ixgbevf_main.c 94.7 KB
Newer Older
1 2 3
/*******************************************************************************

  Intel 82599 Virtual Function driver
G
Greg Rose 已提交
4
  Copyright(c) 1999 - 2012 Intel Corporation.
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31

  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

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


/******************************************************************************
 Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
******************************************************************************/
32 33 34

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

35
#include <linux/types.h>
J
Jiri Pirko 已提交
36
#include <linux/bitops.h>
37 38 39 40 41 42 43 44
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/tcp.h>
45
#include <linux/sctp.h>
46
#include <linux/ipv6.h>
47
#include <linux/slab.h>
48 49 50
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
51
#include <linux/if.h>
52
#include <linux/if_vlan.h>
53
#include <linux/prefetch.h>
54 55 56

#include "ixgbevf.h"

57
const char ixgbevf_driver_name[] = "ixgbevf";
58
static const char ixgbevf_driver_string[] =
G
Greg Rose 已提交
59
	"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
60

G
Greg Rose 已提交
61
#define DRV_VERSION "2.7.12-k"
62
const char ixgbevf_driver_version[] = DRV_VERSION;
63
static char ixgbevf_copyright[] =
G
Greg Rose 已提交
64
	"Copyright (c) 2009 - 2012 Intel Corporation.";
65 66

static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
67 68
	[board_82599_vf] = &ixgbevf_82599_vf_info,
	[board_X540_vf]  = &ixgbevf_X540_vf_info,
69 70 71 72 73 74 75 76 77 78 79 80 81
};

/* ixgbevf_pci_tbl - PCI Device ID Table
 *
 * Wildcard entries (PCI_ANY_ID) should come last
 * Last entry must be all 0s
 *
 * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
 *   Class, Class Mask, private data (not used) }
 */
static struct pci_device_id ixgbevf_pci_tbl[] = {
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_VF),
	board_82599_vf},
82 83
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540_VF),
	board_X540_vf},
84 85 86 87 88 89 90 91 92 93 94

	/* required last entry */
	{0, }
};
MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl);

MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 82599 Virtual Function Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);

95 96 97 98
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)
static int debug = -1;
module_param(debug, int, 0);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
99 100

/* forward decls */
101
static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector);
102
static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter);
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117

static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw,
					   struct ixgbevf_ring *rx_ring,
					   u32 val)
{
	/*
	 * 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();
	IXGBE_WRITE_REG(hw, IXGBE_VFRDT(rx_ring->reg_idx), val);
}

118
/**
119
 * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
 * @adapter: pointer to adapter struct
 * @direction: 0 for Rx, 1 for Tx, -1 for other causes
 * @queue: queue to map the corresponding interrupt to
 * @msix_vector: the vector to map to the corresponding queue
 *
 */
static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction,
			     u8 queue, u8 msix_vector)
{
	u32 ivar, index;
	struct ixgbe_hw *hw = &adapter->hw;
	if (direction == -1) {
		/* other causes */
		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
		ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC);
		ivar &= ~0xFF;
		ivar |= msix_vector;
		IXGBE_WRITE_REG(hw, IXGBE_VTIVAR_MISC, ivar);
	} else {
		/* tx or rx causes */
		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
		index = ((16 * (queue & 1)) + (8 * direction));
		ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR(queue >> 1));
		ivar &= ~(0xFF << index);
		ivar |= (msix_vector << index);
		IXGBE_WRITE_REG(hw, IXGBE_VTIVAR(queue >> 1), ivar);
	}
}

149
static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring,
150 151 152 153 154
					       struct ixgbevf_tx_buffer
					       *tx_buffer_info)
{
	if (tx_buffer_info->dma) {
		if (tx_buffer_info->mapped_as_page)
155
			dma_unmap_page(tx_ring->dev,
156 157
				       tx_buffer_info->dma,
				       tx_buffer_info->length,
158
				       DMA_TO_DEVICE);
159
		else
160
			dma_unmap_single(tx_ring->dev,
161 162
					 tx_buffer_info->dma,
					 tx_buffer_info->length,
163
					 DMA_TO_DEVICE);
164 165 166 167 168 169 170 171 172 173 174 175 176 177
		tx_buffer_info->dma = 0;
	}
	if (tx_buffer_info->skb) {
		dev_kfree_skb_any(tx_buffer_info->skb);
		tx_buffer_info->skb = NULL;
	}
	tx_buffer_info->time_stamp = 0;
	/* tx_buffer_info must be completely set up in the transmit path */
}

#define IXGBE_MAX_TXD_PWR	14
#define IXGBE_MAX_DATA_PER_TXD	(1 << IXGBE_MAX_TXD_PWR)

/* Tx Descriptors needed, worst case */
178 179
#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD)
#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
180 181 182 183 184

static void ixgbevf_tx_timeout(struct net_device *netdev);

/**
 * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes
185
 * @q_vector: board private structure
186 187
 * @tx_ring: tx ring to clean
 **/
188
static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
189 190
				 struct ixgbevf_ring *tx_ring)
{
191
	struct ixgbevf_adapter *adapter = q_vector->adapter;
192 193 194 195 196
	union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
	struct ixgbevf_tx_buffer *tx_buffer_info;
	unsigned int i, eop, count = 0;
	unsigned int total_bytes = 0, total_packets = 0;

197 198 199
	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
		return true;

200 201
	i = tx_ring->next_to_clean;
	eop = tx_ring->tx_buffer_info[i].next_to_watch;
202
	eop_desc = IXGBEVF_TX_DESC(tx_ring, eop);
203 204

	while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
205
	       (count < tx_ring->count)) {
206
		bool cleaned = false;
207
		rmb(); /* read buffer_info after eop_desc */
208 209 210
		/* eop could change between read and DD-check */
		if (unlikely(eop != tx_ring->tx_buffer_info[i].next_to_watch))
			goto cont_loop;
211 212
		for ( ; !cleaned; count++) {
			struct sk_buff *skb;
213
			tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
			tx_buffer_info = &tx_ring->tx_buffer_info[i];
			cleaned = (i == eop);
			skb = tx_buffer_info->skb;

			if (cleaned && 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;
			}

230
			ixgbevf_unmap_and_free_tx_resource(tx_ring,
231 232 233 234 235 236 237 238 239
							   tx_buffer_info);

			tx_desc->wb.status = 0;

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

240
cont_loop:
241
		eop = tx_ring->tx_buffer_info[i].next_to_watch;
242
		eop_desc = IXGBEVF_TX_DESC(tx_ring, eop);
243 244 245 246 247
	}

	tx_ring->next_to_clean = i;

#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
248
	if (unlikely(count && netif_carrier_ok(tx_ring->netdev) &&
249 250 251 252 253
		     (IXGBE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
		/* Make sure that anybody stopping the queue after this
		 * sees the new next_to_clean.
		 */
		smp_mb();
254 255
		if (__netif_subqueue_stopped(tx_ring->netdev,
					     tx_ring->queue_index) &&
256
		    !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
257 258
			netif_wake_subqueue(tx_ring->netdev,
					    tx_ring->queue_index);
259 260 261 262
			++adapter->restart_queue;
		}
	}

263
	u64_stats_update_begin(&tx_ring->syncp);
264 265
	tx_ring->total_bytes += total_bytes;
	tx_ring->total_packets += total_packets;
266
	u64_stats_update_end(&tx_ring->syncp);
267 268
	q_vector->tx.total_bytes += total_bytes;
	q_vector->tx.total_packets += total_packets;
269

270
	return count < tx_ring->count;
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
}

/**
 * ixgbevf_receive_skb - Send a completed packet up the stack
 * @q_vector: structure containing interrupt and ring information
 * @skb: packet to send up
 * @status: hardware indication of status of receive
 * @rx_desc: rx descriptor
 **/
static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
				struct sk_buff *skb, u8 status,
				union ixgbe_adv_rx_desc *rx_desc)
{
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	bool is_vlan = (status & IXGBE_RXD_STAT_VP);
G
Greg Rose 已提交
286
	u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan);
287

288
	if (is_vlan && test_bit(tag & VLAN_VID_MASK, adapter->active_vlans))
J
Jiri Pirko 已提交
289 290
		__vlan_hwaccel_put_tag(skb, tag);

291
	napi_gro_receive(&q_vector->napi, skb);
292 293 294 295 296 297 298 299 300
}

/**
 * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum
 * @adapter: address of board private structure
 * @status_err: hardware indication of status of receive
 * @skb: skb currently being received and modified
 **/
static inline void ixgbevf_rx_checksum(struct ixgbevf_adapter *adapter,
301
				       struct ixgbevf_ring *ring,
302 303
				       u32 status_err, struct sk_buff *skb)
{
304
	skb_checksum_none_assert(skb);
305 306

	/* Rx csum disabled */
307
	if (!(ring->netdev->features & NETIF_F_RXCSUM))
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
		return;

	/* if IP and error */
	if ((status_err & IXGBE_RXD_STAT_IPCS) &&
	    (status_err & IXGBE_RXDADV_ERR_IPE)) {
		adapter->hw_csum_rx_error++;
		return;
	}

	if (!(status_err & IXGBE_RXD_STAT_L4CS))
		return;

	if (status_err & IXGBE_RXDADV_ERR_TCPE) {
		adapter->hw_csum_rx_error++;
		return;
	}

	/* It must be a TCP or UDP packet with a valid checksum */
	skb->ip_summed = CHECKSUM_UNNECESSARY;
	adapter->hw_csum_rx_good++;
}

/**
 * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split
 * @adapter: address of board private structure
 **/
static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
				     struct ixgbevf_ring *rx_ring,
				     int cleaned_count)
{
	struct pci_dev *pdev = adapter->pdev;
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbevf_rx_buffer *bi;
	struct sk_buff *skb;
342
	unsigned int i = rx_ring->next_to_use;
343 344 345 346

	bi = &rx_ring->rx_buffer_info[i];

	while (cleaned_count--) {
347
		rx_desc = IXGBEVF_RX_DESC(rx_ring, i);
348 349
		skb = bi->skb;
		if (!skb) {
350 351
			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
							rx_ring->rx_buf_len);
352 353 354 355 356 357 358
			if (!skb) {
				adapter->alloc_rx_buff_failed++;
				goto no_buffers;
			}
			bi->skb = skb;
		}
		if (!bi->dma) {
359
			bi->dma = dma_map_single(&pdev->dev, skb->data,
360
						 rx_ring->rx_buf_len,
361
						 DMA_FROM_DEVICE);
362 363 364 365 366 367
			if (dma_mapping_error(&pdev->dev, bi->dma)) {
				dev_kfree_skb(skb);
				bi->skb = NULL;
				dev_err(&pdev->dev, "RX DMA map failed\n");
				break;
			}
368
		}
369
		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385

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

no_buffers:
	if (rx_ring->next_to_use != i) {
		rx_ring->next_to_use = i;

		ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i);
	}
}

static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
386
					     u32 qmask)
387 388 389
{
	struct ixgbe_hw *hw = &adapter->hw;

390
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask);
391 392 393 394
}

static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
				 struct ixgbevf_ring *rx_ring,
395
				 int budget)
396 397 398 399 400 401 402 403 404 405 406 407
{
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	struct pci_dev *pdev = adapter->pdev;
	union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
	struct ixgbevf_rx_buffer *rx_buffer_info, *next_buffer;
	struct sk_buff *skb;
	unsigned int i;
	u32 len, staterr;
	int cleaned_count = 0;
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;

	i = rx_ring->next_to_clean;
408
	rx_desc = IXGBEVF_RX_DESC(rx_ring, i);
409 410 411 412
	staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
	rx_buffer_info = &rx_ring->rx_buffer_info[i];

	while (staterr & IXGBE_RXD_STAT_DD) {
413
		if (!budget)
414
			break;
415
		budget--;
416

417
		rmb(); /* read descriptor and rx_buffer_info after status DD */
418
		len = le16_to_cpu(rx_desc->wb.upper.length);
419 420 421 422 423
		skb = rx_buffer_info->skb;
		prefetch(skb->data - NET_IP_ALIGN);
		rx_buffer_info->skb = NULL;

		if (rx_buffer_info->dma) {
424
			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
425
					 rx_ring->rx_buf_len,
426
					 DMA_FROM_DEVICE);
427 428 429 430 431 432 433 434
			rx_buffer_info->dma = 0;
			skb_put(skb, len);
		}

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

435
		next_rxd = IXGBEVF_RX_DESC(rx_ring, i);
436 437 438 439 440 441
		prefetch(next_rxd);
		cleaned_count++;

		next_buffer = &rx_ring->rx_buffer_info[i];

		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
442
			skb->next = next_buffer->skb;
443
			IXGBE_CB(skb->next)->prev = skb;
444 445 446 447
			adapter->non_eop_descs++;
			goto next_desc;
		}

