netdev.c 168.8 KB
Newer Older
1 2 3
/*******************************************************************************

  Intel PRO/1000 Linux driver
4
  Copyright(c) 1999 - 2010 Intel Corporation.
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28

  This program is free software; you can redistribute it and/or modify it
  under the terms and conditions of the GNU General Public License,
  version 2, as published by the Free Software Foundation.

  This program is distributed in the hope it will be useful, but WITHOUT
  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  more details.

  You should have received a copy of the GNU General Public License along with
  this program; if not, write to the Free Software Foundation, Inc.,
  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.

  The full GNU General Public License is included in this distribution in
  the file called "COPYING".

  Contact Information:
  Linux NICS <linux.nics@intel.com>
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

*******************************************************************************/

29 30
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

31 32 33 34 35 36 37 38 39 40
#include <linux/module.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/tcp.h>
#include <linux/ipv6.h>
41
#include <linux/slab.h>
42 43 44 45 46 47 48
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/cpu.h>
#include <linux/smp.h>
49
#include <linux/pm_qos_params.h>
50
#include <linux/pm_runtime.h>
J
Jesse Brandeburg 已提交
51
#include <linux/aer.h>
52 53 54

#include "e1000.h"

55 56 57
#define DRV_EXTRAVERSION "-k2"

#define DRV_VERSION "1.2.7" DRV_EXTRAVERSION
58 59 60 61 62 63 64
char e1000e_driver_name[] = "e1000e";
const char e1000e_driver_version[] = DRV_VERSION;

static const struct e1000_info *e1000_info_tbl[] = {
	[board_82571]		= &e1000_82571_info,
	[board_82572]		= &e1000_82572_info,
	[board_82573]		= &e1000_82573_info,
65
	[board_82574]		= &e1000_82574_info,
66
	[board_82583]		= &e1000_82583_info,
67 68 69
	[board_80003es2lan]	= &e1000_es2_info,
	[board_ich8lan]		= &e1000_ich8_info,
	[board_ich9lan]		= &e1000_ich9_info,
70
	[board_ich10lan]	= &e1000_ich10_info,
71
	[board_pchlan]		= &e1000_pch_info,
72
	[board_pch2lan]		= &e1000_pch2_info,
73 74
};

75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
struct e1000_reg_info {
	u32 ofs;
	char *name;
};

#define E1000_RDFH	0x02410 /* Rx Data FIFO Head - RW */
#define E1000_RDFT	0x02418 /* Rx Data FIFO Tail - RW */
#define E1000_RDFHS	0x02420 /* Rx Data FIFO Head Saved - RW */
#define E1000_RDFTS	0x02428 /* Rx Data FIFO Tail Saved - RW */
#define E1000_RDFPC	0x02430 /* Rx Data FIFO Packet Count - RW */

#define E1000_TDFH	0x03410 /* Tx Data FIFO Head - RW */
#define E1000_TDFT	0x03418 /* Tx Data FIFO Tail - RW */
#define E1000_TDFHS	0x03420 /* Tx Data FIFO Head Saved - RW */
#define E1000_TDFTS	0x03428 /* Tx Data FIFO Tail Saved - RW */
#define E1000_TDFPC	0x03430 /* Tx Data FIFO Packet Count - RW */

static const struct e1000_reg_info e1000_reg_info_tbl[] = {

	/* General Registers */
	{E1000_CTRL, "CTRL"},
	{E1000_STATUS, "STATUS"},
	{E1000_CTRL_EXT, "CTRL_EXT"},

	/* Interrupt Registers */
	{E1000_ICR, "ICR"},

	/* RX Registers */
	{E1000_RCTL, "RCTL"},
	{E1000_RDLEN, "RDLEN"},
	{E1000_RDH, "RDH"},
	{E1000_RDT, "RDT"},
	{E1000_RDTR, "RDTR"},
	{E1000_RXDCTL(0), "RXDCTL"},
	{E1000_ERT, "ERT"},
	{E1000_RDBAL, "RDBAL"},
	{E1000_RDBAH, "RDBAH"},
	{E1000_RDFH, "RDFH"},
	{E1000_RDFT, "RDFT"},
	{E1000_RDFHS, "RDFHS"},
	{E1000_RDFTS, "RDFTS"},
	{E1000_RDFPC, "RDFPC"},

	/* TX Registers */
	{E1000_TCTL, "TCTL"},
	{E1000_TDBAL, "TDBAL"},
	{E1000_TDBAH, "TDBAH"},
	{E1000_TDLEN, "TDLEN"},
	{E1000_TDH, "TDH"},
	{E1000_TDT, "TDT"},
	{E1000_TIDV, "TIDV"},
	{E1000_TXDCTL(0), "TXDCTL"},
	{E1000_TADV, "TADV"},
	{E1000_TARC(0), "TARC"},
	{E1000_TDFH, "TDFH"},
	{E1000_TDFT, "TDFT"},
	{E1000_TDFHS, "TDFHS"},
	{E1000_TDFTS, "TDFTS"},
	{E1000_TDFPC, "TDFPC"},

	/* List Terminator */
	{}
};

/*
 * e1000_regdump - register printout routine
 */
static void e1000_regdump(struct e1000_hw *hw, struct e1000_reg_info *reginfo)
{
	int n = 0;
	char rname[16];
	u32 regs[8];

	switch (reginfo->ofs) {
	case E1000_RXDCTL(0):
		for (n = 0; n < 2; n++)
			regs[n] = __er32(hw, E1000_RXDCTL(n));
		break;
	case E1000_TXDCTL(0):
		for (n = 0; n < 2; n++)
			regs[n] = __er32(hw, E1000_TXDCTL(n));
		break;
	case E1000_TARC(0):
		for (n = 0; n < 2; n++)
			regs[n] = __er32(hw, E1000_TARC(n));
		break;
	default:
		printk(KERN_INFO "%-15s %08x\n",
			reginfo->name, __er32(hw, reginfo->ofs));
		return;
	}

	snprintf(rname, 16, "%s%s", reginfo->name, "[0-1]");
	printk(KERN_INFO "%-15s ", rname);
	for (n = 0; n < 2; n++)
		printk(KERN_CONT "%08x ", regs[n]);
	printk(KERN_CONT "\n");
}


/*
 * e1000e_dump - Print registers, tx-ring and rx-ring
 */
static void e1000e_dump(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_reg_info *reginfo;
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_tx_desc *tx_desc;
	struct my_u0 { u64 a; u64 b; } *u0;
	struct e1000_buffer *buffer_info;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	union e1000_rx_desc_packet_split *rx_desc_ps;
	struct e1000_rx_desc *rx_desc;
	struct my_u1 { u64 a; u64 b; u64 c; u64 d; } *u1;
	u32 staterr;
	int i = 0;

	if (!netif_msg_hw(adapter))
		return;

	/* Print netdevice Info */
	if (netdev) {
		dev_info(&adapter->pdev->dev, "Net device Info\n");
		printk(KERN_INFO "Device Name     state            "
			"trans_start      last_rx\n");
		printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
			netdev->name,
			netdev->state,
			netdev->trans_start,
			netdev->last_rx);
	}

	/* Print Registers */
	dev_info(&adapter->pdev->dev, "Register Dump\n");
	printk(KERN_INFO " Register Name   Value\n");
	for (reginfo = (struct e1000_reg_info *)e1000_reg_info_tbl;
	     reginfo->name; reginfo++) {
		e1000_regdump(hw, reginfo);
	}

	/* Print TX Ring Summary */
	if (!netdev || !netif_running(netdev))
		goto exit;

	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
	printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma  ]"
		" leng ntw timestamp\n");
	buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean];
	printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n",
		0, tx_ring->next_to_use, tx_ring->next_to_clean,
227
		(unsigned long long)buffer_info->dma,
228 229
		buffer_info->length,
		buffer_info->next_to_watch,
230
		(unsigned long long)buffer_info->time_stamp);
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281

	/* Print TX Rings */
	if (!netif_msg_tx_done(adapter))
		goto rx_ring_summary;

	dev_info(&adapter->pdev->dev, "TX Rings Dump\n");

	/* Transmit Descriptor Formats - DEXT[29] is 0 (Legacy) or 1 (Extended)
	 *
	 * Legacy Transmit Descriptor
	 *   +--------------------------------------------------------------+
	 * 0 |         Buffer Address [63:0] (Reserved on Write Back)       |
	 *   +--------------------------------------------------------------+
	 * 8 | Special  |    CSS     | Status |  CMD    |  CSO   |  Length  |
	 *   +--------------------------------------------------------------+
	 *   63       48 47        36 35    32 31     24 23    16 15        0
	 *
	 * Extended Context Descriptor (DTYP=0x0) for TSO or checksum offload
	 *   63      48 47    40 39       32 31             16 15    8 7      0
	 *   +----------------------------------------------------------------+
	 * 0 |  TUCSE  | TUCS0  |   TUCSS   |     IPCSE       | IPCS0 | IPCSS |
	 *   +----------------------------------------------------------------+
	 * 8 |   MSS   | HDRLEN | RSV | STA | TUCMD | DTYP |      PAYLEN      |
	 *   +----------------------------------------------------------------+
	 *   63      48 47    40 39 36 35 32 31   24 23  20 19                0
	 *
	 * Extended Data Descriptor (DTYP=0x1)
	 *   +----------------------------------------------------------------+
	 * 0 |                     Buffer Address [63:0]                      |
	 *   +----------------------------------------------------------------+
	 * 8 | VLAN tag |  POPTS  | Rsvd | Status | Command | DTYP |  DTALEN  |
	 *   +----------------------------------------------------------------+
	 *   63       48 47     40 39  36 35    32 31     24 23  20 19        0
	 */
	printk(KERN_INFO "Tl[desc]     [address 63:0  ] [SpeCssSCmCsLen]"
		" [bi->dma       ] leng  ntw timestamp        bi->skb "
		"<-- Legacy format\n");
	printk(KERN_INFO "Tc[desc]     [Ce CoCsIpceCoS] [MssHlRSCm0Plen]"
		" [bi->dma       ] leng  ntw timestamp        bi->skb "
		"<-- Ext Context format\n");
	printk(KERN_INFO "Td[desc]     [address 63:0  ] [VlaPoRSCm1Dlen]"
		" [bi->dma       ] leng  ntw timestamp        bi->skb "
		"<-- Ext Data format\n");
	for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
		tx_desc = E1000_TX_DESC(*tx_ring, i);
		buffer_info = &tx_ring->buffer_info[i];
		u0 = (struct my_u0 *)tx_desc;
		printk(KERN_INFO "T%c[0x%03X]    %016llX %016llX %016llX "
			"%04X  %3X %016llX %p",
		       (!(le64_to_cpu(u0->b) & (1<<29)) ? 'l' :
			((le64_to_cpu(u0->b) & (1<<20)) ? 'd' : 'c')), i,
282 283 284 285 286
		       (unsigned long long)le64_to_cpu(u0->a),
		       (unsigned long long)le64_to_cpu(u0->b),
		       (unsigned long long)buffer_info->dma,
		       buffer_info->length, buffer_info->next_to_watch,
		       (unsigned long long)buffer_info->time_stamp,
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
		       buffer_info->skb);
		if (i == tx_ring->next_to_use && i == tx_ring->next_to_clean)
			printk(KERN_CONT " NTC/U\n");
		else if (i == tx_ring->next_to_use)
			printk(KERN_CONT " NTU\n");
		else if (i == tx_ring->next_to_clean)
			printk(KERN_CONT " NTC\n");
		else
			printk(KERN_CONT "\n");

		if (netif_msg_pktdata(adapter) && buffer_info->dma != 0)
			print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS,
					16, 1, phys_to_virt(buffer_info->dma),
					buffer_info->length, true);
	}

	/* Print RX Rings Summary */
rx_ring_summary:
	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
	printk(KERN_INFO "Queue [NTU] [NTC]\n");
	printk(KERN_INFO " %5d %5X %5X\n", 0,
		rx_ring->next_to_use, rx_ring->next_to_clean);

	/* Print RX Rings */
	if (!netif_msg_rx_status(adapter))
		goto exit;

	dev_info(&adapter->pdev->dev, "RX Rings Dump\n");
	switch (adapter->rx_ps_pages) {
	case 1:
	case 2:
	case 3:
		/* [Extended] Packet Split Receive Descriptor Format
		 *
		 *    +-----------------------------------------------------+
		 *  0 |                Buffer Address 0 [63:0]              |
		 *    +-----------------------------------------------------+
		 *  8 |                Buffer Address 1 [63:0]              |
		 *    +-----------------------------------------------------+
		 * 16 |                Buffer Address 2 [63:0]              |
		 *    +-----------------------------------------------------+
		 * 24 |                Buffer Address 3 [63:0]              |
		 *    +-----------------------------------------------------+
		 */
		printk(KERN_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");
		/* [Extended] Receive Descriptor (Write-Back) Format
		 *
		 *   63       48 47    32 31     13 12    8 7    4 3        0
		 *   +------------------------------------------------------+
		 * 0 | Packet   | IP     |  Rsvd   | MRQ   | Rsvd | MRQ RSS |
		 *   | Checksum | Ident  |         | Queue |      |  Type   |
		 *   +------------------------------------------------------+
		 * 8 | VLAN Tag | Length | Extended Error | Extended Status |
		 *   +------------------------------------------------------+
		 *   63       48 47    32 31            20 19               0
		 */
		printk(KERN_INFO "RWB[desc]      [ck ipid mrqhsh] "
			"[vl   l0 ee  es] "
		       "[ l3  l2  l1 hs] [reserved      ] ---------------- "
		       "[bi->skb] <-- Ext Rx Write-Back format\n");
		for (i = 0; i < rx_ring->count; i++) {
			buffer_info = &rx_ring->buffer_info[i];
			rx_desc_ps = E1000_RX_DESC_PS(*rx_ring, i);
			u1 = (struct my_u1 *)rx_desc_ps;
			staterr =
				le32_to_cpu(rx_desc_ps->wb.middle.status_error);
			if (staterr & E1000_RXD_STAT_DD) {
				/* Descriptor Done */
				printk(KERN_INFO "RWB[0x%03X]     %016llX "
					"%016llX %016llX %016llX "
					"---------------- %p", i,
361 362 363 364
					(unsigned long long)le64_to_cpu(u1->a),
					(unsigned long long)le64_to_cpu(u1->b),
					(unsigned long long)le64_to_cpu(u1->c),
					(unsigned long long)le64_to_cpu(u1->d),
365 366 367 368
					buffer_info->skb);
			} else {
				printk(KERN_INFO "R  [0x%03X]     %016llX "
					"%016llX %016llX %016llX %016llX %p", i,
369 370 371 372 373
					(unsigned long long)le64_to_cpu(u1->a),
					(unsigned long long)le64_to_cpu(u1->b),
					(unsigned long long)le64_to_cpu(u1->c),
					(unsigned long long)le64_to_cpu(u1->d),
					(unsigned long long)buffer_info->dma,
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
					buffer_info->skb);

				if (netif_msg_pktdata(adapter))
					print_hex_dump(KERN_INFO, "",
						DUMP_PREFIX_ADDRESS, 16, 1,
						phys_to_virt(buffer_info->dma),
						adapter->rx_ps_bsize0, true);
			}

			if (i == rx_ring->next_to_use)
				printk(KERN_CONT " NTU\n");
			else if (i == rx_ring->next_to_clean)
				printk(KERN_CONT " NTC\n");
			else
				printk(KERN_CONT "\n");
		}
		break;
	default:
	case 0:
		/* Legacy Receive Descriptor Format
		 *
		 * +-----------------------------------------------------+
		 * |                Buffer Address [63:0]                |
		 * +-----------------------------------------------------+
		 * | VLAN Tag | Errors | Status 0 | Packet csum | Length |
		 * +-----------------------------------------------------+
		 * 63       48 47    40 39      32 31         16 15      0
		 */
		printk(KERN_INFO "Rl[desc]     [address 63:0  ] "
			"[vl er S cks ln] [bi->dma       ] [bi->skb] "
			"<-- Legacy format\n");
		for (i = 0; rx_ring->desc && (i < rx_ring->count); i++) {
			rx_desc = E1000_RX_DESC(*rx_ring, i);
			buffer_info = &rx_ring->buffer_info[i];
			u0 = (struct my_u0 *)rx_desc;
			printk(KERN_INFO "Rl[0x%03X]    %016llX %016llX "
410 411 412 413 414
				"%016llX %p", i,
				(unsigned long long)le64_to_cpu(u0->a),
				(unsigned long long)le64_to_cpu(u0->b),
				(unsigned long long)buffer_info->dma,
				buffer_info->skb);
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
			if (i == rx_ring->next_to_use)
				printk(KERN_CONT " NTU\n");
			else if (i == rx_ring->next_to_clean)
				printk(KERN_CONT " NTC\n");
			else
				printk(KERN_CONT "\n");

			if (netif_msg_pktdata(adapter))
				print_hex_dump(KERN_INFO, "",
					DUMP_PREFIX_ADDRESS,
					16, 1, phys_to_virt(buffer_info->dma),
					adapter->rx_buffer_len, true);
		}
	}

exit:
	return;
}

434 435 436 437 438 439 440 441 442 443 444 445
/**
 * e1000_desc_unused - calculate if we have unused descriptors
 **/
static int e1000_desc_unused(struct e1000_ring *ring)
{
	if (ring->next_to_clean > ring->next_to_use)
		return ring->next_to_clean - ring->next_to_use - 1;

	return ring->count + ring->next_to_clean - ring->next_to_use - 1;
}

/**
446
 * e1000_receive_skb - helper function to handle Rx indications
447 448 449 450 451 452 453 454
 * @adapter: board private structure
 * @status: descriptor status field as written by hardware
 * @vlan: descriptor vlan field as written by hardware (no le/be conversion)
 * @skb: pointer to sk_buff to be indicated to stack
 **/
static void e1000_receive_skb(struct e1000_adapter *adapter,
			      struct net_device *netdev,
			      struct sk_buff *skb,
A
Al Viro 已提交
455
			      u8 status, __le16 vlan)
456 457 458 459
{
	skb->protocol = eth_type_trans(skb, netdev);

	if (adapter->vlgrp && (status & E1000_RXD_STAT_VP))
H
Herbert Xu 已提交
460 461
		vlan_gro_receive(&adapter->napi, adapter->vlgrp,
				 le16_to_cpu(vlan), skb);
462
	else
H
Herbert Xu 已提交
463
		napi_gro_receive(&adapter->napi, skb);
464 465 466 467 468 469 470 471 472 473 474 475 476 477
}

/**
 * e1000_rx_checksum - Receive Checksum Offload for 82543
 * @adapter:     board private structure
 * @status_err:  receive descriptor status and error fields
 * @csum:	receive descriptor csum field
 * @sk_buff:     socket buffer with received data
 **/
static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
			      u32 csum, struct sk_buff *skb)
{
	u16 status = (u16)status_err;
	u8 errors = (u8)(status_err >> 24);
478 479

	skb_checksum_none_assert(skb);
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499

	/* Ignore Checksum bit is set */
	if (status & E1000_RXD_STAT_IXSM)
		return;
	/* TCP/UDP checksum error bit is set */
	if (errors & E1000_RXD_ERR_TCPE) {
		/* let the stack verify checksum errors */
		adapter->hw_csum_err++;
		return;
	}

	/* TCP/UDP Checksum has not been calculated */
	if (!(status & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS)))
		return;

	/* It must be a TCP or UDP packet with a valid checksum */
	if (status & E1000_RXD_STAT_TCPCS) {
		/* TCP checksum is good */
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else {
500 501 502
		/*
		 * IP fragment with UDP payload
		 * Hardware complements the payload checksum, so we undo it
503 504
		 * and then put the value in host order for further stack use.
		 */
A
Al Viro 已提交
505 506
		__sum16 sum = (__force __sum16)htons(csum);
		skb->csum = csum_unfold(~sum);
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525
		skb->ip_summed = CHECKSUM_COMPLETE;
	}
	adapter->hw_csum_good++;
}

/**
 * e1000_alloc_rx_buffers - Replace used receive buffers; legacy & extended
 * @adapter: address of board private structure
 **/
static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
				   int cleaned_count)
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_rx_desc *rx_desc;
	struct e1000_buffer *buffer_info;
	struct sk_buff *skb;
	unsigned int i;
526
	unsigned int bufsz = adapter->rx_buffer_len;
527 528 529 530 531 532 533 534 535 536 537

	i = rx_ring->next_to_use;
	buffer_info = &rx_ring->buffer_info[i];

	while (cleaned_count--) {
		skb = buffer_info->skb;
		if (skb) {
			skb_trim(skb, 0);
			goto map_skb;
		}

538
		skb = netdev_alloc_skb_ip_align(netdev, bufsz);
539 540 541 542 543 544 545 546
		if (!skb) {
			/* Better luck next round */
			adapter->alloc_rx_buff_failed++;
			break;
		}

		buffer_info->skb = skb;
map_skb:
547
		buffer_info->dma = dma_map_single(&pdev->dev, skb->data,
548
						  adapter->rx_buffer_len,
549 550
						  DMA_FROM_DEVICE);
		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
551 552 553 554 555 556 557 558
			dev_err(&pdev->dev, "RX DMA map failed\n");
			adapter->rx_dma_failed++;
			break;
		}

		rx_desc = E1000_RX_DESC(*rx_ring, i);
		rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);

559 560 561 562 563 564 565 566 567 568
		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
			/*
			 * Force memory writes to complete before letting h/w
			 * know there are new descriptors to fetch.  (Only
			 * applicable for weak-ordered memory model archs,
			 * such as IA-64).
			 */
			wmb();
			writel(i, adapter->hw.hw_addr + rx_ring->tail);
		}
569 570 571 572 573 574
		i++;
		if (i == rx_ring->count)
			i = 0;
		buffer_info = &rx_ring->buffer_info[i];
	}

575
	rx_ring->next_to_use = i;
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
}

/**
 * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split
 * @adapter: address of board private structure
 **/
static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter,
				      int cleaned_count)
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	union e1000_rx_desc_packet_split *rx_desc;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_buffer *buffer_info;
	struct e1000_ps_page *ps_page;
	struct sk_buff *skb;
	unsigned int i, j;

	i = rx_ring->next_to_use;
	buffer_info = &rx_ring->buffer_info[i];

	while (cleaned_count--) {
		rx_desc = E1000_RX_DESC_PS(*rx_ring, i);

		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
A
Auke Kok 已提交
601 602 603
			ps_page = &buffer_info->ps_pages[j];
			if (j >= adapter->rx_ps_pages) {
				/* all unused desc entries get hw null ptr */
A
Al Viro 已提交
604
				rx_desc->read.buffer_addr[j+1] = ~cpu_to_le64(0);
A
Auke Kok 已提交
605 606 607 608
				continue;
			}
			if (!ps_page->page) {
				ps_page->page = alloc_page(GFP_ATOMIC);
609
				if (!ps_page->page) {
A
Auke Kok 已提交
610 611 612
					adapter->alloc_rx_buff_failed++;
					goto no_buffers;
				}
613 614 615 616 617 618
				ps_page->dma = dma_map_page(&pdev->dev,
							    ps_page->page,
							    0, PAGE_SIZE,
							    DMA_FROM_DEVICE);
				if (dma_mapping_error(&pdev->dev,
						      ps_page->dma)) {
A
Auke Kok 已提交
619 620 621 622
					dev_err(&adapter->pdev->dev,
					  "RX DMA page map failed\n");
					adapter->rx_dma_failed++;
					goto no_buffers;
623 624
				}
			}
A
Auke Kok 已提交
625 626 627 628 629 630 631
			/*
			 * Refresh the desc even if buffer_addrs
			 * didn't change because each write-back
			 * erases this info.
			 */
			rx_desc->read.buffer_addr[j+1] =
			     cpu_to_le64(ps_page->dma);
632 633
		}

634 635
		skb = netdev_alloc_skb_ip_align(netdev,
						adapter->rx_ps_bsize0);
636 637 638 639 640 641 642

		if (!skb) {
			adapter->alloc_rx_buff_failed++;
			break;
		}

		buffer_info->skb = skb;
643
		buffer_info->dma = dma_map_single(&pdev->dev, skb->data,
644
						  adapter->rx_ps_bsize0,
645 646
						  DMA_FROM_DEVICE);
		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
647 648 649 650 651 652 653 654 655 656
			dev_err(&pdev->dev, "RX DMA map failed\n");
			adapter->rx_dma_failed++;
			/* cleanup skb */
			dev_kfree_skb_any(skb);
			buffer_info->skb = NULL;
			break;
		}

		rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma);

657 658 659 660 661 662 663 664 665 666 667
		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
			/*
			 * Force memory writes to complete before letting h/w
			 * know there are new descriptors to fetch.  (Only
			 * applicable for weak-ordered memory model archs,
			 * such as IA-64).
			 */
			wmb();
			writel(i<<1, adapter->hw.hw_addr + rx_ring->tail);
		}

668 669 670 671 672 673 674
		i++;
		if (i == rx_ring->count)
			i = 0;
		buffer_info = &rx_ring->buffer_info[i];
	}

no_buffers:
675
	rx_ring->next_to_use = i;
676 677
}

678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
/**
 * e1000_alloc_jumbo_rx_buffers - Replace used jumbo receive buffers
 * @adapter: address of board private structure
 * @cleaned_count: number of buffers to allocate this pass
 **/

static void e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter,
                                         int cleaned_count)
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_rx_desc *rx_desc;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_buffer *buffer_info;
	struct sk_buff *skb;
	unsigned int i;
694
	unsigned int bufsz = 256 - 16 /* for skb_reserve */;
695 696 697 698 699 700 701 702 703 704 705

	i = rx_ring->next_to_use;
	buffer_info = &rx_ring->buffer_info[i];

	while (cleaned_count--) {
		skb = buffer_info->skb;
		if (skb) {
			skb_trim(skb, 0);
			goto check_page;
		}

706
		skb = netdev_alloc_skb_ip_align(netdev, bufsz);
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724
		if (unlikely(!skb)) {
			/* Better luck next round */
			adapter->alloc_rx_buff_failed++;
			break;
		}

		buffer_info->skb = skb;
check_page:
		/* allocate a new page if necessary */
		if (!buffer_info->page) {
			buffer_info->page = alloc_page(GFP_ATOMIC);
			if (unlikely(!buffer_info->page)) {
				adapter->alloc_rx_buff_failed++;
				break;
			}
		}

		if (!buffer_info->dma)
725
			buffer_info->dma = dma_map_page(&pdev->dev,
726 727
			                                buffer_info->page, 0,
			                                PAGE_SIZE,
728
							DMA_FROM_DEVICE);
729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751

		rx_desc = E1000_RX_DESC(*rx_ring, i);
		rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);

		if (unlikely(++i == rx_ring->count))
			i = 0;
		buffer_info = &rx_ring->buffer_info[i];
	}

	if (likely(rx_ring->next_to_use != i)) {
		rx_ring->next_to_use = i;
		if (unlikely(i-- == 0))
			i = (rx_ring->count - 1);

