1/*
2 * This file is part of the Chelsio T4 Ethernet driver for Linux.
3 *
4 * Copyright (c) 2003-2016 Chelsio Communications, Inc. All rights reserved.
5 *
6 * This software is available to you under a choice of one of two
7 * licenses.  You may choose to be licensed under the terms of the GNU
8 * General Public License (GPL) Version 2, available from the file
9 * COPYING in the main directory of this source tree, or the
10 * OpenIB.org BSD license below:
11 *
12 *     Redistribution and use in source and binary forms, with or
13 *     without modification, are permitted provided that the following
14 *     conditions are met:
15 *
16 *      - Redistributions of source code must retain the above
17 *        copyright notice, this list of conditions and the following
18 *        disclaimer.
19 *
20 *      - Redistributions in binary form must reproduce the above
21 *        copyright notice, this list of conditions and the following
22 *        disclaimer in the documentation and/or other materials
23 *        provided with the distribution.
24 *
25 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
26 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
27 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
28 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
29 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
30 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
31 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
32 * SOFTWARE.
33 */
34
35#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
36
37#include <linux/bitmap.h>
38#include <linux/crc32.h>
39#include <linux/ctype.h>
40#include <linux/debugfs.h>
41#include <linux/err.h>
42#include <linux/etherdevice.h>
43#include <linux/firmware.h>
44#include <linux/if.h>
45#include <linux/if_vlan.h>
46#include <linux/init.h>
47#include <linux/log2.h>
48#include <linux/mdio.h>
49#include <linux/module.h>
50#include <linux/moduleparam.h>
51#include <linux/mutex.h>
52#include <linux/netdevice.h>
53#include <linux/pci.h>
54#include <linux/aer.h>
55#include <linux/rtnetlink.h>
56#include <linux/sched.h>
57#include <linux/seq_file.h>
58#include <linux/sockios.h>
59#include <linux/vmalloc.h>
60#include <linux/workqueue.h>
61#include <net/neighbour.h>
62#include <net/netevent.h>
63#include <net/addrconf.h>
64#include <net/bonding.h>
65#include <linux/uaccess.h>
66#include <linux/crash_dump.h>
67#include <net/udp_tunnel.h>
68#include <net/xfrm.h>
69#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
70#include <net/tls.h>
71#endif
72
73#include "cxgb4.h"
74#include "cxgb4_filter.h"
75#include "t4_regs.h"
76#include "t4_values.h"
77#include "t4_msg.h"
78#include "t4fw_api.h"
79#include "t4fw_version.h"
80#include "cxgb4_dcb.h"
81#include "srq.h"
82#include "cxgb4_debugfs.h"
83#include "clip_tbl.h"
84#include "l2t.h"
85#include "smt.h"
86#include "sched.h"
87#include "cxgb4_tc_u32.h"
88#include "cxgb4_tc_flower.h"
89#include "cxgb4_tc_mqprio.h"
90#include "cxgb4_tc_matchall.h"
91#include "cxgb4_ptp.h"
92#include "cxgb4_cudbg.h"
93
94char cxgb4_driver_name[] = KBUILD_MODNAME;
95
96#define DRV_DESC "Chelsio T4/T5/T6 Network Driver"
97
98#define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
99			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
100			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
101
102/* Macros needed to support the PCI Device ID Table ...
103 */
104#define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \
105	static const struct pci_device_id cxgb4_pci_tbl[] = {
106#define CXGB4_UNIFIED_PF 0x4
107
108#define CH_PCI_DEVICE_ID_FUNCTION CXGB4_UNIFIED_PF
109
110/* Include PCI Device IDs for both PF4 and PF0-3 so our PCI probe() routine is
111 * called for both.
112 */
113#define CH_PCI_DEVICE_ID_FUNCTION2 0x0
114
115#define CH_PCI_ID_TABLE_ENTRY(devid) \
116		{PCI_VDEVICE(CHELSIO, (devid)), CXGB4_UNIFIED_PF}
117
118#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END \
119		{ 0, } \
120	}
121
122#include "t4_pci_id_tbl.h"
123
124#define FW4_FNAME "cxgb4/t4fw.bin"
125#define FW5_FNAME "cxgb4/t5fw.bin"
126#define FW6_FNAME "cxgb4/t6fw.bin"
127#define FW4_CFNAME "cxgb4/t4-config.txt"
128#define FW5_CFNAME "cxgb4/t5-config.txt"
129#define FW6_CFNAME "cxgb4/t6-config.txt"
130#define PHY_AQ1202_FIRMWARE "cxgb4/aq1202_fw.cld"
131#define PHY_BCM84834_FIRMWARE "cxgb4/bcm8483.bin"
132#define PHY_AQ1202_DEVICEID 0x4409
133#define PHY_BCM84834_DEVICEID 0x4486
134
135MODULE_DESCRIPTION(DRV_DESC);
136MODULE_AUTHOR("Chelsio Communications");
137MODULE_LICENSE("Dual BSD/GPL");
138MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl);
139MODULE_FIRMWARE(FW4_FNAME);
140MODULE_FIRMWARE(FW5_FNAME);
141MODULE_FIRMWARE(FW6_FNAME);
142
143/*
144 * The driver uses the best interrupt scheme available on a platform in the
145 * order MSI-X, MSI, legacy INTx interrupts.  This parameter determines which
146 * of these schemes the driver may consider as follows:
147 *
148 * msi = 2: choose from among all three options
149 * msi = 1: only consider MSI and INTx interrupts
150 * msi = 0: force INTx interrupts
151 */
152static int msi = 2;
153
154module_param(msi, int, 0644);
155MODULE_PARM_DESC(msi, "whether to use INTx (0), MSI (1) or MSI-X (2)");
156
157/*
158 * Normally we tell the chip to deliver Ingress Packets into our DMA buffers
159 * offset by 2 bytes in order to have the IP headers line up on 4-byte
160 * boundaries.  This is a requirement for many architectures which will throw
161 * a machine check fault if an attempt is made to access one of the 4-byte IP
162 * header fields on a non-4-byte boundary.  And it's a major performance issue
163 * even on some architectures which allow it like some implementations of the
164 * x86 ISA.  However, some architectures don't mind this and for some very
165 * edge-case performance sensitive applications (like forwarding large volumes
166 * of small packets), setting this DMA offset to 0 will decrease the number of
167 * PCI-E Bus transfers enough to measurably affect performance.
168 */
169static int rx_dma_offset = 2;
170
171/* TX Queue select used to determine what algorithm to use for selecting TX
172 * queue. Select between the kernel provided function (select_queue=0) or user
173 * cxgb_select_queue function (select_queue=1)
174 *
175 * Default: select_queue=0
176 */
177static int select_queue;
178module_param(select_queue, int, 0644);
179MODULE_PARM_DESC(select_queue,
180		 "Select between kernel provided method of selecting or driver method of selecting TX queue. Default is kernel method.");
181
182static struct dentry *cxgb4_debugfs_root;
183
184LIST_HEAD(adapter_list);
185DEFINE_MUTEX(uld_mutex);
186LIST_HEAD(uld_list);
187
188static int cfg_queues(struct adapter *adap);
189
190static void link_report(struct net_device *dev)
191{
192	if (!netif_carrier_ok(dev))
193		netdev_info(dev, "link down\n");
194	else {
195		static const char *fc[] = { "no", "Rx", "Tx", "Tx/Rx" };
196
197		const char *s;
198		const struct port_info *p = netdev_priv(dev);
199
200		switch (p->link_cfg.speed) {
201		case 100:
202			s = "100Mbps";
203			break;
204		case 1000:
205			s = "1Gbps";
206			break;
207		case 10000:
208			s = "10Gbps";
209			break;
210		case 25000:
211			s = "25Gbps";
212			break;
213		case 40000:
214			s = "40Gbps";
215			break;
216		case 50000:
217			s = "50Gbps";
218			break;
219		case 100000:
220			s = "100Gbps";
221			break;
222		default:
223			pr_info("%s: unsupported speed: %d\n",
224				dev->name, p->link_cfg.speed);
225			return;
226		}
227
228		netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s,
229			    fc[p->link_cfg.fc]);
230	}
231}
232
233#ifdef CONFIG_CHELSIO_T4_DCB
234/* Set up/tear down Data Center Bridging Priority mapping for a net device. */
235static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
236{
237	struct port_info *pi = netdev_priv(dev);
238	struct adapter *adap = pi->adapter;
239	struct sge_eth_txq *txq = &adap->sge.ethtxq[pi->first_qset];
240	int i;
241
242	/* We use a simple mapping of Port TX Queue Index to DCB
243	 * Priority when we're enabling DCB.
244	 */
245	for (i = 0; i < pi->nqsets; i++, txq++) {
246		u32 name, value;
247		int err;
248
249		name = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
250			FW_PARAMS_PARAM_X_V(
251				FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH) |
252			FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id));
253		value = enable ? i : 0xffffffff;
254
255		/* Since we can be called while atomic (from "interrupt
256		 * level") we need to issue the Set Parameters Commannd
257		 * without sleeping (timeout < 0).
258		 */
259		err = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1,
260					    &name, &value,
261					    -FW_CMD_MAX_TIMEOUT);
262
263		if (err)
264			dev_err(adap->pdev_dev,
265				"Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n",
266				enable ? "set" : "unset", pi->port_id, i, -err);
267		else
268			txq->dcb_prio = enable ? value : 0;
269	}
270}
271
272int cxgb4_dcb_enabled(const struct net_device *dev)
273{
274	struct port_info *pi = netdev_priv(dev);
275
276	if (!pi->dcb.enabled)
277		return 0;
278
279	return ((pi->dcb.state == CXGB4_DCB_STATE_FW_ALLSYNCED) ||
280		(pi->dcb.state == CXGB4_DCB_STATE_HOST));
281}
282#endif /* CONFIG_CHELSIO_T4_DCB */
283
284void t4_os_link_changed(struct adapter *adapter, int port_id, int link_stat)
285{
286	struct net_device *dev = adapter->port[port_id];
287
288	/* Skip changes from disabled ports. */
289	if (netif_running(dev) && link_stat != netif_carrier_ok(dev)) {
290		if (link_stat)
291			netif_carrier_on(dev);
292		else {
293#ifdef CONFIG_CHELSIO_T4_DCB
294			if (cxgb4_dcb_enabled(dev)) {
295				cxgb4_dcb_reset(dev);
296				dcb_tx_queue_prio_enable(dev, false);
297			}
298#endif /* CONFIG_CHELSIO_T4_DCB */
299			netif_carrier_off(dev);
300		}
301
302		link_report(dev);
303	}
304}
305
306void t4_os_portmod_changed(struct adapter *adap, int port_id)
307{
308	static const char *mod_str[] = {
309		NULL, "LR", "SR", "ER", "passive DA", "active DA", "LRM"
310	};
311
312	struct net_device *dev = adap->port[port_id];
313	struct port_info *pi = netdev_priv(dev);
314
315	if (pi->mod_type == FW_PORT_MOD_TYPE_NONE)
316		netdev_info(dev, "port module unplugged\n");
317	else if (pi->mod_type < ARRAY_SIZE(mod_str))
318		netdev_info(dev, "%s module inserted\n", mod_str[pi->mod_type]);
319	else if (pi->mod_type == FW_PORT_MOD_TYPE_NOTSUPPORTED)
320		netdev_info(dev, "%s: unsupported port module inserted\n",
321			    dev->name);
322	else if (pi->mod_type == FW_PORT_MOD_TYPE_UNKNOWN)
323		netdev_info(dev, "%s: unknown port module inserted\n",
324			    dev->name);
325	else if (pi->mod_type == FW_PORT_MOD_TYPE_ERROR)
326		netdev_info(dev, "%s: transceiver module error\n", dev->name);
327	else
328		netdev_info(dev, "%s: unknown module type %d inserted\n",
329			    dev->name, pi->mod_type);
330
331	/* If the interface is running, then we'll need any "sticky" Link
332	 * Parameters redone with a new Transceiver Module.
333	 */
334	pi->link_cfg.redo_l1cfg = netif_running(dev);
335}
336
337int dbfifo_int_thresh = 10; /* 10 == 640 entry threshold */
338module_param(dbfifo_int_thresh, int, 0644);
339MODULE_PARM_DESC(dbfifo_int_thresh, "doorbell fifo interrupt threshold");
340
341/*
342 * usecs to sleep while draining the dbfifo
343 */
344static int dbfifo_drain_delay = 1000;
345module_param(dbfifo_drain_delay, int, 0644);
346MODULE_PARM_DESC(dbfifo_drain_delay,
347		 "usecs to sleep while draining the dbfifo");
348
349static inline int cxgb4_set_addr_hash(struct port_info *pi)
350{
351	struct adapter *adap = pi->adapter;
352	u64 vec = 0;
353	bool ucast = false;
354	struct hash_mac_addr *entry;
355
356	/* Calculate the hash vector for the updated list and program it */
357	list_for_each_entry(entry, &adap->mac_hlist, list) {
358		ucast |= is_unicast_ether_addr(entry->addr);
359		vec |= (1ULL << hash_mac_addr(entry->addr));
360	}
361	return t4_set_addr_hash(adap, adap->mbox, pi->viid, ucast,
362				vec, false);
363}
364
365static int cxgb4_mac_sync(struct net_device *netdev, const u8 *mac_addr)
366{
367	struct port_info *pi = netdev_priv(netdev);
368	struct adapter *adap = pi->adapter;
369	int ret;
370	u64 mhash = 0;
371	u64 uhash = 0;
372	/* idx stores the index of allocated filters,
373	 * its size should be modified based on the number of
374	 * MAC addresses that we allocate filters for
375	 */
376
377	u16 idx[1] = {};
378	bool free = false;
379	bool ucast = is_unicast_ether_addr(mac_addr);
380	const u8 *maclist[1] = {mac_addr};
381	struct hash_mac_addr *new_entry;
382
383	ret = cxgb4_alloc_mac_filt(adap, pi->viid, free, 1, maclist,
384				   idx, ucast ? &uhash : &mhash, false);
385	if (ret < 0)
386		goto out;
387	/* if hash != 0, then add the addr to hash addr list
388	 * so on the end we will calculate the hash for the
389	 * list and program it
390	 */
391	if (uhash || mhash) {
392		new_entry = kzalloc(sizeof(*new_entry), GFP_ATOMIC);
393		if (!new_entry)
394			return -ENOMEM;
395		ether_addr_copy(new_entry->addr, mac_addr);
396		list_add_tail(&new_entry->list, &adap->mac_hlist);
397		ret = cxgb4_set_addr_hash(pi);
398	}
399out:
400	return ret < 0 ? ret : 0;
401}
402
403static int cxgb4_mac_unsync(struct net_device *netdev, const u8 *mac_addr)
404{
405	struct port_info *pi = netdev_priv(netdev);
406	struct adapter *adap = pi->adapter;
407	int ret;
408	const u8 *maclist[1] = {mac_addr};
409	struct hash_mac_addr *entry, *tmp;
410
411	/* If the MAC address to be removed is in the hash addr
412	 * list, delete it from the list and update hash vector
413	 */
414	list_for_each_entry_safe(entry, tmp, &adap->mac_hlist, list) {
415		if (ether_addr_equal(entry->addr, mac_addr)) {
416			list_del(&entry->list);
417			kfree(entry);
418			return cxgb4_set_addr_hash(pi);
419		}
420	}
421
422	ret = cxgb4_free_mac_filt(adap, pi->viid, 1, maclist, false);
423	return ret < 0 ? -EINVAL : 0;
424}
425
426/*
427 * Set Rx properties of a port, such as promiscruity, address filters, and MTU.
428 * If @mtu is -1 it is left unchanged.
429 */
430static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
431{
432	struct port_info *pi = netdev_priv(dev);
433	struct adapter *adapter = pi->adapter;
434
435	__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
436	__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
437
438	return t4_set_rxmode(adapter, adapter->mbox, pi->viid, pi->viid_mirror,
439			     mtu, (dev->flags & IFF_PROMISC) ? 1 : 0,
440			     (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1,
441			     sleep_ok);
442}
443
444/**
445 *	cxgb4_change_mac - Update match filter for a MAC address.
446 *	@pi: the port_info
447 *	@viid: the VI id
448 *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
449 *		   or -1
450 *	@addr: the new MAC address value
451 *	@persist: whether a new MAC allocation should be persistent
452 *	@smt_idx: the destination to store the new SMT index.
453 *
454 *	Modifies an MPS filter and sets it to the new MAC address if
455 *	@tcam_idx >= 0, or adds the MAC address to a new filter if
456 *	@tcam_idx < 0. In the latter case the address is added persistently
457 *	if @persist is %true.
458 *	Addresses are programmed to hash region, if tcam runs out of entries.
459 *
460 */
461int cxgb4_change_mac(struct port_info *pi, unsigned int viid,
462		     int *tcam_idx, const u8 *addr, bool persist,
463		     u8 *smt_idx)
464{
465	struct adapter *adapter = pi->adapter;
466	struct hash_mac_addr *entry, *new_entry;
467	int ret;
468
469	ret = t4_change_mac(adapter, adapter->mbox, viid,
470			    *tcam_idx, addr, persist, smt_idx);
471	/* We ran out of TCAM entries. try programming hash region. */
472	if (ret == -ENOMEM) {
473		/* If the MAC address to be updated is in the hash addr
474		 * list, update it from the list
475		 */
476		list_for_each_entry(entry, &adapter->mac_hlist, list) {
477			if (entry->iface_mac) {
478				ether_addr_copy(entry->addr, addr);
479				goto set_hash;
480			}
481		}
482		new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL);
483		if (!new_entry)
484			return -ENOMEM;
485		ether_addr_copy(new_entry->addr, addr);
486		new_entry->iface_mac = true;
487		list_add_tail(&new_entry->list, &adapter->mac_hlist);
488set_hash:
489		ret = cxgb4_set_addr_hash(pi);
490	} else if (ret >= 0) {
491		*tcam_idx = ret;
492		ret = 0;
493	}
494
495	return ret;
496}
497
498/*
499 *	link_start - enable a port
500 *	@dev: the port to enable
501 *
502 *	Performs the MAC and PHY actions needed to enable a port.
503 */
504static int link_start(struct net_device *dev)
505{
506	struct port_info *pi = netdev_priv(dev);
507	unsigned int mb = pi->adapter->mbox;
508	int ret;
509
510	/*
511	 * We do not set address filters and promiscuity here, the stack does
512	 * that step explicitly.
513	 */
514	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, pi->viid_mirror,
515			    dev->mtu, -1, -1, -1,
516			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
517	if (ret == 0)
518		ret = cxgb4_update_mac_filt(pi, pi->viid, &pi->xact_addr_filt,
519					    dev->dev_addr, true, &pi->smt_idx);
520	if (ret == 0)
521		ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan,
522				    &pi->link_cfg);
523	if (ret == 0) {
524		local_bh_disable();
525		ret = t4_enable_pi_params(pi->adapter, mb, pi, true,
526					  true, CXGB4_DCB_ENABLED);
527		local_bh_enable();
528	}
529
530	return ret;
531}
532
533#ifdef CONFIG_CHELSIO_T4_DCB
534/* Handle a Data Center Bridging update message from the firmware. */
535static void dcb_rpl(struct adapter *adap, const struct fw_port_cmd *pcmd)
536{
537	int port = FW_PORT_CMD_PORTID_G(ntohl(pcmd->op_to_portid));
538	struct net_device *dev = adap->port[adap->chan_map[port]];
539	int old_dcb_enabled = cxgb4_dcb_enabled(dev);
540	int new_dcb_enabled;
541
542	cxgb4_dcb_handle_fw_update(adap, pcmd);
543	new_dcb_enabled = cxgb4_dcb_enabled(dev);
544
545	/* If the DCB has become enabled or disabled on the port then we're
546	 * going to need to set up/tear down DCB Priority parameters for the
547	 * TX Queues associated with the port.
548	 */
549	if (new_dcb_enabled != old_dcb_enabled)
550		dcb_tx_queue_prio_enable(dev, new_dcb_enabled);
551}
552#endif /* CONFIG_CHELSIO_T4_DCB */
553
554/* Response queue handler for the FW event queue.
555 */
556static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
557			  const struct pkt_gl *gl)
558{
559	u8 opcode = ((const struct rss_header *)rsp)->opcode;
560
561	rsp++;                                          /* skip RSS header */
562
563	/* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG.
564	 */
565	if (unlikely(opcode == CPL_FW4_MSG &&
566	   ((const struct cpl_fw4_msg *)rsp)->type == FW_TYPE_RSSCPL)) {
567		rsp++;
568		opcode = ((const struct rss_header *)rsp)->opcode;
569		rsp++;
570		if (opcode != CPL_SGE_EGR_UPDATE) {
571			dev_err(q->adap->pdev_dev, "unexpected FW4/CPL %#x on FW event queue\n"
572				, opcode);
573			goto out;
574		}
575	}
576
577	if (likely(opcode == CPL_SGE_EGR_UPDATE)) {
578		const struct cpl_sge_egr_update *p = (void *)rsp;
579		unsigned int qid = EGR_QID_G(ntohl(p->opcode_qid));
580		struct sge_txq *txq;
581
582		txq = q->adap->sge.egr_map[qid - q->adap->sge.egr_start];
583		txq->restarts++;
584		if (txq->q_type == CXGB4_TXQ_ETH) {
585			struct sge_eth_txq *eq;
586
587			eq = container_of(txq, struct sge_eth_txq, q);
588			t4_sge_eth_txq_egress_update(q->adap, eq, -1);
589		} else {
590			struct sge_uld_txq *oq;
591
592			oq = container_of(txq, struct sge_uld_txq, q);
593			tasklet_schedule(&oq->qresume_tsk);
594		}
595	} else if (opcode == CPL_FW6_MSG || opcode == CPL_FW4_MSG) {
596		const struct cpl_fw6_msg *p = (void *)rsp;
597
598#ifdef CONFIG_CHELSIO_T4_DCB
599		const struct fw_port_cmd *pcmd = (const void *)p->data;
600		unsigned int cmd = FW_CMD_OP_G(ntohl(pcmd->op_to_portid));
601		unsigned int action =
602			FW_PORT_CMD_ACTION_G(ntohl(pcmd->action_to_len16));
603
604		if (cmd == FW_PORT_CMD &&
605		    (action == FW_PORT_ACTION_GET_PORT_INFO ||
606		     action == FW_PORT_ACTION_GET_PORT_INFO32)) {
607			int port = FW_PORT_CMD_PORTID_G(
608					be32_to_cpu(pcmd->op_to_portid));
609			struct net_device *dev;
610			int dcbxdis, state_input;
611
612			dev = q->adap->port[q->adap->chan_map[port]];
613			dcbxdis = (action == FW_PORT_ACTION_GET_PORT_INFO
614			  ? !!(pcmd->u.info.dcbxdis_pkd & FW_PORT_CMD_DCBXDIS_F)
615			  : !!(be32_to_cpu(pcmd->u.info32.lstatus32_to_cbllen32)
616			       & FW_PORT_CMD_DCBXDIS32_F));
617			state_input = (dcbxdis
618				       ? CXGB4_DCB_INPUT_FW_DISABLED
619				       : CXGB4_DCB_INPUT_FW_ENABLED);
620
621			cxgb4_dcb_state_fsm(dev, state_input);
622		}
623
624		if (cmd == FW_PORT_CMD &&
625		    action == FW_PORT_ACTION_L2_DCB_CFG)
626			dcb_rpl(q->adap, pcmd);
627		else
628#endif
629			if (p->type == 0)
630				t4_handle_fw_rpl(q->adap, p->data);
631	} else if (opcode == CPL_L2T_WRITE_RPL) {
632		const struct cpl_l2t_write_rpl *p = (void *)rsp;
633
634		do_l2t_write_rpl(q->adap, p);
635	} else if (opcode == CPL_SMT_WRITE_RPL) {
636		const struct cpl_smt_write_rpl *p = (void *)rsp;
637
638		do_smt_write_rpl(q->adap, p);
639	} else if (opcode == CPL_SET_TCB_RPL) {
640		const struct cpl_set_tcb_rpl *p = (void *)rsp;
641
642		filter_rpl(q->adap, p);
643	} else if (opcode == CPL_ACT_OPEN_RPL) {
644		const struct cpl_act_open_rpl *p = (void *)rsp;
645
646		hash_filter_rpl(q->adap, p);
647	} else if (opcode == CPL_ABORT_RPL_RSS) {
648		const struct cpl_abort_rpl_rss *p = (void *)rsp;
649
650		hash_del_filter_rpl(q->adap, p);
651	} else if (opcode == CPL_SRQ_TABLE_RPL) {
652		const struct cpl_srq_table_rpl *p = (void *)rsp;
653
654		do_srq_table_rpl(q->adap, p);
655	} else
656		dev_err(q->adap->pdev_dev,
657			"unexpected CPL %#x on FW event queue\n", opcode);
658out:
659	return 0;
660}
661
662static void disable_msi(struct adapter *adapter)
663{
664	if (adapter->flags & CXGB4_USING_MSIX) {
665		pci_disable_msix(adapter->pdev);
666		adapter->flags &= ~CXGB4_USING_MSIX;
667	} else if (adapter->flags & CXGB4_USING_MSI) {
668		pci_disable_msi(adapter->pdev);
669		adapter->flags &= ~CXGB4_USING_MSI;
670	}
671}
672
673/*
674 * Interrupt handler for non-data events used with MSI-X.
675 */
676static irqreturn_t t4_nondata_intr(int irq, void *cookie)
677{
678	struct adapter *adap = cookie;
679	u32 v = t4_read_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A));
680
681	if (v & PFSW_F) {
682		adap->swintr = 1;
683		t4_write_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A), v);
684	}
685	if (adap->flags & CXGB4_MASTER_PF)
686		t4_slow_intr_handler(adap);
687	return IRQ_HANDLED;
688}
689
690int cxgb4_set_msix_aff(struct adapter *adap, unsigned short vec,
691		       cpumask_var_t *aff_mask, int idx)
692{
693	int rv;
694
695	if (!zalloc_cpumask_var(aff_mask, GFP_KERNEL)) {
696		dev_err(adap->pdev_dev, "alloc_cpumask_var failed\n");
697		return -ENOMEM;
698	}
699
700	cpumask_set_cpu(cpumask_local_spread(idx, dev_to_node(adap->pdev_dev)),
701			*aff_mask);
702
703	rv = irq_set_affinity_hint(vec, *aff_mask);
704	if (rv)
705		dev_warn(adap->pdev_dev,
706			 "irq_set_affinity_hint %u failed %d\n",
707			 vec, rv);
708
709	return 0;
710}
711
712void cxgb4_clear_msix_aff(unsigned short vec, cpumask_var_t aff_mask)
713{
714	irq_set_affinity_hint(vec, NULL);
715	free_cpumask_var(aff_mask);
716}
717
718static int request_msix_queue_irqs(struct adapter *adap)
719{
720	struct sge *s = &adap->sge;
721	struct msix_info *minfo;
722	int err, ethqidx;
723
724	if (s->fwevtq_msix_idx < 0)
725		return -ENOMEM;
726
727	err = request_irq(adap->msix_info[s->fwevtq_msix_idx].vec,
728			  t4_sge_intr_msix, 0,
729			  adap->msix_info[s->fwevtq_msix_idx].desc,
730			  &s->fw_evtq);
731	if (err)
732		return err;
733
734	for_each_ethrxq(s, ethqidx) {
735		minfo = s->ethrxq[ethqidx].msix;
736		err = request_irq(minfo->vec,
737				  t4_sge_intr_msix, 0,
738				  minfo->desc,
739				  &s->ethrxq[ethqidx].rspq);
740		if (err)
741			goto unwind;
742
743		cxgb4_set_msix_aff(adap, minfo->vec,
744				   &minfo->aff_mask, ethqidx);
745	}
746	return 0;
747
748unwind:
749	while (--ethqidx >= 0) {
750		minfo = s->ethrxq[ethqidx].msix;
751		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
752		free_irq(minfo->vec, &s->ethrxq[ethqidx].rspq);
753	}
754	free_irq(adap->msix_info[s->fwevtq_msix_idx].vec, &s->fw_evtq);
755	return err;
756}
757
758static void free_msix_queue_irqs(struct adapter *adap)
759{
760	struct sge *s = &adap->sge;
761	struct msix_info *minfo;
762	int i;
763
764	free_irq(adap->msix_info[s->fwevtq_msix_idx].vec, &s->fw_evtq);
765	for_each_ethrxq(s, i) {
766		minfo = s->ethrxq[i].msix;
767		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
768		free_irq(minfo->vec, &s->ethrxq[i].rspq);
769	}
770}
771
772static int setup_ppod_edram(struct adapter *adap)
773{
774	unsigned int param, val;
775	int ret;
776
777	/* Driver sends FW_PARAMS_PARAM_DEV_PPOD_EDRAM read command to check
778	 * if firmware supports ppod edram feature or not. If firmware
779	 * returns 1, then driver can enable this feature by sending
780	 * FW_PARAMS_PARAM_DEV_PPOD_EDRAM write command with value 1 to
781	 * enable ppod edram feature.
782	 */
783	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
784		FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PPOD_EDRAM));
785
786	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
787	if (ret < 0) {
788		dev_warn(adap->pdev_dev,
789			 "querying PPOD_EDRAM support failed: %d\n",
790			 ret);
791		return -1;
792	}
793
794	if (val != 1)
795		return -1;
796
797	ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
798	if (ret < 0) {
799		dev_err(adap->pdev_dev,
800			"setting PPOD_EDRAM failed: %d\n", ret);
801		return -1;
802	}
803	return 0;
804}
805
806static void adap_config_hpfilter(struct adapter *adapter)
807{
808	u32 param, val = 0;
809	int ret;
810
811	/* Enable HP filter region. Older fw will fail this request and
812	 * it is fine.
813	 */
814	param = FW_PARAM_DEV(HPFILTER_REGION_SUPPORT);
815	ret = t4_set_params(adapter, adapter->mbox, adapter->pf, 0,
816			    1, &param, &val);
817
818	/* An error means FW doesn't know about HP filter support,
819	 * it's not a problem, don't return an error.
820	 */
821	if (ret < 0)
822		dev_err(adapter->pdev_dev,
823			"HP filter region isn't supported by FW\n");
824}
825
826static int cxgb4_config_rss(const struct port_info *pi, u16 *rss,
827			    u16 rss_size, u16 viid)
828{
829	struct adapter *adap = pi->adapter;
830	int ret;
831
832	ret = t4_config_rss_range(adap, adap->mbox, viid, 0, rss_size, rss,
833				  rss_size);
834	if (ret)
835		return ret;
836
837	/* If Tunnel All Lookup isn't specified in the global RSS
838	 * Configuration, then we need to specify a default Ingress
839	 * Queue for any ingress packets which aren't hashed.  We'll
840	 * use our first ingress queue ...
841	 */
842	return t4_config_vi_rss(adap, adap->mbox, viid,
843				FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F |
844				FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F |
845				FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F |
846				FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F |
847				FW_RSS_VI_CONFIG_CMD_UDPEN_F,
848				rss[0]);
849}
850
851/**
852 *	cxgb4_write_rss - write the RSS table for a given port
853 *	@pi: the port
854 *	@queues: array of queue indices for RSS
855 *
856 *	Sets up the portion of the HW RSS table for the port's VI to distribute
857 *	packets to the Rx queues in @queues.
858 *	Should never be called before setting up sge eth rx queues
859 */
860int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
861{
862	struct adapter *adapter = pi->adapter;
863	const struct sge_eth_rxq *rxq;
864	int i, err;
865	u16 *rss;
866
867	rxq = &adapter->sge.ethrxq[pi->first_qset];
868	rss = kmalloc_array(pi->rss_size, sizeof(u16), GFP_KERNEL);
869	if (!rss)
870		return -ENOMEM;
871
872	/* map the queue indices to queue ids */
873	for (i = 0; i < pi->rss_size; i++, queues++)
874		rss[i] = rxq[*queues].rspq.abs_id;
875
876	err = cxgb4_config_rss(pi, rss, pi->rss_size, pi->viid);
877	kfree(rss);
878	return err;
879}
880
881/**
882 *	setup_rss - configure RSS
883 *	@adap: the adapter
884 *
885 *	Sets up RSS for each port.
886 */
887static int setup_rss(struct adapter *adap)
888{
889	int i, j, err;
890
891	for_each_port(adap, i) {
892		const struct port_info *pi = adap2pinfo(adap, i);
893
894		/* Fill default values with equal distribution */
895		for (j = 0; j < pi->rss_size; j++)
896			pi->rss[j] = j % pi->nqsets;
897
898		err = cxgb4_write_rss(pi, pi->rss);
899		if (err)
900			return err;
901	}
902	return 0;
903}
904
905/*
906 * Return the channel of the ingress queue with the given qid.
907 */
908static unsigned int rxq_to_chan(const struct sge *p, unsigned int qid)
909{
910	qid -= p->ingr_start;
911	return netdev2pinfo(p->ingr_map[qid]->netdev)->tx_chan;
912}
913
914void cxgb4_quiesce_rx(struct sge_rspq *q)
915{
916	if (q->handler)
917		napi_disable(&q->napi);
918}
919
920/*
921 * Wait until all NAPI handlers are descheduled.
922 */
923static void quiesce_rx(struct adapter *adap)
924{
925	int i;
926
927	for (i = 0; i < adap->sge.ingr_sz; i++) {
928		struct sge_rspq *q = adap->sge.ingr_map[i];
929
930		if (!q)
931			continue;
932
933		cxgb4_quiesce_rx(q);
934	}
935}
936
937/* Disable interrupt and napi handler */
938static void disable_interrupts(struct adapter *adap)
939{
940	struct sge *s = &adap->sge;
941
942	if (adap->flags & CXGB4_FULL_INIT_DONE) {
943		t4_intr_disable(adap);
944		if (adap->flags & CXGB4_USING_MSIX) {
945			free_msix_queue_irqs(adap);
946			free_irq(adap->msix_info[s->nd_msix_idx].vec,
947				 adap);
948		} else {
949			free_irq(adap->pdev->irq, adap);
950		}
951		quiesce_rx(adap);
952	}
953}
954
955void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q)
956{
957	if (q->handler)
958		napi_enable(&q->napi);
959
960	/* 0-increment GTS to start the timer and enable interrupts */
961	t4_write_reg(adap, MYPF_REG(SGE_PF_GTS_A),
962		     SEINTARM_V(q->intr_params) |
963		     INGRESSQID_V(q->cntxt_id));
964}
965
966/*
967 * Enable NAPI scheduling and interrupt generation for all Rx queues.
