MBX_POLL_DELAY);
+		mbx->ops.process(hw, mbx);
+		timeout -= FM10K_MBX_POLL_DELAY;
+	} while ((timeout > 0) && (mbx->state != FM10K_STATE_CLOSED));
+
+	/* in case we didn't close just force the mailbox into shutdown */
+	mbx->state = FM10K_STATE_CLOSED;
+	mbx->remote = 0;
+	fm10k_mbx_reset_work(mbx);
+	fm10k_fifo_drop_all(&mbx->tx);
+
+	fm10k_write_reg(hw, mbx->mbmem_reg, 0);
+}
+
+/**
+ *  fm10k_sm_mbx_validate_fifo_hdr - Validate fields in the remote FIFO header
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will parse up the fields in the mailbox header and return
+ *  an error if the header contains any of a number of invalid configurations
+ *  including unrecognized offsets or version numbers.
+ **/
+static s32 fm10k_sm_mbx_validate_fifo_hdr(struct fm10k_mbx_info *mbx)
+{
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 tail, head, ver;
+
+	tail = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_TAIL);
+	ver = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_VER);
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_HEAD);
+
+	switch (ver) {
+	case 0:
+		break;
+	case FM10K_SM_MBX_VERSION:
+		if (!head || head > FM10K_SM_MBX_FIFO_LEN)
+			return FM10K_MBX_ERR_HEAD;
+		if (!tail || tail > FM10K_SM_MBX_FIFO_LEN)
+			return FM10K_MBX_ERR_TAIL;
+		if (mbx->tail < head)
+			head += mbx->mbmem_len - 1;
+		if (tail < mbx->head)
+			tail += mbx->mbmem_len - 1;
+		if (fm10k_mbx_index_len(mbx, head, mbx->tail) > mbx->tail_len)
+			return FM10K_MBX_ERR_HEAD;
+		if (fm10k_mbx_index_len(mbx, mbx->head, tail) < mbx->mbmem_len)
+			break;
+		return FM10K_MBX_ERR_TAIL;
+	default:
+		return FM10K_MBX_ERR_SRC;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_sm_mbx_process_error - Process header with error flag set
+ *  @mbx: pointer to mailbox
+ *
+ *  This function is meant to respond to a request where the error flag
+ *  is set.  As a result we will terminate a connection if one is present
+ *  and fall back into the reset state with a connection header of version
+ *  0 (RESET).
+ **/
+static void fm10k_sm_mbx_process_error(struct fm10k_mbx_info *mbx)
+{
+	const enum fm10k_mbx_state state = mbx->state;
+
+	switch (state) {
+	case FM10K_STATE_DISCONNECT:
+		/* if there is an error just disconnect */
+		mbx->remote = 0;
+		break;
+	case FM10K_STATE_OPEN:
+		/* flush any uncompleted work */
+		fm10k_sm_mbx_connect_reset(mbx);
+		break;
+	case FM10K_STATE_CONNECT:
+		/* try connecting at lower version */
+		if (mbx->remote) {
+			while (mbx->local > 1)
+				mbx->local--;
+			mbx->remote = 0;
+		}
+		break;
+	default:
+		break;
+	}
+
+	fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+}
+
+/**
+ *  fm10k_sm_mbx_create_error_msg - Process an error in FIFO header
+ *  @mbx: pointer to mailbox
+ *  @err: local error encountered
+ *
+ *  This function will interpret the error provided by err, and based on
+ *  that it may set the error bit in the local message header
+ **/
+static void fm10k_sm_mbx_create_error_msg(struct fm10k_mbx_info *mbx, s32 err)
+{
+	/* only generate an error message for these types */
+	switch (err) {
+	case FM10K_MBX_ERR_TAIL:
+	case FM10K_MBX_ERR_HEAD:
+	case FM10K_MBX_ERR_SRC:
+	case FM10K_MBX_ERR_SIZE:
+	case FM10K_MBX_ERR_RSVD0:
+		break;
+	default:
+		return;
+	}
+
+	/* process it as though we received an error, and send error reply */
+	fm10k_sm_mbx_process_error(mbx);
+	fm10k_sm_mbx_create_connect_hdr(mbx, 1);
+}
+
+/**
+ *  fm10k_sm_mbx_receive - Take message from Rx mailbox FIFO and put it in Rx
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @tail: tail index of message
+ *
+ *  This function will dequeue one message from the Rx switch manager mailbox
+ *  FIFO and place it in the Rx mailbox FIFO for processing by software.
+ **/
+static s32 fm10k_sm_mbx_receive(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx,
+				u16 tail)
+{
+	/* reduce length by 1 to convert to a mask */
+	u16 mbmem_len = mbx->mbmem_len - 1;
+	s32 err;
+
+	/* push tail in front of head */
+	if (tail < mbx->head)
+		tail += mbmem_len;
+
+	/* copy data to the Rx FIFO */
+	err = fm10k_mbx_push_tail(hw, mbx, tail);
+	if (err < 0)
+		return err;
+
+	/* process messages if we have received any */
+	fm10k_mbx_dequeue_rx(hw, mbx);
+
+	/* guarantee head aligns with the end of the last message */
+	mbx->head = fm10k_mbx_head_sub(mbx, mbx->pushed);
+	mbx->pushed = 0;
+
+	/* clear any extra bits left over since index adds 1 extra bit */
+	if (mbx->head > mbmem_len)
+		mbx->head -= mbmem_len;
+
+	return err;
+}
+
+/**
+ *  fm10k_sm_mbx_transmit - Take message from Tx and put it in Tx mailbox FIFO
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @head: head index of message
+ *
+ *  This function will dequeue one message from the Tx mailbox FIFO and place
+ *  it in the Tx switch manager mailbox FIFO for processing by hardware.
+ **/
+static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw,
+				  struct fm10k_mbx_info *mbx, u16 head)
+{
+	struct fm10k_mbx_fifo *fifo = &mbx->tx;
+	/* reduce length by 1 to convert to a mask */
+	u16 mbmem_len = mbx->mbmem_len - 1;
+	u16 tail_len, len = 0;
+
+	/* push head behind tail */
+	if (mbx->tail < head)
+		head += mbmem_len;
+
+	fm10k_mbx_pull_head(hw, mbx, head);
+
+	/* determine msg aligned offset for end of buffer */
+	do {
+		u32 *msg;
+
+		msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len);
+		tail_len = len;
+		len += FM10K_TLV_DWORD_LEN(*msg);
+	} while ((len <= mbx->tail_len) && (len < mbmem_len));
+
+	/* guarantee we stop on a message boundary */
+	if (mbx->tail_len > tail_len) {
+		mbx->tail = fm10k_mbx_tail_sub(mbx, mbx->tail_len - tail_len);
+		mbx->tail_len = tail_len;
+	}
+
+	/* clear any extra bits left over since index adds 1 extra bit */
+	if (mbx->tail > mbmem_len)
+		mbx->tail -= mbmem_len;
+}
+
+/**
+ *  fm10k_sm_mbx_create_reply - Generate reply based on state and remote head
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @head: acknowledgement number
+ *
+ *  This function will generate an outgoing message based on the current
+ *  mailbox state and the remote FIFO head.  It will return the length
+ *  of the outgoing message excluding header on success, and a negative value
+ *  on error.
+ **/
+static void fm10k_sm_mbx_create_reply(struct fm10k_hw *hw,
+				      struct fm10k_mbx_info *mbx, u16 head)
+{
+	switch (mbx->state) {
+	case FM10K_STATE_OPEN:
+	case FM10K_STATE_DISCONNECT:
+		/* flush out Tx data */
+		fm10k_sm_mbx_transmit(hw, mbx, head);
+
+		/* generate new header based on data */
+		if (mbx->tail_len || (mbx->state == FM10K_STATE_OPEN)) {
+			fm10k_sm_mbx_create_data_hdr(mbx);
+		} else {
+			mbx->remote = 0;
+			fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+		}
+		break;
+	case FM10K_STATE_CONNECT:
+	case FM10K_STATE_CLOSED:
+		fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ *  fm10k_sm_mbx_process_reset - Process header with version == 0 (RESET)
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function is meant to respond to a request where the version data
+ *  is set to 0.  As such we will either terminate the connection or go
+ *  into the connect state in order to re-establish the connection.  This
+ *  function can also be used to respond to an error as the connection
+ *  resetting would also be a means of dealing with errors.
+ **/
+static s32 fm10k_sm_mbx_process_reset(struct fm10k_hw *hw,
+				      struct fm10k_mbx_info *mbx)
+{
+	s32 err = 0;
+	const enum fm10k_mbx_state state = mbx->state;
+
+	switch (state) {
+	case FM10K_STATE_DISCONNECT:
+		/* drop remote connections and disconnect */
+		mbx->state = FM10K_STATE_CLOSED;
+		mbx->remote = 0;
+		mbx->local = 0;
+		break;
+	case FM10K_STATE_OPEN:
+		/* flush any incomplete work */
+		fm10k_sm_mbx_connect_reset(mbx);
+		err = FM10K_ERR_RESET_REQUESTED;
+		break;
+	case FM10K_STATE_CONNECT:
+		/* Update remote value to match local value */
+		mbx->remote = mbx->local;
+		break;
+	default:
+		break;
+	}
+
+	fm10k_sm_mbx_create_reply(hw, mbx, mbx->tail);
+
+	return err;
+}
+
+/**
+ *  fm10k_sm_mbx_process_version_1 - Process header with version == 1
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function is meant to process messages received when the remote
+ *  mailbox is active.
+ **/
+static s32 fm10k_sm_mbx_process_version_1(struct fm10k_hw *hw,
+					  struct fm10k_mbx_info *mbx)
+{
+	const u32 *hdr = &mbx->mbx_hdr;
+	u16 head, tail;
+	s32 len;
+
+	/* pull all fields needed for verification */
+	tail = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_TAIL);
+	head = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_HEAD);
+
+	/* if we are in connect and wanting version 1 then start up and go */
+	if (mbx->state == FM10K_STATE_CONNECT) {
+		if (!mbx->remote)
+			goto send_reply;
+		if (mbx->remote != 1)
+			return FM10K_MBX_ERR_SRC;
+
+		mbx->state = FM10K_STATE_OPEN;
+	}
+
+	do {
+		/* abort on message size errors */
+		len = fm10k_sm_mbx_receive(hw, mbx, tail);
+		if (len < 0)
+			return len;
+
+		/* continue until we have flushed the Rx FIFO */
+	} while (len);
+
+send_reply:
+	fm10k_sm_mbx_create_reply(hw, mbx, head);
+
+	return 0;
+}
+
+/**
+ *  fm10k_sm_mbx_process - Process switch manager mailbox interrupt
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *
+ *  This function will process incoming mailbox events and generate mailbox
+ *  replies.  It will return a value indicating the number of DWORDs
+ *  transmitted excluding header on success or a negative value on error.
+ **/
+static s32 fm10k_sm_mbx_process(struct fm10k_hw *hw,
+				struct fm10k_mbx_info *mbx)
+{
+	s32 err;
+
+	/* we do not read mailbox if closed */
+	if (mbx->state == FM10K_STATE_CLOSED)
+		return 0;
+
+	/* retrieve data from switch manager */
+	err = fm10k_mbx_read(hw, mbx);
+	if (err)
+		return err;
+
+	err = fm10k_sm_mbx_validate_fifo_hdr(mbx);
+	if (err < 0)
+		goto fifo_err;
+
+	if (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, SM_ERR)) {
+		fm10k_sm_mbx_process_error(mbx);
+		goto fifo_err;
+	}
+
+	switch (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, SM_VER)) {
+	case 0:
+		err = fm10k_sm_mbx_process_reset(hw, mbx);
+		break;
+	case FM10K_SM_MBX_VERSION:
+		err = fm10k_sm_mbx_process_version_1(hw, mbx);
+		break;
+	}
+
+fifo_err:
+	if (err < 0)
+		fm10k_sm_mbx_create_error_msg(mbx, err);
+
+	/* report data to switch manager */
+	fm10k_mbx_write(hw, mbx);
+
+	return err;
+}
+
+/**
+ *  fm10k_sm_mbx_init - Initialize mailbox memory for PF/SM mailbox
+ *  @hw: pointer to hardware structure
+ *  @mbx: pointer to mailbox
+ *  @msg_data: handlers for mailbox events
+ *
+ *  This function initializes the PF/SM mailbox for use.  It will split the
+ *  buffer provided and use that to populate both the Tx and Rx FIFO by
+ *  evenly splitting it.  In order to allow for easy masking of head/tail
+ *  the value reported in size must be a power of 2 and is reported in
+ *  DWORDs, not bytes.  Any invalid values will cause the mailbox to return
+ *  error.
+ **/
+s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw,
+		      struct fm10k_mbx_info *mbx,
+		      const struct fm10k_msg_data *msg_data)
+{
+	mbx->mbx_reg = FM10K_GMBX;
+	mbx->mbmem_reg = FM10K_MBMEM_PF(0);
+
+	/* start out in closed state */
+	mbx->state = FM10K_STATE_CLOSED;
+
+	/* validate layout of handlers before assigning them */
+	if (fm10k_mbx_validate_handlers(msg_data))
+		return FM10K_ERR_PARAM;
+
+	/* initialize the message handlers */
+	mbx->msg_data = msg_data;
+
+	/* start mailbox as timed out and let the reset_hw call
+	 * set the timeout value to begin communications
+	 */
+	mbx->timeout = 0;
+	mbx->udelay = FM10K_MBX_INIT_DELAY;
+
+	/* Split buffer for use by Tx/Rx FIFOs */
+	mbx->max_size = FM10K_MBX_MSG_MAX_SIZE;
+	mbx->mbmem_len = FM10K_MBMEM_PF_XOR;
+
+	/* initialize the FIFOs, sizes are in 4 byte increments */
+	fm10k_fifo_init(&mbx->tx, mbx->buffer, FM10K_MBX_TX_BUFFER_SIZE);
+	fm10k_fifo_init(&mbx->rx, &mbx->buffer[FM10K_MBX_TX_BUFFER_SIZE],
+			FM10K_MBX_RX_BUFFER_SIZE);
+
+	/* initialize function pointers */
+	mbx->ops.connect = fm10k_sm_mbx_connect;
+	mbx->ops.disconnect = fm10k_sm_mbx_disconnect;
+	mbx->ops.rx_ready = fm10k_mbx_rx_ready;
+	mbx->ops.tx_ready = fm10k_mbx_tx_ready;
+	mbx->ops.tx_complete = fm10k_mbx_tx_complete;
+	mbx->ops.enqueue_tx = fm10k_mbx_enqueue_tx;
+	mbx->ops.process = fm10k_sm_mbx_process;
+	mbx->ops.register_handlers = fm10k_mbx_register_handlers;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
new file mode 100644
index 000000000..56d1abff0
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _FM10K_MBX_H_
+#define _FM10K_MBX_H_
+
+/* forward declaration */
+struct fm10k_mbx_info;
+
+#include "fm10k_type.h"
+#include "fm10k_tlv.h"
+
+/* PF Mailbox Registers */
+#define FM10K_MBMEM(_n)		((_n) + 0x18000)
+#define FM10K_MBMEM_VF(_n, _m)	(((_n) * 0x10) + (_m) + 0x18000)
+#define FM10K_MBMEM_SM(_n)	((_n) + 0x18400)
+#define FM10K_MBMEM_PF(_n)	((_n) + 0x18600)
+/* XOR provides means of switching from Tx to Rx FIFO */
+#define FM10K_MBMEM_PF_XOR	(FM10K_MBMEM_SM(0) ^ FM10K_MBMEM_PF(0))
+#define FM10K_MBX(_n)		((_n) + 0x18800)
+#define FM10K_MBX_REQ				0x00000002
+#define FM10K_MBX_ACK				0x00000004
+#define FM10K_MBX_REQ_INTERRUPT			0x00000008
+#define FM10K_MBX_ACK_INTERRUPT			0x00000010
+#define FM10K_MBX_INTERRUPT_ENABLE		0x00000020
+#define FM10K_MBX_INTERRUPT_DISABLE		0x00000040
+#define FM10K_MBX_GLOBAL_REQ_INTERRUPT		0x00000200
+#define FM10K_MBX_GLOBAL_ACK_INTERRUPT		0x00000400
+#define FM10K_MBICR(_n)		((_n) + 0x18840)
+#define FM10K_GMBX		0x18842
+
+/* VF Mailbox Registers */
+#define FM10K_VFMBX		0x00010
+#define FM10K_VFMBMEM(_n)	((_n) + 0x00020)
+#define FM10K_VFMBMEM_LEN	16
+#define FM10K_VFMBMEM_VF_XOR	(FM10K_VFMBMEM_LEN / 2)
+
+/* Delays/timeouts */
+#define FM10K_MBX_DISCONNECT_TIMEOUT		500
+#define FM10K_MBX_POLL_DELAY			19
+#define FM10K_MBX_INT_DELAY			20
+
+/* PF/VF Mailbox state machine
+ *
+ * +----------+	    connect()	+----------+
+ * |  CLOSED  | --------------> |  CONNECT |
+ * +----------+			+----------+
+ *   ^				  ^	 |
+ *   | rcv:	      rcv:	  |	 | rcv:
+ *   |  Connect	       Disconnect |	 |  Connect
+ *   |  Disconnect     Error	  |	 |  Data
+ *   |				  |	 |
+ *   |				  |	 V
+ * +----------+   disconnect()	+----------+
+ * |DISCONNECT| <-------------- |   OPEN   |
+ * +----------+			+----------+
+ *
+ * The diagram above describes the PF/VF mailbox state machine.  There
+ * are four main states to this machine.
+ * Closed: This state represents a mailbox that is in a standby state
+ *	   with interrupts disabled.  In this state the mailbox should not
+ *	   read the mailbox or write any data.  The only means of exiting
+ *	   this state is for the system to make the connect() call for the
+ *	   mailbox, it will then transition to the connect state.
+ * Connect: In this state the mailbox is seeking a connection.  It will
+ *	    post a connect message with no specified destination and will
+ *	    wait for a reply from the other side of the mailbox.  This state
+ *	    is exited when either a connect with the local mailbox as the
+ *	    destination is received or when a data message is received with
+ *	    a valid sequence number.
+ * Open: In this state the mailbox is able to transfer data between the local
+ *       entity and the remote.  It will fall back to connect in the event of
+ *       receiving either an error message, or a disconnect message.  It will
+ *       transition to disconnect on a call to disconnect();
+ * Disconnect: In this state the mailbox is attempting to gracefully terminate
+ *	       the connection.  It will do so at the first point where it knows
+ *	       that the remote endpoint is either done sending, or when the
+ *	       remote endpoint has fallen back into connect.
+ */
+enum fm10k_mbx_state {
+	FM10K_STATE_CLOSED,
+	FM10K_STATE_CONNECT,
+	FM10K_STATE_OPEN,
+	FM10K_STATE_DISCONNECT,
+};
+
+/* PF/VF Mailbox header format
+ *    3			  2		      1			  0
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |        Size/Err_no/CRC        | Rsvd0 | Head  | Tail  | Type  |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * The layout above describes the format for the header used in the PF/VF
+ * mailbox.  The header is broken out into the following fields:
+ * Type: There are 4 supported message types
+ *		0x8: Data header - used to transport message data
+ *		0xC: Connect header - used to establish connection
+ *		0xD: Disconnect header - used to tear down a connection
+ *		0xE: Error header - used to address message exceptions
+ * Tail: Tail index for local FIFO
+ *		Tail index actually consists of two parts.  The MSB of
+ *		the head is a loop tracker, it is 0 on an even numbered
+ *		loop through the FIFO, and 1 on the odd numbered loops.
+ *		To get the actual mailbox offset based on the tail it
+ *		is necessary to add bit 3 to bit 0 and clear bit 3.  This
+ *		gives us a valid range of 0x1 - 0xE.
+ * Head: Head index for remote FIFO
+ *		Head index follows the same format as the tail index.
+ * Rsvd0: Reserved 0 portion of the mailbox header
+ * CRC: Running CRC for all data since connect plus current message header
+ * Size: Maximum message size - Applies only to connect headers
+ *		The maximum message size is provided during connect to avoid
+ *		jamming the mailbox with messages that do not fit.
+ * Err_no: Error number - Applies only to error headers
+ *		The error number provides an indication of the type of error
+ *		experienced.
+ */
+
+/* macros for retrieving and setting header values */
+#define FM10K_MSG_HDR_MASK(name) \
+	((0x1u << FM10K_MSG_##name##_SIZE) - 1)
+#define FM10K_MSG_HDR_FIELD_SET(value, name) \
+	(((u32)(value) & FM10K_MSG_HDR_MASK(name)) << FM10K_MSG_##name##_SHIFT)
+#define FM10K_MSG_HDR_FIELD_GET(value, name) \
+	((u16)((value) >> FM10K_MSG_##name##_SHIFT) & FM10K_MSG_HDR_MASK(name))
+
+/* offsets shared between all headers */
+#define FM10K_MSG_TYPE_SHIFT			0
+#define FM10K_MSG_TYPE_SIZE			4
+#define FM10K_MSG_TAIL_SHIFT			4
+#define FM10K_MSG_TAIL_SIZE			4
+#define FM10K_MSG_HEAD_SHIFT			8
+#define FM10K_MSG_HEAD_SIZE			4
+#define FM10K_MSG_RSVD0_SHIFT			12
+#define FM10K_MSG_RSVD0_SIZE			4
+
+/* offsets for data/disconnect headers */
+#define FM10K_MSG_CRC_SHIFT			16
+#define FM10K_MSG_CRC_SIZE			16
+
+/* offsets for connect headers */
+#define FM10K_MSG_CONNECT_SIZE_SHIFT		16
+#define FM10K_MSG_CONNECT_SIZE_SIZE		16
+
+/* offsets for error headers */
+#define FM10K_MSG_ERR_NO_SHIFT			16
+#define FM10K_MSG_ERR_NO_SIZE			16
+
+enum fm10k_msg_type {
+	FM10K_MSG_DATA			= 0x8,
+	FM10K_MSG_CONNECT		= 0xC,
+	FM10K_MSG_DISCONNECT		= 0xD,
+	FM10K_MSG_ERROR			= 0xE,
+};
+
+/* HNI/SM Mailbox FIFO format
+ *    3                   2                   1                   0
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-------+-----------------------+-------+-----------------------+
+ * | Error |      Remote Head      |Version|      Local Tail       |
+ * +-------+-----------------------+-------+-----------------------+
+ * |                                                               |
+ * .                        Local FIFO Data                        .
+ * .                                                               .
+ * +-------+-----------------------+-------+-----------------------+
+ *
+ * The layout above describes the format for the FIFOs used by the host
+ * network interface and the switch manager to communicate messages back
+ * and forth.  Both the HNI and the switch maintain one such FIFO.  The
+ * layout in memory has the switch manager FIFO followed immediately by
+ * the HNI FIFO.  For this reason I am using just the pointer to the
+ * HNI FIFO in the mailbox ops as the offset between the two is fixed.
+ *
+ * The header for the FIFO is broken out into the following fields:
+ * Local Tail:  Offset into FIFO region for next DWORD to write.
+ * Version:  Version info for mailbox, only values of 0/1 are supported.
+ * Remote Head:  Offset into remote FIFO to indicate how much we have read.
+ * Error: Error indication, values TBD.
+ */
+
+/* version number for switch manager mailboxes */
+#define FM10K_SM_MBX_VERSION		1
+#define FM10K_SM_MBX_FIFO_LEN		(FM10K_MBMEM_PF_XOR - 1)
+
+/* offsets shared between all SM FIFO headers */
+#define FM10K_MSG_SM_TAIL_SHIFT			0
+#define FM10K_MSG_SM_TAIL_SIZE			12
+#define FM10K_MSG_SM_VER_SHIFT			12
+#define FM10K_MSG_SM_VER_SIZE			4
+#define FM10K_MSG_SM_HEAD_SHIFT			16
+#define FM10K_MSG_SM_HEAD_SIZE			12
+#define FM10K_MSG_SM_ERR_SHIFT			28
+#define FM10K_MSG_SM_ERR_SIZE			4
+
+/* All error messages returned by mailbox functions
+ * The value -511 is 0xFE01 in hex.  The idea is to order the errors
+ * from 0xFE01 - 0xFEFF so error codes are easily visible in the mailbox
+ * messages.  This also helps to avoid error number collisions as Linux
+ * doesn't appear to use error numbers 256 - 511.
+ */
+#define FM10K_MBX_ERR(_n) ((_n) - 512)
+#define FM10K_MBX_ERR_NO_MBX		FM10K_MBX_ERR(0x01)
+#define FM10K_MBX_ERR_NO_SPACE		FM10K_MBX_ERR(0x03)
+#define FM10K_MBX_ERR_TAIL		FM10K_MBX_ERR(0x05)
+#define FM10K_MBX_ERR_HEAD		FM10K_MBX_ERR(0x06)
+#define FM10K_MBX_ERR_SRC		FM10K_MBX_ERR(0x08)
+#define FM10K_MBX_ERR_TYPE		FM10K_MBX_ERR(0x09)
+#define FM10K_MBX_ERR_SIZE		FM10K_MBX_ERR(0x0B)
+#define FM10K_MBX_ERR_BUSY		FM10K_MBX_ERR(0x0C)
+#define FM10K_MBX_ERR_RSVD0		FM10K_MBX_ERR(0x0E)
+#define FM10K_MBX_ERR_CRC		FM10K_MBX_ERR(0x0F)
+
+#define FM10K_MBX_CRC_SEED		0xFFFF
+
+struct fm10k_mbx_ops {
+	s32 (*connect)(struct fm10k_hw *, struct fm10k_mbx_info *);
+	void (*disconnect)(struct fm10k_hw *, struct fm10k_mbx_info *);
+	bool (*rx_ready)(struct fm10k_mbx_info *);
+	bool (*tx_ready)(struct fm10k_mbx_info *, u16);
+	bool (*tx_complete)(struct fm10k_mbx_info *);
+	s32 (*enqueue_tx)(struct fm10k_hw *, struct fm10k_mbx_info *,
+			  const u32 *);
+	s32 (*process)(struct fm10k_hw *, struct fm10k_mbx_info *);
+	s32 (*register_handlers)(struct fm10k_mbx_info *,
+				 const struct fm10k_msg_data *);
+};
+
+struct fm10k_mbx_fifo {
+	u32 *buffer;
+	u16 head;
+	u16 tail;
+	u16 size;
+};
+
+/* size of buffer to be stored in mailbox for FIFOs */
+#define FM10K_MBX_TX_BUFFER_SIZE	512
+#define FM10K_MBX_RX_BUFFER_SIZE	128
+#define FM10K_MBX_BUFFER_SIZE \
+	(FM10K_MBX_TX_BUFFER_SIZE + FM10K_MBX_RX_BUFFER_SIZE)
+
+/* minimum and maximum message size in dwords */
+#define FM10K_MBX_MSG_MAX_SIZE \
+	((FM10K_MBX_TX_BUFFER_SIZE - 1) & (FM10K_MBX_RX_BUFFER_SIZE - 1))
+#define FM10K_VFMBX_MSG_MTU	((FM10K_VFMBMEM_LEN / 2) - 1)
+
+#define FM10K_MBX_INIT_TIMEOUT	2000 /* number of retries on mailbox */
+#define FM10K_MBX_INIT_DELAY	500  /* microseconds between retries */
+
+struct fm10k_mbx_info {
+	/* function pointers for mailbox operations */
+	struct fm10k_mbx_ops ops;
+	const struct fm10k_msg_data *msg_data;
+
+	/* message FIFOs */
+	struct fm10k_mbx_fifo rx;
+	struct fm10k_mbx_fifo tx;
+
+	/* delay for handling timeouts */
+	u32 timeout;
+	u32 udelay;
+
+	/* mailbox state info */
+	u32 mbx_reg, mbmem_reg, mbx_lock, mbx_hdr;
+	u16 max_size, mbmem_len;
+	u16 tail, tail_len, pulled;
+	u16 head, head_len, pushed;
+	u16 local, remote;
+	enum fm10k_mbx_state state;
+
+	/* result of last mailbox test */
+	s32 test_result;
+
+	/* statistics */
+	u64 tx_busy;
+	u64 tx_dropped;
+	u64 tx_messages;
+	u64 tx_dwords;
+	u64 tx_mbmem_pulled;
+	u64 rx_messages;
+	u64 rx_dwords;
+	u64 rx_mbmem_pushed;
+	u64 rx_parse_err;
+
+	/* Buffer to store messages */
+	u32 buffer[FM10K_MBX_BUFFER_SIZE];
+};
+
+s32 fm10k_pfvf_mbx_init(struct fm10k_hw *, struct fm10k_mbx_info *,
+			const struct fm10k_msg_data *, u8);
+s32 fm10k_sm_mbx_init(struct fm10k_hw *, struct fm10k_mbx_info *,
+		      const struct fm10k_msg_data *);
+
+#endif /* _FM10K_MBX_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
new file mode 100644
index 000000000..2cca9e84e
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -0,0 +1,1610 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k.h"
+#include <linux/vmalloc.h>
+#include <net/udp_tunnel.h>
+#include <linux/if_macvlan.h>
+
+/**
+ * fm10k_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
+ **/
+int fm10k_setup_tx_resources(struct fm10k_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int size;
+
+	size = sizeof(struct fm10k_tx_buffer) * tx_ring->count;
+
+	tx_ring->tx_buffer = vzalloc(size);
+	if (!tx_ring->tx_buffer)
+		goto err;
+
+	u64_stats_init(&tx_ring->syncp);
+
+	/* round up to nearest 4K */
+	tx_ring->size = tx_ring->count * sizeof(struct fm10k_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;
+
+	return 0;
+
+err:
+	vfree(tx_ring->tx_buffer);
+	tx_ring->tx_buffer = NULL;
+	return -ENOMEM;
+}
+
+/**
+ * fm10k_setup_all_tx_resources - allocate all queues Tx resources
+ * @interface: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not).  It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface)
+{
+	int i, err;
+
+	for (i = 0; i < interface->num_tx_queues; i++) {
+		err = fm10k_setup_tx_resources(interface->tx_ring[i]);
+		if (!err)
+			continue;
+
+		netif_err(interface, probe, interface->netdev,
+			  "Allocation for Tx Queue %u failed\n", i);
+		goto err_setup_tx;
+	}
+
+	return 0;
+err_setup_tx:
+	/* rewind the index freeing the rings as we go */
+	while (i--)
+		fm10k_free_tx_resources(interface->tx_ring[i]);
+	return err;
+}
+
+/**
+ * fm10k_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
+ **/
+int fm10k_setup_rx_resources(struct fm10k_ring *rx_ring)
+{
+	struct device *dev = rx_ring->dev;
+	int size;
+
+	size = sizeof(struct fm10k_rx_buffer) * rx_ring->count;
+
+	rx_ring->rx_buffer = vzalloc(size);
+	if (!rx_ring->rx_buffer)
+		goto err;
+
+	u64_stats_init(&rx_ring->syncp);
+
+	/* Round up to nearest 4K */
+	rx_ring->size = rx_ring->count * sizeof(union fm10k_rx_desc);
+	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;
+
+	return 0;
+err:
+	vfree(rx_ring->rx_buffer);
+	rx_ring->rx_buffer = NULL;
+	return -ENOMEM;
+}
+
+/**
+ * fm10k_setup_all_rx_resources - allocate all queues Rx resources
+ * @interface: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not).  It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface)
+{
+	int i, err;
+
+	for (i = 0; i < interface->num_rx_queues; i++) {
+		err = fm10k_setup_rx_resources(interface->rx_ring[i]);
+		if (!err)
+			continue;
+
+		netif_err(interface, probe, interface->netdev,
+			  "Allocation for Rx Queue %u failed\n", i);
+		goto err_setup_rx;
+	}
+
+	return 0;
+err_setup_rx:
+	/* rewind the index freeing the rings as we go */
+	while (i--)
+		fm10k_free_rx_resources(interface->rx_ring[i]);
+	return err;
+}
+
+void fm10k_unmap_and_free_tx_resource(struct fm10k_ring *ring,
+				      struct fm10k_tx_buffer *tx_buffer)
+{
+	if (tx_buffer->skb) {
+		dev_kfree_skb_any(tx_buffer->skb);
+		if (dma_unmap_len(tx_buffer, len))
+			dma_unmap_single(ring->dev,
+					 dma_unmap_addr(tx_buffer, dma),
+					 dma_unmap_len(tx_buffer, len),
+					 DMA_TO_DEVICE);
+	} else if (dma_unmap_len(tx_buffer, len)) {
+		dma_unmap_page(ring->dev,
+			       dma_unmap_addr(tx_buffer, dma),
+			       dma_unmap_len(tx_buffer, len),
+			       DMA_TO_DEVICE);
+	}
+	tx_buffer->next_to_watch = NULL;
+	tx_buffer->skb = NULL;
+	dma_unmap_len_set(tx_buffer, len, 0);
+	/* tx_buffer must be completely set up in the transmit path */
+}
+
+/**
+ * fm10k_clean_tx_ring - Free Tx Buffers
+ * @tx_ring: ring to be cleaned
+ **/
+static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring)
+{
+	unsigned long size;
+	u16 i;
+
+	/* ring already cleared, nothing to do */
+	if (!tx_ring->tx_buffer)
+		return;
+
+	/* Free all the Tx ring sk_buffs */
+	for (i = 0; i < tx_ring->count; i++) {
+		struct fm10k_tx_buffer *tx_buffer = &tx_ring->tx_buffer[i];
+
+		fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+	}
+
+	/* reset BQL values */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	size = sizeof(struct fm10k_tx_buffer) * tx_ring->count;
+	memset(tx_ring->tx_buffer, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(tx_ring->desc, 0, tx_ring->size);
+}
+
+/**
+ * fm10k_free_tx_resources - Free Tx Resources per Queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ **/
+void fm10k_free_tx_resources(struct fm10k_ring *tx_ring)
+{
+	fm10k_clean_tx_ring(tx_ring);
+
+	vfree(tx_ring->tx_buffer);
+	tx_ring->tx_buffer = 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;
+}
+
+/**
+ * fm10k_clean_all_tx_rings - Free Tx Buffers for all queues
+ * @interface: board private structure
+ **/
+void fm10k_clean_all_tx_rings(struct fm10k_intfc *interface)
+{
+	int i;
+
+	for (i = 0; i < interface->num_tx_queues; i++)
+		fm10k_clean_tx_ring(interface->tx_ring[i]);
+}
+
+/**
+ * fm10k_free_all_tx_resources - Free Tx Resources for All Queues
+ * @interface: board private structure
+ *
+ * Free all transmit software resources
+ **/
+static void fm10k_free_all_tx_resources(struct fm10k_intfc *interface)
+{
+	int i = interface->num_tx_queues;
+
+	while (i--)
+		fm10k_free_tx_resources(interface->tx_ring[i]);
+}
+
+/**
+ * fm10k_clean_rx_ring - Free Rx Buffers per Queue
+ * @rx_ring: ring to free buffers from
+ **/
+static void fm10k_clean_rx_ring(struct fm10k_ring *rx_ring)
+{
+	unsigned long size;
+	u16 i;
+
+	if (!rx_ring->rx_buffer)
+		return;
+
+	dev_kfree_skb(rx_ring->skb);
+	rx_ring->skb = NULL;
+
+	/* Free all the Rx ring sk_buffs */
+	for (i = 0; i < rx_ring->count; i++) {
+		struct fm10k_rx_buffer *buffer = &rx_ring->rx_buffer[i];
+		/* clean-up will only set page pointer to NULL */
+		if (!buffer->page)
+			continue;
+
+		dma_unmap_page(rx_ring->dev, buffer->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+		__free_page(buffer->page);
+
+		buffer->page = NULL;
+	}
+
+	size = sizeof(struct fm10k_rx_buffer) * rx_ring->count;
+	memset(rx_ring->rx_buffer, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(rx_ring->desc, 0, rx_ring->size);
+
+	rx_ring->next_to_alloc = 0;
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+}
+
+/**
+ * fm10k_free_rx_resources - Free Rx Resources
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ **/
+void fm10k_free_rx_resources(struct fm10k_ring *rx_ring)
+{
+	fm10k_clean_rx_ring(rx_ring);
+
+	vfree(rx_ring->rx_buffer);
+	rx_ring->rx_buffer = 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;
+}
+
+/**
+ * fm10k_clean_all_rx_rings - Free Rx Buffers for all queues
+ * @interface: board private structure
+ **/
+void fm10k_clean_all_rx_rings(struct fm10k_intfc *interface)
+{
+	int i;
+
+	for (i = 0; i < interface->num_rx_queues; i++)
+		fm10k_clean_rx_ring(interface->rx_ring[i]);
+}
+
+/**
+ * fm10k_free_all_rx_resources - Free Rx Resources for All Queues
+ * @interface: board private structure
+ *
+ * Free all receive software resources
+ **/
+static void fm10k_free_all_rx_resources(struct fm10k_intfc *interface)
+{
+	int i = interface->num_rx_queues;
+
+	while (i--)
+		fm10k_free_rx_resources(interface->rx_ring[i]);
+}
+
+/**
+ * fm10k_request_glort_range - Request GLORTs for use in configuring rules
+ * @interface: board private structure
+ *
+ * This function allocates a range of glorts for this interface to use.
+ **/
+static void fm10k_request_glort_range(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	u16 mask = (~hw->mac.dglort_map) >> FM10K_DGLORTMAP_MASK_SHIFT;
+
+	/* establish GLORT base */
+	interface->glort = hw->mac.dglort_map & FM10K_DGLORTMAP_NONE;
+	interface->glort_count = 0;
+
+	/* nothing we can do until mask is allocated */
+	if (hw->mac.dglort_map == FM10K_DGLORTMAP_NONE)
+		return;
+
+	/* we support 3 possible GLORT configurations.
+	 * 1: VFs consume all but the last 1
+	 * 2: VFs and PF split glorts with possible gap between
+	 * 3: VFs allocated first 64, all others belong to PF
+	 */
+	if (mask <= hw->iov.total_vfs) {
+		interface->glort_count = 1;
+		interface->glort += mask;
+	} else if (mask < 64) {
+		interface->glort_count = (mask + 1) / 2;
+		interface->glort += interface->glort_count;
+	} else {
+		interface->glort_count = mask - 63;
+		interface->glort += 64;
+	}
+}
+
+/**
+ * fm10k_restore_udp_port_info
+ * @interface: board private structure
+ *
+ * This function restores the value in the tunnel_cfg register(s) after reset
+ **/
+static void fm10k_restore_udp_port_info(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* only the PF supports configuring tunnels */
+	if (hw->mac.type != fm10k_mac_pf)
+		return;
+
+	/* restore tunnel configuration register */
+	fm10k_write_reg(hw, FM10K_TUNNEL_CFG,
+			ntohs(interface->vxlan_port) |
+			(ETH_P_TEB << FM10K_TUNNEL_CFG_NVGRE_SHIFT));
+
+	/* restore Geneve tunnel configuration register */
+	fm10k_write_reg(hw, FM10K_TUNNEL_CFG_GENEVE,
+			ntohs(interface->geneve_port));
+}
+
+/**
+ * fm10k_udp_tunnel_sync - Called when UDP tunnel ports change
+ * @dev: network interface device structure
+ * @table: Tunnel table (according to tables of @fm10k_udp_tunnels)
+ *
+ * This function is called when a new UDP tunnel port is added or deleted.
+ * Due to hardware restrictions, only one port per type can be offloaded at
+ * once. Core will send to the driver a port of its choice.
+ **/
+static int fm10k_udp_tunnel_sync(struct net_device *dev, unsigned int table)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct udp_tunnel_info ti;
+
+	udp_tunnel_nic_get_port(dev, table, 0, &ti);
+	if (!table)
+		interface->vxlan_port = ti.port;
+	else
+		interface->geneve_port = ti.port;
+
+	fm10k_restore_udp_port_info(interface);
+	return 0;
+}
+
+static const struct udp_tunnel_nic_info fm10k_udp_tunnels = {
+	.sync_table	= fm10k_udp_tunnel_sync,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+	},
+};
+
+/**
+ * fm10k_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.
+ **/
+int fm10k_open(struct net_device *netdev)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	int err;
+
+	/* allocate transmit descriptors */
+	err = fm10k_setup_all_tx_resources(interface);
+	if (err)
+		goto err_setup_tx;
+
+	/* allocate receive descriptors */
+	err = fm10k_setup_all_rx_resources(interface);
+	if (err)
+		goto err_setup_rx;
+
+	/* allocate interrupt resources */
+	err = fm10k_qv_request_irq(interface);
+	if (err)
+		goto err_req_irq;
+
+	/* setup GLORT assignment for this port */
+	fm10k_request_glort_range(interface);
+
+	/* Notify the stack of the actual queue counts */
+	err = netif_set_real_num_tx_queues(netdev,
+					   interface->num_tx_queues);
+	if (err)
+		goto err_set_queues;
+
+	err = netif_set_real_num_rx_queues(netdev,
+					   interface->num_rx_queues);
+	if (err)
+		goto err_set_queues;
+
+	fm10k_up(interface);
+
+	return 0;
+
+err_set_queues:
+	fm10k_qv_free_irq(interface);
+err_req_irq:
+	fm10k_free_all_rx_resources(interface);
+err_setup_rx:
+	fm10k_free_all_tx_resources(interface);
+err_setup_tx:
+	return err;
+}
+
+/**
+ * fm10k_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 drivers control, but
+ * needs to be disabled.  A global MAC reset is issued to stop the
+ * hardware, and all transmit and receive resources are freed.
