1// SPDX-License-Identifier: GPL-2.0
2/* Copyright(c) 1999 - 2018 Intel Corporation. */
3
4#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
5
6#include <linux/module.h>
7#include <linux/types.h>
8#include <linux/init.h>
9#include <linux/pci.h>
10#include <linux/vmalloc.h>
11#include <linux/pagemap.h>
12#include <linux/delay.h>
13#include <linux/netdevice.h>
14#include <linux/interrupt.h>
15#include <linux/tcp.h>
16#include <linux/ipv6.h>
17#include <linux/slab.h>
18#include <net/checksum.h>
19#include <net/ip6_checksum.h>
20#include <linux/ethtool.h>
21#include <linux/if_vlan.h>
22#include <linux/cpu.h>
23#include <linux/smp.h>
24#include <linux/pm_qos.h>
25#include <linux/pm_runtime.h>
26#include <linux/prefetch.h>
27#include <linux/suspend.h>
28
29#include "e1000.h"
30#define CREATE_TRACE_POINTS
31#include "e1000e_trace.h"
32
33char e1000e_driver_name[] = "e1000e";
34
35#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
36static int debug = -1;
37module_param(debug, int, 0);
38MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
39
40static const struct e1000_info *e1000_info_tbl[] = {
41	[board_82571]		= &e1000_82571_info,
42	[board_82572]		= &e1000_82572_info,
43	[board_82573]		= &e1000_82573_info,
44	[board_82574]		= &e1000_82574_info,
45	[board_82583]		= &e1000_82583_info,
46	[board_80003es2lan]	= &e1000_es2_info,
47	[board_ich8lan]		= &e1000_ich8_info,
48	[board_ich9lan]		= &e1000_ich9_info,
49	[board_ich10lan]	= &e1000_ich10_info,
50	[board_pchlan]		= &e1000_pch_info,
51	[board_pch2lan]		= &e1000_pch2_info,
52	[board_pch_lpt]		= &e1000_pch_lpt_info,
53	[board_pch_spt]		= &e1000_pch_spt_info,
54	[board_pch_cnp]		= &e1000_pch_cnp_info,
55	[board_pch_tgp]		= &e1000_pch_tgp_info,
56	[board_pch_adp]		= &e1000_pch_adp_info,
57	[board_pch_mtp]		= &e1000_pch_mtp_info,
58};
59
60struct e1000_reg_info {
61	u32 ofs;
62	char *name;
63};
64
65static const struct e1000_reg_info e1000_reg_info_tbl[] = {
66	/* General Registers */
67	{E1000_CTRL, "CTRL"},
68	{E1000_STATUS, "STATUS"},
69	{E1000_CTRL_EXT, "CTRL_EXT"},
70
71	/* Interrupt Registers */
72	{E1000_ICR, "ICR"},
73
74	/* Rx Registers */
75	{E1000_RCTL, "RCTL"},
76	{E1000_RDLEN(0), "RDLEN"},
77	{E1000_RDH(0), "RDH"},
78	{E1000_RDT(0), "RDT"},
79	{E1000_RDTR, "RDTR"},
80	{E1000_RXDCTL(0), "RXDCTL"},
81	{E1000_ERT, "ERT"},
82	{E1000_RDBAL(0), "RDBAL"},
83	{E1000_RDBAH(0), "RDBAH"},
84	{E1000_RDFH, "RDFH"},
85	{E1000_RDFT, "RDFT"},
86	{E1000_RDFHS, "RDFHS"},
87	{E1000_RDFTS, "RDFTS"},
88	{E1000_RDFPC, "RDFPC"},
89
90	/* Tx Registers */
91	{E1000_TCTL, "TCTL"},
92	{E1000_TDBAL(0), "TDBAL"},
93	{E1000_TDBAH(0), "TDBAH"},
94	{E1000_TDLEN(0), "TDLEN"},
95	{E1000_TDH(0), "TDH"},
96	{E1000_TDT(0), "TDT"},
97	{E1000_TIDV, "TIDV"},
98	{E1000_TXDCTL(0), "TXDCTL"},
99	{E1000_TADV, "TADV"},
100	{E1000_TARC(0), "TARC"},
101	{E1000_TDFH, "TDFH"},
102	{E1000_TDFT, "TDFT"},
103	{E1000_TDFHS, "TDFHS"},
104	{E1000_TDFTS, "TDFTS"},
105	{E1000_TDFPC, "TDFPC"},
106
107	/* List Terminator */
108	{0, NULL}
109};
110
111/**
112 * __ew32_prepare - prepare to write to MAC CSR register on certain parts
113 * @hw: pointer to the HW structure
114 *
115 * When updating the MAC CSR registers, the Manageability Engine (ME) could
116 * be accessing the registers at the same time.  Normally, this is handled in
117 * h/w by an arbiter but on some parts there is a bug that acknowledges Host
118 * accesses later than it should which could result in the register to have
119 * an incorrect value.  Workaround this by checking the FWSM register which
120 * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
121 * and try again a number of times.
122 **/
123static void __ew32_prepare(struct e1000_hw *hw)
124{
125	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
126
127	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
128		udelay(50);
129}
130
131void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
132{
133	if (hw->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
134		__ew32_prepare(hw);
135
136	writel(val, hw->hw_addr + reg);
137}
138
139/**
140 * e1000_regdump - register printout routine
141 * @hw: pointer to the HW structure
142 * @reginfo: pointer to the register info table
143 **/
144static void e1000_regdump(struct e1000_hw *hw, struct e1000_reg_info *reginfo)
145{
146	int n = 0;
147	char rname[16];
148	u32 regs[8];
149
150	switch (reginfo->ofs) {
151	case E1000_RXDCTL(0):
152		for (n = 0; n < 2; n++)
153			regs[n] = __er32(hw, E1000_RXDCTL(n));
154		break;
155	case E1000_TXDCTL(0):
156		for (n = 0; n < 2; n++)
157			regs[n] = __er32(hw, E1000_TXDCTL(n));
158		break;
159	case E1000_TARC(0):
160		for (n = 0; n < 2; n++)
161			regs[n] = __er32(hw, E1000_TARC(n));
162		break;
163	default:
164		pr_info("%-15s %08x\n",
165			reginfo->name, __er32(hw, reginfo->ofs));
166		return;
167	}
168
169	snprintf(rname, 16, "%s%s", reginfo->name, "[0-1]");
170	pr_info("%-15s %08x %08x\n", rname, regs[0], regs[1]);
171}
172
173static void e1000e_dump_ps_pages(struct e1000_adapter *adapter,
174				 struct e1000_buffer *bi)
175{
176	int i;
177	struct e1000_ps_page *ps_page;
178
179	for (i = 0; i < adapter->rx_ps_pages; i++) {
180		ps_page = &bi->ps_pages[i];
181
182		if (ps_page->page) {
183			pr_info("packet dump for ps_page %d:\n", i);
184			print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS,
185				       16, 1, page_address(ps_page->page),
186				       PAGE_SIZE, true);
187		}
188	}
189}
190
191/**
192 * e1000e_dump - Print registers, Tx-ring and Rx-ring
193 * @adapter: board private structure
194 **/
195static void e1000e_dump(struct e1000_adapter *adapter)
196{
197	struct net_device *netdev = adapter->netdev;
198	struct e1000_hw *hw = &adapter->hw;
199	struct e1000_reg_info *reginfo;
200	struct e1000_ring *tx_ring = adapter->tx_ring;
201	struct e1000_tx_desc *tx_desc;
202	struct my_u0 {
203		__le64 a;
204		__le64 b;
205	} *u0;
206	struct e1000_buffer *buffer_info;
207	struct e1000_ring *rx_ring = adapter->rx_ring;
208	union e1000_rx_desc_packet_split *rx_desc_ps;
209	union e1000_rx_desc_extended *rx_desc;
210	struct my_u1 {
211		__le64 a;
212		__le64 b;
213		__le64 c;
214		__le64 d;
215	} *u1;
216	u32 staterr;
217	int i = 0;
218
219	if (!netif_msg_hw(adapter))
220		return;
221
222	/* Print netdevice Info */
223	if (netdev) {
224		dev_info(&adapter->pdev->dev, "Net device Info\n");
225		pr_info("Device Name     state            trans_start\n");
226		pr_info("%-15s %016lX %016lX\n", netdev->name,
227			netdev->state, dev_trans_start(netdev));
228	}
229
230	/* Print Registers */
231	dev_info(&adapter->pdev->dev, "Register Dump\n");
232	pr_info(" Register Name   Value\n");
233	for (reginfo = (struct e1000_reg_info *)e1000_reg_info_tbl;
234	     reginfo->name; reginfo++) {
235		e1000_regdump(hw, reginfo);
236	}
237
238	/* Print Tx Ring Summary */
239	if (!netdev || !netif_running(netdev))
240		return;
241
242	dev_info(&adapter->pdev->dev, "Tx Ring Summary\n");
243	pr_info("Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
244	buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean];
245	pr_info(" %5d %5X %5X %016llX %04X %3X %016llX\n",
246		0, tx_ring->next_to_use, tx_ring->next_to_clean,
247		(unsigned long long)buffer_info->dma,
248		buffer_info->length,
249		buffer_info->next_to_watch,
250		(unsigned long long)buffer_info->time_stamp);
251
252	/* Print Tx Ring */
253	if (!netif_msg_tx_done(adapter))
254		goto rx_ring_summary;
255
256	dev_info(&adapter->pdev->dev, "Tx Ring Dump\n");
257
258	/* Transmit Descriptor Formats - DEXT[29] is 0 (Legacy) or 1 (Extended)
259	 *
260	 * Legacy Transmit Descriptor
261	 *   +--------------------------------------------------------------+
262	 * 0 |         Buffer Address [63:0] (Reserved on Write Back)       |
263	 *   +--------------------------------------------------------------+
264	 * 8 | Special  |    CSS     | Status |  CMD    |  CSO   |  Length  |
265	 *   +--------------------------------------------------------------+
266	 *   63       48 47        36 35    32 31     24 23    16 15        0
267	 *
268	 * Extended Context Descriptor (DTYP=0x0) for TSO or checksum offload
269	 *   63      48 47    40 39       32 31             16 15    8 7      0
270	 *   +----------------------------------------------------------------+
271	 * 0 |  TUCSE  | TUCS0  |   TUCSS   |     IPCSE       | IPCS0 | IPCSS |
272	 *   +----------------------------------------------------------------+
273	 * 8 |   MSS   | HDRLEN | RSV | STA | TUCMD | DTYP |      PAYLEN      |
274	 *   +----------------------------------------------------------------+
275	 *   63      48 47    40 39 36 35 32 31   24 23  20 19                0
276	 *
277	 * Extended Data Descriptor (DTYP=0x1)
278	 *   +----------------------------------------------------------------+
279	 * 0 |                     Buffer Address [63:0]                      |
280	 *   +----------------------------------------------------------------+
281	 * 8 | VLAN tag |  POPTS  | Rsvd | Status | Command | DTYP |  DTALEN  |
282	 *   +----------------------------------------------------------------+
283	 *   63       48 47     40 39  36 35    32 31     24 23  20 19        0
284	 */
285	pr_info("Tl[desc]     [address 63:0  ] [SpeCssSCmCsLen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Legacy format\n");
286	pr_info("Tc[desc]     [Ce CoCsIpceCoS] [MssHlRSCm0Plen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Ext Context format\n");
287	pr_info("Td[desc]     [address 63:0  ] [VlaPoRSCm1Dlen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Ext Data format\n");
288	for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
289		const char *next_desc;
290		tx_desc = E1000_TX_DESC(*tx_ring, i);
291		buffer_info = &tx_ring->buffer_info[i];
292		u0 = (struct my_u0 *)tx_desc;
293		if (i == tx_ring->next_to_use && i == tx_ring->next_to_clean)
294			next_desc = " NTC/U";
295		else if (i == tx_ring->next_to_use)
296			next_desc = " NTU";
297		else if (i == tx_ring->next_to_clean)
298			next_desc = " NTC";
299		else
300			next_desc = "";
301		pr_info("T%c[0x%03X]    %016llX %016llX %016llX %04X  %3X %016llX %p%s\n",
302			(!(le64_to_cpu(u0->b) & BIT(29)) ? 'l' :
303			 ((le64_to_cpu(u0->b) & BIT(20)) ? 'd' : 'c')),
304			i,
305			(unsigned long long)le64_to_cpu(u0->a),
306			(unsigned long long)le64_to_cpu(u0->b),
307			(unsigned long long)buffer_info->dma,
308			buffer_info->length, buffer_info->next_to_watch,
309			(unsigned long long)buffer_info->time_stamp,
310			buffer_info->skb, next_desc);
311
312		if (netif_msg_pktdata(adapter) && buffer_info->skb)
313			print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS,
314				       16, 1, buffer_info->skb->data,
315				       buffer_info->skb->len, true);
316	}
317
318	/* Print Rx Ring Summary */
319rx_ring_summary:
320	dev_info(&adapter->pdev->dev, "Rx Ring Summary\n");
321	pr_info("Queue [NTU] [NTC]\n");
322	pr_info(" %5d %5X %5X\n",
323		0, rx_ring->next_to_use, rx_ring->next_to_clean);
324
325	/* Print Rx Ring */
326	if (!netif_msg_rx_status(adapter))
327		return;
328
329	dev_info(&adapter->pdev->dev, "Rx Ring Dump\n");
330	switch (adapter->rx_ps_pages) {
331	case 1:
332	case 2:
333	case 3:
334		/* [Extended] Packet Split Receive Descriptor Format
335		 *
336		 *    +-----------------------------------------------------+
337		 *  0 |                Buffer Address 0 [63:0]              |
338		 *    +-----------------------------------------------------+
339		 *  8 |                Buffer Address 1 [63:0]              |
340		 *    +-----------------------------------------------------+
341		 * 16 |                Buffer Address 2 [63:0]              |
342		 *    +-----------------------------------------------------+
343		 * 24 |                Buffer Address 3 [63:0]              |
344		 *    +-----------------------------------------------------+
345		 */
346		pr_info("R  [desc]      [buffer 0 63:0 ] [buffer 1 63:0 ] [buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma       ] [bi->skb] <-- Ext Pkt Split format\n");
347		/* [Extended] Receive Descriptor (Write-Back) Format
348		 *
349		 *   63       48 47    32 31     13 12    8 7    4 3        0
350		 *   +------------------------------------------------------+
351		 * 0 | Packet   | IP     |  Rsvd   | MRQ   | Rsvd | MRQ RSS |
352		 *   | Checksum | Ident  |         | Queue |      |  Type   |
353		 *   +------------------------------------------------------+
354		 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
355		 *   +------------------------------------------------------+
356		 *   63       48 47    32 31            20 19               0
357		 */
358		pr_info("RWB[desc]      [ck ipid mrqhsh] [vl   l0 ee  es] [ l3  l2  l1 hs] [reserved      ] ---------------- [bi->skb] <-- Ext Rx Write-Back format\n");
359		for (i = 0; i < rx_ring->count; i++) {
360			const char *next_desc;
361			buffer_info = &rx_ring->buffer_info[i];
362			rx_desc_ps = E1000_RX_DESC_PS(*rx_ring, i);
363			u1 = (struct my_u1 *)rx_desc_ps;
364			staterr =
365			    le32_to_cpu(rx_desc_ps->wb.middle.status_error);
366
367			if (i == rx_ring->next_to_use)
368				next_desc = " NTU";
369			else if (i == rx_ring->next_to_clean)
370				next_desc = " NTC";
371			else
372				next_desc = "";
373
374			if (staterr & E1000_RXD_STAT_DD) {
375				/* Descriptor Done */
376				pr_info("%s[0x%03X]     %016llX %016llX %016llX %016llX ---------------- %p%s\n",
377					"RWB", i,
378					(unsigned long long)le64_to_cpu(u1->a),
379					(unsigned long long)le64_to_cpu(u1->b),
380					(unsigned long long)le64_to_cpu(u1->c),
381					(unsigned long long)le64_to_cpu(u1->d),
382					buffer_info->skb, next_desc);
383			} else {
384				pr_info("%s[0x%03X]     %016llX %016llX %016llX %016llX %016llX %p%s\n",
385					"R  ", i,
386					(unsigned long long)le64_to_cpu(u1->a),
387					(unsigned long long)le64_to_cpu(u1->b),
388					(unsigned long long)le64_to_cpu(u1->c),
389					(unsigned long long)le64_to_cpu(u1->d),
390					(unsigned long long)buffer_info->dma,
391					buffer_info->skb, next_desc);
392
393				if (netif_msg_pktdata(adapter))
394					e1000e_dump_ps_pages(adapter,
395							     buffer_info);
396			}
397		}
398		break;
399	default:
400	case 0:
401		/* Extended Receive Descriptor (Read) Format
402		 *
403		 *   +-----------------------------------------------------+
404		 * 0 |                Buffer Address [63:0]                |
405		 *   +-----------------------------------------------------+
406		 * 8 |                      Reserved                       |
407		 *   +-----------------------------------------------------+
408		 */
409		pr_info("R  [desc]      [buf addr 63:0 ] [reserved 63:0 ] [bi->dma       ] [bi->skb] <-- Ext (Read) format\n");
410		/* Extended Receive Descriptor (Write-Back) Format
411		 *
412		 *   63       48 47    32 31    24 23            4 3        0
413		 *   +------------------------------------------------------+
414		 *   |     RSS Hash      |        |               |         |
415		 * 0 +-------------------+  Rsvd  |   Reserved    | MRQ RSS |
416		 *   | Packet   | IP     |        |               |  Type   |
417		 *   | Checksum | Ident  |        |               |         |
418		 *   +------------------------------------------------------+
419		 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
420		 *   +------------------------------------------------------+
421		 *   63       48 47    32 31            20 19               0
422		 */
423		pr_info("RWB[desc]      [cs ipid    mrq] [vt   ln xe  xs] [bi->skb] <-- Ext (Write-Back) format\n");
424
425		for (i = 0; i < rx_ring->count; i++) {
426			const char *next_desc;
427
428			buffer_info = &rx_ring->buffer_info[i];
429			rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
430			u1 = (struct my_u1 *)rx_desc;
431			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
432
433			if (i == rx_ring->next_to_use)
434				next_desc = " NTU";
435			else if (i == rx_ring->next_to_clean)
436				next_desc = " NTC";
437			else
438				next_desc = "";
439
440			if (staterr & E1000_RXD_STAT_DD) {
441				/* Descriptor Done */
442				pr_info("%s[0x%03X]     %016llX %016llX ---------------- %p%s\n",
443					"RWB", i,
444					(unsigned long long)le64_to_cpu(u1->a),
445					(unsigned long long)le64_to_cpu(u1->b),
446					buffer_info->skb, next_desc);
447			} else {
448				pr_info("%s[0x%03X]     %016llX %016llX %016llX %p%s\n",
449					"R  ", i,
450					(unsigned long long)le64_to_cpu(u1->a),
451					(unsigned long long)le64_to_cpu(u1->b),
452					(unsigned long long)buffer_info->dma,
453					buffer_info->skb, next_desc);
454
455				if (netif_msg_pktdata(adapter) &&
456				    buffer_info->skb)
457					print_hex_dump(KERN_INFO, "",
458						       DUMP_PREFIX_ADDRESS, 16,
459						       1,
460						       buffer_info->skb->data,
461						       adapter->rx_buffer_len,
462						       true);
463			}
464		}
465	}
466}
467
468/**
469 * e1000_desc_unused - calculate if we have unused descriptors
470 * @ring: pointer to ring struct to perform calculation on
471 **/
472static int e1000_desc_unused(struct e1000_ring *ring)
473{
474	if (ring->next_to_clean > ring->next_to_use)
475		return ring->next_to_clean - ring->next_to_use - 1;
476
477	return ring->count + ring->next_to_clean - ring->next_to_use - 1;
478}
479
480/**
481 * e1000e_systim_to_hwtstamp - convert system time value to hw time stamp
482 * @adapter: board private structure
483 * @hwtstamps: time stamp structure to update
484 * @systim: unsigned 64bit system time value.
485 *
486 * Convert the system time value stored in the RX/TXSTMP registers into a
487 * hwtstamp which can be used by the upper level time stamping functions.
488 *
489 * The 'systim_lock' spinlock is used to protect the consistency of the
490 * system time value. This is needed because reading the 64 bit time
491 * value involves reading two 32 bit registers. The first read latches the
492 * value.
493 **/
494static void e1000e_systim_to_hwtstamp(struct e1000_adapter *adapter,
495				      struct skb_shared_hwtstamps *hwtstamps,
496				      u64 systim)
497{
498	u64 ns;
499	unsigned long flags;
500
501	spin_lock_irqsave(&adapter->systim_lock, flags);
502	ns = timecounter_cyc2time(&adapter->tc, systim);
503	spin_unlock_irqrestore(&adapter->systim_lock, flags);
504
505	memset(hwtstamps, 0, sizeof(*hwtstamps));
506	hwtstamps->hwtstamp = ns_to_ktime(ns);
507}
508
509/**
510 * e1000e_rx_hwtstamp - utility function which checks for Rx time stamp
511 * @adapter: board private structure
512 * @status: descriptor extended error and status field
513 * @skb: particular skb to include time stamp
514 *
515 * If the time stamp is valid, convert it into the timecounter ns value
516 * and store that result into the shhwtstamps structure which is passed
517 * up the network stack.
518 **/
519static void e1000e_rx_hwtstamp(struct e1000_adapter *adapter, u32 status,
520			       struct sk_buff *skb)
521{
522	struct e1000_hw *hw = &adapter->hw;
523	u64 rxstmp;
524
525	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP) ||
526	    !(status & E1000_RXDEXT_STATERR_TST) ||
527	    !(er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID))
528		return;
529
530	/* The Rx time stamp registers contain the time stamp.  No other
531	 * received packet will be time stamped until the Rx time stamp
532	 * registers are read.  Because only one packet can be time stamped
533	 * at a time, the register values must belong to this packet and
534	 * therefore none of the other additional attributes need to be
535	 * compared.
536	 */
537	rxstmp = (u64)er32(RXSTMPL);
538	rxstmp |= (u64)er32(RXSTMPH) << 32;
539	e1000e_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), rxstmp);
540
541	adapter->flags2 &= ~FLAG2_CHECK_RX_HWTSTAMP;
542}
543
544/**
545 * e1000_receive_skb - helper function to handle Rx indications
546 * @adapter: board private structure
547 * @netdev: pointer to netdev struct
548 * @staterr: descriptor extended error and status field as written by hardware
549 * @vlan: descriptor vlan field as written by hardware (no le/be conversion)
550 * @skb: pointer to sk_buff to be indicated to stack
551 **/
552static void e1000_receive_skb(struct e1000_adapter *adapter,
553			      struct net_device *netdev, struct sk_buff *skb,
554			      u32 staterr, __le16 vlan)
555{
556	u16 tag = le16_to_cpu(vlan);
557
558	e1000e_rx_hwtstamp(adapter, staterr, skb);
559
560	skb->protocol = eth_type_trans(skb, netdev);
561
562	if (staterr & E1000_RXD_STAT_VP)
563		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag);
564
565	napi_gro_receive(&adapter->napi, skb);
566}
567
568/**
569 * e1000_rx_checksum - Receive Checksum Offload
570 * @adapter: board private structure
571 * @status_err: receive descriptor status and error fields
572 * @skb: socket buffer with received data
573 **/
574static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
575			      struct sk_buff *skb)
576{
577	u16 status = (u16)status_err;
578	u8 errors = (u8)(status_err >> 24);
579
580	skb_checksum_none_assert(skb);
581
582	/* Rx checksum disabled */
583	if (!(adapter->netdev->features & NETIF_F_RXCSUM))
584		return;
585
586	/* Ignore Checksum bit is set */
587	if (status & E1000_RXD_STAT_IXSM)
588		return;
589
590	/* TCP/UDP checksum error bit or IP checksum error bit is set */
591	if (errors & (E1000_RXD_ERR_TCPE | E1000_RXD_ERR_IPE)) {
592		/* let the stack verify checksum errors */
593		adapter->hw_csum_err++;
594		return;
595	}
596
597	/* TCP/UDP Checksum has not been calculated */
598	if (!(status & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS)))
599		return;
600
601	/* It must be a TCP or UDP packet with a valid checksum */
602	skb->ip_summed = CHECKSUM_UNNECESSARY;
603	adapter->hw_csum_good++;
604}
605
606static void e1000e_update_rdt_wa(struct e1000_ring *rx_ring, unsigned int i)
607{
608	struct e1000_adapter *adapter = rx_ring->adapter;
609	struct e1000_hw *hw = &adapter->hw;
610
611	__ew32_prepare(hw);
612	writel(i, rx_ring->tail);
613
614	if (unlikely(i != readl(rx_ring->tail))) {
615		u32 rctl = er32(RCTL);
616
617		ew32(RCTL, rctl & ~E1000_RCTL_EN);
618		e_err("ME firmware caused invalid RDT - resetting\n");
619		schedule_work(&adapter->reset_task);
620	}
621}
622
623static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
624{
625	struct e1000_adapter *adapter = tx_ring->adapter;
626	struct e1000_hw *hw = &adapter->hw;
627
628	__ew32_prepare(hw);
629	writel(i, tx_ring->tail);
630
631	if (unlikely(i != readl(tx_ring->tail))) {
632		u32 tctl = er32(TCTL);
633
634		ew32(TCTL, tctl & ~E1000_TCTL_EN);
635		e_err("ME firmware caused invalid TDT - resetting\n");
636		schedule_work(&adapter->reset_task);
637	}
638}
639
640/**
641 * e1000_alloc_rx_buffers - Replace used receive buffers
642 * @rx_ring: Rx descriptor ring
643 * @cleaned_count: number to reallocate
644 * @gfp: flags for allocation
645 **/
646static void e1000_alloc_rx_buffers(struct e1000_ring *rx_ring,
647				   int cleaned_count, gfp_t gfp)
648{
649	struct e1000_adapter *adapter = rx_ring->adapter;
650	struct net_device *netdev = adapter->netdev;
651	struct pci_dev *pdev = adapter->pdev;
652	union e1000_rx_desc_extended *rx_desc;
653	struct e1000_buffer *buffer_info;
654	struct sk_buff *skb;
655	unsigned int i;
656	unsigned int bufsz = adapter->rx_buffer_len;
657
658	i = rx_ring->next_to_use;
659	buffer_info = &rx_ring->buffer_info[i];
660
661	while (cleaned_count--) {
662		skb = buffer_info->skb;
663		if (skb) {
664			skb_trim(skb, 0);
665			goto map_skb;
666		}
667
668		skb = __netdev_alloc_skb_ip_align(netdev, bufsz, gfp);
669		if (!skb) {
670			/* Better luck next round */
671			adapter->alloc_rx_buff_failed++;
672			break;
673		}
674
675		buffer_info->skb = skb;
676map_skb:
677		buffer_info->dma = dma_map_single(&pdev->dev, skb->data,
678						  adapter->rx_buffer_len,
679						  DMA_FROM_DEVICE);
680		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
681			dev_err(&pdev->dev, "Rx DMA map failed\n");
682			adapter->rx_dma_failed++;
683			break;
684		}
685
686		rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
687		rx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
688
689		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
690			/* Force memory writes to complete before letting h/w
691			 * know there are new descriptors to fetch.  (Only
692			 * applicable for weak-ordered memory model archs,
693			 * such as IA-64).
694			 */
695			wmb();
696			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
697				e1000e_update_rdt_wa(rx_ring, i);
698			else
699				writel(i, rx_ring->tail);
700		}
701		i++;
702		if (i == rx_ring->count)
703			i = 0;
704		buffer_info = &rx_ring->buffer_info[i];
705	}
706
707	rx_ring->next_to_use = i;
708}
709
710/**
711 * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split
712 * @rx_ring: Rx descriptor ring
713 * @cleaned_count: number to reallocate
714 * @gfp: flags for allocation
715 **/
716static void e1000_alloc_rx_buffers_ps(struct e1000_ring *rx_ring,
717				      int cleaned_count, gfp_t gfp)
718{
719	struct e1000_adapter *adapter = rx_ring->adapter;
720	struct net_device *netdev = adapter->netdev;
721	struct pci_dev *pdev = adapter->pdev;
722	union e1000_rx_desc_packet_split *rx_desc;
723	struct e1000_buffer *buffer_info;
724	struct e1000_ps_page *ps_page;
725	struct sk_buff *skb;
726	unsigned int i, j;
727
728	i = rx_ring->next_to_use;
729	buffer_info = &rx_ring->buffer_info[i];
730
731	while (cleaned_count--) {
732		rx_desc = E1000_RX_DESC_PS(*rx_ring, i);
733
734		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
735			ps_page = &buffer_info->ps_pages[j];
736			if (j >= adapter->rx_ps_pages) {
737				/* all unused desc entries get hw null ptr */
738				rx_desc->read.buffer_addr[j + 1] =
739				    ~cpu_to_le64(0);
740				continue;
741			}
742			if (!ps_page->page) {
743				ps_page->page = alloc_page(gfp);
744				if (!ps_page->page) {
745					adapter->alloc_rx_buff_failed++;
746					goto no_buffers;
747				}
748				ps_page->dma = dma_map_page(&pdev->dev,
749							    ps_page->page,
750							    0, PAGE_SIZE,
751							    DMA_FROM_DEVICE);
752				if (dma_mapping_error(&pdev->dev,
753						      ps_page->dma)) {
754					dev_err(&adapter->pdev->dev,
755						"Rx DMA page map failed\n");
756					adapter->rx_dma_failed++;
757					goto no_buffers;
758				}
759			}
760			/* Refresh the desc even if buffer_addrs
761			 * didn't change because each write-back
762			 * erases this info.
763			 */
764			rx_desc->read.buffer_addr[j + 1] =
765			    cpu_to_le64(ps_page->dma);
766		}
767
768		skb = __netdev_alloc_skb_ip_align(netdev, adapter->rx_ps_bsize0,
769						  gfp);
770
771		if (!skb) {
772			adapter->alloc_rx_buff_failed++;
773			break;
774		}
775
776		buffer_info->skb = skb;
777		buffer_info->dma = dma_map_single(&pdev->dev, skb->data,
778						  adapter->rx_ps_bsize0,
779						  DMA_FROM_DEVICE);
780		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
781			dev_err(&pdev->dev, "Rx DMA map failed\n");
782			adapter->rx_dma_failed++;
783			/* cleanup skb */
784			dev_kfree_skb_any(skb);
785			buffer_info->skb = NULL;
786			break;
787		}
788
789		rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma);
790
791		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
792			/* Force memory writes to complete before letting h/w
793			 * know there are new descriptors to fetch.  (Only
794			 * applicable for weak-ordered memory model archs,
795			 * such as IA-64).
796			 */
797			wmb();
798			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
799				e1000e_update_rdt_wa(rx_ring, i << 1);
800			else
801				writel(i << 1, rx_ring->tail);
802		}
803
804		i++;
805		if (i == rx_ring->count)
806			i = 0;
807		buffer_info = &rx_ring->buffer_info[i];
808	}
809
810no_buffers:
811	rx_ring->next_to_use = i;
812}
813
814/**
815 * e1000_alloc_jumbo_rx_buffers - Replace used jumbo receive buffers
816 * @rx_ring: Rx descriptor ring
817 * @cleaned_count: number of buffers to allocate this pass
818 * @gfp: flags for allocation
819 **/
820
821static void e1000_alloc_jumbo_rx_buffers(struct e1000_ring *rx_ring,
822					 int cleaned_count, gfp_t gfp)
823{
824	struct e1000_adapter *adapter = rx_ring->adapter;
825	struct net_device *netdev = adapter->netdev;
826	struct pci_dev *pdev = adapter->pdev;
827	union e1000_rx_desc_extended *rx_desc;
828	struct e1000_buffer *buffer_info;
829	struct sk_buff *skb;
830	unsigned int i;
831	unsigned int bufsz = 256 - 16;	/* for skb_reserve */
832
833	i = rx_ring->next_to_use;
834	buffer_info = &rx_ring->buffer_info[i];
835
836	while (cleaned_count--) {
837		skb = buffer_info->skb;
838		if (skb) {
839			skb_trim(skb, 0);
840			goto check_page;
841		}
842
843		skb = __netdev_alloc_skb_ip_align(netdev, bufsz, gfp);
844		if (unlikely(!skb)) {
845			/* Better luck next round */
846			adapter->alloc_rx_buff_failed++;
847			break;
848		}
849
850		buffer_info->skb = skb;
851check_page:
852		/* allocate a new page if necessary */
853		if (!buffer_info->page) {
854			buffer_info->page = alloc_page(gfp);
855			if (unlikely(!buffer_info->page)) {
856				adapter->alloc_rx_buff_failed++;
857				break;
858			}
859		}
860
861		if (!buffer_info->dma) {
862			buffer_info->dma = dma_map_page(&pdev->dev,
863							buffer_info->page, 0,
864							PAGE_SIZE,
865							DMA_FROM_DEVICE);
866			if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
867				adapter->alloc_rx_buff_failed++;
868				break;
869			}
870		}
871
872		rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
873		rx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
874
875		if (unlikely(++i == rx_ring->count))
876			i = 0;
877		buffer_info = &rx_ring->buffer_info[i];
878	}
879
880	if (likely(rx_ring->next_to_use != i)) {
881		rx_ring->next_to_use = i;
882		if (unlikely(i-- == 0))
883			i = (rx_ring->count - 1);
884
885		/* Force memory writes to complete before letting h/w
886		 * know there are new descriptors to fetch.  (Only
887		 * applicable for weak-ordered memory model archs,
888		 * such as IA-64).
