net: Adding support for Cavium ThunderX network controller

This patch adds support for the Cavium ThunderX network controller.
The driver is on the pci bus and thus requires the Thunder PCIe host
controller driver to be enabled.

Signed-off-by: Maciej Czekaj <mjc@semihalf.com>
Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Sunil Goutham <sgoutham@cavium.com>
Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@caviumnetworks.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@caviumnetworks.com>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Robert Richter <rrichter@cavium.com>
Signed-off-by: Kamil Rytarowski <kamil@semihalf.com>
Signed-off-by: Thanneeru Srinivasulu <tsrinivasulu@caviumnetworks.com>
Signed-off-by: Sruthi Vangala <svangala@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

15 files changed, 7373 insertions, 0 deletions

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index eadcb053807e..9a8308553520 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -34,6 +34,7 @@ source "drivers/net/ethernet/adi/Kconfig"
 source "drivers/net/ethernet/broadcom/Kconfig"
 source "drivers/net/ethernet/brocade/Kconfig"
 source "drivers/net/ethernet/calxeda/Kconfig"
+source "drivers/net/ethernet/cavium/Kconfig"
 source "drivers/net/ethernet/chelsio/Kconfig"
 source "drivers/net/ethernet/cirrus/Kconfig"
 source "drivers/net/ethernet/cisco/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 1367afcd0a8b..4395d99115a0 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_NET_BFIN) += adi/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
 obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
 obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
+obj-$(CONFIG_NET_VENDOR_CAVIUM) += cavium/
 obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
 obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
 obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
new file mode 100644
index 000000000000..6365fb4242be
--- /dev/null
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -0,0 +1,40 @@
+#
+# Cavium ethernet device configuration
+#
+
+config NET_VENDOR_CAVIUM
+	tristate "Cavium ethernet drivers"
+	depends on PCI
+	---help---
+	  Enable support for the Cavium ThunderX Network Interface
+	  Controller (NIC). The NIC provides the controller and DMA
+	  engines to move network traffic to/from the memory. The NIC
+	  works closely with TNS, BGX and SerDes to implement the
+	  functions replacing and virtualizing those of a typical
+	  standalone PCIe NIC chip.
+
+	  If you have a Cavium Thunder board, say Y.
+
+if NET_VENDOR_CAVIUM
+
+config THUNDER_NIC_PF
+	tristate "Thunder Physical function driver"
+	default NET_VENDOR_CAVIUM
+	select THUNDER_NIC_BGX
+	---help---
+	  This driver supports Thunder's NIC physical function.
+
+config THUNDER_NIC_VF
+	tristate "Thunder Virtual function driver"
+	default NET_VENDOR_CAVIUM
+	---help---
+	  This driver supports Thunder's NIC virtual function
+
+config	THUNDER_NIC_BGX
+	tristate "Thunder MAC interface driver (BGX)"
+	default NET_VENDOR_CAVIUM
+	---help---
+	  This driver supports programming and controlling of MAC
+	  interface from NIC physical function driver.
+
+endif # NET_VENDOR_CAVIUM
diff --git a/drivers/net/ethernet/cavium/Makefile b/drivers/net/ethernet/cavium/Makefile
new file mode 100644
index 000000000000..7aac4780d050
--- /dev/null
+++ b/drivers/net/ethernet/cavium/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Cavium ethernet device drivers.
+#
+
+obj-$(CONFIG_NET_VENDOR_CAVIUM) += thunder/
diff --git a/drivers/net/ethernet/cavium/thunder/Makefile b/drivers/net/ethernet/cavium/thunder/Makefile
new file mode 100644
index 000000000000..5c4615ccaa14
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for Cavium's Thunder ethernet device
+#
+
+obj-$(CONFIG_THUNDER_NIC_BGX) += thunder_bgx.o
+obj-$(CONFIG_THUNDER_NIC_PF) += nicpf.o
+obj-$(CONFIG_THUNDER_NIC_VF) += nicvf.o
+
+nicpf-y := nic_main.o
+nicvf-y := nicvf_main.o nicvf_queues.o
+nicvf-y += nicvf_ethtool.o
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
new file mode 100644
index 000000000000..9b0be527909b
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -0,0 +1,414 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef NIC_H
+#define	NIC_H
+
+#include <linux/netdevice.h>
+#include <linux/interrupt.h>
+#include "thunder_bgx.h"
+
+/* PCI device IDs */
+#define	PCI_DEVICE_ID_THUNDER_NIC_PF		0xA01E
+#define	PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF	0x0011
+#define	PCI_DEVICE_ID_THUNDER_NIC_VF		0xA034
+#define	PCI_DEVICE_ID_THUNDER_BGX		0xA026
+
+/* PCI BAR nos */
+#define	PCI_CFG_REG_BAR_NUM		0
+#define	PCI_MSIX_REG_BAR_NUM		4
+
+/* NIC SRIOV VF count */
+#define	MAX_NUM_VFS_SUPPORTED		128
+#define	DEFAULT_NUM_VF_ENABLED		8
+
+#define	NIC_TNS_BYPASS_MODE		0
+#define	NIC_TNS_MODE			1
+
+/* NIC priv flags */
+#define	NIC_SRIOV_ENABLED		BIT(0)
+
+/* Min/Max packet size */
+#define	NIC_HW_MIN_FRS			64
+#define	NIC_HW_MAX_FRS			9200 /* 9216 max packet including FCS */
+
+/* Max pkinds */
+#define	NIC_MAX_PKIND			16
+
+/* Rx Channels */
+/* Receive channel configuration in TNS bypass mode
+ * Below is configuration in TNS bypass mode
+ * BGX0-LMAC0-CHAN0 - VNIC CHAN0
+ * BGX0-LMAC1-CHAN0 - VNIC CHAN16
+ * ...
