Skip to content
cxgb4_main.c 88.5 KiB
Newer Older
2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329
		mk_tid_release(skb, chan, p - adap->tids.tid_tab);
		t4_ofld_send(adap, skb);
		spin_lock_bh(&adap->tid_release_lock);
	}
	adap->tid_release_task_busy = false;
	spin_unlock_bh(&adap->tid_release_lock);
}

/*
 * Release a TID and inform HW.  If we are unable to allocate the release
 * message we defer to a work queue.
 */
void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid)
{
	void *old;
	struct sk_buff *skb;
	struct adapter *adap = container_of(t, struct adapter, tids);

	old = t->tid_tab[tid];
	skb = alloc_skb(sizeof(struct cpl_tid_release), GFP_ATOMIC);
	if (likely(skb)) {
		t->tid_tab[tid] = NULL;
		mk_tid_release(skb, chan, tid);
		t4_ofld_send(adap, skb);
	} else
		cxgb4_queue_tid_release(t, chan, tid);
	if (old)
		atomic_dec(&t->tids_in_use);
}
EXPORT_SYMBOL(cxgb4_remove_tid);

/*
 * Allocate and initialize the TID tables.  Returns 0 on success.
 */
static int tid_init(struct tid_info *t)
{
	size_t size;
	unsigned int natids = t->natids;

	size = t->ntids * sizeof(*t->tid_tab) + natids * sizeof(*t->atid_tab) +
	       t->nstids * sizeof(*t->stid_tab) +
	       BITS_TO_LONGS(t->nstids) * sizeof(long);
	t->tid_tab = t4_alloc_mem(size);
	if (!t->tid_tab)
		return -ENOMEM;

	t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
	t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids];
	spin_lock_init(&t->stid_lock);
	spin_lock_init(&t->atid_lock);

	t->stids_in_use = 0;
	t->afree = NULL;
	t->atids_in_use = 0;
	atomic_set(&t->tids_in_use, 0);

	/* Setup the free list for atid_tab and clear the stid bitmap. */
	if (natids) {
		while (--natids)
			t->atid_tab[natids - 1].next = &t->atid_tab[natids];
		t->afree = t->atid_tab;
	}
	bitmap_zero(t->stid_bmap, t->nstids);
	return 0;
}

/**
 *	cxgb4_create_server - create an IP server
 *	@dev: the device
 *	@stid: the server TID
 *	@sip: local IP address to bind server to
 *	@sport: the server's TCP port
 *	@queue: queue to direct messages from this server to
 *
 *	Create an IP server for the given port and address.
 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
 */
int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
			__be32 sip, __be16 sport, unsigned int queue)
{
	unsigned int chan;
	struct sk_buff *skb;
	struct adapter *adap;
	struct cpl_pass_open_req *req;

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	adap = netdev2adap(dev);
	req = (struct cpl_pass_open_req *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, 0);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ, stid));
	req->local_port = sport;
	req->peer_port = htons(0);
	req->local_ip = sip;
	req->peer_ip = htonl(0);
	chan = netdev2pinfo(adap->sge.ingr_map[queue]->netdev)->tx_chan;
	req->opt0 = cpu_to_be64(TX_CHAN(chan));
	req->opt1 = cpu_to_be64(CONN_POLICY_ASK |
				SYN_RSS_ENABLE | SYN_RSS_QUEUE(queue));
	return t4_mgmt_tx(adap, skb);
}
EXPORT_SYMBOL(cxgb4_create_server);

/**
 *	cxgb4_create_server6 - create an IPv6 server
 *	@dev: the device
 *	@stid: the server TID
 *	@sip: local IPv6 address to bind server to
 *	@sport: the server's TCP port
 *	@queue: queue to direct messages from this server to
 *
 *	Create an IPv6 server for the given port and address.
 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
 */
int cxgb4_create_server6(const struct net_device *dev, unsigned int stid,
			 const struct in6_addr *sip, __be16 sport,
			 unsigned int queue)
{
	unsigned int chan;
	struct sk_buff *skb;
	struct adapter *adap;
	struct cpl_pass_open_req6 *req;

