ixgbe_lib.c 23.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
/*******************************************************************************

  Intel 10 Gigabit PCI Express Linux driver
  Copyright(c) 1999 - 2012 Intel Corporation.

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

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

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

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

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

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

#include "ixgbe.h"
#include "ixgbe_sriov.h"

31
#ifdef CONFIG_IXGBE_DCB
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
/* ixgbe_get_first_reg_idx - Return first register index associated with ring */
static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc,
				    unsigned int *tx, unsigned int *rx)
{
	struct net_device *dev = adapter->netdev;
	struct ixgbe_hw *hw = &adapter->hw;
	u8 num_tcs = netdev_get_num_tc(dev);

	*tx = 0;
	*rx = 0;

	switch (hw->mac.type) {
	case ixgbe_mac_82598EB:
		*tx = tc << 2;
		*rx = tc << 3;
		break;
	case ixgbe_mac_82599EB:
	case ixgbe_mac_X540:
		if (num_tcs > 4) {
			if (tc < 3) {
				*tx = tc << 5;
				*rx = tc << 4;
			} else if (tc <  5) {
				*tx = ((tc + 2) << 4);
				*rx = tc << 4;
			} else if (tc < num_tcs) {
				*tx = ((tc + 8) << 3);
				*rx = tc << 4;
			}
		} else {
			*rx =  tc << 5;
			switch (tc) {
			case 0:
				*tx =  0;
				break;
			case 1:
				*tx = 64;
				break;
			case 2:
				*tx = 96;
				break;
			case 3:
				*tx = 112;
				break;
			default:
				break;
			}
		}
		break;
	default:
		break;
	}
}

/**
 * ixgbe_cache_ring_dcb - Descriptor ring to register mapping for DCB
 * @adapter: board private structure to initialize
 *
 * Cache the descriptor ring offsets for DCB to the assigned rings.
 *
 **/
static inline bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter)
{
	struct net_device *dev = adapter->netdev;
	int i, j, k;
	u8 num_tcs = netdev_get_num_tc(dev);

	if (!num_tcs)
		return false;

	for (i = 0, k = 0; i < num_tcs; i++) {
		unsigned int tx_s, rx_s;
		u16 count = dev->tc_to_txq[i].count;

		ixgbe_get_first_reg_idx(adapter, i, &tx_s, &rx_s);
		for (j = 0; j < count; j++, k++) {
			adapter->tx_ring[k]->reg_idx = tx_s + j;
			adapter->rx_ring[k]->reg_idx = rx_s + j;
			adapter->tx_ring[k]->dcb_tc = i;
			adapter->rx_ring[k]->dcb_tc = i;
		}
	}

	return true;
}

118
#endif
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
/**
 * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov
 * @adapter: board private structure to initialize
 *
 * SR-IOV doesn't use any descriptor rings but changes the default if
 * no other mapping is used.
 *
 */
static inline bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
{
	adapter->rx_ring[0]->reg_idx = adapter->num_vfs * 2;
	adapter->tx_ring[0]->reg_idx = adapter->num_vfs * 2;
	if (adapter->num_vfs)
		return true;
	else
		return false;
}

137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
/**
 * ixgbe_cache_ring_rss - Descriptor ring to register mapping for RSS
 * @adapter: board private structure to initialize
 *
 * Cache the descriptor ring offsets for RSS to the assigned rings.
 *
 **/
static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter)
{
	int i;

	if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED))
		return false;

	for (i = 0; i < adapter->num_rx_queues; i++)
		adapter->rx_ring[i]->reg_idx = i;
	for (i = 0; i < adapter->num_tx_queues; i++)
		adapter->tx_ring[i]->reg_idx = i;

	return true;
}

159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183
/**
 * ixgbe_cache_ring_register - Descriptor ring to register mapping
 * @adapter: board private structure to initialize
 *
 * Once we know the feature-set enabled for the device, we'll cache
 * the register offset the descriptor ring is assigned to.
 *
 * Note, the order the various feature calls is important.  It must start with
 * the "most" features enabled at the same time, then trickle down to the
 * least amount of features turned on at once.
 **/
static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
{
	/* start with default case */
	adapter->rx_ring[0]->reg_idx = 0;
	adapter->tx_ring[0]->reg_idx = 0;

	if (ixgbe_cache_ring_sriov(adapter))
		return;

