dmar.c 18.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Copyright (c) 2006, 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., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 *
17 18 19 20
 * Copyright (C) 2006-2008 Intel Corporation
 * Author: Ashok Raj <ashok.raj@intel.com>
 * Author: Shaohua Li <shaohua.li@intel.com>
 * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
21
 *
22
 * This file implements early detection/parsing of Remapping Devices
23 24
 * reported to OS through BIOS via DMA remapping reporting (DMAR) ACPI
 * tables.
25 26
 *
 * These routines are used by both DMA-remapping and Interrupt-remapping
27 28 29 30
 */

#include <linux/pci.h>
#include <linux/dmar.h>
K
Kay, Allen M 已提交
31 32
#include <linux/iova.h>
#include <linux/intel-iommu.h>
33
#include <linux/timer.h>
34 35 36 37 38 39 40 41 42 43 44

#undef PREFIX
#define PREFIX "DMAR:"

/* No locks are needed as DMA remapping hardware unit
 * list is constructed at boot time and hotplug of
 * these units are not supported by the architecture.
 */
LIST_HEAD(dmar_drhd_units);

static struct acpi_table_header * __initdata dmar_tbl;
45
static acpi_size dmar_tbl_size;
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177

static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
{
	/*
	 * add INCLUDE_ALL at the tail, so scan the list will find it at
	 * the very end.
	 */
	if (drhd->include_all)
		list_add_tail(&drhd->list, &dmar_drhd_units);
	else
		list_add(&drhd->list, &dmar_drhd_units);
}

static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
					   struct pci_dev **dev, u16 segment)
{
	struct pci_bus *bus;
	struct pci_dev *pdev = NULL;
	struct acpi_dmar_pci_path *path;
	int count;

	bus = pci_find_bus(segment, scope->bus);
	path = (struct acpi_dmar_pci_path *)(scope + 1);
	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
		/ sizeof(struct acpi_dmar_pci_path);

	while (count) {
		if (pdev)
			pci_dev_put(pdev);
		/*
		 * Some BIOSes list non-exist devices in DMAR table, just
		 * ignore it
		 */
		if (!bus) {
			printk(KERN_WARNING
			PREFIX "Device scope bus [%d] not found\n",
			scope->bus);
			break;
		}
		pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn));
		if (!pdev) {
			printk(KERN_WARNING PREFIX
			"Device scope device [%04x:%02x:%02x.%02x] not found\n",
				segment, bus->number, path->dev, path->fn);
			break;
		}
		path ++;
		count --;
		bus = pdev->subordinate;
	}
	if (!pdev) {
		printk(KERN_WARNING PREFIX
		"Device scope device [%04x:%02x:%02x.%02x] not found\n",
		segment, scope->bus, path->dev, path->fn);
		*dev = NULL;
		return 0;
	}
	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
			pdev->subordinate) || (scope->entry_type == \
			ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
		pci_dev_put(pdev);
		printk(KERN_WARNING PREFIX
			"Device scope type does not match for %s\n",
			 pci_name(pdev));
		return -EINVAL;
	}
	*dev = pdev;
	return 0;
}

static int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
				       struct pci_dev ***devices, u16 segment)
{
	struct acpi_dmar_device_scope *scope;
	void * tmp = start;
	int index;
	int ret;

	*cnt = 0;
	while (start < end) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
			(*cnt)++;
		else
			printk(KERN_WARNING PREFIX
				"Unsupported device scope\n");
		start += scope->length;
	}
	if (*cnt == 0)
		return 0;

	*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
	if (!*devices)
		return -ENOMEM;

	start = tmp;
	index = 0;
	while (start < end) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
			ret = dmar_parse_one_dev_scope(scope,
				&(*devices)[index], segment);
			if (ret) {
				kfree(*devices);
				return ret;
			}
			index ++;
		}
		start += scope->length;
	}

	return 0;
}

/**
 * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
 * structure which uniquely represent one DMA remapping hardware unit
 * present in the platform
 */
static int __init
dmar_parse_one_drhd(struct acpi_dmar_header *header)
{
	struct acpi_dmar_hardware_unit *drhd;
	struct dmar_drhd_unit *dmaru;
	int ret = 0;

	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
	if (!dmaru)
		return -ENOMEM;

178
	dmaru->hdr = header;
179 180 181 182
	drhd = (struct acpi_dmar_hardware_unit *)header;
	dmaru->reg_base_addr = drhd->address;
	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */

183 184 185 186 187 188 189 190 191
	ret = alloc_iommu(dmaru);
	if (ret) {
		kfree(dmaru);
		return ret;
	}
	dmar_register_drhd_unit(dmaru);
	return 0;
}

