be_main.c

/*
 * Copyright (C) 2005 - 2013 Emulex
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation.  The full GNU General
 * Public License is included in this distribution in the file called COPYING.
 *
 * Contact Information:
 * linux-drivers@emulex.com
 *
 * Emulex
 * 3333 Susan Street
 * Costa Mesa, CA 92626
 */

#include <linux/prefetch.h>
#include <linux/module.h>
#include "be.h"
#include "be_cmds.h"
#include <asm/div64.h>
#include <linux/aer.h>
#include <linux/if_bridge.h>

MODULE_VERSION(DRV_VER);
MODULE_DEVICE_TABLE(pci, be_dev_ids);
MODULE_DESCRIPTION(DRV_DESC " " DRV_VER);
MODULE_AUTHOR("Emulex Corporation");
MODULE_LICENSE("GPL");

static unsigned int num_vfs;
module_param(num_vfs, uint, S_IRUGO);
MODULE_PARM_DESC(num_vfs, "Number of PCI VFs to initialize");

static ushort rx_frag_size = 2048;
module_param(rx_frag_size, ushort, S_IRUGO);
MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");

static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID1) },
	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID6)},
	{ 0 }
};
MODULE_DEVICE_TABLE(pci, be_dev_ids);
/* UE Status Low CSR */
static const char * const ue_status_low_desc[] = {
	"CEV",
	"CTX",
	"DBUF",
	"ERX",
	"Host",
	"MPU",
	"NDMA",
	"PTC ",
	"RDMA ",
	"RXF ",
	"RXIPS ",
	"RXULP0 ",
	"RXULP1 ",
	"RXULP2 ",
	"TIM ",
	"TPOST ",
	"TPRE ",
	"TXIPS ",
	"TXULP0 ",
	"TXULP1 ",
	"UC ",
	"WDMA ",
	"TXULP2 ",
	"HOST1 ",
	"P0_OB_LINK ",
	"P1_OB_LINK ",
	"HOST_GPIO ",
	"MBOX ",
	"AXGMAC0",
	"AXGMAC1",
	"JTAG",
	"MPU_INTPEND"
};
/* UE Status High CSR */
static const char * const ue_status_hi_desc[] = {
	"LPCMEMHOST",
	"MGMT_MAC",
	"PCS0ONLINE",
	"MPU_IRAM",
	"PCS1ONLINE",
	"PCTL0",
	"PCTL1",
	"PMEM",
	"RR",
	"TXPB",
	"RXPP",
	"XAUI",
	"TXP",
	"ARM",
	"IPC",
	"HOST2",
	"HOST3",
	"HOST4",
	"HOST5",
	"HOST6",
	"HOST7",
	"HOST8",
	"HOST9",
	"NETC",
	"Unknown",
	"Unknown",
	"Unknown",
	"Unknown",
	"Unknown",
	"Unknown",
	"Unknown",
	"Unknown"
};

/* Is BE in a multi-channel mode */
static inline bool be_is_mc(struct be_adapter *adapter) {
	return (adapter->function_mode & FLEX10_MODE ||
		adapter->function_mode & VNIC_MODE ||
		adapter->function_mode & UMC_ENABLED);
}

static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q)
{
	struct be_dma_mem *mem = &q->dma_mem;
	if (mem->va) {
		dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va,
				  mem->dma);
		mem->va = NULL;
	}
}

static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q,
		u16 len, u16 entry_size)
{
	struct be_dma_mem *mem = &q->dma_mem;

	memset(q, 0, sizeof(*q));
	q->len = len;
	q->entry_size = entry_size;
	mem->size = len * entry_size;
	mem->va = dma_zalloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma,
				      GFP_KERNEL);
	if (!mem->va)
		return -ENOMEM;
	return 0;
}

static void be_reg_intr_set(struct be_adapter *adapter, bool enable)
{
	u32 reg, enabled;

	pci_read_config_dword(adapter->pdev, PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET,
				&reg);
	enabled = reg & MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;

	if (!enabled && enable)
		reg |= MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;
	else if (enabled && !enable)
		reg &= ~MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;
	else
		return;

	pci_write_config_dword(adapter->pdev,
			PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg);
}

static void be_intr_set(struct be_adapter *adapter, bool enable)
{
	int status = 0;