448 449 450 451 452 453 454 455 456 457
		/* we should not be chaining buffers, if we did drop the skb */
		if (IXGBE_CB(skb)->prev) {
			do {
				struct sk_buff *this = skb;
				skb = IXGBE_CB(skb)->prev;
				dev_kfree_skb(this);
			} while (skb);
			goto next_desc;
		}

458 459 460 461 462 463
		/* ERR_MASK will only have valid bits if EOP set */
		if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) {
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

464
		ixgbevf_rx_checksum(adapter, rx_ring, staterr, skb);
465 466 467 468 469 470 471 472 473 474

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

		/*
		 * Work around issue of some types of VM to VM loop back
		 * packets not getting split correctly
		 */
		if (staterr & IXGBE_RXD_STAT_LB) {
E
Eric Dumazet 已提交
475
			u32 header_fixup_len = skb_headlen(skb);
476 477 478
			if (header_fixup_len < 14)
				skb_push(skb, header_fixup_len);
		}
479
		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
480

481 482 483 484 485 486 487 488 489 490
		/* Workaround hardware that can't do proper VEPA multicast
		 * source pruning.
		 */
		if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) &&
		    !(compare_ether_addr(adapter->netdev->dev_addr,
					eth_hdr(skb)->h_source))) {
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

491
		ixgbevf_receive_skb(q_vector, skb, staterr, rx_desc);
492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515

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

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

		/* use prefetched values */
		rx_desc = next_rxd;
		rx_buffer_info = &rx_ring->rx_buffer_info[i];

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

	rx_ring->next_to_clean = i;
	cleaned_count = IXGBE_DESC_UNUSED(rx_ring);

	if (cleaned_count)
		ixgbevf_alloc_rx_buffers(adapter, rx_ring, cleaned_count);

516
	u64_stats_update_begin(&rx_ring->syncp);
517 518
	rx_ring->total_packets += total_rx_packets;
	rx_ring->total_bytes += total_rx_bytes;
519
	u64_stats_update_end(&rx_ring->syncp);
520 521
	q_vector->rx.total_packets += total_rx_packets;
	q_vector->rx.total_bytes += total_rx_bytes;
522

523
	return !!budget;
524 525 526
}

/**
527
 * ixgbevf_poll - NAPI polling calback
528 529 530
 * @napi: napi struct with our devices info in it
 * @budget: amount of work driver is allowed to do this pass, in packets
 *
531
 * This function will clean more than one or more rings associated with a
532 533
 * q_vector.
 **/
534
static int ixgbevf_poll(struct napi_struct *napi, int budget)
535 536 537 538
{
	struct ixgbevf_q_vector *q_vector =
		container_of(napi, struct ixgbevf_q_vector, napi);
	struct ixgbevf_adapter *adapter = q_vector->adapter;
539 540 541 542 543 544
	struct ixgbevf_ring *ring;
	int per_ring_budget;
	bool clean_complete = true;

	ixgbevf_for_each_ring(ring, q_vector->tx)
		clean_complete &= ixgbevf_clean_tx_irq(q_vector, ring);
545 546 547

	/* attempt to distribute budget to each queue fairly, but don't allow
	 * the budget to go below 1 because we'll exit polling */
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566
	if (q_vector->rx.count > 1)
		per_ring_budget = max(budget/q_vector->rx.count, 1);
	else
		per_ring_budget = budget;

	ixgbevf_for_each_ring(ring, q_vector->rx)
		clean_complete &= ixgbevf_clean_rx_irq(q_vector, ring,
						       per_ring_budget);

	/* If all work not completed, return budget and keep polling */
	if (!clean_complete)
		return budget;
	/* all work done, exit the polling mode */
	napi_complete(napi);
	if (adapter->rx_itr_setting & 1)
		ixgbevf_set_itr(q_vector);
	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
		ixgbevf_irq_enable_queues(adapter,
					  1 << q_vector->v_idx);
567

568
	return 0;
569 570
}

571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589
/**
 * ixgbevf_write_eitr - write VTEITR register in hardware specific way
 * @q_vector: structure containing interrupt and ring information
 */
static void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector)
{
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	struct ixgbe_hw *hw = &adapter->hw;
	int v_idx = q_vector->v_idx;
	u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR;

	/*
	 * set the WDIS bit to not clear the timer bits and cause an
	 * immediate assertion of the interrupt
	 */
	itr_reg |= IXGBE_EITR_CNT_WDIS;

	IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg);
}
590 591 592 593 594 595 596 597 598 599 600

/**
 * ixgbevf_configure_msix - Configure MSI-X hardware
 * @adapter: board private structure
 *
 * ixgbevf_configure_msix sets up the hardware to properly generate MSI-X
 * interrupts.
 **/
static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter)
{
	struct ixgbevf_q_vector *q_vector;
601
	int q_vectors, v_idx;
602 603

	q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
604
	adapter->eims_enable_mask = 0;
605 606 607 608 609 610

	/*
	 * Populate the IVAR table and set the ITR values to the
	 * corresponding register.
	 */
	for (v_idx = 0; v_idx < q_vectors; v_idx++) {
611
		struct ixgbevf_ring *ring;
612
		q_vector = adapter->q_vector[v_idx];
613 614 615 616 617 618

		ixgbevf_for_each_ring(ring, q_vector->rx)
			ixgbevf_set_ivar(adapter, 0, ring->reg_idx, v_idx);

		ixgbevf_for_each_ring(ring, q_vector->tx)
			ixgbevf_set_ivar(adapter, 1, ring->reg_idx, v_idx);
619

620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635
		if (q_vector->tx.ring && !q_vector->rx.ring) {
			/* tx only vector */
			if (adapter->tx_itr_setting == 1)
				q_vector->itr = IXGBE_10K_ITR;
			else
				q_vector->itr = adapter->tx_itr_setting;
		} else {
			/* rx or rx/tx vector */
			if (adapter->rx_itr_setting == 1)
				q_vector->itr = IXGBE_20K_ITR;
			else
				q_vector->itr = adapter->rx_itr_setting;
		}

		/* add q_vector eims value to global eims_enable_mask */
		adapter->eims_enable_mask |= 1 << v_idx;
636

637
		ixgbevf_write_eitr(q_vector);
638 639 640
	}

	ixgbevf_set_ivar(adapter, -1, 1, v_idx);
641 642 643
	/* setup eims_other and add value to global eims_enable_mask */
	adapter->eims_other = 1 << v_idx;
	adapter->eims_enable_mask |= adapter->eims_other;
644 645 646 647 648 649 650 651 652 653 654
}

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

/**
 * ixgbevf_update_itr - update the dynamic ITR value based on statistics
655 656
 * @q_vector: structure containing interrupt and ring information
 * @ring_container: structure containing ring performance data
657 658 659 660 661 662 663 664 665
 *
 *      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.
 **/
666 667
static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector,
			       struct ixgbevf_ring_container *ring_container)
668
{
669 670
	int bytes = ring_container->total_bytes;
	int packets = ring_container->total_packets;
671 672
	u32 timepassed_us;
	u64 bytes_perint;
673
	u8 itr_setting = ring_container->itr;
674 675

	if (packets == 0)
676
		return;
677 678 679 680 681 682 683

	/* simple throttlerate management
	 *    0-20MB/s lowest (100000 ints/s)
	 *   20-100MB/s low   (20000 ints/s)
	 *  100-1249MB/s bulk (8000 ints/s)
	 */
	/* what was last interrupt timeslice? */
684
	timepassed_us = q_vector->itr >> 2;
685 686 687 688
	bytes_perint = bytes / timepassed_us; /* bytes/usec */

	switch (itr_setting) {
	case lowest_latency:
689
		if (bytes_perint > 10)
690
			itr_setting = low_latency;
691 692
		break;
	case low_latency:
693
		if (bytes_perint > 20)
694
			itr_setting = bulk_latency;
695
		else if (bytes_perint <= 10)
696
			itr_setting = lowest_latency;
697 698
		break;
	case bulk_latency:
699
		if (bytes_perint <= 20)
700
			itr_setting = low_latency;
701 702 703
		break;
	}

704 705 706 707 708 709
	/* clear work counters since we have the values we need */
	ring_container->total_bytes = 0;
	ring_container->total_packets = 0;

	/* write updated itr to ring container */
	ring_container->itr = itr_setting;
710 711
}

712
static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector)
713
{
714 715
	u32 new_itr = q_vector->itr;
	u8 current_itr;
716

717 718
	ixgbevf_update_itr(q_vector, &q_vector->tx);
	ixgbevf_update_itr(q_vector, &q_vector->rx);
719

720
	current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
721 722 723 724

	switch (current_itr) {
	/* counts and packets in update_itr are dependent on these numbers */
	case lowest_latency:
725
		new_itr = IXGBE_100K_ITR;
726 727
		break;
	case low_latency:
728
		new_itr = IXGBE_20K_ITR;
729 730 731
		break;
	case bulk_latency:
	default:
732
		new_itr = IXGBE_8K_ITR;
733 734 735
		break;
	}

736
	if (new_itr != q_vector->itr) {
737
		/* do an exponential smoothing */
738 739 740 741 742 743 744
		new_itr = (10 * new_itr * q_vector->itr) /
			  ((9 * new_itr) + q_vector->itr);

		/* save the algorithm value here */
		q_vector->itr = new_itr;

		ixgbevf_write_eitr(q_vector);
745 746 747
	}
}

748
static irqreturn_t ixgbevf_msix_other(int irq, void *data)
749
{
750
	struct ixgbevf_adapter *adapter = data;
751
	struct ixgbe_hw *hw = &adapter->hw;
752

753
	hw->mac.get_link_status = 1;
754

755 756
	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
		mod_timer(&adapter->watchdog_timer, jiffies);
757

758 759
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other);

760 761 762 763 764
	return IRQ_HANDLED;
}


/**
765
 * ixgbevf_msix_clean_rings - single unshared vector rx clean (all queues)
766 767 768
 * @irq: unused
 * @data: pointer to our q_vector struct for this interrupt vector
 **/
769
static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data)
770 771 772
{
	struct ixgbevf_q_vector *q_vector = data;

773
	/* EIAM disabled interrupts (on this vector) for us */
774 775
	if (q_vector->rx.ring || q_vector->tx.ring)
		napi_schedule(&q_vector->napi);
776 777 778 779 780 781 782 783 784

	return IRQ_HANDLED;
}

static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx,
				     int r_idx)
{
	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];

785 786 787
	a->rx_ring[r_idx].next = q_vector->rx.ring;
	q_vector->rx.ring = &a->rx_ring[r_idx];
	q_vector->rx.count++;
788 789 790 791 792 793 794
}

static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx,
				     int t_idx)
{
	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];

795 796 797
	a->tx_ring[t_idx].next = q_vector->tx.ring;
	q_vector->tx.ring = &a->tx_ring[t_idx];
	q_vector->tx.count++;
798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
}

/**
 * ixgbevf_map_rings_to_vectors - Maps descriptor rings to vectors
 * @adapter: board private structure to initialize
 *
 * This function maps descriptor rings to the queue-specific vectors
 * we were allotted through the MSI-X enabling code.  Ideally, we'd have
 * one vector per ring/queue, but on a constrained vector budget, we
 * group the rings as "efficiently" as possible.  You would add new
 * mapping configurations in here.
 **/
static int ixgbevf_map_rings_to_vectors(struct ixgbevf_adapter *adapter)
{
	int q_vectors;
	int v_start = 0;
	int rxr_idx = 0, txr_idx = 0;
	int rxr_remaining = adapter->num_rx_queues;
	int txr_remaining = adapter->num_tx_queues;
	int i, j;
	int rqpv, tqpv;
	int err = 0;

	q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	/*
	 * The ideal configuration...
	 * We have enough vectors to map one per queue.
	 */
	if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) {
		for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
			map_vector_to_rxq(adapter, v_start, rxr_idx);

		for (; txr_idx < txr_remaining; v_start++, txr_idx++)
			map_vector_to_txq(adapter, v_start, txr_idx);
		goto out;
	}

