vfio.c 56.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
Alex Williamson's avatar
Alex Williamson committed
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
/*
 * VFIO core
 *
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * Derived from original vfio:
 * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
 * Author: Tom Lyon, pugs@cisco.com
 */

#include <linux/cdev.h>
#include <linux/compat.h>
#include <linux/device.h>
#include <linux/file.h>
#include <linux/anon_inodes.h>
#include <linux/fs.h>
#include <linux/idr.h>
#include <linux/iommu.h>
#include <linux/list.h>
22
#include <linux/miscdevice.h>
Alex Williamson's avatar
Alex Williamson committed
23 24
#include <linux/module.h>
#include <linux/mutex.h>
25
#include <linux/pci.h>
26
#include <linux/rwsem.h>
Alex Williamson's avatar
Alex Williamson committed
27 28
#include <linux/sched.h>
#include <linux/slab.h>
29
#include <linux/stat.h>
Alex Williamson's avatar
Alex Williamson committed
30 31 32 33
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/wait.h>
34
#include <linux/sched/signal.h>
Alex Williamson's avatar
Alex Williamson committed
35 36 37 38 39 40 41 42 43 44 45 46 47

#define DRIVER_VERSION	"0.3"
#define DRIVER_AUTHOR	"Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC	"VFIO - User Level meta-driver"

static struct vfio {
	struct class			*class;
	struct list_head		iommu_drivers_list;
	struct mutex			iommu_drivers_lock;
	struct list_head		group_list;
	struct idr			group_idr;
	struct mutex			group_lock;
	struct cdev			group_cdev;
48
	dev_t				group_devt;
Alex Williamson's avatar
Alex Williamson committed
49 50 51 52 53 54 55 56 57 58 59
	wait_queue_head_t		release_q;
} vfio;

struct vfio_iommu_driver {
	const struct vfio_iommu_driver_ops	*ops;
	struct list_head			vfio_next;
};

struct vfio_container {
	struct kref			kref;
	struct list_head		group_list;
60
	struct rw_semaphore		group_lock;
Alex Williamson's avatar
Alex Williamson committed
61 62
	struct vfio_iommu_driver	*iommu_driver;
	void				*iommu_data;
63
	bool				noiommu;
Alex Williamson's avatar
Alex Williamson committed
64 65
};

66 67 68 69 70
struct vfio_unbound_dev {
	struct device			*dev;
	struct list_head		unbound_next;
};

Alex Williamson's avatar
Alex Williamson committed
71 72 73 74 75 76 77 78 79 80 81 82
struct vfio_group {
	struct kref			kref;
	int				minor;
	atomic_t			container_users;
	struct iommu_group		*iommu_group;
	struct vfio_container		*container;
	struct list_head		device_list;
	struct mutex			device_lock;
	struct device			*dev;
	struct notifier_block		nb;
	struct list_head		vfio_next;
	struct list_head		container_next;
83 84
	struct list_head		unbound_list;
	struct mutex			unbound_lock;
85
	atomic_t			opened;
86
	wait_queue_head_t		container_q;
87
	bool				noiommu;
88 89
	struct kvm			*kvm;
	struct blocking_notifier_head	notifier;
Alex Williamson's avatar
Alex Williamson committed
90 91 92 93 94 95 96 97 98 99 100
};

struct vfio_device {
	struct kref			kref;
	struct device			*dev;
	const struct vfio_device_ops	*ops;
	struct vfio_group		*group;
	struct list_head		group_next;
	void				*device_data;
};

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
#ifdef CONFIG_VFIO_NOIOMMU
static bool noiommu __read_mostly;
module_param_named(enable_unsafe_noiommu_mode,
		   noiommu, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
#endif

/*
 * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe
 * and remove functions, any use cases other than acquiring the first
 * reference for the purpose of calling vfio_add_group_dev() or removing
 * that symmetric reference after vfio_del_group_dev() should use the raw
 * iommu_group_{get,put} functions.  In particular, vfio_iommu_group_put()
 * removes the device from the dummy group and cannot be nested.
 */
struct iommu_group *vfio_iommu_group_get(struct device *dev)
{
	struct iommu_group *group;
	int __maybe_unused ret;

	group = iommu_group_get(dev);

#ifdef CONFIG_VFIO_NOIOMMU
	/*
	 * With noiommu enabled, an IOMMU group will be created for a device
	 * that doesn't already have one and doesn't have an iommu_ops on their
127 128
	 * bus.  We set iommudata simply to be able to identify these groups
	 * as special use and for reclamation later.
129 130 131 132 133 134 135 136 137
	 */
	if (group || !noiommu || iommu_present(dev->bus))
		return group;