968 */
969static void enable_rx(struct adapter *adap)
970{
971	int i;
972
973	for (i = 0; i < adap->sge.ingr_sz; i++) {
974		struct sge_rspq *q = adap->sge.ingr_map[i];
975
976		if (!q)
977			continue;
978
979		cxgb4_enable_rx(adap, q);
980	}
981}
982
983static int setup_non_data_intr(struct adapter *adap)
984{
985	int msix;
986
987	adap->sge.nd_msix_idx = -1;
988	if (!(adap->flags & CXGB4_USING_MSIX))
989		return 0;
990
991	/* Request MSI-X vector for non-data interrupt */
992	msix = cxgb4_get_msix_idx_from_bmap(adap);
993	if (msix < 0)
994		return -ENOMEM;
995
996	snprintf(adap->msix_info[msix].desc,
997		 sizeof(adap->msix_info[msix].desc),
998		 "%s", adap->port[0]->name);
999
1000	adap->sge.nd_msix_idx = msix;
1001	return 0;
1002}
1003
1004static int setup_fw_sge_queues(struct adapter *adap)
1005{
1006	struct sge *s = &adap->sge;
1007	int msix, err = 0;
1008
1009	bitmap_zero(s->starving_fl, s->egr_sz);
1010	bitmap_zero(s->txq_maperr, s->egr_sz);
1011
1012	if (adap->flags & CXGB4_USING_MSIX) {
1013		s->fwevtq_msix_idx = -1;
1014		msix = cxgb4_get_msix_idx_from_bmap(adap);
1015		if (msix < 0)
1016			return -ENOMEM;
1017
1018		snprintf(adap->msix_info[msix].desc,
1019			 sizeof(adap->msix_info[msix].desc),
1020			 "%s-FWeventq", adap->port[0]->name);
1021	} else {
1022		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
1023				       NULL, NULL, NULL, -1);
1024		if (err)
1025			return err;
1026		msix = -((int)s->intrq.abs_id + 1);
1027	}
1028
1029	err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0],
1030			       msix, NULL, fwevtq_handler, NULL, -1);
1031	if (err && msix >= 0)
1032		cxgb4_free_msix_idx_in_bmap(adap, msix);
1033
1034	s->fwevtq_msix_idx = msix;
1035	return err;
1036}
1037
1038/**
1039 *	setup_sge_queues - configure SGE Tx/Rx/response queues
1040 *	@adap: the adapter
1041 *
1042 *	Determines how many sets of SGE queues to use and initializes them.
1043 *	We support multiple queue sets per port if we have MSI-X, otherwise
1044 *	just one queue set per port.
1045 */
1046static int setup_sge_queues(struct adapter *adap)
1047{
1048	struct sge_uld_rxq_info *rxq_info = NULL;
1049	struct sge *s = &adap->sge;
1050	unsigned int cmplqid = 0;
1051	int err, i, j, msix = 0;
1052
1053	if (is_uld(adap))
1054		rxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA];
1055
1056	if (!(adap->flags & CXGB4_USING_MSIX))
1057		msix = -((int)s->intrq.abs_id + 1);
1058
1059	for_each_port(adap, i) {
1060		struct net_device *dev = adap->port[i];
1061		struct port_info *pi = netdev_priv(dev);
1062		struct sge_eth_rxq *q = &s->ethrxq[pi->first_qset];
1063		struct sge_eth_txq *t = &s->ethtxq[pi->first_qset];
1064
1065		for (j = 0; j < pi->nqsets; j++, q++) {
1066			if (msix >= 0) {
1067				msix = cxgb4_get_msix_idx_from_bmap(adap);
1068				if (msix < 0) {
1069					err = msix;
1070					goto freeout;
1071				}
1072
1073				snprintf(adap->msix_info[msix].desc,
1074					 sizeof(adap->msix_info[msix].desc),
1075					 "%s-Rx%d", dev->name, j);
1076				q->msix = &adap->msix_info[msix];
1077			}
1078
1079			err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev,
1080					       msix, &q->fl,
1081					       t4_ethrx_handler,
1082					       NULL,
1083					       t4_get_tp_ch_map(adap,
1084								pi->tx_chan));
1085			if (err)
1086				goto freeout;
1087			q->rspq.idx = j;
1088			memset(&q->stats, 0, sizeof(q->stats));
1089		}
1090
1091		q = &s->ethrxq[pi->first_qset];
1092		for (j = 0; j < pi->nqsets; j++, t++, q++) {
1093			err = t4_sge_alloc_eth_txq(adap, t, dev,
1094					netdev_get_tx_queue(dev, j),
1095					q->rspq.cntxt_id,
1096					!!(adap->flags & CXGB4_SGE_DBQ_TIMER));
1097			if (err)
1098				goto freeout;
1099		}
1100	}
1101
1102	for_each_port(adap, i) {
1103		/* Note that cmplqid below is 0 if we don't
1104		 * have RDMA queues, and that's the right value.
1105		 */
1106		if (rxq_info)
1107			cmplqid	= rxq_info->uldrxq[i].rspq.cntxt_id;
1108
1109		err = t4_sge_alloc_ctrl_txq(adap, &s->ctrlq[i], adap->port[i],
1110					    s->fw_evtq.cntxt_id, cmplqid);
1111		if (err)
1112			goto freeout;
1113	}
1114
1115	if (!is_t4(adap->params.chip)) {
1116		err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0],
1117					   netdev_get_tx_queue(adap->port[0], 0)
1118					   , s->fw_evtq.cntxt_id, false);
1119		if (err)
1120			goto freeout;
1121	}
1122
1123	t4_write_reg(adap, is_t4(adap->params.chip) ?
1124				MPS_TRC_RSS_CONTROL_A :
1125				MPS_T5_TRC_RSS_CONTROL_A,
1126		     RSSCONTROL_V(netdev2pinfo(adap->port[0])->tx_chan) |
1127		     QUEUENUMBER_V(s->ethrxq[0].rspq.abs_id));
1128	return 0;
1129freeout:
1130	dev_err(adap->pdev_dev, "Can't allocate queues, err=%d\n", -err);
1131	t4_free_sge_resources(adap);
1132	return err;
1133}
1134
1135static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
1136			     struct net_device *sb_dev)
1137{
1138	int txq;
1139
1140#ifdef CONFIG_CHELSIO_T4_DCB
1141	/* If a Data Center Bridging has been successfully negotiated on this
1142	 * link then we'll use the skb's priority to map it to a TX Queue.
1143	 * The skb's priority is determined via the VLAN Tag Priority Code
1144	 * Point field.
1145	 */
1146	if (cxgb4_dcb_enabled(dev) && !is_kdump_kernel()) {
1147		u16 vlan_tci;
1148		int err;
1149
1150		err = vlan_get_tag(skb, &vlan_tci);
1151		if (unlikely(err)) {
1152			if (net_ratelimit())
1153				netdev_warn(dev,
1154					    "TX Packet without VLAN Tag on DCB Link\n");
1155			txq = 0;
1156		} else {
1157			txq = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
1158#ifdef CONFIG_CHELSIO_T4_FCOE
1159			if (skb->protocol == htons(ETH_P_FCOE))
1160				txq = skb->priority & 0x7;
1161#endif /* CONFIG_CHELSIO_T4_FCOE */
1162		}
1163		return txq;
1164	}
1165#endif /* CONFIG_CHELSIO_T4_DCB */
1166
1167	if (dev->num_tc) {
1168		struct port_info *pi = netdev2pinfo(dev);
1169		u8 ver, proto;
1170
1171		ver = ip_hdr(skb)->version;
1172		proto = (ver == 6) ? ipv6_hdr(skb)->nexthdr :
1173				     ip_hdr(skb)->protocol;
1174
1175		/* Send unsupported traffic pattern to normal NIC queues. */
1176		txq = netdev_pick_tx(dev, skb, sb_dev);
1177		if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) ||
1178		    skb->encapsulation ||
1179		    cxgb4_is_ktls_skb(skb) ||
1180		    (proto != IPPROTO_TCP && proto != IPPROTO_UDP))
1181			txq = txq % pi->nqsets;
1182
1183		return txq;
1184	}
1185
1186	if (select_queue) {
1187		txq = (skb_rx_queue_recorded(skb)
1188			? skb_get_rx_queue(skb)
1189			: smp_processor_id());
1190
1191		while (unlikely(txq >= dev->real_num_tx_queues))
1192			txq -= dev->real_num_tx_queues;
1193
1194		return txq;
1195	}
1196
1197	return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues;
1198}
1199
1200static int closest_timer(const struct sge *s, int time)
1201{
1202	int i, delta, match = 0, min_delta = INT_MAX;
1203
1204	for (i = 0; i < ARRAY_SIZE(s->timer_val); i++) {
1205		delta = time - s->timer_val[i];
1206		if (delta < 0)
1207			delta = -delta;
1208		if (delta < min_delta) {
1209			min_delta = delta;
1210			match = i;
1211		}
1212	}
1213	return match;
1214}
1215
1216static int closest_thres(const struct sge *s, int thres)
1217{
1218	int i, delta, match = 0, min_delta = INT_MAX;
1219
1220	for (i = 0; i < ARRAY_SIZE(s->counter_val); i++) {
1221		delta = thres - s->counter_val[i];
1222		if (delta < 0)
1223			delta = -delta;
1224		if (delta < min_delta) {
1225			min_delta = delta;
1226			match = i;
1227		}
1228	}
1229	return match;
1230}
1231
1232/**
1233 *	cxgb4_set_rspq_intr_params - set a queue's interrupt holdoff parameters
1234 *	@q: the Rx queue
1235 *	@us: the hold-off time in us, or 0 to disable timer
1236 *	@cnt: the hold-off packet count, or 0 to disable counter
1237 *
1238 *	Sets an Rx queue's interrupt hold-off time and packet count.  At least
1239 *	one of the two needs to be enabled for the queue to generate interrupts.
1240 */
1241int cxgb4_set_rspq_intr_params(struct sge_rspq *q,
1242			       unsigned int us, unsigned int cnt)
1243{
1244	struct adapter *adap = q->adap;
1245
1246	if ((us | cnt) == 0)
1247		cnt = 1;
1248
1249	if (cnt) {
1250		int err;
1251		u32 v, new_idx;
1252
1253		new_idx = closest_thres(&adap->sge, cnt);
1254		if (q->desc && q->pktcnt_idx != new_idx) {
1255			/* the queue has already been created, update it */
1256			v = FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
1257			    FW_PARAMS_PARAM_X_V(
1258					FW_PARAMS_PARAM_DMAQ_IQ_INTCNTTHRESH) |
1259			    FW_PARAMS_PARAM_YZ_V(q->cntxt_id);
1260			err = t4_set_params(adap, adap->mbox, adap->pf, 0, 1,
1261					    &v, &new_idx);
1262			if (err)
1263				return err;
1264		}
1265		q->pktcnt_idx = new_idx;
1266	}
1267
1268	us = us == 0 ? 6 : closest_timer(&adap->sge, us);
1269	q->intr_params = QINTR_TIMER_IDX_V(us) | QINTR_CNT_EN_V(cnt > 0);
1270	return 0;
1271}
1272
1273static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
1274{
1275	netdev_features_t changed = dev->features ^ features;
1276	const struct port_info *pi = netdev_priv(dev);
1277	int err;
1278
1279	if (!(changed & NETIF_F_HW_VLAN_CTAG_RX))
1280		return 0;
1281
1282	err = t4_set_rxmode(pi->adapter, pi->adapter->mbox, pi->viid,
1283			    pi->viid_mirror, -1, -1, -1, -1,
1284			    !!(features & NETIF_F_HW_VLAN_CTAG_RX), true);
1285	if (unlikely(err))
1286		dev->features = features ^ NETIF_F_HW_VLAN_CTAG_RX;
1287	return err;
1288}
1289
1290static int setup_debugfs(struct adapter *adap)
1291{
1292	if (IS_ERR_OR_NULL(adap->debugfs_root))
1293		return -1;
1294
1295#ifdef CONFIG_DEBUG_FS
1296	t4_setup_debugfs(adap);
1297#endif
1298	return 0;
1299}
1300
1301static void cxgb4_port_mirror_free_rxq(struct adapter *adap,
1302				       struct sge_eth_rxq *mirror_rxq)
1303{
1304	if ((adap->flags & CXGB4_FULL_INIT_DONE) &&
1305	    !(adap->flags & CXGB4_SHUTTING_DOWN))
1306		cxgb4_quiesce_rx(&mirror_rxq->rspq);
1307
1308	if (adap->flags & CXGB4_USING_MSIX) {
1309		cxgb4_clear_msix_aff(mirror_rxq->msix->vec,
1310				     mirror_rxq->msix->aff_mask);
1311		free_irq(mirror_rxq->msix->vec, &mirror_rxq->rspq);
1312		cxgb4_free_msix_idx_in_bmap(adap, mirror_rxq->msix->idx);
1313	}
1314
1315	free_rspq_fl(adap, &mirror_rxq->rspq, &mirror_rxq->fl);
1316}
1317
1318static int cxgb4_port_mirror_alloc_queues(struct net_device *dev)
1319{
1320	struct port_info *pi = netdev2pinfo(dev);
1321	struct adapter *adap = netdev2adap(dev);
1322	struct sge_eth_rxq *mirror_rxq;
1323	struct sge *s = &adap->sge;
1324	int ret = 0, msix = 0;
1325	u16 i, rxqid;
1326	u16 *rss;
1327
1328	if (!pi->vi_mirror_count)
1329		return 0;
1330
1331	if (s->mirror_rxq[pi->port_id])
1332		return 0;
1333
1334	mirror_rxq = kcalloc(pi->nmirrorqsets, sizeof(*mirror_rxq), GFP_KERNEL);
1335	if (!mirror_rxq)
1336		return -ENOMEM;
1337
1338	s->mirror_rxq[pi->port_id] = mirror_rxq;
1339
1340	if (!(adap->flags & CXGB4_USING_MSIX))
1341		msix = -((int)adap->sge.intrq.abs_id + 1);
1342
1343	for (i = 0, rxqid = 0; i < pi->nmirrorqsets; i++, rxqid++) {
1344		mirror_rxq = &s->mirror_rxq[pi->port_id][i];
1345
1346		/* Allocate Mirror Rxqs */
1347		if (msix >= 0) {
1348			msix = cxgb4_get_msix_idx_from_bmap(adap);
1349			if (msix < 0) {
1350				ret = msix;
1351				goto out_free_queues;
1352			}
1353
1354			mirror_rxq->msix = &adap->msix_info[msix];
1355			snprintf(mirror_rxq->msix->desc,
1356				 sizeof(mirror_rxq->msix->desc),
1357				 "%s-mirrorrxq%d", dev->name, i);
1358		}
1359
1360		init_rspq(adap, &mirror_rxq->rspq,
1361			  CXGB4_MIRROR_RXQ_DEFAULT_INTR_USEC,
1362			  CXGB4_MIRROR_RXQ_DEFAULT_PKT_CNT,
1363			  CXGB4_MIRROR_RXQ_DEFAULT_DESC_NUM,
1364			  CXGB4_MIRROR_RXQ_DEFAULT_DESC_SIZE);
1365
1366		mirror_rxq->fl.size = CXGB4_MIRROR_FLQ_DEFAULT_DESC_NUM;
1367
1368		ret = t4_sge_alloc_rxq(adap, &mirror_rxq->rspq, false,
1369				       dev, msix, &mirror_rxq->fl,
1370				       t4_ethrx_handler, NULL, 0);
1371		if (ret)
1372			goto out_free_msix_idx;
1373
1374		/* Setup MSI-X vectors for Mirror Rxqs */
1375		if (adap->flags & CXGB4_USING_MSIX) {
1376			ret = request_irq(mirror_rxq->msix->vec,
1377					  t4_sge_intr_msix, 0,
1378					  mirror_rxq->msix->desc,
1379					  &mirror_rxq->rspq);
1380			if (ret)
1381				goto out_free_rxq;
1382
1383			cxgb4_set_msix_aff(adap, mirror_rxq->msix->vec,
1384					   &mirror_rxq->msix->aff_mask, i);
1385		}
1386
1387		/* Start NAPI for Mirror Rxqs */
1388		cxgb4_enable_rx(adap, &mirror_rxq->rspq);
1389	}
1390
1391	/* Setup RSS for Mirror Rxqs */
1392	rss = kcalloc(pi->rss_size, sizeof(u16), GFP_KERNEL);
1393	if (!rss) {
1394		ret = -ENOMEM;
1395		goto out_free_queues;
1396	}
1397
1398	mirror_rxq = &s->mirror_rxq[pi->port_id][0];
1399	for (i = 0; i < pi->rss_size; i++)
1400		rss[i] = mirror_rxq[i % pi->nmirrorqsets].rspq.abs_id;
1401
1402	ret = cxgb4_config_rss(pi, rss, pi->rss_size, pi->viid_mirror);
1403	kfree(rss);
1404	if (ret)
1405		goto out_free_queues;
1406
1407	return 0;
1408
1409out_free_rxq:
1410	free_rspq_fl(adap, &mirror_rxq->rspq, &mirror_rxq->fl);
1411
1412out_free_msix_idx:
1413	cxgb4_free_msix_idx_in_bmap(adap, mirror_rxq->msix->idx);
1414
1415out_free_queues:
1416	while (rxqid-- > 0)
1417		cxgb4_port_mirror_free_rxq(adap,
1418					   &s->mirror_rxq[pi->port_id][rxqid]);
1419
1420	kfree(s->mirror_rxq[pi->port_id]);
1421	s->mirror_rxq[pi->port_id] = NULL;
1422	return ret;
1423}
1424
1425static void cxgb4_port_mirror_free_queues(struct net_device *dev)
1426{
1427	struct port_info *pi = netdev2pinfo(dev);
1428	struct adapter *adap = netdev2adap(dev);
1429	struct sge *s = &adap->sge;
1430	u16 i;
1431
1432	if (!pi->vi_mirror_count)
1433		return;
1434
1435	if (!s->mirror_rxq[pi->port_id])
1436		return;
1437
1438	for (i = 0; i < pi->nmirrorqsets; i++)
1439		cxgb4_port_mirror_free_rxq(adap,
1440					   &s->mirror_rxq[pi->port_id][i]);
1441
1442	kfree(s->mirror_rxq[pi->port_id]);
1443	s->mirror_rxq[pi->port_id] = NULL;
1444}
1445
1446static int cxgb4_port_mirror_start(struct net_device *dev)
1447{
1448	struct port_info *pi = netdev2pinfo(dev);
1449	struct adapter *adap = netdev2adap(dev);
1450	int ret, idx = -1;
1451
1452	if (!pi->vi_mirror_count)
1453		return 0;
1454
1455	/* Mirror VIs can be created dynamically after stack had
1456	 * already setup Rx modes like MTU, promisc, allmulti, etc.
1457	 * on main VI. So, parse what the stack had setup on the
1458	 * main VI and update the same on the mirror VI.
1459	 */
1460	ret = t4_set_rxmode(adap, adap->mbox, pi->viid, pi->viid_mirror,
1461			    dev->mtu, (dev->flags & IFF_PROMISC) ? 1 : 0,
1462			    (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1,
1463			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
1464	if (ret) {
1465		dev_err(adap->pdev_dev,
1466			"Failed start up Rx mode for Mirror VI 0x%x, ret: %d\n",
1467			pi->viid_mirror, ret);
1468		return ret;
1469	}
1470
1471	/* Enable replication bit for the device's MAC address
1472	 * in MPS TCAM, so that the packets for the main VI are
1473	 * replicated to mirror VI.
1474	 */
1475	ret = cxgb4_update_mac_filt(pi, pi->viid_mirror, &idx,
1476				    dev->dev_addr, true, NULL);
1477	if (ret) {
1478		dev_err(adap->pdev_dev,
1479			"Failed updating MAC filter for Mirror VI 0x%x, ret: %d\n",
1480			pi->viid_mirror, ret);
1481		return ret;
1482	}
1483
1484	/* Enabling a Virtual Interface can result in an interrupt
1485	 * during the processing of the VI Enable command and, in some
1486	 * paths, result in an attempt to issue another command in the
1487	 * interrupt context. Thus, we disable interrupts during the
1488	 * course of the VI Enable command ...
1489	 */
1490	local_bh_disable();
1491	ret = t4_enable_vi_params(adap, adap->mbox, pi->viid_mirror, true, true,
1492				  false);
1493	local_bh_enable();
1494	if (ret)
1495		dev_err(adap->pdev_dev,
1496			"Failed starting Mirror VI 0x%x, ret: %d\n",
1497			pi->viid_mirror, ret);
1498
1499	return ret;
1500}
1501
1502static void cxgb4_port_mirror_stop(struct net_device *dev)
1503{
1504	struct port_info *pi = netdev2pinfo(dev);
1505	struct adapter *adap = netdev2adap(dev);
1506
1507	if (!pi->vi_mirror_count)
1508		return;
1509
1510	t4_enable_vi_params(adap, adap->mbox, pi->viid_mirror, false, false,
1511			    false);
1512}
1513
1514int cxgb4_port_mirror_alloc(struct net_device *dev)
1515{
1516	struct port_info *pi = netdev2pinfo(dev);
1517	struct adapter *adap = netdev2adap(dev);
1518	int ret = 0;
1519
1520	if (!pi->nmirrorqsets)
1521		return -EOPNOTSUPP;
1522
1523	mutex_lock(&pi->vi_mirror_mutex);
1524	if (pi->viid_mirror) {
1525		pi->vi_mirror_count++;
1526		goto out_unlock;
1527	}
1528
1529	ret = t4_init_port_mirror(pi, adap->mbox, pi->port_id, adap->pf, 0,
1530				  &pi->viid_mirror);
1531	if (ret)
1532		goto out_unlock;
1533
1534	pi->vi_mirror_count = 1;
1535
1536	if (adap->flags & CXGB4_FULL_INIT_DONE) {
1537		ret = cxgb4_port_mirror_alloc_queues(dev);
1538		if (ret)
1539			goto out_free_vi;
1540
1541		ret = cxgb4_port_mirror_start(dev);
1542		if (ret)
1543			goto out_free_queues;
1544	}
1545
1546	mutex_unlock(&pi->vi_mirror_mutex);
1547	return 0;
1548
1549out_free_queues:
1550	cxgb4_port_mirror_free_queues(dev);
1551
1552out_free_vi:
1553	pi->vi_mirror_count = 0;
1554	t4_free_vi(adap, adap->mbox, adap->pf, 0, pi->viid_mirror);
1555	pi->viid_mirror = 0;
1556
1557out_unlock:
1558	mutex_unlock(&pi->vi_mirror_mutex);
1559	return ret;
1560}
1561
1562void cxgb4_port_mirror_free(struct net_device *dev)
1563{
1564	struct port_info *pi = netdev2pinfo(dev);
1565	struct adapter *adap = netdev2adap(dev);
1566
1567	mutex_lock(&pi->vi_mirror_mutex);
1568	if (!pi->viid_mirror)
1569		goto out_unlock;
1570
1571	if (pi->vi_mirror_count > 1) {
1572		pi->vi_mirror_count--;
1573		goto out_unlock;
1574	}
1575
1576	cxgb4_port_mirror_stop(dev);
1577	cxgb4_port_mirror_free_queues(dev);
1578
1579	pi->vi_mirror_count = 0;
1580	t4_free_vi(adap, adap->mbox, adap->pf, 0, pi->viid_mirror);
1581	pi->viid_mirror = 0;
1582
1583out_unlock:
1584	mutex_unlock(&pi->vi_mirror_mutex);
1585}
1586
1587/*
1588 * upper-layer driver support
1589 */
1590
1591/*
1592 * Allocate an active-open TID and set it to the supplied value.
1593 */
1594int cxgb4_alloc_atid(struct tid_info *t, void *data)
1595{
1596	int atid = -1;
1597
1598	spin_lock_bh(&t->atid_lock);
1599	if (t->afree) {
1600		union aopen_entry *p = t->afree;
1601
1602		atid = (p - t->atid_tab) + t->atid_base;
1603		t->afree = p->next;
1604		p->data = data;
1605		t->atids_in_use++;
1606	}
1607	spin_unlock_bh(&t->atid_lock);
1608	return atid;
1609}
1610EXPORT_SYMBOL(cxgb4_alloc_atid);
1611
1612/*
1613 * Release an active-open TID.
1614 */
1615void cxgb4_free_atid(struct tid_info *t, unsigned int atid)
1616{
1617	union aopen_entry *p = &t->atid_tab[atid - t->atid_base];
1618
1619	spin_lock_bh(&t->atid_lock);
1620	p->next = t->afree;
1621	t->afree = p;
1622	t->atids_in_use--;
1623	spin_unlock_bh(&t->atid_lock);
1624}
1625EXPORT_SYMBOL(cxgb4_free_atid);
1626
1627/*
1628 * Allocate a server TID and set it to the supplied value.
1629 */
1630int cxgb4_alloc_stid(struct tid_info *t, int family, void *data)
1631{
1632	int stid;
1633
1634	spin_lock_bh(&t->stid_lock);
1635	if (family == PF_INET) {
1636		stid = find_first_zero_bit(t->stid_bmap, t->nstids);
1637		if (stid < t->nstids)
1638			__set_bit(stid, t->stid_bmap);
1639		else
1640			stid = -1;
1641	} else {
1642		stid = bitmap_find_free_region(t->stid_bmap, t->nstids, 1);
1643		if (stid < 0)
1644			stid = -1;
1645	}
1646	if (stid >= 0) {
1647		t->stid_tab[stid].data = data;
1648		stid += t->stid_base;
1649		/* IPv6 requires max of 520 bits or 16 cells in TCAM
1650		 * This is equivalent to 4 TIDs. With CLIP enabled it
1651		 * needs 2 TIDs.
1652		 */
1653		if (family == PF_INET6) {
1654			t->stids_in_use += 2;
1655			t->v6_stids_in_use += 2;
1656		} else {
1657			t->stids_in_use++;
1658		}
1659	}
1660	spin_unlock_bh(&t->stid_lock);
1661	return stid;
1662}
1663EXPORT_SYMBOL(cxgb4_alloc_stid);
1664
1665/* Allocate a server filter TID and set it to the supplied value.
1666 */
1667int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
1668{
1669	int stid;
1670
1671	spin_lock_bh(&t->stid_lock);
1672	if (family == PF_INET) {
1673		stid = find_next_zero_bit(t->stid_bmap,
1674				t->nstids + t->nsftids, t->nstids);
1675		if (stid < (t->nstids + t->nsftids))
1676			__set_bit(stid, t->stid_bmap);
1677		else
1678			stid = -1;
1679	} else {
1680		stid = -1;
1681	}
1682	if (stid >= 0) {
1683		t->stid_tab[stid].data = data;
1684		stid -= t->nstids;
1685		stid += t->sftid_base;
1686		t->sftids_in_use++;
1687	}
1688	spin_unlock_bh(&t->stid_lock);
1689	return stid;
1690}
1691EXPORT_SYMBOL(cxgb4_alloc_sftid);
1692
1693/* Release a server TID.
1694 */
1695void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
1696{
1697	/* Is it a server filter TID? */
1698	if (t->nsftids && (stid >= t->sftid_base)) {
1699		stid -= t->sftid_base;
1700		stid += t->nstids;
1701	} else {
1702		stid -= t->stid_base;
1703	}
1704
1705	spin_lock_bh(&t->stid_lock);
1706	if (family == PF_INET)
1707		__clear_bit(stid, t->stid_bmap);
1708	else
1709		bitmap_release_region(t->stid_bmap, stid, 1);
1710	t->stid_tab[stid].data = NULL;
1711	if (stid < t->nstids) {
1712		if (family == PF_INET6) {
1713			t->stids_in_use -= 2;
1714			t->v6_stids_in_use -= 2;
1715		} else {
1716			t->stids_in_use--;
1717		}
1718	} else {
1719		t->sftids_in_use--;
1720	}
1721
1722	spin_unlock_bh(&t->stid_lock);
1723}
1724EXPORT_SYMBOL(cxgb4_free_stid);
1725
1726/*
1727 * Populate a TID_RELEASE WR.  Caller must properly size the skb.
1728 */
1729static void mk_tid_release(struct sk_buff *skb, unsigned int chan,
1730			   unsigned int tid)
1731{
1732	struct cpl_tid_release *req;
1733
1734	set_wr_txq(skb, CPL_PRIORITY_SETUP, chan);
1735	req = __skb_put(skb, sizeof(*req));
1736	INIT_TP_WR(req, tid);
1737	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_TID_RELEASE, tid));
1738}
1739
1740/*
1741 * Queue a TID release request and if necessary schedule a work queue to
1742 * process it.
1743 */
1744static void cxgb4_queue_tid_release(struct tid_info *t, unsigned int chan,
1745				    unsigned int tid)
1746{
1747	struct adapter *adap = container_of(t, struct adapter, tids);
1748	void **p = &t->tid_tab[tid - t->tid_base];
1749
1750	spin_lock_bh(&adap->tid_release_lock);
1751	*p = adap->tid_release_head;
1752	/* Low 2 bits encode the Tx channel number */
1753	adap->tid_release_head = (void **)((uintptr_t)p | chan);
1754	if (!adap->tid_release_task_busy) {
1755		adap->tid_release_task_busy = true;
1756		queue_work(adap->workq, &adap->tid_release_task);
1757	}
1758	spin_unlock_bh(&adap->tid_release_lock);
1759}
1760
1761/*
1762 * Process the list of pending TID release requests.
1763 */
1764static void process_tid_release_list(struct work_struct *work)
1765{
1766	struct sk_buff *skb;
1767	struct adapter *adap;
1768
1769	adap = container_of(work, struct adapter, tid_release_task);
1770
1771	spin_lock_bh(&adap->tid_release_lock);
1772	while (adap->tid_release_head) {
1773		void **p = adap->tid_release_head;
1774		unsigned int chan = (uintptr_t)p & 3;
1775		p = (void *)p - chan;
1776
1777		adap->tid_release_head = *p;
1778		*p = NULL;
1779		spin_unlock_bh(&adap->tid_release_lock);
1780
1781		while (!(skb = alloc_skb(sizeof(struct cpl_tid_release),
1782					 GFP_KERNEL)))
1783			schedule_timeout_uninterruptible(1);
1784
1785		mk_tid_release(skb, chan, p - adap->tids.tid_tab);
1786		t4_ofld_send(adap, skb);
1787		spin_lock_bh(&adap->tid_release_lock);
1788	}
1789	adap->tid_release_task_busy = false;
1790	spin_unlock_bh(&adap->tid_release_lock);
1791}
1792
1793/*
1794 * Release a TID and inform HW.  If we are unable to allocate the release
1795 * message we defer to a work queue.
1796 */
1797void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid,
1798		      unsigned short family)
1799{
1800	struct adapter *adap = container_of(t, struct adapter, tids);
1801	struct sk_buff *skb;
1802
1803	WARN_ON(tid_out_of_range(&adap->tids, tid));
1804
1805	if (t->tid_tab[tid - adap->tids.tid_base]) {
1806		t->tid_tab[tid - adap->tids.tid_base] = NULL;
1807		atomic_dec(&t->conns_in_use);
1808		if (t->hash_base && (tid >= t->hash_base)) {
1809			if (family == AF_INET6)
1810				atomic_sub(2, &t->hash_tids_in_use);
1811			else
1812				atomic_dec(&t->hash_tids_in_use);
1813		} else {
1814			if (family == AF_INET6)
1815				atomic_sub(2, &t->tids_in_use);
1816			else
1817				atomic_dec(&t->tids_in_use);
1818		}
1819	}
1820
1821	skb = alloc_skb(sizeof(struct cpl_tid_release), GFP_ATOMIC);
1822	if (likely(skb)) {
1823		mk_tid_release(skb, chan, tid);
1824		t4_ofld_send(adap, skb);
1825	} else
1826		cxgb4_queue_tid_release(t, chan, tid);
1827}
1828EXPORT_SYMBOL(cxgb4_remove_tid);
1829
1830/*
1831 * Allocate and initialize the TID tables.  Returns 0 on success.
1832 */
1833static int tid_init(struct tid_info *t)
1834{
1835	struct adapter *adap = container_of(t, struct adapter, tids);
1836	unsigned int max_ftids = t->nftids + t->nsftids;
1837	unsigned int natids = t->natids;
1838	unsigned int hpftid_bmap_size;
1839	unsigned int eotid_bmap_size;
1840	unsigned int stid_bmap_size;
1841	unsigned int ftid_bmap_size;
1842	size_t size;
1843
1844	stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
1845	ftid_bmap_size = BITS_TO_LONGS(t->nftids);
1846	hpftid_bmap_size = BITS_TO_LONGS(t->nhpftids);
1847	eotid_bmap_size = BITS_TO_LONGS(t->neotids);
1848	size = t->ntids * sizeof(*t->tid_tab) +
1849	       natids * sizeof(*t->atid_tab) +
1850	       t->nstids * sizeof(*t->stid_tab) +
1851	       t->nsftids * sizeof(*t->stid_tab) +
1852	       stid_bmap_size * sizeof(long) +
1853	       t->nhpftids * sizeof(*t->hpftid_tab) +
1854	       hpftid_bmap_size * sizeof(long) +
1855	       max_ftids * sizeof(*t->ftid_tab) +
1856	       ftid_bmap_size * sizeof(long) +
1857	       t->neotids * sizeof(*t->eotid_tab) +
1858	       eotid_bmap_size * sizeof(long);
1859
1860	t->tid_tab = kvzalloc(size, GFP_KERNEL);
1861	if (!t->tid_tab)
1862		return -ENOMEM;
1863
1864	t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
1865	t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
1866	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids + t->nsftids];
1867	t->hpftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
1868	t->hpftid_bmap = (unsigned long *)&t->hpftid_tab[t->nhpftids];
1869	t->ftid_tab = (struct filter_entry *)&t->hpftid_bmap[hpftid_bmap_size];
1870	t->ftid_bmap = (unsigned long *)&t->ftid_tab[max_ftids];
1871	t->eotid_tab = (struct eotid_entry *)&t->ftid_bmap[ftid_bmap_size];
1872	t->eotid_bmap = (unsigned long *)&t->eotid_tab[t->neotids];
1873	spin_lock_init(&t->stid_lock);
1874	spin_lock_init(&t->atid_lock);
1875	spin_lock_init(&t->ftid_lock);
1876
1877	t->stids_in_use = 0;
1878	t->v6_stids_in_use = 0;
1879	t->sftids_in_use = 0;
1880	t->afree = NULL;
1881	t->atids_in_use = 0;
1882	atomic_set(&t->tids_in_use, 0);
1883	atomic_set(&t->conns_in_use, 0);
1884	atomic_set(&t->hash_tids_in_use, 0);
1885	atomic_set(&t->eotids_in_use, 0);
1886
1887	/* Setup the free list for atid_tab and clear the stid bitmap. */
1888	if (natids) {
1889		while (--natids)
1890			t->atid_tab[natids - 1].next = &t->atid_tab[natids];
1891		t->afree = t->atid_tab;
1892	}
1893
1894	if (is_offload(adap)) {
1895		bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
1896		/* Reserve stid 0 for T4/T5 adapters */
1897		if (!t->stid_base &&
1898		    CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
1899			__set_bit(0, t->stid_bmap);
1900
1901		if (t->neotids)
1902			bitmap_zero(t->eotid_bmap, t->neotids);
1903	}
1904
1905	if (t->nhpftids)
1906		bitmap_zero(t->hpftid_bmap, t->nhpftids);
1907	bitmap_zero(t->ftid_bmap, t->nftids);
1908	return 0;
1909}
1910
1911/**
1912 *	cxgb4_create_server - create an IP server
1913 *	@dev: the device
1914 *	@stid: the server TID
1915 *	@sip: local IP address to bind server to
1916 *	@sport: the server's TCP port
1917 *	@vlan: the VLAN header information
1918 *	@queue: queue to direct messages from this server to
1919 *
1920 *	Create an IP server for the given port and address.
