iommu.c 42.9 KB
Newer Older
1 2
/*
 * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
J
Joerg Roedel 已提交
3
 * Author: Joerg Roedel <jroedel@suse.de>
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation.
 *
 * This program is distributed in the hope that 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
 */

19
#define pr_fmt(fmt)    "iommu: " fmt
20

21
#include <linux/device.h>
22
#include <linux/kernel.h>
23 24
#include <linux/bug.h>
#include <linux/types.h>
25 26
#include <linux/module.h>
#include <linux/slab.h>
27 28
#include <linux/errno.h>
#include <linux/iommu.h>
A
Alex Williamson 已提交
29 30 31
#include <linux/idr.h>
#include <linux/notifier.h>
#include <linux/err.h>
32
#include <linux/pci.h>
33
#include <linux/bitops.h>
R
Robin Murphy 已提交
34
#include <linux/property.h>
35
#include <trace/events/iommu.h>
A
Alex Williamson 已提交
36 37

static struct kset *iommu_group_kset;
H
Heiner Kallweit 已提交
38
static DEFINE_IDA(iommu_group_ida);
A
Alex Williamson 已提交
39

40 41 42 43
struct iommu_callback_data {
	const struct iommu_ops *ops;
};

A
Alex Williamson 已提交
44 45 46 47 48 49 50 51 52 53
struct iommu_group {
	struct kobject kobj;
	struct kobject *devices_kobj;
	struct list_head devices;
	struct mutex mutex;
	struct blocking_notifier_head notifier;
	void *iommu_data;
	void (*iommu_data_release)(void *iommu_data);
	char *name;
	int id;
54
	struct iommu_domain *default_domain;
55
	struct iommu_domain *domain;
A
Alex Williamson 已提交
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73
};

struct iommu_device {
	struct list_head list;
	struct device *dev;
	char *name;
};

struct iommu_group_attribute {
	struct attribute attr;
	ssize_t (*show)(struct iommu_group *group, char *buf);
	ssize_t (*store)(struct iommu_group *group,
			 const char *buf, size_t count);
};

#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
struct iommu_group_attribute iommu_group_attr_##_name =		\
	__ATTR(_name, _mode, _show, _store)
74

A
Alex Williamson 已提交
75 76 77 78
#define to_iommu_group_attr(_attr)	\
	container_of(_attr, struct iommu_group_attribute, attr)
#define to_iommu_group(_kobj)		\
	container_of(_kobj, struct iommu_group, kobj)
79

80 81
static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
						 unsigned type);
82 83 84 85 86 87
static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev);
static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group);
static void __iommu_detach_group(struct iommu_domain *domain,
				 struct iommu_group *group);
88

A
Alex Williamson 已提交
89 90
static ssize_t iommu_group_attr_show(struct kobject *kobj,
				     struct attribute *__attr, char *buf)
91
{
A
Alex Williamson 已提交
92 93 94
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;
95

A
Alex Williamson 已提交
96 97 98 99 100 101 102 103 104 105 106 107
	if (attr->show)
		ret = attr->show(group, buf);
	return ret;
}

static ssize_t iommu_group_attr_store(struct kobject *kobj,
				      struct attribute *__attr,
				      const char *buf, size_t count)
{
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;
108

A
Alex Williamson 已提交
109 110 111
	if (attr->store)
		ret = attr->store(group, buf, count);
	return ret;
112 113
}

A
Alex Williamson 已提交
114 115 116 117
static const struct sysfs_ops iommu_group_sysfs_ops = {
	.show = iommu_group_attr_show,
	.store = iommu_group_attr_store,
};
118

A
Alex Williamson 已提交
119 120 121 122
static int iommu_group_create_file(struct iommu_group *group,
				   struct iommu_group_attribute *attr)
{
	return sysfs_create_file(&group->kobj, &attr->attr);
123 124
}

A
Alex Williamson 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141
static void iommu_group_remove_file(struct iommu_group *group,
				    struct iommu_group_attribute *attr)
{
	sysfs_remove_file(&group->kobj, &attr->attr);
}

static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
{
	return sprintf(buf, "%s\n", group->name);
}

static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);

static void iommu_group_release(struct kobject *kobj)
{
	struct iommu_group *group = to_iommu_group(kobj);

142 143
	pr_debug("Releasing group %d\n", group->id);

A
Alex Williamson 已提交
144 145 146
	if (group->iommu_data_release)
		group->iommu_data_release(group->iommu_data);

147
	ida_simple_remove(&iommu_group_ida, group->id);
A
Alex Williamson 已提交
148

149 150 151
	if (group->default_domain)
		iommu_domain_free(group->default_domain);

A
Alex Williamson 已提交
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
	kfree(group->name);
	kfree(group);
}

static struct kobj_type iommu_group_ktype = {
	.sysfs_ops = &iommu_group_sysfs_ops,
	.release = iommu_group_release,
};

/**
 * iommu_group_alloc - Allocate a new group
 * @name: Optional name to associate with group, visible in sysfs
 *
 * This function is called by an iommu driver to allocate a new iommu
 * group.  The iommu group represents the minimum granularity of the iommu.
 * Upon successful return, the caller holds a reference to the supplied
 * group in order to hold the group until devices are added.  Use
 * iommu_group_put() to release this extra reference count, allowing the
 * group to be automatically reclaimed once it has no devices or external
 * references.
 */
struct iommu_group *iommu_group_alloc(void)
174
{
A
Alex Williamson 已提交
175 176 177 178 179 180 181 182 183 184 185 186
	struct iommu_group *group;
	int ret;

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

	group->kobj.kset = iommu_group_kset;
	mutex_init(&group->mutex);
	INIT_LIST_HEAD(&group->devices);
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

187 188
	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
	if (ret < 0) {
A
Alex Williamson 已提交
189
		kfree(group);
190
		return ERR_PTR(ret);
A
Alex Williamson 已提交
191
	}
192
	group->id = ret;
193

A
Alex Williamson 已提交
194 195 196
	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
				   NULL, "%d", group->id);
	if (ret) {
197
		ida_simple_remove(&iommu_group_ida, group->id);
A
Alex Williamson 已提交
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
		kfree(group);
		return ERR_PTR(ret);
	}

	group->devices_kobj = kobject_create_and_add("devices", &group->kobj);
	if (!group->devices_kobj) {
		kobject_put(&group->kobj); /* triggers .release & free */
		return ERR_PTR(-ENOMEM);
	}

