iommu.c 24.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
/*
 * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
 * Author: Joerg Roedel <joerg.roedel@amd.com>
 *
 * 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 20
#define pr_fmt(fmt)    "%s: " fmt, __func__

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 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
#include <linux/idr.h>
#include <linux/notifier.h>
#include <linux/err.h>

static struct kset *iommu_group_kset;
static struct ida iommu_group_ida;
static struct mutex iommu_group_mutex;

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;
};

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)
65

A
Alex Williamson 已提交
66 67 68 69
#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)
70

A
Alex Williamson 已提交
71 72
static ssize_t iommu_group_attr_show(struct kobject *kobj,
				     struct attribute *__attr, char *buf)
73
{
A
Alex Williamson 已提交
74 75 76
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;
77

A
Alex Williamson 已提交
78 79 80 81 82 83 84 85 86 87 88 89
	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;
90

A
Alex Williamson 已提交
91 92 93
	if (attr->store)
		ret = attr->store(group, buf, count);
	return ret;
94 95
}

A
Alex Williamson 已提交
96 97 98 99
static const struct sysfs_ops iommu_group_sysfs_ops = {
	.show = iommu_group_attr_show,
	.store = iommu_group_attr_store,
};
100

A
Alex Williamson 已提交
101 102 103 104
static int iommu_group_create_file(struct iommu_group *group,
				   struct iommu_group_attribute *attr)
{
	return sysfs_create_file(&group->kobj, &attr->attr);
105 106
}

A
Alex Williamson 已提交
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
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);

	if (group->iommu_data_release)
		group->iommu_data_release(group->iommu_data);

	mutex_lock(&iommu_group_mutex);
	ida_remove(&iommu_group_ida, group->id);
	mutex_unlock(&iommu_group_mutex);

	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)
153
{
A
Alex Williamson 已提交
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
	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);

	mutex_lock(&iommu_group_mutex);

again:
	if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) {
		kfree(group);
		mutex_unlock(&iommu_group_mutex);
		return ERR_PTR(-ENOMEM);
	}

	if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id))
		goto again;

	mutex_unlock(&iommu_group_mutex);
179

A
Alex Williamson 已提交
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
				   NULL, "%d", group->id);
	if (ret) {
		mutex_lock(&iommu_group_mutex);
		ida_remove(&iommu_group_ida, group->id);
		mutex_unlock(&iommu_group_mutex);
		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);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_alloc);

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
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
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
/**
 * 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))
262
{
A
Alex Williamson 已提交
263 264 265 266
	group->iommu_data = iommu_data;
	group->iommu_data_release = release;
}
EXPORT_SYMBOL_GPL(iommu_group_set_iommudata);
267

A
Alex Williamson 已提交
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
/**
 * 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;
	}
298 299 300

	return 0;
}
A
Alex Williamson 已提交
301
EXPORT_SYMBOL_GPL(iommu_group_set_name);
302

A
Alex Williamson 已提交
303 304 305 306 307 308 309 310 311
/**
 * 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)
312
{
A
Alex Williamson 已提交
313 314 315 316 317 318 319 320
	int ret, i = 0;
	struct iommu_device *device;

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

	device->dev = dev;
321

A
Alex Williamson 已提交
322 323 324 325 326 327 328 329 330 331 332 333 334
	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;
	}
335

A
Alex Williamson 已提交
336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
	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;

	mutex_lock(&group->mutex);
	list_add_tail(&device->list, &group->devices);
	mutex_unlock(&group->mutex);

	/* Notify any listeners about change to group. */
	blocking_notifier_call_chain(&group->notifier,
				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
366 367
	return 0;
}
A
Alex Williamson 已提交
368
EXPORT_SYMBOL_GPL(iommu_group_add_device);
369

A
Alex Williamson 已提交
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510
/**
 * 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;

	/* 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");

	kfree(device->name);
	kfree(device);
	dev->iommu_group = NULL;
	kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_remove_device);

/**
 * 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.
 */
int iommu_group_for_each_dev(struct iommu_group *group, void *data,
			     int (*fn)(struct device *, void *))
{
	struct iommu_device *device;
	int ret = 0;

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

/**
 * 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);
511

A
Alex Williamson 已提交
512
static int add_iommu_group(struct device *dev, void *data)
513
{
A
Alex Williamson 已提交
514 515 516 517
	struct iommu_ops *ops = data;

	if (!ops->add_device)
		return -ENODEV;
518

A
Alex Williamson 已提交
519 520 521
	WARN_ON(dev->iommu_group);

	ops->add_device(dev);
522 523 524 525

	return 0;
}

A
Alex Williamson 已提交
526 527
static int iommu_bus_notifier(struct notifier_block *nb,
			      unsigned long action, void *data)
528 529
{
	struct device *dev = data;
A
Alex Williamson 已提交
530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
	struct iommu_ops *ops = dev->bus->iommu_ops;
	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);
	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
		if (ops->remove_device && dev->iommu_group) {
			ops->remove_device(dev);
			return 0;
		}
	}
547