1921 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
1922 */
1923int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
1924			__be32 sip, __be16 sport, __be16 vlan,
1925			unsigned int queue)
1926{
1927	unsigned int chan;
1928	struct sk_buff *skb;
1929	struct adapter *adap;
1930	struct cpl_pass_open_req *req;
1931	int ret;
1932
1933	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
1934	if (!skb)
1935		return -ENOMEM;
1936
1937	adap = netdev2adap(dev);
1938	req = __skb_put(skb, sizeof(*req));
1939	INIT_TP_WR(req, 0);
1940	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ, stid));
1941	req->local_port = sport;
1942	req->peer_port = htons(0);
1943	req->local_ip = sip;
1944	req->peer_ip = htonl(0);
1945	chan = rxq_to_chan(&adap->sge, queue);
1946	req->opt0 = cpu_to_be64(TX_CHAN_V(chan));
1947	req->opt1 = cpu_to_be64(CONN_POLICY_V(CPL_CONN_POLICY_ASK) |
1948				SYN_RSS_ENABLE_F | SYN_RSS_QUEUE_V(queue));
1949	ret = t4_mgmt_tx(adap, skb);
1950	return net_xmit_eval(ret);
1951}
1952EXPORT_SYMBOL(cxgb4_create_server);
1953
1954/*	cxgb4_create_server6 - create an IPv6 server
1955 *	@dev: the device
1956 *	@stid: the server TID
1957 *	@sip: local IPv6 address to bind server to
1958 *	@sport: the server's TCP port
1959 *	@queue: queue to direct messages from this server to
1960 *
1961 *	Create an IPv6 server for the given port and address.
1962 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
1963 */
1964int cxgb4_create_server6(const struct net_device *dev, unsigned int stid,
1965			 const struct in6_addr *sip, __be16 sport,
1966			 unsigned int queue)
1967{
1968	unsigned int chan;
1969	struct sk_buff *skb;
1970	struct adapter *adap;
1971	struct cpl_pass_open_req6 *req;
1972	int ret;
1973
1974	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
1975	if (!skb)
1976		return -ENOMEM;
1977
1978	adap = netdev2adap(dev);
1979	req = __skb_put(skb, sizeof(*req));
1980	INIT_TP_WR(req, 0);
1981	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ6, stid));
1982	req->local_port = sport;
1983	req->peer_port = htons(0);
1984	req->local_ip_hi = *(__be64 *)(sip->s6_addr);
1985	req->local_ip_lo = *(__be64 *)(sip->s6_addr + 8);
1986	req->peer_ip_hi = cpu_to_be64(0);
1987	req->peer_ip_lo = cpu_to_be64(0);
1988	chan = rxq_to_chan(&adap->sge, queue);
1989	req->opt0 = cpu_to_be64(TX_CHAN_V(chan));
1990	req->opt1 = cpu_to_be64(CONN_POLICY_V(CPL_CONN_POLICY_ASK) |
1991				SYN_RSS_ENABLE_F | SYN_RSS_QUEUE_V(queue));
1992	ret = t4_mgmt_tx(adap, skb);
1993	return net_xmit_eval(ret);
1994}
1995EXPORT_SYMBOL(cxgb4_create_server6);
1996
1997int cxgb4_remove_server(const struct net_device *dev, unsigned int stid,
1998			unsigned int queue, bool ipv6)
1999{
2000	struct sk_buff *skb;
2001	struct adapter *adap;
2002	struct cpl_close_listsvr_req *req;
2003	int ret;
2004
2005	adap = netdev2adap(dev);
2006
2007	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
2008	if (!skb)
2009		return -ENOMEM;
2010
2011	req = __skb_put(skb, sizeof(*req));
2012	INIT_TP_WR(req, 0);
2013	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_LISTSRV_REQ, stid));
2014	req->reply_ctrl = htons(NO_REPLY_V(0) | (ipv6 ? LISTSVR_IPV6_V(1) :
2015				LISTSVR_IPV6_V(0)) | QUEUENO_V(queue));
2016	ret = t4_mgmt_tx(adap, skb);
2017	return net_xmit_eval(ret);
2018}
2019EXPORT_SYMBOL(cxgb4_remove_server);
2020
2021/**
2022 *	cxgb4_best_mtu - find the entry in the MTU table closest to an MTU
2023 *	@mtus: the HW MTU table
2024 *	@mtu: the target MTU
2025 *	@idx: index of selected entry in the MTU table
2026 *
2027 *	Returns the index and the value in the HW MTU table that is closest to
2028 *	but does not exceed @mtu, unless @mtu is smaller than any value in the
2029 *	table, in which case that smallest available value is selected.
2030 */
2031unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
2032			    unsigned int *idx)
2033{
2034	unsigned int i = 0;
2035
2036	while (i < NMTUS - 1 && mtus[i + 1] <= mtu)
2037		++i;
2038	if (idx)
2039		*idx = i;
2040	return mtus[i];
2041}
2042EXPORT_SYMBOL(cxgb4_best_mtu);
2043
2044/**
2045 *     cxgb4_best_aligned_mtu - find best MTU, [hopefully] data size aligned
2046 *     @mtus: the HW MTU table
2047 *     @header_size: Header Size
2048 *     @data_size_max: maximum Data Segment Size
2049 *     @data_size_align: desired Data Segment Size Alignment (2^N)
2050 *     @mtu_idxp: HW MTU Table Index return value pointer (possibly NULL)
2051 *
2052 *     Similar to cxgb4_best_mtu() but instead of searching the Hardware
2053 *     MTU Table based solely on a Maximum MTU parameter, we break that
2054 *     parameter up into a Header Size and Maximum Data Segment Size, and
2055 *     provide a desired Data Segment Size Alignment.  If we find an MTU in
2056 *     the Hardware MTU Table which will result in a Data Segment Size with
2057 *     the requested alignment _and_ that MTU isn't "too far" from the
2058 *     closest MTU, then we'll return that rather than the closest MTU.
2059 */
2060unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
2061				    unsigned short header_size,
2062				    unsigned short data_size_max,
2063				    unsigned short data_size_align,
2064				    unsigned int *mtu_idxp)
2065{
2066	unsigned short max_mtu = header_size + data_size_max;
2067	unsigned short data_size_align_mask = data_size_align - 1;
2068	int mtu_idx, aligned_mtu_idx;
2069
2070	/* Scan the MTU Table till we find an MTU which is larger than our
2071	 * Maximum MTU or we reach the end of the table.  Along the way,
2072	 * record the last MTU found, if any, which will result in a Data
2073	 * Segment Length matching the requested alignment.
2074	 */
2075	for (mtu_idx = 0, aligned_mtu_idx = -1; mtu_idx < NMTUS; mtu_idx++) {
2076		unsigned short data_size = mtus[mtu_idx] - header_size;
2077
2078		/* If this MTU minus the Header Size would result in a
2079		 * Data Segment Size of the desired alignment, remember it.
2080		 */
2081		if ((data_size & data_size_align_mask) == 0)
2082			aligned_mtu_idx = mtu_idx;
2083
2084		/* If we're not at the end of the Hardware MTU Table and the
2085		 * next element is larger than our Maximum MTU, drop out of
2086		 * the loop.
2087		 */
2088		if (mtu_idx+1 < NMTUS && mtus[mtu_idx+1] > max_mtu)
2089			break;
2090	}
2091
2092	/* If we fell out of the loop because we ran to the end of the table,
2093	 * then we just have to use the last [largest] entry.
2094	 */
2095	if (mtu_idx == NMTUS)
2096		mtu_idx--;
2097
2098	/* If we found an MTU which resulted in the requested Data Segment
2099	 * Length alignment and that's "not far" from the largest MTU which is
2100	 * less than or equal to the maximum MTU, then use that.
2101	 */
2102	if (aligned_mtu_idx >= 0 &&
2103	    mtu_idx - aligned_mtu_idx <= 1)
2104		mtu_idx = aligned_mtu_idx;
2105
2106	/* If the caller has passed in an MTU Index pointer, pass the
2107	 * MTU Index back.  Return the MTU value.
2108	 */
2109	if (mtu_idxp)
2110		*mtu_idxp = mtu_idx;
2111	return mtus[mtu_idx];
2112}
2113EXPORT_SYMBOL(cxgb4_best_aligned_mtu);
2114
2115/**
2116 *	cxgb4_port_chan - get the HW channel of a port
2117 *	@dev: the net device for the port
2118 *
2119 *	Return the HW Tx channel of the given port.
2120 */
2121unsigned int cxgb4_port_chan(const struct net_device *dev)
2122{
2123	return netdev2pinfo(dev)->tx_chan;
2124}
2125EXPORT_SYMBOL(cxgb4_port_chan);
2126
2127/**
2128 *      cxgb4_port_e2cchan - get the HW c-channel of a port
2129 *      @dev: the net device for the port
2130 *
2131 *      Return the HW RX c-channel of the given port.
2132 */
2133unsigned int cxgb4_port_e2cchan(const struct net_device *dev)
2134{
2135	return netdev2pinfo(dev)->rx_cchan;
2136}
2137EXPORT_SYMBOL(cxgb4_port_e2cchan);
2138
2139unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo)
2140{
2141	struct adapter *adap = netdev2adap(dev);
2142	u32 v1, v2, lp_count, hp_count;
2143
2144	v1 = t4_read_reg(adap, SGE_DBFIFO_STATUS_A);
2145	v2 = t4_read_reg(adap, SGE_DBFIFO_STATUS2_A);
2146	if (is_t4(adap->params.chip)) {
2147		lp_count = LP_COUNT_G(v1);
2148		hp_count = HP_COUNT_G(v1);
2149	} else {
2150		lp_count = LP_COUNT_T5_G(v1);
2151		hp_count = HP_COUNT_T5_G(v2);
2152	}
2153	return lpfifo ? lp_count : hp_count;
2154}
2155EXPORT_SYMBOL(cxgb4_dbfifo_count);
2156
2157/**
2158 *	cxgb4_port_viid - get the VI id of a port
2159 *	@dev: the net device for the port
2160 *
2161 *	Return the VI id of the given port.
2162 */
2163unsigned int cxgb4_port_viid(const struct net_device *dev)
2164{
2165	return netdev2pinfo(dev)->viid;
2166}
2167EXPORT_SYMBOL(cxgb4_port_viid);
2168
2169/**
2170 *	cxgb4_port_idx - get the index of a port
2171 *	@dev: the net device for the port
2172 *
2173 *	Return the index of the given port.
2174 */
2175unsigned int cxgb4_port_idx(const struct net_device *dev)
2176{
2177	return netdev2pinfo(dev)->port_id;
2178}
2179EXPORT_SYMBOL(cxgb4_port_idx);
2180
2181void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4,
2182			 struct tp_tcp_stats *v6)
2183{
2184	struct adapter *adap = pci_get_drvdata(pdev);
2185
2186	spin_lock(&adap->stats_lock);
2187	t4_tp_get_tcp_stats(adap, v4, v6, false);
2188	spin_unlock(&adap->stats_lock);
2189}
2190EXPORT_SYMBOL(cxgb4_get_tcp_stats);
2191
2192void cxgb4_iscsi_init(struct net_device *dev, unsigned int tag_mask,
2193		      const unsigned int *pgsz_order)
2194{
2195	struct adapter *adap = netdev2adap(dev);
2196
2197	t4_write_reg(adap, ULP_RX_ISCSI_TAGMASK_A, tag_mask);
2198	t4_write_reg(adap, ULP_RX_ISCSI_PSZ_A, HPZ0_V(pgsz_order[0]) |
2199		     HPZ1_V(pgsz_order[1]) | HPZ2_V(pgsz_order[2]) |
2200		     HPZ3_V(pgsz_order[3]));
2201}
2202EXPORT_SYMBOL(cxgb4_iscsi_init);
2203
2204int cxgb4_flush_eq_cache(struct net_device *dev)
2205{
2206	struct adapter *adap = netdev2adap(dev);
2207
2208	return t4_sge_ctxt_flush(adap, adap->mbox, CTXT_EGRESS);
2209}
2210EXPORT_SYMBOL(cxgb4_flush_eq_cache);
2211
2212static int read_eq_indices(struct adapter *adap, u16 qid, u16 *pidx, u16 *cidx)
2213{
2214	u32 addr = t4_read_reg(adap, SGE_DBQ_CTXT_BADDR_A) + 24 * qid + 8;
2215	__be64 indices;
2216	int ret;
2217
2218	spin_lock(&adap->win0_lock);
2219	ret = t4_memory_rw(adap, 0, MEM_EDC0, addr,
2220			   sizeof(indices), (__be32 *)&indices,
2221			   T4_MEMORY_READ);
2222	spin_unlock(&adap->win0_lock);
2223	if (!ret) {
2224		*cidx = (be64_to_cpu(indices) >> 25) & 0xffff;
2225		*pidx = (be64_to_cpu(indices) >> 9) & 0xffff;
2226	}
2227	return ret;
2228}
2229
2230int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx,
2231			u16 size)
2232{
2233	struct adapter *adap = netdev2adap(dev);
2234	u16 hw_pidx, hw_cidx;
2235	int ret;
2236
2237	ret = read_eq_indices(adap, qid, &hw_pidx, &hw_cidx);
2238	if (ret)
2239		goto out;
2240
2241	if (pidx != hw_pidx) {
2242		u16 delta;
2243		u32 val;
2244
2245		if (pidx >= hw_pidx)
2246			delta = pidx - hw_pidx;
2247		else
2248			delta = size - hw_pidx + pidx;
2249
2250		if (is_t4(adap->params.chip))
2251			val = PIDX_V(delta);
2252		else
2253			val = PIDX_T5_V(delta);
2254		wmb();
2255		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
2256			     QID_V(qid) | val);
2257	}
2258out:
2259	return ret;
2260}
2261EXPORT_SYMBOL(cxgb4_sync_txq_pidx);
2262
2263int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte)
2264{
2265	u32 edc0_size, edc1_size, mc0_size, mc1_size, size;
2266	u32 edc0_end, edc1_end, mc0_end, mc1_end;
2267	u32 offset, memtype, memaddr;
2268	struct adapter *adap;
2269	u32 hma_size = 0;
2270	int ret;
2271
2272	adap = netdev2adap(dev);
2273
2274	offset = ((stag >> 8) * 32) + adap->vres.stag.start;
2275
2276	/* Figure out where the offset lands in the Memory Type/Address scheme.
2277	 * This code assumes that the memory is laid out starting at offset 0
2278	 * with no breaks as: EDC0, EDC1, MC0, MC1. All cards have both EDC0
2279	 * and EDC1.  Some cards will have neither MC0 nor MC1, most cards have
2280	 * MC0, and some have both MC0 and MC1.
2281	 */
2282	size = t4_read_reg(adap, MA_EDRAM0_BAR_A);
2283	edc0_size = EDRAM0_SIZE_G(size) << 20;
2284	size = t4_read_reg(adap, MA_EDRAM1_BAR_A);
2285	edc1_size = EDRAM1_SIZE_G(size) << 20;
2286	size = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
2287	mc0_size = EXT_MEM0_SIZE_G(size) << 20;
2288
2289	if (t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A) & HMA_MUX_F) {
2290		size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
2291		hma_size = EXT_MEM1_SIZE_G(size) << 20;
2292	}
2293	edc0_end = edc0_size;
2294	edc1_end = edc0_end + edc1_size;
2295	mc0_end = edc1_end + mc0_size;
2296
2297	if (offset < edc0_end) {
2298		memtype = MEM_EDC0;
2299		memaddr = offset;
2300	} else if (offset < edc1_end) {
2301		memtype = MEM_EDC1;
2302		memaddr = offset - edc0_end;
2303	} else {
2304		if (hma_size && (offset < (edc1_end + hma_size))) {
2305			memtype = MEM_HMA;
2306			memaddr = offset - edc1_end;
2307		} else if (offset < mc0_end) {
2308			memtype = MEM_MC0;
2309			memaddr = offset - edc1_end;
2310		} else if (is_t5(adap->params.chip)) {
2311			size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
2312			mc1_size = EXT_MEM1_SIZE_G(size) << 20;
2313			mc1_end = mc0_end + mc1_size;
2314			if (offset < mc1_end) {
2315				memtype = MEM_MC1;
2316				memaddr = offset - mc0_end;
2317			} else {
2318				/* offset beyond the end of any memory */
2319				goto err;
2320			}
2321		} else {
2322			/* T4/T6 only has a single memory channel */
2323			goto err;
2324		}
2325	}
2326
2327	spin_lock(&adap->win0_lock);
2328	ret = t4_memory_rw(adap, 0, memtype, memaddr, 32, tpte, T4_MEMORY_READ);
2329	spin_unlock(&adap->win0_lock);
2330	return ret;
2331
2332err:
2333	dev_err(adap->pdev_dev, "stag %#x, offset %#x out of range\n",
2334		stag, offset);
2335	return -EINVAL;
2336}
2337EXPORT_SYMBOL(cxgb4_read_tpte);
2338
2339u64 cxgb4_read_sge_timestamp(struct net_device *dev)
2340{
2341	u32 hi, lo;
2342	struct adapter *adap;
2343
2344	adap = netdev2adap(dev);
2345	lo = t4_read_reg(adap, SGE_TIMESTAMP_LO_A);
2346	hi = TSVAL_G(t4_read_reg(adap, SGE_TIMESTAMP_HI_A));
2347
2348	return ((u64)hi << 32) | (u64)lo;
2349}
2350EXPORT_SYMBOL(cxgb4_read_sge_timestamp);
2351
2352int cxgb4_bar2_sge_qregs(struct net_device *dev,
2353			 unsigned int qid,
2354			 enum cxgb4_bar2_qtype qtype,
2355			 int user,
2356			 u64 *pbar2_qoffset,
2357			 unsigned int *pbar2_qid)
2358{
2359	return t4_bar2_sge_qregs(netdev2adap(dev),
2360				 qid,
2361				 (qtype == CXGB4_BAR2_QTYPE_EGRESS
2362				  ? T4_BAR2_QTYPE_EGRESS
2363				  : T4_BAR2_QTYPE_INGRESS),
2364				 user,
2365				 pbar2_qoffset,
2366				 pbar2_qid);
2367}
2368EXPORT_SYMBOL(cxgb4_bar2_sge_qregs);
2369
2370static struct pci_driver cxgb4_driver;
2371
2372static void check_neigh_update(struct neighbour *neigh)
2373{
2374	const struct device *parent;
2375	const struct net_device *netdev = neigh->dev;
2376
2377	if (is_vlan_dev(netdev))
2378		netdev = vlan_dev_real_dev(netdev);
2379	parent = netdev->dev.parent;
2380	if (parent && parent->driver == &cxgb4_driver.driver)
2381		t4_l2t_update(dev_get_drvdata(parent), neigh);
2382}
2383
2384static int netevent_cb(struct notifier_block *nb, unsigned long event,
2385		       void *data)
2386{
2387	switch (event) {
2388	case NETEVENT_NEIGH_UPDATE:
2389		check_neigh_update(data);
2390		break;
2391	case NETEVENT_REDIRECT:
2392	default:
2393		break;
2394	}
2395	return 0;
2396}
2397
2398static bool netevent_registered;
2399static struct notifier_block cxgb4_netevent_nb = {
2400	.notifier_call = netevent_cb
2401};
2402
2403static void drain_db_fifo(struct adapter *adap, int usecs)
2404{
2405	u32 v1, v2, lp_count, hp_count;
2406
2407	do {
2408		v1 = t4_read_reg(adap, SGE_DBFIFO_STATUS_A);
2409		v2 = t4_read_reg(adap, SGE_DBFIFO_STATUS2_A);
2410		if (is_t4(adap->params.chip)) {
2411			lp_count = LP_COUNT_G(v1);
2412			hp_count = HP_COUNT_G(v1);
2413		} else {
2414			lp_count = LP_COUNT_T5_G(v1);
2415			hp_count = HP_COUNT_T5_G(v2);
2416		}
2417
2418		if (lp_count == 0 && hp_count == 0)
2419			break;
2420		set_current_state(TASK_UNINTERRUPTIBLE);
2421		schedule_timeout(usecs_to_jiffies(usecs));
2422	} while (1);
2423}
2424
2425static void disable_txq_db(struct sge_txq *q)
2426{
2427	unsigned long flags;
2428
2429	spin_lock_irqsave(&q->db_lock, flags);
2430	q->db_disabled = 1;
2431	spin_unlock_irqrestore(&q->db_lock, flags);
2432}
2433
2434static void enable_txq_db(struct adapter *adap, struct sge_txq *q)
2435{
2436	spin_lock_irq(&q->db_lock);
2437	if (q->db_pidx_inc) {
2438		/* Make sure that all writes to the TX descriptors
2439		 * are committed before we tell HW about them.
2440		 */
2441		wmb();
2442		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
2443			     QID_V(q->cntxt_id) | PIDX_V(q->db_pidx_inc));
2444		q->db_pidx_inc = 0;
2445	}
2446	q->db_disabled = 0;
2447	spin_unlock_irq(&q->db_lock);
2448}
2449
2450static void disable_dbs(struct adapter *adap)
2451{
2452	int i;
2453
2454	for_each_ethrxq(&adap->sge, i)
2455		disable_txq_db(&adap->sge.ethtxq[i].q);
2456	if (is_offload(adap)) {
2457		struct sge_uld_txq_info *txq_info =
2458			adap->sge.uld_txq_info[CXGB4_TX_OFLD];
2459
2460		if (txq_info) {
2461			for_each_ofldtxq(&adap->sge, i) {
2462				struct sge_uld_txq *txq = &txq_info->uldtxq[i];
2463
2464				disable_txq_db(&txq->q);
2465			}
2466		}
2467	}
2468	for_each_port(adap, i)
2469		disable_txq_db(&adap->sge.ctrlq[i].q);
2470}
2471
2472static void enable_dbs(struct adapter *adap)
2473{
2474	int i;
2475
2476	for_each_ethrxq(&adap->sge, i)
2477		enable_txq_db(adap, &adap->sge.ethtxq[i].q);
2478	if (is_offload(adap)) {
2479		struct sge_uld_txq_info *txq_info =
2480			adap->sge.uld_txq_info[CXGB4_TX_OFLD];
2481
2482		if (txq_info) {
2483			for_each_ofldtxq(&adap->sge, i) {
2484				struct sge_uld_txq *txq = &txq_info->uldtxq[i];
2485
2486				enable_txq_db(adap, &txq->q);
2487			}
2488		}
2489	}
2490	for_each_port(adap, i)
2491		enable_txq_db(adap, &adap->sge.ctrlq[i].q);
2492}
2493
2494static void notify_rdma_uld(struct adapter *adap, enum cxgb4_control cmd)
2495{
2496	enum cxgb4_uld type = CXGB4_ULD_RDMA;
2497
2498	if (adap->uld && adap->uld[type].handle)
2499		adap->uld[type].control(adap->uld[type].handle, cmd);
2500}
2501
2502static void process_db_full(struct work_struct *work)
2503{
2504	struct adapter *adap;
2505
2506	adap = container_of(work, struct adapter, db_full_task);
2507
2508	drain_db_fifo(adap, dbfifo_drain_delay);
2509	enable_dbs(adap);
2510	notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
2511	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
2512		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
2513				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F,
2514				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F);
2515	else
2516		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
2517				 DBFIFO_LP_INT_F, DBFIFO_LP_INT_F);
2518}
2519
2520static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q)
2521{
2522	u16 hw_pidx, hw_cidx;
2523	int ret;
2524
2525	spin_lock_irq(&q->db_lock);
2526	ret = read_eq_indices(adap, (u16)q->cntxt_id, &hw_pidx, &hw_cidx);
2527	if (ret)
2528		goto out;
2529	if (q->db_pidx != hw_pidx) {
2530		u16 delta;
2531		u32 val;
2532
2533		if (q->db_pidx >= hw_pidx)
2534			delta = q->db_pidx - hw_pidx;
2535		else
2536			delta = q->size - hw_pidx + q->db_pidx;
2537
2538		if (is_t4(adap->params.chip))
2539			val = PIDX_V(delta);
2540		else
2541			val = PIDX_T5_V(delta);
2542		wmb();
2543		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
2544			     QID_V(q->cntxt_id) | val);
2545	}
2546out:
2547	q->db_disabled = 0;
2548	q->db_pidx_inc = 0;
2549	spin_unlock_irq(&q->db_lock);
2550	if (ret)
2551		CH_WARN(adap, "DB drop recovery failed.\n");
2552}
2553
2554static void recover_all_queues(struct adapter *adap)
2555{
2556	int i;
2557
2558	for_each_ethrxq(&adap->sge, i)
2559		sync_txq_pidx(adap, &adap->sge.ethtxq[i].q);
2560	if (is_offload(adap)) {
2561		struct sge_uld_txq_info *txq_info =
2562			adap->sge.uld_txq_info[CXGB4_TX_OFLD];
2563		if (txq_info) {
2564			for_each_ofldtxq(&adap->sge, i) {
2565				struct sge_uld_txq *txq = &txq_info->uldtxq[i];
2566
2567				sync_txq_pidx(adap, &txq->q);
2568			}
2569		}
2570	}
2571	for_each_port(adap, i)
2572		sync_txq_pidx(adap, &adap->sge.ctrlq[i].q);
2573}
2574
2575static void process_db_drop(struct work_struct *work)
2576{
2577	struct adapter *adap;
2578
2579	adap = container_of(work, struct adapter, db_drop_task);
2580
2581	if (is_t4(adap->params.chip)) {
2582		drain_db_fifo(adap, dbfifo_drain_delay);
2583		notify_rdma_uld(adap, CXGB4_CONTROL_DB_DROP);
2584		drain_db_fifo(adap, dbfifo_drain_delay);
2585		recover_all_queues(adap);
2586		drain_db_fifo(adap, dbfifo_drain_delay);
2587		enable_dbs(adap);
2588		notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
2589	} else if (is_t5(adap->params.chip)) {
2590		u32 dropped_db = t4_read_reg(adap, 0x010ac);
2591		u16 qid = (dropped_db >> 15) & 0x1ffff;
2592		u16 pidx_inc = dropped_db & 0x1fff;
2593		u64 bar2_qoffset;
2594		unsigned int bar2_qid;
2595		int ret;
2596
2597		ret = t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS,
2598					0, &bar2_qoffset, &bar2_qid);
2599		if (ret)
2600			dev_err(adap->pdev_dev, "doorbell drop recovery: "
2601				"qid=%d, pidx_inc=%d\n", qid, pidx_inc);
2602		else
2603			writel(PIDX_T5_V(pidx_inc) | QID_V(bar2_qid),
2604			       adap->bar2 + bar2_qoffset + SGE_UDB_KDOORBELL);
2605
2606		/* Re-enable BAR2 WC */
2607		t4_set_reg_field(adap, 0x10b0, 1<<15, 1<<15);
2608	}
2609
2610	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
2611		t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0);
2612}
2613
2614void t4_db_full(struct adapter *adap)
2615{
2616	if (is_t4(adap->params.chip)) {
2617		disable_dbs(adap);
2618		notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
2619		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
2620				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F, 0);
2621		queue_work(adap->workq, &adap->db_full_task);
2622	}
2623}
2624
2625void t4_db_dropped(struct adapter *adap)
2626{
2627	if (is_t4(adap->params.chip)) {
2628		disable_dbs(adap);
2629		notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
2630	}
2631	queue_work(adap->workq, &adap->db_drop_task);
2632}
2633
2634void t4_register_netevent_notifier(void)
2635{
2636	if (!netevent_registered) {
2637		register_netevent_notifier(&cxgb4_netevent_nb);
2638		netevent_registered = true;
2639	}
2640}
2641
2642static void detach_ulds(struct adapter *adap)
2643{
2644	unsigned int i;
2645
2646	if (!is_uld(adap))
2647		return;
2648
2649	mutex_lock(&uld_mutex);
2650	list_del(&adap->list_node);
2651
2652	for (i = 0; i < CXGB4_ULD_MAX; i++)
2653		if (adap->uld && adap->uld[i].handle)
2654			adap->uld[i].state_change(adap->uld[i].handle,
2655					     CXGB4_STATE_DETACH);
2656
2657	if (netevent_registered && list_empty(&adapter_list)) {
2658		unregister_netevent_notifier(&cxgb4_netevent_nb);
2659		netevent_registered = false;
2660	}
2661	mutex_unlock(&uld_mutex);
2662}
2663
2664static void notify_ulds(struct adapter *adap, enum cxgb4_state new_state)
2665{
2666	unsigned int i;
2667
2668	mutex_lock(&uld_mutex);
2669	for (i = 0; i < CXGB4_ULD_MAX; i++)
2670		if (adap->uld && adap->uld[i].handle)
2671			adap->uld[i].state_change(adap->uld[i].handle,
2672						  new_state);
2673	mutex_unlock(&uld_mutex);
2674}
2675
2676#if IS_ENABLED(CONFIG_IPV6)
2677static int cxgb4_inet6addr_handler(struct notifier_block *this,
2678				   unsigned long event, void *data)
2679{
2680	struct inet6_ifaddr *ifa = data;
2681	struct net_device *event_dev = ifa->idev->dev;
2682	const struct device *parent = NULL;
2683#if IS_ENABLED(CONFIG_BONDING)
2684	struct adapter *adap;
2685#endif
2686	if (is_vlan_dev(event_dev))
2687		event_dev = vlan_dev_real_dev(event_dev);
2688#if IS_ENABLED(CONFIG_BONDING)
2689	if (event_dev->flags & IFF_MASTER) {
2690		list_for_each_entry(adap, &adapter_list, list_node) {
2691			switch (event) {
2692			case NETDEV_UP:
2693				cxgb4_clip_get(adap->port[0],
2694					       (const u32 *)ifa, 1);
2695				break;
2696			case NETDEV_DOWN:
2697				cxgb4_clip_release(adap->port[0],
2698						   (const u32 *)ifa, 1);
2699				break;
2700			default:
2701				break;
2702			}
2703		}
2704		return NOTIFY_OK;
2705	}
2706#endif
2707
2708	if (event_dev)
2709		parent = event_dev->dev.parent;
2710
2711	if (parent && parent->driver == &cxgb4_driver.driver) {
2712		switch (event) {
2713		case NETDEV_UP:
2714			cxgb4_clip_get(event_dev, (const u32 *)ifa, 1);
2715			break;
2716		case NETDEV_DOWN:
2717			cxgb4_clip_release(event_dev, (const u32 *)ifa, 1);
2718			break;
2719		default:
2720			break;
2721		}
2722	}
2723	return NOTIFY_OK;
2724}
2725
2726static bool inet6addr_registered;
2727static struct notifier_block cxgb4_inet6addr_notifier = {
2728	.notifier_call = cxgb4_inet6addr_handler
2729};
2730
2731static void update_clip(const struct adapter *adap)
2732{
2733	int i;
2734	struct net_device *dev;
2735	int ret;
2736
2737	rcu_read_lock();
2738
2739	for (i = 0; i < MAX_NPORTS; i++) {
2740		dev = adap->port[i];
2741		ret = 0;
2742
2743		if (dev)
2744			ret = cxgb4_update_root_dev_clip(dev);
2745
2746		if (ret < 0)
2747			break;
2748	}
2749	rcu_read_unlock();
2750}
2751#endif /* IS_ENABLED(CONFIG_IPV6) */
2752
2753/**
2754 *	cxgb_up - enable the adapter
2755 *	@adap: adapter being enabled
2756 *
2757 *	Called when the first port is enabled, this function performs the
2758 *	actions necessary to make an adapter operational, such as completing
2759 *	the initialization of HW modules, and enabling interrupts.
2760 *
2761 *	Must be called with the rtnl lock held.