	/* On lancer interrupts can't be controlled via this register */
	if (lancer_chip(adapter))
		return;

	if (adapter->eeh_error)
		return;

	status = be_cmd_intr_set(adapter, enable);
	if (status)
		be_reg_intr_set(adapter, enable);
}

static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
{
	u32 val = 0;
	val |= qid & DB_RQ_RING_ID_MASK;
	val |= posted << DB_RQ_NUM_POSTED_SHIFT;

	wmb();
	iowrite32(val, adapter->db + DB_RQ_OFFSET);
}

static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
			  u16 posted)
{
	u32 val = 0;
	val |= txo->q.id & DB_TXULP_RING_ID_MASK;
	val |= (posted & DB_TXULP_NUM_POSTED_MASK) << DB_TXULP_NUM_POSTED_SHIFT;

	wmb();
	iowrite32(val, adapter->db + txo->db_offset);
}

static void be_eq_notify(struct be_adapter *adapter, u16 qid,
		bool arm, bool clear_int, u16 num_popped)
{
	u32 val = 0;
	val |= qid & DB_EQ_RING_ID_MASK;
	val |= ((qid & DB_EQ_RING_ID_EXT_MASK) <<
			DB_EQ_RING_ID_EXT_MASK_SHIFT);

	if (adapter->eeh_error)
		return;

	if (arm)
		val |= 1 << DB_EQ_REARM_SHIFT;
	if (clear_int)
		val |= 1 << DB_EQ_CLR_SHIFT;
	val |= 1 << DB_EQ_EVNT_SHIFT;
	val |= num_popped << DB_EQ_NUM_POPPED_SHIFT;
	iowrite32(val, adapter->db + DB_EQ_OFFSET);
}

void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped)
{
	u32 val = 0;
	val |= qid & DB_CQ_RING_ID_MASK;
	val |= ((qid & DB_CQ_RING_ID_EXT_MASK) <<
			DB_CQ_RING_ID_EXT_MASK_SHIFT);

	if (adapter->eeh_error)
		return;

	if (arm)
		val |= 1 << DB_CQ_REARM_SHIFT;
	val |= num_popped << DB_CQ_NUM_POPPED_SHIFT;
	iowrite32(val, adapter->db + DB_CQ_OFFSET);
}

static int be_mac_addr_set(struct net_device *netdev, void *p)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	struct device *dev = &adapter->pdev->dev;
	struct sockaddr *addr = p;
	int status;
	u8 mac[ETH_ALEN];
	u32 old_pmac_id = adapter->pmac_id[0], curr_pmac_id = 0;

	if (!is_valid_ether_addr(addr->sa_data))
		return -EADDRNOTAVAIL;

	/* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT
	 * privilege or if PF did not provision the new MAC address.
	 * On BE3, this cmd will always fail if the VF doesn't have the
	 * FILTMGMT privilege. This failure is OK, only if the PF programmed
	 * the MAC for the VF.
	 */
	status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data,
				 adapter->if_handle, &adapter->pmac_id[0], 0);
	if (!status) {
		curr_pmac_id = adapter->pmac_id[0];

		/* Delete the old programmed MAC. This call may fail if the
		 * old MAC was already deleted by the PF driver.
		 */
		if (adapter->pmac_id[0] != old_pmac_id)
			be_cmd_pmac_del(adapter, adapter->if_handle,
					old_pmac_id, 0);
	}

	/* Decide if the new MAC is successfully activated only after
	 * querying the FW
	 */
	status = be_cmd_get_active_mac(adapter, curr_pmac_id, mac);
	if (status)
		goto err;

	/* The MAC change did not happen, either due to lack of privilege
	 * or PF didn't pre-provision.
	 */
	if (memcmp(addr->sa_data, mac, ETH_ALEN)) {
		status = -EPERM;
		goto err;
	}

	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
	dev_info(dev, "MAC address changed to %pM\n", mac);
	return 0;
err:
	dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data);
	return status;
}

/* BE2 supports only v0 cmd */
static void *hw_stats_from_cmd(struct be_adapter *adapter)
{
	if (BE2_chip(adapter)) {
		struct be_cmd_resp_get_stats_v0 *cmd = adapter->stats_cmd.va;

		return &cmd->hw_stats;
	} else  {
		struct be_cmd_resp_get_stats_v1 *cmd = adapter->stats_cmd.va;

		return &cmd->hw_stats;
	}
}

/* BE2 supports only v0 cmd */
static void *be_erx_stats_from_cmd(struct be_adapter *adapter)
{
	if (BE2_chip(adapter)) {
		struct be_hw_stats_v0 *hw_stats = hw_stats_from_cmd(adapter);

		return &hw_stats->erx;
	} else {
		struct be_hw_stats_v1 *hw_stats = hw_stats_from_cmd(adapter);

		return &hw_stats->erx;
	}
}

static void populate_be_v0_stats(struct be_adapter *adapter)
{
	struct be_hw_stats_v0 *hw_stats = hw_stats_from_cmd(adapter);
	struct be_pmem_stats *pmem_sts = &hw_stats->pmem;
	struct be_rxf_stats_v0 *rxf_stats = &hw_stats->rxf;
	struct be_port_rxf_stats_v0 *port_stats =
					&rxf_stats->port[adapter->port_num];
	struct be_drv_stats *drvs = &adapter->drv_stats;