	/*
	 * If we don't have enough vectors for a 1-to-1
	 * mapping, we'll have to group them so there are
	 * multiple queues per vector.
	 */
	/* Re-adjusting *qpv takes care of the remainder. */
	for (i = v_start; i < q_vectors; i++) {
		rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
		for (j = 0; j < rqpv; j++) {
			map_vector_to_rxq(adapter, i, rxr_idx);
			rxr_idx++;
			rxr_remaining--;
		}
	}
	for (i = v_start; i < q_vectors; i++) {
		tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
		for (j = 0; j < tqpv; j++) {
			map_vector_to_txq(adapter, i, txr_idx);
			txr_idx++;
			txr_remaining--;
		}
	}

out:
	return err;
}

/**
 * ixgbevf_request_msix_irqs - Initialize MSI-X interrupts
 * @adapter: board private structure
 *
 * ixgbevf_request_msix_irqs allocates MSI-X vectors and requests
 * interrupts from the kernel.
 **/
static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
873 874
	int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
	int vector, err;
875 876 877
	int ri = 0, ti = 0;

	for (vector = 0; vector < q_vectors; vector++) {
878 879 880 881 882 883 884 885 886 887 888 889 890
		struct ixgbevf_q_vector *q_vector = adapter->q_vector[vector];
		struct msix_entry *entry = &adapter->msix_entries[vector];

		if (q_vector->tx.ring && q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "TxRx", ri++);
			ti++;
		} else if (q_vector->rx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "rx", ri++);
		} else if (q_vector->tx.ring) {
			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
				 "%s-%s-%d", netdev->name, "tx", ti++);
891 892 893 894
		} else {
			/* skip this unused q_vector */
			continue;
		}
895 896
		err = request_irq(entry->vector, &ixgbevf_msix_clean_rings, 0,
				  q_vector->name, q_vector);
897 898 899 900 901 902 903 904 905
		if (err) {
			hw_dbg(&adapter->hw,
			       "request_irq failed for MSIX interrupt "
			       "Error: %d\n", err);
			goto free_queue_irqs;
		}
	}

	err = request_irq(adapter->msix_entries[vector].vector,
906
			  &ixgbevf_msix_other, 0, netdev->name, adapter);
907 908
	if (err) {
		hw_dbg(&adapter->hw,
909
		       "request_irq for msix_other failed: %d\n", err);
910 911 912 913 914 915
		goto free_queue_irqs;
	}

	return 0;

free_queue_irqs:
916 917 918 919 920
	while (vector) {
		vector--;
		free_irq(adapter->msix_entries[vector].vector,
			 adapter->q_vector[vector]);
	}
921 922 923 924 925 926 927 928 929 930 931 932
	pci_disable_msix(adapter->pdev);
	kfree(adapter->msix_entries);
	adapter->msix_entries = NULL;
	return err;
}

static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter)
{
	int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	for (i = 0; i < q_vectors; i++) {
		struct ixgbevf_q_vector *q_vector = adapter->q_vector[i];
933 934 935 936
		q_vector->rx.ring = NULL;
		q_vector->tx.ring = NULL;
		q_vector->rx.count = 0;
		q_vector->tx.count = 0;
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
	}
}

/**
 * ixgbevf_request_irq - initialize interrupts
 * @adapter: board private structure
 *
 * Attempts to configure interrupts using the best available
 * capabilities of the hardware and kernel.
 **/
static int ixgbevf_request_irq(struct ixgbevf_adapter *adapter)
{
	int err = 0;

	err = ixgbevf_request_msix_irqs(adapter);

	if (err)
		hw_dbg(&adapter->hw,
		       "request_irq failed, Error %d\n", err);

	return err;
}

static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter)
{
	int i, q_vectors;

	q_vectors = adapter->num_msix_vectors;
	i = q_vectors - 1;

967
	free_irq(adapter->msix_entries[i].vector, adapter);
968 969 970
	i--;

	for (; i >= 0; i--) {
971 972 973 974 975
		/* free only the irqs that were actually requested */
		if (!adapter->q_vector[i]->rx.ring &&
		    !adapter->q_vector[i]->tx.ring)
			continue;

976 977 978 979 980 981 982 983 984 985 986 987 988 989
		free_irq(adapter->msix_entries[i].vector,
			 adapter->q_vector[i]);
	}

	ixgbevf_reset_q_vectors(adapter);
}

/**
 * ixgbevf_irq_disable - Mask off interrupt generation on the NIC
 * @adapter: board private structure
 **/
static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
990
	int i;
991

992
	IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, 0);
993
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0);
994
	IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, 0);
995 996 997 998 999 1000 1001 1002 1003 1004 1005

	IXGBE_WRITE_FLUSH(hw);

	for (i = 0; i < adapter->num_msix_vectors; i++)
		synchronize_irq(adapter->msix_entries[i].vector);
}

/**
 * ixgbevf_irq_enable - Enable default interrupt generation settings
 * @adapter: board private structure
 **/
1006
static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter)
1007 1008 1009
{
	struct ixgbe_hw *hw = &adapter->hw;

1010 1011 1012
	IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, adapter->eims_enable_mask);
	IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, adapter->eims_enable_mask);
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_enable_mask);
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
}

/**
 * ixgbevf_configure_tx - Configure 82599 VF Transmit Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Tx unit of the MAC after a reset.
 **/
static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter)
{
	u64 tdba;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 i, j, tdlen, txctrl;

	/* Setup the HW Tx Head and Tail descriptor pointers */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		struct ixgbevf_ring *ring = &adapter->tx_ring[i];
		j = ring->reg_idx;
		tdba = ring->dma;
		tdlen = ring->count * sizeof(union ixgbe_adv_tx_desc);
		IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(j),
				(tdba & DMA_BIT_MASK(32)));
		IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(j), (tdba >> 32));
		IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(j), tdlen);
		IXGBE_WRITE_REG(hw, IXGBE_VFTDH(j), 0);
		IXGBE_WRITE_REG(hw, IXGBE_VFTDT(j), 0);
		adapter->tx_ring[i].head = IXGBE_VFTDH(j);
		adapter->tx_ring[i].tail = IXGBE_VFTDT(j);
		/* Disable Tx Head Writeback RO bit, since this hoses
		 * bookkeeping if things aren't delivered in order.
		 */
		txctrl = IXGBE_READ_REG(hw, IXGBE_VFDCA_TXCTRL(j));
		txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
		IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(j), txctrl);
	}
}

#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT	2

static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
{
	struct ixgbevf_ring *rx_ring;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 srrctl;

	rx_ring = &adapter->rx_ring[index];

	srrctl = IXGBE_SRRCTL_DROP_EN;

1062
	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
1063

1064 1065 1066
	srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >>
		  IXGBE_SRRCTL_BSIZEPKT_SHIFT;

1067 1068 1069
	IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
}

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
static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;
	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	int i;
	u16 rx_buf_len;

	/* notify the PF of our intent to use this size of frame */
	ixgbevf_rlpml_set_vf(hw, max_frame);

	/* PF will allow an extra 4 bytes past for vlan tagged frames */
	max_frame += VLAN_HLEN;

	/*
	 * Make best use of allocation by using all but 1K of a
	 * power of 2 allocation that will be used for skb->head.
	 */
	if ((hw->mac.type == ixgbe_mac_X540_vf) &&
	    (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE))
		rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
	else if (max_frame <= IXGBEVF_RXBUFFER_3K)
		rx_buf_len = IXGBEVF_RXBUFFER_3K;
	else if (max_frame <= IXGBEVF_RXBUFFER_7K)
		rx_buf_len = IXGBEVF_RXBUFFER_7K;
	else if (max_frame <= IXGBEVF_RXBUFFER_15K)
		rx_buf_len = IXGBEVF_RXBUFFER_15K;
	else
		rx_buf_len = IXGBEVF_MAX_RXBUFFER;

	for (i = 0; i < adapter->num_rx_queues; i++)
		adapter->rx_ring[i].rx_buf_len = rx_buf_len;
}

1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
/**
 * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset
 * @adapter: board private structure
 *
 * Configure the Rx unit of the MAC after a reset.
 **/
static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
{
	u64 rdba;
	struct ixgbe_hw *hw = &adapter->hw;
	int i, j;
	u32 rdlen;

1117 1118
	/* PSRTYPE must be initialized in 82599 */
	IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
1119 1120 1121

	/* set_rx_buffer_len must be called before ring initialization */
	ixgbevf_set_rx_buffer_len(adapter);
1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141

	rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc);
	/* 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++) {
		rdba = adapter->rx_ring[i].dma;
		j = adapter->rx_ring[i].reg_idx;
		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(j),
				(rdba & DMA_BIT_MASK(32)));
		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(j), (rdba >> 32));
		IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(j), rdlen);
		IXGBE_WRITE_REG(hw, IXGBE_VFRDH(j), 0);
		IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0);
		adapter->rx_ring[i].head = IXGBE_VFRDH(j);
		adapter->rx_ring[i].tail = IXGBE_VFRDT(j);

		ixgbevf_configure_srrctl(adapter, j);
	}
}

1142
static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
1143 1144 1145
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
1146 1147 1148 1149
	int err;

	if (!hw->mac.ops.set_vfta)
		return -EOPNOTSUPP;
1150

1151
	spin_lock_bh(&adapter->mbx_lock);
1152

1153
	/* add VID to filter table */
1154
	err = hw->mac.ops.set_vfta(hw, vid, 0, true);
1155

1156
	spin_unlock_bh(&adapter->mbx_lock);
1157

1158 1159 1160 1161 1162 1163 1164
	/* translate error return types so error makes sense */
	if (err == IXGBE_ERR_MBX)
		return -EIO;

	if (err == IXGBE_ERR_INVALID_ARGUMENT)
		return -EACCES;

J
Jiri Pirko 已提交
1165
	set_bit(vid, adapter->active_vlans);
1166

1167
	return err;
1168 1169
}

1170
static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
1171 1172 1173
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
1174
	int err = -EOPNOTSUPP;
1175

1176
	spin_lock_bh(&adapter->mbx_lock);
1177

1178 1179
	/* remove VID from filter table */
	if (hw->mac.ops.set_vfta)
1180
		err = hw->mac.ops.set_vfta(hw, vid, 0, false);
1181

1182
	spin_unlock_bh(&adapter->mbx_lock);
1183

J
Jiri Pirko 已提交
1184
	clear_bit(vid, adapter->active_vlans);
1185

1186
	return err;
1187 1188 1189 1190
}

static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
{
J
Jiri Pirko 已提交
1191
	u16 vid;
1192

J
Jiri Pirko 已提交
1193 1194
	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
		ixgbevf_vlan_rx_add_vid(adapter->netdev, vid);
1195 1196
}

1197 1198 1199 1200 1201 1202 1203
static int ixgbevf_write_uc_addr_list(struct net_device *netdev)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	int count = 0;

	if ((netdev_uc_count(netdev)) > 10) {
1204
		pr_err("Too many unicast filters - No Space\n");
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
		return -ENOSPC;
	}

	if (!netdev_uc_empty(netdev)) {
		struct netdev_hw_addr *ha;
		netdev_for_each_uc_addr(ha, netdev) {
			hw->mac.ops.set_uc_addr(hw, ++count, ha->addr);
			udelay(200);
		}
	} else {
		/*
		 * If the list is empty then send message to PF driver to
		 * clear all macvlans on this VF.
		 */
		hw->mac.ops.set_uc_addr(hw, 0, NULL);
	}

	return count;
}

1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237
/**
 * ixgbevf_set_rx_mode - Multicast set
 * @netdev: network interface device structure
 *
 * The set_rx_method 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 mode.
 **/
static void ixgbevf_set_rx_mode(struct net_device *netdev)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

1238
	spin_lock_bh(&adapter->mbx_lock);
1239

1240 1241
	/* reprogram multicast list */
	if (hw->mac.ops.update_mc_addr_list)
1242
		hw->mac.ops.update_mc_addr_list(hw, netdev);
1243 1244

	ixgbevf_write_uc_addr_list(netdev);
1245

1246
	spin_unlock_bh(&adapter->mbx_lock);
1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
}

static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter)
{
	int q_idx;
	struct ixgbevf_q_vector *q_vector;
	int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
		q_vector = adapter->q_vector[q_idx];
1257
		napi_enable(&q_vector->napi);
1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
	}
}

static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter)
{
	int q_idx;
	struct ixgbevf_q_vector *q_vector;
	int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
		q_vector = adapter->q_vector[q_idx];
		napi_disable(&q_vector->napi);
	}
}

static void ixgbevf_configure(struct ixgbevf_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	int i;

	ixgbevf_set_rx_mode(netdev);

	ixgbevf_restore_vlan(adapter);

	ixgbevf_configure_tx(adapter);
	ixgbevf_configure_rx(adapter);
	for (i = 0; i < adapter->num_rx_queues; i++) {
		struct ixgbevf_ring *ring = &adapter->rx_ring[i];
1286 1287
		ixgbevf_alloc_rx_buffers(adapter, ring,
					 IXGBE_DESC_UNUSED(ring));
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313
	}
}

#define IXGBE_MAX_RX_DESC_POLL 10
static inline void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter,
						int rxr)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int j = adapter->rx_ring[rxr].reg_idx;
	int k;

	for (k = 0; k < IXGBE_MAX_RX_DESC_POLL; k++) {
		if (IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j)) & IXGBE_RXDCTL_ENABLE)
			break;
		else
			msleep(1);
	}
	if (k >= IXGBE_MAX_RX_DESC_POLL) {
		hw_dbg(hw, "RXDCTL.ENABLE on Rx queue %d "
		       "not set within the polling period\n", rxr);
	}

	ixgbevf_release_rx_desc(&adapter->hw, &adapter->rx_ring[rxr],
				(adapter->rx_ring[rxr].count - 1));
}