+ **/
+int fm10k_close(struct net_device *netdev)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+
+	fm10k_down(interface);
+
+	fm10k_qv_free_irq(interface);
+
+	fm10k_free_all_tx_resources(interface);
+	fm10k_free_all_rx_resources(interface);
+
+	return 0;
+}
+
+static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	int num_tx_queues = READ_ONCE(interface->num_tx_queues);
+	unsigned int r_idx = skb->queue_mapping;
+	int err;
+
+	if (!num_tx_queues)
+		return NETDEV_TX_BUSY;
+
+	if ((skb->protocol == htons(ETH_P_8021Q)) &&
+	    !skb_vlan_tag_present(skb)) {
+		/* FM10K only supports hardware tagging, any tags in frame
+		 * are considered 2nd level or "outer" tags
+		 */
+		struct vlan_hdr *vhdr;
+		__be16 proto;
+
+		/* make sure skb is not shared */
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (!skb)
+			return NETDEV_TX_OK;
+
+		/* make sure there is enough room to move the ethernet header */
+		if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+			return NETDEV_TX_OK;
+
+		/* verify the skb head is not shared */
+		err = skb_cow_head(skb, 0);
+		if (err) {
+			dev_kfree_skb(skb);
+			return NETDEV_TX_OK;
+		}
+
+		/* locate VLAN header */
+		vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+
+		/* pull the 2 key pieces of data out of it */
+		__vlan_hwaccel_put_tag(skb,
+				       htons(ETH_P_8021Q),
+				       ntohs(vhdr->h_vlan_TCI));
+		proto = vhdr->h_vlan_encapsulated_proto;
+		skb->protocol = (ntohs(proto) >= 1536) ? proto :
+							 htons(ETH_P_802_2);
+
+		/* squash it by moving the ethernet addresses up 4 bytes */
+		memmove(skb->data + VLAN_HLEN, skb->data, 12);
+		__skb_pull(skb, VLAN_HLEN);
+		skb_reset_mac_header(skb);
+	}
+
+	/* The minimum packet size for a single buffer is 17B so pad the skb
+	 * in order to meet this minimum size requirement.
+	 */
+	if (unlikely(skb->len < 17)) {
+		int pad_len = 17 - skb->len;
+
+		if (skb_pad(skb, pad_len))
+			return NETDEV_TX_OK;
+		__skb_put(skb, pad_len);
+	}
+
+	if (r_idx >= num_tx_queues)
+		r_idx %= num_tx_queues;
+
+	err = fm10k_xmit_frame_ring(skb, interface->tx_ring[r_idx]);
+
+	return err;
+}
+
+/**
+ * fm10k_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ * @txqueue: the index of the Tx queue that timed out
+ **/
+static void fm10k_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_ring *tx_ring;
+	bool real_tx_hang = false;
+
+	if (txqueue >= interface->num_tx_queues) {
+		WARN(1, "invalid Tx queue index %d", txqueue);
+		return;
+	}
+
+	tx_ring = interface->tx_ring[txqueue];
+	if (check_for_tx_hang(tx_ring) && fm10k_check_tx_hang(tx_ring))
+		real_tx_hang = true;
+
+#define TX_TIMEO_LIMIT 16000
+	if (real_tx_hang) {
+		fm10k_tx_timeout_reset(interface);
+	} else {
+		netif_info(interface, drv, netdev,
+			   "Fake Tx hang detected with timeout of %d seconds\n",
+			   netdev->watchdog_timeo / HZ);
+
+		/* fake Tx hang - increase the kernel timeout */
+		if (netdev->watchdog_timeo < TX_TIMEO_LIMIT)
+			netdev->watchdog_timeo *= 2;
+	}
+}
+
+/**
+ * fm10k_host_mbx_ready - Check PF interface's mailbox readiness
+ * @interface: board private structure
+ *
+ * This function checks if the PF interface's mailbox is ready before queueing
+ * mailbox messages for transmission. This will prevent filling the TX mailbox
+ * queue when the receiver is not ready. VF interfaces are exempt from this
+ * check since it will block all PF-VF mailbox messages from being sent from
+ * the VF to the PF at initialization.
+ **/
+static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	return (hw->mac.type == fm10k_mac_vf || interface->host_ready);
+}
+
+/**
+ * fm10k_queue_vlan_request - Queue a VLAN update request
+ * @interface: the fm10k interface structure
+ * @vid: the VLAN vid
+ * @vsi: VSI index number
+ * @set: whether to set or clear
+ *
+ * This function queues up a VLAN update. For VFs, this must be sent to the
+ * managing PF over the mailbox. For PFs, we'll use the same handling so that
+ * it's similar to the VF. This avoids storming the PF<->VF mailbox with too
+ * many VLAN updates during reset.
+ */
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface,
+			     u32 vid, u8 vsi, bool set)
+{
+	struct fm10k_macvlan_request *request;
+	unsigned long flags;
+
+	/* This must be atomic since we may be called while the netdev
+	 * addr_list_lock is held
+	 */
+	request = kzalloc(sizeof(*request), GFP_ATOMIC);
+	if (!request)
+		return -ENOMEM;
+
+	request->type = FM10K_VLAN_REQUEST;
+	request->vlan.vid = vid;
+	request->vlan.vsi = vsi;
+	request->set = set;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+	list_add_tail(&request->list, &interface->macvlan_requests);
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+	fm10k_macvlan_schedule(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_queue_mac_request - Queue a MAC update request
+ * @interface: the fm10k interface structure
+ * @glort: the target glort for this update
+ * @addr: the address to update
+ * @vid: the vid to update
+ * @set: whether to add or remove
+ *
+ * This function queues up a MAC request for sending to the switch manager.
+ * A separate thread monitors the queue and sends updates to the switch
+ * manager. Return 0 on success, and negative error code on failure.
+ **/
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+			    const unsigned char *addr, u16 vid, bool set)
+{
+	struct fm10k_macvlan_request *request;
+	unsigned long flags;
+
+	/* This must be atomic since we may be called while the netdev
+	 * addr_list_lock is held
+	 */
+	request = kzalloc(sizeof(*request), GFP_ATOMIC);
+	if (!request)
+		return -ENOMEM;
+
+	if (is_multicast_ether_addr(addr))
+		request->type = FM10K_MC_MAC_REQUEST;
+	else
+		request->type = FM10K_UC_MAC_REQUEST;
+
+	ether_addr_copy(request->mac.addr, addr);
+	request->mac.glort = glort;
+	request->mac.vid = vid;
+	request->set = set;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+	list_add_tail(&request->list, &interface->macvlan_requests);
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+	fm10k_macvlan_schedule(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_clear_macvlan_queue - Cancel pending updates for a given glort
+ * @interface: the fm10k interface structure
+ * @glort: the target glort to clear
+ * @vlans: true to clear VLAN messages, false to ignore them
+ *
+ * Cancel any outstanding MAC/VLAN requests for a given glort. This is
+ * expected to be called when a logical port goes down.
+ **/
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+			       u16 glort, bool vlans)
+
+{
+	struct fm10k_macvlan_request *r, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&interface->macvlan_lock, flags);
+
+	/* Free any outstanding MAC/VLAN requests for this interface */
+	list_for_each_entry_safe(r, tmp, &interface->macvlan_requests, list) {
+		switch (r->type) {
+		case FM10K_MC_MAC_REQUEST:
+		case FM10K_UC_MAC_REQUEST:
+			/* Don't free requests for other interfaces */
+			if (r->mac.glort != glort)
+				break;
+			fallthrough;
+		case FM10K_VLAN_REQUEST:
+			if (vlans) {
+				list_del(&r->list);
+				kfree(r);
+			}
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+}
+
+static int fm10k_uc_vlan_unsync(struct net_device *netdev,
+				const unsigned char *uc_addr)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	u16 glort = interface->glort;
+	u16 vid = interface->vid;
+	bool set = !!(vid / VLAN_N_VID);
+	int err;
+
+	/* drop any leading bits on the VLAN ID */
+	vid &= VLAN_N_VID - 1;
+
+	err = fm10k_queue_mac_request(interface, glort, uc_addr, vid, set);
+	if (err)
+		return err;
+
+	/* return non-zero value as we are only doing a partial sync/unsync */
+	return 1;
+}
+
+static int fm10k_mc_vlan_unsync(struct net_device *netdev,
+				const unsigned char *mc_addr)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	u16 glort = interface->glort;
+	u16 vid = interface->vid;
+	bool set = !!(vid / VLAN_N_VID);
+	int err;
+
+	/* drop any leading bits on the VLAN ID */
+	vid &= VLAN_N_VID - 1;
+
+	err = fm10k_queue_mac_request(interface, glort, mc_addr, vid, set);
+	if (err)
+		return err;
+
+	/* return non-zero value as we are only doing a partial sync/unsync */
+	return 1;
+}
+
+static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_l2_accel *l2_accel = interface->l2_accel;
+	struct fm10k_hw *hw = &interface->hw;
+	u16 glort;
+	s32 err;
+	int i;
+
+	/* updates do not apply to VLAN 0 */
+	if (!vid)
+		return 0;
+
+	if (vid >= VLAN_N_VID)
+		return -EINVAL;
+
+	/* Verify that we have permission to add VLANs. If this is a request
+	 * to remove a VLAN, we still want to allow the user to remove the
+	 * VLAN device. In that case, we need to clear the bit in the
+	 * active_vlans bitmask.
+	 */
+	if (set && hw->mac.vlan_override)
+		return -EACCES;
+
+	/* update active_vlans bitmask */
+	set_bit(vid, interface->active_vlans);
+	if (!set)
+		clear_bit(vid, interface->active_vlans);
+
+	/* disable the default VLAN ID on ring if we have an active VLAN */
+	for (i = 0; i < interface->num_rx_queues; i++) {
+		struct fm10k_ring *rx_ring = interface->rx_ring[i];
+		u16 rx_vid = rx_ring->vid & (VLAN_N_VID - 1);
+
+		if (test_bit(rx_vid, interface->active_vlans))
+			rx_ring->vid |= FM10K_VLAN_CLEAR;
+		else
+			rx_ring->vid &= ~FM10K_VLAN_CLEAR;
+	}
+
+	/* If our VLAN has been overridden, there is no reason to send VLAN
+	 * removal requests as they will be silently ignored.
+	 */
+	if (hw->mac.vlan_override)
+		return 0;
+
+	/* Do not remove default VLAN ID related entries from VLAN and MAC
+	 * tables
+	 */
+	if (!set && vid == hw->mac.default_vid)
+		return 0;
+
+	/* Do not throw an error if the interface is down. We will sync once
+	 * we come up
+	 */
+	if (test_bit(__FM10K_DOWN, interface->state))
+		return 0;
+
+	fm10k_mbx_lock(interface);
+
+	/* only need to update the VLAN if not in promiscuous mode */
+	if (!(netdev->flags & IFF_PROMISC)) {
+		err = fm10k_queue_vlan_request(interface, vid, 0, set);
+		if (err)
+			goto err_out;
+	}
+
+	/* Update our base MAC address */
+	err = fm10k_queue_mac_request(interface, interface->glort,
+				      hw->mac.addr, vid, set);
+	if (err)
+		goto err_out;
+
+	/* Update L2 accelerated macvlan addresses */
+	if (l2_accel) {
+		for (i = 0; i < l2_accel->size; i++) {
+			struct net_device *sdev = l2_accel->macvlan[i];
+
+			if (!sdev)
+				continue;
+
+			glort = l2_accel->dglort + 1 + i;
+
+			fm10k_queue_mac_request(interface, glort,
+						sdev->dev_addr,
+						vid, set);
+		}
+	}
+
+	/* set VLAN ID prior to syncing/unsyncing the VLAN */
+	interface->vid = vid + (set ? VLAN_N_VID : 0);
+
+	/* Update the unicast and multicast address list to add/drop VLAN */
+	__dev_uc_unsync(netdev, fm10k_uc_vlan_unsync);
+	__dev_mc_unsync(netdev, fm10k_mc_vlan_unsync);
+
+err_out:
+	fm10k_mbx_unlock(interface);
+
+	return err;
+}
+
+static int fm10k_vlan_rx_add_vid(struct net_device *netdev,
+				 __always_unused __be16 proto, u16 vid)
+{
+	/* update VLAN and address table based on changes */
+	return fm10k_update_vid(netdev, vid, true);
+}
+
+static int fm10k_vlan_rx_kill_vid(struct net_device *netdev,
+				  __always_unused __be16 proto, u16 vid)
+{
+	/* update VLAN and address table based on changes */
+	return fm10k_update_vid(netdev, vid, false);
+}
+
+static u16 fm10k_find_next_vlan(struct fm10k_intfc *interface, u16 vid)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	u16 default_vid = hw->mac.default_vid;
+	u16 vid_limit = vid < default_vid ? default_vid : VLAN_N_VID;
+
+	vid = find_next_bit(interface->active_vlans, vid_limit, ++vid);
+
+	return vid;
+}
+
+static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface)
+{
+	u32 vid, prev_vid;
+
+	/* loop through and find any gaps in the table */
+	for (vid = 0, prev_vid = 0;
+	     prev_vid < VLAN_N_VID;
+	     prev_vid = vid + 1, vid = fm10k_find_next_vlan(interface, vid)) {
+		if (prev_vid == vid)
+			continue;
+
+		/* send request to clear multiple bits at a time */
+		prev_vid += (vid - prev_vid - 1) << FM10K_VLAN_LENGTH_SHIFT;
+		fm10k_queue_vlan_request(interface, prev_vid, 0, false);
+	}
+}
+
+static int __fm10k_uc_sync(struct net_device *dev,
+			   const unsigned char *addr, bool sync)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	u16 vid, glort = interface->glort;
+	s32 err;
+
+	if (!is_valid_ether_addr(addr))
+		return -EADDRNOTAVAIL;
+
+	for (vid = fm10k_find_next_vlan(interface, 0);
+	     vid < VLAN_N_VID;
+	     vid = fm10k_find_next_vlan(interface, vid)) {
+		err = fm10k_queue_mac_request(interface, glort,
+					      addr, vid, sync);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fm10k_uc_sync(struct net_device *dev,
+			 const unsigned char *addr)
+{
+	return __fm10k_uc_sync(dev, addr, true);
+}
+
+static int fm10k_uc_unsync(struct net_device *dev,
+			   const unsigned char *addr)
+{
+	return __fm10k_uc_sync(dev, addr, false);
+}
+
+static int fm10k_set_mac(struct net_device *dev, void *p)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+	struct sockaddr *addr = p;
+	s32 err = 0;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (dev->flags & IFF_UP) {
+		/* setting MAC address requires mailbox */
+		fm10k_mbx_lock(interface);
+
+		err = fm10k_uc_sync(dev, addr->sa_data);
+		if (!err)
+			fm10k_uc_unsync(dev, hw->mac.addr);
+
+		fm10k_mbx_unlock(interface);
+	}
+
+	if (!err) {
+		eth_hw_addr_set(dev, addr->sa_data);
+		ether_addr_copy(hw->mac.addr, addr->sa_data);
+		dev->addr_assign_type &= ~NET_ADDR_RANDOM;
+	}
+
+	/* if we had a mailbox error suggest trying again */
+	return err ? -EAGAIN : 0;
+}
+
+static int __fm10k_mc_sync(struct net_device *dev,
+			   const unsigned char *addr, bool sync)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	u16 vid, glort = interface->glort;
+	s32 err;
+
+	if (!is_multicast_ether_addr(addr))
+		return -EADDRNOTAVAIL;
+
+	for (vid = fm10k_find_next_vlan(interface, 0);
+	     vid < VLAN_N_VID;
+	     vid = fm10k_find_next_vlan(interface, vid)) {
+		err = fm10k_queue_mac_request(interface, glort,
+					      addr, vid, sync);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fm10k_mc_sync(struct net_device *dev,
+			 const unsigned char *addr)
+{
+	return __fm10k_mc_sync(dev, addr, true);
+}
+
+static int fm10k_mc_unsync(struct net_device *dev,
+			   const unsigned char *addr)
+{
+	return __fm10k_mc_sync(dev, addr, false);
+}
+
+static void fm10k_set_rx_mode(struct net_device *dev)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_hw *hw = &interface->hw;
+	int xcast_mode;
+
+	/* no need to update the harwdare if we are not running */
+	if (!(dev->flags & IFF_UP))
+		return;
+
+	/* determine new mode based on flags */
+	xcast_mode = (dev->flags & IFF_PROMISC) ? FM10K_XCAST_MODE_PROMISC :
+		     (dev->flags & IFF_ALLMULTI) ? FM10K_XCAST_MODE_ALLMULTI :
+		     (dev->flags & (IFF_BROADCAST | IFF_MULTICAST)) ?
+		     FM10K_XCAST_MODE_MULTI : FM10K_XCAST_MODE_NONE;
+
+	fm10k_mbx_lock(interface);
+
+	/* update xcast mode first, but only if it changed */
+	if (interface->xcast_mode != xcast_mode) {
+		/* update VLAN table when entering promiscuous mode */
+		if (xcast_mode == FM10K_XCAST_MODE_PROMISC)
+			fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL,
+						 0, true);
+
+		/* clear VLAN table when exiting promiscuous mode */
+		if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC)
+			fm10k_clear_unused_vlans(interface);
+
+		/* update xcast mode if host's mailbox is ready */
+		if (fm10k_host_mbx_ready(interface))
+			hw->mac.ops.update_xcast_mode(hw, interface->glort,
+						      xcast_mode);
+
+		/* record updated xcast mode state */
+		interface->xcast_mode = xcast_mode;
+	}
+
+	/* synchronize all of the addresses */
+	__dev_uc_sync(dev, fm10k_uc_sync, fm10k_uc_unsync);
+	__dev_mc_sync(dev, fm10k_mc_sync, fm10k_mc_unsync);
+
+	fm10k_mbx_unlock(interface);
+}
+
+void fm10k_restore_rx_state(struct fm10k_intfc *interface)
+{
+	struct fm10k_l2_accel *l2_accel = interface->l2_accel;
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int xcast_mode, i;
+	u16 vid, glort;
+
+	/* record glort for this interface */
+	glort = interface->glort;
+
+	/* convert interface flags to xcast mode */
+	if (netdev->flags & IFF_PROMISC)
+		xcast_mode = FM10K_XCAST_MODE_PROMISC;
+	else if (netdev->flags & IFF_ALLMULTI)
+		xcast_mode = FM10K_XCAST_MODE_ALLMULTI;
+	else if (netdev->flags & (IFF_BROADCAST | IFF_MULTICAST))
+		xcast_mode = FM10K_XCAST_MODE_MULTI;
+	else
+		xcast_mode = FM10K_XCAST_MODE_NONE;
+
+	fm10k_mbx_lock(interface);
+
+	/* Enable logical port if host's mailbox is ready */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_lport_state(hw, glort,
+					       interface->glort_count, true);
+
+	/* update VLAN table */
+	fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0,
+				 xcast_mode == FM10K_XCAST_MODE_PROMISC);
+
+	/* update table with current entries */
+	for (vid = fm10k_find_next_vlan(interface, 0);
+	     vid < VLAN_N_VID;
+	     vid = fm10k_find_next_vlan(interface, vid)) {
+		fm10k_queue_vlan_request(interface, vid, 0, true);
+
+		fm10k_queue_mac_request(interface, glort,
+					hw->mac.addr, vid, true);
+
+		/* synchronize macvlan addresses */
+		if (l2_accel) {
+			for (i = 0; i < l2_accel->size; i++) {
+				struct net_device *sdev = l2_accel->macvlan[i];
+
+				if (!sdev)
+					continue;
+
+				glort = l2_accel->dglort + 1 + i;
+
+				fm10k_queue_mac_request(interface, glort,
+							sdev->dev_addr,
+							vid, true);
+			}
+		}
+	}
+
+	/* update xcast mode before synchronizing addresses if host's mailbox
+	 * is ready
+	 */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode);
+
+	/* synchronize all of the addresses */
+	__dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync);
+	__dev_mc_sync(netdev, fm10k_mc_sync, fm10k_mc_unsync);
+
+	/* synchronize macvlan addresses */
+	if (l2_accel) {
+		for (i = 0; i < l2_accel->size; i++) {
+			struct net_device *sdev = l2_accel->macvlan[i];
+
+			if (!sdev)
+				continue;
+
+			glort = l2_accel->dglort + 1 + i;
+
+			hw->mac.ops.update_xcast_mode(hw, glort,
+						      FM10K_XCAST_MODE_NONE);
+			fm10k_queue_mac_request(interface, glort,
+						sdev->dev_addr,
+						hw->mac.default_vid, true);
+		}
+	}
+
+	fm10k_mbx_unlock(interface);
+
+	/* record updated xcast mode state */
+	interface->xcast_mode = xcast_mode;
+
+	/* Restore tunnel configuration */
+	fm10k_restore_udp_port_info(interface);
+}
+
+void fm10k_reset_rx_state(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* Wait for MAC/VLAN work to finish */
+	while (test_bit(__FM10K_MACVLAN_SCHED, interface->state))
+		usleep_range(1000, 2000);
+
+	/* Cancel pending MAC/VLAN requests */
+	fm10k_clear_macvlan_queue(interface, interface->glort, true);
+
+	fm10k_mbx_lock(interface);
+
+	/* clear the logical port state on lower device if host's mailbox is
+	 * ready
+	 */
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_lport_state(hw, interface->glort,
+					       interface->glort_count, false);
+
+	fm10k_mbx_unlock(interface);
+
+	/* reset flags to default state */
+	interface->xcast_mode = FM10K_XCAST_MODE_NONE;
+
+	/* clear the sync flag since the lport has been dropped */
+	__dev_uc_unsync(netdev, NULL);
+	__dev_mc_unsync(netdev, NULL);
+}
+
+/**
+ * fm10k_get_stats64 - Get System Network Statistics
+ * @netdev: network interface device structure
+ * @stats: storage space for 64bit statistics
+ *
+ * Obtain 64bit statistics in a way that is safe for both 32bit and 64bit
+ * architectures.
+ */
+static void fm10k_get_stats64(struct net_device *netdev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct fm10k_intfc *interface = netdev_priv(netdev);
+	struct fm10k_ring *ring;
+	unsigned int start, i;
+	u64 bytes, packets;
+
+	rcu_read_lock();
+
+	for (i = 0; i < interface->num_rx_queues; i++) {
+		ring = READ_ONCE(interface->rx_ring[i]);
+
+		if (!ring)
+			continue;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
+			packets = ring->stats.packets;
+			bytes   = ring->stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
+
+		stats->rx_packets += packets;
+		stats->rx_bytes   += bytes;
+	}
+
+	for (i = 0; i < interface->num_tx_queues; i++) {
+		ring = READ_ONCE(interface->tx_ring[i]);
+
+		if (!ring)
+			continue;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
+			packets = ring->stats.packets;
+			bytes   = ring->stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
+
+		stats->tx_packets += packets;
+		stats->tx_bytes   += bytes;
+	}
+
+	rcu_read_unlock();
+
+	/* following stats updated by fm10k_service_task() */
+	stats->rx_missed_errors	= netdev->stats.rx_missed_errors;
+}
+
+int fm10k_setup_tc(struct net_device *dev, u8 tc)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	int err;
+
+	/* Currently only the PF supports priority classes */
+	if (tc && (interface->hw.mac.type != fm10k_mac_pf))
+		return -EINVAL;
+
+	/* Hardware supports up to 8 traffic classes */
+	if (tc > 8)
+		return -EINVAL;
+
+	/* Hardware has to reinitialize queues to match packet
+	 * buffer alignment. Unfortunately, the hardware is not
+	 * flexible enough to do this dynamically.
+	 */
+	if (netif_running(dev))
+		fm10k_close(dev);
+
+	fm10k_mbx_free_irq(interface);
+
+	fm10k_clear_queueing_scheme(interface);
+
+	/* we expect the prio_tc map to be repopulated later */
+	netdev_reset_tc(dev);
+	netdev_set_num_tc(dev, tc);
+
+	err = fm10k_init_queueing_scheme(interface);
+	if (err)
+		goto err_queueing_scheme;
+
+	err = fm10k_mbx_request_irq(interface);
+	if (err)
+		goto err_mbx_irq;
+
+	err = netif_running(dev) ? fm10k_open(dev) : 0;
+	if (err)
+		goto err_open;
+
+	/* flag to indicate SWPRI has yet to be updated */
+	set_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
+
+	return 0;
+err_open:
+	fm10k_mbx_free_irq(interface);
+err_mbx_irq:
+	fm10k_clear_queueing_scheme(interface);
+err_queueing_scheme:
+	netif_device_detach(dev);
+
+	return err;
+}
+
+static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			    void *type_data)
+{
+	struct tc_mqprio_qopt *mqprio = type_data;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EOPNOTSUPP;
+
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return fm10k_setup_tc(dev, mqprio->num_tc);
+}
+
+static void fm10k_assign_l2_accel(struct fm10k_intfc *interface,
+				  struct fm10k_l2_accel *l2_accel)
+{
+	int i;
+
+	for (i = 0; i < interface->num_rx_queues; i++) {
+		struct fm10k_ring *ring = interface->rx_ring[i];
+
+		rcu_assign_pointer(ring->l2_accel, l2_accel);
+	}
+
+	interface->l2_accel = l2_accel;
+}
+
+static void *fm10k_dfwd_add_station(struct net_device *dev,
+				    struct net_device *sdev)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_l2_accel *l2_accel = interface->l2_accel;
+	struct fm10k_l2_accel *old_l2_accel = NULL;
+	struct fm10k_dglort_cfg dglort = { 0 };
+	struct fm10k_hw *hw = &interface->hw;
+	int size, i;
+	u16 vid, glort;
+
+	/* The hardware supported by fm10k only filters on the destination MAC
+	 * address. In order to avoid issues we only support offloading modes
+	 * where the hardware can actually provide the functionality.
+	 */
+	if (!macvlan_supports_dest_filter(sdev))
+		return ERR_PTR(-EMEDIUMTYPE);
+
+	/* allocate l2 accel structure if it is not available */
+	if (!l2_accel) {
+		/* verify there is enough free GLORTs to support l2_accel */
+		if (interface->glort_count < 7)
+			return ERR_PTR(-EBUSY);
+
+		size = offsetof(struct fm10k_l2_accel, macvlan[7]);
+		l2_accel = kzalloc(size, GFP_KERNEL);
+		if (!l2_accel)
+			return ERR_PTR(-ENOMEM);
+
+		l2_accel->size = 7;
+		l2_accel->dglort = interface->glort;
+
+		/* update pointers */
+		fm10k_assign_l2_accel(interface, l2_accel);
+	/* do not expand if we are at our limit */
+	} else if ((l2_accel->count == FM10K_MAX_STATIONS) ||
+		   (l2_accel->count == (interface->glort_count - 1))) {
+		return ERR_PTR(-EBUSY);
+	/* expand if we have hit the size limit */
+	} else if (l2_accel->count == l2_accel->size) {
+		old_l2_accel = l2_accel;
+		size = offsetof(struct fm10k_l2_accel,
+				macvlan[(l2_accel->size * 2) + 1]);
+		l2_accel = kzalloc(size, GFP_KERNEL);
+		if (!l2_accel)
+			return ERR_PTR(-ENOMEM);
+
+		memcpy(l2_accel, old_l2_accel,
+		       offsetof(struct fm10k_l2_accel,
+				macvlan[old_l2_accel->size]));
+
+		l2_accel->size = (old_l2_accel->size * 2) + 1;
+
+		/* update pointers */
+		fm10k_assign_l2_accel(interface, l2_accel);
+		kfree_rcu(old_l2_accel, rcu);
+	}
+
+	/* add macvlan to accel table, and record GLORT for position */
+	for (i = 0; i < l2_accel->size; i++) {
+		if (!l2_accel->macvlan[i])
+			break;
+	}
+
+	/* record station */
+	l2_accel->macvlan[i] = sdev;
+	l2_accel->count++;
+
+	/* configure default DGLORT mapping for RSS/DCB */
+	dglort.idx = fm10k_dglort_pf_rss;
+	dglort.inner_rss = 1;
+	dglort.rss_l = fls(interface->ring_feature[RING_F_RSS].mask);
+	dglort.pc_l = fls(interface->ring_feature[RING_F_QOS].mask);
+	dglort.glort = interface->glort;
+	dglort.shared_l = fls(l2_accel->size);
+	hw->mac.ops.configure_dglort_map(hw, &dglort);
+
+	/* Add rules for this specific dglort to the switch */
+	fm10k_mbx_lock(interface);
+
+	glort = l2_accel->dglort + 1 + i;
+
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_xcast_mode(hw, glort,
+					      FM10K_XCAST_MODE_NONE);
+
+	fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+				hw->mac.default_vid, true);
+
+	for (vid = fm10k_find_next_vlan(interface, 0);
+	     vid < VLAN_N_VID;
+	     vid = fm10k_find_next_vlan(interface, vid))
+		fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+					vid, true);
+
+	fm10k_mbx_unlock(interface);
+
+	return sdev;
+}
+
+static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
+{
+	struct fm10k_intfc *interface = netdev_priv(dev);
+	struct fm10k_l2_accel *l2_accel = READ_ONCE(interface->l2_accel);
+	struct fm10k_dglort_cfg dglort = { 0 };
+	struct fm10k_hw *hw = &interface->hw;
+	struct net_device *sdev = priv;
+	u16 vid, glort;
+	int i;
+
+	if (!l2_accel)
+		return;
+
+	/* search table for matching interface */
+	for (i = 0; i < l2_accel->size; i++) {
+		if (l2_accel->macvlan[i] == sdev)
+			break;
+	}
+
+	/* exit if macvlan not found */
+	if (i == l2_accel->size)
+		return;
+
+	/* Remove any rules specific to this dglort */
+	fm10k_mbx_lock(interface);
+
+	glort = l2_accel->dglort + 1 + i;
+
+	if (fm10k_host_mbx_ready(interface))
+		hw->mac.ops.update_xcast_mode(hw, glort,
+					      FM10K_XCAST_MODE_NONE);
+
+	fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+				hw->mac.default_vid, false);
+
+	for (vid = fm10k_find_next_vlan(interface, 0);
+	     vid < VLAN_N_VID;
+	     vid = fm10k_find_next_vlan(interface, vid))
+		fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+					vid, false);
+
+	fm10k_mbx_unlock(interface);
+
+	/* record removal */
+	l2_accel->macvlan[i] = NULL;
+	l2_accel->count--;
+
+	/* configure default DGLORT mapping for RSS/DCB */
+	dglort.idx = fm10k_dglort_pf_rss;
+	dglort.inner_rss = 1;
+	dglort.rss_l = fls(interface->ring_feature[RING_F_RSS].mask);
+	dglort.pc_l = fls(interface->ring_feature[RING_F_QOS].mask);
+	dglort.glort = interface->glort;
+	dglort.shared_l = fls(l2_accel->size);
+	hw->mac.ops.configure_dglort_map(hw, &dglort);
+
+	/* If table is empty remove it */
+	if (l2_accel->count == 0) {
+		fm10k_assign_l2_accel(interface, NULL);
+		kfree_rcu(l2_accel, rcu);
+	}
+}
+
+static netdev_features_t fm10k_features_check(struct sk_buff *skb,
+					      struct net_device *dev,
+					      netdev_features_t features)
+{
+	if (!skb->encapsulation || fm10k_tx_encap_offload(skb))
+		return features;
+
+	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+}
+
+static const struct net_device_ops fm10k_netdev_ops = {
+	.ndo_open		= fm10k_open,
+	.ndo_stop		= fm10k_close,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_start_xmit		= fm10k_xmit_frame,
+	.ndo_set_mac_address	= fm10k_set_mac,
+	.ndo_tx_timeout		= fm10k_tx_timeout,
+	.ndo_vlan_rx_add_vid	= fm10k_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= fm10k_vlan_rx_kill_vid,
+	.ndo_set_rx_mode	= fm10k_set_rx_mode,
+	.ndo_get_stats64	= fm10k_get_stats64,
+	.ndo_setup_tc		= __fm10k_setup_tc,
+	.ndo_set_vf_mac		= fm10k_ndo_set_vf_mac,
+	.ndo_set_vf_vlan	= fm10k_ndo_set_vf_vlan,
+	.ndo_set_vf_rate	= fm10k_ndo_set_vf_bw,
+	.ndo_get_vf_config	= fm10k_ndo_get_vf_config,
+	.ndo_get_vf_stats	= fm10k_ndo_get_vf_stats,
+	.ndo_dfwd_add_station	= fm10k_dfwd_add_station,
+	.ndo_dfwd_del_station	= fm10k_dfwd_del_station,
+	.ndo_features_check	= fm10k_features_check,
+};
+
+#define DEFAULT_DEBUG_LEVEL_SHIFT 3
+
+struct net_device *fm10k_alloc_netdev(const struct fm10k_info *info)
+{
+	netdev_features_t hw_features;
+	struct fm10k_intfc *interface;
+	struct net_device *dev;
+
+	dev = alloc_etherdev_mq(sizeof(struct fm10k_intfc), MAX_QUEUES);
+	if (!dev)
+		return NULL;
+
+	/* set net device and ethtool ops */
+	dev->netdev_ops = &fm10k_netdev_ops;
+	fm10k_set_ethtool_ops(dev);
+
+	/* configure default debug level */
+	interface = netdev_priv(dev);
+	interface->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
+
+	/* configure default features */
+	dev->features |= NETIF_F_IP_CSUM |
+			 NETIF_F_IPV6_CSUM |
+			 NETIF_F_SG |
+			 NETIF_F_TSO |
+			 NETIF_F_TSO6 |
+			 NETIF_F_TSO_ECN |
+			 NETIF_F_RXHASH |
+			 NETIF_F_RXCSUM;
+
+	/* Only the PF can support VXLAN and NVGRE tunnel offloads */
+	if (info->mac == fm10k_mac_pf) {
+		dev->hw_enc_features = NETIF_F_IP_CSUM |
+				       NETIF_F_TSO |
+				       NETIF_F_TSO6 |
+				       NETIF_F_TSO_ECN |
+				       NETIF_F_GSO_UDP_TUNNEL |
+				       NETIF_F_IPV6_CSUM |
+				       NETIF_F_SG;
+
+		dev->features |= NETIF_F_GSO_UDP_TUNNEL;
+
+		dev->udp_tunnel_nic_info = &fm10k_udp_tunnels;
+	}
+
+	/* all features defined to this point should be changeable */
+	hw_features = dev->features;
+
+	/* allow user to enable L2 forwarding acceleration */
+	hw_features |= NETIF_F_HW_L2FW_DOFFLOAD;
+
+	/* configure VLAN features */
+	dev->vlan_features |= dev->features;
+
+	/* we want to leave these both on as we cannot disable VLAN tag
+	 * insertion or stripping on the hardware since it is contained
+	 * in the FTAG and not in the frame itself.
+	 */
+	dev->features |= NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX |
+			 NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	dev->priv_flags |= IFF_UNICAST_FLT;
+
+	dev->hw_features |= hw_features;
+
+	/* MTU range: 68 - 15342 */
+	dev->min_mtu = ETH_MIN_MTU;
+	dev->max_mtu = FM10K_MAX_JUMBO_FRAME_SIZE;
+
+	return dev;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
new file mode 100644
index 000000000..b473cb7d7
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -0,0 +1,2543 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/aer.h>
+
+#include "fm10k.h"
+
+static const struct fm10k_info *fm10k_info_tbl[] = {
+	[fm10k_device_pf] = &fm10k_pf_info,
+	[fm10k_device_vf] = &fm10k_vf_info,
+};
+
+/*
+ * fm10k_pci_tbl - PCI Device ID Table
+ *
+ * Wildcard entries (PCI_ANY_ID) should come last
+ * Last entry must be all 0s
+ *
+ * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
+ *   Class, Class Mask, private data (not used) }
+ */
+static const struct pci_device_id fm10k_pci_tbl[] = {
+	{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_PF), fm10k_device_pf },
+	{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_QDA2), fm10k_device_pf },
+	{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_DA2), fm10k_device_pf },
+	{ PCI_VDEVICE(INTEL, FM10K_DEV_ID_VF), fm10k_device_vf },
+	/* required last entry */
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, fm10k_pci_tbl);
+
+u16 fm10k_read_pci_cfg_word(struct fm10k_hw *hw, u32 reg)
+{
+	struct fm10k_intfc *interface = hw->back;
+	u16 value = 0;
+
+	if (FM10K_REMOVED(hw->hw_addr))
+		return ~value;
+
+	pci_read_config_word(interface->pdev, reg, &value);
+	if (value == 0xFFFF)
+		fm10k_write_flush(hw);
+
+	return value;
+}
+
+u32 fm10k_read_reg(struct fm10k_hw *hw, int reg)
+{
+	u32 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
+	u32 value = 0;
+
+	if (FM10K_REMOVED(hw_addr))
+		return ~value;
+
+	value = readl(&hw_addr[reg]);
+	if (!(~value) && (!reg || !(~readl(hw_addr)))) {
+		struct fm10k_intfc *interface = hw->back;
+		struct net_device *netdev = interface->netdev;
+
+		hw->hw_addr = NULL;
+		netif_device_detach(netdev);
+		netdev_err(netdev, "PCIe link lost, device now detached\n");
+	}
+
+	return value;
+}
+
+static int fm10k_hw_ready(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	fm10k_write_flush(hw);
+
+	return FM10K_REMOVED(hw->hw_addr) ? -ENODEV : 0;
+}
+
+/**
+ * fm10k_macvlan_schedule - Schedule MAC/VLAN queue task
+ * @interface: fm10k private interface structure
+ *
+ * Schedule the MAC/VLAN queue monitor task. If the MAC/VLAN task cannot be
+ * started immediately, request that it be restarted when possible.
+ */
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface)
+{
+	/* Avoid processing the MAC/VLAN queue when the service task is
+	 * disabled, or when we're resetting the device.
+	 */
+	if (!test_bit(__FM10K_MACVLAN_DISABLE, interface->state) &&
+	    !test_and_set_bit(__FM10K_MACVLAN_SCHED, interface->state)) {
+		clear_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+		/* We delay the actual start of execution in order to allow
+		 * multiple MAC/VLAN updates to accumulate before handling
+		 * them, and to allow some time to let the mailbox drain
+		 * between runs.
+		 */
+		queue_delayed_work(fm10k_workqueue,
+				   &interface->macvlan_task, 10);
+	} else {
+		set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+	}
+}
+
+/**
+ * fm10k_stop_macvlan_task - Stop the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Wait until the MAC/VLAN queue task has stopped, and cancel any future
+ * requests.
+ */
+static void fm10k_stop_macvlan_task(struct fm10k_intfc *interface)
+{
+	/* Disable the MAC/VLAN work item */
+	set_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+	/* Make sure we waited until any current invocations have stopped */
+	cancel_delayed_work_sync(&interface->macvlan_task);
+
+	/* We set the __FM10K_MACVLAN_SCHED bit when we schedule the task.
+	 * However, it may not be unset of the MAC/VLAN task never actually
+	 * got a chance to run. Since we've canceled the task here, and it
+	 * cannot be rescheuled right now, we need to ensure the scheduled bit
+	 * gets unset.
+	 */
+	clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+}
+
+/**
+ * fm10k_resume_macvlan_task - Restart the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Clear the __FM10K_MACVLAN_DISABLE bit and, if a request occurred, schedule
+ * the MAC/VLAN work monitor.
+ */
+static void fm10k_resume_macvlan_task(struct fm10k_intfc *interface)
+{
+	/* Re-enable the MAC/VLAN work item */
+	clear_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+	/* We might have received a MAC/VLAN request while disabled. If so,
+	 * kick off the queue now.
+	 */
+	if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+		fm10k_macvlan_schedule(interface);
+}
+
+void fm10k_service_event_schedule(struct fm10k_intfc *interface)
+{
+	if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) &&
+	    !test_and_set_bit(__FM10K_SERVICE_SCHED, interface->state)) {
+		clear_bit(__FM10K_SERVICE_REQUEST, interface->state);
+		queue_work(fm10k_workqueue, &interface->service_task);
+	} else {
+		set_bit(__FM10K_SERVICE_REQUEST, interface->state);
+	}
+}
+
+static void fm10k_service_event_complete(struct fm10k_intfc *interface)
+{
+	WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, interface->state));
+
+	/* flush memory to make sure state is correct before next watchog */
+	smp_mb__before_atomic();
+	clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+
+	/* If a service event was requested since we started, immediately
+	 * re-schedule now. This ensures we don't drop a request until the
+	 * next timer event.
+	 */
+	if (test_bit(__FM10K_SERVICE_REQUEST, interface->state))
+		fm10k_service_event_schedule(interface);
+}
+
+static void fm10k_stop_service_event(struct fm10k_intfc *interface)
+{
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	cancel_work_sync(&interface->service_task);
+
+	/* It's possible that cancel_work_sync stopped the service task from
+	 * running before it could actually start. In this case the
+	 * __FM10K_SERVICE_SCHED bit will never be cleared. Since we know that
+	 * the service task cannot be running at this point, we need to clear
+	 * the scheduled bit, as otherwise the service task may never be
+	 * restarted.
+	 */
+	clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+}
+
+static void fm10k_start_service_event(struct fm10k_intfc *interface)
+{
+	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	fm10k_service_event_schedule(interface);
+}
+
+/**
+ * fm10k_service_timer - Timer Call-back
+ * @t: pointer to timer data
+ **/
+static void fm10k_service_timer(struct timer_list *t)
+{
+	struct fm10k_intfc *interface = from_timer(interface, t,
+						   service_timer);
+
+	/* Reset the timer */
+	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
+
+	fm10k_service_event_schedule(interface);
+}
+
+/**
+ * fm10k_prepare_for_reset - Prepare the driver and device for a pending reset
+ * @interface: fm10k private data structure
+ *
+ * This function prepares for a device reset by shutting as much down as we
+ * can. It does nothing and returns false if __FM10K_RESETTING was already set
+ * prior to calling this function. It returns true if it actually did work.