2762 */
2763static int cxgb_up(struct adapter *adap)
2764{
2765	struct sge *s = &adap->sge;
2766	int err;
2767
2768	mutex_lock(&uld_mutex);
2769	err = setup_sge_queues(adap);
2770	if (err)
2771		goto rel_lock;
2772	err = setup_rss(adap);
2773	if (err)
2774		goto freeq;
2775
2776	if (adap->flags & CXGB4_USING_MSIX) {
2777		if (s->nd_msix_idx < 0) {
2778			err = -ENOMEM;
2779			goto irq_err;
2780		}
2781
2782		err = request_irq(adap->msix_info[s->nd_msix_idx].vec,
2783				  t4_nondata_intr, 0,
2784				  adap->msix_info[s->nd_msix_idx].desc, adap);
2785		if (err)
2786			goto irq_err;
2787
2788		err = request_msix_queue_irqs(adap);
2789		if (err)
2790			goto irq_err_free_nd_msix;
2791	} else {
2792		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
2793				  (adap->flags & CXGB4_USING_MSI) ? 0
2794								  : IRQF_SHARED,
2795				  adap->port[0]->name, adap);
2796		if (err)
2797			goto irq_err;
2798	}
2799
2800	enable_rx(adap);
2801	t4_sge_start(adap);
2802	t4_intr_enable(adap);
2803	adap->flags |= CXGB4_FULL_INIT_DONE;
2804	mutex_unlock(&uld_mutex);
2805
2806	notify_ulds(adap, CXGB4_STATE_UP);
2807#if IS_ENABLED(CONFIG_IPV6)
2808	update_clip(adap);
2809#endif
2810	return err;
2811
2812irq_err_free_nd_msix:
2813	free_irq(adap->msix_info[s->nd_msix_idx].vec, adap);
2814irq_err:
2815	dev_err(adap->pdev_dev, "request_irq failed, err %d\n", err);
2816freeq:
2817	t4_free_sge_resources(adap);
2818rel_lock:
2819	mutex_unlock(&uld_mutex);
2820	return err;
2821}
2822
2823static void cxgb_down(struct adapter *adapter)
2824{
2825	cancel_work_sync(&adapter->tid_release_task);
2826	cancel_work_sync(&adapter->db_full_task);
2827	cancel_work_sync(&adapter->db_drop_task);
2828	adapter->tid_release_task_busy = false;
2829	adapter->tid_release_head = NULL;
2830
2831	t4_sge_stop(adapter);
2832	t4_free_sge_resources(adapter);
2833
2834	adapter->flags &= ~CXGB4_FULL_INIT_DONE;
2835}
2836
2837/*
2838 * net_device operations
2839 */
2840static int cxgb_open(struct net_device *dev)
2841{
2842	struct port_info *pi = netdev_priv(dev);
2843	struct adapter *adapter = pi->adapter;
2844	int err;
2845
2846	netif_carrier_off(dev);
2847
2848	if (!(adapter->flags & CXGB4_FULL_INIT_DONE)) {
2849		err = cxgb_up(adapter);
2850		if (err < 0)
2851			return err;
2852	}
2853
2854	/* It's possible that the basic port information could have
2855	 * changed since we first read it.
2856	 */
2857	err = t4_update_port_info(pi);
2858	if (err < 0)
2859		return err;
2860
2861	err = link_start(dev);
2862	if (err)
2863		return err;
2864
2865	if (pi->nmirrorqsets) {
2866		mutex_lock(&pi->vi_mirror_mutex);
2867		err = cxgb4_port_mirror_alloc_queues(dev);
2868		if (err)
2869			goto out_unlock;
2870
2871		err = cxgb4_port_mirror_start(dev);
2872		if (err)
2873			goto out_free_queues;
2874		mutex_unlock(&pi->vi_mirror_mutex);
2875	}
2876
2877	netif_tx_start_all_queues(dev);
2878	return 0;
2879
2880out_free_queues:
2881	cxgb4_port_mirror_free_queues(dev);
2882
2883out_unlock:
2884	mutex_unlock(&pi->vi_mirror_mutex);
2885	return err;
2886}
2887
2888static int cxgb_close(struct net_device *dev)
2889{
2890	struct port_info *pi = netdev_priv(dev);
2891	struct adapter *adapter = pi->adapter;
2892	int ret;
2893
2894	netif_tx_stop_all_queues(dev);
2895	netif_carrier_off(dev);
2896	ret = t4_enable_pi_params(adapter, adapter->pf, pi,
2897				  false, false, false);
2898#ifdef CONFIG_CHELSIO_T4_DCB
2899	cxgb4_dcb_reset(dev);
2900	dcb_tx_queue_prio_enable(dev, false);
2901#endif
2902	if (ret)
2903		return ret;
2904
2905	if (pi->nmirrorqsets) {
2906		mutex_lock(&pi->vi_mirror_mutex);
2907		cxgb4_port_mirror_stop(dev);
2908		cxgb4_port_mirror_free_queues(dev);
2909		mutex_unlock(&pi->vi_mirror_mutex);
2910	}
2911
2912	return 0;
2913}
2914
2915int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
2916		__be32 sip, __be16 sport, __be16 vlan,
2917		unsigned int queue, unsigned char port, unsigned char mask)
2918{
2919	int ret;
2920	struct filter_entry *f;
2921	struct adapter *adap;
2922	int i;
2923	u8 *val;
2924
2925	adap = netdev2adap(dev);
2926
2927	/* Adjust stid to correct filter index */
2928	stid -= adap->tids.sftid_base;
2929	stid += adap->tids.nftids;
2930
2931	/* Check to make sure the filter requested is writable ...
2932	 */
2933	f = &adap->tids.ftid_tab[stid];
2934	ret = writable_filter(f);
2935	if (ret)
2936		return ret;
2937
2938	/* Clear out any old resources being used by the filter before
2939	 * we start constructing the new filter.
2940	 */
2941	if (f->valid)
2942		clear_filter(adap, f);
2943
2944	/* Clear out filter specifications */
2945	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
2946	f->fs.val.lport = be16_to_cpu(sport);
2947	f->fs.mask.lport  = ~0;
2948	val = (u8 *)&sip;
2949	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
2950		for (i = 0; i < 4; i++) {
2951			f->fs.val.lip[i] = val[i];
2952			f->fs.mask.lip[i] = ~0;
2953		}
2954		if (adap->params.tp.vlan_pri_map & PORT_F) {
2955			f->fs.val.iport = port;
2956			f->fs.mask.iport = mask;
2957		}
2958	}
2959
2960	if (adap->params.tp.vlan_pri_map & PROTOCOL_F) {
2961		f->fs.val.proto = IPPROTO_TCP;
2962		f->fs.mask.proto = ~0;
2963	}
2964
2965	f->fs.dirsteer = 1;
2966	f->fs.iq = queue;
2967	/* Mark filter as locked */
2968	f->locked = 1;
2969	f->fs.rpttid = 1;
2970
2971	/* Save the actual tid. We need this to get the corresponding
2972	 * filter entry structure in filter_rpl.
2973	 */
2974	f->tid = stid + adap->tids.ftid_base;
2975	ret = set_filter_wr(adap, stid);
2976	if (ret) {
2977		clear_filter(adap, f);
2978		return ret;
2979	}
2980
2981	return 0;
2982}
2983EXPORT_SYMBOL(cxgb4_create_server_filter);
2984
2985int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
2986		unsigned int queue, bool ipv6)
2987{
2988	struct filter_entry *f;
2989	struct adapter *adap;
2990
2991	adap = netdev2adap(dev);
2992
2993	/* Adjust stid to correct filter index */
2994	stid -= adap->tids.sftid_base;
2995	stid += adap->tids.nftids;
2996
2997	f = &adap->tids.ftid_tab[stid];
2998	/* Unlock the filter */
2999	f->locked = 0;
3000
3001	return delete_filter(adap, stid);
3002}
3003EXPORT_SYMBOL(cxgb4_remove_server_filter);
3004
3005static void cxgb_get_stats(struct net_device *dev,
3006			   struct rtnl_link_stats64 *ns)
3007{
3008	struct port_stats stats;
3009	struct port_info *p = netdev_priv(dev);
3010	struct adapter *adapter = p->adapter;
3011
3012	/* Block retrieving statistics during EEH error
3013	 * recovery. Otherwise, the recovery might fail
3014	 * and the PCI device will be removed permanently
3015	 */
3016	spin_lock(&adapter->stats_lock);
3017	if (!netif_device_present(dev)) {
3018		spin_unlock(&adapter->stats_lock);
3019		return;
3020	}
3021	t4_get_port_stats_offset(adapter, p->tx_chan, &stats,
3022				 &p->stats_base);
3023	spin_unlock(&adapter->stats_lock);
3024
3025	ns->tx_bytes   = stats.tx_octets;
3026	ns->tx_packets = stats.tx_frames;
3027	ns->rx_bytes   = stats.rx_octets;
3028	ns->rx_packets = stats.rx_frames;
3029	ns->multicast  = stats.rx_mcast_frames;
3030
3031	/* detailed rx_errors */
3032	ns->rx_length_errors = stats.rx_jabber + stats.rx_too_long +
3033			       stats.rx_runt;
3034	ns->rx_over_errors   = 0;
3035	ns->rx_crc_errors    = stats.rx_fcs_err;
3036	ns->rx_frame_errors  = stats.rx_symbol_err;
3037	ns->rx_dropped	     = stats.rx_ovflow0 + stats.rx_ovflow1 +
3038			       stats.rx_ovflow2 + stats.rx_ovflow3 +
3039			       stats.rx_trunc0 + stats.rx_trunc1 +
3040			       stats.rx_trunc2 + stats.rx_trunc3;
3041	ns->rx_missed_errors = 0;
3042
3043	/* detailed tx_errors */
3044	ns->tx_aborted_errors   = 0;
3045	ns->tx_carrier_errors   = 0;
3046	ns->tx_fifo_errors      = 0;
3047	ns->tx_heartbeat_errors = 0;
3048	ns->tx_window_errors    = 0;
3049
3050	ns->tx_errors = stats.tx_error_frames;
3051	ns->rx_errors = stats.rx_symbol_err + stats.rx_fcs_err +
3052		ns->rx_length_errors + stats.rx_len_err + ns->rx_fifo_errors;
3053}
3054
3055static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
3056{
3057	unsigned int mbox;
3058	int ret = 0, prtad, devad;
3059	struct port_info *pi = netdev_priv(dev);
3060	struct adapter *adapter = pi->adapter;
3061	struct mii_ioctl_data *data = (struct mii_ioctl_data *)&req->ifr_data;
3062
3063	switch (cmd) {
3064	case SIOCGMIIPHY:
3065		if (pi->mdio_addr < 0)
3066			return -EOPNOTSUPP;
3067		data->phy_id = pi->mdio_addr;
3068		break;
3069	case SIOCGMIIREG:
3070	case SIOCSMIIREG:
3071		if (mdio_phy_id_is_c45(data->phy_id)) {
3072			prtad = mdio_phy_id_prtad(data->phy_id);
3073			devad = mdio_phy_id_devad(data->phy_id);
3074		} else if (data->phy_id < 32) {
3075			prtad = data->phy_id;
3076			devad = 0;
3077			data->reg_num &= 0x1f;
3078		} else
3079			return -EINVAL;
3080
3081		mbox = pi->adapter->pf;
3082		if (cmd == SIOCGMIIREG)
3083			ret = t4_mdio_rd(pi->adapter, mbox, prtad, devad,
3084					 data->reg_num, &data->val_out);
3085		else
3086			ret = t4_mdio_wr(pi->adapter, mbox, prtad, devad,
3087					 data->reg_num, data->val_in);
3088		break;
3089	case SIOCGHWTSTAMP:
3090		return copy_to_user(req->ifr_data, &pi->tstamp_config,
3091				    sizeof(pi->tstamp_config)) ?
3092			-EFAULT : 0;
3093	case SIOCSHWTSTAMP:
3094		if (copy_from_user(&pi->tstamp_config, req->ifr_data,
3095				   sizeof(pi->tstamp_config)))
3096			return -EFAULT;
3097
3098		if (!is_t4(adapter->params.chip)) {
3099			switch (pi->tstamp_config.tx_type) {
3100			case HWTSTAMP_TX_OFF:
3101			case HWTSTAMP_TX_ON:
3102				break;
3103			default:
3104				return -ERANGE;
3105			}
3106
3107			switch (pi->tstamp_config.rx_filter) {
3108			case HWTSTAMP_FILTER_NONE:
3109				pi->rxtstamp = false;
3110				break;
3111			case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
3112			case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
3113				cxgb4_ptprx_timestamping(pi, pi->port_id,
3114							 PTP_TS_L4);
3115				break;
3116			case HWTSTAMP_FILTER_PTP_V2_EVENT:
3117				cxgb4_ptprx_timestamping(pi, pi->port_id,
3118							 PTP_TS_L2_L4);
3119				break;
3120			case HWTSTAMP_FILTER_ALL:
3121			case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
3122			case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
3123			case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
3124			case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
3125				pi->rxtstamp = true;
3126				break;
3127			default:
3128				pi->tstamp_config.rx_filter =
3129					HWTSTAMP_FILTER_NONE;
3130				return -ERANGE;
3131			}
3132
3133			if ((pi->tstamp_config.tx_type == HWTSTAMP_TX_OFF) &&
3134			    (pi->tstamp_config.rx_filter ==
3135				HWTSTAMP_FILTER_NONE)) {
3136				if (cxgb4_ptp_txtype(adapter, pi->port_id) >= 0)
3137					pi->ptp_enable = false;
3138			}
3139
3140			if (pi->tstamp_config.rx_filter !=
3141				HWTSTAMP_FILTER_NONE) {
3142				if (cxgb4_ptp_redirect_rx_packet(adapter,
3143								 pi) >= 0)
3144					pi->ptp_enable = true;
3145			}
3146		} else {
3147			/* For T4 Adapters */
3148			switch (pi->tstamp_config.rx_filter) {
3149			case HWTSTAMP_FILTER_NONE:
3150			pi->rxtstamp = false;
3151			break;
3152			case HWTSTAMP_FILTER_ALL:
3153			pi->rxtstamp = true;
3154			break;
3155			default:
3156			pi->tstamp_config.rx_filter =
3157			HWTSTAMP_FILTER_NONE;
3158			return -ERANGE;
3159			}
3160		}
3161		return copy_to_user(req->ifr_data, &pi->tstamp_config,
3162				    sizeof(pi->tstamp_config)) ?
3163			-EFAULT : 0;
3164	default:
3165		return -EOPNOTSUPP;
3166	}
3167	return ret;
3168}
3169
3170static void cxgb_set_rxmode(struct net_device *dev)
3171{
3172	/* unfortunately we can't return errors to the stack */
3173	set_rxmode(dev, -1, false);
3174}
3175
3176static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
3177{
3178	struct port_info *pi = netdev_priv(dev);
3179	int ret;
3180
3181	ret = t4_set_rxmode(pi->adapter, pi->adapter->mbox, pi->viid,
3182			    pi->viid_mirror, new_mtu, -1, -1, -1, -1, true);
3183	if (!ret)
3184		dev->mtu = new_mtu;
3185	return ret;
3186}
3187
3188#ifdef CONFIG_PCI_IOV
3189static int cxgb4_mgmt_open(struct net_device *dev)
3190{
3191	/* Turn carrier off since we don't have to transmit anything on this
3192	 * interface.
3193	 */
3194	netif_carrier_off(dev);
3195	return 0;
3196}
3197
3198/* Fill MAC address that will be assigned by the FW */
3199static void cxgb4_mgmt_fill_vf_station_mac_addr(struct adapter *adap)
3200{
3201	u8 hw_addr[ETH_ALEN], macaddr[ETH_ALEN];
3202	unsigned int i, vf, nvfs;
3203	u16 a, b;
3204	int err;
3205	u8 *na;
3206
3207	adap->params.pci.vpd_cap_addr = pci_find_capability(adap->pdev,
3208							    PCI_CAP_ID_VPD);
3209	err = t4_get_raw_vpd_params(adap, &adap->params.vpd);
3210	if (err)
3211		return;
3212
3213	na = adap->params.vpd.na;
3214	for (i = 0; i < ETH_ALEN; i++)
3215		hw_addr[i] = (hex2val(na[2 * i + 0]) * 16 +
3216			      hex2val(na[2 * i + 1]));
3217
3218	a = (hw_addr[0] << 8) | hw_addr[1];
3219	b = (hw_addr[1] << 8) | hw_addr[2];
3220	a ^= b;
3221	a |= 0x0200;    /* locally assigned Ethernet MAC address */
3222	a &= ~0x0100;   /* not a multicast Ethernet MAC address */
3223	macaddr[0] = a >> 8;
3224	macaddr[1] = a & 0xff;
3225
3226	for (i = 2; i < 5; i++)
3227		macaddr[i] = hw_addr[i + 1];
3228
3229	for (vf = 0, nvfs = pci_sriov_get_totalvfs(adap->pdev);
3230		vf < nvfs; vf++) {
3231		macaddr[5] = adap->pf * nvfs + vf;
3232		ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, macaddr);
3233	}
3234}
3235
3236static int cxgb4_mgmt_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
3237{
3238	struct port_info *pi = netdev_priv(dev);
3239	struct adapter *adap = pi->adapter;
3240	int ret;
3241
3242	/* verify MAC addr is valid */
3243	if (!is_valid_ether_addr(mac)) {
3244		dev_err(pi->adapter->pdev_dev,
3245			"Invalid Ethernet address %pM for VF %d\n",
3246			mac, vf);
3247		return -EINVAL;
3248	}
3249
3250	dev_info(pi->adapter->pdev_dev,
3251		 "Setting MAC %pM on VF %d\n", mac, vf);
3252	ret = t4_set_vf_mac_acl(adap, vf + 1, 1, mac);
3253	if (!ret)
3254		ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, mac);
3255	return ret;
3256}
3257
3258static int cxgb4_mgmt_get_vf_config(struct net_device *dev,
3259				    int vf, struct ifla_vf_info *ivi)
3260{
3261	struct port_info *pi = netdev_priv(dev);
3262	struct adapter *adap = pi->adapter;
3263	struct vf_info *vfinfo;
3264
3265	if (vf >= adap->num_vfs)
3266		return -EINVAL;
3267	vfinfo = &adap->vfinfo[vf];
3268
3269	ivi->vf = vf;
3270	ivi->max_tx_rate = vfinfo->tx_rate;
3271	ivi->min_tx_rate = 0;
3272	ether_addr_copy(ivi->mac, vfinfo->vf_mac_addr);
3273	ivi->vlan = vfinfo->vlan;
3274	ivi->linkstate = vfinfo->link_state;
3275	return 0;
3276}
3277
3278static int cxgb4_mgmt_get_phys_port_id(struct net_device *dev,
3279				       struct netdev_phys_item_id *ppid)
3280{
3281	struct port_info *pi = netdev_priv(dev);
3282	unsigned int phy_port_id;
3283
3284	phy_port_id = pi->adapter->adap_idx * 10 + pi->port_id;
3285	ppid->id_len = sizeof(phy_port_id);
3286	memcpy(ppid->id, &phy_port_id, ppid->id_len);
3287	return 0;
3288}
3289
3290static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf,
3291				  int min_tx_rate, int max_tx_rate)
3292{
3293	struct port_info *pi = netdev_priv(dev);
3294	struct adapter *adap = pi->adapter;
3295	unsigned int link_ok, speed, mtu;
3296	u32 fw_pfvf, fw_class;
3297	int class_id = vf;
3298	int ret;
3299	u16 pktsize;
3300
3301	if (vf >= adap->num_vfs)
3302		return -EINVAL;
3303
3304	if (min_tx_rate) {
3305		dev_err(adap->pdev_dev,
3306			"Min tx rate (%d) (> 0) for VF %d is Invalid.\n",
3307			min_tx_rate, vf);
3308		return -EINVAL;
3309	}
3310
3311	if (max_tx_rate == 0) {
3312		/* unbind VF to to any Traffic Class */
3313		fw_pfvf =
3314		    (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
3315		     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_SCHEDCLASS_ETH));
3316		fw_class = 0xffffffff;
3317		ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1,
3318				    &fw_pfvf, &fw_class);
3319		if (ret) {
3320			dev_err(adap->pdev_dev,
3321				"Err %d in unbinding PF %d VF %d from TX Rate Limiting\n",
3322				ret, adap->pf, vf);
3323			return -EINVAL;
3324		}
3325		dev_info(adap->pdev_dev,
3326			 "PF %d VF %d is unbound from TX Rate Limiting\n",
3327			 adap->pf, vf);
3328		adap->vfinfo[vf].tx_rate = 0;
3329		return 0;
3330	}
3331
3332	ret = t4_get_link_params(pi, &link_ok, &speed, &mtu);
3333	if (ret != FW_SUCCESS) {
3334		dev_err(adap->pdev_dev,
3335			"Failed to get link information for VF %d\n", vf);
3336		return -EINVAL;
3337	}
3338
3339	if (!link_ok) {
3340		dev_err(adap->pdev_dev, "Link down for VF %d\n", vf);
3341		return -EINVAL;
3342	}
3343
3344	if (max_tx_rate > speed) {
3345		dev_err(adap->pdev_dev,
3346			"Max tx rate %d for VF %d can't be > link-speed %u",
3347			max_tx_rate, vf, speed);
3348		return -EINVAL;
3349	}
3350
3351	pktsize = mtu;
3352	/* subtract ethhdr size and 4 bytes crc since, f/w appends it */
3353	pktsize = pktsize - sizeof(struct ethhdr) - 4;
3354	/* subtract ipv4 hdr size, tcp hdr size to get typical IPv4 MSS size */
3355	pktsize = pktsize - sizeof(struct iphdr) - sizeof(struct tcphdr);
3356	/* configure Traffic Class for rate-limiting */
3357	ret = t4_sched_params(adap, SCHED_CLASS_TYPE_PACKET,
3358			      SCHED_CLASS_LEVEL_CL_RL,
3359			      SCHED_CLASS_MODE_CLASS,
3360			      SCHED_CLASS_RATEUNIT_BITS,
3361			      SCHED_CLASS_RATEMODE_ABS,
3362			      pi->tx_chan, class_id, 0,
3363			      max_tx_rate * 1000, 0, pktsize, 0);
3364	if (ret) {
3365		dev_err(adap->pdev_dev, "Err %d for Traffic Class config\n",
3366			ret);
3367		return -EINVAL;
3368	}
3369	dev_info(adap->pdev_dev,
3370		 "Class %d with MSS %u configured with rate %u\n",
3371		 class_id, pktsize, max_tx_rate);
3372
3373	/* bind VF to configured Traffic Class */
3374	fw_pfvf = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
3375		   FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_SCHEDCLASS_ETH));
3376	fw_class = class_id;
3377	ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1, &fw_pfvf,
3378			    &fw_class);
3379	if (ret) {
3380		dev_err(adap->pdev_dev,
3381			"Err %d in binding PF %d VF %d to Traffic Class %d\n",
3382			ret, adap->pf, vf, class_id);
3383		return -EINVAL;
3384	}
3385	dev_info(adap->pdev_dev, "PF %d VF %d is bound to Class %d\n",
3386		 adap->pf, vf, class_id);
3387	adap->vfinfo[vf].tx_rate = max_tx_rate;
3388	return 0;
3389}
3390
3391static int cxgb4_mgmt_set_vf_vlan(struct net_device *dev, int vf,
3392				  u16 vlan, u8 qos, __be16 vlan_proto)
3393{
3394	struct port_info *pi = netdev_priv(dev);
3395	struct adapter *adap = pi->adapter;
3396	int ret;
3397
3398	if (vf >= adap->num_vfs || vlan > 4095 || qos > 7)
3399		return -EINVAL;
3400
3401	if (vlan_proto != htons(ETH_P_8021Q) || qos != 0)
3402		return -EPROTONOSUPPORT;
3403
3404	ret = t4_set_vlan_acl(adap, adap->mbox, vf + 1, vlan);
3405	if (!ret) {
3406		adap->vfinfo[vf].vlan = vlan;
3407		return 0;
3408	}
3409
3410	dev_err(adap->pdev_dev, "Err %d %s VLAN ACL for PF/VF %d/%d\n",
3411		ret, (vlan ? "setting" : "clearing"), adap->pf, vf);
3412	return ret;
3413}
3414
3415static int cxgb4_mgmt_set_vf_link_state(struct net_device *dev, int vf,
3416					int link)
3417{
3418	struct port_info *pi = netdev_priv(dev);
3419	struct adapter *adap = pi->adapter;
3420	u32 param, val;
3421	int ret = 0;
3422
3423	if (vf >= adap->num_vfs)
3424		return -EINVAL;
3425
3426	switch (link) {
3427	case IFLA_VF_LINK_STATE_AUTO:
3428		val = FW_VF_LINK_STATE_AUTO;
3429		break;
3430
3431	case IFLA_VF_LINK_STATE_ENABLE:
3432		val = FW_VF_LINK_STATE_ENABLE;
3433		break;
3434
3435	case IFLA_VF_LINK_STATE_DISABLE:
3436		val = FW_VF_LINK_STATE_DISABLE;
3437		break;
3438
3439	default:
3440		return -EINVAL;
3441	}
3442
3443	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
3444		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_LINK_STATE));
3445	ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1,
3446			    &param, &val);
3447	if (ret) {
3448		dev_err(adap->pdev_dev,
3449			"Error %d in setting PF %d VF %d link state\n",
3450			ret, adap->pf, vf);
3451		return -EINVAL;
3452	}
3453
3454	adap->vfinfo[vf].link_state = link;
3455	return ret;
3456}
3457#endif /* CONFIG_PCI_IOV */
3458
3459static int cxgb_set_mac_addr(struct net_device *dev, void *p)
3460{
3461	int ret;
3462	struct sockaddr *addr = p;
3463	struct port_info *pi = netdev_priv(dev);
3464
3465	if (!is_valid_ether_addr(addr->sa_data))
3466		return -EADDRNOTAVAIL;
3467
3468	ret = cxgb4_update_mac_filt(pi, pi->viid, &pi->xact_addr_filt,
3469				    addr->sa_data, true, &pi->smt_idx);
3470	if (ret < 0)
3471		return ret;
3472
3473	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
3474	return 0;
3475}
3476
3477#ifdef CONFIG_NET_POLL_CONTROLLER
3478static void cxgb_netpoll(struct net_device *dev)
3479{
3480	struct port_info *pi = netdev_priv(dev);
3481	struct adapter *adap = pi->adapter;
3482
3483	if (adap->flags & CXGB4_USING_MSIX) {
3484		int i;
3485		struct sge_eth_rxq *rx = &adap->sge.ethrxq[pi->first_qset];
3486
3487		for (i = pi->nqsets; i; i--, rx++)
3488			t4_sge_intr_msix(0, &rx->rspq);
3489	} else
3490		t4_intr_handler(adap)(0, adap);
3491}
3492#endif
3493
3494static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
3495{
3496	struct port_info *pi = netdev_priv(dev);
3497	struct adapter *adap = pi->adapter;
3498	struct ch_sched_queue qe = { 0 };
3499	struct ch_sched_params p = { 0 };
3500	struct sched_class *e;
3501	u32 req_rate;
3502	int err = 0;
3503
3504	if (!can_sched(dev))
3505		return -ENOTSUPP;
3506
3507	if (index < 0 || index > pi->nqsets - 1)
3508		return -EINVAL;
3509
3510	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
3511		dev_err(adap->pdev_dev,
3512			"Failed to rate limit on queue %d. Link Down?\n",
3513			index);
3514		return -EINVAL;
3515	}
3516
3517	qe.queue = index;
3518	e = cxgb4_sched_queue_lookup(dev, &qe);
3519	if (e && e->info.u.params.level != SCHED_CLASS_LEVEL_CL_RL) {
3520		dev_err(adap->pdev_dev,
3521			"Queue %u already bound to class %u of type: %u\n",
3522			index, e->idx, e->info.u.params.level);
3523		return -EBUSY;
3524	}
3525
3526	/* Convert from Mbps to Kbps */
3527	req_rate = rate * 1000;
3528
3529	/* Max rate is 100 Gbps */
3530	if (req_rate > SCHED_MAX_RATE_KBPS) {
3531		dev_err(adap->pdev_dev,
3532			"Invalid rate %u Mbps, Max rate is %u Mbps\n",
3533			rate, SCHED_MAX_RATE_KBPS / 1000);
3534		return -ERANGE;
3535	}
3536
3537	/* First unbind the queue from any existing class */
3538	memset(&qe, 0, sizeof(qe));
3539	qe.queue = index;
3540	qe.class = SCHED_CLS_NONE;
3541
3542	err = cxgb4_sched_class_unbind(dev, (void *)(&qe), SCHED_QUEUE);
3543	if (err) {
3544		dev_err(adap->pdev_dev,
3545			"Unbinding Queue %d on port %d fail. Err: %d\n",
3546			index, pi->port_id, err);
3547		return err;
3548	}
3549
3550	/* Queue already unbound */
3551	if (!req_rate)
3552		return 0;
3553
3554	/* Fetch any available unused or matching scheduling class */
3555	p.type = SCHED_CLASS_TYPE_PACKET;
3556	p.u.params.level    = SCHED_CLASS_LEVEL_CL_RL;
3557	p.u.params.mode     = SCHED_CLASS_MODE_CLASS;
3558	p.u.params.rateunit = SCHED_CLASS_RATEUNIT_BITS;
3559	p.u.params.ratemode = SCHED_CLASS_RATEMODE_ABS;
3560	p.u.params.channel  = pi->tx_chan;
3561	p.u.params.class    = SCHED_CLS_NONE;
3562	p.u.params.minrate  = 0;
3563	p.u.params.maxrate  = req_rate;
3564	p.u.params.weight   = 0;
3565	p.u.params.pktsize  = dev->mtu;
3566
3567	e = cxgb4_sched_class_alloc(dev, &p);
3568	if (!e)
3569		return -ENOMEM;
3570
3571	/* Bind the queue to a scheduling class */
3572	memset(&qe, 0, sizeof(qe));
3573	qe.queue = index;
3574	qe.class = e->idx;
3575
3576	err = cxgb4_sched_class_bind(dev, (void *)(&qe), SCHED_QUEUE);
3577	if (err)
3578		dev_err(adap->pdev_dev,
3579			"Queue rate limiting failed. Err: %d\n", err);
3580	return err;
3581}
3582
3583static int cxgb_setup_tc_flower(struct net_device *dev,
3584				struct flow_cls_offload *cls_flower)
3585{
3586	switch (cls_flower->command) {
3587	case FLOW_CLS_REPLACE:
3588		return cxgb4_tc_flower_replace(dev, cls_flower);
3589	case FLOW_CLS_DESTROY:
3590		return cxgb4_tc_flower_destroy(dev, cls_flower);
3591	case FLOW_CLS_STATS:
3592		return cxgb4_tc_flower_stats(dev, cls_flower);
3593	default:
3594		return -EOPNOTSUPP;
3595	}
3596}
3597
3598static int cxgb_setup_tc_cls_u32(struct net_device *dev,
3599				 struct tc_cls_u32_offload *cls_u32)
3600{
3601	switch (cls_u32->command) {
3602	case TC_CLSU32_NEW_KNODE:
3603	case TC_CLSU32_REPLACE_KNODE:
3604		return cxgb4_config_knode(dev, cls_u32);
3605	case TC_CLSU32_DELETE_KNODE:
3606		return cxgb4_delete_knode(dev, cls_u32);
3607	default:
3608		return -EOPNOTSUPP;
3609	}
3610}
3611
3612static int cxgb_setup_tc_matchall(struct net_device *dev,
3613				  struct tc_cls_matchall_offload *cls_matchall,
3614				  bool ingress)
3615{
3616	struct adapter *adap = netdev2adap(dev);
3617
3618	if (!adap->tc_matchall)
3619		return -ENOMEM;
3620
3621	switch (cls_matchall->command) {
3622	case TC_CLSMATCHALL_REPLACE:
3623		return cxgb4_tc_matchall_replace(dev, cls_matchall, ingress);
3624	case TC_CLSMATCHALL_DESTROY:
3625		return cxgb4_tc_matchall_destroy(dev, cls_matchall, ingress);
3626	case TC_CLSMATCHALL_STATS:
3627		if (ingress)
3628			return cxgb4_tc_matchall_stats(dev, cls_matchall);
3629		break;
3630	default:
3631		break;
3632	}
3633
3634	return -EOPNOTSUPP;
3635}
3636
3637static int cxgb_setup_tc_block_ingress_cb(enum tc_setup_type type,
3638					  void *type_data, void *cb_priv)
3639{
3640	struct net_device *dev = cb_priv;
3641	struct port_info *pi = netdev2pinfo(dev);
3642	struct adapter *adap = netdev2adap(dev);
3643
3644	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
3645		dev_err(adap->pdev_dev,
3646			"Failed to setup tc on port %d. Link Down?\n",
3647			pi->port_id);
3648		return -EINVAL;
3649	}
3650
3651	if (!tc_cls_can_offload_and_chain0(dev, type_data))
3652		return -EOPNOTSUPP;
3653
3654	switch (type) {
3655	case TC_SETUP_CLSU32:
3656		return cxgb_setup_tc_cls_u32(dev, type_data);
3657	case TC_SETUP_CLSFLOWER:
3658		return cxgb_setup_tc_flower(dev, type_data);
3659	case TC_SETUP_CLSMATCHALL:
3660		return cxgb_setup_tc_matchall(dev, type_data, true);
3661	default:
3662		return -EOPNOTSUPP;
3663	}
3664}
3665
3666static int cxgb_setup_tc_block_egress_cb(enum tc_setup_type type,
3667					 void *type_data, void *cb_priv)
3668{
3669	struct net_device *dev = cb_priv;
3670	struct port_info *pi = netdev2pinfo(dev);
3671	struct adapter *adap = netdev2adap(dev);
3672
3673	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
3674		dev_err(adap->pdev_dev,
3675			"Failed to setup tc on port %d. Link Down?\n",
3676			pi->port_id);
3677		return -EINVAL;
3678	}
3679
3680	if (!tc_cls_can_offload_and_chain0(dev, type_data))
3681		return -EOPNOTSUPP;
3682
3683	switch (type) {
3684	case TC_SETUP_CLSMATCHALL:
3685		return cxgb_setup_tc_matchall(dev, type_data, false);
3686	default:
3687		break;
3688	}
3689
3690	return -EOPNOTSUPP;
3691}
3692
3693static int cxgb_setup_tc_mqprio(struct net_device *dev,
3694				struct tc_mqprio_qopt_offload *mqprio)
3695{
3696	struct adapter *adap = netdev2adap(dev);
3697
3698	if (!is_ethofld(adap) || !adap->tc_mqprio)
3699		return -ENOMEM;
3700
3701	return cxgb4_setup_tc_mqprio(dev, mqprio);
3702}
3703
3704static LIST_HEAD(cxgb_block_cb_list);
3705
3706static int cxgb_setup_tc_block(struct net_device *dev,
3707			       struct flow_block_offload *f)
3708{
3709	struct port_info *pi = netdev_priv(dev);
3710	flow_setup_cb_t *cb;
3711	bool ingress_only;
3712
3713	pi->tc_block_shared = f->block_shared;
3714	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
3715		cb = cxgb_setup_tc_block_egress_cb;
3716		ingress_only = false;
3717	} else {
3718		cb = cxgb_setup_tc_block_ingress_cb;
3719		ingress_only = true;
3720	}
3721
3722	return flow_block_cb_setup_simple(f, &cxgb_block_cb_list,
3723					  cb, pi, dev, ingress_only);
3724}
3725
3726static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
3727			 void *type_data)
3728{
3729	switch (type) {
3730	case TC_SETUP_QDISC_MQPRIO:
3731		return cxgb_setup_tc_mqprio(dev, type_data);
3732	case TC_SETUP_BLOCK:
3733		return cxgb_setup_tc_block(dev, type_data);
3734	default:
3735		return -EOPNOTSUPP;
3736	}
3737}
3738
3739static int cxgb_udp_tunnel_unset_port(struct net_device *netdev,
3740				      unsigned int table, unsigned int entry,
3741				      struct udp_tunnel_info *ti)
3742{
3743	struct port_info *pi = netdev_priv(netdev);
3744	struct adapter *adapter = pi->adapter;
3745	u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
3746	int ret = 0, i;
3747
3748	switch (ti->type) {
3749	case UDP_TUNNEL_TYPE_VXLAN:
3750		adapter->vxlan_port = 0;
3751		t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A, 0);
3752		break;
3753	case UDP_TUNNEL_TYPE_GENEVE:
3754		adapter->geneve_port = 0;
3755		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0);
3756		break;
3757	default:
3758		return -EINVAL;
3759	}
3760
3761	/* Matchall mac entries can be deleted only after all tunnel ports
3762	 * are brought down or removed.