1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351
static void ixgbevf_save_reset_stats(struct ixgbevf_adapter *adapter)
{
	/* Only save pre-reset stats if there are some */
	if (adapter->stats.vfgprc || adapter->stats.vfgptc) {
		adapter->stats.saved_reset_vfgprc += adapter->stats.vfgprc -
			adapter->stats.base_vfgprc;
		adapter->stats.saved_reset_vfgptc += adapter->stats.vfgptc -
			adapter->stats.base_vfgptc;
		adapter->stats.saved_reset_vfgorc += adapter->stats.vfgorc -
			adapter->stats.base_vfgorc;
		adapter->stats.saved_reset_vfgotc += adapter->stats.vfgotc -
			adapter->stats.base_vfgotc;
		adapter->stats.saved_reset_vfmprc += adapter->stats.vfmprc -
			adapter->stats.base_vfmprc;
	}
}

static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	adapter->stats.last_vfgprc = IXGBE_READ_REG(hw, IXGBE_VFGPRC);
	adapter->stats.last_vfgorc = IXGBE_READ_REG(hw, IXGBE_VFGORC_LSB);
	adapter->stats.last_vfgorc |=
		(((u64)(IXGBE_READ_REG(hw, IXGBE_VFGORC_MSB))) << 32);
	adapter->stats.last_vfgptc = IXGBE_READ_REG(hw, IXGBE_VFGPTC);
	adapter->stats.last_vfgotc = IXGBE_READ_REG(hw, IXGBE_VFGOTC_LSB);
	adapter->stats.last_vfgotc |=
		(((u64)(IXGBE_READ_REG(hw, IXGBE_VFGOTC_MSB))) << 32);
	adapter->stats.last_vfmprc = IXGBE_READ_REG(hw, IXGBE_VFMPRC);

	adapter->stats.base_vfgprc = adapter->stats.last_vfgprc;
	adapter->stats.base_vfgorc = adapter->stats.last_vfgorc;
	adapter->stats.base_vfgptc = adapter->stats.last_vfgptc;
	adapter->stats.base_vfgotc = adapter->stats.last_vfgotc;
	adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
}

1352 1353 1354
static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
1355 1356
	int api[] = { ixgbe_mbox_api_11,
		      ixgbe_mbox_api_10,
1357 1358 1359
		      ixgbe_mbox_api_unknown };
	int err = 0, idx = 0;

1360
	spin_lock_bh(&adapter->mbx_lock);
1361 1362 1363 1364 1365 1366 1367 1368

	while (api[idx] != ixgbe_mbox_api_unknown) {
		err = ixgbevf_negotiate_api_version(hw, api[idx]);
		if (!err)
			break;
		idx++;
	}

1369
	spin_unlock_bh(&adapter->mbx_lock);
1370 1371
}

1372
static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	int i, j = 0;
	int num_rx_rings = adapter->num_rx_queues;
	u32 txdctl, rxdctl;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		j = adapter->tx_ring[i].reg_idx;
		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
		/* enable WTHRESH=8 descriptors, to encourage burst writeback */
		txdctl |= (8 << 16);
		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
	}

	for (i = 0; i < adapter->num_tx_queues; i++) {
		j = adapter->tx_ring[i].reg_idx;
		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
		txdctl |= IXGBE_TXDCTL_ENABLE;
		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
	}

	for (i = 0; i < num_rx_rings; i++) {
		j = adapter->rx_ring[i].reg_idx;
		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
J
Jiri Pirko 已提交
1398
		rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME;
1399 1400 1401 1402 1403
		if (hw->mac.type == ixgbe_mac_X540_vf) {
			rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
			rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) |
				   IXGBE_RXDCTL_RLPML_EN);
		}
1404 1405 1406 1407 1408 1409
		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl);
		ixgbevf_rx_desc_queue_enable(adapter, i);
	}

	ixgbevf_configure_msix(adapter);

1410
	spin_lock_bh(&adapter->mbx_lock);
1411

1412 1413 1414 1415 1416 1417 1418
	if (hw->mac.ops.set_rar) {
		if (is_valid_ether_addr(hw->mac.addr))
			hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0);
		else
			hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0);
	}

1419
	spin_unlock_bh(&adapter->mbx_lock);
1420

1421 1422 1423 1424 1425 1426
	clear_bit(__IXGBEVF_DOWN, &adapter->state);
	ixgbevf_napi_enable_all(adapter);

	/* enable transmits */
	netif_tx_start_all_queues(netdev);

1427 1428 1429
	ixgbevf_save_reset_stats(adapter);
	ixgbevf_init_last_counter_stats(adapter);

1430
	hw->mac.get_link_status = 1;
1431 1432 1433
	mod_timer(&adapter->watchdog_timer, jiffies);
}

1434 1435 1436 1437 1438 1439 1440 1441 1442
static int ixgbevf_reset_queues(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbevf_ring *rx_ring;
	unsigned int def_q = 0;
	unsigned int num_tcs = 0;
	unsigned int num_rx_queues = 1;
	int err, i;

1443
	spin_lock_bh(&adapter->mbx_lock);
1444 1445 1446 1447

	/* fetch queue configuration from the PF */
	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);

1448
	spin_unlock_bh(&adapter->mbx_lock);
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 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506

	if (err)
		return err;

	if (num_tcs > 1) {
		/* update default Tx ring register index */
		adapter->tx_ring[0].reg_idx = def_q;

		/* we need as many queues as traffic classes */
		num_rx_queues = num_tcs;
	}

	/* nothing to do if we have the correct number of queues */
	if (adapter->num_rx_queues == num_rx_queues)
		return 0;

	/* allocate new rings */
	rx_ring = kcalloc(num_rx_queues,
			  sizeof(struct ixgbevf_ring), GFP_KERNEL);
	if (!rx_ring)
		return -ENOMEM;

	/* setup ring fields */
	for (i = 0; i < num_rx_queues; i++) {
		rx_ring[i].count = adapter->rx_ring_count;
		rx_ring[i].queue_index = i;
		rx_ring[i].reg_idx = i;
		rx_ring[i].dev = &adapter->pdev->dev;
		rx_ring[i].netdev = adapter->netdev;

		/* allocate resources on the ring */
		err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]);
		if (err) {
			while (i) {
				i--;
				ixgbevf_free_rx_resources(adapter, &rx_ring[i]);
			}
			kfree(rx_ring);
			return err;
		}
	}

	/* free the existing rings and queues */
	ixgbevf_free_all_rx_resources(adapter);
	adapter->num_rx_queues = 0;
	kfree(adapter->rx_ring);

	/* move new rings into position on the adapter struct */
	adapter->rx_ring = rx_ring;
	adapter->num_rx_queues = num_rx_queues;

	/* reset ring to vector mapping */
	ixgbevf_reset_q_vectors(adapter);
	ixgbevf_map_rings_to_vectors(adapter);

	return 0;
}

1507
void ixgbevf_up(struct ixgbevf_adapter *adapter)
1508 1509 1510
{
	struct ixgbe_hw *hw = &adapter->hw;

1511 1512
	ixgbevf_negotiate_api(adapter);

1513 1514
	ixgbevf_reset_queues(adapter);

1515 1516
	ixgbevf_configure(adapter);

1517
	ixgbevf_up_complete(adapter);
1518 1519 1520 1521

	/* clear any pending interrupts, may auto mask */
	IXGBE_READ_REG(hw, IXGBE_VTEICR);

1522
	ixgbevf_irq_enable(adapter);
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536
}

/**
 * ixgbevf_clean_rx_ring - Free Rx Buffers per Queue
 * @adapter: board private structure
 * @rx_ring: ring to free buffers from
 **/
static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
				  struct ixgbevf_ring *rx_ring)
{
	struct pci_dev *pdev = adapter->pdev;
	unsigned long size;
	unsigned int i;

G
Greg Rose 已提交
1537 1538
	if (!rx_ring->rx_buffer_info)
		return;
1539

G
Greg Rose 已提交
1540
	/* Free all the Rx ring sk_buffs */
1541 1542 1543 1544 1545
	for (i = 0; i < rx_ring->count; i++) {
		struct ixgbevf_rx_buffer *rx_buffer_info;

		rx_buffer_info = &rx_ring->rx_buffer_info[i];
		if (rx_buffer_info->dma) {
1546
			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
1547
					 rx_ring->rx_buf_len,
1548
					 DMA_FROM_DEVICE);
1549 1550 1551 1552 1553 1554 1555
			rx_buffer_info->dma = 0;
		}
		if (rx_buffer_info->skb) {
			struct sk_buff *skb = rx_buffer_info->skb;
			rx_buffer_info->skb = NULL;
			do {
				struct sk_buff *this = skb;
1556
				skb = IXGBE_CB(skb)->prev;
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
				dev_kfree_skb(this);
			} while (skb);
		}
	}

	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
	memset(rx_ring->rx_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;

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

/**
 * ixgbevf_clean_tx_ring - Free Tx Buffers
 * @adapter: board private structure
 * @tx_ring: ring to be cleaned
 **/
static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter,
				  struct ixgbevf_ring *tx_ring)
{
	struct ixgbevf_tx_buffer *tx_buffer_info;
	unsigned long size;
	unsigned int i;

G
Greg Rose 已提交
1589 1590 1591
	if (!tx_ring->tx_buffer_info)
		return;

1592 1593 1594 1595
	/* Free all the Tx ring sk_buffs */

	for (i = 0; i < tx_ring->count; i++) {
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
1596
		ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 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
	}

	size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count;
	memset(tx_ring->tx_buffer_info, 0, size);

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

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

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

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

	for (i = 0; i < adapter->num_rx_queues; i++)
		ixgbevf_clean_rx_ring(adapter, &adapter->rx_ring[i]);
}

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

	for (i = 0; i < adapter->num_tx_queues; i++)
		ixgbevf_clean_tx_ring(adapter, &adapter->tx_ring[i]);
}

void ixgbevf_down(struct ixgbevf_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 txdctl;
	int i, j;

	/* signal that we are down to the interrupt handler */
	set_bit(__IXGBEVF_DOWN, &adapter->state);
	/* disable receives */

	netif_tx_disable(netdev);

	msleep(10);

	netif_tx_stop_all_queues(netdev);

	ixgbevf_irq_disable(adapter);

	ixgbevf_napi_disable_all(adapter);

	del_timer_sync(&adapter->watchdog_timer);
	/* can't call flush scheduled work here because it can deadlock
	 * if linkwatch_event tries to acquire the rtnl_lock which we are
	 * holding */
	while (adapter->flags & IXGBE_FLAG_IN_WATCHDOG_TASK)
		msleep(1);

	/* disable transmits in the hardware now that interrupts are off */
	for (i = 0; i < adapter->num_tx_queues; i++) {
		j = adapter->tx_ring[i].reg_idx;
		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j),
				(txdctl & ~IXGBE_TXDCTL_ENABLE));
	}

	netif_carrier_off(netdev);

	if (!pci_channel_offline(adapter->pdev))
		ixgbevf_reset(adapter);

	ixgbevf_clean_all_tx_rings(adapter);
	ixgbevf_clean_all_rx_rings(adapter);
}

void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter)
{
	WARN_ON(in_interrupt());
G
Greg Rose 已提交
1685

1686 1687 1688
	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
		msleep(1);

G
Greg Rose 已提交
1689 1690 1691 1692 1693 1694 1695
	/*
	 * Check if PF is up before re-init.  If not then skip until
	 * later when the PF is up and ready to service requests from
	 * the VF via mailbox.  If the VF is up and running then the
	 * watchdog task will continue to schedule reset tasks until
	 * the PF is up and running.
	 */
1696 1697
	ixgbevf_down(adapter);
	ixgbevf_up(adapter);
1698 1699 1700 1701 1702 1703 1704 1705 1706

	clear_bit(__IXGBEVF_RESETTING, &adapter->state);
}

void ixgbevf_reset(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct net_device *netdev = adapter->netdev;

1707
	spin_lock_bh(&adapter->mbx_lock);
1708

1709 1710 1711 1712 1713
	if (hw->mac.ops.reset_hw(hw))
		hw_dbg(hw, "PF still resetting\n");
	else
		hw->mac.ops.init_hw(hw);

1714
	spin_unlock_bh(&adapter->mbx_lock);
1715

1716 1717 1718 1719 1720 1721 1722 1723
	if (is_valid_ether_addr(adapter->hw.mac.addr)) {
		memcpy(netdev->dev_addr, adapter->hw.mac.addr,
		       netdev->addr_len);
		memcpy(netdev->perm_addr, adapter->hw.mac.addr,
		       netdev->addr_len);
	}
}

1724 1725
static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
					int vectors)
1726 1727 1728
{
	int err, vector_threshold;