A
Alex Williamson 已提交
548 549 550 551 552 553 554
	/*
	 * Remaining BUS_NOTIFYs get filtered and republished to the
	 * group, if anyone is listening
	 */
	group = iommu_group_get(dev);
	if (!group)
		return 0;
555

A
Alex Williamson 已提交
556 557 558 559 560 561 562 563 564 565 566 567 568 569
	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;
	}
570

A
Alex Williamson 已提交
571 572 573
	if (group_action)
		blocking_notifier_call_chain(&group->notifier,
					     group_action, dev);
574

A
Alex Williamson 已提交
575
	iommu_group_put(group);
576 577 578
	return 0;
}

A
Alex Williamson 已提交
579 580
static struct notifier_block iommu_bus_nb = {
	.notifier_call = iommu_bus_notifier,
581 582
};

583 584
static void iommu_bus_init(struct bus_type *bus, struct iommu_ops *ops)
{
A
Alex Williamson 已提交
585 586
	bus_register_notifier(bus, &iommu_bus_nb);
	bus_for_each_dev(bus, NULL, ops, add_iommu_group);
587
}
588

589 590 591 592 593 594 595 596 597 598 599 600 601 602
/**
 * 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.
 */
int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops)
603
{
604 605
	if (bus->iommu_ops != NULL)
		return -EBUSY;
606

607 608 609 610
	bus->iommu_ops = ops;

	/* Do IOMMU specific setup for this bus-type */
	iommu_bus_init(bus, ops);
611

612
	return 0;
613
}
614
EXPORT_SYMBOL_GPL(bus_set_iommu);
615

616
bool iommu_present(struct bus_type *bus)
617
{
618
	return bus->iommu_ops != NULL;
619
}
620
EXPORT_SYMBOL_GPL(iommu_present);
621

622 623 624 625
/**
 * iommu_set_fault_handler() - set a fault handler for an iommu domain
 * @domain: iommu domain
 * @handler: fault handler
626
 * @token: user data, will be passed back to the fault handler
627 628 629 630 631 632
 *
 * 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.
633 634
 */
void iommu_set_fault_handler(struct iommu_domain *domain,
635 636
					iommu_fault_handler_t handler,
					void *token)
637 638 639 640
{
	BUG_ON(!domain);

	domain->handler = handler;
641
	domain->handler_token = token;
642
}
643
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
644

645
struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
646 647 648 649
{
	struct iommu_domain *domain;
	int ret;

650
	if (bus == NULL || bus->iommu_ops == NULL)
651 652
		return NULL;

653
	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
654 655 656
	if (!domain)
		return NULL;

657
	domain->ops = bus->iommu_ops;
658

659
	ret = domain->ops->domain_init(domain);
660 661 662 663 664 665 666 667 668 669 670 671 672 673
	if (ret)
		goto out_free;

	return domain;

out_free:
	kfree(domain);

	return NULL;
}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);

void iommu_domain_free(struct iommu_domain *domain)
{
674 675 676
	if (likely(domain->ops->domain_destroy != NULL))
		domain->ops->domain_destroy(domain);

677 678 679 680 681 682
	kfree(domain);
}
EXPORT_SYMBOL_GPL(iommu_domain_free);

int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
{
683 684 685 686
	if (unlikely(domain->ops->attach_dev == NULL))
		return -ENODEV;

	return domain->ops->attach_dev(domain, dev);
687 688 689 690 691
}
EXPORT_SYMBOL_GPL(iommu_attach_device);

void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
{
692 693 694 695
	if (unlikely(domain->ops->detach_dev == NULL))
		return;

	domain->ops->detach_dev(domain, dev);
696 697 698
}
EXPORT_SYMBOL_GPL(iommu_detach_device);

A
Alex Williamson 已提交
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
/*
 * 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;

	return iommu_attach_device(domain, dev);
}

int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	return iommu_group_for_each_dev(group, domain,
					iommu_group_do_attach_device);
}
EXPORT_SYMBOL_GPL(iommu_attach_group);

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

	iommu_detach_device(domain, dev);

	return 0;
}

void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device);
}
EXPORT_SYMBOL_GPL(iommu_detach_group);