	be_dws_le_to_cpu(hw_stats, sizeof(*hw_stats));
	drvs->rx_pause_frames = port_stats->rx_pause_frames;
	drvs->rx_crc_errors = port_stats->rx_crc_errors;
	drvs->rx_control_frames = port_stats->rx_control_frames;
	drvs->rx_in_range_errors = port_stats->rx_in_range_errors;
	drvs->rx_frame_too_long = port_stats->rx_frame_too_long;
	drvs->rx_dropped_runt = port_stats->rx_dropped_runt;
	drvs->rx_ip_checksum_errs = port_stats->rx_ip_checksum_errs;
	drvs->rx_tcp_checksum_errs = port_stats->rx_tcp_checksum_errs;
	drvs->rx_udp_checksum_errs = port_stats->rx_udp_checksum_errs;
	drvs->rxpp_fifo_overflow_drop = port_stats->rx_fifo_overflow;
	drvs->rx_dropped_tcp_length = port_stats->rx_dropped_tcp_length;
	drvs->rx_dropped_too_small = port_stats->rx_dropped_too_small;
	drvs->rx_dropped_too_short = port_stats->rx_dropped_too_short;
	drvs->rx_out_range_errors = port_stats->rx_out_range_errors;
	drvs->rx_input_fifo_overflow_drop = port_stats->rx_input_fifo_overflow;
	drvs->rx_dropped_header_too_small =
		port_stats->rx_dropped_header_too_small;
	drvs->rx_address_filtered =
					port_stats->rx_address_filtered +
					port_stats->rx_vlan_filtered;
	drvs->rx_alignment_symbol_errors =
		port_stats->rx_alignment_symbol_errors;

	drvs->tx_pauseframes = port_stats->tx_pauseframes;
	drvs->tx_controlframes = port_stats->tx_controlframes;

	if (adapter->port_num)
		drvs->jabber_events = rxf_stats->port1_jabber_events;
	else
		drvs->jabber_events = rxf_stats->port0_jabber_events;
	drvs->rx_drops_no_pbuf = rxf_stats->rx_drops_no_pbuf;
	drvs->rx_drops_no_erx_descr = rxf_stats->rx_drops_no_erx_descr;
	drvs->forwarded_packets = rxf_stats->forwarded_packets;
	drvs->rx_drops_mtu = rxf_stats->rx_drops_mtu;
	drvs->rx_drops_no_tpre_descr = rxf_stats->rx_drops_no_tpre_descr;
	drvs->rx_drops_too_many_frags = rxf_stats->rx_drops_too_many_frags;
	adapter->drv_stats.eth_red_drops = pmem_sts->eth_red_drops;
}

static void populate_be_v1_stats(struct be_adapter *adapter)
{
	struct be_hw_stats_v1 *hw_stats = hw_stats_from_cmd(adapter);
	struct be_pmem_stats *pmem_sts = &hw_stats->pmem;
	struct be_rxf_stats_v1 *rxf_stats = &hw_stats->rxf;
	struct be_port_rxf_stats_v1 *port_stats =
					&rxf_stats->port[adapter->port_num];
	struct be_drv_stats *drvs = &adapter->drv_stats;

	be_dws_le_to_cpu(hw_stats, sizeof(*hw_stats));
	drvs->pmem_fifo_overflow_drop = port_stats->pmem_fifo_overflow_drop;
	drvs->rx_priority_pause_frames = port_stats->rx_priority_pause_frames;
	drvs->rx_pause_frames = port_stats->rx_pause_frames;
	drvs->rx_crc_errors = port_stats->rx_crc_errors;
	drvs->rx_control_frames = port_stats->rx_control_frames;
	drvs->rx_in_range_errors = port_stats->rx_in_range_errors;
	drvs->rx_frame_too_long = port_stats->rx_frame_too_long;
	drvs->rx_dropped_runt = port_stats->rx_dropped_runt;
	drvs->rx_ip_checksum_errs = port_stats->rx_ip_checksum_errs;
	drvs->rx_tcp_checksum_errs = port_stats->rx_tcp_checksum_errs;
	drvs->rx_udp_checksum_errs = port_stats->rx_udp_checksum_errs;
	drvs->rx_dropped_tcp_length = port_stats->rx_dropped_tcp_length;
	drvs->rx_dropped_too_small = port_stats->rx_dropped_too_small;
	drvs->rx_dropped_too_short = port_stats->rx_dropped_too_short;
	drvs->rx_out_range_errors = port_stats->rx_out_range_errors;
	drvs->rx_dropped_header_too_small =
		port_stats->rx_dropped_header_too_small;
	drvs->rx_input_fifo_overflow_drop =
		port_stats->rx_input_fifo_overflow_drop;
	drvs->rx_address_filtered = port_stats->rx_address_filtered;
	drvs->rx_alignment_symbol_errors =
		port_stats->rx_alignment_symbol_errors;
	drvs->rxpp_fifo_overflow_drop = port_stats->rxpp_fifo_overflow_drop;
	drvs->tx_pauseframes = port_stats->tx_pauseframes;
	drvs->tx_controlframes = port_stats->tx_controlframes;
	drvs->tx_priority_pauseframes = port_stats->tx_priority_pauseframes;
	drvs->jabber_events = port_stats->jabber_events;
	drvs->rx_drops_no_pbuf = rxf_stats->rx_drops_no_pbuf;
	drvs->rx_drops_no_erx_descr = rxf_stats->rx_drops_no_erx_descr;
	drvs->forwarded_packets = rxf_stats->forwarded_packets;
	drvs->rx_drops_mtu = rxf_stats->rx_drops_mtu;
	drvs->rx_drops_no_tpre_descr = rxf_stats->rx_drops_no_tpre_descr;
	drvs->rx_drops_too_many_frags = rxf_stats->rx_drops_too_many_frags;
	adapter->drv_stats.eth_red_drops = pmem_sts->eth_red_drops;
}

