ixgbevf_main.c 92.1 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 45
#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>
#include <linux/ipv6.h>
46
#include <linux/slab.h>
47 48 49
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
50
#include <linux/if.h>
51
#include <linux/if_vlan.h>
52
#include <linux/prefetch.h>
53 54 55

#include "ixgbevf.h"

56
const char ixgbevf_driver_name[] = "ixgbevf";
57
static const char ixgbevf_driver_string[] =
G
Greg Rose 已提交
58
	"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
59

G
Greg Rose 已提交
60
#define DRV_VERSION "2.6.0-k"
61
const char ixgbevf_driver_version[] = DRV_VERSION;
62
static char ixgbevf_copyright[] =
G
Greg Rose 已提交
63
	"Copyright (c) 2009 - 2012 Intel Corporation.";
64 65

static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
66 67
	[board_82599_vf] = &ixgbevf_82599_vf_info,
	[board_X540_vf]  = &ixgbevf_X540_vf_info,
68 69 70 71 72 73 74 75 76 77 78 79 80
};

/* 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},
81 82
	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540_VF),
	board_X540_vf},
83 84 85 86 87 88 89 90 91 92 93

	/* 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);

94 95 96 97
#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)");
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117

/* forward decls */
static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector);
static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx,
			       u32 itr_reg);

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
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
 * @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);
	}
}

static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter,
					       struct ixgbevf_tx_buffer
					       *tx_buffer_info)
{
	if (tx_buffer_info->dma) {
		if (tx_buffer_info->mapped_as_page)
155
			dma_unmap_page(&adapter->pdev->dev,
156 157
				       tx_buffer_info->dma,
				       tx_buffer_info->length,
158
				       DMA_TO_DEVICE);
159
		else
160
			dma_unmap_single(&adapter->pdev->dev,
161 162
					 tx_buffer_info->dma,
					 tx_buffer_info->length,
163
					 DMA_TO_DEVICE);
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
		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 */
#define TXD_USE_COUNT(S) (((S) >> IXGBE_MAX_TXD_PWR) + \
			 (((S) & (IXGBE_MAX_DATA_PER_TXD - 1)) ? 1 : 0))
#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \
	MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1)      /* for context */

static void ixgbevf_tx_timeout(struct net_device *netdev);

/**
 * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes
 * @adapter: board private structure
 * @tx_ring: tx ring to clean
 **/
static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter,
				 struct ixgbevf_ring *tx_ring)
{
	struct net_device *netdev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	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;

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

	while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
	       (count < tx_ring->work_limit)) {
		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;
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
		for ( ; !cleaned; count++) {
			struct sk_buff *skb;
			tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
			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;
			}

			ixgbevf_unmap_and_free_tx_resource(adapter,
							   tx_buffer_info);

			tx_desc->wb.status = 0;

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

240
cont_loop:
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266
		eop = tx_ring->tx_buffer_info[i].next_to_watch;
		eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
	}

	tx_ring->next_to_clean = i;

#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
	if (unlikely(count && netif_carrier_ok(netdev) &&
		     (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();
		if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
		    !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
			netif_wake_subqueue(netdev, tx_ring->queue_index);
			++adapter->restart_queue;
		}
	}

	/* re-arm the interrupt */
	if ((count >= tx_ring->work_limit) &&
	    (!test_bit(__IXGBEVF_DOWN, &adapter->state))) {
		IXGBE_WRITE_REG(hw, IXGBE_VTEICS, tx_ring->v_idx);
	}

267
	u64_stats_update_begin(&tx_ring->syncp);
268 269
	tx_ring->total_bytes += total_bytes;
	tx_ring->total_packets += total_packets;
270
	u64_stats_update_end(&tx_ring->syncp);
271

272
	return count < tx_ring->work_limit;
273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
}

/**
 * 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_ring: rx descriptor ring (for a specific queue) to setup
 * @rx_desc: rx descriptor
 **/
static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
				struct sk_buff *skb, u8 status,
				struct ixgbevf_ring *ring,
				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
290
	u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan);
291

G
Greg Rose 已提交
292
	if (is_vlan && test_bit(tag, adapter->active_vlans))
J
Jiri Pirko 已提交
293 294
		__vlan_hwaccel_put_tag(skb, tag);

295
	napi_gro_receive(&q_vector->napi, skb);
296 297 298 299 300 301 302 303 304 305 306
}

/**
 * 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,
				       u32 status_err, struct sk_buff *skb)
{
307
	skb_checksum_none_assert(skb);
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372

	/* Rx csum disabled */
	if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED))
		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;
	unsigned int i;
	unsigned int bufsz = rx_ring->rx_buf_len + NET_IP_ALIGN;

	i = rx_ring->next_to_use;
	bi = &rx_ring->rx_buffer_info[i];

	while (cleaned_count--) {
		rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
		skb = bi->skb;
		if (!skb) {
			skb = netdev_alloc_skb(adapter->netdev,
							       bufsz);

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

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

			bi->skb = skb;
		}
		if (!bi->dma) {
373
			bi->dma = dma_map_single(&pdev->dev, skb->data,
374
						 rx_ring->rx_buf_len,
375
						 DMA_FROM_DEVICE);
376
		}
377
		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429

		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;
		if (i-- == 0)
			i = (rx_ring->count - 1);

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

static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
					     u64 qmask)
{
	u32 mask;
	struct ixgbe_hw *hw = &adapter->hw;

	mask = (qmask & 0xFFFFFFFF);
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask);
}

static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
				 struct ixgbevf_ring *rx_ring,
				 int *work_done, int work_to_do)
{
	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;
	bool cleaned = false;
	int cleaned_count = 0;
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;

	i = rx_ring->next_to_clean;
	rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
	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) {
		if (*work_done >= work_to_do)
			break;
		(*work_done)++;

430
		rmb(); /* read descriptor and rx_buffer_info after status DD */
431
		len = le16_to_cpu(rx_desc->wb.upper.length);
432 433 434 435 436 437
		cleaned = true;
		skb = rx_buffer_info->skb;
		prefetch(skb->data - NET_IP_ALIGN);
		rx_buffer_info->skb = NULL;

		if (rx_buffer_info->dma) {
438
			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
439
					 rx_ring->rx_buf_len,
440
					 DMA_FROM_DEVICE);
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455
			rx_buffer_info->dma = 0;
			skb_put(skb, len);
		}