192
static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
193 194
{
	struct acpi_dmar_hardware_unit *drhd;
195
	int ret = 0;
196 197 198

	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;

199 200 201 202
	if (dmaru->include_all)
		return 0;

	ret = dmar_parse_dev_scope((void *)(drhd + 1),
203
				((void *)drhd) + drhd->header.length,
204 205
				&dmaru->devices_cnt, &dmaru->devices,
				drhd->segment);
206
	if (ret) {
207
		list_del(&dmaru->list);
208
		kfree(dmaru);
209
	}
210 211 212
	return ret;
}

213 214 215 216 217 218 219 220 221
#ifdef CONFIG_DMAR
LIST_HEAD(dmar_rmrr_units);

static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
{
	list_add(&rmrr->list, &dmar_rmrr_units);
}


222 223 224 225 226 227 228 229 230 231
static int __init
dmar_parse_one_rmrr(struct acpi_dmar_header *header)
{
	struct acpi_dmar_reserved_memory *rmrr;
	struct dmar_rmrr_unit *rmrru;

	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
	if (!rmrru)
		return -ENOMEM;

232
	rmrru->hdr = header;
233 234 235
	rmrr = (struct acpi_dmar_reserved_memory *)header;
	rmrru->base_address = rmrr->base_address;
	rmrru->end_address = rmrr->end_address;
236 237 238 239 240 241 242 243 244 245 246 247

	dmar_register_rmrr_unit(rmrru);
	return 0;
}

static int __init
rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
{
	struct acpi_dmar_reserved_memory *rmrr;
	int ret;

	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
248
	ret = dmar_parse_dev_scope((void *)(rmrr + 1),
249
		((void *)rmrr) + rmrr->header.length,
250 251
		&rmrru->devices_cnt, &rmrru->devices, rmrr->segment);

252 253
	if (ret || (rmrru->devices_cnt == 0)) {
		list_del(&rmrru->list);
254
		kfree(rmrru);
255
	}
256 257
	return ret;
}
258
#endif
259 260 261 262 263 264 265 266 267 268 269 270

static void __init
dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
{
	struct acpi_dmar_hardware_unit *drhd;
	struct acpi_dmar_reserved_memory *rmrr;

	switch (header->type) {
	case ACPI_DMAR_TYPE_HARDWARE_UNIT:
		drhd = (struct acpi_dmar_hardware_unit *)header;
		printk (KERN_INFO PREFIX
			"DRHD (flags: 0x%08x)base: 0x%016Lx\n",
F
Fenghua Yu 已提交
271
			drhd->flags, (unsigned long long)drhd->address);
272 273 274 275 276 277
		break;
	case ACPI_DMAR_TYPE_RESERVED_MEMORY:
		rmrr = (struct acpi_dmar_reserved_memory *)header;

		printk (KERN_INFO PREFIX
			"RMRR base: 0x%016Lx end: 0x%016Lx\n",
F
Fenghua Yu 已提交
278 279
			(unsigned long long)rmrr->base_address,
			(unsigned long long)rmrr->end_address);
280 281 282 283
		break;
	}
}

284 285 286 287 288 289 290 291
/**
 * dmar_table_detect - checks to see if the platform supports DMAR devices
 */
static int __init dmar_table_detect(void)
{
	acpi_status status = AE_OK;

	/* if we could find DMAR table, then there are DMAR devices */
292 293 294
	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
				(struct acpi_table_header **)&dmar_tbl,
				&dmar_tbl_size);
295 296 297 298 299 300 301 302

	if (ACPI_SUCCESS(status) && !dmar_tbl) {
		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
		status = AE_NOT_FOUND;
	}

	return (ACPI_SUCCESS(status) ? 1 : 0);
}
303

304 305 306 307 308 309 310 311 312 313
/**
 * parse_dmar_table - parses the DMA reporting table
 */
static int __init
parse_dmar_table(void)
{
	struct acpi_table_dmar *dmar;
	struct acpi_dmar_header *entry_header;
	int ret = 0;

314 315 316 317 318 319
	/*
	 * Do it again, earlier dmar_tbl mapping could be mapped with
	 * fixed map.
	 */
	dmar_table_detect();

320 321 322 323
	dmar = (struct acpi_table_dmar *)dmar_tbl;
	if (!dmar)
		return -ENODEV;

