igb_main.c 122.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
/*******************************************************************************

  Intel(R) Gigabit Ethernet Linux driver
  Copyright(c) 2007 Intel Corporation.

  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:
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

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

#include <linux/module.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/netdevice.h>
#include <linux/ipv6.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/pci.h>
41
#include <linux/pci-aspm.h>
42 43 44
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
45
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
46 47
#include <linux/dca.h>
#endif
48 49
#include "igb.h"

A
Auke Kok 已提交
50
#define DRV_VERSION "1.2.45-k2"
51 52 53 54
char igb_driver_name[] = "igb";
char igb_driver_version[] = DRV_VERSION;
static const char igb_driver_string[] =
				"Intel(R) Gigabit Ethernet Network Driver";
A
Alexander Duyck 已提交
55
static const char igb_copyright[] = "Copyright (c) 2008 Intel Corporation.";
56 57 58 59 60 61

static const struct e1000_info *igb_info_tbl[] = {
	[board_82575] = &e1000_82575_info,
};

static struct pci_device_id igb_pci_tbl[] = {
A
Alexander Duyck 已提交
62 63 64
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576), board_82575 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_FIBER), board_82575 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82576_SERDES), board_82575 },
65 66 67 68 69 70 71 72 73 74 75 76 77 78
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_COPPER), board_82575 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575EB_FIBER_SERDES), board_82575 },
	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82575GB_QUAD_COPPER), board_82575 },
	/* required last entry */
	{0, }
};

MODULE_DEVICE_TABLE(pci, igb_pci_tbl);

void igb_reset(struct igb_adapter *);
static int igb_setup_all_tx_resources(struct igb_adapter *);
static int igb_setup_all_rx_resources(struct igb_adapter *);
static void igb_free_all_tx_resources(struct igb_adapter *);
static void igb_free_all_rx_resources(struct igb_adapter *);
79 80
static void igb_free_tx_resources(struct igb_ring *);
static void igb_free_rx_resources(struct igb_ring *);
81 82 83 84 85 86 87 88 89 90 91
void igb_update_stats(struct igb_adapter *);
static int igb_probe(struct pci_dev *, const struct pci_device_id *);
static void __devexit igb_remove(struct pci_dev *pdev);
static int igb_sw_init(struct igb_adapter *);
static int igb_open(struct net_device *);
static int igb_close(struct net_device *);
static void igb_configure_tx(struct igb_adapter *);
static void igb_configure_rx(struct igb_adapter *);
static void igb_setup_rctl(struct igb_adapter *);
static void igb_clean_all_tx_rings(struct igb_adapter *);
static void igb_clean_all_rx_rings(struct igb_adapter *);
92 93
static void igb_clean_tx_ring(struct igb_ring *);
static void igb_clean_rx_ring(struct igb_ring *);
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
static void igb_set_multi(struct net_device *);
static void igb_update_phy_info(unsigned long);
static void igb_watchdog(unsigned long);
static void igb_watchdog_task(struct work_struct *);
static int igb_xmit_frame_ring_adv(struct sk_buff *, struct net_device *,
				  struct igb_ring *);
static int igb_xmit_frame_adv(struct sk_buff *skb, struct net_device *);
static struct net_device_stats *igb_get_stats(struct net_device *);
static int igb_change_mtu(struct net_device *, int);
static int igb_set_mac(struct net_device *, void *);
static irqreturn_t igb_intr(int irq, void *);
static irqreturn_t igb_intr_msi(int irq, void *);
static irqreturn_t igb_msix_other(int irq, void *);
static irqreturn_t igb_msix_rx(int irq, void *);
static irqreturn_t igb_msix_tx(int irq, void *);
static int igb_clean_rx_ring_msix(struct napi_struct *, int);
110
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
111 112 113
static void igb_update_rx_dca(struct igb_ring *);
static void igb_update_tx_dca(struct igb_ring *);
static void igb_setup_dca(struct igb_adapter *);
114
#endif /* CONFIG_IGB_DCA */
115
static bool igb_clean_tx_irq(struct igb_ring *);
116
static int igb_poll(struct napi_struct *, int);
117 118
static bool igb_clean_rx_irq_adv(struct igb_ring *, int *, int);
static void igb_alloc_rx_buffers_adv(struct igb_ring *, int);
119 120 121
#ifdef CONFIG_IGB_LRO
static int igb_get_skb_hdr(struct sk_buff *skb, void **, void **, u64 *, void *);
#endif
122 123 124 125 126 127 128 129 130 131 132 133 134
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
static void igb_tx_timeout(struct net_device *);
static void igb_reset_task(struct work_struct *);
static void igb_vlan_rx_register(struct net_device *, struct vlan_group *);
static void igb_vlan_rx_add_vid(struct net_device *, u16);
static void igb_vlan_rx_kill_vid(struct net_device *, u16);
static void igb_restore_vlan(struct igb_adapter *);

static int igb_suspend(struct pci_dev *, pm_message_t);
#ifdef CONFIG_PM
static int igb_resume(struct pci_dev *);
#endif
static void igb_shutdown(struct pci_dev *);
135
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
136 137 138 139 140 141 142
static int igb_notify_dca(struct notifier_block *, unsigned long, void *);
static struct notifier_block dca_notifier = {
	.notifier_call	= igb_notify_dca,
	.next		= NULL,
	.priority	= 0
};
#endif
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

#ifdef CONFIG_NET_POLL_CONTROLLER
/* for netdump / net console */
static void igb_netpoll(struct net_device *);
#endif

static pci_ers_result_t igb_io_error_detected(struct pci_dev *,
		     pci_channel_state_t);
static pci_ers_result_t igb_io_slot_reset(struct pci_dev *);
static void igb_io_resume(struct pci_dev *);

static struct pci_error_handlers igb_err_handler = {
	.error_detected = igb_io_error_detected,
	.slot_reset = igb_io_slot_reset,
	.resume = igb_io_resume,
};


static struct pci_driver igb_driver = {
	.name     = igb_driver_name,
	.id_table = igb_pci_tbl,
	.probe    = igb_probe,
	.remove   = __devexit_p(igb_remove),
#ifdef CONFIG_PM
	/* Power Managment Hooks */
	.suspend  = igb_suspend,
	.resume   = igb_resume,
#endif
	.shutdown = igb_shutdown,
	.err_handler = &igb_err_handler
};

175 176
static int global_quad_port_a; /* global quad port a indication */

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
MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

#ifdef DEBUG
/**
 * igb_get_hw_dev_name - return device name string
 * used by hardware layer to print debugging information
 **/
char *igb_get_hw_dev_name(struct e1000_hw *hw)
{
	struct igb_adapter *adapter = hw->back;
	return adapter->netdev->name;
}
#endif

/**
 * igb_init_module - Driver Registration Routine
 *
 * igb_init_module is the first routine called when the driver is
 * loaded. All it does is register with the PCI subsystem.
 **/
static int __init igb_init_module(void)
{
	int ret;
	printk(KERN_INFO "%s - version %s\n",
	       igb_driver_string, igb_driver_version);

	printk(KERN_INFO "%s\n", igb_copyright);

208 209
	global_quad_port_a = 0;

210
	ret = pci_register_driver(&igb_driver);
211
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
212 213
	dca_register_notify(&dca_notifier);
#endif
214 215 216 217 218 219 220 221 222 223 224 225 226
	return ret;
}

module_init(igb_init_module);

/**
 * igb_exit_module - Driver Exit Cleanup Routine
 *
 * igb_exit_module is called just before the driver is removed
 * from memory.
 **/
static void __exit igb_exit_module(void)
{
227
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
228 229
	dca_unregister_notify(&dca_notifier);
#endif
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257
	pci_unregister_driver(&igb_driver);
}

module_exit(igb_exit_module);

/**
 * igb_alloc_queues - Allocate memory for all rings
 * @adapter: board private structure to initialize
 *
 * We allocate one ring per queue at run-time since we don't know the
 * number of queues at compile-time.
 **/
static int igb_alloc_queues(struct igb_adapter *adapter)
{
	int i;

	adapter->tx_ring = kcalloc(adapter->num_tx_queues,
				   sizeof(struct igb_ring), GFP_KERNEL);
	if (!adapter->tx_ring)
		return -ENOMEM;

	adapter->rx_ring = kcalloc(adapter->num_rx_queues,
				   sizeof(struct igb_ring), GFP_KERNEL);
	if (!adapter->rx_ring) {
		kfree(adapter->tx_ring);
		return -ENOMEM;
	}

258 259
	adapter->rx_ring->buddy = adapter->tx_ring;

260 261 262 263 264
	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct igb_ring *ring = &(adapter->tx_ring[i]);
		ring->adapter = adapter;
		ring->queue_index = i;
	}
265 266 267
	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct igb_ring *ring = &(adapter->rx_ring[i]);
		ring->adapter = adapter;
P
PJ Waskiewicz 已提交
268
		ring->queue_index = i;
269 270
		ring->itr_register = E1000_ITR;

P
PJ Waskiewicz 已提交
271
		/* set a default napi handler for each rx_ring */
272
		netif_napi_add(adapter->netdev, &ring->napi, igb_poll, 64);
273 274 275 276
	}
	return 0;
}

A
Alexander Duyck 已提交
277 278 279 280 281 282 283 284 285 286 287
static void igb_free_queues(struct igb_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_rx_queues; i++)
		netif_napi_del(&adapter->rx_ring[i].napi);

	kfree(adapter->tx_ring);
	kfree(adapter->rx_ring);
}

288 289 290 291 292 293
#define IGB_N0_QUEUE -1
static void igb_assign_vector(struct igb_adapter *adapter, int rx_queue,
			      int tx_queue, int msix_vector)
{
	u32 msixbm = 0;
	struct e1000_hw *hw = &adapter->hw;
A
Alexander Duyck 已提交
294 295 296 297
	u32 ivar, index;

	switch (hw->mac.type) {
	case e1000_82575:
298 299 300 301 302 303 304 305 306 307 308 309 310 311
		/* The 82575 assigns vectors using a bitmask, which matches the
		   bitmask for the EICR/EIMS/EIMC registers.  To assign one
		   or more queues to a vector, we write the appropriate bits
		   into the MSIXBM register for that vector. */
		if (rx_queue > IGB_N0_QUEUE) {
			msixbm = E1000_EICR_RX_QUEUE0 << rx_queue;
			adapter->rx_ring[rx_queue].eims_value = msixbm;
		}
		if (tx_queue > IGB_N0_QUEUE) {
			msixbm |= E1000_EICR_TX_QUEUE0 << tx_queue;
			adapter->tx_ring[tx_queue].eims_value =
				  E1000_EICR_TX_QUEUE0 << tx_queue;
		}
		array_wr32(E1000_MSIXBM(0), msix_vector, msixbm);
A
Alexander Duyck 已提交
312 313
		break;
	case e1000_82576:
A
Alexander Duyck 已提交
314
		/* The 82576 uses a table-based method for assigning vectors.
A
Alexander Duyck 已提交
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
		   Each queue has a single entry in the table to which we write
		   a vector number along with a "valid" bit.  Sadly, the layout
		   of the table is somewhat counterintuitive. */
		if (rx_queue > IGB_N0_QUEUE) {
			index = (rx_queue & 0x7);
			ivar = array_rd32(E1000_IVAR0, index);
			if (rx_queue < 8) {
				/* vector goes into low byte of register */
				ivar = ivar & 0xFFFFFF00;
				ivar |= msix_vector | E1000_IVAR_VALID;
			} else {
				/* vector goes into third byte of register */
				ivar = ivar & 0xFF00FFFF;
				ivar |= (msix_vector | E1000_IVAR_VALID) << 16;
			}
			adapter->rx_ring[rx_queue].eims_value= 1 << msix_vector;
			array_wr32(E1000_IVAR0, index, ivar);
		}
		if (tx_queue > IGB_N0_QUEUE) {
			index = (tx_queue & 0x7);
			ivar = array_rd32(E1000_IVAR0, index);
			if (tx_queue < 8) {
				/* vector goes into second byte of register */
				ivar = ivar & 0xFFFF00FF;
				ivar |= (msix_vector | E1000_IVAR_VALID) << 8;
			} else {
				/* vector goes into high byte of register */
				ivar = ivar & 0x00FFFFFF;
				ivar |= (msix_vector | E1000_IVAR_VALID) << 24;
			}
			adapter->tx_ring[tx_queue].eims_value= 1 << msix_vector;
			array_wr32(E1000_IVAR0, index, ivar);
		}
		break;
	default:
		BUG();
		break;
	}
353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
}

/**
 * igb_configure_msix - Configure MSI-X hardware
 *
 * igb_configure_msix sets up the hardware to properly
 * generate MSI-X interrupts.
 **/
static void igb_configure_msix(struct igb_adapter *adapter)
{
	u32 tmp;
	int i, vector = 0;
	struct e1000_hw *hw = &adapter->hw;

	adapter->eims_enable_mask = 0;
A
Alexander Duyck 已提交
368 369 370 371 372 373
	if (hw->mac.type == e1000_82576)
		/* Turn on MSI-X capability first, or our settings
		 * won't stick.  And it will take days to debug. */
		wr32(E1000_GPIE, E1000_GPIE_MSIX_MODE |
				   E1000_GPIE_PBA | E1000_GPIE_EIAME | 
 				   E1000_GPIE_NSICR);
374 375 376 377 378 379

	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct igb_ring *tx_ring = &adapter->tx_ring[i];
		igb_assign_vector(adapter, IGB_N0_QUEUE, i, vector++);
		adapter->eims_enable_mask |= tx_ring->eims_value;
		if (tx_ring->itr_val)
380
			writel(tx_ring->itr_val,
381 382 383 384 385 386 387
			       hw->hw_addr + tx_ring->itr_register);
		else
			writel(1, hw->hw_addr + tx_ring->itr_register);
	}

	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct igb_ring *rx_ring = &adapter->rx_ring[i];
388
		rx_ring->buddy = NULL;
389 390 391
		igb_assign_vector(adapter, i, IGB_N0_QUEUE, vector++);
		adapter->eims_enable_mask |= rx_ring->eims_value;
		if (rx_ring->itr_val)
392
			writel(rx_ring->itr_val,
393 394 395 396 397 398 399
			       hw->hw_addr + rx_ring->itr_register);
		else
			writel(1, hw->hw_addr + rx_ring->itr_register);
	}


	/* set vector for other causes, i.e. link changes */
A
Alexander Duyck 已提交
400 401
	switch (hw->mac.type) {
	case e1000_82575:
402 403 404 405 406 407 408 409 410 411 412 413 414
		array_wr32(E1000_MSIXBM(0), vector++,
				      E1000_EIMS_OTHER);

		tmp = rd32(E1000_CTRL_EXT);
		/* enable MSI-X PBA support*/
		tmp |= E1000_CTRL_EXT_PBA_CLR;

		/* Auto-Mask interrupts upon ICR read. */
		tmp |= E1000_CTRL_EXT_EIAME;
		tmp |= E1000_CTRL_EXT_IRCA;

		wr32(E1000_CTRL_EXT, tmp);
		adapter->eims_enable_mask |= E1000_EIMS_OTHER;
P
PJ Waskiewicz 已提交
415
		adapter->eims_other = E1000_EIMS_OTHER;
416

A
Alexander Duyck 已提交
417 418 419 420 421 422 423 424 425 426 427 428 429
		break;

	case e1000_82576:
		tmp = (vector++ | E1000_IVAR_VALID) << 8;
		wr32(E1000_IVAR_MISC, tmp);

		adapter->eims_enable_mask = (1 << (vector)) - 1;
		adapter->eims_other = 1 << (vector - 1);
		break;
	default:
		/* do nothing, since nothing else supports MSI-X */
		break;
	} /* switch (hw->mac.type) */
430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
	wrfl();
}

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

	vector = 0;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct igb_ring *ring = &(adapter->tx_ring[i]);
		sprintf(ring->name, "%s-tx%d", netdev->name, i);
		err = request_irq(adapter->msix_entries[vector].vector,
				  &igb_msix_tx, 0, ring->name,
				  &(adapter->tx_ring[i]));
		if (err)
			goto out;
		ring->itr_register = E1000_EITR(0) + (vector << 2);
455
		ring->itr_val = 976; /* ~4000 ints/sec */
456 457 458 459 460 461 462 463 464 465 466 467 468 469 470
		vector++;
	}
	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct igb_ring *ring = &(adapter->rx_ring[i]);
		if (strlen(netdev->name) < (IFNAMSIZ - 5))
			sprintf(ring->name, "%s-rx%d", netdev->name, i);
		else
			memcpy(ring->name, netdev->name, IFNAMSIZ);
		err = request_irq(adapter->msix_entries[vector].vector,
				  &igb_msix_rx, 0, ring->name,
				  &(adapter->rx_ring[i]));
		if (err)
			goto out;
		ring->itr_register = E1000_EITR(0) + (vector << 2);
		ring->itr_val = adapter->itr;
P
PJ Waskiewicz 已提交
471 472 473
		/* overwrite the poll routine for MSIX, we've already done
		 * netif_napi_add */
		ring->napi.poll = &igb_clean_rx_ring_msix;
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
		vector++;
	}

	err = request_irq(adapter->msix_entries[vector].vector,
			  &igb_msix_other, 0, netdev->name, netdev);
	if (err)
		goto out;

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

static void igb_reset_interrupt_capability(struct igb_adapter *adapter)
{
	if (adapter->msix_entries) {
		pci_disable_msix(adapter->pdev);
		kfree(adapter->msix_entries);
		adapter->msix_entries = NULL;
494
	} else if (adapter->flags & IGB_FLAG_HAS_MSI)
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
		pci_disable_msi(adapter->pdev);
	return;
}