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	adap = netdev2adap(dev);
	req = (struct cpl_pass_open_req6 *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, 0);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ6, stid));
	req->local_port = sport;
	req->peer_port = htons(0);
	req->local_ip_hi = *(__be64 *)(sip->s6_addr);
	req->local_ip_lo = *(__be64 *)(sip->s6_addr + 8);
	req->peer_ip_hi = cpu_to_be64(0);
	req->peer_ip_lo = cpu_to_be64(0);
	chan = netdev2pinfo(adap->sge.ingr_map[queue]->netdev)->tx_chan;
	req->opt0 = cpu_to_be64(TX_CHAN(chan));
	req->opt1 = cpu_to_be64(CONN_POLICY_ASK |
				SYN_RSS_ENABLE | SYN_RSS_QUEUE(queue));
	return t4_mgmt_tx(adap, skb);
}
EXPORT_SYMBOL(cxgb4_create_server6);

/**
 *	cxgb4_best_mtu - find the entry in the MTU table closest to an MTU
 *	@mtus: the HW MTU table
 *	@mtu: the target MTU
 *	@idx: index of selected entry in the MTU table
 *
 *	Returns the index and the value in the HW MTU table that is closest to
 *	but does not exceed @mtu, unless @mtu is smaller than any value in the
 *	table, in which case that smallest available value is selected.
 */
unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
			    unsigned int *idx)
{
	unsigned int i = 0;

	while (i < NMTUS - 1 && mtus[i + 1] <= mtu)
		++i;
	if (idx)
		*idx = i;
	return mtus[i];
}
EXPORT_SYMBOL(cxgb4_best_mtu);

/**
 *	cxgb4_port_chan - get the HW channel of a port
 *	@dev: the net device for the port
 *
 *	Return the HW Tx channel of the given port.
 */
unsigned int cxgb4_port_chan(const struct net_device *dev)
{
	return netdev2pinfo(dev)->tx_chan;
}
EXPORT_SYMBOL(cxgb4_port_chan);

/**
 *	cxgb4_port_viid - get the VI id of a port
 *	@dev: the net device for the port
 *
 *	Return the VI id of the given port.
 */
unsigned int cxgb4_port_viid(const struct net_device *dev)
{
	return netdev2pinfo(dev)->viid;
}
EXPORT_SYMBOL(cxgb4_port_viid);

/**
 *	cxgb4_port_idx - get the index of a port
 *	@dev: the net device for the port
 *
 *	Return the index of the given port.
 */
unsigned int cxgb4_port_idx(const struct net_device *dev)
{
	return netdev2pinfo(dev)->port_id;
}
EXPORT_SYMBOL(cxgb4_port_idx);

/**
 *	cxgb4_netdev_by_hwid - return the net device of a HW port
 *	@pdev: identifies the adapter
 *	@id: the HW port id
 *
 *	Return the net device associated with the interface with the given HW
 *	id.
 */
struct net_device *cxgb4_netdev_by_hwid(struct pci_dev *pdev, unsigned int id)
{
	const struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap || id >= NCHAN)
		return NULL;
	id = adap->chan_map[id];
	return id < MAX_NPORTS ? adap->port[id] : NULL;
}
EXPORT_SYMBOL(cxgb4_netdev_by_hwid);

void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4,
			 struct tp_tcp_stats *v6)
{
	struct adapter *adap = pci_get_drvdata(pdev);

	spin_lock(&adap->stats_lock);
	t4_tp_get_tcp_stats(adap, v4, v6);
	spin_unlock(&adap->stats_lock);
}
EXPORT_SYMBOL(cxgb4_get_tcp_stats);

void cxgb4_iscsi_init(struct net_device *dev, unsigned int tag_mask,
		      const unsigned int *pgsz_order)
{
	struct adapter *adap = netdev2adap(dev);

	t4_write_reg(adap, ULP_RX_ISCSI_TAGMASK, tag_mask);
	t4_write_reg(adap, ULP_RX_ISCSI_PSZ, HPZ0(pgsz_order[0]) |
		     HPZ1(pgsz_order[1]) | HPZ2(pgsz_order[2]) |
		     HPZ3(pgsz_order[3]));
}
EXPORT_SYMBOL(cxgb4_iscsi_init);