	/*
	 * The devices_kobj holds a reference on the group kobject, so
	 * as long as that exists so will the group.  We can therefore
	 * use the devices_kobj for reference counting.
	 */
	kobject_put(&group->kobj);

215 216
	pr_debug("Allocated group %d\n", group->id);

A
Alex Williamson 已提交
217 218 219 220
	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_alloc);

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
struct iommu_group *iommu_group_get_by_id(int id)
{
	struct kobject *group_kobj;
	struct iommu_group *group;
	const char *name;

	if (!iommu_group_kset)
		return NULL;

	name = kasprintf(GFP_KERNEL, "%d", id);
	if (!name)
		return NULL;

	group_kobj = kset_find_obj(iommu_group_kset, name);
	kfree(name);

	if (!group_kobj)
		return NULL;

	group = container_of(group_kobj, struct iommu_group, kobj);
	BUG_ON(group->id != id);

	kobject_get(group->devices_kobj);
	kobject_put(&group->kobj);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_get_by_id);

A
Alex Williamson 已提交
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275
/**
 * iommu_group_get_iommudata - retrieve iommu_data registered for a group
 * @group: the group
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to retrieve it.  Caller
 * should hold a group reference.
 */
void *iommu_group_get_iommudata(struct iommu_group *group)
{
	return group->iommu_data;
}
EXPORT_SYMBOL_GPL(iommu_group_get_iommudata);

/**
 * iommu_group_set_iommudata - set iommu_data for a group
 * @group: the group
 * @iommu_data: new data
 * @release: release function for iommu_data
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to set the data after
 * the group has been allocated.  Caller should hold a group reference.
 */
void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data,
			       void (*release)(void *iommu_data))
276
{
A
Alex Williamson 已提交
277 278 279 280
	group->iommu_data = iommu_data;
	group->iommu_data_release = release;
}
EXPORT_SYMBOL_GPL(iommu_group_set_iommudata);
281

A
Alex Williamson 已提交
282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
/**
 * iommu_group_set_name - set name for a group
 * @group: the group
 * @name: name
 *
 * Allow iommu driver to set a name for a group.  When set it will
 * appear in a name attribute file under the group in sysfs.
 */
int iommu_group_set_name(struct iommu_group *group, const char *name)
{
	int ret;

	if (group->name) {
		iommu_group_remove_file(group, &iommu_group_attr_name);
		kfree(group->name);
		group->name = NULL;
		if (!name)
			return 0;
	}

	group->name = kstrdup(name, GFP_KERNEL);
	if (!group->name)
		return -ENOMEM;

	ret = iommu_group_create_file(group, &iommu_group_attr_name);
	if (ret) {
		kfree(group->name);
		group->name = NULL;
		return ret;
	}
312 313 314

	return 0;
}
A
Alex Williamson 已提交
315
EXPORT_SYMBOL_GPL(iommu_group_set_name);
316

317 318 319 320
static int iommu_group_create_direct_mappings(struct iommu_group *group,
					      struct device *dev)
{
	struct iommu_domain *domain = group->default_domain;
321
	struct iommu_resv_region *entry;
322 323 324 325 326 327 328
	struct list_head mappings;
	unsigned long pg_size;
	int ret = 0;

	if (!domain || domain->type != IOMMU_DOMAIN_DMA)
		return 0;

329
	BUG_ON(!domain->pgsize_bitmap);
330

331
	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
332 333
	INIT_LIST_HEAD(&mappings);

334
	iommu_get_resv_regions(dev, &mappings);
335 336 337 338 339

	/* We need to consider overlapping regions for different devices */
	list_for_each_entry(entry, &mappings, list) {
		dma_addr_t start, end, addr;

340 341
		if (domain->ops->apply_resv_region)
			domain->ops->apply_resv_region(dev, domain, entry);
342

343 344 345
		start = ALIGN(entry->start, pg_size);
		end   = ALIGN(entry->start + entry->length, pg_size);

346 347 348
		if (entry->type != IOMMU_RESV_DIRECT)
			continue;

349 350 351 352 353 354 355 356 357 358 359 360 361 362 363
		for (addr = start; addr < end; addr += pg_size) {
			phys_addr_t phys_addr;

			phys_addr = iommu_iova_to_phys(domain, addr);
			if (phys_addr)
				continue;

			ret = iommu_map(domain, addr, addr, pg_size, entry->prot);
			if (ret)
				goto out;
		}

	}

out:
364
	iommu_put_resv_regions(dev, &mappings);
365 366 367 368

	return ret;
}

A
Alex Williamson 已提交
369 370 371 372 373 374 375 376 377
/**
 * iommu_group_add_device - add a device to an iommu group
 * @group: the group into which to add the device (reference should be held)
 * @dev: the device
 *
 * This function is called by an iommu driver to add a device into a
 * group.  Adding a device increments the group reference count.
 */
int iommu_group_add_device(struct iommu_group *group, struct device *dev)
378
{
A
Alex Williamson 已提交
379 380 381 382 383 384 385 386
	int ret, i = 0;
	struct iommu_device *device;

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

	device->dev = dev;
387

A
Alex Williamson 已提交
388 389 390 391 392 393 394 395 396 397 398 399 400
	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
	if (ret) {
		kfree(device);
		return ret;
	}

	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
rename:
	if (!device->name) {
		sysfs_remove_link(&dev->kobj, "iommu_group");
		kfree(device);
		return -ENOMEM;
	}
401

A
Alex Williamson 已提交
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
	ret = sysfs_create_link_nowarn(group->devices_kobj,
				       &dev->kobj, device->name);
	if (ret) {
		kfree(device->name);
		if (ret == -EEXIST && i >= 0) {
			/*
			 * Account for the slim chance of collision
			 * and append an instance to the name.
			 */
			device->name = kasprintf(GFP_KERNEL, "%s.%d",
						 kobject_name(&dev->kobj), i++);
			goto rename;
		}

		sysfs_remove_link(&dev->kobj, "iommu_group");
		kfree(device);
		return ret;
	}

	kobject_get(group->devices_kobj);

	dev->iommu_group = group;