#ifdef CONFIG_IXGBE_DCB
	if (ixgbe_cache_ring_dcb(adapter))
		return;
#endif

184
	ixgbe_cache_ring_rss(adapter);
185 186 187
}

/**
188
 * ixgbe_set_sriov_queues - Allocate queues for IOV use
189 190 191 192 193 194 195 196 197 198 199
 * @adapter: board private structure to initialize
 *
 * IOV doesn't actually use anything, so just NAK the
 * request for now and let the other queue routines
 * figure out what to do.
 */
static inline bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
{
	return false;
}

200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267
#define IXGBE_RSS_16Q_MASK	0xF
#define IXGBE_RSS_8Q_MASK	0x7
#define IXGBE_RSS_4Q_MASK	0x3
#define IXGBE_RSS_2Q_MASK	0x1
#define IXGBE_RSS_DISABLED_MASK	0x0

#ifdef CONFIG_IXGBE_DCB
static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter)
{
	struct net_device *dev = adapter->netdev;
	struct ixgbe_ring_feature *f;
	int rss_i, rss_m, i;
	int tcs;

	/* Map queue offset and counts onto allocated tx queues */
	tcs = netdev_get_num_tc(dev);

	/* verify we have DCB queueing enabled before proceeding */
	if (tcs <= 1)
		return false;

	/* determine the upper limit for our current DCB mode */
	rss_i = dev->num_tx_queues / tcs;
	if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
		/* 8 TC w/ 4 queues per TC */
		rss_i = min_t(u16, rss_i, 4);
		rss_m = IXGBE_RSS_4Q_MASK;
	} else if (tcs > 4) {
		/* 8 TC w/ 8 queues per TC */
		rss_i = min_t(u16, rss_i, 8);
		rss_m = IXGBE_RSS_8Q_MASK;
	} else {
		/* 4 TC w/ 16 queues per TC */
		rss_i = min_t(u16, rss_i, 16);
		rss_m = IXGBE_RSS_16Q_MASK;
	}

	/* set RSS mask and indices */
	f = &adapter->ring_feature[RING_F_RSS];
	rss_i = min_t(int, rss_i, f->limit);
	f->indices = rss_i;
	f->mask = rss_m;

#ifdef IXGBE_FCOE
	/* FCoE enabled queues require special configuration indexed
	 * by feature specific indices and offset. Here we map FCoE
	 * indices onto the DCB queue pairs allowing FCoE to own
	 * configuration later.
	 */
	if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
		u8 tc = ixgbe_fcoe_get_tc(adapter);

		f = &adapter->ring_feature[RING_F_FCOE];
		f->indices = min_t(u16, rss_i, f->limit);
		f->offset = rss_i * tc;
	}

#endif /* IXGBE_FCOE */
	for (i = 0; i < tcs; i++)
		netdev_set_tc_queue(dev, i, rss_i, rss_i * i);

	adapter->num_tx_queues = rss_i * tcs;
	adapter->num_rx_queues = rss_i * tcs;

	return true;
}

#endif
268
/**
269
 * ixgbe_set_rss_queues - Allocate queues for RSS
270 271 272 273 274 275
 * @adapter: board private structure to initialize
 *
 * This is our "base" multiqueue mode.  RSS (Receive Side Scaling) will try
 * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU.
 *
 **/
276
static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter)
277
{
278 279
	struct ixgbe_ring_feature *f;
	u16 rss_i;
280

281 282 283
	if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) {
		adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
		return false;
284 285
	}