889		 */
890		wmb();
891		if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
892			e1000e_update_rdt_wa(rx_ring, i);
893		else
894			writel(i, rx_ring->tail);
895	}
896}
897
898static inline void e1000_rx_hash(struct net_device *netdev, __le32 rss,
899				 struct sk_buff *skb)
900{
901	if (netdev->features & NETIF_F_RXHASH)
902		skb_set_hash(skb, le32_to_cpu(rss), PKT_HASH_TYPE_L3);
903}
904
905/**
906 * e1000_clean_rx_irq - Send received data up the network stack
907 * @rx_ring: Rx descriptor ring
908 * @work_done: output parameter for indicating completed work
909 * @work_to_do: how many packets we can clean
910 *
911 * the return value indicates whether actual cleaning was done, there
912 * is no guarantee that everything was cleaned
913 **/
914static bool e1000_clean_rx_irq(struct e1000_ring *rx_ring, int *work_done,
915			       int work_to_do)
916{
917	struct e1000_adapter *adapter = rx_ring->adapter;
918	struct net_device *netdev = adapter->netdev;
919	struct pci_dev *pdev = adapter->pdev;
920	struct e1000_hw *hw = &adapter->hw;
921	union e1000_rx_desc_extended *rx_desc, *next_rxd;
922	struct e1000_buffer *buffer_info, *next_buffer;
923	u32 length, staterr;
924	unsigned int i;
925	int cleaned_count = 0;
926	bool cleaned = false;
927	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
928
929	i = rx_ring->next_to_clean;
930	rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
931	staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
932	buffer_info = &rx_ring->buffer_info[i];
933
934	while (staterr & E1000_RXD_STAT_DD) {
935		struct sk_buff *skb;
936
937		if (*work_done >= work_to_do)
938			break;
939		(*work_done)++;
940		dma_rmb();	/* read descriptor and rx_buffer_info after status DD */
941
942		skb = buffer_info->skb;
943		buffer_info->skb = NULL;
944
945		prefetch(skb->data - NET_IP_ALIGN);
946
947		i++;
948		if (i == rx_ring->count)
949			i = 0;
950		next_rxd = E1000_RX_DESC_EXT(*rx_ring, i);
951		prefetch(next_rxd);
952
953		next_buffer = &rx_ring->buffer_info[i];
954
955		cleaned = true;
956		cleaned_count++;
957		dma_unmap_single(&pdev->dev, buffer_info->dma,
958				 adapter->rx_buffer_len, DMA_FROM_DEVICE);
959		buffer_info->dma = 0;
960
961		length = le16_to_cpu(rx_desc->wb.upper.length);
962
963		/* !EOP means multiple descriptors were used to store a single
964		 * packet, if that's the case we need to toss it.  In fact, we
965		 * need to toss every packet with the EOP bit clear and the
966		 * next frame that _does_ have the EOP bit set, as it is by
967		 * definition only a frame fragment
968		 */
969		if (unlikely(!(staterr & E1000_RXD_STAT_EOP)))
970			adapter->flags2 |= FLAG2_IS_DISCARDING;
971
972		if (adapter->flags2 & FLAG2_IS_DISCARDING) {
973			/* All receives must fit into a single buffer */
974			e_dbg("Receive packet consumed multiple buffers\n");
975			/* recycle */
976			buffer_info->skb = skb;
977			if (staterr & E1000_RXD_STAT_EOP)
978				adapter->flags2 &= ~FLAG2_IS_DISCARDING;
979			goto next_desc;
980		}
981
982		if (unlikely((staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) &&
983			     !(netdev->features & NETIF_F_RXALL))) {
984			/* recycle */
985			buffer_info->skb = skb;
986			goto next_desc;
987		}
988
989		/* adjust length to remove Ethernet CRC */
990		if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) {
991			/* If configured to store CRC, don't subtract FCS,
992			 * but keep the FCS bytes out of the total_rx_bytes
993			 * counter
994			 */
995			if (netdev->features & NETIF_F_RXFCS)
996				total_rx_bytes -= 4;
997			else
998				length -= 4;
999		}
1000
1001		total_rx_bytes += length;
1002		total_rx_packets++;
1003
1004		/* code added for copybreak, this should improve
1005		 * performance for small packets with large amounts
1006		 * of reassembly being done in the stack
1007		 */
1008		if (length < copybreak) {
1009			struct sk_buff *new_skb =
1010				napi_alloc_skb(&adapter->napi, length);
1011			if (new_skb) {
1012				skb_copy_to_linear_data_offset(new_skb,
1013							       -NET_IP_ALIGN,
1014							       (skb->data -
1015								NET_IP_ALIGN),
1016							       (length +
1017								NET_IP_ALIGN));
1018				/* save the skb in buffer_info as good */
1019				buffer_info->skb = skb;
1020				skb = new_skb;
1021			}
1022			/* else just continue with the old one */
1023		}
1024		/* end copybreak code */
1025		skb_put(skb, length);
1026
1027		/* Receive Checksum Offload */
1028		e1000_rx_checksum(adapter, staterr, skb);
1029
1030		e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb);
1031
1032		e1000_receive_skb(adapter, netdev, skb, staterr,
1033				  rx_desc->wb.upper.vlan);
1034
1035next_desc:
1036		rx_desc->wb.upper.status_error &= cpu_to_le32(~0xFF);
1037
1038		/* return some buffers to hardware, one at a time is too slow */
1039		if (cleaned_count >= E1000_RX_BUFFER_WRITE) {
1040			adapter->alloc_rx_buf(rx_ring, cleaned_count,
1041					      GFP_ATOMIC);
1042			cleaned_count = 0;
1043		}
1044
1045		/* use prefetched values */
1046		rx_desc = next_rxd;
1047		buffer_info = next_buffer;
1048
1049		staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
1050	}
1051	rx_ring->next_to_clean = i;
1052
1053	cleaned_count = e1000_desc_unused(rx_ring);
1054	if (cleaned_count)
1055		adapter->alloc_rx_buf(rx_ring, cleaned_count, GFP_ATOMIC);
1056
1057	adapter->total_rx_bytes += total_rx_bytes;
1058	adapter->total_rx_packets += total_rx_packets;
1059	return cleaned;
1060}
1061
1062static void e1000_put_txbuf(struct e1000_ring *tx_ring,
1063			    struct e1000_buffer *buffer_info,
1064			    bool drop)
1065{
1066	struct e1000_adapter *adapter = tx_ring->adapter;
1067
1068	if (buffer_info->dma) {
1069		if (buffer_info->mapped_as_page)
1070			dma_unmap_page(&adapter->pdev->dev, buffer_info->dma,
1071				       buffer_info->length, DMA_TO_DEVICE);
1072		else
1073			dma_unmap_single(&adapter->pdev->dev, buffer_info->dma,
1074					 buffer_info->length, DMA_TO_DEVICE);
1075		buffer_info->dma = 0;
1076	}
1077	if (buffer_info->skb) {
1078		if (drop)
1079			dev_kfree_skb_any(buffer_info->skb);
1080		else
1081			dev_consume_skb_any(buffer_info->skb);
1082		buffer_info->skb = NULL;
1083	}
1084	buffer_info->time_stamp = 0;
1085}
1086
1087static void e1000_print_hw_hang(struct work_struct *work)
1088{
1089	struct e1000_adapter *adapter = container_of(work,
1090						     struct e1000_adapter,
1091						     print_hang_task);
1092	struct net_device *netdev = adapter->netdev;
1093	struct e1000_ring *tx_ring = adapter->tx_ring;
1094	unsigned int i = tx_ring->next_to_clean;
1095	unsigned int eop = tx_ring->buffer_info[i].next_to_watch;
1096	struct e1000_tx_desc *eop_desc = E1000_TX_DESC(*tx_ring, eop);
1097	struct e1000_hw *hw = &adapter->hw;
1098	u16 phy_status, phy_1000t_status, phy_ext_status;
1099	u16 pci_status;
1100
1101	if (test_bit(__E1000_DOWN, &adapter->state))
1102		return;
1103
1104	if (!adapter->tx_hang_recheck && (adapter->flags2 & FLAG2_DMA_BURST)) {
1105		/* May be block on write-back, flush and detect again
1106		 * flush pending descriptor writebacks to memory
1107		 */
1108		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
1109		/* execute the writes immediately */
1110		e1e_flush();
1111		/* Due to rare timing issues, write to TIDV again to ensure
1112		 * the write is successful
1113		 */
1114		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
1115		/* execute the writes immediately */
1116		e1e_flush();
1117		adapter->tx_hang_recheck = true;
1118		return;
1119	}
1120	adapter->tx_hang_recheck = false;
1121
1122	if (er32(TDH(0)) == er32(TDT(0))) {
1123		e_dbg("false hang detected, ignoring\n");
1124		return;
1125	}
1126
1127	/* Real hang detected */
1128	netif_stop_queue(netdev);
1129
1130	e1e_rphy(hw, MII_BMSR, &phy_status);
1131	e1e_rphy(hw, MII_STAT1000, &phy_1000t_status);
1132	e1e_rphy(hw, MII_ESTATUS, &phy_ext_status);
1133
1134	pci_read_config_word(adapter->pdev, PCI_STATUS, &pci_status);
1135
1136	/* detected Hardware unit hang */
1137	e_err("Detected Hardware Unit Hang:\n"
1138	      "  TDH                  <%x>\n"
1139	      "  TDT                  <%x>\n"
1140	      "  next_to_use          <%x>\n"
1141	      "  next_to_clean        <%x>\n"
1142	      "buffer_info[next_to_clean]:\n"
1143	      "  time_stamp           <%lx>\n"
1144	      "  next_to_watch        <%x>\n"
1145	      "  jiffies              <%lx>\n"
1146	      "  next_to_watch.status <%x>\n"
1147	      "MAC Status             <%x>\n"
1148	      "PHY Status             <%x>\n"
1149	      "PHY 1000BASE-T Status  <%x>\n"
1150	      "PHY Extended Status    <%x>\n"
1151	      "PCI Status             <%x>\n",
1152	      readl(tx_ring->head), readl(tx_ring->tail), tx_ring->next_to_use,
1153	      tx_ring->next_to_clean, tx_ring->buffer_info[eop].time_stamp,
1154	      eop, jiffies, eop_desc->upper.fields.status, er32(STATUS),
1155	      phy_status, phy_1000t_status, phy_ext_status, pci_status);
1156
1157	e1000e_dump(adapter);
1158
1159	/* Suggest workaround for known h/w issue */
1160	if ((hw->mac.type == e1000_pchlan) && (er32(CTRL) & E1000_CTRL_TFCE))
1161		e_err("Try turning off Tx pause (flow control) via ethtool\n");
1162}
1163
1164/**
1165 * e1000e_tx_hwtstamp_work - check for Tx time stamp
1166 * @work: pointer to work struct
1167 *
1168 * This work function polls the TSYNCTXCTL valid bit to determine when a
1169 * timestamp has been taken for the current stored skb.  The timestamp must
1170 * be for this skb because only one such packet is allowed in the queue.
1171 */
1172static void e1000e_tx_hwtstamp_work(struct work_struct *work)
1173{
1174	struct e1000_adapter *adapter = container_of(work, struct e1000_adapter,
1175						     tx_hwtstamp_work);
1176	struct e1000_hw *hw = &adapter->hw;
1177
1178	if (er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID) {
1179		struct sk_buff *skb = adapter->tx_hwtstamp_skb;
1180		struct skb_shared_hwtstamps shhwtstamps;
1181		u64 txstmp;
1182
1183		txstmp = er32(TXSTMPL);
1184		txstmp |= (u64)er32(TXSTMPH) << 32;
1185
1186		e1000e_systim_to_hwtstamp(adapter, &shhwtstamps, txstmp);
1187
1188		/* Clear the global tx_hwtstamp_skb pointer and force writes
1189		 * prior to notifying the stack of a Tx timestamp.
1190		 */
1191		adapter->tx_hwtstamp_skb = NULL;
1192		wmb(); /* force write prior to skb_tstamp_tx */
1193
1194		skb_tstamp_tx(skb, &shhwtstamps);
1195		dev_consume_skb_any(skb);
1196	} else if (time_after(jiffies, adapter->tx_hwtstamp_start
1197			      + adapter->tx_timeout_factor * HZ)) {
1198		dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
1199		adapter->tx_hwtstamp_skb = NULL;
1200		adapter->tx_hwtstamp_timeouts++;
1201		e_warn("clearing Tx timestamp hang\n");
1202	} else {
1203		/* reschedule to check later */
1204		schedule_work(&adapter->tx_hwtstamp_work);
1205	}
1206}
1207
1208/**
1209 * e1000_clean_tx_irq - Reclaim resources after transmit completes
1210 * @tx_ring: Tx descriptor ring
1211 *
1212 * the return value indicates whether actual cleaning was done, there
1213 * is no guarantee that everything was cleaned
1214 **/
1215static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring)
1216{
1217	struct e1000_adapter *adapter = tx_ring->adapter;
1218	struct net_device *netdev = adapter->netdev;
1219	struct e1000_hw *hw = &adapter->hw;
1220	struct e1000_tx_desc *tx_desc, *eop_desc;
1221	struct e1000_buffer *buffer_info;
1222	unsigned int i, eop;
1223	unsigned int count = 0;
1224	unsigned int total_tx_bytes = 0, total_tx_packets = 0;
1225	unsigned int bytes_compl = 0, pkts_compl = 0;
1226
1227	i = tx_ring->next_to_clean;
1228	eop = tx_ring->buffer_info[i].next_to_watch;
1229	eop_desc = E1000_TX_DESC(*tx_ring, eop);
1230
1231	while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) &&
1232	       (count < tx_ring->count)) {
1233		bool cleaned = false;
1234
1235		dma_rmb();		/* read buffer_info after eop_desc */
1236		for (; !cleaned; count++) {
1237			tx_desc = E1000_TX_DESC(*tx_ring, i);
1238			buffer_info = &tx_ring->buffer_info[i];
1239			cleaned = (i == eop);
1240
1241			if (cleaned) {
1242				total_tx_packets += buffer_info->segs;
1243				total_tx_bytes += buffer_info->bytecount;
1244				if (buffer_info->skb) {
1245					bytes_compl += buffer_info->skb->len;
1246					pkts_compl++;
1247				}
1248			}
1249
1250			e1000_put_txbuf(tx_ring, buffer_info, false);
1251			tx_desc->upper.data = 0;
1252
1253			i++;
1254			if (i == tx_ring->count)
1255				i = 0;
1256		}
1257
1258		if (i == tx_ring->next_to_use)
1259			break;
1260		eop = tx_ring->buffer_info[i].next_to_watch;
1261		eop_desc = E1000_TX_DESC(*tx_ring, eop);
1262	}
1263
1264	tx_ring->next_to_clean = i;
1265
1266	netdev_completed_queue(netdev, pkts_compl, bytes_compl);
1267
1268#define TX_WAKE_THRESHOLD 32
1269	if (count && netif_carrier_ok(netdev) &&
1270	    e1000_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD) {
1271		/* Make sure that anybody stopping the queue after this
1272		 * sees the new next_to_clean.
1273		 */
1274		smp_mb();
1275
1276		if (netif_queue_stopped(netdev) &&
1277		    !(test_bit(__E1000_DOWN, &adapter->state))) {
1278			netif_wake_queue(netdev);
1279			++adapter->restart_queue;
1280		}
1281	}
1282
1283	if (adapter->detect_tx_hung) {
1284		/* Detect a transmit hang in hardware, this serializes the
1285		 * check with the clearing of time_stamp and movement of i
1286		 */
1287		adapter->detect_tx_hung = false;
1288		if (tx_ring->buffer_info[i].time_stamp &&
1289		    time_after(jiffies, tx_ring->buffer_info[i].time_stamp
1290			       + (adapter->tx_timeout_factor * HZ)) &&
1291		    !(er32(STATUS) & E1000_STATUS_TXOFF))
1292			schedule_work(&adapter->print_hang_task);
1293		else
1294			adapter->tx_hang_recheck = false;
1295	}
1296	adapter->total_tx_bytes += total_tx_bytes;
1297	adapter->total_tx_packets += total_tx_packets;
1298	return count < tx_ring->count;
1299}
1300
1301/**
1302 * e1000_clean_rx_irq_ps - Send received data up the network stack; packet split
1303 * @rx_ring: Rx descriptor ring
1304 * @work_done: output parameter for indicating completed work
1305 * @work_to_do: how many packets we can clean
1306 *
1307 * the return value indicates whether actual cleaning was done, there
1308 * is no guarantee that everything was cleaned
1309 **/
1310static bool e1000_clean_rx_irq_ps(struct e1000_ring *rx_ring, int *work_done,
1311				  int work_to_do)
1312{
1313	struct e1000_adapter *adapter = rx_ring->adapter;
1314	struct e1000_hw *hw = &adapter->hw;
1315	union e1000_rx_desc_packet_split *rx_desc, *next_rxd;
1316	struct net_device *netdev = adapter->netdev;
1317	struct pci_dev *pdev = adapter->pdev;
1318	struct e1000_buffer *buffer_info, *next_buffer;
1319	struct e1000_ps_page *ps_page;
1320	struct sk_buff *skb;
1321	unsigned int i, j;
1322	u32 length, staterr;
1323	int cleaned_count = 0;
1324	bool cleaned = false;
1325	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
1326
1327	i = rx_ring->next_to_clean;
1328	rx_desc = E1000_RX_DESC_PS(*rx_ring, i);
1329	staterr = le32_to_cpu(rx_desc->wb.middle.status_error);
1330	buffer_info = &rx_ring->buffer_info[i];
1331
1332	while (staterr & E1000_RXD_STAT_DD) {
1333		if (*work_done >= work_to_do)
1334			break;
1335		(*work_done)++;
1336		skb = buffer_info->skb;
1337		dma_rmb();	/* read descriptor and rx_buffer_info after status DD */
1338
1339		/* in the packet split case this is header only */
1340		prefetch(skb->data - NET_IP_ALIGN);
1341
1342		i++;
1343		if (i == rx_ring->count)
1344			i = 0;
1345		next_rxd = E1000_RX_DESC_PS(*rx_ring, i);
1346		prefetch(next_rxd);
1347
1348		next_buffer = &rx_ring->buffer_info[i];
1349
1350		cleaned = true;
1351		cleaned_count++;
1352		dma_unmap_single(&pdev->dev, buffer_info->dma,
1353				 adapter->rx_ps_bsize0, DMA_FROM_DEVICE);
1354		buffer_info->dma = 0;
1355
1356		/* see !EOP comment in other Rx routine */
1357		if (!(staterr & E1000_RXD_STAT_EOP))
1358			adapter->flags2 |= FLAG2_IS_DISCARDING;
1359
1360		if (adapter->flags2 & FLAG2_IS_DISCARDING) {
1361			e_dbg("Packet Split buffers didn't pick up the full packet\n");
1362			dev_kfree_skb_irq(skb);
1363			if (staterr & E1000_RXD_STAT_EOP)
1364				adapter->flags2 &= ~FLAG2_IS_DISCARDING;
1365			goto next_desc;
1366		}
1367
1368		if (unlikely((staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) &&
1369			     !(netdev->features & NETIF_F_RXALL))) {
1370			dev_kfree_skb_irq(skb);
1371			goto next_desc;
1372		}
1373
1374		length = le16_to_cpu(rx_desc->wb.middle.length0);
1375
1376		if (!length) {
1377			e_dbg("Last part of the packet spanning multiple descriptors\n");
1378			dev_kfree_skb_irq(skb);
1379			goto next_desc;
1380		}
1381
1382		/* Good Receive */
1383		skb_put(skb, length);
1384
1385		{
1386			/* this looks ugly, but it seems compiler issues make
1387			 * it more efficient than reusing j
1388			 */
1389			int l1 = le16_to_cpu(rx_desc->wb.upper.length[0]);
1390
1391			/* page alloc/put takes too long and effects small
1392			 * packet throughput, so unsplit small packets and
1393			 * save the alloc/put
1394			 */
1395			if (l1 && (l1 <= copybreak) &&
1396			    ((length + l1) <= adapter->rx_ps_bsize0)) {
1397				ps_page = &buffer_info->ps_pages[0];
1398
1399				dma_sync_single_for_cpu(&pdev->dev,
1400							ps_page->dma,
1401							PAGE_SIZE,
1402							DMA_FROM_DEVICE);
1403				memcpy(skb_tail_pointer(skb),
1404				       page_address(ps_page->page), l1);
1405				dma_sync_single_for_device(&pdev->dev,
1406							   ps_page->dma,
1407							   PAGE_SIZE,
1408							   DMA_FROM_DEVICE);
1409
1410				/* remove the CRC */
1411				if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) {
1412					if (!(netdev->features & NETIF_F_RXFCS))
1413						l1 -= 4;
1414				}
1415
1416				skb_put(skb, l1);
1417				goto copydone;
1418			}	/* if */
1419		}
1420
1421		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
1422			length = le16_to_cpu(rx_desc->wb.upper.length[j]);
1423			if (!length)
1424				break;
1425
1426			ps_page = &buffer_info->ps_pages[j];
1427			dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE,
1428				       DMA_FROM_DEVICE);
1429			ps_page->dma = 0;
1430			skb_fill_page_desc(skb, j, ps_page->page, 0, length);
1431			ps_page->page = NULL;
1432			skb->len += length;
1433			skb->data_len += length;
1434			skb->truesize += PAGE_SIZE;
1435		}
1436
1437		/* strip the ethernet crc, problem is we're using pages now so
1438		 * this whole operation can get a little cpu intensive
1439		 */
1440		if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) {
1441			if (!(netdev->features & NETIF_F_RXFCS))
1442				pskb_trim(skb, skb->len - 4);
1443		}
1444
1445copydone:
1446		total_rx_bytes += skb->len;
1447		total_rx_packets++;
1448
1449		e1000_rx_checksum(adapter, staterr, skb);
1450
1451		e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb);
1452
1453		if (rx_desc->wb.upper.header_status &
1454		    cpu_to_le16(E1000_RXDPS_HDRSTAT_HDRSP))
1455			adapter->rx_hdr_split++;
1456
1457		e1000_receive_skb(adapter, netdev, skb, staterr,
1458				  rx_desc->wb.middle.vlan);
1459
1460next_desc:
1461		rx_desc->wb.middle.status_error &= cpu_to_le32(~0xFF);
1462		buffer_info->skb = NULL;
1463
1464		/* return some buffers to hardware, one at a time is too slow */
1465		if (cleaned_count >= E1000_RX_BUFFER_WRITE) {
1466			adapter->alloc_rx_buf(rx_ring, cleaned_count,
1467					      GFP_ATOMIC);
1468			cleaned_count = 0;
1469		}
1470
1471		/* use prefetched values */
1472		rx_desc = next_rxd;
1473		buffer_info = next_buffer;
1474
1475		staterr = le32_to_cpu(rx_desc->wb.middle.status_error);
1476	}
1477	rx_ring->next_to_clean = i;
1478
1479	cleaned_count = e1000_desc_unused(rx_ring);
1480	if (cleaned_count)
1481		adapter->alloc_rx_buf(rx_ring, cleaned_count, GFP_ATOMIC);
1482
1483	adapter->total_rx_bytes += total_rx_bytes;
1484	adapter->total_rx_packets += total_rx_packets;
1485	return cleaned;
1486}
1487
1488static void e1000_consume_page(struct e1000_buffer *bi, struct sk_buff *skb,
1489			       u16 length)
1490{
1491	bi->page = NULL;
1492	skb->len += length;
1493	skb->data_len += length;
1494	skb->truesize += PAGE_SIZE;
1495}
1496
1497/**
1498 * e1000_clean_jumbo_rx_irq - Send received data up the network stack; legacy
1499 * @rx_ring: Rx descriptor ring
1500 * @work_done: output parameter for indicating completed work
1501 * @work_to_do: how many packets we can clean
1502 *
1503 * the return value indicates whether actual cleaning was done, there
1504 * is no guarantee that everything was cleaned
1505 **/
1506static bool e1000_clean_jumbo_rx_irq(struct e1000_ring *rx_ring, int *work_done,
1507				     int work_to_do)
1508{
1509	struct e1000_adapter *adapter = rx_ring->adapter;
1510	struct net_device *netdev = adapter->netdev;
1511	struct pci_dev *pdev = adapter->pdev;
1512	union e1000_rx_desc_extended *rx_desc, *next_rxd;
1513	struct e1000_buffer *buffer_info, *next_buffer;
1514	u32 length, staterr;
1515	unsigned int i;
1516	int cleaned_count = 0;
1517	bool cleaned = false;
1518	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
1519	struct skb_shared_info *shinfo;
1520
1521	i = rx_ring->next_to_clean;
1522	rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
1523	staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
1524	buffer_info = &rx_ring->buffer_info[i];
1525
1526	while (staterr & E1000_RXD_STAT_DD) {
1527		struct sk_buff *skb;
1528
1529		if (*work_done >= work_to_do)
1530			break;
1531		(*work_done)++;
1532		dma_rmb();	/* read descriptor and rx_buffer_info after status DD */
1533
1534		skb = buffer_info->skb;
1535		buffer_info->skb = NULL;
1536
1537		++i;
1538		if (i == rx_ring->count)
1539			i = 0;
1540		next_rxd = E1000_RX_DESC_EXT(*rx_ring, i);
1541		prefetch(next_rxd);
1542
1543		next_buffer = &rx_ring->buffer_info[i];
1544
1545		cleaned = true;
1546		cleaned_count++;
1547		dma_unmap_page(&pdev->dev, buffer_info->dma, PAGE_SIZE,
1548			       DMA_FROM_DEVICE);
1549		buffer_info->dma = 0;
1550
1551		length = le16_to_cpu(rx_desc->wb.upper.length);
1552
1553		/* errors is only valid for DD + EOP descriptors */
1554		if (unlikely((staterr & E1000_RXD_STAT_EOP) &&
1555			     ((staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) &&
1556			      !(netdev->features & NETIF_F_RXALL)))) {
1557			/* recycle both page and skb */
1558			buffer_info->skb = skb;
1559			/* an error means any chain goes out the window too */
1560			if (rx_ring->rx_skb_top)
1561				dev_kfree_skb_irq(rx_ring->rx_skb_top);
1562			rx_ring->rx_skb_top = NULL;
1563			goto next_desc;
1564		}
1565#define rxtop (rx_ring->rx_skb_top)
1566		if (!(staterr & E1000_RXD_STAT_EOP)) {
1567			/* this descriptor is only the beginning (or middle) */
1568			if (!rxtop) {
1569				/* this is the beginning of a chain */
1570				rxtop = skb;
1571				skb_fill_page_desc(rxtop, 0, buffer_info->page,
1572						   0, length);
1573			} else {
1574				/* this is the middle of a chain */
1575				shinfo = skb_shinfo(rxtop);
1576				skb_fill_page_desc(rxtop, shinfo->nr_frags,
1577						   buffer_info->page, 0,
1578						   length);
1579				/* re-use the skb, only consumed the page */
1580				buffer_info->skb = skb;
1581			}
1582			e1000_consume_page(buffer_info, rxtop, length);
1583			goto next_desc;
1584		} else {
1585			if (rxtop) {
1586				/* end of the chain */
1587				shinfo = skb_shinfo(rxtop);
1588				skb_fill_page_desc(rxtop, shinfo->nr_frags,
1589						   buffer_info->page, 0,
1590						   length);
1591				/* re-use the current skb, we only consumed the
1592				 * page
1593				 */
1594				buffer_info->skb = skb;
1595				skb = rxtop;
1596				rxtop = NULL;
1597				e1000_consume_page(buffer_info, skb, length);
1598			} else {
1599				/* no chain, got EOP, this buf is the packet
1600				 * copybreak to save the put_page/alloc_page
1601				 */
1602				if (length <= copybreak &&
1603				    skb_tailroom(skb) >= length) {
1604					memcpy(skb_tail_pointer(skb),
1605					       page_address(buffer_info->page),
1606					       length);
1607					/* re-use the page, so don't erase
1608					 * buffer_info->page
1609					 */
1610					skb_put(skb, length);
1611				} else {
1612					skb_fill_page_desc(skb, 0,
1613							   buffer_info->page, 0,
1614							   length);
1615					e1000_consume_page(buffer_info, skb,
1616							   length);
1617				}
1618			}
1619		}
1620
1621		/* Receive Checksum Offload */
1622		e1000_rx_checksum(adapter, staterr, skb);
1623
1624		e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb);
1625
1626		/* probably a little skewed due to removing CRC */
1627		total_rx_bytes += skb->len;
1628		total_rx_packets++;
1629
1630		/* eth type trans needs skb->data to point to something */
1631		if (!pskb_may_pull(skb, ETH_HLEN)) {
1632			e_err("pskb_may_pull failed.\n");
1633			dev_kfree_skb_irq(skb);
1634			goto next_desc;
1635		}
1636
1637		e1000_receive_skb(adapter, netdev, skb, staterr,
1638				  rx_desc->wb.upper.vlan);
1639
1640next_desc:
1641		rx_desc->wb.upper.status_error &= cpu_to_le32(~0xFF);
1642
1643		/* return some buffers to hardware, one at a time is too slow */
1644		if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) {
1645			adapter->alloc_rx_buf(rx_ring, cleaned_count,
1646					      GFP_ATOMIC);
1647			cleaned_count = 0;
1648		}
1649
1650		/* use prefetched values */
1651		rx_desc = next_rxd;
1652		buffer_info = next_buffer;
1653
1654		staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
1655	}
1656	rx_ring->next_to_clean = i;
1657
1658	cleaned_count = e1000_desc_unused(rx_ring);
1659	if (cleaned_count)
1660		adapter->alloc_rx_buf(rx_ring, cleaned_count, GFP_ATOMIC);
1661
1662	adapter->total_rx_bytes += total_rx_bytes;
1663	adapter->total_rx_packets += total_rx_packets;
1664	return cleaned;
1665}
1666
1667/**
1668 * e1000_clean_rx_ring - Free Rx Buffers per Queue
1669 * @rx_ring: Rx descriptor ring
1670 **/
1671static void e1000_clean_rx_ring(struct e1000_ring *rx_ring)
1672{
1673	struct e1000_adapter *adapter = rx_ring->adapter;
1674	struct e1000_buffer *buffer_info;
1675	struct e1000_ps_page *ps_page;
1676	struct pci_dev *pdev = adapter->pdev;
1677	unsigned int i, j;
1678
1679	/* Free all the Rx ring sk_buffs */
1680	for (i = 0; i < rx_ring->count; i++) {
1681		buffer_info = &rx_ring->buffer_info[i];
1682		if (buffer_info->dma) {
1683			if (adapter->clean_rx == e1000_clean_rx_irq)
1684				dma_unmap_single(&pdev->dev, buffer_info->dma,
1685						 adapter->rx_buffer_len,
1686						 DMA_FROM_DEVICE);
1687			else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq)
1688				dma_unmap_page(&pdev->dev, buffer_info->dma,
1689					       PAGE_SIZE, DMA_FROM_DEVICE);
1690			else if (adapter->clean_rx == e1000_clean_rx_irq_ps)
1691				dma_unmap_single(&pdev->dev, buffer_info->dma,
1692						 adapter->rx_ps_bsize0,
1693						 DMA_FROM_DEVICE);
1694			buffer_info->dma = 0;
1695		}
1696
1697		if (buffer_info->page) {
1698			put_page(buffer_info->page);
1699			buffer_info->page = NULL;
1700		}
1701
1702		if (buffer_info->skb) {
1703			dev_kfree_skb(buffer_info->skb);
1704			buffer_info->skb = NULL;
1705		}
1706
1707		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
1708			ps_page = &buffer_info->ps_pages[j];
1709			if (!ps_page->page)
1710				break;
1711			dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE,
1712				       DMA_FROM_DEVICE);
1713			ps_page->dma = 0;
1714			put_page(ps_page->page);
1715			ps_page->page = NULL;
1716		}
1717	}
1718
1719	/* there also may be some cached data from a chained receive */
1720	if (rx_ring->rx_skb_top) {
1721		dev_kfree_skb(rx_ring->rx_skb_top);
1722		rx_ring->rx_skb_top = NULL;
1723	}
1724
1725	/* Zero out the descriptor ring */
1726	memset(rx_ring->desc, 0, rx_ring->size);
1727
1728	rx_ring->next_to_clean = 0;
1729	rx_ring->next_to_use = 0;
1730	adapter->flags2 &= ~FLAG2_IS_DISCARDING;
1731}
1732
1733static void e1000e_downshift_workaround(struct work_struct *work)
1734{
1735	struct e1000_adapter *adapter = container_of(work,
1736						     struct e1000_adapter,
1737						     downshift_task);
1738
1739	if (test_bit(__E1000_DOWN, &adapter->state))
1740		return;
1741
1742	e1000e_gig_downshift_workaround_ich8lan(&adapter->hw);
1743}
1744
1745/**
1746 * e1000_intr_msi - Interrupt Handler
1747 * @irq: interrupt number
1748 * @data: pointer to a network interface device structure
1749 **/
1750static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
1751{
1752	struct net_device *netdev = data;
1753	struct e1000_adapter *adapter = netdev_priv(netdev);
1754	struct e1000_hw *hw = &adapter->hw;
1755	u32 icr = er32(ICR);
1756
1757	/* read ICR disables interrupts using IAM */
1758	if (icr & E1000_ICR_LSC) {
1759		hw->mac.get_link_status = true;
1760		/* ICH8 workaround-- Call gig speed drop workaround on cable
1761		 * disconnect (LSC) before accessing any PHY registers
1762		 */
1763		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
1764		    (!(er32(STATUS) & E1000_STATUS_LU)))
1765			schedule_work(&adapter->downshift_task);
1766
1767		/* 80003ES2LAN workaround-- For packet buffer work-around on
1768		 * link down event; disable receives here in the ISR and reset
1769		 * adapter in watchdog
1770		 */
1771		if (netif_carrier_ok(netdev) &&
1772		    adapter->flags & FLAG_RX_NEEDS_RESTART) {
1773			/* disable receives */
1774			u32 rctl = er32(RCTL);
1775
1776			ew32(RCTL, rctl & ~E1000_RCTL_EN);
1777			adapter->flags |= FLAG_RESTART_NOW;
1778		}
1779		/* guard against interrupt when we're going down */
1780		if (!test_bit(__E1000_DOWN, &adapter->state))
1781			mod_timer(&adapter->watchdog_timer, jiffies + 1);
1782	}
1783
1784	/* Reset on uncorrectable ECC error */
1785	if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) {
1786		u32 pbeccsts = er32(PBECCSTS);
1787
1788		adapter->corr_errors +=
1789		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
1790		adapter->uncorr_errors +=
1791		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
1792		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
1793
1794		/* Do the reset outside of interrupt context */
1795		schedule_work(&adapter->reset_task);
1796
1797		/* return immediately since reset is imminent */
1798		return IRQ_HANDLED;
1799	}
1800
1801	if (napi_schedule_prep(&adapter->napi)) {
1802		adapter->total_tx_bytes = 0;
1803		adapter->total_tx_packets = 0;
1804		adapter->total_rx_bytes = 0;
1805		adapter->total_rx_packets = 0;
1806		__napi_schedule(&adapter->napi);
1807	}
1808
1809	return IRQ_HANDLED;
1810}
1811
1812/**
1813 * e1000_intr - Interrupt Handler
1814 * @irq: interrupt number
1815 * @data: pointer to a network interface device structure
1816 **/
1817static irqreturn_t e1000_intr(int __always_unused irq, void *data)
1818{
1819	struct net_device *netdev = data;
1820	struct e1000_adapter *adapter = netdev_priv(netdev);
1821	struct e1000_hw *hw = &adapter->hw;
1822	u32 rctl, icr = er32(ICR);
1823
1824	if (!icr || test_bit(__E1000_DOWN, &adapter->state))
1825		return IRQ_NONE;	/* Not our interrupt */
1826
1827	/* IMS will not auto-mask if INT_ASSERTED is not set, and if it is
1828	 * not set, then the adapter didn't send an interrupt
1829	 */
1830	if (!(icr & E1000_ICR_INT_ASSERTED))
1831		return IRQ_NONE;
1832
1833	/* Interrupt Auto-Mask...upon reading ICR,
1834	 * interrupts are masked.  No need for the
1835	 * IMC write
1836	 */
1837
1838	if (icr & E1000_ICR_LSC) {
1839		hw->mac.get_link_status = true;
1840		/* ICH8 workaround-- Call gig speed drop workaround on cable
1841		 * disconnect (LSC) before accessing any PHY registers
1842		 */
1843		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
1844		    (!(er32(STATUS) & E1000_STATUS_LU)))
1845			schedule_work(&adapter->downshift_task);
1846
1847		/* 80003ES2LAN workaround--
1848		 * For packet buffer work-around on link down event;
1849		 * disable receives here in the ISR and
1850		 * reset adapter in watchdog
1851		 */
1852		if (netif_carrier_ok(netdev) &&
1853		    (adapter->flags & FLAG_RX_NEEDS_RESTART)) {
1854			/* disable receives */
1855			rctl = er32(RCTL);
1856			ew32(RCTL, rctl & ~E1000_RCTL_EN);
1857			adapter->flags |= FLAG_RESTART_NOW;
1858		}
1859		/* guard against interrupt when we're going down */
1860		if (!test_bit(__E1000_DOWN, &adapter->state))
1861			mod_timer(&adapter->watchdog_timer, jiffies + 1);
1862	}
1863
1864	/* Reset on uncorrectable ECC error */
1865	if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) {
1866		u32 pbeccsts = er32(PBECCSTS);
1867
1868		adapter->corr_errors +=
1869		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
1870		adapter->uncorr_errors +=
1871		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
1872		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
1873
1874		/* Do the reset outside of interrupt context */
1875		schedule_work(&adapter->reset_task);
1876
1877		/* return immediately since reset is imminent */
1878		return IRQ_HANDLED;
1879	}
1880
1881	if (napi_schedule_prep(&adapter->napi)) {
1882		adapter->total_tx_bytes = 0;
1883		adapter->total_tx_packets = 0;
1884		adapter->total_rx_bytes = 0;
1885		adapter->total_rx_packets = 0;
1886		__napi_schedule(&adapter->napi);
1887	}
1888
1889	return IRQ_HANDLED;
1890}
1891
1892static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
1893{
1894	struct net_device *netdev = data;
1895	struct e1000_adapter *adapter = netdev_priv(netdev);
1896	struct e1000_hw *hw = &adapter->hw;
1897	u32 icr = er32(ICR);
1898
1899	if (icr & adapter->eiac_mask)
1900		ew32(ICS, (icr & adapter->eiac_mask));
1901
1902	if (icr & E1000_ICR_LSC) {
1903		hw->mac.get_link_status = true;
1904		/* guard against interrupt when we're going down */
1905		if (!test_bit(__E1000_DOWN, &adapter->state))
1906			mod_timer(&adapter->watchdog_timer, jiffies + 1);
1907	}
1908
1909	if (!test_bit(__E1000_DOWN, &adapter->state))
1910		ew32(IMS, E1000_IMS_OTHER | IMS_OTHER_MASK);
1911
1912	return IRQ_HANDLED;
1913}
1914
1915static irqreturn_t e1000_intr_msix_tx(int __always_unused irq, void *data)
1916{
1917	struct net_device *netdev = data;
1918	struct e1000_adapter *adapter = netdev_priv(netdev);
1919	struct e1000_hw *hw = &adapter->hw;
1920	struct e1000_ring *tx_ring = adapter->tx_ring;
1921
1922	adapter->total_tx_bytes = 0;
1923	adapter->total_tx_packets = 0;
1924
1925	if (!e1000_clean_tx_irq(tx_ring))
1926		/* Ring was not completely cleaned, so fire another interrupt */
1927		ew32(ICS, tx_ring->ims_val);
1928
1929	if (!test_bit(__E1000_DOWN, &adapter->state))
1930		ew32(IMS, adapter->tx_ring->ims_val);
1931
1932	return IRQ_HANDLED;
1933}
1934
1935static irqreturn_t e1000_intr_msix_rx(int __always_unused irq, void *data)
1936{
1937	struct net_device *netdev = data;
1938	struct e1000_adapter *adapter = netdev_priv(netdev);
1939	struct e1000_ring *rx_ring = adapter->rx_ring;
1940
1941	/* Write the ITR value calculated at the end of the
1942	 * previous interrupt.
1943	 */
1944	if (rx_ring->set_itr) {
1945		u32 itr = rx_ring->itr_val ?
1946			  1000000000 / (rx_ring->itr_val * 256) : 0;
1947
1948		writel(itr, rx_ring->itr_register);
1949		rx_ring->set_itr = 0;
1950	}
1951
1952	if (napi_schedule_prep(&adapter->napi)) {
1953		adapter->total_rx_bytes = 0;
1954		adapter->total_rx_packets = 0;
1955		__napi_schedule(&adapter->napi);
1956	}
1957	return IRQ_HANDLED;
1958}
1959
1960/**
1961 * e1000_configure_msix - Configure MSI-X hardware
1962 * @adapter: board private structure
1963 *
1964 * e1000_configure_msix sets up the hardware to properly
1965 * generate MSI-X interrupts.