+ * BGX1-LMAC0-CHAN0 - VNIC CHAN128
+ * ...
+ * BGX1-LMAC3-CHAN0 - VNIC CHAN174
+ */
+#define	NIC_INTF_COUNT			2  /* Interfaces btw VNIC and TNS/BGX */
+#define	NIC_CHANS_PER_INF		128
+#define	NIC_MAX_CHANS			(NIC_INTF_COUNT * NIC_CHANS_PER_INF)
+#define	NIC_CPI_COUNT			2048 /* No of channel parse indices */
+
+/* TNS bypass mode: 1-1 mapping between VNIC and BGX:LMAC */
+#define NIC_MAX_BGX			MAX_BGX_PER_CN88XX
+#define	NIC_CPI_PER_BGX			(NIC_CPI_COUNT / NIC_MAX_BGX)
+#define	NIC_MAX_CPI_PER_LMAC		64 /* Max when CPI_ALG is IP diffserv */
+#define	NIC_RSSI_PER_BGX		(NIC_RSSI_COUNT / NIC_MAX_BGX)
+
+/* Tx scheduling */
+#define	NIC_MAX_TL4			1024
+#define	NIC_MAX_TL4_SHAPERS		256 /* 1 shaper for 4 TL4s */
+#define	NIC_MAX_TL3			256
+#define	NIC_MAX_TL3_SHAPERS		64  /* 1 shaper for 4 TL3s */
+#define	NIC_MAX_TL2			64
+#define	NIC_MAX_TL2_SHAPERS		2  /* 1 shaper for 32 TL2s */
+#define	NIC_MAX_TL1			2
+
+/* TNS bypass mode */
+#define	NIC_TL2_PER_BGX			32
+#define	NIC_TL4_PER_BGX			(NIC_MAX_TL4 / NIC_MAX_BGX)
+#define	NIC_TL4_PER_LMAC		(NIC_MAX_TL4 / NIC_CHANS_PER_INF)
+
+/* NIC VF Interrupts */
+#define	NICVF_INTR_CQ			0
+#define	NICVF_INTR_SQ			1
+#define	NICVF_INTR_RBDR			2
+#define	NICVF_INTR_PKT_DROP		3
+#define	NICVF_INTR_TCP_TIMER		4
+#define	NICVF_INTR_MBOX			5
+#define	NICVF_INTR_QS_ERR		6
+
+#define	NICVF_INTR_CQ_SHIFT		0
+#define	NICVF_INTR_SQ_SHIFT		8
+#define	NICVF_INTR_RBDR_SHIFT		16
+#define	NICVF_INTR_PKT_DROP_SHIFT	20
+#define	NICVF_INTR_TCP_TIMER_SHIFT	21
+#define	NICVF_INTR_MBOX_SHIFT		22
+#define	NICVF_INTR_QS_ERR_SHIFT		23
+
+#define	NICVF_INTR_CQ_MASK		(0xFF << NICVF_INTR_CQ_SHIFT)
+#define	NICVF_INTR_SQ_MASK		(0xFF << NICVF_INTR_SQ_SHIFT)
+#define	NICVF_INTR_RBDR_MASK		(0x03 << NICVF_INTR_RBDR_SHIFT)
+#define	NICVF_INTR_PKT_DROP_MASK	BIT(NICVF_INTR_PKT_DROP_SHIFT)
+#define	NICVF_INTR_TCP_TIMER_MASK	BIT(NICVF_INTR_TCP_TIMER_SHIFT)
+#define	NICVF_INTR_MBOX_MASK		BIT(NICVF_INTR_MBOX_SHIFT)
+#define	NICVF_INTR_QS_ERR_MASK		BIT(NICVF_INTR_QS_ERR_SHIFT)
+
+/* MSI-X interrupts */
+#define	NIC_PF_MSIX_VECTORS		10
+#define	NIC_VF_MSIX_VECTORS		20
+
+#define NIC_PF_INTR_ID_ECC0_SBE		0
+#define NIC_PF_INTR_ID_ECC0_DBE		1
+#define NIC_PF_INTR_ID_ECC1_SBE		2
+#define NIC_PF_INTR_ID_ECC1_DBE		3
+#define NIC_PF_INTR_ID_ECC2_SBE		4
+#define NIC_PF_INTR_ID_ECC2_DBE		5
+#define NIC_PF_INTR_ID_ECC3_SBE		6
+#define NIC_PF_INTR_ID_ECC3_DBE		7
+#define NIC_PF_INTR_ID_MBOX0		8
+#define NIC_PF_INTR_ID_MBOX1		9
+
+/* Global timer for CQ timer thresh interrupts
+ * Calculated for SCLK of 700Mhz
+ * value written should be a 1/16th of what is expected
+ *
+ * 1 tick per 0.05usec = value of 2.2
+ * This 10% would be covered in CQ timer thresh value
+ */
+#define NICPF_CLK_PER_INT_TICK		2
+
+struct nicvf_cq_poll {
+	u8	cq_idx;		/* Completion queue index */
+	struct	napi_struct napi;
+};
+
+#define	NIC_RSSI_COUNT			4096 /* Total no of RSS indices */
+#define NIC_MAX_RSS_HASH_BITS		8
+#define NIC_MAX_RSS_IDR_TBL_SIZE	(1 << NIC_MAX_RSS_HASH_BITS)
+#define RSS_HASH_KEY_SIZE		5 /* 320 bit key */
