cxgb4_main.c

/*
 * This file is part of the Chelsio T4 Ethernet driver for Linux.
 *
 * Copyright (c) 2003-2010 Chelsio Communications, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/bitmap.h>
#include <linux/crc32.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/err.h>
#include <linux/etherdevice.h>
#include <linux/firmware.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/log2.h>
#include <linux/mdio.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <linux/rtnetlink.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/sockios.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <net/neighbour.h>
#include <net/netevent.h>
#include <asm/uaccess.h>

#include "cxgb4.h"
#include "t4_regs.h"
#include "t4_msg.h"
#include "t4fw_api.h"
#include "l2t.h"

#define DRV_VERSION "1.0.0-ko"
#define DRV_DESC "Chelsio T4 Network Driver"

/*
 * Max interrupt hold-off timer value in us.  Queues fall back to this value
 * under extreme memory pressure so it's largish to give the system time to
 * recover.
 */
#define MAX_SGE_TIMERVAL 200U

#ifdef CONFIG_PCI_IOV
/*
 * Virtual Function provisioning constants.  We need two extra Ingress Queues
 * with Interrupt capability to serve as the VF's Firmware Event Queue and
 * Forwarded Interrupt Queue (when using MSI mode) -- neither will have Free
 * Lists associated with them).  For each Ethernet/Control Egress Queue and
 * for each Free List, we need an Egress Context.
 */
enum {
	VFRES_NPORTS = 1,		/* # of "ports" per VF */
	VFRES_NQSETS = 2,		/* # of "Queue Sets" per VF */

	VFRES_NVI = VFRES_NPORTS,	/* # of Virtual Interfaces */
	VFRES_NETHCTRL = VFRES_NQSETS,	/* # of EQs used for ETH or CTRL Qs */
	VFRES_NIQFLINT = VFRES_NQSETS+2,/* # of ingress Qs/w Free List(s)/intr */
	VFRES_NIQ = 0,			/* # of non-fl/int ingress queues */
	VFRES_NEQ = VFRES_NQSETS*2,	/* # of egress queues */
	VFRES_TC = 0,			/* PCI-E traffic class */
	VFRES_NEXACTF = 16,		/* # of exact MPS filters */

	VFRES_R_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF|FW_CMD_CAP_PORT,
	VFRES_WX_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF,
};

/*
 * Provide a Port Access Rights Mask for the specified PF/VF.  This is very
 * static and likely not to be useful in the long run.  We really need to
 * implement some form of persistent configuration which the firmware
 * controls.
 */
static unsigned int pfvfres_pmask(struct adapter *adapter,
				  unsigned int pf, unsigned int vf)
{
	unsigned int portn, portvec;

	/*
	 * Give PF's access to all of the ports.
	 */
	if (vf == 0)
		return FW_PFVF_CMD_PMASK_MASK;

	/*
	 * For VFs, we'll assign them access to the ports based purely on the
	 * PF.  We assign active ports in order, wrapping around if there are
	 * fewer active ports than PFs: e.g. active port[pf % nports].
	 * Unfortunately the adapter's port_info structs haven't been
	 * initialized yet so we have to compute this.
	 */
	if (adapter->params.nports == 0)
		return 0;

	portn = pf % adapter->params.nports;
	portvec = adapter->params.portvec;
	for (;;) {
		/*
		 * Isolate the lowest set bit in the port vector.  If we're at
		 * the port number that we want, return that as the pmask.
		 * otherwise mask that bit out of the port vector and
		 * decrement our port number ...
		 */
		unsigned int pmask = portvec ^ (portvec & (portvec-1));
		if (portn == 0)
			return pmask;
		portn--;
		portvec &= ~pmask;
	}
	/*NOTREACHED*/
}
#endif

enum {
	MEMWIN0_APERTURE = 65536,
	MEMWIN0_BASE     = 0x30000,
	MEMWIN1_APERTURE = 32768,
	MEMWIN1_BASE     = 0x28000,
	MEMWIN2_APERTURE = 2048,
	MEMWIN2_BASE     = 0x1b800,
};