static void populate_lancer_stats(struct be_adapter *adapter)
{

	struct be_drv_stats *drvs = &adapter->drv_stats;
	struct lancer_pport_stats *pport_stats =
					pport_stats_from_cmd(adapter);

	be_dws_le_to_cpu(pport_stats, sizeof(*pport_stats));
	drvs->rx_pause_frames = pport_stats->rx_pause_frames_lo;
	drvs->rx_crc_errors = pport_stats->rx_crc_errors_lo;
	drvs->rx_control_frames = pport_stats->rx_control_frames_lo;
	drvs->rx_in_range_errors = pport_stats->rx_in_range_errors;
	drvs->rx_frame_too_long = pport_stats->rx_frames_too_long_lo;
	drvs->rx_dropped_runt = pport_stats->rx_dropped_runt;
	drvs->rx_ip_checksum_errs = pport_stats->rx_ip_checksum_errors;
	drvs->rx_tcp_checksum_errs = pport_stats->rx_tcp_checksum_errors;
	drvs->rx_udp_checksum_errs = pport_stats->rx_udp_checksum_errors;
	drvs->rx_dropped_tcp_length =
				pport_stats->rx_dropped_invalid_tcp_length;
	drvs->rx_dropped_too_small = pport_stats->rx_dropped_too_small;
	drvs->rx_dropped_too_short = pport_stats->rx_dropped_too_short;
	drvs->rx_out_range_errors = pport_stats->rx_out_of_range_errors;
	drvs->rx_dropped_header_too_small =
				pport_stats->rx_dropped_header_too_small;
	drvs->rx_input_fifo_overflow_drop = pport_stats->rx_fifo_overflow;
	drvs->rx_address_filtered =
					pport_stats->rx_address_filtered +
					pport_stats->rx_vlan_filtered;
	drvs->rx_alignment_symbol_errors = pport_stats->rx_symbol_errors_lo;
	drvs->rxpp_fifo_overflow_drop = pport_stats->rx_fifo_overflow;
	drvs->tx_pauseframes = pport_stats->tx_pause_frames_lo;
	drvs->tx_controlframes = pport_stats->tx_control_frames_lo;
	drvs->jabber_events = pport_stats->rx_jabbers;
	drvs->forwarded_packets = pport_stats->num_forwards_lo;
	drvs->rx_drops_mtu = pport_stats->rx_drops_mtu_lo;
	drvs->rx_drops_too_many_frags =
				pport_stats->rx_drops_too_many_frags_lo;
}

static void accumulate_16bit_val(u32 *acc, u16 val)
{
#define lo(x)			(x & 0xFFFF)
#define hi(x)			(x & 0xFFFF0000)
	bool wrapped = val < lo(*acc);
	u32 newacc = hi(*acc) + val;

	if (wrapped)
		newacc += 65536;
	ACCESS_ONCE(*acc) = newacc;
}

static void populate_erx_stats(struct be_adapter *adapter,
			struct be_rx_obj *rxo,
			u32 erx_stat)
{
	if (!BEx_chip(adapter))
		rx_stats(rxo)->rx_drops_no_frags = erx_stat;
	else
		/* below erx HW counter can actually wrap around after
		 * 65535. Driver accumulates a 32-bit value
		 */
		accumulate_16bit_val(&rx_stats(rxo)->rx_drops_no_frags,
				     (u16)erx_stat);
}

void be_parse_stats(struct be_adapter *adapter)
{
	struct be_erx_stats_v1 *erx = be_erx_stats_from_cmd(adapter);
	struct be_rx_obj *rxo;
	int i;
	u32 erx_stat;

	if (lancer_chip(adapter)) {
		populate_lancer_stats(adapter);
	} else {
		if (BE2_chip(adapter))
			populate_be_v0_stats(adapter);
		else
			/* for BE3 and Skyhawk */
			populate_be_v1_stats(adapter);