3763	 */
3764	if (!adapter->rawf_cnt)
3765		return 0;
3766	for_each_port(adapter, i) {
3767		pi = adap2pinfo(adapter, i);
3768		ret = t4_free_raw_mac_filt(adapter, pi->viid,
3769					   match_all_mac, match_all_mac,
3770					   adapter->rawf_start + pi->port_id,
3771					   1, pi->port_id, false);
3772		if (ret < 0) {
3773			netdev_info(netdev, "Failed to free mac filter entry, for port %d\n",
3774				    i);
3775			return ret;
3776		}
3777	}
3778
3779	return 0;
3780}
3781
3782static int cxgb_udp_tunnel_set_port(struct net_device *netdev,
3783				    unsigned int table, unsigned int entry,
3784				    struct udp_tunnel_info *ti)
3785{
3786	struct port_info *pi = netdev_priv(netdev);
3787	struct adapter *adapter = pi->adapter;
3788	u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
3789	int i, ret;
3790
3791	switch (ti->type) {
3792	case UDP_TUNNEL_TYPE_VXLAN:
3793		adapter->vxlan_port = ti->port;
3794		t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A,
3795			     VXLAN_V(be16_to_cpu(ti->port)) | VXLAN_EN_F);
3796		break;
3797	case UDP_TUNNEL_TYPE_GENEVE:
3798		adapter->geneve_port = ti->port;
3799		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A,
3800			     GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F);
3801		break;
3802	default:
3803		return -EINVAL;
3804	}
3805
3806	/* Create a 'match all' mac filter entry for inner mac,
3807	 * if raw mac interface is supported. Once the linux kernel provides
3808	 * driver entry points for adding/deleting the inner mac addresses,
3809	 * we will remove this 'match all' entry and fallback to adding
3810	 * exact match filters.
3811	 */
3812	for_each_port(adapter, i) {
3813		pi = adap2pinfo(adapter, i);
3814
3815		ret = t4_alloc_raw_mac_filt(adapter, pi->viid,
3816					    match_all_mac,
3817					    match_all_mac,
3818					    adapter->rawf_start + pi->port_id,
3819					    1, pi->port_id, false);
3820		if (ret < 0) {
3821			netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n",
3822				    be16_to_cpu(ti->port));
3823			return ret;
3824		}
3825	}
3826
3827	return 0;
3828}
3829
3830static const struct udp_tunnel_nic_info cxgb_udp_tunnels = {
3831	.set_port	= cxgb_udp_tunnel_set_port,
3832	.unset_port	= cxgb_udp_tunnel_unset_port,
3833	.tables		= {
3834		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
3835		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
3836	},
3837};
3838
3839static netdev_features_t cxgb_features_check(struct sk_buff *skb,
3840					     struct net_device *dev,
3841					     netdev_features_t features)
3842{
3843	struct port_info *pi = netdev_priv(dev);
3844	struct adapter *adapter = pi->adapter;
3845
3846	if (CHELSIO_CHIP_VERSION(adapter->params.chip) < CHELSIO_T6)
3847		return features;
3848
3849	/* Check if hw supports offload for this packet */
3850	if (!skb->encapsulation || cxgb_encap_offload_supported(skb))
3851		return features;
3852
3853	/* Offload is not supported for this encapsulated packet */
3854	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
3855}
3856
3857static netdev_features_t cxgb_fix_features(struct net_device *dev,
3858					   netdev_features_t features)
3859{
3860	/* Disable GRO, if RX_CSUM is disabled */
3861	if (!(features & NETIF_F_RXCSUM))
3862		features &= ~NETIF_F_GRO;
3863
3864	return features;
3865}
3866
3867static const struct net_device_ops cxgb4_netdev_ops = {
3868	.ndo_open             = cxgb_open,
3869	.ndo_stop             = cxgb_close,
3870	.ndo_start_xmit       = t4_start_xmit,
3871	.ndo_select_queue     =	cxgb_select_queue,
3872	.ndo_get_stats64      = cxgb_get_stats,
3873	.ndo_set_rx_mode      = cxgb_set_rxmode,
3874	.ndo_set_mac_address  = cxgb_set_mac_addr,
3875	.ndo_set_features     = cxgb_set_features,
3876	.ndo_validate_addr    = eth_validate_addr,
3877	.ndo_do_ioctl         = cxgb_ioctl,
3878	.ndo_change_mtu       = cxgb_change_mtu,
3879#ifdef CONFIG_NET_POLL_CONTROLLER
3880	.ndo_poll_controller  = cxgb_netpoll,
3881#endif
3882#ifdef CONFIG_CHELSIO_T4_FCOE
3883	.ndo_fcoe_enable      = cxgb_fcoe_enable,
3884	.ndo_fcoe_disable     = cxgb_fcoe_disable,
3885#endif /* CONFIG_CHELSIO_T4_FCOE */
3886	.ndo_set_tx_maxrate   = cxgb_set_tx_maxrate,
3887	.ndo_setup_tc         = cxgb_setup_tc,
3888	.ndo_udp_tunnel_add   = udp_tunnel_nic_add_port,
3889	.ndo_udp_tunnel_del   = udp_tunnel_nic_del_port,
3890	.ndo_features_check   = cxgb_features_check,
3891	.ndo_fix_features     = cxgb_fix_features,
3892};
3893
3894#ifdef CONFIG_PCI_IOV
3895static const struct net_device_ops cxgb4_mgmt_netdev_ops = {
3896	.ndo_open               = cxgb4_mgmt_open,
3897	.ndo_set_vf_mac         = cxgb4_mgmt_set_vf_mac,
3898	.ndo_get_vf_config      = cxgb4_mgmt_get_vf_config,
3899	.ndo_set_vf_rate        = cxgb4_mgmt_set_vf_rate,
3900	.ndo_get_phys_port_id   = cxgb4_mgmt_get_phys_port_id,
3901	.ndo_set_vf_vlan        = cxgb4_mgmt_set_vf_vlan,
3902	.ndo_set_vf_link_state	= cxgb4_mgmt_set_vf_link_state,
3903};
3904#endif
3905
3906static void cxgb4_mgmt_get_drvinfo(struct net_device *dev,
3907				   struct ethtool_drvinfo *info)
3908{
3909	struct adapter *adapter = netdev2adap(dev);
3910
3911	strlcpy(info->driver, cxgb4_driver_name, sizeof(info->driver));
3912	strlcpy(info->bus_info, pci_name(adapter->pdev),
3913		sizeof(info->bus_info));
3914}
3915
3916static const struct ethtool_ops cxgb4_mgmt_ethtool_ops = {
3917	.get_drvinfo       = cxgb4_mgmt_get_drvinfo,
3918};
3919
3920static void notify_fatal_err(struct work_struct *work)
3921{
3922	struct adapter *adap;
3923
3924	adap = container_of(work, struct adapter, fatal_err_notify_task);
3925	notify_ulds(adap, CXGB4_STATE_FATAL_ERROR);
3926}
3927
3928void t4_fatal_err(struct adapter *adap)
3929{
3930	int port;
3931
3932	if (pci_channel_offline(adap->pdev))
3933		return;
3934
3935	/* Disable the SGE since ULDs are going to free resources that
3936	 * could be exposed to the adapter.  RDMA MWs for example...
3937	 */
3938	t4_shutdown_adapter(adap);
3939	for_each_port(adap, port) {
3940		struct net_device *dev = adap->port[port];
3941
3942		/* If we get here in very early initialization the network
3943		 * devices may not have been set up yet.
3944		 */
3945		if (!dev)
3946			continue;
3947
3948		netif_tx_stop_all_queues(dev);
3949		netif_carrier_off(dev);
3950	}
3951	dev_alert(adap->pdev_dev, "encountered fatal error, adapter stopped\n");
3952	queue_work(adap->workq, &adap->fatal_err_notify_task);
3953}
3954
3955static void setup_memwin(struct adapter *adap)
3956{
3957	u32 nic_win_base = t4_get_util_window(adap);
3958
3959	t4_setup_memwin(adap, nic_win_base, MEMWIN_NIC);
3960}
3961
3962static void setup_memwin_rdma(struct adapter *adap)
3963{
3964	if (adap->vres.ocq.size) {
3965		u32 start;
3966		unsigned int sz_kb;
3967
3968		start = t4_read_pcie_cfg4(adap, PCI_BASE_ADDRESS_2);
3969		start &= PCI_BASE_ADDRESS_MEM_MASK;
3970		start += OCQ_WIN_OFFSET(adap->pdev, &adap->vres);
3971		sz_kb = roundup_pow_of_two(adap->vres.ocq.size) >> 10;
3972		t4_write_reg(adap,
3973			     PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 3),
3974			     start | BIR_V(1) | WINDOW_V(ilog2(sz_kb)));
3975		t4_write_reg(adap,
3976			     PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, 3),
3977			     adap->vres.ocq.start);
3978		t4_read_reg(adap,
3979			    PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, 3));
3980	}
3981}
3982
3983/* HMA Definitions */
3984
3985/* The maximum number of address that can be send in a single FW cmd */
3986#define HMA_MAX_ADDR_IN_CMD	5
3987
3988#define HMA_PAGE_SIZE		PAGE_SIZE
3989
3990#define HMA_MAX_NO_FW_ADDRESS	(16 << 10)  /* FW supports 16K addresses */
3991
3992#define HMA_PAGE_ORDER					\
3993	((HMA_PAGE_SIZE < HMA_MAX_NO_FW_ADDRESS) ?	\
3994	ilog2(HMA_MAX_NO_FW_ADDRESS / HMA_PAGE_SIZE) : 0)
3995
3996/* The minimum and maximum possible HMA sizes that can be specified in the FW
3997 * configuration(in units of MB).
3998 */
3999#define HMA_MIN_TOTAL_SIZE	1
4000#define HMA_MAX_TOTAL_SIZE				\
4001	(((HMA_PAGE_SIZE << HMA_PAGE_ORDER) *		\
4002	  HMA_MAX_NO_FW_ADDRESS) >> 20)
4003
4004static void adap_free_hma_mem(struct adapter *adapter)
4005{
4006	struct scatterlist *iter;
4007	struct page *page;
4008	int i;
4009
4010	if (!adapter->hma.sgt)
4011		return;
4012
4013	if (adapter->hma.flags & HMA_DMA_MAPPED_FLAG) {
4014		dma_unmap_sg(adapter->pdev_dev, adapter->hma.sgt->sgl,
4015			     adapter->hma.sgt->nents, PCI_DMA_BIDIRECTIONAL);
4016		adapter->hma.flags &= ~HMA_DMA_MAPPED_FLAG;
4017	}
4018
4019	for_each_sg(adapter->hma.sgt->sgl, iter,
4020		    adapter->hma.sgt->orig_nents, i) {
4021		page = sg_page(iter);
4022		if (page)
4023			__free_pages(page, HMA_PAGE_ORDER);
4024	}
4025
4026	kfree(adapter->hma.phy_addr);
4027	sg_free_table(adapter->hma.sgt);
4028	kfree(adapter->hma.sgt);
4029	adapter->hma.sgt = NULL;
4030}
4031
4032static int adap_config_hma(struct adapter *adapter)
4033{
4034	struct scatterlist *sgl, *iter;
4035	struct sg_table *sgt;
4036	struct page *newpage;
4037	unsigned int i, j, k;
4038	u32 param, hma_size;
4039	unsigned int ncmds;
4040	size_t page_size;
4041	u32 page_order;
4042	int node, ret;
4043
4044	/* HMA is supported only for T6+ cards.
4045	 * Avoid initializing HMA in kdump kernels.
4046	 */
4047	if (is_kdump_kernel() ||
4048	    CHELSIO_CHIP_VERSION(adapter->params.chip) < CHELSIO_T6)
4049		return 0;
4050
4051	/* Get the HMA region size required by fw */
4052	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4053		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_HMA_SIZE));
4054	ret = t4_query_params(adapter, adapter->mbox, adapter->pf, 0,
4055			      1, &param, &hma_size);
4056	/* An error means card has its own memory or HMA is not supported by
4057	 * the firmware. Return without any errors.
4058	 */
4059	if (ret || !hma_size)
4060		return 0;
4061
4062	if (hma_size < HMA_MIN_TOTAL_SIZE ||
4063	    hma_size > HMA_MAX_TOTAL_SIZE) {
4064		dev_err(adapter->pdev_dev,
4065			"HMA size %uMB beyond bounds(%u-%lu)MB\n",
4066			hma_size, HMA_MIN_TOTAL_SIZE, HMA_MAX_TOTAL_SIZE);
4067		return -EINVAL;
4068	}
4069
4070	page_size = HMA_PAGE_SIZE;
4071	page_order = HMA_PAGE_ORDER;
4072	adapter->hma.sgt = kzalloc(sizeof(*adapter->hma.sgt), GFP_KERNEL);
4073	if (unlikely(!adapter->hma.sgt)) {
4074		dev_err(adapter->pdev_dev, "HMA SG table allocation failed\n");
4075		return -ENOMEM;
4076	}
4077	sgt = adapter->hma.sgt;
4078	/* FW returned value will be in MB's
4079	 */
4080	sgt->orig_nents = (hma_size << 20) / (page_size << page_order);
4081	if (sg_alloc_table(sgt, sgt->orig_nents, GFP_KERNEL)) {
4082		dev_err(adapter->pdev_dev, "HMA SGL allocation failed\n");
4083		kfree(adapter->hma.sgt);
4084		adapter->hma.sgt = NULL;
4085		return -ENOMEM;
4086	}
4087
4088	sgl = adapter->hma.sgt->sgl;
4089	node = dev_to_node(adapter->pdev_dev);
4090	for_each_sg(sgl, iter, sgt->orig_nents, i) {
4091		newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL |
4092					   __GFP_ZERO, page_order);
4093		if (!newpage) {
4094			dev_err(adapter->pdev_dev,
4095				"Not enough memory for HMA page allocation\n");
4096			ret = -ENOMEM;
4097			goto free_hma;
4098		}
4099		sg_set_page(iter, newpage, page_size << page_order, 0);
4100	}
4101
4102	sgt->nents = dma_map_sg(adapter->pdev_dev, sgl, sgt->orig_nents,
4103				DMA_BIDIRECTIONAL);
4104	if (!sgt->nents) {
4105		dev_err(adapter->pdev_dev,
4106			"Not enough memory for HMA DMA mapping");
4107		ret = -ENOMEM;
4108		goto free_hma;
4109	}
4110	adapter->hma.flags |= HMA_DMA_MAPPED_FLAG;
4111
4112	adapter->hma.phy_addr = kcalloc(sgt->nents, sizeof(dma_addr_t),
4113					GFP_KERNEL);
4114	if (unlikely(!adapter->hma.phy_addr))
4115		goto free_hma;
4116
4117	for_each_sg(sgl, iter, sgt->nents, i) {
4118		newpage = sg_page(iter);
4119		adapter->hma.phy_addr[i] = sg_dma_address(iter);
4120	}
4121
4122	ncmds = DIV_ROUND_UP(sgt->nents, HMA_MAX_ADDR_IN_CMD);
4123	/* Pass on the addresses to firmware */
4124	for (i = 0, k = 0; i < ncmds; i++, k += HMA_MAX_ADDR_IN_CMD) {
4125		struct fw_hma_cmd hma_cmd;
4126		u8 naddr = HMA_MAX_ADDR_IN_CMD;
4127		u8 soc = 0, eoc = 0;
4128		u8 hma_mode = 1; /* Presently we support only Page table mode */
4129
4130		soc = (i == 0) ? 1 : 0;
4131		eoc = (i == ncmds - 1) ? 1 : 0;
4132
4133		/* For last cmd, set naddr corresponding to remaining
4134		 * addresses
4135		 */
4136		if (i == ncmds - 1) {
4137			naddr = sgt->nents % HMA_MAX_ADDR_IN_CMD;
4138			naddr = naddr ? naddr : HMA_MAX_ADDR_IN_CMD;
4139		}
4140		memset(&hma_cmd, 0, sizeof(hma_cmd));
4141		hma_cmd.op_pkd = htonl(FW_CMD_OP_V(FW_HMA_CMD) |
4142				       FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
4143		hma_cmd.retval_len16 = htonl(FW_LEN16(hma_cmd));
4144
4145		hma_cmd.mode_to_pcie_params =
4146			htonl(FW_HMA_CMD_MODE_V(hma_mode) |
4147			      FW_HMA_CMD_SOC_V(soc) | FW_HMA_CMD_EOC_V(eoc));
4148
4149		/* HMA cmd size specified in MB's */
4150		hma_cmd.naddr_size =
4151			htonl(FW_HMA_CMD_SIZE_V(hma_size) |
4152			      FW_HMA_CMD_NADDR_V(naddr));
4153
4154		/* Total Page size specified in units of 4K */
4155		hma_cmd.addr_size_pkd =
4156			htonl(FW_HMA_CMD_ADDR_SIZE_V
4157				((page_size << page_order) >> 12));
4158
4159		/* Fill the 5 addresses */
4160		for (j = 0; j < naddr; j++) {
4161			hma_cmd.phy_address[j] =
4162				cpu_to_be64(adapter->hma.phy_addr[j + k]);
4163		}
4164		ret = t4_wr_mbox(adapter, adapter->mbox, &hma_cmd,
4165				 sizeof(hma_cmd), &hma_cmd);
4166		if (ret) {
4167			dev_err(adapter->pdev_dev,
4168				"HMA FW command failed with err %d\n", ret);
4169			goto free_hma;
4170		}
4171	}
4172
4173	if (!ret)
4174		dev_info(adapter->pdev_dev,
4175			 "Reserved %uMB host memory for HMA\n", hma_size);
4176	return ret;
4177
4178free_hma:
4179	adap_free_hma_mem(adapter);
4180	return ret;
4181}
4182
4183static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
4184{
4185	u32 v;
4186	int ret;
4187
4188	/* Now that we've successfully configured and initialized the adapter
4189	 * can ask the Firmware what resources it has provisioned for us.
4190	 */
4191	ret = t4_get_pfres(adap);
4192	if (ret) {
4193		dev_err(adap->pdev_dev,
4194			"Unable to retrieve resource provisioning information\n");
4195		return ret;
4196	}
4197
4198	/* get device capabilities */
4199	memset(c, 0, sizeof(*c));
4200	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
4201			       FW_CMD_REQUEST_F | FW_CMD_READ_F);
4202	c->cfvalid_to_len16 = htonl(FW_LEN16(*c));
4203	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), c);
4204	if (ret < 0)
4205		return ret;
4206
4207	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
4208			       FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
4209	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), NULL);
4210	if (ret < 0)
4211		return ret;
4212
4213	ret = t4_config_glbl_rss(adap, adap->pf,
4214				 FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL,
4215				 FW_RSS_GLB_CONFIG_CMD_TNLMAPEN_F |
4216				 FW_RSS_GLB_CONFIG_CMD_TNLALLLKP_F);
4217	if (ret < 0)
4218		return ret;
4219
4220	ret = t4_cfg_pfvf(adap, adap->mbox, adap->pf, 0, adap->sge.egr_sz, 64,
4221			  MAX_INGQ, 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF,
4222			  FW_CMD_CAP_PF);
4223	if (ret < 0)
4224		return ret;
4225
4226	t4_sge_init(adap);
4227
4228	/* tweak some settings */
4229	t4_write_reg(adap, TP_SHIFT_CNT_A, 0x64f8849);
4230	t4_write_reg(adap, ULP_RX_TDDP_PSZ_A, HPZ0_V(PAGE_SHIFT - 12));
4231	t4_write_reg(adap, TP_PIO_ADDR_A, TP_INGRESS_CONFIG_A);
4232	v = t4_read_reg(adap, TP_PIO_DATA_A);
4233	t4_write_reg(adap, TP_PIO_DATA_A, v & ~CSUM_HAS_PSEUDO_HDR_F);
4234
4235	/* first 4 Tx modulation queues point to consecutive Tx channels */
4236	adap->params.tp.tx_modq_map = 0xE4;
4237	t4_write_reg(adap, TP_TX_MOD_QUEUE_REQ_MAP_A,
4238		     TX_MOD_QUEUE_REQ_MAP_V(adap->params.tp.tx_modq_map));
4239
4240	/* associate each Tx modulation queue with consecutive Tx channels */
4241	v = 0x84218421;
4242	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
4243			  &v, 1, TP_TX_SCHED_HDR_A);
4244	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
4245			  &v, 1, TP_TX_SCHED_FIFO_A);
4246	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
4247			  &v, 1, TP_TX_SCHED_PCMD_A);
4248
4249#define T4_TX_MODQ_10G_WEIGHT_DEFAULT 16 /* in KB units */
4250	if (is_offload(adap)) {
4251		t4_write_reg(adap, TP_TX_MOD_QUEUE_WEIGHT0_A,
4252			     TX_MODQ_WEIGHT0_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4253			     TX_MODQ_WEIGHT1_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4254			     TX_MODQ_WEIGHT2_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4255			     TX_MODQ_WEIGHT3_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
4256		t4_write_reg(adap, TP_TX_MOD_CHANNEL_WEIGHT_A,
4257			     TX_MODQ_WEIGHT0_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4258			     TX_MODQ_WEIGHT1_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4259			     TX_MODQ_WEIGHT2_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
4260			     TX_MODQ_WEIGHT3_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
4261	}
4262
4263	/* get basic stuff going */
4264	return t4_early_init(adap, adap->pf);
4265}
4266
4267/*
4268 * Max # of ATIDs.  The absolute HW max is 16K but we keep it lower.
4269 */
4270#define MAX_ATIDS 8192U
4271
4272/*
4273 * Phase 0 of initialization: contact FW, obtain config, perform basic init.
4274 *
4275 * If the firmware we're dealing with has Configuration File support, then
4276 * we use that to perform all configuration
4277 */
4278
4279/*
4280 * Tweak configuration based on module parameters, etc.  Most of these have
4281 * defaults assigned to them by Firmware Configuration Files (if we're using
4282 * them) but need to be explicitly set if we're using hard-coded
4283 * initialization.  But even in the case of using Firmware Configuration
4284 * Files, we'd like to expose the ability to change these via module
4285 * parameters so these are essentially common tweaks/settings for
4286 * Configuration Files and hard-coded initialization ...
4287 */
4288static int adap_init0_tweaks(struct adapter *adapter)
4289{
4290	/*
4291	 * Fix up various Host-Dependent Parameters like Page Size, Cache
4292	 * Line Size, etc.  The firmware default is for a 4KB Page Size and
4293	 * 64B Cache Line Size ...
4294	 */
4295	t4_fixup_host_params(adapter, PAGE_SIZE, L1_CACHE_BYTES);
4296
4297	/*
4298	 * Process module parameters which affect early initialization.
4299	 */
4300	if (rx_dma_offset != 2 && rx_dma_offset != 0) {
4301		dev_err(&adapter->pdev->dev,
4302			"Ignoring illegal rx_dma_offset=%d, using 2\n",
4303			rx_dma_offset);
4304		rx_dma_offset = 2;
4305	}
4306	t4_set_reg_field(adapter, SGE_CONTROL_A,
4307			 PKTSHIFT_V(PKTSHIFT_M),
4308			 PKTSHIFT_V(rx_dma_offset));
4309
4310	/*
4311	 * Don't include the "IP Pseudo Header" in CPL_RX_PKT checksums: Linux
4312	 * adds the pseudo header itself.
4313	 */
4314	t4_tp_wr_bits_indirect(adapter, TP_INGRESS_CONFIG_A,
4315			       CSUM_HAS_PSEUDO_HDR_F, 0);
4316
4317	return 0;
4318}
4319
4320/* 10Gb/s-BT PHY Support. chip-external 10Gb/s-BT PHYs are complex chips
4321 * unto themselves and they contain their own firmware to perform their
4322 * tasks ...
4323 */
4324static int phy_aq1202_version(const u8 *phy_fw_data,
4325			      size_t phy_fw_size)
4326{
4327	int offset;
4328
4329	/* At offset 0x8 you're looking for the primary image's
4330	 * starting offset which is 3 Bytes wide
4331	 *
4332	 * At offset 0xa of the primary image, you look for the offset
4333	 * of the DRAM segment which is 3 Bytes wide.
4334	 *
4335	 * The FW version is at offset 0x27e of the DRAM and is 2 Bytes
4336	 * wide
4337	 */
4338	#define be16(__p) (((__p)[0] << 8) | (__p)[1])
4339	#define le16(__p) ((__p)[0] | ((__p)[1] << 8))
4340	#define le24(__p) (le16(__p) | ((__p)[2] << 16))
4341
4342	offset = le24(phy_fw_data + 0x8) << 12;
4343	offset = le24(phy_fw_data + offset + 0xa);
4344	return be16(phy_fw_data + offset + 0x27e);
4345
4346	#undef be16
4347	#undef le16
4348	#undef le24
4349}
4350
4351static struct info_10gbt_phy_fw {
4352	unsigned int phy_fw_id;		/* PCI Device ID */
4353	char *phy_fw_file;		/* /lib/firmware/ PHY Firmware file */
4354	int (*phy_fw_version)(const u8 *phy_fw_data, size_t phy_fw_size);
4355	int phy_flash;			/* Has FLASH for PHY Firmware */
4356} phy_info_array[] = {
4357	{
4358		PHY_AQ1202_DEVICEID,
4359		PHY_AQ1202_FIRMWARE,
4360		phy_aq1202_version,
4361		1,
4362	},
4363	{
4364		PHY_BCM84834_DEVICEID,
4365		PHY_BCM84834_FIRMWARE,
4366		NULL,
4367		0,
4368	},
4369	{ 0, NULL, NULL },
4370};
4371
4372static struct info_10gbt_phy_fw *find_phy_info(int devid)
4373{
4374	int i;
4375
4376	for (i = 0; i < ARRAY_SIZE(phy_info_array); i++) {
4377		if (phy_info_array[i].phy_fw_id == devid)
4378			return &phy_info_array[i];
4379	}
4380	return NULL;
4381}
4382
4383/* Handle updating of chip-external 10Gb/s-BT PHY firmware.  This needs to
4384 * happen after the FW_RESET_CMD but before the FW_INITIALIZE_CMD.  On error
4385 * we return a negative error number.  If we transfer new firmware we return 1
4386 * (from t4_load_phy_fw()).  If we don't do anything we return 0.
4387 */
4388static int adap_init0_phy(struct adapter *adap)
4389{
4390	const struct firmware *phyf;
4391	int ret;
4392	struct info_10gbt_phy_fw *phy_info;
4393
4394	/* Use the device ID to determine which PHY file to flash.
4395	 */
4396	phy_info = find_phy_info(adap->pdev->device);
4397	if (!phy_info) {
4398		dev_warn(adap->pdev_dev,
4399			 "No PHY Firmware file found for this PHY\n");
4400		return -EOPNOTSUPP;
4401	}
4402
4403	/* If we have a T4 PHY firmware file under /lib/firmware/cxgb4/, then
4404	 * use that. The adapter firmware provides us with a memory buffer
4405	 * where we can load a PHY firmware file from the host if we want to
4406	 * override the PHY firmware File in flash.
4407	 */
4408	ret = request_firmware_direct(&phyf, phy_info->phy_fw_file,
4409				      adap->pdev_dev);
4410	if (ret < 0) {
4411		/* For adapters without FLASH attached to PHY for their
4412		 * firmware, it's obviously a fatal error if we can't get the
4413		 * firmware to the adapter.  For adapters with PHY firmware
4414		 * FLASH storage, it's worth a warning if we can't find the
4415		 * PHY Firmware but we'll neuter the error ...
4416		 */
4417		dev_err(adap->pdev_dev, "unable to find PHY Firmware image "
4418			"/lib/firmware/%s, error %d\n",
4419			phy_info->phy_fw_file, -ret);
4420		if (phy_info->phy_flash) {
4421			int cur_phy_fw_ver = 0;
4422
4423			t4_phy_fw_ver(adap, &cur_phy_fw_ver);
4424			dev_warn(adap->pdev_dev, "continuing with, on-adapter "
4425				 "FLASH copy, version %#x\n", cur_phy_fw_ver);
4426			ret = 0;
4427		}
4428
4429		return ret;
4430	}
4431
4432	/* Load PHY Firmware onto adapter.
4433	 */
4434	ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version,
4435			     (u8 *)phyf->data, phyf->size);
4436	if (ret < 0)
4437		dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
4438			-ret);
4439	else if (ret > 0) {
4440		int new_phy_fw_ver = 0;
4441
4442		if (phy_info->phy_fw_version)
4443			new_phy_fw_ver = phy_info->phy_fw_version(phyf->data,
4444								  phyf->size);
4445		dev_info(adap->pdev_dev, "Successfully transferred PHY "
4446			 "Firmware /lib/firmware/%s, version %#x\n",
4447			 phy_info->phy_fw_file, new_phy_fw_ver);
4448	}
4449
4450	release_firmware(phyf);
4451
4452	return ret;
4453}
4454
4455/*
4456 * Attempt to initialize the adapter via a Firmware Configuration File.
4457 */
4458static int adap_init0_config(struct adapter *adapter, int reset)
4459{
4460	char *fw_config_file, fw_config_file_path[256];
4461	u32 finiver, finicsum, cfcsum, param, val;
4462	struct fw_caps_config_cmd caps_cmd;
4463	unsigned long mtype = 0, maddr = 0;
4464	const struct firmware *cf;
4465	char *config_name = NULL;
4466	int config_issued = 0;
4467	int ret;
4468
4469	/*
4470	 * Reset device if necessary.
4471	 */
4472	if (reset) {
4473		ret = t4_fw_reset(adapter, adapter->mbox,
4474				  PIORSTMODE_F | PIORST_F);
4475		if (ret < 0)
4476			goto bye;
4477	}
4478
4479	/* If this is a 10Gb/s-BT adapter make sure the chip-external
4480	 * 10Gb/s-BT PHYs have up-to-date firmware.  Note that this step needs
4481	 * to be performed after any global adapter RESET above since some
4482	 * PHYs only have local RAM copies of the PHY firmware.
4483	 */
4484	if (is_10gbt_device(adapter->pdev->device)) {
4485		ret = adap_init0_phy(adapter);
4486		if (ret < 0)
4487			goto bye;
4488	}
4489	/*
4490	 * If we have a T4 configuration file under /lib/firmware/cxgb4/,
4491	 * then use that.  Otherwise, use the configuration file stored
4492	 * in the adapter flash ...
4493	 */
4494	switch (CHELSIO_CHIP_VERSION(adapter->params.chip)) {
4495	case CHELSIO_T4:
4496		fw_config_file = FW4_CFNAME;
4497		break;
4498	case CHELSIO_T5:
4499		fw_config_file = FW5_CFNAME;
4500		break;
4501	case CHELSIO_T6:
4502		fw_config_file = FW6_CFNAME;
4503		break;
4504	default:
4505		dev_err(adapter->pdev_dev, "Device %d is not supported\n",
4506		       adapter->pdev->device);
4507		ret = -EINVAL;
4508		goto bye;
4509	}
4510
4511	ret = request_firmware(&cf, fw_config_file, adapter->pdev_dev);
4512	if (ret < 0) {
4513		config_name = "On FLASH";
4514		mtype = FW_MEMTYPE_CF_FLASH;
4515		maddr = t4_flash_cfg_addr(adapter);
4516	} else {
4517		u32 params[7], val[7];
4518
4519		sprintf(fw_config_file_path,
4520			"/lib/firmware/%s", fw_config_file);
4521		config_name = fw_config_file_path;
4522
4523		if (cf->size >= FLASH_CFG_MAX_SIZE)
4524			ret = -ENOMEM;
4525		else {
4526			params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4527			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
4528			ret = t4_query_params(adapter, adapter->mbox,
4529					      adapter->pf, 0, 1, params, val);
4530			if (ret == 0) {
4531				/*
4532				 * For t4_memory_rw() below addresses and
4533				 * sizes have to be in terms of multiples of 4
4534				 * bytes.  So, if the Configuration File isn't
4535				 * a multiple of 4 bytes in length we'll have
4536				 * to write that out separately since we can't
4537				 * guarantee that the bytes following the
4538				 * residual byte in the buffer returned by
4539				 * request_firmware() are zeroed out ...
4540				 */
4541				size_t resid = cf->size & 0x3;
4542				size_t size = cf->size & ~0x3;
4543				__be32 *data = (__be32 *)cf->data;
4544
4545				mtype = FW_PARAMS_PARAM_Y_G(val[0]);
4546				maddr = FW_PARAMS_PARAM_Z_G(val[0]) << 16;
4547
4548				spin_lock(&adapter->win0_lock);
4549				ret = t4_memory_rw(adapter, 0, mtype, maddr,
4550						   size, data, T4_MEMORY_WRITE);
4551				if (ret == 0 && resid != 0) {
4552					union {
4553						__be32 word;
4554						char buf[4];
4555					} last;
4556					int i;
4557
4558					last.word = data[size >> 2];
4559					for (i = resid; i < 4; i++)
4560						last.buf[i] = 0;
4561					ret = t4_memory_rw(adapter, 0, mtype,
4562							   maddr + size,
4563							   4, &last.word,
4564							   T4_MEMORY_WRITE);
4565				}
4566				spin_unlock(&adapter->win0_lock);
4567			}
4568		}
4569
4570		release_firmware(cf);
4571		if (ret)
4572			goto bye;
4573	}
4574
4575	val = 0;
4576
4577	/* Ofld + Hash filter is supported. Older fw will fail this request and
4578	 * it is fine.
4579	 */
4580	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4581		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_HASHFILTER_WITH_OFLD));
4582	ret = t4_set_params(adapter, adapter->mbox, adapter->pf, 0,
4583			    1, &param, &val);
4584
4585	/* FW doesn't know about Hash filter + ofld support,
4586	 * it's not a problem, don't return an error.