enum {
	MAX_TXQ_ENTRIES      = 16384,
	MAX_CTRL_TXQ_ENTRIES = 1024,
	MAX_RSPQ_ENTRIES     = 16384,
	MAX_RX_BUFFERS       = 16384,
	MIN_TXQ_ENTRIES      = 32,
	MIN_CTRL_TXQ_ENTRIES = 32,
	MIN_RSPQ_ENTRIES     = 128,
	MIN_FL_ENTRIES       = 16
};

#define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)

#define CH_DEVICE(devid) { PCI_VDEVICE(CHELSIO, devid), 0 }

static DEFINE_PCI_DEVICE_TABLE(cxgb4_pci_tbl) = {
	CH_DEVICE(0xa000),  /* PE10K */
	{ 0, }
};

#define FW_FNAME "cxgb4/t4fw.bin"

MODULE_DESCRIPTION(DRV_DESC);
MODULE_AUTHOR("Chelsio Communications");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl);
MODULE_FIRMWARE(FW_FNAME);

static int dflt_msg_enable = DFLT_MSG_ENABLE;

module_param(dflt_msg_enable, int, 0644);
MODULE_PARM_DESC(dflt_msg_enable, "Chelsio T4 default message enable bitmap");

/*
 * The driver uses the best interrupt scheme available on a platform in the
 * order MSI-X, MSI, legacy INTx interrupts.  This parameter determines which
 * of these schemes the driver may consider as follows:
 *
 * msi = 2: choose from among all three options
 * msi = 1: only consider MSI and INTx interrupts
 * msi = 0: force INTx interrupts
 */
static int msi = 2;

module_param(msi, int, 0644);
MODULE_PARM_DESC(msi, "whether to use INTx (0), MSI (1) or MSI-X (2)");

/*
 * Queue interrupt hold-off timer values.  Queues default to the first of these
 * upon creation.
 */
static unsigned int intr_holdoff[SGE_NTIMERS - 1] = { 5, 10, 20, 50, 100 };

module_param_array(intr_holdoff, uint, NULL, 0644);
MODULE_PARM_DESC(intr_holdoff, "values for queue interrupt hold-off timers "
		 "0..4 in microseconds");

static unsigned int intr_cnt[SGE_NCOUNTERS - 1] = { 4, 8, 16 };

module_param_array(intr_cnt, uint, NULL, 0644);
MODULE_PARM_DESC(intr_cnt,
		 "thresholds 1..3 for queue interrupt packet counters");

static int vf_acls;

#ifdef CONFIG_PCI_IOV
module_param(vf_acls, bool, 0644);
MODULE_PARM_DESC(vf_acls, "if set enable virtualization L2 ACL enforcement");

static unsigned int num_vf[4];

module_param_array(num_vf, uint, NULL, 0644);
MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3");
#endif

static struct dentry *cxgb4_debugfs_root;

static LIST_HEAD(adapter_list);
static DEFINE_MUTEX(uld_mutex);
static struct cxgb4_uld_info ulds[CXGB4_ULD_MAX];
static const char *uld_str[] = { "RDMA", "iSCSI" };

static void link_report(struct net_device *dev)
{
	if (!netif_carrier_ok(dev))
		netdev_info(dev, "link down\n");
	else {
		static const char *fc[] = { "no", "Rx", "Tx", "Tx/Rx" };

		const char *s = "10Mbps";
		const struct port_info *p = netdev_priv(dev);

		switch (p->link_cfg.speed) {
		case SPEED_10000:
			s = "10Gbps";
			break;
		case SPEED_1000:
			s = "1000Mbps";
			break;
		case SPEED_100:
			s = "100Mbps";
			break;
		}

		netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s,
			    fc[p->link_cfg.fc]);
	}
}

void t4_os_link_changed(struct adapter *adapter, int port_id, int link_stat)
{
	struct net_device *dev = adapter->port[port_id];