1966 **/
1967static void e1000_configure_msix(struct e1000_adapter *adapter)
1968{
1969	struct e1000_hw *hw = &adapter->hw;
1970	struct e1000_ring *rx_ring = adapter->rx_ring;
1971	struct e1000_ring *tx_ring = adapter->tx_ring;
1972	int vector = 0;
1973	u32 ctrl_ext, ivar = 0;
1974
1975	adapter->eiac_mask = 0;
1976
1977	/* Workaround issue with spurious interrupts on 82574 in MSI-X mode */
1978	if (hw->mac.type == e1000_82574) {
1979		u32 rfctl = er32(RFCTL);
1980
1981		rfctl |= E1000_RFCTL_ACK_DIS;
1982		ew32(RFCTL, rfctl);
1983	}
1984
1985	/* Configure Rx vector */
1986	rx_ring->ims_val = E1000_IMS_RXQ0;
1987	adapter->eiac_mask |= rx_ring->ims_val;
1988	if (rx_ring->itr_val)
1989		writel(1000000000 / (rx_ring->itr_val * 256),
1990		       rx_ring->itr_register);
1991	else
1992		writel(1, rx_ring->itr_register);
1993	ivar = E1000_IVAR_INT_ALLOC_VALID | vector;
1994
1995	/* Configure Tx vector */
1996	tx_ring->ims_val = E1000_IMS_TXQ0;
1997	vector++;
1998	if (tx_ring->itr_val)
1999		writel(1000000000 / (tx_ring->itr_val * 256),
2000		       tx_ring->itr_register);
2001	else
2002		writel(1, tx_ring->itr_register);
2003	adapter->eiac_mask |= tx_ring->ims_val;
2004	ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 8);
2005
2006	/* set vector for Other Causes, e.g. link changes */
2007	vector++;
2008	ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 16);
2009	if (rx_ring->itr_val)
2010		writel(1000000000 / (rx_ring->itr_val * 256),
2011		       hw->hw_addr + E1000_EITR_82574(vector));
2012	else
2013		writel(1, hw->hw_addr + E1000_EITR_82574(vector));
2014
2015	/* Cause Tx interrupts on every write back */
2016	ivar |= BIT(31);
2017
2018	ew32(IVAR, ivar);
2019
2020	/* enable MSI-X PBA support */
2021	ctrl_ext = er32(CTRL_EXT) & ~E1000_CTRL_EXT_IAME;
2022	ctrl_ext |= E1000_CTRL_EXT_PBA_CLR | E1000_CTRL_EXT_EIAME;
2023	ew32(CTRL_EXT, ctrl_ext);
2024	e1e_flush();
2025}
2026
2027void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter)
2028{
2029	if (adapter->msix_entries) {
2030		pci_disable_msix(adapter->pdev);
2031		kfree(adapter->msix_entries);
2032		adapter->msix_entries = NULL;
2033	} else if (adapter->flags & FLAG_MSI_ENABLED) {
2034		pci_disable_msi(adapter->pdev);
2035		adapter->flags &= ~FLAG_MSI_ENABLED;
2036	}
2037}
2038
2039/**
2040 * e1000e_set_interrupt_capability - set MSI or MSI-X if supported
2041 * @adapter: board private structure
2042 *
2043 * Attempt to configure interrupts using the best available
2044 * capabilities of the hardware and kernel.
2045 **/
2046void e1000e_set_interrupt_capability(struct e1000_adapter *adapter)
2047{
2048	int err;
2049	int i;
2050
2051	switch (adapter->int_mode) {
2052	case E1000E_INT_MODE_MSIX:
2053		if (adapter->flags & FLAG_HAS_MSIX) {
2054			adapter->num_vectors = 3; /* RxQ0, TxQ0 and other */
2055			adapter->msix_entries = kcalloc(adapter->num_vectors,
2056							sizeof(struct
2057							       msix_entry),
2058							GFP_KERNEL);
2059			if (adapter->msix_entries) {
2060				struct e1000_adapter *a = adapter;
2061
2062				for (i = 0; i < adapter->num_vectors; i++)
2063					adapter->msix_entries[i].entry = i;
2064
2065				err = pci_enable_msix_range(a->pdev,
2066							    a->msix_entries,
2067							    a->num_vectors,
2068							    a->num_vectors);
2069				if (err > 0)
2070					return;
2071			}
2072			/* MSI-X failed, so fall through and try MSI */
2073			e_err("Failed to initialize MSI-X interrupts.  Falling back to MSI interrupts.\n");
2074			e1000e_reset_interrupt_capability(adapter);
2075		}
2076		adapter->int_mode = E1000E_INT_MODE_MSI;
2077		fallthrough;
2078	case E1000E_INT_MODE_MSI:
2079		if (!pci_enable_msi(adapter->pdev)) {
2080			adapter->flags |= FLAG_MSI_ENABLED;
2081		} else {
2082			adapter->int_mode = E1000E_INT_MODE_LEGACY;
2083			e_err("Failed to initialize MSI interrupts.  Falling back to legacy interrupts.\n");
2084		}
2085		fallthrough;
2086	case E1000E_INT_MODE_LEGACY:
2087		/* Don't do anything; this is the system default */
2088		break;
2089	}
2090
2091	/* store the number of vectors being used */
2092	adapter->num_vectors = 1;
2093}
2094
2095/**
2096 * e1000_request_msix - Initialize MSI-X interrupts
2097 * @adapter: board private structure
2098 *
2099 * e1000_request_msix allocates MSI-X vectors and requests interrupts from the
2100 * kernel.
2101 **/
2102static int e1000_request_msix(struct e1000_adapter *adapter)
2103{
2104	struct net_device *netdev = adapter->netdev;
2105	int err = 0, vector = 0;
2106
2107	if (strlen(netdev->name) < (IFNAMSIZ - 5))
2108		snprintf(adapter->rx_ring->name,
2109			 sizeof(adapter->rx_ring->name) - 1,
2110			 "%.14s-rx-0", netdev->name);
2111	else
2112		memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
2113	err = request_irq(adapter->msix_entries[vector].vector,
2114			  e1000_intr_msix_rx, 0, adapter->rx_ring->name,
2115			  netdev);
2116	if (err)
2117		return err;
2118	adapter->rx_ring->itr_register = adapter->hw.hw_addr +
2119	    E1000_EITR_82574(vector);
2120	adapter->rx_ring->itr_val = adapter->itr;
2121	vector++;
2122
2123	if (strlen(netdev->name) < (IFNAMSIZ - 5))
2124		snprintf(adapter->tx_ring->name,
2125			 sizeof(adapter->tx_ring->name) - 1,
2126			 "%.14s-tx-0", netdev->name);
2127	else
2128		memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
2129	err = request_irq(adapter->msix_entries[vector].vector,
2130			  e1000_intr_msix_tx, 0, adapter->tx_ring->name,
2131			  netdev);
2132	if (err)
2133		return err;
2134	adapter->tx_ring->itr_register = adapter->hw.hw_addr +
2135	    E1000_EITR_82574(vector);
2136	adapter->tx_ring->itr_val = adapter->itr;
2137	vector++;
2138
2139	err = request_irq(adapter->msix_entries[vector].vector,
2140			  e1000_msix_other, 0, netdev->name, netdev);
2141	if (err)
2142		return err;
2143
2144	e1000_configure_msix(adapter);
2145
2146	return 0;
2147}
2148
2149/**
2150 * e1000_request_irq - initialize interrupts
2151 * @adapter: board private structure
2152 *
2153 * Attempts to configure interrupts using the best available
2154 * capabilities of the hardware and kernel.
2155 **/
2156static int e1000_request_irq(struct e1000_adapter *adapter)
2157{
2158	struct net_device *netdev = adapter->netdev;
2159	int err;
2160
2161	if (adapter->msix_entries) {
2162		err = e1000_request_msix(adapter);
2163		if (!err)
2164			return err;
2165		/* fall back to MSI */
2166		e1000e_reset_interrupt_capability(adapter);
2167		adapter->int_mode = E1000E_INT_MODE_MSI;
2168		e1000e_set_interrupt_capability(adapter);
2169	}
2170	if (adapter->flags & FLAG_MSI_ENABLED) {
2171		err = request_irq(adapter->pdev->irq, e1000_intr_msi, 0,
2172				  netdev->name, netdev);
2173		if (!err)
2174			return err;
2175
2176		/* fall back to legacy interrupt */
2177		e1000e_reset_interrupt_capability(adapter);
2178		adapter->int_mode = E1000E_INT_MODE_LEGACY;
2179	}
2180
2181	err = request_irq(adapter->pdev->irq, e1000_intr, IRQF_SHARED,
2182			  netdev->name, netdev);
2183	if (err)
2184		e_err("Unable to allocate interrupt, Error: %d\n", err);
2185
2186	return err;
2187}
2188
2189static void e1000_free_irq(struct e1000_adapter *adapter)
2190{
2191	struct net_device *netdev = adapter->netdev;
2192
2193	if (adapter->msix_entries) {
2194		int vector = 0;
2195
2196		free_irq(adapter->msix_entries[vector].vector, netdev);
2197		vector++;
2198
2199		free_irq(adapter->msix_entries[vector].vector, netdev);
2200		vector++;
2201
2202		/* Other Causes interrupt vector */
2203		free_irq(adapter->msix_entries[vector].vector, netdev);
2204		return;
2205	}
2206
2207	free_irq(adapter->pdev->irq, netdev);
2208}
2209
2210/**
2211 * e1000_irq_disable - Mask off interrupt generation on the NIC
2212 * @adapter: board private structure
2213 **/
2214static void e1000_irq_disable(struct e1000_adapter *adapter)
2215{
2216	struct e1000_hw *hw = &adapter->hw;
2217
2218	ew32(IMC, ~0);
2219	if (adapter->msix_entries)
2220		ew32(EIAC_82574, 0);
2221	e1e_flush();
2222
2223	if (adapter->msix_entries) {
2224		int i;
2225
2226		for (i = 0; i < adapter->num_vectors; i++)
2227			synchronize_irq(adapter->msix_entries[i].vector);
2228	} else {
2229		synchronize_irq(adapter->pdev->irq);
2230	}
2231}
2232
2233/**
2234 * e1000_irq_enable - Enable default interrupt generation settings
2235 * @adapter: board private structure
2236 **/
2237static void e1000_irq_enable(struct e1000_adapter *adapter)
2238{
2239	struct e1000_hw *hw = &adapter->hw;
2240
2241	if (adapter->msix_entries) {
2242		ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574);
2243		ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER |
2244		     IMS_OTHER_MASK);
2245	} else if (hw->mac.type >= e1000_pch_lpt) {
2246		ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER);
2247	} else {
2248		ew32(IMS, IMS_ENABLE_MASK);
2249	}
2250	e1e_flush();
2251}
2252
2253/**
2254 * e1000e_get_hw_control - get control of the h/w from f/w
2255 * @adapter: address of board private structure
2256 *
2257 * e1000e_get_hw_control sets {CTRL_EXT|SWSM}:DRV_LOAD bit.
2258 * For ASF and Pass Through versions of f/w this means that
2259 * the driver is loaded. For AMT version (only with 82573)
2260 * of the f/w this means that the network i/f is open.
2261 **/
2262void e1000e_get_hw_control(struct e1000_adapter *adapter)
2263{
2264	struct e1000_hw *hw = &adapter->hw;
2265	u32 ctrl_ext;
2266	u32 swsm;
2267
2268	/* Let firmware know the driver has taken over */
2269	if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) {
2270		swsm = er32(SWSM);
2271		ew32(SWSM, swsm | E1000_SWSM_DRV_LOAD);
2272	} else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) {
2273		ctrl_ext = er32(CTRL_EXT);
2274		ew32(CTRL_EXT, ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
2275	}
2276}
2277
2278/**
2279 * e1000e_release_hw_control - release control of the h/w to f/w
2280 * @adapter: address of board private structure
2281 *
2282 * e1000e_release_hw_control resets {CTRL_EXT|SWSM}:DRV_LOAD bit.
2283 * For ASF and Pass Through versions of f/w this means that the
2284 * driver is no longer loaded. For AMT version (only with 82573) i
2285 * of the f/w this means that the network i/f is closed.
2286 *
2287 **/
2288void e1000e_release_hw_control(struct e1000_adapter *adapter)
2289{
2290	struct e1000_hw *hw = &adapter->hw;
2291	u32 ctrl_ext;
2292	u32 swsm;
2293
2294	/* Let firmware taken over control of h/w */
2295	if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) {
2296		swsm = er32(SWSM);
2297		ew32(SWSM, swsm & ~E1000_SWSM_DRV_LOAD);
2298	} else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) {
2299		ctrl_ext = er32(CTRL_EXT);
2300		ew32(CTRL_EXT, ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD);
2301	}
2302}
2303
2304/**
2305 * e1000_alloc_ring_dma - allocate memory for a ring structure
2306 * @adapter: board private structure
2307 * @ring: ring struct for which to allocate dma
2308 **/
2309static int e1000_alloc_ring_dma(struct e1000_adapter *adapter,
2310				struct e1000_ring *ring)
2311{
2312	struct pci_dev *pdev = adapter->pdev;
2313
2314	ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma,
2315					GFP_KERNEL);
2316	if (!ring->desc)
2317		return -ENOMEM;
2318
2319	return 0;
2320}
2321
2322/**
2323 * e1000e_setup_tx_resources - allocate Tx resources (Descriptors)
2324 * @tx_ring: Tx descriptor ring
2325 *
2326 * Return 0 on success, negative on failure
2327 **/
2328int e1000e_setup_tx_resources(struct e1000_ring *tx_ring)
2329{
2330	struct e1000_adapter *adapter = tx_ring->adapter;
2331	int err = -ENOMEM, size;
2332
2333	size = sizeof(struct e1000_buffer) * tx_ring->count;
2334	tx_ring->buffer_info = vzalloc(size);
2335	if (!tx_ring->buffer_info)
2336		goto err;
2337
2338	/* round up to nearest 4K */
2339	tx_ring->size = tx_ring->count * sizeof(struct e1000_tx_desc);
2340	tx_ring->size = ALIGN(tx_ring->size, 4096);
2341
2342	err = e1000_alloc_ring_dma(adapter, tx_ring);
2343	if (err)
2344		goto err;
2345
2346	tx_ring->next_to_use = 0;
2347	tx_ring->next_to_clean = 0;
2348
2349	return 0;
2350err:
2351	vfree(tx_ring->buffer_info);
2352	e_err("Unable to allocate memory for the transmit descriptor ring\n");
2353	return err;
2354}
2355
2356/**
2357 * e1000e_setup_rx_resources - allocate Rx resources (Descriptors)
2358 * @rx_ring: Rx descriptor ring
2359 *
2360 * Returns 0 on success, negative on failure
2361 **/
2362int e1000e_setup_rx_resources(struct e1000_ring *rx_ring)
2363{
2364	struct e1000_adapter *adapter = rx_ring->adapter;
2365	struct e1000_buffer *buffer_info;
2366	int i, size, desc_len, err = -ENOMEM;
2367
2368	size = sizeof(struct e1000_buffer) * rx_ring->count;
2369	rx_ring->buffer_info = vzalloc(size);
2370	if (!rx_ring->buffer_info)
2371		goto err;
2372
2373	for (i = 0; i < rx_ring->count; i++) {
2374		buffer_info = &rx_ring->buffer_info[i];
2375		buffer_info->ps_pages = kcalloc(PS_PAGE_BUFFERS,
2376						sizeof(struct e1000_ps_page),
2377						GFP_KERNEL);
2378		if (!buffer_info->ps_pages)
2379			goto err_pages;
2380	}
2381
2382	desc_len = sizeof(union e1000_rx_desc_packet_split);
2383
2384	/* Round up to nearest 4K */
2385	rx_ring->size = rx_ring->count * desc_len;
2386	rx_ring->size = ALIGN(rx_ring->size, 4096);
2387
2388	err = e1000_alloc_ring_dma(adapter, rx_ring);
2389	if (err)
2390		goto err_pages;
2391
2392	rx_ring->next_to_clean = 0;
2393	rx_ring->next_to_use = 0;
2394	rx_ring->rx_skb_top = NULL;
2395
2396	return 0;
2397
2398err_pages:
2399	for (i = 0; i < rx_ring->count; i++) {
2400		buffer_info = &rx_ring->buffer_info[i];
2401		kfree(buffer_info->ps_pages);
2402	}
2403err:
2404	vfree(rx_ring->buffer_info);
2405	e_err("Unable to allocate memory for the receive descriptor ring\n");
2406	return err;
2407}
2408
2409/**
2410 * e1000_clean_tx_ring - Free Tx Buffers
2411 * @tx_ring: Tx descriptor ring
2412 **/
2413static void e1000_clean_tx_ring(struct e1000_ring *tx_ring)
2414{
2415	struct e1000_adapter *adapter = tx_ring->adapter;
2416	struct e1000_buffer *buffer_info;
2417	unsigned long size;
2418	unsigned int i;
2419
2420	for (i = 0; i < tx_ring->count; i++) {
2421		buffer_info = &tx_ring->buffer_info[i];
2422		e1000_put_txbuf(tx_ring, buffer_info, false);
2423	}
2424
2425	netdev_reset_queue(adapter->netdev);
2426	size = sizeof(struct e1000_buffer) * tx_ring->count;
2427	memset(tx_ring->buffer_info, 0, size);
2428
2429	memset(tx_ring->desc, 0, tx_ring->size);
2430
2431	tx_ring->next_to_use = 0;
2432	tx_ring->next_to_clean = 0;
2433}
2434
2435/**
2436 * e1000e_free_tx_resources - Free Tx Resources per Queue
2437 * @tx_ring: Tx descriptor ring
2438 *
2439 * Free all transmit software resources
2440 **/
2441void e1000e_free_tx_resources(struct e1000_ring *tx_ring)
2442{
2443	struct e1000_adapter *adapter = tx_ring->adapter;
2444	struct pci_dev *pdev = adapter->pdev;
2445
2446	e1000_clean_tx_ring(tx_ring);
2447
2448	vfree(tx_ring->buffer_info);
2449	tx_ring->buffer_info = NULL;
2450
2451	dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
2452			  tx_ring->dma);
2453	tx_ring->desc = NULL;
2454}
2455
2456/**
2457 * e1000e_free_rx_resources - Free Rx Resources
2458 * @rx_ring: Rx descriptor ring
2459 *
2460 * Free all receive software resources
2461 **/
2462void e1000e_free_rx_resources(struct e1000_ring *rx_ring)
2463{
2464	struct e1000_adapter *adapter = rx_ring->adapter;
2465	struct pci_dev *pdev = adapter->pdev;
2466	int i;
2467
2468	e1000_clean_rx_ring(rx_ring);
2469
2470	for (i = 0; i < rx_ring->count; i++)
2471		kfree(rx_ring->buffer_info[i].ps_pages);
2472
2473	vfree(rx_ring->buffer_info);
2474	rx_ring->buffer_info = NULL;
2475
2476	dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
2477			  rx_ring->dma);
2478	rx_ring->desc = NULL;
2479}
2480
2481/**
2482 * e1000_update_itr - update the dynamic ITR value based on statistics
2483 * @itr_setting: current adapter->itr
2484 * @packets: the number of packets during this measurement interval
2485 * @bytes: the number of bytes during this measurement interval
2486 *
2487 *      Stores a new ITR value based on packets and byte
2488 *      counts during the last interrupt.  The advantage of per interrupt
2489 *      computation is faster updates and more accurate ITR for the current
2490 *      traffic pattern.  Constants in this function were computed
2491 *      based on theoretical maximum wire speed and thresholds were set based
2492 *      on testing data as well as attempting to minimize response time
2493 *      while increasing bulk throughput.  This functionality is controlled
2494 *      by the InterruptThrottleRate module parameter.
2495 **/
2496static unsigned int e1000_update_itr(u16 itr_setting, int packets, int bytes)
2497{
2498	unsigned int retval = itr_setting;
2499
2500	if (packets == 0)
2501		return itr_setting;
2502
2503	switch (itr_setting) {
2504	case lowest_latency:
2505		/* handle TSO and jumbo frames */
2506		if (bytes / packets > 8000)
2507			retval = bulk_latency;
2508		else if ((packets < 5) && (bytes > 512))
2509			retval = low_latency;
2510		break;
2511	case low_latency:	/* 50 usec aka 20000 ints/s */
2512		if (bytes > 10000) {
2513			/* this if handles the TSO accounting */
2514			if (bytes / packets > 8000)
2515				retval = bulk_latency;
2516			else if ((packets < 10) || ((bytes / packets) > 1200))
2517				retval = bulk_latency;
2518			else if ((packets > 35))
2519				retval = lowest_latency;
2520		} else if (bytes / packets > 2000) {
2521			retval = bulk_latency;
2522		} else if (packets <= 2 && bytes < 512) {
2523			retval = lowest_latency;
2524		}
2525		break;
2526	case bulk_latency:	/* 250 usec aka 4000 ints/s */
2527		if (bytes > 25000) {
2528			if (packets > 35)
2529				retval = low_latency;
2530		} else if (bytes < 6000) {
2531			retval = low_latency;
2532		}
2533		break;
2534	}
2535
2536	return retval;
2537}
2538
2539static void e1000_set_itr(struct e1000_adapter *adapter)
2540{
2541	u16 current_itr;
2542	u32 new_itr = adapter->itr;
2543
2544	/* for non-gigabit speeds, just fix the interrupt rate at 4000 */
2545	if (adapter->link_speed != SPEED_1000) {
2546		new_itr = 4000;
2547		goto set_itr_now;
2548	}
2549
2550	if (adapter->flags2 & FLAG2_DISABLE_AIM) {
2551		new_itr = 0;
2552		goto set_itr_now;
2553	}
2554
2555	adapter->tx_itr = e1000_update_itr(adapter->tx_itr,
2556					   adapter->total_tx_packets,
2557					   adapter->total_tx_bytes);
2558	/* conservative mode (itr 3) eliminates the lowest_latency setting */
2559	if (adapter->itr_setting == 3 && adapter->tx_itr == lowest_latency)
2560		adapter->tx_itr = low_latency;
2561
2562	adapter->rx_itr = e1000_update_itr(adapter->rx_itr,
2563					   adapter->total_rx_packets,
2564					   adapter->total_rx_bytes);
2565	/* conservative mode (itr 3) eliminates the lowest_latency setting */
2566	if (adapter->itr_setting == 3 && adapter->rx_itr == lowest_latency)
2567		adapter->rx_itr = low_latency;
2568
2569	current_itr = max(adapter->rx_itr, adapter->tx_itr);
2570
2571	/* counts and packets in update_itr are dependent on these numbers */
2572	switch (current_itr) {
2573	case lowest_latency:
2574		new_itr = 70000;
2575		break;
2576	case low_latency:
2577		new_itr = 20000;	/* aka hwitr = ~200 */
2578		break;
2579	case bulk_latency:
2580		new_itr = 4000;
2581		break;
2582	default:
2583		break;
2584	}
2585
2586set_itr_now:
2587	if (new_itr != adapter->itr) {
2588		/* this attempts to bias the interrupt rate towards Bulk
2589		 * by adding intermediate steps when interrupt rate is
2590		 * increasing
2591		 */
2592		new_itr = new_itr > adapter->itr ?
2593		    min(adapter->itr + (new_itr >> 2), new_itr) : new_itr;
2594		adapter->itr = new_itr;
2595		adapter->rx_ring->itr_val = new_itr;
2596		if (adapter->msix_entries)
2597			adapter->rx_ring->set_itr = 1;
2598		else
2599			e1000e_write_itr(adapter, new_itr);
2600	}
2601}
2602
2603/**
2604 * e1000e_write_itr - write the ITR value to the appropriate registers
2605 * @adapter: address of board private structure
2606 * @itr: new ITR value to program
2607 *
2608 * e1000e_write_itr determines if the adapter is in MSI-X mode
2609 * and, if so, writes the EITR registers with the ITR value.
2610 * Otherwise, it writes the ITR value into the ITR register.
2611 **/
2612void e1000e_write_itr(struct e1000_adapter *adapter, u32 itr)
2613{
2614	struct e1000_hw *hw = &adapter->hw;
2615	u32 new_itr = itr ? 1000000000 / (itr * 256) : 0;
2616
2617	if (adapter->msix_entries) {
2618		int vector;
2619
2620		for (vector = 0; vector < adapter->num_vectors; vector++)
2621			writel(new_itr, hw->hw_addr + E1000_EITR_82574(vector));
2622	} else {
2623		ew32(ITR, new_itr);
2624	}
2625}
2626
2627/**
2628 * e1000_alloc_queues - Allocate memory for all rings
2629 * @adapter: board private structure to initialize
2630 **/
2631static int e1000_alloc_queues(struct e1000_adapter *adapter)
2632{
2633	int size = sizeof(struct e1000_ring);
2634
2635	adapter->tx_ring = kzalloc(size, GFP_KERNEL);
2636	if (!adapter->tx_ring)
2637		goto err;
2638	adapter->tx_ring->count = adapter->tx_ring_count;
2639	adapter->tx_ring->adapter = adapter;
2640
2641	adapter->rx_ring = kzalloc(size, GFP_KERNEL);
2642	if (!adapter->rx_ring)
2643		goto err;
2644	adapter->rx_ring->count = adapter->rx_ring_count;
2645	adapter->rx_ring->adapter = adapter;
2646
2647	return 0;
2648err:
2649	e_err("Unable to allocate memory for queues\n");
2650	kfree(adapter->rx_ring);
2651	kfree(adapter->tx_ring);
2652	return -ENOMEM;
2653}
2654
2655/**
2656 * e1000e_poll - NAPI Rx polling callback
2657 * @napi: struct associated with this polling callback
2658 * @budget: number of packets driver is allowed to process this poll
2659 **/
2660static int e1000e_poll(struct napi_struct *napi, int budget)
2661{
2662	struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter,
2663						     napi);
2664	struct e1000_hw *hw = &adapter->hw;
2665	struct net_device *poll_dev = adapter->netdev;
2666	int tx_cleaned = 1, work_done = 0;
2667
2668	adapter = netdev_priv(poll_dev);
2669
2670	if (!adapter->msix_entries ||
2671	    (adapter->rx_ring->ims_val & adapter->tx_ring->ims_val))
2672		tx_cleaned = e1000_clean_tx_irq(adapter->tx_ring);
2673
2674	adapter->clean_rx(adapter->rx_ring, &work_done, budget);
2675
2676	if (!tx_cleaned || work_done == budget)
2677		return budget;
2678
2679	/* Exit the polling mode, but don't re-enable interrupts if stack might
2680	 * poll us due to busy-polling
2681	 */
2682	if (likely(napi_complete_done(napi, work_done))) {
2683		if (adapter->itr_setting & 3)
2684			e1000_set_itr(adapter);
2685		if (!test_bit(__E1000_DOWN, &adapter->state)) {
2686			if (adapter->msix_entries)
2687				ew32(IMS, adapter->rx_ring->ims_val);
2688			else
2689				e1000_irq_enable(adapter);
2690		}
2691	}
2692
2693	return work_done;
2694}
2695
2696static int e1000_vlan_rx_add_vid(struct net_device *netdev,
2697				 __always_unused __be16 proto, u16 vid)
2698{
2699	struct e1000_adapter *adapter = netdev_priv(netdev);
2700	struct e1000_hw *hw = &adapter->hw;
2701	u32 vfta, index;
2702
2703	/* don't update vlan cookie if already programmed */
2704	if ((adapter->hw.mng_cookie.status &
2705	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
2706	    (vid == adapter->mng_vlan_id))
2707		return 0;
2708
2709	/* add VID to filter table */
2710	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
2711		index = (vid >> 5) & 0x7F;
2712		vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index);
2713		vfta |= BIT((vid & 0x1F));
2714		hw->mac.ops.write_vfta(hw, index, vfta);
2715	}
2716
2717	set_bit(vid, adapter->active_vlans);
2718
2719	return 0;
2720}
2721
2722static int e1000_vlan_rx_kill_vid(struct net_device *netdev,
2723				  __always_unused __be16 proto, u16 vid)
2724{
2725	struct e1000_adapter *adapter = netdev_priv(netdev);
2726	struct e1000_hw *hw = &adapter->hw;
2727	u32 vfta, index;
2728
2729	if ((adapter->hw.mng_cookie.status &
2730	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
2731	    (vid == adapter->mng_vlan_id)) {
2732		/* release control to f/w */
2733		e1000e_release_hw_control(adapter);
2734		return 0;
2735	}
2736
2737	/* remove VID from filter table */
2738	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
2739		index = (vid >> 5) & 0x7F;
2740		vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index);
2741		vfta &= ~BIT((vid & 0x1F));
2742		hw->mac.ops.write_vfta(hw, index, vfta);
2743	}
2744
2745	clear_bit(vid, adapter->active_vlans);
2746
2747	return 0;
2748}
2749
2750/**
2751 * e1000e_vlan_filter_disable - helper to disable hw VLAN filtering
2752 * @adapter: board private structure to initialize
2753 **/
2754static void e1000e_vlan_filter_disable(struct e1000_adapter *adapter)
2755{
2756	struct net_device *netdev = adapter->netdev;
2757	struct e1000_hw *hw = &adapter->hw;
2758	u32 rctl;
2759
2760	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
2761		/* disable VLAN receive filtering */
2762		rctl = er32(RCTL);
2763		rctl &= ~(E1000_RCTL_VFE | E1000_RCTL_CFIEN);
2764		ew32(RCTL, rctl);
2765
2766		if (adapter->mng_vlan_id != (u16)E1000_MNG_VLAN_NONE) {
2767			e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
2768					       adapter->mng_vlan_id);
2769			adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
2770		}
2771	}
2772}
2773
2774/**
2775 * e1000e_vlan_filter_enable - helper to enable HW VLAN filtering
2776 * @adapter: board private structure to initialize
2777 **/
2778static void e1000e_vlan_filter_enable(struct e1000_adapter *adapter)
2779{
2780	struct e1000_hw *hw = &adapter->hw;
2781	u32 rctl;
2782
2783	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
2784		/* enable VLAN receive filtering */
2785		rctl = er32(RCTL);
2786		rctl |= E1000_RCTL_VFE;
2787		rctl &= ~E1000_RCTL_CFIEN;
2788		ew32(RCTL, rctl);
2789	}
2790}
2791
2792/**
2793 * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping
2794 * @adapter: board private structure to initialize
2795 **/
2796static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter)
2797{
2798	struct e1000_hw *hw = &adapter->hw;
2799	u32 ctrl;
2800
2801	/* disable VLAN tag insert/strip */
2802	ctrl = er32(CTRL);
2803	ctrl &= ~E1000_CTRL_VME;
2804	ew32(CTRL, ctrl);
2805}
2806
2807/**
2808 * e1000e_vlan_strip_enable - helper to enable HW VLAN stripping
2809 * @adapter: board private structure to initialize
2810 **/
2811static void e1000e_vlan_strip_enable(struct e1000_adapter *adapter)
2812{
2813	struct e1000_hw *hw = &adapter->hw;
2814	u32 ctrl;
2815
2816	/* enable VLAN tag insert/strip */
2817	ctrl = er32(CTRL);
2818	ctrl |= E1000_CTRL_VME;
2819	ew32(CTRL, ctrl);
2820}
2821
2822static void e1000_update_mng_vlan(struct e1000_adapter *adapter)
2823{
2824	struct net_device *netdev = adapter->netdev;
2825	u16 vid = adapter->hw.mng_cookie.vlan_id;
2826	u16 old_vid = adapter->mng_vlan_id;
2827
2828	if (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) {
2829		e1000_vlan_rx_add_vid(netdev, htons(ETH_P_8021Q), vid);
2830		adapter->mng_vlan_id = vid;
2831	}
2832
2833	if ((old_vid != (u16)E1000_MNG_VLAN_NONE) && (vid != old_vid))
2834		e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q), old_vid);
2835}
2836
2837static void e1000_restore_vlan(struct e1000_adapter *adapter)
2838{
2839	u16 vid;
2840
2841	e1000_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0);
2842
2843	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
2844	    e1000_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid);
2845}
2846
2847static void e1000_init_manageability_pt(struct e1000_adapter *adapter)
2848{
2849	struct e1000_hw *hw = &adapter->hw;
2850	u32 manc, manc2h, mdef, i, j;
2851
2852	if (!(adapter->flags & FLAG_MNG_PT_ENABLED))
2853		return;
2854
2855	manc = er32(MANC);
2856
2857	/* enable receiving management packets to the host. this will probably
2858	 * generate destination unreachable messages from the host OS, but
2859	 * the packets will be handled on SMBUS
2860	 */
2861	manc |= E1000_MANC_EN_MNG2HOST;
2862	manc2h = er32(MANC2H);
2863
2864	switch (hw->mac.type) {
2865	default:
2866		manc2h |= (E1000_MANC2H_PORT_623 | E1000_MANC2H_PORT_664);
2867		break;
2868	case e1000_82574:
2869	case e1000_82583:
2870		/* Check if IPMI pass-through decision filter already exists;
2871		 * if so, enable it.
2872		 */
2873		for (i = 0, j = 0; i < 8; i++) {
2874			mdef = er32(MDEF(i));
2875
2876			/* Ignore filters with anything other than IPMI ports */
2877			if (mdef & ~(E1000_MDEF_PORT_623 | E1000_MDEF_PORT_664))
2878				continue;
2879
2880			/* Enable this decision filter in MANC2H */
2881			if (mdef)
2882				manc2h |= BIT(i);
2883
2884			j |= mdef;
2885		}
2886
2887		if (j == (E1000_MDEF_PORT_623 | E1000_MDEF_PORT_664))
2888			break;
2889
2890		/* Create new decision filter in an empty filter */
2891		for (i = 0, j = 0; i < 8; i++)
2892			if (er32(MDEF(i)) == 0) {
2893				ew32(MDEF(i), (E1000_MDEF_PORT_623 |
2894					       E1000_MDEF_PORT_664));
2895				manc2h |= BIT(1);
2896				j++;
2897				break;
2898			}
2899
2900		if (!j)
2901			e_warn("Unable to create IPMI pass-through filter\n");
2902		break;
2903	}
2904
2905	ew32(MANC2H, manc2h);
2906	ew32(MANC, manc);
2907}
2908
2909/**
2910 * e1000_configure_tx - Configure Transmit Unit after Reset
2911 * @adapter: board private structure
2912 *
2913 * Configure the Tx unit of the MAC after a reset.
2914 **/
2915static void e1000_configure_tx(struct e1000_adapter *adapter)
2916{
2917	struct e1000_hw *hw = &adapter->hw;
2918	struct e1000_ring *tx_ring = adapter->tx_ring;
2919	u64 tdba;
2920	u32 tdlen, tctl, tarc;
2921
2922	/* Setup the HW Tx Head and Tail descriptor pointers */
2923	tdba = tx_ring->dma;
2924	tdlen = tx_ring->count * sizeof(struct e1000_tx_desc);
2925	ew32(TDBAL(0), (tdba & DMA_BIT_MASK(32)));
2926	ew32(TDBAH(0), (tdba >> 32));
2927	ew32(TDLEN(0), tdlen);
2928	ew32(TDH(0), 0);
2929	ew32(TDT(0), 0);
2930	tx_ring->head = adapter->hw.hw_addr + E1000_TDH(0);
2931	tx_ring->tail = adapter->hw.hw_addr + E1000_TDT(0);
2932
2933	writel(0, tx_ring->head);
2934	if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
2935		e1000e_update_tdt_wa(tx_ring, 0);
2936	else
2937		writel(0, tx_ring->tail);
2938
2939	/* Set the Tx Interrupt Delay register */
2940	ew32(TIDV, adapter->tx_int_delay);
2941	/* Tx irq moderation */
2942	ew32(TADV, adapter->tx_abs_int_delay);
2943
2944	if (adapter->flags2 & FLAG2_DMA_BURST) {
2945		u32 txdctl = er32(TXDCTL(0));
2946
2947		txdctl &= ~(E1000_TXDCTL_PTHRESH | E1000_TXDCTL_HTHRESH |
2948			    E1000_TXDCTL_WTHRESH);
2949		/* set up some performance related parameters to encourage the
2950		 * hardware to use the bus more efficiently in bursts, depends
2951		 * on the tx_int_delay to be enabled,
2952		 * wthresh = 1 ==> burst write is disabled to avoid Tx stalls
2953		 * hthresh = 1 ==> prefetch when one or more available
2954		 * pthresh = 0x1f ==> prefetch if internal cache 31 or less
2955		 * BEWARE: this seems to work but should be considered first if
2956		 * there are Tx hangs or other Tx related bugs
2957		 */
2958		txdctl |= E1000_TXDCTL_DMA_BURST_ENABLE;
2959		ew32(TXDCTL(0), txdctl);
2960	}
2961	/* erratum work around: set txdctl the same for both queues */
2962	ew32(TXDCTL(1), er32(TXDCTL(0)));
2963
2964	/* Program the Transmit Control Register */
2965	tctl = er32(TCTL);
2966	tctl &= ~E1000_TCTL_CT;
2967	tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC |
2968		(E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT);
2969
2970	if (adapter->flags & FLAG_TARC_SPEED_MODE_BIT) {
2971		tarc = er32(TARC(0));
2972		/* set the speed mode bit, we'll clear it if we're not at
2973		 * gigabit link later
2974		 */
2975#define SPEED_MODE_BIT BIT(21)
2976		tarc |= SPEED_MODE_BIT;
2977		ew32(TARC(0), tarc);
2978	}
2979
2980	/* errata: program both queues to unweighted RR */
2981	if (adapter->flags & FLAG_TARC_SET_BIT_ZERO) {
2982		tarc = er32(TARC(0));
2983		tarc |= 1;
2984		ew32(TARC(0), tarc);
2985		tarc = er32(TARC(1));
2986		tarc |= 1;
2987		ew32(TARC(1), tarc);
2988	}
2989
2990	/* Setup Transmit Descriptor Settings for eop descriptor */
2991	adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_IFCS;
2992
2993	/* only set IDE if we are delaying interrupts using the timers */
2994	if (adapter->tx_int_delay)
2995		adapter->txd_cmd |= E1000_TXD_CMD_IDE;
2996
2997	/* enable Report Status bit */
2998	adapter->txd_cmd |= E1000_TXD_CMD_RS;
2999
3000	ew32(TCTL, tctl);
3001
3002	hw->mac.ops.config_collision_dist(hw);
3003
3004	/* SPT and KBL Si errata workaround to avoid data corruption */
3005	if (hw->mac.type == e1000_pch_spt) {
3006		u32 reg_val;
3007
3008		reg_val = er32(IOSFPC);
3009		reg_val |= E1000_RCTL_RDMTS_HEX;
3010		ew32(IOSFPC, reg_val);
3011
3012		reg_val = er32(TARC(0));
3013		/* SPT and KBL Si errata workaround to avoid Tx hang.
3014		 * Dropping the number of outstanding requests from
3015		 * 3 to 2 in order to avoid a buffer overrun.
3016		 */
3017		reg_val &= ~E1000_TARC0_CB_MULTIQ_3_REQ;
3018		reg_val |= E1000_TARC0_CB_MULTIQ_2_REQ;
3019		ew32(TARC(0), reg_val);
3020	}
3021}
3022
3023#define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \
3024			   (((S) & (PAGE_SIZE - 1)) ? 1 : 0))
3025
3026/**
3027 * e1000_setup_rctl - configure the receive control registers
3028 * @adapter: Board private structure
3029 **/
3030static void e1000_setup_rctl(struct e1000_adapter *adapter)
3031{
3032	struct e1000_hw *hw = &adapter->hw;
3033	u32 rctl, rfctl;
3034	u32 pages = 0;
3035
3036	/* Workaround Si errata on PCHx - configure jumbo frame flow.