4587	 */
4588	if (ret < 0) {
4589		dev_warn(adapter->pdev_dev,
4590			 "Hash filter with ofld is not supported by FW\n");
4591	}
4592
4593	/*
4594	 * Issue a Capability Configuration command to the firmware to get it
4595	 * to parse the Configuration File.  We don't use t4_fw_config_file()
4596	 * because we want the ability to modify various features after we've
4597	 * processed the configuration file ...
4598	 */
4599	memset(&caps_cmd, 0, sizeof(caps_cmd));
4600	caps_cmd.op_to_write =
4601		htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
4602		      FW_CMD_REQUEST_F |
4603		      FW_CMD_READ_F);
4604	caps_cmd.cfvalid_to_len16 =
4605		htonl(FW_CAPS_CONFIG_CMD_CFVALID_F |
4606		      FW_CAPS_CONFIG_CMD_MEMTYPE_CF_V(mtype) |
4607		      FW_CAPS_CONFIG_CMD_MEMADDR64K_CF_V(maddr >> 16) |
4608		      FW_LEN16(caps_cmd));
4609	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
4610			 &caps_cmd);
4611
4612	/* If the CAPS_CONFIG failed with an ENOENT (for a Firmware
4613	 * Configuration File in FLASH), our last gasp effort is to use the
4614	 * Firmware Configuration File which is embedded in the firmware.  A
4615	 * very few early versions of the firmware didn't have one embedded
4616	 * but we can ignore those.
4617	 */
4618	if (ret == -ENOENT) {
4619		memset(&caps_cmd, 0, sizeof(caps_cmd));
4620		caps_cmd.op_to_write =
4621			htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
4622					FW_CMD_REQUEST_F |
4623					FW_CMD_READ_F);
4624		caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
4625		ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd,
4626				sizeof(caps_cmd), &caps_cmd);
4627		config_name = "Firmware Default";
4628	}
4629
4630	config_issued = 1;
4631	if (ret < 0)
4632		goto bye;
4633
4634	finiver = ntohl(caps_cmd.finiver);
4635	finicsum = ntohl(caps_cmd.finicsum);
4636	cfcsum = ntohl(caps_cmd.cfcsum);
4637	if (finicsum != cfcsum)
4638		dev_warn(adapter->pdev_dev, "Configuration File checksum "\
4639			 "mismatch: [fini] csum=%#x, computed csum=%#x\n",
4640			 finicsum, cfcsum);
4641
4642	/*
4643	 * And now tell the firmware to use the configuration we just loaded.
4644	 */
4645	caps_cmd.op_to_write =
4646		htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
4647		      FW_CMD_REQUEST_F |
4648		      FW_CMD_WRITE_F);
4649	caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
4650	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
4651			 NULL);
4652	if (ret < 0)
4653		goto bye;
4654
4655	/*
4656	 * Tweak configuration based on system architecture, module
4657	 * parameters, etc.
4658	 */
4659	ret = adap_init0_tweaks(adapter);
4660	if (ret < 0)
4661		goto bye;
4662
4663	/* We will proceed even if HMA init fails. */
4664	ret = adap_config_hma(adapter);
4665	if (ret)
4666		dev_err(adapter->pdev_dev,
4667			"HMA configuration failed with error %d\n", ret);
4668
4669	if (is_t6(adapter->params.chip)) {
4670		adap_config_hpfilter(adapter);
4671		ret = setup_ppod_edram(adapter);
4672		if (!ret)
4673			dev_info(adapter->pdev_dev, "Successfully enabled "
4674				 "ppod edram feature\n");
4675	}
4676
4677	/*
4678	 * And finally tell the firmware to initialize itself using the
4679	 * parameters from the Configuration File.
4680	 */
4681	ret = t4_fw_initialize(adapter, adapter->mbox);
4682	if (ret < 0)
4683		goto bye;
4684
4685	/* Emit Firmware Configuration File information and return
4686	 * successfully.
4687	 */
4688	dev_info(adapter->pdev_dev, "Successfully configured using Firmware "\
4689		 "Configuration File \"%s\", version %#x, computed checksum %#x\n",
4690		 config_name, finiver, cfcsum);
4691	return 0;
4692
4693	/*
4694	 * Something bad happened.  Return the error ...  (If the "error"
4695	 * is that there's no Configuration File on the adapter we don't
4696	 * want to issue a warning since this is fairly common.)
4697	 */
4698bye:
4699	if (config_issued && ret != -ENOENT)
4700		dev_warn(adapter->pdev_dev, "\"%s\" configuration file error %d\n",
4701			 config_name, -ret);
4702	return ret;
4703}
4704
4705static struct fw_info fw_info_array[] = {
4706	{
4707		.chip = CHELSIO_T4,
4708		.fs_name = FW4_CFNAME,
4709		.fw_mod_name = FW4_FNAME,
4710		.fw_hdr = {
4711			.chip = FW_HDR_CHIP_T4,
4712			.fw_ver = __cpu_to_be32(FW_VERSION(T4)),
4713			.intfver_nic = FW_INTFVER(T4, NIC),
4714			.intfver_vnic = FW_INTFVER(T4, VNIC),
4715			.intfver_ri = FW_INTFVER(T4, RI),
4716			.intfver_iscsi = FW_INTFVER(T4, ISCSI),
4717			.intfver_fcoe = FW_INTFVER(T4, FCOE),
4718		},
4719	}, {
4720		.chip = CHELSIO_T5,
4721		.fs_name = FW5_CFNAME,
4722		.fw_mod_name = FW5_FNAME,
4723		.fw_hdr = {
4724			.chip = FW_HDR_CHIP_T5,
4725			.fw_ver = __cpu_to_be32(FW_VERSION(T5)),
4726			.intfver_nic = FW_INTFVER(T5, NIC),
4727			.intfver_vnic = FW_INTFVER(T5, VNIC),
4728			.intfver_ri = FW_INTFVER(T5, RI),
4729			.intfver_iscsi = FW_INTFVER(T5, ISCSI),
4730			.intfver_fcoe = FW_INTFVER(T5, FCOE),
4731		},
4732	}, {
4733		.chip = CHELSIO_T6,
4734		.fs_name = FW6_CFNAME,
4735		.fw_mod_name = FW6_FNAME,
4736		.fw_hdr = {
4737			.chip = FW_HDR_CHIP_T6,
4738			.fw_ver = __cpu_to_be32(FW_VERSION(T6)),
4739			.intfver_nic = FW_INTFVER(T6, NIC),
4740			.intfver_vnic = FW_INTFVER(T6, VNIC),
4741			.intfver_ofld = FW_INTFVER(T6, OFLD),
4742			.intfver_ri = FW_INTFVER(T6, RI),
4743			.intfver_iscsipdu = FW_INTFVER(T6, ISCSIPDU),
4744			.intfver_iscsi = FW_INTFVER(T6, ISCSI),
4745			.intfver_fcoepdu = FW_INTFVER(T6, FCOEPDU),
4746			.intfver_fcoe = FW_INTFVER(T6, FCOE),
4747		},
4748	}
4749
4750};
4751
4752static struct fw_info *find_fw_info(int chip)
4753{
4754	int i;
4755
4756	for (i = 0; i < ARRAY_SIZE(fw_info_array); i++) {
4757		if (fw_info_array[i].chip == chip)
4758			return &fw_info_array[i];
4759	}
4760	return NULL;
4761}
4762
4763/*
4764 * Phase 0 of initialization: contact FW, obtain config, perform basic init.
4765 */
4766static int adap_init0(struct adapter *adap, int vpd_skip)
4767{
4768	struct fw_caps_config_cmd caps_cmd;
4769	u32 params[7], val[7];
4770	enum dev_state state;
4771	u32 v, port_vec;
4772	int reset = 1;
4773	int ret;
4774
4775	/* Grab Firmware Device Log parameters as early as possible so we have
4776	 * access to it for debugging, etc.
4777	 */
4778	ret = t4_init_devlog_params(adap);
4779	if (ret < 0)
4780		return ret;
4781
4782	/* Contact FW, advertising Master capability */
4783	ret = t4_fw_hello(adap, adap->mbox, adap->mbox,
4784			  is_kdump_kernel() ? MASTER_MUST : MASTER_MAY, &state);
4785	if (ret < 0) {
4786		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
4787			ret);
4788		return ret;
4789	}
4790	if (ret == adap->mbox)
4791		adap->flags |= CXGB4_MASTER_PF;
4792
4793	/*
4794	 * If we're the Master PF Driver and the device is uninitialized,
4795	 * then let's consider upgrading the firmware ...  (We always want
4796	 * to check the firmware version number in order to A. get it for
4797	 * later reporting and B. to warn if the currently loaded firmware
4798	 * is excessively mismatched relative to the driver.)
4799	 */
4800
4801	t4_get_version_info(adap);
4802	ret = t4_check_fw_version(adap);
4803	/* If firmware is too old (not supported by driver) force an update. */
4804	if (ret)
4805		state = DEV_STATE_UNINIT;
4806	if ((adap->flags & CXGB4_MASTER_PF) && state != DEV_STATE_INIT) {
4807		struct fw_info *fw_info;
4808		struct fw_hdr *card_fw;
4809		const struct firmware *fw;
4810		const u8 *fw_data = NULL;
4811		unsigned int fw_size = 0;
4812
4813		/* This is the firmware whose headers the driver was compiled
4814		 * against
4815		 */
4816		fw_info = find_fw_info(CHELSIO_CHIP_VERSION(adap->params.chip));
4817		if (fw_info == NULL) {
4818			dev_err(adap->pdev_dev,
4819				"unable to get firmware info for chip %d.\n",
4820				CHELSIO_CHIP_VERSION(adap->params.chip));
4821			return -EINVAL;
4822		}
4823
4824		/* allocate memory to read the header of the firmware on the
4825		 * card
4826		 */
4827		card_fw = kvzalloc(sizeof(*card_fw), GFP_KERNEL);
4828		if (!card_fw) {
4829			ret = -ENOMEM;
4830			goto bye;
4831		}
4832
4833		/* Get FW from from /lib/firmware/ */
4834		ret = request_firmware(&fw, fw_info->fw_mod_name,
4835				       adap->pdev_dev);
4836		if (ret < 0) {
4837			dev_err(adap->pdev_dev,
4838				"unable to load firmware image %s, error %d\n",
4839				fw_info->fw_mod_name, ret);
4840		} else {
4841			fw_data = fw->data;
4842			fw_size = fw->size;
4843		}
4844
4845		/* upgrade FW logic */
4846		ret = t4_prep_fw(adap, fw_info, fw_data, fw_size, card_fw,
4847				 state, &reset);
4848
4849		/* Cleaning up */
4850		release_firmware(fw);
4851		kvfree(card_fw);
4852
4853		if (ret < 0)
4854			goto bye;
4855	}
4856
4857	/* If the firmware is initialized already, emit a simply note to that
4858	 * effect. Otherwise, it's time to try initializing the adapter.
4859	 */
4860	if (state == DEV_STATE_INIT) {
4861		ret = adap_config_hma(adap);
4862		if (ret)
4863			dev_err(adap->pdev_dev,
4864				"HMA configuration failed with error %d\n",
4865				ret);
4866		dev_info(adap->pdev_dev, "Coming up as %s: "\
4867			 "Adapter already initialized\n",
4868			 adap->flags & CXGB4_MASTER_PF ? "MASTER" : "SLAVE");
4869	} else {
4870		dev_info(adap->pdev_dev, "Coming up as MASTER: "\
4871			 "Initializing adapter\n");
4872
4873		/* Find out whether we're dealing with a version of the
4874		 * firmware which has configuration file support.
4875		 */
4876		params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4877			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
4878		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
4879				      params, val);
4880
4881		/* If the firmware doesn't support Configuration Files,
4882		 * return an error.
4883		 */
4884		if (ret < 0) {
4885			dev_err(adap->pdev_dev, "firmware doesn't support "
4886				"Firmware Configuration Files\n");
4887			goto bye;
4888		}
4889
4890		/* The firmware provides us with a memory buffer where we can
4891		 * load a Configuration File from the host if we want to
4892		 * override the Configuration File in flash.
4893		 */
4894		ret = adap_init0_config(adap, reset);
4895		if (ret == -ENOENT) {
4896			dev_err(adap->pdev_dev, "no Configuration File "
4897				"present on adapter.\n");
4898			goto bye;
4899		}
4900		if (ret < 0) {
4901			dev_err(adap->pdev_dev, "could not initialize "
4902				"adapter, error %d\n", -ret);
4903			goto bye;
4904		}
4905	}
4906
4907	/* Now that we've successfully configured and initialized the adapter
4908	 * (or found it already initialized), we can ask the Firmware what
4909	 * resources it has provisioned for us.
4910	 */
4911	ret = t4_get_pfres(adap);
4912	if (ret) {
4913		dev_err(adap->pdev_dev,
4914			"Unable to retrieve resource provisioning information\n");
4915		goto bye;
4916	}
4917
4918	/* Grab VPD parameters.  This should be done after we establish a
4919	 * connection to the firmware since some of the VPD parameters
4920	 * (notably the Core Clock frequency) are retrieved via requests to
4921	 * the firmware.  On the other hand, we need these fairly early on
4922	 * so we do this right after getting ahold of the firmware.
4923	 *
4924	 * We need to do this after initializing the adapter because someone
4925	 * could have FLASHed a new VPD which won't be read by the firmware
4926	 * until we do the RESET ...
4927	 */
4928	if (!vpd_skip) {
4929		ret = t4_get_vpd_params(adap, &adap->params.vpd);
4930		if (ret < 0)
4931			goto bye;
4932	}
4933
4934	/* Find out what ports are available to us.  Note that we need to do
4935	 * this before calling adap_init0_no_config() since it needs nports
4936	 * and portvec ...
4937	 */
4938	v =
4939	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4940	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
4941	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
4942	if (ret < 0)
4943		goto bye;
4944
4945	adap->params.nports = hweight32(port_vec);
4946	adap->params.portvec = port_vec;
4947
4948	/* Give the SGE code a chance to pull in anything that it needs ...
4949	 * Note that this must be called after we retrieve our VPD parameters
4950	 * in order to know how to convert core ticks to seconds, etc.
4951	 */
4952	ret = t4_sge_init(adap);
4953	if (ret < 0)
4954		goto bye;
4955
4956	/* Grab the SGE Doorbell Queue Timer values.  If successful, that
4957	 * indicates that the Firmware and Hardware support this.
4958	 */
4959	params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
4960		    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK));
4961	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
4962			      1, params, val);
4963
4964	if (!ret) {
4965		adap->sge.dbqtimer_tick = val[0];
4966		ret = t4_read_sge_dbqtimers(adap,
4967					    ARRAY_SIZE(adap->sge.dbqtimer_val),
4968					    adap->sge.dbqtimer_val);
4969	}
4970
4971	if (!ret)
4972		adap->flags |= CXGB4_SGE_DBQ_TIMER;
4973
4974	if (is_bypass_device(adap->pdev->device))
4975		adap->params.bypass = 1;
4976
4977	/*
4978	 * Grab some of our basic fundamental operating parameters.
4979	 */
4980	params[0] = FW_PARAM_PFVF(EQ_START);
4981	params[1] = FW_PARAM_PFVF(L2T_START);
4982	params[2] = FW_PARAM_PFVF(L2T_END);
4983	params[3] = FW_PARAM_PFVF(FILTER_START);
4984	params[4] = FW_PARAM_PFVF(FILTER_END);
4985	params[5] = FW_PARAM_PFVF(IQFLINT_START);
4986	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val);
4987	if (ret < 0)
4988		goto bye;
4989	adap->sge.egr_start = val[0];
4990	adap->l2t_start = val[1];
4991	adap->l2t_end = val[2];
4992	adap->tids.ftid_base = val[3];
4993	adap->tids.nftids = val[4] - val[3] + 1;
4994	adap->sge.ingr_start = val[5];
4995
4996	if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
4997		params[0] = FW_PARAM_PFVF(HPFILTER_START);
4998		params[1] = FW_PARAM_PFVF(HPFILTER_END);
4999		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5000				      params, val);
5001		if (ret < 0)
5002			goto bye;
5003
5004		adap->tids.hpftid_base = val[0];
5005		adap->tids.nhpftids = val[1] - val[0] + 1;
5006
5007		/* Read the raw mps entries. In T6, the last 2 tcam entries
5008		 * are reserved for raw mac addresses (rawf = 2, one per port).
5009		 */
5010		params[0] = FW_PARAM_PFVF(RAWF_START);
5011		params[1] = FW_PARAM_PFVF(RAWF_END);
5012		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5013				      params, val);
5014		if (ret == 0) {
5015			adap->rawf_start = val[0];
5016			adap->rawf_cnt = val[1] - val[0] + 1;
5017		}
5018
5019		adap->tids.tid_base =
5020			t4_read_reg(adap, LE_DB_ACTIVE_TABLE_START_INDEX_A);
5021	}
5022
5023	/* qids (ingress/egress) returned from firmware can be anywhere
5024	 * in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END.
5025	 * Hence driver needs to allocate memory for this range to
5026	 * store the queue info. Get the highest IQFLINT/EQ index returned
5027	 * in FW_EQ_*_CMD.alloc command.
5028	 */
5029	params[0] = FW_PARAM_PFVF(EQ_END);
5030	params[1] = FW_PARAM_PFVF(IQFLINT_END);
5031	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
5032	if (ret < 0)
5033		goto bye;
5034	adap->sge.egr_sz = val[0] - adap->sge.egr_start + 1;
5035	adap->sge.ingr_sz = val[1] - adap->sge.ingr_start + 1;
5036
5037	adap->sge.egr_map = kcalloc(adap->sge.egr_sz,
5038				    sizeof(*adap->sge.egr_map), GFP_KERNEL);
5039	if (!adap->sge.egr_map) {
5040		ret = -ENOMEM;
5041		goto bye;
5042	}
5043
5044	adap->sge.ingr_map = kcalloc(adap->sge.ingr_sz,
5045				     sizeof(*adap->sge.ingr_map), GFP_KERNEL);
5046	if (!adap->sge.ingr_map) {
5047		ret = -ENOMEM;
5048		goto bye;
5049	}
5050
5051	/* Allocate the memory for the vaious egress queue bitmaps
5052	 * ie starving_fl, txq_maperr and blocked_fl.
5053	 */
5054	adap->sge.starving_fl =	kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
5055					sizeof(long), GFP_KERNEL);
5056	if (!adap->sge.starving_fl) {
5057		ret = -ENOMEM;
5058		goto bye;
5059	}
5060
5061	adap->sge.txq_maperr = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
5062				       sizeof(long), GFP_KERNEL);
5063	if (!adap->sge.txq_maperr) {
5064		ret = -ENOMEM;
5065		goto bye;
5066	}
5067
5068#ifdef CONFIG_DEBUG_FS
5069	adap->sge.blocked_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
5070				       sizeof(long), GFP_KERNEL);
5071	if (!adap->sge.blocked_fl) {
5072		ret = -ENOMEM;
5073		goto bye;
5074	}
5075	bitmap_zero(adap->sge.blocked_fl, adap->sge.egr_sz);
5076#endif
5077
5078	params[0] = FW_PARAM_PFVF(CLIP_START);
5079	params[1] = FW_PARAM_PFVF(CLIP_END);
5080	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
5081	if (ret < 0)
5082		goto bye;
5083	adap->clipt_start = val[0];
5084	adap->clipt_end = val[1];
5085
5086	/* Get the supported number of traffic classes */
5087	params[0] = FW_PARAM_DEV(NUM_TM_CLASS);
5088	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params, val);
5089	if (ret < 0) {
5090		/* We couldn't retrieve the number of Traffic Classes
5091		 * supported by the hardware/firmware. So we hard
5092		 * code it here.
5093		 */
5094		adap->params.nsched_cls = is_t4(adap->params.chip) ? 15 : 16;
5095	} else {
5096		adap->params.nsched_cls = val[0];
5097	}
5098
5099	/* query params related to active filter region */
5100	params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START);
5101	params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END);
5102	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
5103	/* If Active filter size is set we enable establishing
5104	 * offload connection through firmware work request
5105	 */
5106	if ((val[0] != val[1]) && (ret >= 0)) {
5107		adap->flags |= CXGB4_FW_OFLD_CONN;
5108		adap->tids.aftid_base = val[0];
5109		adap->tids.aftid_end = val[1];
5110	}
5111
5112	/* If we're running on newer firmware, let it know that we're
5113	 * prepared to deal with encapsulated CPL messages.  Older
5114	 * firmware won't understand this and we'll just get
5115	 * unencapsulated messages ...
5116	 */
5117	params[0] = FW_PARAM_PFVF(CPLFW4MSG_ENCAP);
5118	val[0] = 1;
5119	(void)t4_set_params(adap, adap->mbox, adap->pf, 0, 1, params, val);
5120
5121	/*
5122	 * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL
5123	 * capability.  Earlier versions of the firmware didn't have the
5124	 * ULPTX_MEMWRITE_DSGL so we'll interpret a query failure as no
5125	 * permission to use ULPTX MEMWRITE DSGL.
5126	 */
5127	if (is_t4(adap->params.chip)) {
5128		adap->params.ulptx_memwrite_dsgl = false;
5129	} else {
5130		params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL);
5131		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5132				      1, params, val);
5133		adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0);
5134	}
5135
5136	/* See if FW supports FW_RI_FR_NSMR_TPTE_WR work request */
5137	params[0] = FW_PARAM_DEV(RI_FR_NSMR_TPTE_WR);
5138	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5139			      1, params, val);
5140	adap->params.fr_nsmr_tpte_wr_support = (ret == 0 && val[0] != 0);
5141
5142	/* See if FW supports FW_FILTER2 work request */
5143	if (is_t4(adap->params.chip)) {
5144		adap->params.filter2_wr_support = 0;
5145	} else {
5146		params[0] = FW_PARAM_DEV(FILTER2_WR);
5147		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5148				      1, params, val);
5149		adap->params.filter2_wr_support = (ret == 0 && val[0] != 0);
5150	}
5151
5152	/* Check if FW supports returning vin and smt index.
5153	 * If this is not supported, driver will interpret
5154	 * these values from viid.
5155	 */
5156	params[0] = FW_PARAM_DEV(OPAQUE_VIID_SMT_EXTN);
5157	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5158			      1, params, val);
5159	adap->params.viid_smt_extn_support = (ret == 0 && val[0] != 0);
5160
5161	/*
5162	 * Get device capabilities so we can determine what resources we need
5163	 * to manage.
5164	 */
5165	memset(&caps_cmd, 0, sizeof(caps_cmd));
5166	caps_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
5167				     FW_CMD_REQUEST_F | FW_CMD_READ_F);
5168	caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
5169	ret = t4_wr_mbox(adap, adap->mbox, &caps_cmd, sizeof(caps_cmd),
5170			 &caps_cmd);
5171	if (ret < 0)
5172		goto bye;
5173
5174	/* hash filter has some mandatory register settings to be tested and for
5175	 * that it needs to test whether offload is enabled or not, hence
5176	 * checking and setting it here.
5177	 */
5178	if (caps_cmd.ofldcaps)
5179		adap->params.offload = 1;
5180
5181	if (caps_cmd.ofldcaps ||
5182	    (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER)) ||
5183	    (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_ETHOFLD))) {
5184		/* query offload-related parameters */
5185		params[0] = FW_PARAM_DEV(NTID);
5186		params[1] = FW_PARAM_PFVF(SERVER_START);
5187		params[2] = FW_PARAM_PFVF(SERVER_END);
5188		params[3] = FW_PARAM_PFVF(TDDP_START);
5189		params[4] = FW_PARAM_PFVF(TDDP_END);
5190		params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ);
5191		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
5192				      params, val);
5193		if (ret < 0)
5194			goto bye;
5195		adap->tids.ntids = val[0];
5196		adap->tids.natids = min(adap->tids.ntids / 2, MAX_ATIDS);
5197		adap->tids.stid_base = val[1];
5198		adap->tids.nstids = val[2] - val[1] + 1;
5199		/*
5200		 * Setup server filter region. Divide the available filter
5201		 * region into two parts. Regular filters get 1/3rd and server
5202		 * filters get 2/3rd part. This is only enabled if workarond
5203		 * path is enabled.
5204		 * 1. For regular filters.
5205		 * 2. Server filter: This are special filters which are used
5206		 * to redirect SYN packets to offload queue.
5207		 */
5208		if (adap->flags & CXGB4_FW_OFLD_CONN && !is_bypass(adap)) {
5209			adap->tids.sftid_base = adap->tids.ftid_base +
5210					DIV_ROUND_UP(adap->tids.nftids, 3);
5211			adap->tids.nsftids = adap->tids.nftids -
5212					 DIV_ROUND_UP(adap->tids.nftids, 3);
5213			adap->tids.nftids = adap->tids.sftid_base -
5214						adap->tids.ftid_base;
5215		}
5216		adap->vres.ddp.start = val[3];
5217		adap->vres.ddp.size = val[4] - val[3] + 1;
5218		adap->params.ofldq_wr_cred = val[5];
5219
5220		if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER)) {
5221			init_hash_filter(adap);
5222		} else {
5223			adap->num_ofld_uld += 1;
5224		}
5225
5226		if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_ETHOFLD)) {
5227			params[0] = FW_PARAM_PFVF(ETHOFLD_START);
5228			params[1] = FW_PARAM_PFVF(ETHOFLD_END);
5229			ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5230					      params, val);
5231			if (!ret) {
5232				adap->tids.eotid_base = val[0];
5233				adap->tids.neotids = min_t(u32, MAX_ATIDS,
5234							   val[1] - val[0] + 1);
5235				adap->params.ethofld = 1;
5236			}
5237		}
5238	}
5239	if (caps_cmd.rdmacaps) {
5240		params[0] = FW_PARAM_PFVF(STAG_START);
5241		params[1] = FW_PARAM_PFVF(STAG_END);
5242		params[2] = FW_PARAM_PFVF(RQ_START);
5243		params[3] = FW_PARAM_PFVF(RQ_END);
5244		params[4] = FW_PARAM_PFVF(PBL_START);
5245		params[5] = FW_PARAM_PFVF(PBL_END);
5246		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
5247				      params, val);
5248		if (ret < 0)
5249			goto bye;
5250		adap->vres.stag.start = val[0];
5251		adap->vres.stag.size = val[1] - val[0] + 1;
5252		adap->vres.rq.start = val[2];
5253		adap->vres.rq.size = val[3] - val[2] + 1;
5254		adap->vres.pbl.start = val[4];
5255		adap->vres.pbl.size = val[5] - val[4] + 1;
5256
5257		params[0] = FW_PARAM_PFVF(SRQ_START);
5258		params[1] = FW_PARAM_PFVF(SRQ_END);
5259		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5260				      params, val);
5261		if (!ret) {
5262			adap->vres.srq.start = val[0];
5263			adap->vres.srq.size = val[1] - val[0] + 1;
5264		}
5265		if (adap->vres.srq.size) {
5266			adap->srq = t4_init_srq(adap->vres.srq.size);
5267			if (!adap->srq)
5268				dev_warn(&adap->pdev->dev, "could not allocate SRQ, continuing\n");
5269		}
5270
5271		params[0] = FW_PARAM_PFVF(SQRQ_START);
5272		params[1] = FW_PARAM_PFVF(SQRQ_END);
5273		params[2] = FW_PARAM_PFVF(CQ_START);
5274		params[3] = FW_PARAM_PFVF(CQ_END);
5275		params[4] = FW_PARAM_PFVF(OCQ_START);
5276		params[5] = FW_PARAM_PFVF(OCQ_END);
5277		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params,
5278				      val);
5279		if (ret < 0)
5280			goto bye;
5281		adap->vres.qp.start = val[0];
5282		adap->vres.qp.size = val[1] - val[0] + 1;
5283		adap->vres.cq.start = val[2];
5284		adap->vres.cq.size = val[3] - val[2] + 1;
5285		adap->vres.ocq.start = val[4];
5286		adap->vres.ocq.size = val[5] - val[4] + 1;
5287
5288		params[0] = FW_PARAM_DEV(MAXORDIRD_QP);
5289		params[1] = FW_PARAM_DEV(MAXIRD_ADAPTER);
5290		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params,
5291				      val);
5292		if (ret < 0) {
5293			adap->params.max_ordird_qp = 8;
5294			adap->params.max_ird_adapter = 32 * adap->tids.ntids;
5295			ret = 0;
5296		} else {
5297			adap->params.max_ordird_qp = val[0];
5298			adap->params.max_ird_adapter = val[1];
5299		}
5300		dev_info(adap->pdev_dev,
5301			 "max_ordird_qp %d max_ird_adapter %d\n",
5302			 adap->params.max_ordird_qp,
5303			 adap->params.max_ird_adapter);
5304
5305		/* Enable write_with_immediate if FW supports it */
5306		params[0] = FW_PARAM_DEV(RDMA_WRITE_WITH_IMM);
5307		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params,
5308				      val);
5309		adap->params.write_w_imm_support = (ret == 0 && val[0] != 0);
5310
5311		/* Enable write_cmpl if FW supports it */
5312		params[0] = FW_PARAM_DEV(RI_WRITE_CMPL_WR);
5313		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params,
5314				      val);
5315		adap->params.write_cmpl_support = (ret == 0 && val[0] != 0);
5316		adap->num_ofld_uld += 2;
5317	}
5318	if (caps_cmd.iscsicaps) {
5319		params[0] = FW_PARAM_PFVF(ISCSI_START);
5320		params[1] = FW_PARAM_PFVF(ISCSI_END);
5321		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5322				      params, val);
5323		if (ret < 0)
5324			goto bye;
5325		adap->vres.iscsi.start = val[0];
5326		adap->vres.iscsi.size = val[1] - val[0] + 1;
5327		if (is_t6(adap->params.chip)) {
5328			params[0] = FW_PARAM_PFVF(PPOD_EDRAM_START);
5329			params[1] = FW_PARAM_PFVF(PPOD_EDRAM_END);
5330			ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
5331					      params, val);
5332			if (!ret) {
5333				adap->vres.ppod_edram.start = val[0];
5334				adap->vres.ppod_edram.size =
5335					val[1] - val[0] + 1;
5336
5337				dev_info(adap->pdev_dev,
5338					 "ppod edram start 0x%x end 0x%x size 0x%x\n",
5339					 val[0], val[1],
5340					 adap->vres.ppod_edram.size);
5341			}
5342		}
5343		/* LIO target and cxgb4i initiaitor */
5344		adap->num_ofld_uld += 2;
5345	}
5346	if (caps_cmd.cryptocaps) {
5347		if (ntohs(caps_cmd.cryptocaps) &
5348		    FW_CAPS_CONFIG_CRYPTO_LOOKASIDE) {
5349			params[0] = FW_PARAM_PFVF(NCRYPTO_LOOKASIDE);
5350			ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5351					      2, params, val);
5352			if (ret < 0) {
5353				if (ret != -EINVAL)
5354					goto bye;
5355			} else {
5356				adap->vres.ncrypto_fc = val[0];
5357			}
5358			adap->num_ofld_uld += 1;
5359		}
5360		if (ntohs(caps_cmd.cryptocaps) &
5361		    FW_CAPS_CONFIG_TLS_INLINE) {
5362			params[0] = FW_PARAM_PFVF(TLS_START);
5363			params[1] = FW_PARAM_PFVF(TLS_END);
5364			ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
5365					      2, params, val);
5366			if (ret < 0)
5367				goto bye;
5368			adap->vres.key.start = val[0];
5369			adap->vres.key.size = val[1] - val[0] + 1;
5370			adap->num_uld += 1;
5371		}
5372		adap->params.crypto = ntohs(caps_cmd.cryptocaps);
5373	}
5374
5375	/* The MTU/MSS Table is initialized by now, so load their values.  If
5376	 * we're initializing the adapter, then we'll make any modifications
5377	 * we want to the MTU/MSS Table and also initialize the congestion
5378	 * parameters.
5379	 */
5380	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
5381	if (state != DEV_STATE_INIT) {
5382		int i;
5383
5384		/* The default MTU Table contains values 1492 and 1500.
5385		 * However, for TCP, it's better to have two values which are
5386		 * a multiple of 8 +/- 4 bytes apart near this popular MTU.
5387		 * This allows us to have a TCP Data Payload which is a
5388		 * multiple of 8 regardless of what combination of TCP Options
5389		 * are in use (always a multiple of 4 bytes) which is
5390		 * important for performance reasons.  For instance, if no
5391		 * options are in use, then we have a 20-byte IP header and a
5392		 * 20-byte TCP header.  In this case, a 1500-byte MSS would
5393		 * result in a TCP Data Payload of 1500 - 40 == 1460 bytes
5394		 * which is not a multiple of 8.  So using an MSS of 1488 in
5395		 * this case results in a TCP Data Payload of 1448 bytes which
5396		 * is a multiple of 8.  On the other hand, if 12-byte TCP Time
5397		 * Stamps have been negotiated, then an MTU of 1500 bytes
5398		 * results in a TCP Data Payload of 1448 bytes which, as
5399		 * above, is a multiple of 8 bytes ...
5400		 */
5401		for (i = 0; i < NMTUS; i++)
5402			if (adap->params.mtus[i] == 1492) {
5403				adap->params.mtus[i] = 1488;
5404				break;
5405			}
5406
5407		t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
5408			     adap->params.b_wnd);
5409	}
5410	t4_init_sge_params(adap);
5411	adap->flags |= CXGB4_FW_OK;
5412	t4_init_tp_params(adap, true);
5413	return 0;
5414
5415	/*
5416	 * Something bad happened.  If a command timed out or failed with EIO
5417	 * FW does not operate within its spec or something catastrophic
5418	 * happened to HW/FW, stop issuing commands.
5419	 */
5420bye:
5421	adap_free_hma_mem(adap);
5422	kfree(adap->sge.egr_map);
5423	kfree(adap->sge.ingr_map);
5424	kfree(adap->sge.starving_fl);
5425	kfree(adap->sge.txq_maperr);
5426#ifdef CONFIG_DEBUG_FS
5427	kfree(adap->sge.blocked_fl);
5428#endif
5429	if (ret != -ETIMEDOUT && ret != -EIO)
5430		t4_fw_bye(adap, adap->mbox);
5431	return ret;
5432}
5433
5434/* EEH callbacks */
5435
5436static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
5437					 pci_channel_state_t state)
5438{
5439	int i;
5440	struct adapter *adap = pci_get_drvdata(pdev);
5441
5442	if (!adap)
5443		goto out;
5444
5445	rtnl_lock();
5446	adap->flags &= ~CXGB4_FW_OK;
5447	notify_ulds(adap, CXGB4_STATE_START_RECOVERY);
5448	spin_lock(&adap->stats_lock);
5449	for_each_port(adap, i) {
5450		struct net_device *dev = adap->port[i];
5451		if (dev) {
5452			netif_device_detach(dev);
5453			netif_carrier_off(dev);
5454		}
5455	}
5456	spin_unlock(&adap->stats_lock);
5457	disable_interrupts(adap);
5458	if (adap->flags & CXGB4_FULL_INIT_DONE)
5459		cxgb_down(adap);
5460	rtnl_unlock();
5461	if ((adap->flags & CXGB4_DEV_ENABLED)) {
5462		pci_disable_device(pdev);
5463		adap->flags &= ~CXGB4_DEV_ENABLED;
5464	}
5465out:	return state == pci_channel_io_perm_failure ?