	/* Skip changes from disabled ports. */
	if (netif_running(dev) && link_stat != netif_carrier_ok(dev)) {
		if (link_stat)
			netif_carrier_on(dev);
		else
			netif_carrier_off(dev);

		link_report(dev);
	}
}

void t4_os_portmod_changed(const struct adapter *adap, int port_id)
{
	static const char *mod_str[] = {
		NULL, "LR", "SR", "ER", "passive DA", "active DA", "LRM"
	};

	const struct net_device *dev = adap->port[port_id];
	const struct port_info *pi = netdev_priv(dev);

	if (pi->mod_type == FW_PORT_MOD_TYPE_NONE)
		netdev_info(dev, "port module unplugged\n");
	else if (pi->mod_type < ARRAY_SIZE(mod_str))
		netdev_info(dev, "%s module inserted\n", mod_str[pi->mod_type]);
}

/*
 * Configure the exact and hash address filters to handle a port's multicast
 * and secondary unicast MAC addresses.
 */
static int set_addr_filters(const struct net_device *dev, bool sleep)
{
	u64 mhash = 0;
	u64 uhash = 0;
	bool free = true;
	u16 filt_idx[7];
	const u8 *addr[7];
	int ret, naddr = 0;
	const struct netdev_hw_addr *ha;
	int uc_cnt = netdev_uc_count(dev);
	int mc_cnt = netdev_mc_count(dev);
	const struct port_info *pi = netdev_priv(dev);

	/* first do the secondary unicast addresses */
	netdev_for_each_uc_addr(ha, dev) {
		addr[naddr++] = ha->addr;
		if (--uc_cnt == 0 || naddr >= ARRAY_SIZE(addr)) {
			ret = t4_alloc_mac_filt(pi->adapter, 0, pi->viid, free,
					naddr, addr, filt_idx, &uhash, sleep);
			if (ret < 0)
				return ret;

			free = false;
			naddr = 0;
		}
	}

	/* next set up the multicast addresses */
	netdev_for_each_mc_addr(ha, dev) {
		addr[naddr++] = ha->addr;
		if (--mc_cnt == 0 || naddr >= ARRAY_SIZE(addr)) {
			ret = t4_alloc_mac_filt(pi->adapter, 0, pi->viid, free,
					naddr, addr, filt_idx, &mhash, sleep);
			if (ret < 0)
				return ret;

			free = false;
			naddr = 0;
		}
	}

	return t4_set_addr_hash(pi->adapter, 0, pi->viid, uhash != 0,
				uhash | mhash, sleep);
}

/*
 * Set Rx properties of a port, such as promiscruity, address filters, and MTU.
 * If @mtu is -1 it is left unchanged.
 */
static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);

	ret = set_addr_filters(dev, sleep_ok);
	if (ret == 0)
		ret = t4_set_rxmode(pi->adapter, 0, pi->viid, mtu,
				    (dev->flags & IFF_PROMISC) ? 1 : 0,
				    (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1,
				    sleep_ok);
	return ret;
}

/**
 *	link_start - enable a port
 *	@dev: the port to enable
 *
 *	Performs the MAC and PHY actions needed to enable a port.
 */
static int link_start(struct net_device *dev)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);

	/*
	 * We do not set address filters and promiscuity here, the stack does
	 * that step explicitly.
	 */
	ret = t4_set_rxmode(pi->adapter, 0, pi->viid, dev->mtu, -1, -1, -1,
			    pi->vlan_grp != NULL, true);
	if (ret == 0) {
		ret = t4_change_mac(pi->adapter, 0, pi->viid,
				    pi->xact_addr_filt, dev->dev_addr, true,
				    true);
		if (ret >= 0) {
			pi->xact_addr_filt = ret;
			ret = 0;
		}
	}
	if (ret == 0)
		ret = t4_link_start(pi->adapter, 0, pi->tx_chan, &pi->link_cfg);
	if (ret == 0)
		ret = t4_enable_vi(pi->adapter, 0, pi->viid, true, true);
	return ret;
}