		/* Force memory writes to complete before letting h/w
		 * know there are new descriptors to fetch.  (Only
		 * applicable for weak-ordered memory model archs,
		 * such as IA-64). */
		wmb();
		writel(i, adapter->hw.hw_addr + rx_ring->tail);
	}
}

752 753 754 755 756 757 758 759 760 761 762 763
/**
 * e1000_clean_rx_irq - Send received data up the network stack; legacy
 * @adapter: board private structure
 *
 * the return value indicates whether actual cleaning was done, there
 * is no guarantee that everything was cleaned
 **/
static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
			       int *work_done, int work_to_do)
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
764
	struct e1000_hw *hw = &adapter->hw;
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_rx_desc *rx_desc, *next_rxd;
	struct e1000_buffer *buffer_info, *next_buffer;
	u32 length;
	unsigned int i;
	int cleaned_count = 0;
	bool cleaned = 0;
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;

	i = rx_ring->next_to_clean;
	rx_desc = E1000_RX_DESC(*rx_ring, i);
	buffer_info = &rx_ring->buffer_info[i];

	while (rx_desc->status & E1000_RXD_STAT_DD) {
		struct sk_buff *skb;
		u8 status;

		if (*work_done >= work_to_do)
			break;
		(*work_done)++;
785
		rmb();	/* read descriptor and rx_buffer_info after status DD */
786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802

		status = rx_desc->status;
		skb = buffer_info->skb;
		buffer_info->skb = NULL;

		prefetch(skb->data - NET_IP_ALIGN);

		i++;
		if (i == rx_ring->count)
			i = 0;
		next_rxd = E1000_RX_DESC(*rx_ring, i);
		prefetch(next_rxd);

		next_buffer = &rx_ring->buffer_info[i];

		cleaned = 1;
		cleaned_count++;
803
		dma_unmap_single(&pdev->dev,
804 805
				 buffer_info->dma,
				 adapter->rx_buffer_len,
806
				 DMA_FROM_DEVICE);
807 808 809 810
		buffer_info->dma = 0;

		length = le16_to_cpu(rx_desc->length);

811 812 813 814 815 816 817 818 819 820 821
		/*
		 * !EOP means multiple descriptors were used to store a single
		 * packet, if that's the case we need to toss it.  In fact, we
		 * need to toss every packet with the EOP bit clear and the
		 * next frame that _does_ have the EOP bit set, as it is by
		 * definition only a frame fragment
		 */
		if (unlikely(!(status & E1000_RXD_STAT_EOP)))
			adapter->flags2 |= FLAG2_IS_DISCARDING;

		if (adapter->flags2 & FLAG2_IS_DISCARDING) {
822
			/* All receives must fit into a single buffer */
823
			e_dbg("Receive packet consumed multiple buffers\n");
824 825
			/* recycle */
			buffer_info->skb = skb;
826 827
			if (status & E1000_RXD_STAT_EOP)
				adapter->flags2 &= ~FLAG2_IS_DISCARDING;
828 829 830 831 832 833 834 835 836
			goto next_desc;
		}

		if (rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK) {
			/* recycle */
			buffer_info->skb = skb;
			goto next_desc;
		}

J
Jeff Kirsher 已提交
837 838 839 840
		/* adjust length to remove Ethernet CRC */
		if (!(adapter->flags2 & FLAG2_CRC_STRIPPING))
			length -= 4;

841 842 843
		total_rx_bytes += length;
		total_rx_packets++;

844 845
		/*
		 * code added for copybreak, this should improve
846
		 * performance for small packets with large amounts
847 848
		 * of reassembly being done in the stack
		 */
849 850
		if (length < copybreak) {
			struct sk_buff *new_skb =
851
			    netdev_alloc_skb_ip_align(netdev, length);
852
			if (new_skb) {
853 854 855 856 857 858
				skb_copy_to_linear_data_offset(new_skb,
							       -NET_IP_ALIGN,
							       (skb->data -
								NET_IP_ALIGN),
							       (length +
								NET_IP_ALIGN));
859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895
				/* save the skb in buffer_info as good */
				buffer_info->skb = skb;
				skb = new_skb;
			}
			/* else just continue with the old one */
		}
		/* end copybreak code */
		skb_put(skb, length);

		/* Receive Checksum Offload */
		e1000_rx_checksum(adapter,
				  (u32)(status) |
				  ((u32)(rx_desc->errors) << 24),
				  le16_to_cpu(rx_desc->csum), skb);

		e1000_receive_skb(adapter, netdev, skb,status,rx_desc->special);

next_desc:
		rx_desc->status = 0;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= E1000_RX_BUFFER_WRITE) {
			adapter->alloc_rx_buf(adapter, cleaned_count);
			cleaned_count = 0;
		}

		/* use prefetched values */
		rx_desc = next_rxd;
		buffer_info = next_buffer;
	}
	rx_ring->next_to_clean = i;

	cleaned_count = e1000_desc_unused(rx_ring);
	if (cleaned_count)
		adapter->alloc_rx_buf(adapter, cleaned_count);

	adapter->total_rx_bytes += total_rx_bytes;
896
	adapter->total_rx_packets += total_rx_packets;
897 898
	netdev->stats.rx_bytes += total_rx_bytes;
	netdev->stats.rx_packets += total_rx_packets;
899 900 901 902 903 904
	return cleaned;
}

static void e1000_put_txbuf(struct e1000_adapter *adapter,
			     struct e1000_buffer *buffer_info)
{
905 906
	if (buffer_info->dma) {
		if (buffer_info->mapped_as_page)
907 908
			dma_unmap_page(&adapter->pdev->dev, buffer_info->dma,
				       buffer_info->length, DMA_TO_DEVICE);
909
		else
910 911
			dma_unmap_single(&adapter->pdev->dev, buffer_info->dma,
					 buffer_info->length, DMA_TO_DEVICE);
912 913
		buffer_info->dma = 0;
	}
914 915 916 917
	if (buffer_info->skb) {
		dev_kfree_skb_any(buffer_info->skb);
		buffer_info->skb = NULL;
	}
918
	buffer_info->time_stamp = 0;
919 920
}

921
static void e1000_print_hw_hang(struct work_struct *work)
922
{
923 924 925
	struct e1000_adapter *adapter = container_of(work,
	                                             struct e1000_adapter,
	                                             print_hang_task);
926 927 928 929
	struct e1000_ring *tx_ring = adapter->tx_ring;
	unsigned int i = tx_ring->next_to_clean;
	unsigned int eop = tx_ring->buffer_info[i].next_to_watch;
	struct e1000_tx_desc *eop_desc = E1000_TX_DESC(*tx_ring, eop);
930 931 932 933 934 935 936
	struct e1000_hw *hw = &adapter->hw;
	u16 phy_status, phy_1000t_status, phy_ext_status;
	u16 pci_status;

	e1e_rphy(hw, PHY_STATUS, &phy_status);
	e1e_rphy(hw, PHY_1000T_STATUS, &phy_1000t_status);
	e1e_rphy(hw, PHY_EXT_STATUS, &phy_ext_status);
937

938 939 940 941
	pci_read_config_word(adapter->pdev, PCI_STATUS, &pci_status);

	/* detected Hardware unit hang */
	e_err("Detected Hardware Unit Hang:\n"
942 943 944 945 946 947 948 949
	      "  TDH                  <%x>\n"
	      "  TDT                  <%x>\n"
	      "  next_to_use          <%x>\n"
	      "  next_to_clean        <%x>\n"
	      "buffer_info[next_to_clean]:\n"
	      "  time_stamp           <%lx>\n"
	      "  next_to_watch        <%x>\n"
	      "  jiffies              <%lx>\n"
950 951 952 953 954 955
	      "  next_to_watch.status <%x>\n"
	      "MAC Status             <%x>\n"
	      "PHY Status             <%x>\n"
	      "PHY 1000BASE-T Status  <%x>\n"
	      "PHY Extended Status    <%x>\n"
	      "PCI Status             <%x>\n",
956 957 958 959 960 961 962
	      readl(adapter->hw.hw_addr + tx_ring->head),
	      readl(adapter->hw.hw_addr + tx_ring->tail),
	      tx_ring->next_to_use,
	      tx_ring->next_to_clean,
	      tx_ring->buffer_info[eop].time_stamp,
	      eop,
	      jiffies,
963 964 965 966 967 968
	      eop_desc->upper.fields.status,
	      er32(STATUS),
	      phy_status,
	      phy_1000t_status,
	      phy_ext_status,
	      pci_status);
969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992
}

/**
 * e1000_clean_tx_irq - Reclaim resources after transmit completes
 * @adapter: board private structure
 *
 * the return value indicates whether actual cleaning was done, there
 * is no guarantee that everything was cleaned
 **/
static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_tx_desc *tx_desc, *eop_desc;
	struct e1000_buffer *buffer_info;
	unsigned int i, eop;
	unsigned int count = 0;
	unsigned int total_tx_bytes = 0, total_tx_packets = 0;

	i = tx_ring->next_to_clean;
	eop = tx_ring->buffer_info[i].next_to_watch;
	eop_desc = E1000_TX_DESC(*tx_ring, eop);

993 994
	while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) &&
	       (count < tx_ring->count)) {
995
		bool cleaned = false;
996
		rmb(); /* read buffer_info after eop_desc */
997
		for (; !cleaned; count++) {
998 999 1000 1001 1002
			tx_desc = E1000_TX_DESC(*tx_ring, i);
			buffer_info = &tx_ring->buffer_info[i];
			cleaned = (i == eop);

			if (cleaned) {
1003 1004
				total_tx_packets += buffer_info->segs;
				total_tx_bytes += buffer_info->bytecount;
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
			}

			e1000_put_txbuf(adapter, buffer_info);
			tx_desc->upper.data = 0;

			i++;
			if (i == tx_ring->count)
				i = 0;
		}

1015 1016
		if (i == tx_ring->next_to_use)
			break;
1017 1018 1019 1020 1021 1022 1023
		eop = tx_ring->buffer_info[i].next_to_watch;
		eop_desc = E1000_TX_DESC(*tx_ring, eop);
	}

	tx_ring->next_to_clean = i;

#define TX_WAKE_THRESHOLD 32
1024 1025
	if (count && netif_carrier_ok(netdev) &&
	    e1000_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD) {
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
		/* Make sure that anybody stopping the queue after this
		 * sees the new next_to_clean.
		 */
		smp_mb();

		if (netif_queue_stopped(netdev) &&
		    !(test_bit(__E1000_DOWN, &adapter->state))) {
			netif_wake_queue(netdev);
			++adapter->restart_queue;
		}
	}

	if (adapter->detect_tx_hung) {
1039 1040 1041 1042
		/*
		 * Detect a transmit hang in hardware, this serializes the
		 * check with the clearing of time_stamp and movement of i
		 */
1043
		adapter->detect_tx_hung = 0;
1044 1045
		if (tx_ring->buffer_info[i].time_stamp &&
		    time_after(jiffies, tx_ring->buffer_info[i].time_stamp
1046 1047
			       + (adapter->tx_timeout_factor * HZ)) &&
		    !(er32(STATUS) & E1000_STATUS_TXOFF)) {
1048
			schedule_work(&adapter->print_hang_task);
1049 1050 1051 1052 1053
			netif_stop_queue(netdev);
		}
	}
	adapter->total_tx_bytes += total_tx_bytes;
	adapter->total_tx_packets += total_tx_packets;
1054 1055
	netdev->stats.tx_bytes += total_tx_bytes;
	netdev->stats.tx_packets += total_tx_packets;
1056
	return count < tx_ring->count;
1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068
}

/**
 * e1000_clean_rx_irq_ps - Send received data up the network stack; packet split
 * @adapter: board private structure
 *
 * the return value indicates whether actual cleaning was done, there
 * is no guarantee that everything was cleaned
 **/
static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter,
				  int *work_done, int work_to_do)
{
1069
	struct e1000_hw *hw = &adapter->hw;
1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
	union e1000_rx_desc_packet_split *rx_desc, *next_rxd;
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_buffer *buffer_info, *next_buffer;
	struct e1000_ps_page *ps_page;
	struct sk_buff *skb;
	unsigned int i, j;
	u32 length, staterr;
	int cleaned_count = 0;
	bool cleaned = 0;
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;

	i = rx_ring->next_to_clean;
	rx_desc = E1000_RX_DESC_PS(*rx_ring, i);
	staterr = le32_to_cpu(rx_desc->wb.middle.status_error);
	buffer_info = &rx_ring->buffer_info[i];

	while (staterr & E1000_RXD_STAT_DD) {
		if (*work_done >= work_to_do)
			break;
		(*work_done)++;
		skb = buffer_info->skb;
1093
		rmb();	/* read descriptor and rx_buffer_info after status DD */
1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107

		/* in the packet split case this is header only */
		prefetch(skb->data - NET_IP_ALIGN);

		i++;
		if (i == rx_ring->count)
			i = 0;
		next_rxd = E1000_RX_DESC_PS(*rx_ring, i);
		prefetch(next_rxd);

		next_buffer = &rx_ring->buffer_info[i];

		cleaned = 1;
		cleaned_count++;
1108
		dma_unmap_single(&pdev->dev, buffer_info->dma,
1109
				 adapter->rx_ps_bsize0,
1110
				 DMA_FROM_DEVICE);
1111 1112
		buffer_info->dma = 0;

1113 1114 1115 1116 1117
		/* see !EOP comment in other rx routine */
		if (!(staterr & E1000_RXD_STAT_EOP))
			adapter->flags2 |= FLAG2_IS_DISCARDING;

		if (adapter->flags2 & FLAG2_IS_DISCARDING) {
1118 1119
			e_dbg("Packet Split buffers didn't pick up the full "
			      "packet\n");
1120
			dev_kfree_skb_irq(skb);
1121 1122
			if (staterr & E1000_RXD_STAT_EOP)
				adapter->flags2 &= ~FLAG2_IS_DISCARDING;
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
			goto next_desc;
		}

		if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) {
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

		length = le16_to_cpu(rx_desc->wb.middle.length0);

		if (!length) {
1134 1135
			e_dbg("Last part of the packet spanning multiple "
			      "descriptors\n");
1136 1137 1138 1139 1140 1141 1142 1143
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

		/* Good Receive */
		skb_put(skb, length);

		{
1144 1145 1146 1147
		/*
		 * this looks ugly, but it seems compiler issues make it
		 * more efficient than reusing j
		 */
1148 1149
		int l1 = le16_to_cpu(rx_desc->wb.upper.length[0]);

1150 1151 1152 1153 1154
		/*
		 * page alloc/put takes too long and effects small packet
		 * throughput, so unsplit small packets and save the alloc/put
		 * only valid in softirq (napi) context to call kmap_*
		 */
1155 1156 1157 1158
		if (l1 && (l1 <= copybreak) &&
		    ((length + l1) <= adapter->rx_ps_bsize0)) {
			u8 *vaddr;

A
Auke Kok 已提交
1159
			ps_page = &buffer_info->ps_pages[0];
1160

1161 1162
			/*
			 * there is no documentation about how to call
1163
			 * kmap_atomic, so we can't hold the mapping
1164 1165
			 * very long
			 */
1166 1167
			dma_sync_single_for_cpu(&pdev->dev, ps_page->dma,
						PAGE_SIZE, DMA_FROM_DEVICE);
1168 1169 1170
			vaddr = kmap_atomic(ps_page->page, KM_SKB_DATA_SOFTIRQ);
			memcpy(skb_tail_pointer(skb), vaddr, l1);
			kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ);
1171 1172
			dma_sync_single_for_device(&pdev->dev, ps_page->dma,
						   PAGE_SIZE, DMA_FROM_DEVICE);
A
Auke Kok 已提交
1173

J
Jeff Kirsher 已提交
1174 1175 1176 1177
			/* remove the CRC */
			if (!(adapter->flags2 & FLAG2_CRC_STRIPPING))
				l1 -= 4;

1178 1179 1180 1181 1182 1183 1184 1185 1186 1187
			skb_put(skb, l1);
			goto copydone;
		} /* if */
		}

		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
			length = le16_to_cpu(rx_desc->wb.upper.length[j]);
			if (!length)
				break;

A
Auke Kok 已提交
1188
			ps_page = &buffer_info->ps_pages[j];
1189 1190
			dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE,
				       DMA_FROM_DEVICE);
1191 1192 1193 1194 1195 1196 1197 1198
			ps_page->dma = 0;
			skb_fill_page_desc(skb, j, ps_page->page, 0, length);
			ps_page->page = NULL;
			skb->len += length;
			skb->data_len += length;
			skb->truesize += length;
		}

J
Jeff Kirsher 已提交
1199 1200 1201 1202 1203 1204
		/* strip the ethernet crc, problem is we're using pages now so
		 * this whole operation can get a little cpu intensive
		 */
		if (!(adapter->flags2 & FLAG2_CRC_STRIPPING))
			pskb_trim(skb, skb->len - 4);

1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
copydone:
		total_rx_bytes += skb->len;
		total_rx_packets++;

		e1000_rx_checksum(adapter, staterr, le16_to_cpu(
			rx_desc->wb.lower.hi_dword.csum_ip.csum), skb);

		if (rx_desc->wb.upper.header_status &
			   cpu_to_le16(E1000_RXDPS_HDRSTAT_HDRSP))
			adapter->rx_hdr_split++;

		e1000_receive_skb(adapter, netdev, skb,
				  staterr, rx_desc->wb.middle.vlan);

next_desc:
		rx_desc->wb.middle.status_error &= cpu_to_le32(~0xFF);
		buffer_info->skb = NULL;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= E1000_RX_BUFFER_WRITE) {
			adapter->alloc_rx_buf(adapter, cleaned_count);
			cleaned_count = 0;
		}

		/* use prefetched values */
		rx_desc = next_rxd;
		buffer_info = next_buffer;

		staterr = le32_to_cpu(rx_desc->wb.middle.status_error);
	}
	rx_ring->next_to_clean = i;

	cleaned_count = e1000_desc_unused(rx_ring);
	if (cleaned_count)
		adapter->alloc_rx_buf(adapter, cleaned_count);

	adapter->total_rx_bytes += total_rx_bytes;
1242
	adapter->total_rx_packets += total_rx_packets;
1243 1244
	netdev->stats.rx_bytes += total_rx_bytes;
	netdev->stats.rx_packets += total_rx_packets;
1245 1246 1247
	return cleaned;
}

1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292
/**
 * e1000_consume_page - helper function
 **/
static void e1000_consume_page(struct e1000_buffer *bi, struct sk_buff *skb,
                               u16 length)
{
	bi->page = NULL;
	skb->len += length;
	skb->data_len += length;
	skb->truesize += length;
}

/**
 * e1000_clean_jumbo_rx_irq - Send received data up the network stack; legacy
 * @adapter: board private structure
 *
 * the return value indicates whether actual cleaning was done, there
 * is no guarantee that everything was cleaned
 **/

static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
                                     int *work_done, int work_to_do)
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_rx_desc *rx_desc, *next_rxd;
	struct e1000_buffer *buffer_info, *next_buffer;
	u32 length;
	unsigned int i;
	int cleaned_count = 0;
	bool cleaned = false;
	unsigned int total_rx_bytes=0, total_rx_packets=0;

	i = rx_ring->next_to_clean;
	rx_desc = E1000_RX_DESC(*rx_ring, i);
	buffer_info = &rx_ring->buffer_info[i];

	while (rx_desc->status & E1000_RXD_STAT_DD) {
		struct sk_buff *skb;
		u8 status;

		if (*work_done >= work_to_do)
			break;
		(*work_done)++;
1293
		rmb();	/* read descriptor and rx_buffer_info after status DD */
1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308

		status = rx_desc->status;
		skb = buffer_info->skb;
		buffer_info->skb = NULL;

		++i;
		if (i == rx_ring->count)
			i = 0;
		next_rxd = E1000_RX_DESC(*rx_ring, i);
		prefetch(next_rxd);

		next_buffer = &rx_ring->buffer_info[i];

		cleaned = true;
		cleaned_count++;
1309 1310
		dma_unmap_page(&pdev->dev, buffer_info->dma, PAGE_SIZE,
			       DMA_FROM_DEVICE);
1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
		buffer_info->dma = 0;

		length = le16_to_cpu(rx_desc->length);

		/* errors is only valid for DD + EOP descriptors */
		if (unlikely((status & E1000_RXD_STAT_EOP) &&
		    (rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK))) {
				/* recycle both page and skb */
				buffer_info->skb = skb;
				/* an error means any chain goes out the window
				 * too */
				if (rx_ring->rx_skb_top)
					dev_kfree_skb(rx_ring->rx_skb_top);
				rx_ring->rx_skb_top = NULL;
				goto next_desc;
		}

#define rxtop rx_ring->rx_skb_top
		if (!(status & E1000_RXD_STAT_EOP)) {
			/* this descriptor is only the beginning (or middle) */
			if (!rxtop) {
				/* this is the beginning of a chain */
				rxtop = skb;
				skb_fill_page_desc(rxtop, 0, buffer_info->page,
				                   0, length);
			} else {
				/* this is the middle of a chain */
				skb_fill_page_desc(rxtop,
				    skb_shinfo(rxtop)->nr_frags,
				    buffer_info->page, 0, length);
				/* re-use the skb, only consumed the page */
				buffer_info->skb = skb;
			}
			e1000_consume_page(buffer_info, rxtop, length);
			goto next_desc;
		} else {
			if (rxtop) {
				/* end of the chain */
				skb_fill_page_desc(rxtop,
				    skb_shinfo(rxtop)->nr_frags,
				    buffer_info->page, 0, length);
				/* re-use the current skb, we only consumed the
				 * page */
				buffer_info->skb = skb;
				skb = rxtop;
				rxtop = NULL;
				e1000_consume_page(buffer_info, skb, length);
			} else {
				/* no chain, got EOP, this buf is the packet
				 * copybreak to save the put_page/alloc_page */
				if (length <= copybreak &&
				    skb_tailroom(skb) >= length) {
					u8 *vaddr;
					vaddr = kmap_atomic(buffer_info->page,
					                   KM_SKB_DATA_SOFTIRQ);
					memcpy(skb_tail_pointer(skb), vaddr,
					       length);
					kunmap_atomic(vaddr,
					              KM_SKB_DATA_SOFTIRQ);
					/* re-use the page, so don't erase
					 * buffer_info->page */
					skb_put(skb, length);
				} else {
					skb_fill_page_desc(skb, 0,
					                   buffer_info->page, 0,
				                           length);
					e1000_consume_page(buffer_info, skb,
					                   length);
				}
			}
		}

		/* Receive Checksum Offload XXX recompute due to CRC strip? */
		e1000_rx_checksum(adapter,
		                  (u32)(status) |
		                  ((u32)(rx_desc->errors) << 24),
		                  le16_to_cpu(rx_desc->csum), skb);

		/* probably a little skewed due to removing CRC */
		total_rx_bytes += skb->len;
		total_rx_packets++;

		/* eth type trans needs skb->data to point to something */
		if (!pskb_may_pull(skb, ETH_HLEN)) {
1395
			e_err("pskb_may_pull failed.\n");
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423
			dev_kfree_skb(skb);
			goto next_desc;
		}

		e1000_receive_skb(adapter, netdev, skb, status,
		                  rx_desc->special);

next_desc:
		rx_desc->status = 0;

		/* return some buffers to hardware, one at a time is too slow */
		if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) {
			adapter->alloc_rx_buf(adapter, cleaned_count);
			cleaned_count = 0;
		}

		/* use prefetched values */
		rx_desc = next_rxd;
		buffer_info = next_buffer;
	}
	rx_ring->next_to_clean = i;

	cleaned_count = e1000_desc_unused(rx_ring);
	if (cleaned_count)
		adapter->alloc_rx_buf(adapter, cleaned_count);

	adapter->total_rx_bytes += total_rx_bytes;
	adapter->total_rx_packets += total_rx_packets;
1424 1425
	netdev->stats.rx_bytes += total_rx_bytes;
	netdev->stats.rx_packets += total_rx_packets;
1426 1427 1428
	return cleaned;
}

1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
/**
 * e1000_clean_rx_ring - Free Rx Buffers per Queue
 * @adapter: board private structure
 **/
static void e1000_clean_rx_ring(struct e1000_adapter *adapter)
{
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_buffer *buffer_info;
	struct e1000_ps_page *ps_page;
	struct pci_dev *pdev = adapter->pdev;
	unsigned int i, j;

	/* Free all the Rx ring sk_buffs */
	for (i = 0; i < rx_ring->count; i++) {
		buffer_info = &rx_ring->buffer_info[i];
		if (buffer_info->dma) {
			if (adapter->clean_rx == e1000_clean_rx_irq)
1446
				dma_unmap_single(&pdev->dev, buffer_info->dma,
1447
						 adapter->rx_buffer_len,
1448
						 DMA_FROM_DEVICE);
1449
			else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq)
1450
				dma_unmap_page(&pdev->dev, buffer_info->dma,
1451
				               PAGE_SIZE,
1452
					       DMA_FROM_DEVICE);
1453
			else if (adapter->clean_rx == e1000_clean_rx_irq_ps)
1454
				dma_unmap_single(&pdev->dev, buffer_info->dma,
1455
						 adapter->rx_ps_bsize0,
1456
						 DMA_FROM_DEVICE);
1457 1458 1459
			buffer_info->dma = 0;
		}

1460 1461 1462 1463 1464
		if (buffer_info->page) {
			put_page(buffer_info->page);
			buffer_info->page = NULL;
		}

1465 1466 1467 1468 1469 1470
		if (buffer_info->skb) {
			dev_kfree_skb(buffer_info->skb);
			buffer_info->skb = NULL;
		}

		for (j = 0; j < PS_PAGE_BUFFERS; j++) {
A
Auke Kok 已提交
1471
			ps_page = &buffer_info->ps_pages[j];
1472 1473
			if (!ps_page->page)
				break;
1474 1475
			dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE,
				       DMA_FROM_DEVICE);
1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492
			ps_page->dma = 0;
			put_page(ps_page->page);
			ps_page->page = NULL;
		}
	}

	/* there also may be some cached data from a chained receive */
	if (rx_ring->rx_skb_top) {
		dev_kfree_skb(rx_ring->rx_skb_top);
		rx_ring->rx_skb_top = NULL;
	}

	/* Zero out the descriptor ring */
	memset(rx_ring->desc, 0, rx_ring->size);

	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;
1493
	adapter->flags2 &= ~FLAG2_IS_DISCARDING;
1494 1495 1496 1497 1498

	writel(0, adapter->hw.hw_addr + rx_ring->head);
	writel(0, adapter->hw.hw_addr + rx_ring->tail);
}