+
+struct nicvf_rss_info {
+	bool enable;
+#define	RSS_L2_EXTENDED_HASH_ENA	BIT(0)
+#define	RSS_IP_HASH_ENA			BIT(1)
+#define	RSS_TCP_HASH_ENA		BIT(2)
+#define	RSS_TCP_SYN_DIS			BIT(3)
+#define	RSS_UDP_HASH_ENA		BIT(4)
+#define RSS_L4_EXTENDED_HASH_ENA	BIT(5)
+#define	RSS_ROCE_ENA			BIT(6)
+#define	RSS_L3_BI_DIRECTION_ENA		BIT(7)
+#define	RSS_L4_BI_DIRECTION_ENA		BIT(8)
+	u64 cfg;
+	u8  hash_bits;
+	u16 rss_size;
+	u8  ind_tbl[NIC_MAX_RSS_IDR_TBL_SIZE];
+	u64 key[RSS_HASH_KEY_SIZE];
+} ____cacheline_aligned_in_smp;
+
+enum rx_stats_reg_offset {
+	RX_OCTS = 0x0,
+	RX_UCAST = 0x1,
+	RX_BCAST = 0x2,
+	RX_MCAST = 0x3,
+	RX_RED = 0x4,
+	RX_RED_OCTS = 0x5,
+	RX_ORUN = 0x6,
+	RX_ORUN_OCTS = 0x7,
+	RX_FCS = 0x8,
+	RX_L2ERR = 0x9,
+	RX_DRP_BCAST = 0xa,
+	RX_DRP_MCAST = 0xb,
+	RX_DRP_L3BCAST = 0xc,
+	RX_DRP_L3MCAST = 0xd,
+	RX_STATS_ENUM_LAST,
+};
+
+enum tx_stats_reg_offset {
+	TX_OCTS = 0x0,
+	TX_UCAST = 0x1,
+	TX_BCAST = 0x2,
+	TX_MCAST = 0x3,
+	TX_DROP = 0x4,
+	TX_STATS_ENUM_LAST,
+};
+
+struct nicvf_hw_stats {
+	u64 rx_bytes_ok;
+	u64 rx_ucast_frames_ok;
+	u64 rx_bcast_frames_ok;
+	u64 rx_mcast_frames_ok;
+	u64 rx_fcs_errors;
+	u64 rx_l2_errors;
+	u64 rx_drop_red;
+	u64 rx_drop_red_bytes;
+	u64 rx_drop_overrun;
+	u64 rx_drop_overrun_bytes;
+	u64 rx_drop_bcast;
+	u64 rx_drop_mcast;
+	u64 rx_drop_l3_bcast;
+	u64 rx_drop_l3_mcast;
+	u64 tx_bytes_ok;
+	u64 tx_ucast_frames_ok;
+	u64 tx_bcast_frames_ok;
+	u64 tx_mcast_frames_ok;
+	u64 tx_drops;
+};
+
+struct nicvf_drv_stats {
+	/* Rx */
+	u64 rx_frames_ok;
+	u64 rx_frames_64;
+	u64 rx_frames_127;
+	u64 rx_frames_255;
+	u64 rx_frames_511;
+	u64 rx_frames_1023;
+	u64 rx_frames_1518;
+	u64 rx_frames_jumbo;
+	u64 rx_drops;
+	/* Tx */
+	u64 tx_frames_ok;
+	u64 tx_drops;
+	u64 tx_busy;
+	u64 tx_tso;
+};
+
+struct nicvf {
+	struct net_device	*netdev;
+	struct pci_dev		*pdev;
+	u8			vf_id;
+	u8			node;
+	u8			tns_mode;
+	u16			mtu;
+	struct queue_set	*qs;
+	void __iomem		*reg_base;
+	bool			link_up;
+	u8			duplex;
+	u32			speed;
+	struct page		*rb_page;
+	u32			rb_page_offset;
+	bool			rb_alloc_fail;
+	bool			rb_work_scheduled;
+	struct delayed_work	rbdr_work;
+	struct tasklet_struct	rbdr_task;
+	struct tasklet_struct	qs_err_task;
+	struct tasklet_struct	cq_task;
+	struct nicvf_cq_poll	*napi[8];
+	struct nicvf_rss_info	rss_info;
+	u8			cpi_alg;
+	/* Interrupt coalescing settings */
+	u32			cq_coalesce_usecs;
+
+	u32			msg_enable;
+	struct nicvf_hw_stats   stats;
+	struct nicvf_drv_stats  drv_stats;
+	struct bgx_stats	bgx_stats;
+	struct work_struct	reset_task;
+
+	/* MSI-X  */
+	bool			msix_enabled;
+	u8			num_vec;
+	struct msix_entry	msix_entries[NIC_VF_MSIX_VECTORS];
+	char			irq_name[NIC_VF_MSIX_VECTORS][20];
+	bool			irq_allocated[NIC_VF_MSIX_VECTORS];
+
+	bool			pf_ready_to_rcv_msg;
+	bool			pf_acked;
+	bool			pf_nacked;
+	bool			bgx_stats_acked;
+} ____cacheline_aligned_in_smp;
+
+/* PF <--> VF Mailbox communication
+ * Eight 64bit registers are shared between PF and VF.
+ * Separate set for each VF.