/*
 * Response queue handler for the FW event queue.
 */
static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
			  const struct pkt_gl *gl)
{
	u8 opcode = ((const struct rss_header *)rsp)->opcode;

	rsp++;                                          /* skip RSS header */
	if (likely(opcode == CPL_SGE_EGR_UPDATE)) {
		const struct cpl_sge_egr_update *p = (void *)rsp;
		unsigned int qid = EGR_QID(ntohl(p->opcode_qid));
		struct sge_txq *txq = q->adap->sge.egr_map[qid];

		txq->restarts++;
		if ((u8 *)txq < (u8 *)q->adap->sge.ethrxq) {
			struct sge_eth_txq *eq;

			eq = container_of(txq, struct sge_eth_txq, q);
			netif_tx_wake_queue(eq->txq);
		} else {
			struct sge_ofld_txq *oq;

			oq = container_of(txq, struct sge_ofld_txq, q);
			tasklet_schedule(&oq->qresume_tsk);
		}
	} else if (opcode == CPL_FW6_MSG || opcode == CPL_FW4_MSG) {
		const struct cpl_fw6_msg *p = (void *)rsp;

		if (p->type == 0)
			t4_handle_fw_rpl(q->adap, p->data);
	} else if (opcode == CPL_L2T_WRITE_RPL) {
		const struct cpl_l2t_write_rpl *p = (void *)rsp;

		do_l2t_write_rpl(q->adap, p);
	} else
		dev_err(q->adap->pdev_dev,
			"unexpected CPL %#x on FW event queue\n", opcode);
	return 0;
}

/**
 *	uldrx_handler - response queue handler for ULD queues
 *	@q: the response queue that received the packet
 *	@rsp: the response queue descriptor holding the offload message
 *	@gl: the gather list of packet fragments
 *
 *	Deliver an ingress offload packet to a ULD.  All processing is done by
 *	the ULD, we just maintain statistics.
 */
static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
			 const struct pkt_gl *gl)
{
	struct sge_ofld_rxq *rxq = container_of(q, struct sge_ofld_rxq, rspq);

	if (ulds[q->uld].rx_handler(q->adap->uld_handle[q->uld], rsp, gl)) {
		rxq->stats.nomem++;
		return -1;
	}
	if (gl == NULL)
		rxq->stats.imm++;
	else if (gl == CXGB4_MSG_AN)
		rxq->stats.an++;
	else
		rxq->stats.pkts++;
	return 0;
}

static void disable_msi(struct adapter *adapter)
{
	if (adapter->flags & USING_MSIX) {
		pci_disable_msix(adapter->pdev);
		adapter->flags &= ~USING_MSIX;
	} else if (adapter->flags & USING_MSI) {
		pci_disable_msi(adapter->pdev);
		adapter->flags &= ~USING_MSI;
	}
}

/*
 * Interrupt handler for non-data events used with MSI-X.
 */
static irqreturn_t t4_nondata_intr(int irq, void *cookie)
{
	struct adapter *adap = cookie;

	u32 v = t4_read_reg(adap, MYPF_REG(PL_PF_INT_CAUSE));
	if (v & PFSW) {
		adap->swintr = 1;
		t4_write_reg(adap, MYPF_REG(PL_PF_INT_CAUSE), v);
	}
	t4_slow_intr_handler(adap);
	return IRQ_HANDLED;
}

/*
 * Name the MSI-X interrupts.
 */
static void name_msix_vecs(struct adapter *adap)
{
	int i, j, msi_idx = 2, n = sizeof(adap->msix_info[0].desc) - 1;

	/* non-data interrupts */
	snprintf(adap->msix_info[0].desc, n, "%s", adap->name);
	adap->msix_info[0].desc[n] = 0;