static struct pci_driver cxgb4_driver;

static void check_neigh_update(struct neighbour *neigh)
{
	const struct device *parent;
	const struct net_device *netdev = neigh->dev;

	if (netdev->priv_flags & IFF_802_1Q_VLAN)
		netdev = vlan_dev_real_dev(netdev);
	parent = netdev->dev.parent;
	if (parent && parent->driver == &cxgb4_driver.driver)
		t4_l2t_update(dev_get_drvdata(parent), neigh);
}

static int netevent_cb(struct notifier_block *nb, unsigned long event,
		       void *data)
{
	switch (event) {
	case NETEVENT_NEIGH_UPDATE:
		check_neigh_update(data);
		break;
	case NETEVENT_PMTU_UPDATE:
	case NETEVENT_REDIRECT:
	default:
		break;
	}
	return 0;
}

static bool netevent_registered;
static struct notifier_block cxgb4_netevent_nb = {
	.notifier_call = netevent_cb
};

static void uld_attach(struct adapter *adap, unsigned int uld)
{
	void *handle;
	struct cxgb4_lld_info lli;

	lli.pdev = adap->pdev;
	lli.l2t = adap->l2t;
	lli.tids = &adap->tids;
	lli.ports = adap->port;
	lli.vr = &adap->vres;
	lli.mtus = adap->params.mtus;
	if (uld == CXGB4_ULD_RDMA) {
		lli.rxq_ids = adap->sge.rdma_rxq;
		lli.nrxq = adap->sge.rdmaqs;
	} else if (uld == CXGB4_ULD_ISCSI) {
		lli.rxq_ids = adap->sge.ofld_rxq;
		lli.nrxq = adap->sge.ofldqsets;
	}
	lli.ntxq = adap->sge.ofldqsets;
	lli.nchan = adap->params.nports;
	lli.nports = adap->params.nports;
	lli.wr_cred = adap->params.ofldq_wr_cred;
	lli.adapter_type = adap->params.rev;
	lli.iscsi_iolen = MAXRXDATA_GET(t4_read_reg(adap, TP_PARA_REG2));
	lli.udb_density = 1 << QUEUESPERPAGEPF0_GET(
			t4_read_reg(adap, SGE_EGRESS_QUEUES_PER_PAGE_PF));
	lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
			t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF));
	lli.gts_reg = adap->regs + MYPF_REG(SGE_PF_GTS);
	lli.db_reg = adap->regs + MYPF_REG(SGE_PF_KDOORBELL);
	lli.fw_vers = adap->params.fw_vers;

	handle = ulds[uld].add(&lli);
	if (IS_ERR(handle)) {
		dev_warn(adap->pdev_dev,
			 "could not attach to the %s driver, error %ld\n",
			 uld_str[uld], PTR_ERR(handle));
		return;
	}

	adap->uld_handle[uld] = handle;

	if (!netevent_registered) {
		register_netevent_notifier(&cxgb4_netevent_nb);
		netevent_registered = true;
	}

	if (adap->flags & FULL_INIT_DONE)
		ulds[uld].state_change(handle, CXGB4_STATE_UP);
}

static void attach_ulds(struct adapter *adap)
{
	unsigned int i;

	mutex_lock(&uld_mutex);
	list_add_tail(&adap->list_node, &adapter_list);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (ulds[i].add)
			uld_attach(adap, i);
	mutex_unlock(&uld_mutex);
}

static void detach_ulds(struct adapter *adap)
{
	unsigned int i;

	mutex_lock(&uld_mutex);
	list_del(&adap->list_node);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (adap->uld_handle[i]) {
			ulds[i].state_change(adap->uld_handle[i],
					     CXGB4_STATE_DETACH);
			adap->uld_handle[i] = NULL;
		}
	if (netevent_registered && list_empty(&adapter_list)) {
		unregister_netevent_notifier(&cxgb4_netevent_nb);
		netevent_registered = false;
	}
	mutex_unlock(&uld_mutex);
}

static void notify_ulds(struct adapter *adap, enum cxgb4_state new_state)
{
	unsigned int i;

	mutex_lock(&uld_mutex);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (adap->uld_handle[i])
			ulds[i].state_change(adap->uld_handle[i], new_state);
	mutex_unlock(&uld_mutex);
}