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

		next_rxd = IXGBE_RX_DESC_ADV(*rx_ring, i);
		prefetch(next_rxd);
		cleaned_count++;

		next_buffer = &rx_ring->rx_buffer_info[i];

		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
456 457
			skb->next = next_buffer->skb;
			skb->next->prev = skb;
458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478
			adapter->non_eop_descs++;
			goto next_desc;
		}

		/* 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;
		}

		ixgbevf_rx_checksum(adapter, staterr, skb);

		/* 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
479
			u32 header_fixup_len = skb_headlen(skb);
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509
			if (header_fixup_len < 14)
				skb_push(skb, header_fixup_len);
		}
		skb->protocol = eth_type_trans(skb, adapter->netdev);

		ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);

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);

510
	u64_stats_update_begin(&rx_ring->syncp);
511 512
	rx_ring->total_packets += total_rx_packets;
	rx_ring->total_bytes += total_rx_bytes;
513
	u64_stats_update_end(&rx_ring->syncp);
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620

	return cleaned;
}

/**
 * ixgbevf_clean_rxonly - msix (aka one shot) rx clean routine
 * @napi: napi struct with our devices info in it
 * @budget: amount of work driver is allowed to do this pass, in packets
 *
 * This function is optimized for cleaning one queue only on a single
 * q_vector!!!
 **/
static int ixgbevf_clean_rxonly(struct napi_struct *napi, int budget)
{
	struct ixgbevf_q_vector *q_vector =
		container_of(napi, struct ixgbevf_q_vector, napi);
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	struct ixgbevf_ring *rx_ring = NULL;
	int work_done = 0;
	long r_idx;

	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	rx_ring = &(adapter->rx_ring[r_idx]);

	ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget);

	/* If all Rx work done, exit the polling mode */
	if (work_done < budget) {
		napi_complete(napi);
		if (adapter->itr_setting & 1)
			ixgbevf_set_itr_msix(q_vector);
		if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
			ixgbevf_irq_enable_queues(adapter, rx_ring->v_idx);
	}

	return work_done;
}

/**
 * ixgbevf_clean_rxonly_many - msix (aka one shot) rx clean routine
 * @napi: napi struct with our devices info in it
 * @budget: amount of work driver is allowed to do this pass, in packets
 *
 * This function will clean more than one rx queue associated with a
 * q_vector.
 **/
static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget)
{
	struct ixgbevf_q_vector *q_vector =
		container_of(napi, struct ixgbevf_q_vector, napi);
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	struct ixgbevf_ring *rx_ring = NULL;
	int work_done = 0, i;
	long r_idx;
	u64 enable_mask = 0;

	/* attempt to distribute budget to each queue fairly, but don't allow
	 * the budget to go below 1 because we'll exit polling */
	budget /= (q_vector->rxr_count ?: 1);
	budget = max(budget, 1);
	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	for (i = 0; i < q_vector->rxr_count; i++) {
		rx_ring = &(adapter->rx_ring[r_idx]);
		ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget);
		enable_mask |= rx_ring->v_idx;
		r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
				      r_idx + 1);
	}

	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	rx_ring = &(adapter->rx_ring[r_idx]);

	/* If all Rx work done, exit the polling mode */
	if (work_done < budget) {
		napi_complete(napi);
		if (adapter->itr_setting & 1)
			ixgbevf_set_itr_msix(q_vector);
		if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
			ixgbevf_irq_enable_queues(adapter, enable_mask);
	}

	return work_done;
}


/**
 * 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;
	struct ixgbe_hw *hw = &adapter->hw;
	int i, j, q_vectors, v_idx, r_idx;
	u32 mask;

	q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

	/*
	 * Populate the IVAR table and set the ITR values to the
	 * corresponding register.
	 */
	for (v_idx = 0; v_idx < q_vectors; v_idx++) {
		q_vector = adapter->q_vector[v_idx];
621
		/* XXX for_each_set_bit(...) */
622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823
		r_idx = find_first_bit(q_vector->rxr_idx,
				       adapter->num_rx_queues);

		for (i = 0; i < q_vector->rxr_count; i++) {
			j = adapter->rx_ring[r_idx].reg_idx;
			ixgbevf_set_ivar(adapter, 0, j, v_idx);
			r_idx = find_next_bit(q_vector->rxr_idx,
					      adapter->num_rx_queues,
					      r_idx + 1);
		}
		r_idx = find_first_bit(q_vector->txr_idx,
				       adapter->num_tx_queues);

		for (i = 0; i < q_vector->txr_count; i++) {
			j = adapter->tx_ring[r_idx].reg_idx;
			ixgbevf_set_ivar(adapter, 1, j, v_idx);
			r_idx = find_next_bit(q_vector->txr_idx,
					      adapter->num_tx_queues,
					      r_idx + 1);
		}

		/* if this is a tx only vector halve the interrupt rate */
		if (q_vector->txr_count && !q_vector->rxr_count)
			q_vector->eitr = (adapter->eitr_param >> 1);
		else if (q_vector->rxr_count)
			/* rx only */
			q_vector->eitr = adapter->eitr_param;

		ixgbevf_write_eitr(adapter, v_idx, q_vector->eitr);
	}

	ixgbevf_set_ivar(adapter, -1, 1, v_idx);

	/* set up to autoclear timer, and the vectors */
	mask = IXGBE_EIMS_ENABLE_MASK;
	mask &= ~IXGBE_EIMS_OTHER;
	IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, mask);
}

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
 * @adapter: pointer to adapter
 * @eitr: eitr setting (ints per sec) to give last timeslice
 * @itr_setting: current throttle rate in ints/second
 * @packets: the number of packets during this measurement interval
 * @bytes: the number of bytes during this measurement interval
 *
 *      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.
 **/
static u8 ixgbevf_update_itr(struct ixgbevf_adapter *adapter,
			     u32 eitr, u8 itr_setting,
			     int packets, int bytes)
{
	unsigned int retval = itr_setting;
	u32 timepassed_us;
	u64 bytes_perint;

	if (packets == 0)
		goto update_itr_done;