1729 1730 1731
	/* We'll want at least 2 (vector_threshold):
	 * 1) TxQ[0] + RxQ[0] handler
	 * 2) Other (Link Status Change, etc.)
1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742
	 */
	vector_threshold = MIN_MSIX_COUNT;

	/* The more we get, the more we will assign to Tx/Rx Cleanup
	 * for the separate queues...where Rx Cleanup >= Tx Cleanup.
	 * Right now, we simply care about how many we'll get; we'll
	 * set them up later while requesting irq's.
	 */
	while (vectors >= vector_threshold) {
		err = pci_enable_msix(adapter->pdev, adapter->msix_entries,
				      vectors);
1743
		if (!err || err < 0) /* Success or a nasty failure. */
1744 1745 1746 1747 1748
			break;
		else /* err == number of vectors we should try again with */
			vectors = err;
	}

1749 1750 1751 1752 1753 1754
	if (vectors < vector_threshold)
		err = -ENOMEM;

	if (err) {
		dev_err(&adapter->pdev->dev,
			"Unable to allocate MSI-X interrupts\n");
1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
		kfree(adapter->msix_entries);
		adapter->msix_entries = NULL;
	} else {
		/*
		 * Adjust for only the vectors we'll use, which is minimum
		 * of max_msix_q_vectors + NON_Q_VECTORS, or the number of
		 * vectors we were allocated.
		 */
		adapter->num_msix_vectors = vectors;
	}
1765
	return err;
1766 1767
}

1768 1769
/**
 * ixgbevf_set_num_queues - Allocate queues for device, feature dependent
1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810
 * @adapter: board private structure to initialize
 *
 * This is the top level queue allocation routine.  The order here is very
 * important, starting with the "most" number of features turned on at once,
 * and ending with the smallest set of features.  This way large combinations
 * can be allocated if they're turned on, and smaller combinations are the
 * fallthrough conditions.
 *
 **/
static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
{
	/* Start with base case */
	adapter->num_rx_queues = 1;
	adapter->num_tx_queues = 1;
}

/**
 * ixgbevf_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.  The polling_netdev array is
 * intended for Multiqueue, but should work fine with a single queue.
 **/
static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter)
{
	int i;

	adapter->tx_ring = kcalloc(adapter->num_tx_queues,
				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
	if (!adapter->tx_ring)
		goto err_tx_ring_allocation;

	adapter->rx_ring = kcalloc(adapter->num_rx_queues,
				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
	if (!adapter->rx_ring)
		goto err_rx_ring_allocation;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		adapter->tx_ring[i].count = adapter->tx_ring_count;
		adapter->tx_ring[i].queue_index = i;
1811
		/* reg_idx may be remapped later by DCB config */
1812
		adapter->tx_ring[i].reg_idx = i;
1813 1814
		adapter->tx_ring[i].dev = &adapter->pdev->dev;
		adapter->tx_ring[i].netdev = adapter->netdev;
1815 1816 1817 1818 1819 1820
	}

	for (i = 0; i < adapter->num_rx_queues; i++) {
		adapter->rx_ring[i].count = adapter->rx_ring_count;
		adapter->rx_ring[i].queue_index = i;
		adapter->rx_ring[i].reg_idx = i;
1821 1822
		adapter->rx_ring[i].dev = &adapter->pdev->dev;
		adapter->rx_ring[i].netdev = adapter->netdev;
1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
	}

	return 0;

err_rx_ring_allocation:
	kfree(adapter->tx_ring);
err_tx_ring_allocation:
	return -ENOMEM;
}

/**
 * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported
 * @adapter: board private structure to initialize
 *
 * Attempt to configure the interrupts using the best available
 * capabilities of the hardware and the kernel.
 **/
static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter)
{
1842
	struct net_device *netdev = adapter->netdev;
1843 1844 1845 1846 1847 1848 1849
	int err = 0;
	int vector, v_budget;

	/*
	 * It's easy to be greedy for MSI-X vectors, but it really
	 * doesn't do us much good if we have a lot more vectors
	 * than CPU's.  So let's be conservative and only ask for
1850 1851
	 * (roughly) the same number of vectors as there are CPU's.
	 * The default is to use pairs of vectors.
1852
	 */
1853 1854 1855
	v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues);
	v_budget = min_t(int, v_budget, num_online_cpus());
	v_budget += NON_Q_VECTORS;
1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868

	/* A failure in MSI-X entry allocation isn't fatal, but it does
	 * mean we disable MSI-X capabilities of the adapter. */
	adapter->msix_entries = kcalloc(v_budget,
					sizeof(struct msix_entry), GFP_KERNEL);
	if (!adapter->msix_entries) {
		err = -ENOMEM;
		goto out;
	}

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

1869 1870 1871
	err = ixgbevf_acquire_msix_vectors(adapter, v_budget);
	if (err)
		goto out;
1872

1873 1874 1875 1876 1877 1878
	err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
	if (err)
		goto out;

	err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues);

1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902
out:
	return err;
}

/**
 * ixgbevf_alloc_q_vectors - Allocate memory for interrupt vectors
 * @adapter: board private structure to initialize
 *
 * We allocate one q_vector per queue interrupt.  If allocation fails we
 * return -ENOMEM.
 **/
static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter)
{
	int q_idx, num_q_vectors;
	struct ixgbevf_q_vector *q_vector;

	num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
		q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL);
		if (!q_vector)
			goto err_out;
		q_vector->adapter = adapter;
		q_vector->v_idx = q_idx;
1903 1904
		netif_napi_add(adapter->netdev, &q_vector->napi,
			       ixgbevf_poll, 64);
1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930
		adapter->q_vector[q_idx] = q_vector;
	}

	return 0;

err_out:
	while (q_idx) {
		q_idx--;
		q_vector = adapter->q_vector[q_idx];
		netif_napi_del(&q_vector->napi);
		kfree(q_vector);
		adapter->q_vector[q_idx] = NULL;
	}
	return -ENOMEM;
}

/**
 * ixgbevf_free_q_vectors - Free memory allocated for interrupt vectors
 * @adapter: board private structure to initialize
 *
 * This function frees the memory allocated to the q_vectors.  In addition if
 * NAPI is enabled it will delete any references to the NAPI struct prior
 * to freeing the q_vector.
 **/
static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter)
{
1931
	int q_idx, num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
1932 1933 1934 1935 1936

	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
		struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx];

		adapter->q_vector[q_idx] = NULL;
1937
		netif_napi_del(&q_vector->napi);
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
		kfree(q_vector);
	}
}

/**
 * ixgbevf_reset_interrupt_capability - Reset MSIX setup
 * @adapter: board private structure
 *
 **/
static void ixgbevf_reset_interrupt_capability(struct ixgbevf_adapter *adapter)
{
	pci_disable_msix(adapter->pdev);
	kfree(adapter->msix_entries);
	adapter->msix_entries = NULL;
}

/**
 * ixgbevf_init_interrupt_scheme - Determine if MSIX is supported and init
 * @adapter: board private structure to initialize
 *
 **/
static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter)
{
	int err;

	/* Number of supported queues */
	ixgbevf_set_num_queues(adapter);

	err = ixgbevf_set_interrupt_capability(adapter);
	if (err) {
		hw_dbg(&adapter->hw,
		       "Unable to setup interrupt capabilities\n");
		goto err_set_interrupt;
	}

	err = ixgbevf_alloc_q_vectors(adapter);
	if (err) {
		hw_dbg(&adapter->hw, "Unable to allocate memory for queue "
		       "vectors\n");
		goto err_alloc_q_vectors;
	}

	err = ixgbevf_alloc_queues(adapter);
	if (err) {
1982
		pr_err("Unable to allocate memory for queues\n");
1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001
		goto err_alloc_queues;
	}

	hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, "
	       "Tx Queue count = %u\n",
	       (adapter->num_rx_queues > 1) ? "Enabled" :
	       "Disabled", adapter->num_rx_queues, adapter->num_tx_queues);

	set_bit(__IXGBEVF_DOWN, &adapter->state);

	return 0;
err_alloc_queues:
	ixgbevf_free_q_vectors(adapter);
err_alloc_q_vectors:
	ixgbevf_reset_interrupt_capability(adapter);
err_set_interrupt:
	return err;
}

2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017
/**
 * ixgbevf_clear_interrupt_scheme - Clear the current interrupt scheme settings
 * @adapter: board private structure to clear interrupt scheme on
 *
 * We go through and clear interrupt specific resources and reset the structure
 * to pre-load conditions
 **/
static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter)
{
	adapter->num_tx_queues = 0;
	adapter->num_rx_queues = 0;

	ixgbevf_free_q_vectors(adapter);
	ixgbevf_reset_interrupt_capability(adapter);
}

2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036
/**
 * ixgbevf_sw_init - Initialize general software structures
 * (struct ixgbevf_adapter)
 * @adapter: board private structure to initialize
 *
 * ixgbevf_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 ixgbevf_sw_init(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct pci_dev *pdev = adapter->pdev;
	int err;

	/* PCI config space info */

	hw->vendor_id = pdev->vendor;
	hw->device_id = pdev->device;
2037
	hw->revision_id = pdev->revision;
2038 2039 2040 2041
	hw->subsystem_vendor_id = pdev->subsystem_vendor;
	hw->subsystem_device_id = pdev->subsystem_device;

	hw->mbx.ops.init_params(hw);
2042 2043 2044 2045 2046

	/* assume legacy case in which PF would only give VF 2 queues */
	hw->mac.max_tx_queues = 2;
	hw->mac.max_rx_queues = 2;

2047 2048 2049 2050
	err = hw->mac.ops.reset_hw(hw);
	if (err) {
		dev_info(&pdev->dev,
		         "PF still in reset state, assigning new address\n");
2051 2052 2053
		eth_hw_addr_random(adapter->netdev);
		memcpy(adapter->hw.mac.addr, adapter->netdev->dev_addr,
			adapter->netdev->addr_len);
2054 2055 2056
	} else {
		err = hw->mac.ops.init_hw(hw);
		if (err) {
2057
			pr_err("init_shared_code failed: %d\n", err);
2058 2059
			goto out;
		}
2060 2061
		memcpy(adapter->netdev->dev_addr, adapter->hw.mac.addr,
			adapter->netdev->addr_len);
2062 2063
	}

2064 2065 2066
	/* lock to protect mailbox accesses */
	spin_lock_init(&adapter->mbx_lock);

2067
	/* Enable dynamic interrupt throttling rates */
2068 2069
	adapter->rx_itr_setting = 1;
	adapter->tx_itr_setting = 1;
2070 2071 2072 2073 2074 2075

	/* set default ring sizes */
	adapter->tx_ring_count = IXGBEVF_DEFAULT_TXD;
	adapter->rx_ring_count = IXGBEVF_DEFAULT_RXD;

	set_bit(__IXGBEVF_DOWN, &adapter->state);
2076
	return 0;
2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133

out:
	return err;
}

#define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter)	\
	{							\
		u32 current_counter = IXGBE_READ_REG(hw, reg);	\
		if (current_counter < last_counter)		\
			counter += 0x100000000LL;		\
		last_counter = current_counter;			\
		counter &= 0xFFFFFFFF00000000LL;		\
		counter |= current_counter;			\
	}

#define UPDATE_VF_COUNTER_36bit(reg_lsb, reg_msb, last_counter, counter) \
	{								 \
		u64 current_counter_lsb = IXGBE_READ_REG(hw, reg_lsb);	 \
		u64 current_counter_msb = IXGBE_READ_REG(hw, reg_msb);	 \
		u64 current_counter = (current_counter_msb << 32) |      \
			current_counter_lsb;                             \
		if (current_counter < last_counter)			 \
			counter += 0x1000000000LL;			 \
		last_counter = current_counter;				 \
		counter &= 0xFFFFFFF000000000LL;			 \
		counter |= current_counter;				 \
	}
/**
 * ixgbevf_update_stats - Update the board statistics counters.
 * @adapter: board private structure
 **/
void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc,
				adapter->stats.vfgprc);
	UPDATE_VF_COUNTER_32bit(IXGBE_VFGPTC, adapter->stats.last_vfgptc,
				adapter->stats.vfgptc);
	UPDATE_VF_COUNTER_36bit(IXGBE_VFGORC_LSB, IXGBE_VFGORC_MSB,
				adapter->stats.last_vfgorc,
				adapter->stats.vfgorc);
	UPDATE_VF_COUNTER_36bit(IXGBE_VFGOTC_LSB, IXGBE_VFGOTC_MSB,
				adapter->stats.last_vfgotc,
				adapter->stats.vfgotc);
	UPDATE_VF_COUNTER_32bit(IXGBE_VFMPRC, adapter->stats.last_vfmprc,
				adapter->stats.vfmprc);
}