+ * Writing '1' into last register mbx7 means end of message.
+ */
+
+/* PF <--> VF mailbox communication */
+#define	NIC_PF_VF_MAILBOX_SIZE		2
+#define	NIC_MBOX_MSG_TIMEOUT		2000 /* ms */
+
+/* Mailbox message types */
+#define	NIC_MBOX_MSG_READY		0x01	/* Is PF ready to rcv msgs */
+#define	NIC_MBOX_MSG_ACK		0x02	/* ACK the message received */
+#define	NIC_MBOX_MSG_NACK		0x03	/* NACK the message received */
+#define	NIC_MBOX_MSG_QS_CFG		0x04	/* Configure Qset */
+#define	NIC_MBOX_MSG_RQ_CFG		0x05	/* Configure receive queue */
+#define	NIC_MBOX_MSG_SQ_CFG		0x06	/* Configure Send queue */
+#define	NIC_MBOX_MSG_RQ_DROP_CFG	0x07	/* Configure receive queue */
+#define	NIC_MBOX_MSG_SET_MAC		0x08	/* Add MAC ID to DMAC filter */
+#define	NIC_MBOX_MSG_SET_MAX_FRS	0x09	/* Set max frame size */
+#define	NIC_MBOX_MSG_CPI_CFG		0x0A	/* Config CPI, RSSI */
+#define	NIC_MBOX_MSG_RSS_SIZE		0x0B	/* Get RSS indir_tbl size */
+#define	NIC_MBOX_MSG_RSS_CFG		0x0C	/* Config RSS table */
+#define	NIC_MBOX_MSG_RSS_CFG_CONT	0x0D	/* RSS config continuation */
+#define	NIC_MBOX_MSG_RQ_BP_CFG		0x0E	/* RQ backpressure config */
+#define	NIC_MBOX_MSG_RQ_SW_SYNC		0x0F	/* Flush inflight pkts to RQ */
+#define	NIC_MBOX_MSG_BGX_STATS		0x10	/* Get stats from BGX */
+#define	NIC_MBOX_MSG_BGX_LINK_CHANGE	0x11	/* BGX:LMAC link status */
+#define NIC_MBOX_MSG_CFG_DONE		0x12	/* VF configuration done */
+#define NIC_MBOX_MSG_SHUTDOWN		0x13	/* VF is being shutdown */
+
+struct nic_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    tns_mode;
+	u8    node_id;
+	u64   mac_addr;
+};
+
+/* Qset configuration */
+struct qs_cfg_msg {
+	u8    msg;
+	u8    num;
+	u64   cfg;
+};
+
+/* Receive queue configuration */
+struct rq_cfg_msg {
+	u8    msg;
+	u8    qs_num;
+	u8    rq_num;
+	u64   cfg;
+};
+
+/* Send queue configuration */
+struct sq_cfg_msg {
+	u8    msg;
+	u8    qs_num;
+	u8    sq_num;
+	u64   cfg;
+};
+
+/* Set VF's MAC address */
+struct set_mac_msg {
+	u8    msg;
+	u8    vf_id;
+	u64   addr;
+};
+
+/* Set Maximum frame size */
+struct set_frs_msg {
+	u8    msg;
+	u8    vf_id;
+	u16   max_frs;
+};
+
+/* Set CPI algorithm type */
+struct cpi_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    rq_cnt;
+	u8    cpi_alg;
+};
+
+/* Get RSS table size */
+struct rss_sz_msg {
+	u8    msg;
+	u8    vf_id;
+	u16   ind_tbl_size;
+};
+
+/* Set RSS configuration */
+struct rss_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    hash_bits;
+	u8    tbl_len;
+	u8    tbl_offset;
+#define RSS_IND_TBL_LEN_PER_MBX_MSG	8
+	u8    ind_tbl[RSS_IND_TBL_LEN_PER_MBX_MSG];
+};
+
+struct bgx_stats_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    rx;
+	u8    idx;
+	u64   stats;
+};
+
+/* Physical interface link status */
+struct bgx_link_status {
+	u8    msg;
+	u8    link_up;
+	u8    duplex;
+	u32   speed;
+};
+
+/* 128 bit shared memory between PF and each VF */
+union nic_mbx {
+	struct { u8 msg; }	msg;
+	struct nic_cfg_msg	nic_cfg;
+	struct qs_cfg_msg	qs;
+	struct rq_cfg_msg	rq;
+	struct sq_cfg_msg	sq;
+	struct set_mac_msg	mac;