3037	 * If jumbo frames not set, program related MAC/PHY registers
3038	 * to h/w defaults
3039	 */
3040	if (hw->mac.type >= e1000_pch2lan) {
3041		s32 ret_val;
3042
3043		if (adapter->netdev->mtu > ETH_DATA_LEN)
3044			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true);
3045		else
3046			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false);
3047
3048		if (ret_val)
3049			e_dbg("failed to enable|disable jumbo frame workaround mode\n");
3050	}
3051
3052	/* Program MC offset vector base */
3053	rctl = er32(RCTL);
3054	rctl &= ~(3 << E1000_RCTL_MO_SHIFT);
3055	rctl |= E1000_RCTL_EN | E1000_RCTL_BAM |
3056	    E1000_RCTL_LBM_NO | E1000_RCTL_RDMTS_HALF |
3057	    (adapter->hw.mac.mc_filter_type << E1000_RCTL_MO_SHIFT);
3058
3059	/* Do not Store bad packets */
3060	rctl &= ~E1000_RCTL_SBP;
3061
3062	/* Enable Long Packet receive */
3063	if (adapter->netdev->mtu <= ETH_DATA_LEN)
3064		rctl &= ~E1000_RCTL_LPE;
3065	else
3066		rctl |= E1000_RCTL_LPE;
3067
3068	/* Some systems expect that the CRC is included in SMBUS traffic. The
3069	 * hardware strips the CRC before sending to both SMBUS (BMC) and to
3070	 * host memory when this is enabled
3071	 */
3072	if (adapter->flags2 & FLAG2_CRC_STRIPPING)
3073		rctl |= E1000_RCTL_SECRC;
3074
3075	/* Workaround Si errata on 82577 PHY - configure IPG for jumbos */
3076	if ((hw->phy.type == e1000_phy_82577) && (rctl & E1000_RCTL_LPE)) {
3077		u16 phy_data;
3078
3079		e1e_rphy(hw, PHY_REG(770, 26), &phy_data);
3080		phy_data &= 0xfff8;
3081		phy_data |= BIT(2);
3082		e1e_wphy(hw, PHY_REG(770, 26), phy_data);
3083
3084		e1e_rphy(hw, 22, &phy_data);
3085		phy_data &= 0x0fff;
3086		phy_data |= BIT(14);
3087		e1e_wphy(hw, 0x10, 0x2823);
3088		e1e_wphy(hw, 0x11, 0x0003);
3089		e1e_wphy(hw, 22, phy_data);
3090	}
3091
3092	/* Setup buffer sizes */
3093	rctl &= ~E1000_RCTL_SZ_4096;
3094	rctl |= E1000_RCTL_BSEX;
3095	switch (adapter->rx_buffer_len) {
3096	case 2048:
3097	default:
3098		rctl |= E1000_RCTL_SZ_2048;
3099		rctl &= ~E1000_RCTL_BSEX;
3100		break;
3101	case 4096:
3102		rctl |= E1000_RCTL_SZ_4096;
3103		break;
3104	case 8192:
3105		rctl |= E1000_RCTL_SZ_8192;
3106		break;
3107	case 16384:
3108		rctl |= E1000_RCTL_SZ_16384;
3109		break;
3110	}
3111
3112	/* Enable Extended Status in all Receive Descriptors */
3113	rfctl = er32(RFCTL);
3114	rfctl |= E1000_RFCTL_EXTEN;
3115	ew32(RFCTL, rfctl);
3116
3117	/* 82571 and greater support packet-split where the protocol
3118	 * header is placed in skb->data and the packet data is
3119	 * placed in pages hanging off of skb_shinfo(skb)->nr_frags.
3120	 * In the case of a non-split, skb->data is linearly filled,
3121	 * followed by the page buffers.  Therefore, skb->data is
3122	 * sized to hold the largest protocol header.
3123	 *
3124	 * allocations using alloc_page take too long for regular MTU
3125	 * so only enable packet split for jumbo frames
3126	 *
3127	 * Using pages when the page size is greater than 16k wastes
3128	 * a lot of memory, since we allocate 3 pages at all times
3129	 * per packet.
3130	 */
3131	pages = PAGE_USE_COUNT(adapter->netdev->mtu);
3132	if ((pages <= 3) && (PAGE_SIZE <= 16384) && (rctl & E1000_RCTL_LPE))
3133		adapter->rx_ps_pages = pages;
3134	else
3135		adapter->rx_ps_pages = 0;
3136
3137	if (adapter->rx_ps_pages) {
3138		u32 psrctl = 0;
3139
3140		/* Enable Packet split descriptors */
3141		rctl |= E1000_RCTL_DTYP_PS;
3142
3143		psrctl |= adapter->rx_ps_bsize0 >> E1000_PSRCTL_BSIZE0_SHIFT;
3144
3145		switch (adapter->rx_ps_pages) {
3146		case 3:
3147			psrctl |= PAGE_SIZE << E1000_PSRCTL_BSIZE3_SHIFT;
3148			fallthrough;
3149		case 2:
3150			psrctl |= PAGE_SIZE << E1000_PSRCTL_BSIZE2_SHIFT;
3151			fallthrough;
3152		case 1:
3153			psrctl |= PAGE_SIZE >> E1000_PSRCTL_BSIZE1_SHIFT;
3154			break;
3155		}
3156
3157		ew32(PSRCTL, psrctl);
3158	}
3159
3160	/* This is useful for sniffing bad packets. */
3161	if (adapter->netdev->features & NETIF_F_RXALL) {
3162		/* UPE and MPE will be handled by normal PROMISC logic
3163		 * in e1000e_set_rx_mode
3164		 */
3165		rctl |= (E1000_RCTL_SBP |	/* Receive bad packets */
3166			 E1000_RCTL_BAM |	/* RX All Bcast Pkts */
3167			 E1000_RCTL_PMCF);	/* RX All MAC Ctrl Pkts */
3168
3169		rctl &= ~(E1000_RCTL_VFE |	/* Disable VLAN filter */
3170			  E1000_RCTL_DPF |	/* Allow filtered pause */
3171			  E1000_RCTL_CFIEN);	/* Dis VLAN CFIEN Filter */
3172		/* Do not mess with E1000_CTRL_VME, it affects transmit as well,
3173		 * and that breaks VLANs.
3174		 */
3175	}
3176
3177	ew32(RCTL, rctl);
3178	/* just started the receive unit, no need to restart */
3179	adapter->flags &= ~FLAG_RESTART_NOW;
3180}
3181
3182/**
3183 * e1000_configure_rx - Configure Receive Unit after Reset
3184 * @adapter: board private structure
3185 *
3186 * Configure the Rx unit of the MAC after a reset.
3187 **/
3188static void e1000_configure_rx(struct e1000_adapter *adapter)
3189{
3190	struct e1000_hw *hw = &adapter->hw;
3191	struct e1000_ring *rx_ring = adapter->rx_ring;
3192	u64 rdba;
3193	u32 rdlen, rctl, rxcsum, ctrl_ext;
3194
3195	if (adapter->rx_ps_pages) {
3196		/* this is a 32 byte descriptor */
3197		rdlen = rx_ring->count *
3198		    sizeof(union e1000_rx_desc_packet_split);
3199		adapter->clean_rx = e1000_clean_rx_irq_ps;
3200		adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps;
3201	} else if (adapter->netdev->mtu > ETH_FRAME_LEN + ETH_FCS_LEN) {
3202		rdlen = rx_ring->count * sizeof(union e1000_rx_desc_extended);
3203		adapter->clean_rx = e1000_clean_jumbo_rx_irq;
3204		adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers;
3205	} else {
3206		rdlen = rx_ring->count * sizeof(union e1000_rx_desc_extended);
3207		adapter->clean_rx = e1000_clean_rx_irq;
3208		adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
3209	}
3210
3211	/* disable receives while setting up the descriptors */
3212	rctl = er32(RCTL);
3213	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
3214		ew32(RCTL, rctl & ~E1000_RCTL_EN);
3215	e1e_flush();
3216	usleep_range(10000, 11000);
3217
3218	if (adapter->flags2 & FLAG2_DMA_BURST) {
3219		/* set the writeback threshold (only takes effect if the RDTR
3220		 * is set). set GRAN=1 and write back up to 0x4 worth, and
3221		 * enable prefetching of 0x20 Rx descriptors
3222		 * granularity = 01
3223		 * wthresh = 04,
3224		 * hthresh = 04,
3225		 * pthresh = 0x20
3226		 */
3227		ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE);
3228		ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE);
3229	}
3230
3231	/* set the Receive Delay Timer Register */
3232	ew32(RDTR, adapter->rx_int_delay);
3233
3234	/* irq moderation */
3235	ew32(RADV, adapter->rx_abs_int_delay);
3236	if ((adapter->itr_setting != 0) && (adapter->itr != 0))
3237		e1000e_write_itr(adapter, adapter->itr);
3238
3239	ctrl_ext = er32(CTRL_EXT);
3240	/* Auto-Mask interrupts upon ICR access */
3241	ctrl_ext |= E1000_CTRL_EXT_IAME;
3242	ew32(IAM, 0xffffffff);
3243	ew32(CTRL_EXT, ctrl_ext);
3244	e1e_flush();
3245
3246	/* Setup the HW Rx Head and Tail Descriptor Pointers and
3247	 * the Base and Length of the Rx Descriptor Ring
3248	 */
3249	rdba = rx_ring->dma;
3250	ew32(RDBAL(0), (rdba & DMA_BIT_MASK(32)));
3251	ew32(RDBAH(0), (rdba >> 32));
3252	ew32(RDLEN(0), rdlen);
3253	ew32(RDH(0), 0);
3254	ew32(RDT(0), 0);
3255	rx_ring->head = adapter->hw.hw_addr + E1000_RDH(0);
3256	rx_ring->tail = adapter->hw.hw_addr + E1000_RDT(0);
3257
3258	writel(0, rx_ring->head);
3259	if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
3260		e1000e_update_rdt_wa(rx_ring, 0);
3261	else
3262		writel(0, rx_ring->tail);
3263
3264	/* Enable Receive Checksum Offload for TCP and UDP */
3265	rxcsum = er32(RXCSUM);
3266	if (adapter->netdev->features & NETIF_F_RXCSUM)
3267		rxcsum |= E1000_RXCSUM_TUOFL;
3268	else
3269		rxcsum &= ~E1000_RXCSUM_TUOFL;
3270	ew32(RXCSUM, rxcsum);
3271
3272	/* With jumbo frames, excessive C-state transition latencies result
3273	 * in dropped transactions.
3274	 */
3275	if (adapter->netdev->mtu > ETH_DATA_LEN) {
3276		u32 lat =
3277		    ((er32(PBA) & E1000_PBA_RXA_MASK) * 1024 -
3278		     adapter->max_frame_size) * 8 / 1000;
3279
3280		if (adapter->flags & FLAG_IS_ICH) {
3281			u32 rxdctl = er32(RXDCTL(0));
3282
3283			ew32(RXDCTL(0), rxdctl | 0x3 | BIT(8));
3284		}
3285
3286		dev_info(&adapter->pdev->dev,
3287			 "Some CPU C-states have been disabled in order to enable jumbo frames\n");
3288		cpu_latency_qos_update_request(&adapter->pm_qos_req, lat);
3289	} else {
3290		cpu_latency_qos_update_request(&adapter->pm_qos_req,
3291					       PM_QOS_DEFAULT_VALUE);
3292	}
3293
3294	/* Enable Receives */
3295	ew32(RCTL, rctl);
3296}
3297
3298/**
3299 * e1000e_write_mc_addr_list - write multicast addresses to MTA
3300 * @netdev: network interface device structure
3301 *
3302 * Writes multicast address list to the MTA hash table.
3303 * Returns: -ENOMEM on failure
3304 *                0 on no addresses written
3305 *                X on writing X addresses to MTA
3306 */
3307static int e1000e_write_mc_addr_list(struct net_device *netdev)
3308{
3309	struct e1000_adapter *adapter = netdev_priv(netdev);
3310	struct e1000_hw *hw = &adapter->hw;
3311	struct netdev_hw_addr *ha;
3312	u8 *mta_list;
3313	int i;
3314
3315	if (netdev_mc_empty(netdev)) {
3316		/* nothing to program, so clear mc list */
3317		hw->mac.ops.update_mc_addr_list(hw, NULL, 0);
3318		return 0;
3319	}
3320
3321	mta_list = kcalloc(netdev_mc_count(netdev), ETH_ALEN, GFP_ATOMIC);
3322	if (!mta_list)
3323		return -ENOMEM;
3324
3325	/* update_mc_addr_list expects a packed array of only addresses. */
3326	i = 0;
3327	netdev_for_each_mc_addr(ha, netdev)
3328	    memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
3329
3330	hw->mac.ops.update_mc_addr_list(hw, mta_list, i);
3331	kfree(mta_list);
3332
3333	return netdev_mc_count(netdev);
3334}
3335
3336/**
3337 * e1000e_write_uc_addr_list - write unicast addresses to RAR table
3338 * @netdev: network interface device structure
3339 *
3340 * Writes unicast address list to the RAR table.
3341 * Returns: -ENOMEM on failure/insufficient address space
3342 *                0 on no addresses written
3343 *                X on writing X addresses to the RAR table
3344 **/
3345static int e1000e_write_uc_addr_list(struct net_device *netdev)
3346{
3347	struct e1000_adapter *adapter = netdev_priv(netdev);
3348	struct e1000_hw *hw = &adapter->hw;
3349	unsigned int rar_entries;
3350	int count = 0;
3351
3352	rar_entries = hw->mac.ops.rar_get_count(hw);
3353
3354	/* save a rar entry for our hardware address */
3355	rar_entries--;
3356
3357	/* save a rar entry for the LAA workaround */
3358	if (adapter->flags & FLAG_RESET_OVERWRITES_LAA)
3359		rar_entries--;
3360
3361	/* return ENOMEM indicating insufficient memory for addresses */
3362	if (netdev_uc_count(netdev) > rar_entries)
3363		return -ENOMEM;
3364
3365	if (!netdev_uc_empty(netdev) && rar_entries) {
3366		struct netdev_hw_addr *ha;
3367
3368		/* write the addresses in reverse order to avoid write
3369		 * combining
3370		 */
3371		netdev_for_each_uc_addr(ha, netdev) {
3372			int ret_val;
3373
3374			if (!rar_entries)
3375				break;
3376			ret_val = hw->mac.ops.rar_set(hw, ha->addr, rar_entries--);
3377			if (ret_val < 0)
3378				return -ENOMEM;
3379			count++;
3380		}
3381	}
3382
3383	/* zero out the remaining RAR entries not used above */
3384	for (; rar_entries > 0; rar_entries--) {
3385		ew32(RAH(rar_entries), 0);
3386		ew32(RAL(rar_entries), 0);
3387	}
3388	e1e_flush();
3389
3390	return count;
3391}
3392
3393/**
3394 * e1000e_set_rx_mode - secondary unicast, Multicast and Promiscuous mode set
3395 * @netdev: network interface device structure
3396 *
3397 * The ndo_set_rx_mode entry point is called whenever the unicast or multicast
3398 * address list or the network interface flags are updated.  This routine is
3399 * responsible for configuring the hardware for proper unicast, multicast,
3400 * promiscuous mode, and all-multi behavior.
3401 **/
3402static void e1000e_set_rx_mode(struct net_device *netdev)
3403{
3404	struct e1000_adapter *adapter = netdev_priv(netdev);
3405	struct e1000_hw *hw = &adapter->hw;
3406	u32 rctl;
3407
3408	if (pm_runtime_suspended(netdev->dev.parent))
3409		return;
3410
3411	/* Check for Promiscuous and All Multicast modes */
3412	rctl = er32(RCTL);
3413
3414	/* clear the affected bits */
3415	rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
3416
3417	if (netdev->flags & IFF_PROMISC) {
3418		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
3419		/* Do not hardware filter VLANs in promisc mode */
3420		e1000e_vlan_filter_disable(adapter);
3421	} else {
3422		int count;
3423
3424		if (netdev->flags & IFF_ALLMULTI) {
3425			rctl |= E1000_RCTL_MPE;
3426		} else {
3427			/* Write addresses to the MTA, if the attempt fails
3428			 * then we should just turn on promiscuous mode so
3429			 * that we can at least receive multicast traffic
3430			 */
3431			count = e1000e_write_mc_addr_list(netdev);
3432			if (count < 0)
3433				rctl |= E1000_RCTL_MPE;
3434		}
3435		e1000e_vlan_filter_enable(adapter);
3436		/* Write addresses to available RAR registers, if there is not
3437		 * sufficient space to store all the addresses then enable
3438		 * unicast promiscuous mode
3439		 */
3440		count = e1000e_write_uc_addr_list(netdev);
3441		if (count < 0)
3442			rctl |= E1000_RCTL_UPE;
3443	}
3444
3445	ew32(RCTL, rctl);
3446
3447	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
3448		e1000e_vlan_strip_enable(adapter);
3449	else
3450		e1000e_vlan_strip_disable(adapter);
3451}
3452
3453static void e1000e_setup_rss_hash(struct e1000_adapter *adapter)
3454{
3455	struct e1000_hw *hw = &adapter->hw;
3456	u32 mrqc, rxcsum;
3457	u32 rss_key[10];
3458	int i;
3459
3460	netdev_rss_key_fill(rss_key, sizeof(rss_key));
3461	for (i = 0; i < 10; i++)
3462		ew32(RSSRK(i), rss_key[i]);
3463
3464	/* Direct all traffic to queue 0 */
3465	for (i = 0; i < 32; i++)
3466		ew32(RETA(i), 0);
3467
3468	/* Disable raw packet checksumming so that RSS hash is placed in
3469	 * descriptor on writeback.
3470	 */
3471	rxcsum = er32(RXCSUM);
3472	rxcsum |= E1000_RXCSUM_PCSD;
3473
3474	ew32(RXCSUM, rxcsum);
3475
3476	mrqc = (E1000_MRQC_RSS_FIELD_IPV4 |
3477		E1000_MRQC_RSS_FIELD_IPV4_TCP |
3478		E1000_MRQC_RSS_FIELD_IPV6 |
3479		E1000_MRQC_RSS_FIELD_IPV6_TCP |
3480		E1000_MRQC_RSS_FIELD_IPV6_TCP_EX);
3481
3482	ew32(MRQC, mrqc);
3483}
3484
3485/**
3486 * e1000e_get_base_timinca - get default SYSTIM time increment attributes
3487 * @adapter: board private structure
3488 * @timinca: pointer to returned time increment attributes
3489 *
3490 * Get attributes for incrementing the System Time Register SYSTIML/H at
3491 * the default base frequency, and set the cyclecounter shift value.
3492 **/
3493s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
3494{
3495	struct e1000_hw *hw = &adapter->hw;
3496	u32 incvalue, incperiod, shift;
3497
3498	/* Make sure clock is enabled on I217/I218/I219  before checking
3499	 * the frequency
3500	 */
3501	if ((hw->mac.type >= e1000_pch_lpt) &&
3502	    !(er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) &&
3503	    !(er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_ENABLED)) {
3504		u32 fextnvm7 = er32(FEXTNVM7);
3505
3506		if (!(fextnvm7 & BIT(0))) {
3507			ew32(FEXTNVM7, fextnvm7 | BIT(0));
3508			e1e_flush();
3509		}
3510	}
3511
3512	switch (hw->mac.type) {
3513	case e1000_pch2lan:
3514		/* Stable 96MHz frequency */
3515		incperiod = INCPERIOD_96MHZ;
3516		incvalue = INCVALUE_96MHZ;
3517		shift = INCVALUE_SHIFT_96MHZ;
3518		adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ;
3519		break;
3520	case e1000_pch_lpt:
3521		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
3522			/* Stable 96MHz frequency */
3523			incperiod = INCPERIOD_96MHZ;
3524			incvalue = INCVALUE_96MHZ;
3525			shift = INCVALUE_SHIFT_96MHZ;
3526			adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ;
3527		} else {
3528			/* Stable 25MHz frequency */
3529			incperiod = INCPERIOD_25MHZ;
3530			incvalue = INCVALUE_25MHZ;
3531			shift = INCVALUE_SHIFT_25MHZ;
3532			adapter->cc.shift = shift;
3533		}
3534		break;
3535	case e1000_pch_spt:
3536		/* Stable 24MHz frequency */
3537		incperiod = INCPERIOD_24MHZ;
3538		incvalue = INCVALUE_24MHZ;
3539		shift = INCVALUE_SHIFT_24MHZ;
3540		adapter->cc.shift = shift;
3541		break;
3542	case e1000_pch_cnp:
3543	case e1000_pch_tgp:
3544	case e1000_pch_adp:
3545	case e1000_pch_mtp:
3546	case e1000_pch_lnp:
3547	case e1000_pch_ptp:
3548	case e1000_pch_nvp:
3549		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
3550			/* Stable 24MHz frequency */
3551			incperiod = INCPERIOD_24MHZ;
3552			incvalue = INCVALUE_24MHZ;
3553			shift = INCVALUE_SHIFT_24MHZ;
3554			adapter->cc.shift = shift;
3555		} else {
3556			/* Stable 38400KHz frequency */
3557			incperiod = INCPERIOD_38400KHZ;
3558			incvalue = INCVALUE_38400KHZ;
3559			shift = INCVALUE_SHIFT_38400KHZ;
3560			adapter->cc.shift = shift;
3561		}
3562		break;
3563	case e1000_82574:
3564	case e1000_82583:
3565		/* Stable 25MHz frequency */
3566		incperiod = INCPERIOD_25MHZ;
3567		incvalue = INCVALUE_25MHZ;
3568		shift = INCVALUE_SHIFT_25MHZ;
3569		adapter->cc.shift = shift;
3570		break;
3571	default:
3572		return -EINVAL;
3573	}
3574
3575	*timinca = ((incperiod << E1000_TIMINCA_INCPERIOD_SHIFT) |
3576		    ((incvalue << shift) & E1000_TIMINCA_INCVALUE_MASK));
3577
3578	return 0;
3579}
3580
3581/**
3582 * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable
3583 * @adapter: board private structure
3584 * @config: timestamp configuration
3585 *
3586 * Outgoing time stamping can be enabled and disabled. Play nice and
3587 * disable it when requested, although it shouldn't cause any overhead
3588 * when no packet needs it. At most one packet in the queue may be
3589 * marked for time stamping, otherwise it would be impossible to tell
3590 * for sure to which packet the hardware time stamp belongs.
3591 *
3592 * Incoming time stamping has to be configured via the hardware filters.
3593 * Not all combinations are supported, in particular event type has to be
3594 * specified. Matching the kind of event packet is not supported, with the
3595 * exception of "all V2 events regardless of level 2 or 4".
3596 **/
3597static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
3598				  struct hwtstamp_config *config)
3599{
3600	struct e1000_hw *hw = &adapter->hw;
3601	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
3602	u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
3603	u32 rxmtrl = 0;
3604	u16 rxudp = 0;
3605	bool is_l4 = false;
3606	bool is_l2 = false;
3607	u32 regval;
3608
3609	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP))
3610		return -EINVAL;
3611
3612	switch (config->tx_type) {
3613	case HWTSTAMP_TX_OFF:
3614		tsync_tx_ctl = 0;
3615		break;
3616	case HWTSTAMP_TX_ON:
3617		break;
3618	default:
3619		return -ERANGE;
3620	}
3621
3622	switch (config->rx_filter) {
3623	case HWTSTAMP_FILTER_NONE:
3624		tsync_rx_ctl = 0;
3625		break;
3626	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
3627		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
3628		rxmtrl = E1000_RXMTRL_PTP_V1_SYNC_MESSAGE;
3629		is_l4 = true;
3630		break;
3631	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
3632		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
3633		rxmtrl = E1000_RXMTRL_PTP_V1_DELAY_REQ_MESSAGE;
3634		is_l4 = true;
3635		break;
3636	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
3637		/* Also time stamps V2 L2 Path Delay Request/Response */
3638		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_V2;
3639		rxmtrl = E1000_RXMTRL_PTP_V2_SYNC_MESSAGE;
3640		is_l2 = true;
3641		break;
3642	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
3643		/* Also time stamps V2 L2 Path Delay Request/Response. */
3644		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_V2;
3645		rxmtrl = E1000_RXMTRL_PTP_V2_DELAY_REQ_MESSAGE;
3646		is_l2 = true;
3647		break;
3648	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
3649		/* Hardware cannot filter just V2 L4 Sync messages */
3650		fallthrough;
3651	case HWTSTAMP_FILTER_PTP_V2_SYNC:
3652		/* Also time stamps V2 Path Delay Request/Response. */
3653		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
3654		rxmtrl = E1000_RXMTRL_PTP_V2_SYNC_MESSAGE;
3655		is_l2 = true;
3656		is_l4 = true;
3657		break;
3658	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
3659		/* Hardware cannot filter just V2 L4 Delay Request messages */
3660		fallthrough;
3661	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
3662		/* Also time stamps V2 Path Delay Request/Response. */
3663		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
3664		rxmtrl = E1000_RXMTRL_PTP_V2_DELAY_REQ_MESSAGE;
3665		is_l2 = true;
3666		is_l4 = true;
3667		break;
3668	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
3669	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
3670		/* Hardware cannot filter just V2 L4 or L2 Event messages */
3671		fallthrough;
3672	case HWTSTAMP_FILTER_PTP_V2_EVENT:
3673		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2;
3674		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
3675		is_l2 = true;
3676		is_l4 = true;
3677		break;
3678	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
3679		/* For V1, the hardware can only filter Sync messages or
3680		 * Delay Request messages but not both so fall-through to
3681		 * time stamp all packets.
3682		 */
3683		fallthrough;
3684	case HWTSTAMP_FILTER_NTP_ALL:
3685	case HWTSTAMP_FILTER_ALL:
3686		is_l2 = true;
3687		is_l4 = true;
3688		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
3689		config->rx_filter = HWTSTAMP_FILTER_ALL;
3690		break;
3691	default:
3692		return -ERANGE;
3693	}
3694
3695	adapter->hwtstamp_config = *config;
3696
3697	/* enable/disable Tx h/w time stamping */
3698	regval = er32(TSYNCTXCTL);
3699	regval &= ~E1000_TSYNCTXCTL_ENABLED;
3700	regval |= tsync_tx_ctl;
3701	ew32(TSYNCTXCTL, regval);
3702	if ((er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) !=
3703	    (regval & E1000_TSYNCTXCTL_ENABLED)) {
3704		e_err("Timesync Tx Control register not set as expected\n");
3705		return -EAGAIN;
3706	}
3707
3708	/* enable/disable Rx h/w time stamping */
3709	regval = er32(TSYNCRXCTL);
3710	regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK);
3711	regval |= tsync_rx_ctl;
3712	ew32(TSYNCRXCTL, regval);
3713	if ((er32(TSYNCRXCTL) & (E1000_TSYNCRXCTL_ENABLED |
3714				 E1000_TSYNCRXCTL_TYPE_MASK)) !=
3715	    (regval & (E1000_TSYNCRXCTL_ENABLED |
3716		       E1000_TSYNCRXCTL_TYPE_MASK))) {
3717		e_err("Timesync Rx Control register not set as expected\n");
3718		return -EAGAIN;
3719	}
3720
3721	/* L2: define ethertype filter for time stamped packets */
3722	if (is_l2)
3723		rxmtrl |= ETH_P_1588;
3724
3725	/* define which PTP packets get time stamped */
3726	ew32(RXMTRL, rxmtrl);
3727
3728	/* Filter by destination port */
3729	if (is_l4) {
3730		rxudp = PTP_EV_PORT;
3731		cpu_to_be16s(&rxudp);
3732	}
3733	ew32(RXUDP, rxudp);
3734
3735	e1e_flush();
3736
3737	/* Clear TSYNCRXCTL_VALID & TSYNCTXCTL_VALID bit */
3738	er32(RXSTMPH);
3739	er32(TXSTMPH);
3740
3741	return 0;
3742}
3743
3744/**
3745 * e1000_configure - configure the hardware for Rx and Tx
3746 * @adapter: private board structure
3747 **/
3748static void e1000_configure(struct e1000_adapter *adapter)
3749{
3750	struct e1000_ring *rx_ring = adapter->rx_ring;
3751
3752	e1000e_set_rx_mode(adapter->netdev);
3753
3754	e1000_restore_vlan(adapter);
3755	e1000_init_manageability_pt(adapter);
3756
3757	e1000_configure_tx(adapter);
3758
3759	if (adapter->netdev->features & NETIF_F_RXHASH)
3760		e1000e_setup_rss_hash(adapter);
3761	e1000_setup_rctl(adapter);
3762	e1000_configure_rx(adapter);
3763	adapter->alloc_rx_buf(rx_ring, e1000_desc_unused(rx_ring), GFP_KERNEL);
3764}
3765
3766/**
3767 * e1000e_power_up_phy - restore link in case the phy was powered down
3768 * @adapter: address of board private structure
3769 *
3770 * The phy may be powered down to save power and turn off link when the
3771 * driver is unloaded and wake on lan is not enabled (among others)
3772 * *** this routine MUST be followed by a call to e1000e_reset ***
3773 **/
3774void e1000e_power_up_phy(struct e1000_adapter *adapter)
3775{
3776	if (adapter->hw.phy.ops.power_up)
3777		adapter->hw.phy.ops.power_up(&adapter->hw);
3778
3779	adapter->hw.mac.ops.setup_link(&adapter->hw);
3780}
3781
3782/**
3783 * e1000_power_down_phy - Power down the PHY
3784 * @adapter: board private structure
3785 *
3786 * Power down the PHY so no link is implied when interface is down.
3787 * The PHY cannot be powered down if management or WoL is active.
3788 */
3789static void e1000_power_down_phy(struct e1000_adapter *adapter)
3790{
3791	if (adapter->hw.phy.ops.power_down)
3792		adapter->hw.phy.ops.power_down(&adapter->hw);
3793}
3794
3795/**
3796 * e1000_flush_tx_ring - remove all descriptors from the tx_ring
3797 * @adapter: board private structure
3798 *
3799 * We want to clear all pending descriptors from the TX ring.
3800 * zeroing happens when the HW reads the regs. We  assign the ring itself as
3801 * the data of the next descriptor. We don't care about the data we are about
3802 * to reset the HW.
3803 */
3804static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
3805{
3806	struct e1000_hw *hw = &adapter->hw;
3807	struct e1000_ring *tx_ring = adapter->tx_ring;
3808	struct e1000_tx_desc *tx_desc = NULL;
3809	u32 tdt, tctl, txd_lower = E1000_TXD_CMD_IFCS;
3810	u16 size = 512;
3811
3812	tctl = er32(TCTL);
3813	ew32(TCTL, tctl | E1000_TCTL_EN);
3814	tdt = er32(TDT(0));
3815	BUG_ON(tdt != tx_ring->next_to_use);
3816	tx_desc =  E1000_TX_DESC(*tx_ring, tx_ring->next_to_use);
3817	tx_desc->buffer_addr = cpu_to_le64(tx_ring->dma);
3818
3819	tx_desc->lower.data = cpu_to_le32(txd_lower | size);
3820	tx_desc->upper.data = 0;
3821	/* flush descriptors to memory before notifying the HW */
3822	wmb();
3823	tx_ring->next_to_use++;
3824	if (tx_ring->next_to_use == tx_ring->count)
3825		tx_ring->next_to_use = 0;
3826	ew32(TDT(0), tx_ring->next_to_use);
3827	usleep_range(200, 250);
3828}
3829
3830/**
3831 * e1000_flush_rx_ring - remove all descriptors from the rx_ring
3832 * @adapter: board private structure
3833 *
3834 * Mark all descriptors in the RX ring as consumed and disable the rx ring
3835 */
3836static void e1000_flush_rx_ring(struct e1000_adapter *adapter)
3837{
3838	u32 rctl, rxdctl;
3839	struct e1000_hw *hw = &adapter->hw;
3840
3841	rctl = er32(RCTL);
3842	ew32(RCTL, rctl & ~E1000_RCTL_EN);
3843	e1e_flush();
3844	usleep_range(100, 150);
3845
3846	rxdctl = er32(RXDCTL(0));
3847	/* zero the lower 14 bits (prefetch and host thresholds) */
3848	rxdctl &= 0xffffc000;
3849
3850	/* update thresholds: prefetch threshold to 31, host threshold to 1
3851	 * and make sure the granularity is "descriptors" and not "cache lines"
3852	 */
3853	rxdctl |= (0x1F | BIT(8) | E1000_RXDCTL_THRESH_UNIT_DESC);
3854
3855	ew32(RXDCTL(0), rxdctl);
3856	/* momentarily enable the RX ring for the changes to take effect */
3857	ew32(RCTL, rctl | E1000_RCTL_EN);
3858	e1e_flush();
3859	usleep_range(100, 150);
3860	ew32(RCTL, rctl & ~E1000_RCTL_EN);
3861}
3862
3863/**
3864 * e1000_flush_desc_rings - remove all descriptors from the descriptor rings
3865 * @adapter: board private structure
3866 *
3867 * In i219, the descriptor rings must be emptied before resetting the HW
3868 * or before changing the device state to D3 during runtime (runtime PM).
3869 *
3870 * Failure to do this will cause the HW to enter a unit hang state which can
3871 * only be released by PCI reset on the device
3872 *
3873 */
3874
3875static void e1000_flush_desc_rings(struct e1000_adapter *adapter)
3876{
3877	u16 hang_state;
3878	u32 fext_nvm11, tdlen;
3879	struct e1000_hw *hw = &adapter->hw;
3880
3881	/* First, disable MULR fix in FEXTNVM11 */
3882	fext_nvm11 = er32(FEXTNVM11);
3883	fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX;
3884	ew32(FEXTNVM11, fext_nvm11);
3885	/* do nothing if we're not in faulty state, or if the queue is empty */
3886	tdlen = er32(TDLEN(0));
3887	pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS,
3888			     &hang_state);
3889	if (!(hang_state & FLUSH_DESC_REQUIRED) || !tdlen)
3890		return;
3891	e1000_flush_tx_ring(adapter);
3892	/* recheck, maybe the fault is caused by the rx ring */
3893	pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS,
3894			     &hang_state);
3895	if (hang_state & FLUSH_DESC_REQUIRED)
3896		e1000_flush_rx_ring(adapter);
3897}
3898
3899/**
3900 * e1000e_systim_reset - reset the timesync registers after a hardware reset
3901 * @adapter: board private structure
3902 *
3903 * When the MAC is reset, all hardware bits for timesync will be reset to the
3904 * default values. This function will restore the settings last in place.
3905 * Since the clock SYSTIME registers are reset, we will simply restore the
3906 * cyclecounter to the kernel real clock time.
3907 **/
3908static void e1000e_systim_reset(struct e1000_adapter *adapter)
3909{
3910	struct ptp_clock_info *info = &adapter->ptp_clock_info;
3911	struct e1000_hw *hw = &adapter->hw;
3912	unsigned long flags;
3913	u32 timinca;
3914	s32 ret_val;
3915
3916	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP))
3917		return;
3918
3919	if (info->adjfine) {
3920		/* restore the previous ptp frequency delta */
3921		ret_val = info->adjfine(info, adapter->ptp_delta);
3922	} else {
3923		/* set the default base frequency if no adjustment possible */
3924		ret_val = e1000e_get_base_timinca(adapter, &timinca);
3925		if (!ret_val)
3926			ew32(TIMINCA, timinca);
3927	}
3928
3929	if (ret_val) {
3930		dev_warn(&adapter->pdev->dev,
3931			 "Failed to restore TIMINCA clock rate delta: %d\n",
3932			 ret_val);
3933		return;
3934	}
3935
3936	/* reset the systim ns time counter */
3937	spin_lock_irqsave(&adapter->systim_lock, flags);
3938	timecounter_init(&adapter->tc, &adapter->cc,
3939			 ktime_to_ns(ktime_get_real()));
3940	spin_unlock_irqrestore(&adapter->systim_lock, flags);
3941
3942	/* restore the previous hwtstamp configuration settings */
3943	e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config);
3944}
3945
3946/**
3947 * e1000e_reset - bring the hardware into a known good state
3948 * @adapter: board private structure
3949 *
3950 * This function boots the hardware and enables some settings that
3951 * require a configuration cycle of the hardware - those cannot be
3952 * set/changed during runtime. After reset the device needs to be
3953 * properly configured for Rx, Tx etc.
3954 */
3955void e1000e_reset(struct e1000_adapter *adapter)
3956{
3957	struct e1000_mac_info *mac = &adapter->hw.mac;
3958	struct e1000_fc_info *fc = &adapter->hw.fc;
3959	struct e1000_hw *hw = &adapter->hw;
3960	u32 tx_space, min_tx_space, min_rx_space;
3961	u32 pba = adapter->pba;
3962	u16 hwm;
3963
3964	/* reset Packet Buffer Allocation to default */
3965	ew32(PBA, pba);
3966
3967	if (adapter->max_frame_size > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) {
3968		/* To maintain wire speed transmits, the Tx FIFO should be
3969		 * large enough to accommodate two full transmit packets,
3970		 * rounded up to the next 1KB and expressed in KB.  Likewise,
3971		 * the Rx FIFO should be large enough to accommodate at least
3972		 * one full receive packet and is similarly rounded up and
3973		 * expressed in KB.
3974		 */
3975		pba = er32(PBA);
3976		/* upper 16 bits has Tx packet buffer allocation size in KB */
3977		tx_space = pba >> 16;
3978		/* lower 16 bits has Rx packet buffer allocation size in KB */
3979		pba &= 0xffff;
3980		/* the Tx fifo also stores 16 bytes of information about the Tx
3981		 * but don't include ethernet FCS because hardware appends it
3982		 */
3983		min_tx_space = (adapter->max_frame_size +
3984				sizeof(struct e1000_tx_desc) - ETH_FCS_LEN) * 2;
3985		min_tx_space = ALIGN(min_tx_space, 1024);
3986		min_tx_space >>= 10;
3987		/* software strips receive CRC, so leave room for it */
3988		min_rx_space = adapter->max_frame_size;
3989		min_rx_space = ALIGN(min_rx_space, 1024);
3990		min_rx_space >>= 10;
3991
3992		/* If current Tx allocation is less than the min Tx FIFO size,
3993		 * and the min Tx FIFO size is less than the current Rx FIFO
3994		 * allocation, take space away from current Rx allocation
3995		 */
3996		if ((tx_space < min_tx_space) &&
3997		    ((min_tx_space - tx_space) < pba)) {
3998			pba -= min_tx_space - tx_space;
3999
4000			/* if short on Rx space, Rx wins and must trump Tx
4001			 * adjustment
4002			 */
4003			if (pba < min_rx_space)
4004				pba = min_rx_space;
4005		}
4006
4007		ew32(PBA, pba);
4008	}
4009
4010	/* flow control settings
4011	 *
4012	 * The high water mark must be low enough to fit one full frame
4013	 * (or the size used for early receive) above it in the Rx FIFO.