+ */
+static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+
+	/* put off any impending NetWatchDogTimeout */
+	netif_trans_update(netdev);
+
+	/* Nothing to do if a reset is already in progress */
+	if (test_and_set_bit(__FM10K_RESETTING, interface->state))
+		return false;
+
+	/* As the MAC/VLAN task will be accessing registers it must not be
+	 * running while we reset. Although the task will not be scheduled
+	 * once we start resetting it may already be running
+	 */
+	fm10k_stop_macvlan_task(interface);
+
+	rtnl_lock();
+
+	fm10k_iov_suspend(interface->pdev);
+
+	if (netif_running(netdev))
+		fm10k_close(netdev);
+
+	fm10k_mbx_free_irq(interface);
+
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
+	/* delay any future reset requests */
+	interface->last_reset = jiffies + (10 * HZ);
+
+	rtnl_unlock();
+
+	return true;
+}
+
+static int fm10k_handle_reset(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	WARN_ON(!test_bit(__FM10K_RESETTING, interface->state));
+
+	rtnl_lock();
+
+	pci_set_master(interface->pdev);
+
+	/* reset and initialize the hardware so it is in a known state */
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&interface->pdev->dev, "reset_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
+	if (err) {
+		dev_err(&interface->pdev->dev, "init_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = fm10k_init_queueing_scheme(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev,
+			"init_queueing_scheme failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	/* re-associate interrupts */
+	err = fm10k_mbx_request_irq(interface);
+	if (err)
+		goto err_mbx_irq;
+
+	err = fm10k_hw_ready(interface);
+	if (err)
+		goto err_open;
+
+	/* update hardware address for VFs if perm_addr has changed */
+	if (hw->mac.type == fm10k_mac_vf) {
+		if (is_valid_ether_addr(hw->mac.perm_addr)) {
+			ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
+			ether_addr_copy(netdev->perm_addr, hw->mac.perm_addr);
+			eth_hw_addr_set(netdev, hw->mac.perm_addr);
+			netdev->addr_assign_type &= ~NET_ADDR_RANDOM;
+		}
+
+		if (hw->mac.vlan_override)
+			netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
+		else
+			netdev->features |= NETIF_F_HW_VLAN_CTAG_RX;
+	}
+
+	err = netif_running(netdev) ? fm10k_open(netdev) : 0;
+	if (err)
+		goto err_open;
+
+	fm10k_iov_resume(interface->pdev);
+
+	rtnl_unlock();
+
+	fm10k_resume_macvlan_task(interface);
+
+	clear_bit(__FM10K_RESETTING, interface->state);
+
+	return err;
+err_open:
+	fm10k_mbx_free_irq(interface);
+err_mbx_irq:
+	fm10k_clear_queueing_scheme(interface);
+reinit_err:
+	netif_device_detach(netdev);
+
+	rtnl_unlock();
+
+	clear_bit(__FM10K_RESETTING, interface->state);
+
+	return err;
+}
+
+static void fm10k_detach_subtask(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+	u32 __iomem *hw_addr;
+	u32 value;
+
+	/* do nothing if netdev is still present or hw_addr is set */
+	if (netif_device_present(netdev) || interface->hw.hw_addr)
+		return;
+
+	/* We've lost the PCIe register space, and can no longer access the
+	 * device. Shut everything except the detach subtask down and prepare
+	 * to reset the device in case we recover. If we actually prepare for
+	 * reset, indicate that we're detached.
+	 */
+	if (fm10k_prepare_for_reset(interface))
+		set_bit(__FM10K_RESET_DETACHED, interface->state);
+
+	/* check the real address space to see if we've recovered */
+	hw_addr = READ_ONCE(interface->uc_addr);
+	value = readl(hw_addr);
+	if (~value) {
+		int err;
+
+		/* Make sure the reset was initiated because we detached,
+		 * otherwise we might race with a different reset flow.
+		 */
+		if (!test_and_clear_bit(__FM10K_RESET_DETACHED,
+					interface->state))
+			return;
+
+		/* Restore the hardware address */
+		interface->hw.hw_addr = interface->uc_addr;
+
+		/* PCIe link has been restored, and the device is active
+		 * again. Restore everything and reset the device.
+		 */
+		err = fm10k_handle_reset(interface);
+		if (err) {
+			netdev_err(netdev, "Unable to reset device: %d\n", err);
+			interface->hw.hw_addr = NULL;
+			return;
+		}
+
+		/* Re-attach the netdev */
+		netif_device_attach(netdev);
+		netdev_warn(netdev, "PCIe link restored, device now attached\n");
+		return;
+	}
+}
+
+static void fm10k_reset_subtask(struct fm10k_intfc *interface)
+{
+	int err;
+
+	if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED,
+				interface->flags))
+		return;
+
+	/* If another thread has already prepared to reset the device, we
+	 * should not attempt to handle a reset here, since we'd race with
+	 * that thread. This may happen if we suspend the device or if the
+	 * PCIe link is lost. In this case, we'll just ignore the RESET
+	 * request, as it will (eventually) be taken care of when the thread
+	 * which actually started the reset is finished.
+	 */
+	if (!fm10k_prepare_for_reset(interface))
+		return;
+
+	netdev_err(interface->netdev, "Reset interface\n");
+
+	err = fm10k_handle_reset(interface);
+	if (err)
+		dev_err(&interface->pdev->dev,
+			"fm10k_handle_reset failed: %d\n", err);
+}
+
+/**
+ * fm10k_configure_swpri_map - Configure Receive SWPRI to PC mapping
+ * @interface: board private structure
+ *
+ * Configure the SWPRI to PC mapping for the port.
+ **/
+static void fm10k_configure_swpri_map(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int i;
+
+	/* clear flag indicating update is needed */
+	clear_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
+
+	/* these registers are only available on the PF */
+	if (hw->mac.type != fm10k_mac_pf)
+		return;
+
+	/* configure SWPRI to PC map */
+	for (i = 0; i < FM10K_SWPRI_MAX; i++)
+		fm10k_write_reg(hw, FM10K_SWPRI_MAP(i),
+				netdev_get_prio_tc_map(netdev, i));
+}
+
+/**
+ * fm10k_watchdog_update_host_state - Update the link status based on host.
+ * @interface: board private structure
+ **/
+static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	s32 err;
+
+	if (test_bit(__FM10K_LINK_DOWN, interface->state)) {
+		interface->host_ready = false;
+		if (time_is_after_jiffies(interface->link_down_event))
+			return;
+		clear_bit(__FM10K_LINK_DOWN, interface->state);
+	}
+
+	if (test_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags)) {
+		if (rtnl_trylock()) {
+			fm10k_configure_swpri_map(interface);
+			rtnl_unlock();
+		}
+	}
+
+	/* lock the mailbox for transmit and receive */
+	fm10k_mbx_lock(interface);
+
+	err = hw->mac.ops.get_host_state(hw, &interface->host_ready);
+	if (err && time_is_before_jiffies(interface->last_reset))
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+	/* free the lock */
+	fm10k_mbx_unlock(interface);
+}
+
+/**
+ * fm10k_mbx_subtask - Process upstream and downstream mailboxes
+ * @interface: board private structure
+ *
+ * This function will process both the upstream and downstream mailboxes.
+ **/
+static void fm10k_mbx_subtask(struct fm10k_intfc *interface)
+{
+	/* If we're resetting, bail out */
+	if (test_bit(__FM10K_RESETTING, interface->state))
+		return;
+
+	/* process upstream mailbox and update device state */
+	fm10k_watchdog_update_host_state(interface);
+
+	/* process downstream mailboxes */
+	fm10k_iov_mbx(interface);
+}
+
+/**
+ * fm10k_watchdog_host_is_ready - Update netdev status based on host ready
+ * @interface: board private structure
+ **/
+static void fm10k_watchdog_host_is_ready(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+
+	/* only continue if link state is currently down */
+	if (netif_carrier_ok(netdev))
+		return;
+
+	netif_info(interface, drv, netdev, "NIC Link is up\n");
+
+	netif_carrier_on(netdev);
+	netif_tx_wake_all_queues(netdev);
+}
+
+/**
+ * fm10k_watchdog_host_not_ready - Update netdev status based on host not ready
+ * @interface: board private structure
+ **/
+static void fm10k_watchdog_host_not_ready(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+
+	/* only continue if link state is currently up */
+	if (!netif_carrier_ok(netdev))
+		return;
+
+	netif_info(interface, drv, netdev, "NIC Link is down\n");
+
+	netif_carrier_off(netdev);
+	netif_tx_stop_all_queues(netdev);
+}
+
+/**
+ * fm10k_update_stats - Update the board statistics counters.
+ * @interface: board private structure
+ **/
+void fm10k_update_stats(struct fm10k_intfc *interface)
+{
+	struct net_device_stats *net_stats = &interface->netdev->stats;
+	struct fm10k_hw *hw = &interface->hw;
+	u64 hw_csum_tx_good = 0, hw_csum_rx_good = 0, rx_length_errors = 0;
+	u64 rx_switch_errors = 0, rx_drops = 0, rx_pp_errors = 0;
+	u64 rx_link_errors = 0;
+	u64 rx_errors = 0, rx_csum_errors = 0, tx_csum_errors = 0;
+	u64 restart_queue = 0, tx_busy = 0, alloc_failed = 0;
+	u64 rx_bytes_nic = 0, rx_pkts_nic = 0, rx_drops_nic = 0;
+	u64 tx_bytes_nic = 0, tx_pkts_nic = 0;
+	u64 bytes, pkts;
+	int i;
+
+	/* ensure only one thread updates stats at a time */
+	if (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
+		return;
+
+	/* do not allow stats update via service task for next second */
+	interface->next_stats_update = jiffies + HZ;
+
+	/* gather some stats to the interface struct that are per queue */
+	for (bytes = 0, pkts = 0, i = 0; i < interface->num_tx_queues; i++) {
+		struct fm10k_ring *tx_ring = READ_ONCE(interface->tx_ring[i]);
+
+		if (!tx_ring)
+			continue;
+
+		restart_queue += tx_ring->tx_stats.restart_queue;
+		tx_busy += tx_ring->tx_stats.tx_busy;
+		tx_csum_errors += tx_ring->tx_stats.csum_err;
+		bytes += tx_ring->stats.bytes;
+		pkts += tx_ring->stats.packets;
+		hw_csum_tx_good += tx_ring->tx_stats.csum_good;
+	}
+
+	interface->restart_queue = restart_queue;
+	interface->tx_busy = tx_busy;
+	net_stats->tx_bytes = bytes;
+	net_stats->tx_packets = pkts;
+	interface->tx_csum_errors = tx_csum_errors;
+	interface->hw_csum_tx_good = hw_csum_tx_good;
+
+	/* gather some stats to the interface struct that are per queue */
+	for (bytes = 0, pkts = 0, i = 0; i < interface->num_rx_queues; i++) {
+		struct fm10k_ring *rx_ring = READ_ONCE(interface->rx_ring[i]);
+
+		if (!rx_ring)
+			continue;
+
+		bytes += rx_ring->stats.bytes;
+		pkts += rx_ring->stats.packets;
+		alloc_failed += rx_ring->rx_stats.alloc_failed;
+		rx_csum_errors += rx_ring->rx_stats.csum_err;
+		rx_errors += rx_ring->rx_stats.errors;
+		hw_csum_rx_good += rx_ring->rx_stats.csum_good;
+		rx_switch_errors += rx_ring->rx_stats.switch_errors;
+		rx_drops += rx_ring->rx_stats.drops;
+		rx_pp_errors += rx_ring->rx_stats.pp_errors;
+		rx_link_errors += rx_ring->rx_stats.link_errors;
+		rx_length_errors += rx_ring->rx_stats.length_errors;
+	}
+
+	net_stats->rx_bytes = bytes;
+	net_stats->rx_packets = pkts;
+	interface->alloc_failed = alloc_failed;
+	interface->rx_csum_errors = rx_csum_errors;
+	interface->hw_csum_rx_good = hw_csum_rx_good;
+	interface->rx_switch_errors = rx_switch_errors;
+	interface->rx_drops = rx_drops;
+	interface->rx_pp_errors = rx_pp_errors;
+	interface->rx_link_errors = rx_link_errors;
+	interface->rx_length_errors = rx_length_errors;
+
+	hw->mac.ops.update_hw_stats(hw, &interface->stats);
+
+	for (i = 0; i < hw->mac.max_queues; i++) {
+		struct fm10k_hw_stats_q *q = &interface->stats.q[i];
+
+		tx_bytes_nic += q->tx_bytes.count;
+		tx_pkts_nic += q->tx_packets.count;
+		rx_bytes_nic += q->rx_bytes.count;
+		rx_pkts_nic += q->rx_packets.count;
+		rx_drops_nic += q->rx_drops.count;
+	}
+
+	interface->tx_bytes_nic = tx_bytes_nic;
+	interface->tx_packets_nic = tx_pkts_nic;
+	interface->rx_bytes_nic = rx_bytes_nic;
+	interface->rx_packets_nic = rx_pkts_nic;
+	interface->rx_drops_nic = rx_drops_nic;
+
+	/* Fill out the OS statistics structure */
+	net_stats->rx_errors = rx_errors;
+	net_stats->rx_dropped = interface->stats.nodesc_drop.count;
+
+	/* Update VF statistics */
+	fm10k_iov_update_stats(interface);
+
+	clear_bit(__FM10K_UPDATING_STATS, interface->state);
+}
+
+/**
+ * fm10k_watchdog_flush_tx - flush queues on host not ready
+ * @interface: pointer to the device interface structure
+ **/
+static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface)
+{
+	int some_tx_pending = 0;
+	int i;
+
+	/* nothing to do if carrier is up */
+	if (netif_carrier_ok(interface->netdev))
+		return;
+
+	for (i = 0; i < interface->num_tx_queues; i++) {
+		struct fm10k_ring *tx_ring = interface->tx_ring[i];
+
+		if (tx_ring->next_to_use != tx_ring->next_to_clean) {
+			some_tx_pending = 1;
+			break;
+		}
+	}
+
+	/* 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.
+	 */
+	if (some_tx_pending)
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+}
+
+/**
+ * fm10k_watchdog_subtask - check and bring link up
+ * @interface: pointer to the device interface structure
+ **/
+static void fm10k_watchdog_subtask(struct fm10k_intfc *interface)
+{
+	/* if interface is down do nothing */
+	if (test_bit(__FM10K_DOWN, interface->state) ||
+	    test_bit(__FM10K_RESETTING, interface->state))
+		return;
+
+	if (interface->host_ready)
+		fm10k_watchdog_host_is_ready(interface);
+	else
+		fm10k_watchdog_host_not_ready(interface);
+
+	/* update stats only once every second */
+	if (time_is_before_jiffies(interface->next_stats_update))
+		fm10k_update_stats(interface);
+
+	/* flush any uncompleted work */
+	fm10k_watchdog_flush_tx(interface);
+}
+
+/**
+ * fm10k_check_hang_subtask - check for hung queues and dropped interrupts
+ * @interface: pointer to the device interface structure
+ *
+ * This function serves two purposes.  First it strobes the interrupt lines
+ * in order to make certain interrupts are occurring.  Secondly it sets the
+ * bits needed to check for TX hangs.  As a result we should immediately
+ * determine if a hang has occurred.
+ */
+static void fm10k_check_hang_subtask(struct fm10k_intfc *interface)
+{
+	/* If we're down or resetting, just bail */
+	if (test_bit(__FM10K_DOWN, interface->state) ||
+	    test_bit(__FM10K_RESETTING, interface->state))
+		return;
+
+	/* rate limit tx hang checks to only once every 2 seconds */
+	if (time_is_after_eq_jiffies(interface->next_tx_hang_check))
+		return;
+	interface->next_tx_hang_check = jiffies + (2 * HZ);
+
+	if (netif_carrier_ok(interface->netdev)) {
+		int i;
+
+		/* Force detection of hung controller */
+		for (i = 0; i < interface->num_tx_queues; i++)
+			set_check_for_tx_hang(interface->tx_ring[i]);
+
+		/* Rearm all in-use q_vectors for immediate firing */
+		for (i = 0; i < interface->num_q_vectors; i++) {
+			struct fm10k_q_vector *qv = interface->q_vector[i];
+
+			if (!qv->tx.count && !qv->rx.count)
+				continue;
+			writel(FM10K_ITR_ENABLE | FM10K_ITR_PENDING2, qv->itr);
+		}
+	}
+}
+
+/**
+ * fm10k_service_task - manages and runs subtasks
+ * @work: pointer to work_struct containing our data
+ **/
+static void fm10k_service_task(struct work_struct *work)
+{
+	struct fm10k_intfc *interface;
+
+	interface = container_of(work, struct fm10k_intfc, service_task);
+
+	/* Check whether we're detached first */
+	fm10k_detach_subtask(interface);
+
+	/* tasks run even when interface is down */
+	fm10k_mbx_subtask(interface);
+	fm10k_reset_subtask(interface);
+
+	/* tasks only run when interface is up */
+	fm10k_watchdog_subtask(interface);
+	fm10k_check_hang_subtask(interface);
+
+	/* release lock on service events to allow scheduling next event */
+	fm10k_service_event_complete(interface);
+}
+
+/**
+ * fm10k_macvlan_task - send queued MAC/VLAN requests to switch manager
+ * @work: pointer to work_struct containing our data
+ *
+ * This work item handles sending MAC/VLAN updates to the switch manager. When
+ * the interface is up, it will attempt to queue mailbox messages to the
+ * switch manager requesting updates for MAC/VLAN pairs. If the Tx fifo of the
+ * mailbox is full, it will reschedule itself to try again in a short while.
+ * This ensures that the driver does not overload the switch mailbox with too
+ * many simultaneous requests, causing an unnecessary reset.
+ **/
+static void fm10k_macvlan_task(struct work_struct *work)
+{
+	struct fm10k_macvlan_request *item;
+	struct fm10k_intfc *interface;
+	struct delayed_work *dwork;
+	struct list_head *requests;
+	struct fm10k_hw *hw;
+	unsigned long flags;
+
+	dwork = to_delayed_work(work);
+	interface = container_of(dwork, struct fm10k_intfc, macvlan_task);
+	hw = &interface->hw;
+	requests = &interface->macvlan_requests;
+
+	do {
+		/* Pop the first item off the list */
+		spin_lock_irqsave(&interface->macvlan_lock, flags);
+		item = list_first_entry_or_null(requests,
+						struct fm10k_macvlan_request,
+						list);
+		if (item)
+			list_del_init(&item->list);
+
+		spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+		/* We have no more items to process */
+		if (!item)
+			goto done;
+
+		fm10k_mbx_lock(interface);
+
+		/* Check that we have plenty of space to send the message. We
+		 * want to ensure that the mailbox stays low enough to avoid a
+		 * change in the host state, otherwise we may see spurious
+		 * link up / link down notifications.
+		 */
+		if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU + 5)) {
+			hw->mbx.ops.process(hw, &hw->mbx);
+			set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+			fm10k_mbx_unlock(interface);
+
+			/* Put the request back on the list */
+			spin_lock_irqsave(&interface->macvlan_lock, flags);
+			list_add(&item->list, requests);
+			spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+			break;
+		}
+
+		switch (item->type) {
+		case FM10K_MC_MAC_REQUEST:
+			hw->mac.ops.update_mc_addr(hw,
+						   item->mac.glort,
+						   item->mac.addr,
+						   item->mac.vid,
+						   item->set);
+			break;
+		case FM10K_UC_MAC_REQUEST:
+			hw->mac.ops.update_uc_addr(hw,
+						   item->mac.glort,
+						   item->mac.addr,
+						   item->mac.vid,
+						   item->set,
+						   0);
+			break;
+		case FM10K_VLAN_REQUEST:
+			hw->mac.ops.update_vlan(hw,
+						item->vlan.vid,
+						item->vlan.vsi,
+						item->set);
+			break;
+		default:
+			break;
+		}
+
+		fm10k_mbx_unlock(interface);
+
+		/* Free the item now that we've sent the update */
+		kfree(item);
+	} while (true);
+
+done:
+	WARN_ON(!test_bit(__FM10K_MACVLAN_SCHED, interface->state));
+
+	/* flush memory to make sure state is correct */
+	smp_mb__before_atomic();
+	clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+
+	/* If a MAC/VLAN request was scheduled since we started, we should
+	 * re-schedule. However, there is no reason to re-schedule if there is
+	 * no work to do.
+	 */
+	if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+		fm10k_macvlan_schedule(interface);
+}
+
+/**
+ * fm10k_configure_tx_ring - Configure Tx ring after Reset
+ * @interface: board private structure
+ * @ring: structure containing ring specific data
+ *
+ * Configure the Tx descriptor ring after a reset.
+ **/
+static void fm10k_configure_tx_ring(struct fm10k_intfc *interface,
+				    struct fm10k_ring *ring)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	u64 tdba = ring->dma;
+	u32 size = ring->count * sizeof(struct fm10k_tx_desc);
+	u32 txint = FM10K_INT_MAP_DISABLE;
+	u32 txdctl = BIT(FM10K_TXDCTL_MAX_TIME_SHIFT) | FM10K_TXDCTL_ENABLE;
+	u8 reg_idx = ring->reg_idx;
+
+	/* disable queue to avoid issues while updating state */
+	fm10k_write_reg(hw, FM10K_TXDCTL(reg_idx), 0);
+	fm10k_write_flush(hw);
+
+	/* possible poll here to verify ring resources have been cleaned */
+
+	/* set location and size for descriptor ring */
+	fm10k_write_reg(hw, FM10K_TDBAL(reg_idx), tdba & DMA_BIT_MASK(32));
+	fm10k_write_reg(hw, FM10K_TDBAH(reg_idx), tdba >> 32);
+	fm10k_write_reg(hw, FM10K_TDLEN(reg_idx), size);
+
+	/* reset head and tail pointers */
+	fm10k_write_reg(hw, FM10K_TDH(reg_idx), 0);
+	fm10k_write_reg(hw, FM10K_TDT(reg_idx), 0);
+
+	/* store tail pointer */
+	ring->tail = &interface->uc_addr[FM10K_TDT(reg_idx)];
+
+	/* reset ntu and ntc to place SW in sync with hardware */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
+
+	/* Map interrupt */
+	if (ring->q_vector) {
+		txint = ring->q_vector->v_idx + NON_Q_VECTORS;
+		txint |= FM10K_INT_MAP_TIMER0;
+	}
+
+	fm10k_write_reg(hw, FM10K_TXINT(reg_idx), txint);
+
+	/* enable use of FTAG bit in Tx descriptor, register is RO for VF */
+	fm10k_write_reg(hw, FM10K_PFVTCTL(reg_idx),
+			FM10K_PFVTCTL_FTAG_DESC_ENABLE);
+
+	/* Initialize XPS */
+	if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, ring->state) &&
+	    ring->q_vector)
+		netif_set_xps_queue(ring->netdev,
+				    &ring->q_vector->affinity_mask,
+				    ring->queue_index);
+
+	/* enable queue */
+	fm10k_write_reg(hw, FM10K_TXDCTL(reg_idx), txdctl);
+}
+
+/**
+ * fm10k_enable_tx_ring - Verify Tx ring is enabled after configuration
+ * @interface: board private structure
+ * @ring: structure containing ring specific data
+ *
+ * Verify the Tx descriptor ring is ready for transmit.
+ **/
+static void fm10k_enable_tx_ring(struct fm10k_intfc *interface,
+				 struct fm10k_ring *ring)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	int wait_loop = 10;
+	u32 txdctl;
+	u8 reg_idx = ring->reg_idx;
+
+	/* if we are already enabled just exit */
+	if (fm10k_read_reg(hw, FM10K_TXDCTL(reg_idx)) & FM10K_TXDCTL_ENABLE)
+		return;
+
+	/* poll to verify queue is enabled */
+	do {
+		usleep_range(1000, 2000);
+		txdctl = fm10k_read_reg(hw, FM10K_TXDCTL(reg_idx));
+	} while (!(txdctl & FM10K_TXDCTL_ENABLE) && --wait_loop);
+	if (!wait_loop)
+		netif_err(interface, drv, interface->netdev,
+			  "Could not enable Tx Queue %d\n", reg_idx);
+}
+
+/**
+ * fm10k_configure_tx - Configure Transmit Unit after Reset
+ * @interface: board private structure
+ *
+ * Configure the Tx unit of the MAC after a reset.
+ **/
+static void fm10k_configure_tx(struct fm10k_intfc *interface)
+{
+	int i;
+
+	/* Setup the HW Tx Head and Tail descriptor pointers */
+	for (i = 0; i < interface->num_tx_queues; i++)
+		fm10k_configure_tx_ring(interface, interface->tx_ring[i]);
+
+	/* poll here to verify that Tx rings are now enabled */
+	for (i = 0; i < interface->num_tx_queues; i++)
+		fm10k_enable_tx_ring(interface, interface->tx_ring[i]);
+}
+
+/**
+ * fm10k_configure_rx_ring - Configure Rx ring after Reset
+ * @interface: board private structure
+ * @ring: structure containing ring specific data
+ *
+ * Configure the Rx descriptor ring after a reset.
+ **/
+static void fm10k_configure_rx_ring(struct fm10k_intfc *interface,
+				    struct fm10k_ring *ring)
+{
+	u64 rdba = ring->dma;
+	struct fm10k_hw *hw = &interface->hw;
+	u32 size = ring->count * sizeof(union fm10k_rx_desc);
+	u32 rxqctl, rxdctl = FM10K_RXDCTL_WRITE_BACK_MIN_DELAY;
+	u32 srrctl = FM10K_SRRCTL_BUFFER_CHAINING_EN;
+	u32 rxint = FM10K_INT_MAP_DISABLE;
+	u8 rx_pause = interface->rx_pause;
+	u8 reg_idx = ring->reg_idx;
+
+	/* disable queue to avoid issues while updating state */
+	rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx));
+	rxqctl &= ~FM10K_RXQCTL_ENABLE;
+	fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl);
+	fm10k_write_flush(hw);
+
+	/* possible poll here to verify ring resources have been cleaned */
+
+	/* set location and size for descriptor ring */
+	fm10k_write_reg(hw, FM10K_RDBAL(reg_idx), rdba & DMA_BIT_MASK(32));
+	fm10k_write_reg(hw, FM10K_RDBAH(reg_idx), rdba >> 32);
+	fm10k_write_reg(hw, FM10K_RDLEN(reg_idx), size);
+
+	/* reset head and tail pointers */
+	fm10k_write_reg(hw, FM10K_RDH(reg_idx), 0);
+	fm10k_write_reg(hw, FM10K_RDT(reg_idx), 0);
+
+	/* store tail pointer */
+	ring->tail = &interface->uc_addr[FM10K_RDT(reg_idx)];
+
+	/* reset ntu and ntc to place SW in sync with hardware */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
+	ring->next_to_alloc = 0;
+
+	/* Configure the Rx buffer size for one buff without split */
+	srrctl |= FM10K_RX_BUFSZ >> FM10K_SRRCTL_BSIZEPKT_SHIFT;
+
+	/* Configure the Rx ring to suppress loopback packets */
+	srrctl |= FM10K_SRRCTL_LOOPBACK_SUPPRESS;
+	fm10k_write_reg(hw, FM10K_SRRCTL(reg_idx), srrctl);
+
+	/* Enable drop on empty */
+#ifdef CONFIG_DCB
+	if (interface->pfc_en)
+		rx_pause = interface->pfc_en;
+#endif
+	if (!(rx_pause & BIT(ring->qos_pc)))
+		rxdctl |= FM10K_RXDCTL_DROP_ON_EMPTY;
+
+	fm10k_write_reg(hw, FM10K_RXDCTL(reg_idx), rxdctl);
+
+	/* assign default VLAN to queue */
+	ring->vid = hw->mac.default_vid;
+
+	/* if we have an active VLAN, disable default VLAN ID */
+	if (test_bit(hw->mac.default_vid, interface->active_vlans))
+		ring->vid |= FM10K_VLAN_CLEAR;
+
+	/* Map interrupt */
+	if (ring->q_vector) {
+		rxint = ring->q_vector->v_idx + NON_Q_VECTORS;
+		rxint |= FM10K_INT_MAP_TIMER1;
+	}
+
+	fm10k_write_reg(hw, FM10K_RXINT(reg_idx), rxint);
+
+	/* enable queue */
+	rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx));
+	rxqctl |= FM10K_RXQCTL_ENABLE;
+	fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl);
+
+	/* place buffers on ring for receive data */
+	fm10k_alloc_rx_buffers(ring, fm10k_desc_unused(ring));
+}
+
+/**
+ * fm10k_update_rx_drop_en - Configures the drop enable bits for Rx rings
+ * @interface: board private structure
+ *
+ * Configure the drop enable bits for the Rx rings.
+ **/
+void fm10k_update_rx_drop_en(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	u8 rx_pause = interface->rx_pause;
+	int i;
+
+#ifdef CONFIG_DCB
+	if (interface->pfc_en)
+		rx_pause = interface->pfc_en;
+
+#endif
+	for (i = 0; i < interface->num_rx_queues; i++) {
+		struct fm10k_ring *ring = interface->rx_ring[i];
+		u32 rxdctl = FM10K_RXDCTL_WRITE_BACK_MIN_DELAY;
+		u8 reg_idx = ring->reg_idx;
+
+		if (!(rx_pause & BIT(ring->qos_pc)))
+			rxdctl |= FM10K_RXDCTL_DROP_ON_EMPTY;
+
+		fm10k_write_reg(hw, FM10K_RXDCTL(reg_idx), rxdctl);
+	}
+}
+
+/**
+ * fm10k_configure_dglort - Configure Receive DGLORT after reset
+ * @interface: board private structure
+ *
+ * Configure the DGLORT description and RSS tables.
+ **/
+static void fm10k_configure_dglort(struct fm10k_intfc *interface)
+{
+	struct fm10k_dglort_cfg dglort = { 0 };
+	struct fm10k_hw *hw = &interface->hw;
+	int i;
+	u32 mrqc;
+
+	/* Fill out hash function seeds */
+	for (i = 0; i < FM10K_RSSRK_SIZE; i++)
+		fm10k_write_reg(hw, FM10K_RSSRK(0, i), interface->rssrk[i]);
+
+	/* Write RETA table to hardware */
+	for (i = 0; i < FM10K_RETA_SIZE; i++)
+		fm10k_write_reg(hw, FM10K_RETA(0, i), interface->reta[i]);
+
+	/* Generate RSS hash based on packet types, TCP/UDP
+	 * port numbers and/or IPv4/v6 src and dst addresses
+	 */
+	mrqc = FM10K_MRQC_IPV4 |
+	       FM10K_MRQC_TCP_IPV4 |
+	       FM10K_MRQC_IPV6 |
+	       FM10K_MRQC_TCP_IPV6;
+
+	if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags))
+		mrqc |= FM10K_MRQC_UDP_IPV4;
+	if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, interface->flags))
+		mrqc |= FM10K_MRQC_UDP_IPV6;
+
+	fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
+
+	/* configure default DGLORT mapping for RSS/DCB */
+	dglort.inner_rss = 1;
+	dglort.rss_l = fls(interface->ring_feature[RING_F_RSS].mask);
+	dglort.pc_l = fls(interface->ring_feature[RING_F_QOS].mask);
+	hw->mac.ops.configure_dglort_map(hw, &dglort);
+
+	/* assign GLORT per queue for queue mapped testing */
+	if (interface->glort_count > 64) {
+		memset(&dglort, 0, sizeof(dglort));
+		dglort.inner_rss = 1;
+		dglort.glort = interface->glort + 64;
+		dglort.idx = fm10k_dglort_pf_queue;
+		dglort.queue_l = fls(interface->num_rx_queues - 1);
+		hw->mac.ops.configure_dglort_map(hw, &dglort);
+	}
+
+	/* assign glort value for RSS/DCB specific to this interface */
+	memset(&dglort, 0, sizeof(dglort));
+	dglort.inner_rss = 1;
+	dglort.glort = interface->glort;
+	dglort.rss_l = fls(interface->ring_feature[RING_F_RSS].mask);
+	dglort.pc_l = fls(interface->ring_feature[RING_F_QOS].mask);
+	/* configure DGLORT mapping for RSS/DCB */
+	dglort.idx = fm10k_dglort_pf_rss;
+	if (interface->l2_accel)
+		dglort.shared_l = fls(interface->l2_accel->size);
+	hw->mac.ops.configure_dglort_map(hw, &dglort);
+}
+
+/**
+ * fm10k_configure_rx - Configure Receive Unit after Reset
+ * @interface: board private structure
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ **/
+static void fm10k_configure_rx(struct fm10k_intfc *interface)
+{
+	int i;
+
+	/* Configure SWPRI to PC map */
+	fm10k_configure_swpri_map(interface);
+
+	/* Configure RSS and DGLORT map */
+	fm10k_configure_dglort(interface);
+
+	/* Setup the HW Rx Head and Tail descriptor pointers */
+	for (i = 0; i < interface->num_rx_queues; i++)
+		fm10k_configure_rx_ring(interface, interface->rx_ring[i]);
+
+	/* possible poll here to verify that Rx rings are now enabled */
+}
+
+static void fm10k_napi_enable_all(struct fm10k_intfc *interface)
+{
+	struct fm10k_q_vector *q_vector;
+	int q_idx;
+
+	for (q_idx = 0; q_idx < interface->num_q_vectors; q_idx++) {
+		q_vector = interface->q_vector[q_idx];
+		napi_enable(&q_vector->napi);
+	}
+}
+
+static irqreturn_t fm10k_msix_clean_rings(int __always_unused irq, void *data)
+{
+	struct fm10k_q_vector *q_vector = data;
+
+	if (q_vector->rx.count || q_vector->tx.count)
+		napi_schedule_irqoff(&q_vector->napi);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fm10k_msix_mbx_vf(int __always_unused irq, void *data)
+{
+	struct fm10k_intfc *interface = data;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+
+	/* re-enable mailbox interrupt and indicate 20us delay */
+	fm10k_write_reg(hw, FM10K_VFITR(FM10K_MBX_VECTOR),
+			(FM10K_MBX_INT_DELAY >> hw->mac.itr_scale) |
+			FM10K_ITR_ENABLE);
+
+	/* service upstream mailbox */
+	if (fm10k_mbx_trylock(interface)) {
+		mbx->ops.process(hw, mbx);
+		fm10k_mbx_unlock(interface);
+	}
+
+	hw->mac.get_host_state = true;
+	fm10k_service_event_schedule(interface);
+
+	return IRQ_HANDLED;
+}
+
+#define FM10K_ERR_MSG(type) case (type): error = #type; break
+static void fm10k_handle_fault(struct fm10k_intfc *interface, int type,
+			       struct fm10k_fault *fault)
+{
+	struct pci_dev *pdev = interface->pdev;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_iov_data *iov_data = interface->iov_data;
+	char *error;
+
+	switch (type) {
+	case FM10K_PCA_FAULT:
+		switch (fault->type) {
+		default:
+			error = "Unknown PCA error";
+			break;
+		FM10K_ERR_MSG(PCA_NO_FAULT);
+		FM10K_ERR_MSG(PCA_UNMAPPED_ADDR);
+		FM10K_ERR_MSG(PCA_BAD_QACCESS_PF);
+		FM10K_ERR_MSG(PCA_BAD_QACCESS_VF);
+		FM10K_ERR_MSG(PCA_MALICIOUS_REQ);
+		FM10K_ERR_MSG(PCA_POISONED_TLP);
+		FM10K_ERR_MSG(PCA_TLP_ABORT);
+		}
+		break;
+	case FM10K_THI_FAULT:
+		switch (fault->type) {
+		default:
+			error = "Unknown THI error";
+			break;
+		FM10K_ERR_MSG(THI_NO_FAULT);
+		FM10K_ERR_MSG(THI_MAL_DIS_Q_FAULT);
+		}
+		break;
+	case FM10K_FUM_FAULT:
+		switch (fault->type) {
+		default:
+			error = "Unknown FUM error";
+			break;
+		FM10K_ERR_MSG(FUM_NO_FAULT);
+		FM10K_ERR_MSG(FUM_UNMAPPED_ADDR);
+		FM10K_ERR_MSG(FUM_BAD_VF_QACCESS);
+		FM10K_ERR_MSG(FUM_ADD_DECODE_ERR);
+		FM10K_ERR_MSG(FUM_RO_ERROR);
+		FM10K_ERR_MSG(FUM_QPRC_CRC_ERROR);
+		FM10K_ERR_MSG(FUM_CSR_TIMEOUT);
+		FM10K_ERR_MSG(FUM_INVALID_TYPE);
+		FM10K_ERR_MSG(FUM_INVALID_LENGTH);
+		FM10K_ERR_MSG(FUM_INVALID_BE);
+		FM10K_ERR_MSG(FUM_INVALID_ALIGN);
+		}
+		break;
+	default:
+		error = "Undocumented fault";
+		break;
+	}
+
+	dev_warn(&pdev->dev,
+		 "%s Address: 0x%llx SpecInfo: 0x%x Func: %02x.%0x\n",
+		 error, fault->address, fault->specinfo,
+		 PCI_SLOT(fault->func), PCI_FUNC(fault->func));
+
+	/* For VF faults, clear out the respective LPORT, reset the queue
+	 * resources, and then reconnect to the mailbox. This allows the
+	 * VF in question to resume behavior. For transient faults that are
+	 * the result of non-malicious behavior this will log the fault and
+	 * allow the VF to resume functionality. Obviously for malicious VFs
+	 * they will be able to attempt malicious behavior again. In this
+	 * case, the system administrator will need to step in and manually
+	 * remove or disable the VF in question.