+	struct set_frs_msg	frs;
+	struct cpi_cfg_msg	cpi_cfg;
+	struct rss_sz_msg	rss_size;
+	struct rss_cfg_msg	rss_cfg;
+	struct bgx_stats_msg    bgx_stats;
+	struct bgx_link_status  link_status;
+};
+
+int nicvf_set_real_num_queues(struct net_device *netdev,
+			      int tx_queues, int rx_queues);
+int nicvf_open(struct net_device *netdev);
+int nicvf_stop(struct net_device *netdev);
+int nicvf_send_msg_to_pf(struct nicvf *vf, union nic_mbx *mbx);
+void nicvf_config_cpi(struct nicvf *nic);
+void nicvf_config_rss(struct nicvf *nic);
+void nicvf_set_rss_key(struct nicvf *nic);
+void nicvf_free_skb(struct nicvf *nic, struct sk_buff *skb);
+void nicvf_set_ethtool_ops(struct net_device *netdev);
+void nicvf_update_stats(struct nicvf *nic);
+void nicvf_update_lmac_stats(struct nicvf *nic);
+
+#endif /* NIC_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
new file mode 100644
index 000000000000..0f1f58b54bf1
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -0,0 +1,940 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/etherdevice.h>
+#include <linux/of.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "q_struct.h"
+#include "thunder_bgx.h"
+
+#define DRV_NAME	"thunder-nic"
+#define DRV_VERSION	"1.0"
+
+struct nicpf {
+	struct pci_dev		*pdev;
+	u8			rev_id;
+#define NIC_NODE_ID_MASK	0x300000000000
+#define NIC_NODE_ID(x)		((x & NODE_ID_MASK) >> 44)
+	u8			node;
+	unsigned int		flags;
+	u8			num_vf_en;      /* No of VF enabled */
+	bool			vf_enabled[MAX_NUM_VFS_SUPPORTED];
+	void __iomem		*reg_base;       /* Register start address */
+	struct pkind_cfg	pkind;
+#define	NIC_SET_VF_LMAC_MAP(bgx, lmac)	(((bgx & 0xF) << 4) | (lmac & 0xF))
+#define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
+#define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
+	u8			vf_lmac_map[MAX_LMAC];
+	struct delayed_work     dwork;
+	struct workqueue_struct *check_link;
+	u8			link[MAX_LMAC];
+	u8			duplex[MAX_LMAC];
+	u32			speed[MAX_LMAC];
+	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
+	u16			rss_ind_tbl_size;
+	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
+
+	/* MSI-X */
+	bool			msix_enabled;
+	u8			num_vec;
+	struct msix_entry	msix_entries[NIC_PF_MSIX_VECTORS];
+	bool			irq_allocated[NIC_PF_MSIX_VECTORS];
+};
+
+/* Supported devices */
+static const struct pci_device_id nic_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) },
+	{ 0, }  /* end of table */
+};
+
+MODULE_AUTHOR("Sunil Goutham");
+MODULE_DESCRIPTION("Cavium Thunder NIC Physical Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DEVICE_TABLE(pci, nic_id_table);
+
+/* The Cavium ThunderX network controller can *only* be found in SoCs
+ * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
+ * registers on this platform are implicitly strongly ordered with respect
+ * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use
+ * with no memory barriers in this driver.  The readq()/writeq() functions add
+ * explicit ordering operation which in this case are redundant, and only
+ * add overhead.