286 287 288
	/* set mask for 16 queue limit of RSS */
	f = &adapter->ring_feature[RING_F_RSS];
	rss_i = f->limit;
289

290
	f->indices = rss_i;
291
	f->mask = IXGBE_RSS_16Q_MASK;
292 293

	/*
294
	 * Use Flow Director in addition to RSS to ensure the best
295 296 297
	 * distribution of flows across cores, even when an FDIR flow
	 * isn't matched.
	 */
298 299 300 301 302
	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
		f = &adapter->ring_feature[RING_F_FDIR];

		f->indices = min_t(u16, num_online_cpus(), f->limit);
		rss_i = max_t(u16, rss_i, f->indices);
303
	}
304

305
#ifdef IXGBE_FCOE
306 307 308 309 310 311 312 313 314 315 316
	/*
	 * FCoE can exist on the same rings as standard network traffic
	 * however it is preferred to avoid that if possible.  In order
	 * to get the best performance we allocate as many FCoE queues
	 * as we can and we place them at the end of the ring array to
	 * avoid sharing queues with standard RSS on systems with 24 or
	 * more CPUs.
	 */
	if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
		struct net_device *dev = adapter->netdev;
		u16 fcoe_i;
317

318
		f = &adapter->ring_feature[RING_F_FCOE];
319

320 321 322
		/* merge FCoE queues with RSS queues */
		fcoe_i = min_t(u16, f->limit + rss_i, num_online_cpus());
		fcoe_i = min_t(u16, fcoe_i, dev->num_tx_queues);
323

324 325 326
		/* limit indices to rss_i if MSI-X is disabled */
		if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
			fcoe_i = rss_i;
327

328 329 330 331
		/* attempt to reserve some queues for just FCoE */
		f->indices = min_t(u16, fcoe_i, f->limit);
		f->offset = fcoe_i - f->indices;
		rss_i = max_t(u16, fcoe_i, rss_i);
332 333 334
	}

#endif /* IXGBE_FCOE */
335 336
	adapter->num_rx_queues = rss_i;
	adapter->num_tx_queues = rss_i;
337 338 339 340 341

	return true;
}

/**
342
 * ixgbe_set_num_queues - Allocate queues for device, feature dependent
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430
 * @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 int ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
{
	/* Start with base case */
	adapter->num_rx_queues = 1;
	adapter->num_tx_queues = 1;
	adapter->num_rx_pools = adapter->num_rx_queues;
	adapter->num_rx_queues_per_pool = 1;

	if (ixgbe_set_sriov_queues(adapter))
		goto done;

#ifdef CONFIG_IXGBE_DCB
	if (ixgbe_set_dcb_queues(adapter))
		goto done;

#endif
	if (ixgbe_set_rss_queues(adapter))
		goto done;

	/* fallback to base case */
	adapter->num_rx_queues = 1;
	adapter->num_tx_queues = 1;

done:
	if ((adapter->netdev->reg_state == NETREG_UNREGISTERED) ||
	    (adapter->netdev->reg_state == NETREG_UNREGISTERING))
		return 0;

	/* Notify the stack of the (possibly) reduced queue counts. */
	netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues);
	return netif_set_real_num_rx_queues(adapter->netdev,
					    adapter->num_rx_queues);
}

static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter,
				       int vectors)
{
	int err, vector_threshold;

	/* We'll want at least 2 (vector_threshold):
	 * 1) TxQ[0] + RxQ[0] handler
	 * 2) 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.
		 */
		netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev,
			     "Unable to allocate MSI-X interrupts\n");
		adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
		kfree(adapter->msix_entries);
		adapter->msix_entries = NULL;
	} else {
		adapter->flags |= IXGBE_FLAG_MSIX_ENABLED; /* Woot! */
		/*
		 * 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.
		 */
431 432
		vectors -= NON_Q_VECTORS;
		adapter->num_q_vectors = min(vectors, adapter->max_q_vectors);
433 434 435 436 437 438 439 440 441 442 443 444 445 446
	}
}

static void ixgbe_add_ring(struct ixgbe_ring *ring,
			   struct ixgbe_ring_container *head)
{
	ring->next = head->ring;
	head->ring = ring;
	head->count++;
}