F
Fenghua Yu 已提交
324
	if (dmar->width < PAGE_SHIFT - 1) {
F
Fenghua Yu 已提交
325
		printk(KERN_WARNING PREFIX "Invalid DMAR haw\n");
326 327 328 329 330 331 332 333 334
		return -EINVAL;
	}

	printk (KERN_INFO PREFIX "Host address width %d\n",
		dmar->width + 1);

	entry_header = (struct acpi_dmar_header *)(dmar + 1);
	while (((unsigned long)entry_header) <
			(((unsigned long)dmar) + dmar_tbl->length)) {
335 336 337 338 339 340 341 342
		/* Avoid looping forever on bad ACPI tables */
		if (entry_header->length == 0) {
			printk(KERN_WARNING PREFIX
				"Invalid 0-length structure\n");
			ret = -EINVAL;
			break;
		}

343 344 345 346 347 348 349
		dmar_table_print_dmar_entry(entry_header);

		switch (entry_header->type) {
		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
			ret = dmar_parse_one_drhd(entry_header);
			break;
		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
350
#ifdef CONFIG_DMAR
351
			ret = dmar_parse_one_rmrr(entry_header);
352
#endif
353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
			break;
		default:
			printk(KERN_WARNING PREFIX
				"Unknown DMAR structure type\n");
			ret = 0; /* for forward compatibility */
			break;
		}
		if (ret)
			break;

		entry_header = ((void *)entry_header + entry_header->length);
	}
	return ret;
}

368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
			  struct pci_dev *dev)
{
	int index;

	while (dev) {
		for (index = 0; index < cnt; index++)
			if (dev == devices[index])
				return 1;

		/* Check our parent */
		dev = dev->bus->self;
	}

	return 0;
}

struct dmar_drhd_unit *
dmar_find_matched_drhd_unit(struct pci_dev *dev)
{
388 389 390 391 392 393 394 395 396 397 398
	struct dmar_drhd_unit *dmaru = NULL;
	struct acpi_dmar_hardware_unit *drhd;

	list_for_each_entry(dmaru, &dmar_drhd_units, list) {
		drhd = container_of(dmaru->hdr,
				    struct acpi_dmar_hardware_unit,
				    header);

		if (dmaru->include_all &&
		    drhd->segment == pci_domain_nr(dev->bus))
			return dmaru;
399

400 401 402
		if (dmar_pci_device_match(dmaru->devices,
					  dmaru->devices_cnt, dev))
			return dmaru;
403 404 405 406 407
	}

	return NULL;
}

408 409
int __init dmar_dev_scope_init(void)
{
410
	struct dmar_drhd_unit *drhd, *drhd_n;
411 412
	int ret = -ENODEV;

413
	list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
414 415 416 417 418
		ret = dmar_parse_dev(drhd);
		if (ret)
			return ret;
	}

419 420
#ifdef CONFIG_DMAR
	{
421 422
		struct dmar_rmrr_unit *rmrr, *rmrr_n;
		list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
423 424 425 426
			ret = rmrr_parse_dev(rmrr);
			if (ret)
				return ret;
		}
427
	}
428
#endif
429 430 431 432

	return ret;
}

433 434 435

int __init dmar_table_init(void)
{
436
	static int dmar_table_initialized;
F
Fenghua Yu 已提交
437 438
	int ret;

439 440 441 442 443
	if (dmar_table_initialized)
		return 0;

	dmar_table_initialized = 1;

F
Fenghua Yu 已提交
444 445
	ret = parse_dmar_table();
	if (ret) {
446 447
		if (ret != -ENODEV)
			printk(KERN_INFO PREFIX "parse DMAR table failure.\n");
F
Fenghua Yu 已提交
448 449 450
		return ret;
	}

451 452 453 454
	if (list_empty(&dmar_drhd_units)) {
		printk(KERN_INFO PREFIX "No DMAR devices found\n");
		return -ENODEV;
	}
F
Fenghua Yu 已提交
455

456
#ifdef CONFIG_DMAR
457
	if (list_empty(&dmar_rmrr_units))
F
Fenghua Yu 已提交
458
		printk(KERN_INFO PREFIX "No RMRR found\n");
459
#endif
F
Fenghua Yu 已提交
460

461 462 463
#ifdef CONFIG_INTR_REMAP
	parse_ioapics_under_ir();
#endif
464 465 466
	return 0;
}

467 468 469 470
void __init detect_intel_iommu(void)
{
	int ret;