+ */
+
+/* Register read/write APIs */
+static void nic_reg_write(struct nicpf *nic, u64 offset, u64 val)
+{
+	writeq_relaxed(val, nic->reg_base + offset);
+}
+
+static u64 nic_reg_read(struct nicpf *nic, u64 offset)
+{
+	return readq_relaxed(nic->reg_base + offset);
+}
+
+/* PF -> VF mailbox communication APIs */
+static void nic_enable_mbx_intr(struct nicpf *nic)
+{
+	/* Enable mailbox interrupt for all 128 VFs */
+	nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S, ~0ull);
+	nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S + sizeof(u64), ~0ull);
+}
+
+static void nic_clear_mbx_intr(struct nicpf *nic, int vf, int mbx_reg)
+{
+	nic_reg_write(nic, NIC_PF_MAILBOX_INT + (mbx_reg << 3), BIT_ULL(vf));
+}
+
+static u64 nic_get_mbx_addr(int vf)
+{
+	return NIC_PF_VF_0_127_MAILBOX_0_1 + (vf << NIC_VF_NUM_SHIFT);
+}
+
+/* Send a mailbox message to VF
+ * @vf: vf to which this message to be sent
+ * @mbx: Message to be sent
+ */
+static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx)
+{
+	void __iomem *mbx_addr = nic->reg_base + nic_get_mbx_addr(vf);
+	u64 *msg = (u64 *)mbx;
+
+	/* In first revision HW, mbox interrupt is triggerred
+	 * when PF writes to MBOX(1), in next revisions when
+	 * PF writes to MBOX(0)
+	 */
+	if (nic->rev_id == 0) {
+		/* see the comment for nic_reg_write()/nic_reg_read()
+		 * functions above
+		 */
+		writeq_relaxed(msg[0], mbx_addr);
+		writeq_relaxed(msg[1], mbx_addr + 8);
+	} else {
+		writeq_relaxed(msg[1], mbx_addr + 8);
+		writeq_relaxed(msg[0], mbx_addr);
+	}
+}
+
+/* Responds to VF's READY message with VF's
+ * ID, node, MAC address e.t.c
+ * @vf: VF which sent READY message
+ */
+static void nic_mbx_send_ready(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+	int bgx_idx, lmac;
+	const char *mac;
+
+	mbx.nic_cfg.msg = NIC_MBOX_MSG_READY;
+	mbx.nic_cfg.vf_id = vf;
+
+	mbx.nic_cfg.tns_mode = NIC_TNS_BYPASS_MODE;
+
+	bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+	mac = bgx_get_lmac_mac(nic->node, bgx_idx, lmac);
+	if (mac)
+		ether_addr_copy((u8 *)&mbx.nic_cfg.mac_addr, mac);
+
+	mbx.nic_cfg.node_id = nic->node;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* ACKs VF's mailbox message
+ * @vf: VF to which ACK to be sent
+ */
+static void nic_mbx_send_ack(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_ACK;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* NACKs VF's mailbox message that PF is not able to
+ * complete the action
+ * @vf: VF to which ACK to be sent
+ */
+static void nic_mbx_send_nack(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_NACK;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* Flush all in flight receive packets to memory and
+ * bring down an active RQ
+ */
+static int nic_rcv_queue_sw_sync(struct nicpf *nic)
+{
+	u16 timeout = ~0x00;
+
+	nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x01);
+	/* Wait till sync cycle is finished */
+	while (timeout) {
+		if (nic_reg_read(nic, NIC_PF_SW_SYNC_RX_DONE) & 0x1)
+			break;
+		timeout--;
+	}
+	nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x00);
+	if (!timeout) {
+		dev_err(&nic->pdev->dev, "Receive queue software sync failed");
+		return 1;
+	}
+	return 0;
+}
+
+/* Get BGX Rx/Tx stats and respond to VF's request */
+static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx)
+{
+	int bgx_idx, lmac;
+	union nic_mbx mbx = {};
+
+	bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]);
+
+	mbx.bgx_stats.msg = NIC_MBOX_MSG_BGX_STATS;
+	mbx.bgx_stats.vf_id = bgx->vf_id;
+	mbx.bgx_stats.rx = bgx->rx;
+	mbx.bgx_stats.idx = bgx->idx;
+	if (bgx->rx)
+		mbx.bgx_stats.stats = bgx_get_rx_stats(nic->node, bgx_idx,
+							    lmac, bgx->idx);
+	else
+		mbx.bgx_stats.stats = bgx_get_tx_stats(nic->node, bgx_idx,
+							    lmac, bgx->idx);
+	nic_send_msg_to_vf(nic, bgx->vf_id, &mbx);
+}
+
+/* Update hardware min/max frame size */
+static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf)
+{
+	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) {
+		dev_err(&nic->pdev->dev,
+			"Invalid MTU setting from VF%d rejected, should be between %d and %d\n",
+			   vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS);
+		return 1;
+	}
+	new_frs += ETH_HLEN;
+	if (new_frs <= nic->pkind.maxlen)
+		return 0;
+
+	nic->pkind.maxlen = new_frs;
+	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind);
+	return 0;
+}
+
+/* Set minimum transmit packet size */
+static void nic_set_tx_pkt_pad(struct nicpf *nic, int size)
+{
+	int lmac;
+	u64 lmac_cfg;
+
+	/* Max value that can be set is 60 */
+	if (size > 60)
+		size = 60;
+
+	for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) {
+		lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3));
+		lmac_cfg &= ~(0xF << 2);
+		lmac_cfg |= ((size / 4) << 2);
+		nic_reg_write(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3), lmac_cfg);
+	}
+}
+
+/* Function to check number of LMACs present and set VF::LMAC mapping.