/**
 * ixgbevf_watchdog - Timer Call-back
 * @data: pointer to adapter cast into an unsigned long
 **/
static void ixgbevf_watchdog(unsigned long data)
{
	struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data;
	struct ixgbe_hw *hw = &adapter->hw;
2134
	u32 eics = 0;
2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147
	int i;

	/*
	 * Do the watchdog outside of interrupt context due to the lovely
	 * delays that some of the newer hardware requires
	 */

	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
		goto watchdog_short_circuit;

	/* get one bit for every active tx/rx interrupt vector */
	for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) {
		struct ixgbevf_q_vector *qv = adapter->q_vector[i];
2148
		if (qv->rx.ring || qv->tx.ring)
2149
			eics |= 1 << i;
2150 2151
	}

2152
	IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics);
2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205

watchdog_short_circuit:
	schedule_work(&adapter->watchdog_task);
}

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

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

static void ixgbevf_reset_task(struct work_struct *work)
{
	struct ixgbevf_adapter *adapter;
	adapter = container_of(work, struct ixgbevf_adapter, reset_task);

	/* If we're already down or resetting, just bail */
	if (test_bit(__IXGBEVF_DOWN, &adapter->state) ||
	    test_bit(__IXGBEVF_RESETTING, &adapter->state))
		return;

	adapter->tx_timeout_count++;

	ixgbevf_reinit_locked(adapter);
}

/**
 * ixgbevf_watchdog_task - worker thread to bring link up
 * @work: pointer to work_struct containing our data
 **/
static void ixgbevf_watchdog_task(struct work_struct *work)
{
	struct ixgbevf_adapter *adapter = container_of(work,
						       struct ixgbevf_adapter,
						       watchdog_task);
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 link_speed = adapter->link_speed;
	bool link_up = adapter->link_up;

	adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK;

	/*
	 * Always check the link on the watchdog because we have
	 * no LSC interrupt
	 */
	if (hw->mac.ops.check_link) {
2206 2207
		s32 need_reset;

2208
		spin_lock_bh(&adapter->mbx_lock);
2209 2210 2211 2212

		need_reset = hw->mac.ops.check_link(hw, &link_speed,
						    &link_up, false);

2213
		spin_unlock_bh(&adapter->mbx_lock);
2214 2215

		if (need_reset) {
2216 2217
			adapter->link_up = link_up;
			adapter->link_speed = link_speed;
2218 2219
			netif_carrier_off(netdev);
			netif_tx_stop_all_queues(netdev);
2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233
			schedule_work(&adapter->reset_task);
			goto pf_has_reset;
		}
	} else {
		/* always assume link is up, if no check link
		 * function */
		link_speed = IXGBE_LINK_SPEED_10GB_FULL;
		link_up = true;
	}
	adapter->link_up = link_up;
	adapter->link_speed = link_speed;

	if (link_up) {
		if (!netif_carrier_ok(netdev)) {
J
Joe Perches 已提交
2234 2235 2236
			hw_dbg(&adapter->hw, "NIC Link is Up, %u Gbps\n",
			       (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
			       10 : 1);
2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251
			netif_carrier_on(netdev);
			netif_tx_wake_all_queues(netdev);
		}
	} else {
		adapter->link_up = false;
		adapter->link_speed = 0;
		if (netif_carrier_ok(netdev)) {
			hw_dbg(&adapter->hw, "NIC Link is Down\n");
			netif_carrier_off(netdev);
			netif_tx_stop_all_queues(netdev);
		}
	}

	ixgbevf_update_stats(adapter);

2252
pf_has_reset:
2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277
	/* Reset the timer */
	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
		mod_timer(&adapter->watchdog_timer,
			  round_jiffies(jiffies + (2 * HZ)));

	adapter->flags &= ~IXGBE_FLAG_IN_WATCHDOG_TASK;
}

/**
 * ixgbevf_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
 **/
void ixgbevf_free_tx_resources(struct ixgbevf_adapter *adapter,
			       struct ixgbevf_ring *tx_ring)
{
	struct pci_dev *pdev = adapter->pdev;

	ixgbevf_clean_tx_ring(adapter, tx_ring);

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

2278 2279
	dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
			  tx_ring->dma);
2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314

	tx_ring->desc = NULL;
}

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

	for (i = 0; i < adapter->num_tx_queues; i++)
		if (adapter->tx_ring[i].desc)
			ixgbevf_free_tx_resources(adapter,
						  &adapter->tx_ring[i]);

}

/**
 * ixgbevf_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 ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter,
			       struct ixgbevf_ring *tx_ring)
{
	struct pci_dev *pdev = adapter->pdev;
	int size;

	size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count;
E
Eric Dumazet 已提交
2315
	tx_ring->tx_buffer_info = vzalloc(size);
2316 2317 2318 2319 2320 2321 2322
	if (!tx_ring->tx_buffer_info)
		goto err;

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

2323 2324
	tx_ring->desc = dma_alloc_coherent(&pdev->dev, tx_ring->size,
					   &tx_ring->dma, GFP_KERNEL);
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 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379
	if (!tx_ring->desc)
		goto err;

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

err:
	vfree(tx_ring->tx_buffer_info);
	tx_ring->tx_buffer_info = NULL;
	hw_dbg(&adapter->hw, "Unable to allocate memory for the transmit "
	       "descriptor ring\n");
	return -ENOMEM;
}

/**
 * ixgbevf_setup_all_tx_resources - allocate all queues Tx resources
 * @adapter: board private structure
 *
 * If this function returns with an error, then it's possible one or
 * more of the rings is populated (while the rest are not).  It is the
 * callers duty to clean those orphaned rings.
 *
 * Return 0 on success, negative on failure
 **/
static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
{
	int i, err = 0;

	for (i = 0; i < adapter->num_tx_queues; i++) {
		err = ixgbevf_setup_tx_resources(adapter, &adapter->tx_ring[i]);
		if (!err)
			continue;
		hw_dbg(&adapter->hw,
		       "Allocation for Tx Queue %u failed\n", i);
		break;
	}

	return err;
}

/**
 * ixgbevf_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 ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter,
			       struct ixgbevf_ring *rx_ring)
{
	struct pci_dev *pdev = adapter->pdev;
	int size;

	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
E
Eric Dumazet 已提交
2380
	rx_ring->rx_buffer_info = vzalloc(size);
2381
	if (!rx_ring->rx_buffer_info)
2382 2383 2384 2385 2386 2387
		goto alloc_failed;

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

2388 2389
	rx_ring->desc = dma_alloc_coherent(&pdev->dev, rx_ring->size,
					   &rx_ring->dma, GFP_KERNEL);
2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449

	if (!rx_ring->desc) {
		hw_dbg(&adapter->hw,
		       "Unable to allocate memory for "
		       "the receive descriptor ring\n");
		vfree(rx_ring->rx_buffer_info);
		rx_ring->rx_buffer_info = NULL;
		goto alloc_failed;
	}

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

	return 0;
alloc_failed:
	return -ENOMEM;
}

/**
 * ixgbevf_setup_all_rx_resources - allocate all queues Rx resources
 * @adapter: board private structure
 *
 * If this function returns with an error, then it's possible one or
 * more of the rings is populated (while the rest are not).  It is the
 * callers duty to clean those orphaned rings.
 *
 * Return 0 on success, negative on failure
 **/
static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter)
{
	int i, err = 0;

	for (i = 0; i < adapter->num_rx_queues; i++) {
		err = ixgbevf_setup_rx_resources(adapter, &adapter->rx_ring[i]);
		if (!err)
			continue;
		hw_dbg(&adapter->hw,
		       "Allocation for Rx Queue %u failed\n", i);
		break;
	}
	return err;
}

/**
 * ixgbevf_free_rx_resources - Free Rx Resources
 * @adapter: board private structure
 * @rx_ring: ring to clean the resources from
 *
 * Free all receive software resources
 **/
void ixgbevf_free_rx_resources(struct ixgbevf_adapter *adapter,
			       struct ixgbevf_ring *rx_ring)
{
	struct pci_dev *pdev = adapter->pdev;

	ixgbevf_clean_rx_ring(adapter, rx_ring);

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

2450 2451
	dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
			  rx_ring->dma);
2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471

	rx_ring->desc = NULL;
}

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

	for (i = 0; i < adapter->num_rx_queues; i++)
		if (adapter->rx_ring[i].desc)
			ixgbevf_free_rx_resources(adapter,
						  &adapter->rx_ring[i]);
}

2472 2473 2474 2475 2476 2477 2478 2479 2480
static int ixgbevf_setup_queues(struct ixgbevf_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbevf_ring *rx_ring;
	unsigned int def_q = 0;
	unsigned int num_tcs = 0;
	unsigned int num_rx_queues = 1;
	int err, i;

2481
	spin_lock_bh(&adapter->mbx_lock);
2482 2483 2484 2485

	/* fetch queue configuration from the PF */
	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);

2486
	spin_unlock_bh(&adapter->mbx_lock);
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

	if (err)
		return err;

	if (num_tcs > 1) {
		/* update default Tx ring register index */
		adapter->tx_ring[0].reg_idx = def_q;

		/* we need as many queues as traffic classes */
		num_rx_queues = num_tcs;
	}

	/* nothing to do if we have the correct number of queues */
	if (adapter->num_rx_queues == num_rx_queues)
		return 0;

	/* allocate new rings */
	rx_ring = kcalloc(num_rx_queues,
			  sizeof(struct ixgbevf_ring), GFP_KERNEL);
	if (!rx_ring)
		return -ENOMEM;

	/* setup ring fields */
	for (i = 0; i < num_rx_queues; i++) {
		rx_ring[i].count = adapter->rx_ring_count;
		rx_ring[i].queue_index = i;
		rx_ring[i].reg_idx = i;
		rx_ring[i].dev = &adapter->pdev->dev;
		rx_ring[i].netdev = adapter->netdev;
	}

	/* free the existing ring and queues */
	adapter->num_rx_queues = 0;
	kfree(adapter->rx_ring);

	/* move new rings into position on the adapter struct */
	adapter->rx_ring = rx_ring;
	adapter->num_rx_queues = num_rx_queues;

	return 0;
}

2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556
/**
 * ixgbevf_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 ixgbevf_open(struct net_device *netdev)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	int err;

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

	if (hw->adapter_stopped) {
		ixgbevf_reset(adapter);
		/* if adapter is still stopped then PF isn't up and
		 * the vf can't start. */
		if (hw->adapter_stopped) {
			err = IXGBE_ERR_MBX;
2557 2558
			pr_err("Unable to start - perhaps the PF Driver isn't "
			       "up yet\n");
2559 2560 2561 2562
			goto err_setup_reset;
		}
	}

2563 2564
	ixgbevf_negotiate_api(adapter);

2565 2566 2567 2568 2569
	/* setup queue reg_idx and Rx queue count */
	err = ixgbevf_setup_queues(adapter);
	if (err)
		goto err_setup_queues;

2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588
	/* allocate transmit descriptors */
	err = ixgbevf_setup_all_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

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

	ixgbevf_configure(adapter);

	/*
	 * Map the Tx/Rx rings to the vectors we were allotted.
	 * if request_irq will be called in this function map_rings
	 * must be called *before* up_complete
	 */
	ixgbevf_map_rings_to_vectors(adapter);

2589
	ixgbevf_up_complete(adapter);
2590 2591 2592 2593 2594 2595 2596

	/* clear any pending interrupts, may auto mask */
	IXGBE_READ_REG(hw, IXGBE_VTEICR);
	err = ixgbevf_request_irq(adapter);
	if (err)
		goto err_req_irq;

2597
	ixgbevf_irq_enable(adapter);
2598 2599 2600 2601 2602 2603 2604 2605 2606 2607

	return 0;

err_req_irq:
	ixgbevf_down(adapter);
	ixgbevf_free_irq(adapter);
err_setup_rx:
	ixgbevf_free_all_rx_resources(adapter);
err_setup_tx:
	ixgbevf_free_all_tx_resources(adapter);
2608
err_setup_queues:
2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639
	ixgbevf_reset(adapter);

err_setup_reset:

	return err;
}

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

	ixgbevf_down(adapter);
	ixgbevf_free_irq(adapter);

	ixgbevf_free_all_tx_resources(adapter);
	ixgbevf_free_all_rx_resources(adapter);

	return 0;
}

2640 2641 2642
static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring,
				u32 vlan_macip_lens, u32 type_tucmd,
				u32 mss_l4len_idx)
2643 2644
{
	struct ixgbe_adv_tx_context_desc *context_desc;
2645
	u16 i = tx_ring->next_to_use;
2646

2647
	context_desc = IXGBEVF_TX_CTXTDESC(tx_ring, i);
2648

2649 2650
	i++;
	tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
2651

2652 2653
	/* set bits to identify this as an advanced context descriptor */
	type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT;
2654