/**
 *	cxgb4_register_uld - register an upper-layer driver
 *	@type: the ULD type
 *	@p: the ULD methods
 *
 *	Registers an upper-layer driver with this driver and notifies the ULD
 *	about any presently available devices that support its type.  Returns
 *	%-EBUSY if a ULD of the same type is already registered.
 */
int cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p)
{
	int ret = 0;
	struct adapter *adap;

	if (type >= CXGB4_ULD_MAX)
		return -EINVAL;
	mutex_lock(&uld_mutex);
	if (ulds[type].add) {
		ret = -EBUSY;
		goto out;
	}
	ulds[type] = *p;
	list_for_each_entry(adap, &adapter_list, list_node)
		uld_attach(adap, type);
out:	mutex_unlock(&uld_mutex);
	return ret;
}
EXPORT_SYMBOL(cxgb4_register_uld);

/**
 *	cxgb4_unregister_uld - unregister an upper-layer driver
 *	@type: the ULD type
 *
 *	Unregisters an existing upper-layer driver.
 */
int cxgb4_unregister_uld(enum cxgb4_uld type)
{
	struct adapter *adap;

	if (type >= CXGB4_ULD_MAX)
		return -EINVAL;
	mutex_lock(&uld_mutex);
	list_for_each_entry(adap, &adapter_list, list_node)
		adap->uld_handle[type] = NULL;
	ulds[type].add = NULL;
	mutex_unlock(&uld_mutex);
	return 0;
}
EXPORT_SYMBOL(cxgb4_unregister_uld);

/**
 *	cxgb_up - enable the adapter
 *	@adap: adapter being enabled
 *
 *	Called when the first port is enabled, this function performs the
 *	actions necessary to make an adapter operational, such as completing
 *	the initialization of HW modules, and enabling interrupts.
 *
 *	Must be called with the rtnl lock held.
 */
static int cxgb_up(struct adapter *adap)
{
	err = setup_sge_queues(adap);
	if (err)
		goto out;
	err = setup_rss(adap);
	if (err)
		goto freeq;

	if (adap->flags & USING_MSIX) {
		err = request_irq(adap->msix_info[0].vec, t4_nondata_intr, 0,
				  adap->msix_info[0].desc, adap);
		if (err)
			goto irq_err;

		err = request_msix_queue_irqs(adap);
		if (err) {
			free_irq(adap->msix_info[0].vec, adap);
			goto irq_err;
		}
	} else {
		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
				  adap->name, adap);
		if (err)
			goto irq_err;
	}
	enable_rx(adap);
	t4_sge_start(adap);
	t4_intr_enable(adap);
	notify_ulds(adap, CXGB4_STATE_UP);
 out:
	return err;
 irq_err:
	dev_err(adap->pdev_dev, "request_irq failed, err %d\n", err);
	goto out;
}

static void cxgb_down(struct adapter *adapter)
{
	t4_intr_disable(adapter);
	cancel_work_sync(&adapter->tid_release_task);
	adapter->tid_release_task_busy = false;
	adapter->tid_release_head = NULL;

	if (adapter->flags & USING_MSIX) {
		free_msix_queue_irqs(adapter);
		free_irq(adapter->msix_info[0].vec, adapter);
	} else
		free_irq(adapter->pdev->irq, adapter);
	quiesce_rx(adapter);
	t4_sge_stop(adapter);
	t4_free_sge_resources(adapter);
	adapter->flags &= ~FULL_INIT_DONE;
}