	/* 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? */
	timepassed_us = 1000000/eitr;
	bytes_perint = bytes / timepassed_us; /* bytes/usec */

	switch (itr_setting) {
	case lowest_latency:
		if (bytes_perint > adapter->eitr_low)
			retval = low_latency;
		break;
	case low_latency:
		if (bytes_perint > adapter->eitr_high)
			retval = bulk_latency;
		else if (bytes_perint <= adapter->eitr_low)
			retval = lowest_latency;
		break;
	case bulk_latency:
		if (bytes_perint <= adapter->eitr_high)
			retval = low_latency;
		break;
	}

update_itr_done:
	return retval;
}

/**
 * ixgbevf_write_eitr - write VTEITR register in hardware specific way
 * @adapter: pointer to adapter struct
 * @v_idx: vector index into q_vector array
 * @itr_reg: new value to be written in *register* format, not ints/s
 *
 * This function is made to be called by ethtool and by the driver
 * when it needs to update VTEITR registers at runtime.  Hardware
 * specific quirks/differences are taken care of here.
 */
static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx,
			       u32 itr_reg)
{
	struct ixgbe_hw *hw = &adapter->hw;

	itr_reg = EITR_INTS_PER_SEC_TO_REG(itr_reg);

	/*
	 * 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);
}

static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector)
{
	struct ixgbevf_adapter *adapter = q_vector->adapter;
	u32 new_itr;
	u8 current_itr, ret_itr;
	int i, r_idx, v_idx = q_vector->v_idx;
	struct ixgbevf_ring *rx_ring, *tx_ring;

	r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
	for (i = 0; i < q_vector->txr_count; i++) {
		tx_ring = &(adapter->tx_ring[r_idx]);
		ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr,
					     q_vector->tx_itr,
					     tx_ring->total_packets,
					     tx_ring->total_bytes);
		/* if the result for this queue would decrease interrupt
		 * rate for this vector then use that result */
		q_vector->tx_itr = ((q_vector->tx_itr > ret_itr) ?
				    q_vector->tx_itr - 1 : ret_itr);
		r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
				      r_idx + 1);
	}

	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	for (i = 0; i < q_vector->rxr_count; i++) {
		rx_ring = &(adapter->rx_ring[r_idx]);
		ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr,
					     q_vector->rx_itr,
					     rx_ring->total_packets,
					     rx_ring->total_bytes);
		/* if the result for this queue would decrease interrupt
		 * rate for this vector then use that result */
		q_vector->rx_itr = ((q_vector->rx_itr > ret_itr) ?
				    q_vector->rx_itr - 1 : ret_itr);
		r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
				      r_idx + 1);
	}

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

	switch (current_itr) {
	/* counts and packets in update_itr are dependent on these numbers */
	case lowest_latency:
		new_itr = 100000;
		break;
	case low_latency:
		new_itr = 20000; /* aka hwitr = ~200 */
		break;
	case bulk_latency:
	default:
		new_itr = 8000;
		break;
	}

	if (new_itr != q_vector->eitr) {
		u32 itr_reg;

		/* save the algorithm value here, not the smoothed one */
		q_vector->eitr = new_itr;
		/* do an exponential smoothing */
		new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
		itr_reg = EITR_INTS_PER_SEC_TO_REG(new_itr);
		ixgbevf_write_eitr(adapter, v_idx, itr_reg);
	}
}

static irqreturn_t ixgbevf_msix_mbx(int irq, void *data)
{
	struct net_device *netdev = data;
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	u32 eicr;
824
	u32 msg;
825
	bool got_ack = false;
826 827 828 829

	eicr = IXGBE_READ_REG(hw, IXGBE_VTEICS);
	IXGBE_WRITE_REG(hw, IXGBE_VTEICR, eicr);

830 831
	if (!hw->mbx.ops.check_for_ack(hw))
		got_ack = true;
832

833 834
	if (!hw->mbx.ops.check_for_msg(hw)) {
		hw->mbx.ops.read(hw, &msg, 1);
835

836 837 838
		if ((msg & IXGBE_MBVFICR_VFREQ_MASK) == IXGBE_PF_CONTROL_MSG)
			mod_timer(&adapter->watchdog_timer,
				  round_jiffies(jiffies + 1));
839

840 841 842
		if (msg & IXGBE_VT_MSGTYPE_NACK)
			pr_warn("Last Request of type %2.2x to PF Nacked\n",
				msg & 0xFF);
843 844 845 846 847
		/*
		 * Restore the PFSTS bit in case someone is polling for a
		 * return message from the PF
		 */
		hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFSTS;
848 849 850 851 852 853 854 855 856
	}

	/*
	 * checking for the ack clears the PFACK bit.  Place
	 * it back in the v2p_mailbox cache so that anyone
	 * polling for an ack will not miss it
	 */
	if (got_ack)
		hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFACK;
857

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887
	return IRQ_HANDLED;
}

static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data)
{
	struct ixgbevf_q_vector *q_vector = data;
	struct ixgbevf_adapter  *adapter = q_vector->adapter;
	struct ixgbevf_ring     *tx_ring;
	int i, r_idx;

	if (!q_vector->txr_count)
		return IRQ_HANDLED;

	r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
	for (i = 0; i < q_vector->txr_count; i++) {
		tx_ring = &(adapter->tx_ring[r_idx]);
		tx_ring->total_bytes = 0;
		tx_ring->total_packets = 0;
		ixgbevf_clean_tx_irq(adapter, tx_ring);
		r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
				      r_idx + 1);
	}

	if (adapter->itr_setting & 1)
		ixgbevf_set_itr_msix(q_vector);

	return IRQ_HANDLED;
}

/**
888
 * ixgbevf_msix_clean_rx - single unshared vector rx clean (all queues)
889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 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 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
 * @irq: unused
 * @data: pointer to our q_vector struct for this interrupt vector
 **/
static irqreturn_t ixgbevf_msix_clean_rx(int irq, void *data)
{
	struct ixgbevf_q_vector *q_vector = data;
	struct ixgbevf_adapter  *adapter = q_vector->adapter;
	struct ixgbe_hw *hw = &adapter->hw;
	struct ixgbevf_ring  *rx_ring;
	int r_idx;
	int i;