	/* FW events */
	snprintf(adap->msix_info[1].desc, n, "%s-FWeventq", adap->name);
	adap->msix_info[1].desc[n] = 0;

	/* Ethernet queues */
	for_each_port(adap, j) {
		struct net_device *d = adap->port[j];
		const struct port_info *pi = netdev_priv(d);

		for (i = 0; i < pi->nqsets; i++, msi_idx++) {
			snprintf(adap->msix_info[msi_idx].desc, n, "%s-Rx%d",
				 d->name, i);
			adap->msix_info[msi_idx].desc[n] = 0;
		}
	}

	/* offload queues */
	for_each_ofldrxq(&adap->sge, i) {
		snprintf(adap->msix_info[msi_idx].desc, n, "%s-ofld%d",
			 adap->name, i);
		adap->msix_info[msi_idx++].desc[n] = 0;
	}
	for_each_rdmarxq(&adap->sge, i) {
		snprintf(adap->msix_info[msi_idx].desc, n, "%s-rdma%d",
			 adap->name, i);
		adap->msix_info[msi_idx++].desc[n] = 0;
	}
}

static int request_msix_queue_irqs(struct adapter *adap)
{
	struct sge *s = &adap->sge;
	int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, msi = 2;

	err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0,
			  adap->msix_info[1].desc, &s->fw_evtq);
	if (err)
		return err;

	for_each_ethrxq(s, ethqidx) {
		err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0,
				  adap->msix_info[msi].desc,
				  &s->ethrxq[ethqidx].rspq);
		if (err)
			goto unwind;
		msi++;
	}
	for_each_ofldrxq(s, ofldqidx) {
		err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0,
				  adap->msix_info[msi].desc,
				  &s->ofldrxq[ofldqidx].rspq);
		if (err)
			goto unwind;
		msi++;
	}
	for_each_rdmarxq(s, rdmaqidx) {
		err = request_irq(adap->msix_info[msi].vec, t4_sge_intr_msix, 0,
				  adap->msix_info[msi].desc,
				  &s->rdmarxq[rdmaqidx].rspq);
		if (err)
			goto unwind;
		msi++;
	}
	return 0;

unwind:
	while (--rdmaqidx >= 0)
		free_irq(adap->msix_info[--msi].vec,
			 &s->rdmarxq[rdmaqidx].rspq);
	while (--ofldqidx >= 0)
		free_irq(adap->msix_info[--msi].vec,
			 &s->ofldrxq[ofldqidx].rspq);
	while (--ethqidx >= 0)
		free_irq(adap->msix_info[--msi].vec, &s->ethrxq[ethqidx].rspq);
	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
	return err;
}

static void free_msix_queue_irqs(struct adapter *adap)
{
	int i, msi = 2;
	struct sge *s = &adap->sge;

	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
	for_each_ethrxq(s, i)
		free_irq(adap->msix_info[msi++].vec, &s->ethrxq[i].rspq);
	for_each_ofldrxq(s, i)
		free_irq(adap->msix_info[msi++].vec, &s->ofldrxq[i].rspq);
	for_each_rdmarxq(s, i)
		free_irq(adap->msix_info[msi++].vec, &s->rdmarxq[i].rspq);
}

/**
 *	setup_rss - configure RSS
 *	@adap: the adapter
 *
 *	Sets up RSS to distribute packets to multiple receive queues.  We
 *	configure the RSS CPU lookup table to distribute to the number of HW
 *	receive queues, and the response queue lookup table to narrow that
 *	down to the response queues actually configured for each port.
 *	We always configure the RSS mapping for all ports since the mapping
 *	table has plenty of entries.
 */
static int setup_rss(struct adapter *adap)
{
	int i, j, err;
	u16 rss[MAX_ETH_QSETS];

	for_each_port(adap, i) {
		const struct port_info *pi = adap2pinfo(adap, i);
		const struct sge_eth_rxq *q = &adap->sge.ethrxq[pi->first_qset];

		for (j = 0; j < pi->nqsets; j++)
			rss[j] = q[j].rspq.abs_id;

		err = t4_config_rss_range(adap, 0, pi->viid, 0, pi->rss_size,
					  rss, pi->nqsets);
		if (err)
			return err;
	}
	return 0;
}