1499 1500 1501 1502 1503 1504 1505 1506
static void e1000e_downshift_workaround(struct work_struct *work)
{
	struct e1000_adapter *adapter = container_of(work,
					struct e1000_adapter, downshift_task);

	e1000e_gig_downshift_workaround_ich8lan(&adapter->hw);
}

1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518
/**
 * e1000_intr_msi - Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t e1000_intr_msi(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 icr = er32(ICR);

1519 1520 1521
	/*
	 * read ICR disables interrupts using IAM
	 */
1522

1523
	if (icr & E1000_ICR_LSC) {
1524
		hw->mac.get_link_status = 1;
1525 1526 1527 1528
		/*
		 * ICH8 workaround-- Call gig speed drop workaround on cable
		 * disconnect (LSC) before accessing any PHY registers
		 */
1529 1530
		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
		    (!(er32(STATUS) & E1000_STATUS_LU)))
1531
			schedule_work(&adapter->downshift_task);
1532

1533 1534
		/*
		 * 80003ES2LAN workaround-- For packet buffer work-around on
1535
		 * link down event; disable receives here in the ISR and reset
1536 1537
		 * adapter in watchdog
		 */
1538 1539 1540 1541 1542
		if (netif_carrier_ok(netdev) &&
		    adapter->flags & FLAG_RX_NEEDS_RESTART) {
			/* disable receives */
			u32 rctl = er32(RCTL);
			ew32(RCTL, rctl & ~E1000_RCTL_EN);
1543
			adapter->flags |= FLAG_RX_RESTART_NOW;
1544 1545 1546 1547 1548 1549
		}
		/* guard against interrupt when we're going down */
		if (!test_bit(__E1000_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}

1550
	if (napi_schedule_prep(&adapter->napi)) {
1551 1552 1553 1554
		adapter->total_tx_bytes = 0;
		adapter->total_tx_packets = 0;
		adapter->total_rx_bytes = 0;
		adapter->total_rx_packets = 0;
1555
		__napi_schedule(&adapter->napi);
1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
	}

	return IRQ_HANDLED;
}

/**
 * e1000_intr - Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t e1000_intr(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 rctl, icr = er32(ICR);
1572

1573
	if (!icr || test_bit(__E1000_DOWN, &adapter->state))
1574 1575
		return IRQ_NONE;  /* Not our interrupt */

1576 1577 1578 1579
	/*
	 * IMS will not auto-mask if INT_ASSERTED is not set, and if it is
	 * not set, then the adapter didn't send an interrupt
	 */
1580 1581 1582
	if (!(icr & E1000_ICR_INT_ASSERTED))
		return IRQ_NONE;

1583 1584 1585 1586 1587
	/*
	 * Interrupt Auto-Mask...upon reading ICR,
	 * interrupts are masked.  No need for the
	 * IMC write
	 */
1588

1589
	if (icr & E1000_ICR_LSC) {
1590
		hw->mac.get_link_status = 1;
1591 1592 1593 1594
		/*
		 * ICH8 workaround-- Call gig speed drop workaround on cable
		 * disconnect (LSC) before accessing any PHY registers
		 */
1595 1596
		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
		    (!(er32(STATUS) & E1000_STATUS_LU)))
1597
			schedule_work(&adapter->downshift_task);
1598

1599 1600
		/*
		 * 80003ES2LAN workaround--
1601 1602 1603 1604 1605 1606 1607 1608 1609
		 * For packet buffer work-around on link down event;
		 * disable receives here in the ISR and
		 * reset adapter in watchdog
		 */
		if (netif_carrier_ok(netdev) &&
		    (adapter->flags & FLAG_RX_NEEDS_RESTART)) {
			/* disable receives */
			rctl = er32(RCTL);
			ew32(RCTL, rctl & ~E1000_RCTL_EN);
1610
			adapter->flags |= FLAG_RX_RESTART_NOW;
1611 1612 1613 1614 1615 1616
		}
		/* guard against interrupt when we're going down */
		if (!test_bit(__E1000_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}

1617
	if (napi_schedule_prep(&adapter->napi)) {
1618 1619 1620 1621
		adapter->total_tx_bytes = 0;
		adapter->total_tx_packets = 0;
		adapter->total_rx_bytes = 0;
		adapter->total_rx_packets = 0;
1622
		__napi_schedule(&adapter->napi);
1623 1624 1625 1626 1627
	}

	return IRQ_HANDLED;
}

1628 1629 1630 1631 1632 1633 1634 1635
static irqreturn_t e1000_msix_other(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 icr = er32(ICR);

	if (!(icr & E1000_ICR_INT_ASSERTED)) {
1636 1637
		if (!test_bit(__E1000_DOWN, &adapter->state))
			ew32(IMS, E1000_IMS_OTHER);
1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653
		return IRQ_NONE;
	}

	if (icr & adapter->eiac_mask)
		ew32(ICS, (icr & adapter->eiac_mask));

	if (icr & E1000_ICR_OTHER) {
		if (!(icr & E1000_ICR_LSC))
			goto no_link_interrupt;
		hw->mac.get_link_status = 1;
		/* guard against interrupt when we're going down */
		if (!test_bit(__E1000_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}

no_link_interrupt:
1654 1655
	if (!test_bit(__E1000_DOWN, &adapter->state))
		ew32(IMS, E1000_IMS_LSC | E1000_IMS_OTHER);
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692

	return IRQ_HANDLED;
}


static irqreturn_t e1000_intr_msix_tx(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *tx_ring = adapter->tx_ring;


	adapter->total_tx_bytes = 0;
	adapter->total_tx_packets = 0;

	if (!e1000_clean_tx_irq(adapter))
		/* Ring was not completely cleaned, so fire another interrupt */
		ew32(ICS, tx_ring->ims_val);

	return IRQ_HANDLED;
}

static irqreturn_t e1000_intr_msix_rx(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);

	/* Write the ITR value calculated at the end of the
	 * previous interrupt.
	 */
	if (adapter->rx_ring->set_itr) {
		writel(1000000000 / (adapter->rx_ring->itr_val * 256),
		       adapter->hw.hw_addr + adapter->rx_ring->itr_register);
		adapter->rx_ring->set_itr = 0;
	}

1693
	if (napi_schedule_prep(&adapter->napi)) {
1694 1695
		adapter->total_rx_bytes = 0;
		adapter->total_rx_packets = 0;
1696
		__napi_schedule(&adapter->napi);
1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792
	}
	return IRQ_HANDLED;
}

/**
 * e1000_configure_msix - Configure MSI-X hardware
 *
 * e1000_configure_msix sets up the hardware to properly
 * generate MSI-X interrupts.
 **/
static void e1000_configure_msix(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	struct e1000_ring *tx_ring = adapter->tx_ring;
	int vector = 0;
	u32 ctrl_ext, ivar = 0;

	adapter->eiac_mask = 0;

	/* Workaround issue with spurious interrupts on 82574 in MSI-X mode */
	if (hw->mac.type == e1000_82574) {
		u32 rfctl = er32(RFCTL);
		rfctl |= E1000_RFCTL_ACK_DIS;
		ew32(RFCTL, rfctl);
	}

#define E1000_IVAR_INT_ALLOC_VALID	0x8
	/* Configure Rx vector */
	rx_ring->ims_val = E1000_IMS_RXQ0;
	adapter->eiac_mask |= rx_ring->ims_val;
	if (rx_ring->itr_val)
		writel(1000000000 / (rx_ring->itr_val * 256),
		       hw->hw_addr + rx_ring->itr_register);
	else
		writel(1, hw->hw_addr + rx_ring->itr_register);
	ivar = E1000_IVAR_INT_ALLOC_VALID | vector;

	/* Configure Tx vector */
	tx_ring->ims_val = E1000_IMS_TXQ0;
	vector++;
	if (tx_ring->itr_val)
		writel(1000000000 / (tx_ring->itr_val * 256),
		       hw->hw_addr + tx_ring->itr_register);
	else
		writel(1, hw->hw_addr + tx_ring->itr_register);
	adapter->eiac_mask |= tx_ring->ims_val;
	ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 8);

	/* set vector for Other Causes, e.g. link changes */
	vector++;
	ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 16);
	if (rx_ring->itr_val)
		writel(1000000000 / (rx_ring->itr_val * 256),
		       hw->hw_addr + E1000_EITR_82574(vector));
	else
		writel(1, hw->hw_addr + E1000_EITR_82574(vector));

	/* Cause Tx interrupts on every write back */
	ivar |= (1 << 31);

	ew32(IVAR, ivar);

	/* enable MSI-X PBA support */
	ctrl_ext = er32(CTRL_EXT);
	ctrl_ext |= E1000_CTRL_EXT_PBA_CLR;

	/* Auto-Mask Other interrupts upon ICR read */
#define E1000_EIAC_MASK_82574   0x01F00000
	ew32(IAM, ~E1000_EIAC_MASK_82574 | E1000_IMS_OTHER);
	ctrl_ext |= E1000_CTRL_EXT_EIAME;
	ew32(CTRL_EXT, ctrl_ext);
	e1e_flush();
}

void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter)
{
	if (adapter->msix_entries) {
		pci_disable_msix(adapter->pdev);
		kfree(adapter->msix_entries);
		adapter->msix_entries = NULL;
	} else if (adapter->flags & FLAG_MSI_ENABLED) {
		pci_disable_msi(adapter->pdev);
		adapter->flags &= ~FLAG_MSI_ENABLED;
	}
}

/**
 * e1000e_set_interrupt_capability - set MSI or MSI-X if supported
 *
 * Attempt to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
void e1000e_set_interrupt_capability(struct e1000_adapter *adapter)
{
	int err;
1793
	int i;
1794 1795 1796 1797

	switch (adapter->int_mode) {
	case E1000E_INT_MODE_MSIX:
		if (adapter->flags & FLAG_HAS_MSIX) {
1798 1799
			adapter->num_vectors = 3; /* RxQ0, TxQ0 and other */
			adapter->msix_entries = kcalloc(adapter->num_vectors,
1800 1801 1802
						      sizeof(struct msix_entry),
						      GFP_KERNEL);
			if (adapter->msix_entries) {
1803
				for (i = 0; i < adapter->num_vectors; i++)
1804 1805 1806 1807
					adapter->msix_entries[i].entry = i;

				err = pci_enable_msix(adapter->pdev,
						      adapter->msix_entries,
1808 1809
						      adapter->num_vectors);
				if (err == 0) {
1810
					return;
1811
				}
1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832
			}
			/* MSI-X failed, so fall through and try MSI */
			e_err("Failed to initialize MSI-X interrupts.  "
			      "Falling back to MSI interrupts.\n");
			e1000e_reset_interrupt_capability(adapter);
		}
		adapter->int_mode = E1000E_INT_MODE_MSI;
		/* Fall through */
	case E1000E_INT_MODE_MSI:
		if (!pci_enable_msi(adapter->pdev)) {
			adapter->flags |= FLAG_MSI_ENABLED;
		} else {
			adapter->int_mode = E1000E_INT_MODE_LEGACY;
			e_err("Failed to initialize MSI interrupts.  Falling "
			      "back to legacy interrupts.\n");
		}
		/* Fall through */
	case E1000E_INT_MODE_LEGACY:
		/* Don't do anything; this is the system default */
		break;
	}
1833 1834 1835

	/* store the number of vectors being used */
	adapter->num_vectors = 1;
1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849
}

/**
 * e1000_request_msix - Initialize MSI-X interrupts
 *
 * e1000_request_msix allocates MSI-X vectors and requests interrupts from the
 * kernel.
 **/
static int e1000_request_msix(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int err = 0, vector = 0;

	if (strlen(netdev->name) < (IFNAMSIZ - 5))
1850
		sprintf(adapter->rx_ring->name, "%s-rx-0", netdev->name);
1851 1852 1853
	else
		memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
	err = request_irq(adapter->msix_entries[vector].vector,
1854
			  e1000_intr_msix_rx, 0, adapter->rx_ring->name,
1855 1856 1857 1858 1859 1860 1861 1862
			  netdev);
	if (err)
		goto out;
	adapter->rx_ring->itr_register = E1000_EITR_82574(vector);
	adapter->rx_ring->itr_val = adapter->itr;
	vector++;

	if (strlen(netdev->name) < (IFNAMSIZ - 5))
1863
		sprintf(adapter->tx_ring->name, "%s-tx-0", netdev->name);
1864 1865 1866
	else
		memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
	err = request_irq(adapter->msix_entries[vector].vector,
1867
			  e1000_intr_msix_tx, 0, adapter->tx_ring->name,
1868 1869 1870 1871 1872 1873 1874 1875
			  netdev);
	if (err)
		goto out;
	adapter->tx_ring->itr_register = E1000_EITR_82574(vector);
	adapter->tx_ring->itr_val = adapter->itr;
	vector++;

	err = request_irq(adapter->msix_entries[vector].vector,
1876
			  e1000_msix_other, 0, netdev->name, netdev);
1877 1878 1879 1880 1881 1882 1883 1884 1885
	if (err)
		goto out;

	e1000_configure_msix(adapter);
	return 0;
out:
	return err;
}

1886 1887 1888 1889 1890 1891
/**
 * e1000_request_irq - initialize interrupts
 *
 * Attempts to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
1892 1893 1894 1895 1896
static int e1000_request_irq(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int err;

1897 1898 1899 1900 1901 1902 1903 1904
	if (adapter->msix_entries) {
		err = e1000_request_msix(adapter);
		if (!err)
			return err;
		/* fall back to MSI */
		e1000e_reset_interrupt_capability(adapter);
		adapter->int_mode = E1000E_INT_MODE_MSI;
		e1000e_set_interrupt_capability(adapter);
1905
	}
1906
	if (adapter->flags & FLAG_MSI_ENABLED) {
1907
		err = request_irq(adapter->pdev->irq, e1000_intr_msi, 0,
1908 1909 1910
				  netdev->name, netdev);
		if (!err)
			return err;
1911

1912 1913 1914
		/* fall back to legacy interrupt */
		e1000e_reset_interrupt_capability(adapter);
		adapter->int_mode = E1000E_INT_MODE_LEGACY;
1915 1916
	}

1917
	err = request_irq(adapter->pdev->irq, e1000_intr, IRQF_SHARED,
1918 1919 1920 1921
			  netdev->name, netdev);
	if (err)
		e_err("Unable to allocate interrupt, Error: %d\n", err);

1922 1923 1924 1925 1926 1927 1928
	return err;
}

static void e1000_free_irq(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;

1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940
	if (adapter->msix_entries) {
		int vector = 0;

		free_irq(adapter->msix_entries[vector].vector, netdev);
		vector++;

		free_irq(adapter->msix_entries[vector].vector, netdev);
		vector++;

		/* Other Causes interrupt vector */
		free_irq(adapter->msix_entries[vector].vector, netdev);
		return;
1941
	}
1942 1943

	free_irq(adapter->pdev->irq, netdev);
1944 1945 1946 1947 1948 1949 1950 1951 1952 1953
}

/**
 * e1000_irq_disable - Mask off interrupt generation on the NIC
 **/
static void e1000_irq_disable(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;

	ew32(IMC, ~0);
1954 1955
	if (adapter->msix_entries)
		ew32(EIAC_82574, 0);
1956
	e1e_flush();
1957 1958 1959 1960 1961 1962 1963 1964

	if (adapter->msix_entries) {
		int i;
		for (i = 0; i < adapter->num_vectors; i++)
			synchronize_irq(adapter->msix_entries[i].vector);
	} else {
		synchronize_irq(adapter->pdev->irq);
	}
1965 1966 1967 1968 1969 1970 1971 1972 1973
}

/**
 * e1000_irq_enable - Enable default interrupt generation settings
 **/
static void e1000_irq_enable(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;

1974 1975 1976 1977 1978 1979
	if (adapter->msix_entries) {
		ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574);
		ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC);
	} else {
		ew32(IMS, IMS_ENABLE_MASK);
	}
J
Jesse Brandeburg 已提交
1980
	e1e_flush();
1981 1982 1983 1984 1985 1986
}

/**
 * e1000_get_hw_control - get control of the h/w from f/w
 * @adapter: address of board private structure
 *
1987
 * e1000_get_hw_control sets {CTRL_EXT|SWSM}:DRV_LOAD bit.
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
 * For ASF and Pass Through versions of f/w this means that
 * the driver is loaded. For AMT version (only with 82573)
 * of the f/w this means that the network i/f is open.
 **/
static void e1000_get_hw_control(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl_ext;
	u32 swsm;

	/* Let firmware know the driver has taken over */
	if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) {
		swsm = er32(SWSM);
		ew32(SWSM, swsm | E1000_SWSM_DRV_LOAD);
	} else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) {
		ctrl_ext = er32(CTRL_EXT);
2004
		ew32(CTRL_EXT, ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
2005 2006 2007 2008 2009 2010 2011
	}
}

/**
 * e1000_release_hw_control - release control of the h/w to f/w
 * @adapter: address of board private structure
 *
2012
 * e1000_release_hw_control resets {CTRL_EXT|SWSM}:DRV_LOAD bit.
2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
 * For ASF and Pass Through versions of f/w this means that the
 * driver is no longer loaded. For AMT version (only with 82573) i
 * of the f/w this means that the network i/f is closed.
 *
 **/
static void e1000_release_hw_control(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl_ext;
	u32 swsm;

	/* Let firmware taken over control of h/w */
	if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) {
		swsm = er32(SWSM);
		ew32(SWSM, swsm & ~E1000_SWSM_DRV_LOAD);
	} else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) {
		ctrl_ext = er32(CTRL_EXT);
2030
		ew32(CTRL_EXT, ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD);
2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080
	}
}

/**
 * @e1000_alloc_ring - allocate memory for a ring structure
 **/
static int e1000_alloc_ring_dma(struct e1000_adapter *adapter,
				struct e1000_ring *ring)
{
	struct pci_dev *pdev = adapter->pdev;

	ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma,
					GFP_KERNEL);
	if (!ring->desc)
		return -ENOMEM;

	return 0;
}

/**
 * e1000e_setup_tx_resources - allocate Tx resources (Descriptors)
 * @adapter: board private structure
 *
 * Return 0 on success, negative on failure
 **/
int e1000e_setup_tx_resources(struct e1000_adapter *adapter)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	int err = -ENOMEM, size;

	size = sizeof(struct e1000_buffer) * tx_ring->count;
	tx_ring->buffer_info = vmalloc(size);
	if (!tx_ring->buffer_info)
		goto err;
	memset(tx_ring->buffer_info, 0, size);

	/* round up to nearest 4K */
	tx_ring->size = tx_ring->count * sizeof(struct e1000_tx_desc);
	tx_ring->size = ALIGN(tx_ring->size, 4096);

	err = e1000_alloc_ring_dma(adapter, tx_ring);
	if (err)
		goto err;

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;

	return 0;
err:
	vfree(tx_ring->buffer_info);
2081
	e_err("Unable to allocate memory for the transmit descriptor ring\n");
2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093
	return err;
}

/**
 * e1000e_setup_rx_resources - allocate Rx resources (Descriptors)
 * @adapter: board private structure
 *
 * Returns 0 on success, negative on failure
 **/
int e1000e_setup_rx_resources(struct e1000_adapter *adapter)
{
	struct e1000_ring *rx_ring = adapter->rx_ring;
A
Auke Kok 已提交
2094 2095
	struct e1000_buffer *buffer_info;
	int i, size, desc_len, err = -ENOMEM;
2096 2097 2098 2099 2100 2101 2102

	size = sizeof(struct e1000_buffer) * rx_ring->count;
	rx_ring->buffer_info = vmalloc(size);
	if (!rx_ring->buffer_info)
		goto err;
	memset(rx_ring->buffer_info, 0, size);

A
Auke Kok 已提交
2103 2104 2105 2106 2107 2108 2109 2110
	for (i = 0; i < rx_ring->count; i++) {
		buffer_info = &rx_ring->buffer_info[i];
		buffer_info->ps_pages = kcalloc(PS_PAGE_BUFFERS,
						sizeof(struct e1000_ps_page),
						GFP_KERNEL);
		if (!buffer_info->ps_pages)
			goto err_pages;
	}
2111 2112 2113 2114 2115 2116 2117 2118 2119

	desc_len = sizeof(union e1000_rx_desc_packet_split);

	/* Round up to nearest 4K */
	rx_ring->size = rx_ring->count * desc_len;
	rx_ring->size = ALIGN(rx_ring->size, 4096);

	err = e1000_alloc_ring_dma(adapter, rx_ring);
	if (err)
A
Auke Kok 已提交
2120
		goto err_pages;
2121 2122 2123 2124 2125 2126

	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;
	rx_ring->rx_skb_top = NULL;

	return 0;
A
Auke Kok 已提交
2127 2128 2129 2130 2131 2132

err_pages:
	for (i = 0; i < rx_ring->count; i++) {
		buffer_info = &rx_ring->buffer_info[i];
		kfree(buffer_info->ps_pages);
	}
2133 2134
err:
	vfree(rx_ring->buffer_info);
2135
	e_err("Unable to allocate memory for the transmit descriptor ring\n");
2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198
	return err;
}

/**
 * e1000_clean_tx_ring - Free Tx Buffers
 * @adapter: board private structure
 **/
static void e1000_clean_tx_ring(struct e1000_adapter *adapter)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_buffer *buffer_info;
	unsigned long size;
	unsigned int i;

	for (i = 0; i < tx_ring->count; i++) {
		buffer_info = &tx_ring->buffer_info[i];
		e1000_put_txbuf(adapter, buffer_info);
	}

	size = sizeof(struct e1000_buffer) * tx_ring->count;
	memset(tx_ring->buffer_info, 0, size);

	memset(tx_ring->desc, 0, tx_ring->size);

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;

	writel(0, adapter->hw.hw_addr + tx_ring->head);
	writel(0, adapter->hw.hw_addr + tx_ring->tail);
}

/**
 * e1000e_free_tx_resources - Free Tx Resources per Queue
 * @adapter: board private structure
 *
 * Free all transmit software resources
 **/
void e1000e_free_tx_resources(struct e1000_adapter *adapter)
{
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_ring *tx_ring = adapter->tx_ring;

	e1000_clean_tx_ring(adapter);

	vfree(tx_ring->buffer_info);
	tx_ring->buffer_info = NULL;

	dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
			  tx_ring->dma);
	tx_ring->desc = NULL;
}

/**
 * e1000e_free_rx_resources - Free Rx Resources
 * @adapter: board private structure
 *
 * Free all receive software resources
 **/

void e1000e_free_rx_resources(struct e1000_adapter *adapter)
{
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_ring *rx_ring = adapter->rx_ring;
A
Auke Kok 已提交
2199
	int i;
2200 2201 2202

	e1000_clean_rx_ring(adapter);

A
Auke Kok 已提交
2203 2204 2205 2206
	for (i = 0; i < rx_ring->count; i++) {
		kfree(rx_ring->buffer_info[i].ps_pages);
	}

2207 2208 2209 2210 2211 2212 2213 2214 2215 2216
	vfree(rx_ring->buffer_info);
	rx_ring->buffer_info = NULL;

	dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
			  rx_ring->dma);
	rx_ring->desc = NULL;
}

/**
 * e1000_update_itr - update the dynamic ITR value based on statistics
2217 2218 2219 2220 2221
 * @adapter: pointer to adapter
 * @itr_setting: current adapter->itr
 * @packets: the number of packets during this measurement interval
 * @bytes: the number of bytes during this measurement interval
 *
2222 2223 2224 2225 2226 2227
 *      Stores a new ITR value based on packets and byte
 *      counts during the last interrupt.  The advantage of per interrupt
 *      computation is faster updates and more accurate ITR for the current
 *      traffic pattern.  Constants in this function were computed
 *      based on theoretical maximum wire speed and thresholds were set based
 *      on testing data as well as attempting to minimize response time
2228 2229
 *      while increasing bulk throughput.  This functionality is controlled
 *      by the InterruptThrottleRate module parameter.
2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292
 **/
static unsigned int e1000_update_itr(struct e1000_adapter *adapter,
				     u16 itr_setting, int packets,
				     int bytes)
{
	unsigned int retval = itr_setting;

	if (packets == 0)
		goto update_itr_done;

	switch (itr_setting) {
	case lowest_latency:
		/* handle TSO and jumbo frames */
		if (bytes/packets > 8000)
			retval = bulk_latency;
		else if ((packets < 5) && (bytes > 512)) {
			retval = low_latency;
		}
		break;
	case low_latency:  /* 50 usec aka 20000 ints/s */
		if (bytes > 10000) {
			/* this if handles the TSO accounting */
			if (bytes/packets > 8000) {
				retval = bulk_latency;
			} else if ((packets < 10) || ((bytes/packets) > 1200)) {
				retval = bulk_latency;
			} else if ((packets > 35)) {
				retval = lowest_latency;
			}
		} else if (bytes/packets > 2000) {
			retval = bulk_latency;
		} else if (packets <= 2 && bytes < 512) {
			retval = lowest_latency;
		}
		break;
	case bulk_latency: /* 250 usec aka 4000 ints/s */
		if (bytes > 25000) {
			if (packets > 35) {
				retval = low_latency;
			}
		} else if (bytes < 6000) {
			retval = low_latency;
		}
		break;
	}

update_itr_done:
	return retval;
}

static void e1000_set_itr(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u16 current_itr;
	u32 new_itr = adapter->itr;

	/* for non-gigabit speeds, just fix the interrupt rate at 4000 */
	if (adapter->link_speed != SPEED_1000) {
		current_itr = 0;
		new_itr = 4000;
		goto set_itr_now;
	}

2293 2294 2295 2296 2297
	if (adapter->flags2 & FLAG2_DISABLE_AIM) {
		new_itr = 0;
		goto set_itr_now;
	}

2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332
	adapter->tx_itr = e1000_update_itr(adapter,
				    adapter->tx_itr,
				    adapter->total_tx_packets,
				    adapter->total_tx_bytes);
	/* conservative mode (itr 3) eliminates the lowest_latency setting */
	if (adapter->itr_setting == 3 && adapter->tx_itr == lowest_latency)
		adapter->tx_itr = low_latency;

	adapter->rx_itr = e1000_update_itr(adapter,
				    adapter->rx_itr,
				    adapter->total_rx_packets,
				    adapter->total_rx_bytes);
	/* conservative mode (itr 3) eliminates the lowest_latency setting */
	if (adapter->itr_setting == 3 && adapter->rx_itr == lowest_latency)
		adapter->rx_itr = low_latency;

	current_itr = max(adapter->rx_itr, adapter->tx_itr);

	switch (current_itr) {
	/* counts and packets in update_itr are dependent on these numbers */
	case lowest_latency:
		new_itr = 70000;
		break;
	case low_latency:
		new_itr = 20000; /* aka hwitr = ~200 */
		break;
	case bulk_latency:
		new_itr = 4000;
		break;
	default:
		break;
	}

set_itr_now:
	if (new_itr != adapter->itr) {
2333 2334
		/*
		 * this attempts to bias the interrupt rate towards Bulk
2335
		 * by adding intermediate steps when interrupt rate is
2336 2337
		 * increasing
		 */
2338 2339 2340 2341
		new_itr = new_itr > adapter->itr ?
			     min(adapter->itr + (new_itr >> 2), new_itr) :
			     new_itr;
		adapter->itr = new_itr;
2342 2343 2344 2345
		adapter->rx_ring->itr_val = new_itr;
		if (adapter->msix_entries)
			adapter->rx_ring->set_itr = 1;
		else
2346 2347 2348 2349
			if (new_itr)
				ew32(ITR, 1000000000 / (new_itr * 256));
			else
				ew32(ITR, 0);
2350 2351 2352
	}
}