		/* as erx_v1 is longer than v0, ok to use v1 for v0 access */
		for_all_rx_queues(adapter, rxo, i) {
			erx_stat = erx->rx_drops_no_fragments[rxo->q.id];
			populate_erx_stats(adapter, rxo, erx_stat);
		}
	}
}

static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
					struct rtnl_link_stats64 *stats)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	struct be_drv_stats *drvs = &adapter->drv_stats;
	struct be_rx_obj *rxo;
	struct be_tx_obj *txo;
	u64 pkts, bytes;
	unsigned int start;
	int i;

	for_all_rx_queues(adapter, rxo, i) {
		const struct be_rx_stats *rx_stats = rx_stats(rxo);
		do {
			start = u64_stats_fetch_begin_bh(&rx_stats->sync);
			pkts = rx_stats(rxo)->rx_pkts;
			bytes = rx_stats(rxo)->rx_bytes;
		} while (u64_stats_fetch_retry_bh(&rx_stats->sync, start));
		stats->rx_packets += pkts;
		stats->rx_bytes += bytes;
		stats->multicast += rx_stats(rxo)->rx_mcast_pkts;
		stats->rx_dropped += rx_stats(rxo)->rx_drops_no_skbs +
					rx_stats(rxo)->rx_drops_no_frags;
	}

	for_all_tx_queues(adapter, txo, i) {
		const struct be_tx_stats *tx_stats = tx_stats(txo);
		do {
			start = u64_stats_fetch_begin_bh(&tx_stats->sync);
			pkts = tx_stats(txo)->tx_pkts;
			bytes = tx_stats(txo)->tx_bytes;
		} while (u64_stats_fetch_retry_bh(&tx_stats->sync, start));
		stats->tx_packets += pkts;
		stats->tx_bytes += bytes;
	}

	/* bad pkts received */
	stats->rx_errors = drvs->rx_crc_errors +
		drvs->rx_alignment_symbol_errors +
		drvs->rx_in_range_errors +
		drvs->rx_out_range_errors +
		drvs->rx_frame_too_long +
		drvs->rx_dropped_too_small +
		drvs->rx_dropped_too_short +
		drvs->rx_dropped_header_too_small +
		drvs->rx_dropped_tcp_length +
		drvs->rx_dropped_runt;

	/* detailed rx errors */
	stats->rx_length_errors = drvs->rx_in_range_errors +
		drvs->rx_out_range_errors +
		drvs->rx_frame_too_long;

	stats->rx_crc_errors = drvs->rx_crc_errors;

	/* frame alignment errors */
	stats->rx_frame_errors = drvs->rx_alignment_symbol_errors;

	/* receiver fifo overrun */
	/* drops_no_pbuf is no per i/f, it's per BE card */
	stats->rx_fifo_errors = drvs->rxpp_fifo_overflow_drop +
				drvs->rx_input_fifo_overflow_drop +
				drvs->rx_drops_no_pbuf;
	return stats;
}

void be_link_status_update(struct be_adapter *adapter, u8 link_status)
{
	struct net_device *netdev = adapter->netdev;

	if (!(adapter->flags & BE_FLAGS_LINK_STATUS_INIT)) {
		netif_carrier_off(netdev);
		adapter->flags |= BE_FLAGS_LINK_STATUS_INIT;
	}

	if ((link_status & LINK_STATUS_MASK) == LINK_UP)
		netif_carrier_on(netdev);
	else
		netif_carrier_off(netdev);
}

static void be_tx_stats_update(struct be_tx_obj *txo,
			u32 wrb_cnt, u32 copied, u32 gso_segs, bool stopped)
{
	struct be_tx_stats *stats = tx_stats(txo);

	u64_stats_update_begin(&stats->sync);
	stats->tx_reqs++;
	stats->tx_wrbs += wrb_cnt;
	stats->tx_bytes += copied;
	stats->tx_pkts += (gso_segs ? gso_segs : 1);
	if (stopped)
		stats->tx_stops++;
	u64_stats_update_end(&stats->sync);
}

/* Determine number of WRB entries needed to xmit data in an skb */
static u32 wrb_cnt_for_skb(struct be_adapter *adapter, struct sk_buff *skb,
								bool *dummy)
{
	int cnt = (skb->len > skb->data_len);

	cnt += skb_shinfo(skb)->nr_frags;