471
	ret = dmar_table_detect();
472 473

	{
474
#ifdef CONFIG_INTR_REMAP
475 476 477 478 479 480 481 482
		struct acpi_table_dmar *dmar;
		/*
		 * for now we will disable dma-remapping when interrupt
		 * remapping is enabled.
		 * When support for queued invalidation for IOTLB invalidation
		 * is added, we will not need this any more.
		 */
		dmar = (struct acpi_table_dmar *) dmar_tbl;
483
		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
484 485 486
			printk(KERN_INFO
			       "Queued invalidation will be enabled to support "
			       "x2apic and Intr-remapping.\n");
487 488
#endif
#ifdef CONFIG_DMAR
489 490 491 492
		if (ret && !no_iommu && !iommu_detected && !swiotlb &&
		    !dmar_disabled)
			iommu_detected = 1;
#endif
493
	}
494
	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
495
	dmar_tbl = NULL;
496 497 498
}


499
int alloc_iommu(struct dmar_drhd_unit *drhd)
500
{
501
	struct intel_iommu *iommu;
502 503
	int map_size;
	u32 ver;
504
	static int iommu_allocated = 0;
505
	int agaw = 0;
506 507 508

	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
	if (!iommu)
509
		return -ENOMEM;
510 511

	iommu->seq_id = iommu_allocated++;
512

F
Fenghua Yu 已提交
513
	iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
514 515 516 517 518 519 520
	if (!iommu->reg) {
		printk(KERN_ERR "IOMMU: can't map the region\n");
		goto error;
	}
	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);

521
#ifdef CONFIG_DMAR
W
Weidong Han 已提交
522 523 524 525 526 527 528
	agaw = iommu_calculate_agaw(iommu);
	if (agaw < 0) {
		printk(KERN_ERR
			"Cannot get a valid agaw for iommu (seq_id = %d)\n",
			iommu->seq_id);
		goto error;
	}
529
#endif
W
Weidong Han 已提交
530 531
	iommu->agaw = agaw;

532 533 534
	/* the registers might be more than one page */
	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
		cap_max_fault_reg_offset(iommu->cap));
F
Fenghua Yu 已提交
535 536
	map_size = VTD_PAGE_ALIGN(map_size);
	if (map_size > VTD_PAGE_SIZE) {
537 538 539 540 541 542 543 544 545 546
		iounmap(iommu->reg);
		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
		if (!iommu->reg) {
			printk(KERN_ERR "IOMMU: can't map the region\n");
			goto error;
		}
	}

	ver = readl(iommu->reg + DMAR_VER_REG);
	pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
F
Fenghua Yu 已提交
547 548 549 550
		(unsigned long long)drhd->reg_base_addr,
		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
		(unsigned long long)iommu->cap,
		(unsigned long long)iommu->ecap);
551 552 553 554

	spin_lock_init(&iommu->register_lock);

	drhd->iommu = iommu;
555
	return 0;
556 557
error:
	kfree(iommu);
558
	return -1;
559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
}

void free_iommu(struct intel_iommu *iommu)
{
	if (!iommu)
		return;

#ifdef CONFIG_DMAR
	free_dmar_iommu(iommu);
#endif

	if (iommu->reg)
		iounmap(iommu->reg);
	kfree(iommu);
}
574 575 576 577 578 579 580 581 582 583 584 585 586

/*
 * Reclaim all the submitted descriptors which have completed its work.
 */
static inline void reclaim_free_desc(struct q_inval *qi)
{
	while (qi->desc_status[qi->free_tail] == QI_DONE) {
		qi->desc_status[qi->free_tail] = QI_FREE;
		qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
		qi->free_cnt++;
	}
}

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
static int qi_check_fault(struct intel_iommu *iommu, int index)
{
	u32 fault;
	int head;
	struct q_inval *qi = iommu->qi;
	int wait_index = (index + 1) % QI_LENGTH;

	fault = readl(iommu->reg + DMAR_FSTS_REG);

	/*
	 * If IQE happens, the head points to the descriptor associated
	 * with the error. No new descriptors are fetched until the IQE
	 * is cleared.
	 */
	if (fault & DMA_FSTS_IQE) {
		head = readl(iommu->reg + DMAR_IQH_REG);
		if ((head >> 4) == index) {
			memcpy(&qi->desc[index], &qi->desc[wait_index],
					sizeof(struct qi_desc));
			__iommu_flush_cache(iommu, &qi->desc[index],
					sizeof(struct qi_desc));
			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
			return -EINVAL;
		}
	}

	return 0;
}

616 617 618 619
/*
 * Submit the queued invalidation descriptor to the remapping
 * hardware unit and wait for its completion.
 */
620
int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
621
{
622
	int rc = 0;
623 624 625 626 627 628
	struct q_inval *qi = iommu->qi;
	struct qi_desc *hw, wait_desc;
	int wait_index, index;
	unsigned long flags;

	if (!qi)
629
		return 0;
630 631 632

	hw = qi->desc;