4014	 * Set it to the lower of:
4015	 * - 90% of the Rx FIFO size, and
4016	 * - the full Rx FIFO size minus one full frame
4017	 */
4018	if (adapter->flags & FLAG_DISABLE_FC_PAUSE_TIME)
4019		fc->pause_time = 0xFFFF;
4020	else
4021		fc->pause_time = E1000_FC_PAUSE_TIME;
4022	fc->send_xon = true;
4023	fc->current_mode = fc->requested_mode;
4024
4025	switch (hw->mac.type) {
4026	case e1000_ich9lan:
4027	case e1000_ich10lan:
4028		if (adapter->netdev->mtu > ETH_DATA_LEN) {
4029			pba = 14;
4030			ew32(PBA, pba);
4031			fc->high_water = 0x2800;
4032			fc->low_water = fc->high_water - 8;
4033			break;
4034		}
4035		fallthrough;
4036	default:
4037		hwm = min(((pba << 10) * 9 / 10),
4038			  ((pba << 10) - adapter->max_frame_size));
4039
4040		fc->high_water = hwm & E1000_FCRTH_RTH;	/* 8-byte granularity */
4041		fc->low_water = fc->high_water - 8;
4042		break;
4043	case e1000_pchlan:
4044		/* Workaround PCH LOM adapter hangs with certain network
4045		 * loads.  If hangs persist, try disabling Tx flow control.
4046		 */
4047		if (adapter->netdev->mtu > ETH_DATA_LEN) {
4048			fc->high_water = 0x3500;
4049			fc->low_water = 0x1500;
4050		} else {
4051			fc->high_water = 0x5000;
4052			fc->low_water = 0x3000;
4053		}
4054		fc->refresh_time = 0x1000;
4055		break;
4056	case e1000_pch2lan:
4057	case e1000_pch_lpt:
4058	case e1000_pch_spt:
4059	case e1000_pch_cnp:
4060	case e1000_pch_tgp:
4061	case e1000_pch_adp:
4062	case e1000_pch_mtp:
4063	case e1000_pch_lnp:
4064	case e1000_pch_ptp:
4065	case e1000_pch_nvp:
4066		fc->refresh_time = 0xFFFF;
4067		fc->pause_time = 0xFFFF;
4068
4069		if (adapter->netdev->mtu <= ETH_DATA_LEN) {
4070			fc->high_water = 0x05C20;
4071			fc->low_water = 0x05048;
4072			break;
4073		}
4074
4075		pba = 14;
4076		ew32(PBA, pba);
4077		fc->high_water = ((pba << 10) * 9 / 10) & E1000_FCRTH_RTH;
4078		fc->low_water = ((pba << 10) * 8 / 10) & E1000_FCRTL_RTL;
4079		break;
4080	}
4081
4082	/* Alignment of Tx data is on an arbitrary byte boundary with the
4083	 * maximum size per Tx descriptor limited only to the transmit
4084	 * allocation of the packet buffer minus 96 bytes with an upper
4085	 * limit of 24KB due to receive synchronization limitations.
4086	 */
4087	adapter->tx_fifo_limit = min_t(u32, ((er32(PBA) >> 16) << 10) - 96,
4088				       24 << 10);
4089
4090	/* Disable Adaptive Interrupt Moderation if 2 full packets cannot
4091	 * fit in receive buffer.
4092	 */
4093	if (adapter->itr_setting & 0x3) {
4094		if ((adapter->max_frame_size * 2) > (pba << 10)) {
4095			if (!(adapter->flags2 & FLAG2_DISABLE_AIM)) {
4096				dev_info(&adapter->pdev->dev,
4097					 "Interrupt Throttle Rate off\n");
4098				adapter->flags2 |= FLAG2_DISABLE_AIM;
4099				e1000e_write_itr(adapter, 0);
4100			}
4101		} else if (adapter->flags2 & FLAG2_DISABLE_AIM) {
4102			dev_info(&adapter->pdev->dev,
4103				 "Interrupt Throttle Rate on\n");
4104			adapter->flags2 &= ~FLAG2_DISABLE_AIM;
4105			adapter->itr = 20000;
4106			e1000e_write_itr(adapter, adapter->itr);
4107		}
4108	}
4109
4110	if (hw->mac.type >= e1000_pch_spt)
4111		e1000_flush_desc_rings(adapter);
4112	/* Allow time for pending master requests to run */
4113	mac->ops.reset_hw(hw);
4114
4115	/* For parts with AMT enabled, let the firmware know
4116	 * that the network interface is in control
4117	 */
4118	if (adapter->flags & FLAG_HAS_AMT)
4119		e1000e_get_hw_control(adapter);
4120
4121	ew32(WUC, 0);
4122
4123	if (mac->ops.init_hw(hw))
4124		e_err("Hardware Error\n");
4125
4126	e1000_update_mng_vlan(adapter);
4127
4128	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
4129	ew32(VET, ETH_P_8021Q);
4130
4131	e1000e_reset_adaptive(hw);
4132
4133	/* restore systim and hwtstamp settings */
4134	e1000e_systim_reset(adapter);
4135
4136	/* Set EEE advertisement as appropriate */
4137	if (adapter->flags2 & FLAG2_HAS_EEE) {
4138		s32 ret_val;
4139		u16 adv_addr;
4140
4141		switch (hw->phy.type) {
4142		case e1000_phy_82579:
4143			adv_addr = I82579_EEE_ADVERTISEMENT;
4144			break;
4145		case e1000_phy_i217:
4146			adv_addr = I217_EEE_ADVERTISEMENT;
4147			break;
4148		default:
4149			dev_err(&adapter->pdev->dev,
4150				"Invalid PHY type setting EEE advertisement\n");
4151			return;
4152		}
4153
4154		ret_val = hw->phy.ops.acquire(hw);
4155		if (ret_val) {
4156			dev_err(&adapter->pdev->dev,
4157				"EEE advertisement - unable to acquire PHY\n");
4158			return;
4159		}
4160
4161		e1000_write_emi_reg_locked(hw, adv_addr,
4162					   hw->dev_spec.ich8lan.eee_disable ?
4163					   0 : adapter->eee_advert);
4164
4165		hw->phy.ops.release(hw);
4166	}
4167
4168	if (!netif_running(adapter->netdev) &&
4169	    !test_bit(__E1000_TESTING, &adapter->state))
4170		e1000_power_down_phy(adapter);
4171
4172	e1000_get_phy_info(hw);
4173
4174	if ((adapter->flags & FLAG_HAS_SMART_POWER_DOWN) &&
4175	    !(adapter->flags & FLAG_SMART_POWER_DOWN)) {
4176		u16 phy_data = 0;
4177		/* speed up time to link by disabling smart power down, ignore
4178		 * the return value of this function because there is nothing
4179		 * different we would do if it failed
4180		 */
4181		e1e_rphy(hw, IGP02E1000_PHY_POWER_MGMT, &phy_data);
4182		phy_data &= ~IGP02E1000_PM_SPD;
4183		e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data);
4184	}
4185	if (hw->mac.type >= e1000_pch_spt && adapter->int_mode == 0) {
4186		u32 reg;
4187
4188		/* Fextnvm7 @ 0xe4[2] = 1 */
4189		reg = er32(FEXTNVM7);
4190		reg |= E1000_FEXTNVM7_SIDE_CLK_UNGATE;
4191		ew32(FEXTNVM7, reg);
4192		/* Fextnvm9 @ 0x5bb4[13:12] = 11 */
4193		reg = er32(FEXTNVM9);
4194		reg |= E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS |
4195		       E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS;
4196		ew32(FEXTNVM9, reg);
4197	}
4198
4199}
4200
4201/**
4202 * e1000e_trigger_lsc - trigger an LSC interrupt
4203 * @adapter: board private structure
4204 *
4205 * Fire a link status change interrupt to start the watchdog.
4206 **/
4207static void e1000e_trigger_lsc(struct e1000_adapter *adapter)
4208{
4209	struct e1000_hw *hw = &adapter->hw;
4210
4211	if (adapter->msix_entries)
4212		ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER);
4213	else
4214		ew32(ICS, E1000_ICS_LSC);
4215}
4216
4217void e1000e_up(struct e1000_adapter *adapter)
4218{
4219	/* hardware has been reset, we need to reload some things */
4220	e1000_configure(adapter);
4221
4222	clear_bit(__E1000_DOWN, &adapter->state);
4223
4224	if (adapter->msix_entries)
4225		e1000_configure_msix(adapter);
4226	e1000_irq_enable(adapter);
4227
4228	/* Tx queue started by watchdog timer when link is up */
4229
4230	e1000e_trigger_lsc(adapter);
4231}
4232
4233static void e1000e_flush_descriptors(struct e1000_adapter *adapter)
4234{
4235	struct e1000_hw *hw = &adapter->hw;
4236
4237	if (!(adapter->flags2 & FLAG2_DMA_BURST))
4238		return;
4239
4240	/* flush pending descriptor writebacks to memory */
4241	ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
4242	ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
4243
4244	/* execute the writes immediately */
4245	e1e_flush();
4246
4247	/* due to rare timing issues, write to TIDV/RDTR again to ensure the
4248	 * write is successful
4249	 */
4250	ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
4251	ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
4252
4253	/* execute the writes immediately */
4254	e1e_flush();
4255}
4256
4257static void e1000e_update_stats(struct e1000_adapter *adapter);
4258
4259/**
4260 * e1000e_down - quiesce the device and optionally reset the hardware
4261 * @adapter: board private structure
4262 * @reset: boolean flag to reset the hardware or not
4263 */
4264void e1000e_down(struct e1000_adapter *adapter, bool reset)
4265{
4266	struct net_device *netdev = adapter->netdev;
4267	struct e1000_hw *hw = &adapter->hw;
4268	u32 tctl, rctl;
4269
4270	/* signal that we're down so the interrupt handler does not
4271	 * reschedule our watchdog timer
4272	 */
4273	set_bit(__E1000_DOWN, &adapter->state);
4274
4275	netif_carrier_off(netdev);
4276
4277	/* disable receives in the hardware */
4278	rctl = er32(RCTL);
4279	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
4280		ew32(RCTL, rctl & ~E1000_RCTL_EN);
4281	/* flush and sleep below */
4282
4283	netif_stop_queue(netdev);
4284
4285	/* disable transmits in the hardware */
4286	tctl = er32(TCTL);
4287	tctl &= ~E1000_TCTL_EN;
4288	ew32(TCTL, tctl);
4289
4290	/* flush both disables and wait for them to finish */
4291	e1e_flush();
4292	usleep_range(10000, 11000);
4293
4294	e1000_irq_disable(adapter);
4295
4296	napi_synchronize(&adapter->napi);
4297
4298	del_timer_sync(&adapter->watchdog_timer);
4299	del_timer_sync(&adapter->phy_info_timer);
4300
4301	spin_lock(&adapter->stats64_lock);
4302	e1000e_update_stats(adapter);
4303	spin_unlock(&adapter->stats64_lock);
4304
4305	e1000e_flush_descriptors(adapter);
4306
4307	adapter->link_speed = 0;
4308	adapter->link_duplex = 0;
4309
4310	/* Disable Si errata workaround on PCHx for jumbo frame flow */
4311	if ((hw->mac.type >= e1000_pch2lan) &&
4312	    (adapter->netdev->mtu > ETH_DATA_LEN) &&
4313	    e1000_lv_jumbo_workaround_ich8lan(hw, false))
4314		e_dbg("failed to disable jumbo frame workaround mode\n");
4315
4316	if (!pci_channel_offline(adapter->pdev)) {
4317		if (reset)
4318			e1000e_reset(adapter);
4319		else if (hw->mac.type >= e1000_pch_spt)
4320			e1000_flush_desc_rings(adapter);
4321	}
4322	e1000_clean_tx_ring(adapter->tx_ring);
4323	e1000_clean_rx_ring(adapter->rx_ring);
4324}
4325
4326void e1000e_reinit_locked(struct e1000_adapter *adapter)
4327{
4328	might_sleep();
4329	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
4330		usleep_range(1000, 1100);
4331	e1000e_down(adapter, true);
4332	e1000e_up(adapter);
4333	clear_bit(__E1000_RESETTING, &adapter->state);
4334}
4335
4336/**
4337 * e1000e_sanitize_systim - sanitize raw cycle counter reads
4338 * @hw: pointer to the HW structure
4339 * @systim: PHC time value read, sanitized and returned
4340 * @sts: structure to hold system time before and after reading SYSTIML,
4341 * may be NULL
4342 *
4343 * Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
4344 * check to see that the time is incrementing at a reasonable
4345 * rate and is a multiple of incvalue.
4346 **/
4347static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim,
4348				  struct ptp_system_timestamp *sts)
4349{
4350	u64 time_delta, rem, temp;
4351	u64 systim_next;
4352	u32 incvalue;
4353	int i;
4354
4355	incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
4356	for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
4357		/* latch SYSTIMH on read of SYSTIML */
4358		ptp_read_system_prets(sts);
4359		systim_next = (u64)er32(SYSTIML);
4360		ptp_read_system_postts(sts);
4361		systim_next |= (u64)er32(SYSTIMH) << 32;
4362
4363		time_delta = systim_next - systim;
4364		temp = time_delta;
4365		/* VMWare users have seen incvalue of zero, don't div / 0 */
4366		rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0);
4367
4368		systim = systim_next;
4369
4370		if ((time_delta < E1000_82574_SYSTIM_EPSILON) && (rem == 0))
4371			break;
4372	}
4373
4374	return systim;
4375}
4376
4377/**
4378 * e1000e_read_systim - read SYSTIM register
4379 * @adapter: board private structure
4380 * @sts: structure which will contain system time before and after reading
4381 * SYSTIML, may be NULL
4382 **/
4383u64 e1000e_read_systim(struct e1000_adapter *adapter,
4384		       struct ptp_system_timestamp *sts)
4385{
4386	struct e1000_hw *hw = &adapter->hw;
4387	u32 systimel, systimel_2, systimeh;
4388	u64 systim;
4389	/* SYSTIMH latching upon SYSTIML read does not work well.
4390	 * This means that if SYSTIML overflows after we read it but before
4391	 * we read SYSTIMH, the value of SYSTIMH has been incremented and we
4392	 * will experience a huge non linear increment in the systime value
4393	 * to fix that we test for overflow and if true, we re-read systime.
4394	 */
4395	ptp_read_system_prets(sts);
4396	systimel = er32(SYSTIML);
4397	ptp_read_system_postts(sts);
4398	systimeh = er32(SYSTIMH);
4399	/* Is systimel is so large that overflow is possible? */
4400	if (systimel >= (u32)0xffffffff - E1000_TIMINCA_INCVALUE_MASK) {
4401		ptp_read_system_prets(sts);
4402		systimel_2 = er32(SYSTIML);
4403		ptp_read_system_postts(sts);
4404		if (systimel > systimel_2) {
4405			/* There was an overflow, read again SYSTIMH, and use
4406			 * systimel_2
4407			 */
4408			systimeh = er32(SYSTIMH);
4409			systimel = systimel_2;
4410		}
4411	}
4412	systim = (u64)systimel;
4413	systim |= (u64)systimeh << 32;
4414
4415	if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
4416		systim = e1000e_sanitize_systim(hw, systim, sts);
4417
4418	return systim;
4419}
4420
4421/**
4422 * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
4423 * @cc: cyclecounter structure
4424 **/
4425static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
4426{
4427	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
4428						     cc);
4429
4430	return e1000e_read_systim(adapter, NULL);
4431}
4432
4433/**
4434 * e1000_sw_init - Initialize general software structures (struct e1000_adapter)
4435 * @adapter: board private structure to initialize
4436 *
4437 * e1000_sw_init initializes the Adapter private data structure.
4438 * Fields are initialized based on PCI device information and
4439 * OS network device settings (MTU size).
4440 **/
4441static int e1000_sw_init(struct e1000_adapter *adapter)
4442{
4443	struct net_device *netdev = adapter->netdev;
4444
4445	adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
4446	adapter->rx_ps_bsize0 = 128;
4447	adapter->max_frame_size = netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
4448	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
4449	adapter->tx_ring_count = E1000_DEFAULT_TXD;
4450	adapter->rx_ring_count = E1000_DEFAULT_RXD;
4451
4452	spin_lock_init(&adapter->stats64_lock);
4453
4454	e1000e_set_interrupt_capability(adapter);
4455
4456	if (e1000_alloc_queues(adapter))
4457		return -ENOMEM;
4458
4459	/* Setup hardware time stamping cyclecounter */
4460	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
4461		adapter->cc.read = e1000e_cyclecounter_read;
4462		adapter->cc.mask = CYCLECOUNTER_MASK(64);
4463		adapter->cc.mult = 1;
4464		/* cc.shift set in e1000e_get_base_tininca() */
4465
4466		spin_lock_init(&adapter->systim_lock);
4467		INIT_WORK(&adapter->tx_hwtstamp_work, e1000e_tx_hwtstamp_work);
4468	}
4469
4470	/* Explicitly disable IRQ since the NIC can be in any state. */
4471	e1000_irq_disable(adapter);
4472
4473	set_bit(__E1000_DOWN, &adapter->state);
4474	return 0;
4475}
4476
4477/**
4478 * e1000_intr_msi_test - Interrupt Handler
4479 * @irq: interrupt number
4480 * @data: pointer to a network interface device structure
4481 **/
4482static irqreturn_t e1000_intr_msi_test(int __always_unused irq, void *data)
4483{
4484	struct net_device *netdev = data;
4485	struct e1000_adapter *adapter = netdev_priv(netdev);
4486	struct e1000_hw *hw = &adapter->hw;
4487	u32 icr = er32(ICR);
4488
4489	e_dbg("icr is %08X\n", icr);
4490	if (icr & E1000_ICR_RXSEQ) {
4491		adapter->flags &= ~FLAG_MSI_TEST_FAILED;
4492		/* Force memory writes to complete before acknowledging the
4493		 * interrupt is handled.
4494		 */
4495		wmb();
4496	}
4497
4498	return IRQ_HANDLED;
4499}
4500
4501/**
4502 * e1000_test_msi_interrupt - Returns 0 for successful test
4503 * @adapter: board private struct
4504 *
4505 * code flow taken from tg3.c
4506 **/
4507static int e1000_test_msi_interrupt(struct e1000_adapter *adapter)
4508{
4509	struct net_device *netdev = adapter->netdev;
4510	struct e1000_hw *hw = &adapter->hw;
4511	int err;
4512
4513	/* poll_enable hasn't been called yet, so don't need disable */
4514	/* clear any pending events */
4515	er32(ICR);
4516
4517	/* free the real vector and request a test handler */
4518	e1000_free_irq(adapter);
4519	e1000e_reset_interrupt_capability(adapter);
4520
4521	/* Assume that the test fails, if it succeeds then the test
4522	 * MSI irq handler will unset this flag
4523	 */
4524	adapter->flags |= FLAG_MSI_TEST_FAILED;
4525
4526	err = pci_enable_msi(adapter->pdev);
4527	if (err)
4528		goto msi_test_failed;
4529
4530	err = request_irq(adapter->pdev->irq, e1000_intr_msi_test, 0,
4531			  netdev->name, netdev);
4532	if (err) {
4533		pci_disable_msi(adapter->pdev);
4534		goto msi_test_failed;
4535	}
4536
4537	/* Force memory writes to complete before enabling and firing an
4538	 * interrupt.
4539	 */
4540	wmb();
4541
4542	e1000_irq_enable(adapter);
4543
4544	/* fire an unusual interrupt on the test handler */
4545	ew32(ICS, E1000_ICS_RXSEQ);
4546	e1e_flush();
4547	msleep(100);
4548
4549	e1000_irq_disable(adapter);
4550
4551	rmb();			/* read flags after interrupt has been fired */
4552
4553	if (adapter->flags & FLAG_MSI_TEST_FAILED) {
4554		adapter->int_mode = E1000E_INT_MODE_LEGACY;
4555		e_info("MSI interrupt test failed, using legacy interrupt.\n");
4556	} else {
4557		e_dbg("MSI interrupt test succeeded!\n");
4558	}
4559
4560	free_irq(adapter->pdev->irq, netdev);
4561	pci_disable_msi(adapter->pdev);
4562
4563msi_test_failed:
4564	e1000e_set_interrupt_capability(adapter);
4565	return e1000_request_irq(adapter);
4566}
4567
4568/**
4569 * e1000_test_msi - Returns 0 if MSI test succeeds or INTx mode is restored
4570 * @adapter: board private struct
4571 *
4572 * code flow taken from tg3.c, called with e1000 interrupts disabled.
4573 **/
4574static int e1000_test_msi(struct e1000_adapter *adapter)
4575{
4576	int err;
4577	u16 pci_cmd;
4578
4579	if (!(adapter->flags & FLAG_MSI_ENABLED))
4580		return 0;
4581
4582	/* disable SERR in case the MSI write causes a master abort */
4583	pci_read_config_word(adapter->pdev, PCI_COMMAND, &pci_cmd);
4584	if (pci_cmd & PCI_COMMAND_SERR)
4585		pci_write_config_word(adapter->pdev, PCI_COMMAND,
4586				      pci_cmd & ~PCI_COMMAND_SERR);
4587
4588	err = e1000_test_msi_interrupt(adapter);
4589
4590	/* re-enable SERR */
4591	if (pci_cmd & PCI_COMMAND_SERR) {
4592		pci_read_config_word(adapter->pdev, PCI_COMMAND, &pci_cmd);
4593		pci_cmd |= PCI_COMMAND_SERR;
4594		pci_write_config_word(adapter->pdev, PCI_COMMAND, pci_cmd);
4595	}
4596
4597	return err;
4598}
4599
4600/**
4601 * e1000e_open - Called when a network interface is made active
4602 * @netdev: network interface device structure
4603 *
4604 * Returns 0 on success, negative value on failure
4605 *
4606 * The open entry point is called when a network interface is made
4607 * active by the system (IFF_UP).  At this point all resources needed
4608 * for transmit and receive operations are allocated, the interrupt
4609 * handler is registered with the OS, the watchdog timer is started,
4610 * and the stack is notified that the interface is ready.
4611 **/
4612int e1000e_open(struct net_device *netdev)
4613{
4614	struct e1000_adapter *adapter = netdev_priv(netdev);
4615	struct e1000_hw *hw = &adapter->hw;
4616	struct pci_dev *pdev = adapter->pdev;
4617	int err;
4618
4619	/* disallow open during test */
4620	if (test_bit(__E1000_TESTING, &adapter->state))
4621		return -EBUSY;
4622
4623	pm_runtime_get_sync(&pdev->dev);
4624
4625	netif_carrier_off(netdev);
4626	netif_stop_queue(netdev);
4627
4628	/* allocate transmit descriptors */
4629	err = e1000e_setup_tx_resources(adapter->tx_ring);
4630	if (err)
4631		goto err_setup_tx;
4632
4633	/* allocate receive descriptors */
4634	err = e1000e_setup_rx_resources(adapter->rx_ring);
4635	if (err)
4636		goto err_setup_rx;
4637
4638	/* If AMT is enabled, let the firmware know that the network
4639	 * interface is now open and reset the part to a known state.
4640	 */
4641	if (adapter->flags & FLAG_HAS_AMT) {
4642		e1000e_get_hw_control(adapter);
4643		e1000e_reset(adapter);
4644	}
4645
4646	e1000e_power_up_phy(adapter);
4647
4648	adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
4649	if ((adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN))
4650		e1000_update_mng_vlan(adapter);
4651
4652	/* DMA latency requirement to workaround jumbo issue */
4653	cpu_latency_qos_add_request(&adapter->pm_qos_req, PM_QOS_DEFAULT_VALUE);
4654
4655	/* before we allocate an interrupt, we must be ready to handle it.
4656	 * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
4657	 * as soon as we call pci_request_irq, so we have to setup our
4658	 * clean_rx handler before we do so.
4659	 */
4660	e1000_configure(adapter);
4661
4662	err = e1000_request_irq(adapter);
4663	if (err)
4664		goto err_req_irq;
4665
4666	/* Work around PCIe errata with MSI interrupts causing some chipsets to
4667	 * ignore e1000e MSI messages, which means we need to test our MSI
4668	 * interrupt now
4669	 */
4670	if (adapter->int_mode != E1000E_INT_MODE_LEGACY) {
4671		err = e1000_test_msi(adapter);
4672		if (err) {
4673			e_err("Interrupt allocation failed\n");
4674			goto err_req_irq;
4675		}
4676	}
4677
4678	/* From here on the code is the same as e1000e_up() */
4679	clear_bit(__E1000_DOWN, &adapter->state);
4680
4681	napi_enable(&adapter->napi);
4682
4683	e1000_irq_enable(adapter);
4684
4685	adapter->tx_hang_recheck = false;
4686
4687	hw->mac.get_link_status = true;
4688	pm_runtime_put(&pdev->dev);
4689
4690	e1000e_trigger_lsc(adapter);
4691
4692	return 0;
4693
4694err_req_irq:
4695	cpu_latency_qos_remove_request(&adapter->pm_qos_req);
4696	e1000e_release_hw_control(adapter);
4697	e1000_power_down_phy(adapter);
4698	e1000e_free_rx_resources(adapter->rx_ring);
4699err_setup_rx:
4700	e1000e_free_tx_resources(adapter->tx_ring);
4701err_setup_tx:
4702	e1000e_reset(adapter);
4703	pm_runtime_put_sync(&pdev->dev);
4704
4705	return err;
4706}
4707
4708/**
4709 * e1000e_close - Disables a network interface
4710 * @netdev: network interface device structure
4711 *
4712 * Returns 0, this is not allowed to fail
4713 *
4714 * The close entry point is called when an interface is de-activated
4715 * by the OS.  The hardware is still under the drivers control, but
4716 * needs to be disabled.  A global MAC reset is issued to stop the
4717 * hardware, and all transmit and receive resources are freed.
4718 **/
4719int e1000e_close(struct net_device *netdev)
4720{
4721	struct e1000_adapter *adapter = netdev_priv(netdev);
4722	struct pci_dev *pdev = adapter->pdev;
4723	int count = E1000_CHECK_RESET_COUNT;
4724
4725	while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
4726		usleep_range(10000, 11000);
4727
4728	WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
4729
4730	pm_runtime_get_sync(&pdev->dev);
4731
4732	if (netif_device_present(netdev)) {
4733		e1000e_down(adapter, true);
4734		e1000_free_irq(adapter);
4735
4736		/* Link status message must follow this format */
4737		netdev_info(netdev, "NIC Link is Down\n");
4738	}
4739
4740	napi_disable(&adapter->napi);
4741
4742	e1000e_free_tx_resources(adapter->tx_ring);
4743	e1000e_free_rx_resources(adapter->rx_ring);
4744
4745	/* kill manageability vlan ID if supported, but not if a vlan with
4746	 * the same ID is registered on the host OS (let 8021q kill it)
4747	 */
4748	if (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN)
4749		e1000_vlan_rx_kill_vid(netdev, htons(ETH_P_8021Q),
4750				       adapter->mng_vlan_id);
4751
4752	/* If AMT is enabled, let the firmware know that the network
4753	 * interface is now closed
4754	 */
4755	if ((adapter->flags & FLAG_HAS_AMT) &&
4756	    !test_bit(__E1000_TESTING, &adapter->state))
4757		e1000e_release_hw_control(adapter);
4758
4759	cpu_latency_qos_remove_request(&adapter->pm_qos_req);
4760
4761	pm_runtime_put_sync(&pdev->dev);
4762
4763	return 0;
4764}
4765
4766/**
4767 * e1000_set_mac - Change the Ethernet Address of the NIC
4768 * @netdev: network interface device structure
4769 * @p: pointer to an address structure
4770 *
4771 * Returns 0 on success, negative on failure
4772 **/
4773static int e1000_set_mac(struct net_device *netdev, void *p)
4774{
4775	struct e1000_adapter *adapter = netdev_priv(netdev);
4776	struct e1000_hw *hw = &adapter->hw;
4777	struct sockaddr *addr = p;
4778
4779	if (!is_valid_ether_addr(addr->sa_data))
4780		return -EADDRNOTAVAIL;
4781
4782	eth_hw_addr_set(netdev, addr->sa_data);
4783	memcpy(adapter->hw.mac.addr, addr->sa_data, netdev->addr_len);
4784
4785	hw->mac.ops.rar_set(&adapter->hw, adapter->hw.mac.addr, 0);
4786
4787	if (adapter->flags & FLAG_RESET_OVERWRITES_LAA) {
4788		/* activate the work around */
4789		e1000e_set_laa_state_82571(&adapter->hw, 1);
4790
4791		/* Hold a copy of the LAA in RAR[14] This is done so that
4792		 * between the time RAR[0] gets clobbered  and the time it
4793		 * gets fixed (in e1000_watchdog), the actual LAA is in one
4794		 * of the RARs and no incoming packets directed to this port
4795		 * are dropped. Eventually the LAA will be in RAR[0] and
4796		 * RAR[14]
4797		 */
4798		hw->mac.ops.rar_set(&adapter->hw, adapter->hw.mac.addr,
4799				    adapter->hw.mac.rar_entry_count - 1);
4800	}
4801
4802	return 0;
4803}
4804
4805/**
4806 * e1000e_update_phy_task - work thread to update phy
4807 * @work: pointer to our work struct
4808 *
4809 * this worker thread exists because we must acquire a
4810 * semaphore to read the phy, which we could msleep while
4811 * waiting for it, and we can't msleep in a timer.
4812 **/
4813static void e1000e_update_phy_task(struct work_struct *work)
4814{
4815	struct e1000_adapter *adapter = container_of(work,
4816						     struct e1000_adapter,
4817						     update_phy_task);
4818	struct e1000_hw *hw = &adapter->hw;
4819
4820	if (test_bit(__E1000_DOWN, &adapter->state))
4821		return;
4822
4823	e1000_get_phy_info(hw);
4824
4825	/* Enable EEE on 82579 after link up */
4826	if (hw->phy.type >= e1000_phy_82579)
4827		e1000_set_eee_pchlan(hw);
4828}
4829
4830/**
4831 * e1000_update_phy_info - timre call-back to update PHY info
4832 * @t: pointer to timer_list containing private info adapter
4833 *
4834 * Need to wait a few seconds after link up to get diagnostic information from
4835 * the phy
4836 **/
4837static void e1000_update_phy_info(struct timer_list *t)
4838{
4839	struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer);
4840
4841	if (test_bit(__E1000_DOWN, &adapter->state))
4842		return;
4843
4844	schedule_work(&adapter->update_phy_task);
4845}
4846
4847/**
4848 * e1000e_update_phy_stats - Update the PHY statistics counters
4849 * @adapter: board private structure
4850 *
4851 * Read/clear the upper 16-bit PHY registers and read/accumulate lower
4852 **/
4853static void e1000e_update_phy_stats(struct e1000_adapter *adapter)
4854{
4855	struct e1000_hw *hw = &adapter->hw;
4856	s32 ret_val;
4857	u16 phy_data;
4858
4859	ret_val = hw->phy.ops.acquire(hw);
4860	if (ret_val)
4861		return;
4862
4863	/* A page set is expensive so check if already on desired page.
4864	 * If not, set to the page with the PHY status registers.
4865	 */
4866	hw->phy.addr = 1;
4867	ret_val = e1000e_read_phy_reg_mdic(hw, IGP01E1000_PHY_PAGE_SELECT,
4868					   &phy_data);
4869	if (ret_val)
4870		goto release;
4871	if (phy_data != (HV_STATS_PAGE << IGP_PAGE_SHIFT)) {
4872		ret_val = hw->phy.ops.set_page(hw,
4873					       HV_STATS_PAGE << IGP_PAGE_SHIFT);
4874		if (ret_val)
4875			goto release;
4876	}
4877
4878	/* Single Collision Count */
4879	hw->phy.ops.read_reg_page(hw, HV_SCC_UPPER, &phy_data);
4880	ret_val = hw->phy.ops.read_reg_page(hw, HV_SCC_LOWER, &phy_data);
4881	if (!ret_val)
4882		adapter->stats.scc += phy_data;
4883
4884	/* Excessive Collision Count */
4885	hw->phy.ops.read_reg_page(hw, HV_ECOL_UPPER, &phy_data);
4886	ret_val = hw->phy.ops.read_reg_page(hw, HV_ECOL_LOWER, &phy_data);
4887	if (!ret_val)
4888		adapter->stats.ecol += phy_data;
4889
4890	/* Multiple Collision Count */
4891	hw->phy.ops.read_reg_page(hw, HV_MCC_UPPER, &phy_data);
4892	ret_val = hw->phy.ops.read_reg_page(hw, HV_MCC_LOWER, &phy_data);
4893	if (!ret_val)
4894		adapter->stats.mcc += phy_data;
4895
4896	/* Late Collision Count */
4897	hw->phy.ops.read_reg_page(hw, HV_LATECOL_UPPER, &phy_data);
4898	ret_val = hw->phy.ops.read_reg_page(hw, HV_LATECOL_LOWER, &phy_data);
4899	if (!ret_val)
4900		adapter->stats.latecol += phy_data;
4901
4902	/* Collision Count - also used for adaptive IFS */
4903	hw->phy.ops.read_reg_page(hw, HV_COLC_UPPER, &phy_data);
4904	ret_val = hw->phy.ops.read_reg_page(hw, HV_COLC_LOWER, &phy_data);
4905	if (!ret_val)
4906		hw->mac.collision_delta = phy_data;
4907
4908	/* Defer Count */
4909	hw->phy.ops.read_reg_page(hw, HV_DC_UPPER, &phy_data);
4910	ret_val = hw->phy.ops.read_reg_page(hw, HV_DC_LOWER, &phy_data);
4911	if (!ret_val)
4912		adapter->stats.dc += phy_data;
4913
4914	/* Transmit with no CRS */
4915	hw->phy.ops.read_reg_page(hw, HV_TNCRS_UPPER, &phy_data);
4916	ret_val = hw->phy.ops.read_reg_page(hw, HV_TNCRS_LOWER, &phy_data);
4917	if (!ret_val)
4918		adapter->stats.tncrs += phy_data;
4919
4920release:
4921	hw->phy.ops.release(hw);
4922}
4923
4924/**
4925 * e1000e_update_stats - Update the board statistics counters
4926 * @adapter: board private structure
4927 **/
4928static void e1000e_update_stats(struct e1000_adapter *adapter)
4929{
4930	struct net_device *netdev = adapter->netdev;
4931	struct e1000_hw *hw = &adapter->hw;
4932	struct pci_dev *pdev = adapter->pdev;
4933
4934	/* Prevent stats update while adapter is being reset, or if the pci
4935	 * connection is down.