2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374
/**
 * e1000_alloc_queues - Allocate memory for all rings
 * @adapter: board private structure to initialize
 **/
static int __devinit e1000_alloc_queues(struct e1000_adapter *adapter)
{
	adapter->tx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL);
	if (!adapter->tx_ring)
		goto err;

	adapter->rx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL);
	if (!adapter->rx_ring)
		goto err;

	return 0;
err:
	e_err("Unable to allocate memory for queues\n");
	kfree(adapter->rx_ring);
	kfree(adapter->tx_ring);
	return -ENOMEM;
}

2375 2376
/**
 * e1000_clean - NAPI Rx polling callback
2377
 * @napi: struct associated with this polling callback
2378
 * @budget: amount of packets driver is allowed to process this poll
2379 2380 2381 2382
 **/
static int e1000_clean(struct napi_struct *napi, int budget)
{
	struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter, napi);
2383
	struct e1000_hw *hw = &adapter->hw;
2384
	struct net_device *poll_dev = adapter->netdev;
2385
	int tx_cleaned = 1, work_done = 0;
2386

2387
	adapter = netdev_priv(poll_dev);
2388

2389 2390 2391 2392
	if (adapter->msix_entries &&
	    !(adapter->rx_ring->ims_val & adapter->tx_ring->ims_val))
		goto clean_rx;

2393
	tx_cleaned = e1000_clean_tx_irq(adapter);
2394

2395
clean_rx:
2396
	adapter->clean_rx(adapter, &work_done, budget);
2397

2398
	if (!tx_cleaned)
2399
		work_done = budget;
2400

2401 2402
	/* If budget not fully consumed, exit the polling mode */
	if (work_done < budget) {
2403 2404
		if (adapter->itr_setting & 3)
			e1000_set_itr(adapter);
2405
		napi_complete(napi);
2406 2407 2408 2409 2410 2411
		if (!test_bit(__E1000_DOWN, &adapter->state)) {
			if (adapter->msix_entries)
				ew32(IMS, adapter->rx_ring->ims_val);
			else
				e1000_irq_enable(adapter);
		}
2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427
	}

	return work_done;
}

static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 vfta, index;

	/* don't update vlan cookie if already programmed */
	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
	    (vid == adapter->mng_vlan_id))
		return;
2428

2429
	/* add VID to filter table */
2430 2431 2432 2433 2434 2435
	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
		index = (vid >> 5) & 0x7F;
		vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index);
		vfta |= (1 << (vid & 0x1F));
		hw->mac.ops.write_vfta(hw, index, vfta);
	}
2436 2437 2438 2439 2440 2441 2442 2443
}

static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 vfta, index;

J
Jesse Brandeburg 已提交
2444 2445
	if (!test_bit(__E1000_DOWN, &adapter->state))
		e1000_irq_disable(adapter);
2446
	vlan_group_set_device(adapter->vlgrp, vid, NULL);
J
Jesse Brandeburg 已提交
2447 2448 2449

	if (!test_bit(__E1000_DOWN, &adapter->state))
		e1000_irq_enable(adapter);
2450 2451 2452 2453 2454 2455 2456 2457 2458 2459

	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
	    (vid == adapter->mng_vlan_id)) {
		/* release control to f/w */
		e1000_release_hw_control(adapter);
		return;
	}

	/* remove VID from filter table */
2460 2461 2462 2463 2464 2465
	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
		index = (vid >> 5) & 0x7F;
		vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index);
		vfta &= ~(1 << (vid & 0x1F));
		hw->mac.ops.write_vfta(hw, index, vfta);
	}
2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501
}

static void e1000_update_mng_vlan(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	u16 vid = adapter->hw.mng_cookie.vlan_id;
	u16 old_vid = adapter->mng_vlan_id;

	if (!adapter->vlgrp)
		return;

	if (!vlan_group_get_device(adapter->vlgrp, vid)) {
		adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
		if (adapter->hw.mng_cookie.status &
			E1000_MNG_DHCP_COOKIE_STATUS_VLAN) {
			e1000_vlan_rx_add_vid(netdev, vid);
			adapter->mng_vlan_id = vid;
		}

		if ((old_vid != (u16)E1000_MNG_VLAN_NONE) &&
				(vid != old_vid) &&
		    !vlan_group_get_device(adapter->vlgrp, old_vid))
			e1000_vlan_rx_kill_vid(netdev, old_vid);
	} else {
		adapter->mng_vlan_id = vid;
	}
}


static void e1000_vlan_rx_register(struct net_device *netdev,
				   struct vlan_group *grp)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl, rctl;

J
Jesse Brandeburg 已提交
2502 2503
	if (!test_bit(__E1000_DOWN, &adapter->state))
		e1000_irq_disable(adapter);
2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534
	adapter->vlgrp = grp;

	if (grp) {
		/* enable VLAN tag insert/strip */
		ctrl = er32(CTRL);
		ctrl |= E1000_CTRL_VME;
		ew32(CTRL, ctrl);

		if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
			/* enable VLAN receive filtering */
			rctl = er32(RCTL);
			rctl &= ~E1000_RCTL_CFIEN;
			ew32(RCTL, rctl);
			e1000_update_mng_vlan(adapter);
		}
	} else {
		/* disable VLAN tag insert/strip */
		ctrl = er32(CTRL);
		ctrl &= ~E1000_CTRL_VME;
		ew32(CTRL, ctrl);

		if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
			if (adapter->mng_vlan_id !=
			    (u16)E1000_MNG_VLAN_NONE) {
				e1000_vlan_rx_kill_vid(netdev,
						       adapter->mng_vlan_id);
				adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
			}
		}
	}

J
Jesse Brandeburg 已提交
2535 2536
	if (!test_bit(__E1000_DOWN, &adapter->state))
		e1000_irq_enable(adapter);
2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547
}

static void e1000_restore_vlan(struct e1000_adapter *adapter)
{
	u16 vid;

	e1000_vlan_rx_register(adapter->netdev, adapter->vlgrp);

	if (!adapter->vlgrp)
		return;

2548
	for (vid = 0; vid < VLAN_N_VID; vid++) {
2549 2550 2551 2552 2553 2554
		if (!vlan_group_get_device(adapter->vlgrp, vid))
			continue;
		e1000_vlan_rx_add_vid(adapter->netdev, vid);
	}
}

2555
static void e1000_init_manageability_pt(struct e1000_adapter *adapter)
2556 2557
{
	struct e1000_hw *hw = &adapter->hw;
2558
	u32 manc, manc2h, mdef, i, j;
2559 2560 2561 2562 2563 2564

	if (!(adapter->flags & FLAG_MNG_PT_ENABLED))
		return;

	manc = er32(MANC);

2565 2566
	/*
	 * enable receiving management packets to the host. this will probably
2567
	 * generate destination unreachable messages from the host OS, but
2568 2569
	 * the packets will be handled on SMBUS
	 */
2570 2571
	manc |= E1000_MANC_EN_MNG2HOST;
	manc2h = er32(MANC2H);
2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586

	switch (hw->mac.type) {
	default:
		manc2h |= (E1000_MANC2H_PORT_623 | E1000_MANC2H_PORT_664);
		break;
	case e1000_82574:
	case e1000_82583:
		/*
		 * Check if IPMI pass-through decision filter already exists;
		 * if so, enable it.
		 */
		for (i = 0, j = 0; i < 8; i++) {
			mdef = er32(MDEF(i));

			/* Ignore filters with anything other than IPMI ports */
2587
			if (mdef & ~(E1000_MDEF_PORT_623 | E1000_MDEF_PORT_664))
2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614
				continue;

			/* Enable this decision filter in MANC2H */
			if (mdef)
				manc2h |= (1 << i);

			j |= mdef;
		}

		if (j == (E1000_MDEF_PORT_623 | E1000_MDEF_PORT_664))
			break;

		/* Create new decision filter in an empty filter */
		for (i = 0, j = 0; i < 8; i++)
			if (er32(MDEF(i)) == 0) {
				ew32(MDEF(i), (E1000_MDEF_PORT_623 |
					       E1000_MDEF_PORT_664));
				manc2h |= (1 << 1);
				j++;
				break;
			}

		if (!j)
			e_warn("Unable to create IPMI pass-through filter\n");
		break;
	}

2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635
	ew32(MANC2H, manc2h);
	ew32(MANC, manc);
}

/**
 * e1000_configure_tx - Configure 8254x Transmit Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Tx unit of the MAC after a reset.
 **/
static void e1000_configure_tx(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *tx_ring = adapter->tx_ring;
	u64 tdba;
	u32 tdlen, tctl, tipg, tarc;
	u32 ipgr1, ipgr2;

	/* Setup the HW Tx Head and Tail descriptor pointers */
	tdba = tx_ring->dma;
	tdlen = tx_ring->count * sizeof(struct e1000_tx_desc);
2636
	ew32(TDBAL, (tdba & DMA_BIT_MASK(32)));
2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657
	ew32(TDBAH, (tdba >> 32));
	ew32(TDLEN, tdlen);
	ew32(TDH, 0);
	ew32(TDT, 0);
	tx_ring->head = E1000_TDH;
	tx_ring->tail = E1000_TDT;

	/* Set the default values for the Tx Inter Packet Gap timer */
	tipg = DEFAULT_82543_TIPG_IPGT_COPPER;          /*  8  */
	ipgr1 = DEFAULT_82543_TIPG_IPGR1;               /*  8  */
	ipgr2 = DEFAULT_82543_TIPG_IPGR2;               /*  6  */

	if (adapter->flags & FLAG_TIPG_MEDIUM_FOR_80003ESLAN)
		ipgr2 = DEFAULT_80003ES2LAN_TIPG_IPGR2; /*  7  */

	tipg |= ipgr1 << E1000_TIPG_IPGR1_SHIFT;
	tipg |= ipgr2 << E1000_TIPG_IPGR2_SHIFT;
	ew32(TIPG, tipg);

	/* Set the Tx Interrupt Delay register */
	ew32(TIDV, adapter->tx_int_delay);
2658
	/* Tx irq moderation */
2659 2660
	ew32(TADV, adapter->tx_abs_int_delay);

2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680
	if (adapter->flags2 & FLAG2_DMA_BURST) {
		u32 txdctl = er32(TXDCTL(0));
		txdctl &= ~(E1000_TXDCTL_PTHRESH | E1000_TXDCTL_HTHRESH |
			    E1000_TXDCTL_WTHRESH);
		/*
		 * set up some performance related parameters to encourage the
		 * hardware to use the bus more efficiently in bursts, depends
		 * on the tx_int_delay to be enabled,
		 * wthresh = 5 ==> burst write a cacheline (64 bytes) at a time
		 * hthresh = 1 ==> prefetch when one or more available
		 * pthresh = 0x1f ==> prefetch if internal cache 31 or less
		 * BEWARE: this seems to work but should be considered first if
		 * there are tx hangs or other tx related bugs
		 */
		txdctl |= E1000_TXDCTL_DMA_BURST_ENABLE;
		ew32(TXDCTL(0), txdctl);
		/* erratum work around: set txdctl the same for both queues */
		ew32(TXDCTL(1), txdctl);
	}

2681 2682 2683 2684 2685 2686 2687
	/* Program the Transmit Control Register */
	tctl = er32(TCTL);
	tctl &= ~E1000_TCTL_CT;
	tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC |
		(E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT);

	if (adapter->flags & FLAG_TARC_SPEED_MODE_BIT) {
2688
		tarc = er32(TARC(0));
2689 2690 2691 2692
		/*
		 * set the speed mode bit, we'll clear it if we're not at
		 * gigabit link later
		 */
2693 2694
#define SPEED_MODE_BIT (1 << 21)
		tarc |= SPEED_MODE_BIT;
2695
		ew32(TARC(0), tarc);
2696 2697 2698 2699
	}

	/* errata: program both queues to unweighted RR */
	if (adapter->flags & FLAG_TARC_SET_BIT_ZERO) {
2700
		tarc = er32(TARC(0));
2701
		tarc |= 1;
2702 2703
		ew32(TARC(0), tarc);
		tarc = er32(TARC(1));
2704
		tarc |= 1;
2705
		ew32(TARC(1), tarc);
2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719
	}

	/* Setup Transmit Descriptor Settings for eop descriptor */
	adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_IFCS;

	/* only set IDE if we are delaying interrupts using the timers */
	if (adapter->tx_int_delay)
		adapter->txd_cmd |= E1000_TXD_CMD_IDE;

	/* enable Report Status bit */
	adapter->txd_cmd |= E1000_TXD_CMD_RS;

	ew32(TCTL, tctl);

2720
	e1000e_config_collision_dist(hw);
2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735
}

/**
 * e1000_setup_rctl - configure the receive control registers
 * @adapter: Board private structure
 **/
#define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \
			   (((S) & (PAGE_SIZE - 1)) ? 1 : 0))
static void e1000_setup_rctl(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 rctl, rfctl;
	u32 psrctl = 0;
	u32 pages = 0;

2736 2737 2738 2739 2740 2741 2742 2743 2744 2745
	/* Workaround Si errata on 82579 - configure jumbo frame flow */
	if (hw->mac.type == e1000_pch2lan) {
		s32 ret_val;

		if (adapter->netdev->mtu > ETH_DATA_LEN)
			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true);
		else
			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false);
	}

2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761
	/* Program MC offset vector base */
	rctl = er32(RCTL);
	rctl &= ~(3 << E1000_RCTL_MO_SHIFT);
	rctl |= E1000_RCTL_EN | E1000_RCTL_BAM |
		E1000_RCTL_LBM_NO | E1000_RCTL_RDMTS_HALF |
		(adapter->hw.mac.mc_filter_type << E1000_RCTL_MO_SHIFT);

	/* Do not Store bad packets */
	rctl &= ~E1000_RCTL_SBP;

	/* Enable Long Packet receive */
	if (adapter->netdev->mtu <= ETH_DATA_LEN)
		rctl &= ~E1000_RCTL_LPE;
	else
		rctl |= E1000_RCTL_LPE;

J
Jeff Kirsher 已提交
2762 2763 2764 2765 2766 2767
	/* Some systems expect that the CRC is included in SMBUS traffic. The
	 * hardware strips the CRC before sending to both SMBUS (BMC) and to
	 * host memory when this is enabled
	 */
	if (adapter->flags2 & FLAG2_CRC_STRIPPING)
		rctl |= E1000_RCTL_SECRC;
2768

2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785
	/* Workaround Si errata on 82577 PHY - configure IPG for jumbos */
	if ((hw->phy.type == e1000_phy_82577) && (rctl & E1000_RCTL_LPE)) {
		u16 phy_data;

		e1e_rphy(hw, PHY_REG(770, 26), &phy_data);
		phy_data &= 0xfff8;
		phy_data |= (1 << 2);
		e1e_wphy(hw, PHY_REG(770, 26), phy_data);

		e1e_rphy(hw, 22, &phy_data);
		phy_data &= 0x0fff;
		phy_data |= (1 << 14);
		e1e_wphy(hw, 0x10, 0x2823);
		e1e_wphy(hw, 0x11, 0x0003);
		e1e_wphy(hw, 22, phy_data);
	}

2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821
	/* Setup buffer sizes */
	rctl &= ~E1000_RCTL_SZ_4096;
	rctl |= E1000_RCTL_BSEX;
	switch (adapter->rx_buffer_len) {
	case 2048:
	default:
		rctl |= E1000_RCTL_SZ_2048;
		rctl &= ~E1000_RCTL_BSEX;
		break;
	case 4096:
		rctl |= E1000_RCTL_SZ_4096;
		break;
	case 8192:
		rctl |= E1000_RCTL_SZ_8192;
		break;
	case 16384:
		rctl |= E1000_RCTL_SZ_16384;
		break;
	}

	/*
	 * 82571 and greater support packet-split where the protocol
	 * header is placed in skb->data and the packet data is
	 * placed in pages hanging off of skb_shinfo(skb)->nr_frags.
	 * In the case of a non-split, skb->data is linearly filled,
	 * followed by the page buffers.  Therefore, skb->data is
	 * sized to hold the largest protocol header.
	 *
	 * allocations using alloc_page take too long for regular MTU
	 * so only enable packet split for jumbo frames
	 *
	 * Using pages when the page size is greater than 16k wastes
	 * a lot of memory, since we allocate 3 pages at all times
	 * per packet.
	 */
	pages = PAGE_USE_COUNT(adapter->netdev->mtu);
2822
	if (!(adapter->flags & FLAG_HAS_ERT) && (pages <= 3) &&
2823
	    (PAGE_SIZE <= 16384) && (rctl & E1000_RCTL_LPE))
2824
		adapter->rx_ps_pages = pages;
2825 2826
	else
		adapter->rx_ps_pages = 0;
2827 2828 2829 2830 2831

	if (adapter->rx_ps_pages) {
		/* Configure extra packet-split registers */
		rfctl = er32(RFCTL);
		rfctl |= E1000_RFCTL_EXTEN;
2832 2833 2834 2835
		/*
		 * disable packet split support for IPv6 extension headers,
		 * because some malformed IPv6 headers can hang the Rx
		 */
2836 2837 2838 2839 2840
		rfctl |= (E1000_RFCTL_IPV6_EX_DIS |
			  E1000_RFCTL_NEW_IPV6_EXT_DIS);

		ew32(RFCTL, rfctl);

A
Auke Kok 已提交
2841 2842
		/* Enable Packet split descriptors */
		rctl |= E1000_RCTL_DTYP_PS;
2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863

		psrctl |= adapter->rx_ps_bsize0 >>
			E1000_PSRCTL_BSIZE0_SHIFT;

		switch (adapter->rx_ps_pages) {
		case 3:
			psrctl |= PAGE_SIZE <<
				E1000_PSRCTL_BSIZE3_SHIFT;
		case 2:
			psrctl |= PAGE_SIZE <<
				E1000_PSRCTL_BSIZE2_SHIFT;
		case 1:
			psrctl |= PAGE_SIZE >>
				E1000_PSRCTL_BSIZE1_SHIFT;
			break;
		}

		ew32(PSRCTL, psrctl);
	}

	ew32(RCTL, rctl);
2864 2865
	/* just started the receive unit, no need to restart */
	adapter->flags &= ~FLAG_RX_RESTART_NOW;
2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
}

/**
 * e1000_configure_rx - Configure Receive Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Rx unit of the MAC after a reset.
 **/
static void e1000_configure_rx(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	u64 rdba;
	u32 rdlen, rctl, rxcsum, ctrl_ext;

	if (adapter->rx_ps_pages) {
		/* this is a 32 byte descriptor */
		rdlen = rx_ring->count *
			sizeof(union e1000_rx_desc_packet_split);
		adapter->clean_rx = e1000_clean_rx_irq_ps;
		adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps;
2887 2888 2889 2890
	} else if (adapter->netdev->mtu > ETH_FRAME_LEN + ETH_FCS_LEN) {
		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
		adapter->clean_rx = e1000_clean_jumbo_rx_irq;
		adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers;
2891
	} else {
2892
		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
2893 2894 2895 2896 2897 2898 2899 2900 2901 2902
		adapter->clean_rx = e1000_clean_rx_irq;
		adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
	}

	/* disable receives while setting up the descriptors */
	rctl = er32(RCTL);
	ew32(RCTL, rctl & ~E1000_RCTL_EN);
	e1e_flush();
	msleep(10);

2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925
	if (adapter->flags2 & FLAG2_DMA_BURST) {
		/*
		 * set the writeback threshold (only takes effect if the RDTR
		 * is set). set GRAN=1 and write back up to 0x4 worth, and
		 * enable prefetching of 0x20 rx descriptors
		 * granularity = 01
		 * wthresh = 04,
		 * hthresh = 04,
		 * pthresh = 0x20
		 */
		ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE);
		ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE);

		/*
		 * override the delay timers for enabling bursting, only if
		 * the value was not set by the user via module options
		 */
		if (adapter->rx_int_delay == DEFAULT_RDTR)
			adapter->rx_int_delay = BURST_RDTR;
		if (adapter->rx_abs_int_delay == DEFAULT_RADV)
			adapter->rx_abs_int_delay = BURST_RADV;
	}

2926 2927 2928 2929 2930
	/* set the Receive Delay Timer Register */
	ew32(RDTR, adapter->rx_int_delay);

	/* irq moderation */
	ew32(RADV, adapter->rx_abs_int_delay);
2931
	if ((adapter->itr_setting != 0) && (adapter->itr != 0))
2932
		ew32(ITR, 1000000000 / (adapter->itr * 256));
2933 2934 2935 2936 2937 2938 2939 2940

	ctrl_ext = er32(CTRL_EXT);
	/* Auto-Mask interrupts upon ICR access */
	ctrl_ext |= E1000_CTRL_EXT_IAME;
	ew32(IAM, 0xffffffff);
	ew32(CTRL_EXT, ctrl_ext);
	e1e_flush();

2941 2942 2943 2944
	/*
	 * Setup the HW Rx Head and Tail Descriptor Pointers and
	 * the Base and Length of the Rx Descriptor Ring
	 */
2945
	rdba = rx_ring->dma;
2946
	ew32(RDBAL, (rdba & DMA_BIT_MASK(32)));
2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958
	ew32(RDBAH, (rdba >> 32));
	ew32(RDLEN, rdlen);
	ew32(RDH, 0);
	ew32(RDT, 0);
	rx_ring->head = E1000_RDH;
	rx_ring->tail = E1000_RDT;

	/* Enable Receive Checksum Offload for TCP and UDP */
	rxcsum = er32(RXCSUM);
	if (adapter->flags & FLAG_RX_CSUM_ENABLED) {
		rxcsum |= E1000_RXCSUM_TUOFL;

2959 2960 2961 2962
		/*
		 * IPv4 payload checksum for UDP fragments must be
		 * used in conjunction with packet-split.
		 */
2963 2964 2965 2966 2967 2968 2969 2970
		if (adapter->rx_ps_pages)
			rxcsum |= E1000_RXCSUM_IPPCSE;
	} else {
		rxcsum &= ~E1000_RXCSUM_TUOFL;
		/* no need to clear IPPCSE as it defaults to 0 */
	}
	ew32(RXCSUM, rxcsum);

2971 2972
	/*
	 * Enable early receives on supported devices, only takes effect when
2973
	 * packet size is equal or larger than the specified value (in 8 byte
2974 2975
	 * units), e.g. using jumbo frames when setting to E1000_ERT_2048
	 */
2976 2977
	if ((adapter->flags & FLAG_HAS_ERT) ||
	    (adapter->hw.mac.type == e1000_pch2lan)) {
2978 2979 2980
		if (adapter->netdev->mtu > ETH_DATA_LEN) {
			u32 rxdctl = er32(RXDCTL(0));
			ew32(RXDCTL(0), rxdctl | 0x3);
2981 2982
			if (adapter->flags & FLAG_HAS_ERT)
				ew32(ERT, E1000_ERT_2048 | (1 << 13));
2983 2984 2985 2986 2987
			/*
			 * With jumbo frames and early-receive enabled,
			 * excessive C-state transition latencies result in
			 * dropped transactions.
			 */
M
Mark Gross 已提交
2988
			pm_qos_update_request(
2989
				&adapter->netdev->pm_qos_req, 55);
2990
		} else {
M
Mark Gross 已提交
2991
			pm_qos_update_request(
2992
				&adapter->netdev->pm_qos_req,
M
Mark Gross 已提交
2993
				PM_QOS_DEFAULT_VALUE);
2994
		}
2995
	}
2996 2997 2998 2999 3000 3001

	/* Enable Receives */
	ew32(RCTL, rctl);
}

/**
3002
 *  e1000_update_mc_addr_list - Update Multicast addresses
3003 3004 3005 3006
 *  @hw: pointer to the HW structure
 *  @mc_addr_list: array of multicast addresses to program
 *  @mc_addr_count: number of multicast addresses to program
 *
3007
 *  Updates the Multicast Table Array.
3008 3009
 *  The caller must have a packed mc_addr_list of multicast addresses.
 **/
3010
static void e1000_update_mc_addr_list(struct e1000_hw *hw, u8 *mc_addr_list,
3011
				      u32 mc_addr_count)
3012
{
3013
	hw->mac.ops.update_mc_addr_list(hw, mc_addr_list, mc_addr_count);
3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028
}

/**
 * e1000_set_multi - Multicast and Promiscuous mode set
 * @netdev: network interface device structure
 *
 * The set_multi entry point is called whenever the multicast address
 * list or the network interface flags are updated.  This routine is
 * responsible for configuring the hardware for proper multicast,
 * promiscuous mode, and all-multi behavior.
 **/
static void e1000_set_multi(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
3029
	struct netdev_hw_addr *ha;
3030 3031 3032 3033 3034 3035 3036 3037 3038 3039
	u8  *mta_list;
	u32 rctl;
	int i;

	/* Check for Promiscuous and All Multicast modes */

	rctl = er32(RCTL);

	if (netdev->flags & IFF_PROMISC) {
		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
3040
		rctl &= ~E1000_RCTL_VFE;
3041
	} else {
3042 3043 3044 3045 3046 3047
		if (netdev->flags & IFF_ALLMULTI) {
			rctl |= E1000_RCTL_MPE;
			rctl &= ~E1000_RCTL_UPE;
		} else {
			rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
		}
3048
		if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER)
3049
			rctl |= E1000_RCTL_VFE;
3050 3051 3052 3053
	}

	ew32(RCTL, rctl);

3054 3055
	if (!netdev_mc_empty(netdev)) {
		mta_list = kmalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC);
3056 3057 3058 3059
		if (!mta_list)
			return;

		/* prepare a packed array of only addresses. */
3060
		i = 0;
3061 3062
		netdev_for_each_mc_addr(ha, netdev)
			memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
3063

3064
		e1000_update_mc_addr_list(hw, mta_list, i);
3065 3066 3067 3068 3069 3070
		kfree(mta_list);
	} else {
		/*
		 * if we're called from probe, we might not have
		 * anything to do here, so clear out the list
		 */
3071
		e1000_update_mc_addr_list(hw, NULL, 0);
3072 3073 3074 3075
	}
}