/*
 * net_device operations
 */
static int cxgb_open(struct net_device *dev)
{
	int err;
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	if (!(adapter->flags & FULL_INIT_DONE)) {
		err = cxgb_up(adapter);
		if (err < 0)
			return err;
	}

	dev->real_num_tx_queues = pi->nqsets;
	err = link_start(dev);
	if (!err)
		netif_tx_start_all_queues(dev);
	return err;
}

static int cxgb_close(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	netif_tx_stop_all_queues(dev);
	netif_carrier_off(dev);
	return t4_enable_vi(adapter, 0, pi->viid, false, false);
static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev)
{
	struct port_stats stats;
	struct port_info *p = netdev_priv(dev);
	struct adapter *adapter = p->adapter;
	struct rtnl_link_stats64 *ns = &dev->stats64;

	spin_lock(&adapter->stats_lock);
	t4_get_port_stats(adapter, p->tx_chan, &stats);
	spin_unlock(&adapter->stats_lock);

	ns->tx_bytes   = stats.tx_octets;
	ns->tx_packets = stats.tx_frames;
	ns->rx_bytes   = stats.rx_octets;
	ns->rx_packets = stats.rx_frames;
	ns->multicast  = stats.rx_mcast_frames;

	/* detailed rx_errors */
	ns->rx_length_errors = stats.rx_jabber + stats.rx_too_long +
			       stats.rx_runt;
	ns->rx_over_errors   = 0;
	ns->rx_crc_errors    = stats.rx_fcs_err;
	ns->rx_frame_errors  = stats.rx_symbol_err;
	ns->rx_fifo_errors   = stats.rx_ovflow0 + stats.rx_ovflow1 +
			       stats.rx_ovflow2 + stats.rx_ovflow3 +
			       stats.rx_trunc0 + stats.rx_trunc1 +
			       stats.rx_trunc2 + stats.rx_trunc3;
	ns->rx_missed_errors = 0;

	/* detailed tx_errors */
	ns->tx_aborted_errors   = 0;
	ns->tx_carrier_errors   = 0;
	ns->tx_fifo_errors      = 0;
	ns->tx_heartbeat_errors = 0;
	ns->tx_window_errors    = 0;

	ns->tx_errors = stats.tx_error_frames;
	ns->rx_errors = stats.rx_symbol_err + stats.rx_fcs_err +
		ns->rx_length_errors + stats.rx_len_err + ns->rx_fifo_errors;
	return ns;
}

static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
{
	int ret = 0, prtad, devad;
	struct port_info *pi = netdev_priv(dev);
	struct mii_ioctl_data *data = (struct mii_ioctl_data *)&req->ifr_data;

	switch (cmd) {
	case SIOCGMIIPHY:
		if (pi->mdio_addr < 0)
			return -EOPNOTSUPP;
		data->phy_id = pi->mdio_addr;
		break;
	case SIOCGMIIREG:
	case SIOCSMIIREG:
		if (mdio_phy_id_is_c45(data->phy_id)) {
			prtad = mdio_phy_id_prtad(data->phy_id);
			devad = mdio_phy_id_devad(data->phy_id);
		} else if (data->phy_id < 32) {
			prtad = data->phy_id;
			devad = 0;
			data->reg_num &= 0x1f;
		} else
			return -EINVAL;

		if (cmd == SIOCGMIIREG)
			ret = t4_mdio_rd(pi->adapter, 0, prtad, devad,
					 data->reg_num, &data->val_out);
		else
			ret = t4_mdio_wr(pi->adapter, 0, prtad, devad,
					 data->reg_num, data->val_in);
		break;
	default:
		return -EOPNOTSUPP;
	}
	return ret;
}

static void cxgb_set_rxmode(struct net_device *dev)
{
	/* unfortunately we can't return errors to the stack */
	set_rxmode(dev, -1, false);
}

static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);

	if (new_mtu < 81 || new_mtu > MAX_MTU)         /* accommodate SACK */
		return -EINVAL;
	ret = t4_set_rxmode(pi->adapter, 0, pi->viid, new_mtu, -1, -1, -1, -1,
			    true);
	if (!ret)
		dev->mtu = new_mtu;
	return ret;
}

static int cxgb_set_mac_addr(struct net_device *dev, void *p)
{
	int ret;
	struct sockaddr *addr = p;
	struct port_info *pi = netdev_priv(dev);

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

	ret = t4_change_mac(pi->adapter, 0, pi->viid, pi->xact_addr_filt,
			    addr->sa_data, true, true);
	if (ret < 0)
		return ret;