/**
 * igb_set_interrupt_capability - set MSI or MSI-X if supported
 *
 * Attempt to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
static void igb_set_interrupt_capability(struct igb_adapter *adapter)
{
	int err;
	int numvecs, i;

	numvecs = adapter->num_tx_queues + adapter->num_rx_queues + 1;
	adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry),
					GFP_KERNEL);
	if (!adapter->msix_entries)
		goto msi_only;

	for (i = 0; i < numvecs; i++)
		adapter->msix_entries[i].entry = i;

	err = pci_enable_msix(adapter->pdev,
			      adapter->msix_entries,
			      numvecs);
	if (err == 0)
524
		goto out;
525 526 527 528 529 530

	igb_reset_interrupt_capability(adapter);

	/* If we can't do MSI-X, try MSI */
msi_only:
	adapter->num_rx_queues = 1;
531
	adapter->num_tx_queues = 1;
532
	if (!pci_enable_msi(adapter->pdev))
533
		adapter->flags |= IGB_FLAG_HAS_MSI;
534
out:
535
	/* Notify the stack of the (possibly) reduced Tx Queue count. */
536
	adapter->netdev->real_num_tx_queues = adapter->num_tx_queues;
537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553
	return;
}

/**
 * igb_request_irq - initialize interrupts
 *
 * Attempts to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
static int igb_request_irq(struct igb_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_hw *hw = &adapter->hw;
	int err = 0;

	if (adapter->msix_entries) {
		err = igb_request_msix(adapter);
P
PJ Waskiewicz 已提交
554
		if (!err)
555 556 557 558
			goto request_done;
		/* fall back to MSI */
		igb_reset_interrupt_capability(adapter);
		if (!pci_enable_msi(adapter->pdev))
559
			adapter->flags |= IGB_FLAG_HAS_MSI;
560 561 562 563
		igb_free_all_tx_resources(adapter);
		igb_free_all_rx_resources(adapter);
		adapter->num_rx_queues = 1;
		igb_alloc_queues(adapter);
P
PJ Waskiewicz 已提交
564
	} else {
A
Alexander Duyck 已提交
565 566 567 568 569 570 571 572 573 574 575
		switch (hw->mac.type) {
		case e1000_82575:
			wr32(E1000_MSIXBM(0),
			     (E1000_EICR_RX_QUEUE0 | E1000_EIMS_OTHER));
			break;
		case e1000_82576:
			wr32(E1000_IVAR0, E1000_IVAR_VALID);
			break;
		default:
			break;
		}
576
	}
P
PJ Waskiewicz 已提交
577

578
	if (adapter->flags & IGB_FLAG_HAS_MSI) {
579 580 581 582 583 584
		err = request_irq(adapter->pdev->irq, &igb_intr_msi, 0,
				  netdev->name, netdev);
		if (!err)
			goto request_done;
		/* fall back to legacy interrupts */
		igb_reset_interrupt_capability(adapter);
585
		adapter->flags &= ~IGB_FLAG_HAS_MSI;
586 587 588 589 590
	}

	err = request_irq(adapter->pdev->irq, &igb_intr, IRQF_SHARED,
			  netdev->name, netdev);

A
Andy Gospodarek 已提交
591
	if (err)
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
		dev_err(&adapter->pdev->dev, "Error %d getting interrupt\n",
			err);

request_done:
	return err;
}

static void igb_free_irq(struct igb_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;

	if (adapter->msix_entries) {
		int vector = 0, i;

		for (i = 0; i < adapter->num_tx_queues; i++)
			free_irq(adapter->msix_entries[vector++].vector,
				&(adapter->tx_ring[i]));
		for (i = 0; i < adapter->num_rx_queues; i++)
			free_irq(adapter->msix_entries[vector++].vector,
				&(adapter->rx_ring[i]));

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

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

/**
 * igb_irq_disable - Mask off interrupt generation on the NIC
 * @adapter: board private structure
 **/
static void igb_irq_disable(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;

	if (adapter->msix_entries) {
P
PJ Waskiewicz 已提交
629
		wr32(E1000_EIAM, 0);
630 631 632
		wr32(E1000_EIMC, ~0);
		wr32(E1000_EIAC, 0);
	}
P
PJ Waskiewicz 已提交
633 634

	wr32(E1000_IAM, 0);
635 636 637 638 639 640 641 642 643 644 645 646 647 648
	wr32(E1000_IMC, ~0);
	wrfl();
	synchronize_irq(adapter->pdev->irq);
}

/**
 * igb_irq_enable - Enable default interrupt generation settings
 * @adapter: board private structure
 **/
static void igb_irq_enable(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;

	if (adapter->msix_entries) {
P
PJ Waskiewicz 已提交
649 650 651
		wr32(E1000_EIAC, adapter->eims_enable_mask);
		wr32(E1000_EIAM, adapter->eims_enable_mask);
		wr32(E1000_EIMS, adapter->eims_enable_mask);
652
		wr32(E1000_IMS, E1000_IMS_LSC);
P
PJ Waskiewicz 已提交
653 654 655 656
	} else {
		wr32(E1000_IMS, IMS_ENABLE_MASK);
		wr32(E1000_IAM, IMS_ENABLE_MASK);
	}
657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739
}

static void igb_update_mng_vlan(struct igb_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) {
		if (!vlan_group_get_device(adapter->vlgrp, vid)) {
			if (adapter->hw.mng_cookie.status &
				E1000_MNG_DHCP_COOKIE_STATUS_VLAN) {
				igb_vlan_rx_add_vid(netdev, vid);
				adapter->mng_vlan_id = vid;
			} else
				adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;

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

/**
 * igb_release_hw_control - release control of the h/w to f/w
 * @adapter: address of board private structure
 *
 * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit.
 * For ASF and Pass Through versions of f/w this means that the
 * driver is no longer loaded.
 *
 **/
static void igb_release_hw_control(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl_ext;

	/* Let firmware take over control of h/w */
	ctrl_ext = rd32(E1000_CTRL_EXT);
	wr32(E1000_CTRL_EXT,
			ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD);
}


/**
 * igb_get_hw_control - get control of the h/w from f/w
 * @adapter: address of board private structure
 *
 * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit.
 * For ASF and Pass Through versions of f/w this means that
 * the driver is loaded.
 *
 **/
static void igb_get_hw_control(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 ctrl_ext;

	/* Let firmware know the driver has taken over */
	ctrl_ext = rd32(E1000_CTRL_EXT);
	wr32(E1000_CTRL_EXT,
			ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
}

/**
 * igb_configure - configure the hardware for RX and TX
 * @adapter: private board structure
 **/
static void igb_configure(struct igb_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int i;

	igb_get_hw_control(adapter);
	igb_set_multi(netdev);

	igb_restore_vlan(adapter);

	igb_configure_tx(adapter);
	igb_setup_rctl(adapter);
	igb_configure_rx(adapter);
740 741 742

	igb_rx_fifo_flush_82575(&adapter->hw);

743 744 745 746 747
	/* call IGB_DESC_UNUSED which always leaves
	 * at least 1 descriptor unused to make sure
	 * next_to_use != next_to_clean */
	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct igb_ring *ring = &adapter->rx_ring[i];
748
		igb_alloc_rx_buffers_adv(ring, IGB_DESC_UNUSED(ring));
749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
	}


	adapter->tx_queue_len = netdev->tx_queue_len;
}


/**
 * igb_up - Open the interface and prepare it to handle traffic
 * @adapter: board private structure
 **/

int igb_up(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	int i;

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

	clear_bit(__IGB_DOWN, &adapter->state);

P
PJ Waskiewicz 已提交
771 772 773
	for (i = 0; i < adapter->num_rx_queues; i++)
		napi_enable(&adapter->rx_ring[i].napi);
	if (adapter->msix_entries)
774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800
		igb_configure_msix(adapter);

	/* Clear any pending interrupts. */
	rd32(E1000_ICR);
	igb_irq_enable(adapter);

	/* Fire a link change interrupt to start the watchdog. */
	wr32(E1000_ICS, E1000_ICS_LSC);
	return 0;
}

void igb_down(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
	u32 tctl, rctl;
	int i;

	/* signal that we're down so the interrupt handler does not
	 * reschedule our watchdog timer */
	set_bit(__IGB_DOWN, &adapter->state);

	/* disable receives in the hardware */
	rctl = rd32(E1000_RCTL);
	wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN);
	/* flush and sleep below */

801
	netif_tx_stop_all_queues(netdev);
802 803 804 805 806 807 808 809 810

	/* disable transmits in the hardware */
	tctl = rd32(E1000_TCTL);
	tctl &= ~E1000_TCTL_EN;
	wr32(E1000_TCTL, tctl);
	/* flush both disables and wait for them to finish */
	wrfl();
	msleep(10);

P
PJ Waskiewicz 已提交
811 812
	for (i = 0; i < adapter->num_rx_queues; i++)
		napi_disable(&adapter->rx_ring[i].napi);
813 814 815 816 817 818 819 820 821 822 823

	igb_irq_disable(adapter);

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

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

824 825
	if (!pci_channel_offline(adapter->pdev))
		igb_reset(adapter);
826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
	igb_clean_all_tx_rings(adapter);
	igb_clean_all_rx_rings(adapter);
}

void igb_reinit_locked(struct igb_adapter *adapter)
{
	WARN_ON(in_interrupt());
	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
		msleep(1);
	igb_down(adapter);
	igb_up(adapter);
	clear_bit(__IGB_RESETTING, &adapter->state);
}

void igb_reset(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
A
Alexander Duyck 已提交
843 844
	struct e1000_mac_info *mac = &hw->mac;
	struct e1000_fc_info *fc = &hw->fc;
845 846 847 848 849 850
	u32 pba = 0, tx_space, min_tx_space, min_rx_space;
	u16 hwm;

	/* Repartition Pba for greater than 9k mtu
	 * To take effect CTRL.RST is required.
	 */
A
Alexander Duyck 已提交
851
	if (mac->type != e1000_82576) {
852
	pba = E1000_PBA_34K;
A
Alexander Duyck 已提交
853 854 855 856
	}
	else {
		pba = E1000_PBA_64K;
	}
857

A
Alexander Duyck 已提交
858 859
	if ((adapter->max_frame_size > ETH_FRAME_LEN + ETH_FCS_LEN) &&
	    (mac->type < e1000_82576)) {
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
		/* adjust PBA for jumbo frames */
		wr32(E1000_PBA, pba);

		/* To maintain wire speed transmits, the Tx FIFO should be
		 * 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
		 * expressed in KB. */
		pba = rd32(E1000_PBA);
		/* upper 16 bits has Tx packet buffer allocation size in KB */
		tx_space = pba >> 16;
		/* lower 16 bits has Rx packet buffer allocation size in KB */
		pba &= 0xffff;
		/* the tx fifo also stores 16 bytes of information about the tx
		 * but don't include ethernet FCS because hardware appends it */
		min_tx_space = (adapter->max_frame_size +
				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 */
		min_rx_space = adapter->max_frame_size;
		min_rx_space = ALIGN(min_rx_space, 1024);
		min_rx_space >>= 10;

		/* If current Tx allocation is less than the min Tx FIFO size,
		 * and the min Tx FIFO size is less than the current Rx FIFO
		 * allocation, take space away from current Rx allocation */
		if (tx_space < min_tx_space &&
		    ((min_tx_space - tx_space) < pba)) {
			pba = pba - (min_tx_space - tx_space);

			/* if short on rx space, rx wins and must trump tx
			 * adjustment */
			if (pba < min_rx_space)
				pba = min_rx_space;
		}
A
Alexander Duyck 已提交
898
		wr32(E1000_PBA, pba);
899 900 901 902 903 904 905 906 907
	}

	/* flow control settings */
	/* The high water mark must be low enough to fit one full frame
	 * (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, or
	 * - the full Rx FIFO size minus one full frame */
	hwm = min(((pba << 10) * 9 / 10),
A
Alexander Duyck 已提交
908
			((pba << 10) - 2 * adapter->max_frame_size));
909

A
Alexander Duyck 已提交
910 911 912 913 914 915 916
	if (mac->type < e1000_82576) {
		fc->high_water = hwm & 0xFFF8;	/* 8-byte granularity */
		fc->low_water = fc->high_water - 8;
	} else {
		fc->high_water = hwm & 0xFFF0;	/* 16-byte granularity */
		fc->low_water = fc->high_water - 16;
	}
917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933
	fc->pause_time = 0xFFFF;
	fc->send_xon = 1;
	fc->type = fc->original_type;

	/* Allow time for pending master requests to run */
	adapter->hw.mac.ops.reset_hw(&adapter->hw);
	wr32(E1000_WUC, 0);

	if (adapter->hw.mac.ops.init_hw(&adapter->hw))
		dev_err(&adapter->pdev->dev, "Hardware Error\n");

	igb_update_mng_vlan(adapter);

	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
	wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);

	igb_reset_adaptive(&adapter->hw);
934 935
	if (adapter->hw.phy.ops.get_phy_info)
		adapter->hw.phy.ops.get_phy_info(&adapter->hw);
936 937
}

T
Taku Izumi 已提交
938 939 940 941 942 943 944 945 946 947 948 949 950 951 952
/**
 * igb_is_need_ioport - determine if an adapter needs ioport resources or not
 * @pdev: PCI device information struct
 *
 * Returns true if an adapter needs ioport resources
 **/
static int igb_is_need_ioport(struct pci_dev *pdev)
{
	switch (pdev->device) {
	/* Currently there are no adapters that need ioport resources */
	default:
		return false;
	}
}

953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969
/**
 * igb_probe - Device Initialization Routine
 * @pdev: PCI device information struct
 * @ent: entry in igb_pci_tbl
 *
 * Returns 0 on success, negative on failure
 *
 * igb_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 igb_probe(struct pci_dev *pdev,
			       const struct pci_device_id *ent)
{
	struct net_device *netdev;
	struct igb_adapter *adapter;
	struct e1000_hw *hw;
970
	struct pci_dev *us_dev;
971 972
	const struct e1000_info *ei = igb_info_tbl[ent->driver_data];
	unsigned long mmio_start, mmio_len;
973 974
	int i, err, pci_using_dac, pos;
	u16 eeprom_data = 0, state = 0;
975 976
	u16 eeprom_apme_mask = IGB_EEPROM_APME;
	u32 part_num;
T
Taku Izumi 已提交
977
	int bars, need_ioport;
978

T
Taku Izumi 已提交
979 980 981 982 983 984 985 986 987
	/* do not allocate ioport bars when not needed */
	need_ioport = igb_is_need_ioport(pdev);
	if (need_ioport) {
		bars = pci_select_bars(pdev, IORESOURCE_MEM | IORESOURCE_IO);
		err = pci_enable_device(pdev);
	} else {
		bars = pci_select_bars(pdev, IORESOURCE_MEM);
		err = pci_enable_device_mem(pdev);
	}
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008
	if (err)
		return err;

	pci_using_dac = 0;
	err = pci_set_dma_mask(pdev, DMA_64BIT_MASK);
	if (!err) {
		err = pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
		if (!err)
			pci_using_dac = 1;
	} else {
		err = pci_set_dma_mask(pdev, DMA_32BIT_MASK);
		if (err) {
			err = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK);
			if (err) {
				dev_err(&pdev->dev, "No usable DMA "
					"configuration, aborting\n");
				goto err_dma;
			}
		}
	}

1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
	/* 82575 requires that the pci-e link partner disable the L0s state */
	switch (pdev->device) {
	case E1000_DEV_ID_82575EB_COPPER:
	case E1000_DEV_ID_82575EB_FIBER_SERDES:
	case E1000_DEV_ID_82575GB_QUAD_COPPER:
		us_dev = pdev->bus->self;
		pos = pci_find_capability(us_dev, PCI_CAP_ID_EXP);
		if (pos) {
			pci_read_config_word(us_dev, pos + PCI_EXP_LNKCTL,
			                     &state);
			state &= ~PCIE_LINK_STATE_L0S;
			pci_write_config_word(us_dev, pos + PCI_EXP_LNKCTL,
			                      state);
			printk(KERN_INFO "Disabling ASPM L0s upstream switch "
			       "port %x:%x.%x\n", us_dev->bus->number,
			       PCI_SLOT(us_dev->devfn),
			       PCI_FUNC(us_dev->devfn));
		}
	default:
		break;
	}

T
Taku Izumi 已提交
1031
	err = pci_request_selected_regions(pdev, bars, igb_driver_name);
1032 1033 1034 1035
	if (err)
		goto err_pci_reg;

	pci_set_master(pdev);
1036
	pci_save_state(pdev);
1037 1038

	err = -ENOMEM;
1039
	netdev = alloc_etherdev_mq(sizeof(struct igb_adapter), IGB_MAX_TX_QUEUES);
1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	if (!netdev)
		goto err_alloc_etherdev;

	SET_NETDEV_DEV(netdev, &pdev->dev);

	pci_set_drvdata(pdev, netdev);
	adapter = netdev_priv(netdev);
	adapter->netdev = netdev;
	adapter->pdev = pdev;
	hw = &adapter->hw;
	hw->back = adapter;
	adapter->msg_enable = NETIF_MSG_DRV | NETIF_MSG_PROBE;
T
Taku Izumi 已提交
1052 1053
	adapter->bars = bars;
	adapter->need_ioport = need_ioport;
1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109