425 426
	iommu_group_create_direct_mappings(group, dev);

A
Alex Williamson 已提交
427 428
	mutex_lock(&group->mutex);
	list_add_tail(&device->list, &group->devices);
429 430
	if (group->domain)
		__iommu_attach_device(group->domain, dev);
A
Alex Williamson 已提交
431 432 433 434 435
	mutex_unlock(&group->mutex);

	/* Notify any listeners about change to group. */
	blocking_notifier_call_chain(&group->notifier,
				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
436 437

	trace_add_device_to_group(group->id, dev);
438 439 440

	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);

441 442
	return 0;
}
A
Alex Williamson 已提交
443
EXPORT_SYMBOL_GPL(iommu_group_add_device);
444

A
Alex Williamson 已提交
445 446 447 448 449 450 451 452 453 454 455 456
/**
 * iommu_group_remove_device - remove a device from it's current group
 * @dev: device to be removed
 *
 * This function is called by an iommu driver to remove the device from
 * it's current group.  This decrements the iommu group reference count.
 */
void iommu_group_remove_device(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;
	struct iommu_device *tmp_device, *device = NULL;

457 458
	pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);

A
Alex Williamson 已提交
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478
	/* Pre-notify listeners that a device is being removed. */
	blocking_notifier_call_chain(&group->notifier,
				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);

	mutex_lock(&group->mutex);
	list_for_each_entry(tmp_device, &group->devices, list) {
		if (tmp_device->dev == dev) {
			device = tmp_device;
			list_del(&device->list);
			break;
		}
	}
	mutex_unlock(&group->mutex);

	if (!device)
		return;

	sysfs_remove_link(group->devices_kobj, device->name);
	sysfs_remove_link(&dev->kobj, "iommu_group");

479 480
	trace_remove_device_from_group(group->id, dev);

A
Alex Williamson 已提交
481 482 483 484 485 486 487
	kfree(device->name);
	kfree(device);
	dev->iommu_group = NULL;
	kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_remove_device);

488 489 490 491 492 493 494 495 496 497 498
static int iommu_group_device_count(struct iommu_group *group)
{
	struct iommu_device *entry;
	int ret = 0;

	list_for_each_entry(entry, &group->devices, list)
		ret++;

	return ret;
}

A
Alex Williamson 已提交
499 500 501 502 503 504 505 506 507 508 509
/**
 * iommu_group_for_each_dev - iterate over each device in the group
 * @group: the group
 * @data: caller opaque data to be passed to callback function
 * @fn: caller supplied callback function
 *
 * This function is called by group users to iterate over group devices.
 * Callers should hold a reference count to the group during callback.
 * The group->mutex is held across callbacks, which will block calls to
 * iommu_group_add/remove_device.
 */
510 511
static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
				      int (*fn)(struct device *, void *))
A
Alex Williamson 已提交
512 513 514 515 516 517 518 519 520
{
	struct iommu_device *device;
	int ret = 0;

	list_for_each_entry(device, &group->devices, list) {
		ret = fn(device->dev, data);
		if (ret)
			break;
	}
521 522 523 524 525 526 527 528 529 530 531
	return ret;
}


int iommu_group_for_each_dev(struct iommu_group *group, void *data,
			     int (*fn)(struct device *, void *))
{
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_group_for_each_dev(group, data, fn);
A
Alex Williamson 已提交
532
	mutex_unlock(&group->mutex);
533

A
Alex Williamson 已提交
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);

/**
 * iommu_group_get - Return the group for a device and increment reference
 * @dev: get the group that this device belongs to
 *
 * This function is called by iommu drivers and users to get the group
 * for the specified device.  If found, the group is returned and the group
 * reference in incremented, else NULL.
 */
struct iommu_group *iommu_group_get(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;

	if (group)
		kobject_get(group->devices_kobj);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_get);

557 558 559 560 561 562 563 564 565 566 567 568 569
/**
 * iommu_group_ref_get - Increment reference on a group
 * @group: the group to use, must not be NULL
 *
 * This function is called by iommu drivers to take additional references on an
 * existing group.  Returns the given group for convenience.
 */
struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
{
	kobject_get(group->devices_kobj);
	return group;
}

A
Alex Williamson 已提交
570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
/**
 * iommu_group_put - Decrement group reference
 * @group: the group to use
 *
 * This function is called by iommu drivers and users to release the
 * iommu group.  Once the reference count is zero, the group is released.
 */
void iommu_group_put(struct iommu_group *group)
{
	if (group)
		kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_put);

/**
 * iommu_group_register_notifier - Register a notifier for group changes
 * @group: the group to watch
 * @nb: notifier block to signal
 *
 * This function allows iommu group users to track changes in a group.
 * See include/linux/iommu.h for actions sent via this notifier.  Caller
 * should hold a reference to the group throughout notifier registration.
 */
int iommu_group_register_notifier(struct iommu_group *group,
				  struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&group->notifier, nb);
}
EXPORT_SYMBOL_GPL(iommu_group_register_notifier);

/**
 * iommu_group_unregister_notifier - Unregister a notifier
 * @group: the group to watch
 * @nb: notifier block to signal
 *
 * Unregister a previously registered group notifier block.
 */
int iommu_group_unregister_notifier(struct iommu_group *group,
				    struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&group->notifier, nb);
}
EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);

/**
 * iommu_group_id - Return ID for a group
 * @group: the group to ID
 *
 * Return the unique ID for the group matching the sysfs group number.
 */
int iommu_group_id(struct iommu_group *group)
{
	return group->id;
}
EXPORT_SYMBOL_GPL(iommu_group_id);
625

626 627 628
static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns);

629 630 631 632 633 634 635 636 637 638
/*
 * To consider a PCI device isolated, we require ACS to support Source
 * Validation, Request Redirection, Completer Redirection, and Upstream
 * Forwarding.  This effectively means that devices cannot spoof their
 * requester ID, requests and completions cannot be redirected, and all
 * transactions are forwarded upstream, even as it passes through a
 * bridge where the target device is downstream.
 */
#define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)