	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
	pi->xact_addr_filt = ret;
	return 0;
}

static void vlan_rx_register(struct net_device *dev, struct vlan_group *grp)
{
	struct port_info *pi = netdev_priv(dev);

	pi->vlan_grp = grp;
	t4_set_rxmode(pi->adapter, 0, pi->viid, -1, -1, -1, -1, grp != NULL,
		      true);
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void cxgb_netpoll(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adap = pi->adapter;

	if (adap->flags & USING_MSIX) {
		int i;
		struct sge_eth_rxq *rx = &adap->sge.ethrxq[pi->first_qset];

		for (i = pi->nqsets; i; i--, rx++)
			t4_sge_intr_msix(0, &rx->rspq);
	} else
		t4_intr_handler(adap)(0, adap);
}
#endif

static const struct net_device_ops cxgb4_netdev_ops = {
	.ndo_open             = cxgb_open,
	.ndo_stop             = cxgb_close,
	.ndo_start_xmit       = t4_eth_xmit,
	.ndo_get_stats64      = cxgb_get_stats,
	.ndo_set_rx_mode      = cxgb_set_rxmode,
	.ndo_set_mac_address  = cxgb_set_mac_addr,
	.ndo_validate_addr    = eth_validate_addr,
	.ndo_do_ioctl         = cxgb_ioctl,
	.ndo_change_mtu       = cxgb_change_mtu,
	.ndo_vlan_rx_register = vlan_rx_register,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller  = cxgb_netpoll,
#endif
};

void t4_fatal_err(struct adapter *adap)
{
	t4_set_reg_field(adap, SGE_CONTROL, GLOBALENABLE, 0);
	t4_intr_disable(adap);
	dev_alert(adap->pdev_dev, "encountered fatal error, adapter stopped\n");
}

static void setup_memwin(struct adapter *adap)
{
	u32 bar0;

	bar0 = pci_resource_start(adap->pdev, 0);  /* truncation intentional */
	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN, 0),
		     (bar0 + MEMWIN0_BASE) | BIR(0) |
		     WINDOW(ilog2(MEMWIN0_APERTURE) - 10));
	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN, 1),
		     (bar0 + MEMWIN1_BASE) | BIR(0) |
		     WINDOW(ilog2(MEMWIN1_APERTURE) - 10));
	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN, 2),
		     (bar0 + MEMWIN2_BASE) | BIR(0) |
		     WINDOW(ilog2(MEMWIN2_APERTURE) - 10));
}

static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
{
	u32 v;
	int ret;

	/* get device capabilities */
	memset(c, 0, sizeof(*c));
	c->op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
			       FW_CMD_REQUEST | FW_CMD_READ);
	c->retval_len16 = htonl(FW_LEN16(*c));
	ret = t4_wr_mbox(adap, 0, c, sizeof(*c), c);
	if (ret < 0)
		return ret;

	/* select capabilities we'll be using */
	if (c->niccaps & htons(FW_CAPS_CONFIG_NIC_VM)) {
		if (!vf_acls)
			c->niccaps ^= htons(FW_CAPS_CONFIG_NIC_VM);
		else
			c->niccaps = htons(FW_CAPS_CONFIG_NIC_VM);
	} else if (vf_acls) {
		dev_err(adap->pdev_dev, "virtualization ACLs not supported");
		return ret;
	}
	c->op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) |
			       FW_CMD_REQUEST | FW_CMD_WRITE);
	ret = t4_wr_mbox(adap, 0, c, sizeof(*c), NULL);
	if (ret < 0)
		return ret;

	ret = t4_config_glbl_rss(adap, 0,
				 FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL,
				 FW_RSS_GLB_CONFIG_CMD_TNLMAPEN |
				 FW_RSS_GLB_CONFIG_CMD_TNLALLLKP);
	if (ret < 0)
		return ret;

	ret = t4_cfg_pfvf(adap, 0, 0, 0, 64, 64, 64, 0, 0, 4, 0xf, 0xf, 16,
			  FW_CMD_CAP_PF, FW_CMD_CAP_PF);
	if (ret < 0)
		return ret;

	t4_sge_init(adap);

	/* get basic stuff going */
	ret = t4_early_init(adap, 0);
	if (ret < 0)
		return ret;