	/* to account for hdr wrb */
	cnt++;
	if (lancer_chip(adapter) || !(cnt & 1)) {
		*dummy = false;
	} else {
		/* add a dummy to make it an even num */
		cnt++;
		*dummy = true;
	}
	BUG_ON(cnt > BE_MAX_TX_FRAG_COUNT);
	return cnt;
}

static inline void wrb_fill(struct be_eth_wrb *wrb, u64 addr, int len)
{
	wrb->frag_pa_hi = upper_32_bits(addr);
	wrb->frag_pa_lo = addr & 0xFFFFFFFF;
	wrb->frag_len = len & ETH_WRB_FRAG_LEN_MASK;
	wrb->rsvd0 = 0;
}

static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
					struct sk_buff *skb)
{
	u8 vlan_prio;
	u16 vlan_tag;

	vlan_tag = vlan_tx_tag_get(skb);
	vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
	/* If vlan priority provided by OS is NOT in available bmap */
	if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
		vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
				adapter->recommended_prio;

	return vlan_tag;
}

static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
		struct sk_buff *skb, u32 wrb_cnt, u32 len, bool skip_hw_vlan)
{
	u16 vlan_tag;

	memset(hdr, 0, sizeof(*hdr));

	AMAP_SET_BITS(struct amap_eth_hdr_wrb, crc, hdr, 1);

	if (skb_is_gso(skb)) {
		AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso, hdr, 1);
		AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso_mss,
			hdr, skb_shinfo(skb)->gso_size);
		if (skb_is_gso_v6(skb) && !lancer_chip(adapter))
			AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso6, hdr, 1);
	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
		if (is_tcp_pkt(skb))
			AMAP_SET_BITS(struct amap_eth_hdr_wrb, tcpcs, hdr, 1);
		else if (is_udp_pkt(skb))
			AMAP_SET_BITS(struct amap_eth_hdr_wrb, udpcs, hdr, 1);
	}

	if (vlan_tx_tag_present(skb)) {
		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan, hdr, 1);
		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan_tag, hdr, vlan_tag);
	}

	/* To skip HW VLAN tagging: evt = 1, compl = 0 */
	AMAP_SET_BITS(struct amap_eth_hdr_wrb, complete, hdr, !skip_hw_vlan);
	AMAP_SET_BITS(struct amap_eth_hdr_wrb, event, hdr, 1);
	AMAP_SET_BITS(struct amap_eth_hdr_wrb, num_wrb, hdr, wrb_cnt);
	AMAP_SET_BITS(struct amap_eth_hdr_wrb, len, hdr, len);
}

static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
		bool unmap_single)
{
	dma_addr_t dma;

	be_dws_le_to_cpu(wrb, sizeof(*wrb));

	dma = (u64)wrb->frag_pa_hi << 32 | (u64)wrb->frag_pa_lo;
	if (wrb->frag_len) {
		if (unmap_single)
			dma_unmap_single(dev, dma, wrb->frag_len,
					 DMA_TO_DEVICE);
		else
			dma_unmap_page(dev, dma, wrb->frag_len, DMA_TO_DEVICE);
	}
}

static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
		struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb,
		bool skip_hw_vlan)
{
	dma_addr_t busaddr;
	int i, copied = 0;
	struct device *dev = &adapter->pdev->dev;
	struct sk_buff *first_skb = skb;
	struct be_eth_wrb *wrb;
	struct be_eth_hdr_wrb *hdr;
	bool map_single = false;
	u16 map_head;

	hdr = queue_head_node(txq);
	queue_head_inc(txq);
	map_head = txq->head;

	if (skb->len > skb->data_len) {
		int len = skb_headlen(skb);
		busaddr = dma_map_single(dev, skb->data, len, DMA_TO_DEVICE);
		if (dma_mapping_error(dev, busaddr))
			goto dma_err;
		map_single = true;
		wrb = queue_head_node(txq);
		wrb_fill(wrb, busaddr, len);
		be_dws_cpu_to_le(wrb, sizeof(*wrb));
		queue_head_inc(txq);
		copied += len;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		const struct skb_frag_struct *frag =
			&skb_shinfo(skb)->frags[i];
		busaddr = skb_frag_dma_map(dev, frag, 0,
					   skb_frag_size(frag), DMA_TO_DEVICE);
		if (dma_mapping_error(dev, busaddr))
			goto dma_err;
		wrb = queue_head_node(txq);
		wrb_fill(wrb, busaddr, skb_frag_size(frag));
		be_dws_cpu_to_le(wrb, sizeof(*wrb));
		queue_head_inc(txq);
		copied += skb_frag_size(frag);
	}

	if (dummy_wrb) {
		wrb = queue_head_node(txq);
		wrb_fill(wrb, 0, 0);
		be_dws_cpu_to_le(wrb, sizeof(*wrb));
		queue_head_inc(txq);
	}

	wrb_fill_hdr(adapter, hdr, first_skb, wrb_cnt, copied, skip_hw_vlan);
	be_dws_cpu_to_le(hdr, sizeof(*hdr));

	return copied;
dma_err:
	txq->head = map_head;
	while (copied) {
		wrb = queue_head_node(txq);
		unmap_tx_frag(dev, wrb, map_single);
		map_single = false;
		copied -= wrb->frag_len;
		queue_head_inc(txq);
	}
	return 0;
}

static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
					     struct sk_buff *skb,
					     bool *skip_hw_vlan)
{
	u16 vlan_tag = 0;