	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;

	netdev->open = &igb_open;
	netdev->stop = &igb_close;
	netdev->get_stats = &igb_get_stats;
	netdev->set_multicast_list = &igb_set_multi;
	netdev->set_mac_address = &igb_set_mac;
	netdev->change_mtu = &igb_change_mtu;
	netdev->do_ioctl = &igb_ioctl;
	igb_set_ethtool_ops(netdev);
	netdev->tx_timeout = &igb_tx_timeout;
	netdev->watchdog_timeo = 5 * HZ;
	netdev->vlan_rx_register = igb_vlan_rx_register;
	netdev->vlan_rx_add_vid = igb_vlan_rx_add_vid;
	netdev->vlan_rx_kill_vid = igb_vlan_rx_kill_vid;
#ifdef CONFIG_NET_POLL_CONTROLLER
	netdev->poll_controller = igb_netpoll;
#endif
	netdev->hard_start_xmit = &igb_xmit_frame_adv;

	strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);

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

	/* PCI config space info */
	hw->vendor_id = pdev->vendor;
	hw->device_id = pdev->device;
	hw->revision_id = pdev->revision;
	hw->subsystem_vendor_id = pdev->subsystem_vendor;
	hw->subsystem_device_id = pdev->subsystem_device;

	/* setup the private structure */
	hw->back = adapter;
	/* Copy the default MAC, PHY and NVM function pointers */
	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
	memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops));
	/* Initialize skew-specific constants */
	err = ei->get_invariants(hw);
	if (err)
		goto err_hw_init;

	err = igb_sw_init(adapter);
	if (err)
		goto err_sw_init;

	igb_get_bus_info_pcie(hw);

1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
	/* set flags */
	switch (hw->mac.type) {
	case e1000_82576:
	case e1000_82575:
		adapter->flags |= IGB_FLAG_HAS_DCA;
		adapter->flags |= IGB_FLAG_NEED_CTX_IDX;
		break;
	default:
		break;
	}

1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142
	hw->phy.autoneg_wait_to_complete = false;
	hw->mac.adaptive_ifs = true;

	/* Copper options */
	if (hw->phy.media_type == e1000_media_type_copper) {
		hw->phy.mdix = AUTO_ALL_MODES;
		hw->phy.disable_polarity_correction = false;
		hw->phy.ms_type = e1000_ms_hw_default;
	}

	if (igb_check_reset_block(hw))
		dev_info(&pdev->dev,
			"PHY reset is blocked due to SOL/IDER session.\n");

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

	netdev->features |= NETIF_F_TSO;
	netdev->features |= NETIF_F_TSO6;
1143

1144 1145 1146 1147
#ifdef CONFIG_IGB_LRO
	netdev->features |= NETIF_F_LRO;
#endif

1148 1149 1150 1151 1152
	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;

1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 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
	if (pci_using_dac)
		netdev->features |= NETIF_F_HIGHDMA;

	netdev->features |= NETIF_F_LLTX;
	adapter->en_mng_pt = igb_enable_mng_pass_thru(&adapter->hw);

	/* before reading the NVM, reset the controller to put the device in a
	 * known good starting state */
	hw->mac.ops.reset_hw(hw);

	/* make sure the NVM is good */
	if (igb_validate_nvm_checksum(hw) < 0) {
		dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
		err = -EIO;
		goto err_eeprom;
	}

	/* copy the MAC address out of the NVM */
	if (hw->mac.ops.read_mac_addr(hw))
		dev_err(&pdev->dev, "NVM Read Error\n");

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

	if (!is_valid_ether_addr(netdev->perm_addr)) {
		dev_err(&pdev->dev, "Invalid MAC Address\n");
		err = -EIO;
		goto err_eeprom;
	}

	init_timer(&adapter->watchdog_timer);
	adapter->watchdog_timer.function = &igb_watchdog;
	adapter->watchdog_timer.data = (unsigned long) adapter;

	init_timer(&adapter->phy_info_timer);
	adapter->phy_info_timer.function = &igb_update_phy_info;
	adapter->phy_info_timer.data = (unsigned long) adapter;

	INIT_WORK(&adapter->reset_task, igb_reset_task);
	INIT_WORK(&adapter->watchdog_task, igb_watchdog_task);

	/* Initialize link & ring properties that are user-changeable */
	adapter->tx_ring->count = 256;
	for (i = 0; i < adapter->num_tx_queues; i++)
		adapter->tx_ring[i].count = adapter->tx_ring->count;
	adapter->rx_ring->count = 256;
	for (i = 0; i < adapter->num_rx_queues; i++)
		adapter->rx_ring[i].count = adapter->rx_ring->count;

	adapter->fc_autoneg = true;
	hw->mac.autoneg = true;
	hw->phy.autoneg_advertised = 0x2f;

	hw->fc.original_type = e1000_fc_default;
	hw->fc.type = e1000_fc_default;

	adapter->itr_setting = 3;
	adapter->itr = IGB_START_ITR;

	igb_validate_mdi_setting(hw);

	adapter->rx_csum = 1;

	/* Initial Wake on LAN setting If APM wake is enabled in the EEPROM,
	 * enable the ACPI Magic Packet filter
	 */

	if (hw->bus.func == 0 ||
	    hw->device_id == E1000_DEV_ID_82575EB_COPPER)
		hw->nvm.ops.read_nvm(hw, NVM_INIT_CONTROL3_PORT_A, 1,
				     &eeprom_data);

	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 */
	switch (pdev->device) {
	case E1000_DEV_ID_82575GB_QUAD_COPPER:
		adapter->eeprom_wol = 0;
		break;
	case E1000_DEV_ID_82575EB_FIBER_SERDES:
A
Alexander Duyck 已提交
1236 1237
	case E1000_DEV_ID_82576_FIBER:
	case E1000_DEV_ID_82576_SERDES:
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
		/* Wake events only supported on port A for dual fiber
		 * regardless of eeprom setting */
		if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1)
			adapter->eeprom_wol = 0;
		break;
	}

	/* initialize the wol settings based on the eeprom settings */
	adapter->wol = adapter->eeprom_wol;

	/* reset the hardware with the new settings */
	igb_reset(adapter);

	/* let the f/w know that the h/w is now under the control of the
	 * driver. */
	igb_get_hw_control(adapter);

	/* tell the stack to leave us alone until igb_open() is called */
	netif_carrier_off(netdev);
1257
	netif_tx_stop_all_queues(netdev);
1258 1259 1260 1261 1262 1263

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

1264
#ifdef CONFIG_IGB_DCA
1265 1266 1267
	if ((adapter->flags & IGB_FLAG_HAS_DCA) &&
	    (dca_add_requester(&pdev->dev) == 0)) {
		adapter->flags |= IGB_FLAG_DCA_ENABLED;
J
Jeb Cramer 已提交
1268 1269 1270 1271 1272 1273 1274 1275
		dev_info(&pdev->dev, "DCA enabled\n");
		/* Always use CB2 mode, difference is masked
		 * in the CB driver. */
		wr32(E1000_DCA_CTRL, 2);
		igb_setup_dca(adapter);
	}
#endif

1276 1277
	dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
	/* print bus type/speed/width info */
J
Johannes Berg 已提交
1278
	dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n",
1279 1280 1281 1282 1283 1284
		 netdev->name,
		 ((hw->bus.speed == e1000_bus_speed_2500)
		  ? "2.5Gb/s" : "unknown"),
		 ((hw->bus.width == e1000_bus_width_pcie_x4)
		  ? "Width x4" : (hw->bus.width == e1000_bus_width_pcie_x1)
		  ? "Width x1" : "unknown"),
J
Johannes Berg 已提交
1285
		 netdev->dev_addr);
1286 1287 1288 1289 1290 1291 1292 1293

	igb_read_part_num(hw, &part_num);
	dev_info(&pdev->dev, "%s: PBA No: %06x-%03x\n", netdev->name,
		(part_num >> 8), (part_num & 0xff));

	dev_info(&pdev->dev,
		"Using %s interrupts. %d rx queue(s), %d tx queue(s)\n",
		adapter->msix_entries ? "MSI-X" :
1294
		(adapter->flags & IGB_FLAG_HAS_MSI) ? "MSI" : "legacy",
1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308
		adapter->num_rx_queues, adapter->num_tx_queues);

	return 0;

err_register:
	igb_release_hw_control(adapter);
err_eeprom:
	if (!igb_check_reset_block(hw))
		hw->phy.ops.reset_phy(hw);

	if (hw->flash_address)
		iounmap(hw->flash_address);

	igb_remove_device(hw);
A
Alexander Duyck 已提交
1309
	igb_free_queues(adapter);
1310 1311 1312 1313 1314 1315
err_sw_init:
err_hw_init:
	iounmap(hw->hw_addr);
err_ioremap:
	free_netdev(netdev);
err_alloc_etherdev:
T
Taku Izumi 已提交
1316
	pci_release_selected_regions(pdev, bars);
1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
err_pci_reg:
err_dma:
	pci_disable_device(pdev);
	return err;
}

/**
 * igb_remove - Device Removal Routine
 * @pdev: PCI device information struct
 *
 * igb_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 igb_remove(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);
1336
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
1337
	struct e1000_hw *hw = &adapter->hw;
1338
#endif
1339 1340 1341 1342 1343 1344 1345 1346 1347

	/* flush_scheduled work may reschedule our watchdog task, so
	 * explicitly disable watchdog tasks from being rescheduled  */
	set_bit(__IGB_DOWN, &adapter->state);
	del_timer_sync(&adapter->watchdog_timer);
	del_timer_sync(&adapter->phy_info_timer);

	flush_scheduled_work();

1348
#ifdef CONFIG_IGB_DCA
1349
	if (adapter->flags & IGB_FLAG_DCA_ENABLED) {
J
Jeb Cramer 已提交
1350 1351
		dev_info(&pdev->dev, "DCA disabled\n");
		dca_remove_requester(&pdev->dev);
1352
		adapter->flags &= ~IGB_FLAG_DCA_ENABLED;
J
Jeb Cramer 已提交
1353 1354 1355 1356
		wr32(E1000_DCA_CTRL, 1);
	}
#endif

1357 1358 1359 1360 1361 1362
	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
	 * would have already happened in close and is redundant. */
	igb_release_hw_control(adapter);

	unregister_netdev(netdev);

1363 1364
	if (adapter->hw.phy.ops.reset_phy &&
	    !igb_check_reset_block(&adapter->hw))
1365 1366 1367 1368 1369
		adapter->hw.phy.ops.reset_phy(&adapter->hw);

	igb_remove_device(&adapter->hw);
	igb_reset_interrupt_capability(adapter);

A
Alexander Duyck 已提交
1370
	igb_free_queues(adapter);
1371 1372 1373 1374

	iounmap(adapter->hw.hw_addr);
	if (adapter->hw.flash_address)
		iounmap(adapter->hw.flash_address);
T
Taku Izumi 已提交
1375
	pci_release_selected_regions(pdev, adapter->bars);
1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404

	free_netdev(netdev);

	pci_disable_device(pdev);
}

/**
 * igb_sw_init - Initialize general software structures (struct igb_adapter)
 * @adapter: board private structure to initialize
 *
 * igb_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 igb_sw_init(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;

	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);

	adapter->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE;
	adapter->rx_ps_hdr_size = 0; /* disable packet split */
	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;

	/* Number of supported queues. */
	/* Having more queues than CPUs doesn't make sense. */
1405 1406
	adapter->num_rx_queues = min((u32)IGB_MAX_RX_QUEUES, (u32)num_online_cpus());
	adapter->num_tx_queues = min(IGB_MAX_TX_QUEUES, num_online_cpus());
1407

1408 1409
	/* This call may decrease the number of queues depending on
	 * interrupt mode. */
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476
	igb_set_interrupt_capability(adapter);

	if (igb_alloc_queues(adapter)) {
		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
		return -ENOMEM;
	}

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

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

/**
 * igb_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 igb_open(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	int err;
	int i;

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

	/* allocate transmit descriptors */
	err = igb_setup_all_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

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

	/* e1000_power_up_phy(adapter); */

	adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN))
		igb_update_mng_vlan(adapter);

	/* before we allocate an interrupt, we must be ready to handle it.
	 * 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
	 * clean_rx handler before we do so.  */
	igb_configure(adapter);

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

	/* From here on the code is the same as igb_up() */
	clear_bit(__IGB_DOWN, &adapter->state);

P
PJ Waskiewicz 已提交
1477 1478
	for (i = 0; i < adapter->num_rx_queues; i++)
		napi_enable(&adapter->rx_ring[i].napi);
1479 1480 1481

	/* Clear any pending interrupts. */
	rd32(E1000_ICR);
P
PJ Waskiewicz 已提交
1482 1483 1484

	igb_irq_enable(adapter);

1485 1486
	netif_tx_start_all_queues(netdev);

1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590
	/* Fire a link status change interrupt to start the watchdog. */
	wr32(E1000_ICS, E1000_ICS_LSC);

	return 0;

err_req_irq:
	igb_release_hw_control(adapter);
	/* e1000_power_down_phy(adapter); */
	igb_free_all_rx_resources(adapter);
err_setup_rx:
	igb_free_all_tx_resources(adapter);
err_setup_tx:
	igb_reset(adapter);

	return err;
}

/**
 * igb_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 driver's 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 igb_close(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);

	WARN_ON(test_bit(__IGB_RESETTING, &adapter->state));
	igb_down(adapter);

	igb_free_irq(adapter);

	igb_free_all_tx_resources(adapter);
	igb_free_all_rx_resources(adapter);

	/* 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) */
	if ((adapter->hw.mng_cookie.status &
			  E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
	     !(adapter->vlgrp &&
	       vlan_group_get_device(adapter->vlgrp, adapter->mng_vlan_id)))
		igb_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id);

	return 0;
}

/**
 * igb_setup_tx_resources - allocate Tx resources (Descriptors)
 * @adapter: board private structure
 * @tx_ring: tx descriptor ring (for a specific queue) to setup
 *
 * Return 0 on success, negative on failure
 **/

int igb_setup_tx_resources(struct igb_adapter *adapter,
			   struct igb_ring *tx_ring)
{
	struct pci_dev *pdev = adapter->pdev;
	int size;

	size = sizeof(struct igb_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)
			+ sizeof(u32);
	tx_ring->size = ALIGN(tx_ring->size, 4096);

	tx_ring->desc = pci_alloc_consistent(pdev, tx_ring->size,
					     &tx_ring->dma);

	if (!tx_ring->desc)
		goto err;

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

err:
	vfree(tx_ring->buffer_info);
	dev_err(&adapter->pdev->dev,
		"Unable to allocate memory for the transmit descriptor ring\n");
	return -ENOMEM;
}

/**
 * igb_setup_all_tx_resources - wrapper to allocate Tx resources
 *				  (Descriptors) for all queues
 * @adapter: board private structure
 *
 * Return 0 on success, negative on failure
 **/
static int igb_setup_all_tx_resources(struct igb_adapter *adapter)
{
	int i, err = 0;
1591
	int r_idx;
1592 1593 1594 1595 1596 1597 1598

	for (i = 0; i < adapter->num_tx_queues; i++) {
		err = igb_setup_tx_resources(adapter, &adapter->tx_ring[i]);
		if (err) {
			dev_err(&adapter->pdev->dev,
				"Allocation for Tx Queue %u failed\n", i);
			for (i--; i >= 0; i--)
1599
				igb_free_tx_resources(&adapter->tx_ring[i]);
1600 1601 1602 1603
			break;
		}
	}

1604 1605 1606 1607
	for (i = 0; i < IGB_MAX_TX_QUEUES; i++) {
		r_idx = i % adapter->num_tx_queues;
		adapter->multi_tx_table[i] = &adapter->tx_ring[r_idx];
	}	
1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 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 1693
	return err;
}

/**
 * igb_configure_tx - Configure transmit Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Tx unit of the MAC after a reset.
 **/
static void igb_configure_tx(struct igb_adapter *adapter)
{
	u64 tdba, tdwba;
	struct e1000_hw *hw = &adapter->hw;
	u32 tctl;
	u32 txdctl, txctrl;
	int i;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct igb_ring *ring = &(adapter->tx_ring[i]);

		wr32(E1000_TDLEN(i),
				ring->count * sizeof(struct e1000_tx_desc));
		tdba = ring->dma;
		wr32(E1000_TDBAL(i),
				tdba & 0x00000000ffffffffULL);
		wr32(E1000_TDBAH(i), tdba >> 32);

		tdwba = ring->dma + ring->count * sizeof(struct e1000_tx_desc);
		tdwba |= 1; /* enable head wb */
		wr32(E1000_TDWBAL(i),
				tdwba & 0x00000000ffffffffULL);
		wr32(E1000_TDWBAH(i), tdwba >> 32);

		ring->head = E1000_TDH(i);
		ring->tail = E1000_TDT(i);
		writel(0, hw->hw_addr + ring->tail);
		writel(0, hw->hw_addr + ring->head);
		txdctl = rd32(E1000_TXDCTL(i));
		txdctl |= E1000_TXDCTL_QUEUE_ENABLE;
		wr32(E1000_TXDCTL(i), txdctl);

		/* Turn off Relaxed Ordering on head write-backs.  The
		 * writebacks MUST be delivered in order or it will
		 * completely screw up our bookeeping.
		 */
		txctrl = rd32(E1000_DCA_TXCTRL(i));
		txctrl &= ~E1000_DCA_TXCTRL_TX_WB_RO_EN;
		wr32(E1000_DCA_TXCTRL(i), txctrl);
	}



	/* Use the default values for the Tx Inter Packet Gap (IPG) timer */

	/* Program the Transmit Control Register */

	tctl = rd32(E1000_TCTL);
	tctl &= ~E1000_TCTL_CT;
	tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC |
		(E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT);

	igb_config_collision_dist(hw);

	/* Setup Transmit Descriptor Settings for eop descriptor */
	adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_RS;