/**
 * ixgbe_alloc_q_vector - Allocate memory for a single interrupt vector
 * @adapter: board private structure to initialize
447
 * @v_count: q_vectors allocated on adapter, used for ring interleaving
448
 * @v_idx: index of vector in adapter struct
449 450 451 452
 * @txr_count: total number of Tx rings to allocate
 * @txr_idx: index of first Tx ring to allocate
 * @rxr_count: total number of Rx rings to allocate
 * @rxr_idx: index of first Rx ring to allocate
453 454 455
 *
 * We allocate one q_vector.  If allocation fails we return -ENOMEM.
 **/
456 457
static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
				int v_count, int v_idx,
458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
				int txr_count, int txr_idx,
				int rxr_count, int rxr_idx)
{
	struct ixgbe_q_vector *q_vector;
	struct ixgbe_ring *ring;
	int node = -1;
	int cpu = -1;
	int ring_count, size;

	ring_count = txr_count + rxr_count;
	size = sizeof(struct ixgbe_q_vector) +
	       (sizeof(struct ixgbe_ring) * ring_count);

	/* customize cpu for Flow Director mapping */
	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
		if (cpu_online(v_idx)) {
			cpu = v_idx;
			node = cpu_to_node(cpu);
		}
	}

	/* allocate q_vector and rings */
	q_vector = kzalloc_node(size, GFP_KERNEL, node);
	if (!q_vector)
		q_vector = kzalloc(size, GFP_KERNEL);
	if (!q_vector)
		return -ENOMEM;

	/* setup affinity mask and node */
	if (cpu != -1)
		cpumask_set_cpu(cpu, &q_vector->affinity_mask);
	else
		cpumask_copy(&q_vector->affinity_mask, cpu_online_mask);
	q_vector->numa_node = node;

	/* initialize NAPI */
	netif_napi_add(adapter->netdev, &q_vector->napi,
		       ixgbe_poll, 64);

	/* tie q_vector and adapter together */
	adapter->q_vector[v_idx] = q_vector;
	q_vector->adapter = adapter;
	q_vector->v_idx = v_idx;

	/* initialize work limits */
	q_vector->tx.work_limit = adapter->tx_work_limit;

	/* initialize pointer to rings */
	ring = q_vector->ring;

	while (txr_count) {
		/* assign generic ring traits */
		ring->dev = &adapter->pdev->dev;
		ring->netdev = adapter->netdev;

		/* configure backlink on ring */
		ring->q_vector = q_vector;

		/* update q_vector Tx values */
		ixgbe_add_ring(ring, &q_vector->tx);

		/* apply Tx specific ring traits */
		ring->count = adapter->tx_ring_count;
		ring->queue_index = txr_idx;

		/* assign ring to adapter */
		adapter->tx_ring[txr_idx] = ring;

		/* update count and index */
		txr_count--;
528
		txr_idx += v_count;
529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551

		/* push pointer to next ring */
		ring++;
	}

	while (rxr_count) {
		/* assign generic ring traits */
		ring->dev = &adapter->pdev->dev;
		ring->netdev = adapter->netdev;

		/* configure backlink on ring */
		ring->q_vector = q_vector;

		/* update q_vector Rx values */
		ixgbe_add_ring(ring, &q_vector->rx);

		/*
		 * 82599 errata, UDP frames with a 0 checksum
		 * can be marked as checksum errors.
		 */
		if (adapter->hw.mac.type == ixgbe_mac_82599EB)
			set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state);

552 553 554 555
#ifdef IXGBE_FCOE
		if (adapter->netdev->features & NETIF_F_FCOE_MTU) {
			struct ixgbe_ring_feature *f;
			f = &adapter->ring_feature[RING_F_FCOE];
556 557
			if ((rxr_idx >= f->offset) &&
			    (rxr_idx < f->offset + f->indices))
558
				set_bit(__IXGBE_RX_FCOE, &ring->state);
559 560 561
		}