4936	 */
4937	if (adapter->link_speed == 0)
4938		return;
4939	if (pci_channel_offline(pdev))
4940		return;
4941
4942	adapter->stats.crcerrs += er32(CRCERRS);
4943	adapter->stats.gprc += er32(GPRC);
4944	adapter->stats.gorc += er32(GORCL);
4945	er32(GORCH);		/* Clear gorc */
4946	adapter->stats.bprc += er32(BPRC);
4947	adapter->stats.mprc += er32(MPRC);
4948	adapter->stats.roc += er32(ROC);
4949
4950	adapter->stats.mpc += er32(MPC);
4951
4952	/* Half-duplex statistics */
4953	if (adapter->link_duplex == HALF_DUPLEX) {
4954		if (adapter->flags2 & FLAG2_HAS_PHY_STATS) {
4955			e1000e_update_phy_stats(adapter);
4956		} else {
4957			adapter->stats.scc += er32(SCC);
4958			adapter->stats.ecol += er32(ECOL);
4959			adapter->stats.mcc += er32(MCC);
4960			adapter->stats.latecol += er32(LATECOL);
4961			adapter->stats.dc += er32(DC);
4962
4963			hw->mac.collision_delta = er32(COLC);
4964
4965			if ((hw->mac.type != e1000_82574) &&
4966			    (hw->mac.type != e1000_82583))
4967				adapter->stats.tncrs += er32(TNCRS);
4968		}
4969		adapter->stats.colc += hw->mac.collision_delta;
4970	}
4971
4972	adapter->stats.xonrxc += er32(XONRXC);
4973	adapter->stats.xontxc += er32(XONTXC);
4974	adapter->stats.xoffrxc += er32(XOFFRXC);
4975	adapter->stats.xofftxc += er32(XOFFTXC);
4976	adapter->stats.gptc += er32(GPTC);
4977	adapter->stats.gotc += er32(GOTCL);
4978	er32(GOTCH);		/* Clear gotc */
4979	adapter->stats.rnbc += er32(RNBC);
4980	adapter->stats.ruc += er32(RUC);
4981
4982	adapter->stats.mptc += er32(MPTC);
4983	adapter->stats.bptc += er32(BPTC);
4984
4985	/* used for adaptive IFS */
4986
4987	hw->mac.tx_packet_delta = er32(TPT);
4988	adapter->stats.tpt += hw->mac.tx_packet_delta;
4989
4990	adapter->stats.algnerrc += er32(ALGNERRC);
4991	adapter->stats.rxerrc += er32(RXERRC);
4992	adapter->stats.cexterr += er32(CEXTERR);
4993	adapter->stats.tsctc += er32(TSCTC);
4994	adapter->stats.tsctfc += er32(TSCTFC);
4995
4996	/* Fill out the OS statistics structure */
4997	netdev->stats.multicast = adapter->stats.mprc;
4998	netdev->stats.collisions = adapter->stats.colc;
4999
5000	/* Rx Errors */
5001
5002	/* RLEC on some newer hardware can be incorrect so build
5003	 * our own version based on RUC and ROC
5004	 */
5005	netdev->stats.rx_errors = adapter->stats.rxerrc +
5006	    adapter->stats.crcerrs + adapter->stats.algnerrc +
5007	    adapter->stats.ruc + adapter->stats.roc + adapter->stats.cexterr;
5008	netdev->stats.rx_length_errors = adapter->stats.ruc +
5009	    adapter->stats.roc;
5010	netdev->stats.rx_crc_errors = adapter->stats.crcerrs;
5011	netdev->stats.rx_frame_errors = adapter->stats.algnerrc;
5012	netdev->stats.rx_missed_errors = adapter->stats.mpc;
5013
5014	/* Tx Errors */
5015	netdev->stats.tx_errors = adapter->stats.ecol + adapter->stats.latecol;
5016	netdev->stats.tx_aborted_errors = adapter->stats.ecol;
5017	netdev->stats.tx_window_errors = adapter->stats.latecol;
5018	netdev->stats.tx_carrier_errors = adapter->stats.tncrs;
5019
5020	/* Tx Dropped needs to be maintained elsewhere */
5021
5022	/* Management Stats */
5023	adapter->stats.mgptc += er32(MGTPTC);
5024	adapter->stats.mgprc += er32(MGTPRC);
5025	adapter->stats.mgpdc += er32(MGTPDC);
5026
5027	/* Correctable ECC Errors */
5028	if (hw->mac.type >= e1000_pch_lpt) {
5029		u32 pbeccsts = er32(PBECCSTS);
5030
5031		adapter->corr_errors +=
5032		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
5033		adapter->uncorr_errors +=
5034		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
5035		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
5036	}
5037}
5038
5039/**
5040 * e1000_phy_read_status - Update the PHY register status snapshot
5041 * @adapter: board private structure
5042 **/
5043static void e1000_phy_read_status(struct e1000_adapter *adapter)
5044{
5045	struct e1000_hw *hw = &adapter->hw;
5046	struct e1000_phy_regs *phy = &adapter->phy_regs;
5047
5048	if (!pm_runtime_suspended((&adapter->pdev->dev)->parent) &&
5049	    (er32(STATUS) & E1000_STATUS_LU) &&
5050	    (adapter->hw.phy.media_type == e1000_media_type_copper)) {
5051		int ret_val;
5052
5053		ret_val = e1e_rphy(hw, MII_BMCR, &phy->bmcr);
5054		ret_val |= e1e_rphy(hw, MII_BMSR, &phy->bmsr);
5055		ret_val |= e1e_rphy(hw, MII_ADVERTISE, &phy->advertise);
5056		ret_val |= e1e_rphy(hw, MII_LPA, &phy->lpa);
5057		ret_val |= e1e_rphy(hw, MII_EXPANSION, &phy->expansion);
5058		ret_val |= e1e_rphy(hw, MII_CTRL1000, &phy->ctrl1000);
5059		ret_val |= e1e_rphy(hw, MII_STAT1000, &phy->stat1000);
5060		ret_val |= e1e_rphy(hw, MII_ESTATUS, &phy->estatus);
5061		if (ret_val)
5062			e_warn("Error reading PHY register\n");
5063	} else {
5064		/* Do not read PHY registers if link is not up
5065		 * Set values to typical power-on defaults
5066		 */
5067		phy->bmcr = (BMCR_SPEED1000 | BMCR_ANENABLE | BMCR_FULLDPLX);
5068		phy->bmsr = (BMSR_100FULL | BMSR_100HALF | BMSR_10FULL |
5069			     BMSR_10HALF | BMSR_ESTATEN | BMSR_ANEGCAPABLE |
5070			     BMSR_ERCAP);
5071		phy->advertise = (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP |
5072				  ADVERTISE_ALL | ADVERTISE_CSMA);
5073		phy->lpa = 0;
5074		phy->expansion = EXPANSION_ENABLENPAGE;
5075		phy->ctrl1000 = ADVERTISE_1000FULL;
5076		phy->stat1000 = 0;
5077		phy->estatus = (ESTATUS_1000_TFULL | ESTATUS_1000_THALF);
5078	}
5079}
5080
5081static void e1000_print_link_info(struct e1000_adapter *adapter)
5082{
5083	struct e1000_hw *hw = &adapter->hw;
5084	u32 ctrl = er32(CTRL);
5085
5086	/* Link status message must follow this format for user tools */
5087	netdev_info(adapter->netdev,
5088		    "NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
5089		    adapter->link_speed,
5090		    adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half",
5091		    (ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE) ? "Rx/Tx" :
5092		    (ctrl & E1000_CTRL_RFCE) ? "Rx" :
5093		    (ctrl & E1000_CTRL_TFCE) ? "Tx" : "None");
5094}
5095
5096static bool e1000e_has_link(struct e1000_adapter *adapter)
5097{
5098	struct e1000_hw *hw = &adapter->hw;
5099	bool link_active = false;
5100	s32 ret_val = 0;
5101
5102	/* get_link_status is set on LSC (link status) interrupt or
5103	 * Rx sequence error interrupt.  get_link_status will stay
5104	 * true until the check_for_link establishes link
5105	 * for copper adapters ONLY
5106	 */
5107	switch (hw->phy.media_type) {
5108	case e1000_media_type_copper:
5109		if (hw->mac.get_link_status) {
5110			ret_val = hw->mac.ops.check_for_link(hw);
5111			link_active = !hw->mac.get_link_status;
5112		} else {
5113			link_active = true;
5114		}
5115		break;
5116	case e1000_media_type_fiber:
5117		ret_val = hw->mac.ops.check_for_link(hw);
5118		link_active = !!(er32(STATUS) & E1000_STATUS_LU);
5119		break;
5120	case e1000_media_type_internal_serdes:
5121		ret_val = hw->mac.ops.check_for_link(hw);
5122		link_active = hw->mac.serdes_has_link;
5123		break;
5124	default:
5125	case e1000_media_type_unknown:
5126		break;
5127	}
5128
5129	if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
5130	    (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) {
5131		/* See e1000_kmrn_lock_loss_workaround_ich8lan() */
5132		e_info("Gigabit has been disabled, downgrading speed\n");
5133	}
5134
5135	return link_active;
5136}
5137
5138static void e1000e_enable_receives(struct e1000_adapter *adapter)
5139{
5140	/* make sure the receive unit is started */
5141	if ((adapter->flags & FLAG_RX_NEEDS_RESTART) &&
5142	    (adapter->flags & FLAG_RESTART_NOW)) {
5143		struct e1000_hw *hw = &adapter->hw;
5144		u32 rctl = er32(RCTL);
5145
5146		ew32(RCTL, rctl | E1000_RCTL_EN);
5147		adapter->flags &= ~FLAG_RESTART_NOW;
5148	}
5149}
5150
5151static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
5152{
5153	struct e1000_hw *hw = &adapter->hw;
5154
5155	/* With 82574 controllers, PHY needs to be checked periodically
5156	 * for hung state and reset, if two calls return true
5157	 */
5158	if (e1000_check_phy_82574(hw))
5159		adapter->phy_hang_count++;
5160	else
5161		adapter->phy_hang_count = 0;
5162
5163	if (adapter->phy_hang_count > 1) {
5164		adapter->phy_hang_count = 0;
5165		e_dbg("PHY appears hung - resetting\n");
5166		schedule_work(&adapter->reset_task);
5167	}
5168}
5169
5170/**
5171 * e1000_watchdog - Timer Call-back
5172 * @t: pointer to timer_list containing private info adapter
5173 **/
5174static void e1000_watchdog(struct timer_list *t)
5175{
5176	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
5177
5178	/* Do the rest outside of interrupt context */
5179	schedule_work(&adapter->watchdog_task);
5180
5181	/* TODO: make this use queue_delayed_work() */
5182}
5183
5184static void e1000_watchdog_task(struct work_struct *work)
5185{
5186	struct e1000_adapter *adapter = container_of(work,
5187						     struct e1000_adapter,
5188						     watchdog_task);
5189	struct net_device *netdev = adapter->netdev;
5190	struct e1000_mac_info *mac = &adapter->hw.mac;
5191	struct e1000_phy_info *phy = &adapter->hw.phy;
5192	struct e1000_ring *tx_ring = adapter->tx_ring;
5193	u32 dmoff_exit_timeout = 100, tries = 0;
5194	struct e1000_hw *hw = &adapter->hw;
5195	u32 link, tctl, pcim_state;
5196
5197	if (test_bit(__E1000_DOWN, &adapter->state))
5198		return;
5199
5200	link = e1000e_has_link(adapter);
5201	if ((netif_carrier_ok(netdev)) && link) {
5202		/* Cancel scheduled suspend requests. */
5203		pm_runtime_resume(netdev->dev.parent);
5204
5205		e1000e_enable_receives(adapter);
5206		goto link_up;
5207	}
5208
5209	if ((e1000e_enable_tx_pkt_filtering(hw)) &&
5210	    (adapter->mng_vlan_id != adapter->hw.mng_cookie.vlan_id))
5211		e1000_update_mng_vlan(adapter);
5212
5213	if (link) {
5214		if (!netif_carrier_ok(netdev)) {
5215			bool txb2b = true;
5216
5217			/* Cancel scheduled suspend requests. */
5218			pm_runtime_resume(netdev->dev.parent);
5219
5220			/* Checking if MAC is in DMoff state*/
5221			if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
5222				pcim_state = er32(STATUS);
5223				while (pcim_state & E1000_STATUS_PCIM_STATE) {
5224					if (tries++ == dmoff_exit_timeout) {
5225						e_dbg("Error in exiting dmoff\n");
5226						break;
5227					}
5228					usleep_range(10000, 20000);
5229					pcim_state = er32(STATUS);
5230
5231					/* Checking if MAC exited DMoff state */
5232					if (!(pcim_state & E1000_STATUS_PCIM_STATE))
5233						e1000_phy_hw_reset(&adapter->hw);
5234				}
5235			}
5236
5237			/* update snapshot of PHY registers on LSC */
5238			e1000_phy_read_status(adapter);
5239			mac->ops.get_link_up_info(&adapter->hw,
5240						  &adapter->link_speed,
5241						  &adapter->link_duplex);
5242			e1000_print_link_info(adapter);
5243
5244			/* check if SmartSpeed worked */
5245			e1000e_check_downshift(hw);
5246			if (phy->speed_downgraded)
5247				netdev_warn(netdev,
5248					    "Link Speed was downgraded by SmartSpeed\n");
5249
5250			/* On supported PHYs, check for duplex mismatch only
5251			 * if link has autonegotiated at 10/100 half
5252			 */
5253			if ((hw->phy.type == e1000_phy_igp_3 ||
5254			     hw->phy.type == e1000_phy_bm) &&
5255			    hw->mac.autoneg &&
5256			    (adapter->link_speed == SPEED_10 ||
5257			     adapter->link_speed == SPEED_100) &&
5258			    (adapter->link_duplex == HALF_DUPLEX)) {
5259				u16 autoneg_exp;
5260
5261				e1e_rphy(hw, MII_EXPANSION, &autoneg_exp);
5262
5263				if (!(autoneg_exp & EXPANSION_NWAY))
5264					e_info("Autonegotiated half duplex but link partner cannot autoneg.  Try forcing full duplex if link gets many collisions.\n");
5265			}
5266
5267			/* adjust timeout factor according to speed/duplex */
5268			adapter->tx_timeout_factor = 1;
5269			switch (adapter->link_speed) {
5270			case SPEED_10:
5271				txb2b = false;
5272				adapter->tx_timeout_factor = 16;
5273				break;
5274			case SPEED_100:
5275				txb2b = false;
5276				adapter->tx_timeout_factor = 10;
5277				break;
5278			}
5279
5280			/* workaround: re-program speed mode bit after
5281			 * link-up event
5282			 */
5283			if ((adapter->flags & FLAG_TARC_SPEED_MODE_BIT) &&
5284			    !txb2b) {
5285				u32 tarc0;
5286
5287				tarc0 = er32(TARC(0));
5288				tarc0 &= ~SPEED_MODE_BIT;
5289				ew32(TARC(0), tarc0);
5290			}
5291
5292			/* enable transmits in the hardware, need to do this
5293			 * after setting TARC(0)
5294			 */
5295			tctl = er32(TCTL);
5296			tctl |= E1000_TCTL_EN;
5297			ew32(TCTL, tctl);
5298
5299			/* Perform any post-link-up configuration before
5300			 * reporting link up.
5301			 */
5302			if (phy->ops.cfg_on_link_up)
5303				phy->ops.cfg_on_link_up(hw);
5304
5305			netif_wake_queue(netdev);
5306			netif_carrier_on(netdev);
5307
5308			if (!test_bit(__E1000_DOWN, &adapter->state))
5309				mod_timer(&adapter->phy_info_timer,
5310					  round_jiffies(jiffies + 2 * HZ));
5311		}
5312	} else {
5313		if (netif_carrier_ok(netdev)) {
5314			adapter->link_speed = 0;
5315			adapter->link_duplex = 0;
5316			/* Link status message must follow this format */
5317			netdev_info(netdev, "NIC Link is Down\n");
5318			netif_carrier_off(netdev);
5319			netif_stop_queue(netdev);
5320			if (!test_bit(__E1000_DOWN, &adapter->state))
5321				mod_timer(&adapter->phy_info_timer,
5322					  round_jiffies(jiffies + 2 * HZ));
5323
5324			/* 8000ES2LAN requires a Rx packet buffer work-around
5325			 * on link down event; reset the controller to flush
5326			 * the Rx packet buffer.
5327			 */
5328			if (adapter->flags & FLAG_RX_NEEDS_RESTART)
5329				adapter->flags |= FLAG_RESTART_NOW;
5330			else
5331				pm_schedule_suspend(netdev->dev.parent,
5332						    LINK_TIMEOUT);
5333		}
5334	}
5335
5336link_up:
5337	spin_lock(&adapter->stats64_lock);
5338	e1000e_update_stats(adapter);
5339
5340	mac->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old;
5341	adapter->tpt_old = adapter->stats.tpt;
5342	mac->collision_delta = adapter->stats.colc - adapter->colc_old;
5343	adapter->colc_old = adapter->stats.colc;
5344
5345	adapter->gorc = adapter->stats.gorc - adapter->gorc_old;
5346	adapter->gorc_old = adapter->stats.gorc;
5347	adapter->gotc = adapter->stats.gotc - adapter->gotc_old;
5348	adapter->gotc_old = adapter->stats.gotc;
5349	spin_unlock(&adapter->stats64_lock);
5350
5351	/* If the link is lost the controller stops DMA, but
5352	 * if there is queued Tx work it cannot be done.  So
5353	 * reset the controller to flush the Tx packet buffers.
5354	 */
5355	if (!netif_carrier_ok(netdev) &&
5356	    (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
5357		adapter->flags |= FLAG_RESTART_NOW;
5358
5359	/* If reset is necessary, do it outside of interrupt context. */
5360	if (adapter->flags & FLAG_RESTART_NOW) {
5361		schedule_work(&adapter->reset_task);
5362		/* return immediately since reset is imminent */
5363		return;
5364	}
5365
5366	e1000e_update_adaptive(&adapter->hw);
5367
5368	/* Simple mode for Interrupt Throttle Rate (ITR) */
5369	if (adapter->itr_setting == 4) {
5370		/* Symmetric Tx/Rx gets a reduced ITR=2000;
5371		 * Total asymmetrical Tx or Rx gets ITR=8000;
5372		 * everyone else is between 2000-8000.
5373		 */
5374		u32 goc = (adapter->gotc + adapter->gorc) / 10000;
5375		u32 dif = (adapter->gotc > adapter->gorc ?
5376			   adapter->gotc - adapter->gorc :
5377			   adapter->gorc - adapter->gotc) / 10000;
5378		u32 itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000;
5379
5380		e1000e_write_itr(adapter, itr);
5381	}
5382
5383	/* Cause software interrupt to ensure Rx ring is cleaned */
5384	if (adapter->msix_entries)
5385		ew32(ICS, adapter->rx_ring->ims_val);
5386	else
5387		ew32(ICS, E1000_ICS_RXDMT0);
5388
5389	/* flush pending descriptors to memory before detecting Tx hang */
5390	e1000e_flush_descriptors(adapter);
5391
5392	/* Force detection of hung controller every watchdog period */
5393	adapter->detect_tx_hung = true;
5394
5395	/* With 82571 controllers, LAA may be overwritten due to controller
5396	 * reset from the other port. Set the appropriate LAA in RAR[0]
5397	 */
5398	if (e1000e_get_laa_state_82571(hw))
5399		hw->mac.ops.rar_set(hw, adapter->hw.mac.addr, 0);
5400
5401	if (adapter->flags2 & FLAG2_CHECK_PHY_HANG)
5402		e1000e_check_82574_phy_workaround(adapter);
5403
5404	/* Clear valid timestamp stuck in RXSTMPL/H due to a Rx error */
5405	if (adapter->hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) {
5406		if ((adapter->flags2 & FLAG2_CHECK_RX_HWTSTAMP) &&
5407		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) {
5408			er32(RXSTMPH);
5409			adapter->rx_hwtstamp_cleared++;
5410		} else {
5411			adapter->flags2 |= FLAG2_CHECK_RX_HWTSTAMP;
5412		}
5413	}
5414
5415	/* Reset the timer */
5416	if (!test_bit(__E1000_DOWN, &adapter->state))
5417		mod_timer(&adapter->watchdog_timer,
5418			  round_jiffies(jiffies + 2 * HZ));
5419}
5420
5421#define E1000_TX_FLAGS_CSUM		0x00000001
5422#define E1000_TX_FLAGS_VLAN		0x00000002
5423#define E1000_TX_FLAGS_TSO		0x00000004
5424#define E1000_TX_FLAGS_IPV4		0x00000008
5425#define E1000_TX_FLAGS_NO_FCS		0x00000010
5426#define E1000_TX_FLAGS_HWTSTAMP		0x00000020
5427#define E1000_TX_FLAGS_VLAN_MASK	0xffff0000
5428#define E1000_TX_FLAGS_VLAN_SHIFT	16
5429
5430static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb,
5431		     __be16 protocol)
5432{
5433	struct e1000_context_desc *context_desc;
5434	struct e1000_buffer *buffer_info;
5435	unsigned int i;
5436	u32 cmd_length = 0;
5437	u16 ipcse = 0, mss;
5438	u8 ipcss, ipcso, tucss, tucso, hdr_len;
5439	int err;
5440
5441	if (!skb_is_gso(skb))
5442		return 0;
5443
5444	err = skb_cow_head(skb, 0);
5445	if (err < 0)
5446		return err;
5447
5448	hdr_len = skb_tcp_all_headers(skb);
5449	mss = skb_shinfo(skb)->gso_size;
5450	if (protocol == htons(ETH_P_IP)) {
5451		struct iphdr *iph = ip_hdr(skb);
5452		iph->tot_len = 0;
5453		iph->check = 0;
5454		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
5455							 0, IPPROTO_TCP, 0);
5456		cmd_length = E1000_TXD_CMD_IP;
5457		ipcse = skb_transport_offset(skb) - 1;
5458	} else if (skb_is_gso_v6(skb)) {
5459		tcp_v6_gso_csum_prep(skb);
5460		ipcse = 0;
5461	}
5462	ipcss = skb_network_offset(skb);
5463	ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data;
5464	tucss = skb_transport_offset(skb);
5465	tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data;
5466
5467	cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE |
5468		       E1000_TXD_CMD_TCP | (skb->len - (hdr_len)));
5469
5470	i = tx_ring->next_to_use;
5471	context_desc = E1000_CONTEXT_DESC(*tx_ring, i);
5472	buffer_info = &tx_ring->buffer_info[i];
5473
5474	context_desc->lower_setup.ip_fields.ipcss = ipcss;
5475	context_desc->lower_setup.ip_fields.ipcso = ipcso;
5476	context_desc->lower_setup.ip_fields.ipcse = cpu_to_le16(ipcse);
5477	context_desc->upper_setup.tcp_fields.tucss = tucss;
5478	context_desc->upper_setup.tcp_fields.tucso = tucso;
5479	context_desc->upper_setup.tcp_fields.tucse = 0;
5480	context_desc->tcp_seg_setup.fields.mss = cpu_to_le16(mss);
5481	context_desc->tcp_seg_setup.fields.hdr_len = hdr_len;
5482	context_desc->cmd_and_length = cpu_to_le32(cmd_length);
5483
5484	buffer_info->time_stamp = jiffies;
5485	buffer_info->next_to_watch = i;
5486
5487	i++;
5488	if (i == tx_ring->count)
5489		i = 0;
5490	tx_ring->next_to_use = i;
5491
5492	return 1;
5493}
5494
5495static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb,
5496			  __be16 protocol)
5497{
5498	struct e1000_adapter *adapter = tx_ring->adapter;
5499	struct e1000_context_desc *context_desc;
5500	struct e1000_buffer *buffer_info;
5501	unsigned int i;
5502	u8 css;
5503	u32 cmd_len = E1000_TXD_CMD_DEXT;
5504
5505	if (skb->ip_summed != CHECKSUM_PARTIAL)
5506		return false;
5507
5508	switch (protocol) {
5509	case cpu_to_be16(ETH_P_IP):
5510		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
5511			cmd_len |= E1000_TXD_CMD_TCP;
5512		break;
5513	case cpu_to_be16(ETH_P_IPV6):
5514		/* XXX not handling all IPV6 headers */
5515		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
5516			cmd_len |= E1000_TXD_CMD_TCP;
5517		break;
5518	default:
5519		if (unlikely(net_ratelimit()))
5520			e_warn("checksum_partial proto=%x!\n",
5521			       be16_to_cpu(protocol));
5522		break;
5523	}
5524
5525	css = skb_checksum_start_offset(skb);
5526
5527	i = tx_ring->next_to_use;
5528	buffer_info = &tx_ring->buffer_info[i];
5529	context_desc = E1000_CONTEXT_DESC(*tx_ring, i);
5530
5531	context_desc->lower_setup.ip_config = 0;
5532	context_desc->upper_setup.tcp_fields.tucss = css;
5533	context_desc->upper_setup.tcp_fields.tucso = css + skb->csum_offset;
5534	context_desc->upper_setup.tcp_fields.tucse = 0;
5535	context_desc->tcp_seg_setup.data = 0;
5536	context_desc->cmd_and_length = cpu_to_le32(cmd_len);
5537
5538	buffer_info->time_stamp = jiffies;
5539	buffer_info->next_to_watch = i;
5540
5541	i++;
5542	if (i == tx_ring->count)
5543		i = 0;
5544	tx_ring->next_to_use = i;
5545
5546	return true;
5547}
5548
5549static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb,
5550			unsigned int first, unsigned int max_per_txd,
5551			unsigned int nr_frags)
5552{
5553	struct e1000_adapter *adapter = tx_ring->adapter;
5554	struct pci_dev *pdev = adapter->pdev;
5555	struct e1000_buffer *buffer_info;
5556	unsigned int len = skb_headlen(skb);
5557	unsigned int offset = 0, size, count = 0, i;
5558	unsigned int f, bytecount, segs;
5559
5560	i = tx_ring->next_to_use;
5561
5562	while (len) {
5563		buffer_info = &tx_ring->buffer_info[i];
5564		size = min(len, max_per_txd);
5565
5566		buffer_info->length = size;
5567		buffer_info->time_stamp = jiffies;
5568		buffer_info->next_to_watch = i;
5569		buffer_info->dma = dma_map_single(&pdev->dev,
5570						  skb->data + offset,
5571						  size, DMA_TO_DEVICE);
5572		buffer_info->mapped_as_page = false;
5573		if (dma_mapping_error(&pdev->dev, buffer_info->dma))
5574			goto dma_error;
5575
5576		len -= size;
5577		offset += size;
5578		count++;
5579
5580		if (len) {
5581			i++;
5582			if (i == tx_ring->count)
5583				i = 0;
5584		}
5585	}
5586
5587	for (f = 0; f < nr_frags; f++) {
5588		const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
5589
5590		len = skb_frag_size(frag);
5591		offset = 0;
5592
5593		while (len) {
5594			i++;
5595			if (i == tx_ring->count)
5596				i = 0;
5597
5598			buffer_info = &tx_ring->buffer_info[i];
5599			size = min(len, max_per_txd);
5600
5601			buffer_info->length = size;
5602			buffer_info->time_stamp = jiffies;
5603			buffer_info->next_to_watch = i;
5604			buffer_info->dma = skb_frag_dma_map(&pdev->dev, frag,
5605							    offset, size,
5606							    DMA_TO_DEVICE);
5607			buffer_info->mapped_as_page = true;
5608			if (dma_mapping_error(&pdev->dev, buffer_info->dma))
5609				goto dma_error;
5610
5611			len -= size;
5612			offset += size;
5613			count++;
5614		}
5615	}
5616
5617	segs = skb_shinfo(skb)->gso_segs ? : 1;
5618	/* multiply data chunks by size of headers */
5619	bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len;
5620
5621	tx_ring->buffer_info[i].skb = skb;
5622	tx_ring->buffer_info[i].segs = segs;
5623	tx_ring->buffer_info[i].bytecount = bytecount;
5624	tx_ring->buffer_info[first].next_to_watch = i;
5625
5626	return count;
5627
5628dma_error:
5629	dev_err(&pdev->dev, "Tx DMA map failed\n");
5630	buffer_info->dma = 0;
5631	if (count)
5632		count--;
5633
5634	while (count--) {
5635		if (i == 0)
5636			i += tx_ring->count;
5637		i--;
5638		buffer_info = &tx_ring->buffer_info[i];
5639		e1000_put_txbuf(tx_ring, buffer_info, true);
5640	}
5641
5642	return 0;
5643}
5644
5645static void e1000_tx_queue(struct e1000_ring *tx_ring, int tx_flags, int count)
5646{
5647	struct e1000_adapter *adapter = tx_ring->adapter;
5648	struct e1000_tx_desc *tx_desc = NULL;
5649	struct e1000_buffer *buffer_info;
5650	u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS;
5651	unsigned int i;
5652
5653	if (tx_flags & E1000_TX_FLAGS_TSO) {
5654		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D |
5655		    E1000_TXD_CMD_TSE;
5656		txd_upper |= E1000_TXD_POPTS_TXSM << 8;
5657
5658		if (tx_flags & E1000_TX_FLAGS_IPV4)
5659			txd_upper |= E1000_TXD_POPTS_IXSM << 8;
5660	}
5661
5662	if (tx_flags & E1000_TX_FLAGS_CSUM) {
5663		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D;
5664		txd_upper |= E1000_TXD_POPTS_TXSM << 8;
5665	}
5666
5667	if (tx_flags & E1000_TX_FLAGS_VLAN) {
5668		txd_lower |= E1000_TXD_CMD_VLE;
5669		txd_upper |= (tx_flags & E1000_TX_FLAGS_VLAN_MASK);
5670	}
5671
5672	if (unlikely(tx_flags & E1000_TX_FLAGS_NO_FCS))
5673		txd_lower &= ~(E1000_TXD_CMD_IFCS);
5674
5675	if (unlikely(tx_flags & E1000_TX_FLAGS_HWTSTAMP)) {
5676		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D;
5677		txd_upper |= E1000_TXD_EXTCMD_TSTAMP;
5678	}
5679
5680	i = tx_ring->next_to_use;
5681
5682	do {
5683		buffer_info = &tx_ring->buffer_info[i];
5684		tx_desc = E1000_TX_DESC(*tx_ring, i);
5685		tx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
5686		tx_desc->lower.data = cpu_to_le32(txd_lower |
5687						  buffer_info->length);
5688		tx_desc->upper.data = cpu_to_le32(txd_upper);
5689
5690		i++;
5691		if (i == tx_ring->count)
5692			i = 0;
5693	} while (--count > 0);
5694
5695	tx_desc->lower.data |= cpu_to_le32(adapter->txd_cmd);
5696
5697	/* txd_cmd re-enables FCS, so we'll re-disable it here as desired. */
5698	if (unlikely(tx_flags & E1000_TX_FLAGS_NO_FCS))
5699		tx_desc->lower.data &= ~(cpu_to_le32(E1000_TXD_CMD_IFCS));
5700
5701	/* Force memory writes to complete before letting h/w
5702	 * know there are new descriptors to fetch.  (Only
5703	 * applicable for weak-ordered memory model archs,
5704	 * such as IA-64).
5705	 */
5706	wmb();
5707
5708	tx_ring->next_to_use = i;
5709}
5710
5711#define MINIMUM_DHCP_PACKET_SIZE 282
5712static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter,
5713				    struct sk_buff *skb)
5714{
5715	struct e1000_hw *hw = &adapter->hw;
5716	u16 length, offset;
5717
5718	if (skb_vlan_tag_present(skb) &&
5719	    !((skb_vlan_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) &&
5720	      (adapter->hw.mng_cookie.status &
5721	       E1000_MNG_DHCP_COOKIE_STATUS_VLAN)))
5722		return 0;
5723
5724	if (skb->len <= MINIMUM_DHCP_PACKET_SIZE)
5725		return 0;
5726
5727	if (((struct ethhdr *)skb->data)->h_proto != htons(ETH_P_IP))
5728		return 0;
5729
5730	{
5731		const struct iphdr *ip = (struct iphdr *)((u8 *)skb->data + 14);
5732		struct udphdr *udp;
5733
5734		if (ip->protocol != IPPROTO_UDP)
5735			return 0;
5736
5737		udp = (struct udphdr *)((u8 *)ip + (ip->ihl << 2));
5738		if (ntohs(udp->dest) != 67)
5739			return 0;
5740
5741		offset = (u8 *)udp + 8 - skb->data;
5742		length = skb->len - offset;
5743		return e1000e_mng_write_dhcp_info(hw, (u8 *)udp + 8, length);
5744	}
5745
5746	return 0;
5747}
5748
5749static int __e1000_maybe_stop_tx(struct e1000_ring *tx_ring, int size)
5750{
5751	struct e1000_adapter *adapter = tx_ring->adapter;
5752
5753	netif_stop_queue(adapter->netdev);
5754	/* Herbert's original patch had:
5755	 *  smp_mb__after_netif_stop_queue();
5756	 * but since that doesn't exist yet, just open code it.
5757	 */
5758	smp_mb();
5759
5760	/* We need to check again in a case another CPU has just
5761	 * made room available.
5762	 */
5763	if (e1000_desc_unused(tx_ring) < size)
5764		return -EBUSY;
5765
5766	/* A reprieve! */
5767	netif_start_queue(adapter->netdev);
5768	++adapter->restart_queue;
5769	return 0;
5770}
5771
5772static int e1000_maybe_stop_tx(struct e1000_ring *tx_ring, int size)
5773{
5774	BUG_ON(size > tx_ring->count);
5775
5776	if (e1000_desc_unused(tx_ring) >= size)
5777		return 0;
5778	return __e1000_maybe_stop_tx(tx_ring, size);
5779}
5780
5781static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
5782				    struct net_device *netdev)
5783{
5784	struct e1000_adapter *adapter = netdev_priv(netdev);
5785	struct e1000_ring *tx_ring = adapter->tx_ring;
5786	unsigned int first;
5787	unsigned int tx_flags = 0;
5788	unsigned int len = skb_headlen(skb);
5789	unsigned int nr_frags;
5790	unsigned int mss;
5791	int count = 0;
5792	int tso;
5793	unsigned int f;
5794	__be16 protocol = vlan_get_protocol(skb);
5795
5796	if (test_bit(__E1000_DOWN, &adapter->state)) {
5797		dev_kfree_skb_any(skb);
5798		return NETDEV_TX_OK;
5799	}
5800
5801	if (skb->len <= 0) {
5802		dev_kfree_skb_any(skb);
5803		return NETDEV_TX_OK;
5804	}
5805
5806	/* The minimum packet size with TCTL.PSP set is 17 bytes so
5807	 * pad skb in order to meet this minimum size requirement
5808	 */
5809	if (skb_put_padto(skb, 17))
5810		return NETDEV_TX_OK;
5811
5812	mss = skb_shinfo(skb)->gso_size;
5813	if (mss) {
5814		u8 hdr_len;
5815
5816		/* TSO Workaround for 82571/2/3 Controllers -- if skb->data
5817		 * points to just header, pull a few bytes of payload from
5818		 * frags into skb->data
5819		 */
5820		hdr_len = skb_tcp_all_headers(skb);
5821		/* we do this workaround for ES2LAN, but it is un-necessary,
5822		 * avoiding it could save a lot of cycles
5823		 */
5824		if (skb->data_len && (hdr_len == len)) {
5825			unsigned int pull_size;
5826
5827			pull_size = min_t(unsigned int, 4, skb->data_len);
5828			if (!__pskb_pull_tail(skb, pull_size)) {
5829				e_err("__pskb_pull_tail failed.\n");
5830				dev_kfree_skb_any(skb);
5831				return NETDEV_TX_OK;
5832			}
5833			len = skb_headlen(skb);
5834		}
5835	}
5836
5837	/* reserve a descriptor for the offload context */
5838	if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL))
5839		count++;
5840	count++;
5841
5842	count += DIV_ROUND_UP(len, adapter->tx_fifo_limit);
5843
5844	nr_frags = skb_shinfo(skb)->nr_frags;
5845	for (f = 0; f < nr_frags; f++)
5846		count += DIV_ROUND_UP(skb_frag_size(&skb_shinfo(skb)->frags[f]),
5847				      adapter->tx_fifo_limit);
5848
5849	if (adapter->hw.mac.tx_pkt_filtering)
5850		e1000_transfer_dhcp_info(adapter, skb);
5851
5852	/* need: count + 2 desc gap to keep tail from touching
5853	 * head, otherwise try next time
5854	 */
5855	if (e1000_maybe_stop_tx(tx_ring, count + 2))
5856		return NETDEV_TX_BUSY;
5857
5858	if (skb_vlan_tag_present(skb)) {
5859		tx_flags |= E1000_TX_FLAGS_VLAN;
5860		tx_flags |= (skb_vlan_tag_get(skb) <<
5861			     E1000_TX_FLAGS_VLAN_SHIFT);
5862	}
5863
5864	first = tx_ring->next_to_use;
5865
5866	tso = e1000_tso(tx_ring, skb, protocol);
5867	if (tso < 0) {
5868		dev_kfree_skb_any(skb);
5869		return NETDEV_TX_OK;
5870	}
5871
5872	if (tso)
5873		tx_flags |= E1000_TX_FLAGS_TSO;
5874	else if (e1000_tx_csum(tx_ring, skb, protocol))
5875		tx_flags |= E1000_TX_FLAGS_CSUM;
5876
5877	/* Old method was to assume IPv4 packet by default if TSO was enabled.
5878	 * 82571 hardware supports TSO capabilities for IPv6 as well...
5879	 * no longer assume, we must.
5880	 */
5881	if (protocol == htons(ETH_P_IP))
5882		tx_flags |= E1000_TX_FLAGS_IPV4;
5883
5884	if (unlikely(skb->no_fcs))
5885		tx_flags |= E1000_TX_FLAGS_NO_FCS;
5886
5887	/* if count is 0 then mapping error has occurred */
5888	count = e1000_tx_map(tx_ring, skb, first, adapter->tx_fifo_limit,
5889			     nr_frags);
5890	if (count) {
5891		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
5892		    (adapter->flags & FLAG_HAS_HW_TIMESTAMP)) {
5893			if (!adapter->tx_hwtstamp_skb) {
5894				skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
5895				tx_flags |= E1000_TX_FLAGS_HWTSTAMP;
5896				adapter->tx_hwtstamp_skb = skb_get(skb);
5897				adapter->tx_hwtstamp_start = jiffies;
5898				schedule_work(&adapter->tx_hwtstamp_work);
5899			} else {
5900				adapter->tx_hwtstamp_skipped++;
5901			}
5902		}
5903
5904		skb_tx_timestamp(skb);
5905
5906		netdev_sent_queue(netdev, skb->len);
5907		e1000_tx_queue(tx_ring, tx_flags, count);
5908		/* Make sure there is space in the ring for the next send. */
5909		e1000_maybe_stop_tx(tx_ring,
5910				    ((MAX_SKB_FRAGS + 1) *
5911				     DIV_ROUND_UP(PAGE_SIZE,
5912						  adapter->tx_fifo_limit) + 4));
5913
5914		if (!netdev_xmit_more() ||
5915		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
5916			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
5917				e1000e_update_tdt_wa(tx_ring,
5918						     tx_ring->next_to_use);
5919			else
5920				writel(tx_ring->next_to_use, tx_ring->tail);
5921		}
5922	} else {
5923		dev_kfree_skb_any(skb);
5924		tx_ring->buffer_info[first].time_stamp = 0;
5925		tx_ring->next_to_use = first;
5926	}
5927
5928	return NETDEV_TX_OK;
5929}
5930
5931/**
5932 * e1000_tx_timeout - Respond to a Tx Hang
5933 * @netdev: network interface device structure
5934 * @txqueue: index of the hung queue (unused)
5935 **/
5936static void e1000_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
5937{
5938	struct e1000_adapter *adapter = netdev_priv(netdev);
5939
5940	/* Do the reset outside of interrupt context */
5941	adapter->tx_timeout_count++;
5942	schedule_work(&adapter->reset_task);
5943}
5944
5945static void e1000_reset_task(struct work_struct *work)
5946{
5947	struct e1000_adapter *adapter;
5948	adapter = container_of(work, struct e1000_adapter, reset_task);
5949
5950	rtnl_lock();
5951	/* don't run the task if already down */
5952	if (test_bit(__E1000_DOWN, &adapter->state)) {
5953		rtnl_unlock();
5954		return;
5955	}
5956
5957	if (!(adapter->flags & FLAG_RESTART_NOW)) {
5958		e1000e_dump(adapter);
5959		e_err("Reset adapter unexpectedly\n");
5960	}
5961	e1000e_reinit_locked(adapter);
5962	rtnl_unlock();
5963}
5964
5965/**
5966 * e1000e_get_stats64 - Get System Network Statistics
5967 * @netdev: network interface device structure
5968 * @stats: rtnl_link_stats64 pointer
5969 *
5970 * Returns the address of the device statistics structure.