/**
3076
 * e1000_configure - configure the hardware for Rx and Tx
3077 3078 3079 3080 3081 3082 3083
 * @adapter: private board structure
 **/
static void e1000_configure(struct e1000_adapter *adapter)
{
	e1000_set_multi(adapter->netdev);

	e1000_restore_vlan(adapter);
3084
	e1000_init_manageability_pt(adapter);
3085 3086 3087 3088

	e1000_configure_tx(adapter);
	e1000_setup_rctl(adapter);
	e1000_configure_rx(adapter);
3089
	adapter->alloc_rx_buf(adapter, e1000_desc_unused(adapter->rx_ring));
3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101
}

/**
 * e1000e_power_up_phy - restore link in case the phy was powered down
 * @adapter: address of board private structure
 *
 * The phy may be powered down to save power and turn off link when the
 * driver is unloaded and wake on lan is not enabled (among others)
 * *** this routine MUST be followed by a call to e1000e_reset ***
 **/
void e1000e_power_up_phy(struct e1000_adapter *adapter)
{
3102 3103
	if (adapter->hw.phy.ops.power_up)
		adapter->hw.phy.ops.power_up(&adapter->hw);
3104 3105 3106 3107 3108 3109 3110

	adapter->hw.mac.ops.setup_link(&adapter->hw);
}

/**
 * e1000_power_down_phy - Power down the PHY
 *
3111 3112
 * Power down the PHY so no link is implied when interface is down.
 * The PHY cannot be powered down if management or WoL is active.
3113 3114 3115 3116
 */
static void e1000_power_down_phy(struct e1000_adapter *adapter)
{
	/* WoL is enabled */
3117
	if (adapter->wol)
3118 3119
		return;

3120 3121
	if (adapter->hw.phy.ops.power_down)
		adapter->hw.phy.ops.power_down(&adapter->hw);
3122 3123 3124 3125 3126 3127 3128 3129
}

/**
 * e1000e_reset - bring the hardware into a known good state
 *
 * This function boots the hardware and enables some settings that
 * require a configuration cycle of the hardware - those cannot be
 * set/changed during runtime. After reset the device needs to be
3130
 * properly configured for Rx, Tx etc.
3131 3132 3133 3134
 */
void e1000e_reset(struct e1000_adapter *adapter)
{
	struct e1000_mac_info *mac = &adapter->hw.mac;
3135
	struct e1000_fc_info *fc = &adapter->hw.fc;
3136 3137
	struct e1000_hw *hw = &adapter->hw;
	u32 tx_space, min_tx_space, min_rx_space;
3138
	u32 pba = adapter->pba;
3139 3140
	u16 hwm;

3141
	/* reset Packet Buffer Allocation to default */
3142
	ew32(PBA, pba);
3143

3144
	if (adapter->max_frame_size > ETH_FRAME_LEN + ETH_FCS_LEN) {
3145 3146
		/*
		 * To maintain wire speed transmits, the Tx FIFO should be
3147 3148 3149 3150
		 * large enough to accommodate two full transmit packets,
		 * rounded up to the next 1KB and expressed in KB.  Likewise,
		 * the Rx FIFO should be large enough to accommodate at least
		 * one full receive packet and is similarly rounded up and
3151 3152
		 * expressed in KB.
		 */
3153
		pba = er32(PBA);
3154
		/* upper 16 bits has Tx packet buffer allocation size in KB */
3155
		tx_space = pba >> 16;
3156
		/* lower 16 bits has Rx packet buffer allocation size in KB */
3157
		pba &= 0xffff;
3158 3159 3160
		/*
		 * the Tx fifo also stores 16 bytes of information about the tx
		 * but don't include ethernet FCS because hardware appends it
3161 3162
		 */
		min_tx_space = (adapter->max_frame_size +
3163 3164 3165 3166 3167
				sizeof(struct e1000_tx_desc) -
				ETH_FCS_LEN) * 2;
		min_tx_space = ALIGN(min_tx_space, 1024);
		min_tx_space >>= 10;
		/* software strips receive CRC, so leave room for it */
3168
		min_rx_space = adapter->max_frame_size;
3169 3170 3171
		min_rx_space = ALIGN(min_rx_space, 1024);
		min_rx_space >>= 10;

3172 3173
		/*
		 * If current Tx allocation is less than the min Tx FIFO size,
3174
		 * and the min Tx FIFO size is less than the current Rx FIFO
3175 3176
		 * allocation, take space away from current Rx allocation
		 */
3177 3178 3179
		if ((tx_space < min_tx_space) &&
		    ((min_tx_space - tx_space) < pba)) {
			pba -= min_tx_space - tx_space;
3180

3181 3182 3183 3184
			/*
			 * if short on Rx space, Rx wins and must trump tx
			 * adjustment or use Early Receive if available
			 */
3185
			if ((pba < min_rx_space) &&
3186 3187
			    (!(adapter->flags & FLAG_HAS_ERT)))
				/* ERT enabled in e1000_configure_rx */
3188
				pba = min_rx_space;
3189
		}
3190 3191

		ew32(PBA, pba);
3192 3193 3194
	}


3195 3196 3197
	/*
	 * flow control settings
	 *
3198
	 * The high water mark must be low enough to fit one full frame
3199 3200 3201 3202 3203
	 * (or the size used for early receive) above it in the Rx FIFO.
	 * Set it to the lower of:
	 * - 90% of the Rx FIFO size, and
	 * - the full Rx FIFO size minus the early receive size (for parts
	 *   with ERT support assuming ERT set to E1000_ERT_2048), or
3204
	 * - the full Rx FIFO size minus one full frame
3205
	 */
3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226
	if (adapter->flags & FLAG_DISABLE_FC_PAUSE_TIME)
		fc->pause_time = 0xFFFF;
	else
		fc->pause_time = E1000_FC_PAUSE_TIME;
	fc->send_xon = 1;
	fc->current_mode = fc->requested_mode;

	switch (hw->mac.type) {
	default:
		if ((adapter->flags & FLAG_HAS_ERT) &&
		    (adapter->netdev->mtu > ETH_DATA_LEN))
			hwm = min(((pba << 10) * 9 / 10),
				  ((pba << 10) - (E1000_ERT_2048 << 3)));
		else
			hwm = min(((pba << 10) * 9 / 10),
				  ((pba << 10) - adapter->max_frame_size));

		fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */
		fc->low_water = fc->high_water - 8;
		break;
	case e1000_pchlan:
3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237
		/*
		 * Workaround PCH LOM adapter hangs with certain network
		 * loads.  If hangs persist, try disabling Tx flow control.
		 */
		if (adapter->netdev->mtu > ETH_DATA_LEN) {
			fc->high_water = 0x3500;
			fc->low_water  = 0x1500;
		} else {
			fc->high_water = 0x5000;
			fc->low_water  = 0x3000;
		}
3238
		fc->refresh_time = 0x1000;
3239 3240 3241 3242 3243 3244
		break;
	case e1000_pch2lan:
		fc->high_water = 0x05C20;
		fc->low_water = 0x05048;
		fc->pause_time = 0x0650;
		fc->refresh_time = 0x0400;
3245 3246 3247 3248
		if (adapter->netdev->mtu > ETH_DATA_LEN) {
			pba = 14;
			ew32(PBA, pba);
		}
3249
		break;
3250
	}
3251

3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273
	/*
	 * Disable Adaptive Interrupt Moderation if 2 full packets cannot
	 * fit in receive buffer and early-receive not supported.
	 */
	if (adapter->itr_setting & 0x3) {
		if (((adapter->max_frame_size * 2) > (pba << 10)) &&
		    !(adapter->flags & FLAG_HAS_ERT)) {
			if (!(adapter->flags2 & FLAG2_DISABLE_AIM)) {
				dev_info(&adapter->pdev->dev,
					"Interrupt Throttle Rate turned off\n");
				adapter->flags2 |= FLAG2_DISABLE_AIM;
				ew32(ITR, 0);
			}
		} else if (adapter->flags2 & FLAG2_DISABLE_AIM) {
			dev_info(&adapter->pdev->dev,
				 "Interrupt Throttle Rate turned on\n");
			adapter->flags2 &= ~FLAG2_DISABLE_AIM;
			adapter->itr = 20000;
			ew32(ITR, 1000000000 / (adapter->itr * 256));
		}
	}

3274 3275
	/* Allow time for pending master requests to run */
	mac->ops.reset_hw(hw);
3276 3277 3278 3279 3280

	/*
	 * For parts with AMT enabled, let the firmware know
	 * that the network interface is in control
	 */
J
Jesse Brandeburg 已提交
3281
	if (adapter->flags & FLAG_HAS_AMT)
3282 3283
		e1000_get_hw_control(adapter);

3284 3285 3286
	ew32(WUC, 0);

	if (mac->ops.init_hw(hw))
3287
		e_err("Hardware Error\n");
3288 3289 3290 3291 3292 3293 3294 3295 3296

	e1000_update_mng_vlan(adapter);

	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
	ew32(VET, ETH_P_8021Q);

	e1000e_reset_adaptive(hw);
	e1000_get_phy_info(hw);

3297 3298
	if ((adapter->flags & FLAG_HAS_SMART_POWER_DOWN) &&
	    !(adapter->flags & FLAG_SMART_POWER_DOWN)) {
3299
		u16 phy_data = 0;
3300 3301
		/*
		 * speed up time to link by disabling smart power down, ignore
3302
		 * the return value of this function because there is nothing
3303 3304
		 * different we would do if it failed
		 */
3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320
		e1e_rphy(hw, IGP02E1000_PHY_POWER_MGMT, &phy_data);
		phy_data &= ~IGP02E1000_PM_SPD;
		e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data);
	}
}

int e1000e_up(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;

	/* hardware has been reset, we need to reload some things */
	e1000_configure(adapter);

	clear_bit(__E1000_DOWN, &adapter->state);

	napi_enable(&adapter->napi);
3321 3322
	if (adapter->msix_entries)
		e1000_configure_msix(adapter);
3323 3324
	e1000_irq_enable(adapter);

3325 3326
	netif_wake_queue(adapter->netdev);

3327
	/* fire a link change interrupt to start the watchdog */
3328 3329 3330 3331 3332
	if (adapter->msix_entries)
		ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER);
	else
		ew32(ICS, E1000_ICS_LSC);

3333 3334 3335 3336 3337 3338 3339 3340 3341
	return 0;
}

void e1000e_down(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_hw *hw = &adapter->hw;
	u32 tctl, rctl;

3342 3343 3344 3345
	/*
	 * signal that we're down so the interrupt handler does not
	 * reschedule our watchdog timer
	 */
3346 3347 3348 3349 3350 3351 3352
	set_bit(__E1000_DOWN, &adapter->state);

	/* disable receives in the hardware */
	rctl = er32(RCTL);
	ew32(RCTL, rctl & ~E1000_RCTL_EN);
	/* flush and sleep below */

3353
	netif_stop_queue(netdev);
3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372

	/* disable transmits in the hardware */
	tctl = er32(TCTL);
	tctl &= ~E1000_TCTL_EN;
	ew32(TCTL, tctl);
	/* flush both disables and wait for them to finish */
	e1e_flush();
	msleep(10);

	napi_disable(&adapter->napi);
	e1000_irq_disable(adapter);

	del_timer_sync(&adapter->watchdog_timer);
	del_timer_sync(&adapter->phy_info_timer);

	netif_carrier_off(netdev);
	adapter->link_speed = 0;
	adapter->link_duplex = 0;

3373 3374
	if (!pci_channel_offline(adapter->pdev))
		e1000e_reset(adapter);
3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407
	e1000_clean_tx_ring(adapter);
	e1000_clean_rx_ring(adapter);

	/*
	 * TODO: for power management, we could drop the link and
	 * pci_disable_device here.
	 */
}

void e1000e_reinit_locked(struct e1000_adapter *adapter)
{
	might_sleep();
	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
		msleep(1);
	e1000e_down(adapter);
	e1000e_up(adapter);
	clear_bit(__E1000_RESETTING, &adapter->state);
}

/**
 * e1000_sw_init - Initialize general software structures (struct e1000_adapter)
 * @adapter: board private structure to initialize
 *
 * e1000_sw_init initializes the Adapter private data structure.
 * Fields are initialized based on PCI device information and
 * OS network device settings (MTU size).
 **/
static int __devinit e1000_sw_init(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;

	adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN;
	adapter->rx_ps_bsize0 = 128;
3408 3409
	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
3410

3411
	e1000e_set_interrupt_capability(adapter);
3412

3413 3414
	if (e1000_alloc_queues(adapter))
		return -ENOMEM;
3415 3416 3417 3418 3419 3420 3421 3422

	/* Explicitly disable IRQ since the NIC can be in any state. */
	e1000_irq_disable(adapter);

	set_bit(__E1000_DOWN, &adapter->state);
	return 0;
}

3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434
/**
 * e1000_intr_msi_test - Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t e1000_intr_msi_test(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 icr = er32(ICR);

3435
	e_dbg("icr is %08X\n", icr);
3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461
	if (icr & E1000_ICR_RXSEQ) {
		adapter->flags &= ~FLAG_MSI_TEST_FAILED;
		wmb();
	}

	return IRQ_HANDLED;
}

/**
 * e1000_test_msi_interrupt - Returns 0 for successful test
 * @adapter: board private struct
 *
 * code flow taken from tg3.c
 **/
static int e1000_test_msi_interrupt(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_hw *hw = &adapter->hw;
	int err;

	/* poll_enable hasn't been called yet, so don't need disable */
	/* clear any pending events */
	er32(ICR);

	/* free the real vector and request a test handler */
	e1000_free_irq(adapter);
3462
	e1000e_reset_interrupt_capability(adapter);
3463 3464 3465 3466 3467 3468 3469 3470 3471

	/* Assume that the test fails, if it succeeds then the test
	 * MSI irq handler will unset this flag */
	adapter->flags |= FLAG_MSI_TEST_FAILED;

	err = pci_enable_msi(adapter->pdev);
	if (err)
		goto msi_test_failed;

3472
	err = request_irq(adapter->pdev->irq, e1000_intr_msi_test, 0,
3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492
			  netdev->name, netdev);
	if (err) {
		pci_disable_msi(adapter->pdev);
		goto msi_test_failed;
	}

	wmb();

	e1000_irq_enable(adapter);

	/* fire an unusual interrupt on the test handler */
	ew32(ICS, E1000_ICS_RXSEQ);
	e1e_flush();
	msleep(50);

	e1000_irq_disable(adapter);

	rmb();

	if (adapter->flags & FLAG_MSI_TEST_FAILED) {
3493
		adapter->int_mode = E1000E_INT_MODE_LEGACY;
3494 3495 3496
		e_info("MSI interrupt test failed, using legacy interrupt.\n");
	} else
		e_dbg("MSI interrupt test succeeded!\n");
3497 3498 3499 3500 3501

	free_irq(adapter->pdev->irq, netdev);
	pci_disable_msi(adapter->pdev);

msi_test_failed:
3502
	e1000e_set_interrupt_capability(adapter);
3503
	return e1000_request_irq(adapter);
3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521
}

/**
 * e1000_test_msi - Returns 0 if MSI test succeeds or INTx mode is restored
 * @adapter: board private struct
 *
 * code flow taken from tg3.c, called with e1000 interrupts disabled.
 **/
static int e1000_test_msi(struct e1000_adapter *adapter)
{
	int err;
	u16 pci_cmd;

	if (!(adapter->flags & FLAG_MSI_ENABLED))
		return 0;

	/* disable SERR in case the MSI write causes a master abort */
	pci_read_config_word(adapter->pdev, PCI_COMMAND, &pci_cmd);
3522 3523 3524
	if (pci_cmd & PCI_COMMAND_SERR)
		pci_write_config_word(adapter->pdev, PCI_COMMAND,
				      pci_cmd & ~PCI_COMMAND_SERR);
3525 3526 3527

	err = e1000_test_msi_interrupt(adapter);

3528 3529 3530 3531 3532 3533
	/* re-enable SERR */
	if (pci_cmd & PCI_COMMAND_SERR) {
		pci_read_config_word(adapter->pdev, PCI_COMMAND, &pci_cmd);
		pci_cmd |= PCI_COMMAND_SERR;
		pci_write_config_word(adapter->pdev, PCI_COMMAND, pci_cmd);
	}
3534 3535 3536 3537

	return err;
}

3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553
/**
 * e1000_open - Called when a network interface is made active
 * @netdev: network interface device structure
 *
 * Returns 0 on success, negative value on failure
 *
 * The open entry point is called when a network interface is made
 * active by the system (IFF_UP).  At this point all resources needed
 * for transmit and receive operations are allocated, the interrupt
 * handler is registered with the OS, the watchdog timer is started,
 * and the stack is notified that the interface is ready.
 **/
static int e1000_open(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
3554
	struct pci_dev *pdev = adapter->pdev;
3555 3556 3557 3558 3559 3560
	int err;

	/* disallow open during test */
	if (test_bit(__E1000_TESTING, &adapter->state))
		return -EBUSY;

3561 3562
	pm_runtime_get_sync(&pdev->dev);

3563 3564
	netif_carrier_off(netdev);

3565 3566 3567 3568 3569 3570 3571 3572 3573 3574
	/* allocate transmit descriptors */
	err = e1000e_setup_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

	/* allocate receive descriptors */
	err = e1000e_setup_rx_resources(adapter);
	if (err)
		goto err_setup_rx;

3575 3576 3577 3578 3579 3580 3581 3582 3583
	/*
	 * If AMT is enabled, let the firmware know that the network
	 * interface is now open and reset the part to a known state.
	 */
	if (adapter->flags & FLAG_HAS_AMT) {
		e1000_get_hw_control(adapter);
		e1000e_reset(adapter);
	}

3584 3585 3586 3587 3588 3589 3590
	e1000e_power_up_phy(adapter);

	adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN))
		e1000_update_mng_vlan(adapter);

3591
	/* DMA latency requirement to workaround early-receive/jumbo issue */
3592 3593
	if ((adapter->flags & FLAG_HAS_ERT) ||
	    (adapter->hw.mac.type == e1000_pch2lan))
3594 3595 3596
		pm_qos_add_request(&adapter->netdev->pm_qos_req,
				   PM_QOS_CPU_DMA_LATENCY,
				   PM_QOS_DEFAULT_VALUE);
3597

3598 3599
	/*
	 * before we allocate an interrupt, we must be ready to handle it.
3600 3601
	 * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
	 * as soon as we call pci_request_irq, so we have to setup our
3602 3603
	 * clean_rx handler before we do so.
	 */
3604 3605 3606 3607 3608 3609
	e1000_configure(adapter);

	err = e1000_request_irq(adapter);
	if (err)
		goto err_req_irq;

3610 3611 3612 3613 3614
	/*
	 * Work around PCIe errata with MSI interrupts causing some chipsets to
	 * ignore e1000e MSI messages, which means we need to test our MSI
	 * interrupt now
	 */
3615
	if (adapter->int_mode != E1000E_INT_MODE_LEGACY) {
3616 3617 3618 3619 3620 3621 3622
		err = e1000_test_msi(adapter);
		if (err) {
			e_err("Interrupt allocation failed\n");
			goto err_req_irq;
		}
	}

3623 3624 3625 3626 3627 3628 3629
	/* From here on the code is the same as e1000e_up() */
	clear_bit(__E1000_DOWN, &adapter->state);

	napi_enable(&adapter->napi);

	e1000_irq_enable(adapter);

3630
	netif_start_queue(netdev);
3631

3632 3633 3634
	adapter->idle_check = true;
	pm_runtime_put(&pdev->dev);

3635
	/* fire a link status change interrupt to start the watchdog */
3636 3637 3638 3639
	if (adapter->msix_entries)
		ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER);
	else
		ew32(ICS, E1000_ICS_LSC);
3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650

	return 0;

err_req_irq:
	e1000_release_hw_control(adapter);
	e1000_power_down_phy(adapter);
	e1000e_free_rx_resources(adapter);
err_setup_rx:
	e1000e_free_tx_resources(adapter);
err_setup_tx:
	e1000e_reset(adapter);
3651
	pm_runtime_put_sync(&pdev->dev);
3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669

	return err;
}

/**
 * e1000_close - Disables a network interface
 * @netdev: network interface device structure
 *
 * Returns 0, this is not allowed to fail
 *
 * The close entry point is called when an interface is de-activated
 * by the OS.  The hardware is still under the drivers control, but
 * needs to be disabled.  A global MAC reset is issued to stop the
 * hardware, and all transmit and receive resources are freed.
 **/
static int e1000_close(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
3670
	struct pci_dev *pdev = adapter->pdev;
3671 3672

	WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
3673 3674 3675 3676 3677 3678 3679

	pm_runtime_get_sync(&pdev->dev);

	if (!test_bit(__E1000_DOWN, &adapter->state)) {
		e1000e_down(adapter);
		e1000_free_irq(adapter);
	}
3680 3681 3682 3683 3684
	e1000_power_down_phy(adapter);

	e1000e_free_tx_resources(adapter);
	e1000e_free_rx_resources(adapter);

3685 3686 3687 3688
	/*
	 * kill manageability vlan ID if supported, but not if a vlan with
	 * the same ID is registered on the host OS (let 8021q kill it)
	 */
3689 3690 3691 3692 3693 3694
	if ((adapter->hw.mng_cookie.status &
			  E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
	     !(adapter->vlgrp &&
	       vlan_group_get_device(adapter->vlgrp, adapter->mng_vlan_id)))
		e1000_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id);

3695 3696 3697 3698
	/*
	 * If AMT is enabled, let the firmware know that the network
	 * interface is now closed
	 */
J
Jesse Brandeburg 已提交
3699
	if (adapter->flags & FLAG_HAS_AMT)
3700 3701
		e1000_release_hw_control(adapter);

3702 3703
	if ((adapter->flags & FLAG_HAS_ERT) ||
	    (adapter->hw.mac.type == e1000_pch2lan))
3704
		pm_qos_remove_request(&adapter->netdev->pm_qos_req);
3705

3706 3707
	pm_runtime_put_sync(&pdev->dev);

3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733
	return 0;
}
/**
 * e1000_set_mac - Change the Ethernet Address of the NIC
 * @netdev: network interface device structure
 * @p: pointer to an address structure
 *
 * Returns 0 on success, negative on failure
 **/
static int e1000_set_mac(struct net_device *netdev, void *p)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct sockaddr *addr = p;

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

	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
	memcpy(adapter->hw.mac.addr, addr->sa_data, netdev->addr_len);

	e1000e_rar_set(&adapter->hw, adapter->hw.mac.addr, 0);

	if (adapter->flags & FLAG_RESET_OVERWRITES_LAA) {
		/* activate the work around */
		e1000e_set_laa_state_82571(&adapter->hw, 1);

3734 3735
		/*
		 * Hold a copy of the LAA in RAR[14] This is done so that
3736 3737 3738 3739
		 * between the time RAR[0] gets clobbered  and the time it
		 * gets fixed (in e1000_watchdog), the actual LAA is in one
		 * of the RARs and no incoming packets directed to this port
		 * are dropped. Eventually the LAA will be in RAR[0] and
3740 3741
		 * RAR[14]
		 */
3742 3743 3744 3745 3746 3747 3748 3749
		e1000e_rar_set(&adapter->hw,
			      adapter->hw.mac.addr,
			      adapter->hw.mac.rar_entry_count - 1);
	}

	return 0;
}

3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764
/**
 * e1000e_update_phy_task - work thread to update phy
 * @work: pointer to our work struct
 *
 * this worker thread exists because we must acquire a
 * semaphore to read the phy, which we could msleep while
 * waiting for it, and we can't msleep in a timer.
 **/
static void e1000e_update_phy_task(struct work_struct *work)
{
	struct e1000_adapter *adapter = container_of(work,
					struct e1000_adapter, update_phy_task);
	e1000_get_phy_info(&adapter->hw);
}

3765 3766 3767 3768
/*
 * Need to wait a few seconds after link up to get diagnostic information from
 * the phy
 */
3769 3770 3771
static void e1000_update_phy_info(unsigned long data)
{
	struct e1000_adapter *adapter = (struct e1000_adapter *) data;
3772
	schedule_work(&adapter->update_phy_task);
3773 3774
}

3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878
/**
 * e1000e_update_phy_stats - Update the PHY statistics counters
 * @adapter: board private structure
 **/
static void e1000e_update_phy_stats(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	s32 ret_val;
	u16 phy_data;

	ret_val = hw->phy.ops.acquire(hw);
	if (ret_val)
		return;

	hw->phy.addr = 1;

#define HV_PHY_STATS_PAGE	778
	/*
	 * A page set is expensive so check if already on desired page.
	 * If not, set to the page with the PHY status registers.
	 */
	ret_val = e1000e_read_phy_reg_mdic(hw, IGP01E1000_PHY_PAGE_SELECT,
					   &phy_data);
	if (ret_val)
		goto release;
	if (phy_data != (HV_PHY_STATS_PAGE << IGP_PAGE_SHIFT)) {
		ret_val = e1000e_write_phy_reg_mdic(hw,
						    IGP01E1000_PHY_PAGE_SELECT,
						    (HV_PHY_STATS_PAGE <<
						     IGP_PAGE_SHIFT));
		if (ret_val)
			goto release;
	}

	/* Read/clear the upper 16-bit registers and read/accumulate lower */

	/* Single Collision Count */
	e1000e_read_phy_reg_mdic(hw, HV_SCC_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_SCC_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.scc += phy_data;

	/* Excessive Collision Count */
	e1000e_read_phy_reg_mdic(hw, HV_ECOL_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_ECOL_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.ecol += phy_data;

	/* Multiple Collision Count */
	e1000e_read_phy_reg_mdic(hw, HV_MCC_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_MCC_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.mcc += phy_data;

	/* Late Collision Count */
	e1000e_read_phy_reg_mdic(hw, HV_LATECOL_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_LATECOL_LOWER &
					   MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.latecol += phy_data;

	/* Collision Count - also used for adaptive IFS */
	e1000e_read_phy_reg_mdic(hw, HV_COLC_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_COLC_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		hw->mac.collision_delta = phy_data;

	/* Defer Count */
	e1000e_read_phy_reg_mdic(hw, HV_DC_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_DC_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.dc += phy_data;