#endif /* IXGBE_FCOE */
562 563 564 565 566 567 568 569 570
		/* apply Rx specific ring traits */
		ring->count = adapter->rx_ring_count;
		ring->queue_index = rxr_idx;

		/* assign ring to adapter */
		adapter->rx_ring[rxr_idx] = ring;

		/* update count and index */
		rxr_count--;
571
		rxr_idx += v_count;
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

		/* push pointer to next ring */
		ring++;
	}

	return 0;
}

/**
 * ixgbe_free_q_vector - Free memory allocated for specific interrupt vector
 * @adapter: board private structure to initialize
 * @v_idx: Index of vector to be freed
 *
 * This function frees the memory allocated to the q_vector.  In addition if
 * NAPI is enabled it will delete any references to the NAPI struct prior
 * to freeing the q_vector.
 **/
static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
{
	struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx];
	struct ixgbe_ring *ring;

	ixgbe_for_each_ring(ring, q_vector->tx)
		adapter->tx_ring[ring->queue_index] = NULL;

	ixgbe_for_each_ring(ring, q_vector->rx)
		adapter->rx_ring[ring->queue_index] = NULL;

	adapter->q_vector[v_idx] = NULL;
	netif_napi_del(&q_vector->napi);

	/*
	 * ixgbe_get_stats64() might access the rings on this vector,
	 * we must wait a grace period before freeing it.
	 */
	kfree_rcu(q_vector, rcu);
}

/**
 * ixgbe_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 ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
{
619
	int q_vectors = adapter->num_q_vectors;
620 621 622 623 624 625 626 627 628 629
	int rxr_remaining = adapter->num_rx_queues;
	int txr_remaining = adapter->num_tx_queues;
	int rxr_idx = 0, txr_idx = 0, v_idx = 0;
	int err;

	/* only one q_vector if MSI-X is disabled. */
	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
		q_vectors = 1;

	if (q_vectors >= (rxr_remaining + txr_remaining)) {
630 631 632
		for (; rxr_remaining; v_idx++) {
			err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
						   0, 0, 1, rxr_idx);
633 634 635 636 637

			if (err)
				goto err_out;

			/* update counts and index */
638 639
			rxr_remaining--;
			rxr_idx++;
640 641 642
		}
	}

643 644 645 646
	for (; v_idx < q_vectors; v_idx++) {
		int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
		int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
		err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
647 648 649 650 651 652 653 654 655
					   tqpv, txr_idx,
					   rqpv, rxr_idx);

		if (err)
			goto err_out;

		/* update counts and index */
		rxr_remaining -= rqpv;
		txr_remaining -= tqpv;
656 657
		rxr_idx++;
		txr_idx++;
658 659 660 661 662
	}

	return 0;

err_out:
663 664 665 666 667
	adapter->num_tx_queues = 0;
	adapter->num_rx_queues = 0;
	adapter->num_q_vectors = 0;

	while (v_idx--)
668 669 670 671 672 673 674 675 676 677 678 679 680 681 682
		ixgbe_free_q_vector(adapter, v_idx);

	return -ENOMEM;
}

/**
 * ixgbe_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 ixgbe_free_q_vectors(struct ixgbe_adapter *adapter)
{
683
	int v_idx = adapter->num_q_vectors;
684

685 686 687
	adapter->num_tx_queues = 0;
	adapter->num_rx_queues = 0;
	adapter->num_q_vectors = 0;
688

689
	while (v_idx--)
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
		ixgbe_free_q_vector(adapter, v_idx);
}

static void ixgbe_reset_interrupt_capability(struct ixgbe_adapter *adapter)
{
	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
		adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
		pci_disable_msix(adapter->pdev);
		kfree(adapter->msix_entries);
		adapter->msix_entries = NULL;
	} else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) {
		adapter->flags &= ~IXGBE_FLAG_MSI_ENABLED;
		pci_disable_msi(adapter->pdev);
	}
}