738
phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
739
{
740 741 742 743
	if (unlikely(domain->ops->iova_to_phys == NULL))
		return 0;

	return domain->ops->iova_to_phys(domain, iova);
744 745
}
EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
S
Sheng Yang 已提交
746 747 748 749

int iommu_domain_has_cap(struct iommu_domain *domain,
			 unsigned long cap)
{
750 751 752 753
	if (unlikely(domain->ops->domain_has_cap == NULL))
		return 0;

	return domain->ops->domain_has_cap(domain, cap);
S
Sheng Yang 已提交
754 755
}
EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
756

A
Alex Williamson 已提交
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
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 */
	pgsize &= domain->ops->pgsize_bitmap;

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

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

	return pgsize;
}

789
int iommu_map(struct iommu_domain *domain, unsigned long iova,
790
	      phys_addr_t paddr, size_t size, int prot)
791
{
792 793 794 795
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;
	size_t orig_size = size;
	int ret = 0;
796

797 798
	if (unlikely(domain->ops->unmap == NULL ||
		     domain->ops->pgsize_bitmap == 0UL))
799
		return -ENODEV;
800

801 802 803 804 805 806 807 808 809
	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);

	/*
	 * 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)) {
810 811
		pr_err("unaligned: iova 0x%lx pa 0x%pa size 0x%zx min_pagesz 0x%x\n",
		       iova, &paddr, size, min_pagesz);
812 813 814
		return -EINVAL;
	}

815
	pr_debug("map: iova 0x%lx pa 0x%pa size 0x%zx\n", iova, &paddr, size);
816 817

	while (size) {
A
Alex Williamson 已提交
818
		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
819

820 821
		pr_debug("mapping: iova 0x%lx pa 0x%pa pgsize 0x%zx\n",
			 iova, &paddr, pgsize);
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836

		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);

	return ret;
837 838 839
}
EXPORT_SYMBOL_GPL(iommu_map);

840
size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
841
{
842 843
	size_t unmapped_page, unmapped = 0;
	unsigned int min_pagesz;
844

845 846
	if (unlikely(domain->ops->unmap == NULL ||
		     domain->ops->pgsize_bitmap == 0UL))
847 848
		return -ENODEV;

849 850 851 852 853 854 855 856 857
	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);

	/*
	 * 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)) {
858 859
		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
		       iova, size, min_pagesz);
860 861 862
		return -EINVAL;
	}

863
	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
864 865 866 867 868 869

	/*
	 * 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
870
		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
871

A
Alex Williamson 已提交
872
		unmapped_page = domain->ops->unmap(domain, iova, pgsize);
873 874 875
		if (!unmapped_page)
			break;

876 877
		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
			 iova, unmapped_page);
878 879 880 881 882 883

		iova += unmapped_page;
		unmapped += unmapped_page;
	}

	return unmapped;
884 885
}
EXPORT_SYMBOL_GPL(iommu_unmap);
886

887 888

int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
889
			       phys_addr_t paddr, u64 size, int prot)
890 891 892 893
{
	if (unlikely(domain->ops->domain_window_enable == NULL))
		return -ENODEV;

894 895
	return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size,
						 prot);
896 897 898 899 900 901 902 903 904 905 906 907
}
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
908
static int __init iommu_init(void)
909
{
A
Alex Williamson 已提交
910 911 912 913
	iommu_group_kset = kset_create_and_add("iommu_groups",
					       NULL, kernel_kobj);
	ida_init(&iommu_group_ida);
	mutex_init(&iommu_group_mutex);
914

A
Alex Williamson 已提交
915 916 917
	BUG_ON(!iommu_group_kset);

	return 0;
918
}
919
arch_initcall(iommu_init);
920 921 922 923

int iommu_domain_get_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
924
	struct iommu_domain_geometry *geometry;
925
	bool *paging;
926
	int ret = 0;
927
	u32 *count;
928 929 930 931 932 933

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

934 935 936 937
		break;
	case DOMAIN_ATTR_PAGING:
		paging  = data;
		*paging = (domain->ops->pgsize_bitmap != 0UL);
938 939 940 941 942 943 944 945 946
		break;
	case DOMAIN_ATTR_WINDOWS:
		count = data;

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

947 948 949 950
		break;
	default:
		if (!domain->ops->domain_get_attr)
			return -EINVAL;
951

952 953 954 955
		ret = domain->ops->domain_get_attr(domain, attr, data);
	}

	return ret;
956 957 958 959 960 961
}
EXPORT_SYMBOL_GPL(iommu_domain_get_attr);

int iommu_domain_set_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
962 963 964 965 966 967 968 969 970 971 972
	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;
973

974 975 976 977 978 979 980 981 982
		break;
	default:
		if (domain->ops->domain_set_attr == NULL)
			return -EINVAL;

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

	return ret;
983
}
984
EXPORT_SYMBOL_GPL(iommu_domain_set_attr);