	/* Enable transmits */
	tctl |= E1000_TCTL_EN;

	wr32(E1000_TCTL, tctl);
}

/**
 * igb_setup_rx_resources - allocate Rx resources (Descriptors)
 * @adapter: board private structure
 * @rx_ring:    rx descriptor ring (for a specific queue) to setup
 *
 * Returns 0 on success, negative on failure
 **/

int igb_setup_rx_resources(struct igb_adapter *adapter,
			   struct igb_ring *rx_ring)
{
	struct pci_dev *pdev = adapter->pdev;
	int size, desc_len;

1694 1695 1696 1697 1698 1699 1700 1701
#ifdef CONFIG_IGB_LRO
	size = sizeof(struct net_lro_desc) * MAX_LRO_DESCRIPTORS;
	rx_ring->lro_mgr.lro_arr = vmalloc(size);
	if (!rx_ring->lro_mgr.lro_arr)
		goto err;
	memset(rx_ring->lro_mgr.lro_arr, 0, size);
#endif

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

	desc_len = sizeof(union e1000_adv_rx_desc);

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

	rx_ring->desc = pci_alloc_consistent(pdev, rx_ring->size,
					     &rx_ring->dma);

	if (!rx_ring->desc)
		goto err;

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

	rx_ring->adapter = adapter;

	return 0;

err:
1728 1729 1730 1731
#ifdef CONFIG_IGB_LRO
	vfree(rx_ring->lro_mgr.lro_arr);
	rx_ring->lro_mgr.lro_arr = NULL;
#endif
1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754
	vfree(rx_ring->buffer_info);
	dev_err(&adapter->pdev->dev, "Unable to allocate memory for "
		"the receive descriptor ring\n");
	return -ENOMEM;
}

/**
 * igb_setup_all_rx_resources - wrapper to allocate Rx resources
 *				  (Descriptors) for all queues
 * @adapter: board private structure
 *
 * Return 0 on success, negative on failure
 **/
static int igb_setup_all_rx_resources(struct igb_adapter *adapter)
{
	int i, err = 0;

	for (i = 0; i < adapter->num_rx_queues; i++) {
		err = igb_setup_rx_resources(adapter, &adapter->rx_ring[i]);
		if (err) {
			dev_err(&adapter->pdev->dev,
				"Allocation for Rx Queue %u failed\n", i);
			for (i--; i >= 0; i--)
1755
				igb_free_rx_resources(&adapter->rx_ring[i]);
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
			break;
		}
	}

	return err;
}

/**
 * igb_setup_rctl - configure the receive control registers
 * @adapter: Board private structure
 **/
static void igb_setup_rctl(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	u32 rctl;
	u32 srrctl = 0;
	int i;

	rctl = rd32(E1000_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);

1782 1783 1784 1785
	/*
	 * enable stripping of CRC. It's unlikely this will break BMC
	 * redirection as it did with e1000. Newer features require
	 * that the HW strips the CRC.
1786
	*/
1787
	rctl |= E1000_RCTL_SECRC;
1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833

	rctl &= ~E1000_RCTL_SBP;

	if (adapter->netdev->mtu <= ETH_DATA_LEN)
		rctl &= ~E1000_RCTL_LPE;
	else
		rctl |= E1000_RCTL_LPE;
	if (adapter->rx_buffer_len <= IGB_RXBUFFER_2048) {
		/* Setup buffer sizes */
		rctl &= ~E1000_RCTL_SZ_4096;
		rctl |= E1000_RCTL_BSEX;
		switch (adapter->rx_buffer_len) {
		case IGB_RXBUFFER_256:
			rctl |= E1000_RCTL_SZ_256;
			rctl &= ~E1000_RCTL_BSEX;
			break;
		case IGB_RXBUFFER_512:
			rctl |= E1000_RCTL_SZ_512;
			rctl &= ~E1000_RCTL_BSEX;
			break;
		case IGB_RXBUFFER_1024:
			rctl |= E1000_RCTL_SZ_1024;
			rctl &= ~E1000_RCTL_BSEX;
			break;
		case IGB_RXBUFFER_2048:
		default:
			rctl |= E1000_RCTL_SZ_2048;
			rctl &= ~E1000_RCTL_BSEX;
			break;
		}
	} else {
		rctl &= ~E1000_RCTL_BSEX;
		srrctl = adapter->rx_buffer_len >> E1000_SRRCTL_BSIZEPKT_SHIFT;
	}

	/* 82575 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 */
	if (rctl & E1000_RCTL_LPE) {
		adapter->rx_ps_hdr_size = IGB_RXBUFFER_128;
1834
		srrctl |= adapter->rx_ps_hdr_size <<
1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868
			 E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
		srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
	} else {
		adapter->rx_ps_hdr_size = 0;
		srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
	}

	for (i = 0; i < adapter->num_rx_queues; i++)
		wr32(E1000_SRRCTL(i), srrctl);

	wr32(E1000_RCTL, rctl);
}

/**
 * igb_configure_rx - Configure receive Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Rx unit of the MAC after a reset.
 **/
static void igb_configure_rx(struct igb_adapter *adapter)
{
	u64 rdba;
	struct e1000_hw *hw = &adapter->hw;
	u32 rctl, rxcsum;
	u32 rxdctl;
	int i;

	/* disable receives while setting up the descriptors */
	rctl = rd32(E1000_RCTL);
	wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN);
	wrfl();
	mdelay(10);

	if (adapter->itr_setting > 3)
1869
		wr32(E1000_ITR, adapter->itr);
1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893

	/* Setup the HW Rx Head and Tail Descriptor Pointers and
	 * the Base and Length of the Rx Descriptor Ring */
	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct igb_ring *ring = &(adapter->rx_ring[i]);
		rdba = ring->dma;
		wr32(E1000_RDBAL(i),
				rdba & 0x00000000ffffffffULL);
		wr32(E1000_RDBAH(i), rdba >> 32);
		wr32(E1000_RDLEN(i),
			       ring->count * sizeof(union e1000_adv_rx_desc));

		ring->head = E1000_RDH(i);
		ring->tail = E1000_RDT(i);
		writel(0, hw->hw_addr + ring->tail);
		writel(0, hw->hw_addr + ring->head);

		rxdctl = rd32(E1000_RXDCTL(i));
		rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
		rxdctl &= 0xFFF00000;
		rxdctl |= IGB_RX_PTHRESH;
		rxdctl |= IGB_RX_HTHRESH << 8;
		rxdctl |= IGB_RX_WTHRESH << 16;
		wr32(E1000_RXDCTL(i), rxdctl);
1894 1895 1896 1897 1898 1899 1900 1901 1902 1903
#ifdef CONFIG_IGB_LRO
		/* Intitial LRO Settings */
		ring->lro_mgr.max_aggr = MAX_LRO_AGGR;
		ring->lro_mgr.max_desc = MAX_LRO_DESCRIPTORS;
		ring->lro_mgr.get_skb_header = igb_get_skb_hdr;
		ring->lro_mgr.features = LRO_F_NAPI | LRO_F_EXTRACT_VLAN_ID;
		ring->lro_mgr.dev = adapter->netdev;
		ring->lro_mgr.ip_summed = CHECKSUM_UNNECESSARY;
		ring->lro_mgr.ip_summed_aggr = CHECKSUM_UNNECESSARY;
#endif
1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916
	}

	if (adapter->num_rx_queues > 1) {
		u32 random[10];
		u32 mrqc;
		u32 j, shift;
		union e1000_reta {
			u32 dword;
			u8  bytes[4];
		} reta;

		get_random_bytes(&random[0], 40);

A
Alexander Duyck 已提交
1917 1918 1919 1920
		if (hw->mac.type >= e1000_82576)
			shift = 0;
		else
			shift = 6;
1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985
		for (j = 0; j < (32 * 4); j++) {
			reta.bytes[j & 3] =
				(j % adapter->num_rx_queues) << shift;
			if ((j & 3) == 3)
				writel(reta.dword,
				       hw->hw_addr + E1000_RETA(0) + (j & ~3));
		}
		mrqc = E1000_MRQC_ENABLE_RSS_4Q;

		/* Fill out hash function seeds */
		for (j = 0; j < 10; j++)
			array_wr32(E1000_RSSRK(0), j, random[j]);

		mrqc |= (E1000_MRQC_RSS_FIELD_IPV4 |
			 E1000_MRQC_RSS_FIELD_IPV4_TCP);
		mrqc |= (E1000_MRQC_RSS_FIELD_IPV6 |
			 E1000_MRQC_RSS_FIELD_IPV6_TCP);
		mrqc |= (E1000_MRQC_RSS_FIELD_IPV4_UDP |
			 E1000_MRQC_RSS_FIELD_IPV6_UDP);
		mrqc |= (E1000_MRQC_RSS_FIELD_IPV6_UDP_EX |
			 E1000_MRQC_RSS_FIELD_IPV6_TCP_EX);


		wr32(E1000_MRQC, mrqc);

		/* Multiqueue and raw packet checksumming are mutually
		 * exclusive.  Note that this not the same as TCP/IP
		 * checksumming, which works fine. */
		rxcsum = rd32(E1000_RXCSUM);
		rxcsum |= E1000_RXCSUM_PCSD;
		wr32(E1000_RXCSUM, rxcsum);
	} else {
		/* Enable Receive Checksum Offload for TCP and UDP */
		rxcsum = rd32(E1000_RXCSUM);
		if (adapter->rx_csum) {
			rxcsum |= E1000_RXCSUM_TUOFL;

			/* Enable IPv4 payload checksum for UDP fragments
			 * Must be used in conjunction with packet-split. */
			if (adapter->rx_ps_hdr_size)
				rxcsum |= E1000_RXCSUM_IPPCSE;
		} else {
			rxcsum &= ~E1000_RXCSUM_TUOFL;
			/* don't need to clear IPPCSE as it defaults to 0 */
		}
		wr32(E1000_RXCSUM, rxcsum);
	}

	if (adapter->vlgrp)
		wr32(E1000_RLPML,
				adapter->max_frame_size + VLAN_TAG_SIZE);
	else
		wr32(E1000_RLPML, adapter->max_frame_size);

	/* Enable Receives */
	wr32(E1000_RCTL, rctl);
}

/**
 * igb_free_tx_resources - Free Tx Resources per Queue
 * @adapter: board private structure
 * @tx_ring: Tx descriptor ring for a specific queue
 *
 * Free all transmit software resources
 **/
1986
static void igb_free_tx_resources(struct igb_ring *tx_ring)
1987
{
1988
	struct pci_dev *pdev = tx_ring->adapter->pdev;
1989

1990
	igb_clean_tx_ring(tx_ring);
1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

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

	pci_free_consistent(pdev, tx_ring->size, tx_ring->desc, tx_ring->dma);

	tx_ring->desc = NULL;
}

/**
 * igb_free_all_tx_resources - Free Tx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all transmit software resources
 **/
static void igb_free_all_tx_resources(struct igb_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_tx_queues; i++)
2011
		igb_free_tx_resources(&adapter->tx_ring[i]);
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036
}

static void igb_unmap_and_free_tx_resource(struct igb_adapter *adapter,
					   struct igb_buffer *buffer_info)
{
	if (buffer_info->dma) {
		pci_unmap_page(adapter->pdev,
				buffer_info->dma,
				buffer_info->length,
				PCI_DMA_TODEVICE);
		buffer_info->dma = 0;
	}
	if (buffer_info->skb) {
		dev_kfree_skb_any(buffer_info->skb);
		buffer_info->skb = NULL;
	}
	buffer_info->time_stamp = 0;
	/* buffer_info must be completely set up in the transmit path */
}

/**
 * igb_clean_tx_ring - Free Tx Buffers
 * @adapter: board private structure
 * @tx_ring: ring to be cleaned
 **/
2037
static void igb_clean_tx_ring(struct igb_ring *tx_ring)
2038
{
2039
	struct igb_adapter *adapter = tx_ring->adapter;
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
	struct igb_buffer *buffer_info;
	unsigned long size;
	unsigned int i;

	if (!tx_ring->buffer_info)
		return;
	/* Free all the Tx ring sk_buffs */

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

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

	/* Zero out the descriptor ring */

	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);
}

/**
 * igb_clean_all_tx_rings - Free Tx Buffers for all queues
 * @adapter: board private structure
 **/
static void igb_clean_all_tx_rings(struct igb_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_tx_queues; i++)
2076
		igb_clean_tx_ring(&adapter->tx_ring[i]);
2077 2078 2079 2080 2081 2082 2083 2084 2085
}

/**
 * igb_free_rx_resources - Free Rx Resources
 * @adapter: board private structure
 * @rx_ring: ring to clean the resources from
 *
 * Free all receive software resources
 **/
2086
static void igb_free_rx_resources(struct igb_ring *rx_ring)
2087
{
2088
	struct pci_dev *pdev = rx_ring->adapter->pdev;
2089

2090
	igb_clean_rx_ring(rx_ring);
2091 2092 2093 2094

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

2095 2096 2097 2098 2099
#ifdef CONFIG_IGB_LRO
	vfree(rx_ring->lro_mgr.lro_arr);
	rx_ring->lro_mgr.lro_arr = NULL;
#endif 

2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115
	pci_free_consistent(pdev, rx_ring->size, rx_ring->desc, rx_ring->dma);

	rx_ring->desc = NULL;
}

/**
 * igb_free_all_rx_resources - Free Rx Resources for All Queues
 * @adapter: board private structure
 *
 * Free all receive software resources
 **/
static void igb_free_all_rx_resources(struct igb_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_rx_queues; i++)
2116
		igb_free_rx_resources(&adapter->rx_ring[i]);
2117 2118 2119 2120 2121 2122 2123
}

/**
 * igb_clean_rx_ring - Free Rx Buffers per Queue
 * @adapter: board private structure
 * @rx_ring: ring to free buffers from
 **/
2124
static void igb_clean_rx_ring(struct igb_ring *rx_ring)
2125
{
2126
	struct igb_adapter *adapter = rx_ring->adapter;
2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153
	struct igb_buffer *buffer_info;
	struct pci_dev *pdev = adapter->pdev;
	unsigned long size;
	unsigned int i;

	if (!rx_ring->buffer_info)
		return;
	/* 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->rx_ps_hdr_size)
				pci_unmap_single(pdev, buffer_info->dma,
						 adapter->rx_ps_hdr_size,
						 PCI_DMA_FROMDEVICE);
			else
				pci_unmap_single(pdev, buffer_info->dma,
						 adapter->rx_buffer_len,
						 PCI_DMA_FROMDEVICE);
			buffer_info->dma = 0;
		}

		if (buffer_info->skb) {
			dev_kfree_skb(buffer_info->skb);
			buffer_info->skb = NULL;
		}
		if (buffer_info->page) {
2154 2155 2156 2157
			if (buffer_info->page_dma)
				pci_unmap_page(pdev, buffer_info->page_dma,
					       PAGE_SIZE / 2,
					       PCI_DMA_FROMDEVICE);
2158 2159 2160
			put_page(buffer_info->page);
			buffer_info->page = NULL;
			buffer_info->page_dma = 0;
2161
			buffer_info->page_offset = 0;
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
		}
	}

	size = sizeof(struct igb_buffer) * rx_ring->count;
	memset(rx_ring->buffer_info, 0, size);

	/* 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;

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

/**
 * igb_clean_all_rx_rings - Free Rx Buffers for all queues
 * @adapter: board private structure
 **/
static void igb_clean_all_rx_rings(struct igb_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_rx_queues; i++)
2187
		igb_clean_rx_ring(&adapter->rx_ring[i]);
2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235
}

/**
 * igb_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 igb_set_mac(struct net_device *netdev, void *p)
{
	struct igb_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);

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

	return 0;
}

/**
 * igb_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 igb_set_multi(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_mac_info *mac = &hw->mac;
	struct dev_mc_list *mc_ptr;
	u8  *mta_list;
	u32 rctl;
	int i;

	/* Check for Promiscuous and All Multicast modes */

	rctl = rd32(E1000_RCTL);

2236
	if (netdev->flags & IFF_PROMISC) {
2237
		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
2238 2239 2240 2241 2242 2243 2244
		rctl &= ~E1000_RCTL_VFE;
	} else {
		if (netdev->flags & IFF_ALLMULTI) {
			rctl |= E1000_RCTL_MPE;
			rctl &= ~E1000_RCTL_UPE;
		} else
			rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
2245
		rctl |= E1000_RCTL_VFE;
2246
	}
2247 2248 2249 2250
	wr32(E1000_RCTL, rctl);

	if (!netdev->mc_count) {
		/* nothing to program, so clear mc list */
A
Alexander Duyck 已提交
2251
		igb_update_mc_addr_list_82575(hw, NULL, 0, 1,
2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268
					  mac->rar_entry_count);
		return;
	}

	mta_list = kzalloc(netdev->mc_count * 6, GFP_ATOMIC);
	if (!mta_list)
		return;

	/* The shared function expects a packed array of only addresses. */
	mc_ptr = netdev->mc_list;

	for (i = 0; i < netdev->mc_count; i++) {
		if (!mc_ptr)
			break;
		memcpy(mta_list + (i*ETH_ALEN), mc_ptr->dmi_addr, ETH_ALEN);
		mc_ptr = mc_ptr->next;
	}
A
Alexander Duyck 已提交
2269 2270
	igb_update_mc_addr_list_82575(hw, mta_list, i, 1,
	                              mac->rar_entry_count);
2271 2272 2273 2274 2275 2276 2277 2278
	kfree(mta_list);
}

/* Need to wait a few seconds after link up to get diagnostic information from
 * the phy */
static void igb_update_phy_info(unsigned long data)
{
	struct igb_adapter *adapter = (struct igb_adapter *) data;
2279 2280
	if (adapter->hw.phy.ops.get_phy_info)
		adapter->hw.phy.ops.get_phy_info(&adapter->hw);
2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303
}