+	 */
+	if (fault->func && iov_data) {
+		int vf = fault->func - 1;
+		struct fm10k_vf_info *vf_info = &iov_data->vf_info[vf];
+
+		hw->iov.ops.reset_lport(hw, vf_info);
+		hw->iov.ops.reset_resources(hw, vf_info);
+
+		/* reset_lport disables the VF, so re-enable it */
+		hw->iov.ops.set_lport(hw, vf_info, vf,
+				      FM10K_VF_FLAG_MULTI_CAPABLE);
+
+		/* reset_resources will disconnect from the mbx  */
+		vf_info->mbx.ops.connect(hw, &vf_info->mbx);
+	}
+}
+
+static void fm10k_report_fault(struct fm10k_intfc *interface, u32 eicr)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_fault fault = { 0 };
+	int type, err;
+
+	for (eicr &= FM10K_EICR_FAULT_MASK, type = FM10K_PCA_FAULT;
+	     eicr;
+	     eicr >>= 1, type += FM10K_FAULT_SIZE) {
+		/* only check if there is an error reported */
+		if (!(eicr & 0x1))
+			continue;
+
+		/* retrieve fault info */
+		err = hw->mac.ops.get_fault(hw, type, &fault);
+		if (err) {
+			dev_err(&interface->pdev->dev,
+				"error reading fault\n");
+			continue;
+		}
+
+		fm10k_handle_fault(interface, type, &fault);
+	}
+}
+
+static void fm10k_reset_drop_on_empty(struct fm10k_intfc *interface, u32 eicr)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	const u32 rxdctl = FM10K_RXDCTL_WRITE_BACK_MIN_DELAY;
+	u32 maxholdq;
+	int q;
+
+	if (!(eicr & FM10K_EICR_MAXHOLDTIME))
+		return;
+
+	maxholdq = fm10k_read_reg(hw, FM10K_MAXHOLDQ(7));
+	if (maxholdq)
+		fm10k_write_reg(hw, FM10K_MAXHOLDQ(7), maxholdq);
+	for (q = 255;;) {
+		if (maxholdq & BIT(31)) {
+			if (q < FM10K_MAX_QUEUES_PF) {
+				interface->rx_overrun_pf++;
+				fm10k_write_reg(hw, FM10K_RXDCTL(q), rxdctl);
+			} else {
+				interface->rx_overrun_vf++;
+			}
+		}
+
+		maxholdq *= 2;
+		if (!maxholdq)
+			q &= ~(32 - 1);
+
+		if (!q)
+			break;
+
+		if (q-- % 32)
+			continue;
+
+		maxholdq = fm10k_read_reg(hw, FM10K_MAXHOLDQ(q / 32));
+		if (maxholdq)
+			fm10k_write_reg(hw, FM10K_MAXHOLDQ(q / 32), maxholdq);
+	}
+}
+
+static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data)
+{
+	struct fm10k_intfc *interface = data;
+	struct fm10k_hw *hw = &interface->hw;
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 eicr;
+
+	/* unmask any set bits related to this interrupt */
+	eicr = fm10k_read_reg(hw, FM10K_EICR);
+	fm10k_write_reg(hw, FM10K_EICR, eicr & (FM10K_EICR_MAILBOX |
+						FM10K_EICR_SWITCHREADY |
+						FM10K_EICR_SWITCHNOTREADY));
+
+	/* report any faults found to the message log */
+	fm10k_report_fault(interface, eicr);
+
+	/* reset any queues disabled due to receiver overrun */
+	fm10k_reset_drop_on_empty(interface, eicr);
+
+	/* service mailboxes */
+	if (fm10k_mbx_trylock(interface)) {
+		s32 err = mbx->ops.process(hw, mbx);
+
+		if (err == FM10K_ERR_RESET_REQUESTED)
+			set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+		/* handle VFLRE events */
+		fm10k_iov_event(interface);
+		fm10k_mbx_unlock(interface);
+	}
+
+	/* if switch toggled state we should reset GLORTs */
+	if (eicr & FM10K_EICR_SWITCHNOTREADY) {
+		/* force link down for at least 4 seconds */
+		interface->link_down_event = jiffies + (4 * HZ);
+		set_bit(__FM10K_LINK_DOWN, interface->state);
+
+		/* reset dglort_map back to no config */
+		hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
+	}
+
+	/* we should validate host state after interrupt event */
+	hw->mac.get_host_state = true;
+
+	/* validate host state, and handle VF mailboxes in the service task */
+	fm10k_service_event_schedule(interface);
+
+	/* re-enable mailbox interrupt and indicate 20us delay */
+	fm10k_write_reg(hw, FM10K_ITR(FM10K_MBX_VECTOR),
+			(FM10K_MBX_INT_DELAY >> hw->mac.itr_scale) |
+			FM10K_ITR_ENABLE);
+
+	return IRQ_HANDLED;
+}
+
+void fm10k_mbx_free_irq(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	struct msix_entry *entry;
+	int itr_reg;
+
+	/* no mailbox IRQ to free if MSI-X is not enabled */
+	if (!interface->msix_entries)
+		return;
+
+	entry = &interface->msix_entries[FM10K_MBX_VECTOR];
+
+	/* disconnect the mailbox */
+	hw->mbx.ops.disconnect(hw, &hw->mbx);
+
+	/* disable Mailbox cause */
+	if (hw->mac.type == fm10k_mac_pf) {
+		fm10k_write_reg(hw, FM10K_EIMR,
+				FM10K_EIMR_DISABLE(PCA_FAULT) |
+				FM10K_EIMR_DISABLE(FUM_FAULT) |
+				FM10K_EIMR_DISABLE(MAILBOX) |
+				FM10K_EIMR_DISABLE(SWITCHREADY) |
+				FM10K_EIMR_DISABLE(SWITCHNOTREADY) |
+				FM10K_EIMR_DISABLE(SRAMERROR) |
+				FM10K_EIMR_DISABLE(VFLR) |
+				FM10K_EIMR_DISABLE(MAXHOLDTIME));
+		itr_reg = FM10K_ITR(FM10K_MBX_VECTOR);
+	} else {
+		itr_reg = FM10K_VFITR(FM10K_MBX_VECTOR);
+	}
+
+	fm10k_write_reg(hw, itr_reg, FM10K_ITR_MASK_SET);
+
+	free_irq(entry->vector, interface);
+}
+
+static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results,
+			      struct fm10k_mbx_info *mbx)
+{
+	bool vlan_override = hw->mac.vlan_override;
+	u16 default_vid = hw->mac.default_vid;
+	struct fm10k_intfc *interface;
+	s32 err;
+
+	err = fm10k_msg_mac_vlan_vf(hw, results, mbx);
+	if (err)
+		return err;
+
+	interface = container_of(hw, struct fm10k_intfc, hw);
+
+	/* MAC was changed so we need reset */
+	if (is_valid_ether_addr(hw->mac.perm_addr) &&
+	    !ether_addr_equal(hw->mac.perm_addr, hw->mac.addr))
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+	/* VLAN override was changed, or default VLAN changed */
+	if ((vlan_override != hw->mac.vlan_override) ||
+	    (default_vid != hw->mac.default_vid))
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+	return 0;
+}
+
+/* generic error handler for mailbox issues */
+static s32 fm10k_mbx_error(struct fm10k_hw *hw, u32 **results,
+			   struct fm10k_mbx_info __always_unused *mbx)
+{
+	struct fm10k_intfc *interface;
+	struct pci_dev *pdev;
+
+	interface = container_of(hw, struct fm10k_intfc, hw);
+	pdev = interface->pdev;
+
+	dev_err(&pdev->dev, "Unknown message ID %u\n",
+		**results & FM10K_TLV_ID_MASK);
+
+	return 0;
+}
+
+static const struct fm10k_msg_data vf_mbx_data[] = {
+	FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test),
+	FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_mbx_mac_addr),
+	FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_msg_lport_state_vf),
+	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_mbx_error),
+};
+
+static int fm10k_mbx_request_irq_vf(struct fm10k_intfc *interface)
+{
+	struct msix_entry *entry = &interface->msix_entries[FM10K_MBX_VECTOR];
+	struct net_device *dev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	/* Use timer0 for interrupt moderation on the mailbox */
+	u32 itr = entry->entry | FM10K_INT_MAP_TIMER0;
+
+	/* register mailbox handlers */
+	err = hw->mbx.ops.register_handlers(&hw->mbx, vf_mbx_data);
+	if (err)
+		return err;
+
+	/* request the IRQ */
+	err = request_irq(entry->vector, fm10k_msix_mbx_vf, 0,
+			  dev->name, interface);
+	if (err) {
+		netif_err(interface, probe, dev,
+			  "request_irq for msix_mbx failed: %d\n", err);
+		return err;
+	}
+
+	/* map all of the interrupt sources */
+	fm10k_write_reg(hw, FM10K_VFINT_MAP, itr);
+
+	/* enable interrupt */
+	fm10k_write_reg(hw, FM10K_VFITR(entry->entry), FM10K_ITR_ENABLE);
+
+	return 0;
+}
+
+static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results,
+			   struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_intfc *interface;
+	u32 dglort_map = hw->mac.dglort_map;
+	s32 err;
+
+	interface = container_of(hw, struct fm10k_intfc, hw);
+
+	err = fm10k_msg_err_pf(hw, results, mbx);
+	if (!err && hw->swapi.status) {
+		/* force link down for a reasonable delay */
+		interface->link_down_event = jiffies + (2 * HZ);
+		set_bit(__FM10K_LINK_DOWN, interface->state);
+
+		/* reset dglort_map back to no config */
+		hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
+
+		fm10k_service_event_schedule(interface);
+
+		/* prevent overloading kernel message buffer */
+		if (interface->lport_map_failed)
+			return 0;
+
+		interface->lport_map_failed = true;
+
+		if (hw->swapi.status == FM10K_MSG_ERR_PEP_NOT_SCHEDULED)
+			dev_warn(&interface->pdev->dev,
+				 "cannot obtain link because the host interface is configured for a PCIe host interface bandwidth of zero\n");
+		dev_warn(&interface->pdev->dev,
+			 "request logical port map failed: %d\n",
+			 hw->swapi.status);
+
+		return 0;
+	}
+
+	err = fm10k_msg_lport_map_pf(hw, results, mbx);
+	if (err)
+		return err;
+
+	interface->lport_map_failed = false;
+
+	/* we need to reset if port count was just updated */
+	if (dglort_map != hw->mac.dglort_map)
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+	return 0;
+}
+
+static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results,
+			     struct fm10k_mbx_info __always_unused *mbx)
+{
+	struct fm10k_intfc *interface;
+	u16 glort, pvid;
+	u32 pvid_update;
+	s32 err;
+
+	err = fm10k_tlv_attr_get_u32(results[FM10K_PF_ATTR_ID_UPDATE_PVID],
+				     &pvid_update);
+	if (err)
+		return err;
+
+	/* extract values from the pvid update */
+	glort = FM10K_MSG_HDR_FIELD_GET(pvid_update, UPDATE_PVID_GLORT);
+	pvid = FM10K_MSG_HDR_FIELD_GET(pvid_update, UPDATE_PVID_PVID);
+
+	/* if glort is not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort))
+		return FM10K_ERR_PARAM;
+
+	/* verify VLAN ID is valid */
+	if (pvid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	interface = container_of(hw, struct fm10k_intfc, hw);
+
+	/* check to see if this belongs to one of the VFs */
+	err = fm10k_iov_update_pvid(interface, glort, pvid);
+	if (!err)
+		return 0;
+
+	/* we need to reset if default VLAN was just updated */
+	if (pvid != hw->mac.default_vid)
+		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
+	hw->mac.default_vid = pvid;
+
+	return 0;
+}
+
+static const struct fm10k_msg_data pf_mbx_data[] = {
+	FM10K_PF_MSG_ERR_HANDLER(XCAST_MODES, fm10k_msg_err_pf),
+	FM10K_PF_MSG_ERR_HANDLER(UPDATE_MAC_FWD_RULE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_LPORT_MAP_HANDLER(fm10k_lport_map),
+	FM10K_PF_MSG_ERR_HANDLER(LPORT_CREATE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_ERR_HANDLER(LPORT_DELETE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_UPDATE_PVID_HANDLER(fm10k_update_pvid),
+	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_mbx_error),
+};
+
+static int fm10k_mbx_request_irq_pf(struct fm10k_intfc *interface)
+{
+	struct msix_entry *entry = &interface->msix_entries[FM10K_MBX_VECTOR];
+	struct net_device *dev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	/* Use timer0 for interrupt moderation on the mailbox */
+	u32 mbx_itr = entry->entry | FM10K_INT_MAP_TIMER0;
+	u32 other_itr = entry->entry | FM10K_INT_MAP_IMMEDIATE;
+
+	/* register mailbox handlers */
+	err = hw->mbx.ops.register_handlers(&hw->mbx, pf_mbx_data);
+	if (err)
+		return err;
+
+	/* request the IRQ */
+	err = request_irq(entry->vector, fm10k_msix_mbx_pf, 0,
+			  dev->name, interface);
+	if (err) {
+		netif_err(interface, probe, dev,
+			  "request_irq for msix_mbx failed: %d\n", err);
+		return err;
+	}
+
+	/* Enable interrupts w/ no moderation for "other" interrupts */
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_pcie_fault), other_itr);
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_switch_up_down), other_itr);
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_sram), other_itr);
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_max_hold_time), other_itr);
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_vflr), other_itr);
+
+	/* Enable interrupts w/ moderation for mailbox */
+	fm10k_write_reg(hw, FM10K_INT_MAP(fm10k_int_mailbox), mbx_itr);
+
+	/* Enable individual interrupt causes */
+	fm10k_write_reg(hw, FM10K_EIMR, FM10K_EIMR_ENABLE(PCA_FAULT) |
+					FM10K_EIMR_ENABLE(FUM_FAULT) |
+					FM10K_EIMR_ENABLE(MAILBOX) |
+					FM10K_EIMR_ENABLE(SWITCHREADY) |
+					FM10K_EIMR_ENABLE(SWITCHNOTREADY) |
+					FM10K_EIMR_ENABLE(SRAMERROR) |
+					FM10K_EIMR_ENABLE(VFLR) |
+					FM10K_EIMR_ENABLE(MAXHOLDTIME));
+
+	/* enable interrupt */
+	fm10k_write_reg(hw, FM10K_ITR(entry->entry), FM10K_ITR_ENABLE);
+
+	return 0;
+}
+
+int fm10k_mbx_request_irq(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	/* enable Mailbox cause */
+	if (hw->mac.type == fm10k_mac_pf)
+		err = fm10k_mbx_request_irq_pf(interface);
+	else
+		err = fm10k_mbx_request_irq_vf(interface);
+	if (err)
+		return err;
+
+	/* connect mailbox */
+	err = hw->mbx.ops.connect(hw, &hw->mbx);
+
+	/* if the mailbox failed to connect, then free IRQ */
+	if (err)
+		fm10k_mbx_free_irq(interface);
+
+	return err;
+}
+
+/**
+ * fm10k_qv_free_irq - release interrupts associated with queue vectors
+ * @interface: board private structure
+ *
+ * Release all interrupts associated with this interface
+ **/
+void fm10k_qv_free_irq(struct fm10k_intfc *interface)
+{
+	int vector = interface->num_q_vectors;
+	struct msix_entry *entry;
+
+	entry = &interface->msix_entries[NON_Q_VECTORS + vector];
+
+	while (vector) {
+		struct fm10k_q_vector *q_vector;
+
+		vector--;
+		entry--;
+		q_vector = interface->q_vector[vector];
+
+		if (!q_vector->tx.count && !q_vector->rx.count)
+			continue;
+
+		/* clear the affinity_mask in the IRQ descriptor */
+		irq_set_affinity_hint(entry->vector, NULL);
+
+		/* disable interrupts */
+		writel(FM10K_ITR_MASK_SET, q_vector->itr);
+
+		free_irq(entry->vector, q_vector);
+	}
+}
+
+/**
+ * fm10k_qv_request_irq - initialize interrupts for queue vectors
+ * @interface: board private structure
+ *
+ * Attempts to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ **/
+int fm10k_qv_request_irq(struct fm10k_intfc *interface)
+{
+	struct net_device *dev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	struct msix_entry *entry;
+	unsigned int ri = 0, ti = 0;
+	int vector, err;
+
+	entry = &interface->msix_entries[NON_Q_VECTORS];
+
+	for (vector = 0; vector < interface->num_q_vectors; vector++) {
+		struct fm10k_q_vector *q_vector = interface->q_vector[vector];
+
+		/* name the vector */
+		if (q_vector->tx.count && q_vector->rx.count) {
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-TxRx-%u", dev->name, ri++);
+			ti++;
+		} else if (q_vector->rx.count) {
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-rx-%u", dev->name, ri++);
+		} else if (q_vector->tx.count) {
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "%s-tx-%u", dev->name, ti++);
+		} else {
+			/* skip this unused q_vector */
+			continue;
+		}
+
+		/* Assign ITR register to q_vector */
+		q_vector->itr = (hw->mac.type == fm10k_mac_pf) ?
+				&interface->uc_addr[FM10K_ITR(entry->entry)] :
+				&interface->uc_addr[FM10K_VFITR(entry->entry)];
+
+		/* request the IRQ */
+		err = request_irq(entry->vector, &fm10k_msix_clean_rings, 0,
+				  q_vector->name, q_vector);
+		if (err) {
+			netif_err(interface, probe, dev,
+				  "request_irq failed for MSIX interrupt Error: %d\n",
+				  err);
+			goto err_out;
+		}
+
+		/* assign the mask for this irq */
+		irq_set_affinity_hint(entry->vector, &q_vector->affinity_mask);
+
+		/* Enable q_vector */
+		writel(FM10K_ITR_ENABLE, q_vector->itr);
+
+		entry++;
+	}
+
+	return 0;
+
+err_out:
+	/* wind through the ring freeing all entries and vectors */
+	while (vector) {
+		struct fm10k_q_vector *q_vector;
+
+		entry--;
+		vector--;
+		q_vector = interface->q_vector[vector];
+
+		if (!q_vector->tx.count && !q_vector->rx.count)
+			continue;
+
+		/* clear the affinity_mask in the IRQ descriptor */
+		irq_set_affinity_hint(entry->vector, NULL);
+
+		/* disable interrupts */
+		writel(FM10K_ITR_MASK_SET, q_vector->itr);
+
+		free_irq(entry->vector, q_vector);
+	}
+
+	return err;
+}
+
+void fm10k_up(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* Enable Tx/Rx DMA */
+	hw->mac.ops.start_hw(hw);
+
+	/* configure Tx descriptor rings */
+	fm10k_configure_tx(interface);
+
+	/* configure Rx descriptor rings */
+	fm10k_configure_rx(interface);
+
+	/* configure interrupts */
+	hw->mac.ops.update_int_moderator(hw);
+
+	/* enable statistics capture again */
+	clear_bit(__FM10K_UPDATING_STATS, interface->state);
+
+	/* clear down bit to indicate we are ready to go */
+	clear_bit(__FM10K_DOWN, interface->state);
+
+	/* enable polling cleanups */
+	fm10k_napi_enable_all(interface);
+
+	/* re-establish Rx filters */
+	fm10k_restore_rx_state(interface);
+
+	/* enable transmits */
+	netif_tx_start_all_queues(interface->netdev);
+
+	/* kick off the service timer now */
+	hw->mac.get_host_state = true;
+	mod_timer(&interface->service_timer, jiffies);
+}
+
+static void fm10k_napi_disable_all(struct fm10k_intfc *interface)
+{
+	struct fm10k_q_vector *q_vector;
+	int q_idx;
+
+	for (q_idx = 0; q_idx < interface->num_q_vectors; q_idx++) {
+		q_vector = interface->q_vector[q_idx];
+		napi_disable(&q_vector->napi);
+	}
+}
+
+void fm10k_down(struct fm10k_intfc *interface)
+{
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int err, i = 0, count = 0;
+
+	/* signal that we are down to the interrupt handler and service task */
+	if (test_and_set_bit(__FM10K_DOWN, interface->state))
+		return;
+
+	/* call carrier off first to avoid false dev_watchdog timeouts */
+	netif_carrier_off(netdev);
+
+	/* disable transmits */
+	netif_tx_stop_all_queues(netdev);
+	netif_tx_disable(netdev);
+
+	/* reset Rx filters */
+	fm10k_reset_rx_state(interface);
+
+	/* disable polling routines */
+	fm10k_napi_disable_all(interface);
+
+	/* capture stats one last time before stopping interface */
+	fm10k_update_stats(interface);
+
+	/* prevent updating statistics while we're down */
+	while (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
+		usleep_range(1000, 2000);
+
+	/* skip waiting for TX DMA if we lost PCIe link */
+	if (FM10K_REMOVED(hw->hw_addr))
+		goto skip_tx_dma_drain;
+
+	/* In some rare circumstances it can take a while for Tx queues to
+	 * quiesce and be fully disabled. Attempt to .stop_hw() first, and
+	 * then if we get ERR_REQUESTS_PENDING, go ahead and wait in a loop
+	 * until the Tx queues have emptied, or until a number of retries. If
+	 * we fail to clear within the retry loop, we will issue a warning
+	 * indicating that Tx DMA is probably hung. Note this means we call
+	 * .stop_hw() twice but this shouldn't cause any problems.
+	 */
+	err = hw->mac.ops.stop_hw(hw);
+	if (err != FM10K_ERR_REQUESTS_PENDING)
+		goto skip_tx_dma_drain;
+
+#define TX_DMA_DRAIN_RETRIES 25
+	for (count = 0; count < TX_DMA_DRAIN_RETRIES; count++) {
+		usleep_range(10000, 20000);
+
+		/* start checking at the last ring to have pending Tx */
+		for (; i < interface->num_tx_queues; i++)
+			if (fm10k_get_tx_pending(interface->tx_ring[i], false))
+				break;
+
+		/* if all the queues are drained, we can break now */
+		if (i == interface->num_tx_queues)
+			break;
+	}
+
+	if (count >= TX_DMA_DRAIN_RETRIES)
+		dev_err(&interface->pdev->dev,
+			"Tx queues failed to drain after %d tries. Tx DMA is probably hung.\n",
+			count);
+skip_tx_dma_drain:
+	/* Disable DMA engine for Tx/Rx */
+	err = hw->mac.ops.stop_hw(hw);
+	if (err == FM10K_ERR_REQUESTS_PENDING)
+		dev_err(&interface->pdev->dev,
+			"due to pending requests hw was not shut down gracefully\n");
+	else if (err)
+		dev_err(&interface->pdev->dev, "stop_hw failed: %d\n", err);
+
+	/* free any buffers still on the rings */
+	fm10k_clean_all_tx_rings(interface);
+	fm10k_clean_all_rx_rings(interface);
+}
+
+/**
+ * fm10k_sw_init - Initialize general software structures
+ * @interface: host interface private structure to initialize
+ * @ent: PCI device ID entry
+ *
+ * fm10k_sw_init initializes the interface private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ **/
+static int fm10k_sw_init(struct fm10k_intfc *interface,
+			 const struct pci_device_id *ent)
+{
+	const struct fm10k_info *fi = fm10k_info_tbl[ent->driver_data];
+	struct fm10k_hw *hw = &interface->hw;
+	struct pci_dev *pdev = interface->pdev;
+	struct net_device *netdev = interface->netdev;
+	u32 rss_key[FM10K_RSSRK_SIZE];
+	unsigned int rss;
+	int err;
+
+	/* initialize back pointer */
+	hw->back = interface;
+	hw->hw_addr = interface->uc_addr;
+
+	/* 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;
+
+	/* Setup hw api */
+	memcpy(&hw->mac.ops, fi->mac_ops, sizeof(hw->mac.ops));
+	hw->mac.type = fi->mac;
+
+	/* Setup IOV handlers */
+	if (fi->iov_ops)
+		memcpy(&hw->iov.ops, fi->iov_ops, sizeof(hw->iov.ops));
+
+	/* Set common capability flags and settings */
+	rss = min_t(int, FM10K_MAX_RSS_INDICES, num_online_cpus());
+	interface->ring_feature[RING_F_RSS].limit = rss;
+	fi->get_invariants(hw);
+
+	/* pick up the PCIe bus settings for reporting later */
+	if (hw->mac.ops.get_bus_info)
+		hw->mac.ops.get_bus_info(hw);
+
+	/* limit the usable DMA range */
+	if (hw->mac.ops.set_dma_mask)
+		hw->mac.ops.set_dma_mask(hw, dma_get_mask(&pdev->dev));
+
+	/* update netdev with DMA restrictions */
+	if (dma_get_mask(&pdev->dev) > DMA_BIT_MASK(32)) {
+		netdev->features |= NETIF_F_HIGHDMA;
+		netdev->vlan_features |= NETIF_F_HIGHDMA;
+	}
+
+	/* reset and initialize the hardware so it is in a known state */
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&pdev->dev, "reset_hw failed: %d\n", err);
+		return err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
+	if (err) {
+		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
+		return err;
+	}
+
+	/* initialize hardware statistics */
+	hw->mac.ops.update_hw_stats(hw, &interface->stats);
+
+	/* Set upper limit on IOV VFs that can be allocated */
+	pci_sriov_set_totalvfs(pdev, hw->iov.total_vfs);
+
+	/* Start with random Ethernet address */
+	eth_random_addr(hw->mac.addr);
+
+	/* Initialize MAC address from hardware */
+	err = hw->mac.ops.read_mac_addr(hw);
+	if (err) {
+		dev_warn(&pdev->dev,
+			 "Failed to obtain MAC address defaulting to random\n");
+		/* tag address assignment as random */
+		netdev->addr_assign_type |= NET_ADDR_RANDOM;
+	}
+
+	eth_hw_addr_set(netdev, hw->mac.addr);
+	ether_addr_copy(netdev->perm_addr, hw->mac.addr);
+
+	if (!is_valid_ether_addr(netdev->perm_addr)) {
+		dev_err(&pdev->dev, "Invalid MAC Address\n");
+		return -EIO;
+	}
+
+	/* initialize DCBNL interface */
+	fm10k_dcbnl_set_ops(netdev);
+
+	/* set default ring sizes */
+	interface->tx_ring_count = FM10K_DEFAULT_TXD;
+	interface->rx_ring_count = FM10K_DEFAULT_RXD;
+
+	/* set default interrupt moderation */
+	interface->tx_itr = FM10K_TX_ITR_DEFAULT;
+	interface->rx_itr = FM10K_ITR_ADAPTIVE | FM10K_RX_ITR_DEFAULT;
+
+	/* Initialize the MAC/VLAN queue */
+	INIT_LIST_HEAD(&interface->macvlan_requests);
+
+	netdev_rss_key_fill(rss_key, sizeof(rss_key));
+	memcpy(interface->rssrk, rss_key, sizeof(rss_key));
+
+	/* Initialize the mailbox lock */
+	spin_lock_init(&interface->mbx_lock);
+	spin_lock_init(&interface->macvlan_lock);
+
+	/* Start off interface as being down */
+	set_bit(__FM10K_DOWN, interface->state);
+	set_bit(__FM10K_UPDATING_STATS, interface->state);
+
+	return 0;
+}
+
+/**
+ * fm10k_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in fm10k_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * fm10k_probe initializes an interface identified by a pci_dev structure.
+ * The OS initialization, configuring of the interface private structure,
+ * and a hardware reset occur.
+ **/
+static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct net_device *netdev;
+	struct fm10k_intfc *interface;
+	int err;
+
+	if (pdev->error_state != pci_channel_io_normal) {
+		dev_err(&pdev->dev,
+			"PCI device still in an error state. Unable to load...\n");
+		return -EIO;
+	}
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"PCI enable device failed: %d\n", err);
+		return err;
+	}
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
+	if (err)
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (err) {
+		dev_err(&pdev->dev,
+			"DMA configuration failed: %d\n", err);
+		goto err_dma;
+	}
+
+	err = pci_request_mem_regions(pdev, fm10k_driver_name);
+	if (err) {
+		dev_err(&pdev->dev,
+			"pci_request_selected_regions failed: %d\n", err);
+		goto err_pci_reg;
+	}
+
+	pci_enable_pcie_error_reporting(pdev);
+
+	pci_set_master(pdev);
+	pci_save_state(pdev);
+
+	netdev = fm10k_alloc_netdev(fm10k_info_tbl[ent->driver_data]);
+	if (!netdev) {
+		err = -ENOMEM;
+		goto err_alloc_netdev;
+	}
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+
+	interface = netdev_priv(netdev);
+	pci_set_drvdata(pdev, interface);
+
+	interface->netdev = netdev;
+	interface->pdev = pdev;
+
+	interface->uc_addr = ioremap(pci_resource_start(pdev, 0),
+				     FM10K_UC_ADDR_SIZE);
+	if (!interface->uc_addr) {
+		err = -EIO;
+		goto err_ioremap;
+	}
+
+	err = fm10k_sw_init(interface, ent);
+	if (err)
+		goto err_sw_init;
+
+	/* enable debugfs support */
+	fm10k_dbg_intfc_init(interface);
+
+	err = fm10k_init_queueing_scheme(interface);
+	if (err)
+		goto err_sw_init;
+
+	/* the mbx interrupt might attempt to schedule the service task, so we
+	 * must ensure it is disabled since we haven't yet requested the timer
+	 * or work item.
+	 */
+	set_bit(__FM10K_SERVICE_DISABLE, interface->state);
+
+	err = fm10k_mbx_request_irq(interface);
+	if (err)
+		goto err_mbx_interrupt;
+
+	/* final check of hardware state before registering the interface */
+	err = fm10k_hw_ready(interface);
+	if (err)
+		goto err_register;
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_register;
+
+	/* carrier off reporting is important to ethtool even BEFORE open */
+	netif_carrier_off(netdev);
+
+	/* stop all the transmit queues from transmitting until link is up */
+	netif_tx_stop_all_queues(netdev);
+
+	/* Initialize service timer and service task late in order to avoid
+	 * cleanup issues.
+	 */
+	timer_setup(&interface->service_timer, fm10k_service_timer, 0);
+	INIT_WORK(&interface->service_task, fm10k_service_task);
+
+	/* Setup the MAC/VLAN queue */
+	INIT_DELAYED_WORK(&interface->macvlan_task, fm10k_macvlan_task);
+
+	/* kick off service timer now, even when interface is down */
+	mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
+
+	/* print warning for non-optimal configurations */
+	pcie_print_link_status(interface->pdev);
+
+	/* report MAC address for logging */
+	dev_info(&pdev->dev, "%pM\n", netdev->dev_addr);
+
+	/* enable SR-IOV after registering netdev to enforce PF/VF ordering */
+	fm10k_iov_configure(pdev, 0);
+
+	/* clear the service task disable bit and kick off service task */
+	clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+	fm10k_service_event_schedule(interface);
+
+	return 0;
+
+err_register:
+	fm10k_mbx_free_irq(interface);
+err_mbx_interrupt:
+	fm10k_clear_queueing_scheme(interface);
+err_sw_init:
+	if (interface->sw_addr)
+		iounmap(interface->sw_addr);
+	iounmap(interface->uc_addr);
+err_ioremap:
+	free_netdev(netdev);
+err_alloc_netdev:
+	pci_disable_pcie_error_reporting(pdev);
+	pci_release_mem_regions(pdev);
+err_pci_reg:
+err_dma:
+	pci_disable_device(pdev);
+	return err;
+}
+
+/**
+ * fm10k_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * fm10k_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.  The could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ **/
+static void fm10k_remove(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct net_device *netdev = interface->netdev;
+
+	del_timer_sync(&interface->service_timer);
+
+	fm10k_stop_service_event(interface);
+	fm10k_stop_macvlan_task(interface);
+
+	/* Remove all pending MAC/VLAN requests */
+	fm10k_clear_macvlan_queue(interface, interface->glort, true);
+
+	/* free netdev, this may bounce the interrupts due to setup_tc */
+	if (netdev->reg_state == NETREG_REGISTERED)
+		unregister_netdev(netdev);
+
+	/* release VFs */
+	fm10k_iov_disable(pdev);
+
+	/* disable mailbox interrupt */
+	fm10k_mbx_free_irq(interface);
+
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
+	/* remove any debugfs interfaces */
+	fm10k_dbg_intfc_exit(interface);
+
+	if (interface->sw_addr)
+		iounmap(interface->sw_addr);
+	iounmap(interface->uc_addr);
+
+	free_netdev(netdev);
+
+	pci_release_mem_regions(pdev);
+
+	pci_disable_pcie_error_reporting(pdev);
+
+	pci_disable_device(pdev);
+}
+
+static void fm10k_prepare_suspend(struct fm10k_intfc *interface)
+{
+	/* the watchdog task reads from registers, which might appear like
+	 * a surprise remove if the PCIe device is disabled while we're
+	 * stopped. We stop the watchdog task until after we resume software
+	 * activity.
+	 *
+	 * Note that the MAC/VLAN task will be stopped as part of preparing
+	 * for reset so we don't need to handle it here.
+	 */
+	fm10k_stop_service_event(interface);
+
+	if (fm10k_prepare_for_reset(interface))
+		set_bit(__FM10K_RESET_SUSPENDED, interface->state);
+}
+
+static int fm10k_handle_resume(struct fm10k_intfc *interface)
+{
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	/* Even if we didn't properly prepare for reset in
+	 * fm10k_prepare_suspend, we'll attempt to resume anyways.
+	 */
+	if (!test_and_clear_bit(__FM10K_RESET_SUSPENDED, interface->state))
+		dev_warn(&interface->pdev->dev,
+			 "Device was shut down as part of suspend... Attempting to recover\n");
+
+	/* reset statistics starting values */
+	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
+
+	err = fm10k_handle_reset(interface);
+	if (err)
+		return err;
+
+	/* assume host is not ready, to prevent race with watchdog in case we
+	 * actually don't have connection to the switch
+	 */
+	interface->host_ready = false;
+	fm10k_watchdog_host_not_ready(interface);
+
+	/* force link to stay down for a second to prevent link flutter */
+	interface->link_down_event = jiffies + (HZ);
+	set_bit(__FM10K_LINK_DOWN, interface->state);
+
+	/* restart the service task */
+	fm10k_start_service_event(interface);
+
+	/* Restart the MAC/VLAN request queue in-case of outstanding events */
+	fm10k_macvlan_schedule(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_resume - Generic PM resume hook
+ * @dev: generic device structure
+ *
+ * Generic PM hook used when waking the device from a low power state after
+ * suspend or hibernation. This function does not need to handle lower PCIe
+ * device state as the stack takes care of that for us.
+ **/
+static int __maybe_unused fm10k_resume(struct device *dev)
+{
+	struct fm10k_intfc *interface = dev_get_drvdata(dev);
+	struct net_device *netdev = interface->netdev;
+	struct fm10k_hw *hw = &interface->hw;
+	int err;
+
+	/* refresh hw_addr in case it was dropped */
+	hw->hw_addr = interface->uc_addr;
+
+	err = fm10k_handle_resume(interface);
+	if (err)
+		return err;
+
+	netif_device_attach(netdev);
+
+	return 0;
+}
+
+/**
+ * fm10k_suspend - Generic PM suspend hook
+ * @dev: generic device structure
+ *
+ * Generic PM hook used when setting the device into a low power state for
+ * system suspend or hibernation. This function does not need to handle lower
+ * PCIe device state as the stack takes care of that for us.
+ **/
+static int __maybe_unused fm10k_suspend(struct device *dev)
+{
+	struct fm10k_intfc *interface = dev_get_drvdata(dev);
+	struct net_device *netdev = interface->netdev;
+
+	netif_device_detach(netdev);
+
+	fm10k_prepare_suspend(interface);
+
+	return 0;
+}
+
+/**
+ * fm10k_io_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
+ *
+ * This function is called after a PCI bus error affecting
+ * this device has been detected.
+ */
+static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev,
+						pci_channel_state_t state)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct net_device *netdev = interface->netdev;
+
+	netif_device_detach(netdev);
+
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	fm10k_prepare_suspend(interface);
+
+	/* Request a slot reset. */
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * fm10k_io_slot_reset - called after the pci bus has been reset.
+ * @pdev: Pointer to PCI device
+ *
+ * Restart the card from scratch, as if from a cold-boot.
+ */
+static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev)
+{
+	pci_ers_result_t result;
+
+	if (pci_reenable_device(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot re-enable PCI device after reset.\n");
+		result = PCI_ERS_RESULT_DISCONNECT;
+	} else {
+		pci_set_master(pdev);
+		pci_restore_state(pdev);
+
+		/* After second error pci->state_saved is false, this
+		 * resets it so EEH doesn't break.
+		 */
+		pci_save_state(pdev);
+
+		pci_wake_from_d3(pdev, false);
+
+		result = PCI_ERS_RESULT_RECOVERED;
+	}
+
+	return result;
+}
+
+/**
+ * fm10k_io_resume - called when traffic can start flowing again.
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the error recovery driver tells us that
+ * its OK to resume normal operation.
+ */
+static void fm10k_io_resume(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	struct net_device *netdev = interface->netdev;
+	int err;
+
+	err = fm10k_handle_resume(interface);
+
+	if (err)
+		dev_warn(&pdev->dev,
+			 "%s failed: %d\n", __func__, err);
+	else
+		netif_device_attach(netdev);
+}
+
+/**
+ * fm10k_io_reset_prepare - called when PCI function is about to be reset
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the PCI function is about to be reset,
+ * allowing the device driver to prepare for it.
+ */
+static void fm10k_io_reset_prepare(struct pci_dev *pdev)
+{
+	/* warn incase we have any active VF devices */
+	if (pci_num_vf(pdev))
+		dev_warn(&pdev->dev,
+			 "PCIe FLR may cause issues for any active VF devices\n");
+	fm10k_prepare_suspend(pci_get_drvdata(pdev));
+}
+
+/**
+ * fm10k_io_reset_done - called when PCI function has finished resetting
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called just after the PCI function is reset, such as via
+ * /sys/class/net/<enpX>/device/reset or similar.
+ */
+static void fm10k_io_reset_done(struct pci_dev *pdev)
+{
+	struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+	int err = fm10k_handle_resume(interface);
+
+	if (err) {
+		dev_warn(&pdev->dev,
+			 "%s failed: %d\n", __func__, err);
+		netif_device_detach(interface->netdev);
+	}
+}
+
+static const struct pci_error_handlers fm10k_err_handler = {
+	.error_detected = fm10k_io_error_detected,
+	.slot_reset = fm10k_io_slot_reset,
+	.resume = fm10k_io_resume,
+	.reset_prepare = fm10k_io_reset_prepare,
+	.reset_done = fm10k_io_reset_done,
+};
+
+static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume);
+
+static struct pci_driver fm10k_driver = {
+	.name			= fm10k_driver_name,
+	.id_table		= fm10k_pci_tbl,
+	.probe			= fm10k_probe,
+	.remove			= fm10k_remove,
+	.driver = {
+		.pm		= &fm10k_pm_ops,
+	},
+	.sriov_configure	= fm10k_iov_configure,
+	.err_handler		= &fm10k_err_handler
+};
+
+/**
+ * fm10k_register_pci_driver - register driver interface
+ *
+ * This function is called on module load in order to register the driver.
+ **/
+int fm10k_register_pci_driver(void)
+{
+	return pci_register_driver(&fm10k_driver);
+}
+
+/**
+ * fm10k_unregister_pci_driver - unregister driver interface
+ *
+ * This function is called on module unload in order to remove the driver.
+ **/
+void fm10k_unregister_pci_driver(void)
+{
+	pci_unregister_driver(&fm10k_driver);
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
new file mode 100644
index 000000000..af1b0cde3
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -0,0 +1,1825 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k_pf.h"
+#include "fm10k_vf.h"
+
+/**
+ *  fm10k_reset_hw_pf - PF hardware reset
+ *  @hw: pointer to hardware structure
+ *
+ *  This function should return the hardware to a state similar to the
+ *  one it is in after being powered on.
+ **/
+static s32 fm10k_reset_hw_pf(struct fm10k_hw *hw)
+{
+	s32 err;
+	u32 reg;
+	u16 i;
+
+	/* Disable interrupts */
+	fm10k_write_reg(hw, FM10K_EIMR, FM10K_EIMR_DISABLE(ALL));
+
+	/* Lock ITR2 reg 0 into itself and disable interrupt moderation */
+	fm10k_write_reg(hw, FM10K_ITR2(0), 0);
+	fm10k_write_reg(hw, FM10K_INT_CTRL, 0);
+
+	/* We assume here Tx and Rx queue 0 are owned by the PF */
+
+	/* Shut off VF access to their queues forcing them to queue 0 */
+	for (i = 0; i < FM10K_TQMAP_TABLE_SIZE; i++) {
+		fm10k_write_reg(hw, FM10K_TQMAP(i), 0);
+		fm10k_write_reg(hw, FM10K_RQMAP(i), 0);
+	}
+
+	/* shut down all rings */
+	err = fm10k_disable_queues_generic(hw, FM10K_MAX_QUEUES);
+	if (err == FM10K_ERR_REQUESTS_PENDING) {
+		hw->mac.reset_while_pending++;
+		goto force_reset;
+	} else if (err) {
+		return err;
+	}
+
+	/* Verify that DMA is no longer active */
+	reg = fm10k_read_reg(hw, FM10K_DMA_CTRL);
+	if (reg & (FM10K_DMA_CTRL_TX_ACTIVE | FM10K_DMA_CTRL_RX_ACTIVE))
+		return FM10K_ERR_DMA_PENDING;
+
+force_reset:
+	/* Inititate data path reset */
+	reg = FM10K_DMA_CTRL_DATAPATH_RESET;
+	fm10k_write_reg(hw, FM10K_DMA_CTRL, reg);
+
+	/* Flush write and allow 100us for reset to complete */
+	fm10k_write_flush(hw);
+	udelay(FM10K_RESET_TIMEOUT);
+
+	/* Verify we made it out of reset */
+	reg = fm10k_read_reg(hw, FM10K_IP);
+	if (!(reg & FM10K_IP_NOTINRESET))
+		return FM10K_ERR_RESET_FAILED;
+
+	return 0;
+}
+
+/**
+ *  fm10k_is_ari_hierarchy_pf - Indicate ARI hierarchy support
+ *  @hw: pointer to hardware structure
+ *
+ *  Looks at the ARI hierarchy bit to determine whether ARI is supported or not.
+ **/
+static bool fm10k_is_ari_hierarchy_pf(struct fm10k_hw *hw)
+{
+	u16 sriov_ctrl = fm10k_read_pci_cfg_word(hw, FM10K_PCIE_SRIOV_CTRL);
+
+	return !!(sriov_ctrl & FM10K_PCIE_SRIOV_CTRL_VFARI);
+}
+
+/**
+ *  fm10k_init_hw_pf - PF hardware initialization
+ *  @hw: pointer to hardware structure
+ *
+ **/
+static s32 fm10k_init_hw_pf(struct fm10k_hw *hw)
+{
+	u32 dma_ctrl, txqctl;
+	u16 i;
+
+	/* Establish default VSI as valid */
+	fm10k_write_reg(hw, FM10K_DGLORTDEC(fm10k_dglort_default), 0);
+	fm10k_write_reg(hw, FM10K_DGLORTMAP(fm10k_dglort_default),
+			FM10K_DGLORTMAP_ANY);
+
+	/* Invalidate all other GLORT entries */
+	for (i = 1; i < FM10K_DGLORT_COUNT; i++)
+		fm10k_write_reg(hw, FM10K_DGLORTMAP(i), FM10K_DGLORTMAP_NONE);
+
+	/* reset ITR2(0) to point to itself */
+	fm10k_write_reg(hw, FM10K_ITR2(0), 0);
+
+	/* reset VF ITR2(0) to point to 0 avoid PF registers */
+	fm10k_write_reg(hw, FM10K_ITR2(FM10K_ITR_REG_COUNT_PF), 0);
+
+	/* loop through all PF ITR2 registers pointing them to the previous */
+	for (i = 1; i < FM10K_ITR_REG_COUNT_PF; i++)
+		fm10k_write_reg(hw, FM10K_ITR2(i), i - 1);
+
+	/* Enable interrupt moderator if not already enabled */
+	fm10k_write_reg(hw, FM10K_INT_CTRL, FM10K_INT_CTRL_ENABLEMODERATOR);
+
+	/* compute the default txqctl configuration */
+	txqctl = FM10K_TXQCTL_PF | FM10K_TXQCTL_UNLIMITED_BW |
+		 (hw->mac.default_vid << FM10K_TXQCTL_VID_SHIFT);
+
+	for (i = 0; i < FM10K_MAX_QUEUES; i++) {
+		/* configure rings for 256 Queue / 32 Descriptor cache mode */
+		fm10k_write_reg(hw, FM10K_TQDLOC(i),
+				(i * FM10K_TQDLOC_BASE_32_DESC) |
+				FM10K_TQDLOC_SIZE_32_DESC);
+		fm10k_write_reg(hw, FM10K_TXQCTL(i), txqctl);
+
+		/* configure rings to provide TPH processing hints */
+		fm10k_write_reg(hw, FM10K_TPH_TXCTRL(i),
+				FM10K_TPH_TXCTRL_DESC_TPHEN |
+				FM10K_TPH_TXCTRL_DESC_RROEN |
+				FM10K_TPH_TXCTRL_DESC_WROEN |
+				FM10K_TPH_TXCTRL_DATA_RROEN);
+		fm10k_write_reg(hw, FM10K_TPH_RXCTRL(i),
+				FM10K_TPH_RXCTRL_DESC_TPHEN |
+				FM10K_TPH_RXCTRL_DESC_RROEN |
+				FM10K_TPH_RXCTRL_DATA_WROEN |
+				FM10K_TPH_RXCTRL_HDR_WROEN);
+	}
+
+	/* set max hold interval to align with 1.024 usec in all modes and
+	 * store ITR scale
+	 */
+	switch (hw->bus.speed) {
+	case fm10k_bus_speed_2500:
+		dma_ctrl = FM10K_DMA_CTRL_MAX_HOLD_1US_GEN1;
+		hw->mac.itr_scale = FM10K_TDLEN_ITR_SCALE_GEN1;
+		break;
+	case fm10k_bus_speed_5000:
+		dma_ctrl = FM10K_DMA_CTRL_MAX_HOLD_1US_GEN2;
+		hw->mac.itr_scale = FM10K_TDLEN_ITR_SCALE_GEN2;
+		break;
+	case fm10k_bus_speed_8000:
+		dma_ctrl = FM10K_DMA_CTRL_MAX_HOLD_1US_GEN3;
+		hw->mac.itr_scale = FM10K_TDLEN_ITR_SCALE_GEN3;
+		break;
+	default:
+		dma_ctrl = 0;
+		/* just in case, assume Gen3 ITR scale */
+		hw->mac.itr_scale = FM10K_TDLEN_ITR_SCALE_GEN3;
+		break;
+	}
+
+	/* Configure TSO flags */
+	fm10k_write_reg(hw, FM10K_DTXTCPFLGL, FM10K_TSO_FLAGS_LOW);
+	fm10k_write_reg(hw, FM10K_DTXTCPFLGH, FM10K_TSO_FLAGS_HI);
+
+	/* Enable DMA engine
+	 * Set Rx Descriptor size to 32
+	 * Set Minimum MSS to 64
+	 * Set Maximum number of Rx queues to 256 / 32 Descriptor
+	 */
+	dma_ctrl |= FM10K_DMA_CTRL_TX_ENABLE | FM10K_DMA_CTRL_RX_ENABLE |
+		    FM10K_DMA_CTRL_RX_DESC_SIZE | FM10K_DMA_CTRL_MINMSS_64 |
+		    FM10K_DMA_CTRL_32_DESC;
+
+	fm10k_write_reg(hw, FM10K_DMA_CTRL, dma_ctrl);
+
+	/* record maximum queue count, we limit ourselves to 128 */
+	hw->mac.max_queues = FM10K_MAX_QUEUES_PF;
+
+	/* We support either 64 VFs or 7 VFs depending on if we have ARI */
+	hw->iov.total_vfs = fm10k_is_ari_hierarchy_pf(hw) ? 64 : 7;
+
+	return 0;
+}
+
+/**
+ *  fm10k_update_vlan_pf - Update status of VLAN ID in VLAN filter table
+ *  @hw: pointer to hardware structure
+ *  @vid: VLAN ID to add to table
+ *  @vsi: Index indicating VF ID or PF ID in table
+ *  @set: Indicates if this is a set or clear operation
+ *
+ *  This function adds or removes the corresponding VLAN ID from the VLAN
+ *  filter table for the corresponding function.  In addition to the
+ *  standard set/clear that supports one bit a multi-bit write is
+ *  supported to set 64 bits at a time.