2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668
	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
	context_desc->seqnum_seed	= 0;
	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
}

static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
		       struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
{
	u32 vlan_macip_lens, type_tucmd;
	u32 mss_l4len_idx, l4len;

	if (!skb_is_gso(skb))
		return 0;
2669

2670 2671 2672 2673
	if (skb_header_cloned(skb)) {
		int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (err)
			return err;
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 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714
	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
	type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;

	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);
		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
	} else if (skb_is_gso_v6(skb)) {
		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);
	}

	/* compute header lengths */
	l4len = tcp_hdrlen(skb);
	*hdr_len += l4len;
	*hdr_len = skb_transport_offset(skb) + l4len;

	/* mss_l4len_id: use 1 as index for TSO */
	mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT;
	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
	mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_SHIFT;

	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
	vlan_macip_lens = skb_network_header_len(skb);
	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
	vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;

	ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
			    type_tucmd, mss_l4len_idx);

	return 1;
2715 2716
}

2717
static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
2718 2719 2720 2721 2722
			    struct sk_buff *skb, u32 tx_flags)
{



2723 2724 2725
	u32 vlan_macip_lens = 0;
	u32 mss_l4len_idx = 0;
	u32 type_tucmd = 0;
2726

2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		u8 l4_hdr = 0;
		switch (skb->protocol) {
		case __constant_htons(ETH_P_IP):
			vlan_macip_lens |= skb_network_header_len(skb);
			type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
			l4_hdr = ip_hdr(skb)->protocol;
			break;
		case __constant_htons(ETH_P_IPV6):
			vlan_macip_lens |= skb_network_header_len(skb);
			l4_hdr = ipv6_hdr(skb)->nexthdr;
			break;
		default:
			if (unlikely(net_ratelimit())) {
				dev_warn(tx_ring->dev,
				 "partial checksum but proto=%x!\n",
				 skb->protocol);
			}
			break;
		}
2747

2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770
		switch (l4_hdr) {
		case IPPROTO_TCP:
			type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_TCP;
			mss_l4len_idx = tcp_hdrlen(skb) <<
					IXGBE_ADVTXD_L4LEN_SHIFT;
			break;
		case IPPROTO_SCTP:
			type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_SCTP;
			mss_l4len_idx = sizeof(struct sctphdr) <<
					IXGBE_ADVTXD_L4LEN_SHIFT;
			break;
		case IPPROTO_UDP:
			mss_l4len_idx = sizeof(struct udphdr) <<
					IXGBE_ADVTXD_L4LEN_SHIFT;
			break;
		default:
			if (unlikely(net_ratelimit())) {
				dev_warn(tx_ring->dev,
				 "partial checksum but l4 proto=%x!\n",
				 l4_hdr);
			}
			break;
		}
2771 2772
	}

2773 2774 2775 2776 2777 2778 2779 2780
	/* vlan_macip_lens: MACLEN, VLAN tag */
	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
	vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;

	ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
			    type_tucmd, mss_l4len_idx);

	return (skb->ip_summed == CHECKSUM_PARTIAL);
2781 2782
}

2783
static int ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
2784 2785 2786 2787 2788 2789
			  struct sk_buff *skb, u32 tx_flags,
			  unsigned int first)
{
	struct ixgbevf_tx_buffer *tx_buffer_info;
	unsigned int len;
	unsigned int total = skb->len;
2790 2791
	unsigned int offset = 0, size;
	int count = 0;
2792 2793
	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
	unsigned int f;
2794
	int i;
2795 2796 2797 2798 2799 2800 2801 2802 2803 2804

	i = tx_ring->next_to_use;

	len = min(skb_headlen(skb), total);
	while (len) {
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
		size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);

		tx_buffer_info->length = size;
		tx_buffer_info->mapped_as_page = false;
2805
		tx_buffer_info->dma = dma_map_single(tx_ring->dev,
2806
						     skb->data + offset,
2807
						     size, DMA_TO_DEVICE);
2808
		if (dma_mapping_error(tx_ring->dev, tx_buffer_info->dma))
2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821
			goto dma_error;
		tx_buffer_info->next_to_watch = i;

		len -= size;
		total -= size;
		offset += size;
		count++;
		i++;
		if (i == tx_ring->count)
			i = 0;
	}

	for (f = 0; f < nr_frags; f++) {
E
Eric Dumazet 已提交
2822
		const struct skb_frag_struct *frag;
2823 2824

		frag = &skb_shinfo(skb)->frags[f];
E
Eric Dumazet 已提交
2825
		len = min((unsigned int)skb_frag_size(frag), total);
2826
		offset = 0;
2827 2828 2829 2830 2831 2832

		while (len) {
			tx_buffer_info = &tx_ring->tx_buffer_info[i];
			size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);

			tx_buffer_info->length = size;
2833
			tx_buffer_info->dma =
2834
				skb_frag_dma_map(tx_ring->dev, frag,
2835
						 offset, size, DMA_TO_DEVICE);
2836 2837
			if (dma_mapping_error(tx_ring->dev,
					      tx_buffer_info->dma))
2838
				goto dma_error;
2839
			tx_buffer_info->mapped_as_page = true;
2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859
			tx_buffer_info->next_to_watch = i;

			len -= size;
			total -= size;
			offset += size;
			count++;
			i++;
			if (i == tx_ring->count)
				i = 0;
		}
		if (total == 0)
			break;
	}

	if (i == 0)
		i = tx_ring->count - 1;
	else
		i = i - 1;
	tx_ring->tx_buffer_info[i].skb = skb;
	tx_ring->tx_buffer_info[first].next_to_watch = i;
2860
	tx_ring->tx_buffer_info[first].time_stamp = jiffies;
2861 2862 2863 2864

	return count;

dma_error:
2865
	dev_err(tx_ring->dev, "TX DMA map failed\n");
2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878

	/* clear timestamp and dma mappings for failed tx_buffer_info map */
	tx_buffer_info->dma = 0;
	tx_buffer_info->next_to_watch = 0;
	count--;

	/* clear timestamp and dma mappings for remaining portion of packet */
	while (count >= 0) {
		count--;
		i--;
		if (i < 0)
			i += tx_ring->count;
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
2879
		ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
2880 2881 2882 2883 2884
	}

	return count;
}

2885
static void ixgbevf_tx_queue(struct ixgbevf_ring *tx_ring, int tx_flags,
2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901
			     int count, u32 paylen, u8 hdr_len)
{
	union ixgbe_adv_tx_desc *tx_desc = NULL;
	struct ixgbevf_tx_buffer *tx_buffer_info;
	u32 olinfo_status = 0, cmd_type_len = 0;
	unsigned int i;

	u32 txd_cmd = IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS | IXGBE_TXD_CMD_IFCS;

	cmd_type_len |= IXGBE_ADVTXD_DTYP_DATA;

	cmd_type_len |= IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT;

	if (tx_flags & IXGBE_TX_FLAGS_VLAN)
		cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE;

2902 2903 2904
	if (tx_flags & IXGBE_TX_FLAGS_CSUM)
		olinfo_status |= IXGBE_ADVTXD_POPTS_TXSM;

2905 2906 2907 2908 2909 2910
	if (tx_flags & IXGBE_TX_FLAGS_TSO) {
		cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE;

		/* use index 1 context for tso */
		olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
		if (tx_flags & IXGBE_TX_FLAGS_IPV4)
2911 2912 2913
			olinfo_status |= IXGBE_ADVTXD_POPTS_IXSM;

	}
2914

2915 2916 2917 2918 2919
	/*
	 * Check Context must be set if Tx switch is enabled, which it
	 * always is for case where virtual functions are running
	 */
	olinfo_status |= IXGBE_ADVTXD_CC;
2920 2921 2922 2923 2924 2925

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

	i = tx_ring->next_to_use;
	while (count--) {
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
2926
		tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940
		tx_desc->read.buffer_addr = cpu_to_le64(tx_buffer_info->dma);
		tx_desc->read.cmd_type_len =
			cpu_to_le32(cmd_type_len | tx_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(txd_cmd);

	tx_ring->next_to_use = i;
}

2941
static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size)
2942
{
2943
	struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev);
2944

2945
	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956
	/* 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 (likely(IXGBE_DESC_UNUSED(tx_ring) < size))
		return -EBUSY;

	/* A reprieve! - use start_queue because it doesn't call schedule */
2957
	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
2958 2959 2960 2961
	++adapter->restart_queue;
	return 0;
}

2962
static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size)
2963 2964 2965
{
	if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size))
		return 0;
2966
	return __ixgbevf_maybe_stop_tx(tx_ring, size);
2967 2968 2969 2970 2971 2972 2973 2974 2975 2976
}

static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbevf_ring *tx_ring;
	unsigned int first;
	unsigned int tx_flags = 0;
	u8 hdr_len = 0;
	int r_idx = 0, tso;
2977 2978 2979 2980
	u16 count = TXD_USE_COUNT(skb_headlen(skb));
#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
	unsigned short f;
#endif
2981
	u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
2982
	if (!dst_mac || is_link_local_ether_addr(dst_mac)) {
2983 2984 2985
		dev_kfree_skb(skb);
		return NETDEV_TX_OK;
	}
2986 2987 2988

	tx_ring = &adapter->tx_ring[r_idx];

2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001
	/*
	 * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD,
	 *       + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD,
	 *       + 2 desc gap to keep tail from touching head,
	 *       + 1 desc for context descriptor,
	 * otherwise try next time
	 */
#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
#else
	count += skb_shinfo(skb)->nr_frags;
#endif
3002
	if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) {
3003 3004 3005 3006
		adapter->tx_busy++;
		return NETDEV_TX_BUSY;
	}

3007
	if (vlan_tx_tag_present(skb)) {
3008 3009 3010 3011 3012 3013 3014 3015 3016
		tx_flags |= vlan_tx_tag_get(skb);
		tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
		tx_flags |= IXGBE_TX_FLAGS_VLAN;
	}

	first = tx_ring->next_to_use;

	if (skb->protocol == htons(ETH_P_IP))
		tx_flags |= IXGBE_TX_FLAGS_IPV4;
3017
	tso = ixgbevf_tso(tx_ring, skb, tx_flags, &hdr_len);
3018 3019 3020 3021 3022 3023
	if (tso < 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (tso)
3024 3025
		tx_flags |= IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_CSUM;
	else if (ixgbevf_tx_csum(tx_ring, skb, tx_flags))
3026 3027
		tx_flags |= IXGBE_TX_FLAGS_CSUM;

3028 3029
	ixgbevf_tx_queue(tx_ring, tx_flags,
			 ixgbevf_tx_map(tx_ring, skb, tx_flags, first),
3030
			 skb->len, hdr_len);
3031 3032 3033 3034 3035 3036 3037 3038 3039
	/*
	 * 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(tx_ring->next_to_use, adapter->hw.hw_addr + tx_ring->tail);
3040

3041
	ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED);
3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064

	return NETDEV_TX_OK;
}

/**
 * ixgbevf_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 ixgbevf_set_mac(struct net_device *netdev, void *p)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	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(hw->mac.addr, addr->sa_data, netdev->addr_len);

3065
	spin_lock_bh(&adapter->mbx_lock);
3066

3067 3068 3069
	if (hw->mac.ops.set_rar)
		hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0);

3070
	spin_unlock_bh(&adapter->mbx_lock);
3071

3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085
	return 0;
}

/**
 * ixgbevf_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 ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
3086 3087
	int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE;

3088 3089
	switch (adapter->hw.api_version) {
	case ixgbe_mbox_api_11:
3090
		max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE;
3091 3092 3093 3094 3095 3096
		break;
	default:
		if (adapter->hw.mac.type == ixgbe_mac_X540_vf)
			max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE;
		break;
	}
3097 3098

	/* MTU < 68 is an error and causes problems on some kernels */
3099
	if ((new_mtu < 68) || (max_frame > max_possible_frame))
3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112
		return -EINVAL;

	hw_dbg(&adapter->hw, "changing MTU from %d to %d\n",
	       netdev->mtu, new_mtu);
	/* must set new MTU before calling down or up */
	netdev->mtu = new_mtu;

	if (netif_running(netdev))
		ixgbevf_reinit_locked(adapter);

	return 0;
}

3113
static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
3114 3115 3116
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
3117 3118 3119
#ifdef CONFIG_PM
	int retval = 0;
#endif
3120 3121 3122 3123

	netif_device_detach(netdev);

	if (netif_running(netdev)) {
3124
		rtnl_lock();
3125 3126 3127 3128
		ixgbevf_down(adapter);
		ixgbevf_free_irq(adapter);
		ixgbevf_free_all_tx_resources(adapter);
		ixgbevf_free_all_rx_resources(adapter);
3129
		rtnl_unlock();
3130 3131
	}

3132
	ixgbevf_clear_interrupt_scheme(adapter);
3133

3134 3135 3136 3137
#ifdef CONFIG_PM
	retval = pci_save_state(pdev);
	if (retval)
		return retval;
3138