	/* Transmit with no CRS */
	e1000e_read_phy_reg_mdic(hw, HV_TNCRS_UPPER & MAX_PHY_REG_ADDRESS,
				 &phy_data);
	ret_val = e1000e_read_phy_reg_mdic(hw,
					   HV_TNCRS_LOWER & MAX_PHY_REG_ADDRESS,
					   &phy_data);
	if (!ret_val)
		adapter->stats.tncrs += phy_data;

release:
	hw->phy.ops.release(hw);
}

3879 3880 3881 3882 3883 3884
/**
 * e1000e_update_stats - Update the board statistics counters
 * @adapter: board private structure
 **/
void e1000e_update_stats(struct e1000_adapter *adapter)
{
3885
	struct net_device *netdev = adapter->netdev;
3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899
	struct e1000_hw *hw = &adapter->hw;
	struct pci_dev *pdev = adapter->pdev;

	/*
	 * Prevent stats update while adapter is being reset, or if the pci
	 * connection is down.
	 */
	if (adapter->link_speed == 0)
		return;
	if (pci_channel_offline(pdev))
		return;

	adapter->stats.crcerrs += er32(CRCERRS);
	adapter->stats.gprc += er32(GPRC);
3900 3901
	adapter->stats.gorc += er32(GORCL);
	er32(GORCH); /* Clear gorc */
3902 3903 3904 3905 3906
	adapter->stats.bprc += er32(BPRC);
	adapter->stats.mprc += er32(MPRC);
	adapter->stats.roc += er32(ROC);

	adapter->stats.mpc += er32(MPC);
3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925

	/* Half-duplex statistics */
	if (adapter->link_duplex == HALF_DUPLEX) {
		if (adapter->flags2 & FLAG2_HAS_PHY_STATS) {
			e1000e_update_phy_stats(adapter);
		} else {
			adapter->stats.scc += er32(SCC);
			adapter->stats.ecol += er32(ECOL);
			adapter->stats.mcc += er32(MCC);
			adapter->stats.latecol += er32(LATECOL);
			adapter->stats.dc += er32(DC);

			hw->mac.collision_delta = er32(COLC);

			if ((hw->mac.type != e1000_82574) &&
			    (hw->mac.type != e1000_82583))
				adapter->stats.tncrs += er32(TNCRS);
		}
		adapter->stats.colc += hw->mac.collision_delta;
3926
	}
3927

3928 3929 3930 3931 3932
	adapter->stats.xonrxc += er32(XONRXC);
	adapter->stats.xontxc += er32(XONTXC);
	adapter->stats.xoffrxc += er32(XOFFRXC);
	adapter->stats.xofftxc += er32(XOFFTXC);
	adapter->stats.gptc += er32(GPTC);
3933 3934
	adapter->stats.gotc += er32(GOTCL);
	er32(GOTCH); /* Clear gotc */
3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952
	adapter->stats.rnbc += er32(RNBC);
	adapter->stats.ruc += er32(RUC);

	adapter->stats.mptc += er32(MPTC);
	adapter->stats.bptc += er32(BPTC);

	/* used for adaptive IFS */

	hw->mac.tx_packet_delta = er32(TPT);
	adapter->stats.tpt += hw->mac.tx_packet_delta;

	adapter->stats.algnerrc += er32(ALGNERRC);
	adapter->stats.rxerrc += er32(RXERRC);
	adapter->stats.cexterr += er32(CEXTERR);
	adapter->stats.tsctc += er32(TSCTC);
	adapter->stats.tsctfc += er32(TSCTFC);

	/* Fill out the OS statistics structure */
3953 3954
	netdev->stats.multicast = adapter->stats.mprc;
	netdev->stats.collisions = adapter->stats.colc;
3955 3956 3957

	/* Rx Errors */

3958 3959 3960 3961
	/*
	 * RLEC on some newer hardware can be incorrect so build
	 * our own version based on RUC and ROC
	 */
3962
	netdev->stats.rx_errors = adapter->stats.rxerrc +
3963 3964 3965
		adapter->stats.crcerrs + adapter->stats.algnerrc +
		adapter->stats.ruc + adapter->stats.roc +
		adapter->stats.cexterr;
3966
	netdev->stats.rx_length_errors = adapter->stats.ruc +
3967
					      adapter->stats.roc;
3968 3969 3970
	netdev->stats.rx_crc_errors = adapter->stats.crcerrs;
	netdev->stats.rx_frame_errors = adapter->stats.algnerrc;
	netdev->stats.rx_missed_errors = adapter->stats.mpc;
3971 3972

	/* Tx Errors */
3973
	netdev->stats.tx_errors = adapter->stats.ecol +
3974
				       adapter->stats.latecol;
3975 3976 3977
	netdev->stats.tx_aborted_errors = adapter->stats.ecol;
	netdev->stats.tx_window_errors = adapter->stats.latecol;
	netdev->stats.tx_carrier_errors = adapter->stats.tncrs;
3978 3979 3980 3981 3982 3983 3984 3985 3986

	/* Tx Dropped needs to be maintained elsewhere */

	/* Management Stats */
	adapter->stats.mgptc += er32(MGTPTC);
	adapter->stats.mgprc += er32(MGTPRC);
	adapter->stats.mgpdc += er32(MGTPDC);
}

3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007
/**
 * e1000_phy_read_status - Update the PHY register status snapshot
 * @adapter: board private structure
 **/
static void e1000_phy_read_status(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_phy_regs *phy = &adapter->phy_regs;
	int ret_val;

	if ((er32(STATUS) & E1000_STATUS_LU) &&
	    (adapter->hw.phy.media_type == e1000_media_type_copper)) {
		ret_val  = e1e_rphy(hw, PHY_CONTROL, &phy->bmcr);
		ret_val |= e1e_rphy(hw, PHY_STATUS, &phy->bmsr);
		ret_val |= e1e_rphy(hw, PHY_AUTONEG_ADV, &phy->advertise);
		ret_val |= e1e_rphy(hw, PHY_LP_ABILITY, &phy->lpa);
		ret_val |= e1e_rphy(hw, PHY_AUTONEG_EXP, &phy->expansion);
		ret_val |= e1e_rphy(hw, PHY_1000T_CTRL, &phy->ctrl1000);
		ret_val |= e1e_rphy(hw, PHY_1000T_STATUS, &phy->stat1000);
		ret_val |= e1e_rphy(hw, PHY_EXT_STATUS, &phy->estatus);
		if (ret_val)
4008
			e_warn("Error reading PHY register\n");
4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027
	} else {
		/*
		 * Do not read PHY registers if link is not up
		 * Set values to typical power-on defaults
		 */
		phy->bmcr = (BMCR_SPEED1000 | BMCR_ANENABLE | BMCR_FULLDPLX);
		phy->bmsr = (BMSR_100FULL | BMSR_100HALF | BMSR_10FULL |
			     BMSR_10HALF | BMSR_ESTATEN | BMSR_ANEGCAPABLE |
			     BMSR_ERCAP);
		phy->advertise = (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP |
				  ADVERTISE_ALL | ADVERTISE_CSMA);
		phy->lpa = 0;
		phy->expansion = EXPANSION_ENABLENPAGE;
		phy->ctrl1000 = ADVERTISE_1000FULL;
		phy->stat1000 = 0;
		phy->estatus = (ESTATUS_1000_TFULL | ESTATUS_1000_THALF);
	}
}

4028 4029 4030 4031 4032
static void e1000_print_link_info(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl = er32(CTRL);

4033 4034 4035 4036
	/* Link status message must follow this format for user tools */
	printk(KERN_INFO "e1000e: %s NIC Link is Up %d Mbps %s, "
	       "Flow Control: %s\n",
	       adapter->netdev->name,
4037 4038 4039 4040 4041 4042 4043
	       adapter->link_speed,
	       (adapter->link_duplex == FULL_DUPLEX) ?
	                        "Full Duplex" : "Half Duplex",
	       ((ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE)) ?
	                        "RX/TX" :
	       ((ctrl & E1000_CTRL_RFCE) ? "RX" :
	       ((ctrl & E1000_CTRL_TFCE) ? "TX" : "None" )));
4044 4045
}

4046
static bool e1000e_has_link(struct e1000_adapter *adapter)
4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082
{
	struct e1000_hw *hw = &adapter->hw;
	bool link_active = 0;
	s32 ret_val = 0;

	/*
	 * get_link_status is set on LSC (link status) interrupt or
	 * Rx sequence error interrupt.  get_link_status will stay
	 * false until the check_for_link establishes link
	 * for copper adapters ONLY
	 */
	switch (hw->phy.media_type) {
	case e1000_media_type_copper:
		if (hw->mac.get_link_status) {
			ret_val = hw->mac.ops.check_for_link(hw);
			link_active = !hw->mac.get_link_status;
		} else {
			link_active = 1;
		}
		break;
	case e1000_media_type_fiber:
		ret_val = hw->mac.ops.check_for_link(hw);
		link_active = !!(er32(STATUS) & E1000_STATUS_LU);
		break;
	case e1000_media_type_internal_serdes:
		ret_val = hw->mac.ops.check_for_link(hw);
		link_active = adapter->hw.mac.serdes_has_link;
		break;
	default:
	case e1000_media_type_unknown:
		break;
	}

	if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) &&
	    (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) {
		/* See e1000_kmrn_lock_loss_workaround_ich8lan() */
4083
		e_info("Gigabit has been disabled, downgrading speed\n");
4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100
	}

	return link_active;
}

static void e1000e_enable_receives(struct e1000_adapter *adapter)
{
	/* make sure the receive unit is started */
	if ((adapter->flags & FLAG_RX_NEEDS_RESTART) &&
	    (adapter->flags & FLAG_RX_RESTART_NOW)) {
		struct e1000_hw *hw = &adapter->hw;
		u32 rctl = er32(RCTL);
		ew32(RCTL, rctl | E1000_RCTL_EN);
		adapter->flags &= ~FLAG_RX_RESTART_NOW;
	}
}

4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120
/**
 * e1000_watchdog - Timer Call-back
 * @data: pointer to adapter cast into an unsigned long
 **/
static void e1000_watchdog(unsigned long data)
{
	struct e1000_adapter *adapter = (struct e1000_adapter *) data;

	/* Do the rest outside of interrupt context */
	schedule_work(&adapter->watchdog_task);

	/* TODO: make this use queue_delayed_work() */
}

static void e1000_watchdog_task(struct work_struct *work)
{
	struct e1000_adapter *adapter = container_of(work,
					struct e1000_adapter, watchdog_task);
	struct net_device *netdev = adapter->netdev;
	struct e1000_mac_info *mac = &adapter->hw.mac;
B
Bruce Allan 已提交
4121
	struct e1000_phy_info *phy = &adapter->hw.phy;
4122 4123 4124 4125 4126
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_hw *hw = &adapter->hw;
	u32 link, tctl;
	int tx_pending = 0;

4127
	link = e1000e_has_link(adapter);
4128
	if ((netif_carrier_ok(netdev)) && link) {
4129 4130 4131
		/* Cancel scheduled suspend requests. */
		pm_runtime_resume(netdev->dev.parent);

4132
		e1000e_enable_receives(adapter);
4133 4134 4135 4136 4137 4138 4139 4140 4141 4142
		goto link_up;
	}

	if ((e1000e_enable_tx_pkt_filtering(hw)) &&
	    (adapter->mng_vlan_id != adapter->hw.mng_cookie.vlan_id))
		e1000_update_mng_vlan(adapter);

	if (link) {
		if (!netif_carrier_ok(netdev)) {
			bool txb2b = 1;
4143 4144 4145 4146

			/* Cancel scheduled suspend requests. */
			pm_runtime_resume(netdev->dev.parent);

4147
			/* update snapshot of PHY registers on LSC */
4148
			e1000_phy_read_status(adapter);
4149 4150 4151 4152
			mac->ops.get_link_up_info(&adapter->hw,
						   &adapter->link_speed,
						   &adapter->link_duplex);
			e1000_print_link_info(adapter);
4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173
			/*
			 * On supported PHYs, check for duplex mismatch only
			 * if link has autonegotiated at 10/100 half
			 */
			if ((hw->phy.type == e1000_phy_igp_3 ||
			     hw->phy.type == e1000_phy_bm) &&
			    (hw->mac.autoneg == true) &&
			    (adapter->link_speed == SPEED_10 ||
			     adapter->link_speed == SPEED_100) &&
			    (adapter->link_duplex == HALF_DUPLEX)) {
				u16 autoneg_exp;

				e1e_rphy(hw, PHY_AUTONEG_EXP, &autoneg_exp);

				if (!(autoneg_exp & NWAY_ER_LP_NWAY_CAPS))
					e_info("Autonegotiated half duplex but"
					       " link partner cannot autoneg. "
					       " Try forcing full duplex if "
					       "link gets many collisions.\n");
			}

4174
			/* adjust timeout factor according to speed/duplex */
4175 4176 4177 4178
			adapter->tx_timeout_factor = 1;
			switch (adapter->link_speed) {
			case SPEED_10:
				txb2b = 0;
4179
				adapter->tx_timeout_factor = 16;
4180 4181 4182
				break;
			case SPEED_100:
				txb2b = 0;
4183
				adapter->tx_timeout_factor = 10;
4184 4185 4186
				break;
			}

4187 4188 4189 4190
			/*
			 * workaround: re-program speed mode bit after
			 * link-up event
			 */
4191 4192 4193
			if ((adapter->flags & FLAG_TARC_SPEED_MODE_BIT) &&
			    !txb2b) {
				u32 tarc0;
4194
				tarc0 = er32(TARC(0));
4195
				tarc0 &= ~SPEED_MODE_BIT;
4196
				ew32(TARC(0), tarc0);
4197 4198
			}

4199 4200 4201 4202
			/*
			 * disable TSO for pcie and 10/100 speeds, to avoid
			 * some hardware issues
			 */
4203 4204 4205 4206
			if (!(adapter->flags & FLAG_TSO_FORCE)) {
				switch (adapter->link_speed) {
				case SPEED_10:
				case SPEED_100:
4207
					e_info("10/100 speed: disabling TSO\n");
4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220
					netdev->features &= ~NETIF_F_TSO;
					netdev->features &= ~NETIF_F_TSO6;
					break;
				case SPEED_1000:
					netdev->features |= NETIF_F_TSO;
					netdev->features |= NETIF_F_TSO6;
					break;
				default:
					/* oops */
					break;
				}
			}

4221 4222 4223 4224
			/*
			 * enable transmits in the hardware, need to do this
			 * after setting TARC(0)
			 */
4225 4226 4227 4228
			tctl = er32(TCTL);
			tctl |= E1000_TCTL_EN;
			ew32(TCTL, tctl);

B
Bruce Allan 已提交
4229 4230 4231 4232 4233 4234 4235
                        /*
			 * Perform any post-link-up configuration before
			 * reporting link up.
			 */
			if (phy->ops.cfg_on_link_up)
				phy->ops.cfg_on_link_up(hw);

4236 4237 4238 4239 4240 4241 4242 4243 4244 4245
			netif_carrier_on(netdev);

			if (!test_bit(__E1000_DOWN, &adapter->state))
				mod_timer(&adapter->phy_info_timer,
					  round_jiffies(jiffies + 2 * HZ));
		}
	} else {
		if (netif_carrier_ok(netdev)) {
			adapter->link_speed = 0;
			adapter->link_duplex = 0;
4246 4247 4248
			/* Link status message must follow this format */
			printk(KERN_INFO "e1000e: %s NIC Link is Down\n",
			       adapter->netdev->name);
4249 4250 4251 4252 4253 4254 4255
			netif_carrier_off(netdev);
			if (!test_bit(__E1000_DOWN, &adapter->state))
				mod_timer(&adapter->phy_info_timer,
					  round_jiffies(jiffies + 2 * HZ));

			if (adapter->flags & FLAG_RX_NEEDS_RESTART)
				schedule_work(&adapter->reset_task);
4256 4257 4258
			else
				pm_schedule_suspend(netdev->dev.parent,
							LINK_TIMEOUT);
4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269
		}
	}

link_up:
	e1000e_update_stats(adapter);

	mac->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old;
	adapter->tpt_old = adapter->stats.tpt;
	mac->collision_delta = adapter->stats.colc - adapter->colc_old;
	adapter->colc_old = adapter->stats.colc;

4270 4271 4272 4273
	adapter->gorc = adapter->stats.gorc - adapter->gorc_old;
	adapter->gorc_old = adapter->stats.gorc;
	adapter->gotc = adapter->stats.gotc - adapter->gotc_old;
	adapter->gotc_old = adapter->stats.gotc;
4274 4275 4276 4277 4278 4279 4280

	e1000e_update_adaptive(&adapter->hw);

	if (!netif_carrier_ok(netdev)) {
		tx_pending = (e1000_desc_unused(tx_ring) + 1 <
			       tx_ring->count);
		if (tx_pending) {
4281 4282
			/*
			 * We've lost link, so the controller stops DMA,
4283 4284
			 * but we've got queued Tx work that's never going
			 * to get done, so reset controller to flush Tx.
4285 4286
			 * (Do the reset outside of interrupt context).
			 */
4287 4288
			adapter->tx_timeout_count++;
			schedule_work(&adapter->reset_task);
4289 4290
			/* return immediately since reset is imminent */
			return;
4291 4292 4293
		}
	}

4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309
	/* Simple mode for Interrupt Throttle Rate (ITR) */
	if (adapter->itr_setting == 4) {
		/*
		 * Symmetric Tx/Rx gets a reduced ITR=2000;
		 * Total asymmetrical Tx or Rx gets ITR=8000;
		 * everyone else is between 2000-8000.
		 */
		u32 goc = (adapter->gotc + adapter->gorc) / 10000;
		u32 dif = (adapter->gotc > adapter->gorc ?
			    adapter->gotc - adapter->gorc :
			    adapter->gorc - adapter->gotc) / 10000;
		u32 itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000;

		ew32(ITR, 1000000000 / (itr * 256));
	}

4310
	/* Cause software interrupt to ensure Rx ring is cleaned */
4311 4312 4313 4314
	if (adapter->msix_entries)
		ew32(ICS, adapter->rx_ring->ims_val);
	else
		ew32(ICS, E1000_ICS_RXDMT0);
4315 4316 4317 4318

	/* Force detection of hung controller every watchdog period */
	adapter->detect_tx_hung = 1;

4319 4320 4321 4322 4323 4324 4325 4326 4327 4328
	/* flush partial descriptors to memory before detecting tx hang */
	if (adapter->flags2 & FLAG2_DMA_BURST) {
		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
		ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
		/*
		 * no need to flush the writes because the timeout code does
		 * an er32 first thing
		 */
	}

4329 4330 4331 4332
	/*
	 * With 82571 controllers, LAA may be overwritten due to controller
	 * reset from the other port. Set the appropriate LAA in RAR[0]
	 */
4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360
	if (e1000e_get_laa_state_82571(hw))
		e1000e_rar_set(hw, adapter->hw.mac.addr, 0);

	/* Reset the timer */
	if (!test_bit(__E1000_DOWN, &adapter->state))
		mod_timer(&adapter->watchdog_timer,
			  round_jiffies(jiffies + 2 * HZ));
}

#define E1000_TX_FLAGS_CSUM		0x00000001
#define E1000_TX_FLAGS_VLAN		0x00000002
#define E1000_TX_FLAGS_TSO		0x00000004
#define E1000_TX_FLAGS_IPV4		0x00000008
#define E1000_TX_FLAGS_VLAN_MASK	0xffff0000
#define E1000_TX_FLAGS_VLAN_SHIFT	16

static int e1000_tso(struct e1000_adapter *adapter,
		     struct sk_buff *skb)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_context_desc *context_desc;
	struct e1000_buffer *buffer_info;
	unsigned int i;
	u32 cmd_length = 0;
	u16 ipcse = 0, tucse, mss;
	u8 ipcss, ipcso, tucss, tucso, hdr_len;
	int err;

4361 4362
	if (!skb_is_gso(skb))
		return 0;
4363

4364 4365 4366 4367
	if (skb_header_cloned(skb)) {
		err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (err)
			return err;
4368 4369
	}

4370 4371 4372 4373 4374 4375 4376 4377 4378 4379
	hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
	mss = skb_shinfo(skb)->gso_size;
	if (skb->protocol == htons(ETH_P_IP)) {
		struct iphdr *iph = ip_hdr(skb);
		iph->tot_len = 0;
		iph->check = 0;
		tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
		                                         0, IPPROTO_TCP, 0);
		cmd_length = E1000_TXD_CMD_IP;
		ipcse = skb_transport_offset(skb) - 1;
4380
	} else if (skb_is_gso_v6(skb)) {
4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418
		ipv6_hdr(skb)->payload_len = 0;
		tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
		                                       &ipv6_hdr(skb)->daddr,
		                                       0, IPPROTO_TCP, 0);
		ipcse = 0;
	}
	ipcss = skb_network_offset(skb);
	ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data;
	tucss = skb_transport_offset(skb);
	tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data;
	tucse = 0;

	cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE |
	               E1000_TXD_CMD_TCP | (skb->len - (hdr_len)));

	i = tx_ring->next_to_use;
	context_desc = E1000_CONTEXT_DESC(*tx_ring, i);
	buffer_info = &tx_ring->buffer_info[i];

	context_desc->lower_setup.ip_fields.ipcss  = ipcss;
	context_desc->lower_setup.ip_fields.ipcso  = ipcso;
	context_desc->lower_setup.ip_fields.ipcse  = cpu_to_le16(ipcse);
	context_desc->upper_setup.tcp_fields.tucss = tucss;
	context_desc->upper_setup.tcp_fields.tucso = tucso;
	context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse);
	context_desc->tcp_seg_setup.fields.mss     = cpu_to_le16(mss);
	context_desc->tcp_seg_setup.fields.hdr_len = hdr_len;
	context_desc->cmd_and_length = cpu_to_le32(cmd_length);

	buffer_info->time_stamp = jiffies;
	buffer_info->next_to_watch = i;

	i++;
	if (i == tx_ring->count)
		i = 0;
	tx_ring->next_to_use = i;

	return 1;
4419 4420 4421 4422 4423 4424 4425 4426 4427
}

static bool e1000_tx_csum(struct e1000_adapter *adapter, struct sk_buff *skb)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_context_desc *context_desc;
	struct e1000_buffer *buffer_info;
	unsigned int i;
	u8 css;
4428
	u32 cmd_len = E1000_TXD_CMD_DEXT;
4429
	__be16 protocol;
4430

4431 4432
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;
4433

4434 4435 4436 4437 4438
	if (skb->protocol == cpu_to_be16(ETH_P_8021Q))
		protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
	else
		protocol = skb->protocol;

A
Arthur Jones 已提交
4439
	switch (protocol) {
4440
	case cpu_to_be16(ETH_P_IP):
4441 4442 4443
		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
			cmd_len |= E1000_TXD_CMD_TCP;
		break;
4444
	case cpu_to_be16(ETH_P_IPV6):
4445 4446 4447 4448 4449 4450
		/* XXX not handling all IPV6 headers */
		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
			cmd_len |= E1000_TXD_CMD_TCP;
		break;
	default:
		if (unlikely(net_ratelimit()))
4451 4452
			e_warn("checksum_partial proto=%x!\n",
			       be16_to_cpu(protocol));
4453
		break;
4454 4455
	}

4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478
	css = skb_transport_offset(skb);

	i = tx_ring->next_to_use;
	buffer_info = &tx_ring->buffer_info[i];
	context_desc = E1000_CONTEXT_DESC(*tx_ring, i);

	context_desc->lower_setup.ip_config = 0;
	context_desc->upper_setup.tcp_fields.tucss = css;
	context_desc->upper_setup.tcp_fields.tucso =
				css + skb->csum_offset;
	context_desc->upper_setup.tcp_fields.tucse = 0;
	context_desc->tcp_seg_setup.data = 0;
	context_desc->cmd_and_length = cpu_to_le32(cmd_len);

	buffer_info->time_stamp = jiffies;
	buffer_info->next_to_watch = i;

	i++;
	if (i == tx_ring->count)
		i = 0;
	tx_ring->next_to_use = i;

	return 1;
4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489
}

#define E1000_MAX_PER_TXD	8192
#define E1000_MAX_TXD_PWR	12

static int e1000_tx_map(struct e1000_adapter *adapter,
			struct sk_buff *skb, unsigned int first,
			unsigned int max_per_txd, unsigned int nr_frags,
			unsigned int mss)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
4490
	struct pci_dev *pdev = adapter->pdev;
4491
	struct e1000_buffer *buffer_info;
J
Jesse Brandeburg 已提交
4492
	unsigned int len = skb_headlen(skb);
4493
	unsigned int offset = 0, size, count = 0, i;
4494
	unsigned int f, bytecount, segs;
4495 4496 4497 4498

	i = tx_ring->next_to_use;

	while (len) {
4499
		buffer_info = &tx_ring->buffer_info[i];
4500 4501 4502 4503 4504
		size = min(len, max_per_txd);

		buffer_info->length = size;
		buffer_info->time_stamp = jiffies;
		buffer_info->next_to_watch = i;
4505 4506 4507
		buffer_info->dma = dma_map_single(&pdev->dev,
						  skb->data + offset,
						  size,	DMA_TO_DEVICE);
4508
		buffer_info->mapped_as_page = false;
4509
		if (dma_mapping_error(&pdev->dev, buffer_info->dma))
4510
			goto dma_error;
4511 4512 4513

		len -= size;
		offset += size;
4514
		count++;
4515 4516 4517 4518 4519 4520

		if (len) {
			i++;
			if (i == tx_ring->count)
				i = 0;
		}
4521 4522 4523 4524 4525 4526 4527
	}

	for (f = 0; f < nr_frags; f++) {
		struct skb_frag_struct *frag;

		frag = &skb_shinfo(skb)->frags[f];
		len = frag->size;
4528
		offset = frag->page_offset;
4529 4530

		while (len) {
4531 4532 4533 4534
			i++;
			if (i == tx_ring->count)
				i = 0;

4535 4536 4537 4538 4539 4540
			buffer_info = &tx_ring->buffer_info[i];
			size = min(len, max_per_txd);

			buffer_info->length = size;
			buffer_info->time_stamp = jiffies;
			buffer_info->next_to_watch = i;
4541
			buffer_info->dma = dma_map_page(&pdev->dev, frag->page,
4542
							offset, size,
4543
							DMA_TO_DEVICE);
4544
			buffer_info->mapped_as_page = true;
4545
			if (dma_mapping_error(&pdev->dev, buffer_info->dma))
4546
				goto dma_error;
4547 4548 4549 4550 4551 4552 4553

			len -= size;
			offset += size;
			count++;
		}
	}

4554 4555 4556 4557
	segs = skb_shinfo(skb)->gso_segs ?: 1;
	/* multiply data chunks by size of headers */
	bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len;