	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	for (i = 0; i < q_vector->rxr_count; i++) {
		rx_ring = &(adapter->rx_ring[r_idx]);
		rx_ring->total_bytes = 0;
		rx_ring->total_packets = 0;
		r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
				      r_idx + 1);
	}

	if (!q_vector->rxr_count)
		return IRQ_HANDLED;

	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
	rx_ring = &(adapter->rx_ring[r_idx]);
	/* disable interrupts on this vector only */
	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, rx_ring->v_idx);
	napi_schedule(&q_vector->napi);


	return IRQ_HANDLED;
}

static irqreturn_t ixgbevf_msix_clean_many(int irq, void *data)
{
	ixgbevf_msix_clean_rx(irq, data);
	ixgbevf_msix_clean_tx(irq, data);

	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];

	set_bit(r_idx, q_vector->rxr_idx);
	q_vector->rxr_count++;
	a->rx_ring[r_idx].v_idx = 1 << v_idx;
}

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];

	set_bit(t_idx, q_vector->txr_idx);
	q_vector->txr_count++;
	a->tx_ring[t_idx].v_idx = 1 << v_idx;
}

/**
 * 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;
	irqreturn_t (*handler)(int, void *);
	int i, vector, q_vectors, err;
	int ri = 0, ti = 0;

	/* Decrement for Other and TCP Timer vectors */
	q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;

#define SET_HANDLER(_v) (((_v)->rxr_count && (_v)->txr_count)          \
					  ? &ixgbevf_msix_clean_many : \
			  (_v)->rxr_count ? &ixgbevf_msix_clean_rx   : \
			  (_v)->txr_count ? &ixgbevf_msix_clean_tx   : \
			  NULL)
	for (vector = 0; vector < q_vectors; vector++) {
		handler = SET_HANDLER(adapter->q_vector[vector]);

		if (handler == &ixgbevf_msix_clean_rx) {
			sprintf(adapter->name[vector], "%s-%s-%d",
				netdev->name, "rx", ri++);
		} else if (handler == &ixgbevf_msix_clean_tx) {
			sprintf(adapter->name[vector], "%s-%s-%d",
				netdev->name, "tx", ti++);
		} else if (handler == &ixgbevf_msix_clean_many) {
			sprintf(adapter->name[vector], "%s-%s-%d",
				netdev->name, "TxRx", vector);
		} else {
			/* skip this unused q_vector */
			continue;
		}
		err = request_irq(adapter->msix_entries[vector].vector,
				  handler, 0, adapter->name[vector],
				  adapter->q_vector[vector]);
		if (err) {
			hw_dbg(&adapter->hw,
			       "request_irq failed for MSIX interrupt "
			       "Error: %d\n", err);
			goto free_queue_irqs;
		}
	}

	sprintf(adapter->name[vector], "%s:mbx", netdev->name);
	err = request_irq(adapter->msix_entries[vector].vector,
			  &ixgbevf_msix_mbx, 0, adapter->name[vector], netdev);
	if (err) {
		hw_dbg(&adapter->hw,
		       "request_irq for msix_mbx failed: %d\n", err);
		goto free_queue_irqs;
	}

	return 0;

free_queue_irqs:
	for (i = vector - 1; i >= 0; i--)
		free_irq(adapter->msix_entries[--vector].vector,
			 &(adapter->q_vector[i]));
	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];
		bitmap_zero(q_vector->rxr_idx, MAX_RX_QUEUES);
		bitmap_zero(q_vector->txr_idx, MAX_TX_QUEUES);
		q_vector->rxr_count = 0;
		q_vector->txr_count = 0;
		q_vector->eitr = adapter->eitr_param;
	}
}

/**
 * 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)
{
	struct net_device *netdev = adapter->netdev;
	int i, q_vectors;

	q_vectors = adapter->num_msix_vectors;

	i = q_vectors - 1;

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

	for (; i >= 0; i--) {
		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)
{
	int i;
	struct ixgbe_hw *hw = &adapter->hw;

	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0);

	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
 **/
static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter,
				      bool queues, bool flush)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 mask;
	u64 qmask;

	mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);
	qmask = ~0;

	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask);

	if (queues)
		ixgbevf_irq_enable_queues(adapter, qmask);

	if (flush)
		IXGBE_WRITE_FLUSH(hw);
}

/**
 * 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;

1225
	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
1226

1227 1228 1229 1230 1231 1232
	if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE)
		srrctl |= IXGBEVF_RXBUFFER_2048 >>
			IXGBE_SRRCTL_BSIZEPKT_SHIFT;
	else
		srrctl |= rx_ring->rx_buf_len >>
			IXGBE_SRRCTL_BSIZEPKT_SHIFT;
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
	IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
}

/**
 * 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;
	struct net_device *netdev = adapter->netdev;
	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	int i, j;
	u32 rdlen;
	int rx_buf_len;

1252 1253 1254 1255 1256 1257
	/* PSRTYPE must be initialized in 82599 */
	IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
	if (netdev->mtu <= ETH_DATA_LEN)
		rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
	else
		rx_buf_len = ALIGN(max_frame, 1024);
1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278

	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);
		adapter->rx_ring[i].rx_buf_len = rx_buf_len;

		ixgbevf_configure_srrctl(adapter, j);
	}
}

1279
static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
1280 1281 1282 1283 1284 1285 1286
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

	/* add VID to filter table */
	if (hw->mac.ops.set_vfta)
		hw->mac.ops.set_vfta(hw, vid, 0, true);
J
Jiri Pirko 已提交
1287
	set_bit(vid, adapter->active_vlans);
1288 1289

	return 0;
1290 1291
}

1292
static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
1293 1294 1295 1296 1297 1298 1299
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

	/* remove VID from filter table */
	if (hw->mac.ops.set_vfta)
		hw->mac.ops.set_vfta(hw, vid, 0, false);
J
Jiri Pirko 已提交
1300
	clear_bit(vid, adapter->active_vlans);
1301 1302

	return 0;
1303 1304 1305 1306
}

static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
{
J
Jiri Pirko 已提交
1307
	u16 vid;
1308