3139
#endif
3140
	pci_disable_device(pdev);
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

	return 0;
}

#ifdef CONFIG_PM
static int ixgbevf_resume(struct pci_dev *pdev)
{
	struct ixgbevf_adapter *adapter = pci_get_drvdata(pdev);
	struct net_device *netdev = adapter->netdev;
	u32 err;

	pci_set_power_state(pdev, PCI_D0);
	pci_restore_state(pdev);
	/*
	 * pci_restore_state clears dev->state_saved so call
	 * pci_save_state to restore it.
	 */
	pci_save_state(pdev);

	err = pci_enable_device_mem(pdev);
	if (err) {
		dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
		return err;
	}
	pci_set_master(pdev);

	rtnl_lock();
	err = ixgbevf_init_interrupt_scheme(adapter);
	rtnl_unlock();
	if (err) {
		dev_err(&pdev->dev, "Cannot initialize interrupts\n");
		return err;
	}

	ixgbevf_reset(adapter);

	if (netif_running(netdev)) {
		err = ixgbevf_open(netdev);
		if (err)
			return err;
	}

	netif_device_attach(netdev);

	return err;
}

#endif /* CONFIG_PM */
static void ixgbevf_shutdown(struct pci_dev *pdev)
{
	ixgbevf_suspend(pdev, PMSG_SUSPEND);
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
static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
						struct rtnl_link_stats64 *stats)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	unsigned int start;
	u64 bytes, packets;
	const struct ixgbevf_ring *ring;
	int i;

	ixgbevf_update_stats(adapter);

	stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc;

	for (i = 0; i < adapter->num_rx_queues; i++) {
		ring = &adapter->rx_ring[i];
		do {
			start = u64_stats_fetch_begin_bh(&ring->syncp);
			bytes = ring->total_bytes;
			packets = ring->total_packets;
		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
		stats->rx_bytes += bytes;
		stats->rx_packets += packets;
	}

	for (i = 0; i < adapter->num_tx_queues; i++) {
		ring = &adapter->tx_ring[i];
		do {
			start = u64_stats_fetch_begin_bh(&ring->syncp);
			bytes = ring->total_bytes;
			packets = ring->total_packets;
		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
		stats->tx_bytes += bytes;
		stats->tx_packets += packets;
	}

	return stats;
}

3232
static const struct net_device_ops ixgbevf_netdev_ops = {
3233 3234 3235 3236
	.ndo_open		= ixgbevf_open,
	.ndo_stop		= ixgbevf_close,
	.ndo_start_xmit		= ixgbevf_xmit_frame,
	.ndo_set_rx_mode	= ixgbevf_set_rx_mode,
3237
	.ndo_get_stats64	= ixgbevf_get_stats,
3238
	.ndo_validate_addr	= eth_validate_addr,
3239 3240 3241 3242 3243
	.ndo_set_mac_address	= ixgbevf_set_mac,
	.ndo_change_mtu		= ixgbevf_change_mtu,
	.ndo_tx_timeout		= ixgbevf_tx_timeout,
	.ndo_vlan_rx_add_vid	= ixgbevf_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid	= ixgbevf_vlan_rx_kill_vid,
3244 3245 3246 3247
};

static void ixgbevf_assign_netdev_ops(struct net_device *dev)
{
3248
	dev->netdev_ops = &ixgbevf_netdev_ops;
3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277
	ixgbevf_set_ethtool_ops(dev);
	dev->watchdog_timeo = 5 * HZ;
}

/**
 * ixgbevf_probe - Device Initialization Routine
 * @pdev: PCI device information struct
 * @ent: entry in ixgbevf_pci_tbl
 *
 * Returns 0 on success, negative on failure
 *
 * ixgbevf_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 ixgbevf_probe(struct pci_dev *pdev,
				   const struct pci_device_id *ent)
{
	struct net_device *netdev;
	struct ixgbevf_adapter *adapter = NULL;
	struct ixgbe_hw *hw = NULL;
	const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data];
	static int cards_found;
	int err, pci_using_dac;

	err = pci_enable_device(pdev);
	if (err)
		return err;

3278 3279
	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
	    !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
3280 3281
		pci_using_dac = 1;
	} else {
3282
		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
3283
		if (err) {
3284 3285
			err = dma_set_coherent_mask(&pdev->dev,
						    DMA_BIT_MASK(32));
3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318
			if (err) {
				dev_err(&pdev->dev, "No usable DMA "
					"configuration, aborting\n");
				goto err_dma;
			}
		}
		pci_using_dac = 0;
	}

	err = pci_request_regions(pdev, ixgbevf_driver_name);
	if (err) {
		dev_err(&pdev->dev, "pci_request_regions failed 0x%x\n", err);
		goto err_pci_reg;
	}

	pci_set_master(pdev);

	netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter),
				   MAX_TX_QUEUES);
	if (!netdev) {
		err = -ENOMEM;
		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;
3319
	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342

	/*
	 * call save state here in standalone driver because it relies on
	 * adapter struct to exist, and needs to call netdev_priv
	 */
	pci_save_state(pdev);

	hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
			      pci_resource_len(pdev, 0));
	if (!hw->hw_addr) {
		err = -EIO;
		goto err_ioremap;
	}

	ixgbevf_assign_netdev_ops(netdev);

	adapter->bd_number = cards_found;

	/* Setup hw api */
	memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops));
	hw->mac.type  = ii->mac;

	memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
3343
	       sizeof(struct ixgbe_mbx_operations));
3344 3345 3346

	/* setup the private structure */
	err = ixgbevf_sw_init(adapter);
3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357
	if (err)
		goto err_sw_init;

	/* The HW MAC address was set and/or determined in sw_init */
	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);

	if (!is_valid_ether_addr(netdev->dev_addr)) {
		pr_err("invalid MAC address\n");
		err = -EIO;
		goto err_sw_init;
	}
3358

3359
	netdev->hw_features = NETIF_F_SG |
3360
			   NETIF_F_IP_CSUM |
3361 3362 3363 3364 3365 3366
			   NETIF_F_IPV6_CSUM |
			   NETIF_F_TSO |
			   NETIF_F_TSO6 |
			   NETIF_F_RXCSUM;

	netdev->features = netdev->hw_features |
3367 3368 3369 3370 3371 3372 3373
			   NETIF_F_HW_VLAN_TX |
			   NETIF_F_HW_VLAN_RX |
			   NETIF_F_HW_VLAN_FILTER;

	netdev->vlan_features |= NETIF_F_TSO;
	netdev->vlan_features |= NETIF_F_TSO6;
	netdev->vlan_features |= NETIF_F_IP_CSUM;
3374
	netdev->vlan_features |= NETIF_F_IPV6_CSUM;
3375 3376 3377 3378 3379
	netdev->vlan_features |= NETIF_F_SG;

	if (pci_using_dac)
		netdev->features |= NETIF_F_HIGHDMA;

3380 3381
	netdev->priv_flags |= IFF_UNICAST_FLT;

3382
	init_timer(&adapter->watchdog_timer);
3383
	adapter->watchdog_timer.function = ixgbevf_watchdog;
3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402
	adapter->watchdog_timer.data = (unsigned long)adapter;

	INIT_WORK(&adapter->reset_task, ixgbevf_reset_task);
	INIT_WORK(&adapter->watchdog_task, ixgbevf_watchdog_task);

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

	/* pick up the PCI bus settings for reporting later */
	if (hw->mac.ops.get_bus_info)
		hw->mac.ops.get_bus_info(hw);

	strcpy(netdev->name, "eth%d");

	err = register_netdev(netdev);
	if (err)
		goto err_register;

G
Greg Rose 已提交
3403 3404
	netif_carrier_off(netdev);

3405 3406
	ixgbevf_init_last_counter_stats(adapter);

3407
	/* print the MAC address */
3408
	hw_dbg(hw, "%pM\n", netdev->dev_addr);
3409 3410 3411 3412 3413 3414 3415 3416

	hw_dbg(hw, "MAC: %d\n", hw->mac.type);

	hw_dbg(hw, "Intel(R) 82599 Virtual Function\n");
	cards_found++;
	return 0;

err_register:
3417
	ixgbevf_clear_interrupt_scheme(adapter);
3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448
err_sw_init:
	ixgbevf_reset_interrupt_capability(adapter);
	iounmap(hw->hw_addr);
err_ioremap:
	free_netdev(netdev);
err_alloc_etherdev:
	pci_release_regions(pdev);
err_pci_reg:
err_dma:
	pci_disable_device(pdev);
	return err;
}

/**
 * ixgbevf_remove - Device Removal Routine
 * @pdev: PCI device information struct
 *
 * ixgbevf_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 ixgbevf_remove(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	set_bit(__IXGBEVF_DOWN, &adapter->state);

	del_timer_sync(&adapter->watchdog_timer);

3449
	cancel_work_sync(&adapter->reset_task);
3450 3451
	cancel_work_sync(&adapter->watchdog_task);

3452
	if (netdev->reg_state == NETREG_REGISTERED)
3453 3454
		unregister_netdev(netdev);

3455
	ixgbevf_clear_interrupt_scheme(adapter);
3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470
	ixgbevf_reset_interrupt_capability(adapter);

	iounmap(adapter->hw.hw_addr);
	pci_release_regions(pdev);

	hw_dbg(&adapter->hw, "Remove complete\n");

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

	free_netdev(netdev);

	pci_disable_device(pdev);
}

3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543
/**
 * ixgbevf_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 ixgbevf_io_error_detected(struct pci_dev *pdev,
						  pci_channel_state_t state)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	netif_device_detach(netdev);

	if (state == pci_channel_io_perm_failure)
		return PCI_ERS_RESULT_DISCONNECT;

	if (netif_running(netdev))
		ixgbevf_down(adapter);

	pci_disable_device(pdev);

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

/**
 * ixgbevf_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 ixgbevf_resume routine.
 */
static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	if (pci_enable_device_mem(pdev)) {
		dev_err(&pdev->dev,
			"Cannot re-enable PCI device after reset.\n");
		return PCI_ERS_RESULT_DISCONNECT;
	}

	pci_set_master(pdev);

	ixgbevf_reset(adapter);

	return PCI_ERS_RESULT_RECOVERED;
}

/**
 * ixgbevf_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 ixgbevf_resume routine.
 */
static void ixgbevf_io_resume(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	if (netif_running(netdev))
		ixgbevf_up(adapter);

	netif_device_attach(netdev);
}

/* PCI Error Recovery (ERS) */
3544
static const struct pci_error_handlers ixgbevf_err_handler = {
3545 3546 3547 3548 3549
	.error_detected = ixgbevf_io_error_detected,
	.slot_reset = ixgbevf_io_slot_reset,
	.resume = ixgbevf_io_resume,
};

3550 3551 3552 3553 3554
static struct pci_driver ixgbevf_driver = {
	.name     = ixgbevf_driver_name,
	.id_table = ixgbevf_pci_tbl,
	.probe    = ixgbevf_probe,
	.remove   = __devexit_p(ixgbevf_remove),
3555 3556 3557 3558 3559
#ifdef CONFIG_PM
	/* Power Management Hooks */
	.suspend  = ixgbevf_suspend,
	.resume   = ixgbevf_resume,
#endif
3560
	.shutdown = ixgbevf_shutdown,
3561
	.err_handler = &ixgbevf_err_handler
3562 3563 3564
};

/**
3565
 * ixgbevf_init_module - Driver Registration Routine
3566
 *
3567
 * ixgbevf_init_module is the first routine called when the driver is
3568 3569 3570 3571 3572
 * loaded. All it does is register with the PCI subsystem.
 **/
static int __init ixgbevf_init_module(void)
{
	int ret;
3573 3574
	pr_info("%s - version %s\n", ixgbevf_driver_string,
		ixgbevf_driver_version);
3575

3576
	pr_info("%s\n", ixgbevf_copyright);
3577 3578 3579 3580 3581 3582 3583 3584

	ret = pci_register_driver(&ixgbevf_driver);
	return ret;
}

module_init(ixgbevf_init_module);

/**
3585
 * ixgbevf_exit_module - Driver Exit Cleanup Routine
3586
 *
3587
 * ixgbevf_exit_module is called just before the driver is removed
3588 3589 3590 3591 3592 3593 3594 3595 3596
 * from memory.
 **/
static void __exit ixgbevf_exit_module(void)
{
	pci_unregister_driver(&ixgbevf_driver);
}

#ifdef DEBUG
/**
3597
 * ixgbevf_get_hw_dev_name - return device name string
3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609
 * used by hardware layer to print debugging information
 **/
char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw)
{
	struct ixgbevf_adapter *adapter = hw->back;
	return adapter->netdev->name;
}

#endif
module_exit(ixgbevf_exit_module);

/* ixgbevf_main.c */