+ * Mapping will be used while initializing channels.
+ */
+static void nic_set_lmac_vf_mapping(struct nicpf *nic)
+{
+	unsigned bgx_map = bgx_get_map(nic->node);
+	int bgx, next_bgx_lmac = 0;
+	int lmac, lmac_cnt = 0;
+	u64 lmac_credit;
+
+	nic->num_vf_en = 0;
+
+	for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) {
+		if (!(bgx_map & (1 << bgx)))
+			continue;
+		lmac_cnt = bgx_get_lmac_count(nic->node, bgx);
+		for (lmac = 0; lmac < lmac_cnt; lmac++)
+			nic->vf_lmac_map[next_bgx_lmac++] =
+						NIC_SET_VF_LMAC_MAP(bgx, lmac);
+		nic->num_vf_en += lmac_cnt;
+
+		/* Program LMAC credits */
+		lmac_credit = (1ull << 1); /* channel credit enable */
+		lmac_credit |= (0x1ff << 2); /* Max outstanding pkt count */
+		/* 48KB BGX Tx buffer size, each unit is of size 16bytes */
+		lmac_credit |= (((((48 * 1024) / lmac_cnt) -
+				NIC_HW_MAX_FRS) / 16) << 12);
+		lmac = bgx * MAX_LMAC_PER_BGX;
+		for (; lmac < lmac_cnt + (bgx * MAX_LMAC_PER_BGX); lmac++)
+			nic_reg_write(nic,
+				      NIC_PF_LMAC_0_7_CREDIT + (lmac * 8),
+				      lmac_credit);
+	}
+}
+
+#define BGX0_BLOCK 8
+#define BGX1_BLOCK 9
+
+static void nic_init_hw(struct nicpf *nic)
+{
+	int i;
+
+	/* Reset NIC, in case the driver is repeatedly inserted and removed */
+	nic_reg_write(nic, NIC_PF_SOFT_RESET, 1);
+
+	/* Enable NIC HW block */
+	nic_reg_write(nic, NIC_PF_CFG, 0x3);
+
+	/* Enable backpressure */
+	nic_reg_write(nic, NIC_PF_BP_CFG, (1ULL << 6) | 0x03);
+
+	/* Disable TNS mode on both interfaces */
+	nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG,
+		      (NIC_TNS_BYPASS_MODE << 7) | BGX0_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG | (1 << 8),
+		      (NIC_TNS_BYPASS_MODE << 7) | BGX1_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG,
+		      (1ULL << 63) | BGX0_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG + (1 << 8),
+		      (1ULL << 63) | BGX1_BLOCK);
+
+	/* PKIND configuration */
+	nic->pkind.minlen = 0;
+	nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN;
+	nic->pkind.lenerr_en = 1;
+	nic->pkind.rx_hdr = 0;
+	nic->pkind.hdr_sl = 0;
+
+	for (i = 0; i < NIC_MAX_PKIND; i++)
+		nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (i << 3),
+			      *(u64 *)&nic->pkind);
+
+	nic_set_tx_pkt_pad(nic, NIC_HW_MIN_FRS);
+
+	/* Timer config */
+	nic_reg_write(nic, NIC_PF_INTR_TIMER_CFG, NICPF_CLK_PER_INT_TICK);
+}
+
+/* Channel parse index configuration */
+static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg)
+{
+	u32 vnic, bgx, lmac, chan;
+	u32 padd, cpi_count = 0;
+	u64 cpi_base, cpi, rssi_base, rssi;
+	u8  qset, rq_idx = 0;
+
+	vnic = cfg->vf_id;
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+
+	chan = (lmac * MAX_BGX_CHANS_PER_LMAC) + (bgx * NIC_CHANS_PER_INF);
+	cpi_base = (lmac * NIC_MAX_CPI_PER_LMAC) + (bgx * NIC_CPI_PER_BGX);
+	rssi_base = (lmac * nic->rss_ind_tbl_size) + (bgx * NIC_RSSI_PER_BGX);
+
+	/* Rx channel configuration */
+	nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_BP_CFG | (chan << 3),
+		      (1ull << 63) | (vnic << 0));
+	nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_CFG | (chan << 3),
+		      ((u64)cfg->cpi_alg << 62) | (cpi_base << 48));
+
+	if (cfg->cpi_alg == CPI_ALG_NONE)
+		cpi_count = 1;
+	else if (cfg->cpi_alg == CPI_ALG_VLAN) /* 3 bits of PCP */