J
Jiri Pirko 已提交
1309 1310
	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
		ixgbevf_vlan_rx_add_vid(adapter->netdev, vid);
1311 1312
}

1313 1314 1315 1316 1317 1318 1319
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) {
1320
		pr_err("Too many unicast filters - No Space\n");
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340
		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;
}

1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355
/**
 * 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;

	/* reprogram multicast list */
	if (hw->mac.ops.update_mc_addr_list)
1356
		hw->mac.ops.update_mc_addr_list(hw, netdev);
1357 1358

	ixgbevf_write_uc_addr_list(netdev);
1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435
}

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++) {
		struct napi_struct *napi;
		q_vector = adapter->q_vector[q_idx];
		if (!q_vector->rxr_count)
			continue;
		napi = &q_vector->napi;
		if (q_vector->rxr_count > 1)
			napi->poll = &ixgbevf_clean_rxonly_many;

		napi_enable(napi);
	}
}

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];
		if (!q_vector->rxr_count)
			continue;
		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];
		ixgbevf_alloc_rx_buffers(adapter, ring, ring->count);
		ring->next_to_use = ring->count - 1;
		writel(ring->next_to_use, adapter->hw.hw_addr + ring->tail);
	}
}

#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));
}

1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473
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;
}

1474
static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
1475 1476 1477 1478 1479 1480
{
	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;
1481
	u32 msg[2];
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500

	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
1501
		rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME;
1502 1503 1504 1505 1506
		if (hw->mac.type == ixgbe_mac_X540_vf) {
			rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
			rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) |
				   IXGBE_RXDCTL_RLPML_EN);
		}
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519
		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl);
		ixgbevf_rx_desc_queue_enable(adapter, i);
	}

	ixgbevf_configure_msix(adapter);

	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);
	}

1520 1521 1522 1523
	msg[0] = IXGBE_VF_SET_LPE;
	msg[1] = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
	hw->mbx.ops.write_posted(hw, msg, 2);

1524 1525 1526 1527 1528 1529
	clear_bit(__IXGBEVF_DOWN, &adapter->state);
	ixgbevf_napi_enable_all(adapter);

	/* enable transmits */
	netif_tx_start_all_queues(netdev);

1530 1531 1532
	ixgbevf_save_reset_stats(adapter);
	ixgbevf_init_last_counter_stats(adapter);

1533 1534 1535
	mod_timer(&adapter->watchdog_timer, jiffies);
}

1536
void ixgbevf_up(struct ixgbevf_adapter *adapter)
1537 1538 1539 1540 1541
{
	struct ixgbe_hw *hw = &adapter->hw;

	ixgbevf_configure(adapter);

1542
	ixgbevf_up_complete(adapter);
1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561

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

	ixgbevf_irq_enable(adapter, true, true);
}

/**
 * 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
1562 1563
	if (!rx_ring->rx_buffer_info)
		return;
1564

G
Greg Rose 已提交
1565
	/* Free all the Rx ring sk_buffs */
1566 1567 1568 1569 1570
	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) {
1571
			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
1572
					 rx_ring->rx_buf_len,
1573
					 DMA_FROM_DEVICE);
1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613
			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;
				skb = skb->prev;
				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
1614 1615 1616
	if (!tx_ring->tx_buffer_info)
		return;

1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708
	/* Free all the Tx ring sk_buffs */

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

	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)
{
G
Greg Rose 已提交
1709 1710
	struct ixgbe_hw *hw = &adapter->hw;

1711
	WARN_ON(in_interrupt());
G
Greg Rose 已提交
1712

1713 1714 1715
	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
		msleep(1);

G
Greg Rose 已提交
1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726
	/*
	 * 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.
	 */
	if (!hw->mac.ops.reset_hw(hw)) {
		ixgbevf_down(adapter);
		ixgbevf_up(adapter);
	}
1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795

	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;

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

	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);
	}
}

static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
					 int vectors)
{
	int err, vector_threshold;

	/* We'll want at least 3 (vector_threshold):
	 * 1) TxQ[0] Cleanup
	 * 2) RxQ[0] Cleanup
	 * 3) Other (Link Status Change, etc.)
	 */
	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);
		if (!err) /* Success in acquiring all requested vectors. */
			break;
		else if (err < 0)
			vectors = 0; /* Nasty failure, quit now */
		else /* err == number of vectors we should try again with */
			vectors = err;
	}

	if (vectors < vector_threshold) {
		/* Can't allocate enough MSI-X interrupts?  Oh well.
		 * This just means we'll go with either a single MSI
		 * vector or fall back to legacy interrupts.
		 */
		hw_dbg(&adapter->hw,
		       "Unable to allocate MSI-X interrupts\n");
		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;
	}
}

1796 1797
/**
 * ixgbevf_set_num_queues - Allocate queues for device, feature dependent
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 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 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004
 * @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;
		adapter->tx_ring[i].reg_idx = i;
	}

	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;
	}

	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)
{
	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
	 * (roughly) twice the number of vectors as there are CPU's.
	 */
	v_budget = min(adapter->num_rx_queues + adapter->num_tx_queues,
		       (int)(num_online_cpus() * 2)) + NON_Q_VECTORS;

	/* 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;

	ixgbevf_acquire_msix_vectors(adapter, v_budget);

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;
	int napi_vectors;
	int (*poll)(struct napi_struct *, int);

	num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
	napi_vectors = adapter->num_rx_queues;
	poll = &ixgbevf_clean_rxonly;

	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;
		q_vector->eitr = adapter->eitr_param;
		if (q_idx < napi_vectors)
			netif_napi_add(adapter->netdev, &q_vector->napi,
				       (*poll), 64);
		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)
{
	int q_idx, num_q_vectors;
	int napi_vectors;

	num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
	napi_vectors = adapter->num_rx_queues;

	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;
		if (q_idx < napi_vectors)
			netif_napi_del(&q_vector->napi);
		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) {
2005
		pr_err("Unable to allocate memory for queues\n");
2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043
		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;
}