/**
 * igb_watchdog - Timer Call-back
 * @data: pointer to adapter cast into an unsigned long
 **/
static void igb_watchdog(unsigned long data)
{
	struct igb_adapter *adapter = (struct igb_adapter *)data;
	/* Do the rest outside of interrupt context */
	schedule_work(&adapter->watchdog_task);
}

static void igb_watchdog_task(struct work_struct *work)
{
	struct igb_adapter *adapter = container_of(work,
					struct igb_adapter, watchdog_task);
	struct e1000_hw *hw = &adapter->hw;

	struct net_device *netdev = adapter->netdev;
	struct igb_ring *tx_ring = adapter->tx_ring;
	struct e1000_mac_info *mac = &adapter->hw.mac;
	u32 link;
2304
	u32 eics = 0;
2305
	s32 ret_val;
2306
	int i;
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 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361

	if ((netif_carrier_ok(netdev)) &&
	    (rd32(E1000_STATUS) & E1000_STATUS_LU))
		goto link_up;

	ret_val = hw->mac.ops.check_for_link(&adapter->hw);
	if ((ret_val == E1000_ERR_PHY) &&
	    (hw->phy.type == e1000_phy_igp_3) &&
	    (rd32(E1000_CTRL) &
	     E1000_PHY_CTRL_GBE_DISABLE))
		dev_info(&adapter->pdev->dev,
			 "Gigabit has been disabled, downgrading speed\n");

	if ((hw->phy.media_type == e1000_media_type_internal_serdes) &&
	    !(rd32(E1000_TXCW) & E1000_TXCW_ANE))
		link = mac->serdes_has_link;
	else
		link = rd32(E1000_STATUS) &
				      E1000_STATUS_LU;

	if (link) {
		if (!netif_carrier_ok(netdev)) {
			u32 ctrl;
			hw->mac.ops.get_speed_and_duplex(&adapter->hw,
						   &adapter->link_speed,
						   &adapter->link_duplex);

			ctrl = rd32(E1000_CTRL);
			dev_info(&adapter->pdev->dev,
				 "NIC Link is Up %d Mbps %s, "
				 "Flow Control: %s\n",
				 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")));

			/* tweak tx_queue_len according to speed/duplex and
			 * adjust the timeout factor */
			netdev->tx_queue_len = adapter->tx_queue_len;
			adapter->tx_timeout_factor = 1;
			switch (adapter->link_speed) {
			case SPEED_10:
				netdev->tx_queue_len = 10;
				adapter->tx_timeout_factor = 14;
				break;
			case SPEED_100:
				netdev->tx_queue_len = 100;
				/* maybe add some timeout factor ? */
				break;
			}

			netif_carrier_on(netdev);
2362
			netif_tx_wake_all_queues(netdev);
2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373

			if (!test_bit(__IGB_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;
			dev_info(&adapter->pdev->dev, "NIC Link is Down\n");
			netif_carrier_off(netdev);
2374
			netif_tx_stop_all_queues(netdev);
2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407
			if (!test_bit(__IGB_DOWN, &adapter->state))
				mod_timer(&adapter->phy_info_timer,
					  round_jiffies(jiffies + 2 * HZ));
		}
	}

link_up:
	igb_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;

	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;

	igb_update_adaptive(&adapter->hw);

	if (!netif_carrier_ok(netdev)) {
		if (IGB_DESC_UNUSED(tx_ring) + 1 < tx_ring->count) {
			/* We've lost link, so the controller stops DMA,
			 * but we've got queued Tx work that's never going
			 * to get done, so reset controller to flush Tx.
			 * (Do the reset outside of interrupt context). */
			adapter->tx_timeout_count++;
			schedule_work(&adapter->reset_task);
		}
	}

	/* Cause software interrupt to ensure rx ring is cleaned */
2408 2409 2410 2411 2412 2413 2414
	if (adapter->msix_entries) {
		for (i = 0; i < adapter->num_rx_queues; i++)
			eics |= adapter->rx_ring[i].eims_value;
		wr32(E1000_EICS, eics);
	} else {
		wr32(E1000_ICS, E1000_ICS_RXDMT0);
	}
2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432

	/* Force detection of hung controller every watchdog period */
	tx_ring->detect_tx_hung = true;

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

enum latency_range {
	lowest_latency = 0,
	low_latency = 1,
	bulk_latency = 2,
	latency_invalid = 255
};


2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449
/**
 * igb_update_ring_itr - update the dynamic ITR value based on packet size
 *
 *      Stores a new ITR value based on strictly on packet size.  This
 *      algorithm is less sophisticated than that used in igb_update_itr,
 *      due to the difficulty of synchronizing statistics across multiple
 *      receive rings.  The divisors and thresholds used by this fuction
 *      were determined based on theoretical maximum wire speed and testing
 *      data, in order to minimize response time while increasing bulk
 *      throughput.
 *      This functionality is controlled by the InterruptThrottleRate module
 *      parameter (see igb_param.c)
 *      NOTE:  This function is called only when operating in a multiqueue
 *             receive environment.
 * @rx_ring: pointer to ring
 **/
static void igb_update_ring_itr(struct igb_ring *rx_ring)
2450
{
2451 2452 2453
	int new_val = rx_ring->itr_val;
	int avg_wire_size = 0;
	struct igb_adapter *adapter = rx_ring->adapter;
2454

2455 2456
	if (!rx_ring->total_packets)
		goto clear_counts; /* no packets, so don't do anything */
2457

2458 2459 2460 2461 2462 2463
	/* For non-gigabit speeds, just fix the interrupt rate at 4000
	 * ints/sec - ITR timer value of 120 ticks.
	 */
	if (adapter->link_speed != SPEED_1000) {
		new_val = 120;
		goto set_itr_val;
2464
	}
2465
	avg_wire_size = rx_ring->total_bytes / rx_ring->total_packets;
2466

2467 2468 2469 2470 2471
	/* Add 24 bytes to size to account for CRC, preamble, and gap */
	avg_wire_size += 24;

	/* Don't starve jumbo frames */
	avg_wire_size = min(avg_wire_size, 3000);
2472

2473 2474 2475 2476 2477
	/* Give a little boost to mid-size frames */
	if ((avg_wire_size > 300) && (avg_wire_size < 1200))
		new_val = avg_wire_size / 3;
	else
		new_val = avg_wire_size / 2;
2478

2479
set_itr_val:
2480 2481
	if (new_val != rx_ring->itr_val) {
		rx_ring->itr_val = new_val;
2482
		rx_ring->set_itr = 1;
2483
	}
2484 2485 2486
clear_counts:
	rx_ring->total_bytes = 0;
	rx_ring->total_packets = 0;
2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 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 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552
}

/**
 * igb_update_itr - update the dynamic ITR value based on statistics
 *      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
 *      while increasing bulk throughput.
 *      this functionality is controlled by the InterruptThrottleRate module
 *      parameter (see igb_param.c)
 *      NOTE:  These calculations are only valid when operating in a single-
 *             queue environment.
 * @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
 **/
static unsigned int igb_update_itr(struct igb_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;
}

2553
static void igb_set_itr(struct igb_adapter *adapter)
2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569
{
	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;
	}

	adapter->rx_itr = igb_update_itr(adapter,
				    adapter->rx_itr,
				    adapter->rx_ring->total_packets,
				    adapter->rx_ring->total_bytes);

2570
	if (adapter->rx_ring->buddy) {
2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
		adapter->tx_itr = igb_update_itr(adapter,
					    adapter->tx_itr,
					    adapter->tx_ring->total_packets,
					    adapter->tx_ring->total_bytes);

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

2581 2582 2583 2584 2585
	/* conservative mode (itr 3) eliminates the lowest_latency setting */
	if (adapter->itr_setting == 3 &&
	    current_itr == lowest_latency)
		current_itr = low_latency;

2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601
	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:
2602 2603 2604 2605 2606 2607 2608
	adapter->rx_ring->total_bytes = 0;
	adapter->rx_ring->total_packets = 0;
	if (adapter->rx_ring->buddy) {
		adapter->rx_ring->buddy->total_bytes = 0;
		adapter->rx_ring->buddy->total_packets = 0;
	}

2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622
	if (new_itr != adapter->itr) {
		/* this attempts to bias the interrupt rate towards Bulk
		 * by adding intermediate steps when interrupt rate is
		 * increasing */
		new_itr = new_itr > adapter->itr ?
			     min(adapter->itr + (new_itr >> 2), new_itr) :
			     new_itr;
		/* Don't write the value here; it resets the adapter's
		 * internal timer, and causes us to delay far longer than
		 * we should between interrupts.  Instead, we write the ITR
		 * value at the beginning of the next interrupt so the timing
		 * ends up being correct.
		 */
		adapter->itr = new_itr;
2623 2624
		adapter->rx_ring->itr_val = 1000000000 / (new_itr * 256);
		adapter->rx_ring->set_itr = 1;
2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699
	}

	return;
}


#define IGB_TX_FLAGS_CSUM		0x00000001
#define IGB_TX_FLAGS_VLAN		0x00000002
#define IGB_TX_FLAGS_TSO		0x00000004
#define IGB_TX_FLAGS_IPV4		0x00000008
#define IGB_TX_FLAGS_VLAN_MASK	0xffff0000
#define IGB_TX_FLAGS_VLAN_SHIFT	16

static inline int igb_tso_adv(struct igb_adapter *adapter,
			      struct igb_ring *tx_ring,
			      struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
{
	struct e1000_adv_tx_context_desc *context_desc;
	unsigned int i;
	int err;
	struct igb_buffer *buffer_info;
	u32 info = 0, tu_cmd = 0;
	u32 mss_l4len_idx, l4len;
	*hdr_len = 0;

	if (skb_header_cloned(skb)) {
		err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (err)
			return err;
	}

	l4len = tcp_hdrlen(skb);
	*hdr_len += l4len;

	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);
	} else if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV6) {
		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);
	}

	i = tx_ring->next_to_use;

	buffer_info = &tx_ring->buffer_info[i];
	context_desc = E1000_TX_CTXTDESC_ADV(*tx_ring, i);
	/* VLAN MACLEN IPLEN */
	if (tx_flags & IGB_TX_FLAGS_VLAN)
		info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
	info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
	*hdr_len += skb_network_offset(skb);
	info |= skb_network_header_len(skb);
	*hdr_len += skb_network_header_len(skb);
	context_desc->vlan_macip_lens = cpu_to_le32(info);

	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
	tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);

	if (skb->protocol == htons(ETH_P_IP))
		tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
	tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;

	context_desc->type_tucmd_mlhl = cpu_to_le32(tu_cmd);

	/* MSS L4LEN IDX */
	mss_l4len_idx = (skb_shinfo(skb)->gso_size << E1000_ADVTXD_MSS_SHIFT);
	mss_l4len_idx |= (l4len << E1000_ADVTXD_L4LEN_SHIFT);

2700 2701 2702
	/* Context index must be unique per ring. */
	if (adapter->flags & IGB_FLAG_NEED_CTX_IDX)
		mss_l4len_idx |= tx_ring->queue_index << 4;
2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743

	context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
	context_desc->seqnum_seed = 0;

	buffer_info->time_stamp = jiffies;
	buffer_info->dma = 0;
	i++;
	if (i == tx_ring->count)
		i = 0;

	tx_ring->next_to_use = i;

	return true;
}

static inline bool igb_tx_csum_adv(struct igb_adapter *adapter,
					struct igb_ring *tx_ring,
					struct sk_buff *skb, u32 tx_flags)
{
	struct e1000_adv_tx_context_desc *context_desc;
	unsigned int i;
	struct igb_buffer *buffer_info;
	u32 info = 0, tu_cmd = 0;

	if ((skb->ip_summed == CHECKSUM_PARTIAL) ||
	    (tx_flags & IGB_TX_FLAGS_VLAN)) {
		i = tx_ring->next_to_use;
		buffer_info = &tx_ring->buffer_info[i];
		context_desc = E1000_TX_CTXTDESC_ADV(*tx_ring, i);

		if (tx_flags & IGB_TX_FLAGS_VLAN)
			info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
		info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
		if (skb->ip_summed == CHECKSUM_PARTIAL)
			info |= skb_network_header_len(skb);

		context_desc->vlan_macip_lens = cpu_to_le32(info);

		tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);

		if (skb->ip_summed == CHECKSUM_PARTIAL) {
2744 2745
			switch (skb->protocol) {
			case __constant_htons(ETH_P_IP):
2746
				tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761
				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
					tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
				break;
			case __constant_htons(ETH_P_IPV6):
				/* XXX what about other V6 headers?? */
				if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
					tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
				break;
			default:
				if (unlikely(net_ratelimit()))
					dev_warn(&adapter->pdev->dev,
					    "partial checksum but proto=%x!\n",
					    skb->protocol);
				break;
			}
2762 2763 2764 2765
		}

		context_desc->type_tucmd_mlhl = cpu_to_le32(tu_cmd);
		context_desc->seqnum_seed = 0;
2766 2767 2768
		if (adapter->flags & IGB_FLAG_NEED_CTX_IDX)
			context_desc->mss_l4len_idx =
				cpu_to_le32(tx_ring->queue_index << 4);
2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 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 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868

		buffer_info->time_stamp = jiffies;
		buffer_info->dma = 0;

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

		return true;
	}


	return false;
}

#define IGB_MAX_TXD_PWR	16
#define IGB_MAX_DATA_PER_TXD	(1<<IGB_MAX_TXD_PWR)

static inline int igb_tx_map_adv(struct igb_adapter *adapter,
				 struct igb_ring *tx_ring,
				 struct sk_buff *skb)
{
	struct igb_buffer *buffer_info;
	unsigned int len = skb_headlen(skb);
	unsigned int count = 0, i;
	unsigned int f;

	i = tx_ring->next_to_use;

	buffer_info = &tx_ring->buffer_info[i];
	BUG_ON(len >= IGB_MAX_DATA_PER_TXD);
	buffer_info->length = len;
	/* set time_stamp *before* dma to help avoid a possible race */
	buffer_info->time_stamp = jiffies;
	buffer_info->dma = pci_map_single(adapter->pdev, skb->data, len,
					  PCI_DMA_TODEVICE);
	count++;
	i++;
	if (i == tx_ring->count)
		i = 0;

	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) {
		struct skb_frag_struct *frag;

		frag = &skb_shinfo(skb)->frags[f];
		len = frag->size;

		buffer_info = &tx_ring->buffer_info[i];
		BUG_ON(len >= IGB_MAX_DATA_PER_TXD);
		buffer_info->length = len;
		buffer_info->time_stamp = jiffies;
		buffer_info->dma = pci_map_page(adapter->pdev,
						frag->page,
						frag->page_offset,
						len,
						PCI_DMA_TODEVICE);

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

	i = (i == 0) ? tx_ring->count - 1 : i - 1;
	tx_ring->buffer_info[i].skb = skb;

	return count;
}

static inline void igb_tx_queue_adv(struct igb_adapter *adapter,
				    struct igb_ring *tx_ring,
				    int tx_flags, int count, u32 paylen,
				    u8 hdr_len)
{
	union e1000_adv_tx_desc *tx_desc = NULL;
	struct igb_buffer *buffer_info;
	u32 olinfo_status = 0, cmd_type_len;
	unsigned int i;

	cmd_type_len = (E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_IFCS |
			E1000_ADVTXD_DCMD_DEXT);

	if (tx_flags & IGB_TX_FLAGS_VLAN)
		cmd_type_len |= E1000_ADVTXD_DCMD_VLE;

	if (tx_flags & IGB_TX_FLAGS_TSO) {
		cmd_type_len |= E1000_ADVTXD_DCMD_TSE;

		/* insert tcp checksum */
		olinfo_status |= E1000_TXD_POPTS_TXSM << 8;

		/* insert ip checksum */
		if (tx_flags & IGB_TX_FLAGS_IPV4)
			olinfo_status |= E1000_TXD_POPTS_IXSM << 8;

	} else if (tx_flags & IGB_TX_FLAGS_CSUM) {
		olinfo_status |= E1000_TXD_POPTS_TXSM << 8;
	}

2869 2870 2871
	if ((adapter->flags & IGB_FLAG_NEED_CTX_IDX) &&
	    (tx_flags & (IGB_TX_FLAGS_CSUM | IGB_TX_FLAGS_TSO |
			 IGB_TX_FLAGS_VLAN)))
2872
		olinfo_status |= tx_ring->queue_index << 4;
2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907

	olinfo_status |= ((paylen - hdr_len) << E1000_ADVTXD_PAYLEN_SHIFT);

	i = tx_ring->next_to_use;
	while (count--) {
		buffer_info = &tx_ring->buffer_info[i];
		tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
		tx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
		tx_desc->read.cmd_type_len =
			cpu_to_le32(cmd_type_len | buffer_info->length);
		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
		i++;
		if (i == tx_ring->count)
			i = 0;
	}

	tx_desc->read.cmd_type_len |= cpu_to_le32(adapter->txd_cmd);
	/* 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();

	tx_ring->next_to_use = i;
	writel(i, adapter->hw.hw_addr + tx_ring->tail);
	/* we need this if more than one processor can write to our tail
	 * at a time, it syncronizes IO on IA64/Altix systems */
	mmiowb();
}

static int __igb_maybe_stop_tx(struct net_device *netdev,
			       struct igb_ring *tx_ring, int size)
{
	struct igb_adapter *adapter = netdev_priv(netdev);

2908 2909
	netif_stop_subqueue(netdev, tx_ring->queue_index);

2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920
	/* Herbert's original patch had:
	 *  smp_mb__after_netif_stop_queue();
	 * but since that doesn't exist yet, just open code it. */
	smp_mb();

	/* We need to check again in a case another CPU has just
	 * made room available. */
	if (IGB_DESC_UNUSED(tx_ring) < size)
		return -EBUSY;