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (unlikely(!skb))
		return skb;

	if (vlan_tx_tag_present(skb))
		vlan_tag = be_get_tx_vlan_tag(adapter, skb);

	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
		if (!vlan_tag)
			vlan_tag = adapter->pvid;
		/* f/w workaround to set skip_hw_vlan = 1, informs the F/W to
		 * skip VLAN insertion
		 */
		if (skip_hw_vlan)
			*skip_hw_vlan = true;
	}

	if (vlan_tag) {
		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
		if (unlikely(!skb))
			return skb;
		skb->vlan_tci = 0;
	}

	/* Insert the outer VLAN, if any */
	if (adapter->qnq_vid) {
		vlan_tag = adapter->qnq_vid;
		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
		if (unlikely(!skb))
			return skb;
		if (skip_hw_vlan)
			*skip_hw_vlan = true;
	}

	return skb;
}

static bool be_ipv6_exthdr_check(struct sk_buff *skb)
{
	struct ethhdr *eh = (struct ethhdr *)skb->data;
	u16 offset = ETH_HLEN;

	if (eh->h_proto == htons(ETH_P_IPV6)) {
		struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + offset);

		offset += sizeof(struct ipv6hdr);
		if (ip6h->nexthdr != NEXTHDR_TCP &&
		    ip6h->nexthdr != NEXTHDR_UDP) {
			struct ipv6_opt_hdr *ehdr =
				(struct ipv6_opt_hdr *) (skb->data + offset);

			/* offending pkt: 2nd byte following IPv6 hdr is 0xff */
			if (ehdr->hdrlen == 0xff)
				return true;
		}
	}
	return false;
}

static int be_vlan_tag_tx_chk(struct be_adapter *adapter, struct sk_buff *skb)
{
	return vlan_tx_tag_present(skb) || adapter->pvid || adapter->qnq_vid;
}

static int be_ipv6_tx_stall_chk(struct be_adapter *adapter,
				struct sk_buff *skb)
{
	return BE3_chip(adapter) && be_ipv6_exthdr_check(skb);
}

static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
					   struct sk_buff *skb,
					   bool *skip_hw_vlan)
{
	struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
	unsigned int eth_hdr_len;
	struct iphdr *ip;

	/* Lancer ASIC has a bug wherein packets that are 32 bytes or less
	 * may cause a transmit stall on that port. So the work-around is to
	 * pad such packets to a 36-byte length.
	 */
	if (unlikely(lancer_chip(adapter) && skb->len <= 32)) {
		if (skb_padto(skb, 36))
			goto tx_drop;
		skb->len = 36;
	}

	/* For padded packets, BE HW modifies tot_len field in IP header
	 * incorrecly when VLAN tag is inserted by HW.
	 * For padded packets, Lancer computes incorrect checksum.
	 */
	eth_hdr_len = ntohs(skb->protocol) == ETH_P_8021Q ?
						VLAN_ETH_HLEN : ETH_HLEN;
	if (skb->len <= 60 &&
	    (lancer_chip(adapter) || vlan_tx_tag_present(skb)) &&
	    is_ipv4_pkt(skb)) {
		ip = (struct iphdr *)ip_hdr(skb);
		pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len));
	}

	/* If vlan tag is already inlined in the packet, skip HW VLAN
	 * tagging in UMC mode
	 */
	if ((adapter->function_mode & UMC_ENABLED) &&
	    veh->h_vlan_proto == htons(ETH_P_8021Q))
			*skip_hw_vlan = true;

	/* HW has a bug wherein it will calculate CSUM for VLAN
	 * pkts even though it is disabled.
	 * Manually insert VLAN in pkt.
	 */
	if (skb->ip_summed != CHECKSUM_PARTIAL &&
	    vlan_tx_tag_present(skb)) {
		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
		if (unlikely(!skb))
			goto tx_drop;
	}

	/* HW may lockup when VLAN HW tagging is requested on
	 * certain ipv6 packets. Drop such pkts if the HW workaround to
	 * skip HW tagging is not enabled by FW.
	 */
	if (unlikely(be_ipv6_tx_stall_chk(adapter, skb) &&
	    (adapter->pvid || adapter->qnq_vid) &&
	    !qnq_async_evt_rcvd(adapter)))
		goto tx_drop;