5971 **/
5972void e1000e_get_stats64(struct net_device *netdev,
5973			struct rtnl_link_stats64 *stats)
5974{
5975	struct e1000_adapter *adapter = netdev_priv(netdev);
5976
5977	spin_lock(&adapter->stats64_lock);
5978	e1000e_update_stats(adapter);
5979	/* Fill out the OS statistics structure */
5980	stats->rx_bytes = adapter->stats.gorc;
5981	stats->rx_packets = adapter->stats.gprc;
5982	stats->tx_bytes = adapter->stats.gotc;
5983	stats->tx_packets = adapter->stats.gptc;
5984	stats->multicast = adapter->stats.mprc;
5985	stats->collisions = adapter->stats.colc;
5986
5987	/* Rx Errors */
5988
5989	/* RLEC on some newer hardware can be incorrect so build
5990	 * our own version based on RUC and ROC
5991	 */
5992	stats->rx_errors = adapter->stats.rxerrc +
5993	    adapter->stats.crcerrs + adapter->stats.algnerrc +
5994	    adapter->stats.ruc + adapter->stats.roc + adapter->stats.cexterr;
5995	stats->rx_length_errors = adapter->stats.ruc + adapter->stats.roc;
5996	stats->rx_crc_errors = adapter->stats.crcerrs;
5997	stats->rx_frame_errors = adapter->stats.algnerrc;
5998	stats->rx_missed_errors = adapter->stats.mpc;
5999
6000	/* Tx Errors */
6001	stats->tx_errors = adapter->stats.ecol + adapter->stats.latecol;
6002	stats->tx_aborted_errors = adapter->stats.ecol;
6003	stats->tx_window_errors = adapter->stats.latecol;
6004	stats->tx_carrier_errors = adapter->stats.tncrs;
6005
6006	/* Tx Dropped needs to be maintained elsewhere */
6007
6008	spin_unlock(&adapter->stats64_lock);
6009}
6010
6011/**
6012 * e1000_change_mtu - Change the Maximum Transfer Unit
6013 * @netdev: network interface device structure
6014 * @new_mtu: new value for maximum frame size
6015 *
6016 * Returns 0 on success, negative on failure
6017 **/
6018static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
6019{
6020	struct e1000_adapter *adapter = netdev_priv(netdev);
6021	int max_frame = new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
6022
6023	/* Jumbo frame support */
6024	if ((new_mtu > ETH_DATA_LEN) &&
6025	    !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) {
6026		e_err("Jumbo Frames not supported.\n");
6027		return -EINVAL;
6028	}
6029
6030	/* Jumbo frame workaround on 82579 and newer requires CRC be stripped */
6031	if ((adapter->hw.mac.type >= e1000_pch2lan) &&
6032	    !(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
6033	    (new_mtu > ETH_DATA_LEN)) {
6034		e_err("Jumbo Frames not supported on this device when CRC stripping is disabled.\n");
6035		return -EINVAL;
6036	}
6037
6038	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
6039		usleep_range(1000, 1100);
6040	/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
6041	adapter->max_frame_size = max_frame;
6042	netdev_dbg(netdev, "changing MTU from %d to %d\n",
6043		   netdev->mtu, new_mtu);
6044	netdev->mtu = new_mtu;
6045
6046	pm_runtime_get_sync(netdev->dev.parent);
6047
6048	if (netif_running(netdev))
6049		e1000e_down(adapter, true);
6050
6051	/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
6052	 * means we reserve 2 more, this pushes us to allocate from the next
6053	 * larger slab size.
6054	 * i.e. RXBUFFER_2048 --> size-4096 slab
6055	 * However with the new *_jumbo_rx* routines, jumbo receives will use
6056	 * fragmented skbs
6057	 */
6058
6059	if (max_frame <= 2048)
6060		adapter->rx_buffer_len = 2048;
6061	else
6062		adapter->rx_buffer_len = 4096;
6063
6064	/* adjust allocation if LPE protects us, and we aren't using SBP */
6065	if (max_frame <= (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN))
6066		adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
6067
6068	if (netif_running(netdev))
6069		e1000e_up(adapter);
6070	else
6071		e1000e_reset(adapter);
6072
6073	pm_runtime_put_sync(netdev->dev.parent);
6074
6075	clear_bit(__E1000_RESETTING, &adapter->state);
6076
6077	return 0;
6078}
6079
6080static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
6081			   int cmd)
6082{
6083	struct e1000_adapter *adapter = netdev_priv(netdev);
6084	struct mii_ioctl_data *data = if_mii(ifr);
6085
6086	if (adapter->hw.phy.media_type != e1000_media_type_copper)
6087		return -EOPNOTSUPP;
6088
6089	switch (cmd) {
6090	case SIOCGMIIPHY:
6091		data->phy_id = adapter->hw.phy.addr;
6092		break;
6093	case SIOCGMIIREG:
6094		e1000_phy_read_status(adapter);
6095
6096		switch (data->reg_num & 0x1F) {
6097		case MII_BMCR:
6098			data->val_out = adapter->phy_regs.bmcr;
6099			break;
6100		case MII_BMSR:
6101			data->val_out = adapter->phy_regs.bmsr;
6102			break;
6103		case MII_PHYSID1:
6104			data->val_out = (adapter->hw.phy.id >> 16);
6105			break;
6106		case MII_PHYSID2:
6107			data->val_out = (adapter->hw.phy.id & 0xFFFF);
6108			break;
6109		case MII_ADVERTISE:
6110			data->val_out = adapter->phy_regs.advertise;
6111			break;
6112		case MII_LPA:
6113			data->val_out = adapter->phy_regs.lpa;
6114			break;
6115		case MII_EXPANSION:
6116			data->val_out = adapter->phy_regs.expansion;
6117			break;
6118		case MII_CTRL1000:
6119			data->val_out = adapter->phy_regs.ctrl1000;
6120			break;
6121		case MII_STAT1000:
6122			data->val_out = adapter->phy_regs.stat1000;
6123			break;
6124		case MII_ESTATUS:
6125			data->val_out = adapter->phy_regs.estatus;
6126			break;
6127		default:
6128			return -EIO;
6129		}
6130		break;
6131	case SIOCSMIIREG:
6132	default:
6133		return -EOPNOTSUPP;
6134	}
6135	return 0;
6136}
6137
6138/**
6139 * e1000e_hwtstamp_set - control hardware time stamping
6140 * @netdev: network interface device structure
6141 * @ifr: interface request
6142 *
6143 * Outgoing time stamping can be enabled and disabled. Play nice and
6144 * disable it when requested, although it shouldn't cause any overhead
6145 * when no packet needs it. At most one packet in the queue may be
6146 * marked for time stamping, otherwise it would be impossible to tell
6147 * for sure to which packet the hardware time stamp belongs.
6148 *
6149 * Incoming time stamping has to be configured via the hardware filters.
6150 * Not all combinations are supported, in particular event type has to be
6151 * specified. Matching the kind of event packet is not supported, with the
6152 * exception of "all V2 events regardless of level 2 or 4".
6153 **/
6154static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
6155{
6156	struct e1000_adapter *adapter = netdev_priv(netdev);
6157	struct hwtstamp_config config;
6158	int ret_val;
6159
6160	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
6161		return -EFAULT;
6162
6163	ret_val = e1000e_config_hwtstamp(adapter, &config);
6164	if (ret_val)
6165		return ret_val;
6166
6167	switch (config.rx_filter) {
6168	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
6169	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
6170	case HWTSTAMP_FILTER_PTP_V2_SYNC:
6171	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
6172	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
6173	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
6174		/* With V2 type filters which specify a Sync or Delay Request,
6175		 * Path Delay Request/Response messages are also time stamped
6176		 * by hardware so notify the caller the requested packets plus
6177		 * some others are time stamped.
6178		 */
6179		config.rx_filter = HWTSTAMP_FILTER_SOME;
6180		break;
6181	default:
6182		break;
6183	}
6184
6185	return copy_to_user(ifr->ifr_data, &config,
6186			    sizeof(config)) ? -EFAULT : 0;
6187}
6188
6189static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
6190{
6191	struct e1000_adapter *adapter = netdev_priv(netdev);
6192
6193	return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config,
6194			    sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0;
6195}
6196
6197static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
6198{
6199	switch (cmd) {
6200	case SIOCGMIIPHY:
6201	case SIOCGMIIREG:
6202	case SIOCSMIIREG:
6203		return e1000_mii_ioctl(netdev, ifr, cmd);
6204	case SIOCSHWTSTAMP:
6205		return e1000e_hwtstamp_set(netdev, ifr);
6206	case SIOCGHWTSTAMP:
6207		return e1000e_hwtstamp_get(netdev, ifr);
6208	default:
6209		return -EOPNOTSUPP;
6210	}
6211}
6212
6213static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
6214{
6215	struct e1000_hw *hw = &adapter->hw;
6216	u32 i, mac_reg, wuc;
6217	u16 phy_reg, wuc_enable;
6218	int retval;
6219
6220	/* copy MAC RARs to PHY RARs */
6221	e1000_copy_rx_addrs_to_phy_ich8lan(hw);
6222
6223	retval = hw->phy.ops.acquire(hw);
6224	if (retval) {
6225		e_err("Could not acquire PHY\n");
6226		return retval;
6227	}
6228
6229	/* Enable access to wakeup registers on and set page to BM_WUC_PAGE */
6230	retval = e1000_enable_phy_wakeup_reg_access_bm(hw, &wuc_enable);
6231	if (retval)
6232		goto release;
6233
6234	/* copy MAC MTA to PHY MTA - only needed for pchlan */
6235	for (i = 0; i < adapter->hw.mac.mta_reg_count; i++) {
6236		mac_reg = E1000_READ_REG_ARRAY(hw, E1000_MTA, i);
6237		hw->phy.ops.write_reg_page(hw, BM_MTA(i),
6238					   (u16)(mac_reg & 0xFFFF));
6239		hw->phy.ops.write_reg_page(hw, BM_MTA(i) + 1,
6240					   (u16)((mac_reg >> 16) & 0xFFFF));
6241	}
6242
6243	/* configure PHY Rx Control register */
6244	hw->phy.ops.read_reg_page(&adapter->hw, BM_RCTL, &phy_reg);
6245	mac_reg = er32(RCTL);
6246	if (mac_reg & E1000_RCTL_UPE)
6247		phy_reg |= BM_RCTL_UPE;
6248	if (mac_reg & E1000_RCTL_MPE)
6249		phy_reg |= BM_RCTL_MPE;
6250	phy_reg &= ~(BM_RCTL_MO_MASK);
6251	if (mac_reg & E1000_RCTL_MO_3)
6252		phy_reg |= (((mac_reg & E1000_RCTL_MO_3) >> E1000_RCTL_MO_SHIFT)
6253			    << BM_RCTL_MO_SHIFT);
6254	if (mac_reg & E1000_RCTL_BAM)
6255		phy_reg |= BM_RCTL_BAM;
6256	if (mac_reg & E1000_RCTL_PMCF)
6257		phy_reg |= BM_RCTL_PMCF;
6258	mac_reg = er32(CTRL);
6259	if (mac_reg & E1000_CTRL_RFCE)
6260		phy_reg |= BM_RCTL_RFCE;
6261	hw->phy.ops.write_reg_page(&adapter->hw, BM_RCTL, phy_reg);
6262
6263	wuc = E1000_WUC_PME_EN;
6264	if (wufc & (E1000_WUFC_MAG | E1000_WUFC_LNKC))
6265		wuc |= E1000_WUC_APME;
6266
6267	/* enable PHY wakeup in MAC register */
6268	ew32(WUFC, wufc);
6269	ew32(WUC, (E1000_WUC_PHY_WAKE | E1000_WUC_APMPME |
6270		   E1000_WUC_PME_STATUS | wuc));
6271
6272	/* configure and enable PHY wakeup in PHY registers */
6273	hw->phy.ops.write_reg_page(&adapter->hw, BM_WUFC, wufc);
6274	hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, wuc);
6275
6276	/* activate PHY wakeup */
6277	wuc_enable |= BM_WUC_ENABLE_BIT | BM_WUC_HOST_WU_BIT;
6278	retval = e1000_disable_phy_wakeup_reg_access_bm(hw, &wuc_enable);
6279	if (retval)
6280		e_err("Could not set PHY Host Wakeup bit\n");
6281release:
6282	hw->phy.ops.release(hw);
6283
6284	return retval;
6285}
6286
6287static void e1000e_flush_lpic(struct pci_dev *pdev)
6288{
6289	struct net_device *netdev = pci_get_drvdata(pdev);
6290	struct e1000_adapter *adapter = netdev_priv(netdev);
6291	struct e1000_hw *hw = &adapter->hw;
6292	u32 ret_val;
6293
6294	pm_runtime_get_sync(netdev->dev.parent);
6295
6296	ret_val = hw->phy.ops.acquire(hw);
6297	if (ret_val)
6298		goto fl_out;
6299
6300	pr_info("EEE TX LPI TIMER: %08X\n",
6301		er32(LPIC) >> E1000_LPIC_LPIET_SHIFT);
6302
6303	hw->phy.ops.release(hw);
6304
6305fl_out:
6306	pm_runtime_put_sync(netdev->dev.parent);
6307}
6308
6309/* S0ix implementation */
6310static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
6311{
6312	struct e1000_hw *hw = &adapter->hw;
6313	u32 mac_data;
6314	u16 phy_data;
6315
6316	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
6317	    hw->mac.type >= e1000_pch_adp) {
6318		/* Request ME configure the device for S0ix */
6319		mac_data = er32(H2ME);
6320		mac_data |= E1000_H2ME_START_DPG;
6321		mac_data &= ~E1000_H2ME_EXIT_DPG;
6322		trace_e1000e_trace_mac_register(mac_data);
6323		ew32(H2ME, mac_data);
6324	} else {
6325		/* Request driver configure the device to S0ix */
6326		/* Disable the periodic inband message,
6327		 * don't request PCIe clock in K1 page770_17[10:9] = 10b
6328		 */
6329		e1e_rphy(hw, HV_PM_CTRL, &phy_data);
6330		phy_data &= ~HV_PM_CTRL_K1_CLK_REQ;
6331		phy_data |= BIT(10);
6332		e1e_wphy(hw, HV_PM_CTRL, phy_data);
6333
6334		/* Make sure we don't exit K1 every time a new packet arrives
6335		 * 772_29[5] = 1 CS_Mode_Stay_In_K1
6336		 */
6337		e1e_rphy(hw, I217_CGFREG, &phy_data);
6338		phy_data |= BIT(5);
6339		e1e_wphy(hw, I217_CGFREG, phy_data);
6340
6341		/* Change the MAC/PHY interface to SMBus
6342		 * Force the SMBus in PHY page769_23[0] = 1
6343		 * Force the SMBus in MAC CTRL_EXT[11] = 1
6344		 */
6345		e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
6346		phy_data |= CV_SMB_CTRL_FORCE_SMBUS;
6347		e1e_wphy(hw, CV_SMB_CTRL, phy_data);
6348		mac_data = er32(CTRL_EXT);
6349		mac_data |= E1000_CTRL_EXT_FORCE_SMBUS;
6350		ew32(CTRL_EXT, mac_data);
6351
6352		/* DFT control: PHY bit: page769_20[0] = 1
6353		 * page769_20[7] - PHY PLL stop
6354		 * page769_20[8] - PHY go to the electrical idle
6355		 * page769_20[9] - PHY serdes disable
6356		 * Gate PPW via EXTCNF_CTRL - set 0x0F00[7] = 1
6357		 */
6358		e1e_rphy(hw, I82579_DFT_CTRL, &phy_data);
6359		phy_data |= BIT(0);
6360		phy_data |= BIT(7);
6361		phy_data |= BIT(8);
6362		phy_data |= BIT(9);
6363		e1e_wphy(hw, I82579_DFT_CTRL, phy_data);
6364
6365		mac_data = er32(EXTCNF_CTRL);
6366		mac_data |= E1000_EXTCNF_CTRL_GATE_PHY_CFG;
6367		ew32(EXTCNF_CTRL, mac_data);
6368
6369		/* Enable the Dynamic Power Gating in the MAC */
6370		mac_data = er32(FEXTNVM7);
6371		mac_data |= BIT(22);
6372		ew32(FEXTNVM7, mac_data);
6373
6374		/* Disable disconnected cable conditioning for Power Gating */
6375		mac_data = er32(DPGFR);
6376		mac_data |= BIT(2);
6377		ew32(DPGFR, mac_data);
6378
6379		/* Don't wake from dynamic Power Gating with clock request */
6380		mac_data = er32(FEXTNVM12);
6381		mac_data |= BIT(12);
6382		ew32(FEXTNVM12, mac_data);
6383
6384		/* Ungate PGCB clock */
6385		mac_data = er32(FEXTNVM9);
6386		mac_data &= ~BIT(28);
6387		ew32(FEXTNVM9, mac_data);
6388
6389		/* Enable K1 off to enable mPHY Power Gating */
6390		mac_data = er32(FEXTNVM6);
6391		mac_data |= BIT(31);
6392		ew32(FEXTNVM6, mac_data);
6393
6394		/* Enable mPHY power gating for any link and speed */
6395		mac_data = er32(FEXTNVM8);
6396		mac_data |= BIT(9);
6397		ew32(FEXTNVM8, mac_data);
6398
6399		/* Enable the Dynamic Clock Gating in the DMA and MAC */
6400		mac_data = er32(CTRL_EXT);
6401		mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN;
6402		ew32(CTRL_EXT, mac_data);
6403
6404		/* No MAC DPG gating SLP_S0 in modern standby
6405		 * Switch the logic of the lanphypc to use PMC counter
6406		 */
6407		mac_data = er32(FEXTNVM5);
6408		mac_data |= BIT(7);
6409		ew32(FEXTNVM5, mac_data);
6410	}
6411
6412	/* Disable the time synchronization clock */
6413	mac_data = er32(FEXTNVM7);
6414	mac_data |= BIT(31);
6415	mac_data &= ~BIT(0);
6416	ew32(FEXTNVM7, mac_data);
6417
6418	/* Dynamic Power Gating Enable */
6419	mac_data = er32(CTRL_EXT);
6420	mac_data |= BIT(3);
6421	ew32(CTRL_EXT, mac_data);
6422
6423	/* Check MAC Tx/Rx packet buffer pointers.
6424	 * Reset MAC Tx/Rx packet buffer pointers to suppress any
6425	 * pending traffic indication that would prevent power gating.
6426	 */
6427	mac_data = er32(TDFH);
6428	if (mac_data)
6429		ew32(TDFH, 0);
6430	mac_data = er32(TDFT);
6431	if (mac_data)
6432		ew32(TDFT, 0);
6433	mac_data = er32(TDFHS);
6434	if (mac_data)
6435		ew32(TDFHS, 0);
6436	mac_data = er32(TDFTS);
6437	if (mac_data)
6438		ew32(TDFTS, 0);
6439	mac_data = er32(TDFPC);
6440	if (mac_data)
6441		ew32(TDFPC, 0);
6442	mac_data = er32(RDFH);
6443	if (mac_data)
6444		ew32(RDFH, 0);
6445	mac_data = er32(RDFT);
6446	if (mac_data)
6447		ew32(RDFT, 0);
6448	mac_data = er32(RDFHS);
6449	if (mac_data)
6450		ew32(RDFHS, 0);
6451	mac_data = er32(RDFTS);
6452	if (mac_data)
6453		ew32(RDFTS, 0);
6454	mac_data = er32(RDFPC);
6455	if (mac_data)
6456		ew32(RDFPC, 0);
6457}
6458
6459static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter)
6460{
6461	struct e1000_hw *hw = &adapter->hw;
6462	bool firmware_bug = false;
6463	u32 mac_data;
6464	u16 phy_data;
6465	u32 i = 0;
6466
6467	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
6468	    hw->mac.type >= e1000_pch_adp) {
6469		/* Keep the GPT clock enabled for CSME */
6470		mac_data = er32(FEXTNVM);
6471		mac_data |= BIT(3);
6472		ew32(FEXTNVM, mac_data);
6473		/* Request ME unconfigure the device from S0ix */
6474		mac_data = er32(H2ME);
6475		mac_data &= ~E1000_H2ME_START_DPG;
6476		mac_data |= E1000_H2ME_EXIT_DPG;
6477		trace_e1000e_trace_mac_register(mac_data);
6478		ew32(H2ME, mac_data);
6479
6480		/* Poll up to 2.5 seconds for ME to unconfigure DPG.
6481		 * If this takes more than 1 second, show a warning indicating a
6482		 * firmware bug
6483		 */
6484		while (!(er32(EXFWSM) & E1000_EXFWSM_DPG_EXIT_DONE)) {
6485			if (i > 100 && !firmware_bug)
6486				firmware_bug = true;
6487
6488			if (i++ == 250) {
6489				e_dbg("Timeout (firmware bug): %d msec\n",
6490				      i * 10);
6491				break;
6492			}
6493
6494			usleep_range(10000, 11000);
6495		}
6496		if (firmware_bug)
6497			e_warn("DPG_EXIT_DONE took %d msec. This is a firmware bug\n",
6498			       i * 10);
6499		else
6500			e_dbg("DPG_EXIT_DONE cleared after %d msec\n", i * 10);
6501	} else {
6502		/* Request driver unconfigure the device from S0ix */
6503
6504		/* Disable the Dynamic Power Gating in the MAC */
6505		mac_data = er32(FEXTNVM7);
6506		mac_data &= 0xFFBFFFFF;
6507		ew32(FEXTNVM7, mac_data);
6508
6509		/* Disable mPHY power gating for any link and speed */
6510		mac_data = er32(FEXTNVM8);
6511		mac_data &= ~BIT(9);
6512		ew32(FEXTNVM8, mac_data);
6513
6514		/* Disable K1 off */
6515		mac_data = er32(FEXTNVM6);
6516		mac_data &= ~BIT(31);
6517		ew32(FEXTNVM6, mac_data);
6518
6519		/* Disable Ungate PGCB clock */
6520		mac_data = er32(FEXTNVM9);
6521		mac_data |= BIT(28);
6522		ew32(FEXTNVM9, mac_data);
6523
6524		/* Cancel not waking from dynamic
6525		 * Power Gating with clock request
6526		 */
6527		mac_data = er32(FEXTNVM12);
6528		mac_data &= ~BIT(12);
6529		ew32(FEXTNVM12, mac_data);
6530
6531		/* Cancel disable disconnected cable conditioning
6532		 * for Power Gating
6533		 */
6534		mac_data = er32(DPGFR);
6535		mac_data &= ~BIT(2);
6536		ew32(DPGFR, mac_data);
6537
6538		/* Disable the Dynamic Clock Gating in the DMA and MAC */
6539		mac_data = er32(CTRL_EXT);
6540		mac_data &= 0xFFF7FFFF;
6541		ew32(CTRL_EXT, mac_data);
6542
6543		/* Revert the lanphypc logic to use the internal Gbe counter
6544		 * and not the PMC counter
6545		 */
6546		mac_data = er32(FEXTNVM5);
6547		mac_data &= 0xFFFFFF7F;
6548		ew32(FEXTNVM5, mac_data);
6549
6550		/* Enable the periodic inband message,
6551		 * Request PCIe clock in K1 page770_17[10:9] =01b
6552		 */
6553		e1e_rphy(hw, HV_PM_CTRL, &phy_data);
6554		phy_data &= 0xFBFF;
6555		phy_data |= HV_PM_CTRL_K1_CLK_REQ;
6556		e1e_wphy(hw, HV_PM_CTRL, phy_data);
6557
6558		/* Return back configuration
6559		 * 772_29[5] = 0 CS_Mode_Stay_In_K1
6560		 */
6561		e1e_rphy(hw, I217_CGFREG, &phy_data);
6562		phy_data &= 0xFFDF;
6563		e1e_wphy(hw, I217_CGFREG, phy_data);
6564
6565		/* Change the MAC/PHY interface to Kumeran
6566		 * Unforce the SMBus in PHY page769_23[0] = 0
6567		 * Unforce the SMBus in MAC CTRL_EXT[11] = 0
6568		 */
6569		e1e_rphy(hw, CV_SMB_CTRL, &phy_data);
6570		phy_data &= ~CV_SMB_CTRL_FORCE_SMBUS;
6571		e1e_wphy(hw, CV_SMB_CTRL, phy_data);
6572		mac_data = er32(CTRL_EXT);
6573		mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS;
6574		ew32(CTRL_EXT, mac_data);
6575	}
6576
6577	/* Disable Dynamic Power Gating */
6578	mac_data = er32(CTRL_EXT);
6579	mac_data &= 0xFFFFFFF7;
6580	ew32(CTRL_EXT, mac_data);
6581
6582	/* Enable the time synchronization clock */
6583	mac_data = er32(FEXTNVM7);
6584	mac_data &= ~BIT(31);
6585	mac_data |= BIT(0);
6586	ew32(FEXTNVM7, mac_data);
6587}
6588
6589static int e1000e_pm_freeze(struct device *dev)
6590{
6591	struct net_device *netdev = dev_get_drvdata(dev);
6592	struct e1000_adapter *adapter = netdev_priv(netdev);
6593	bool present;
6594
6595	rtnl_lock();
6596
6597	present = netif_device_present(netdev);
6598	netif_device_detach(netdev);
6599
6600	if (present && netif_running(netdev)) {
6601		int count = E1000_CHECK_RESET_COUNT;
6602
6603		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
6604			usleep_range(10000, 11000);
6605
6606		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
6607
6608		/* Quiesce the device without resetting the hardware */
6609		e1000e_down(adapter, false);
6610		e1000_free_irq(adapter);
6611	}
6612	rtnl_unlock();
6613
6614	e1000e_reset_interrupt_capability(adapter);
6615
6616	/* Allow time for pending master requests to run */
6617	e1000e_disable_pcie_master(&adapter->hw);
6618
6619	return 0;
6620}
6621
6622static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
6623{
6624	struct net_device *netdev = pci_get_drvdata(pdev);
6625	struct e1000_adapter *adapter = netdev_priv(netdev);
6626	struct e1000_hw *hw = &adapter->hw;
6627	u32 ctrl, ctrl_ext, rctl, status, wufc;
6628	int retval = 0;
6629
6630	/* Runtime suspend should only enable wakeup for link changes */
6631	if (runtime)
6632		wufc = E1000_WUFC_LNKC;
6633	else if (device_may_wakeup(&pdev->dev))
6634		wufc = adapter->wol;
6635	else
6636		wufc = 0;
6637
6638	status = er32(STATUS);
6639	if (status & E1000_STATUS_LU)
6640		wufc &= ~E1000_WUFC_LNKC;
6641
6642	if (wufc) {
6643		e1000_setup_rctl(adapter);
6644		e1000e_set_rx_mode(netdev);
6645
6646		/* turn on all-multi mode if wake on multicast is enabled */
6647		if (wufc & E1000_WUFC_MC) {
6648			rctl = er32(RCTL);
6649			rctl |= E1000_RCTL_MPE;
6650			ew32(RCTL, rctl);
6651		}
6652
6653		ctrl = er32(CTRL);
6654		ctrl |= E1000_CTRL_ADVD3WUC;
6655		if (!(adapter->flags2 & FLAG2_HAS_PHY_WAKEUP))
6656			ctrl |= E1000_CTRL_EN_PHY_PWR_MGMT;
6657		ew32(CTRL, ctrl);
6658
6659		if (adapter->hw.phy.media_type == e1000_media_type_fiber ||
6660		    adapter->hw.phy.media_type ==
6661		    e1000_media_type_internal_serdes) {
6662			/* keep the laser running in D3 */
6663			ctrl_ext = er32(CTRL_EXT);
6664			ctrl_ext |= E1000_CTRL_EXT_SDP3_DATA;
6665			ew32(CTRL_EXT, ctrl_ext);
6666		}
6667
6668		if (!runtime)
6669			e1000e_power_up_phy(adapter);
6670
6671		if (adapter->flags & FLAG_IS_ICH)
6672			e1000_suspend_workarounds_ich8lan(&adapter->hw);
6673
6674		if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
6675			/* enable wakeup by the PHY */
6676			retval = e1000_init_phy_wakeup(adapter, wufc);
6677			if (retval)
6678				return retval;
6679		} else {
6680			/* enable wakeup by the MAC */
6681			ew32(WUFC, wufc);
6682			ew32(WUC, E1000_WUC_PME_EN);
6683		}
6684	} else {
6685		ew32(WUC, 0);
6686		ew32(WUFC, 0);
6687
6688		e1000_power_down_phy(adapter);
6689	}
6690
6691	if (adapter->hw.phy.type == e1000_phy_igp_3) {
6692		e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
6693	} else if (hw->mac.type >= e1000_pch_lpt) {
6694		if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
6695			/* ULP does not support wake from unicast, multicast
6696			 * or broadcast.
6697			 */
6698			retval = e1000_enable_ulp_lpt_lp(hw, !runtime);
6699
6700		if (retval)
6701			return retval;
6702	}
6703
6704	/* Ensure that the appropriate bits are set in LPI_CTRL
6705	 * for EEE in Sx
6706	 */
6707	if ((hw->phy.type >= e1000_phy_i217) &&
6708	    adapter->eee_advert && hw->dev_spec.ich8lan.eee_lp_ability) {
6709		u16 lpi_ctrl = 0;
6710
6711		retval = hw->phy.ops.acquire(hw);
6712		if (!retval) {
6713			retval = e1e_rphy_locked(hw, I82579_LPI_CTRL,
6714						 &lpi_ctrl);
6715			if (!retval) {
6716				if (adapter->eee_advert &
6717				    hw->dev_spec.ich8lan.eee_lp_ability &
6718				    I82579_EEE_100_SUPPORTED)
6719					lpi_ctrl |= I82579_LPI_CTRL_100_ENABLE;
6720				if (adapter->eee_advert &
6721				    hw->dev_spec.ich8lan.eee_lp_ability &
6722				    I82579_EEE_1000_SUPPORTED)
6723					lpi_ctrl |= I82579_LPI_CTRL_1000_ENABLE;
6724
6725				retval = e1e_wphy_locked(hw, I82579_LPI_CTRL,
6726							 lpi_ctrl);
6727			}
6728		}
6729		hw->phy.ops.release(hw);
6730	}
6731
6732	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
6733	 * would have already happened in close and is redundant.
6734	 */
6735	e1000e_release_hw_control(adapter);
6736
6737	pci_clear_master(pdev);
6738
6739	/* The pci-e switch on some quad port adapters will report a
6740	 * correctable error when the MAC transitions from D0 to D3.  To
6741	 * prevent this we need to mask off the correctable errors on the
6742	 * downstream port of the pci-e switch.
6743	 *
6744	 * We don't have the associated upstream bridge while assigning
6745	 * the PCI device into guest. For example, the KVM on power is
6746	 * one of the cases.
6747	 */
6748	if (adapter->flags & FLAG_IS_QUAD_PORT) {
6749		struct pci_dev *us_dev = pdev->bus->self;
6750		u16 devctl;
6751
6752		if (!us_dev)
6753			return 0;
6754
6755		pcie_capability_read_word(us_dev, PCI_EXP_DEVCTL, &devctl);
6756		pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL,
6757					   (devctl & ~PCI_EXP_DEVCTL_CERE));
6758
6759		pci_save_state(pdev);
6760		pci_prepare_to_sleep(pdev);
6761
6762		pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL, devctl);
6763	}
6764
6765	return 0;
6766}
6767
6768/**
6769 * __e1000e_disable_aspm - Disable ASPM states
6770 * @pdev: pointer to PCI device struct
6771 * @state: bit-mask of ASPM states to disable
6772 * @locked: indication if this context holds pci_bus_sem locked.
6773 *
6774 * Some devices *must* have certain ASPM states disabled per hardware errata.
6775 **/
6776static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state, int locked)
6777{
6778	struct pci_dev *parent = pdev->bus->self;
6779	u16 aspm_dis_mask = 0;
6780	u16 pdev_aspmc, parent_aspmc;
6781
6782	switch (state) {
6783	case PCIE_LINK_STATE_L0S:
6784	case PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1:
6785		aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L0S;
6786		fallthrough; /* can't have L1 without L0s */
6787	case PCIE_LINK_STATE_L1:
6788		aspm_dis_mask |= PCI_EXP_LNKCTL_ASPM_L1;
6789		break;
6790	default:
6791		return;
6792	}
6793
6794	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc);
6795	pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC;
6796
6797	if (parent) {
6798		pcie_capability_read_word(parent, PCI_EXP_LNKCTL,
6799					  &parent_aspmc);
6800		parent_aspmc &= PCI_EXP_LNKCTL_ASPMC;
6801	}
6802
6803	/* Nothing to do if the ASPM states to be disabled already are */
6804	if (!(pdev_aspmc & aspm_dis_mask) &&
6805	    (!parent || !(parent_aspmc & aspm_dis_mask)))
6806		return;
6807
6808	dev_info(&pdev->dev, "Disabling ASPM %s %s\n",
6809		 (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L0S) ?
6810		 "L0s" : "",
6811		 (aspm_dis_mask & pdev_aspmc & PCI_EXP_LNKCTL_ASPM_L1) ?
6812		 "L1" : "");
6813
6814#ifdef CONFIG_PCIEASPM
6815	if (locked)
6816		pci_disable_link_state_locked(pdev, state);
6817	else
6818		pci_disable_link_state(pdev, state);
6819
6820	/* Double-check ASPM control.  If not disabled by the above, the
6821	 * BIOS is preventing that from happening (or CONFIG_PCIEASPM is
6822	 * not enabled); override by writing PCI config space directly.
6823	 */
6824	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &pdev_aspmc);
6825	pdev_aspmc &= PCI_EXP_LNKCTL_ASPMC;
6826
6827	if (!(aspm_dis_mask & pdev_aspmc))
6828		return;
6829#endif
6830
6831	/* Both device and parent should have the same ASPM setting.
6832	 * Disable ASPM in downstream component first and then upstream.
6833	 */
6834	pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_dis_mask);
6835
6836	if (parent)
6837		pcie_capability_clear_word(parent, PCI_EXP_LNKCTL,
6838					   aspm_dis_mask);
6839}
6840
6841/**
6842 * e1000e_disable_aspm - Disable ASPM states.
6843 * @pdev: pointer to PCI device struct
6844 * @state: bit-mask of ASPM states to disable
6845 *
6846 * This function acquires the pci_bus_sem!
6847 * Some devices *must* have certain ASPM states disabled per hardware errata.
6848 **/
6849static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
6850{
6851	__e1000e_disable_aspm(pdev, state, 0);
6852}
6853
6854/**
6855 * e1000e_disable_aspm_locked - Disable ASPM states.
6856 * @pdev: pointer to PCI device struct
6857 * @state: bit-mask of ASPM states to disable
6858 *
6859 * This function must be called with pci_bus_sem acquired!
6860 * Some devices *must* have certain ASPM states disabled per hardware errata.
6861 **/
6862static void e1000e_disable_aspm_locked(struct pci_dev *pdev, u16 state)
6863{
6864	__e1000e_disable_aspm(pdev, state, 1);
6865}
6866
6867static int e1000e_pm_thaw(struct device *dev)
6868{
6869	struct net_device *netdev = dev_get_drvdata(dev);
6870	struct e1000_adapter *adapter = netdev_priv(netdev);
6871	int rc = 0;
6872
6873	e1000e_set_interrupt_capability(adapter);
6874
6875	rtnl_lock();
6876	if (netif_running(netdev)) {
6877		rc = e1000_request_irq(adapter);
6878		if (rc)
6879			goto err_irq;
6880
6881		e1000e_up(adapter);
6882	}
6883
6884	netif_device_attach(netdev);
6885err_irq:
6886	rtnl_unlock();
6887
6888	return rc;
6889}
6890
6891static int __e1000_resume(struct pci_dev *pdev)
6892{
6893	struct net_device *netdev = pci_get_drvdata(pdev);
6894	struct e1000_adapter *adapter = netdev_priv(netdev);
6895	struct e1000_hw *hw = &adapter->hw;
6896	u16 aspm_disable_flag = 0;
6897
6898	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L0S)
6899		aspm_disable_flag = PCIE_LINK_STATE_L0S;
6900	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1)
6901		aspm_disable_flag |= PCIE_LINK_STATE_L1;
6902	if (aspm_disable_flag)
6903		e1000e_disable_aspm(pdev, aspm_disable_flag);
6904
6905	pci_set_master(pdev);
6906
6907	if (hw->mac.type >= e1000_pch2lan)
6908		e1000_resume_workarounds_pchlan(&adapter->hw);
6909
6910	e1000e_power_up_phy(adapter);
6911
6912	/* report the system wakeup cause from S3/S4 */
6913	if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
6914		u16 phy_data;
6915
6916		e1e_rphy(&adapter->hw, BM_WUS, &phy_data);
6917		if (phy_data) {
6918			e_info("PHY Wakeup cause - %s\n",
6919			       phy_data & E1000_WUS_EX ? "Unicast Packet" :
6920			       phy_data & E1000_WUS_MC ? "Multicast Packet" :
6921			       phy_data & E1000_WUS_BC ? "Broadcast Packet" :
6922			       phy_data & E1000_WUS_MAG ? "Magic Packet" :
6923			       phy_data & E1000_WUS_LNKC ?
6924			       "Link Status Change" : "other");
6925		}
6926		e1e_wphy(&adapter->hw, BM_WUS, ~0);
6927	} else {
6928		u32 wus = er32(WUS);
6929
6930		if (wus) {
6931			e_info("MAC Wakeup cause - %s\n",
6932			       wus & E1000_WUS_EX ? "Unicast Packet" :
6933			       wus & E1000_WUS_MC ? "Multicast Packet" :
6934			       wus & E1000_WUS_BC ? "Broadcast Packet" :
6935			       wus & E1000_WUS_MAG ? "Magic Packet" :
6936			       wus & E1000_WUS_LNKC ? "Link Status Change" :
6937			       "other");
6938		}
6939		ew32(WUS, ~0);
6940	}
6941
6942	e1000e_reset(adapter);
6943
6944	e1000_init_manageability_pt(adapter);
6945
6946	/* If the controller has AMT, do not set DRV_LOAD until the interface
6947	 * is up.  For all other cases, let the f/w know that the h/w is now
6948	 * under the control of the driver.