+ **/
+static s32 fm10k_update_vlan_pf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set)
+{
+	u32 vlan_table, reg, mask, bit, len;
+
+	/* verify the VSI index is valid */
+	if (vsi > FM10K_VLAN_TABLE_VSI_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* VLAN multi-bit write:
+	 * The multi-bit write has several parts to it.
+	 *               24              16               8               0
+	 *  7 6 5 4 3 2 1 0 7 6 5 4 3 2 1 0 7 6 5 4 3 2 1 0 7 6 5 4 3 2 1 0
+	 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+	 * | RSVD0 |         Length        |C|RSVD0|        VLAN ID        |
+	 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+	 *
+	 * VLAN ID: Vlan Starting value
+	 * RSVD0: Reserved section, must be 0
+	 * C: Flag field, 0 is set, 1 is clear (Used in VF VLAN message)
+	 * Length: Number of times to repeat the bit being set
+	 */
+	len = vid >> 16;
+	vid = (vid << 17) >> 17;
+
+	/* verify the reserved 0 fields are 0 */
+	if (len >= FM10K_VLAN_TABLE_VID_MAX || vid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* Loop through the table updating all required VLANs */
+	for (reg = FM10K_VLAN_TABLE(vsi, vid / 32), bit = vid % 32;
+	     len < FM10K_VLAN_TABLE_VID_MAX;
+	     len -= 32 - bit, reg++, bit = 0) {
+		/* record the initial state of the register */
+		vlan_table = fm10k_read_reg(hw, reg);
+
+		/* truncate mask if we are at the start or end of the run */
+		mask = (~(u32)0 >> ((len < 31) ? 31 - len : 0)) << bit;
+
+		/* make necessary modifications to the register */
+		mask &= set ? ~vlan_table : vlan_table;
+		if (mask)
+			fm10k_write_reg(hw, reg, vlan_table ^ mask);
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_read_mac_addr_pf - Read device MAC address
+ *  @hw: pointer to the HW structure
+ *
+ *  Reads the device MAC address from the SM_AREA and stores the value.
+ **/
+static s32 fm10k_read_mac_addr_pf(struct fm10k_hw *hw)
+{
+	u8 perm_addr[ETH_ALEN];
+	u32 serial_num;
+
+	serial_num = fm10k_read_reg(hw, FM10K_SM_AREA(1));
+
+	/* last byte should be all 1's */
+	if ((~serial_num) << 24)
+		return  FM10K_ERR_INVALID_MAC_ADDR;
+
+	perm_addr[0] = (u8)(serial_num >> 24);
+	perm_addr[1] = (u8)(serial_num >> 16);
+	perm_addr[2] = (u8)(serial_num >> 8);
+
+	serial_num = fm10k_read_reg(hw, FM10K_SM_AREA(0));
+
+	/* first byte should be all 1's */
+	if ((~serial_num) >> 24)
+		return  FM10K_ERR_INVALID_MAC_ADDR;
+
+	perm_addr[3] = (u8)(serial_num >> 16);
+	perm_addr[4] = (u8)(serial_num >> 8);
+	perm_addr[5] = (u8)(serial_num);
+
+	ether_addr_copy(hw->mac.perm_addr, perm_addr);
+	ether_addr_copy(hw->mac.addr, perm_addr);
+
+	return 0;
+}
+
+/**
+ *  fm10k_glort_valid_pf - Validate that the provided glort is valid
+ *  @hw: pointer to the HW structure
+ *  @glort: base glort to be validated
+ *
+ *  This function will return an error if the provided glort is invalid
+ **/
+bool fm10k_glort_valid_pf(struct fm10k_hw *hw, u16 glort)
+{
+	glort &= hw->mac.dglort_map >> FM10K_DGLORTMAP_MASK_SHIFT;
+
+	return glort == (hw->mac.dglort_map & FM10K_DGLORTMAP_NONE);
+}
+
+/**
+ *  fm10k_update_xc_addr_pf - Update device addresses
+ *  @hw: pointer to the HW structure
+ *  @glort: base resource tag for this request
+ *  @mac: MAC address to add/remove from table
+ *  @vid: VLAN ID to add/remove from table
+ *  @add: Indicates if this is an add or remove operation
+ *  @flags: flags field to indicate add and secure
+ *
+ *  This function generates a message to the Switch API requesting
+ *  that the given logical port add/remove the given L2 MAC/VLAN address.
+ **/
+static s32 fm10k_update_xc_addr_pf(struct fm10k_hw *hw, u16 glort,
+				   const u8 *mac, u16 vid, bool add, u8 flags)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	struct fm10k_mac_update mac_update;
+	u32 msg[5];
+
+	/* clear set bit from VLAN ID */
+	vid &= ~FM10K_VLAN_CLEAR;
+
+	/* if glort or VLAN are not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort) || vid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* record fields */
+	mac_update.mac_lower = cpu_to_le32(((u32)mac[2] << 24) |
+						 ((u32)mac[3] << 16) |
+						 ((u32)mac[4] << 8) |
+						 ((u32)mac[5]));
+	mac_update.mac_upper = cpu_to_le16(((u16)mac[0] << 8) |
+					   ((u16)mac[1]));
+	mac_update.vlan = cpu_to_le16(vid);
+	mac_update.glort = cpu_to_le16(glort);
+	mac_update.action = add ? 0 : 1;
+	mac_update.flags = flags;
+
+	/* populate mac_update fields */
+	fm10k_tlv_msg_init(msg, FM10K_PF_MSG_ID_UPDATE_MAC_FWD_RULE);
+	fm10k_tlv_attr_put_le_struct(msg, FM10K_PF_ATTR_ID_MAC_UPDATE,
+				     &mac_update, sizeof(mac_update));
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_uc_addr_pf - Update device unicast addresses
+ *  @hw: pointer to the HW structure
+ *  @glort: base resource tag for this request
+ *  @mac: MAC address to add/remove from table
+ *  @vid: VLAN ID to add/remove from table
+ *  @add: Indicates if this is an add or remove operation
+ *  @flags: flags field to indicate add and secure
+ *
+ *  This function is used to add or remove unicast addresses for
+ *  the PF.
+ **/
+static s32 fm10k_update_uc_addr_pf(struct fm10k_hw *hw, u16 glort,
+				   const u8 *mac, u16 vid, bool add, u8 flags)
+{
+	/* verify MAC address is valid */
+	if (!is_valid_ether_addr(mac))
+		return FM10K_ERR_PARAM;
+
+	return fm10k_update_xc_addr_pf(hw, glort, mac, vid, add, flags);
+}
+
+/**
+ *  fm10k_update_mc_addr_pf - Update device multicast addresses
+ *  @hw: pointer to the HW structure
+ *  @glort: base resource tag for this request
+ *  @mac: MAC address to add/remove from table
+ *  @vid: VLAN ID to add/remove from table
+ *  @add: Indicates if this is an add or remove operation
+ *
+ *  This function is used to add or remove multicast MAC addresses for
+ *  the PF.
+ **/
+static s32 fm10k_update_mc_addr_pf(struct fm10k_hw *hw, u16 glort,
+				   const u8 *mac, u16 vid, bool add)
+{
+	/* verify multicast address is valid */
+	if (!is_multicast_ether_addr(mac))
+		return FM10K_ERR_PARAM;
+
+	return fm10k_update_xc_addr_pf(hw, glort, mac, vid, add, 0);
+}
+
+/**
+ *  fm10k_update_xcast_mode_pf - Request update of multicast mode
+ *  @hw: pointer to hardware structure
+ *  @glort: base resource tag for this request
+ *  @mode: integer value indicating mode being requested
+ *
+ *  This function will attempt to request a higher mode for the port
+ *  so that it can enable either multicast, multicast promiscuous, or
+ *  promiscuous mode of operation.
+ **/
+static s32 fm10k_update_xcast_mode_pf(struct fm10k_hw *hw, u16 glort, u8 mode)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[3], xcast_mode;
+
+	if (mode > FM10K_XCAST_MODE_NONE)
+		return FM10K_ERR_PARAM;
+
+	/* if glort is not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort))
+		return FM10K_ERR_PARAM;
+
+	/* write xcast mode as a single u32 value,
+	 * lower 16 bits: glort
+	 * upper 16 bits: mode
+	 */
+	xcast_mode = ((u32)mode << 16) | glort;
+
+	/* generate message requesting to change xcast mode */
+	fm10k_tlv_msg_init(msg, FM10K_PF_MSG_ID_XCAST_MODES);
+	fm10k_tlv_attr_put_u32(msg, FM10K_PF_ATTR_ID_XCAST_MODE, xcast_mode);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_int_moderator_pf - Update interrupt moderator linked list
+ *  @hw: pointer to hardware structure
+ *
+ *  This function walks through the MSI-X vector table to determine the
+ *  number of active interrupts and based on that information updates the
+ *  interrupt moderator linked list.
+ **/
+static void fm10k_update_int_moderator_pf(struct fm10k_hw *hw)
+{
+	u32 i;
+
+	/* Disable interrupt moderator */
+	fm10k_write_reg(hw, FM10K_INT_CTRL, 0);
+
+	/* loop through PF from last to first looking enabled vectors */
+	for (i = FM10K_ITR_REG_COUNT_PF - 1; i; i--) {
+		if (!fm10k_read_reg(hw, FM10K_MSIX_VECTOR_MASK(i)))
+			break;
+	}
+
+	/* always reset VFITR2[0] to point to last enabled PF vector */
+	fm10k_write_reg(hw, FM10K_ITR2(FM10K_ITR_REG_COUNT_PF), i);
+
+	/* reset ITR2[0] to point to last enabled PF vector */
+	if (!hw->iov.num_vfs)
+		fm10k_write_reg(hw, FM10K_ITR2(0), i);
+
+	/* Enable interrupt moderator */
+	fm10k_write_reg(hw, FM10K_INT_CTRL, FM10K_INT_CTRL_ENABLEMODERATOR);
+}
+
+/**
+ *  fm10k_update_lport_state_pf - Notify the switch of a change in port state
+ *  @hw: pointer to the HW structure
+ *  @glort: base resource tag for this request
+ *  @count: number of logical ports being updated
+ *  @enable: boolean value indicating enable or disable
+ *
+ *  This function is used to add/remove a logical port from the switch.
+ **/
+static s32 fm10k_update_lport_state_pf(struct fm10k_hw *hw, u16 glort,
+				       u16 count, bool enable)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[3], lport_msg;
+
+	/* do nothing if we are being asked to create or destroy 0 ports */
+	if (!count)
+		return 0;
+
+	/* if glort is not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort))
+		return FM10K_ERR_PARAM;
+
+	/* reset multicast mode if deleting lport */
+	if (!enable)
+		fm10k_update_xcast_mode_pf(hw, glort, FM10K_XCAST_MODE_NONE);
+
+	/* construct the lport message from the 2 pieces of data we have */
+	lport_msg = ((u32)count << 16) | glort;
+
+	/* generate lport create/delete message */
+	fm10k_tlv_msg_init(msg, enable ? FM10K_PF_MSG_ID_LPORT_CREATE :
+					 FM10K_PF_MSG_ID_LPORT_DELETE);
+	fm10k_tlv_attr_put_u32(msg, FM10K_PF_ATTR_ID_PORT, lport_msg);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_configure_dglort_map_pf - Configures GLORT entry and queues
+ *  @hw: pointer to hardware structure
+ *  @dglort: pointer to dglort configuration structure
+ *
+ *  Reads the configuration structure contained in dglort_cfg and uses
+ *  that information to then populate a DGLORTMAP/DEC entry and the queues
+ *  to which it has been assigned.
+ **/
+static s32 fm10k_configure_dglort_map_pf(struct fm10k_hw *hw,
+					 struct fm10k_dglort_cfg *dglort)
+{
+	u16 glort, queue_count, vsi_count, pc_count;
+	u16 vsi, queue, pc, q_idx;
+	u32 txqctl, dglortdec, dglortmap;
+
+	/* verify the dglort pointer */
+	if (!dglort)
+		return FM10K_ERR_PARAM;
+
+	/* verify the dglort values */
+	if ((dglort->idx > 7) || (dglort->rss_l > 7) || (dglort->pc_l > 3) ||
+	    (dglort->vsi_l > 6) || (dglort->vsi_b > 64) ||
+	    (dglort->queue_l > 8) || (dglort->queue_b >= 256))
+		return FM10K_ERR_PARAM;
+
+	/* determine count of VSIs and queues */
+	queue_count = BIT(dglort->rss_l + dglort->pc_l);
+	vsi_count = BIT(dglort->vsi_l + dglort->queue_l);
+	glort = dglort->glort;
+	q_idx = dglort->queue_b;
+
+	/* configure SGLORT for queues */
+	for (vsi = 0; vsi < vsi_count; vsi++, glort++) {
+		for (queue = 0; queue < queue_count; queue++, q_idx++) {
+			if (q_idx >= FM10K_MAX_QUEUES)
+				break;
+
+			fm10k_write_reg(hw, FM10K_TX_SGLORT(q_idx), glort);
+			fm10k_write_reg(hw, FM10K_RX_SGLORT(q_idx), glort);
+		}
+	}
+
+	/* determine count of PCs and queues */
+	queue_count = BIT(dglort->queue_l + dglort->rss_l + dglort->vsi_l);
+	pc_count = BIT(dglort->pc_l);
+
+	/* configure PC for Tx queues */
+	for (pc = 0; pc < pc_count; pc++) {
+		q_idx = pc + dglort->queue_b;
+		for (queue = 0; queue < queue_count; queue++) {
+			if (q_idx >= FM10K_MAX_QUEUES)
+				break;
+
+			txqctl = fm10k_read_reg(hw, FM10K_TXQCTL(q_idx));
+			txqctl &= ~FM10K_TXQCTL_PC_MASK;
+			txqctl |= pc << FM10K_TXQCTL_PC_SHIFT;
+			fm10k_write_reg(hw, FM10K_TXQCTL(q_idx), txqctl);
+
+			q_idx += pc_count;
+		}
+	}
+
+	/* configure DGLORTDEC */
+	dglortdec = ((u32)(dglort->rss_l) << FM10K_DGLORTDEC_RSSLENGTH_SHIFT) |
+		    ((u32)(dglort->queue_b) << FM10K_DGLORTDEC_QBASE_SHIFT) |
+		    ((u32)(dglort->pc_l) << FM10K_DGLORTDEC_PCLENGTH_SHIFT) |
+		    ((u32)(dglort->vsi_b) << FM10K_DGLORTDEC_VSIBASE_SHIFT) |
+		    ((u32)(dglort->vsi_l) << FM10K_DGLORTDEC_VSILENGTH_SHIFT) |
+		    ((u32)(dglort->queue_l));
+	if (dglort->inner_rss)
+		dglortdec |=  FM10K_DGLORTDEC_INNERRSS_ENABLE;
+
+	/* configure DGLORTMAP */
+	dglortmap = (dglort->idx == fm10k_dglort_default) ?
+			FM10K_DGLORTMAP_ANY : FM10K_DGLORTMAP_ZERO;
+	dglortmap <<= dglort->vsi_l + dglort->queue_l + dglort->shared_l;
+	dglortmap |= dglort->glort;
+
+	/* write values to hardware */
+	fm10k_write_reg(hw, FM10K_DGLORTDEC(dglort->idx), dglortdec);
+	fm10k_write_reg(hw, FM10K_DGLORTMAP(dglort->idx), dglortmap);
+
+	return 0;
+}
+
+u16 fm10k_queues_per_pool(struct fm10k_hw *hw)
+{
+	u16 num_pools = hw->iov.num_pools;
+
+	return (num_pools > 32) ? 2 : (num_pools > 16) ? 4 : (num_pools > 8) ?
+	       8 : FM10K_MAX_QUEUES_POOL;
+}
+
+u16 fm10k_vf_queue_index(struct fm10k_hw *hw, u16 vf_idx)
+{
+	u16 num_vfs = hw->iov.num_vfs;
+	u16 vf_q_idx = FM10K_MAX_QUEUES;
+
+	vf_q_idx -= fm10k_queues_per_pool(hw) * (num_vfs - vf_idx);
+
+	return vf_q_idx;
+}
+
+static u16 fm10k_vectors_per_pool(struct fm10k_hw *hw)
+{
+	u16 num_pools = hw->iov.num_pools;
+
+	return (num_pools > 32) ? 8 : (num_pools > 16) ? 16 :
+	       FM10K_MAX_VECTORS_POOL;
+}
+
+static u16 fm10k_vf_vector_index(struct fm10k_hw *hw, u16 vf_idx)
+{
+	u16 vf_v_idx = FM10K_MAX_VECTORS_PF;
+
+	vf_v_idx += fm10k_vectors_per_pool(hw) * vf_idx;
+
+	return vf_v_idx;
+}
+
+/**
+ *  fm10k_iov_assign_resources_pf - Assign pool resources for virtualization
+ *  @hw: pointer to the HW structure
+ *  @num_vfs: number of VFs to be allocated
+ *  @num_pools: number of virtualization pools to be allocated
+ *
+ *  Allocates queues and traffic classes to virtualization entities to prepare
+ *  the PF for SR-IOV and VMDq
+ **/
+static s32 fm10k_iov_assign_resources_pf(struct fm10k_hw *hw, u16 num_vfs,
+					 u16 num_pools)
+{
+	u16 qmap_stride, qpp, vpp, vf_q_idx, vf_q_idx0, qmap_idx;
+	u32 vid = hw->mac.default_vid << FM10K_TXQCTL_VID_SHIFT;
+	int i, j;
+
+	/* hardware only supports up to 64 pools */
+	if (num_pools > 64)
+		return FM10K_ERR_PARAM;
+
+	/* the number of VFs cannot exceed the number of pools */
+	if ((num_vfs > num_pools) || (num_vfs > hw->iov.total_vfs))
+		return FM10K_ERR_PARAM;
+
+	/* record number of virtualization entities */
+	hw->iov.num_vfs = num_vfs;
+	hw->iov.num_pools = num_pools;
+
+	/* determine qmap offsets and counts */
+	qmap_stride = (num_vfs > 8) ? 32 : 256;
+	qpp = fm10k_queues_per_pool(hw);
+	vpp = fm10k_vectors_per_pool(hw);
+
+	/* calculate starting index for queues */
+	vf_q_idx = fm10k_vf_queue_index(hw, 0);
+	qmap_idx = 0;
+
+	/* establish TCs with -1 credits and no quanta to prevent transmit */
+	for (i = 0; i < num_vfs; i++) {
+		fm10k_write_reg(hw, FM10K_TC_MAXCREDIT(i), 0);
+		fm10k_write_reg(hw, FM10K_TC_RATE(i), 0);
+		fm10k_write_reg(hw, FM10K_TC_CREDIT(i),
+				FM10K_TC_CREDIT_CREDIT_MASK);
+	}
+
+	/* zero out all mbmem registers */
+	for (i = FM10K_VFMBMEM_LEN * num_vfs; i--;)
+		fm10k_write_reg(hw, FM10K_MBMEM(i), 0);
+
+	/* clear event notification of VF FLR */
+	fm10k_write_reg(hw, FM10K_PFVFLREC(0), ~0);
+	fm10k_write_reg(hw, FM10K_PFVFLREC(1), ~0);
+
+	/* loop through unallocated rings assigning them back to PF */
+	for (i = FM10K_MAX_QUEUES_PF; i < vf_q_idx; i++) {
+		fm10k_write_reg(hw, FM10K_TXDCTL(i), 0);
+		fm10k_write_reg(hw, FM10K_TXQCTL(i), FM10K_TXQCTL_PF |
+				FM10K_TXQCTL_UNLIMITED_BW | vid);
+		fm10k_write_reg(hw, FM10K_RXQCTL(i), FM10K_RXQCTL_PF);
+	}
+
+	/* PF should have already updated VFITR2[0] */
+
+	/* update all ITR registers to flow to VFITR2[0] */
+	for (i = FM10K_ITR_REG_COUNT_PF + 1; i < FM10K_ITR_REG_COUNT; i++) {
+		if (!(i & (vpp - 1)))
+			fm10k_write_reg(hw, FM10K_ITR2(i), i - vpp);
+		else
+			fm10k_write_reg(hw, FM10K_ITR2(i), i - 1);
+	}
+
+	/* update PF ITR2[0] to reference the last vector */
+	fm10k_write_reg(hw, FM10K_ITR2(0),
+			fm10k_vf_vector_index(hw, num_vfs - 1));
+
+	/* loop through rings populating rings and TCs */
+	for (i = 0; i < num_vfs; i++) {
+		/* record index for VF queue 0 for use in end of loop */
+		vf_q_idx0 = vf_q_idx;
+
+		for (j = 0; j < qpp; j++, qmap_idx++, vf_q_idx++) {
+			/* assign VF and locked TC to queues */
+			fm10k_write_reg(hw, FM10K_TXDCTL(vf_q_idx), 0);
+			fm10k_write_reg(hw, FM10K_TXQCTL(vf_q_idx),
+					(i << FM10K_TXQCTL_TC_SHIFT) | i |
+					FM10K_TXQCTL_VF | vid);
+			fm10k_write_reg(hw, FM10K_RXDCTL(vf_q_idx),
+					FM10K_RXDCTL_WRITE_BACK_MIN_DELAY |
+					FM10K_RXDCTL_DROP_ON_EMPTY);
+			fm10k_write_reg(hw, FM10K_RXQCTL(vf_q_idx),
+					(i << FM10K_RXQCTL_VF_SHIFT) |
+					FM10K_RXQCTL_VF);
+
+			/* map queue pair to VF */
+			fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx), vf_q_idx);
+			fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx), vf_q_idx);
+		}
+
+		/* repeat the first ring for all of the remaining VF rings */
+		for (; j < qmap_stride; j++, qmap_idx++) {
+			fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx), vf_q_idx0);
+			fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx), vf_q_idx0);
+		}
+	}
+
+	/* loop through remaining indexes assigning all to queue 0 */
+	while (qmap_idx < FM10K_TQMAP_TABLE_SIZE) {
+		fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx), 0);
+		fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx), 0);
+		qmap_idx++;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_iov_configure_tc_pf - Configure the shaping group for VF
+ *  @hw: pointer to the HW structure
+ *  @vf_idx: index of VF receiving GLORT
+ *  @rate: Rate indicated in Mb/s
+ *
+ *  Configured the TC for a given VF to allow only up to a given number
+ *  of Mb/s of outgoing Tx throughput.
+ **/
+static s32 fm10k_iov_configure_tc_pf(struct fm10k_hw *hw, u16 vf_idx, int rate)
+{
+	/* configure defaults */
+	u32 interval = FM10K_TC_RATE_INTERVAL_4US_GEN3;
+	u32 tc_rate = FM10K_TC_RATE_QUANTA_MASK;
+
+	/* verify vf is in range */
+	if (vf_idx >= hw->iov.num_vfs)
+		return FM10K_ERR_PARAM;
+
+	/* set interval to align with 4.096 usec in all modes */
+	switch (hw->bus.speed) {
+	case fm10k_bus_speed_2500:
+		interval = FM10K_TC_RATE_INTERVAL_4US_GEN1;
+		break;
+	case fm10k_bus_speed_5000:
+		interval = FM10K_TC_RATE_INTERVAL_4US_GEN2;
+		break;
+	default:
+		break;
+	}
+
+	if (rate) {
+		if (rate > FM10K_VF_TC_MAX || rate < FM10K_VF_TC_MIN)
+			return FM10K_ERR_PARAM;
+
+		/* The quanta is measured in Bytes per 4.096 or 8.192 usec
+		 * The rate is provided in Mbits per second
+		 * To tralslate from rate to quanta we need to multiply the
+		 * rate by 8.192 usec and divide by 8 bits/byte.  To avoid
+		 * dealing with floating point we can round the values up
+		 * to the nearest whole number ratio which gives us 128 / 125.
+		 */
+		tc_rate = (rate * 128) / 125;
+
+		/* try to keep the rate limiting accurate by increasing
+		 * the number of credits and interval for rates less than 4Gb/s
+		 */
+		if (rate < 4000)
+			interval <<= 1;
+		else
+			tc_rate >>= 1;
+	}
+
+	/* update rate limiter with new values */
+	fm10k_write_reg(hw, FM10K_TC_RATE(vf_idx), tc_rate | interval);
+	fm10k_write_reg(hw, FM10K_TC_MAXCREDIT(vf_idx), FM10K_TC_MAXCREDIT_64K);
+	fm10k_write_reg(hw, FM10K_TC_CREDIT(vf_idx), FM10K_TC_MAXCREDIT_64K);
+
+	return 0;
+}
+
+/**
+ *  fm10k_iov_assign_int_moderator_pf - Add VF interrupts to moderator list
+ *  @hw: pointer to the HW structure
+ *  @vf_idx: index of VF receiving GLORT
+ *
+ *  Update the interrupt moderator linked list to include any MSI-X
+ *  interrupts which the VF has enabled in the MSI-X vector table.
+ **/
+static s32 fm10k_iov_assign_int_moderator_pf(struct fm10k_hw *hw, u16 vf_idx)
+{
+	u16 vf_v_idx, vf_v_limit, i;
+
+	/* verify vf is in range */
+	if (vf_idx >= hw->iov.num_vfs)
+		return FM10K_ERR_PARAM;
+
+	/* determine vector offset and count */
+	vf_v_idx = fm10k_vf_vector_index(hw, vf_idx);
+	vf_v_limit = vf_v_idx + fm10k_vectors_per_pool(hw);
+
+	/* search for first vector that is not masked */
+	for (i = vf_v_limit - 1; i > vf_v_idx; i--) {
+		if (!fm10k_read_reg(hw, FM10K_MSIX_VECTOR_MASK(i)))
+			break;
+	}
+
+	/* reset linked list so it now includes our active vectors */
+	if (vf_idx == (hw->iov.num_vfs - 1))
+		fm10k_write_reg(hw, FM10K_ITR2(0), i);
+	else
+		fm10k_write_reg(hw, FM10K_ITR2(vf_v_limit), i);
+
+	return 0;
+}
+
+/**
+ *  fm10k_iov_assign_default_mac_vlan_pf - Assign a MAC and VLAN to VF
+ *  @hw: pointer to the HW structure
+ *  @vf_info: pointer to VF information structure
+ *
+ *  Assign a MAC address and default VLAN to a VF and notify it of the update
+ **/
+static s32 fm10k_iov_assign_default_mac_vlan_pf(struct fm10k_hw *hw,
+						struct fm10k_vf_info *vf_info)
+{
+	u16 qmap_stride, queues_per_pool, vf_q_idx, timeout, qmap_idx, i;
+	u32 msg[4], txdctl, txqctl, tdbal = 0, tdbah = 0;
+	s32 err = 0;
+	u16 vf_idx, vf_vid;
+
+	/* verify vf is in range */
+	if (!vf_info || vf_info->vf_idx >= hw->iov.num_vfs)
+		return FM10K_ERR_PARAM;
+
+	/* determine qmap offsets and counts */
+	qmap_stride = (hw->iov.num_vfs > 8) ? 32 : 256;
+	queues_per_pool = fm10k_queues_per_pool(hw);
+
+	/* calculate starting index for queues */
+	vf_idx = vf_info->vf_idx;
+	vf_q_idx = fm10k_vf_queue_index(hw, vf_idx);
+	qmap_idx = qmap_stride * vf_idx;
+
+	/* Determine correct default VLAN ID. The FM10K_VLAN_OVERRIDE bit is
+	 * used here to indicate to the VF that it will not have privilege to
+	 * write VLAN_TABLE. All policy is enforced on the PF but this allows
+	 * the VF to correctly report errors to userspace requests.
+	 */
+	if (vf_info->pf_vid)
+		vf_vid = vf_info->pf_vid | FM10K_VLAN_OVERRIDE;
+	else
+		vf_vid = vf_info->sw_vid;
+
+	/* generate MAC_ADDR request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_MAC_VLAN);
+	fm10k_tlv_attr_put_mac_vlan(msg, FM10K_MAC_VLAN_MSG_DEFAULT_MAC,
+				    vf_info->mac, vf_vid);
+
+	/* Configure Queue control register with new VLAN ID. The TXQCTL
+	 * register is RO from the VF, so the PF must do this even in the
+	 * case of notifying the VF of a new VID via the mailbox.
+	 */
+	txqctl = ((u32)vf_vid << FM10K_TXQCTL_VID_SHIFT) &
+		 FM10K_TXQCTL_VID_MASK;
+	txqctl |= (vf_idx << FM10K_TXQCTL_TC_SHIFT) |
+		  FM10K_TXQCTL_VF | vf_idx;
+
+	for (i = 0; i < queues_per_pool; i++)
+		fm10k_write_reg(hw, FM10K_TXQCTL(vf_q_idx + i), txqctl);
+
+	/* try loading a message onto outgoing mailbox first */
+	if (vf_info->mbx.ops.enqueue_tx) {
+		err = vf_info->mbx.ops.enqueue_tx(hw, &vf_info->mbx, msg);
+		if (err != FM10K_MBX_ERR_NO_MBX)
+			return err;
+		err = 0;
+	}
+
+	/* If we aren't connected to a mailbox, this is most likely because
+	 * the VF driver is not running. It should thus be safe to re-map
+	 * queues and use the registers to pass the MAC address so that the VF
+	 * driver gets correct information during its initialization.
+	 */
+
+	/* MAP Tx queue back to 0 temporarily, and disable it */
+	fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx), 0);
+	fm10k_write_reg(hw, FM10K_TXDCTL(vf_q_idx), 0);
+
+	/* verify ring has disabled before modifying base address registers */
+	txdctl = fm10k_read_reg(hw, FM10K_TXDCTL(vf_q_idx));
+	for (timeout = 0; txdctl & FM10K_TXDCTL_ENABLE; timeout++) {
+		/* limit ourselves to a 1ms timeout */
+		if (timeout == 10) {
+			err = FM10K_ERR_DMA_PENDING;
+			goto err_out;
+		}
+
+		usleep_range(100, 200);
+		txdctl = fm10k_read_reg(hw, FM10K_TXDCTL(vf_q_idx));
+	}
+
+	/* Update base address registers to contain MAC address */
+	if (is_valid_ether_addr(vf_info->mac)) {
+		tdbal = (((u32)vf_info->mac[3]) << 24) |
+			(((u32)vf_info->mac[4]) << 16) |
+			(((u32)vf_info->mac[5]) << 8);
+
+		tdbah = (((u32)0xFF)	        << 24) |
+			(((u32)vf_info->mac[0]) << 16) |
+			(((u32)vf_info->mac[1]) << 8) |
+			((u32)vf_info->mac[2]);
+	}
+
+	/* Record the base address into queue 0 */
+	fm10k_write_reg(hw, FM10K_TDBAL(vf_q_idx), tdbal);
+	fm10k_write_reg(hw, FM10K_TDBAH(vf_q_idx), tdbah);
+
+	/* Provide the VF the ITR scale, using software-defined fields in TDLEN
+	 * to pass the information during VF initialization. See definition of
+	 * FM10K_TDLEN_ITR_SCALE_SHIFT for more details.
+	 */
+	fm10k_write_reg(hw, FM10K_TDLEN(vf_q_idx), hw->mac.itr_scale <<
+						   FM10K_TDLEN_ITR_SCALE_SHIFT);
+
+err_out:
+	/* restore the queue back to VF ownership */
+	fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx), vf_q_idx);
+	return err;
+}
+
+/**
+ *  fm10k_iov_reset_resources_pf - Reassign queues and interrupts to a VF
+ *  @hw: pointer to the HW structure
+ *  @vf_info: pointer to VF information structure
+ *
+ *  Reassign the interrupts and queues to a VF following an FLR
+ **/
+static s32 fm10k_iov_reset_resources_pf(struct fm10k_hw *hw,
+					struct fm10k_vf_info *vf_info)
+{
+	u16 qmap_stride, queues_per_pool, vf_q_idx, qmap_idx;
+	u32 tdbal = 0, tdbah = 0, txqctl, rxqctl;
+	u16 vf_v_idx, vf_v_limit, vf_vid;
+	u8 vf_idx = vf_info->vf_idx;
+	int i;
+
+	/* verify vf is in range */
+	if (vf_idx >= hw->iov.num_vfs)
+		return FM10K_ERR_PARAM;
+
+	/* clear event notification of VF FLR */
+	fm10k_write_reg(hw, FM10K_PFVFLREC(vf_idx / 32), BIT(vf_idx % 32));
+
+	/* force timeout and then disconnect the mailbox */
+	vf_info->mbx.timeout = 0;
+	if (vf_info->mbx.ops.disconnect)
+		vf_info->mbx.ops.disconnect(hw, &vf_info->mbx);
+
+	/* determine vector offset and count */
+	vf_v_idx = fm10k_vf_vector_index(hw, vf_idx);
+	vf_v_limit = vf_v_idx + fm10k_vectors_per_pool(hw);
+
+	/* determine qmap offsets and counts */
+	qmap_stride = (hw->iov.num_vfs > 8) ? 32 : 256;
+	queues_per_pool = fm10k_queues_per_pool(hw);
+	qmap_idx = qmap_stride * vf_idx;
+
+	/* make all the queues inaccessible to the VF */
+	for (i = qmap_idx; i < (qmap_idx + qmap_stride); i++) {
+		fm10k_write_reg(hw, FM10K_TQMAP(i), 0);
+		fm10k_write_reg(hw, FM10K_RQMAP(i), 0);
+	}
+
+	/* calculate starting index for queues */
+	vf_q_idx = fm10k_vf_queue_index(hw, vf_idx);
+
+	/* determine correct default VLAN ID */
+	if (vf_info->pf_vid)
+		vf_vid = vf_info->pf_vid;
+	else
+		vf_vid = vf_info->sw_vid;
+
+	/* configure Queue control register */
+	txqctl = ((u32)vf_vid << FM10K_TXQCTL_VID_SHIFT) |
+		 (vf_idx << FM10K_TXQCTL_TC_SHIFT) |
+		 FM10K_TXQCTL_VF | vf_idx;
+	rxqctl = (vf_idx << FM10K_RXQCTL_VF_SHIFT) | FM10K_RXQCTL_VF;
+
+	/* stop further DMA and reset queue ownership back to VF */
+	for (i = vf_q_idx; i < (queues_per_pool + vf_q_idx); i++) {
+		fm10k_write_reg(hw, FM10K_TXDCTL(i), 0);
+		fm10k_write_reg(hw, FM10K_TXQCTL(i), txqctl);
+		fm10k_write_reg(hw, FM10K_RXDCTL(i),
+				FM10K_RXDCTL_WRITE_BACK_MIN_DELAY |
+				FM10K_RXDCTL_DROP_ON_EMPTY);
+		fm10k_write_reg(hw, FM10K_RXQCTL(i), rxqctl);
+	}
+
+	/* reset TC with -1 credits and no quanta to prevent transmit */
+	fm10k_write_reg(hw, FM10K_TC_MAXCREDIT(vf_idx), 0);
+	fm10k_write_reg(hw, FM10K_TC_RATE(vf_idx), 0);
+	fm10k_write_reg(hw, FM10K_TC_CREDIT(vf_idx),
+			FM10K_TC_CREDIT_CREDIT_MASK);
+
+	/* update our first entry in the table based on previous VF */
+	if (!vf_idx)
+		hw->mac.ops.update_int_moderator(hw);
+	else
+		hw->iov.ops.assign_int_moderator(hw, vf_idx - 1);
+
+	/* reset linked list so it now includes our active vectors */
+	if (vf_idx == (hw->iov.num_vfs - 1))
+		fm10k_write_reg(hw, FM10K_ITR2(0), vf_v_idx);
+	else
+		fm10k_write_reg(hw, FM10K_ITR2(vf_v_limit), vf_v_idx);
+
+	/* link remaining vectors so that next points to previous */
+	for (vf_v_idx++; vf_v_idx < vf_v_limit; vf_v_idx++)
+		fm10k_write_reg(hw, FM10K_ITR2(vf_v_idx), vf_v_idx - 1);
+
+	/* zero out MBMEM, VLAN_TABLE, RETA, RSSRK, and MRQC registers */
+	for (i = FM10K_VFMBMEM_LEN; i--;)
+		fm10k_write_reg(hw, FM10K_MBMEM_VF(vf_idx, i), 0);
+	for (i = FM10K_VLAN_TABLE_SIZE; i--;)
+		fm10k_write_reg(hw, FM10K_VLAN_TABLE(vf_info->vsi, i), 0);
+	for (i = FM10K_RETA_SIZE; i--;)
+		fm10k_write_reg(hw, FM10K_RETA(vf_info->vsi, i), 0);
+	for (i = FM10K_RSSRK_SIZE; i--;)
+		fm10k_write_reg(hw, FM10K_RSSRK(vf_info->vsi, i), 0);
+	fm10k_write_reg(hw, FM10K_MRQC(vf_info->vsi), 0);
+
+	/* Update base address registers to contain MAC address */
+	if (is_valid_ether_addr(vf_info->mac)) {
+		tdbal = (((u32)vf_info->mac[3]) << 24) |
+			(((u32)vf_info->mac[4]) << 16) |
+			(((u32)vf_info->mac[5]) << 8);
+		tdbah = (((u32)0xFF)	   << 24) |
+			(((u32)vf_info->mac[0]) << 16) |
+			(((u32)vf_info->mac[1]) << 8) |
+			((u32)vf_info->mac[2]);
+	}
+
+	/* map queue pairs back to VF from last to first */
+	for (i = queues_per_pool; i--;) {
+		fm10k_write_reg(hw, FM10K_TDBAL(vf_q_idx + i), tdbal);
+		fm10k_write_reg(hw, FM10K_TDBAH(vf_q_idx + i), tdbah);
+		/* See definition of FM10K_TDLEN_ITR_SCALE_SHIFT for an
+		 * explanation of how TDLEN is used.
+		 */
+		fm10k_write_reg(hw, FM10K_TDLEN(vf_q_idx + i),
+				hw->mac.itr_scale <<
+				FM10K_TDLEN_ITR_SCALE_SHIFT);
+		fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx + i), vf_q_idx + i);
+		fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx + i), vf_q_idx + i);
+	}
+
+	/* repeat the first ring for all the remaining VF rings */
+	for (i = queues_per_pool; i < qmap_stride; i++) {
+		fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx + i), vf_q_idx);
+		fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx + i), vf_q_idx);
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_iov_set_lport_pf - Assign and enable a logical port for a given VF
+ *  @hw: pointer to hardware structure
+ *  @vf_info: pointer to VF information structure
+ *  @lport_idx: Logical port offset from the hardware glort
+ *  @flags: Set of capability flags to extend port beyond basic functionality
+ *
+ *  This function allows enabling a VF port by assigning it a GLORT and
+ *  setting the flags so that it can enable an Rx mode.
+ **/
+static s32 fm10k_iov_set_lport_pf(struct fm10k_hw *hw,
+				  struct fm10k_vf_info *vf_info,
+				  u16 lport_idx, u8 flags)
+{
+	u16 glort = (hw->mac.dglort_map + lport_idx) & FM10K_DGLORTMAP_NONE;
+
+	/* if glort is not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort))
+		return FM10K_ERR_PARAM;
+
+	vf_info->vf_flags = flags | FM10K_VF_FLAG_NONE_CAPABLE;
+	vf_info->glort = glort;
+
+	return 0;
+}
+
+/**
+ *  fm10k_iov_reset_lport_pf - Disable a logical port for a given VF
+ *  @hw: pointer to hardware structure
+ *  @vf_info: pointer to VF information structure
+ *
+ *  This function disables a VF port by stripping it of a GLORT and
+ *  setting the flags so that it cannot enable any Rx mode.
+ **/
+static void fm10k_iov_reset_lport_pf(struct fm10k_hw *hw,
+				     struct fm10k_vf_info *vf_info)
+{
+	u32 msg[1];
+
+	/* need to disable the port if it is already enabled */
+	if (FM10K_VF_FLAG_ENABLED(vf_info)) {
+		/* notify switch that this port has been disabled */
+		fm10k_update_lport_state_pf(hw, vf_info->glort, 1, false);
+
+		/* generate port state response to notify VF it is not ready */
+		fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_LPORT_STATE);
+		vf_info->mbx.ops.enqueue_tx(hw, &vf_info->mbx, msg);
+	}
+
+	/* clear flags and glort if it exists */
+	vf_info->vf_flags = 0;
+	vf_info->glort = 0;
+}
+
+/**
+ *  fm10k_iov_update_stats_pf - Updates hardware related statistics for VFs
+ *  @hw: pointer to hardware structure
+ *  @q: stats for all queues of a VF
+ *  @vf_idx: index of VF
+ *
+ *  This function collects queue stats for VFs.
+ **/
+static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw,
+				      struct fm10k_hw_stats_q *q,
+				      u16 vf_idx)
+{
+	u32 idx, qpp;
+
+	/* get stats for all of the queues */
+	qpp = fm10k_queues_per_pool(hw);
+	idx = fm10k_vf_queue_index(hw, vf_idx);
+	fm10k_update_hw_stats_q(hw, q, idx, qpp);
+}
+
+/**
+ *  fm10k_iov_msg_msix_pf - Message handler for MSI-X request from VF
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function is a default handler for MSI-X requests from the VF. The
+ *  assumption is that in this case it is acceptable to just directly
+ *  hand off the message from the VF to the underlying shared code.
+ **/
+s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results,
+			  struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	u8 vf_idx = vf_info->vf_idx;
+
+	return hw->iov.ops.assign_int_moderator(hw, vf_idx);
+}
+
+/**
+ * fm10k_iov_select_vid - Select correct default VLAN ID
+ * @vf_info: pointer to VF information structure
+ * @vid: VLAN ID to correct
+ *
+ * Will report an error if the VLAN ID is out of range. For VID = 0, it will
+ * return either the pf_vid or sw_vid depending on which one is set.