/**
 * 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;
2044
	hw->revision_id = pdev->revision;
2045 2046 2047 2048 2049 2050 2051 2052 2053 2054
	hw->subsystem_vendor_id = pdev->subsystem_vendor;
	hw->subsystem_device_id = pdev->subsystem_device;

	hw->mbx.ops.init_params(hw);
	hw->mac.max_tx_queues = MAX_TX_QUEUES;
	hw->mac.max_rx_queues = MAX_RX_QUEUES;
	err = hw->mac.ops.reset_hw(hw);
	if (err) {
		dev_info(&pdev->dev,
		         "PF still in reset state, assigning new address\n");
2055 2056 2057
		eth_hw_addr_random(adapter->netdev);
		memcpy(adapter->hw.mac.addr, adapter->netdev->dev_addr,
			adapter->netdev->addr_len);
2058 2059 2060
	} else {
		err = hw->mac.ops.init_hw(hw);
		if (err) {
2061
			pr_err("init_shared_code failed: %d\n", err);
2062 2063
			goto out;
		}
2064 2065
		memcpy(adapter->netdev->dev_addr, adapter->hw.mac.addr,
			adapter->netdev->addr_len);
2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083
	}

	/* Enable dynamic interrupt throttling rates */
	adapter->eitr_param = 20000;
	adapter->itr_setting = 1;

	/* set defaults for eitr in MegaBytes */
	adapter->eitr_low = 10;
	adapter->eitr_high = 20;

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

	/* enable rx csum by default */
	adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED;

	set_bit(__IXGBEVF_DOWN, &adapter->state);
2084
	return 0;
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 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217

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;
	u64 eics = 0;
	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];
		if (qv->rxr_count || qv->txr_count)
			eics |= (1 << i);
	}

	IXGBE_WRITE_REG(hw, IXGBE_VTEICS, (u32)eics);

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) {
		if ((hw->mac.ops.check_link(hw, &link_speed,
					    &link_up, false)) != 0) {
			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 2380
	if (!tx_ring->desc)
		goto err;

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;
	tx_ring->work_limit = tx_ring->count;
	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
2381
	rx_ring->rx_buffer_info = vzalloc(size);
2382
	if (!rx_ring->rx_buffer_info)
2383 2384 2385 2386 2387 2388
		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);

2389 2390
	rx_ring->desc = dma_alloc_coherent(&pdev->dev, rx_ring->size,
					   &rx_ring->dma, GFP_KERNEL);
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 2450

	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;

2451 2452
	dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
			  rx_ring->dma);
2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500

	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]);
}

/**
 * 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;
2501 2502
			pr_err("Unable to start - perhaps the PF Driver isn't "
			       "up yet\n");
2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525
			goto err_setup_reset;
		}
	}

	/* 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);

2526
	ixgbevf_up_complete(adapter);
2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604

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

	ixgbevf_irq_enable(adapter, true, true);

	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);
	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;
}

static int ixgbevf_tso(struct ixgbevf_adapter *adapter,
		       struct ixgbevf_ring *tx_ring,
		       struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
{
	struct ixgbe_adv_tx_context_desc *context_desc;
	unsigned int i;
	int err;
	struct ixgbevf_tx_buffer *tx_buffer_info;
	u32 vlan_macip_lens = 0, type_tucmd_mlhl;
	u32 mss_l4len_idx, l4len;

	if (skb_is_gso(skb)) {
		if (skb_header_cloned(skb)) {
			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
			if (err)
				return err;
		}
		l4len = tcp_hdrlen(skb);
		*hdr_len += l4len;

		if (skb->protocol == htons(ETH_P_IP)) {
			struct iphdr *iph = ip_hdr(skb);
			iph->tot_len = 0;
			iph->check = 0;
			tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
								 iph->daddr, 0,
								 IPPROTO_TCP,
								 0);
			adapter->hw_tso_ctxt++;
J
Jeff Kirsher 已提交
2605
		} else if (skb_is_gso_v6(skb)) {
2606 2607 2608 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 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709
			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);
			adapter->hw_tso6_ctxt++;
		}

		i = tx_ring->next_to_use;

		tx_buffer_info = &tx_ring->tx_buffer_info[i];
		context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i);

		/* VLAN MACLEN IPLEN */
		if (tx_flags & IXGBE_TX_FLAGS_VLAN)
			vlan_macip_lens |=
				(tx_flags & IXGBE_TX_FLAGS_VLAN_MASK);
		vlan_macip_lens |= ((skb_network_offset(skb)) <<
				    IXGBE_ADVTXD_MACLEN_SHIFT);
		*hdr_len += skb_network_offset(skb);
		vlan_macip_lens |=
			(skb_transport_header(skb) - skb_network_header(skb));
		*hdr_len +=
			(skb_transport_header(skb) - skb_network_header(skb));
		context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
		context_desc->seqnum_seed = 0;

		/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
		type_tucmd_mlhl = (IXGBE_TXD_CMD_DEXT |
				    IXGBE_ADVTXD_DTYP_CTXT);

		if (skb->protocol == htons(ETH_P_IP))
			type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4;
		type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP;
		context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl);

		/* MSS L4LEN IDX */
		mss_l4len_idx =
			(skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT);
		mss_l4len_idx |= (l4len << IXGBE_ADVTXD_L4LEN_SHIFT);
		/* use index 1 for TSO */
		mss_l4len_idx |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
		context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);

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

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

		return true;
	}

	return false;
}

static bool ixgbevf_tx_csum(struct ixgbevf_adapter *adapter,
			    struct ixgbevf_ring *tx_ring,
			    struct sk_buff *skb, u32 tx_flags)
{
	struct ixgbe_adv_tx_context_desc *context_desc;
	unsigned int i;
	struct ixgbevf_tx_buffer *tx_buffer_info;
	u32 vlan_macip_lens = 0, type_tucmd_mlhl = 0;

	if (skb->ip_summed == CHECKSUM_PARTIAL ||
	    (tx_flags & IXGBE_TX_FLAGS_VLAN)) {
		i = tx_ring->next_to_use;
		tx_buffer_info = &tx_ring->tx_buffer_info[i];
		context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i);

		if (tx_flags & IXGBE_TX_FLAGS_VLAN)
			vlan_macip_lens |= (tx_flags &
					    IXGBE_TX_FLAGS_VLAN_MASK);
		vlan_macip_lens |= (skb_network_offset(skb) <<
				    IXGBE_ADVTXD_MACLEN_SHIFT);
		if (skb->ip_summed == CHECKSUM_PARTIAL)
			vlan_macip_lens |= (skb_transport_header(skb) -
					    skb_network_header(skb));