	/* tweak some settings */
	t4_write_reg(adap, TP_SHIFT_CNT, 0x64f8849);
	t4_write_reg(adap, ULP_RX_TDDP_PSZ, HPZ0(PAGE_SHIFT - 12));
	t4_write_reg(adap, TP_PIO_ADDR, TP_INGRESS_CONFIG);
	v = t4_read_reg(adap, TP_PIO_DATA);
	t4_write_reg(adap, TP_PIO_DATA, v & ~CSUM_HAS_PSEUDO_HDR);
	setup_memwin(adap);
	return 0;
}

/*
 * Max # of ATIDs.  The absolute HW max is 16K but we keep it lower.
 */
#define MAX_ATIDS 8192U

/*
 * Phase 0 of initialization: contact FW, obtain config, perform basic init.
 */
static int adap_init0(struct adapter *adap)
{
	int ret;
	u32 v, port_vec;
	enum dev_state state;
	u32 params[7], val[7];
	struct fw_caps_config_cmd c;

	ret = t4_check_fw_version(adap);
	if (ret == -EINVAL || ret > 0) {
		if (upgrade_fw(adap) >= 0)             /* recache FW version */
			ret = t4_check_fw_version(adap);
	}
	if (ret < 0)
		return ret;

	/* contact FW, request master */
	ret = t4_fw_hello(adap, 0, 0, MASTER_MUST, &state);
	if (ret < 0) {
		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
			ret);
		return ret;
	}

	/* reset device */
	ret = t4_fw_reset(adap, 0, PIORSTMODE | PIORST);
	if (ret < 0)
		goto bye;

	for (v = 0; v < SGE_NTIMERS - 1; v++)
		adap->sge.timer_val[v] = min(intr_holdoff[v], MAX_SGE_TIMERVAL);
	adap->sge.timer_val[SGE_NTIMERS - 1] = MAX_SGE_TIMERVAL;
	adap->sge.counter_val[0] = 1;
	for (v = 1; v < SGE_NCOUNTERS; v++)
		adap->sge.counter_val[v] = min(intr_cnt[v - 1],
					       THRESHOLD_3_MASK);
	if (ret < 0)
		goto bye;

#define FW_PARAM_DEV(param) \
	(FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | \
	 FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_##param))

#define FW_PARAM_PFVF(param) \
	(FW_PARAMS_MNEM(FW_PARAMS_MNEM_PFVF) | \
	 FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_PFVF_##param))

	params[0] = FW_PARAM_DEV(PORTVEC);
	params[1] = FW_PARAM_PFVF(L2T_START);
	params[2] = FW_PARAM_PFVF(L2T_END);
	params[3] = FW_PARAM_PFVF(FILTER_START);
	params[4] = FW_PARAM_PFVF(FILTER_END);
	ret = t4_query_params(adap, 0, 0, 0, 5, params, val);
	if (ret < 0)
		goto bye;
	port_vec = val[0];
	adap->tids.ftid_base = val[3];
	adap->tids.nftids = val[4] - val[3] + 1;