+ */
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
+{
+	if (!vid)
+		return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid;
+	else if (vf_info->pf_vid && vid != vf_info->pf_vid)
+		return FM10K_ERR_PARAM;
+	else
+		return vid;
+}
+
+/**
+ *  fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function is a default handler for MAC/VLAN requests from the VF.
+ *  The assumption is that in this case it is acceptable to just directly
+ *  hand off the message from the VF to the underlying shared code.
+ **/
+s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results,
+			      struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	u8 mac[ETH_ALEN];
+	u32 *result;
+	int err = 0;
+	bool set;
+	u16 vlan;
+	u32 vid;
+
+	/* we shouldn't be updating rules on a disabled interface */
+	if (!FM10K_VF_FLAG_ENABLED(vf_info))
+		err = FM10K_ERR_PARAM;
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
+		result = results[FM10K_MAC_VLAN_MSG_VLAN];
+
+		/* record VLAN id requested */
+		err = fm10k_tlv_attr_get_u32(result, &vid);
+		if (err)
+			return err;
+
+		set = !(vid & FM10K_VLAN_CLEAR);
+		vid &= ~FM10K_VLAN_CLEAR;
+
+		/* if the length field has been set, this is a multi-bit
+		 * update request. For multi-bit requests, simply disallow
+		 * them when the pf_vid has been set. In this case, the PF
+		 * should have already cleared the VLAN_TABLE, and if we
+		 * allowed them, it could allow a rogue VF to receive traffic
+		 * on a VLAN it was not assigned. In the single-bit case, we
+		 * need to modify requests for VLAN 0 to use the default PF or
+		 * SW vid when assigned.
+		 */
+
+		if (vid >> 16) {
+			/* prevent multi-bit requests when PF has
+			 * administratively set the VLAN for this VF
+			 */
+			if (vf_info->pf_vid)
+				return FM10K_ERR_PARAM;
+		} else {
+			err = fm10k_iov_select_vid(vf_info, (u16)vid);
+			if (err < 0)
+				return err;
+
+			vid = err;
+		}
+
+		/* update VSI info for VF in regards to VLAN table */
+		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
+		result = results[FM10K_MAC_VLAN_MSG_MAC];
+
+		/* record unicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* block attempts to set MAC for a locked device */
+		if (is_valid_ether_addr(vf_info->mac) &&
+		    !ether_addr_equal(mac, vf_info->mac))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* notify switch of request for new unicast address */
+		err = hw->mac.ops.update_uc_addr(hw, vf_info->glort,
+						 mac, vlan, set, 0);
+	}
+
+	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
+		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
+
+		/* record multicast MAC address requested */
+		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+		if (err)
+			return err;
+
+		/* verify that the VF is allowed to request multicast */
+		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
+			return FM10K_ERR_PARAM;
+
+		set = !(vlan & FM10K_VLAN_CLEAR);
+		vlan &= ~FM10K_VLAN_CLEAR;
+
+		err = fm10k_iov_select_vid(vf_info, vlan);
+		if (err < 0)
+			return err;
+
+		vlan = (u16)err;
+
+		/* notify switch of request for new multicast address */
+		err = hw->mac.ops.update_mc_addr(hw, vf_info->glort,
+						 mac, vlan, set);
+	}
+
+	return err;
+}
+
+/**
+ *  fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode
+ *  @vf_info: VF info structure containing capability flags
+ *  @mode: Requested xcast mode
+ *
+ *  This function outputs the mode that most closely matches the requested
+ *  mode.  If not modes match it will request we disable the port
+ **/
+static u8 fm10k_iov_supported_xcast_mode_pf(struct fm10k_vf_info *vf_info,
+					    u8 mode)
+{
+	u8 vf_flags = vf_info->vf_flags;
+
+	/* match up mode to capabilities as best as possible */
+	switch (mode) {
+	case FM10K_XCAST_MODE_PROMISC:
+		if (vf_flags & FM10K_VF_FLAG_PROMISC_CAPABLE)
+			return FM10K_XCAST_MODE_PROMISC;
+		fallthrough;
+	case FM10K_XCAST_MODE_ALLMULTI:
+		if (vf_flags & FM10K_VF_FLAG_ALLMULTI_CAPABLE)
+			return FM10K_XCAST_MODE_ALLMULTI;
+		fallthrough;
+	case FM10K_XCAST_MODE_MULTI:
+		if (vf_flags & FM10K_VF_FLAG_MULTI_CAPABLE)
+			return FM10K_XCAST_MODE_MULTI;
+		fallthrough;
+	case FM10K_XCAST_MODE_NONE:
+		if (vf_flags & FM10K_VF_FLAG_NONE_CAPABLE)
+			return FM10K_XCAST_MODE_NONE;
+		fallthrough;
+	default:
+		break;
+	}
+
+	/* disable interface as it should not be able to request any */
+	return FM10K_XCAST_MODE_DISABLE;
+}
+
+/**
+ *  fm10k_iov_msg_lport_state_pf - Message handler for port state requests
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function is a default handler for port state requests.  The port
+ *  state requests for now are basic and consist of enabling or disabling
+ *  the port.
+ **/
+s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results,
+				 struct fm10k_mbx_info *mbx)
+{
+	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+	s32 err = 0;
+	u32 msg[2];
+	u8 mode = 0;
+
+	/* verify VF is allowed to enable even minimal mode */
+	if (!(vf_info->vf_flags & FM10K_VF_FLAG_NONE_CAPABLE))
+		return FM10K_ERR_PARAM;
+
+	if (!!results[FM10K_LPORT_STATE_MSG_XCAST_MODE]) {
+		u32 *result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE];
+
+		/* XCAST mode update requested */
+		err = fm10k_tlv_attr_get_u8(result, &mode);
+		if (err)
+			return FM10K_ERR_PARAM;
+
+		/* prep for possible demotion depending on capabilities */
+		mode = fm10k_iov_supported_xcast_mode_pf(vf_info, mode);
+
+		/* if mode is not currently enabled, enable it */
+		if (!(FM10K_VF_FLAG_ENABLED(vf_info) & BIT(mode)))
+			fm10k_update_xcast_mode_pf(hw, vf_info->glort, mode);
+
+		/* swap mode back to a bit flag */
+		mode = FM10K_VF_FLAG_SET_MODE(mode);
+	} else if (!results[FM10K_LPORT_STATE_MSG_DISABLE]) {
+		/* need to disable the port if it is already enabled */
+		if (FM10K_VF_FLAG_ENABLED(vf_info))
+			err = fm10k_update_lport_state_pf(hw, vf_info->glort,
+							  1, false);
+
+		/* we need to clear VF_FLAG_ENABLED flags in order to ensure
+		 * that we actually re-enable the LPORT state below. Note that
+		 * this has no impact if the VF is already disabled, as the
+		 * flags are already cleared.
+		 */
+		if (!err)
+			vf_info->vf_flags = FM10K_VF_FLAG_CAPABLE(vf_info);
+
+		/* when enabling the port we should reset the rate limiters */
+		hw->iov.ops.configure_tc(hw, vf_info->vf_idx, vf_info->rate);
+
+		/* set mode for minimal functionality */
+		mode = FM10K_VF_FLAG_SET_MODE_NONE;
+
+		/* generate port state response to notify VF it is ready */
+		fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_LPORT_STATE);
+		fm10k_tlv_attr_put_bool(msg, FM10K_LPORT_STATE_MSG_READY);
+		mbx->ops.enqueue_tx(hw, mbx, msg);
+	}
+
+	/* if enable state toggled note the update */
+	if (!err && (!FM10K_VF_FLAG_ENABLED(vf_info) != !mode))
+		err = fm10k_update_lport_state_pf(hw, vf_info->glort, 1,
+						  !!mode);
+
+	/* if state change succeeded, then update our stored state */
+	mode |= FM10K_VF_FLAG_CAPABLE(vf_info);
+	if (!err)
+		vf_info->vf_flags = mode;
+
+	return err;
+}
+
+/**
+ *  fm10k_update_hw_stats_pf - Updates hardware related statistics of PF
+ *  @hw: pointer to hardware structure
+ *  @stats: pointer to the stats structure to update
+ *
+ *  This function collects and aggregates global and per queue hardware
+ *  statistics.
+ **/
+static void fm10k_update_hw_stats_pf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats)
+{
+	u32 timeout, ur, ca, um, xec, vlan_drop, loopback_drop, nodesc_drop;
+	u32 id, id_prev;
+
+	/* Use Tx queue 0 as a canary to detect a reset */
+	id = fm10k_read_reg(hw, FM10K_TXQCTL(0));
+
+	/* Read Global Statistics */
+	do {
+		timeout = fm10k_read_hw_stats_32b(hw, FM10K_STATS_TIMEOUT,
+						  &stats->timeout);
+		ur = fm10k_read_hw_stats_32b(hw, FM10K_STATS_UR, &stats->ur);
+		ca = fm10k_read_hw_stats_32b(hw, FM10K_STATS_CA, &stats->ca);
+		um = fm10k_read_hw_stats_32b(hw, FM10K_STATS_UM, &stats->um);
+		xec = fm10k_read_hw_stats_32b(hw, FM10K_STATS_XEC, &stats->xec);
+		vlan_drop = fm10k_read_hw_stats_32b(hw, FM10K_STATS_VLAN_DROP,
+						    &stats->vlan_drop);
+		loopback_drop =
+			fm10k_read_hw_stats_32b(hw,
+						FM10K_STATS_LOOPBACK_DROP,
+						&stats->loopback_drop);
+		nodesc_drop = fm10k_read_hw_stats_32b(hw,
+						      FM10K_STATS_NODESC_DROP,
+						      &stats->nodesc_drop);
+
+		/* if value has not changed then we have consistent data */
+		id_prev = id;
+		id = fm10k_read_reg(hw, FM10K_TXQCTL(0));
+	} while ((id ^ id_prev) & FM10K_TXQCTL_ID_MASK);
+
+	/* drop non-ID bits and set VALID ID bit */
+	id &= FM10K_TXQCTL_ID_MASK;
+	id |= FM10K_STAT_VALID;
+
+	/* Update Global Statistics */
+	if (stats->stats_idx == id) {
+		stats->timeout.count += timeout;
+		stats->ur.count += ur;
+		stats->ca.count += ca;
+		stats->um.count += um;
+		stats->xec.count += xec;
+		stats->vlan_drop.count += vlan_drop;
+		stats->loopback_drop.count += loopback_drop;
+		stats->nodesc_drop.count += nodesc_drop;
+	}
+
+	/* Update bases and record current PF id */
+	fm10k_update_hw_base_32b(&stats->timeout, timeout);
+	fm10k_update_hw_base_32b(&stats->ur, ur);
+	fm10k_update_hw_base_32b(&stats->ca, ca);
+	fm10k_update_hw_base_32b(&stats->um, um);
+	fm10k_update_hw_base_32b(&stats->xec, xec);
+	fm10k_update_hw_base_32b(&stats->vlan_drop, vlan_drop);
+	fm10k_update_hw_base_32b(&stats->loopback_drop, loopback_drop);
+	fm10k_update_hw_base_32b(&stats->nodesc_drop, nodesc_drop);
+	stats->stats_idx = id;
+
+	/* Update Queue Statistics */
+	fm10k_update_hw_stats_q(hw, stats->q, 0, hw->mac.max_queues);
+}
+
+/**
+ *  fm10k_rebind_hw_stats_pf - Resets base for hardware statistics of PF
+ *  @hw: pointer to hardware structure
+ *  @stats: pointer to the stats structure to update
+ *
+ *  This function resets the base for global and per queue hardware
+ *  statistics.
+ **/
+static void fm10k_rebind_hw_stats_pf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats)
+{
+	/* Unbind Global Statistics */
+	fm10k_unbind_hw_stats_32b(&stats->timeout);
+	fm10k_unbind_hw_stats_32b(&stats->ur);
+	fm10k_unbind_hw_stats_32b(&stats->ca);
+	fm10k_unbind_hw_stats_32b(&stats->um);
+	fm10k_unbind_hw_stats_32b(&stats->xec);
+	fm10k_unbind_hw_stats_32b(&stats->vlan_drop);
+	fm10k_unbind_hw_stats_32b(&stats->loopback_drop);
+	fm10k_unbind_hw_stats_32b(&stats->nodesc_drop);
+
+	/* Unbind Queue Statistics */
+	fm10k_unbind_hw_stats_q(stats->q, 0, hw->mac.max_queues);
+
+	/* Reinitialize bases for all stats */
+	fm10k_update_hw_stats_pf(hw, stats);
+}
+
+/**
+ *  fm10k_set_dma_mask_pf - Configures PhyAddrSpace to limit DMA to system
+ *  @hw: pointer to hardware structure
+ *  @dma_mask: 64 bit DMA mask required for platform
+ *
+ *  This function sets the PHYADDR.PhyAddrSpace bits for the endpoint in order
+ *  to limit the access to memory beyond what is physically in the system.
+ **/
+static void fm10k_set_dma_mask_pf(struct fm10k_hw *hw, u64 dma_mask)
+{
+	/* we need to write the upper 32 bits of DMA mask to PhyAddrSpace */
+	u32 phyaddr = (u32)(dma_mask >> 32);
+
+	fm10k_write_reg(hw, FM10K_PHYADDR, phyaddr);
+}
+
+/**
+ *  fm10k_get_fault_pf - Record a fault in one of the interface units
+ *  @hw: pointer to hardware structure
+ *  @type: pointer to fault type register offset
+ *  @fault: pointer to memory location to record the fault
+ *
+ *  Record the fault register contents to the fault data structure and
+ *  clear the entry from the register.
+ *
+ *  Returns ERR_PARAM if invalid register is specified or no error is present.
+ **/
+static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type,
+			      struct fm10k_fault *fault)
+{
+	u32 func;
+
+	/* verify the fault register is in range and is aligned */
+	switch (type) {
+	case FM10K_PCA_FAULT:
+	case FM10K_THI_FAULT:
+	case FM10K_FUM_FAULT:
+		break;
+	default:
+		return FM10K_ERR_PARAM;
+	}
+
+	/* only service faults that are valid */
+	func = fm10k_read_reg(hw, type + FM10K_FAULT_FUNC);
+	if (!(func & FM10K_FAULT_FUNC_VALID))
+		return FM10K_ERR_PARAM;
+
+	/* read remaining fields */
+	fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI);
+	fault->address <<= 32;
+	fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO);
+	fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO);
+
+	/* clear valid bit to allow for next error */
+	fm10k_write_reg(hw, type + FM10K_FAULT_FUNC, FM10K_FAULT_FUNC_VALID);
+
+	/* Record which function triggered the error */
+	if (func & FM10K_FAULT_FUNC_PF)
+		fault->func = 0;
+	else
+		fault->func = 1 + ((func & FM10K_FAULT_FUNC_VF_MASK) >>
+				   FM10K_FAULT_FUNC_VF_SHIFT);
+
+	/* record fault type */
+	fault->type = func & FM10K_FAULT_FUNC_TYPE_MASK;
+
+	return 0;
+}
+
+/**
+ *  fm10k_request_lport_map_pf - Request LPORT map from the switch API
+ *  @hw: pointer to hardware structure
+ *
+ **/
+static s32 fm10k_request_lport_map_pf(struct fm10k_hw *hw)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[1];
+
+	/* issue request asking for LPORT map */
+	fm10k_tlv_msg_init(msg, FM10K_PF_MSG_ID_LPORT_MAP);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_get_host_state_pf - Returns the state of the switch and mailbox
+ *  @hw: pointer to hardware structure
+ *  @switch_ready: pointer to boolean value that will record switch state
+ *
+ *  This function will check the DMA_CTRL2 register and mailbox in order
+ *  to determine if the switch is ready for the PF to begin requesting
+ *  addresses and mapping traffic to the local interface.
+ **/
+static s32 fm10k_get_host_state_pf(struct fm10k_hw *hw, bool *switch_ready)
+{
+	u32 dma_ctrl2;
+
+	/* verify the switch is ready for interaction */
+	dma_ctrl2 = fm10k_read_reg(hw, FM10K_DMA_CTRL2);
+	if (!(dma_ctrl2 & FM10K_DMA_CTRL2_SWITCH_READY))
+		return 0;
+
+	/* retrieve generic host state info */
+	return fm10k_get_host_state_generic(hw, switch_ready);
+}
+
+/* This structure defines the attibutes to be parsed below */
+const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[] = {
+	FM10K_TLV_ATTR_LE_STRUCT(FM10K_PF_ATTR_ID_ERR,
+				 sizeof(struct fm10k_swapi_error)),
+	FM10K_TLV_ATTR_U32(FM10K_PF_ATTR_ID_LPORT_MAP),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_msg_lport_map_pf - Message handler for lport_map message from SM
+ *  @hw: Pointer to hardware structure
+ *  @results: pointer array containing parsed data
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This handler configures the lport mapping based on the reply from the
+ *  switch API.
+ **/
+s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results,
+			   struct fm10k_mbx_info __always_unused *mbx)
+{
+	u16 glort, mask;
+	u32 dglort_map;
+	s32 err;
+
+	err = fm10k_tlv_attr_get_u32(results[FM10K_PF_ATTR_ID_LPORT_MAP],
+				     &dglort_map);
+	if (err)
+		return err;
+
+	/* extract values out of the header */
+	glort = FM10K_MSG_HDR_FIELD_GET(dglort_map, LPORT_MAP_GLORT);
+	mask = FM10K_MSG_HDR_FIELD_GET(dglort_map, LPORT_MAP_MASK);
+
+	/* verify mask is set and none of the masked bits in glort are set */
+	if (!mask || (glort & ~mask))
+		return FM10K_ERR_PARAM;
+
+	/* verify the mask is contiguous, and that it is 1's followed by 0's */
+	if (((~(mask - 1) & mask) + mask) & FM10K_DGLORTMAP_NONE)
+		return FM10K_ERR_PARAM;
+
+	/* record the glort, mask, and port count */
+	hw->mac.dglort_map = dglort_map;
+
+	return 0;
+}
+
+const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = {
+	FM10K_TLV_ATTR_U32(FM10K_PF_ATTR_ID_UPDATE_PVID),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_msg_update_pvid_pf - Message handler for port VLAN message from SM
+ *  @hw: Pointer to hardware structure
+ *  @results: pointer array containing parsed data
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This handler configures the default VLAN for the PF
+ **/
+static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results,
+				    struct fm10k_mbx_info __always_unused *mbx)
+{
+	u16 glort, pvid;
+	u32 pvid_update;
+	s32 err;
+
+	err = fm10k_tlv_attr_get_u32(results[FM10K_PF_ATTR_ID_UPDATE_PVID],
+				     &pvid_update);
+	if (err)
+		return err;
+
+	/* extract values from the pvid update */
+	glort = FM10K_MSG_HDR_FIELD_GET(pvid_update, UPDATE_PVID_GLORT);
+	pvid = FM10K_MSG_HDR_FIELD_GET(pvid_update, UPDATE_PVID_PVID);
+
+	/* if glort is not valid return error */
+	if (!fm10k_glort_valid_pf(hw, glort))
+		return FM10K_ERR_PARAM;
+
+	/* verify VLAN ID is valid */
+	if (pvid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* record the port VLAN ID value */
+	hw->mac.default_vid = pvid;
+
+	return 0;
+}
+
+/**
+ *  fm10k_record_global_table_data - Move global table data to swapi table info
+ *  @from: pointer to source table data structure
+ *  @to: pointer to destination table info structure
+ *
+ *  This function is will copy table_data to the table_info contained in
+ *  the hw struct.
+ **/
+static void fm10k_record_global_table_data(struct fm10k_global_table_data *from,
+					   struct fm10k_swapi_table_info *to)
+{
+	/* convert from le32 struct to CPU byte ordered values */
+	to->used = le32_to_cpu(from->used);
+	to->avail = le32_to_cpu(from->avail);
+}
+
+const struct fm10k_tlv_attr fm10k_err_msg_attr[] = {
+	FM10K_TLV_ATTR_LE_STRUCT(FM10K_PF_ATTR_ID_ERR,
+				 sizeof(struct fm10k_swapi_error)),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_msg_err_pf - Message handler for error reply
+ *  @hw: Pointer to hardware structure
+ *  @results: pointer array containing parsed data
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This handler will capture the data for any error replies to previous
+ *  messages that the PF has sent.
+ **/
+s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results,
+		     struct fm10k_mbx_info __always_unused *mbx)
+{
+	struct fm10k_swapi_error err_msg;
+	s32 err;
+
+	/* extract structure from message */
+	err = fm10k_tlv_attr_get_le_struct(results[FM10K_PF_ATTR_ID_ERR],
+					   &err_msg, sizeof(err_msg));
+	if (err)
+		return err;
+
+	/* record table status */
+	fm10k_record_global_table_data(&err_msg.mac, &hw->swapi.mac);
+	fm10k_record_global_table_data(&err_msg.nexthop, &hw->swapi.nexthop);
+	fm10k_record_global_table_data(&err_msg.ffu, &hw->swapi.ffu);
+
+	/* record SW API status value */
+	hw->swapi.status = le32_to_cpu(err_msg.status);
+
+	return 0;
+}
+
+static const struct fm10k_msg_data fm10k_msg_data_pf[] = {
+	FM10K_PF_MSG_ERR_HANDLER(XCAST_MODES, fm10k_msg_err_pf),
+	FM10K_PF_MSG_ERR_HANDLER(UPDATE_MAC_FWD_RULE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_LPORT_MAP_HANDLER(fm10k_msg_lport_map_pf),
+	FM10K_PF_MSG_ERR_HANDLER(LPORT_CREATE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_ERR_HANDLER(LPORT_DELETE, fm10k_msg_err_pf),
+	FM10K_PF_MSG_UPDATE_PVID_HANDLER(fm10k_msg_update_pvid_pf),
+	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_tlv_msg_error),
+};
+
+static const struct fm10k_mac_ops mac_ops_pf = {
+	.get_bus_info		= fm10k_get_bus_info_generic,
+	.reset_hw		= fm10k_reset_hw_pf,
+	.init_hw		= fm10k_init_hw_pf,
+	.start_hw		= fm10k_start_hw_generic,
+	.stop_hw		= fm10k_stop_hw_generic,
+	.update_vlan		= fm10k_update_vlan_pf,
+	.read_mac_addr		= fm10k_read_mac_addr_pf,
+	.update_uc_addr		= fm10k_update_uc_addr_pf,
+	.update_mc_addr		= fm10k_update_mc_addr_pf,
+	.update_xcast_mode	= fm10k_update_xcast_mode_pf,
+	.update_int_moderator	= fm10k_update_int_moderator_pf,
+	.update_lport_state	= fm10k_update_lport_state_pf,
+	.update_hw_stats	= fm10k_update_hw_stats_pf,
+	.rebind_hw_stats	= fm10k_rebind_hw_stats_pf,
+	.configure_dglort_map	= fm10k_configure_dglort_map_pf,
+	.set_dma_mask		= fm10k_set_dma_mask_pf,
+	.get_fault		= fm10k_get_fault_pf,
+	.get_host_state		= fm10k_get_host_state_pf,
+	.request_lport_map	= fm10k_request_lport_map_pf,
+};
+
+static const struct fm10k_iov_ops iov_ops_pf = {
+	.assign_resources		= fm10k_iov_assign_resources_pf,
+	.configure_tc			= fm10k_iov_configure_tc_pf,
+	.assign_int_moderator		= fm10k_iov_assign_int_moderator_pf,
+	.assign_default_mac_vlan	= fm10k_iov_assign_default_mac_vlan_pf,
+	.reset_resources		= fm10k_iov_reset_resources_pf,
+	.set_lport			= fm10k_iov_set_lport_pf,
+	.reset_lport			= fm10k_iov_reset_lport_pf,
+	.update_stats			= fm10k_iov_update_stats_pf,
+};
+
+static s32 fm10k_get_invariants_pf(struct fm10k_hw *hw)
+{
+	fm10k_get_invariants_generic(hw);
+
+	return fm10k_sm_mbx_init(hw, &hw->mbx, fm10k_msg_data_pf);
+}
+
+const struct fm10k_info fm10k_pf_info = {
+	.mac		= fm10k_mac_pf,
+	.get_invariants	= fm10k_get_invariants_pf,
+	.mac_ops	= &mac_ops_pf,
+	.iov_ops	= &iov_ops_pf,
+};
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
new file mode 100644
index 000000000..8e814df70
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _FM10K_PF_H_
+#define _FM10K_PF_H_
+
+#include "fm10k_type.h"
+#include "fm10k_common.h"
+
+bool fm10k_glort_valid_pf(struct fm10k_hw *hw, u16 glort);
+u16 fm10k_queues_per_pool(struct fm10k_hw *hw);
+u16 fm10k_vf_queue_index(struct fm10k_hw *hw, u16 vf_idx);
+
+enum fm10k_pf_tlv_msg_id_v1 {
+	FM10K_PF_MSG_ID_TEST			= 0x000, /* msg ID reserved */
+	FM10K_PF_MSG_ID_XCAST_MODES		= 0x001,
+	FM10K_PF_MSG_ID_UPDATE_MAC_FWD_RULE	= 0x002,
+	FM10K_PF_MSG_ID_LPORT_MAP		= 0x100,
+	FM10K_PF_MSG_ID_LPORT_CREATE		= 0x200,
+	FM10K_PF_MSG_ID_LPORT_DELETE		= 0x201,
+	FM10K_PF_MSG_ID_CONFIG			= 0x300,
+	FM10K_PF_MSG_ID_UPDATE_PVID		= 0x400,
+	FM10K_PF_MSG_ID_CREATE_FLOW_TABLE	= 0x501,
+	FM10K_PF_MSG_ID_DELETE_FLOW_TABLE	= 0x502,
+	FM10K_PF_MSG_ID_UPDATE_FLOW		= 0x503,
+	FM10K_PF_MSG_ID_DELETE_FLOW		= 0x504,
+	FM10K_PF_MSG_ID_SET_FLOW_STATE		= 0x505,
+};
+
+enum fm10k_pf_tlv_attr_id_v1 {
+	FM10K_PF_ATTR_ID_ERR			= 0x00,
+	FM10K_PF_ATTR_ID_LPORT_MAP		= 0x01,
+	FM10K_PF_ATTR_ID_XCAST_MODE		= 0x02,
+	FM10K_PF_ATTR_ID_MAC_UPDATE		= 0x03,
+	FM10K_PF_ATTR_ID_VLAN_UPDATE		= 0x04,
+	FM10K_PF_ATTR_ID_CONFIG			= 0x05,
+	FM10K_PF_ATTR_ID_CREATE_FLOW_TABLE	= 0x06,
+	FM10K_PF_ATTR_ID_DELETE_FLOW_TABLE	= 0x07,
+	FM10K_PF_ATTR_ID_UPDATE_FLOW		= 0x08,
+	FM10K_PF_ATTR_ID_FLOW_STATE		= 0x09,
+	FM10K_PF_ATTR_ID_FLOW_HANDLE		= 0x0A,
+	FM10K_PF_ATTR_ID_DELETE_FLOW		= 0x0B,
+	FM10K_PF_ATTR_ID_PORT			= 0x0C,
+	FM10K_PF_ATTR_ID_UPDATE_PVID		= 0x0D,
+};
+
+#define FM10K_MSG_LPORT_MAP_GLORT_SHIFT	0
+#define FM10K_MSG_LPORT_MAP_GLORT_SIZE	16
+#define FM10K_MSG_LPORT_MAP_MASK_SHIFT	16
+#define FM10K_MSG_LPORT_MAP_MASK_SIZE	16
+
+#define FM10K_MSG_UPDATE_PVID_GLORT_SHIFT	0
+#define FM10K_MSG_UPDATE_PVID_GLORT_SIZE	16
+#define FM10K_MSG_UPDATE_PVID_PVID_SHIFT	16
+#define FM10K_MSG_UPDATE_PVID_PVID_SIZE		16
+
+#define FM10K_MSG_ERR_PEP_NOT_SCHEDULED	280
+
+/* The following data structures are overlayed directly onto TLV mailbox
+ * messages, and must not break 4 byte alignment. Ensure the structures line
+ * up correctly as per their TLV definition.
+ */
+
+struct fm10k_mac_update {
+	__le32	mac_lower;
+	__le16	mac_upper;
+	__le16	vlan;
+	__le16	glort;
+	u8	flags;
+	u8	action;
+} __aligned(4) __packed;
+
+struct fm10k_global_table_data {
+	__le32	used;
+	__le32	avail;
+} __aligned(4) __packed;
+
+struct fm10k_swapi_error {
+	__le32				status;
+	struct fm10k_global_table_data	mac;
+	struct fm10k_global_table_data	nexthop;
+	struct fm10k_global_table_data	ffu;
+} __aligned(4) __packed;
+
+s32 fm10k_msg_lport_map_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+extern const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[];
+#define FM10K_PF_MSG_LPORT_MAP_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_LPORT_MAP, \
+			  fm10k_lport_map_msg_attr, func)
+extern const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[];
+#define FM10K_PF_MSG_UPDATE_PVID_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_UPDATE_PVID, \
+			  fm10k_update_pvid_msg_attr, func)
+
+s32 fm10k_msg_err_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
+#define FM10K_PF_MSG_ERR_HANDLER(msg, func) \
+	FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_##msg, fm10k_err_msg_attr, func)
+
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
+s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
+			      struct fm10k_mbx_info *);
+s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **,
+				 struct fm10k_mbx_info *);
+
+extern const struct fm10k_info fm10k_pf_info;
+#endif /* _FM10K_PF_H */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
new file mode 100644
index 000000000..75cbdf2db
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
@@ -0,0 +1,850 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k_tlv.h"
+
+/**
+ *  fm10k_tlv_msg_init - Initialize message block for TLV data storage
+ *  @msg: Pointer to message block
+ *  @msg_id: Message ID indicating message type
+ *
+ *  This function return success if provided with a valid message pointer
+ **/
+s32 fm10k_tlv_msg_init(u32 *msg, u16 msg_id)
+{
+	/* verify pointer is not NULL */
+	if (!msg)
+		return FM10K_ERR_PARAM;
+
+	*msg = (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT) | msg_id;
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_put_null_string - Place null terminated string on message
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *  @string: Pointer to string to be stored in attribute
+ *
+ *  This function will reorder a string to be CPU endian and store it in
+ *  the attribute buffer.  It will return success if provided with a valid
+ *  pointers.
+ **/
+static s32 fm10k_tlv_attr_put_null_string(u32 *msg, u16 attr_id,
+					  const unsigned char *string)
+{
+	u32 attr_data = 0, len = 0;
+	u32 *attr;
+
+	/* verify pointers are not NULL */
+	if (!string || !msg)
+		return FM10K_ERR_PARAM;
+
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+	/* copy string into local variable and then write to msg */
+	do {
+		/* write data to message */
+		if (len && !(len % 4)) {
+			attr[len / 4] = attr_data;
+			attr_data = 0;
+		}
+
+		/* record character to offset location */
+		attr_data |= (u32)(*string) << (8 * (len % 4));
+		len++;
+
+		/* test for NULL and then increment */
+	} while (*(string++));
+
+	/* write last piece of data to message */
+	attr[(len + 3) / 4] = attr_data;
+
+	/* record attribute header, update message length */
+	len <<= FM10K_TLV_LEN_SHIFT;
+	attr[0] = len | attr_id;
+
+	/* add header length to length */
+	len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+	*msg += FM10K_TLV_LEN_ALIGN(len);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_get_null_string - Get null terminated string from attribute
+ *  @attr: Pointer to attribute
+ *  @string: Pointer to location of destination string
+ *
+ *  This function pulls the string back out of the attribute and will place
+ *  it in the array pointed by string.  It will return success if provided
+ *  with a valid pointers.
+ **/
+static s32 fm10k_tlv_attr_get_null_string(u32 *attr, unsigned char *string)
+{
+	u32 len;
+
+	/* verify pointers are not NULL */
+	if (!string || !attr)
+		return FM10K_ERR_PARAM;
+
+	len = *attr >> FM10K_TLV_LEN_SHIFT;
+	attr++;
+
+	while (len--)
+		string[len] = (u8)(attr[len / 4] >> (8 * (len % 4)));
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_put_mac_vlan - Store MAC/VLAN attribute in message
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *  @mac_addr: MAC address to be stored
+ *  @vlan: VLAN to be stored
+ *
+ *  This function will reorder a MAC address to be CPU endian and store it
+ *  in the attribute buffer.  It will return success if provided with a
+ *  valid pointers.
+ **/
+s32 fm10k_tlv_attr_put_mac_vlan(u32 *msg, u16 attr_id,
+				const u8 *mac_addr, u16 vlan)
+{
+	u32 len = ETH_ALEN << FM10K_TLV_LEN_SHIFT;
+	u32 *attr;
+
+	/* verify pointers are not NULL */
+	if (!msg || !mac_addr)
+		return FM10K_ERR_PARAM;
+
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+	/* record attribute header, update message length */
+	attr[0] = len | attr_id;
+
+	/* copy value into local variable and then write to msg */
+	attr[1] = le32_to_cpu(*(const __le32 *)&mac_addr[0]);
+	attr[2] = le16_to_cpu(*(const __le16 *)&mac_addr[4]);
+	attr[2] |= (u32)vlan << 16;
+
+	/* add header length to length */
+	len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+	*msg += FM10K_TLV_LEN_ALIGN(len);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_get_mac_vlan - Get MAC/VLAN stored in attribute
+ *  @attr: Pointer to attribute
+ *  @mac_addr: location of buffer to store MAC address
+ *  @vlan: location of buffer to store VLAN
+ *
+ *  This function pulls the MAC address back out of the attribute and will
+ *  place it in the array pointed by mac_addr.  It will return success
+ *  if provided with a valid pointers.
+ **/
+s32 fm10k_tlv_attr_get_mac_vlan(u32 *attr, u8 *mac_addr, u16 *vlan)
+{
+	/* verify pointers are not NULL */
+	if (!mac_addr || !attr)
+		return FM10K_ERR_PARAM;
+
+	*(__le32 *)&mac_addr[0] = cpu_to_le32(attr[1]);
+	*(__le16 *)&mac_addr[4] = cpu_to_le16((u16)(attr[2]));
+	*vlan = (u16)(attr[2] >> 16);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_put_bool - Add header indicating value "true"
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *
+ *  This function will simply add an attribute header, the fact
+ *  that the header is here means the attribute value is true, else
+ *  it is false.  The function will return success if provided with a
+ *  valid pointers.
+ **/
+s32 fm10k_tlv_attr_put_bool(u32 *msg, u16 attr_id)
+{
+	/* verify pointers are not NULL */
+	if (!msg)
+		return FM10K_ERR_PARAM;
+
+	/* record attribute header */
+	msg[FM10K_TLV_DWORD_LEN(*msg)] = attr_id;
+
+	/* add header length to length */
+	*msg += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_put_value - Store integer value attribute in message
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *  @value: Value to be written
+ *  @len: Size of value
+ *
+ *  This function will place an integer value of up to 8 bytes in size
+ *  in a message attribute.  The function will return success provided
+ *  that msg is a valid pointer, and len is 1, 2, 4, or 8.
+ **/
+s32 fm10k_tlv_attr_put_value(u32 *msg, u16 attr_id, s64 value, u32 len)
+{
+	u32 *attr;
+
+	/* verify non-null msg and len is 1, 2, 4, or 8 */
+	if (!msg || !len || len > 8 || (len & (len - 1)))
+		return FM10K_ERR_PARAM;
+
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+	if (len < 4) {
+		attr[1] = (u32)value & (BIT(8 * len) - 1);
+	} else {
+		attr[1] = (u32)value;
+		if (len > 4)
+			attr[2] = (u32)(value >> 32);
+	}
+
+	/* record attribute header, update message length */
+	len <<= FM10K_TLV_LEN_SHIFT;
+	attr[0] = len | attr_id;
+
+	/* add header length to length */
+	len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+	*msg += FM10K_TLV_LEN_ALIGN(len);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_get_value - Get integer value stored in attribute
+ *  @attr: Pointer to attribute
+ *  @value: Pointer to destination buffer
+ *  @len: Size of value
+ *
+ *  This function will place an integer value of up to 8 bytes in size
+ *  in the offset pointed to by value.  The function will return success
+ *  provided that pointers are valid and the len value matches the
+ *  attribute length.
+ **/
+s32 fm10k_tlv_attr_get_value(u32 *attr, void *value, u32 len)
+{
+	/* verify pointers are not NULL */
+	if (!attr || !value)
+		return FM10K_ERR_PARAM;
+
+	if ((*attr >> FM10K_TLV_LEN_SHIFT) != len)
+		return FM10K_ERR_PARAM;
+
+	if (len == 8)
+		*(u64 *)value = ((u64)attr[2] << 32) | attr[1];
+	else if (len == 4)
+		*(u32 *)value = attr[1];
+	else if (len == 2)
+		*(u16 *)value = (u16)attr[1];
+	else
+		*(u8 *)value = (u8)attr[1];
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_put_le_struct - Store little endian structure in message
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *  @le_struct: Pointer to structure to be written
+ *  @len: Size of le_struct
+ *
+ *  This function will place a little endian structure value in a message
+ *  attribute.  The function will return success provided that all pointers
+ *  are valid and length is a non-zero multiple of 4.
+ **/
+s32 fm10k_tlv_attr_put_le_struct(u32 *msg, u16 attr_id,
+				 const void *le_struct, u32 len)
+{
+	const __le32 *le32_ptr = (const __le32 *)le_struct;
+	u32 *attr;
+	u32 i;
+
+	/* verify non-null msg and len is in 32 bit words */
+	if (!msg || !len || (len % 4))
+		return FM10K_ERR_PARAM;
+
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+	/* copy le32 structure into host byte order at 32b boundaries */
+	for (i = 0; i < (len / 4); i++)
+		attr[i + 1] = le32_to_cpu(le32_ptr[i]);
+
+	/* record attribute header, update message length */
+	len <<= FM10K_TLV_LEN_SHIFT;
+	attr[0] = len | attr_id;
+
+	/* add header length to length */
+	len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+	*msg += FM10K_TLV_LEN_ALIGN(len);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_get_le_struct - Get little endian struct form attribute
+ *  @attr: Pointer to attribute
+ *  @le_struct: Pointer to structure to be written
+ *  @len: Size of structure
+ *
+ *  This function will place a little endian structure in the buffer
+ *  pointed to by le_struct.  The function will return success
+ *  provided that pointers are valid and the len value matches the
+ *  attribute length.
+ **/
+s32 fm10k_tlv_attr_get_le_struct(u32 *attr, void *le_struct, u32 len)
+{
+	__le32 *le32_ptr = (__le32 *)le_struct;
+	u32 i;
+
+	/* verify pointers are not NULL */
+	if (!le_struct || !attr)
+		return FM10K_ERR_PARAM;
+
+	if ((*attr >> FM10K_TLV_LEN_SHIFT) != len)
+		return FM10K_ERR_PARAM;
+
+	attr++;
+
+	for (i = 0; len; i++, len -= 4)
+		le32_ptr[i] = cpu_to_le32(attr[i]);
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_nest_start - Start a set of nested attributes
+ *  @msg: Pointer to message block
+ *  @attr_id: Attribute ID
+ *
+ *  This function will mark off a new nested region for encapsulating
+ *  a given set of attributes.  The idea is if you wish to place a secondary
+ *  structure within the message this mechanism allows for that.  The
+ *  function will return NULL on failure, and a pointer to the start
+ *  of the nested attributes on success.
+ **/
+static u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id)
+{
+	u32 *attr;
+
+	/* verify pointer is not NULL */
+	if (!msg)
+		return NULL;
+
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+	attr[0] = attr_id;
+
+	/* return pointer to nest header */
+	return attr;
+}
+
+/**
+ *  fm10k_tlv_attr_nest_stop - Stop a set of nested attributes
+ *  @msg: Pointer to message block
+ *
+ *  This function closes off an existing set of nested attributes.  The
+ *  message pointer should be pointing to the parent of the nest.  So in
+ *  the case of a nest within the nest this would be the outer nest pointer.
+ *  This function will return success provided all pointers are valid.
+ **/
+static s32 fm10k_tlv_attr_nest_stop(u32 *msg)
+{
+	u32 *attr;
+	u32 len;
+
+	/* verify pointer is not NULL */
+	if (!msg)
+		return FM10K_ERR_PARAM;
+
+	/* locate the nested header and retrieve its length */
+	attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+	len = (attr[0] >> FM10K_TLV_LEN_SHIFT) << FM10K_TLV_LEN_SHIFT;
+
+	/* only include nest if data was added to it */
+	if (len) {
+		len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+		*msg += len;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_validate - Validate attribute metadata
+ *  @attr: Pointer to attribute
+ *  @tlv_attr: Type and length info for attribute
+ *
+ *  This function does some basic validation of the input TLV.  It
+ *  verifies the length, and in the case of null terminated strings
+ *  it verifies that the last byte is null.  The function will
+ *  return FM10K_ERR_PARAM if any attribute is malformed, otherwise
+ *  it returns 0.