4558
	tx_ring->buffer_info[i].skb = skb;
4559 4560
	tx_ring->buffer_info[i].segs = segs;
	tx_ring->buffer_info[i].bytecount = bytecount;
4561 4562 4563
	tx_ring->buffer_info[first].next_to_watch = i;

	return count;
4564 4565 4566 4567

dma_error:
	dev_err(&pdev->dev, "TX DMA map failed\n");
	buffer_info->dma = 0;
4568
	if (count)
4569
		count--;
4570 4571 4572

	while (count--) {
		if (i==0)
4573
			i += tx_ring->count;
4574
		i--;
4575 4576 4577 4578 4579
		buffer_info = &tx_ring->buffer_info[i];
		e1000_put_txbuf(adapter, buffer_info);;
	}

	return 0;
4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626
}

static void e1000_tx_queue(struct e1000_adapter *adapter,
			   int tx_flags, int count)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_tx_desc *tx_desc = NULL;
	struct e1000_buffer *buffer_info;
	u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS;
	unsigned int i;

	if (tx_flags & E1000_TX_FLAGS_TSO) {
		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D |
			     E1000_TXD_CMD_TSE;
		txd_upper |= E1000_TXD_POPTS_TXSM << 8;

		if (tx_flags & E1000_TX_FLAGS_IPV4)
			txd_upper |= E1000_TXD_POPTS_IXSM << 8;
	}

	if (tx_flags & E1000_TX_FLAGS_CSUM) {
		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D;
		txd_upper |= E1000_TXD_POPTS_TXSM << 8;
	}

	if (tx_flags & E1000_TX_FLAGS_VLAN) {
		txd_lower |= E1000_TXD_CMD_VLE;
		txd_upper |= (tx_flags & E1000_TX_FLAGS_VLAN_MASK);
	}

	i = tx_ring->next_to_use;

	while (count--) {
		buffer_info = &tx_ring->buffer_info[i];
		tx_desc = E1000_TX_DESC(*tx_ring, i);
		tx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
		tx_desc->lower.data =
			cpu_to_le32(txd_lower | buffer_info->length);
		tx_desc->upper.data = cpu_to_le32(txd_upper);

		i++;
		if (i == tx_ring->count)
			i = 0;
	}

	tx_desc->lower.data |= cpu_to_le32(adapter->txd_cmd);

4627 4628
	/*
	 * Force memory writes to complete before letting h/w
4629 4630
	 * know there are new descriptors to fetch.  (Only
	 * applicable for weak-ordered memory model archs,
4631 4632
	 * such as IA-64).
	 */
4633 4634 4635 4636
	wmb();

	tx_ring->next_to_use = i;
	writel(i, adapter->hw.hw_addr + tx_ring->tail);
4637 4638 4639 4640
	/*
	 * we need this if more than one processor can write to our tail
	 * at a time, it synchronizes IO on IA64/Altix systems
	 */
4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651
	mmiowb();
}

#define MINIMUM_DHCP_PACKET_SIZE 282
static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter,
				    struct sk_buff *skb)
{
	struct e1000_hw *hw =  &adapter->hw;
	u16 length, offset;

	if (vlan_tx_tag_present(skb)) {
4652 4653
		if (!((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) &&
		    (adapter->hw.mng_cookie.status &
4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687
			E1000_MNG_DHCP_COOKIE_STATUS_VLAN)))
			return 0;
	}

	if (skb->len <= MINIMUM_DHCP_PACKET_SIZE)
		return 0;

	if (((struct ethhdr *) skb->data)->h_proto != htons(ETH_P_IP))
		return 0;

	{
		const struct iphdr *ip = (struct iphdr *)((u8 *)skb->data+14);
		struct udphdr *udp;

		if (ip->protocol != IPPROTO_UDP)
			return 0;

		udp = (struct udphdr *)((u8 *)ip + (ip->ihl << 2));
		if (ntohs(udp->dest) != 67)
			return 0;

		offset = (u8 *)udp + 8 - skb->data;
		length = skb->len - offset;
		return e1000e_mng_write_dhcp_info(hw, (u8 *)udp + 8, length);
	}

	return 0;
}

static int __e1000_maybe_stop_tx(struct net_device *netdev, int size)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);

	netif_stop_queue(netdev);
4688 4689
	/*
	 * Herbert's original patch had:
4690
	 *  smp_mb__after_netif_stop_queue();
4691 4692
	 * but since that doesn't exist yet, just open code it.
	 */
4693 4694
	smp_mb();

4695 4696 4697 4698
	/*
	 * We need to check again in a case another CPU has just
	 * made room available.
	 */
4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717
	if (e1000_desc_unused(adapter->tx_ring) < size)
		return -EBUSY;

	/* A reprieve! */
	netif_start_queue(netdev);
	++adapter->restart_queue;
	return 0;
}

static int e1000_maybe_stop_tx(struct net_device *netdev, int size)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);

	if (e1000_desc_unused(adapter->tx_ring) >= size)
		return 0;
	return __e1000_maybe_stop_tx(netdev, size);
}

#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1 )
4718 4719
static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
				    struct net_device *netdev)
4720 4721 4722 4723 4724 4725 4726
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_ring *tx_ring = adapter->tx_ring;
	unsigned int first;
	unsigned int max_per_txd = E1000_MAX_PER_TXD;
	unsigned int max_txd_pwr = E1000_MAX_TXD_PWR;
	unsigned int tx_flags = 0;
E
Eric Dumazet 已提交
4727
	unsigned int len = skb_headlen(skb);
4728 4729
	unsigned int nr_frags;
	unsigned int mss;
4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744
	int count = 0;
	int tso;
	unsigned int f;

	if (test_bit(__E1000_DOWN, &adapter->state)) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (skb->len <= 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	mss = skb_shinfo(skb)->gso_size;
4745 4746
	/*
	 * The controller does a simple calculation to
4747 4748 4749 4750
	 * make sure there is enough room in the FIFO before
	 * initiating the DMA for each buffer.  The calc is:
	 * 4 = ceil(buffer len/mss).  To make sure we don't
	 * overrun the FIFO, adjust the max buffer len if mss
4751 4752
	 * drops.
	 */
4753 4754 4755 4756 4757
	if (mss) {
		u8 hdr_len;
		max_per_txd = min(mss << 2, max_per_txd);
		max_txd_pwr = fls(max_per_txd) - 1;

4758 4759 4760 4761 4762
		/*
		 * TSO Workaround for 82571/2/3 Controllers -- if skb->data
		 * points to just header, pull a few bytes of payload from
		 * frags into skb->data
		 */
4763
		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
4764 4765 4766 4767
		/*
		 * we do this workaround for ES2LAN, but it is un-necessary,
		 * avoiding it could save a lot of cycles
		 */
4768
		if (skb->data_len && (hdr_len == len)) {
4769 4770 4771 4772
			unsigned int pull_size;

			pull_size = min((unsigned int)4, skb->data_len);
			if (!__pskb_pull_tail(skb, pull_size)) {
4773
				e_err("__pskb_pull_tail failed.\n");
4774 4775 4776
				dev_kfree_skb_any(skb);
				return NETDEV_TX_OK;
			}
E
Eric Dumazet 已提交
4777
			len = skb_headlen(skb);
4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795
		}
	}

	/* reserve a descriptor for the offload context */
	if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL))
		count++;
	count++;

	count += TXD_USE_COUNT(len, max_txd_pwr);

	nr_frags = skb_shinfo(skb)->nr_frags;
	for (f = 0; f < nr_frags; f++)
		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size,
				       max_txd_pwr);

	if (adapter->hw.mac.tx_pkt_filtering)
		e1000_transfer_dhcp_info(adapter, skb);

4796 4797 4798 4799
	/*
	 * need: count + 2 desc gap to keep tail from touching
	 * head, otherwise try next time
	 */
4800
	if (e1000_maybe_stop_tx(netdev, count + 2))
4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820
		return NETDEV_TX_BUSY;

	if (adapter->vlgrp && vlan_tx_tag_present(skb)) {
		tx_flags |= E1000_TX_FLAGS_VLAN;
		tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT);
	}

	first = tx_ring->next_to_use;

	tso = e1000_tso(adapter, skb);
	if (tso < 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (tso)
		tx_flags |= E1000_TX_FLAGS_TSO;
	else if (e1000_tx_csum(adapter, skb))
		tx_flags |= E1000_TX_FLAGS_CSUM;

4821 4822
	/*
	 * Old method was to assume IPv4 packet by default if TSO was enabled.
4823
	 * 82571 hardware supports TSO capabilities for IPv6 as well...
4824 4825
	 * no longer assume, we must.
	 */
4826 4827 4828
	if (skb->protocol == htons(ETH_P_IP))
		tx_flags |= E1000_TX_FLAGS_IPV4;

4829
	/* if count is 0 then mapping error has occured */
4830
	count = e1000_tx_map(adapter, skb, first, max_per_txd, nr_frags, mss);
4831 4832 4833 4834 4835 4836
	if (count) {
		e1000_tx_queue(adapter, tx_flags, count);
		/* Make sure there is space in the ring for the next send. */
		e1000_maybe_stop_tx(netdev, MAX_SKB_FRAGS + 2);

	} else {
4837
		dev_kfree_skb_any(skb);
4838 4839
		tx_ring->buffer_info[first].time_stamp = 0;
		tx_ring->next_to_use = first;
4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862
	}

	return NETDEV_TX_OK;
}

/**
 * e1000_tx_timeout - Respond to a Tx Hang
 * @netdev: network interface device structure
 **/
static void e1000_tx_timeout(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);

	/* Do the reset outside of interrupt context */
	adapter->tx_timeout_count++;
	schedule_work(&adapter->reset_task);
}

static void e1000_reset_task(struct work_struct *work)
{
	struct e1000_adapter *adapter;
	adapter = container_of(work, struct e1000_adapter, reset_task);

4863 4864
	e1000e_dump(adapter);
	e_err("Reset adapter\n");
4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877
	e1000e_reinit_locked(adapter);
}

/**
 * e1000_get_stats - Get System Network Statistics
 * @netdev: network interface device structure
 *
 * Returns the address of the device statistics structure.
 * The statistics are actually updated from the timer callback.
 **/
static struct net_device_stats *e1000_get_stats(struct net_device *netdev)
{
	/* only return the current stats */
4878
	return &netdev->stats;
4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892
}

/**
 * e1000_change_mtu - Change the Maximum Transfer Unit
 * @netdev: network interface device structure
 * @new_mtu: new value for maximum frame size
 *
 * Returns 0 on success, negative on failure
 **/
static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;

4893 4894 4895 4896
	/* Jumbo frame support */
	if ((max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) &&
	    !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) {
		e_err("Jumbo Frames not supported.\n");
4897 4898 4899
		return -EINVAL;
	}

4900 4901 4902 4903
	/* Supported frame sizes */
	if ((new_mtu < ETH_ZLEN + ETH_FCS_LEN + VLAN_HLEN) ||
	    (max_frame > adapter->max_hw_frame_size)) {
		e_err("Unsupported MTU setting\n");
4904 4905 4906
		return -EINVAL;
	}

4907 4908 4909 4910 4911 4912 4913 4914 4915
	/* Jumbo frame workaround on 82579 requires CRC be stripped */
	if ((adapter->hw.mac.type == e1000_pch2lan) &&
	    !(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
	    (new_mtu > ETH_DATA_LEN)) {
		e_err("Jumbo Frames not supported on 82579 when CRC "
		      "stripping is disabled.\n");
		return -EINVAL;
	}

4916 4917 4918 4919 4920 4921 4922 4923
	/* 82573 Errata 17 */
	if (((adapter->hw.mac.type == e1000_82573) ||
	     (adapter->hw.mac.type == e1000_82574)) &&
	    (max_frame > ETH_FRAME_LEN + ETH_FCS_LEN)) {
		adapter->flags2 |= FLAG2_DISABLE_ASPM_L1;
		e1000e_disable_aspm(adapter->pdev, PCIE_LINK_STATE_L1);
	}

4924 4925
	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
		msleep(1);
4926
	/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
4927
	adapter->max_frame_size = max_frame;
4928 4929
	e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
	netdev->mtu = new_mtu;
4930 4931 4932
	if (netif_running(netdev))
		e1000e_down(adapter);

4933 4934
	/*
	 * NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
4935 4936
	 * means we reserve 2 more, this pushes us to allocate from the next
	 * larger slab size.
4937
	 * i.e. RXBUFFER_2048 --> size-4096 slab
4938 4939
	 * However with the new *_jumbo_rx* routines, jumbo receives will use
	 * fragmented skbs
4940
	 */
4941

4942
	if (max_frame <= 2048)
4943 4944 4945 4946 4947 4948 4949 4950
		adapter->rx_buffer_len = 2048;
	else
		adapter->rx_buffer_len = 4096;

	/* adjust allocation if LPE protects us, and we aren't using SBP */
	if ((max_frame == ETH_FRAME_LEN + ETH_FCS_LEN) ||
	     (max_frame == ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN))
		adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN
4951
					 + ETH_FCS_LEN;
4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968

	if (netif_running(netdev))
		e1000e_up(adapter);
	else
		e1000e_reset(adapter);

	clear_bit(__E1000_RESETTING, &adapter->state);

	return 0;
}

static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
			   int cmd)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct mii_ioctl_data *data = if_mii(ifr);

4969
	if (adapter->hw.phy.media_type != e1000_media_type_copper)
4970 4971 4972 4973 4974 4975 4976
		return -EOPNOTSUPP;

	switch (cmd) {
	case SIOCGMIIPHY:
		data->phy_id = adapter->hw.phy.addr;
		break;
	case SIOCGMIIREG:
4977 4978
		e1000_phy_read_status(adapter);

4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010
		switch (data->reg_num & 0x1F) {
		case MII_BMCR:
			data->val_out = adapter->phy_regs.bmcr;
			break;
		case MII_BMSR:
			data->val_out = adapter->phy_regs.bmsr;
			break;
		case MII_PHYSID1:
			data->val_out = (adapter->hw.phy.id >> 16);
			break;
		case MII_PHYSID2:
			data->val_out = (adapter->hw.phy.id & 0xFFFF);
			break;
		case MII_ADVERTISE:
			data->val_out = adapter->phy_regs.advertise;
			break;
		case MII_LPA:
			data->val_out = adapter->phy_regs.lpa;
			break;
		case MII_EXPANSION:
			data->val_out = adapter->phy_regs.expansion;
			break;
		case MII_CTRL1000:
			data->val_out = adapter->phy_regs.ctrl1000;
			break;
		case MII_STAT1000:
			data->val_out = adapter->phy_regs.stat1000;
			break;
		case MII_ESTATUS:
			data->val_out = adapter->phy_regs.estatus;
			break;
		default:
5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032
			return -EIO;
		}
		break;
	case SIOCSMIIREG:
	default:
		return -EOPNOTSUPP;
	}
	return 0;
}

static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
{
	switch (cmd) {
	case SIOCGMIIPHY:
	case SIOCGMIIREG:
	case SIOCSMIIREG:
		return e1000_mii_ioctl(netdev, ifr, cmd);
	default:
		return -EOPNOTSUPP;
	}
}

5033 5034 5035 5036 5037 5038 5039 5040
static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 i, mac_reg;
	u16 phy_reg;
	int retval = 0;

	/* copy MAC RARs to PHY RARs */
5041
	e1000_copy_rx_addrs_to_phy_ich8lan(hw);
5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078

	/* copy MAC MTA to PHY MTA */
	for (i = 0; i < adapter->hw.mac.mta_reg_count; i++) {
		mac_reg = E1000_READ_REG_ARRAY(hw, E1000_MTA, i);
		e1e_wphy(hw, BM_MTA(i), (u16)(mac_reg & 0xFFFF));
		e1e_wphy(hw, BM_MTA(i) + 1, (u16)((mac_reg >> 16) & 0xFFFF));
	}

	/* configure PHY Rx Control register */
	e1e_rphy(&adapter->hw, BM_RCTL, &phy_reg);
	mac_reg = er32(RCTL);
	if (mac_reg & E1000_RCTL_UPE)
		phy_reg |= BM_RCTL_UPE;
	if (mac_reg & E1000_RCTL_MPE)
		phy_reg |= BM_RCTL_MPE;
	phy_reg &= ~(BM_RCTL_MO_MASK);
	if (mac_reg & E1000_RCTL_MO_3)
		phy_reg |= (((mac_reg & E1000_RCTL_MO_3) >> E1000_RCTL_MO_SHIFT)
				<< BM_RCTL_MO_SHIFT);
	if (mac_reg & E1000_RCTL_BAM)
		phy_reg |= BM_RCTL_BAM;
	if (mac_reg & E1000_RCTL_PMCF)
		phy_reg |= BM_RCTL_PMCF;
	mac_reg = er32(CTRL);
	if (mac_reg & E1000_CTRL_RFCE)
		phy_reg |= BM_RCTL_RFCE;
	e1e_wphy(&adapter->hw, BM_RCTL, phy_reg);

	/* enable PHY wakeup in MAC register */
	ew32(WUFC, wufc);
	ew32(WUC, E1000_WUC_PHY_WAKE | E1000_WUC_PME_EN);

	/* configure and enable PHY wakeup in PHY registers */
	e1e_wphy(&adapter->hw, BM_WUFC, wufc);
	e1e_wphy(&adapter->hw, BM_WUC, E1000_WUC_PME_EN);

	/* activate PHY wakeup */
5079
	retval = hw->phy.ops.acquire(hw);
5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095
	if (retval) {
		e_err("Could not acquire PHY\n");
		return retval;
	}
	e1000e_write_phy_reg_mdic(hw, IGP01E1000_PHY_PAGE_SELECT,
	                         (BM_WUC_ENABLE_PAGE << IGP_PAGE_SHIFT));
	retval = e1000e_read_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, &phy_reg);
	if (retval) {
		e_err("Could not read PHY page 769\n");
		goto out;
	}
	phy_reg |= BM_WUC_ENABLE_BIT | BM_WUC_HOST_WU_BIT;
	retval = e1000e_write_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, phy_reg);
	if (retval)
		e_err("Could not set PHY Host Wakeup bit\n");
out:
5096
	hw->phy.ops.release(hw);
5097 5098 5099 5100

	return retval;
}

5101 5102
static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake,
			    bool runtime)
5103 5104 5105 5106 5107
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl, ctrl_ext, rctl, status;
5108 5109
	/* Runtime suspend should only enable wakeup for link changes */
	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
5110 5111 5112 5113 5114 5115 5116 5117 5118
	int retval = 0;

	netif_device_detach(netdev);

	if (netif_running(netdev)) {
		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
		e1000e_down(adapter);
		e1000_free_irq(adapter);
	}
5119
	e1000e_reset_interrupt_capability(adapter);
5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144

	retval = pci_save_state(pdev);
	if (retval)
		return retval;

	status = er32(STATUS);
	if (status & E1000_STATUS_LU)
		wufc &= ~E1000_WUFC_LNKC;

	if (wufc) {
		e1000_setup_rctl(adapter);
		e1000_set_multi(netdev);

		/* turn on all-multi mode if wake on multicast is enabled */
		if (wufc & E1000_WUFC_MC) {
			rctl = er32(RCTL);
			rctl |= E1000_RCTL_MPE;
			ew32(RCTL, rctl);
		}

		ctrl = er32(CTRL);
		/* advertise wake from D3Cold */
		#define E1000_CTRL_ADVD3WUC 0x00100000
		/* phy power management enable */
		#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
5145 5146 5147
		ctrl |= E1000_CTRL_ADVD3WUC;
		if (!(adapter->flags2 & FLAG2_HAS_PHY_WAKEUP))
			ctrl |= E1000_CTRL_EN_PHY_PWR_MGMT;
5148 5149
		ew32(CTRL, ctrl);

5150 5151 5152
		if (adapter->hw.phy.media_type == e1000_media_type_fiber ||
		    adapter->hw.phy.media_type ==
		    e1000_media_type_internal_serdes) {
5153 5154
			/* keep the laser running in D3 */
			ctrl_ext = er32(CTRL_EXT);
5155
			ctrl_ext |= E1000_CTRL_EXT_SDP3_DATA;
5156 5157 5158
			ew32(CTRL_EXT, ctrl_ext);
		}

5159 5160 5161
		if (adapter->flags & FLAG_IS_ICH)
			e1000e_disable_gig_wol_ich8lan(&adapter->hw);

5162 5163 5164
		/* Allow time for pending master requests to run */
		e1000e_disable_pcie_master(&adapter->hw);

5165
		if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
5166 5167 5168 5169 5170 5171 5172 5173 5174
			/* enable wakeup by the PHY */
			retval = e1000_init_phy_wakeup(adapter, wufc);
			if (retval)
				return retval;
		} else {
			/* enable wakeup by the MAC */
			ew32(WUFC, wufc);
			ew32(WUC, E1000_WUC_PME_EN);
		}
5175 5176 5177 5178 5179
	} else {
		ew32(WUC, 0);
		ew32(WUFC, 0);
	}

5180 5181
	*enable_wake = !!wufc;

5182
	/* make sure adapter isn't asleep if manageability is enabled */
5183 5184
	if ((adapter->flags & FLAG_MNG_PT_ENABLED) ||
	    (hw->mac.ops.check_mng_mode(hw)))
5185
		*enable_wake = true;
5186 5187 5188 5189

	if (adapter->hw.phy.type == e1000_phy_igp_3)
		e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);

5190 5191 5192 5193
	/*
	 * Release control of h/w to f/w.  If f/w is AMT enabled, this
	 * would have already happened in close and is redundant.
	 */
5194 5195 5196 5197
	e1000_release_hw_control(adapter);

	pci_disable_device(pdev);

5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217
	return 0;
}

static void e1000_power_off(struct pci_dev *pdev, bool sleep, bool wake)
{
	if (sleep && wake) {
		pci_prepare_to_sleep(pdev);
		return;
	}

	pci_wake_from_d3(pdev, wake);
	pci_set_power_state(pdev, PCI_D3hot);
}

static void e1000_complete_shutdown(struct pci_dev *pdev, bool sleep,
                                    bool wake)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232
	/*
	 * The pci-e switch on some quad port adapters will report a
	 * correctable error when the MAC transitions from D0 to D3.  To
	 * prevent this we need to mask off the correctable errors on the
	 * downstream port of the pci-e switch.
	 */
	if (adapter->flags & FLAG_IS_QUAD_PORT) {
		struct pci_dev *us_dev = pdev->bus->self;
		int pos = pci_find_capability(us_dev, PCI_CAP_ID_EXP);
		u16 devctl;

		pci_read_config_word(us_dev, pos + PCI_EXP_DEVCTL, &devctl);
		pci_write_config_word(us_dev, pos + PCI_EXP_DEVCTL,
		                      (devctl & ~PCI_EXP_DEVCTL_CERE));

5233
		e1000_power_off(pdev, sleep, wake);
5234 5235 5236

		pci_write_config_word(us_dev, pos + PCI_EXP_DEVCTL, devctl);
	} else {
5237
		e1000_power_off(pdev, sleep, wake);
5238
	}
5239 5240
}

5241 5242 5243 5244 5245 5246 5247
#ifdef CONFIG_PCIEASPM
static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
{
	pci_disable_link_state(pdev, state);
}
#else
static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
5248 5249
{
	int pos;
5250
	u16 reg16;
5251 5252

	/*
5253 5254
	 * Both device and parent should have the same ASPM setting.
	 * Disable ASPM in downstream component first and then upstream.
5255
	 */
5256 5257 5258 5259 5260
	pos = pci_pcie_cap(pdev);
	pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, &reg16);
	reg16 &= ~state;
	pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);

5261 5262 5263
	if (!pdev->bus->self)
		return;

5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276
	pos = pci_pcie_cap(pdev->bus->self);
	pci_read_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, &reg16);
	reg16 &= ~state;
	pci_write_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, reg16);
}
#endif
void e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
{
	dev_info(&pdev->dev, "Disabling ASPM %s %s\n",
		 (state & PCIE_LINK_STATE_L0S) ? "L0s" : "",
		 (state & PCIE_LINK_STATE_L1) ? "L1" : "");

	__e1000e_disable_aspm(pdev, state);
5277 5278
}

5279
#ifdef CONFIG_PM_OPS
5280
static bool e1000e_pm_ready(struct e1000_adapter *adapter)
5281
{
5282
	return !!adapter->tx_ring->buffer_info;
5283 5284
}

5285
static int __e1000_resume(struct pci_dev *pdev)
5286 5287 5288 5289 5290 5291 5292 5293
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 err;

	pci_set_power_state(pdev, PCI_D0);
	pci_restore_state(pdev);
5294
	pci_save_state(pdev);
5295 5296
	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1)
		e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1);
T
Taku Izumi 已提交
5297

5298
	e1000e_set_interrupt_capability(adapter);
5299 5300 5301 5302 5303 5304 5305
	if (netif_running(netdev)) {
		err = e1000_request_irq(adapter);
		if (err)
			return err;
	}

	e1000e_power_up_phy(adapter);
5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335

	/* report the system wakeup cause from S3/S4 */
	if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
		u16 phy_data;

		e1e_rphy(&adapter->hw, BM_WUS, &phy_data);
		if (phy_data) {
			e_info("PHY Wakeup cause - %s\n",
				phy_data & E1000_WUS_EX ? "Unicast Packet" :
				phy_data & E1000_WUS_MC ? "Multicast Packet" :
				phy_data & E1000_WUS_BC ? "Broadcast Packet" :
				phy_data & E1000_WUS_MAG ? "Magic Packet" :
				phy_data & E1000_WUS_LNKC ? "Link Status "
				" Change" : "other");
		}
		e1e_wphy(&adapter->hw, BM_WUS, ~0);
	} else {
		u32 wus = er32(WUS);
		if (wus) {
			e_info("MAC Wakeup cause - %s\n",
				wus & E1000_WUS_EX ? "Unicast Packet" :
				wus & E1000_WUS_MC ? "Multicast Packet" :
				wus & E1000_WUS_BC ? "Broadcast Packet" :
				wus & E1000_WUS_MAG ? "Magic Packet" :
				wus & E1000_WUS_LNKC ? "Link Status Change" :
				"other");
		}
		ew32(WUS, ~0);
	}

5336 5337
	e1000e_reset(adapter);

5338
	e1000_init_manageability_pt(adapter);
5339 5340 5341 5342 5343 5344

	if (netif_running(netdev))
		e1000e_up(adapter);

	netif_device_attach(netdev);

5345 5346
	/*
	 * If the controller has AMT, do not set DRV_LOAD until the interface
5347
	 * is up.  For all other cases, let the f/w know that the h/w is now
5348 5349
	 * under the control of the driver.
	 */
J
Jesse Brandeburg 已提交
5350
	if (!(adapter->flags & FLAG_HAS_AMT))
5351 5352 5353 5354
		e1000_get_hw_control(adapter);

	return 0;
}
5355

5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369
#ifdef CONFIG_PM_SLEEP
static int e1000_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	int retval;
	bool wake;

	retval = __e1000_shutdown(pdev, &wake, false);
	if (!retval)
		e1000_complete_shutdown(pdev, true, wake);

	return retval;
}

5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380
static int e1000_resume(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

	if (e1000e_pm_ready(adapter))
		adapter->idle_check = true;

	return __e1000_resume(pdev);
}
5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415
#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_PM_RUNTIME
static int e1000_runtime_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

	if (e1000e_pm_ready(adapter)) {
		bool wake;