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

	iommu_group_set_name(group, "vfio-noiommu");
138
	iommu_group_set_iommudata(group, &noiommu, NULL);
139
	ret = iommu_group_add_device(group, dev);
140 141
	if (ret) {
		iommu_group_put(group);
142
		return NULL;
143
	}
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163

	/*
	 * Where to taint?  At this point we've added an IOMMU group for a
	 * device that is not backed by iommu_ops, therefore any iommu_
	 * callback using iommu_ops can legitimately Oops.  So, while we may
	 * be about to give a DMA capable device to a user without IOMMU
	 * protection, which is clearly taint-worthy, let's go ahead and do
	 * it here.
	 */
	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
	dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
#endif

	return group;
}
EXPORT_SYMBOL_GPL(vfio_iommu_group_get);

void vfio_iommu_group_put(struct iommu_group *group, struct device *dev)
{
#ifdef CONFIG_VFIO_NOIOMMU
164
	if (iommu_group_get_iommudata(group) == &noiommu)
165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
		iommu_group_remove_device(dev);
#endif

	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(vfio_iommu_group_put);

#ifdef CONFIG_VFIO_NOIOMMU
static void *vfio_noiommu_open(unsigned long arg)
{
	if (arg != VFIO_NOIOMMU_IOMMU)
		return ERR_PTR(-EINVAL);
	if (!capable(CAP_SYS_RAWIO))
		return ERR_PTR(-EPERM);

	return NULL;
}

static void vfio_noiommu_release(void *iommu_data)
{
}

static long vfio_noiommu_ioctl(void *iommu_data,
			       unsigned int cmd, unsigned long arg)
{
	if (cmd == VFIO_CHECK_EXTENSION)
		return noiommu && (arg == VFIO_NOIOMMU_IOMMU) ? 1 : 0;

	return -ENOTTY;
}

static int vfio_noiommu_attach_group(void *iommu_data,
				     struct iommu_group *iommu_group)
{
199
	return iommu_group_get_iommudata(iommu_group) == &noiommu ? 0 : -EINVAL;
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218
}

static void vfio_noiommu_detach_group(void *iommu_data,
				      struct iommu_group *iommu_group)
{
}

static const struct vfio_iommu_driver_ops vfio_noiommu_ops = {
	.name = "vfio-noiommu",
	.owner = THIS_MODULE,
	.open = vfio_noiommu_open,
	.release = vfio_noiommu_release,
	.ioctl = vfio_noiommu_ioctl,
	.attach_group = vfio_noiommu_attach_group,
	.detach_group = vfio_noiommu_detach_group,
};
#endif


Alex Williamson's avatar
Alex Williamson committed
219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
/**
 * IOMMU driver registration
 */
int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops)
{
	struct vfio_iommu_driver *driver, *tmp;

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

	driver->ops = ops;

	mutex_lock(&vfio.iommu_drivers_lock);

	/* Check for duplicates */
	list_for_each_entry(tmp, &vfio.iommu_drivers_list, vfio_next) {
		if (tmp->ops == ops) {
			mutex_unlock(&vfio.iommu_drivers_lock);
			kfree(driver);
			return -EINVAL;
		}
	}

	list_add(&driver->vfio_next, &vfio.iommu_drivers_list);

	mutex_unlock(&vfio.iommu_drivers_lock);

	return 0;
}
EXPORT_SYMBOL_GPL(vfio_register_iommu_driver);

void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
{
	struct vfio_iommu_driver *driver;

	mutex_lock(&vfio.iommu_drivers_lock);
	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
		if (driver->ops == ops) {
			list_del(&driver->vfio_next);
			mutex_unlock(&vfio.iommu_drivers_lock);
			kfree(driver);
			return;
		}
	}
	mutex_unlock(&vfio.iommu_drivers_lock);
}
EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);

/**
 * Group minor allocation/free - both called with vfio.group_lock held
 */
static int vfio_alloc_group_minor(struct vfio_group *group)
{
273
	return idr_alloc(&vfio.group_idr, group, 0, MINORMASK + 1, GFP_KERNEL);
Alex Williamson's avatar
Alex Williamson committed
274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
}

static void vfio_free_group_minor(int minor)
{
	idr_remove(&vfio.group_idr, minor);
}

static int vfio_iommu_group_notifier(struct notifier_block *nb,
				     unsigned long action, void *data);
static void vfio_group_get(struct vfio_group *group);

/**
 * Container objects - containers are created when /dev/vfio/vfio is
 * opened, but their lifecycle extends until the last user is done, so
 * it's freed via kref.  Must support container/group/device being
 * closed in any order.
 */
static void vfio_container_get(struct vfio_container *container)
{
	kref_get(&container->kref);
}

static void vfio_container_release(struct kref *kref)
{
	struct vfio_container *container;
	container = container_of(kref, struct vfio_container, kref);

	kfree(container);
}

static void vfio_container_put(struct vfio_container *container)
{
	kref_put(&container->kref, vfio_container_release);
}