	/* A reprieve! */
2921
	netif_wake_subqueue(netdev, tx_ring->queue_index);
2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966
	++adapter->restart_queue;
	return 0;
}

static int igb_maybe_stop_tx(struct net_device *netdev,
			     struct igb_ring *tx_ring, int size)
{
	if (IGB_DESC_UNUSED(tx_ring) >= size)
		return 0;
	return __igb_maybe_stop_tx(netdev, tx_ring, size);
}

#define TXD_USE_COUNT(S) (((S) >> (IGB_MAX_TXD_PWR)) + 1)

static int igb_xmit_frame_ring_adv(struct sk_buff *skb,
				   struct net_device *netdev,
				   struct igb_ring *tx_ring)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	unsigned int tx_flags = 0;
	unsigned int len;
	u8 hdr_len = 0;
	int tso = 0;

	len = skb_headlen(skb);

	if (test_bit(__IGB_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;
	}

	/* need: 1 descriptor per page,
	 *       + 2 desc gap to keep tail from touching head,
	 *       + 1 desc for skb->data,
	 *       + 1 desc for context descriptor,
	 * otherwise try next time */
	if (igb_maybe_stop_tx(netdev, tx_ring, skb_shinfo(skb)->nr_frags + 4)) {
		/* this is a hard error */
		return NETDEV_TX_BUSY;
	}
2967
	skb_orphan(skb);
2968 2969 2970 2971 2972 2973

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

2974 2975 2976
	if (skb->protocol == htons(ETH_P_IP))
		tx_flags |= IGB_TX_FLAGS_IPV4;

2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005
	tso = skb_is_gso(skb) ? igb_tso_adv(adapter, tx_ring, skb, tx_flags,
					      &hdr_len) : 0;

	if (tso < 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (tso)
		tx_flags |= IGB_TX_FLAGS_TSO;
	else if (igb_tx_csum_adv(adapter, tx_ring, skb, tx_flags))
			if (skb->ip_summed == CHECKSUM_PARTIAL)
				tx_flags |= IGB_TX_FLAGS_CSUM;

	igb_tx_queue_adv(adapter, tx_ring, tx_flags,
			 igb_tx_map_adv(adapter, tx_ring, skb),
			 skb->len, hdr_len);

	netdev->trans_start = jiffies;

	/* Make sure there is space in the ring for the next send. */
	igb_maybe_stop_tx(netdev, tx_ring, MAX_SKB_FRAGS + 4);

	return NETDEV_TX_OK;
}

static int igb_xmit_frame_adv(struct sk_buff *skb, struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
3006 3007 3008 3009 3010
	struct igb_ring *tx_ring;

	int r_idx = 0;
	r_idx = skb->queue_mapping & (IGB_MAX_TX_QUEUES - 1);
	tx_ring = adapter->multi_tx_table[r_idx];
3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104

	/* This goes back to the question of how to logically map a tx queue
	 * to a flow.  Right now, performance is impacted slightly negatively
	 * if using multiple tx queues.  If the stack breaks away from a
	 * single qdisc implementation, we can look at this again. */
	return (igb_xmit_frame_ring_adv(skb, netdev, tx_ring));
}

/**
 * igb_tx_timeout - Respond to a Tx Hang
 * @netdev: network interface device structure
 **/
static void igb_tx_timeout(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;

	/* Do the reset outside of interrupt context */
	adapter->tx_timeout_count++;
	schedule_work(&adapter->reset_task);
	wr32(E1000_EICS, adapter->eims_enable_mask &
		~(E1000_EIMS_TCP_TIMER | E1000_EIMS_OTHER));
}

static void igb_reset_task(struct work_struct *work)
{
	struct igb_adapter *adapter;
	adapter = container_of(work, struct igb_adapter, reset_task);

	igb_reinit_locked(adapter);
}

/**
 * igb_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 *
igb_get_stats(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);

	/* only return the current stats */
	return &adapter->net_stats;
}

/**
 * igb_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 igb_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;

	if ((max_frame < ETH_ZLEN + ETH_FCS_LEN) ||
	    (max_frame > MAX_JUMBO_FRAME_SIZE)) {
		dev_err(&adapter->pdev->dev, "Invalid MTU setting\n");
		return -EINVAL;
	}

#define MAX_STD_JUMBO_FRAME_SIZE 9234
	if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) {
		dev_err(&adapter->pdev->dev, "MTU > 9216 not supported.\n");
		return -EINVAL;
	}

	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
		msleep(1);
	/* igb_down has a dependency on max_frame_size */
	adapter->max_frame_size = max_frame;
	if (netif_running(netdev))
		igb_down(adapter);

	/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
	 * means we reserve 2 more, this pushes us to allocate from the next
	 * larger slab size.
	 * i.e. RXBUFFER_2048 --> size-4096 slab
	 */

	if (max_frame <= IGB_RXBUFFER_256)
		adapter->rx_buffer_len = IGB_RXBUFFER_256;
	else if (max_frame <= IGB_RXBUFFER_512)
		adapter->rx_buffer_len = IGB_RXBUFFER_512;
	else if (max_frame <= IGB_RXBUFFER_1024)
		adapter->rx_buffer_len = IGB_RXBUFFER_1024;
	else if (max_frame <= IGB_RXBUFFER_2048)
		adapter->rx_buffer_len = IGB_RXBUFFER_2048;
	else
3105 3106 3107 3108 3109
#if (PAGE_SIZE / 2) > IGB_RXBUFFER_16384
		adapter->rx_buffer_len = IGB_RXBUFFER_16384;
#else
		adapter->rx_buffer_len = PAGE_SIZE / 2;
#endif
3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272
	/* adjust allocation if LPE protects us, and we aren't using SBP */
	if ((max_frame == ETH_FRAME_LEN + ETH_FCS_LEN) ||
	     (max_frame == MAXIMUM_ETHERNET_VLAN_SIZE))
		adapter->rx_buffer_len = MAXIMUM_ETHERNET_VLAN_SIZE;

	dev_info(&adapter->pdev->dev, "changing MTU from %d to %d\n",
		 netdev->mtu, new_mtu);
	netdev->mtu = new_mtu;

	if (netif_running(netdev))
		igb_up(adapter);
	else
		igb_reset(adapter);

	clear_bit(__IGB_RESETTING, &adapter->state);

	return 0;
}

/**
 * igb_update_stats - Update the board statistics counters
 * @adapter: board private structure
 **/

void igb_update_stats(struct igb_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct pci_dev *pdev = adapter->pdev;
	u16 phy_tmp;

#define PHY_IDLE_ERROR_COUNT_MASK 0x00FF

	/*
	 * 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 += rd32(E1000_CRCERRS);
	adapter->stats.gprc += rd32(E1000_GPRC);
	adapter->stats.gorc += rd32(E1000_GORCL);
	rd32(E1000_GORCH); /* clear GORCL */
	adapter->stats.bprc += rd32(E1000_BPRC);
	adapter->stats.mprc += rd32(E1000_MPRC);
	adapter->stats.roc += rd32(E1000_ROC);

	adapter->stats.prc64 += rd32(E1000_PRC64);
	adapter->stats.prc127 += rd32(E1000_PRC127);
	adapter->stats.prc255 += rd32(E1000_PRC255);
	adapter->stats.prc511 += rd32(E1000_PRC511);
	adapter->stats.prc1023 += rd32(E1000_PRC1023);
	adapter->stats.prc1522 += rd32(E1000_PRC1522);
	adapter->stats.symerrs += rd32(E1000_SYMERRS);
	adapter->stats.sec += rd32(E1000_SEC);

	adapter->stats.mpc += rd32(E1000_MPC);
	adapter->stats.scc += rd32(E1000_SCC);
	adapter->stats.ecol += rd32(E1000_ECOL);
	adapter->stats.mcc += rd32(E1000_MCC);
	adapter->stats.latecol += rd32(E1000_LATECOL);
	adapter->stats.dc += rd32(E1000_DC);
	adapter->stats.rlec += rd32(E1000_RLEC);
	adapter->stats.xonrxc += rd32(E1000_XONRXC);
	adapter->stats.xontxc += rd32(E1000_XONTXC);
	adapter->stats.xoffrxc += rd32(E1000_XOFFRXC);
	adapter->stats.xofftxc += rd32(E1000_XOFFTXC);
	adapter->stats.fcruc += rd32(E1000_FCRUC);
	adapter->stats.gptc += rd32(E1000_GPTC);
	adapter->stats.gotc += rd32(E1000_GOTCL);
	rd32(E1000_GOTCH); /* clear GOTCL */
	adapter->stats.rnbc += rd32(E1000_RNBC);
	adapter->stats.ruc += rd32(E1000_RUC);
	adapter->stats.rfc += rd32(E1000_RFC);
	adapter->stats.rjc += rd32(E1000_RJC);
	adapter->stats.tor += rd32(E1000_TORH);
	adapter->stats.tot += rd32(E1000_TOTH);
	adapter->stats.tpr += rd32(E1000_TPR);

	adapter->stats.ptc64 += rd32(E1000_PTC64);
	adapter->stats.ptc127 += rd32(E1000_PTC127);
	adapter->stats.ptc255 += rd32(E1000_PTC255);
	adapter->stats.ptc511 += rd32(E1000_PTC511);
	adapter->stats.ptc1023 += rd32(E1000_PTC1023);
	adapter->stats.ptc1522 += rd32(E1000_PTC1522);

	adapter->stats.mptc += rd32(E1000_MPTC);
	adapter->stats.bptc += rd32(E1000_BPTC);

	/* used for adaptive IFS */

	hw->mac.tx_packet_delta = rd32(E1000_TPT);
	adapter->stats.tpt += hw->mac.tx_packet_delta;
	hw->mac.collision_delta = rd32(E1000_COLC);
	adapter->stats.colc += hw->mac.collision_delta;

	adapter->stats.algnerrc += rd32(E1000_ALGNERRC);
	adapter->stats.rxerrc += rd32(E1000_RXERRC);
	adapter->stats.tncrs += rd32(E1000_TNCRS);
	adapter->stats.tsctc += rd32(E1000_TSCTC);
	adapter->stats.tsctfc += rd32(E1000_TSCTFC);

	adapter->stats.iac += rd32(E1000_IAC);
	adapter->stats.icrxoc += rd32(E1000_ICRXOC);
	adapter->stats.icrxptc += rd32(E1000_ICRXPTC);
	adapter->stats.icrxatc += rd32(E1000_ICRXATC);
	adapter->stats.ictxptc += rd32(E1000_ICTXPTC);
	adapter->stats.ictxatc += rd32(E1000_ICTXATC);
	adapter->stats.ictxqec += rd32(E1000_ICTXQEC);
	adapter->stats.ictxqmtc += rd32(E1000_ICTXQMTC);
	adapter->stats.icrxdmtc += rd32(E1000_ICRXDMTC);

	/* Fill out the OS statistics structure */
	adapter->net_stats.multicast = adapter->stats.mprc;
	adapter->net_stats.collisions = adapter->stats.colc;

	/* Rx Errors */

	/* RLEC on some newer hardware can be incorrect so build
	* our own version based on RUC and ROC */
	adapter->net_stats.rx_errors = adapter->stats.rxerrc +
		adapter->stats.crcerrs + adapter->stats.algnerrc +
		adapter->stats.ruc + adapter->stats.roc +
		adapter->stats.cexterr;
	adapter->net_stats.rx_length_errors = adapter->stats.ruc +
					      adapter->stats.roc;
	adapter->net_stats.rx_crc_errors = adapter->stats.crcerrs;
	adapter->net_stats.rx_frame_errors = adapter->stats.algnerrc;
	adapter->net_stats.rx_missed_errors = adapter->stats.mpc;

	/* Tx Errors */
	adapter->net_stats.tx_errors = adapter->stats.ecol +
				       adapter->stats.latecol;
	adapter->net_stats.tx_aborted_errors = adapter->stats.ecol;
	adapter->net_stats.tx_window_errors = adapter->stats.latecol;
	adapter->net_stats.tx_carrier_errors = adapter->stats.tncrs;

	/* Tx Dropped needs to be maintained elsewhere */

	/* Phy Stats */
	if (hw->phy.media_type == e1000_media_type_copper) {
		if ((adapter->link_speed == SPEED_1000) &&
		   (!hw->phy.ops.read_phy_reg(hw, PHY_1000T_STATUS,
					      &phy_tmp))) {
			phy_tmp &= PHY_IDLE_ERROR_COUNT_MASK;
			adapter->phy_stats.idle_errors += phy_tmp;
		}
	}

	/* Management Stats */
	adapter->stats.mgptc += rd32(E1000_MGTPTC);
	adapter->stats.mgprc += rd32(E1000_MGTPRC);
	adapter->stats.mgpdc += rd32(E1000_MGTPDC);
}


static irqreturn_t igb_msix_other(int irq, void *data)
{
	struct net_device *netdev = data;
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
P
PJ Waskiewicz 已提交
3273
	u32 icr = rd32(E1000_ICR);
3274

P
PJ Waskiewicz 已提交
3275 3276 3277 3278 3279 3280 3281
	/* reading ICR causes bit 31 of EICR to be cleared */
	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(__IGB_DOWN, &adapter->state))
		mod_timer(&adapter->watchdog_timer, jiffies + 1);
3282
	
3283 3284
no_link_interrupt:
	wr32(E1000_IMS, E1000_IMS_LSC);
P
PJ Waskiewicz 已提交
3285
	wr32(E1000_EIMS, adapter->eims_other);
3286 3287 3288 3289 3290 3291 3292 3293 3294 3295

	return IRQ_HANDLED;
}

static irqreturn_t igb_msix_tx(int irq, void *data)
{
	struct igb_ring *tx_ring = data;
	struct igb_adapter *adapter = tx_ring->adapter;
	struct e1000_hw *hw = &adapter->hw;

3296
#ifdef CONFIG_IGB_DCA
3297
	if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3298 3299
		igb_update_tx_dca(tx_ring);
#endif
3300 3301
	tx_ring->total_bytes = 0;
	tx_ring->total_packets = 0;
3302 3303 3304

	/* auto mask will automatically reenable the interrupt when we write
	 * EICS */
3305
	if (!igb_clean_tx_irq(tx_ring))
3306 3307
		/* Ring was not completely cleaned, so fire another interrupt */
		wr32(E1000_EICS, tx_ring->eims_value);
3308
	else
3309
		wr32(E1000_EIMS, tx_ring->eims_value);
3310

3311 3312 3313
	return IRQ_HANDLED;
}

3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333
static void igb_write_itr(struct igb_ring *ring)
{
	struct e1000_hw *hw = &ring->adapter->hw;
	if ((ring->adapter->itr_setting & 3) && ring->set_itr) {
		switch (hw->mac.type) {
		case e1000_82576:
			wr32(ring->itr_register,
			     ring->itr_val |
			     0x80000000);
			break;
		default:
			wr32(ring->itr_register,
			     ring->itr_val |
			     (ring->itr_val << 16));
			break;
		}
		ring->set_itr = 0;
	}
}

3334 3335 3336 3337 3338
static irqreturn_t igb_msix_rx(int irq, void *data)
{
	struct igb_ring *rx_ring = data;
	struct igb_adapter *adapter = rx_ring->adapter;

P
PJ Waskiewicz 已提交
3339 3340 3341
	/* Write the ITR value calculated at the end of the
	 * previous interrupt.
	 */
3342

3343
	igb_write_itr(rx_ring);
3344

P
PJ Waskiewicz 已提交
3345 3346 3347
	if (netif_rx_schedule_prep(adapter->netdev, &rx_ring->napi))
		__netif_rx_schedule(adapter->netdev, &rx_ring->napi);

3348
#ifdef CONFIG_IGB_DCA
3349
	if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3350 3351 3352 3353 3354
		igb_update_rx_dca(rx_ring);
#endif
		return IRQ_HANDLED;
}

3355
#ifdef CONFIG_IGB_DCA
J
Jeb Cramer 已提交
3356 3357 3358 3359 3360 3361 3362 3363 3364 3365
static void igb_update_rx_dca(struct igb_ring *rx_ring)
{
	u32 dca_rxctrl;
	struct igb_adapter *adapter = rx_ring->adapter;
	struct e1000_hw *hw = &adapter->hw;
	int cpu = get_cpu();
	int q = rx_ring - adapter->rx_ring;

	if (rx_ring->cpu != cpu) {
		dca_rxctrl = rd32(E1000_DCA_RXCTRL(q));
A
Alexander Duyck 已提交
3366 3367 3368 3369 3370 3371 3372 3373
		if (hw->mac.type == e1000_82576) {
			dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK_82576;
			dca_rxctrl |= dca_get_tag(cpu) <<
			              E1000_DCA_RXCTRL_CPUID_SHIFT;
		} else {
			dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK;
			dca_rxctrl |= dca_get_tag(cpu);
		}
J
Jeb Cramer 已提交
3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392
		dca_rxctrl |= E1000_DCA_RXCTRL_DESC_DCA_EN;
		dca_rxctrl |= E1000_DCA_RXCTRL_HEAD_DCA_EN;
		dca_rxctrl |= E1000_DCA_RXCTRL_DATA_DCA_EN;
		wr32(E1000_DCA_RXCTRL(q), dca_rxctrl);
		rx_ring->cpu = cpu;
	}
	put_cpu();
}

static void igb_update_tx_dca(struct igb_ring *tx_ring)
{
	u32 dca_txctrl;
	struct igb_adapter *adapter = tx_ring->adapter;
	struct e1000_hw *hw = &adapter->hw;
	int cpu = get_cpu();
	int q = tx_ring - adapter->tx_ring;

	if (tx_ring->cpu != cpu) {
		dca_txctrl = rd32(E1000_DCA_TXCTRL(q));
A
Alexander Duyck 已提交
3393 3394 3395 3396 3397 3398 3399 3400
		if (hw->mac.type == e1000_82576) {
			dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK_82576;
			dca_txctrl |= dca_get_tag(cpu) <<
			              E1000_DCA_TXCTRL_CPUID_SHIFT;
		} else {
			dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK;
			dca_txctrl |= dca_get_tag(cpu);
		}
J
Jeb Cramer 已提交
3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411
		dca_txctrl |= E1000_DCA_TXCTRL_DESC_DCA_EN;
		wr32(E1000_DCA_TXCTRL(q), dca_txctrl);
		tx_ring->cpu = cpu;
	}
	put_cpu();
}

static void igb_setup_dca(struct igb_adapter *adapter)
{
	int i;