5466		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
5467}
5468
5469static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
5470{
5471	int i, ret;
5472	struct fw_caps_config_cmd c;
5473	struct adapter *adap = pci_get_drvdata(pdev);
5474
5475	if (!adap) {
5476		pci_restore_state(pdev);
5477		pci_save_state(pdev);
5478		return PCI_ERS_RESULT_RECOVERED;
5479	}
5480
5481	if (!(adap->flags & CXGB4_DEV_ENABLED)) {
5482		if (pci_enable_device(pdev)) {
5483			dev_err(&pdev->dev, "Cannot reenable PCI "
5484					    "device after reset\n");
5485			return PCI_ERS_RESULT_DISCONNECT;
5486		}
5487		adap->flags |= CXGB4_DEV_ENABLED;
5488	}
5489
5490	pci_set_master(pdev);
5491	pci_restore_state(pdev);
5492	pci_save_state(pdev);
5493
5494	if (t4_wait_dev_ready(adap->regs) < 0)
5495		return PCI_ERS_RESULT_DISCONNECT;
5496	if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0)
5497		return PCI_ERS_RESULT_DISCONNECT;
5498	adap->flags |= CXGB4_FW_OK;
5499	if (adap_init1(adap, &c))
5500		return PCI_ERS_RESULT_DISCONNECT;
5501
5502	for_each_port(adap, i) {
5503		struct port_info *pi = adap2pinfo(adap, i);
5504		u8 vivld = 0, vin = 0;
5505
5506		ret = t4_alloc_vi(adap, adap->mbox, pi->tx_chan, adap->pf, 0, 1,
5507				  NULL, NULL, &vivld, &vin);
5508		if (ret < 0)
5509			return PCI_ERS_RESULT_DISCONNECT;
5510		pi->viid = ret;
5511		pi->xact_addr_filt = -1;
5512		/* If fw supports returning the VIN as part of FW_VI_CMD,
5513		 * save the returned values.
5514		 */
5515		if (adap->params.viid_smt_extn_support) {
5516			pi->vivld = vivld;
5517			pi->vin = vin;
5518		} else {
5519			/* Retrieve the values from VIID */
5520			pi->vivld = FW_VIID_VIVLD_G(pi->viid);
5521			pi->vin = FW_VIID_VIN_G(pi->viid);
5522		}
5523	}
5524
5525	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
5526		     adap->params.b_wnd);
5527	setup_memwin(adap);
5528	if (cxgb_up(adap))
5529		return PCI_ERS_RESULT_DISCONNECT;
5530	return PCI_ERS_RESULT_RECOVERED;
5531}
5532
5533static void eeh_resume(struct pci_dev *pdev)
5534{
5535	int i;
5536	struct adapter *adap = pci_get_drvdata(pdev);
5537
5538	if (!adap)
5539		return;
5540
5541	rtnl_lock();
5542	for_each_port(adap, i) {
5543		struct net_device *dev = adap->port[i];
5544		if (dev) {
5545			if (netif_running(dev)) {
5546				link_start(dev);
5547				cxgb_set_rxmode(dev);
5548			}
5549			netif_device_attach(dev);
5550		}
5551	}
5552	rtnl_unlock();
5553}
5554
5555static void eeh_reset_prepare(struct pci_dev *pdev)
5556{
5557	struct adapter *adapter = pci_get_drvdata(pdev);
5558	int i;
5559
5560	if (adapter->pf != 4)
5561		return;
5562
5563	adapter->flags &= ~CXGB4_FW_OK;
5564
5565	notify_ulds(adapter, CXGB4_STATE_DOWN);
5566
5567	for_each_port(adapter, i)
5568		if (adapter->port[i]->reg_state == NETREG_REGISTERED)
5569			cxgb_close(adapter->port[i]);
5570
5571	disable_interrupts(adapter);
5572	cxgb4_free_mps_ref_entries(adapter);
5573
5574	adap_free_hma_mem(adapter);
5575
5576	if (adapter->flags & CXGB4_FULL_INIT_DONE)
5577		cxgb_down(adapter);
5578}
5579
5580static void eeh_reset_done(struct pci_dev *pdev)
5581{
5582	struct adapter *adapter = pci_get_drvdata(pdev);
5583	int err, i;
5584
5585	if (adapter->pf != 4)
5586		return;
5587
5588	err = t4_wait_dev_ready(adapter->regs);
5589	if (err < 0) {
5590		dev_err(adapter->pdev_dev,
5591			"Device not ready, err %d", err);
5592		return;
5593	}
5594
5595	setup_memwin(adapter);
5596
5597	err = adap_init0(adapter, 1);
5598	if (err) {
5599		dev_err(adapter->pdev_dev,
5600			"Adapter init failed, err %d", err);
5601		return;
5602	}
5603
5604	setup_memwin_rdma(adapter);
5605
5606	if (adapter->flags & CXGB4_FW_OK) {
5607		err = t4_port_init(adapter, adapter->pf, adapter->pf, 0);
5608		if (err) {
5609			dev_err(adapter->pdev_dev,
5610				"Port init failed, err %d", err);
5611			return;
5612		}
5613	}
5614
5615	err = cfg_queues(adapter);
5616	if (err) {
5617		dev_err(adapter->pdev_dev,
5618			"Config queues failed, err %d", err);
5619		return;
5620	}
5621
5622	cxgb4_init_mps_ref_entries(adapter);
5623
5624	err = setup_fw_sge_queues(adapter);
5625	if (err) {
5626		dev_err(adapter->pdev_dev,
5627			"FW sge queue allocation failed, err %d", err);
5628		return;
5629	}
5630
5631	for_each_port(adapter, i)
5632		if (adapter->port[i]->reg_state == NETREG_REGISTERED)
5633			cxgb_open(adapter->port[i]);
5634}
5635
5636static const struct pci_error_handlers cxgb4_eeh = {
5637	.error_detected = eeh_err_detected,
5638	.slot_reset     = eeh_slot_reset,
5639	.resume         = eeh_resume,
5640	.reset_prepare  = eeh_reset_prepare,
5641	.reset_done     = eeh_reset_done,
5642};
5643
5644/* Return true if the Link Configuration supports "High Speeds" (those greater
5645 * than 1Gb/s).
5646 */
5647static inline bool is_x_10g_port(const struct link_config *lc)
5648{
5649	unsigned int speeds, high_speeds;
5650
5651	speeds = FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_G(lc->pcaps));
5652	high_speeds = speeds &
5653			~(FW_PORT_CAP32_SPEED_100M | FW_PORT_CAP32_SPEED_1G);
5654
5655	return high_speeds != 0;
5656}
5657
5658/* Perform default configuration of DMA queues depending on the number and type
5659 * of ports we found and the number of available CPUs.  Most settings can be
5660 * modified by the admin prior to actual use.
5661 */
5662static int cfg_queues(struct adapter *adap)
5663{
5664	u32 avail_qsets, avail_eth_qsets, avail_uld_qsets;
5665	u32 ncpus = num_online_cpus();
5666	u32 niqflint, neq, num_ulds;
5667	struct sge *s = &adap->sge;
5668	u32 i, n10g = 0, qidx = 0;
5669	u32 q10g = 0, q1g;
5670
5671	/* Reduce memory usage in kdump environment, disable all offload. */
5672	if (is_kdump_kernel() || (is_uld(adap) && t4_uld_mem_alloc(adap))) {
5673		adap->params.offload = 0;
5674		adap->params.crypto = 0;
5675		adap->params.ethofld = 0;
5676	}
5677
5678	/* Calculate the number of Ethernet Queue Sets available based on
5679	 * resources provisioned for us.  We always have an Asynchronous
5680	 * Firmware Event Ingress Queue.  If we're operating in MSI or Legacy
5681	 * IRQ Pin Interrupt mode, then we'll also have a Forwarded Interrupt
5682	 * Ingress Queue.  Meanwhile, we need two Egress Queues for each
5683	 * Queue Set: one for the Free List and one for the Ethernet TX Queue.
5684	 *
5685	 * Note that we should also take into account all of the various
5686	 * Offload Queues.  But, in any situation where we're operating in
5687	 * a Resource Constrained Provisioning environment, doing any Offload
5688	 * at all is problematic ...
5689	 */
5690	niqflint = adap->params.pfres.niqflint - 1;
5691	if (!(adap->flags & CXGB4_USING_MSIX))
5692		niqflint--;
5693	neq = adap->params.pfres.neq / 2;
5694	avail_qsets = min(niqflint, neq);
5695
5696	if (avail_qsets < adap->params.nports) {
5697		dev_err(adap->pdev_dev, "avail_eth_qsets=%d < nports=%d\n",
5698			avail_qsets, adap->params.nports);
5699		return -ENOMEM;
5700	}
5701
5702	/* Count the number of 10Gb/s or better ports */
5703	for_each_port(adap, i)
5704		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
5705
5706	avail_eth_qsets = min_t(u32, avail_qsets, MAX_ETH_QSETS);
5707
5708	/* We default to 1 queue per non-10G port and up to # of cores queues
5709	 * per 10G port.
5710	 */
5711	if (n10g)
5712		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
5713
5714#ifdef CONFIG_CHELSIO_T4_DCB
5715	/* For Data Center Bridging support we need to be able to support up
5716	 * to 8 Traffic Priorities; each of which will be assigned to its
5717	 * own TX Queue in order to prevent Head-Of-Line Blocking.
5718	 */
5719	q1g = 8;
5720	if (adap->params.nports * 8 > avail_eth_qsets) {
5721		dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n",
5722			avail_eth_qsets, adap->params.nports * 8);
5723		return -ENOMEM;
5724	}
5725
5726	if (adap->params.nports * ncpus < avail_eth_qsets)
5727		q10g = max(8U, ncpus);
5728	else
5729		q10g = max(8U, q10g);
5730
5731	while ((q10g * n10g) >
5732	       (avail_eth_qsets - (adap->params.nports - n10g) * q1g))
5733		q10g--;
5734
5735#else /* !CONFIG_CHELSIO_T4_DCB */
5736	q1g = 1;
5737	q10g = min(q10g, ncpus);
5738#endif /* !CONFIG_CHELSIO_T4_DCB */
5739	if (is_kdump_kernel()) {
5740		q10g = 1;
5741		q1g = 1;
5742	}
5743
5744	for_each_port(adap, i) {
5745		struct port_info *pi = adap2pinfo(adap, i);
5746
5747		pi->first_qset = qidx;
5748		pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : q1g;
5749		qidx += pi->nqsets;
5750	}
5751
5752	s->ethqsets = qidx;
5753	s->max_ethqsets = qidx;   /* MSI-X may lower it later */
5754	avail_qsets -= qidx;
5755
5756	if (is_uld(adap)) {
5757		/* For offload we use 1 queue/channel if all ports are up to 1G,
5758		 * otherwise we divide all available queues amongst the channels
5759		 * capped by the number of available cores.
5760		 */
5761		num_ulds = adap->num_uld + adap->num_ofld_uld;
5762		i = min_t(u32, MAX_OFLD_QSETS, ncpus);
5763		avail_uld_qsets = roundup(i, adap->params.nports);
5764		if (avail_qsets < num_ulds * adap->params.nports) {
5765			adap->params.offload = 0;
5766			adap->params.crypto = 0;
5767			s->ofldqsets = 0;
5768		} else if (avail_qsets < num_ulds * avail_uld_qsets || !n10g) {
5769			s->ofldqsets = adap->params.nports;
5770		} else {
5771			s->ofldqsets = avail_uld_qsets;
5772		}
5773
5774		avail_qsets -= num_ulds * s->ofldqsets;
5775	}
5776
5777	/* ETHOFLD Queues used for QoS offload should follow same
5778	 * allocation scheme as normal Ethernet Queues.
5779	 */
5780	if (is_ethofld(adap)) {
5781		if (avail_qsets < s->max_ethqsets) {
5782			adap->params.ethofld = 0;
5783			s->eoqsets = 0;
5784		} else {
5785			s->eoqsets = s->max_ethqsets;
5786		}
5787		avail_qsets -= s->eoqsets;
5788	}
5789
5790	/* Mirror queues must follow same scheme as normal Ethernet
5791	 * Queues, when there are enough queues available. Otherwise,
5792	 * allocate at least 1 queue per port. If even 1 queue is not
5793	 * available, then disable mirror queues support.
5794	 */
5795	if (avail_qsets >= s->max_ethqsets)
5796		s->mirrorqsets = s->max_ethqsets;
5797	else if (avail_qsets >= adap->params.nports)
5798		s->mirrorqsets = adap->params.nports;
5799	else
5800		s->mirrorqsets = 0;
5801	avail_qsets -= s->mirrorqsets;
5802
5803	for (i = 0; i < ARRAY_SIZE(s->ethrxq); i++) {
5804		struct sge_eth_rxq *r = &s->ethrxq[i];
5805
5806		init_rspq(adap, &r->rspq, 5, 10, 1024, 64);
5807		r->fl.size = 72;
5808	}
5809
5810	for (i = 0; i < ARRAY_SIZE(s->ethtxq); i++)
5811		s->ethtxq[i].q.size = 1024;
5812
5813	for (i = 0; i < ARRAY_SIZE(s->ctrlq); i++)
5814		s->ctrlq[i].q.size = 512;
5815
5816	if (!is_t4(adap->params.chip))
5817		s->ptptxq.q.size = 8;
5818
5819	init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
5820	init_rspq(adap, &s->intrq, 0, 1, 512, 64);
5821
5822	return 0;
5823}
5824
5825/*
5826 * Reduce the number of Ethernet queues across all ports to at most n.
5827 * n provides at least one queue per port.
5828 */
5829static void reduce_ethqs(struct adapter *adap, int n)
5830{
5831	int i;
5832	struct port_info *pi;
5833
5834	while (n < adap->sge.ethqsets)
5835		for_each_port(adap, i) {
5836			pi = adap2pinfo(adap, i);
5837			if (pi->nqsets > 1) {
5838				pi->nqsets--;
5839				adap->sge.ethqsets--;
5840				if (adap->sge.ethqsets <= n)
5841					break;
5842			}
5843		}
5844
5845	n = 0;
5846	for_each_port(adap, i) {
5847		pi = adap2pinfo(adap, i);
5848		pi->first_qset = n;
5849		n += pi->nqsets;
5850	}
5851}
5852
5853static int alloc_msix_info(struct adapter *adap, u32 num_vec)
5854{
5855	struct msix_info *msix_info;
5856
5857	msix_info = kcalloc(num_vec, sizeof(*msix_info), GFP_KERNEL);
5858	if (!msix_info)
5859		return -ENOMEM;
5860
5861	adap->msix_bmap.msix_bmap = kcalloc(BITS_TO_LONGS(num_vec),
5862					    sizeof(long), GFP_KERNEL);
5863	if (!adap->msix_bmap.msix_bmap) {
5864		kfree(msix_info);
5865		return -ENOMEM;
5866	}
5867
5868	spin_lock_init(&adap->msix_bmap.lock);
5869	adap->msix_bmap.mapsize = num_vec;
5870
5871	adap->msix_info = msix_info;
5872	return 0;
5873}
5874
5875static void free_msix_info(struct adapter *adap)
5876{
5877	kfree(adap->msix_bmap.msix_bmap);
5878	kfree(adap->msix_info);
5879}
5880
5881int cxgb4_get_msix_idx_from_bmap(struct adapter *adap)
5882{
5883	struct msix_bmap *bmap = &adap->msix_bmap;
5884	unsigned int msix_idx;
5885	unsigned long flags;
5886
5887	spin_lock_irqsave(&bmap->lock, flags);
5888	msix_idx = find_first_zero_bit(bmap->msix_bmap, bmap->mapsize);
5889	if (msix_idx < bmap->mapsize) {
5890		__set_bit(msix_idx, bmap->msix_bmap);
5891	} else {
5892		spin_unlock_irqrestore(&bmap->lock, flags);
5893		return -ENOSPC;
5894	}
5895
5896	spin_unlock_irqrestore(&bmap->lock, flags);
5897	return msix_idx;
5898}
5899
5900void cxgb4_free_msix_idx_in_bmap(struct adapter *adap,
5901				 unsigned int msix_idx)
5902{
5903	struct msix_bmap *bmap = &adap->msix_bmap;
5904	unsigned long flags;
5905
5906	spin_lock_irqsave(&bmap->lock, flags);
5907	__clear_bit(msix_idx, bmap->msix_bmap);
5908	spin_unlock_irqrestore(&bmap->lock, flags);
5909}
5910
5911/* 2 MSI-X vectors needed for the FW queue and non-data interrupts */
5912#define EXTRA_VECS 2
5913
5914static int enable_msix(struct adapter *adap)
5915{
5916	u32 eth_need, uld_need = 0, ethofld_need = 0, mirror_need = 0;
5917	u32 ethqsets = 0, ofldqsets = 0, eoqsets = 0, mirrorqsets = 0;
5918	u8 num_uld = 0, nchan = adap->params.nports;
5919	u32 i, want, need, num_vec;
5920	struct sge *s = &adap->sge;
5921	struct msix_entry *entries;
5922	struct port_info *pi;
5923	int allocated, ret;
5924
5925	want = s->max_ethqsets;
5926#ifdef CONFIG_CHELSIO_T4_DCB
5927	/* For Data Center Bridging we need 8 Ethernet TX Priority Queues for
5928	 * each port.
5929	 */
5930	need = 8 * nchan;
5931#else
5932	need = nchan;
5933#endif
5934	eth_need = need;
5935	if (is_uld(adap)) {
5936		num_uld = adap->num_ofld_uld + adap->num_uld;
5937		want += num_uld * s->ofldqsets;
5938		uld_need = num_uld * nchan;
5939		need += uld_need;
5940	}
5941
5942	if (is_ethofld(adap)) {
5943		want += s->eoqsets;
5944		ethofld_need = eth_need;
5945		need += ethofld_need;
5946	}
5947
5948	if (s->mirrorqsets) {
5949		want += s->mirrorqsets;
5950		mirror_need = nchan;
5951		need += mirror_need;
5952	}
5953
5954	want += EXTRA_VECS;
5955	need += EXTRA_VECS;
5956
5957	entries = kmalloc_array(want, sizeof(*entries), GFP_KERNEL);
5958	if (!entries)
5959		return -ENOMEM;
5960
5961	for (i = 0; i < want; i++)
5962		entries[i].entry = i;
5963
5964	allocated = pci_enable_msix_range(adap->pdev, entries, need, want);
5965	if (allocated < 0) {
5966		/* Disable offload and attempt to get vectors for NIC
5967		 * only mode.
5968		 */
5969		want = s->max_ethqsets + EXTRA_VECS;
5970		need = eth_need + EXTRA_VECS;
5971		allocated = pci_enable_msix_range(adap->pdev, entries,
5972						  need, want);
5973		if (allocated < 0) {
5974			dev_info(adap->pdev_dev,
5975				 "Disabling MSI-X due to insufficient MSI-X vectors\n");
5976			ret = allocated;
5977			goto out_free;
5978		}
5979
5980		dev_info(adap->pdev_dev,
5981			 "Disabling offload due to insufficient MSI-X vectors\n");
5982		adap->params.offload = 0;
5983		adap->params.crypto = 0;
5984		adap->params.ethofld = 0;
5985		s->ofldqsets = 0;
5986		s->eoqsets = 0;
5987		s->mirrorqsets = 0;
5988		uld_need = 0;
5989		ethofld_need = 0;
5990		mirror_need = 0;
5991	}
5992
5993	num_vec = allocated;
5994	if (num_vec < want) {
5995		/* Distribute available vectors to the various queue groups.
5996		 * Every group gets its minimum requirement and NIC gets top
5997		 * priority for leftovers.
5998		 */
5999		ethqsets = eth_need;
6000		if (is_uld(adap))
6001			ofldqsets = nchan;
6002		if (is_ethofld(adap))
6003			eoqsets = ethofld_need;
6004		if (s->mirrorqsets)
6005			mirrorqsets = mirror_need;
6006
6007		num_vec -= need;
6008		while (num_vec) {
6009			if (num_vec < eth_need + ethofld_need ||
6010			    ethqsets > s->max_ethqsets)
6011				break;
6012
6013			for_each_port(adap, i) {
6014				pi = adap2pinfo(adap, i);
6015				if (pi->nqsets < 2)
6016					continue;
6017
6018				ethqsets++;
6019				num_vec--;
6020				if (ethofld_need) {
6021					eoqsets++;
6022					num_vec--;
6023				}
6024			}
6025		}
6026
6027		if (is_uld(adap)) {
6028			while (num_vec) {
6029				if (num_vec < uld_need ||
6030				    ofldqsets > s->ofldqsets)
6031					break;
6032
6033				ofldqsets++;
6034				num_vec -= uld_need;
6035			}
6036		}
6037
6038		if (s->mirrorqsets) {
6039			while (num_vec) {
6040				if (num_vec < mirror_need ||
6041				    mirrorqsets > s->mirrorqsets)
6042					break;
6043
6044				mirrorqsets++;
6045				num_vec -= mirror_need;
6046			}
6047		}
6048	} else {
6049		ethqsets = s->max_ethqsets;
6050		if (is_uld(adap))
6051			ofldqsets = s->ofldqsets;
6052		if (is_ethofld(adap))
6053			eoqsets = s->eoqsets;
6054		if (s->mirrorqsets)
6055			mirrorqsets = s->mirrorqsets;
6056	}
6057
6058	if (ethqsets < s->max_ethqsets) {
6059		s->max_ethqsets = ethqsets;
6060		reduce_ethqs(adap, ethqsets);
6061	}
6062
6063	if (is_uld(adap)) {
6064		s->ofldqsets = ofldqsets;
6065		s->nqs_per_uld = s->ofldqsets;
6066	}
6067
6068	if (is_ethofld(adap))
6069		s->eoqsets = eoqsets;
6070
6071	if (s->mirrorqsets) {
6072		s->mirrorqsets = mirrorqsets;
6073		for_each_port(adap, i) {
6074			pi = adap2pinfo(adap, i);
6075			pi->nmirrorqsets = s->mirrorqsets / nchan;
6076			mutex_init(&pi->vi_mirror_mutex);
6077		}
6078	}
6079
6080	/* map for msix */
6081	ret = alloc_msix_info(adap, allocated);
6082	if (ret)
6083		goto out_disable_msix;
6084
6085	for (i = 0; i < allocated; i++) {
6086		adap->msix_info[i].vec = entries[i].vector;
6087		adap->msix_info[i].idx = i;
6088	}
6089
6090	dev_info(adap->pdev_dev,
6091		 "%d MSI-X vectors allocated, nic %d eoqsets %d per uld %d mirrorqsets %d\n",
6092		 allocated, s->max_ethqsets, s->eoqsets, s->nqs_per_uld,
6093		 s->mirrorqsets);
6094
6095	kfree(entries);
6096	return 0;
6097
6098out_disable_msix:
6099	pci_disable_msix(adap->pdev);
6100
6101out_free:
6102	kfree(entries);
6103	return ret;
6104}
6105
6106#undef EXTRA_VECS
6107
6108static int init_rss(struct adapter *adap)
6109{
6110	unsigned int i;
6111	int err;
6112
6113	err = t4_init_rss_mode(adap, adap->mbox);
6114	if (err)
6115		return err;
6116
6117	for_each_port(adap, i) {
6118		struct port_info *pi = adap2pinfo(adap, i);
6119
6120		pi->rss = kcalloc(pi->rss_size, sizeof(u16), GFP_KERNEL);
6121		if (!pi->rss)
6122			return -ENOMEM;
6123	}
6124	return 0;
6125}
6126
6127/* Dump basic information about the adapter */
6128static void print_adapter_info(struct adapter *adapter)
6129{
6130	/* Hardware/Firmware/etc. Version/Revision IDs */
6131	t4_dump_version_info(adapter);
6132
6133	/* Software/Hardware configuration */
6134	dev_info(adapter->pdev_dev, "Configuration: %sNIC %s, %s capable\n",
6135		 is_offload(adapter) ? "R" : "",
6136		 ((adapter->flags & CXGB4_USING_MSIX) ? "MSI-X" :
6137		  (adapter->flags & CXGB4_USING_MSI) ? "MSI" : ""),
6138		 is_offload(adapter) ? "Offload" : "non-Offload");
6139}
6140
6141static void print_port_info(const struct net_device *dev)
6142{
6143	char buf[80];
6144	char *bufp = buf;
6145	const struct port_info *pi = netdev_priv(dev);
6146	const struct adapter *adap = pi->adapter;
6147
6148	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100M)
6149		bufp += sprintf(bufp, "100M/");
6150	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_1G)
6151		bufp += sprintf(bufp, "1G/");
6152	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_10G)
6153		bufp += sprintf(bufp, "10G/");
6154	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_25G)
6155		bufp += sprintf(bufp, "25G/");
6156	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_40G)
6157		bufp += sprintf(bufp, "40G/");
6158	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_50G)
6159		bufp += sprintf(bufp, "50G/");
6160	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100G)
6161		bufp += sprintf(bufp, "100G/");
6162	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_200G)
6163		bufp += sprintf(bufp, "200G/");
6164	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_400G)
6165		bufp += sprintf(bufp, "400G/");
6166	if (bufp != buf)
6167		--bufp;
6168	sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
6169
6170	netdev_info(dev, "%s: Chelsio %s (%s) %s\n",
6171		    dev->name, adap->params.vpd.id, adap->name, buf);
6172}
6173
6174/*
6175 * Free the following resources:
6176 * - memory used for tables
6177 * - MSI/MSI-X
6178 * - net devices
6179 * - resources FW is holding for us
6180 */
6181static void free_some_resources(struct adapter *adapter)
6182{
6183	unsigned int i;
6184
6185	kvfree(adapter->smt);
6186	kvfree(adapter->l2t);
6187	kvfree(adapter->srq);
6188	t4_cleanup_sched(adapter);
6189	kvfree(adapter->tids.tid_tab);
6190	cxgb4_cleanup_tc_matchall(adapter);
6191	cxgb4_cleanup_tc_mqprio(adapter);
6192	cxgb4_cleanup_tc_flower(adapter);
6193	cxgb4_cleanup_tc_u32(adapter);
6194	cxgb4_cleanup_ethtool_filters(adapter);
6195	kfree(adapter->sge.egr_map);
6196	kfree(adapter->sge.ingr_map);
6197	kfree(adapter->sge.starving_fl);
6198	kfree(adapter->sge.txq_maperr);
6199#ifdef CONFIG_DEBUG_FS
6200	kfree(adapter->sge.blocked_fl);
6201#endif
6202	disable_msi(adapter);
6203
6204	for_each_port(adapter, i)
6205		if (adapter->port[i]) {
6206			struct port_info *pi = adap2pinfo(adapter, i);
6207
6208			if (pi->viid != 0)
6209				t4_free_vi(adapter, adapter->mbox, adapter->pf,
6210					   0, pi->viid);
6211			kfree(adap2pinfo(adapter, i)->rss);
6212			free_netdev(adapter->port[i]);
6213		}
6214	if (adapter->flags & CXGB4_FW_OK)
6215		t4_fw_bye(adapter, adapter->pf);
6216}
6217
6218#define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN | \
6219		   NETIF_F_GSO_UDP_L4)
6220#define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
6221		   NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
6222#define SEGMENT_SIZE 128
6223
6224static int t4_get_chip_type(struct adapter *adap, int ver)
6225{
6226	u32 pl_rev = REV_G(t4_read_reg(adap, PL_REV_A));
6227
6228	switch (ver) {
6229	case CHELSIO_T4:
6230		return CHELSIO_CHIP_CODE(CHELSIO_T4, pl_rev);
6231	case CHELSIO_T5:
6232		return CHELSIO_CHIP_CODE(CHELSIO_T5, pl_rev);
6233	case CHELSIO_T6:
6234		return CHELSIO_CHIP_CODE(CHELSIO_T6, pl_rev);
6235	default:
6236		break;
6237	}
6238	return -EINVAL;
6239}
6240
6241#ifdef CONFIG_PCI_IOV
6242static void cxgb4_mgmt_setup(struct net_device *dev)
6243{
6244	dev->type = ARPHRD_NONE;
6245	dev->mtu = 0;
6246	dev->hard_header_len = 0;
6247	dev->addr_len = 0;
6248	dev->tx_queue_len = 0;
6249	dev->flags |= IFF_NOARP;
6250	dev->priv_flags |= IFF_NO_QUEUE;
6251
6252	/* Initialize the device structure. */
6253	dev->netdev_ops = &cxgb4_mgmt_netdev_ops;
6254	dev->ethtool_ops = &cxgb4_mgmt_ethtool_ops;
6255}
6256
6257static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs)
6258{
6259	struct adapter *adap = pci_get_drvdata(pdev);
6260	int err = 0;
6261	int current_vfs = pci_num_vf(pdev);
6262	u32 pcie_fw;
6263
6264	pcie_fw = readl(adap->regs + PCIE_FW_A);
6265	/* Check if fw is initialized */
6266	if (!(pcie_fw & PCIE_FW_INIT_F)) {
6267		dev_warn(&pdev->dev, "Device not initialized\n");
6268		return -EOPNOTSUPP;
6269	}
6270
6271	/* If any of the VF's is already assigned to Guest OS, then
6272	 * SRIOV for the same cannot be modified
6273	 */
6274	if (current_vfs && pci_vfs_assigned(pdev)) {
6275		dev_err(&pdev->dev,
6276			"Cannot modify SR-IOV while VFs are assigned\n");
6277		return current_vfs;
6278	}
6279	/* Note that the upper-level code ensures that we're never called with
6280	 * a non-zero "num_vfs" when we already have VFs instantiated.  But
6281	 * it never hurts to code defensively.
6282	 */
6283	if (num_vfs != 0 && current_vfs != 0)
6284		return -EBUSY;
6285
6286	/* Nothing to do for no change. */
6287	if (num_vfs == current_vfs)
6288		return num_vfs;
6289
6290	/* Disable SRIOV when zero is passed. */
6291	if (!num_vfs) {
6292		pci_disable_sriov(pdev);
6293		/* free VF Management Interface */
6294		unregister_netdev(adap->port[0]);
6295		free_netdev(adap->port[0]);
6296		adap->port[0] = NULL;
6297
6298		/* free VF resources */
6299		adap->num_vfs = 0;
6300		kfree(adap->vfinfo);
6301		adap->vfinfo = NULL;
6302		return 0;
6303	}
6304
6305	if (!current_vfs) {
6306		struct fw_pfvf_cmd port_cmd, port_rpl;
6307		struct net_device *netdev;
6308		unsigned int pmask, port;
6309		struct pci_dev *pbridge;
6310		struct port_info *pi;
6311		char name[IFNAMSIZ];
6312		u32 devcap2;
6313		u16 flags;
6314
6315		/* If we want to instantiate Virtual Functions, then our
6316		 * parent bridge's PCI-E needs to support Alternative Routing
6317		 * ID (ARI) because our VFs will show up at function offset 8
6318		 * and above.
6319		 */
6320		pbridge = pdev->bus->self;
6321		pcie_capability_read_word(pbridge, PCI_EXP_FLAGS, &flags);
6322		pcie_capability_read_dword(pbridge, PCI_EXP_DEVCAP2, &devcap2);
6323
6324		if ((flags & PCI_EXP_FLAGS_VERS) < 2 ||
6325		    !(devcap2 & PCI_EXP_DEVCAP2_ARI)) {
6326			/* Our parent bridge does not support ARI so issue a
6327			 * warning and skip instantiating the VFs.  They
6328			 * won't be reachable.