+ **/
+static s32 fm10k_tlv_attr_validate(u32 *attr,
+				   const struct fm10k_tlv_attr *tlv_attr)
+{
+	u32 attr_id = *attr & FM10K_TLV_ID_MASK;
+	u16 len = *attr >> FM10K_TLV_LEN_SHIFT;
+
+	/* verify this is an attribute and not a message */
+	if (*attr & (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT))
+		return FM10K_ERR_PARAM;
+
+	/* search through the list of attributes to find a matching ID */
+	while (tlv_attr->id < attr_id)
+		tlv_attr++;
+
+	/* if didn't find a match then we should exit */
+	if (tlv_attr->id != attr_id)
+		return FM10K_NOT_IMPLEMENTED;
+
+	/* move to start of attribute data */
+	attr++;
+
+	switch (tlv_attr->type) {
+	case FM10K_TLV_NULL_STRING:
+		if (!len ||
+		    (attr[(len - 1) / 4] & (0xFF << (8 * ((len - 1) % 4)))))
+			return FM10K_ERR_PARAM;
+		if (len > tlv_attr->len)
+			return FM10K_ERR_PARAM;
+		break;
+	case FM10K_TLV_MAC_ADDR:
+		if (len != ETH_ALEN)
+			return FM10K_ERR_PARAM;
+		break;
+	case FM10K_TLV_BOOL:
+		if (len)
+			return FM10K_ERR_PARAM;
+		break;
+	case FM10K_TLV_UNSIGNED:
+	case FM10K_TLV_SIGNED:
+		if (len != tlv_attr->len)
+			return FM10K_ERR_PARAM;
+		break;
+	case FM10K_TLV_LE_STRUCT:
+		/* struct must be 4 byte aligned */
+		if ((len % 4) || len != tlv_attr->len)
+			return FM10K_ERR_PARAM;
+		break;
+	case FM10K_TLV_NESTED:
+		/* nested attributes must be 4 byte aligned */
+		if (len % 4)
+			return FM10K_ERR_PARAM;
+		break;
+	default:
+		/* attribute id is mapped to bad value */
+		return FM10K_ERR_PARAM;
+	}
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_attr_parse - Parses stream of attribute data
+ *  @attr: Pointer to attribute list
+ *  @results: Pointer array to store pointers to attributes
+ *  @tlv_attr: Type and length info for attributes
+ *
+ *  This function validates a stream of attributes and parses them
+ *  up into an array of pointers stored in results.  The function will
+ *  return FM10K_ERR_PARAM on any input or message error,
+ *  FM10K_NOT_IMPLEMENTED for any attribute that is outside of the array
+ *  and 0 on success. Any attributes not found in tlv_attr will be silently
+ *  ignored.
+ **/
+static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results,
+				const struct fm10k_tlv_attr *tlv_attr)
+{
+	u32 i, attr_id, offset = 0;
+	s32 err;
+	u16 len;
+
+	/* verify pointers are not NULL */
+	if (!attr || !results)
+		return FM10K_ERR_PARAM;
+
+	/* initialize results to NULL */
+	for (i = 0; i < FM10K_TLV_RESULTS_MAX; i++)
+		results[i] = NULL;
+
+	/* pull length from the message header */
+	len = *attr >> FM10K_TLV_LEN_SHIFT;
+
+	/* no attributes to parse if there is no length */
+	if (!len)
+		return 0;
+
+	/* no attributes to parse, just raw data, message becomes attribute */
+	if (!tlv_attr) {
+		results[0] = attr;
+		return 0;
+	}
+
+	/* move to start of attribute data */
+	attr++;
+
+	/* run through list parsing all attributes */
+	while (offset < len) {
+		attr_id = *attr & FM10K_TLV_ID_MASK;
+
+		if (attr_id >= FM10K_TLV_RESULTS_MAX)
+			return FM10K_NOT_IMPLEMENTED;
+
+		err = fm10k_tlv_attr_validate(attr, tlv_attr);
+		if (err == FM10K_NOT_IMPLEMENTED)
+			; /* silently ignore non-implemented attributes */
+		else if (err)
+			return err;
+		else
+			results[attr_id] = attr;
+
+		/* update offset */
+		offset += FM10K_TLV_DWORD_LEN(*attr) * 4;
+
+		/* move to next attribute */
+		attr = &attr[FM10K_TLV_DWORD_LEN(*attr)];
+	}
+
+	/* we should find ourselves at the end of the list */
+	if (offset != len)
+		return FM10K_ERR_PARAM;
+
+	return 0;
+}
+
+/**
+ *  fm10k_tlv_msg_parse - Parses message header and calls function handler
+ *  @hw: Pointer to hardware structure
+ *  @msg: Pointer to message
+ *  @mbx: Pointer to mailbox information structure
+ *  @data: Pointer to message handler data structure
+ *
+ *  This function should be the first function called upon receiving a
+ *  message.  The handler will identify the message type and call the correct
+ *  handler for the given message.  It will return the value from the function
+ *  call on a recognized message type, otherwise it will return
+ *  FM10K_NOT_IMPLEMENTED on an unrecognized type.
+ **/
+s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg,
+			struct fm10k_mbx_info *mbx,
+			const struct fm10k_msg_data *data)
+{
+	u32 *results[FM10K_TLV_RESULTS_MAX];
+	u32 msg_id;
+	s32 err;
+
+	/* verify pointer is not NULL */
+	if (!msg || !data)
+		return FM10K_ERR_PARAM;
+
+	/* verify this is a message and not an attribute */
+	if (!(*msg & (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT)))
+		return FM10K_ERR_PARAM;
+
+	/* grab message ID */
+	msg_id = *msg & FM10K_TLV_ID_MASK;
+
+	while (data->id < msg_id)
+		data++;
+
+	/* if we didn't find it then pass it up as an error */
+	if (data->id != msg_id) {
+		while (data->id != FM10K_TLV_ERROR)
+			data++;
+	}
+
+	/* parse the attributes into the results list */
+	err = fm10k_tlv_attr_parse(msg, results, data->attr);
+	if (err < 0)
+		return err;
+
+	return data->func(hw, results, mbx);
+}
+
+/**
+ *  fm10k_tlv_msg_error - Default handler for unrecognized TLV message IDs
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to message, results[0] is pointer to message
+ *  @mbx: Unused mailbox pointer
+ *
+ *  This function is a default handler for unrecognized messages.  At a
+ *  minimum it just indicates that the message requested was
+ *  unimplemented.
+ **/
+s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw,
+			u32 __always_unused **results,
+			struct fm10k_mbx_info __always_unused *mbx)
+{
+	return FM10K_NOT_IMPLEMENTED;
+}
+
+static const unsigned char test_str[] =	"fm10k";
+static const unsigned char test_mac[ETH_ALEN] = { 0x12, 0x34, 0x56,
+						  0x78, 0x9a, 0xbc };
+static const u16 test_vlan = 0x0FED;
+static const u64 test_u64 = 0xfedcba9876543210ull;
+static const u32 test_u32 = 0x87654321;
+static const u16 test_u16 = 0x8765;
+static const u8  test_u8  = 0x87;
+static const s64 test_s64 = -0x123456789abcdef0ll;
+static const s32 test_s32 = -0x1235678;
+static const s16 test_s16 = -0x1234;
+static const s8  test_s8  = -0x12;
+static const __le32 test_le[2] = { cpu_to_le32(0x12345678),
+				   cpu_to_le32(0x9abcdef0)};
+
+/* The message below is meant to be used as a test message to demonstrate
+ * how to use the TLV interface and to test the types.  Normally this code
+ * be compiled out by stripping the code wrapped in FM10K_TLV_TEST_MSG
+ */
+const struct fm10k_tlv_attr fm10k_tlv_msg_test_attr[] = {
+	FM10K_TLV_ATTR_NULL_STRING(FM10K_TEST_MSG_STRING, 80),
+	FM10K_TLV_ATTR_MAC_ADDR(FM10K_TEST_MSG_MAC_ADDR),
+	FM10K_TLV_ATTR_U8(FM10K_TEST_MSG_U8),
+	FM10K_TLV_ATTR_U16(FM10K_TEST_MSG_U16),
+	FM10K_TLV_ATTR_U32(FM10K_TEST_MSG_U32),
+	FM10K_TLV_ATTR_U64(FM10K_TEST_MSG_U64),
+	FM10K_TLV_ATTR_S8(FM10K_TEST_MSG_S8),
+	FM10K_TLV_ATTR_S16(FM10K_TEST_MSG_S16),
+	FM10K_TLV_ATTR_S32(FM10K_TEST_MSG_S32),
+	FM10K_TLV_ATTR_S64(FM10K_TEST_MSG_S64),
+	FM10K_TLV_ATTR_LE_STRUCT(FM10K_TEST_MSG_LE_STRUCT, 8),
+	FM10K_TLV_ATTR_NESTED(FM10K_TEST_MSG_NESTED),
+	FM10K_TLV_ATTR_S32(FM10K_TEST_MSG_RESULT),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_tlv_msg_test_generate_data - Stuff message with data
+ *  @msg: Pointer to message
+ *  @attr_flags: List of flags indicating what attributes to add
+ *
+ *  This function is meant to load a message buffer with attribute data
+ **/
+static void fm10k_tlv_msg_test_generate_data(u32 *msg, u32 attr_flags)
+{
+	if (attr_flags & BIT(FM10K_TEST_MSG_STRING))
+		fm10k_tlv_attr_put_null_string(msg, FM10K_TEST_MSG_STRING,
+					       test_str);
+	if (attr_flags & BIT(FM10K_TEST_MSG_MAC_ADDR))
+		fm10k_tlv_attr_put_mac_vlan(msg, FM10K_TEST_MSG_MAC_ADDR,
+					    test_mac, test_vlan);
+	if (attr_flags & BIT(FM10K_TEST_MSG_U8))
+		fm10k_tlv_attr_put_u8(msg, FM10K_TEST_MSG_U8,  test_u8);
+	if (attr_flags & BIT(FM10K_TEST_MSG_U16))
+		fm10k_tlv_attr_put_u16(msg, FM10K_TEST_MSG_U16, test_u16);
+	if (attr_flags & BIT(FM10K_TEST_MSG_U32))
+		fm10k_tlv_attr_put_u32(msg, FM10K_TEST_MSG_U32, test_u32);
+	if (attr_flags & BIT(FM10K_TEST_MSG_U64))
+		fm10k_tlv_attr_put_u64(msg, FM10K_TEST_MSG_U64, test_u64);
+	if (attr_flags & BIT(FM10K_TEST_MSG_S8))
+		fm10k_tlv_attr_put_s8(msg, FM10K_TEST_MSG_S8,  test_s8);
+	if (attr_flags & BIT(FM10K_TEST_MSG_S16))
+		fm10k_tlv_attr_put_s16(msg, FM10K_TEST_MSG_S16, test_s16);
+	if (attr_flags & BIT(FM10K_TEST_MSG_S32))
+		fm10k_tlv_attr_put_s32(msg, FM10K_TEST_MSG_S32, test_s32);
+	if (attr_flags & BIT(FM10K_TEST_MSG_S64))
+		fm10k_tlv_attr_put_s64(msg, FM10K_TEST_MSG_S64, test_s64);
+	if (attr_flags & BIT(FM10K_TEST_MSG_LE_STRUCT))
+		fm10k_tlv_attr_put_le_struct(msg, FM10K_TEST_MSG_LE_STRUCT,
+					     test_le, 8);
+}
+
+/**
+ *  fm10k_tlv_msg_test_create - Create a test message testing all attributes
+ *  @msg: Pointer to message
+ *  @attr_flags: List of flags indicating what attributes to add
+ *
+ *  This function is meant to load a message buffer with all attribute types
+ *  including a nested attribute.
+ **/
+void fm10k_tlv_msg_test_create(u32 *msg, u32 attr_flags)
+{
+	u32 *nest = NULL;
+
+	fm10k_tlv_msg_init(msg, FM10K_TLV_MSG_ID_TEST);
+
+	fm10k_tlv_msg_test_generate_data(msg, attr_flags);
+
+	/* check for nested attributes */
+	attr_flags >>= FM10K_TEST_MSG_NESTED;
+
+	if (attr_flags) {
+		nest = fm10k_tlv_attr_nest_start(msg, FM10K_TEST_MSG_NESTED);
+
+		fm10k_tlv_msg_test_generate_data(nest, attr_flags);
+
+		fm10k_tlv_attr_nest_stop(msg);
+	}
+}
+
+/**
+ *  fm10k_tlv_msg_test - Validate all results on test message receive
+ *  @hw: Pointer to hardware structure
+ *  @results: Pointer array to attributes in the message
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This function does a check to verify all attributes match what the test
+ *  message placed in the message buffer.  It is the default handler
+ *  for TLV test messages.
+ **/
+s32 fm10k_tlv_msg_test(struct fm10k_hw *hw, u32 **results,
+		       struct fm10k_mbx_info *mbx)
+{
+	u32 *nest_results[FM10K_TLV_RESULTS_MAX];
+	unsigned char result_str[80];
+	unsigned char result_mac[ETH_ALEN];
+	s32 err = 0;
+	__le32 result_le[2];
+	u16 result_vlan;
+	u64 result_u64;
+	u32 result_u32;
+	u16 result_u16;
+	u8  result_u8;
+	s64 result_s64;
+	s32 result_s32;
+	s16 result_s16;
+	s8  result_s8;
+	u32 reply[3];
+
+	/* retrieve results of a previous test */
+	if (!!results[FM10K_TEST_MSG_RESULT])
+		return fm10k_tlv_attr_get_s32(results[FM10K_TEST_MSG_RESULT],
+					      &mbx->test_result);
+
+parse_nested:
+	if (!!results[FM10K_TEST_MSG_STRING]) {
+		err = fm10k_tlv_attr_get_null_string(
+					results[FM10K_TEST_MSG_STRING],
+					result_str);
+		if (!err && memcmp(test_str, result_str, sizeof(test_str)))
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_MAC_ADDR]) {
+		err = fm10k_tlv_attr_get_mac_vlan(
+					results[FM10K_TEST_MSG_MAC_ADDR],
+					result_mac, &result_vlan);
+		if (!err && !ether_addr_equal(test_mac, result_mac))
+			err = FM10K_ERR_INVALID_VALUE;
+		if (!err && test_vlan != result_vlan)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_U8]) {
+		err = fm10k_tlv_attr_get_u8(results[FM10K_TEST_MSG_U8],
+					    &result_u8);
+		if (!err && test_u8 != result_u8)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_U16]) {
+		err = fm10k_tlv_attr_get_u16(results[FM10K_TEST_MSG_U16],
+					     &result_u16);
+		if (!err && test_u16 != result_u16)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_U32]) {
+		err = fm10k_tlv_attr_get_u32(results[FM10K_TEST_MSG_U32],
+					     &result_u32);
+		if (!err && test_u32 != result_u32)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_U64]) {
+		err = fm10k_tlv_attr_get_u64(results[FM10K_TEST_MSG_U64],
+					     &result_u64);
+		if (!err && test_u64 != result_u64)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_S8]) {
+		err = fm10k_tlv_attr_get_s8(results[FM10K_TEST_MSG_S8],
+					    &result_s8);
+		if (!err && test_s8 != result_s8)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_S16]) {
+		err = fm10k_tlv_attr_get_s16(results[FM10K_TEST_MSG_S16],
+					     &result_s16);
+		if (!err && test_s16 != result_s16)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_S32]) {
+		err = fm10k_tlv_attr_get_s32(results[FM10K_TEST_MSG_S32],
+					     &result_s32);
+		if (!err && test_s32 != result_s32)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_S64]) {
+		err = fm10k_tlv_attr_get_s64(results[FM10K_TEST_MSG_S64],
+					     &result_s64);
+		if (!err && test_s64 != result_s64)
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+	if (!!results[FM10K_TEST_MSG_LE_STRUCT]) {
+		err = fm10k_tlv_attr_get_le_struct(
+					results[FM10K_TEST_MSG_LE_STRUCT],
+					result_le,
+					sizeof(result_le));
+		if (!err && memcmp(test_le, result_le, sizeof(test_le)))
+			err = FM10K_ERR_INVALID_VALUE;
+		if (err)
+			goto report_result;
+	}
+
+	if (!!results[FM10K_TEST_MSG_NESTED]) {
+		/* clear any pointers */
+		memset(nest_results, 0, sizeof(nest_results));
+
+		/* parse the nested attributes into the nest results list */
+		err = fm10k_tlv_attr_parse(results[FM10K_TEST_MSG_NESTED],
+					   nest_results,
+					   fm10k_tlv_msg_test_attr);
+		if (err)
+			goto report_result;
+
+		/* loop back through to the start */
+		results = nest_results;
+		goto parse_nested;
+	}
+
+report_result:
+	/* generate reply with test result */
+	fm10k_tlv_msg_init(reply, FM10K_TLV_MSG_ID_TEST);
+	fm10k_tlv_attr_put_s32(reply, FM10K_TEST_MSG_RESULT, err);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, reply);
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
new file mode 100644
index 000000000..ceb9b791f
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#ifndef _FM10K_TLV_H_
+#define _FM10K_TLV_H_
+
+/* forward declaration */
+struct fm10k_msg_data;
+
+#include "fm10k_type.h"
+
+/* Message / Argument header format
+ *    3			  2		      1			  0
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |	     Length	   | Flags |	      Type / ID		   |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * The message header format described here is used for messages that are
+ * passed between the PF and the VF.  To allow for messages larger then
+ * mailbox size we will provide a message with the above header and it
+ * will be segmented and transported to the mailbox to the other side where
+ * it is reassembled.  It contains the following fields:
+ * Length: Length of the message in bytes excluding the message header
+ * Flags: TBD
+ * Type/ID: These will be the message/argument types we pass
+ */
+/* message data header */
+#define FM10K_TLV_ID_SHIFT		0
+#define FM10K_TLV_ID_SIZE		16
+#define FM10K_TLV_ID_MASK		((1u << FM10K_TLV_ID_SIZE) - 1)
+#define FM10K_TLV_FLAGS_SHIFT		16
+#define FM10K_TLV_FLAGS_MSG		0x1
+#define FM10K_TLV_FLAGS_SIZE		4
+#define FM10K_TLV_LEN_SHIFT		20
+#define FM10K_TLV_LEN_SIZE		12
+
+#define FM10K_TLV_HDR_LEN		4ul
+#define FM10K_TLV_LEN_ALIGN_MASK \
+	((FM10K_TLV_HDR_LEN - 1) << FM10K_TLV_LEN_SHIFT)
+#define FM10K_TLV_LEN_ALIGN(tlv) \
+	(((tlv) + FM10K_TLV_LEN_ALIGN_MASK) & ~FM10K_TLV_LEN_ALIGN_MASK)
+#define FM10K_TLV_DWORD_LEN(tlv) \
+	((u16)((FM10K_TLV_LEN_ALIGN(tlv)) >> (FM10K_TLV_LEN_SHIFT + 2)) + 1)
+
+#define FM10K_TLV_RESULTS_MAX		32
+
+enum fm10k_tlv_type {
+	FM10K_TLV_NULL_STRING,
+	FM10K_TLV_MAC_ADDR,
+	FM10K_TLV_BOOL,
+	FM10K_TLV_UNSIGNED,
+	FM10K_TLV_SIGNED,
+	FM10K_TLV_LE_STRUCT,
+	FM10K_TLV_NESTED,
+	FM10K_TLV_MAX_TYPE
+};
+
+#define FM10K_TLV_ERROR (~0u)
+
+struct fm10k_tlv_attr {
+	unsigned int		id;
+	enum fm10k_tlv_type	type;
+	u16			len;
+};
+
+#define FM10K_TLV_ATTR_NULL_STRING(id, len) { id, FM10K_TLV_NULL_STRING, len }
+#define FM10K_TLV_ATTR_MAC_ADDR(id)	    { id, FM10K_TLV_MAC_ADDR, 6 }
+#define FM10K_TLV_ATTR_BOOL(id)		    { id, FM10K_TLV_BOOL, 0 }
+#define FM10K_TLV_ATTR_U8(id)		    { id, FM10K_TLV_UNSIGNED, 1 }
+#define FM10K_TLV_ATTR_U16(id)		    { id, FM10K_TLV_UNSIGNED, 2 }
+#define FM10K_TLV_ATTR_U32(id)		    { id, FM10K_TLV_UNSIGNED, 4 }
+#define FM10K_TLV_ATTR_U64(id)		    { id, FM10K_TLV_UNSIGNED, 8 }
+#define FM10K_TLV_ATTR_S8(id)		    { id, FM10K_TLV_SIGNED, 1 }
+#define FM10K_TLV_ATTR_S16(id)		    { id, FM10K_TLV_SIGNED, 2 }
+#define FM10K_TLV_ATTR_S32(id)		    { id, FM10K_TLV_SIGNED, 4 }
+#define FM10K_TLV_ATTR_S64(id)		    { id, FM10K_TLV_SIGNED, 8 }
+#define FM10K_TLV_ATTR_LE_STRUCT(id, len)   { id, FM10K_TLV_LE_STRUCT, len }
+#define FM10K_TLV_ATTR_NESTED(id)	    { id, FM10K_TLV_NESTED, 0 }
+#define FM10K_TLV_ATTR_LAST		    { FM10K_TLV_ERROR, 0, 0 }
+
+struct fm10k_msg_data {
+	unsigned int		    id;
+	const struct fm10k_tlv_attr *attr;
+	s32			    (*func)(struct fm10k_hw *, u32 **,
+					    struct fm10k_mbx_info *);
+};
+
+#define FM10K_MSG_HANDLER(id, attr, func) { id, attr, func }
+
+s32 fm10k_tlv_msg_init(u32 *, u16);
+s32 fm10k_tlv_attr_put_mac_vlan(u32 *, u16, const u8 *, u16);
+s32 fm10k_tlv_attr_get_mac_vlan(u32 *, u8 *, u16 *);
+s32 fm10k_tlv_attr_put_bool(u32 *, u16);
+s32 fm10k_tlv_attr_put_value(u32 *, u16, s64, u32);
+#define fm10k_tlv_attr_put_u8(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 1)
+#define fm10k_tlv_attr_put_u16(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 2)
+#define fm10k_tlv_attr_put_u32(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 4)
+#define fm10k_tlv_attr_put_u64(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 8)
+#define fm10k_tlv_attr_put_s8(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 1)
+#define fm10k_tlv_attr_put_s16(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 2)
+#define fm10k_tlv_attr_put_s32(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 4)
+#define fm10k_tlv_attr_put_s64(msg, attr_id, val) \
+		fm10k_tlv_attr_put_value(msg, attr_id, val, 8)
+s32 fm10k_tlv_attr_get_value(u32 *, void *, u32);
+#define fm10k_tlv_attr_get_u8(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(u8))
+#define fm10k_tlv_attr_get_u16(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(u16))
+#define fm10k_tlv_attr_get_u32(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(u32))
+#define fm10k_tlv_attr_get_u64(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(u64))
+#define fm10k_tlv_attr_get_s8(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(s8))
+#define fm10k_tlv_attr_get_s16(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(s16))
+#define fm10k_tlv_attr_get_s32(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(s32))
+#define fm10k_tlv_attr_get_s64(attr, ptr) \
+		fm10k_tlv_attr_get_value(attr, ptr, sizeof(s64))
+s32 fm10k_tlv_attr_put_le_struct(u32 *, u16, const void *, u32);
+s32 fm10k_tlv_attr_get_le_struct(u32 *, void *, u32);
+s32 fm10k_tlv_msg_parse(struct fm10k_hw *, u32 *, struct fm10k_mbx_info *,
+			const struct fm10k_msg_data *);
+s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results,
+			struct fm10k_mbx_info *);
+
+#define FM10K_TLV_MSG_ID_TEST	0
+
+enum fm10k_tlv_test_attr_id {
+	FM10K_TEST_MSG_UNSET,
+	FM10K_TEST_MSG_STRING,
+	FM10K_TEST_MSG_MAC_ADDR,
+	FM10K_TEST_MSG_U8,
+	FM10K_TEST_MSG_U16,
+	FM10K_TEST_MSG_U32,
+	FM10K_TEST_MSG_U64,
+	FM10K_TEST_MSG_S8,
+	FM10K_TEST_MSG_S16,
+	FM10K_TEST_MSG_S32,
+	FM10K_TEST_MSG_S64,
+	FM10K_TEST_MSG_LE_STRUCT,
+	FM10K_TEST_MSG_NESTED,
+	FM10K_TEST_MSG_RESULT,
+	FM10K_TEST_MSG_MAX
+};
+
+extern const struct fm10k_tlv_attr fm10k_tlv_msg_test_attr[];
+void fm10k_tlv_msg_test_create(u32 *, u32);
+s32 fm10k_tlv_msg_test(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+
+#define FM10K_TLV_MSG_TEST_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_TLV_MSG_ID_TEST, fm10k_tlv_msg_test_attr, func)
+#define FM10K_TLV_MSG_ERROR_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_TLV_ERROR, NULL, func)
+#endif /* _FM10K_MSG_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
new file mode 100644
index 000000000..63968c5d7
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -0,0 +1,768 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#ifndef _FM10K_TYPE_H_
+#define _FM10K_TYPE_H_
+
+/* forward declaration */
+struct fm10k_hw;
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/etherdevice.h>
+
+#include "fm10k_mbx.h"
+
+#define FM10K_DEV_ID_PF			0x15A4
+#define FM10K_DEV_ID_VF			0x15A5
+#define FM10K_DEV_ID_SDI_FM10420_QDA2	0x15D0
+#define FM10K_DEV_ID_SDI_FM10420_DA2	0x15D5
+
+#define FM10K_MAX_QUEUES		256
+#define FM10K_MAX_QUEUES_PF		128
+#define FM10K_MAX_QUEUES_POOL		16
+
+#define FM10K_48_BIT_MASK		0x0000FFFFFFFFFFFFull
+#define FM10K_STAT_VALID		0x80000000
+
+/* PCI Bus Info */
+#define FM10K_PCIE_LINK_CAP		0x7C
+#define FM10K_PCIE_LINK_STATUS		0x82
+#define FM10K_PCIE_LINK_WIDTH		0x3F0
+#define FM10K_PCIE_LINK_WIDTH_1		0x10
+#define FM10K_PCIE_LINK_WIDTH_2		0x20
+#define FM10K_PCIE_LINK_WIDTH_4		0x40
+#define FM10K_PCIE_LINK_WIDTH_8		0x80
+#define FM10K_PCIE_LINK_SPEED		0xF
+#define FM10K_PCIE_LINK_SPEED_2500	0x1
+#define FM10K_PCIE_LINK_SPEED_5000	0x2
+#define FM10K_PCIE_LINK_SPEED_8000	0x3
+
+/* PCIe payload size */
+#define FM10K_PCIE_DEV_CAP			0x74
+#define FM10K_PCIE_DEV_CAP_PAYLOAD		0x07
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_128		0x00
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_256		0x01
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_512		0x02
+#define FM10K_PCIE_DEV_CTRL			0x78
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD		0xE0
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_128		0x00
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_256		0x20
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_512		0x40
+
+/* PCIe MSI-X Capability info */
+#define FM10K_PCI_MSIX_MSG_CTRL			0xB2
+#define FM10K_PCI_MSIX_MSG_CTRL_TBL_SZ_MASK	0x7FF
+#define FM10K_MAX_MSIX_VECTORS			256
+#define FM10K_MAX_VECTORS_PF			256
+#define FM10K_MAX_VECTORS_POOL			32
+
+/* PCIe SR-IOV Info */
+#define FM10K_PCIE_SRIOV_CTRL			0x190
+#define FM10K_PCIE_SRIOV_CTRL_VFARI		0x10
+
+#define FM10K_ERR_PARAM				-2
+#define FM10K_ERR_NO_RESOURCES			-3
+#define FM10K_ERR_REQUESTS_PENDING		-4
+#define FM10K_ERR_RESET_REQUESTED		-5
+#define FM10K_ERR_DMA_PENDING			-6
+#define FM10K_ERR_RESET_FAILED			-7
+#define FM10K_ERR_INVALID_MAC_ADDR		-8
+#define FM10K_ERR_INVALID_VALUE			-9
+#define FM10K_NOT_IMPLEMENTED			0x7FFFFFFF
+
+/* Start of PF registers */
+#define FM10K_CTRL		0x0000
+#define FM10K_CTRL_BAR4_ALLOWED			0x00000004
+
+#define FM10K_CTRL_EXT		0x0001
+#define FM10K_GCR		0x0003
+#define FM10K_GCR_EXT		0x0005
+
+/* Interrupt control registers */
+#define FM10K_EICR		0x0006
+#define FM10K_EICR_FAULT_MASK			0x0000003F
+#define FM10K_EICR_MAILBOX			0x00000040
+#define FM10K_EICR_SWITCHREADY			0x00000080
+#define FM10K_EICR_SWITCHNOTREADY		0x00000100
+#define FM10K_EICR_SWITCHINTERRUPT		0x00000200
+#define FM10K_EICR_VFLR				0x00000800
+#define FM10K_EICR_MAXHOLDTIME			0x00001000
+#define FM10K_EIMR		0x0007
+#define FM10K_EIMR_PCA_FAULT			0x00000001
+#define FM10K_EIMR_THI_FAULT			0x00000010
+#define FM10K_EIMR_FUM_FAULT			0x00000400
+#define FM10K_EIMR_MAILBOX			0x00001000
+#define FM10K_EIMR_SWITCHREADY			0x00004000
+#define FM10K_EIMR_SWITCHNOTREADY		0x00010000
+#define FM10K_EIMR_SWITCHINTERRUPT		0x00040000
+#define FM10K_EIMR_SRAMERROR			0x00100000
+#define FM10K_EIMR_VFLR				0x00400000
+#define FM10K_EIMR_MAXHOLDTIME			0x01000000
+#define FM10K_EIMR_ALL				0x55555555
+#define FM10K_EIMR_DISABLE(NAME)		((FM10K_EIMR_ ## NAME) << 0)
+#define FM10K_EIMR_ENABLE(NAME)			((FM10K_EIMR_ ## NAME) << 1)
+#define FM10K_FAULT_ADDR_LO		0x0
+#define FM10K_FAULT_ADDR_HI		0x1
+#define FM10K_FAULT_SPECINFO		0x2
+#define FM10K_FAULT_FUNC		0x3
+#define FM10K_FAULT_SIZE		0x4
+#define FM10K_FAULT_FUNC_VALID			0x00008000
+#define FM10K_FAULT_FUNC_PF			0x00004000
+#define FM10K_FAULT_FUNC_VF_MASK		0x00003F00
+#define FM10K_FAULT_FUNC_VF_SHIFT		8
+#define FM10K_FAULT_FUNC_TYPE_MASK		0x000000FF
+
+#define FM10K_PCA_FAULT		0x0008
+#define FM10K_THI_FAULT		0x0010
+#define FM10K_FUM_FAULT		0x001C
+
+/* Rx queue timeout indicator */
+#define FM10K_MAXHOLDQ(_n)	((_n) + 0x0020)
+
+/* Switch Manager info */
+#define FM10K_SM_AREA(_n)	((_n) + 0x0028)
+
+/* GLORT mapping registers */
+#define FM10K_DGLORTMAP(_n)	((_n) + 0x0030)
+#define FM10K_DGLORT_COUNT			8
+#define FM10K_DGLORTMAP_MASK_SHIFT		16
+#define FM10K_DGLORTMAP_ANY			0x00000000
+#define FM10K_DGLORTMAP_NONE			0x0000FFFF
+#define FM10K_DGLORTMAP_ZERO			0xFFFF0000
+#define FM10K_DGLORTDEC(_n)	((_n) + 0x0038)
+#define FM10K_DGLORTDEC_VSILENGTH_SHIFT		4
+#define FM10K_DGLORTDEC_VSIBASE_SHIFT		7
+#define FM10K_DGLORTDEC_PCLENGTH_SHIFT		14
+#define FM10K_DGLORTDEC_QBASE_SHIFT		16
+#define FM10K_DGLORTDEC_RSSLENGTH_SHIFT		24
+#define FM10K_DGLORTDEC_INNERRSS_ENABLE		0x08000000
+#define FM10K_TUNNEL_CFG	0x0040
+#define FM10K_TUNNEL_CFG_NVGRE_SHIFT		16
+#define FM10K_TUNNEL_CFG_GENEVE	0x0041
+#define FM10K_SWPRI_MAP(_n)	((_n) + 0x0050)
+#define FM10K_SWPRI_MAX		16
+#define FM10K_RSSRK(_n, _m)	(((_n) * 0x10) + (_m) + 0x0800)
+#define FM10K_RSSRK_SIZE	10
+#define FM10K_RSSRK_ENTRIES_PER_REG		4
+#define FM10K_RETA(_n, _m)	(((_n) * 0x20) + (_m) + 0x1000)
+#define FM10K_RETA_SIZE		32
+#define FM10K_RETA_ENTRIES_PER_REG		4
+#define FM10K_MAX_RSS_INDICES	128
+
+/* Rate limiting registers */
+#define FM10K_TC_CREDIT(_n)	((_n) + 0x2000)
+#define FM10K_TC_CREDIT_CREDIT_MASK		0x001FFFFF
+#define FM10K_TC_MAXCREDIT(_n)	((_n) + 0x2040)
+#define FM10K_TC_MAXCREDIT_64K			0x00010000
+#define FM10K_TC_RATE(_n)	((_n) + 0x2080)
+#define FM10K_TC_RATE_QUANTA_MASK		0x0000FFFF
+#define FM10K_TC_RATE_INTERVAL_4US_GEN1		0x00020000
+#define FM10K_TC_RATE_INTERVAL_4US_GEN2		0x00040000
+#define FM10K_TC_RATE_INTERVAL_4US_GEN3		0x00080000
+
+/* DMA control registers */
+#define FM10K_DMA_CTRL		0x20C3
+#define FM10K_DMA_CTRL_TX_ENABLE		0x00000001
+#define FM10K_DMA_CTRL_TX_ACTIVE		0x00000008
+#define FM10K_DMA_CTRL_RX_ENABLE		0x00000010
+#define FM10K_DMA_CTRL_RX_ACTIVE		0x00000080
+#define FM10K_DMA_CTRL_RX_DESC_SIZE		0x00000100
+#define FM10K_DMA_CTRL_MINMSS_64		0x00008000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN3	0x04800000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN2	0x04000000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN1	0x03800000
+#define FM10K_DMA_CTRL_DATAPATH_RESET		0x20000000
+#define FM10K_DMA_CTRL_32_DESC			0x00000000
+
+#define FM10K_DMA_CTRL2		0x20C4
+#define FM10K_DMA_CTRL2_SWITCH_READY		0x00002000
+
+/* TSO flags configuration
+ * First packet contains all flags except for fin and psh
+ * Middle packet contains only urg and ack
+ * Last packet contains urg, ack, fin, and psh
+ */
+#define FM10K_TSO_FLAGS_LOW		0x00300FF6
+#define FM10K_TSO_FLAGS_HI		0x00000039
+#define FM10K_DTXTCPFLGL	0x20C5
+#define FM10K_DTXTCPFLGH	0x20C6
+
+#define FM10K_TPH_CTRL		0x20C7
+#define FM10K_MRQC(_n)		((_n) + 0x2100)
+#define FM10K_MRQC_TCP_IPV4			0x00000001
+#define FM10K_MRQC_IPV4				0x00000002
+#define FM10K_MRQC_IPV6				0x00000010
+#define FM10K_MRQC_TCP_IPV6			0x00000020
+#define FM10K_MRQC_UDP_IPV4			0x00000040
+#define FM10K_MRQC_UDP_IPV6			0x00000080
+
+#define FM10K_TQMAP(_n)		((_n) + 0x2800)
+#define FM10K_TQMAP_TABLE_SIZE			2048
+#define FM10K_RQMAP(_n)		((_n) + 0x3000)
+
+/* Hardware Statistics */
+#define FM10K_STATS_TIMEOUT		0x3800
+#define FM10K_STATS_UR			0x3801
+#define FM10K_STATS_CA			0x3802
+#define FM10K_STATS_UM			0x3803
+#define FM10K_STATS_XEC			0x3804
+#define FM10K_STATS_VLAN_DROP		0x3805
+#define FM10K_STATS_LOOPBACK_DROP	0x3806
+#define FM10K_STATS_NODESC_DROP		0x3807
+
+/* PCIe state registers */
+#define FM10K_PHYADDR		0x381C
+
+/* Rx ring registers */
+#define FM10K_RDBAL(_n)		((0x40 * (_n)) + 0x4000)
+#define FM10K_RDBAH(_n)		((0x40 * (_n)) + 0x4001)
+#define FM10K_RDLEN(_n)		((0x40 * (_n)) + 0x4002)
+#define FM10K_TPH_RXCTRL(_n)	((0x40 * (_n)) + 0x4003)
+#define FM10K_TPH_RXCTRL_DESC_TPHEN		0x00000020
+#define FM10K_TPH_RXCTRL_DESC_RROEN		0x00000200
+#define FM10K_TPH_RXCTRL_DATA_WROEN		0x00002000
+#define FM10K_TPH_RXCTRL_HDR_WROEN		0x00008000
+#define FM10K_RDH(_n)		((0x40 * (_n)) + 0x4004)
+#define FM10K_RDT(_n)		((0x40 * (_n)) + 0x4005)
+#define FM10K_RXQCTL(_n)	((0x40 * (_n)) + 0x4006)
+#define FM10K_RXQCTL_ENABLE			0x00000001
+#define FM10K_RXQCTL_PF				0x000000FC
+#define FM10K_RXQCTL_VF_SHIFT			2
+#define FM10K_RXQCTL_VF				0x00000100
+#define FM10K_RXQCTL_ID_MASK	(FM10K_RXQCTL_PF | FM10K_RXQCTL_VF)
+#define FM10K_RXDCTL(_n)	((0x40 * (_n)) + 0x4007)
+#define FM10K_RXDCTL_WRITE_BACK_MIN_DELAY	0x00000001
+#define FM10K_RXDCTL_DROP_ON_EMPTY		0x00000200
+#define FM10K_RXINT(_n)		((0x40 * (_n)) + 0x4008)
+#define FM10K_SRRCTL(_n)	((0x40 * (_n)) + 0x4009)
+#define FM10K_SRRCTL_BSIZEPKT_SHIFT		8 /* shift _right_ */
+#define FM10K_SRRCTL_LOOPBACK_SUPPRESS		0x40000000
+#define FM10K_SRRCTL_BUFFER_CHAINING_EN		0x80000000
+
+/* Rx Statistics */
+#define FM10K_QPRC(_n)		((0x40 * (_n)) + 0x400A)
+#define FM10K_QPRDC(_n)		((0x40 * (_n)) + 0x400B)
+#define FM10K_QBRC_L(_n)	((0x40 * (_n)) + 0x400C)
+#define FM10K_QBRC_H(_n)	((0x40 * (_n)) + 0x400D)
+
+/* Rx GLORT register */
+#define FM10K_RX_SGLORT(_n)		((0x40 * (_n)) + 0x400E)
+
+/* Tx ring registers */
+#define FM10K_TDBAL(_n)		((0x40 * (_n)) + 0x8000)
+#define FM10K_TDBAH(_n)		((0x40 * (_n)) + 0x8001)
+#define FM10K_TDLEN(_n)		((0x40 * (_n)) + 0x8002)
+/* When fist initialized, VFs need to know the Interrupt Throttle Rate (ITR)
+ * scale which is based on the PCIe speed but the speed information in the PCI
+ * configuration space may not be accurate. The PF already knows the ITR scale
+ * but there is no defined method to pass that information from the PF to the
+ * VF. This is accomplished during VF initialization by temporarily co-opting
+ * the yet-to-be-used TDLEN register to have the PF store the ITR shift for
+ * the VF to retrieve before the VF needs to use the TDLEN register for its
+ * intended purpose, i.e. before the Tx resources are allocated.