/*
 * Wait until all NAPI handlers are descheduled.
 */
static void quiesce_rx(struct adapter *adap)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(adap->sge.ingr_map); i++) {
		struct sge_rspq *q = adap->sge.ingr_map[i];

		if (q && q->handler)
			napi_disable(&q->napi);
	}
}

/*
 * Enable NAPI scheduling and interrupt generation for all Rx queues.
 */
static void enable_rx(struct adapter *adap)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(adap->sge.ingr_map); i++) {
		struct sge_rspq *q = adap->sge.ingr_map[i];

		if (!q)
			continue;
		if (q->handler)
			napi_enable(&q->napi);
		/* 0-increment GTS to start the timer and enable interrupts */
		t4_write_reg(adap, MYPF_REG(SGE_PF_GTS),
			     SEINTARM(q->intr_params) |
			     INGRESSQID(q->cntxt_id));
	}
}

/**
 *	setup_sge_queues - configure SGE Tx/Rx/response queues
 *	@adap: the adapter
 *
 *	Determines how many sets of SGE queues to use and initializes them.
 *	We support multiple queue sets per port if we have MSI-X, otherwise
 *	just one queue set per port.
 */
static int setup_sge_queues(struct adapter *adap)
{
	int err, msi_idx, i, j;
	struct sge *s = &adap->sge;

	bitmap_zero(s->starving_fl, MAX_EGRQ);
	bitmap_zero(s->txq_maperr, MAX_EGRQ);

	if (adap->flags & USING_MSIX)
		msi_idx = 1;         /* vector 0 is for non-queue interrupts */
	else {
		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
				       NULL, NULL);
		if (err)
			return err;
		msi_idx = -((int)s->intrq.abs_id + 1);
	}

	err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0],
			       msi_idx, NULL, fwevtq_handler);
	if (err) {
freeout:	t4_free_sge_resources(adap);
		return err;
	}

	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];
		struct port_info *pi = netdev_priv(dev);
		struct sge_eth_rxq *q = &s->ethrxq[pi->first_qset];
		struct sge_eth_txq *t = &s->ethtxq[pi->first_qset];

		for (j = 0; j < pi->nqsets; j++, q++) {
			if (msi_idx > 0)
				msi_idx++;
			err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev,
					       msi_idx, &q->fl,
					       t4_ethrx_handler);
			if (err)
				goto freeout;
			q->rspq.idx = j;
			memset(&q->stats, 0, sizeof(q->stats));
		}
		for (j = 0; j < pi->nqsets; j++, t++) {
			err = t4_sge_alloc_eth_txq(adap, t, dev,
					netdev_get_tx_queue(dev, j),
					s->fw_evtq.cntxt_id);
			if (err)
				goto freeout;
		}
	}

	j = s->ofldqsets / adap->params.nports; /* ofld queues per channel */
	for_each_ofldrxq(s, i) {
		struct sge_ofld_rxq *q = &s->ofldrxq[i];
		struct net_device *dev = adap->port[i / j];

		if (msi_idx > 0)
			msi_idx++;
		err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev, msi_idx,
				       &q->fl, uldrx_handler);
		if (err)
			goto freeout;
		memset(&q->stats, 0, sizeof(q->stats));
		s->ofld_rxq[i] = q->rspq.abs_id;
		err = t4_sge_alloc_ofld_txq(adap, &s->ofldtxq[i], dev,
					    s->fw_evtq.cntxt_id);
		if (err)
			goto freeout;
	}

	for_each_rdmarxq(s, i) {
		struct sge_ofld_rxq *q = &s->rdmarxq[i];