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
/*
 * For multifunction devices which are not isolated from each other, find
 * all the other non-isolated functions and look for existing groups.  For
 * each function, we also need to look for aliases to or from other devices
 * that may already have a group.
 */
static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
							unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
		return NULL;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus ||
		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
			continue;

		group = get_pci_alias_group(tmp, devfns);
		if (group) {
			pci_dev_put(tmp);
			return group;
		}
	}

	return NULL;
}

/*
671 672
 * Look for aliases to or from the given device for existing groups. DMA
 * aliases are only supported on the same bus, therefore the search
673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
 * space is quite small (especially since we're really only looking at pcie
 * device, and therefore only expect multiple slots on the root complex or
 * downstream switch ports).  It's conceivable though that a pair of
 * multifunction devices could have aliases between them that would cause a
 * loop.  To prevent this, we use a bitmap to track where we've been.
 */
static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
		return NULL;

	group = iommu_group_get(&pdev->dev);
	if (group)
		return group;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus)
			continue;

		/* We alias them or they alias us */
697
		if (pci_devs_are_dma_aliases(pdev, tmp)) {
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714
			group = get_pci_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}

			group = get_pci_function_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}
		}
	}

	return NULL;
}

715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733
struct group_for_pci_data {
	struct pci_dev *pdev;
	struct iommu_group *group;
};

/*
 * DMA alias iterator callback, return the last seen device.  Stop and return
 * the IOMMU group if we find one along the way.
 */
static int get_pci_alias_or_group(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct group_for_pci_data *data = opaque;

	data->pdev = pdev;
	data->group = iommu_group_get(&pdev->dev);

	return data->group != NULL;
}

734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
/*
 * Generic device_group call-back function. It just allocates one
 * iommu-group per device.
 */
struct iommu_group *generic_device_group(struct device *dev)
{
	struct iommu_group *group;

	group = iommu_group_alloc();
	if (IS_ERR(group))
		return NULL;

	return group;
}

749 750 751 752
/*
 * Use standard PCI bus topology, isolation features, and DMA alias quirks
 * to find or create an IOMMU group for a device.
 */
753
struct iommu_group *pci_device_group(struct device *dev)
754
{
755
	struct pci_dev *pdev = to_pci_dev(dev);
756 757 758
	struct group_for_pci_data data;
	struct pci_bus *bus;
	struct iommu_group *group = NULL;
759
	u64 devfns[4] = { 0 };
760

761 762 763
	if (WARN_ON(!dev_is_pci(dev)))
		return ERR_PTR(-EINVAL);

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
	/*
	 * Find the upstream DMA alias for the device.  A device must not
	 * be aliased due to topology in order to have its own IOMMU group.
	 * If we find an alias along the way that already belongs to a
	 * group, use it.
	 */
	if (pci_for_each_dma_alias(pdev, get_pci_alias_or_group, &data))
		return data.group;

	pdev = data.pdev;

	/*
	 * Continue upstream from the point of minimum IOMMU granularity
	 * due to aliases to the point where devices are protected from
	 * peer-to-peer DMA by PCI ACS.  Again, if we find an existing
	 * group, use it.
	 */
	for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) {
		if (!bus->self)
			continue;

		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
			break;

		pdev = bus->self;

		group = iommu_group_get(&pdev->dev);
		if (group)
			return group;
	}

	/*
796 797
	 * Look for existing groups on device aliases.  If we alias another
	 * device or another device aliases us, use the same group.
798
	 */
799 800 801
	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;
802 803

	/*
804 805 806
	 * Look for existing groups on non-isolated functions on the same
	 * slot and aliases of those funcions, if any.  No need to clear
	 * the search bitmap, the tested devfns are still valid.
807
	 */
808 809 810
	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;
811 812

	/* No shared group found, allocate new */
813
	group = iommu_group_alloc();
814 815 816
	if (IS_ERR(group))
		return NULL;

817
	return group;
818 819 820 821 822 823 824 825 826 827 828 829 830 831
}

/**
 * iommu_group_get_for_dev - Find or create the IOMMU group for a device
 * @dev: target device
 *
 * This function is intended to be called by IOMMU drivers and extended to
 * support common, bus-defined algorithms when determining or creating the
 * IOMMU group for a device.  On success, the caller will hold a reference
 * to the returned IOMMU group, which will already include the provided
 * device.  The reference should be released with iommu_group_put().
 */
struct iommu_group *iommu_group_get_for_dev(struct device *dev)
{
832
	const struct iommu_ops *ops = dev->bus->iommu_ops;
833
	struct iommu_group *group;
834 835 836 837 838 839
	int ret;

	group = iommu_group_get(dev);
	if (group)
		return group;

840
	group = ERR_PTR(-EINVAL);
841

842 843
	if (ops && ops->device_group)
		group = ops->device_group(dev);
844 845 846 847

	if (IS_ERR(group))
		return group;

848 849 850 851 852 853 854
	/*
	 * Try to allocate a default domain - needs support from the
	 * IOMMU driver.
	 */
	if (!group->default_domain) {
		group->default_domain = __iommu_domain_alloc(dev->bus,
							     IOMMU_DOMAIN_DMA);
855 856
		if (!group->domain)
			group->domain = group->default_domain;
857 858
	}

859 860 861 862 863 864 865 866 867
	ret = iommu_group_add_device(group, dev);
	if (ret) {
		iommu_group_put(group);
		return ERR_PTR(ret);
	}

	return group;
}

868 869 870 871 872
struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
{
	return group->default_domain;
}

A
Alex Williamson 已提交
873
static int add_iommu_group(struct device *dev, void *data)
874
{
875 876
	struct iommu_callback_data *cb = data;
	const struct iommu_ops *ops = cb->ops;
877
	int ret;
A
Alex Williamson 已提交
878 879

	if (!ops->add_device)
880
		return 0;
881

A
Alex Williamson 已提交
882 883
	WARN_ON(dev->iommu_group);

884 885 886 887 888 889 890 891 892 893 894
	ret = ops->add_device(dev);