	if (c.ofldcaps) {
		/* query offload-related parameters */
		params[0] = FW_PARAM_DEV(NTID);
		params[1] = FW_PARAM_PFVF(SERVER_START);
		params[2] = FW_PARAM_PFVF(SERVER_END);
		params[3] = FW_PARAM_PFVF(TDDP_START);
		params[4] = FW_PARAM_PFVF(TDDP_END);
		params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ);
		ret = t4_query_params(adap, 0, 0, 0, 6, params, val);
		if (ret < 0)
			goto bye;
		adap->tids.ntids = val[0];
		adap->tids.natids = min(adap->tids.ntids / 2, MAX_ATIDS);
		adap->tids.stid_base = val[1];
		adap->tids.nstids = val[2] - val[1] + 1;
		adap->vres.ddp.start = val[3];
		adap->vres.ddp.size = val[4] - val[3] + 1;
		adap->params.ofldq_wr_cred = val[5];
		adap->params.offload = 1;
	}
	if (c.rdmacaps) {
		params[0] = FW_PARAM_PFVF(STAG_START);
		params[1] = FW_PARAM_PFVF(STAG_END);
		params[2] = FW_PARAM_PFVF(RQ_START);
		params[3] = FW_PARAM_PFVF(RQ_END);
		params[4] = FW_PARAM_PFVF(PBL_START);
		params[5] = FW_PARAM_PFVF(PBL_END);
		ret = t4_query_params(adap, 0, 0, 0, 6, params, val);
		if (ret < 0)
			goto bye;
		adap->vres.stag.start = val[0];
		adap->vres.stag.size = val[1] - val[0] + 1;
		adap->vres.rq.start = val[2];
		adap->vres.rq.size = val[3] - val[2] + 1;
		adap->vres.pbl.start = val[4];
		adap->vres.pbl.size = val[5] - val[4] + 1;
	}
	if (c.iscsicaps) {
		params[0] = FW_PARAM_PFVF(ISCSI_START);
		params[1] = FW_PARAM_PFVF(ISCSI_END);
		ret = t4_query_params(adap, 0, 0, 0, 2, params, val);
		if (ret < 0)
			goto bye;
		adap->vres.iscsi.start = val[0];
		adap->vres.iscsi.size = val[1] - val[0] + 1;
	}
#undef FW_PARAM_PFVF
#undef FW_PARAM_DEV

	adap->params.nports = hweight32(port_vec);
	adap->params.portvec = port_vec;
	adap->flags |= FW_OK;

	/* These are finalized by FW initialization, load their values now */
	v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
	adap->params.tp.tre = TIMERRESOLUTION_GET(v);
	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
		     adap->params.b_wnd);
	return 0;

	/*
	 * If a command timed out or failed with EIO FW does not operate within
	 * its spec or something catastrophic happened to HW/FW, stop issuing
	 * commands.
	 */
bye:	if (ret != -ETIMEDOUT && ret != -EIO)
		t4_fw_bye(adap, 0);
	return ret;
}

/* EEH callbacks */

static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
					 pci_channel_state_t state)
{
	int i;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap)
		goto out;

	rtnl_lock();
	adap->flags &= ~FW_OK;
	notify_ulds(adap, CXGB4_STATE_START_RECOVERY);
	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];

		netif_device_detach(dev);
		netif_carrier_off(dev);
	}
	if (adap->flags & FULL_INIT_DONE)
		cxgb_down(adap);
	rtnl_unlock();
	pci_disable_device(pdev);
out:	return state == pci_channel_io_perm_failure ?
		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
}

static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
{
	int i, ret;
	struct fw_caps_config_cmd c;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap) {
		pci_restore_state(pdev);
		pci_save_state(pdev);
		return PCI_ERS_RESULT_RECOVERED;
	}

	if (pci_enable_device(pdev)) {
		dev_err(&pdev->dev, "cannot reenable PCI device after reset\n");
		return PCI_ERS_RESULT_DISCONNECT;
	}

	pci_set_master(pdev);
	pci_restore_state(pdev);
	pci_save_state(pdev);
	pci_cleanup_aer_uncorrect_error_status(pdev);

	if (t4_wait_dev_ready(adap) < 0)
		return PCI_ERS_RESULT_DISCONNECT;
	if (t4_fw_hello(adap, 0, 0, MASTER_MUST, NULL))
		return PCI_ERS_RESULT_DISCONNECT;
	adap->flags |= FW_OK;
	if (adap_init1(adap, &c))
		return PCI_ERS_RESULT_DISCONNECT;

	for_each_port(adap, i) {
		struct port_info *p = adap2pinfo(adap, i);

		ret = t4_alloc_vi(adap, 0, p->tx_chan, 0, 0, 1, NULL, NULL);
		if (ret < 0)
			return PCI_ERS_RESULT_DISCONNECT;
		p->viid = ret;
		p->xact_addr_filt = -1;
	}

	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
		     adap->params.b_wnd);
	if (cxgb_up(adap))
		return PCI_ERS_RESULT_DISCONNECT;
	return PCI_ERS_RESULT_RECOVERED;
}

static void eeh_resume(struct pci_dev *pdev)
{
	int i;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap)
		return;

	rtnl_lock();
	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];

		if (netif_running(dev)) {
			link_start(dev);