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

		type_tucmd_mlhl |= (IXGBE_TXD_CMD_DEXT |
				    IXGBE_ADVTXD_DTYP_CTXT);

		if (skb->ip_summed == CHECKSUM_PARTIAL) {
			switch (skb->protocol) {
			case __constant_htons(ETH_P_IP):
				type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4;
				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
					type_tucmd_mlhl |=
					    IXGBE_ADVTXD_TUCMD_L4T_TCP;
				break;
			case __constant_htons(ETH_P_IPV6):
				/* XXX what about other V6 headers?? */
				if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
					type_tucmd_mlhl |=
						IXGBE_ADVTXD_TUCMD_L4T_TCP;
				break;
			default:
				if (unlikely(net_ratelimit())) {
2710 2711
					pr_warn("partial checksum but "
						"proto=%x!\n", skb->protocol);
2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744
				}
				break;
			}
		}

		context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl);
		/* use index zero for tx checksum offload */
		context_desc->mss_l4len_idx = 0;

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

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

		return true;
	}

	return false;
}

static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter,
			  struct ixgbevf_ring *tx_ring,
			  struct sk_buff *skb, u32 tx_flags,
			  unsigned int first)
{
	struct pci_dev *pdev = adapter->pdev;
	struct ixgbevf_tx_buffer *tx_buffer_info;
	unsigned int len;
	unsigned int total = skb->len;
2745 2746
	unsigned int offset = 0, size;
	int count = 0;
2747 2748
	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
	unsigned int f;
2749
	int i;
2750 2751 2752 2753 2754 2755 2756 2757 2758 2759

	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;
2760
		tx_buffer_info->dma = dma_map_single(&adapter->pdev->dev,
2761
						     skb->data + offset,
2762 2763
						     size, DMA_TO_DEVICE);
		if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma))
2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777
			goto dma_error;
		tx_buffer_info->time_stamp = jiffies;
		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
2778
		const struct skb_frag_struct *frag;
2779 2780

		frag = &skb_shinfo(skb)->frags[f];
E
Eric Dumazet 已提交
2781
		len = min((unsigned int)skb_frag_size(frag), total);
2782
		offset = 0;
2783 2784 2785 2786 2787 2788

		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;
2789 2790 2791
			tx_buffer_info->dma =
				skb_frag_dma_map(&adapter->pdev->dev, frag,
						 offset, size, DMA_TO_DEVICE);
2792
			tx_buffer_info->mapped_as_page = true;
2793
			if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma))
2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947
				goto dma_error;
			tx_buffer_info->time_stamp = jiffies;
			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;

	return count;

dma_error:
	dev_err(&pdev->dev, "TX DMA map failed\n");

	/* clear timestamp and dma mappings for failed tx_buffer_info map */
	tx_buffer_info->dma = 0;
	tx_buffer_info->time_stamp = 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];
		ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info);
	}

	return count;
}

static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter,
			     struct ixgbevf_ring *tx_ring, int tx_flags,
			     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;

	if (tx_flags & IXGBE_TX_FLAGS_TSO) {
		cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE;

		olinfo_status |= IXGBE_TXD_POPTS_TXSM <<
			IXGBE_ADVTXD_POPTS_SHIFT;

		/* use index 1 context for tso */
		olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
		if (tx_flags & IXGBE_TX_FLAGS_IPV4)
			olinfo_status |= IXGBE_TXD_POPTS_IXSM <<
				IXGBE_ADVTXD_POPTS_SHIFT;

	} else if (tx_flags & IXGBE_TX_FLAGS_CSUM)
		olinfo_status |= IXGBE_TXD_POPTS_TXSM <<
			IXGBE_ADVTXD_POPTS_SHIFT;

	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];
		tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
		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);

	/*
	 * Force memory writes to complete before letting h/w
	 * know there are new descriptors to fetch.  (Only
	 * applicable for weak-ordered memory model archs,
	 * such as IA-64).
	 */
	wmb();

	tx_ring->next_to_use = i;
	writel(i, adapter->hw.hw_addr + tx_ring->tail);
}

static int __ixgbevf_maybe_stop_tx(struct net_device *netdev,
				   struct ixgbevf_ring *tx_ring, int size)
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	netif_stop_subqueue(netdev, tx_ring->queue_index);
	/* 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 */
	netif_start_subqueue(netdev, tx_ring->queue_index);
	++adapter->restart_queue;
	return 0;
}

static int ixgbevf_maybe_stop_tx(struct net_device *netdev,
				 struct ixgbevf_ring *tx_ring, int size)
{
	if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size))
		return 0;
	return __ixgbevf_maybe_stop_tx(netdev, tx_ring, size);
}

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;
	int count = 0;

	unsigned int f;

	tx_ring = &adapter->tx_ring[r_idx];

2948
	if (vlan_tx_tag_present(skb)) {
2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961
		tx_flags |= vlan_tx_tag_get(skb);
		tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
		tx_flags |= IXGBE_TX_FLAGS_VLAN;
	}

	/* four things can cause us to need a context descriptor */
	if (skb_is_gso(skb) ||
	    (skb->ip_summed == CHECKSUM_PARTIAL) ||
	    (tx_flags & IXGBE_TX_FLAGS_VLAN))
		count++;

	count += TXD_USE_COUNT(skb_headlen(skb));
	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
E
Eric Dumazet 已提交
2962
		count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)->frags[f]));
2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028

	if (ixgbevf_maybe_stop_tx(netdev, tx_ring, count)) {
		adapter->tx_busy++;
		return NETDEV_TX_BUSY;
	}

	first = tx_ring->next_to_use;

	if (skb->protocol == htons(ETH_P_IP))
		tx_flags |= IXGBE_TX_FLAGS_IPV4;
	tso = ixgbevf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len);
	if (tso < 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (tso)
		tx_flags |= IXGBE_TX_FLAGS_TSO;
	else if (ixgbevf_tx_csum(adapter, tx_ring, skb, tx_flags) &&
		 (skb->ip_summed == CHECKSUM_PARTIAL))
		tx_flags |= IXGBE_TX_FLAGS_CSUM;

	ixgbevf_tx_queue(adapter, tx_ring, tx_flags,
			 ixgbevf_tx_map(adapter, tx_ring, skb, tx_flags, first),
			 skb->len, hdr_len);

	ixgbevf_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);