	/*
	 * We ignore -ENODEV errors for now, as they just mean that the
	 * device is not translated by an IOMMU. We still care about
	 * other errors and fail to initialize when they happen.
	 */
	if (ret == -ENODEV)
		ret = 0;

	return ret;
895 896
}

897 898 899 900 901 902 903
static int remove_iommu_group(struct device *dev, void *data)
{
	struct iommu_callback_data *cb = data;
	const struct iommu_ops *ops = cb->ops;

	if (ops->remove_device && dev->iommu_group)
		ops->remove_device(dev);
904 905 906 907

	return 0;
}

A
Alex Williamson 已提交
908 909
static int iommu_bus_notifier(struct notifier_block *nb,
			      unsigned long action, void *data)
910 911
{
	struct device *dev = data;
912
	const struct iommu_ops *ops = dev->bus->iommu_ops;
A
Alex Williamson 已提交
913 914 915 916 917 918 919 920 921 922
	struct iommu_group *group;
	unsigned long group_action = 0;

	/*
	 * ADD/DEL call into iommu driver ops if provided, which may
	 * result in ADD/DEL notifiers to group->notifier
	 */
	if (action == BUS_NOTIFY_ADD_DEVICE) {
		if (ops->add_device)
			return ops->add_device(dev);
923
	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
A
Alex Williamson 已提交
924 925 926 927 928
		if (ops->remove_device && dev->iommu_group) {
			ops->remove_device(dev);
			return 0;
		}
	}
929

A
Alex Williamson 已提交
930 931 932 933 934 935 936
	/*
	 * Remaining BUS_NOTIFYs get filtered and republished to the
	 * group, if anyone is listening
	 */
	group = iommu_group_get(dev);
	if (!group)
		return 0;
937

A
Alex Williamson 已提交
938 939 940 941 942 943 944 945 946 947 948 949 950 951
	switch (action) {
	case BUS_NOTIFY_BIND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER;
		break;
	case BUS_NOTIFY_BOUND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER;
		break;
	case BUS_NOTIFY_UNBIND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER;
		break;
	case BUS_NOTIFY_UNBOUND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER;
		break;
	}
952

A
Alex Williamson 已提交
953 954 955
	if (group_action)
		blocking_notifier_call_chain(&group->notifier,
					     group_action, dev);
956

A
Alex Williamson 已提交
957
	iommu_group_put(group);
958 959 960
	return 0;
}

M
Mark Salter 已提交
961
static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
962
{
M
Mark Salter 已提交
963 964
	int err;
	struct notifier_block *nb;
965 966 967 968
	struct iommu_callback_data cb = {
		.ops = ops,
	};

M
Mark Salter 已提交
969 970 971 972 973 974 975
	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
	if (!nb)
		return -ENOMEM;

	nb->notifier_call = iommu_bus_notifier;

	err = bus_register_notifier(bus, nb);
976 977
	if (err)
		goto out_free;
978 979

	err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
980 981 982
	if (err)
		goto out_err;

983 984

	return 0;
985 986 987 988 989 990 991 992 993 994

out_err:
	/* Clean up */
	bus_for_each_dev(bus, NULL, &cb, remove_iommu_group);
	bus_unregister_notifier(bus, nb);

out_free:
	kfree(nb);

	return err;
995
}
996

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
/**
 * bus_set_iommu - set iommu-callbacks for the bus
 * @bus: bus.
 * @ops: the callbacks provided by the iommu-driver
 *
 * This function is called by an iommu driver to set the iommu methods
 * used for a particular bus. Drivers for devices on that bus can use
 * the iommu-api after these ops are registered.
 * This special function is needed because IOMMUs are usually devices on
 * the bus itself, so the iommu drivers are not initialized when the bus
 * is set up. With this function the iommu-driver can set the iommu-ops
 * afterwards.
 */
1010
int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
1011
{
1012 1013
	int err;

1014 1015
	if (bus->iommu_ops != NULL)
		return -EBUSY;
1016

1017 1018 1019
	bus->iommu_ops = ops;

	/* Do IOMMU specific setup for this bus-type */
1020 1021 1022 1023 1024
	err = iommu_bus_init(bus, ops);
	if (err)
		bus->iommu_ops = NULL;

	return err;
1025
}
1026
EXPORT_SYMBOL_GPL(bus_set_iommu);
1027

1028
bool iommu_present(struct bus_type *bus)
1029
{
1030
	return bus->iommu_ops != NULL;
1031
}
1032
EXPORT_SYMBOL_GPL(iommu_present);
1033

1034 1035 1036 1037 1038 1039 1040 1041 1042
bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
{
	if (!bus->iommu_ops || !bus->iommu_ops->capable)
		return false;

	return bus->iommu_ops->capable(cap);
}
EXPORT_SYMBOL_GPL(iommu_capable);

1043 1044 1045 1046
/**
 * iommu_set_fault_handler() - set a fault handler for an iommu domain
 * @domain: iommu domain
 * @handler: fault handler
1047
 * @token: user data, will be passed back to the fault handler
1048 1049 1050 1051 1052 1053
 *
 * This function should be used by IOMMU users which want to be notified
 * whenever an IOMMU fault happens.
 *
 * The fault handler itself should return 0 on success, and an appropriate
 * error code otherwise.
1054 1055
 */
void iommu_set_fault_handler(struct iommu_domain *domain,
1056 1057
					iommu_fault_handler_t handler,
					void *token)
1058 1059 1060 1061
{
	BUG_ON(!domain);

	domain->handler = handler;
1062
	domain->handler_token = token;
1063
}
1064
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
1065

1066 1067
static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
						 unsigned type)
1068 1069 1070
{
	struct iommu_domain *domain;

1071
	if (bus == NULL || bus->iommu_ops == NULL)
1072 1073
		return NULL;

1074
	domain = bus->iommu_ops->domain_alloc(type);
1075 1076 1077
	if (!domain)
		return NULL;

1078
	domain->ops  = bus->iommu_ops;
1079
	domain->type = type;
1080 1081
	/* Assume all sizes by default; the driver may override this later */
	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
1082

1083 1084 1085
	return domain;
}

1086 1087 1088
struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
{
	return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
1089 1090 1091 1092 1093
}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);

void iommu_domain_free(struct iommu_domain *domain)
{
1094
	domain->ops->domain_free(domain);
1095 1096 1097
}
EXPORT_SYMBOL_GPL(iommu_domain_free);