		if (msi_idx > 0)
			msi_idx++;
		err = t4_sge_alloc_rxq(adap, &q->rspq, false, adap->port[i],
				       msi_idx, &q->fl, uldrx_handler);
		if (err)
			goto freeout;
		memset(&q->stats, 0, sizeof(q->stats));
		s->rdma_rxq[i] = q->rspq.abs_id;
	}

	for_each_port(adap, i) {
		/*
		 * Note that ->rdmarxq[i].rspq.cntxt_id below is 0 if we don't
		 * have RDMA queues, and that's the right value.
		 */
		err = t4_sge_alloc_ctrl_txq(adap, &s->ctrlq[i], adap->port[i],
					    s->fw_evtq.cntxt_id,
					    s->rdmarxq[i].rspq.cntxt_id);
		if (err)
			goto freeout;
	}

	t4_write_reg(adap, MPS_TRC_RSS_CONTROL,
		     RSSCONTROL(netdev2pinfo(adap->port[0])->tx_chan) |
		     QUEUENUMBER(s->ethrxq[0].rspq.abs_id));
	return 0;
}

/*
 * Returns 0 if new FW was successfully loaded, a positive errno if a load was
 * started but failed, and a negative errno if flash load couldn't start.
 */
static int upgrade_fw(struct adapter *adap)
{
	int ret;
	u32 vers;
	const struct fw_hdr *hdr;
	const struct firmware *fw;
	struct device *dev = adap->pdev_dev;

	ret = request_firmware(&fw, FW_FNAME, dev);
	if (ret < 0) {
		dev_err(dev, "unable to load firmware image " FW_FNAME
			", error %d\n", ret);
		return ret;
	}

	hdr = (const struct fw_hdr *)fw->data;
	vers = ntohl(hdr->fw_ver);
	if (FW_HDR_FW_VER_MAJOR_GET(vers) != FW_VERSION_MAJOR) {
		ret = -EINVAL;              /* wrong major version, won't do */
		goto out;
	}

	/*
	 * If the flash FW is unusable or we found something newer, load it.
	 */
	if (FW_HDR_FW_VER_MAJOR_GET(adap->params.fw_vers) != FW_VERSION_MAJOR ||
	    vers > adap->params.fw_vers) {
		ret = -t4_load_fw(adap, fw->data, fw->size);
		if (!ret)
			dev_info(dev, "firmware upgraded to version %pI4 from "
				 FW_FNAME "\n", &hdr->fw_ver);
	}
out:	release_firmware(fw);
	return ret;
}

/*
 * Allocate a chunk of memory using kmalloc or, if that fails, vmalloc.
 * The allocated memory is cleared.
 */
void *t4_alloc_mem(size_t size)
{
	void *p = kmalloc(size, GFP_KERNEL);

	if (!p)
		p = vmalloc(size);
	if (p)
		memset(p, 0, size);
	return p;
}

/*
 * Free memory allocated through alloc_mem().
 */
void t4_free_mem(void *addr)
{
	if (is_vmalloc_addr(addr))
		vfree(addr);
	else
		kfree(addr);
}

static inline int is_offload(const struct adapter *adap)
{
	return adap->params.offload;
}

/*
 * Implementation of ethtool operations.
 */

static u32 get_msglevel(struct net_device *dev)
{
	return netdev2adap(dev)->msg_enable;
}

static void set_msglevel(struct net_device *dev, u32 val)
{
	netdev2adap(dev)->msg_enable = val;
}

static char stats_strings[][ETH_GSTRING_LEN] = {
	"TxOctetsOK         ",
	"TxFramesOK         ",
	"TxBroadcastFrames  ",
	"TxMulticastFrames  ",
	"TxUnicastFrames    ",
	"TxErrorFrames      ",

	"TxFrames64         ",
	"TxFrames65To127    ",
	"TxFrames128To255   ",
	"TxFrames256To511   ",
	"TxFrames512To1023  ",
	"TxFrames1024To1518 ",
	"TxFrames1519ToMax  ",