	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);

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

	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);
3029
	struct ixgbe_hw *hw = &adapter->hw;
3030
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
3031 3032 3033 3034 3035
	int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE;
	u32 msg[2];

	if (adapter->hw.mac.type == ixgbe_mac_X540_vf)
		max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE;
3036 3037

	/* MTU < 68 is an error and causes problems on some kernels */
3038
	if ((new_mtu < 68) || (max_frame > max_possible_frame))
3039 3040 3041 3042 3043 3044 3045
		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;

3046 3047 3048 3049 3050
	if (!netif_running(netdev)) {
		msg[0] = IXGBE_VF_SET_LPE;
		msg[1] = max_frame;
		hw->mbx.ops.write_posted(hw, msg, 2);
	}
3051

3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076
	if (netif_running(netdev))
		ixgbevf_reinit_locked(adapter);

	return 0;
}

static void ixgbevf_shutdown(struct pci_dev *pdev)
{
	struct net_device *netdev = pci_get_drvdata(pdev);
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	netif_device_detach(netdev);

	if (netif_running(netdev)) {
		ixgbevf_down(adapter);
		ixgbevf_free_irq(adapter);
		ixgbevf_free_all_tx_resources(adapter);
		ixgbevf_free_all_rx_resources(adapter);
	}

	pci_save_state(pdev);

	pci_disable_device(pdev);
}

3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114
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;
}

3115 3116
static int ixgbevf_set_features(struct net_device *netdev,
	netdev_features_t features)
3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127
{
	struct ixgbevf_adapter *adapter = netdev_priv(netdev);

	if (features & NETIF_F_RXCSUM)
		adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED;
	else
		adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED;

	return 0;
}

3128
static const struct net_device_ops ixgbe_netdev_ops = {
3129 3130 3131 3132
	.ndo_open		= ixgbevf_open,
	.ndo_stop		= ixgbevf_close,
	.ndo_start_xmit		= ixgbevf_xmit_frame,
	.ndo_set_rx_mode	= ixgbevf_set_rx_mode,
3133
	.ndo_get_stats64	= ixgbevf_get_stats,
3134
	.ndo_validate_addr	= eth_validate_addr,
3135 3136 3137 3138 3139
	.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,
3140
	.ndo_set_features	= ixgbevf_set_features,
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
};

static void ixgbevf_assign_netdev_ops(struct net_device *dev)
{
	dev->netdev_ops = &ixgbe_netdev_ops;
	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;

3175 3176
	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
	    !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
3177 3178
		pci_using_dac = 1;
	} else {
3179
		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
3180
		if (err) {
3181 3182
			err = dma_set_coherent_mask(&pdev->dev,
						    DMA_BIT_MASK(32));
3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215
			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;
3216
	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239

	/*
	 * 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,
3240
	       sizeof(struct ixgbe_mbx_operations));
3241 3242 3243

	/* setup the private structure */
	err = ixgbevf_sw_init(adapter);
3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254
	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;
	}
3255

3256
	netdev->hw_features = NETIF_F_SG |
3257
			   NETIF_F_IP_CSUM |
3258 3259 3260 3261 3262 3263
			   NETIF_F_IPV6_CSUM |
			   NETIF_F_TSO |
			   NETIF_F_TSO6 |
			   NETIF_F_RXCSUM;

	netdev->features = netdev->hw_features |
3264 3265 3266 3267 3268 3269 3270
			   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;
3271
	netdev->vlan_features |= NETIF_F_IPV6_CSUM;
3272 3273 3274 3275 3276
	netdev->vlan_features |= NETIF_F_SG;

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

3277 3278
	netdev->priv_flags |= IFF_UNICAST_FLT;

3279
	init_timer(&adapter->watchdog_timer);
3280
	adapter->watchdog_timer.function = ixgbevf_watchdog;
3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299
	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
3300 3301
	netif_carrier_off(netdev);

3302 3303
	ixgbevf_init_last_counter_stats(adapter);

3304
	/* print the MAC address */
3305
	hw_dbg(hw, "%pM\n", netdev->dev_addr);
3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344

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

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

err_register:
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);

3345
	cancel_work_sync(&adapter->reset_task);
3346 3347
	cancel_work_sync(&adapter->watchdog_task);

3348
	if (netdev->reg_state == NETREG_REGISTERED)
3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374
		unregister_netdev(netdev);

	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);
}

static struct pci_driver ixgbevf_driver = {
	.name     = ixgbevf_driver_name,
	.id_table = ixgbevf_pci_tbl,
	.probe    = ixgbevf_probe,
	.remove   = __devexit_p(ixgbevf_remove),
	.shutdown = ixgbevf_shutdown,
};

/**
3375
 * ixgbevf_init_module - Driver Registration Routine
3376
 *
3377
 * ixgbevf_init_module is the first routine called when the driver is
3378 3379 3380 3381 3382
 * loaded. All it does is register with the PCI subsystem.
 **/
static int __init ixgbevf_init_module(void)
{
	int ret;
3383 3384
	pr_info("%s - version %s\n", ixgbevf_driver_string,
		ixgbevf_driver_version);
3385

3386
	pr_info("%s\n", ixgbevf_copyright);
3387 3388 3389 3390 3391 3392 3393 3394

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

module_init(ixgbevf_init_module);

/**
3395
 * ixgbevf_exit_module - Driver Exit Cleanup Routine
3396
 *
3397
 * ixgbevf_exit_module is called just before the driver is removed
3398 3399 3400 3401 3402 3403 3404 3405 3406
 * from memory.
 **/
static void __exit ixgbevf_exit_module(void)
{
	pci_unregister_driver(&ixgbevf_driver);
}

#ifdef DEBUG
/**
3407
 * ixgbevf_get_hw_dev_name - return device name string
3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419
 * 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 */