		__e1000_shutdown(pdev, &wake, true);
	}

	return 0;
}

static int e1000_idle(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

	if (!e1000e_pm_ready(adapter))
		return 0;

	if (adapter->idle_check) {
		adapter->idle_check = false;
		if (!e1000e_has_link(adapter))
			pm_schedule_suspend(dev, MSEC_PER_SEC);
	}

	return -EBUSY;
}
5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428

static int e1000_runtime_resume(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

	if (!e1000e_pm_ready(adapter))
		return 0;

	adapter->idle_check = !dev->power.runtime_auto;
	return __e1000_resume(pdev);
}
5429 5430
#endif /* CONFIG_PM_RUNTIME */
#endif /* CONFIG_PM_OPS */
5431 5432 5433

static void e1000_shutdown(struct pci_dev *pdev)
{
5434 5435
	bool wake = false;

5436
	__e1000_shutdown(pdev, &wake, false);
5437 5438 5439

	if (system_state == SYSTEM_POWER_OFF)
		e1000_complete_shutdown(pdev, false, wake);
5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474
}

#ifdef CONFIG_NET_POLL_CONTROLLER
/*
 * Polling 'interrupt' - used by things like netconsole to send skbs
 * without having to re-enable interrupts. It's not called while
 * the interrupt routine is executing.
 */
static void e1000_netpoll(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);

	disable_irq(adapter->pdev->irq);
	e1000_intr(adapter->pdev->irq, netdev);

	enable_irq(adapter->pdev->irq);
}
#endif

/**
 * e1000_io_error_detected - called when PCI error is detected
 * @pdev: Pointer to PCI device
 * @state: The current pci connection state
 *
 * This function is called after a PCI bus error affecting
 * this device has been detected.
 */
static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
						pci_channel_state_t state)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

	netif_device_detach(netdev);

5475 5476 5477
	if (state == pci_channel_io_perm_failure)
		return PCI_ERS_RESULT_DISCONNECT;

5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497
	if (netif_running(netdev))
		e1000e_down(adapter);
	pci_disable_device(pdev);

	/* Request a slot slot reset. */
	return PCI_ERS_RESULT_NEED_RESET;
}

/**
 * e1000_io_slot_reset - called after the pci bus has been reset.
 * @pdev: Pointer to PCI device
 *
 * Restart the card from scratch, as if from a cold-boot. Implementation
 * resembles the first-half of the e1000_resume routine.
 */
static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
T
Taku Izumi 已提交
5498
	int err;
J
Jesse Brandeburg 已提交
5499
	pci_ers_result_t result;
5500

5501 5502
	if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1)
		e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1);
5503
	err = pci_enable_device_mem(pdev);
T
Taku Izumi 已提交
5504
	if (err) {
5505 5506
		dev_err(&pdev->dev,
			"Cannot re-enable PCI device after reset.\n");
J
Jesse Brandeburg 已提交
5507 5508 5509
		result = PCI_ERS_RESULT_DISCONNECT;
	} else {
		pci_set_master(pdev);
5510
		pdev->state_saved = true;
J
Jesse Brandeburg 已提交
5511
		pci_restore_state(pdev);
5512

J
Jesse Brandeburg 已提交
5513 5514
		pci_enable_wake(pdev, PCI_D3hot, 0);
		pci_enable_wake(pdev, PCI_D3cold, 0);
5515

J
Jesse Brandeburg 已提交
5516 5517 5518 5519
		e1000e_reset(adapter);
		ew32(WUS, ~0);
		result = PCI_ERS_RESULT_RECOVERED;
	}
5520

J
Jesse Brandeburg 已提交
5521 5522 5523
	pci_cleanup_aer_uncorrect_error_status(pdev);

	return result;
5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538
}

/**
 * e1000_io_resume - called when traffic can start flowing again.
 * @pdev: Pointer to PCI device
 *
 * This callback is called when the error recovery driver tells us that
 * its OK to resume normal operation. Implementation resembles the
 * second-half of the e1000_resume routine.
 */
static void e1000_io_resume(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);

5539
	e1000_init_manageability_pt(adapter);
5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550

	if (netif_running(netdev)) {
		if (e1000e_up(adapter)) {
			dev_err(&pdev->dev,
				"can't bring device back up after reset\n");
			return;
		}
	}

	netif_device_attach(netdev);

5551 5552
	/*
	 * If the controller has AMT, do not set DRV_LOAD until the interface
5553
	 * is up.  For all other cases, let the f/w know that the h/w is now
5554 5555
	 * under the control of the driver.
	 */
J
Jesse Brandeburg 已提交
5556
	if (!(adapter->flags & FLAG_HAS_AMT))
5557 5558 5559 5560 5561 5562 5563 5564
		e1000_get_hw_control(adapter);

}

static void e1000_print_device_info(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
J
Jeff Kirsher 已提交
5565
	u32 pba_num;
5566 5567

	/* print bus type/speed/width info */
J
Johannes Berg 已提交
5568
	e_info("(PCI Express:2.5GB/s:%s) %pM\n",
5569 5570 5571 5572
	       /* bus width */
	       ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" :
	        "Width x1"),
	       /* MAC address */
J
Johannes Berg 已提交
5573
	       netdev->dev_addr);
5574 5575
	e_info("Intel(R) PRO/%s Network Connection\n",
	       (hw->phy.type == e1000_phy_ife) ? "10/100" : "1000");
J
Jeff Kirsher 已提交
5576
	e1000e_read_pba_num(hw, &pba_num);
5577 5578
	e_info("MAC: %d, PHY: %d, PBA No: %06x-%03x\n",
	       hw->mac.type, hw->phy.type, (pba_num >> 8), (pba_num & 0xff));
5579 5580
}

5581 5582 5583 5584 5585 5586 5587 5588 5589 5590
static void e1000_eeprom_checks(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	int ret_val;
	u16 buf = 0;

	if (hw->mac.type != e1000_82573)
		return;

	ret_val = e1000_read_nvm(hw, NVM_INIT_CONTROL2_REG, 1, &buf);
5591
	if (!ret_val && (!(le16_to_cpu(buf) & (1 << 0)))) {
5592
		/* Deep Smart Power Down (DSPD) */
5593 5594
		dev_warn(&adapter->pdev->dev,
			 "Warning: detected DSPD enabled in EEPROM\n");
5595 5596 5597
	}
}

5598 5599 5600
static const struct net_device_ops e1000e_netdev_ops = {
	.ndo_open		= e1000_open,
	.ndo_stop		= e1000_close,
5601
	.ndo_start_xmit		= e1000_xmit_frame,
5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617
	.ndo_get_stats		= e1000_get_stats,
	.ndo_set_multicast_list	= e1000_set_multi,
	.ndo_set_mac_address	= e1000_set_mac,
	.ndo_change_mtu		= e1000_change_mtu,
	.ndo_do_ioctl		= e1000_ioctl,
	.ndo_tx_timeout		= e1000_tx_timeout,
	.ndo_validate_addr	= eth_validate_addr,

	.ndo_vlan_rx_register	= e1000_vlan_rx_register,
	.ndo_vlan_rx_add_vid	= e1000_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid	= e1000_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= e1000_netpoll,
#endif
};

5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635
/**
 * e1000_probe - Device Initialization Routine
 * @pdev: PCI device information struct
 * @ent: entry in e1000_pci_tbl
 *
 * Returns 0 on success, negative on failure
 *
 * e1000_probe initializes an adapter identified by a pci_dev structure.
 * The OS initialization, configuring of the adapter private structure,
 * and a hardware reset occur.
 **/
static int __devinit e1000_probe(struct pci_dev *pdev,
				 const struct pci_device_id *ent)
{
	struct net_device *netdev;
	struct e1000_adapter *adapter;
	struct e1000_hw *hw;
	const struct e1000_info *ei = e1000_info_tbl[ent->driver_data];
5636 5637
	resource_size_t mmio_start, mmio_len;
	resource_size_t flash_start, flash_len;
5638 5639 5640 5641 5642 5643

	static int cards_found;
	int i, err, pci_using_dac;
	u16 eeprom_data = 0;
	u16 eeprom_apme_mask = E1000_EEPROM_APME;

5644 5645
	if (ei->flags2 & FLAG2_DISABLE_ASPM_L1)
		e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1);
T
Taku Izumi 已提交
5646

5647
	err = pci_enable_device_mem(pdev);
5648 5649 5650 5651
	if (err)
		return err;

	pci_using_dac = 0;
5652
	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
5653
	if (!err) {
5654
		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
5655 5656 5657
		if (!err)
			pci_using_dac = 1;
	} else {
5658
		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
5659
		if (err) {
5660 5661
			err = dma_set_coherent_mask(&pdev->dev,
						    DMA_BIT_MASK(32));
5662 5663 5664 5665 5666 5667 5668 5669
			if (err) {
				dev_err(&pdev->dev, "No usable DMA "
					"configuration, aborting\n");
				goto err_dma;
			}
		}
	}

5670
	err = pci_request_selected_regions_exclusive(pdev,
5671 5672
	                                  pci_select_bars(pdev, IORESOURCE_MEM),
	                                  e1000e_driver_name);
5673 5674 5675
	if (err)
		goto err_pci_reg;

5676
	/* AER (Advanced Error Reporting) hooks */
5677
	pci_enable_pcie_error_reporting(pdev);
5678

5679
	pci_set_master(pdev);
5680 5681 5682 5683
	/* PCI config space info */
	err = pci_save_state(pdev);
	if (err)
		goto err_alloc_etherdev;
5684 5685 5686 5687 5688 5689 5690 5691

	err = -ENOMEM;
	netdev = alloc_etherdev(sizeof(struct e1000_adapter));
	if (!netdev)
		goto err_alloc_etherdev;

	SET_NETDEV_DEV(netdev, &pdev->dev);

5692 5693
	netdev->irq = pdev->irq;

5694 5695 5696 5697 5698 5699 5700 5701
	pci_set_drvdata(pdev, netdev);
	adapter = netdev_priv(netdev);
	hw = &adapter->hw;
	adapter->netdev = netdev;
	adapter->pdev = pdev;
	adapter->ei = ei;
	adapter->pba = ei->pba;
	adapter->flags = ei->flags;
J
Jeff Kirsher 已提交
5702
	adapter->flags2 = ei->flags2;
5703 5704
	adapter->hw.adapter = adapter;
	adapter->hw.mac.type = ei->mac;
5705
	adapter->max_hw_frame_size = ei->max_hw_frame_size;
5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725
	adapter->msg_enable = (1 << NETIF_MSG_DRV | NETIF_MSG_PROBE) - 1;

	mmio_start = pci_resource_start(pdev, 0);
	mmio_len = pci_resource_len(pdev, 0);

	err = -EIO;
	adapter->hw.hw_addr = ioremap(mmio_start, mmio_len);
	if (!adapter->hw.hw_addr)
		goto err_ioremap;

	if ((adapter->flags & FLAG_HAS_FLASH) &&
	    (pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
		flash_start = pci_resource_start(pdev, 1);
		flash_len = pci_resource_len(pdev, 1);
		adapter->hw.flash_address = ioremap(flash_start, flash_len);
		if (!adapter->hw.flash_address)
			goto err_flashmap;
	}

	/* construct the net_device struct */
5726
	netdev->netdev_ops		= &e1000e_netdev_ops;
5727 5728 5729 5730 5731 5732 5733 5734 5735 5736
	e1000e_set_ethtool_ops(netdev);
	netdev->watchdog_timeo		= 5 * HZ;
	netif_napi_add(netdev, &adapter->napi, e1000_clean, 64);
	strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);

	netdev->mem_start = mmio_start;
	netdev->mem_end = mmio_start + mmio_len;

	adapter->bd_number = cards_found++;

5737 5738
	e1000e_check_options(adapter);

5739 5740 5741 5742 5743 5744 5745 5746 5747
	/* setup adapter struct */
	err = e1000_sw_init(adapter);
	if (err)
		goto err_sw_init;

	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
	memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops));
	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));

J
Jeff Kirsher 已提交
5748
	err = ei->get_variants(adapter);
5749 5750 5751
	if (err)
		goto err_hw_init;

5752 5753 5754 5755
	if ((adapter->flags & FLAG_IS_ICH) &&
	    (adapter->flags & FLAG_READ_ONLY_NVM))
		e1000e_write_protect_nvm_ich8lan(&adapter->hw);

5756 5757
	hw->mac.ops.get_bus_info(&adapter->hw);

5758
	adapter->hw.phy.autoneg_wait_to_complete = 0;
5759 5760

	/* Copper options */
5761
	if (adapter->hw.phy.media_type == e1000_media_type_copper) {
5762 5763 5764 5765 5766 5767
		adapter->hw.phy.mdix = AUTO_ALL_MODES;
		adapter->hw.phy.disable_polarity_correction = 0;
		adapter->hw.phy.ms_type = e1000_ms_hw_default;
	}

	if (e1000_check_reset_block(&adapter->hw))
5768
		e_info("PHY reset is blocked due to SOL/IDER session.\n");
5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780

	netdev->features = NETIF_F_SG |
			   NETIF_F_HW_CSUM |
			   NETIF_F_HW_VLAN_TX |
			   NETIF_F_HW_VLAN_RX;

	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER)
		netdev->features |= NETIF_F_HW_VLAN_FILTER;

	netdev->features |= NETIF_F_TSO;
	netdev->features |= NETIF_F_TSO6;

5781 5782 5783 5784 5785
	netdev->vlan_features |= NETIF_F_TSO;
	netdev->vlan_features |= NETIF_F_TSO6;
	netdev->vlan_features |= NETIF_F_HW_CSUM;
	netdev->vlan_features |= NETIF_F_SG;

5786
	if (pci_using_dac) {
5787
		netdev->features |= NETIF_F_HIGHDMA;
5788 5789
		netdev->vlan_features |= NETIF_F_HIGHDMA;
	}
5790 5791 5792 5793

	if (e1000e_enable_mng_pass_thru(&adapter->hw))
		adapter->flags |= FLAG_MNG_PT_ENABLED;

5794 5795 5796 5797
	/*
	 * before reading the NVM, reset the controller to
	 * put the device in a known good starting state
	 */
5798 5799 5800 5801 5802 5803 5804 5805 5806 5807
	adapter->hw.mac.ops.reset_hw(&adapter->hw);

	/*
	 * systems with ASPM and others may see the checksum fail on the first
	 * attempt. Let's give it a few tries
	 */
	for (i = 0;; i++) {
		if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
			break;
		if (i == 2) {
5808
			e_err("The NVM Checksum Is Not Valid\n");
5809 5810 5811 5812 5813
			err = -EIO;
			goto err_eeprom;
		}
	}

5814 5815
	e1000_eeprom_checks(adapter);

5816
	/* copy the MAC address */
5817
	if (e1000e_read_mac_addr(&adapter->hw))
5818
		e_err("NVM Read Error while reading MAC address\n");
5819 5820 5821 5822 5823

	memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);

	if (!is_valid_ether_addr(netdev->perm_addr)) {
J
Johannes Berg 已提交
5824
		e_err("Invalid MAC Address: %pM\n", netdev->perm_addr);
5825 5826 5827 5828 5829
		err = -EIO;
		goto err_eeprom;
	}

	init_timer(&adapter->watchdog_timer);
5830
	adapter->watchdog_timer.function = e1000_watchdog;
5831 5832 5833
	adapter->watchdog_timer.data = (unsigned long) adapter;

	init_timer(&adapter->phy_info_timer);
5834
	adapter->phy_info_timer.function = e1000_update_phy_info;
5835 5836 5837 5838
	adapter->phy_info_timer.data = (unsigned long) adapter;

	INIT_WORK(&adapter->reset_task, e1000_reset_task);
	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
5839 5840
	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
5841
	INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
5842 5843 5844

	/* Initialize link parameters. User can change them with ethtool */
	adapter->hw.mac.autoneg = 1;
5845
	adapter->fc_autoneg = 1;
5846 5847
	adapter->hw.fc.requested_mode = e1000_fc_default;
	adapter->hw.fc.current_mode = e1000_fc_default;
5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861
	adapter->hw.phy.autoneg_advertised = 0x2f;

	/* ring size defaults */
	adapter->rx_ring->count = 256;
	adapter->tx_ring->count = 256;

	/*
	 * Initial Wake on LAN setting - If APM wake is enabled in
	 * the EEPROM, enable the ACPI Magic Packet filter
	 */
	if (adapter->flags & FLAG_APME_IN_WUC) {
		/* APME bit in EEPROM is mapped to WUC.APME */
		eeprom_data = er32(WUC);
		eeprom_apme_mask = E1000_WUC_APME;
5862 5863
		if (eeprom_data & E1000_WUC_PHY_WAKE)
			adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP;
5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887
	} else if (adapter->flags & FLAG_APME_IN_CTRL3) {
		if (adapter->flags & FLAG_APME_CHECK_PORT_B &&
		    (adapter->hw.bus.func == 1))
			e1000_read_nvm(&adapter->hw,
				NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data);
		else
			e1000_read_nvm(&adapter->hw,
				NVM_INIT_CONTROL3_PORT_A, 1, &eeprom_data);
	}

	/* fetch WoL from EEPROM */
	if (eeprom_data & eeprom_apme_mask)
		adapter->eeprom_wol |= E1000_WUFC_MAG;

	/*
	 * now that we have the eeprom settings, apply the special cases
	 * where the eeprom may be wrong or the board simply won't support
	 * wake on lan on a particular port
	 */
	if (!(adapter->flags & FLAG_HAS_WOL))
		adapter->eeprom_wol = 0;

	/* initialize the wol settings based on the eeprom settings */
	adapter->wol = adapter->eeprom_wol;
5888
	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
5889

5890 5891 5892
	/* save off EEPROM version number */
	e1000_read_nvm(&adapter->hw, 5, 1, &adapter->eeprom_vers);

5893 5894 5895
	/* reset the hardware with the new settings */
	e1000e_reset(adapter);

5896 5897
	/*
	 * If the controller has AMT, do not set DRV_LOAD until the interface
5898
	 * is up.  For all other cases, let the f/w know that the h/w is now
5899 5900
	 * under the control of the driver.
	 */
J
Jesse Brandeburg 已提交
5901
	if (!(adapter->flags & FLAG_HAS_AMT))
5902 5903 5904 5905 5906 5907 5908
		e1000_get_hw_control(adapter);

	strcpy(netdev->name, "eth%d");
	err = register_netdev(netdev);
	if (err)
		goto err_register;

5909 5910 5911
	/* carrier off reporting is important to ethtool even BEFORE open */
	netif_carrier_off(netdev);

5912 5913
	e1000_print_device_info(adapter);

5914 5915
	if (pci_dev_run_wake(pdev))
		pm_runtime_put_noidle(&pdev->dev);
5916

5917 5918 5919
	return 0;

err_register:
J
Jesse Brandeburg 已提交
5920 5921
	if (!(adapter->flags & FLAG_HAS_AMT))
		e1000_release_hw_control(adapter);
5922 5923 5924
err_eeprom:
	if (!e1000_check_reset_block(&adapter->hw))
		e1000_phy_hw_reset(&adapter->hw);
J
Jesse Brandeburg 已提交
5925
err_hw_init:
5926 5927 5928 5929

	kfree(adapter->tx_ring);
	kfree(adapter->rx_ring);
err_sw_init:
J
Jesse Brandeburg 已提交
5930 5931
	if (adapter->hw.flash_address)
		iounmap(adapter->hw.flash_address);
5932
	e1000e_reset_interrupt_capability(adapter);
J
Jesse Brandeburg 已提交
5933
err_flashmap:
5934 5935 5936 5937
	iounmap(adapter->hw.hw_addr);
err_ioremap:
	free_netdev(netdev);
err_alloc_etherdev:
5938 5939
	pci_release_selected_regions(pdev,
	                             pci_select_bars(pdev, IORESOURCE_MEM));
5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958
err_pci_reg:
err_dma:
	pci_disable_device(pdev);
	return err;
}

/**
 * e1000_remove - Device Removal Routine
 * @pdev: PCI device information struct
 *
 * e1000_remove is called by the PCI subsystem to alert the driver
 * that it should release a PCI device.  The could be caused by a
 * Hot-Plug event, or because the driver is going to be removed from
 * memory.
 **/
static void __devexit e1000_remove(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct e1000_adapter *adapter = netdev_priv(netdev);
5959 5960
	bool down = test_bit(__E1000_DOWN, &adapter->state);

5961 5962 5963 5964
	/*
	 * flush_scheduled work may reschedule our watchdog task, so
	 * explicitly disable watchdog tasks from being rescheduled
	 */
5965 5966
	if (!down)
		set_bit(__E1000_DOWN, &adapter->state);
5967 5968 5969
	del_timer_sync(&adapter->watchdog_timer);
	del_timer_sync(&adapter->phy_info_timer);

5970 5971 5972 5973 5974
	cancel_work_sync(&adapter->reset_task);
	cancel_work_sync(&adapter->watchdog_task);
	cancel_work_sync(&adapter->downshift_task);
	cancel_work_sync(&adapter->update_phy_task);
	cancel_work_sync(&adapter->print_hang_task);
5975 5976
	flush_scheduled_work();

5977 5978 5979
	if (!(netdev->flags & IFF_UP))
		e1000_power_down_phy(adapter);

5980 5981 5982
	/* Don't lie to e1000_close() down the road. */
	if (!down)
		clear_bit(__E1000_DOWN, &adapter->state);
5983 5984
	unregister_netdev(netdev);

5985 5986
	if (pci_dev_run_wake(pdev))
		pm_runtime_get_noresume(&pdev->dev);
5987

5988 5989 5990 5991
	/*
	 * Release control of h/w to f/w.  If f/w is AMT enabled, this
	 * would have already happened in close and is redundant.
	 */
5992 5993
	e1000_release_hw_control(adapter);

5994
	e1000e_reset_interrupt_capability(adapter);
5995 5996 5997 5998 5999 6000
	kfree(adapter->tx_ring);
	kfree(adapter->rx_ring);

	iounmap(adapter->hw.hw_addr);
	if (adapter->hw.flash_address)
		iounmap(adapter->hw.flash_address);
6001 6002
	pci_release_selected_regions(pdev,
	                             pci_select_bars(pdev, IORESOURCE_MEM));
6003 6004 6005

	free_netdev(netdev);

J
Jesse Brandeburg 已提交
6006
	/* AER disable */
6007
	pci_disable_pcie_error_reporting(pdev);
J
Jesse Brandeburg 已提交
6008

6009 6010 6011 6012 6013 6014 6015 6016 6017 6018
	pci_disable_device(pdev);
}

/* PCI Error Recovery (ERS) */
static struct pci_error_handlers e1000_err_handler = {
	.error_detected = e1000_io_error_detected,
	.slot_reset = e1000_io_slot_reset,
	.resume = e1000_io_resume,
};

6019
static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = {
6020 6021 6022 6023 6024 6025
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_COPPER), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_FIBER), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER_LP), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_FIBER), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES), board_82571 },
6026 6027 6028
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES_DUAL), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_SERDES_QUAD), board_82571 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571PT_QUAD_COPPER), board_82571 },
6029

6030 6031 6032 6033
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI), board_82572 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_COPPER), board_82572 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_FIBER), board_82572 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82572EI_SERDES), board_82572 },
6034

6035 6036 6037
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573E), board_82573 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573E_IAMT), board_82573 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82573L), board_82573 },
6038

6039
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82574L), board_82574 },
6040
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82574LA), board_82574 },
6041
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82583V), board_82583 },
6042

6043 6044 6045 6046 6047 6048 6049 6050
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_COPPER_DPT),
	  board_80003es2lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_COPPER_SPT),
	  board_80003es2lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_SERDES_DPT),
	  board_80003es2lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_80003ES2LAN_SERDES_SPT),
	  board_80003es2lan },
6051

6052 6053 6054 6055 6056 6057 6058
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE_G), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IFE_GT), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_AMT), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_C), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M), board_ich8lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M_AMT), board_ich8lan },
B
Bruce Allan 已提交
6059
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_82567V_3), board_ich8lan },
6060

6061 6062 6063 6064 6065
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_G), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_GT), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_AMT), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_C), board_ich9lan },
6066
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_BM), board_ich9lan },
6067 6068 6069 6070 6071 6072 6073
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_AMT), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_V), board_ich9lan },

	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LM), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LF), board_ich9lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_V), board_ich9lan },
6074

6075 6076
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_LM), board_ich10lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_LF), board_ich10lan },
6077
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_D_BM_V), board_ich10lan },
6078

6079 6080 6081 6082 6083
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_M_HV_LM), board_pchlan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_M_HV_LC), board_pchlan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_D_HV_DM), board_pchlan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_D_HV_DC), board_pchlan },

6084 6085 6086
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH2_LV_LM), board_pch2lan },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH2_LV_V), board_pch2lan },

6087 6088 6089 6090
	{ }	/* terminate list */
};
MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);

6091
#ifdef CONFIG_PM_OPS
6092
static const struct dev_pm_ops e1000_pm_ops = {
6093 6094 6095
	SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume)
	SET_RUNTIME_PM_OPS(e1000_runtime_suspend,
				e1000_runtime_resume, e1000_idle)
6096
};
6097
#endif
6098

6099 6100 6101 6102 6103 6104
/* PCI Device API Driver */
static struct pci_driver e1000_driver = {
	.name     = e1000e_driver_name,
	.id_table = e1000_pci_tbl,
	.probe    = e1000_probe,
	.remove   = __devexit_p(e1000_remove),
6105
#ifdef CONFIG_PM_OPS
6106
	.driver.pm = &e1000_pm_ops,
6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120
#endif
	.shutdown = e1000_shutdown,
	.err_handler = &e1000_err_handler
};

/**
 * e1000_init_module - Driver Registration Routine
 *
 * e1000_init_module is the first routine called when the driver is
 * loaded. All it does is register with the PCI subsystem.
 **/
static int __init e1000_init_module(void)
{
	int ret;
6121 6122
	pr_info("Intel(R) PRO/1000 Network Driver - %s\n",
		e1000e_driver_version);
6123
	pr_info("Copyright (c) 1999 - 2010 Intel Corporation.\n");
6124
	ret = pci_register_driver(&e1000_driver);
6125

6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148
	return ret;
}
module_init(e1000_init_module);

/**
 * e1000_exit_module - Driver Exit Cleanup Routine
 *
 * e1000_exit_module is called just before the driver is removed
 * from memory.
 **/
static void __exit e1000_exit_module(void)
{
	pci_unregister_driver(&e1000_driver);
}
module_exit(e1000_exit_module);


MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

/* e1000_main.c */