	"TxFramesDropped    ",
	"TxPauseFrames      ",
	"TxPPP0Frames       ",
	"TxPPP1Frames       ",
	"TxPPP2Frames       ",
	"TxPPP3Frames       ",
	"TxPPP4Frames       ",
	"TxPPP5Frames       ",
	"TxPPP6Frames       ",
	"TxPPP7Frames       ",

	"RxOctetsOK         ",
	"RxFramesOK         ",
	"RxBroadcastFrames  ",
	"RxMulticastFrames  ",
	"RxUnicastFrames    ",

	"RxFramesTooLong    ",
	"RxJabberErrors     ",
	"RxFCSErrors        ",
	"RxLengthErrors     ",
	"RxSymbolErrors     ",
	"RxRuntFrames       ",

	"RxFrames64         ",
	"RxFrames65To127    ",
	"RxFrames128To255   ",
	"RxFrames256To511   ",
	"RxFrames512To1023  ",
	"RxFrames1024To1518 ",
	"RxFrames1519ToMax  ",

	"RxPauseFrames      ",
	"RxPPP0Frames       ",
	"RxPPP1Frames       ",
	"RxPPP2Frames       ",
	"RxPPP3Frames       ",
	"RxPPP4Frames       ",
	"RxPPP5Frames       ",
	"RxPPP6Frames       ",
	"RxPPP7Frames       ",

	"RxBG0FramesDropped ",
	"RxBG1FramesDropped ",
	"RxBG2FramesDropped ",
	"RxBG3FramesDropped ",
	"RxBG0FramesTrunc   ",
	"RxBG1FramesTrunc   ",
	"RxBG2FramesTrunc   ",
	"RxBG3FramesTrunc   ",

	"TSO                ",
	"TxCsumOffload      ",
	"RxCsumGood         ",
	"VLANextractions    ",
	"VLANinsertions     ",
	"GROpackets         ",
	"GROmerged          ",
};

static int get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(stats_strings);
	default:
		return -EOPNOTSUPP;
	}
}

#define T4_REGMAP_SIZE (160 * 1024)

static int get_regs_len(struct net_device *dev)
{
	return T4_REGMAP_SIZE;
}

static int get_eeprom_len(struct net_device *dev)
{
	return EEPROMSIZE;
}

static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	struct adapter *adapter = netdev2adap(dev);

	strcpy(info->driver, KBUILD_MODNAME);
	strcpy(info->version, DRV_VERSION);
	strcpy(info->bus_info, pci_name(adapter->pdev));

	if (!adapter->params.fw_vers)
		strcpy(info->fw_version, "N/A");
	else
		snprintf(info->fw_version, sizeof(info->fw_version),
			"%u.%u.%u.%u, TP %u.%u.%u.%u",
			FW_HDR_FW_VER_MAJOR_GET(adapter->params.fw_vers),
			FW_HDR_FW_VER_MINOR_GET(adapter->params.fw_vers),
			FW_HDR_FW_VER_MICRO_GET(adapter->params.fw_vers),
			FW_HDR_FW_VER_BUILD_GET(adapter->params.fw_vers),
			FW_HDR_FW_VER_MAJOR_GET(adapter->params.tp_vers),
			FW_HDR_FW_VER_MINOR_GET(adapter->params.tp_vers),
			FW_HDR_FW_VER_MICRO_GET(adapter->params.tp_vers),
			FW_HDR_FW_VER_BUILD_GET(adapter->params.tp_vers));
}

static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	if (stringset == ETH_SS_STATS)
		memcpy(data, stats_strings, sizeof(stats_strings));
}

/*
 * port stats maintained per queue of the port.  They should be in the same
 * order as in stats_strings above.
 */
struct queue_port_stats {
	u64 tso;
	u64 tx_csum;
	u64 rx_csum;
	u64 vlan_ex;
	u64 vlan_ins;
	u64 gro_pkts;
	u64 gro_merged;
};