6949	 */
6950	if (!(adapter->flags & FLAG_HAS_AMT))
6951		e1000e_get_hw_control(adapter);
6952
6953	return 0;
6954}
6955
6956static __maybe_unused int e1000e_pm_prepare(struct device *dev)
6957{
6958	return pm_runtime_suspended(dev) &&
6959		pm_suspend_via_firmware();
6960}
6961
6962static __maybe_unused int e1000e_pm_suspend(struct device *dev)
6963{
6964	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
6965	struct e1000_adapter *adapter = netdev_priv(netdev);
6966	struct pci_dev *pdev = to_pci_dev(dev);
6967	int rc;
6968
6969	e1000e_flush_lpic(pdev);
6970
6971	e1000e_pm_freeze(dev);
6972
6973	rc = __e1000_shutdown(pdev, false);
6974	if (rc) {
6975		e1000e_pm_thaw(dev);
6976	} else {
6977		/* Introduce S0ix implementation */
6978		if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
6979			e1000e_s0ix_entry_flow(adapter);
6980	}
6981
6982	return rc;
6983}
6984
6985static __maybe_unused int e1000e_pm_resume(struct device *dev)
6986{
6987	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
6988	struct e1000_adapter *adapter = netdev_priv(netdev);
6989	struct pci_dev *pdev = to_pci_dev(dev);
6990	int rc;
6991
6992	/* Introduce S0ix implementation */
6993	if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
6994		e1000e_s0ix_exit_flow(adapter);
6995
6996	rc = __e1000_resume(pdev);
6997	if (rc)
6998		return rc;
6999
7000	return e1000e_pm_thaw(dev);
7001}
7002
7003static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev)
7004{
7005	struct net_device *netdev = dev_get_drvdata(dev);
7006	struct e1000_adapter *adapter = netdev_priv(netdev);
7007	u16 eee_lp;
7008
7009	eee_lp = adapter->hw.dev_spec.ich8lan.eee_lp_ability;
7010
7011	if (!e1000e_has_link(adapter)) {
7012		adapter->hw.dev_spec.ich8lan.eee_lp_ability = eee_lp;
7013		pm_schedule_suspend(dev, 5 * MSEC_PER_SEC);
7014	}
7015
7016	return -EBUSY;
7017}
7018
7019static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev)
7020{
7021	struct pci_dev *pdev = to_pci_dev(dev);
7022	struct net_device *netdev = pci_get_drvdata(pdev);
7023	struct e1000_adapter *adapter = netdev_priv(netdev);
7024	int rc;
7025
7026	pdev->pme_poll = true;
7027
7028	rc = __e1000_resume(pdev);
7029	if (rc)
7030		return rc;
7031
7032	if (netdev->flags & IFF_UP)
7033		e1000e_up(adapter);
7034
7035	return rc;
7036}
7037
7038static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev)
7039{
7040	struct pci_dev *pdev = to_pci_dev(dev);
7041	struct net_device *netdev = pci_get_drvdata(pdev);
7042	struct e1000_adapter *adapter = netdev_priv(netdev);
7043
7044	if (netdev->flags & IFF_UP) {
7045		int count = E1000_CHECK_RESET_COUNT;
7046
7047		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
7048			usleep_range(10000, 11000);
7049
7050		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
7051
7052		/* Down the device without resetting the hardware */
7053		e1000e_down(adapter, false);
7054	}
7055
7056	if (__e1000_shutdown(pdev, true)) {
7057		e1000e_pm_runtime_resume(dev);
7058		return -EBUSY;
7059	}
7060
7061	return 0;
7062}
7063
7064static void e1000_shutdown(struct pci_dev *pdev)
7065{
7066	e1000e_flush_lpic(pdev);
7067
7068	e1000e_pm_freeze(&pdev->dev);
7069
7070	__e1000_shutdown(pdev, false);
7071}
7072
7073#ifdef CONFIG_NET_POLL_CONTROLLER
7074
7075static irqreturn_t e1000_intr_msix(int __always_unused irq, void *data)
7076{
7077	struct net_device *netdev = data;
7078	struct e1000_adapter *adapter = netdev_priv(netdev);
7079
7080	if (adapter->msix_entries) {
7081		int vector, msix_irq;
7082
7083		vector = 0;
7084		msix_irq = adapter->msix_entries[vector].vector;
7085		if (disable_hardirq(msix_irq))
7086			e1000_intr_msix_rx(msix_irq, netdev);
7087		enable_irq(msix_irq);
7088
7089		vector++;
7090		msix_irq = adapter->msix_entries[vector].vector;
7091		if (disable_hardirq(msix_irq))
7092			e1000_intr_msix_tx(msix_irq, netdev);
7093		enable_irq(msix_irq);
7094
7095		vector++;
7096		msix_irq = adapter->msix_entries[vector].vector;
7097		if (disable_hardirq(msix_irq))
7098			e1000_msix_other(msix_irq, netdev);
7099		enable_irq(msix_irq);
7100	}
7101
7102	return IRQ_HANDLED;
7103}
7104
7105/**
7106 * e1000_netpoll
7107 * @netdev: network interface device structure
7108 *
7109 * Polling 'interrupt' - used by things like netconsole to send skbs
7110 * without having to re-enable interrupts. It's not called while
7111 * the interrupt routine is executing.
7112 */
7113static void e1000_netpoll(struct net_device *netdev)
7114{
7115	struct e1000_adapter *adapter = netdev_priv(netdev);
7116
7117	switch (adapter->int_mode) {
7118	case E1000E_INT_MODE_MSIX:
7119		e1000_intr_msix(adapter->pdev->irq, netdev);
7120		break;
7121	case E1000E_INT_MODE_MSI:
7122		if (disable_hardirq(adapter->pdev->irq))
7123			e1000_intr_msi(adapter->pdev->irq, netdev);
7124		enable_irq(adapter->pdev->irq);
7125		break;
7126	default:		/* E1000E_INT_MODE_LEGACY */
7127		if (disable_hardirq(adapter->pdev->irq))
7128			e1000_intr(adapter->pdev->irq, netdev);
7129		enable_irq(adapter->pdev->irq);
7130		break;
7131	}
7132}
7133#endif
7134
7135/**
7136 * e1000_io_error_detected - called when PCI error is detected
7137 * @pdev: Pointer to PCI device
7138 * @state: The current pci connection state
7139 *
7140 * This function is called after a PCI bus error affecting
7141 * this device has been detected.
7142 */
7143static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
7144						pci_channel_state_t state)
7145{
7146	e1000e_pm_freeze(&pdev->dev);
7147
7148	if (state == pci_channel_io_perm_failure)
7149		return PCI_ERS_RESULT_DISCONNECT;
7150
7151	pci_disable_device(pdev);
7152
7153	/* Request a slot reset. */
7154	return PCI_ERS_RESULT_NEED_RESET;
7155}
7156
7157/**
7158 * e1000_io_slot_reset - called after the pci bus has been reset.
7159 * @pdev: Pointer to PCI device
7160 *
7161 * Restart the card from scratch, as if from a cold-boot. Implementation
7162 * resembles the first-half of the e1000e_pm_resume routine.
7163 */
7164static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev)
7165{
7166	struct net_device *netdev = pci_get_drvdata(pdev);
7167	struct e1000_adapter *adapter = netdev_priv(netdev);
7168	struct e1000_hw *hw = &adapter->hw;
7169	u16 aspm_disable_flag = 0;
7170	int err;
7171	pci_ers_result_t result;
7172
7173	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L0S)
7174		aspm_disable_flag = PCIE_LINK_STATE_L0S;
7175	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1)
7176		aspm_disable_flag |= PCIE_LINK_STATE_L1;
7177	if (aspm_disable_flag)
7178		e1000e_disable_aspm_locked(pdev, aspm_disable_flag);
7179
7180	err = pci_enable_device_mem(pdev);
7181	if (err) {
7182		dev_err(&pdev->dev,
7183			"Cannot re-enable PCI device after reset.\n");
7184		result = PCI_ERS_RESULT_DISCONNECT;
7185	} else {
7186		pdev->state_saved = true;
7187		pci_restore_state(pdev);
7188		pci_set_master(pdev);
7189
7190		pci_enable_wake(pdev, PCI_D3hot, 0);
7191		pci_enable_wake(pdev, PCI_D3cold, 0);
7192
7193		e1000e_reset(adapter);
7194		ew32(WUS, ~0);
7195		result = PCI_ERS_RESULT_RECOVERED;
7196	}
7197
7198	return result;
7199}
7200
7201/**
7202 * e1000_io_resume - called when traffic can start flowing again.
7203 * @pdev: Pointer to PCI device
7204 *
7205 * This callback is called when the error recovery driver tells us that
7206 * its OK to resume normal operation. Implementation resembles the
7207 * second-half of the e1000e_pm_resume routine.
7208 */
7209static void e1000_io_resume(struct pci_dev *pdev)
7210{
7211	struct net_device *netdev = pci_get_drvdata(pdev);
7212	struct e1000_adapter *adapter = netdev_priv(netdev);
7213
7214	e1000_init_manageability_pt(adapter);
7215
7216	e1000e_pm_thaw(&pdev->dev);
7217
7218	/* If the controller has AMT, do not set DRV_LOAD until the interface
7219	 * is up.  For all other cases, let the f/w know that the h/w is now
7220	 * under the control of the driver.
7221	 */
7222	if (!(adapter->flags & FLAG_HAS_AMT))
7223		e1000e_get_hw_control(adapter);
7224}
7225
7226static void e1000_print_device_info(struct e1000_adapter *adapter)
7227{
7228	struct e1000_hw *hw = &adapter->hw;
7229	struct net_device *netdev = adapter->netdev;
7230	u32 ret_val;
7231	u8 pba_str[E1000_PBANUM_LENGTH];
7232
7233	/* print bus type/speed/width info */
7234	e_info("(PCI Express:2.5GT/s:%s) %pM\n",
7235	       /* bus width */
7236	       ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" :
7237		"Width x1"),
7238	       /* MAC address */
7239	       netdev->dev_addr);
7240	e_info("Intel(R) PRO/%s Network Connection\n",
7241	       (hw->phy.type == e1000_phy_ife) ? "10/100" : "1000");
7242	ret_val = e1000_read_pba_string_generic(hw, pba_str,
7243						E1000_PBANUM_LENGTH);
7244	if (ret_val)
7245		strscpy((char *)pba_str, "Unknown", sizeof(pba_str));
7246	e_info("MAC: %d, PHY: %d, PBA No: %s\n",
7247	       hw->mac.type, hw->phy.type, pba_str);
7248}
7249
7250static void e1000_eeprom_checks(struct e1000_adapter *adapter)
7251{
7252	struct e1000_hw *hw = &adapter->hw;
7253	int ret_val;
7254	u16 buf = 0;
7255
7256	if (hw->mac.type != e1000_82573)
7257		return;
7258
7259	ret_val = e1000_read_nvm(hw, NVM_INIT_CONTROL2_REG, 1, &buf);
7260	le16_to_cpus(&buf);
7261	if (!ret_val && (!(buf & BIT(0)))) {
7262		/* Deep Smart Power Down (DSPD) */
7263		dev_warn(&adapter->pdev->dev,
7264			 "Warning: detected DSPD enabled in EEPROM\n");
7265	}
7266}
7267
7268static netdev_features_t e1000_fix_features(struct net_device *netdev,
7269					    netdev_features_t features)
7270{
7271	struct e1000_adapter *adapter = netdev_priv(netdev);
7272	struct e1000_hw *hw = &adapter->hw;
7273
7274	/* Jumbo frame workaround on 82579 and newer requires CRC be stripped */
7275	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
7276		features &= ~NETIF_F_RXFCS;
7277
7278	/* Since there is no support for separate Rx/Tx vlan accel
7279	 * enable/disable make sure Tx flag is always in same state as Rx.
7280	 */
7281	if (features & NETIF_F_HW_VLAN_CTAG_RX)
7282		features |= NETIF_F_HW_VLAN_CTAG_TX;
7283	else
7284		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
7285
7286	return features;
7287}
7288
7289static int e1000_set_features(struct net_device *netdev,
7290			      netdev_features_t features)
7291{
7292	struct e1000_adapter *adapter = netdev_priv(netdev);
7293	netdev_features_t changed = features ^ netdev->features;
7294
7295	if (changed & (NETIF_F_TSO | NETIF_F_TSO6))
7296		adapter->flags |= FLAG_TSO_FORCE;
7297
7298	if (!(changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX |
7299			 NETIF_F_RXCSUM | NETIF_F_RXHASH | NETIF_F_RXFCS |
7300			 NETIF_F_RXALL)))
7301		return 0;
7302
7303	if (changed & NETIF_F_RXFCS) {
7304		if (features & NETIF_F_RXFCS) {
7305			adapter->flags2 &= ~FLAG2_CRC_STRIPPING;
7306		} else {
7307			/* We need to take it back to defaults, which might mean
7308			 * stripping is still disabled at the adapter level.
7309			 */
7310			if (adapter->flags2 & FLAG2_DFLT_CRC_STRIPPING)
7311				adapter->flags2 |= FLAG2_CRC_STRIPPING;
7312			else
7313				adapter->flags2 &= ~FLAG2_CRC_STRIPPING;
7314		}
7315	}
7316
7317	netdev->features = features;
7318
7319	if (netif_running(netdev))
7320		e1000e_reinit_locked(adapter);
7321	else
7322		e1000e_reset(adapter);
7323
7324	return 1;
7325}
7326
7327static const struct net_device_ops e1000e_netdev_ops = {
7328	.ndo_open		= e1000e_open,
7329	.ndo_stop		= e1000e_close,
7330	.ndo_start_xmit		= e1000_xmit_frame,
7331	.ndo_get_stats64	= e1000e_get_stats64,
7332	.ndo_set_rx_mode	= e1000e_set_rx_mode,
7333	.ndo_set_mac_address	= e1000_set_mac,
7334	.ndo_change_mtu		= e1000_change_mtu,
7335	.ndo_eth_ioctl		= e1000_ioctl,
7336	.ndo_tx_timeout		= e1000_tx_timeout,
7337	.ndo_validate_addr	= eth_validate_addr,
7338
7339	.ndo_vlan_rx_add_vid	= e1000_vlan_rx_add_vid,
7340	.ndo_vlan_rx_kill_vid	= e1000_vlan_rx_kill_vid,
7341#ifdef CONFIG_NET_POLL_CONTROLLER
7342	.ndo_poll_controller	= e1000_netpoll,
7343#endif
7344	.ndo_set_features = e1000_set_features,
7345	.ndo_fix_features = e1000_fix_features,
7346	.ndo_features_check	= passthru_features_check,
7347};
7348
7349/**
7350 * e1000_probe - Device Initialization Routine
7351 * @pdev: PCI device information struct
7352 * @ent: entry in e1000_pci_tbl
7353 *
7354 * Returns 0 on success, negative on failure
7355 *
7356 * e1000_probe initializes an adapter identified by a pci_dev structure.
7357 * The OS initialization, configuring of the adapter private structure,
7358 * and a hardware reset occur.
7359 **/
7360static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
7361{
7362	struct net_device *netdev;
7363	struct e1000_adapter *adapter;
7364	struct e1000_hw *hw;
7365	const struct e1000_info *ei = e1000_info_tbl[ent->driver_data];
7366	resource_size_t mmio_start, mmio_len;
7367	resource_size_t flash_start, flash_len;
7368	static int cards_found;
7369	u16 aspm_disable_flag = 0;
7370	u16 eeprom_data = 0;
7371	u16 eeprom_apme_mask = E1000_EEPROM_APME;
7372	int bars, i, err;
7373	s32 ret_val = 0;
7374
7375	if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S)
7376		aspm_disable_flag = PCIE_LINK_STATE_L0S;
7377	if (ei->flags2 & FLAG2_DISABLE_ASPM_L1)
7378		aspm_disable_flag |= PCIE_LINK_STATE_L1;
7379	if (aspm_disable_flag)
7380		e1000e_disable_aspm(pdev, aspm_disable_flag);
7381
7382	err = pci_enable_device_mem(pdev);
7383	if (err)
7384		return err;
7385
7386	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
7387	if (err) {
7388		dev_err(&pdev->dev,
7389			"No usable DMA configuration, aborting\n");
7390		goto err_dma;
7391	}
7392
7393	bars = pci_select_bars(pdev, IORESOURCE_MEM);
7394	err = pci_request_selected_regions_exclusive(pdev, bars,
7395						     e1000e_driver_name);
7396	if (err)
7397		goto err_pci_reg;
7398
7399	pci_set_master(pdev);
7400	/* PCI config space info */
7401	err = pci_save_state(pdev);
7402	if (err)
7403		goto err_alloc_etherdev;
7404
7405	err = -ENOMEM;
7406	netdev = alloc_etherdev(sizeof(struct e1000_adapter));
7407	if (!netdev)
7408		goto err_alloc_etherdev;
7409
7410	SET_NETDEV_DEV(netdev, &pdev->dev);
7411
7412	netdev->irq = pdev->irq;
7413
7414	pci_set_drvdata(pdev, netdev);
7415	adapter = netdev_priv(netdev);
7416	hw = &adapter->hw;
7417	adapter->netdev = netdev;
7418	adapter->pdev = pdev;
7419	adapter->ei = ei;
7420	adapter->pba = ei->pba;
7421	adapter->flags = ei->flags;
7422	adapter->flags2 = ei->flags2;
7423	adapter->hw.adapter = adapter;
7424	adapter->hw.mac.type = ei->mac;
7425	adapter->max_hw_frame_size = ei->max_hw_frame_size;
7426	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
7427
7428	mmio_start = pci_resource_start(pdev, 0);
7429	mmio_len = pci_resource_len(pdev, 0);
7430
7431	err = -EIO;
7432	adapter->hw.hw_addr = ioremap(mmio_start, mmio_len);
7433	if (!adapter->hw.hw_addr)
7434		goto err_ioremap;
7435
7436	if ((adapter->flags & FLAG_HAS_FLASH) &&
7437	    (pci_resource_flags(pdev, 1) & IORESOURCE_MEM) &&
7438	    (hw->mac.type < e1000_pch_spt)) {
7439		flash_start = pci_resource_start(pdev, 1);
7440		flash_len = pci_resource_len(pdev, 1);
7441		adapter->hw.flash_address = ioremap(flash_start, flash_len);
7442		if (!adapter->hw.flash_address)
7443			goto err_flashmap;
7444	}
7445
7446	/* Set default EEE advertisement */
7447	if (adapter->flags2 & FLAG2_HAS_EEE)
7448		adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T;
7449
7450	/* construct the net_device struct */
7451	netdev->netdev_ops = &e1000e_netdev_ops;
7452	e1000e_set_ethtool_ops(netdev);
7453	netdev->watchdog_timeo = 5 * HZ;
7454	netif_napi_add(netdev, &adapter->napi, e1000e_poll);
7455	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
7456
7457	netdev->mem_start = mmio_start;
7458	netdev->mem_end = mmio_start + mmio_len;
7459
7460	adapter->bd_number = cards_found++;
7461
7462	e1000e_check_options(adapter);
7463
7464	/* setup adapter struct */
7465	err = e1000_sw_init(adapter);
7466	if (err)
7467		goto err_sw_init;
7468
7469	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
7470	memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops));
7471	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
7472
7473	err = ei->get_variants(adapter);
7474	if (err)
7475		goto err_hw_init;
7476
7477	if ((adapter->flags & FLAG_IS_ICH) &&
7478	    (adapter->flags & FLAG_READ_ONLY_NVM) &&
7479	    (hw->mac.type < e1000_pch_spt))
7480		e1000e_write_protect_nvm_ich8lan(&adapter->hw);
7481
7482	hw->mac.ops.get_bus_info(&adapter->hw);
7483
7484	adapter->hw.phy.autoneg_wait_to_complete = 0;
7485
7486	/* Copper options */
7487	if (adapter->hw.phy.media_type == e1000_media_type_copper) {
7488		adapter->hw.phy.mdix = AUTO_ALL_MODES;
7489		adapter->hw.phy.disable_polarity_correction = 0;
7490		adapter->hw.phy.ms_type = e1000_ms_hw_default;
7491	}
7492
7493	if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw))
7494		dev_info(&pdev->dev,
7495			 "PHY reset is blocked due to SOL/IDER session.\n");
7496
7497	/* Set initial default active device features */
7498	netdev->features = (NETIF_F_SG |
7499			    NETIF_F_HW_VLAN_CTAG_RX |
7500			    NETIF_F_HW_VLAN_CTAG_TX |
7501			    NETIF_F_TSO |
7502			    NETIF_F_TSO6 |
7503			    NETIF_F_RXHASH |
7504			    NETIF_F_RXCSUM |
7505			    NETIF_F_HW_CSUM);
7506
7507	/* disable TSO for pcie and 10/100 speeds to avoid
7508	 * some hardware issues and for i219 to fix transfer
7509	 * speed being capped at 60%
7510	 */
7511	if (!(adapter->flags & FLAG_TSO_FORCE)) {
7512		switch (adapter->link_speed) {
7513		case SPEED_10:
7514		case SPEED_100:
7515			e_info("10/100 speed: disabling TSO\n");
7516			netdev->features &= ~NETIF_F_TSO;
7517			netdev->features &= ~NETIF_F_TSO6;
7518			break;
7519		case SPEED_1000:
7520			netdev->features |= NETIF_F_TSO;
7521			netdev->features |= NETIF_F_TSO6;
7522			break;
7523		default:
7524			/* oops */
7525			break;
7526		}
7527		if (hw->mac.type == e1000_pch_spt) {
7528			netdev->features &= ~NETIF_F_TSO;
7529			netdev->features &= ~NETIF_F_TSO6;
7530		}
7531	}
7532
7533	/* Set user-changeable features (subset of all device features) */
7534	netdev->hw_features = netdev->features;
7535	netdev->hw_features |= NETIF_F_RXFCS;
7536	netdev->priv_flags |= IFF_SUPP_NOFCS;
7537	netdev->hw_features |= NETIF_F_RXALL;
7538
7539	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER)
7540		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
7541
7542	netdev->vlan_features |= (NETIF_F_SG |
7543				  NETIF_F_TSO |
7544				  NETIF_F_TSO6 |
7545				  NETIF_F_HW_CSUM);
7546
7547	netdev->priv_flags |= IFF_UNICAST_FLT;
7548
7549	netdev->features |= NETIF_F_HIGHDMA;
7550	netdev->vlan_features |= NETIF_F_HIGHDMA;
7551
7552	/* MTU range: 68 - max_hw_frame_size */
7553	netdev->min_mtu = ETH_MIN_MTU;
7554	netdev->max_mtu = adapter->max_hw_frame_size -
7555			  (VLAN_ETH_HLEN + ETH_FCS_LEN);
7556
7557	if (e1000e_enable_mng_pass_thru(&adapter->hw))
7558		adapter->flags |= FLAG_MNG_PT_ENABLED;
7559
7560	/* before reading the NVM, reset the controller to
7561	 * put the device in a known good starting state
7562	 */
7563	adapter->hw.mac.ops.reset_hw(&adapter->hw);
7564
7565	/* systems with ASPM and others may see the checksum fail on the first
7566	 * attempt. Let's give it a few tries
7567	 */
7568	for (i = 0;; i++) {
7569		if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
7570			break;
7571		if (i == 2) {
7572			dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
7573			err = -EIO;
7574			goto err_eeprom;
7575		}
7576	}
7577
7578	e1000_eeprom_checks(adapter);
7579
7580	/* copy the MAC address */
7581	if (e1000e_read_mac_addr(&adapter->hw))
7582		dev_err(&pdev->dev,
7583			"NVM Read Error while reading MAC address\n");
7584
7585	eth_hw_addr_set(netdev, adapter->hw.mac.addr);
7586
7587	if (!is_valid_ether_addr(netdev->dev_addr)) {
7588		dev_err(&pdev->dev, "Invalid MAC Address: %pM\n",
7589			netdev->dev_addr);
7590		err = -EIO;
7591		goto err_eeprom;
7592	}
7593
7594	timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
7595	timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
7596
7597	INIT_WORK(&adapter->reset_task, e1000_reset_task);
7598	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
7599	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
7600	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
7601	INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
7602
7603	/* Initialize link parameters. User can change them with ethtool */
7604	adapter->hw.mac.autoneg = 1;
7605	adapter->fc_autoneg = true;
7606	adapter->hw.fc.requested_mode = e1000_fc_default;
7607	adapter->hw.fc.current_mode = e1000_fc_default;
7608	adapter->hw.phy.autoneg_advertised = 0x2f;
7609
7610	/* Initial Wake on LAN setting - If APM wake is enabled in
7611	 * the EEPROM, enable the ACPI Magic Packet filter
7612	 */
7613	if (adapter->flags & FLAG_APME_IN_WUC) {
7614		/* APME bit in EEPROM is mapped to WUC.APME */
7615		eeprom_data = er32(WUC);
7616		eeprom_apme_mask = E1000_WUC_APME;
7617		if ((hw->mac.type > e1000_ich10lan) &&
7618		    (eeprom_data & E1000_WUC_PHY_WAKE))
7619			adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP;
7620	} else if (adapter->flags & FLAG_APME_IN_CTRL3) {
7621		if (adapter->flags & FLAG_APME_CHECK_PORT_B &&
7622		    (adapter->hw.bus.func == 1))
7623			ret_val = e1000_read_nvm(&adapter->hw,
7624					      NVM_INIT_CONTROL3_PORT_B,
7625					      1, &eeprom_data);
7626		else
7627			ret_val = e1000_read_nvm(&adapter->hw,
7628					      NVM_INIT_CONTROL3_PORT_A,
7629					      1, &eeprom_data);
7630	}
7631
7632	/* fetch WoL from EEPROM */
7633	if (ret_val)
7634		e_dbg("NVM read error getting WoL initial values: %d\n", ret_val);
7635	else if (eeprom_data & eeprom_apme_mask)
7636		adapter->eeprom_wol |= E1000_WUFC_MAG;
7637
7638	/* now that we have the eeprom settings, apply the special cases
7639	 * where the eeprom may be wrong or the board simply won't support
7640	 * wake on lan on a particular port
7641	 */
7642	if (!(adapter->flags & FLAG_HAS_WOL))
7643		adapter->eeprom_wol = 0;
7644
7645	/* initialize the wol settings based on the eeprom settings */
7646	adapter->wol = adapter->eeprom_wol;
7647
7648	/* make sure adapter isn't asleep if manageability is enabled */
7649	if (adapter->wol || (adapter->flags & FLAG_MNG_PT_ENABLED) ||
7650	    (hw->mac.ops.check_mng_mode(hw)))
7651		device_wakeup_enable(&pdev->dev);
7652
7653	/* save off EEPROM version number */
7654	ret_val = e1000_read_nvm(&adapter->hw, 5, 1, &adapter->eeprom_vers);
7655
7656	if (ret_val) {
7657		e_dbg("NVM read error getting EEPROM version: %d\n", ret_val);
7658		adapter->eeprom_vers = 0;
7659	}
7660
7661	/* init PTP hardware clock */
7662	e1000e_ptp_init(adapter);
7663
7664	/* reset the hardware with the new settings */
7665	e1000e_reset(adapter);
7666
7667	/* If the controller has AMT, do not set DRV_LOAD until the interface
7668	 * is up.  For all other cases, let the f/w know that the h/w is now
7669	 * under the control of the driver.
7670	 */
7671	if (!(adapter->flags & FLAG_HAS_AMT))
7672		e1000e_get_hw_control(adapter);
7673
7674	if (hw->mac.type >= e1000_pch_cnp)
7675		adapter->flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
7676
7677	strscpy(netdev->name, "eth%d", sizeof(netdev->name));
7678	err = register_netdev(netdev);
7679	if (err)
7680		goto err_register;
7681
7682	/* carrier off reporting is important to ethtool even BEFORE open */
7683	netif_carrier_off(netdev);
7684
7685	e1000_print_device_info(adapter);
7686
7687	dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE);
7688
7689	if (pci_dev_run_wake(pdev))
7690		pm_runtime_put_noidle(&pdev->dev);
7691
7692	return 0;
7693
7694err_register:
7695	if (!(adapter->flags & FLAG_HAS_AMT))
7696		e1000e_release_hw_control(adapter);
7697err_eeprom:
7698	if (hw->phy.ops.check_reset_block && !hw->phy.ops.check_reset_block(hw))
7699		e1000_phy_hw_reset(&adapter->hw);
7700err_hw_init:
7701	kfree(adapter->tx_ring);
7702	kfree(adapter->rx_ring);
7703err_sw_init:
7704	if ((adapter->hw.flash_address) && (hw->mac.type < e1000_pch_spt))
7705		iounmap(adapter->hw.flash_address);
7706	e1000e_reset_interrupt_capability(adapter);
7707err_flashmap:
7708	iounmap(adapter->hw.hw_addr);
7709err_ioremap:
7710	free_netdev(netdev);
7711err_alloc_etherdev:
7712	pci_release_mem_regions(pdev);
7713err_pci_reg:
7714err_dma:
7715	pci_disable_device(pdev);
7716	return err;
7717}
7718
7719/**
7720 * e1000_remove - Device Removal Routine
7721 * @pdev: PCI device information struct
7722 *
7723 * e1000_remove is called by the PCI subsystem to alert the driver
7724 * that it should release a PCI device.  This could be caused by a
7725 * Hot-Plug event, or because the driver is going to be removed from
7726 * memory.
7727 **/
7728static void e1000_remove(struct pci_dev *pdev)
7729{
7730	struct net_device *netdev = pci_get_drvdata(pdev);
7731	struct e1000_adapter *adapter = netdev_priv(netdev);
7732
7733	e1000e_ptp_remove(adapter);
7734
7735	/* The timers may be rescheduled, so explicitly disable them
7736	 * from being rescheduled.
7737	 */
7738	set_bit(__E1000_DOWN, &adapter->state);
7739	del_timer_sync(&adapter->watchdog_timer);
7740	del_timer_sync(&adapter->phy_info_timer);
7741
7742	cancel_work_sync(&adapter->reset_task);
7743	cancel_work_sync(&adapter->watchdog_task);
7744	cancel_work_sync(&adapter->downshift_task);
7745	cancel_work_sync(&adapter->update_phy_task);
7746	cancel_work_sync(&adapter->print_hang_task);
7747
7748	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
7749		cancel_work_sync(&adapter->tx_hwtstamp_work);
7750		if (adapter->tx_hwtstamp_skb) {
7751			dev_consume_skb_any(adapter->tx_hwtstamp_skb);
7752			adapter->tx_hwtstamp_skb = NULL;
7753		}
7754	}
7755
7756	unregister_netdev(netdev);
7757
7758	if (pci_dev_run_wake(pdev))
7759		pm_runtime_get_noresume(&pdev->dev);
7760
7761	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
7762	 * would have already happened in close and is redundant.
7763	 */
7764	e1000e_release_hw_control(adapter);
7765
7766	e1000e_reset_interrupt_capability(adapter);
7767	kfree(adapter->tx_ring);
7768	kfree(adapter->rx_ring);
7769
7770	iounmap(adapter->hw.hw_addr);
7771	if ((adapter->hw.flash_address) &&
7772	    (adapter->hw.mac.type < e1000_pch_spt))
7773		iounmap(adapter->hw.flash_address);
7774	pci_release_mem_regions(pdev);
7775
7776	free_netdev(netdev);
7777
7778	pci_disable_device(pdev);
7779}
7780
7781/* PCI Error Recovery (ERS) */
7782static const struct pci_error_handlers e1000_err_handler = {
7783	.error_detected = e1000_io_error_detected,
7784	.slot_reset = e1000_io_slot_reset,
7785	.resume = e1000_io_resume,
7786};
7787
7788static const struct pci_device_id e1000_pci_tbl[] = {
7789	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_COPPER), board_82571 },
7790	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_FIBER), board_82571 },
7791	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER), board_82571 },
7792	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER_LP),
7793	  board_82571 },
7794	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_FIBER), board_82571 },
7795	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES), board_82571 },
7796	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES_DUAL), board_82571 },
7797	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES_QUAD), board_82571 },
7798	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571PT_QUAD_COPPER), board_82571 },
7799
7800	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI), board_82572 },
7801	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_COPPER), board_82572 },
7802	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_FIBER), board_82572 },
7803	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_SERDES), board_82572 },
7804
7805	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573E), board_82573 },
7806	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573E_IAMT), board_82573 },
7807	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573L), board_82573 },
7808
7809	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82574L), board_82574 },
7810	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82574LA), board_82574 },
7811	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82583V), board_82583 },
7812
7813	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_COPPER_DPT),
7814	  board_80003es2lan },
7815	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_COPPER_SPT),
7816	  board_80003es2lan },
7817	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_SERDES_DPT),
7818	  board_80003es2lan },
7819	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_SERDES_SPT),
7820	  board_80003es2lan },
7821
7822	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE), board_ich8lan },
7823	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE_G), board_ich8lan },
7824	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE_GT), board_ich8lan },
7825	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_AMT), board_ich8lan },
7826	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_C), board_ich8lan },
7827	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M), board_ich8lan },
7828	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M_AMT), board_ich8lan },
7829	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_82567V_3), board_ich8lan },
7830
7831	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE), board_ich9lan },
7832	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_G), board_ich9lan },
7833	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_GT), board_ich9lan },
7834	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_AMT), board_ich9lan },
7835	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_C), board_ich9lan },
7836	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_BM), board_ich9lan },
7837	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M), board_ich9lan },
7838	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_AMT), board_ich9lan },
7839	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_V), board_ich9lan },
7840
7841	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LM), board_ich9lan },
7842	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LF), board_ich9lan },
7843	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_V), board_ich9lan },
7844
7845	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_LM), board_ich10lan },
7846	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_LF), board_ich10lan },
7847	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_V), board_ich10lan },
7848
7849	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_M_HV_LM), board_pchlan },
7850	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_M_HV_LC), board_pchlan },
7851	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_D_HV_DM), board_pchlan },
7852	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_D_HV_DC), board_pchlan },
7853
7854	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH2_LV_LM), board_pch2lan },
7855	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH2_LV_V), board_pch2lan },
7856
7857	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_LM), board_pch_lpt },
7858	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_V), board_pch_lpt },
7859	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_LM), board_pch_lpt },
7860	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_V), board_pch_lpt },
7861	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM2), board_pch_lpt },
7862	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V2), board_pch_lpt },
7863	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM3), board_pch_lpt },
7864	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V3), board_pch_lpt },
7865	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM), board_pch_spt },
7866	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V), board_pch_spt },
7867	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM2), board_pch_spt },
7868	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V2), board_pch_spt },
7869	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LBG_I219_LM3), board_pch_spt },
7870	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM4), board_pch_spt },
7871	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V4), board_pch_spt },
7872	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM5), board_pch_spt },
7873	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V5), board_pch_spt },
7874	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM6), board_pch_cnp },
7875	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V6), board_pch_cnp },
7876	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM7), board_pch_cnp },
7877	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V7), board_pch_cnp },
7878	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_LM8), board_pch_cnp },
7879	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_V8), board_pch_cnp },
7880	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_LM9), board_pch_cnp },
7881	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_V9), board_pch_cnp },
7882	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_LM10), board_pch_cnp },
7883	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V10), board_pch_cnp },
7884	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_LM11), board_pch_cnp },
7885	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V11), board_pch_cnp },
7886	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_LM12), board_pch_spt },
7887	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V12), board_pch_spt },
7888	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM13), board_pch_tgp },
7889	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V13), board_pch_tgp },
7890	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_tgp },
7891	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp },
7892	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp },
7893	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp },
7894	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_adp },
7895	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_adp },
7896	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_adp },
7897	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_adp },
7898	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_adp },
7899	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp },
7900	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp },
7901	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp },
7902	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_mtp },
7903	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_mtp },
7904	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_mtp },
7905	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_mtp },
7906	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_mtp },
7907	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_mtp },
7908	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_mtp },
7909	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp },
7910	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp },
7911	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp },
7912	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp },
7913	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp },
7914	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp },
7915	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp },
7916	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp },
7917	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp },
7918	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp },
7919	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp },
7920
7921	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
7922};
7923MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
7924
7925static const struct dev_pm_ops e1000_pm_ops = {
7926#ifdef CONFIG_PM_SLEEP
7927	.prepare	= e1000e_pm_prepare,
7928	.suspend	= e1000e_pm_suspend,
7929	.resume		= e1000e_pm_resume,
7930	.freeze		= e1000e_pm_freeze,
7931	.thaw		= e1000e_pm_thaw,
7932	.poweroff	= e1000e_pm_suspend,
7933	.restore	= e1000e_pm_resume,
7934#endif
7935	SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume,
7936			   e1000e_pm_runtime_idle)
7937};
7938
7939/* PCI Device API Driver */
7940static struct pci_driver e1000_driver = {
7941	.name     = e1000e_driver_name,
7942	.id_table = e1000_pci_tbl,
7943	.probe    = e1000_probe,
7944	.remove   = e1000_remove,
7945	.driver   = {
7946		.pm = &e1000_pm_ops,
7947	},
7948	.shutdown = e1000_shutdown,
7949	.err_handler = &e1000_err_handler
7950};
7951
7952/**
7953 * e1000_init_module - Driver Registration Routine
7954 *
7955 * e1000_init_module is the first routine called when the driver is
7956 * loaded. All it does is register with the PCI subsystem.
7957 **/
7958static int __init e1000_init_module(void)
7959{
7960	pr_info("Intel(R) PRO/1000 Network Driver\n");
7961	pr_info("Copyright(c) 1999 - 2015 Intel Corporation.\n");
7962
7963	return pci_register_driver(&e1000_driver);
7964}
7965module_init(e1000_init_module);
7966
7967/**
7968 * e1000_exit_module - Driver Exit Cleanup Routine
7969 *
7970 * e1000_exit_module is called just before the driver is removed
7971 * from memory.
7972 **/
7973static void __exit e1000_exit_module(void)
7974{
7975	pci_unregister_driver(&e1000_driver);
7976}
7977module_exit(e1000_exit_module);
7978
7979MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
7980MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver");
7981MODULE_LICENSE("GPL v2");
7982
7983/* netdev.c */
7984