	/* Manual VLAN tag insertion to prevent:
	 * ASIC lockup when the ASIC inserts VLAN tag into
	 * certain ipv6 packets. Insert VLAN tags in driver,
	 * and set event, completion, vlan bits accordingly
	 * in the Tx WRB.
	 */
	if (be_ipv6_tx_stall_chk(adapter, skb) &&
	    be_vlan_tag_tx_chk(adapter, skb)) {
		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
		if (unlikely(!skb))
			goto tx_drop;
	}

	return skb;
tx_drop:
	dev_kfree_skb_any(skb);
	return NULL;
}

static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	struct be_tx_obj *txo = &adapter->tx_obj[skb_get_queue_mapping(skb)];
	struct be_queue_info *txq = &txo->q;
	bool dummy_wrb, stopped = false;
	u32 wrb_cnt = 0, copied = 0;
	bool skip_hw_vlan = false;
	u32 start = txq->head;

	skb = be_xmit_workarounds(adapter, skb, &skip_hw_vlan);
	if (!skb)
		return NETDEV_TX_OK;

	wrb_cnt = wrb_cnt_for_skb(adapter, skb, &dummy_wrb);

	copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb,
			      skip_hw_vlan);
	if (copied) {
		int gso_segs = skb_shinfo(skb)->gso_segs;

		/* record the sent skb in the sent_skb table */
		BUG_ON(txo->sent_skb_list[start]);
		txo->sent_skb_list[start] = skb;

		/* Ensure txq has space for the next skb; Else stop the queue
		 * *BEFORE* ringing the tx doorbell, so that we serialze the
		 * tx compls of the current transmit which'll wake up the queue
		 */
		atomic_add(wrb_cnt, &txq->used);
		if ((BE_MAX_TX_FRAG_COUNT + atomic_read(&txq->used)) >=
								txq->len) {
			netif_stop_subqueue(netdev, skb_get_queue_mapping(skb));
			stopped = true;
		}

		be_txq_notify(adapter, txo, wrb_cnt);

		be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped);
	} else {
		txq->head = start;
		dev_kfree_skb_any(skb);
	}
	return NETDEV_TX_OK;
}

static int be_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	if (new_mtu < BE_MIN_MTU ||
			new_mtu > (BE_MAX_JUMBO_FRAME_SIZE -
					(ETH_HLEN + ETH_FCS_LEN))) {
		dev_info(&adapter->pdev->dev,
			"MTU must be between %d and %d bytes\n",
			BE_MIN_MTU,
			(BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN)));
		return -EINVAL;
	}
	dev_info(&adapter->pdev->dev, "MTU changed from %d to %d bytes\n",
			netdev->mtu, new_mtu);
	netdev->mtu = new_mtu;
	return 0;
}

/*
 * A max of 64 (BE_NUM_VLANS_SUPPORTED) vlans can be configured in BE.
 * If the user configures more, place BE in vlan promiscuous mode.
 */
static int be_vid_config(struct be_adapter *adapter)
{
	u16 vids[BE_NUM_VLANS_SUPPORTED];
	u16 num = 0, i;
	int status = 0;

	/* No need to further configure vids if in promiscuous mode */
	if (adapter->promiscuous)
		return 0;

	if (adapter->vlans_added > be_max_vlans(adapter))
		goto set_vlan_promisc;

	/* Construct VLAN Table to give to HW */
	for (i = 0; i < VLAN_N_VID; i++)
		if (adapter->vlan_tag[i])
			vids[num++] = cpu_to_le16(i);

	status = be_cmd_vlan_config(adapter, adapter->if_handle,
				    vids, num, 1, 0);

	/* Set to VLAN promisc mode as setting VLAN filter failed */
	if (status) {
		dev_info(&adapter->pdev->dev, "Exhausted VLAN HW filters.\n");
		dev_info(&adapter->pdev->dev, "Disabling HW VLAN filtering.\n");
		goto set_vlan_promisc;
	}

	return status;

set_vlan_promisc:
	status = be_cmd_vlan_config(adapter, adapter->if_handle,
				    NULL, 0, 1, 1);
	return status;
}

static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	int status = 0;

	if (!lancer_chip(adapter) && !be_physfn(adapter)) {
		status = -EINVAL;
		goto ret;
	}

	/* Packets with VID 0 are always received by Lancer by default */
	if (lancer_chip(adapter) && vid == 0)
		goto ret;

	adapter->vlan_tag[vid] = 1;
	if (adapter->vlans_added <= (be_max_vlans(adapter) + 1))
		status = be_vid_config(adapter);

	if (!status)
		adapter->vlans_added++;
	else
		adapter->vlan_tag[vid] = 0;
ret:
	return status;
}

static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid)
{
	struct be_adapter *adapter = netdev_priv(netdev);
	int status = 0;

	if (!lancer_chip(adapter) && !be_physfn(adapter)) {
		status = -EINVAL;
		goto ret;
	}

	/* Packets with VID 0 are always received by Lancer by default */
	if (lancer_chip(adapter) && vid == 0)
		goto ret;

	adapter->vlan_tag[vid] = 0;
	if (adapter->vlans_added <= be_max_vlans(adapter))
		status = be_vid_config(adapter);