+ */
+#define FM10K_TDLEN_ITR_SCALE_SHIFT		9
+#define FM10K_TDLEN_ITR_SCALE_MASK		0x00000E00
+#define FM10K_TDLEN_ITR_SCALE_GEN1		2
+#define FM10K_TDLEN_ITR_SCALE_GEN2		1
+#define FM10K_TDLEN_ITR_SCALE_GEN3		0
+#define FM10K_TPH_TXCTRL(_n)	((0x40 * (_n)) + 0x8003)
+#define FM10K_TPH_TXCTRL_DESC_TPHEN		0x00000020
+#define FM10K_TPH_TXCTRL_DESC_RROEN		0x00000200
+#define FM10K_TPH_TXCTRL_DESC_WROEN		0x00000800
+#define FM10K_TPH_TXCTRL_DATA_RROEN		0x00002000
+#define FM10K_TDH(_n)		((0x40 * (_n)) + 0x8004)
+#define FM10K_TDT(_n)		((0x40 * (_n)) + 0x8005)
+#define FM10K_TXDCTL(_n)	((0x40 * (_n)) + 0x8006)
+#define FM10K_TXDCTL_ENABLE			0x00004000
+#define FM10K_TXDCTL_MAX_TIME_SHIFT		16
+#define FM10K_TXQCTL(_n)	((0x40 * (_n)) + 0x8007)
+#define FM10K_TXQCTL_PF				0x0000003F
+#define FM10K_TXQCTL_VF				0x00000040
+#define FM10K_TXQCTL_ID_MASK	(FM10K_TXQCTL_PF | FM10K_TXQCTL_VF)
+#define FM10K_TXQCTL_PC_SHIFT			7
+#define FM10K_TXQCTL_PC_MASK			0x00000380
+#define FM10K_TXQCTL_TC_SHIFT			10
+#define FM10K_TXQCTL_VID_SHIFT			16
+#define FM10K_TXQCTL_VID_MASK			0x0FFF0000
+#define FM10K_TXQCTL_UNLIMITED_BW		0x10000000
+#define FM10K_TXINT(_n)		((0x40 * (_n)) + 0x8008)
+
+/* Tx Statistics */
+#define FM10K_QPTC(_n)		((0x40 * (_n)) + 0x8009)
+#define FM10K_QBTC_L(_n)	((0x40 * (_n)) + 0x800A)
+#define FM10K_QBTC_H(_n)	((0x40 * (_n)) + 0x800B)
+
+/* Tx Push registers */
+#define FM10K_TQDLOC(_n)	((0x40 * (_n)) + 0x800C)
+#define FM10K_TQDLOC_BASE_32_DESC		0x08
+#define FM10K_TQDLOC_SIZE_32_DESC		0x00050000
+
+/* Tx GLORT registers */
+#define FM10K_TX_SGLORT(_n)	((0x40 * (_n)) + 0x800D)
+#define FM10K_PFVTCTL(_n)	((0x40 * (_n)) + 0x800E)
+#define FM10K_PFVTCTL_FTAG_DESC_ENABLE		0x00000001
+
+/* Interrupt moderation and control registers */
+#define FM10K_INT_MAP(_n)	((_n) + 0x10080)
+#define FM10K_INT_MAP_TIMER0			0x00000000
+#define FM10K_INT_MAP_TIMER1			0x00000100
+#define FM10K_INT_MAP_IMMEDIATE			0x00000200
+#define FM10K_INT_MAP_DISABLE			0x00000300
+#define FM10K_MSIX_VECTOR_MASK(_n)	((0x4 * (_n)) + 0x11003)
+#define FM10K_INT_CTRL		0x12000
+#define FM10K_INT_CTRL_ENABLEMODERATOR		0x00000400
+#define FM10K_ITR(_n)		((_n) + 0x12400)
+#define FM10K_ITR_INTERVAL1_SHIFT		12
+#define FM10K_ITR_PENDING2			0x10000000
+#define FM10K_ITR_AUTOMASK			0x20000000
+#define FM10K_ITR_MASK_SET			0x40000000
+#define FM10K_ITR_MASK_CLEAR			0x80000000
+#define FM10K_ITR2(_n)		((0x2 * (_n)) + 0x12800)
+#define FM10K_ITR_REG_COUNT			768
+#define FM10K_ITR_REG_COUNT_PF			256
+
+/* Switch manager interrupt registers */
+#define FM10K_IP		0x13000
+#define FM10K_IP_NOTINRESET			0x00000100
+
+/* VLAN registers */
+#define FM10K_VLAN_TABLE(_n, _m)	((0x80 * (_n)) + (_m) + 0x14000)
+#define FM10K_VLAN_TABLE_SIZE			128
+
+/* VLAN specific message offsets */
+#define FM10K_VLAN_TABLE_VID_MAX		4096
+#define FM10K_VLAN_TABLE_VSI_MAX		64
+#define FM10K_VLAN_LENGTH_SHIFT			16
+#define FM10K_VLAN_CLEAR			BIT(15)
+#define FM10K_VLAN_OVERRIDE			FM10K_VLAN_CLEAR
+#define FM10K_VLAN_ALL \
+	((FM10K_VLAN_TABLE_VID_MAX - 1) << FM10K_VLAN_LENGTH_SHIFT)
+
+/* VF FLR event notification registers */
+#define FM10K_PFVFLRE(_n)	((0x1 * (_n)) + 0x18844)
+#define FM10K_PFVFLREC(_n)	((0x1 * (_n)) + 0x18846)
+
+/* Defines for size of uncacheable memories */
+#define FM10K_UC_ADDR_START	0x000000	/* start of standard regs */
+#define FM10K_UC_ADDR_END	0x100000	/* end of standard regs */
+#define FM10K_UC_ADDR_SIZE	(FM10K_UC_ADDR_END - FM10K_UC_ADDR_START)
+
+/* Define timeouts for resets and disables */
+#define FM10K_QUEUE_DISABLE_TIMEOUT		100
+#define FM10K_RESET_TIMEOUT			150
+
+/* Maximum supported combined inner and outer header length for encapsulation */
+#define FM10K_TUNNEL_HEADER_LENGTH	184
+
+/* VF registers */
+#define FM10K_VFCTRL		0x00000
+#define FM10K_VFCTRL_RST			0x00000008
+#define FM10K_VFINT_MAP		0x00030
+#define FM10K_VFSYSTIME		0x00040
+#define FM10K_VFITR(_n)		((_n) + 0x00060)
+
+enum fm10k_int_source {
+	fm10k_int_mailbox		= 0,
+	fm10k_int_pcie_fault		= 1,
+	fm10k_int_switch_up_down	= 2,
+	fm10k_int_switch_event		= 3,
+	fm10k_int_sram			= 4,
+	fm10k_int_vflr			= 5,
+	fm10k_int_max_hold_time		= 6,
+	fm10k_int_sources_max_pf
+};
+
+/* PCIe bus speeds */
+enum fm10k_bus_speed {
+	fm10k_bus_speed_unknown	= 0,
+	fm10k_bus_speed_2500	= 2500,
+	fm10k_bus_speed_5000	= 5000,
+	fm10k_bus_speed_8000	= 8000,
+	fm10k_bus_speed_reserved
+};
+
+/* PCIe bus widths */
+enum fm10k_bus_width {
+	fm10k_bus_width_unknown	= 0,
+	fm10k_bus_width_pcie_x1	= 1,
+	fm10k_bus_width_pcie_x2	= 2,
+	fm10k_bus_width_pcie_x4	= 4,
+	fm10k_bus_width_pcie_x8	= 8,
+	fm10k_bus_width_reserved
+};
+
+/* PCIe payload sizes */
+enum fm10k_bus_payload {
+	fm10k_bus_payload_unknown = 0,
+	fm10k_bus_payload_128	  = 1,
+	fm10k_bus_payload_256	  = 2,
+	fm10k_bus_payload_512	  = 3,
+	fm10k_bus_payload_reserved
+};
+
+/* Bus parameters */
+struct fm10k_bus_info {
+	enum fm10k_bus_speed speed;
+	enum fm10k_bus_width width;
+	enum fm10k_bus_payload payload;
+};
+
+/* Statistics related declarations */
+struct fm10k_hw_stat {
+	u64 count;
+	u32 base_l;
+	u32 base_h;
+};
+
+struct fm10k_hw_stats_q {
+	struct fm10k_hw_stat tx_bytes;
+	struct fm10k_hw_stat tx_packets;
+#define tx_stats_idx	tx_packets.base_h
+	struct fm10k_hw_stat rx_bytes;
+	struct fm10k_hw_stat rx_packets;
+#define rx_stats_idx	rx_packets.base_h
+	struct fm10k_hw_stat rx_drops;
+};
+
+struct fm10k_hw_stats {
+	struct fm10k_hw_stat	timeout;
+#define stats_idx	timeout.base_h
+	struct fm10k_hw_stat	ur;
+	struct fm10k_hw_stat	ca;
+	struct fm10k_hw_stat	um;
+	struct fm10k_hw_stat	xec;
+	struct fm10k_hw_stat	vlan_drop;
+	struct fm10k_hw_stat	loopback_drop;
+	struct fm10k_hw_stat	nodesc_drop;
+	struct fm10k_hw_stats_q q[FM10K_MAX_QUEUES_PF];
+};
+
+/* Establish DGLORT feature priority */
+enum fm10k_dglortdec_idx {
+	fm10k_dglort_default	= 0,
+	fm10k_dglort_vf_rsvd0	= 1,
+	fm10k_dglort_vf_rss	= 2,
+	fm10k_dglort_pf_rsvd0	= 3,
+	fm10k_dglort_pf_queue	= 4,
+	fm10k_dglort_pf_vsi	= 5,
+	fm10k_dglort_pf_rsvd1	= 6,
+	fm10k_dglort_pf_rss	= 7
+};
+
+struct fm10k_dglort_cfg {
+	u16 glort;	/* GLORT base */
+	u16 queue_b;	/* Base value for queue */
+	u8  vsi_b;	/* Base value for VSI */
+	u8  idx;	/* index of DGLORTDEC entry */
+	u8  rss_l;	/* RSS indices */
+	u8  pc_l;	/* Priority Class indices */
+	u8  vsi_l;	/* Number of bits from GLORT used to determine VSI */
+	u8  queue_l;	/* Number of bits from GLORT used to determine queue */
+	u8  shared_l;	/* Ignored bits from GLORT resulting in shared VSI */
+	u8  inner_rss;	/* Boolean value if inner header is used for RSS */
+};
+
+enum fm10k_pca_fault {
+	PCA_NO_FAULT,
+	PCA_UNMAPPED_ADDR,
+	PCA_BAD_QACCESS_PF,
+	PCA_BAD_QACCESS_VF,
+	PCA_MALICIOUS_REQ,
+	PCA_POISONED_TLP,
+	PCA_TLP_ABORT,
+	__PCA_MAX
+};
+
+enum fm10k_thi_fault {
+	THI_NO_FAULT,
+	THI_MAL_DIS_Q_FAULT,
+	__THI_MAX
+};
+
+enum fm10k_fum_fault {
+	FUM_NO_FAULT,
+	FUM_UNMAPPED_ADDR,
+	FUM_POISONED_TLP,
+	FUM_BAD_VF_QACCESS,
+	FUM_ADD_DECODE_ERR,
+	FUM_RO_ERROR,
+	FUM_QPRC_CRC_ERROR,
+	FUM_CSR_TIMEOUT,
+	FUM_INVALID_TYPE,
+	FUM_INVALID_LENGTH,
+	FUM_INVALID_BE,
+	FUM_INVALID_ALIGN,
+	__FUM_MAX
+};
+
+struct fm10k_fault {
+	u64 address;	/* Address at the time fault was detected */
+	u32 specinfo;	/* Extra info on this fault (fault dependent) */
+	u8 type;	/* Fault value dependent on subunit */
+	u8 func;	/* Function number of the fault */
+};
+
+struct fm10k_mac_ops {
+	/* basic bring-up and tear-down */
+	s32 (*reset_hw)(struct fm10k_hw *);
+	s32 (*init_hw)(struct fm10k_hw *);
+	s32 (*start_hw)(struct fm10k_hw *);
+	s32 (*stop_hw)(struct fm10k_hw *);
+	s32 (*get_bus_info)(struct fm10k_hw *);
+	s32 (*get_host_state)(struct fm10k_hw *, bool *);
+	s32 (*request_lport_map)(struct fm10k_hw *);
+	s32 (*update_vlan)(struct fm10k_hw *, u32, u8, bool);
+	s32 (*read_mac_addr)(struct fm10k_hw *);
+	s32 (*update_uc_addr)(struct fm10k_hw *, u16, const u8 *,
+			      u16, bool, u8);
+	s32 (*update_mc_addr)(struct fm10k_hw *, u16, const u8 *, u16, bool);
+	s32 (*update_xcast_mode)(struct fm10k_hw *, u16, u8);
+	void (*update_int_moderator)(struct fm10k_hw *);
+	s32  (*update_lport_state)(struct fm10k_hw *, u16, u16, bool);
+	void (*update_hw_stats)(struct fm10k_hw *, struct fm10k_hw_stats *);
+	void (*rebind_hw_stats)(struct fm10k_hw *, struct fm10k_hw_stats *);
+	s32 (*configure_dglort_map)(struct fm10k_hw *,
+				    struct fm10k_dglort_cfg *);
+	void (*set_dma_mask)(struct fm10k_hw *, u64);
+	s32 (*get_fault)(struct fm10k_hw *, int, struct fm10k_fault *);
+};
+
+enum fm10k_mac_type {
+	fm10k_mac_unknown = 0,
+	fm10k_mac_pf,
+	fm10k_mac_vf,
+	fm10k_num_macs
+};
+
+struct fm10k_mac_info {
+	struct fm10k_mac_ops ops;
+	enum fm10k_mac_type type;
+	u8 addr[ETH_ALEN];
+	u8 perm_addr[ETH_ALEN];
+	u16 default_vid;
+	u16 max_msix_vectors;
+	u16 max_queues;
+	bool vlan_override;
+	bool get_host_state;
+	bool tx_ready;
+	u32 dglort_map;
+	u8 itr_scale;
+	u64 reset_while_pending;
+};
+
+struct fm10k_swapi_table_info {
+	u32 used;
+	u32 avail;
+};
+
+struct fm10k_swapi_info {
+	u32 status;
+	struct fm10k_swapi_table_info mac;
+	struct fm10k_swapi_table_info nexthop;
+	struct fm10k_swapi_table_info ffu;
+};
+
+enum fm10k_xcast_modes {
+	FM10K_XCAST_MODE_ALLMULTI	= 0,
+	FM10K_XCAST_MODE_MULTI		= 1,
+	FM10K_XCAST_MODE_PROMISC	= 2,
+	FM10K_XCAST_MODE_NONE		= 3,
+	FM10K_XCAST_MODE_DISABLE	= 4
+};
+
+#define FM10K_VF_TC_MAX		100000	/* 100,000 Mb/s aka 100Gb/s */
+#define FM10K_VF_TC_MIN		1	/* 1 Mb/s is the slowest rate */
+
+struct fm10k_vf_info {
+	/* mbx must be first field in struct unless all default IOV message
+	 * handlers are redone as the assumption is that vf_info starts
+	 * at the same offset as the mailbox
+	 */
+	struct fm10k_mbx_info	mbx;		/* PF side of VF mailbox */
+	struct fm10k_hw_stats_q	stats[FM10K_MAX_QUEUES_POOL];
+	int			rate;		/* Tx BW cap as defined by OS */
+	u16			glort;		/* resource tag for this VF */
+	u16			sw_vid;		/* Switch API assigned VLAN */
+	u16			pf_vid;		/* PF assigned Default VLAN */
+	u8			mac[ETH_ALEN];	/* PF Default MAC address */
+	u8			vsi;		/* VSI identifier */
+	u8			vf_idx;		/* which VF this is */
+	u8			vf_flags;	/* flags indicating what modes
+						 * are supported for the port
+						 */
+};
+
+#define FM10K_VF_FLAG_ALLMULTI_CAPABLE	(u8)(BIT(FM10K_XCAST_MODE_ALLMULTI))
+#define FM10K_VF_FLAG_MULTI_CAPABLE	(u8)(BIT(FM10K_XCAST_MODE_MULTI))
+#define FM10K_VF_FLAG_PROMISC_CAPABLE	(u8)(BIT(FM10K_XCAST_MODE_PROMISC))
+#define FM10K_VF_FLAG_NONE_CAPABLE	(u8)(BIT(FM10K_XCAST_MODE_NONE))
+#define FM10K_VF_FLAG_CAPABLE(vf_info)	((vf_info)->vf_flags & (u8)0xF)
+#define FM10K_VF_FLAG_ENABLED(vf_info)	((vf_info)->vf_flags >> 4)
+#define FM10K_VF_FLAG_SET_MODE(mode)	((u8)0x10 << (mode))
+#define FM10K_VF_FLAG_SET_MODE_NONE \
+	FM10K_VF_FLAG_SET_MODE(FM10K_XCAST_MODE_NONE)
+#define FM10K_VF_FLAG_MULTI_ENABLED \
+	(FM10K_VF_FLAG_SET_MODE(FM10K_XCAST_MODE_ALLMULTI) | \
+	 FM10K_VF_FLAG_SET_MODE(FM10K_XCAST_MODE_MULTI) | \
+	 FM10K_VF_FLAG_SET_MODE(FM10K_XCAST_MODE_PROMISC))
+
+struct fm10k_iov_ops {
+	/* IOV related bring-up and tear-down */
+	s32 (*assign_resources)(struct fm10k_hw *, u16, u16);
+	s32 (*configure_tc)(struct fm10k_hw *, u16, int);
+	s32 (*assign_int_moderator)(struct fm10k_hw *, u16);
+	s32 (*assign_default_mac_vlan)(struct fm10k_hw *,
+				       struct fm10k_vf_info *);
+	s32 (*reset_resources)(struct fm10k_hw *,
+			       struct fm10k_vf_info *);
+	s32 (*set_lport)(struct fm10k_hw *, struct fm10k_vf_info *, u16, u8);
+	void (*reset_lport)(struct fm10k_hw *, struct fm10k_vf_info *);
+	void (*update_stats)(struct fm10k_hw *, struct fm10k_hw_stats_q *, u16);
+};
+
+struct fm10k_iov_info {
+	struct fm10k_iov_ops ops;
+	u16 total_vfs;
+	u16 num_vfs;
+	u16 num_pools;
+};
+
+enum fm10k_devices {
+	fm10k_device_pf,
+	fm10k_device_vf,
+};
+
+struct fm10k_info {
+	enum fm10k_mac_type		mac;
+	s32				(*get_invariants)(struct fm10k_hw *);
+	const struct fm10k_mac_ops	*mac_ops;
+	const struct fm10k_iov_ops	*iov_ops;
+};
+
+struct fm10k_hw {
+	u32 __iomem *hw_addr;
+	void *back;
+	struct fm10k_mac_info mac;
+	struct fm10k_bus_info bus;
+	struct fm10k_bus_info bus_caps;
+	struct fm10k_iov_info iov;
+	struct fm10k_mbx_info mbx;
+	struct fm10k_swapi_info swapi;
+	u16 device_id;
+	u16 vendor_id;
+	u16 subsystem_device_id;
+	u16 subsystem_vendor_id;
+	u8 revision_id;
+};
+
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define FM10K_REQ_TX_DESCRIPTOR_MULTIPLE	8
+#define FM10K_REQ_RX_DESCRIPTOR_MULTIPLE	8
+
+/* Transmit Descriptor */
+struct fm10k_tx_desc {
+	__le64 buffer_addr;	/* Address of the descriptor's data buffer */
+	__le16 buflen;		/* Length of data to be DMAed */
+	__le16 vlan;		/* VLAN_ID and VPRI to be inserted in FTAG */
+	__le16 mss;		/* MSS for segmentation offload */
+	u8 hdrlen;		/* Header size for segmentation offload */
+	u8 flags;		/* Status and offload request flags */
+};
+
+/* Transmit Descriptor Cache Structure */
+struct fm10k_tx_desc_cache {
+	struct fm10k_tx_desc tx_desc[256];
+};
+
+#define FM10K_TXD_FLAG_INT	0x01
+#define FM10K_TXD_FLAG_TIME	0x02
+#define FM10K_TXD_FLAG_CSUM	0x04
+#define FM10K_TXD_FLAG_FTAG	0x10
+#define FM10K_TXD_FLAG_RS	0x20
+#define FM10K_TXD_FLAG_LAST	0x40
+#define FM10K_TXD_FLAG_DONE	0x80
+
+/* These macros are meant to enable optimal placement of the RS and INT
+ * bits.  It will point us to the last descriptor in the cache for either the
+ * start of the packet, or the end of the packet.  If the index is actually
+ * at the start of the FIFO it will point to the offset for the last index
+ * in the FIFO to prevent an unnecessary write.
+ */
+#define FM10K_TXD_WB_FIFO_SIZE	4
+
+/* Receive Descriptor - 32B */
+union fm10k_rx_desc {
+	struct {
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
+		__le64 reserved; /* Empty space, RSS hash */
+		__le64 timestamp;
+	} q; /* Read, Writeback, 64b quad-words */
+	struct {
+		__le32 data; /* RSS and header data */
+		__le32 rss;  /* RSS Hash */
+		__le32 staterr;
+		__le32 vlan_len;
+		__le32 glort; /* sglort/dglort */
+	} d; /* Writeback, 32b double-words */
+	struct {
+		__le16 pkt_info; /* RSS, Pkt type */
+		__le16 hdr_info; /* Splithdr, hdrlen, xC */
+		__le16 rss_lower;
+		__le16 rss_upper;
+		__le16 status; /* status/error */
+		__le16 csum_err; /* checksum or extended error value */
+		__le16 length; /* Packet length */
+		__le16 vlan; /* VLAN tag */
+		__le16 dglort;
+		__le16 sglort;
+	} w; /* Writeback, 16b words */
+};
+
+#define FM10K_RXD_RSSTYPE_MASK		0x000F
+enum fm10k_rdesc_rss_type {
+	FM10K_RSSTYPE_NONE	= 0x0,
+	FM10K_RSSTYPE_IPV4_TCP	= 0x1,
+	FM10K_RSSTYPE_IPV4	= 0x2,
+	FM10K_RSSTYPE_IPV6_TCP	= 0x3,
+	/* Reserved 0x4 */
+	FM10K_RSSTYPE_IPV6	= 0x5,
+	/* Reserved 0x6 */
+	FM10K_RSSTYPE_IPV4_UDP	= 0x7,
+	FM10K_RSSTYPE_IPV6_UDP	= 0x8
+	/* Reserved 0x9 - 0xF */
+};
+
+#define FM10K_RXD_HDR_INFO_XC_MASK	0x0006
+enum fm10k_rxdesc_xc {
+	FM10K_XC_UNICAST	= 0x0,
+	FM10K_XC_MULTICAST	= 0x4,
+	FM10K_XC_BROADCAST	= 0x6
+};
+
+#define FM10K_RXD_STATUS_DD		0x0001 /* Descriptor done */
+#define FM10K_RXD_STATUS_EOP		0x0002 /* End of packet */
+#define FM10K_RXD_STATUS_L4CS		0x0010 /* Indicates an L4 csum */
+#define FM10K_RXD_STATUS_L4CS2		0x0040 /* Inner header L4 csum */
+#define FM10K_RXD_STATUS_L4E2		0x0800 /* Inner header L4 csum err */
+#define FM10K_RXD_STATUS_IPE2		0x1000 /* Inner header IPv4 csum err */
+#define FM10K_RXD_STATUS_RXE		0x2000 /* Generic Rx error */
+#define FM10K_RXD_STATUS_L4E		0x4000 /* L4 csum error */
+#define FM10K_RXD_STATUS_IPE		0x8000 /* IPv4 csum error */
+
+#define FM10K_RXD_ERR_SWITCH_ERROR	0x0001 /* Switch found bad packet */
+#define FM10K_RXD_ERR_NO_DESCRIPTOR	0x0002 /* No descriptor available */
+#define FM10K_RXD_ERR_PP_ERROR		0x0004 /* RAM error during processing */
+#define FM10K_RXD_ERR_SWITCH_READY	0x0008 /* Link transition mid-packet */
+#define FM10K_RXD_ERR_TOO_BIG		0x0010 /* Pkt too big for single buf */
+
+struct fm10k_ftag {
+	__be16 swpri_type_user;
+	__be16 vlan;
+	__be16 sglort;
+	__be16 dglort;
+};
+
+#endif /* _FM10K_TYPE_H */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
new file mode 100644
index 000000000..dc8ccd378
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -0,0 +1,532 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2019 Intel Corporation. */
+
+#include "fm10k_vf.h"
+
+/**
+ *  fm10k_stop_hw_vf - Stop Tx/Rx units
+ *  @hw: pointer to hardware structure
+ *
+ **/
+static s32 fm10k_stop_hw_vf(struct fm10k_hw *hw)
+{
+	u8 *perm_addr = hw->mac.perm_addr;
+	u32 bal = 0, bah = 0, tdlen;
+	s32 err;
+	u16 i;
+
+	/* we need to disable the queues before taking further steps */
+	err = fm10k_stop_hw_generic(hw);
+	if (err && err != FM10K_ERR_REQUESTS_PENDING)
+		return err;
+
+	/* If permanent address is set then we need to restore it */
+	if (is_valid_ether_addr(perm_addr)) {
+		bal = (((u32)perm_addr[3]) << 24) |
+		      (((u32)perm_addr[4]) << 16) |
+		      (((u32)perm_addr[5]) << 8);
+		bah = (((u32)0xFF)	   << 24) |
+		      (((u32)perm_addr[0]) << 16) |
+		      (((u32)perm_addr[1]) << 8) |
+		       ((u32)perm_addr[2]);
+	}
+
+	/* restore default itr_scale for next VF initialization */
+	tdlen = hw->mac.itr_scale << FM10K_TDLEN_ITR_SCALE_SHIFT;
+
+	/* The queues have already been disabled so we just need to
+	 * update their base address registers
+	 */
+	for (i = 0; i < hw->mac.max_queues; i++) {
+		fm10k_write_reg(hw, FM10K_TDBAL(i), bal);
+		fm10k_write_reg(hw, FM10K_TDBAH(i), bah);
+		fm10k_write_reg(hw, FM10K_RDBAL(i), bal);
+		fm10k_write_reg(hw, FM10K_RDBAH(i), bah);
+		/* Restore ITR scale in software-defined mechanism in TDLEN
+		 * for next VF initialization. See definition of
+		 * FM10K_TDLEN_ITR_SCALE_SHIFT for more details on the use of
+		 * TDLEN here.
+		 */
+		fm10k_write_reg(hw, FM10K_TDLEN(i), tdlen);
+	}
+
+	return err;
+}
+
+/**
+ *  fm10k_reset_hw_vf - VF hardware reset
+ *  @hw: pointer to hardware structure
+ *
+ *  This function should return the hardware to a state similar to the
+ *  one it is in after just being initialized.
+ **/
+static s32 fm10k_reset_hw_vf(struct fm10k_hw *hw)
+{
+	s32 err;
+
+	/* shut down queues we own and reset DMA configuration */
+	err = fm10k_stop_hw_vf(hw);
+	if (err == FM10K_ERR_REQUESTS_PENDING)
+		hw->mac.reset_while_pending++;
+	else if (err)
+		return err;
+
+	/* Inititate VF reset */
+	fm10k_write_reg(hw, FM10K_VFCTRL, FM10K_VFCTRL_RST);
+
+	/* Flush write and allow 100us for reset to complete */
+	fm10k_write_flush(hw);
+	udelay(FM10K_RESET_TIMEOUT);
+
+	/* Clear reset bit and verify it was cleared */
+	fm10k_write_reg(hw, FM10K_VFCTRL, 0);
+	if (fm10k_read_reg(hw, FM10K_VFCTRL) & FM10K_VFCTRL_RST)
+		return FM10K_ERR_RESET_FAILED;
+
+	return 0;
+}
+
+/**
+ *  fm10k_init_hw_vf - VF hardware initialization
+ *  @hw: pointer to hardware structure
+ *
+ **/
+static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
+{
+	u32 tqdloc, tqdloc0 = ~fm10k_read_reg(hw, FM10K_TQDLOC(0));
+	s32 err;
+	u16 i;
+
+	/* verify we have at least 1 queue */
+	if (!~fm10k_read_reg(hw, FM10K_TXQCTL(0)) ||
+	    !~fm10k_read_reg(hw, FM10K_RXQCTL(0))) {
+		err = FM10K_ERR_NO_RESOURCES;
+		goto reset_max_queues;
+	}
+
+	/* determine how many queues we have */
+	for (i = 1; tqdloc0 && (i < FM10K_MAX_QUEUES_POOL); i++) {
+		/* verify the Descriptor cache offsets are increasing */
+		tqdloc = ~fm10k_read_reg(hw, FM10K_TQDLOC(i));
+		if (!tqdloc || (tqdloc == tqdloc0))
+			break;
+
+		/* check to verify the PF doesn't own any of our queues */
+		if (!~fm10k_read_reg(hw, FM10K_TXQCTL(i)) ||
+		    !~fm10k_read_reg(hw, FM10K_RXQCTL(i)))
+			break;
+	}
+
+	/* shut down queues we own and reset DMA configuration */
+	err = fm10k_disable_queues_generic(hw, i);
+	if (err)
+		goto reset_max_queues;
+
+	/* record maximum queue count */
+	hw->mac.max_queues = i;
+
+	/* fetch default VLAN and ITR scale */
+	hw->mac.default_vid = (fm10k_read_reg(hw, FM10K_TXQCTL(0)) &
+			       FM10K_TXQCTL_VID_MASK) >> FM10K_TXQCTL_VID_SHIFT;
+	/* Read the ITR scale from TDLEN. See the definition of
+	 * FM10K_TDLEN_ITR_SCALE_SHIFT for more information about how TDLEN is
+	 * used here.
+	 */
+	hw->mac.itr_scale = (fm10k_read_reg(hw, FM10K_TDLEN(0)) &
+			     FM10K_TDLEN_ITR_SCALE_MASK) >>
+			    FM10K_TDLEN_ITR_SCALE_SHIFT;
+
+	return 0;
+
+reset_max_queues:
+	hw->mac.max_queues = 0;
+
+	return err;
+}
+
+/* This structure defines the attibutes to be parsed below */
+const struct fm10k_tlv_attr fm10k_mac_vlan_msg_attr[] = {
+	FM10K_TLV_ATTR_U32(FM10K_MAC_VLAN_MSG_VLAN),
+	FM10K_TLV_ATTR_BOOL(FM10K_MAC_VLAN_MSG_SET),
+	FM10K_TLV_ATTR_MAC_ADDR(FM10K_MAC_VLAN_MSG_MAC),
+	FM10K_TLV_ATTR_MAC_ADDR(FM10K_MAC_VLAN_MSG_DEFAULT_MAC),
+	FM10K_TLV_ATTR_MAC_ADDR(FM10K_MAC_VLAN_MSG_MULTICAST),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_update_vlan_vf - Update status of VLAN ID in VLAN filter table
+ *  @hw: pointer to hardware structure
+ *  @vid: VLAN ID to add to table
+ *  @vsi: Reserved, should always be 0
+ *  @set: Indicates if this is a set or clear operation
+ *
+ *  This function adds or removes the corresponding VLAN ID from the VLAN
+ *  filter table for this VF.
+ **/
+static s32 fm10k_update_vlan_vf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[4];
+
+	/* verify the index is not set */
+	if (vsi)
+		return FM10K_ERR_PARAM;
+
+	/* clever trick to verify reserved bits in both vid and length */
+	if ((vid << 16 | vid) >> 28)
+		return FM10K_ERR_PARAM;
+
+	/* encode set bit into the VLAN ID */
+	if (!set)
+		vid |= FM10K_VLAN_CLEAR;
+
+	/* generate VLAN request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_MAC_VLAN);
+	fm10k_tlv_attr_put_u32(msg, FM10K_MAC_VLAN_MSG_VLAN, vid);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_msg_mac_vlan_vf - Read device MAC address from mailbox message
+ *  @hw: pointer to the HW structure
+ *  @results: Attributes for message
+ *  @mbx: unused mailbox data
+ *
+ *  This function should determine the MAC address for the VF
+ **/
+s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results,
+			  struct fm10k_mbx_info __always_unused *mbx)
+{
+	u8 perm_addr[ETH_ALEN];
+	u16 vid;
+	s32 err;
+
+	/* record MAC address requested */
+	err = fm10k_tlv_attr_get_mac_vlan(
+					results[FM10K_MAC_VLAN_MSG_DEFAULT_MAC],
+					perm_addr, &vid);
+	if (err)
+		return err;
+
+	ether_addr_copy(hw->mac.perm_addr, perm_addr);
+	hw->mac.default_vid = vid & (FM10K_VLAN_TABLE_VID_MAX - 1);
+	hw->mac.vlan_override = !!(vid & FM10K_VLAN_OVERRIDE);
+
+	return 0;
+}
+
+/**
+ *  fm10k_read_mac_addr_vf - Read device MAC address
+ *  @hw: pointer to the HW structure
+ *
+ *  This function should determine the MAC address for the VF
+ **/
+static s32 fm10k_read_mac_addr_vf(struct fm10k_hw *hw)
+{
+	u8 perm_addr[ETH_ALEN];
+	u32 base_addr;
+
+	base_addr = fm10k_read_reg(hw, FM10K_TDBAL(0));
+
+	/* last byte should be 0 */
+	if (base_addr << 24)
+		return  FM10K_ERR_INVALID_MAC_ADDR;
+
+	perm_addr[3] = (u8)(base_addr >> 24);
+	perm_addr[4] = (u8)(base_addr >> 16);
+	perm_addr[5] = (u8)(base_addr >> 8);
+
+	base_addr = fm10k_read_reg(hw, FM10K_TDBAH(0));
+
+	/* first byte should be all 1's */
+	if ((~base_addr) >> 24)
+		return  FM10K_ERR_INVALID_MAC_ADDR;
+
+	perm_addr[0] = (u8)(base_addr >> 16);
+	perm_addr[1] = (u8)(base_addr >> 8);
+	perm_addr[2] = (u8)(base_addr);
+
+	ether_addr_copy(hw->mac.perm_addr, perm_addr);
+	ether_addr_copy(hw->mac.addr, perm_addr);
+
+	return 0;
+}
+
+/**
+ *  fm10k_update_uc_addr_vf - Update device unicast addresses
+ *  @hw: pointer to the HW structure
+ *  @glort: unused
+ *  @mac: MAC address to add/remove from table
+ *  @vid: VLAN ID to add/remove from table
+ *  @add: Indicates if this is an add or remove operation
+ *  @flags: flags field to indicate add and secure - unused
+ *
+ *  This function is used to add or remove unicast MAC addresses for
+ *  the VF.
+ **/
+static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw,
+				   u16 __always_unused glort,
+				   const u8 *mac, u16 vid, bool add,
+				   u8 __always_unused flags)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[7];
+
+	/* verify VLAN ID is valid */
+	if (vid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* verify MAC address is valid */
+	if (!is_valid_ether_addr(mac))
+		return FM10K_ERR_PARAM;
+
+	/* verify we are not locked down on the MAC address */
+	if (is_valid_ether_addr(hw->mac.perm_addr) &&
+	    !ether_addr_equal(hw->mac.perm_addr, mac))
+		return FM10K_ERR_PARAM;
+
+	/* add bit to notify us if this is a set or clear operation */
+	if (!add)
+		vid |= FM10K_VLAN_CLEAR;
+
+	/* generate VLAN request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_MAC_VLAN);
+	fm10k_tlv_attr_put_mac_vlan(msg, FM10K_MAC_VLAN_MSG_MAC, mac, vid);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_mc_addr_vf - Update device multicast addresses
+ *  @hw: pointer to the HW structure
+ *  @glort: unused
+ *  @mac: MAC address to add/remove from table
+ *  @vid: VLAN ID to add/remove from table
+ *  @add: Indicates if this is an add or remove operation
+ *
+ *  This function is used to add or remove multicast MAC addresses for
+ *  the VF.
+ **/
+static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw,
+				   u16 __always_unused glort,
+				   const u8 *mac, u16 vid, bool add)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[7];
+
+	/* verify VLAN ID is valid */
+	if (vid >= FM10K_VLAN_TABLE_VID_MAX)
+		return FM10K_ERR_PARAM;
+
+	/* verify multicast address is valid */
+	if (!is_multicast_ether_addr(mac))
+		return FM10K_ERR_PARAM;
+
+	/* add bit to notify us if this is a set or clear operation */
+	if (!add)
+		vid |= FM10K_VLAN_CLEAR;
+
+	/* generate VLAN request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_MAC_VLAN);
+	fm10k_tlv_attr_put_mac_vlan(msg, FM10K_MAC_VLAN_MSG_MULTICAST,
+				    mac, vid);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_int_moderator_vf - Request update of interrupt moderator list
+ *  @hw: pointer to hardware structure
+ *
+ *  This function will issue a request to the PF to rescan our MSI-X table
+ *  and to update the interrupt moderator linked list.
+ **/
+static void fm10k_update_int_moderator_vf(struct fm10k_hw *hw)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[1];
+
+	/* generate MSI-X request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_MSIX);
+
+	/* load onto outgoing mailbox */
+	mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/* This structure defines the attibutes to be parsed below */
+const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[] = {
+	FM10K_TLV_ATTR_BOOL(FM10K_LPORT_STATE_MSG_DISABLE),
+	FM10K_TLV_ATTR_U8(FM10K_LPORT_STATE_MSG_XCAST_MODE),
+	FM10K_TLV_ATTR_BOOL(FM10K_LPORT_STATE_MSG_READY),
+	FM10K_TLV_ATTR_LAST
+};
+
+/**
+ *  fm10k_msg_lport_state_vf - Message handler for lport_state message from PF
+ *  @hw: Pointer to hardware structure
+ *  @results: pointer array containing parsed data
+ *  @mbx: Pointer to mailbox information structure
+ *
+ *  This handler is meant to capture the indication from the PF that we
+ *  are ready to bring up the interface.
+ **/
+s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results,
+			     struct fm10k_mbx_info __always_unused *mbx)
+{
+	hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ?
+			     FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO;
+
+	return 0;
+}
+
+/**
+ *  fm10k_update_lport_state_vf - Update device state in lower device
+ *  @hw: pointer to the HW structure
+ *  @glort: unused
+ *  @count: number of logical ports to enable - unused (always 1)
+ *  @enable: boolean value indicating if this is an enable or disable request
+ *
+ *  Notify the lower device of a state change.  If the lower device is
+ *  enabled we can add filters, if it is disabled all filters for this
+ *  logical port are flushed.
+ **/
+static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw,
+				       u16 __always_unused glort,
+				       u16 __always_unused count, bool enable)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[2];
+
+	/* reset glort mask 0 as we have to wait to be enabled */
+	hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
+
+	/* generate port state request */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_LPORT_STATE);
+	if (!enable)
+		fm10k_tlv_attr_put_bool(msg, FM10K_LPORT_STATE_MSG_DISABLE);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_xcast_mode_vf - Request update of multicast mode
+ *  @hw: pointer to hardware structure
+ *  @glort: unused
+ *  @mode: integer value indicating mode being requested
+ *
+ *  This function will attempt to request a higher mode for the port
+ *  so that it can enable either multicast, multicast promiscuous, or
+ *  promiscuous mode of operation.
+ **/
+static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw,
+				      u16 __always_unused glort, u8 mode)
+{
+	struct fm10k_mbx_info *mbx = &hw->mbx;
+	u32 msg[3];
+
+	if (mode > FM10K_XCAST_MODE_NONE)
+		return FM10K_ERR_PARAM;
+
+	/* generate message requesting to change xcast mode */
+	fm10k_tlv_msg_init(msg, FM10K_VF_MSG_ID_LPORT_STATE);
+	fm10k_tlv_attr_put_u8(msg, FM10K_LPORT_STATE_MSG_XCAST_MODE, mode);
+
+	/* load onto outgoing mailbox */
+	return mbx->ops.enqueue_tx(hw, mbx, msg);
+}
+
+/**
+ *  fm10k_update_hw_stats_vf - Updates hardware related statistics of VF
+ *  @hw: pointer to hardware structure
+ *  @stats: pointer to statistics structure
+ *
+ *  This function collects and aggregates per queue hardware statistics.
+ **/
+static void fm10k_update_hw_stats_vf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats)
+{
+	fm10k_update_hw_stats_q(hw, stats->q, 0, hw->mac.max_queues);
+}
+
+/**
+ *  fm10k_rebind_hw_stats_vf - Resets base for hardware statistics of VF
+ *  @hw: pointer to hardware structure
+ *  @stats: pointer to the stats structure to update
+ *
+ *  This function resets the base for queue hardware statistics.
+ **/
+static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw,
+				     struct fm10k_hw_stats *stats)
+{
+	/* Unbind Queue Statistics */
+	fm10k_unbind_hw_stats_q(stats->q, 0, hw->mac.max_queues);
+
+	/* Reinitialize bases for all stats */
+	fm10k_update_hw_stats_vf(hw, stats);
+}
+
+/**
+ *  fm10k_configure_dglort_map_vf - Configures GLORT entry and queues
+ *  @hw: pointer to hardware structure
+ *  @dglort: pointer to dglort configuration structure
+ *
+ *  Reads the configuration structure contained in dglort_cfg and uses
+ *  that information to then populate a DGLORTMAP/DEC entry and the queues
+ *  to which it has been assigned.
+ **/
+static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw,
+					 struct fm10k_dglort_cfg *dglort)
+{
+	/* verify the dglort pointer */
+	if (!dglort)
+		return FM10K_ERR_PARAM;
+
+	/* stub for now until we determine correct message for this */
+
+	return 0;
+}
+
+static const struct fm10k_msg_data fm10k_msg_data_vf[] = {
+	FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test),
+	FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_msg_mac_vlan_vf),
+	FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_msg_lport_state_vf),
+	FM10K_TLV_MSG_ERROR_HANDLER(fm10k_tlv_msg_error),
+};
+
+static const struct fm10k_mac_ops mac_ops_vf = {
+	.get_bus_info		= fm10k_get_bus_info_generic,
+	.reset_hw		= fm10k_reset_hw_vf,
+	.init_hw		= fm10k_init_hw_vf,
+	.start_hw		= fm10k_start_hw_generic,
+	.stop_hw		= fm10k_stop_hw_vf,
+	.update_vlan		= fm10k_update_vlan_vf,
+	.read_mac_addr		= fm10k_read_mac_addr_vf,
+	.update_uc_addr		= fm10k_update_uc_addr_vf,
+	.update_mc_addr		= fm10k_update_mc_addr_vf,
+	.update_xcast_mode	= fm10k_update_xcast_mode_vf,
+	.update_int_moderator	= fm10k_update_int_moderator_vf,
+	.update_lport_state	= fm10k_update_lport_state_vf,
+	.update_hw_stats	= fm10k_update_hw_stats_vf,
+	.rebind_hw_stats	= fm10k_rebind_hw_stats_vf,
+	.configure_dglort_map	= fm10k_configure_dglort_map_vf,
+	.get_host_state		= fm10k_get_host_state_generic,
+};
+
+static s32 fm10k_get_invariants_vf(struct fm10k_hw *hw)
+{
+	fm10k_get_invariants_generic(hw);
+
+	return fm10k_pfvf_mbx_init(hw, &hw->mbx, fm10k_msg_data_vf, 0);
+}
+
+const struct fm10k_info fm10k_vf_info = {
+	.mac		= fm10k_mac_vf,
+	.get_invariants	= fm10k_get_invariants_vf,
+	.mac_ops	= &mac_ops_vf,
+};
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.h b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h
new file mode 100644
index 000000000..787d0d570
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _FM10K_VF_H_
+#define _FM10K_VF_H_
+
+#include "fm10k_type.h"
+#include "fm10k_common.h"
+
+enum fm10k_vf_tlv_msg_id {
+	FM10K_VF_MSG_ID_TEST = 0,	/* msg ID reserved for testing */
+	FM10K_VF_MSG_ID_MSIX,
+	FM10K_VF_MSG_ID_MAC_VLAN,
+	FM10K_VF_MSG_ID_LPORT_STATE,
+	FM10K_VF_MSG_ID_MAX,
+};
+
+enum fm10k_tlv_mac_vlan_attr_id {
+	FM10K_MAC_VLAN_MSG_VLAN,
+	FM10K_MAC_VLAN_MSG_SET,
+	FM10K_MAC_VLAN_MSG_MAC,
+	FM10K_MAC_VLAN_MSG_DEFAULT_MAC,
+	FM10K_MAC_VLAN_MSG_MULTICAST,
+	FM10K_MAC_VLAN_MSG_ID_MAX
+};
+
+enum fm10k_tlv_lport_state_attr_id {
+	FM10K_LPORT_STATE_MSG_DISABLE,
+	FM10K_LPORT_STATE_MSG_XCAST_MODE,
+	FM10K_LPORT_STATE_MSG_READY,
+	FM10K_LPORT_STATE_MSG_MAX
+};
+
+#define FM10K_VF_MSG_MSIX_HANDLER(func) \
+	 FM10K_MSG_HANDLER(FM10K_VF_MSG_ID_MSIX, NULL, func)
+
+s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+extern const struct fm10k_tlv_attr fm10k_mac_vlan_msg_attr[];
+#define FM10K_VF_MSG_MAC_VLAN_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_VF_MSG_ID_MAC_VLAN, \
+			  fm10k_mac_vlan_msg_attr, func)
+
+s32 fm10k_msg_lport_state_vf(struct fm10k_hw *, u32 **,
+			     struct fm10k_mbx_info *);
+extern const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[];
+#define FM10K_VF_MSG_LPORT_STATE_HANDLER(func) \
+	FM10K_MSG_HANDLER(FM10K_VF_MSG_ID_LPORT_STATE, \
+			  fm10k_lport_state_msg_attr, func)
+
+extern const struct fm10k_info fm10k_vf_info;
+#endif /* _FM10K_VF_H */