1098 1099
static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev)
1100
{
1101
	int ret;
1102 1103 1104
	if (unlikely(domain->ops->attach_dev == NULL))
		return -ENODEV;

1105 1106 1107 1108
	ret = domain->ops->attach_dev(domain, dev);
	if (!ret)
		trace_attach_device_to_domain(dev);
	return ret;
1109
}
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129

int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;
	int ret;

	group = iommu_group_get(dev);
	/* FIXME: Remove this when groups a mandatory for iommu drivers */
	if (group == NULL)
		return __iommu_attach_device(domain, dev);

	/*
	 * We have a group - lock it to make sure the device-count doesn't
	 * change while we are attaching
	 */
	mutex_lock(&group->mutex);
	ret = -EINVAL;
	if (iommu_group_device_count(group) != 1)
		goto out_unlock;

1130
	ret = __iommu_attach_group(domain, group);
1131 1132 1133 1134 1135 1136 1137

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
1138 1139
EXPORT_SYMBOL_GPL(iommu_attach_device);

1140 1141
static void __iommu_detach_device(struct iommu_domain *domain,
				  struct device *dev)
1142
{
1143 1144 1145 1146
	if (unlikely(domain->ops->detach_dev == NULL))
		return;

	domain->ops->detach_dev(domain, dev);
1147
	trace_detach_device_from_domain(dev);
1148
}
1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164

void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;

	group = iommu_group_get(dev);
	/* FIXME: Remove this when groups a mandatory for iommu drivers */
	if (group == NULL)
		return __iommu_detach_device(domain, dev);

	mutex_lock(&group->mutex);
	if (iommu_group_device_count(group) != 1) {
		WARN_ON(1);
		goto out_unlock;
	}

1165
	__iommu_detach_group(domain, group);
1166 1167 1168 1169 1170

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);
}
1171 1172
EXPORT_SYMBOL_GPL(iommu_detach_device);

1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
{
	struct iommu_domain *domain;
	struct iommu_group *group;

	group = iommu_group_get(dev);
	/* FIXME: Remove this when groups a mandatory for iommu drivers */
	if (group == NULL)
		return NULL;

	domain = group->domain;

	iommu_group_put(group);

	return domain;
}
EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
1190

A
Alex Williamson 已提交
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
/*
 * IOMMU groups are really the natrual working unit of the IOMMU, but
 * the IOMMU API works on domains and devices.  Bridge that gap by
 * iterating over the devices in a group.  Ideally we'd have a single
 * device which represents the requestor ID of the group, but we also
 * allow IOMMU drivers to create policy defined minimum sets, where
 * the physical hardware may be able to distiguish members, but we
 * wish to group them at a higher level (ex. untrusted multi-function
 * PCI devices).  Thus we attach each device.
 */
static int iommu_group_do_attach_device(struct device *dev, void *data)
{
	struct iommu_domain *domain = data;

1205
	return __iommu_attach_device(domain, dev);
A
Alex Williamson 已提交
1206 1207
}

1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group)
{
	int ret;

	if (group->default_domain && group->domain != group->default_domain)
		return -EBUSY;

	ret = __iommu_group_for_each_dev(group, domain,
					 iommu_group_do_attach_device);
	if (ret == 0)
		group->domain = domain;

	return ret;
A
Alex Williamson 已提交
1222 1223 1224 1225
}

int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
{
1226 1227 1228 1229 1230 1231 1232
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_attach_group(domain, group);
	mutex_unlock(&group->mutex);

	return ret;
A
Alex Williamson 已提交
1233 1234 1235 1236 1237 1238 1239
}
EXPORT_SYMBOL_GPL(iommu_attach_group);

static int iommu_group_do_detach_device(struct device *dev, void *data)
{
	struct iommu_domain *domain = data;

1240
	__iommu_detach_device(domain, dev);
A
Alex Williamson 已提交
1241 1242 1243 1244

	return 0;
}

1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268
static void __iommu_detach_group(struct iommu_domain *domain,
				 struct iommu_group *group)
{
	int ret;

	if (!group->default_domain) {
		__iommu_group_for_each_dev(group, domain,
					   iommu_group_do_detach_device);
		group->domain = NULL;
		return;
	}

	if (group->domain == group->default_domain)
		return;

	/* Detach by re-attaching to the default domain */
	ret = __iommu_group_for_each_dev(group, group->default_domain,
					 iommu_group_do_attach_device);
	if (ret != 0)
		WARN_ON(1);
	else
		group->domain = group->default_domain;
}

A
Alex Williamson 已提交
1269 1270
void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
{
1271 1272 1273
	mutex_lock(&group->mutex);
	__iommu_detach_group(domain, group);
	mutex_unlock(&group->mutex);
A
Alex Williamson 已提交
1274 1275 1276
}
EXPORT_SYMBOL_GPL(iommu_detach_group);

1277
phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
1278
{
1279 1280 1281 1282
	if (unlikely(domain->ops->iova_to_phys == NULL))
		return 0;

	return domain->ops->iova_to_phys(domain, iova);
1283 1284
}
EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
S
Sheng Yang 已提交
1285

A
Alex Williamson 已提交
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305
static size_t iommu_pgsize(struct iommu_domain *domain,
			   unsigned long addr_merge, size_t size)
{
	unsigned int pgsize_idx;
	size_t pgsize;

	/* Max page size that still fits into 'size' */
	pgsize_idx = __fls(size);

	/* need to consider alignment requirements ? */
	if (likely(addr_merge)) {
		/* Max page size allowed by address */
		unsigned int align_pgsize_idx = __ffs(addr_merge);
		pgsize_idx = min(pgsize_idx, align_pgsize_idx);
	}

	/* build a mask of acceptable page sizes */
	pgsize = (1UL << (pgsize_idx + 1)) - 1;

	/* throw away page sizes not supported by the hardware */
1306
	pgsize &= domain->pgsize_bitmap;
A
Alex Williamson 已提交
1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317

	/* make sure we're still sane */
	BUG_ON(!pgsize);