/**
 * ixgbe_set_interrupt_capability - set MSI-X or MSI if 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 ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	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) the same number of vectors as there are CPU's.
	 * The default is to use pairs of vectors.
	 */
	v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues);
	v_budget = min_t(int, v_budget, num_online_cpus());
	v_budget += NON_Q_VECTORS;

	/*
	 * At the same time, hardware can only support a maximum of
	 * hw.mac->max_msix_vectors vectors.  With features
	 * such as RSS and VMDq, we can easily surpass the number of Rx and Tx
	 * descriptor queues supported by our device.  Thus, we cap it off in
	 * those rare cases where the cpu count also exceeds our vector limit.
	 */
	v_budget = min_t(int, v_budget, hw->mac.max_msix_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) {
		for (vector = 0; vector < v_budget; vector++)
			adapter->msix_entries[vector].entry = vector;

		ixgbe_acquire_msix_vectors(adapter, v_budget);

		if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
			goto out;
	}

	adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED;
	adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED;
	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
		e_err(probe,
		      "ATR is not supported while multiple "
		      "queues are disabled.  Disabling Flow Director\n");
	}
	adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
	adapter->atr_sample_rate = 0;
	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
		ixgbe_disable_sriov(adapter);

	err = ixgbe_set_num_queues(adapter);
	if (err)
		return err;

769 770
	adapter->num_q_vectors = 1;

771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868
	err = pci_enable_msi(adapter->pdev);
	if (!err) {
		adapter->flags |= IXGBE_FLAG_MSI_ENABLED;
	} else {
		netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev,
			     "Unable to allocate MSI interrupt, "
			     "falling back to legacy.  Error: %d\n", err);
		/* reset err */
		err = 0;
	}

out:
	return err;
}

/**
 * ixgbe_init_interrupt_scheme - Determine proper interrupt scheme
 * @adapter: board private structure to initialize
 *
 * We determine which interrupt scheme to use based on...
 * - Kernel support (MSI, MSI-X)
 *   - which can be user-defined (via MODULE_PARAM)
 * - Hardware queue count (num_*_queues)
 *   - defined by miscellaneous hardware support/features (RSS, etc.)
 **/
int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter)
{
	int err;

	/* Number of supported queues */
	err = ixgbe_set_num_queues(adapter);
	if (err)
		return err;

	err = ixgbe_set_interrupt_capability(adapter);
	if (err) {
		e_dev_err("Unable to setup interrupt capabilities\n");
		goto err_set_interrupt;
	}

	err = ixgbe_alloc_q_vectors(adapter);
	if (err) {
		e_dev_err("Unable to allocate memory for queue vectors\n");
		goto err_alloc_q_vectors;
	}

	ixgbe_cache_ring_register(adapter);

	e_dev_info("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(__IXGBE_DOWN, &adapter->state);

	return 0;

err_alloc_q_vectors:
	ixgbe_reset_interrupt_capability(adapter);
err_set_interrupt:
	return err;
}

/**
 * ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings
 * @adapter: board private structure to clear interrupt scheme on
 *
 * We go through and clear interrupt specific resources and reset the structure
 * to pre-load conditions
 **/
void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
{
	adapter->num_tx_queues = 0;
	adapter->num_rx_queues = 0;

	ixgbe_free_q_vectors(adapter);
	ixgbe_reset_interrupt_capability(adapter);
}

void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens,
		       u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx)
{
	struct ixgbe_adv_tx_context_desc *context_desc;
	u16 i = tx_ring->next_to_use;

	context_desc = IXGBE_TX_CTXTDESC(tx_ring, i);

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

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

	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
	context_desc->seqnum_seed	= cpu_to_le32(fcoe_sof_eof);
	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
}