+		cpi_count = 8;
+	else if (cfg->cpi_alg == CPI_ALG_VLAN16) /* 3 bits PCP + DEI */
+		cpi_count = 16;
+	else if (cfg->cpi_alg == CPI_ALG_DIFF) /* 6bits DSCP */
+		cpi_count = NIC_MAX_CPI_PER_LMAC;
+
+	/* RSS Qset, Qidx mapping */
+	qset = cfg->vf_id;
+	rssi = rssi_base;
+	for (; rssi < (rssi_base + cfg->rq_cnt); rssi++) {
+		nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3),
+			      (qset << 3) | rq_idx);
+		rq_idx++;
+	}
+
+	rssi = 0;
+	cpi = cpi_base;
+	for (; cpi < (cpi_base + cpi_count); cpi++) {
+		/* Determine port to channel adder */
+		if (cfg->cpi_alg != CPI_ALG_DIFF)
+			padd = cpi % cpi_count;
+		else
+			padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */
+
+		/* Leave RSS_SIZE as '0' to disable RSS */
+		nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3),
+			      (vnic << 24) | (padd << 16) | (rssi_base + rssi));
+
+		if ((rssi + 1) >= cfg->rq_cnt)
+			continue;
+
+		if (cfg->cpi_alg == CPI_ALG_VLAN)
+			rssi++;
+		else if (cfg->cpi_alg == CPI_ALG_VLAN16)
+			rssi = ((cpi - cpi_base) & 0xe) >> 1;
+		else if (cfg->cpi_alg == CPI_ALG_DIFF)
+			rssi = ((cpi - cpi_base) & 0x38) >> 3;
+	}
+	nic->cpi_base[cfg->vf_id] = cpi_base;
+}
+
+/* Responsds to VF with its RSS indirection table size */
+static void nic_send_rss_size(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+	u64  *msg;
+
+	msg = (u64 *)&mbx;
+
+	mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE;
+	mbx.rss_size.ind_tbl_size = nic->rss_ind_tbl_size;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* Receive side scaling configuration
+ * configure:
+ * - RSS index
+ * - indir table i.e hash::RQ mapping
+ * - no of hash bits to consider
+ */
+static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
+{
+	u8  qset, idx = 0;
+	u64 cpi_cfg, cpi_base, rssi_base, rssi;
+
+	cpi_base = nic->cpi_base[cfg->vf_id];
+	cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3));
+	rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset;
+
+	rssi = rssi_base;
+	qset = cfg->vf_id;
+
+	for (; rssi < (rssi_base + cfg->tbl_len); rssi++) {
+		nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3),
+			      (qset << 3) | (cfg->ind_tbl[idx] & 0x7));
+		idx++;
+	}
+
+	cpi_cfg &= ~(0xFULL << 20);
+	cpi_cfg |= (cfg->hash_bits << 20);
+	nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg);
+}
+
+/* 4 level transmit side scheduler configutation
+ * for TNS bypass mode
+ *
+ * Sample configuration for SQ0
+ * VNIC0-SQ0 -> TL4(0)   -> TL3[0]   -> TL2[0]  -> TL1[0] -> BGX0
+ * VNIC1-SQ0 -> TL4(8)   -> TL3[2]   -> TL2[0]  -> TL1[0] -> BGX0
+ * VNIC2-SQ0 -> TL4(16)  -> TL3[4]   -> TL2[1]  -> TL1[0] -> BGX0
+ * VNIC3-SQ0 -> TL4(24)  -> TL3[6]   -> TL2[1]  -> TL1[0] -> BGX0
+ * VNIC4-SQ0 -> TL4(512) -> TL3[128] -> TL2[32] -> TL1[1] -> BGX1
+ * VNIC5-SQ0 -> TL4(520) -> TL3[130] -> TL2[32] -> TL1[1] -> BGX1
+ * VNIC6-SQ0 -> TL4(528) -> TL3[132] -> TL2[33] -> TL1[1] -> BGX1
+ * VNIC7-SQ0 -> TL4(536) -> TL3[134] -> TL2[33] -> TL1[1] -> BGX1
+ */
+static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u8 sq_idx)
+{
+	u32 bgx, lmac, chan;
+	u32 tl2, tl3, tl4;
+	u32 rr_quantum;
+
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	/* 24 bytes for FCS, IPG and preamble */
+	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
+