6329			 */
6330			dev_warn(&pdev->dev, "Parent bridge %02x:%02x.%x doesn't support ARI; can't instantiate Virtual Functions\n",
6331				 pbridge->bus->number, PCI_SLOT(pbridge->devfn),
6332				 PCI_FUNC(pbridge->devfn));
6333			return -ENOTSUPP;
6334		}
6335		memset(&port_cmd, 0, sizeof(port_cmd));
6336		port_cmd.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PFVF_CMD) |
6337						 FW_CMD_REQUEST_F |
6338						 FW_CMD_READ_F |
6339						 FW_PFVF_CMD_PFN_V(adap->pf) |
6340						 FW_PFVF_CMD_VFN_V(0));
6341		port_cmd.retval_len16 = cpu_to_be32(FW_LEN16(port_cmd));
6342		err = t4_wr_mbox(adap, adap->mbox, &port_cmd, sizeof(port_cmd),
6343				 &port_rpl);
6344		if (err)
6345			return err;
6346		pmask = FW_PFVF_CMD_PMASK_G(be32_to_cpu(port_rpl.type_to_neq));
6347		port = ffs(pmask) - 1;
6348		/* Allocate VF Management Interface. */
6349		snprintf(name, IFNAMSIZ, "mgmtpf%d,%d", adap->adap_idx,
6350			 adap->pf);
6351		netdev = alloc_netdev(sizeof(struct port_info),
6352				      name, NET_NAME_UNKNOWN, cxgb4_mgmt_setup);
6353		if (!netdev)
6354			return -ENOMEM;
6355
6356		pi = netdev_priv(netdev);
6357		pi->adapter = adap;
6358		pi->lport = port;
6359		pi->tx_chan = port;
6360		SET_NETDEV_DEV(netdev, &pdev->dev);
6361
6362		adap->port[0] = netdev;
6363		pi->port_id = 0;
6364
6365		err = register_netdev(adap->port[0]);
6366		if (err) {
6367			pr_info("Unable to register VF mgmt netdev %s\n", name);
6368			free_netdev(adap->port[0]);
6369			adap->port[0] = NULL;
6370			return err;
6371		}
6372		/* Allocate and set up VF Information. */
6373		adap->vfinfo = kcalloc(pci_sriov_get_totalvfs(pdev),
6374				       sizeof(struct vf_info), GFP_KERNEL);
6375		if (!adap->vfinfo) {
6376			unregister_netdev(adap->port[0]);
6377			free_netdev(adap->port[0]);
6378			adap->port[0] = NULL;
6379			return -ENOMEM;
6380		}
6381		cxgb4_mgmt_fill_vf_station_mac_addr(adap);
6382	}
6383	/* Instantiate the requested number of VFs. */
6384	err = pci_enable_sriov(pdev, num_vfs);
6385	if (err) {
6386		pr_info("Unable to instantiate %d VFs\n", num_vfs);
6387		if (!current_vfs) {
6388			unregister_netdev(adap->port[0]);
6389			free_netdev(adap->port[0]);
6390			adap->port[0] = NULL;
6391			kfree(adap->vfinfo);
6392			adap->vfinfo = NULL;
6393		}
6394		return err;
6395	}
6396
6397	adap->num_vfs = num_vfs;
6398	return num_vfs;
6399}
6400#endif /* CONFIG_PCI_IOV */
6401
6402#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE) || IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
6403
6404static int chcr_offload_state(struct adapter *adap,
6405			      enum cxgb4_netdev_tls_ops op_val)
6406{
6407	switch (op_val) {
6408#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
6409	case CXGB4_TLSDEV_OPS:
6410		if (!adap->uld[CXGB4_ULD_KTLS].handle) {
6411			dev_dbg(adap->pdev_dev, "ch_ktls driver is not loaded\n");
6412			return -EOPNOTSUPP;
6413		}
6414		if (!adap->uld[CXGB4_ULD_KTLS].tlsdev_ops) {
6415			dev_dbg(adap->pdev_dev,
6416				"ch_ktls driver has no registered tlsdev_ops\n");
6417			return -EOPNOTSUPP;
6418		}
6419		break;
6420#endif /* CONFIG_CHELSIO_TLS_DEVICE */
6421#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
6422	case CXGB4_XFRMDEV_OPS:
6423		if (!adap->uld[CXGB4_ULD_IPSEC].handle) {
6424			dev_dbg(adap->pdev_dev, "chipsec driver is not loaded\n");
6425			return -EOPNOTSUPP;
6426		}
6427		if (!adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops) {
6428			dev_dbg(adap->pdev_dev,
6429				"chipsec driver has no registered xfrmdev_ops\n");
6430			return -EOPNOTSUPP;
6431		}
6432		break;
6433#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
6434	default:
6435		dev_dbg(adap->pdev_dev,
6436			"driver has no support for offload %d\n", op_val);
6437		return -EOPNOTSUPP;
6438	}
6439
6440	return 0;
6441}
6442
6443#endif /* CONFIG_CHELSIO_TLS_DEVICE || CONFIG_CHELSIO_IPSEC_INLINE */
6444
6445#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
6446
6447static int cxgb4_ktls_dev_add(struct net_device *netdev, struct sock *sk,
6448			      enum tls_offload_ctx_dir direction,
6449			      struct tls_crypto_info *crypto_info,
6450			      u32 tcp_sn)
6451{
6452	struct adapter *adap = netdev2adap(netdev);
6453	int ret;
6454
6455	mutex_lock(&uld_mutex);
6456	ret = chcr_offload_state(adap, CXGB4_TLSDEV_OPS);
6457	if (ret)
6458		goto out_unlock;
6459
6460	ret = cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_ENABLE);
6461	if (ret)
6462		goto out_unlock;
6463
6464	ret = adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_add(netdev, sk,
6465								direction,
6466								crypto_info,
6467								tcp_sn);
6468	/* if there is a failure, clear the refcount */
6469	if (ret)
6470		cxgb4_set_ktls_feature(adap,
6471				       FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
6472out_unlock:
6473	mutex_unlock(&uld_mutex);
6474	return ret;
6475}
6476
6477static void cxgb4_ktls_dev_del(struct net_device *netdev,
6478			       struct tls_context *tls_ctx,
6479			       enum tls_offload_ctx_dir direction)
6480{
6481	struct adapter *adap = netdev2adap(netdev);
6482
6483	mutex_lock(&uld_mutex);
6484	if (chcr_offload_state(adap, CXGB4_TLSDEV_OPS))
6485		goto out_unlock;
6486
6487	adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_del(netdev, tls_ctx,
6488							  direction);
6489
6490out_unlock:
6491	cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
6492	mutex_unlock(&uld_mutex);
6493}
6494
6495static const struct tlsdev_ops cxgb4_ktls_ops = {
6496	.tls_dev_add = cxgb4_ktls_dev_add,
6497	.tls_dev_del = cxgb4_ktls_dev_del,
6498};
6499#endif /* CONFIG_CHELSIO_TLS_DEVICE */
6500
6501#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
6502
6503static int cxgb4_xfrm_add_state(struct xfrm_state *x)
6504{
6505	struct adapter *adap = netdev2adap(x->xso.dev);
6506	int ret;
6507
6508	if (!mutex_trylock(&uld_mutex)) {
6509		dev_dbg(adap->pdev_dev,
6510			"crypto uld critical resource is under use\n");
6511		return -EBUSY;
6512	}
6513	ret = chcr_offload_state(adap, CXGB4_XFRMDEV_OPS);
6514	if (ret)
6515		goto out_unlock;
6516
6517	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x);
6518
6519out_unlock:
6520	mutex_unlock(&uld_mutex);
6521
6522	return ret;
6523}
6524
6525static void cxgb4_xfrm_del_state(struct xfrm_state *x)
6526{
6527	struct adapter *adap = netdev2adap(x->xso.dev);
6528
6529	if (!mutex_trylock(&uld_mutex)) {
6530		dev_dbg(adap->pdev_dev,
6531			"crypto uld critical resource is under use\n");
6532		return;
6533	}
6534	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
6535		goto out_unlock;
6536
6537	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x);
6538
6539out_unlock:
6540	mutex_unlock(&uld_mutex);
6541}
6542
6543static void cxgb4_xfrm_free_state(struct xfrm_state *x)
6544{
6545	struct adapter *adap = netdev2adap(x->xso.dev);
6546
6547	if (!mutex_trylock(&uld_mutex)) {
6548		dev_dbg(adap->pdev_dev,
6549			"crypto uld critical resource is under use\n");
6550		return;
6551	}
6552	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
6553		goto out_unlock;
6554
6555	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x);
6556
6557out_unlock:
6558	mutex_unlock(&uld_mutex);
6559}
6560
6561static bool cxgb4_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
6562{
6563	struct adapter *adap = netdev2adap(x->xso.dev);
6564	bool ret = false;
6565
6566	if (!mutex_trylock(&uld_mutex)) {
6567		dev_dbg(adap->pdev_dev,
6568			"crypto uld critical resource is under use\n");
6569		return ret;
6570	}
6571	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
6572		goto out_unlock;
6573
6574	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_offload_ok(skb, x);
6575
6576out_unlock:
6577	mutex_unlock(&uld_mutex);
6578	return ret;
6579}
6580
6581static void cxgb4_advance_esn_state(struct xfrm_state *x)
6582{
6583	struct adapter *adap = netdev2adap(x->xso.dev);
6584
6585	if (!mutex_trylock(&uld_mutex)) {
6586		dev_dbg(adap->pdev_dev,
6587			"crypto uld critical resource is under use\n");
6588		return;
6589	}
6590	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
6591		goto out_unlock;
6592
6593	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_advance_esn(x);
6594
6595out_unlock:
6596	mutex_unlock(&uld_mutex);
6597}
6598
6599static const struct xfrmdev_ops cxgb4_xfrmdev_ops = {
6600	.xdo_dev_state_add      = cxgb4_xfrm_add_state,
6601	.xdo_dev_state_delete   = cxgb4_xfrm_del_state,
6602	.xdo_dev_state_free     = cxgb4_xfrm_free_state,
6603	.xdo_dev_offload_ok     = cxgb4_ipsec_offload_ok,
6604	.xdo_dev_state_advance_esn = cxgb4_advance_esn_state,
6605};
6606
6607#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
6608
6609static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
6610{
6611	struct net_device *netdev;
6612	struct adapter *adapter;
6613	static int adap_idx = 1;
6614	int s_qpp, qpp, num_seg;
6615	struct port_info *pi;
6616	bool highdma = false;
6617	enum chip_type chip;
6618	void __iomem *regs;
6619	int func, chip_ver;
6620	u16 device_id;
6621	int i, err;
6622	u32 whoami;
6623
6624	err = pci_request_regions(pdev, KBUILD_MODNAME);
6625	if (err) {
6626		/* Just info, some other driver may have claimed the device. */
6627		dev_info(&pdev->dev, "cannot obtain PCI resources\n");
6628		return err;
6629	}
6630
6631	err = pci_enable_device(pdev);
6632	if (err) {
6633		dev_err(&pdev->dev, "cannot enable PCI device\n");
6634		goto out_release_regions;
6635	}
6636
6637	regs = pci_ioremap_bar(pdev, 0);
6638	if (!regs) {
6639		dev_err(&pdev->dev, "cannot map device registers\n");
6640		err = -ENOMEM;
6641		goto out_disable_device;
6642	}
6643
6644	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
6645	if (!adapter) {
6646		err = -ENOMEM;
6647		goto out_unmap_bar0;
6648	}
6649
6650	adapter->regs = regs;
6651	err = t4_wait_dev_ready(regs);
6652	if (err < 0)
6653		goto out_free_adapter;
6654
6655	/* We control everything through one PF */
6656	whoami = t4_read_reg(adapter, PL_WHOAMI_A);
6657	pci_read_config_word(pdev, PCI_DEVICE_ID, &device_id);
6658	chip = t4_get_chip_type(adapter, CHELSIO_PCI_ID_VER(device_id));
6659	if ((int)chip < 0) {
6660		dev_err(&pdev->dev, "Device %d is not supported\n", device_id);
6661		err = chip;
6662		goto out_free_adapter;
6663	}
6664	chip_ver = CHELSIO_CHIP_VERSION(chip);
6665	func = chip_ver <= CHELSIO_T5 ?
6666	       SOURCEPF_G(whoami) : T6_SOURCEPF_G(whoami);
6667
6668	adapter->pdev = pdev;
6669	adapter->pdev_dev = &pdev->dev;
6670	adapter->name = pci_name(pdev);
6671	adapter->mbox = func;
6672	adapter->pf = func;
6673	adapter->params.chip = chip;
6674	adapter->adap_idx = adap_idx;
6675	adapter->msg_enable = DFLT_MSG_ENABLE;
6676	adapter->mbox_log = kzalloc(sizeof(*adapter->mbox_log) +
6677				    (sizeof(struct mbox_cmd) *
6678				     T4_OS_LOG_MBOX_CMDS),
6679				    GFP_KERNEL);
6680	if (!adapter->mbox_log) {
6681		err = -ENOMEM;
6682		goto out_free_adapter;
6683	}
6684	spin_lock_init(&adapter->mbox_lock);
6685	INIT_LIST_HEAD(&adapter->mlist.list);
6686	adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
6687	pci_set_drvdata(pdev, adapter);
6688
6689	if (func != ent->driver_data) {
6690		pci_disable_device(pdev);
6691		pci_save_state(pdev);        /* to restore SR-IOV later */
6692		return 0;
6693	}
6694
6695	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
6696		highdma = true;
6697		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
6698		if (err) {
6699			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
6700				"coherent allocations\n");
6701			goto out_free_adapter;
6702		}
6703	} else {
6704		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
6705		if (err) {
6706			dev_err(&pdev->dev, "no usable DMA configuration\n");
6707			goto out_free_adapter;
6708		}
6709	}
6710
6711	pci_enable_pcie_error_reporting(pdev);
6712	pci_set_master(pdev);
6713	pci_save_state(pdev);
6714	adap_idx++;
6715	adapter->workq = create_singlethread_workqueue("cxgb4");
6716	if (!adapter->workq) {
6717		err = -ENOMEM;
6718		goto out_free_adapter;
6719	}
6720
6721	/* PCI device has been enabled */
6722	adapter->flags |= CXGB4_DEV_ENABLED;
6723	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
6724
6725	/* If possible, we use PCIe Relaxed Ordering Attribute to deliver
6726	 * Ingress Packet Data to Free List Buffers in order to allow for
6727	 * chipset performance optimizations between the Root Complex and
6728	 * Memory Controllers.  (Messages to the associated Ingress Queue
6729	 * notifying new Packet Placement in the Free Lists Buffers will be
6730	 * send without the Relaxed Ordering Attribute thus guaranteeing that
6731	 * all preceding PCIe Transaction Layer Packets will be processed
6732	 * first.)  But some Root Complexes have various issues with Upstream
6733	 * Transaction Layer Packets with the Relaxed Ordering Attribute set.
6734	 * The PCIe devices which under the Root Complexes will be cleared the
6735	 * Relaxed Ordering bit in the configuration space, So we check our
6736	 * PCIe configuration space to see if it's flagged with advice against
6737	 * using Relaxed Ordering.
6738	 */
6739	if (!pcie_relaxed_ordering_enabled(pdev))
6740		adapter->flags |= CXGB4_ROOT_NO_RELAXED_ORDERING;
6741
6742	spin_lock_init(&adapter->stats_lock);
6743	spin_lock_init(&adapter->tid_release_lock);
6744	spin_lock_init(&adapter->win0_lock);
6745
6746	INIT_WORK(&adapter->tid_release_task, process_tid_release_list);
6747	INIT_WORK(&adapter->db_full_task, process_db_full);
6748	INIT_WORK(&adapter->db_drop_task, process_db_drop);
6749	INIT_WORK(&adapter->fatal_err_notify_task, notify_fatal_err);
6750
6751	err = t4_prep_adapter(adapter);
6752	if (err)
6753		goto out_free_adapter;
6754
6755	if (is_kdump_kernel()) {
6756		/* Collect hardware state and append to /proc/vmcore */
6757		err = cxgb4_cudbg_vmcore_add_dump(adapter);
6758		if (err) {
6759			dev_warn(adapter->pdev_dev,
6760				 "Fail collecting vmcore device dump, err: %d. Continuing\n",
6761				 err);
6762			err = 0;
6763		}
6764	}
6765
6766	if (!is_t4(adapter->params.chip)) {
6767		s_qpp = (QUEUESPERPAGEPF0_S +
6768			(QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) *
6769			adapter->pf);
6770		qpp = 1 << QUEUESPERPAGEPF0_G(t4_read_reg(adapter,
6771		      SGE_EGRESS_QUEUES_PER_PAGE_PF_A) >> s_qpp);
6772		num_seg = PAGE_SIZE / SEGMENT_SIZE;
6773
6774		/* Each segment size is 128B. Write coalescing is enabled only
6775		 * when SGE_EGRESS_QUEUES_PER_PAGE_PF reg value for the
6776		 * queue is less no of segments that can be accommodated in
6777		 * a page size.
6778		 */
6779		if (qpp > num_seg) {
6780			dev_err(&pdev->dev,
6781				"Incorrect number of egress queues per page\n");
6782			err = -EINVAL;
6783			goto out_free_adapter;
6784		}
6785		adapter->bar2 = ioremap_wc(pci_resource_start(pdev, 2),
6786		pci_resource_len(pdev, 2));
6787		if (!adapter->bar2) {
6788			dev_err(&pdev->dev, "cannot map device bar2 region\n");
6789			err = -ENOMEM;
6790			goto out_free_adapter;
6791		}
6792	}
6793
6794	setup_memwin(adapter);
6795	err = adap_init0(adapter, 0);
6796	if (err)
6797		goto out_unmap_bar;
6798
6799	setup_memwin_rdma(adapter);
6800
6801	/* configure SGE_STAT_CFG_A to read WC stats */
6802	if (!is_t4(adapter->params.chip))
6803		t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7) |
6804			     (is_t5(adapter->params.chip) ? STATMODE_V(0) :
6805			      T6_STATMODE_V(0)));
6806
6807	/* Initialize hash mac addr list */
6808	INIT_LIST_HEAD(&adapter->mac_hlist);
6809
6810	for_each_port(adapter, i) {
6811		/* For supporting MQPRIO Offload, need some extra
6812		 * queues for each ETHOFLD TIDs. Keep it equal to
6813		 * MAX_ATIDs for now. Once we connect to firmware
6814		 * later and query the EOTID params, we'll come to
6815		 * know the actual # of EOTIDs supported.
6816		 */
6817		netdev = alloc_etherdev_mq(sizeof(struct port_info),
6818					   MAX_ETH_QSETS + MAX_ATIDS);
6819		if (!netdev) {
6820			err = -ENOMEM;
6821			goto out_free_dev;
6822		}
6823
6824		SET_NETDEV_DEV(netdev, &pdev->dev);
6825
6826		adapter->port[i] = netdev;
6827		pi = netdev_priv(netdev);
6828		pi->adapter = adapter;
6829		pi->xact_addr_filt = -1;
6830		pi->port_id = i;
6831		netdev->irq = pdev->irq;
6832
6833		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
6834			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
6835			NETIF_F_RXCSUM | NETIF_F_RXHASH | NETIF_F_GRO |
6836			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
6837			NETIF_F_HW_TC | NETIF_F_NTUPLE;
6838
6839		if (chip_ver > CHELSIO_T5) {
6840			netdev->hw_enc_features |= NETIF_F_IP_CSUM |
6841						   NETIF_F_IPV6_CSUM |
6842						   NETIF_F_RXCSUM |
6843						   NETIF_F_GSO_UDP_TUNNEL |
6844						   NETIF_F_GSO_UDP_TUNNEL_CSUM |
6845						   NETIF_F_TSO | NETIF_F_TSO6;
6846
6847			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
6848					       NETIF_F_GSO_UDP_TUNNEL_CSUM |
6849					       NETIF_F_HW_TLS_RECORD;
6850
6851			if (adapter->rawf_cnt)
6852				netdev->udp_tunnel_nic_info = &cxgb_udp_tunnels;
6853		}
6854
6855		if (highdma)
6856			netdev->hw_features |= NETIF_F_HIGHDMA;
6857		netdev->features |= netdev->hw_features;
6858		netdev->vlan_features = netdev->features & VLAN_FEAT;
6859#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
6860		if (pi->adapter->params.crypto & FW_CAPS_CONFIG_TLS_HW) {
6861			netdev->hw_features |= NETIF_F_HW_TLS_TX;
6862			netdev->tlsdev_ops = &cxgb4_ktls_ops;
6863			/* initialize the refcount */
6864			refcount_set(&pi->adapter->chcr_ktls.ktls_refcount, 0);
6865		}
6866#endif /* CONFIG_CHELSIO_TLS_DEVICE */
6867#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
6868		if (pi->adapter->params.crypto & FW_CAPS_CONFIG_IPSEC_INLINE) {
6869			netdev->hw_enc_features |= NETIF_F_HW_ESP;
6870			netdev->features |= NETIF_F_HW_ESP;
6871			netdev->xfrmdev_ops = &cxgb4_xfrmdev_ops;
6872		}
6873#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
6874
6875		netdev->priv_flags |= IFF_UNICAST_FLT;
6876
6877		/* MTU range: 81 - 9600 */
6878		netdev->min_mtu = 81;              /* accommodate SACK */
6879		netdev->max_mtu = MAX_MTU;
6880
6881		netdev->netdev_ops = &cxgb4_netdev_ops;
6882#ifdef CONFIG_CHELSIO_T4_DCB
6883		netdev->dcbnl_ops = &cxgb4_dcb_ops;
6884		cxgb4_dcb_state_init(netdev);
6885		cxgb4_dcb_version_init(netdev);
6886#endif
6887		cxgb4_set_ethtool_ops(netdev);
6888	}
6889
6890	cxgb4_init_ethtool_dump(adapter);
6891
6892	pci_set_drvdata(pdev, adapter);
6893
6894	if (adapter->flags & CXGB4_FW_OK) {
6895		err = t4_port_init(adapter, func, func, 0);
6896		if (err)
6897			goto out_free_dev;
6898	} else if (adapter->params.nports == 1) {
6899		/* If we don't have a connection to the firmware -- possibly
6900		 * because of an error -- grab the raw VPD parameters so we
6901		 * can set the proper MAC Address on the debug network
6902		 * interface that we've created.
6903		 */
6904		u8 hw_addr[ETH_ALEN];
6905		u8 *na = adapter->params.vpd.na;
6906
6907		err = t4_get_raw_vpd_params(adapter, &adapter->params.vpd);
6908		if (!err) {
6909			for (i = 0; i < ETH_ALEN; i++)
6910				hw_addr[i] = (hex2val(na[2 * i + 0]) * 16 +
6911					      hex2val(na[2 * i + 1]));
6912			t4_set_hw_addr(adapter, 0, hw_addr);
6913		}
6914	}
6915
6916	if (!(adapter->flags & CXGB4_FW_OK))
6917		goto fw_attach_fail;
6918
6919	/* Configure queues and allocate tables now, they can be needed as
6920	 * soon as the first register_netdev completes.
6921	 */
6922	err = cfg_queues(adapter);
6923	if (err)
6924		goto out_free_dev;
6925
6926	adapter->smt = t4_init_smt();
6927	if (!adapter->smt) {
6928		/* We tolerate a lack of SMT, giving up some functionality */
6929		dev_warn(&pdev->dev, "could not allocate SMT, continuing\n");
6930	}
6931
6932	adapter->l2t = t4_init_l2t(adapter->l2t_start, adapter->l2t_end);
6933	if (!adapter->l2t) {
6934		/* We tolerate a lack of L2T, giving up some functionality */
6935		dev_warn(&pdev->dev, "could not allocate L2T, continuing\n");
6936		adapter->params.offload = 0;
6937	}
6938
6939#if IS_ENABLED(CONFIG_IPV6)
6940	if (chip_ver <= CHELSIO_T5 &&
6941	    (!(t4_read_reg(adapter, LE_DB_CONFIG_A) & ASLIPCOMPEN_F))) {
6942		/* CLIP functionality is not present in hardware,
6943		 * hence disable all offload features
6944		 */
6945		dev_warn(&pdev->dev,
6946			 "CLIP not enabled in hardware, continuing\n");
6947		adapter->params.offload = 0;
6948	} else {
6949		adapter->clipt = t4_init_clip_tbl(adapter->clipt_start,
6950						  adapter->clipt_end);
6951		if (!adapter->clipt) {
6952			/* We tolerate a lack of clip_table, giving up
6953			 * some functionality
6954			 */
6955			dev_warn(&pdev->dev,
6956				 "could not allocate Clip table, continuing\n");
6957			adapter->params.offload = 0;
6958		}
6959	}
6960#endif
6961
6962	for_each_port(adapter, i) {
6963		pi = adap2pinfo(adapter, i);
6964		pi->sched_tbl = t4_init_sched(adapter->params.nsched_cls);
6965		if (!pi->sched_tbl)
6966			dev_warn(&pdev->dev,
6967				 "could not activate scheduling on port %d\n",
6968				 i);
6969	}
6970
6971	if (is_offload(adapter) || is_hashfilter(adapter)) {
6972		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
6973			u32 v;
6974
6975			v = t4_read_reg(adapter, LE_DB_HASH_CONFIG_A);
6976			if (chip_ver <= CHELSIO_T5) {
6977				adapter->tids.nhash = 1 << HASHTIDSIZE_G(v);
6978				v = t4_read_reg(adapter, LE_DB_TID_HASHBASE_A);
6979				adapter->tids.hash_base = v / 4;
6980			} else {
6981				adapter->tids.nhash = HASHTBLSIZE_G(v) << 3;
6982				v = t4_read_reg(adapter,
6983						T6_LE_DB_HASH_TID_BASE_A);
6984				adapter->tids.hash_base = v;
6985			}
6986		}
6987	}
6988
6989	if (tid_init(&adapter->tids) < 0) {
6990		dev_warn(&pdev->dev, "could not allocate TID table, "
6991			 "continuing\n");
6992		adapter->params.offload = 0;
6993	} else {
6994		adapter->tc_u32 = cxgb4_init_tc_u32(adapter);
6995		if (!adapter->tc_u32)
6996			dev_warn(&pdev->dev,
6997				 "could not offload tc u32, continuing\n");
6998
6999		if (cxgb4_init_tc_flower(adapter))
7000			dev_warn(&pdev->dev,
7001				 "could not offload tc flower, continuing\n");
7002
7003		if (cxgb4_init_tc_mqprio(adapter))
7004			dev_warn(&pdev->dev,
7005				 "could not offload tc mqprio, continuing\n");
7006
7007		if (cxgb4_init_tc_matchall(adapter))
7008			dev_warn(&pdev->dev,
7009				 "could not offload tc matchall, continuing\n");
7010		if (cxgb4_init_ethtool_filters(adapter))
7011			dev_warn(&pdev->dev,
7012				 "could not initialize ethtool filters, continuing\n");
7013	}
7014
7015	/* See what interrupts we'll be using */
7016	if (msi > 1 && enable_msix(adapter) == 0)
7017		adapter->flags |= CXGB4_USING_MSIX;
7018	else if (msi > 0 && pci_enable_msi(pdev) == 0) {
7019		adapter->flags |= CXGB4_USING_MSI;
7020		if (msi > 1)
7021			free_msix_info(adapter);
7022	}
7023
7024	/* check for PCI Express bandwidth capabiltites */
7025	pcie_print_link_status(pdev);
7026
7027	cxgb4_init_mps_ref_entries(adapter);
7028
7029	err = init_rss(adapter);
7030	if (err)
7031		goto out_free_dev;
7032
7033	err = setup_non_data_intr(adapter);
7034	if (err) {
7035		dev_err(adapter->pdev_dev,
7036			"Non Data interrupt allocation failed, err: %d\n", err);
7037		goto out_free_dev;
7038	}
7039
7040	err = setup_fw_sge_queues(adapter);
7041	if (err) {
7042		dev_err(adapter->pdev_dev,
7043			"FW sge queue allocation failed, err %d", err);
7044		goto out_free_dev;
7045	}
7046
7047fw_attach_fail:
7048	/*
7049	 * The card is now ready to go.  If any errors occur during device
7050	 * registration we do not fail the whole card but rather proceed only
7051	 * with the ports we manage to register successfully.  However we must
7052	 * register at least one net device.
7053	 */
7054	for_each_port(adapter, i) {
7055		pi = adap2pinfo(adapter, i);
7056		adapter->port[i]->dev_port = pi->lport;
7057		netif_set_real_num_tx_queues(adapter->port[i], pi->nqsets);
7058		netif_set_real_num_rx_queues(adapter->port[i], pi->nqsets);
7059
7060		netif_carrier_off(adapter->port[i]);
7061
7062		err = register_netdev(adapter->port[i]);
7063		if (err)
7064			break;
7065		adapter->chan_map[pi->tx_chan] = i;
7066		print_port_info(adapter->port[i]);
7067	}
7068	if (i == 0) {
7069		dev_err(&pdev->dev, "could not register any net devices\n");
7070		goto out_free_dev;
7071	}
7072	if (err) {
7073		dev_warn(&pdev->dev, "only %d net devices registered\n", i);
7074		err = 0;
7075	}
7076
7077	if (cxgb4_debugfs_root) {
7078		adapter->debugfs_root = debugfs_create_dir(pci_name(pdev),
7079							   cxgb4_debugfs_root);
7080		setup_debugfs(adapter);
7081	}
7082
7083	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
7084	pdev->needs_freset = 1;
7085
7086	if (is_uld(adapter))
7087		cxgb4_uld_enable(adapter);
7088
7089	if (!is_t4(adapter->params.chip))
7090		cxgb4_ptp_init(adapter);
7091
7092	if (IS_REACHABLE(CONFIG_THERMAL) &&
7093	    !is_t4(adapter->params.chip) && (adapter->flags & CXGB4_FW_OK))
7094		cxgb4_thermal_init(adapter);
7095
7096	print_adapter_info(adapter);
7097	return 0;
7098
7099 out_free_dev:
7100	t4_free_sge_resources(adapter);
7101	free_some_resources(adapter);
7102	if (adapter->flags & CXGB4_USING_MSIX)
7103		free_msix_info(adapter);
7104	if (adapter->num_uld || adapter->num_ofld_uld)
7105		t4_uld_mem_free(adapter);
7106 out_unmap_bar:
7107	if (!is_t4(adapter->params.chip))
7108		iounmap(adapter->bar2);
7109 out_free_adapter:
7110	if (adapter->workq)
7111		destroy_workqueue(adapter->workq);
7112
7113	kfree(adapter->mbox_log);
7114	kfree(adapter);
7115 out_unmap_bar0:
7116	iounmap(regs);
7117 out_disable_device:
7118	pci_disable_pcie_error_reporting(pdev);
7119	pci_disable_device(pdev);
7120 out_release_regions:
7121	pci_release_regions(pdev);
7122	return err;
7123}
7124
7125static void remove_one(struct pci_dev *pdev)
7126{
7127	struct adapter *adapter = pci_get_drvdata(pdev);
7128	struct hash_mac_addr *entry, *tmp;
7129
7130	if (!adapter) {
7131		pci_release_regions(pdev);
7132		return;
7133	}
7134
7135	/* If we allocated filters, free up state associated with any
7136	 * valid filters ...
7137	 */
7138	clear_all_filters(adapter);
7139
7140	adapter->flags |= CXGB4_SHUTTING_DOWN;
7141
7142	if (adapter->pf == 4) {
7143		int i;
7144
7145		/* Tear down per-adapter Work Queue first since it can contain
7146		 * references to our adapter data structure.
7147		 */
7148		destroy_workqueue(adapter->workq);
7149
7150		detach_ulds(adapter);
7151
7152		for_each_port(adapter, i)
7153			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
7154				unregister_netdev(adapter->port[i]);
7155
7156		t4_uld_clean_up(adapter);
7157
7158		adap_free_hma_mem(adapter);
7159
7160		disable_interrupts(adapter);
7161
7162		cxgb4_free_mps_ref_entries(adapter);
7163
7164		debugfs_remove_recursive(adapter->debugfs_root);
7165
7166		if (!is_t4(adapter->params.chip))
7167			cxgb4_ptp_stop(adapter);
7168		if (IS_REACHABLE(CONFIG_THERMAL))
7169			cxgb4_thermal_remove(adapter);
7170
7171		if (adapter->flags & CXGB4_FULL_INIT_DONE)
7172			cxgb_down(adapter);
7173
7174		if (adapter->flags & CXGB4_USING_MSIX)
7175			free_msix_info(adapter);
7176		if (adapter->num_uld || adapter->num_ofld_uld)
7177			t4_uld_mem_free(adapter);
7178		free_some_resources(adapter);
7179		list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist,
7180					 list) {
7181			list_del(&entry->list);
7182			kfree(entry);
7183		}
7184
7185#if IS_ENABLED(CONFIG_IPV6)
7186		t4_cleanup_clip_tbl(adapter);
7187#endif
7188		if (!is_t4(adapter->params.chip))
7189			iounmap(adapter->bar2);
7190	}
7191#ifdef CONFIG_PCI_IOV
7192	else {
7193		cxgb4_iov_configure(adapter->pdev, 0);
7194	}
7195#endif
7196	iounmap(adapter->regs);
7197	pci_disable_pcie_error_reporting(pdev);
7198	if ((adapter->flags & CXGB4_DEV_ENABLED)) {
7199		pci_disable_device(pdev);
7200		adapter->flags &= ~CXGB4_DEV_ENABLED;
7201	}
7202	pci_release_regions(pdev);
7203	kfree(adapter->mbox_log);
7204	synchronize_rcu();
7205	kfree(adapter);
7206}
7207
7208/* "Shutdown" quiesces the device, stopping Ingress Packet and Interrupt
7209 * delivery.  This is essentially a stripped down version of the PCI remove()
7210 * function where we do the minimal amount of work necessary to shutdown any
7211 * further activity.
7212 */
7213static void shutdown_one(struct pci_dev *pdev)
7214{
7215	struct adapter *adapter = pci_get_drvdata(pdev);
7216
7217	/* As with remove_one() above (see extended comment), we only want do
7218	 * do cleanup on PCI Devices which went all the way through init_one()
7219	 * ...
7220	 */
7221	if (!adapter) {
7222		pci_release_regions(pdev);
7223		return;
7224	}
7225
7226	adapter->flags |= CXGB4_SHUTTING_DOWN;
7227
7228	if (adapter->pf == 4) {
7229		int i;
7230
7231		for_each_port(adapter, i)
7232			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
7233				cxgb_close(adapter->port[i]);
7234
7235		rtnl_lock();
7236		cxgb4_mqprio_stop_offload(adapter);
7237		rtnl_unlock();
7238
7239		if (is_uld(adapter)) {
7240			detach_ulds(adapter);
7241			t4_uld_clean_up(adapter);
7242		}
7243
7244		disable_interrupts(adapter);
7245		disable_msi(adapter);
7246
7247		t4_sge_stop(adapter);
7248		if (adapter->flags & CXGB4_FW_OK)
7249			t4_fw_bye(adapter, adapter->mbox);
7250	}
7251}
7252
7253static struct pci_driver cxgb4_driver = {
7254	.name     = KBUILD_MODNAME,
7255	.id_table = cxgb4_pci_tbl,
7256	.probe    = init_one,
7257	.remove   = remove_one,
7258	.shutdown = shutdown_one,
7259#ifdef CONFIG_PCI_IOV
7260	.sriov_configure = cxgb4_iov_configure,
7261#endif
7262	.err_handler = &cxgb4_eeh,
7263};
7264
7265static int __init cxgb4_init_module(void)
7266{
7267	int ret;
7268
7269	cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL);
7270
7271	ret = pci_register_driver(&cxgb4_driver);
7272	if (ret < 0)
7273		goto err_pci;
7274
7275#if IS_ENABLED(CONFIG_IPV6)
7276	if (!inet6addr_registered) {
7277		ret = register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
7278		if (ret)
7279			pci_unregister_driver(&cxgb4_driver);
7280		else
7281			inet6addr_registered = true;
7282	}
7283#endif
7284
7285	if (ret == 0)
7286		return ret;
7287
7288err_pci:
7289	debugfs_remove(cxgb4_debugfs_root);
7290
7291	return ret;
7292}
7293
7294static void __exit cxgb4_cleanup_module(void)
7295{
7296#if IS_ENABLED(CONFIG_IPV6)
7297	if (inet6addr_registered) {
7298		unregister_inet6addr_notifier(&cxgb4_inet6addr_notifier);
7299		inet6addr_registered = false;
7300	}
7301#endif
7302	pci_unregister_driver(&cxgb4_driver);
7303	debugfs_remove(cxgb4_debugfs_root);  /* NULL ok */
7304}
7305
7306module_init(cxgb4_init_module);
7307module_exit(cxgb4_cleanup_module);
7308