3412
	if (!(adapter->flags & IGB_FLAG_DCA_ENABLED))
J
Jeb Cramer 已提交
3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431
		return;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		adapter->tx_ring[i].cpu = -1;
		igb_update_tx_dca(&adapter->tx_ring[i]);
	}
	for (i = 0; i < adapter->num_rx_queues; i++) {
		adapter->rx_ring[i].cpu = -1;
		igb_update_rx_dca(&adapter->rx_ring[i]);
	}
}

static int __igb_notify_dca(struct device *dev, void *data)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	unsigned long event = *(unsigned long *)data;

3432 3433 3434
	if (!(adapter->flags & IGB_FLAG_HAS_DCA))
		goto out;

J
Jeb Cramer 已提交
3435 3436 3437
	switch (event) {
	case DCA_PROVIDER_ADD:
		/* if already enabled, don't do it again */
3438
		if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3439
			break;
3440
		adapter->flags |= IGB_FLAG_DCA_ENABLED;
J
Jeb Cramer 已提交
3441 3442 3443 3444 3445 3446 3447 3448 3449 3450
		/* Always use CB2 mode, difference is masked
		 * in the CB driver. */
		wr32(E1000_DCA_CTRL, 2);
		if (dca_add_requester(dev) == 0) {
			dev_info(&adapter->pdev->dev, "DCA enabled\n");
			igb_setup_dca(adapter);
			break;
		}
		/* Fall Through since DCA is disabled. */
	case DCA_PROVIDER_REMOVE:
3451
		if (adapter->flags & IGB_FLAG_DCA_ENABLED) {
J
Jeb Cramer 已提交
3452 3453 3454 3455
			/* without this a class_device is left
 			 * hanging around in the sysfs model */
			dca_remove_requester(dev);
			dev_info(&adapter->pdev->dev, "DCA disabled\n");
3456
			adapter->flags &= ~IGB_FLAG_DCA_ENABLED;
J
Jeb Cramer 已提交
3457 3458 3459 3460
			wr32(E1000_DCA_CTRL, 1);
		}
		break;
	}
3461
out:
J
Jeb Cramer 已提交
3462
	return 0;
3463 3464
}

J
Jeb Cramer 已提交
3465 3466 3467 3468 3469 3470 3471 3472 3473 3474
static int igb_notify_dca(struct notifier_block *nb, unsigned long event,
                          void *p)
{
	int ret_val;

	ret_val = driver_for_each_device(&igb_driver.driver, NULL, &event,
	                                 __igb_notify_dca);

	return ret_val ? NOTIFY_BAD : NOTIFY_DONE;
}
3475
#endif /* CONFIG_IGB_DCA */
3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489

/**
 * igb_intr_msi - Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t igb_intr_msi(int irq, void *data)
{
	struct net_device *netdev = data;
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	/* read ICR disables interrupts using IAM */
	u32 icr = rd32(E1000_ICR);

3490
	igb_write_itr(adapter->rx_ring);
3491 3492 3493 3494 3495 3496 3497

	if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) {
		hw->mac.get_link_status = 1;
		if (!test_bit(__IGB_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}

P
PJ Waskiewicz 已提交
3498
	netif_rx_schedule(netdev, &adapter->rx_ring[0].napi);
3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519

	return IRQ_HANDLED;
}

/**
 * igb_intr - Interrupt Handler
 * @irq: interrupt number
 * @data: pointer to a network interface device structure
 **/
static irqreturn_t igb_intr(int irq, void *data)
{
	struct net_device *netdev = data;
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	/* Interrupt Auto-Mask...upon reading ICR, interrupts are masked.  No
	 * need for the IMC write */
	u32 icr = rd32(E1000_ICR);
	u32 eicr = 0;
	if (!icr)
		return IRQ_NONE;  /* Not our interrupt */

3520
	igb_write_itr(adapter->rx_ring);
3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535

	/* 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 */
	if (!(icr & E1000_ICR_INT_ASSERTED))
		return IRQ_NONE;

	eicr = rd32(E1000_EICR);

	if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) {
		hw->mac.get_link_status = 1;
		/* guard against interrupt when we're going down */
		if (!test_bit(__IGB_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}

P
PJ Waskiewicz 已提交
3536
	netif_rx_schedule(netdev, &adapter->rx_ring[0].napi);
3537 3538 3539 3540 3541

	return IRQ_HANDLED;
}

/**
3542 3543 3544
 * igb_poll - NAPI Rx polling callback
 * @napi: napi polling structure
 * @budget: count of how many packets we should handle
3545
 **/
3546
static int igb_poll(struct napi_struct *napi, int budget)
3547
{
3548 3549
	struct igb_ring *rx_ring = container_of(napi, struct igb_ring, napi);
	struct igb_adapter *adapter = rx_ring->adapter;
3550
	struct net_device *netdev = adapter->netdev;
3551
	int tx_clean_complete, work_done = 0;
3552

3553
	/* this poll routine only supports one tx and one rx queue */
3554
#ifdef CONFIG_IGB_DCA
3555
	if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3556 3557
		igb_update_tx_dca(&adapter->tx_ring[0]);
#endif
3558
	tx_clean_complete = igb_clean_tx_irq(&adapter->tx_ring[0]);
J
Jeb Cramer 已提交
3559

3560
#ifdef CONFIG_IGB_DCA
3561
	if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3562 3563
		igb_update_rx_dca(&adapter->rx_ring[0]);
#endif
3564
	igb_clean_rx_irq_adv(&adapter->rx_ring[0], &work_done, budget);
3565 3566 3567 3568 3569

	/* If no Tx and not enough Rx work done, exit the polling mode */
	if ((tx_clean_complete && (work_done < budget)) ||
	    !netif_running(netdev)) {
		if (adapter->itr_setting & 3)
3570
			igb_set_itr(adapter);
3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587
		netif_rx_complete(netdev, napi);
		if (!test_bit(__IGB_DOWN, &adapter->state))
			igb_irq_enable(adapter);
		return 0;
	}

	return 1;
}

static int igb_clean_rx_ring_msix(struct napi_struct *napi, int budget)
{
	struct igb_ring *rx_ring = container_of(napi, struct igb_ring, napi);
	struct igb_adapter *adapter = rx_ring->adapter;
	struct e1000_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
	int work_done = 0;

3588
#ifdef CONFIG_IGB_DCA
3589
	if (adapter->flags & IGB_FLAG_DCA_ENABLED)
J
Jeb Cramer 已提交
3590 3591
		igb_update_rx_dca(rx_ring);
#endif
3592
	igb_clean_rx_irq_adv(rx_ring, &work_done, budget);
3593 3594 3595 3596 3597 3598


	/* If not enough Rx work done, exit the polling mode */
	if ((work_done == 0) || !netif_running(netdev)) {
		netif_rx_complete(netdev, napi);

3599 3600 3601 3602 3603
		if (adapter->itr_setting & 3) {
			if (adapter->num_rx_queues == 1)
				igb_set_itr(adapter);
			else
				igb_update_ring_itr(rx_ring);
3604
		}
P
PJ Waskiewicz 已提交
3605 3606 3607 3608

		if (!test_bit(__IGB_DOWN, &adapter->state))
			wr32(E1000_EIMS, rx_ring->eims_value);

3609 3610 3611 3612 3613
		return 0;
	}

	return 1;
}
A
Al Viro 已提交
3614 3615 3616 3617 3618 3619 3620

static inline u32 get_head(struct igb_ring *tx_ring)
{
	void *end = (struct e1000_tx_desc *)tx_ring->desc + tx_ring->count;
	return le32_to_cpu(*(volatile __le32 *)end);
}

3621 3622 3623 3624 3625
/**
 * igb_clean_tx_irq - Reclaim resources after transmit completes
 * @adapter: board private structure
 * returns true if ring is completely cleaned
 **/
3626
static bool igb_clean_tx_irq(struct igb_ring *tx_ring)
3627
{
3628
	struct igb_adapter *adapter = tx_ring->adapter;
3629
	struct e1000_hw *hw = &adapter->hw;
3630
	struct net_device *netdev = adapter->netdev;
3631 3632 3633 3634 3635 3636 3637
	struct e1000_tx_desc *tx_desc;
	struct igb_buffer *buffer_info;
	struct sk_buff *skb;
	unsigned int i;
	u32 head, oldhead;
	unsigned int count = 0;
	unsigned int total_bytes = 0, total_packets = 0;
3638
	bool retval = true;
3639 3640

	rmb();
A
Al Viro 已提交
3641
	head = get_head(tx_ring);
3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673
	i = tx_ring->next_to_clean;
	while (1) {
		while (i != head) {
			tx_desc = E1000_TX_DESC(*tx_ring, i);
			buffer_info = &tx_ring->buffer_info[i];
			skb = buffer_info->skb;

			if (skb) {
				unsigned int segs, bytecount;
				/* gso_segs is currently only valid for tcp */
				segs = skb_shinfo(skb)->gso_segs ?: 1;
				/* multiply data chunks by size of headers */
				bytecount = ((segs - 1) * skb_headlen(skb)) +
					    skb->len;
				total_packets += segs;
				total_bytes += bytecount;
			}

			igb_unmap_and_free_tx_resource(adapter, buffer_info);

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

			count++;
			if (count == IGB_MAX_TX_CLEAN) {
				retval = false;
				goto done_cleaning;
			}
		}
		oldhead = head;
		rmb();
A
Al Viro 已提交
3674
		head = get_head(tx_ring);
3675 3676 3677 3678 3679 3680 3681
		if (head == oldhead)
			goto done_cleaning;
	}  /* while (1) */

done_cleaning:
	tx_ring->next_to_clean = i;

3682
	if (unlikely(count &&
3683 3684 3685 3686 3687 3688
		     netif_carrier_ok(netdev) &&
		     IGB_DESC_UNUSED(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
		/* Make sure that anybody stopping the queue after this
		 * sees the new next_to_clean.
		 */
		smp_mb();
3689 3690 3691 3692 3693
		if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
		    !(test_bit(__IGB_DOWN, &adapter->state))) {
			netif_wake_subqueue(netdev, tx_ring->queue_index);
			++adapter->restart_queue;
		}
3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709
	}

	if (tx_ring->detect_tx_hung) {
		/* Detect a transmit hang in hardware, this serializes the
		 * check with the clearing of time_stamp and movement of i */
		tx_ring->detect_tx_hung = false;
		if (tx_ring->buffer_info[i].time_stamp &&
		    time_after(jiffies, tx_ring->buffer_info[i].time_stamp +
			       (adapter->tx_timeout_factor * HZ))
		    && !(rd32(E1000_STATUS) &
			 E1000_STATUS_TXOFF)) {

			tx_desc = E1000_TX_DESC(*tx_ring, i);
			/* detected Tx unit hang */
			dev_err(&adapter->pdev->dev,
				"Detected Tx Unit Hang\n"
A
Alexander Duyck 已提交
3710
				"  Tx Queue             <%d>\n"
3711 3712 3713 3714 3715 3716 3717 3718 3719
				"  TDH                  <%x>\n"
				"  TDT                  <%x>\n"
				"  next_to_use          <%x>\n"
				"  next_to_clean        <%x>\n"
				"  head (WB)            <%x>\n"
				"buffer_info[next_to_clean]\n"
				"  time_stamp           <%lx>\n"
				"  jiffies              <%lx>\n"
				"  desc.status          <%x>\n",
A
Alexander Duyck 已提交
3720
				tx_ring->queue_index,
3721 3722 3723 3724 3725 3726 3727 3728
				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,
				head,
				tx_ring->buffer_info[i].time_stamp,
				jiffies,
				tx_desc->upper.fields.status);
3729
			netif_stop_subqueue(netdev, tx_ring->queue_index);
3730 3731 3732 3733
		}
	}
	tx_ring->total_bytes += total_bytes;
	tx_ring->total_packets += total_packets;
3734 3735
	tx_ring->tx_stats.bytes += total_bytes;
	tx_ring->tx_stats.packets += total_packets;
3736 3737 3738 3739 3740
	adapter->net_stats.tx_bytes += total_bytes;
	adapter->net_stats.tx_packets += total_packets;
	return retval;
}

3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772
#ifdef CONFIG_IGB_LRO
 /**
 * igb_get_skb_hdr - helper function for LRO header processing
 * @skb: pointer to sk_buff to be added to LRO packet
 * @iphdr: pointer to ip header structure
 * @tcph: pointer to tcp header structure
 * @hdr_flags: pointer to header flags
 * @priv: pointer to the receive descriptor for the current sk_buff
 **/
static int igb_get_skb_hdr(struct sk_buff *skb, void **iphdr, void **tcph,
                           u64 *hdr_flags, void *priv)
{
	union e1000_adv_rx_desc *rx_desc = priv;
	u16 pkt_type = rx_desc->wb.lower.lo_dword.pkt_info &
	               (E1000_RXDADV_PKTTYPE_IPV4 | E1000_RXDADV_PKTTYPE_TCP);

	/* Verify that this is a valid IPv4 TCP packet */
	if (pkt_type != (E1000_RXDADV_PKTTYPE_IPV4 |
	                  E1000_RXDADV_PKTTYPE_TCP))
		return -1;

	/* Set network headers */
	skb_reset_network_header(skb);
	skb_set_transport_header(skb, ip_hdrlen(skb));
	*iphdr = ip_hdr(skb);
	*tcph = tcp_hdr(skb);
	*hdr_flags = LRO_IPV4 | LRO_TCP;

	return 0;

}
#endif /* CONFIG_IGB_LRO */
3773 3774 3775

/**
 * igb_receive_skb - helper function to handle rx indications
3776
 * @ring: pointer to receive ring receving this packet 
3777 3778 3779 3780
 * @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
 **/
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
static void igb_receive_skb(struct igb_ring *ring, u8 status,
                            union e1000_adv_rx_desc * rx_desc,
                            struct sk_buff *skb)
{
	struct igb_adapter * adapter = ring->adapter;
	bool vlan_extracted = (adapter->vlgrp && (status & E1000_RXD_STAT_VP));

#ifdef CONFIG_IGB_LRO
	if (adapter->netdev->features & NETIF_F_LRO &&
	    skb->ip_summed == CHECKSUM_UNNECESSARY) {
		if (vlan_extracted)
			lro_vlan_hwaccel_receive_skb(&ring->lro_mgr, skb,
			                   adapter->vlgrp,
			                   le16_to_cpu(rx_desc->wb.upper.vlan),
			                   rx_desc);
		else
			lro_receive_skb(&ring->lro_mgr,skb, rx_desc);
		ring->lro_used = 1;
	} else {
#endif
		if (vlan_extracted)
			vlan_hwaccel_receive_skb(skb, adapter->vlgrp,
			                  le16_to_cpu(rx_desc->wb.upper.vlan));
		else

			netif_receive_skb(skb);
#ifdef CONFIG_IGB_LRO
	}
#endif
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
}


static inline void igb_rx_checksum_adv(struct igb_adapter *adapter,
				       u32 status_err, struct sk_buff *skb)
{
	skb->ip_summed = CHECKSUM_NONE;

	/* Ignore Checksum bit is set or checksum is disabled through ethtool */
	if ((status_err & E1000_RXD_STAT_IXSM) || !adapter->rx_csum)
		return;
	/* TCP/UDP checksum error bit is set */
	if (status_err &
	    (E1000_RXDEXT_STATERR_TCPE | E1000_RXDEXT_STATERR_IPE)) {
		/* let the stack verify checksum errors */
		adapter->hw_csum_err++;
		return;
	}
	/* It must be a TCP or UDP packet with a valid checksum */
	if (status_err & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS))
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	adapter->hw_csum_good++;
}

3835 3836
static bool igb_clean_rx_irq_adv(struct igb_ring *rx_ring,
				 int *work_done, int budget)
3837
{
3838
	struct igb_adapter *adapter = rx_ring->adapter;
3839 3840 3841 3842 3843
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	union e1000_adv_rx_desc *rx_desc , *next_rxd;
	struct igb_buffer *buffer_info , *next_buffer;
	struct sk_buff *skb;
3844
	unsigned int i;
3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864
	u32 length, hlen, staterr;
	bool cleaned = false;
	int cleaned_count = 0;
	unsigned int total_bytes = 0, total_packets = 0;

	i = rx_ring->next_to_clean;
	rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
	staterr = le32_to_cpu(rx_desc->wb.upper.status_error);

	while (staterr & E1000_RXD_STAT_DD) {
		if (*work_done >= budget)
			break;
		(*work_done)++;
		buffer_info = &rx_ring->buffer_info[i];

		/* HW will not DMA in data larger than the given buffer, even
		 * if it parses the (NFS, of course) header to be larger.  In
		 * that case, it fills the header buffer and spills the rest
		 * into the page.
		 */
A
Al Viro 已提交
3865 3866
		hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hdr_info) &
		  E1000_RXDADV_HDRBUFLEN_MASK) >> E1000_RXDADV_HDRBUFLEN_SHIFT;
3867 3868 3869 3870 3871 3872 3873
		if (hlen > adapter->rx_ps_hdr_size)
			hlen = adapter->rx_ps_hdr_size;

		length = le16_to_cpu(rx_desc->wb.upper.length);
		cleaned = true;
		cleaned_count++;