	/* pick the biggest page */
	pgsize_idx = __fls(pgsize);
	pgsize = 1UL << pgsize_idx;

	return pgsize;
}

1318
int iommu_map(struct iommu_domain *domain, unsigned long iova,
1319
	      phys_addr_t paddr, size_t size, int prot)
1320
{
1321 1322 1323
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;
	size_t orig_size = size;
1324
	phys_addr_t orig_paddr = paddr;
1325
	int ret = 0;
1326

1327
	if (unlikely(domain->ops->map == NULL ||
1328
		     domain->pgsize_bitmap == 0UL))
1329
		return -ENODEV;
1330

1331 1332 1333
	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return -EINVAL;

1334
	/* find out the minimum page size supported */
1335
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
1336 1337 1338 1339 1340 1341 1342

	/*
	 * both the virtual address and the physical one, as well as
	 * the size of the mapping, must be aligned (at least) to the
	 * size of the smallest page supported by the hardware
	 */
	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
1343
		pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n",
1344
		       iova, &paddr, size, min_pagesz);
1345 1346 1347
		return -EINVAL;
	}

1348
	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);
1349 1350

	while (size) {
A
Alex Williamson 已提交
1351
		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
1352

1353
		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
1354
			 iova, &paddr, pgsize);
1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367

		ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
		if (ret)
			break;

		iova += pgsize;
		paddr += pgsize;
		size -= pgsize;
	}

	/* unroll mapping in case something went wrong */
	if (ret)
		iommu_unmap(domain, orig_iova, orig_size - size);
1368
	else
1369
		trace_map(orig_iova, orig_paddr, orig_size);
1370 1371

	return ret;
1372 1373 1374
}
EXPORT_SYMBOL_GPL(iommu_map);

1375
size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
1376
{
1377 1378
	size_t unmapped_page, unmapped = 0;
	unsigned int min_pagesz;
1379
	unsigned long orig_iova = iova;
1380

1381
	if (unlikely(domain->ops->unmap == NULL ||
1382
		     domain->pgsize_bitmap == 0UL))
1383 1384
		return -ENODEV;

1385 1386 1387
	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return -EINVAL;

1388
	/* find out the minimum page size supported */
1389
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
1390 1391 1392 1393 1394 1395 1396

	/*
	 * The virtual address, as well as the size of the mapping, must be
	 * aligned (at least) to the size of the smallest page supported
	 * by the hardware
	 */
	if (!IS_ALIGNED(iova | size, min_pagesz)) {
1397 1398
		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
		       iova, size, min_pagesz);
1399 1400 1401
		return -EINVAL;
	}

1402
	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
1403 1404 1405 1406 1407 1408

	/*
	 * Keep iterating until we either unmap 'size' bytes (or more)
	 * or we hit an area that isn't mapped.
	 */
	while (unmapped < size) {
A
Alex Williamson 已提交
1409
		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
1410

A
Alex Williamson 已提交
1411
		unmapped_page = domain->ops->unmap(domain, iova, pgsize);
1412 1413 1414
		if (!unmapped_page)
			break;

1415 1416
		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
			 iova, unmapped_page);
1417 1418 1419 1420 1421

		iova += unmapped_page;
		unmapped += unmapped_page;
	}

1422
	trace_unmap(orig_iova, size, unmapped);
1423
	return unmapped;
1424 1425
}
EXPORT_SYMBOL_GPL(iommu_unmap);
1426

O
Olav Haugan 已提交
1427 1428 1429
size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
			 struct scatterlist *sg, unsigned int nents, int prot)
{
1430
	struct scatterlist *s;
O
Olav Haugan 已提交
1431
	size_t mapped = 0;
1432
	unsigned int i, min_pagesz;
1433
	int ret;
O
Olav Haugan 已提交
1434

1435
	if (unlikely(domain->pgsize_bitmap == 0UL))
1436
		return 0;
O
Olav Haugan 已提交
1437

1438
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
1439 1440

	for_each_sg(sg, s, nents, i) {
D
Dan Williams 已提交
1441
		phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset;
1442 1443 1444 1445 1446 1447 1448 1449

		/*
		 * We are mapping on IOMMU page boundaries, so offset within
		 * the page must be 0. However, the IOMMU may support pages
		 * smaller than PAGE_SIZE, so s->offset may still represent
		 * an offset of that boundary within the CPU page.
		 */
		if (!IS_ALIGNED(s->offset, min_pagesz))
1450 1451 1452 1453 1454 1455 1456
			goto out_err;

		ret = iommu_map(domain, iova + mapped, phys, s->length, prot);
		if (ret)
			goto out_err;

		mapped += s->length;
O
Olav Haugan 已提交
1457 1458 1459
	}

	return mapped;
1460 1461 1462 1463 1464 1465 1466

out_err:
	/* undo mappings already done */
	iommu_unmap(domain, iova, mapped);

	return 0;

O
Olav Haugan 已提交
1467 1468
}
EXPORT_SYMBOL_GPL(default_iommu_map_sg);
1469 1470

int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
1471
			       phys_addr_t paddr, u64 size, int prot)
1472 1473 1474 1475
{
	if (unlikely(domain->ops->domain_window_enable == NULL))
		return -ENODEV;

1476 1477
	return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size,
						 prot);
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489
}
EXPORT_SYMBOL_GPL(iommu_domain_window_enable);

void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr)
{
	if (unlikely(domain->ops->domain_window_disable == NULL))
		return;

	return domain->ops->domain_window_disable(domain, wnd_nr);
}
EXPORT_SYMBOL_GPL(iommu_domain_window_disable);

A
Alex Williamson 已提交
1490
static int __init iommu_init(void)
1491
{
A
Alex Williamson 已提交
1492 1493 1494 1495 1496
	iommu_group_kset = kset_create_and_add("iommu_groups",
					       NULL, kernel_kobj);
	BUG_ON(!iommu_group_kset);

	return 0;
1497
}
1498
core_initcall(iommu_init);
1499 1500 1501 1502

int iommu_domain_get_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
1503
	struct iommu_domain_geometry *geometry;
1504
	bool *paging;
1505
	int ret = 0;
1506
	u32 *count;
1507 1508 1509 1510 1511 1512

	switch (attr) {
	case DOMAIN_ATTR_GEOMETRY:
		geometry  = data;
		*geometry = domain->geometry;