633
	spin_lock_irqsave(&qi->q_lock, flags);
634
	while (qi->free_cnt < 3) {
635
		spin_unlock_irqrestore(&qi->q_lock, flags);
636
		cpu_relax();
637
		spin_lock_irqsave(&qi->q_lock, flags);
638 639 640 641 642 643 644 645 646
	}

	index = qi->free_head;
	wait_index = (index + 1) % QI_LENGTH;

	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;

	hw[index] = *desc;

647 648
	wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);

	hw[wait_index] = wait_desc;

	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));

	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
	qi->free_cnt -= 2;

	/*
	 * update the HW tail register indicating the presence of
	 * new descriptors.
	 */
	writel(qi->free_head << 4, iommu->reg + DMAR_IQT_REG);

	while (qi->desc_status[wait_index] != QI_DONE) {
666 667 668 669 670 671 672
		/*
		 * We will leave the interrupts disabled, to prevent interrupt
		 * context to queue another cmd while a cmd is already submitted
		 * and waiting for completion on this cpu. This is to avoid
		 * a deadlock where the interrupt context can wait indefinitely
		 * for free slots in the queue.
		 */
673 674 675 676
		rc = qi_check_fault(iommu, index);
		if (rc)
			goto out;

677 678 679 680
		spin_unlock(&qi->q_lock);
		cpu_relax();
		spin_lock(&qi->q_lock);
	}
681 682
out:
	qi->desc_status[index] = qi->desc_status[wait_index] = QI_DONE;
683 684

	reclaim_free_desc(qi);
685
	spin_unlock_irqrestore(&qi->q_lock, flags);
686 687

	return rc;
688 689 690 691 692 693 694 695 696 697 698 699
}

/*
 * Flush the global interrupt entry cache.
 */
void qi_global_iec(struct intel_iommu *iommu)
{
	struct qi_desc desc;

	desc.low = QI_IEC_TYPE;
	desc.high = 0;

700
	/* should never fail */
701 702 703
	qi_submit_sync(&desc, iommu);
}

704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
		     u64 type, int non_present_entry_flush)
{
	struct qi_desc desc;

	if (non_present_entry_flush) {
		if (!cap_caching_mode(iommu->cap))
			return 1;
		else
			did = 0;
	}

	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
			| QI_CC_GRAN(type) | QI_CC_TYPE;
	desc.high = 0;

720
	return qi_submit_sync(&desc, iommu);
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
}

int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
		   unsigned int size_order, u64 type,
		   int non_present_entry_flush)
{
	u8 dw = 0, dr = 0;

	struct qi_desc desc;
	int ih = 0;

	if (non_present_entry_flush) {
		if (!cap_caching_mode(iommu->cap))
			return 1;
		else
			did = 0;
	}

	if (cap_write_drain(iommu->cap))
		dw = 1;

	if (cap_read_drain(iommu->cap))
		dr = 1;

	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
		| QI_IOTLB_AM(size_order);

750
	return qi_submit_sync(&desc, iommu);
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
/*
 * Enable Queued Invalidation interface. This is a must to support
 * interrupt-remapping. Also used by DMA-remapping, which replaces
 * register based IOTLB invalidation.
 */
int dmar_enable_qi(struct intel_iommu *iommu)
{
	u32 cmd, sts;
	unsigned long flags;
	struct q_inval *qi;

	if (!ecap_qis(iommu->ecap))
		return -ENOENT;

	/*
	 * queued invalidation is already setup and enabled.
	 */
	if (iommu->qi)
		return 0;

	iommu->qi = kmalloc(sizeof(*qi), GFP_KERNEL);
	if (!iommu->qi)
		return -ENOMEM;

	qi = iommu->qi;

	qi->desc = (void *)(get_zeroed_page(GFP_KERNEL));
	if (!qi->desc) {
		kfree(qi);
		iommu->qi = 0;
		return -ENOMEM;
	}

	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_KERNEL);
	if (!qi->desc_status) {
		free_page((unsigned long) qi->desc);
		kfree(qi);
		iommu->qi = 0;
		return -ENOMEM;
	}

	qi->free_head = qi->free_tail = 0;
	qi->free_cnt = QI_LENGTH;

	spin_lock_init(&qi->q_lock);

	spin_lock_irqsave(&iommu->register_lock, flags);
	/* write zero to the tail reg */
	writel(0, iommu->reg + DMAR_IQT_REG);

	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));

	cmd = iommu->gcmd | DMA_GCMD_QIE;
	iommu->gcmd |= DMA_GCMD_QIE;
	writel(cmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_QIES), sts);
	spin_unlock_irqrestore(&iommu->register_lock, flags);

	return 0;
}