3874 3875 3876 3877 3878 3879 3880 3881 3882 3883
		skb = buffer_info->skb;
		prefetch(skb->data - NET_IP_ALIGN);
		buffer_info->skb = NULL;
		if (!adapter->rx_ps_hdr_size) {
			pci_unmap_single(pdev, buffer_info->dma,
					 adapter->rx_buffer_len +
					   NET_IP_ALIGN,
					 PCI_DMA_FROMDEVICE);
			skb_put(skb, length);
			goto send_up;
3884 3885
		}

3886 3887 3888 3889 3890 3891 3892 3893 3894
		if (!skb_shinfo(skb)->nr_frags) {
			pci_unmap_single(pdev, buffer_info->dma,
					 adapter->rx_ps_hdr_size +
					   NET_IP_ALIGN,
					 PCI_DMA_FROMDEVICE);
			skb_put(skb, hlen);
		}

		if (length) {
3895
			pci_unmap_page(pdev, buffer_info->page_dma,
3896
				       PAGE_SIZE / 2, PCI_DMA_FROMDEVICE);
3897
			buffer_info->page_dma = 0;
3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908

			skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags++,
						buffer_info->page,
						buffer_info->page_offset,
						length);

			if ((adapter->rx_buffer_len > (PAGE_SIZE / 2)) ||
			    (page_count(buffer_info->page) != 1))
				buffer_info->page = NULL;
			else
				get_page(buffer_info->page);
3909 3910 3911 3912

			skb->len += length;
			skb->data_len += length;

3913
			skb->truesize += length;
3914 3915 3916 3917 3918 3919 3920 3921 3922
		}
send_up:
		i++;
		if (i == rx_ring->count)
			i = 0;
		next_rxd = E1000_RX_DESC_ADV(*rx_ring, i);
		prefetch(next_rxd);
		next_buffer = &rx_ring->buffer_info[i];

3923 3924 3925 3926 3927 3928
		if (!(staterr & E1000_RXD_STAT_EOP)) {
			buffer_info->skb = xchg(&next_buffer->skb, skb);
			buffer_info->dma = xchg(&next_buffer->dma, 0);
			goto next_desc;
		}

3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940
		if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) {
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

		total_bytes += skb->len;
		total_packets++;

		igb_rx_checksum_adv(adapter, staterr, skb);

		skb->protocol = eth_type_trans(skb, netdev);

3941
		igb_receive_skb(rx_ring, staterr, rx_desc, skb);
3942 3943 3944 3945 3946 3947 3948 3949

		netdev->last_rx = jiffies;

next_desc:
		rx_desc->wb.upper.status_error = 0;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
3950
			igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
3951 3952 3953 3954 3955 3956 3957 3958 3959
			cleaned_count = 0;
		}

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

		staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
	}
3960

3961 3962 3963
	rx_ring->next_to_clean = i;
	cleaned_count = IGB_DESC_UNUSED(rx_ring);

3964 3965 3966 3967 3968 3969 3970
#ifdef CONFIG_IGB_LRO
	if (rx_ring->lro_used) {
		lro_flush_all(&rx_ring->lro_mgr);
		rx_ring->lro_used = 0;
	}
#endif

3971
	if (cleaned_count)
3972
		igb_alloc_rx_buffers_adv(rx_ring, cleaned_count);
3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987

	rx_ring->total_packets += total_packets;
	rx_ring->total_bytes += total_bytes;
	rx_ring->rx_stats.packets += total_packets;
	rx_ring->rx_stats.bytes += total_bytes;
	adapter->net_stats.rx_bytes += total_bytes;
	adapter->net_stats.rx_packets += total_packets;
	return cleaned;
}


/**
 * igb_alloc_rx_buffers_adv - Replace used receive buffers; packet split
 * @adapter: address of board private structure
 **/
3988
static void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring,
3989 3990
				     int cleaned_count)
{
3991
	struct igb_adapter *adapter = rx_ring->adapter;
3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	union e1000_adv_rx_desc *rx_desc;
	struct igb_buffer *buffer_info;
	struct sk_buff *skb;
	unsigned int i;

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

	while (cleaned_count--) {
		rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);

4005
		if (adapter->rx_ps_hdr_size && !buffer_info->page_dma) {
4006
			if (!buffer_info->page) {
4007 4008 4009 4010 4011 4012 4013 4014
				buffer_info->page = alloc_page(GFP_ATOMIC);
				if (!buffer_info->page) {
					adapter->alloc_rx_buff_failed++;
					goto no_buffers;
				}
				buffer_info->page_offset = 0;
			} else {
				buffer_info->page_offset ^= PAGE_SIZE / 2;
4015 4016 4017 4018
			}
			buffer_info->page_dma =
				pci_map_page(pdev,
					     buffer_info->page,
4019 4020
					     buffer_info->page_offset,
					     PAGE_SIZE / 2,
4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 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 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281
					     PCI_DMA_FROMDEVICE);
		}

		if (!buffer_info->skb) {
			int bufsz;

			if (adapter->rx_ps_hdr_size)
				bufsz = adapter->rx_ps_hdr_size;
			else
				bufsz = adapter->rx_buffer_len;
			bufsz += NET_IP_ALIGN;
			skb = netdev_alloc_skb(netdev, bufsz);

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

			/* Make buffer alignment 2 beyond a 16 byte boundary
			 * this will result in a 16 byte aligned IP header after
			 * the 14 byte MAC header is removed
			 */
			skb_reserve(skb, NET_IP_ALIGN);

			buffer_info->skb = skb;
			buffer_info->dma = pci_map_single(pdev, skb->data,
							  bufsz,
							  PCI_DMA_FROMDEVICE);

		}
		/* Refresh the desc even if buffer_addrs didn't change because
		 * each write-back erases this info. */
		if (adapter->rx_ps_hdr_size) {
			rx_desc->read.pkt_addr =
			     cpu_to_le64(buffer_info->page_dma);
			rx_desc->read.hdr_addr = cpu_to_le64(buffer_info->dma);
		} else {
			rx_desc->read.pkt_addr =
			     cpu_to_le64(buffer_info->dma);
			rx_desc->read.hdr_addr = 0;
		}

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

no_buffers:
	if (rx_ring->next_to_use != i) {
		rx_ring->next_to_use = i;
		if (i == 0)
			i = (rx_ring->count - 1);
		else
			i--;

		/* 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);
	}
}

/**
 * igb_mii_ioctl -
 * @netdev:
 * @ifreq:
 * @cmd:
 **/
static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct mii_ioctl_data *data = if_mii(ifr);

	if (adapter->hw.phy.media_type != e1000_media_type_copper)
		return -EOPNOTSUPP;

	switch (cmd) {
	case SIOCGMIIPHY:
		data->phy_id = adapter->hw.phy.addr;
		break;
	case SIOCGMIIREG:
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		if (adapter->hw.phy.ops.read_phy_reg(&adapter->hw,
						     data->reg_num
						     & 0x1F, &data->val_out))
			return -EIO;
		break;
	case SIOCSMIIREG:
	default:
		return -EOPNOTSUPP;
	}
	return 0;
}

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

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

	igb_irq_disable(adapter);
	adapter->vlgrp = grp;

	if (grp) {
		/* enable VLAN tag insert/strip */
		ctrl = rd32(E1000_CTRL);
		ctrl |= E1000_CTRL_VME;
		wr32(E1000_CTRL, ctrl);

		/* enable VLAN receive filtering */
		rctl = rd32(E1000_RCTL);
		rctl &= ~E1000_RCTL_CFIEN;
		wr32(E1000_RCTL, rctl);
		igb_update_mng_vlan(adapter);
		wr32(E1000_RLPML,
				adapter->max_frame_size + VLAN_TAG_SIZE);
	} else {
		/* disable VLAN tag insert/strip */
		ctrl = rd32(E1000_CTRL);
		ctrl &= ~E1000_CTRL_VME;
		wr32(E1000_CTRL, ctrl);

		if (adapter->mng_vlan_id != (u16)IGB_MNG_VLAN_NONE) {
			igb_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id);
			adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
		}
		wr32(E1000_RLPML,
				adapter->max_frame_size);
	}

	if (!test_bit(__IGB_DOWN, &adapter->state))
		igb_irq_enable(adapter);
}

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

	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
	    (vid == adapter->mng_vlan_id))
		return;
	/* add VID to filter table */
	index = (vid >> 5) & 0x7F;
	vfta = array_rd32(E1000_VFTA, index);
	vfta |= (1 << (vid & 0x1F));
	igb_write_vfta(&adapter->hw, index, vfta);
}

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

	igb_irq_disable(adapter);
	vlan_group_set_device(adapter->vlgrp, vid, NULL);

	if (!test_bit(__IGB_DOWN, &adapter->state))
		igb_irq_enable(adapter);

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

	/* remove VID from filter table */
	index = (vid >> 5) & 0x7F;
	vfta = array_rd32(E1000_VFTA, index);
	vfta &= ~(1 << (vid & 0x1F));
	igb_write_vfta(&adapter->hw, index, vfta);
}

static void igb_restore_vlan(struct igb_adapter *adapter)
{
	igb_vlan_rx_register(adapter->netdev, adapter->vlgrp);

	if (adapter->vlgrp) {
		u16 vid;
		for (vid = 0; vid < VLAN_GROUP_ARRAY_LEN; vid++) {
			if (!vlan_group_get_device(adapter->vlgrp, vid))
				continue;
			igb_vlan_rx_add_vid(adapter->netdev, vid);
		}
	}
}

int igb_set_spd_dplx(struct igb_adapter *adapter, u16 spddplx)
{
	struct e1000_mac_info *mac = &adapter->hw.mac;

	mac->autoneg = 0;

	/* Fiber NICs only allow 1000 gbps Full duplex */
	if ((adapter->hw.phy.media_type == e1000_media_type_fiber) &&
		spddplx != (SPEED_1000 + DUPLEX_FULL)) {
		dev_err(&adapter->pdev->dev,
			"Unsupported Speed/Duplex configuration\n");
		return -EINVAL;
	}

	switch (spddplx) {
	case SPEED_10 + DUPLEX_HALF:
		mac->forced_speed_duplex = ADVERTISE_10_HALF;
		break;
	case SPEED_10 + DUPLEX_FULL:
		mac->forced_speed_duplex = ADVERTISE_10_FULL;
		break;
	case SPEED_100 + DUPLEX_HALF:
		mac->forced_speed_duplex = ADVERTISE_100_HALF;
		break;
	case SPEED_100 + DUPLEX_FULL:
		mac->forced_speed_duplex = ADVERTISE_100_FULL;
		break;
	case SPEED_1000 + DUPLEX_FULL:
		mac->autoneg = 1;
		adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL;
		break;
	case SPEED_1000 + DUPLEX_HALF: /* not supported */
	default:
		dev_err(&adapter->pdev->dev,
			"Unsupported Speed/Duplex configuration\n");
		return -EINVAL;
	}
	return 0;
}


static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
A
Alexander Duyck 已提交
4282
	u32 ctrl, rctl, status;
4283 4284 4285 4286 4287 4288 4289
	u32 wufc = adapter->wol;
#ifdef CONFIG_PM
	int retval = 0;
#endif

	netif_device_detach(netdev);

A
Alexander Duyck 已提交
4290 4291 4292 4293 4294 4295
	if (netif_running(netdev))
		igb_close(netdev);

	igb_reset_interrupt_capability(adapter);

	igb_free_queues(adapter);
4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335

#ifdef CONFIG_PM
	retval = pci_save_state(pdev);
	if (retval)
		return retval;
#endif

	status = rd32(E1000_STATUS);
	if (status & E1000_STATUS_LU)
		wufc &= ~E1000_WUFC_LNKC;

	if (wufc) {
		igb_setup_rctl(adapter);
		igb_set_multi(netdev);

		/* turn on all-multi mode if wake on multicast is enabled */
		if (wufc & E1000_WUFC_MC) {
			rctl = rd32(E1000_RCTL);
			rctl |= E1000_RCTL_MPE;
			wr32(E1000_RCTL, rctl);
		}

		ctrl = rd32(E1000_CTRL);
		/* advertise wake from D3Cold */
		#define E1000_CTRL_ADVD3WUC 0x00100000
		/* phy power management enable */
		#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
		ctrl |= E1000_CTRL_ADVD3WUC;
		wr32(E1000_CTRL, ctrl);

		/* Allow time for pending master requests to run */
		igb_disable_pcie_master(&adapter->hw);

		wr32(E1000_WUC, E1000_WUC_PME_EN);
		wr32(E1000_WUFC, wufc);
	} else {
		wr32(E1000_WUC, 0);
		wr32(E1000_WUFC, 0);
	}

A
Alexander Duyck 已提交
4336 4337
	/* make sure adapter isn't asleep if manageability/wol is enabled */
	if (wufc || adapter->en_mng_pt) {
4338 4339
		pci_enable_wake(pdev, PCI_D3hot, 1);
		pci_enable_wake(pdev, PCI_D3cold, 1);
A
Alexander Duyck 已提交
4340 4341 4342 4343
	} else {
		igb_shutdown_fiber_serdes_link_82575(hw);
		pci_enable_wake(pdev, PCI_D3hot, 0);
		pci_enable_wake(pdev, PCI_D3cold, 0);
4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366
	}

	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
	 * would have already happened in close and is redundant. */
	igb_release_hw_control(adapter);

	pci_disable_device(pdev);

	pci_set_power_state(pdev, pci_choose_state(pdev, state));

	return 0;
}

#ifdef CONFIG_PM
static int igb_resume(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 err;

	pci_set_power_state(pdev, PCI_D0);
	pci_restore_state(pdev);
T
Taku Izumi 已提交
4367 4368 4369 4370 4371

	if (adapter->need_ioport)
		err = pci_enable_device(pdev);
	else
		err = pci_enable_device_mem(pdev);
4372 4373 4374 4375 4376 4377 4378 4379 4380 4381
	if (err) {
		dev_err(&pdev->dev,
			"igb: Cannot enable PCI device from suspend\n");
		return err;
	}
	pci_set_master(pdev);

	pci_enable_wake(pdev, PCI_D3hot, 0);
	pci_enable_wake(pdev, PCI_D3cold, 0);

A
Alexander Duyck 已提交
4382 4383 4384 4385 4386
	igb_set_interrupt_capability(adapter);

	if (igb_alloc_queues(adapter)) {
		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
		return -ENOMEM;
4387 4388 4389 4390 4391 4392 4393
	}

	/* e1000_power_up_phy(adapter); */

	igb_reset(adapter);
	wr32(E1000_WUS, ~0);

A
Alexander Duyck 已提交
4394 4395 4396 4397 4398
	if (netif_running(netdev)) {
		err = igb_open(netdev);
		if (err)
			return err;
	}
4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427

	netif_device_attach(netdev);

	/* let the f/w know that the h/w is now under the control of the
	 * driver. */
	igb_get_hw_control(adapter);

	return 0;
}
#endif

static void igb_shutdown(struct pci_dev *pdev)
{
	igb_suspend(pdev, PMSG_SUSPEND);
}

#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 igb_netpoll(struct net_device *netdev)
{
	struct igb_adapter *adapter = netdev_priv(netdev);
	int i;
	int work_done = 0;

	igb_irq_disable(adapter);
4428 4429
	adapter->flags |= IGB_FLAG_IN_NETPOLL;

4430
	for (i = 0; i < adapter->num_tx_queues; i++)
4431
		igb_clean_tx_irq(&adapter->tx_ring[i]);
4432 4433

	for (i = 0; i < adapter->num_rx_queues; i++)
4434
		igb_clean_rx_irq_adv(&adapter->rx_ring[i],
4435 4436 4437
				     &work_done,
				     adapter->rx_ring[i].napi.weight);

4438
	adapter->flags &= ~IGB_FLAG_IN_NETPOLL;
4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 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
	igb_irq_enable(adapter);
}
#endif /* CONFIG_NET_POLL_CONTROLLER */

/**
 * igb_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 igb_io_error_detected(struct pci_dev *pdev,
					      pci_channel_state_t state)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);

	netif_device_detach(netdev);

	if (netif_running(netdev))
		igb_down(adapter);
	pci_disable_device(pdev);

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

/**
 * igb_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 igb_resume routine.
 */
static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
T
Taku Izumi 已提交
4479
	int err;
4480

T
Taku Izumi 已提交
4481 4482 4483 4484 4485
	if (adapter->need_ioport)
		err = pci_enable_device(pdev);
	else
		err = pci_enable_device_mem(pdev);
	if (err) {
4486 4487 4488 4489 4490
		dev_err(&pdev->dev,
			"Cannot re-enable PCI device after reset.\n");
		return PCI_ERS_RESULT_DISCONNECT;
	}
	pci_set_master(pdev);
4491
	pci_restore_state(pdev);
4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530

	pci_enable_wake(pdev, PCI_D3hot, 0);
	pci_enable_wake(pdev, PCI_D3cold, 0);

	igb_reset(adapter);
	wr32(E1000_WUS, ~0);

	return PCI_ERS_RESULT_RECOVERED;
}

/**
 * igb_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 igb_resume routine.
 */
static void igb_io_resume(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct igb_adapter *adapter = netdev_priv(netdev);

	if (netif_running(netdev)) {
		if (igb_up(adapter)) {
			dev_err(&pdev->dev, "igb_up failed after reset\n");
			return;
		}
	}

	netif_device_attach(netdev);

	/* let the f/w know that the h/w is now under the control of the
	 * driver. */
	igb_get_hw_control(adapter);

}

/* igb_main.c */