1513 1514 1515
		break;
	case DOMAIN_ATTR_PAGING:
		paging  = data;
1516
		*paging = (domain->pgsize_bitmap != 0UL);
1517 1518 1519 1520 1521 1522 1523 1524 1525
		break;
	case DOMAIN_ATTR_WINDOWS:
		count = data;

		if (domain->ops->domain_get_windows != NULL)
			*count = domain->ops->domain_get_windows(domain);
		else
			ret = -ENODEV;

1526 1527 1528 1529
		break;
	default:
		if (!domain->ops->domain_get_attr)
			return -EINVAL;
1530

1531 1532 1533 1534
		ret = domain->ops->domain_get_attr(domain, attr, data);
	}

	return ret;
1535 1536 1537 1538 1539 1540
}
EXPORT_SYMBOL_GPL(iommu_domain_get_attr);

int iommu_domain_set_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551
	int ret = 0;
	u32 *count;

	switch (attr) {
	case DOMAIN_ATTR_WINDOWS:
		count = data;

		if (domain->ops->domain_set_windows != NULL)
			ret = domain->ops->domain_set_windows(domain, *count);
		else
			ret = -ENODEV;
1552

1553 1554 1555 1556 1557 1558 1559 1560 1561
		break;
	default:
		if (domain->ops->domain_set_attr == NULL)
			return -EINVAL;

		ret = domain->ops->domain_set_attr(domain, attr, data);
	}

	return ret;
1562
}
1563
EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
1564

1565
void iommu_get_resv_regions(struct device *dev, struct list_head *list)
1566 1567 1568
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;

1569 1570
	if (ops && ops->get_resv_regions)
		ops->get_resv_regions(dev, list);
1571 1572
}

1573
void iommu_put_resv_regions(struct device *dev, struct list_head *list)
1574 1575 1576
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;

1577 1578
	if (ops && ops->put_resv_regions)
		ops->put_resv_regions(dev, list);
1579
}
1580

E
Eric Auger 已提交
1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598
struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
						  size_t length,
						  int prot, int type)
{
	struct iommu_resv_region *region;

	region = kzalloc(sizeof(*region), GFP_KERNEL);
	if (!region)
		return NULL;

	INIT_LIST_HEAD(&region->list);
	region->start = start;
	region->length = length;
	region->prot = prot;
	region->type = type;
	return region;
}

1599 1600 1601 1602 1603 1604 1605 1606 1607
/* Request that a device is direct mapped by the IOMMU */
int iommu_request_dm_for_dev(struct device *dev)
{
	struct iommu_domain *dm_domain;
	struct iommu_group *group;
	int ret;

	/* Device must already be in a group before calling this function */
	group = iommu_group_get_for_dev(dev);
1608 1609
	if (IS_ERR(group))
		return PTR_ERR(group);
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650

	mutex_lock(&group->mutex);

	/* Check if the default domain is already direct mapped */
	ret = 0;
	if (group->default_domain &&
	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY)
		goto out;

	/* Don't change mappings of existing devices */
	ret = -EBUSY;
	if (iommu_group_device_count(group) != 1)
		goto out;

	/* Allocate a direct mapped domain */
	ret = -ENOMEM;
	dm_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_IDENTITY);
	if (!dm_domain)
		goto out;

	/* Attach the device to the domain */
	ret = __iommu_attach_group(dm_domain, group);
	if (ret) {
		iommu_domain_free(dm_domain);
		goto out;
	}

	/* Make the direct mapped domain the default for this group */
	if (group->default_domain)
		iommu_domain_free(group->default_domain);
	group->default_domain = dm_domain;

	pr_info("Using direct mapping for device %s\n", dev_name(dev));

	ret = 0;
out:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
R
Robin Murphy 已提交
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
struct iommu_instance {
	struct list_head list;
	struct fwnode_handle *fwnode;
	const struct iommu_ops *ops;
};
static LIST_HEAD(iommu_instance_list);
static DEFINE_SPINLOCK(iommu_instance_lock);

void iommu_register_instance(struct fwnode_handle *fwnode,
			     const struct iommu_ops *ops)
{
	struct iommu_instance *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);

	if (WARN_ON(!iommu))
		return;

	of_node_get(to_of_node(fwnode));
	INIT_LIST_HEAD(&iommu->list);
	iommu->fwnode = fwnode;
	iommu->ops = ops;
	spin_lock(&iommu_instance_lock);
	list_add_tail(&iommu->list, &iommu_instance_list);
	spin_unlock(&iommu_instance_lock);
}

const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
{
	struct iommu_instance *instance;
	const struct iommu_ops *ops = NULL;

	spin_lock(&iommu_instance_lock);
	list_for_each_entry(instance, &iommu_instance_list, list)
		if (instance->fwnode == fwnode) {
			ops = instance->ops;
			break;
		}
	spin_unlock(&iommu_instance_lock);
	return ops;
}

R
Robin Murphy 已提交
1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747
int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
		      const struct iommu_ops *ops)
{
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;

	if (fwspec)
		return ops == fwspec->ops ? 0 : -EINVAL;

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

	of_node_get(to_of_node(iommu_fwnode));
	fwspec->iommu_fwnode = iommu_fwnode;
	fwspec->ops = ops;
	dev->iommu_fwspec = fwspec;
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_init);

void iommu_fwspec_free(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;

	if (fwspec) {
		fwnode_handle_put(fwspec->iommu_fwnode);
		kfree(fwspec);
		dev->iommu_fwspec = NULL;
	}
}
EXPORT_SYMBOL_GPL(iommu_fwspec_free);

int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
{
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
	size_t size;
	int i;

	if (!fwspec)
		return -EINVAL;

	size = offsetof(struct iommu_fwspec, ids[fwspec->num_ids + num_ids]);
	if (size > sizeof(*fwspec)) {
		fwspec = krealloc(dev->iommu_fwspec, size, GFP_KERNEL);
		if (!fwspec)
			return -ENOMEM;
	}

	for (i = 0; i < num_ids; i++)
		fwspec->ids[fwspec->num_ids + i] = ids[i];

	fwspec->num_ids += num_ids;
	dev->iommu_fwspec = fwspec;
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);