309 310 311 312 313 314 315 316 317 318 319
static void vfio_group_unlock_and_free(struct vfio_group *group)
{
	mutex_unlock(&vfio.group_lock);
	/*
	 * Unregister outside of lock.  A spurious callback is harmless now
	 * that the group is no longer in vfio.group_list.
	 */
	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
	kfree(group);
}

Alex Williamson's avatar
Alex Williamson committed
320 321 322
/**
 * Group objects - create, release, get, put, search
 */
323
static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
Alex Williamson's avatar
Alex Williamson committed
324 325 326 327 328 329 330 331 332 333 334 335
{
	struct vfio_group *group, *tmp;
	struct device *dev;
	int ret, minor;

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

	kref_init(&group->kref);
	INIT_LIST_HEAD(&group->device_list);
	mutex_init(&group->device_lock);
336 337
	INIT_LIST_HEAD(&group->unbound_list);
	mutex_init(&group->unbound_lock);
Alex Williamson's avatar
Alex Williamson committed
338
	atomic_set(&group->container_users, 0);
339
	atomic_set(&group->opened, 0);
340
	init_waitqueue_head(&group->container_q);
Alex Williamson's avatar
Alex Williamson committed
341
	group->iommu_group = iommu_group;
342 343 344
#ifdef CONFIG_VFIO_NOIOMMU
	group->noiommu = (iommu_group_get_iommudata(iommu_group) == &noiommu);
#endif
345
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
Alex Williamson's avatar
Alex Williamson committed
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367

	group->nb.notifier_call = vfio_iommu_group_notifier;

	/*
	 * blocking notifiers acquire a rwsem around registering and hold
	 * it around callback.  Therefore, need to register outside of
	 * vfio.group_lock to avoid A-B/B-A contention.  Our callback won't
	 * do anything unless it can find the group in vfio.group_list, so
	 * no harm in registering early.
	 */
	ret = iommu_group_register_notifier(iommu_group, &group->nb);
	if (ret) {
		kfree(group);
		return ERR_PTR(ret);
	}

	mutex_lock(&vfio.group_lock);

	/* Did we race creating this group? */
	list_for_each_entry(tmp, &vfio.group_list, vfio_next) {
		if (tmp->iommu_group == iommu_group) {
			vfio_group_get(tmp);
368
			vfio_group_unlock_and_free(group);
Alex Williamson's avatar
Alex Williamson committed
369 370 371 372
			return tmp;
		}
	}

373 374 375 376 377 378
	minor = vfio_alloc_group_minor(group);
	if (minor < 0) {
		vfio_group_unlock_and_free(group);
		return ERR_PTR(minor);
	}

379 380
	dev = device_create(vfio.class, NULL,
			    MKDEV(MAJOR(vfio.group_devt), minor),
381 382
			    group, "%s%d", group->noiommu ? "noiommu-" : "",
			    iommu_group_id(iommu_group));
Alex Williamson's avatar
Alex Williamson committed
383 384
	if (IS_ERR(dev)) {
		vfio_free_group_minor(minor);
385
		vfio_group_unlock_and_free(group);
386
		return ERR_CAST(dev);
Alex Williamson's avatar
Alex Williamson committed
387 388 389 390 391 392 393 394 395 396 397 398
	}

	group->minor = minor;
	group->dev = dev;

	list_add(&group->vfio_next, &vfio.group_list);

	mutex_unlock(&vfio.group_lock);

	return group;
}

399
/* called with vfio.group_lock held */
Alex Williamson's avatar
Alex Williamson committed
400 401 402
static void vfio_group_release(struct kref *kref)
{
	struct vfio_group *group = container_of(kref, struct vfio_group, kref);
403
	struct vfio_unbound_dev *unbound, *tmp;
404
	struct iommu_group *iommu_group = group->iommu_group;
Alex Williamson's avatar
Alex Williamson committed
405 406

	WARN_ON(!list_empty(&group->device_list));
407
	WARN_ON(group->notifier.head);
Alex Williamson's avatar
Alex Williamson committed
408

409 410 411 412 413 414
	list_for_each_entry_safe(unbound, tmp,
				 &group->unbound_list, unbound_next) {
		list_del(&unbound->unbound_next);
		kfree(unbound);
	}

415
	device_destroy(vfio.class, MKDEV(MAJOR(vfio.group_devt), group->minor));
Alex Williamson's avatar
Alex Williamson committed
416 417
	list_del(&group->vfio_next);
	vfio_free_group_minor(group->minor);
418
	vfio_group_unlock_and_free(group);
419
	iommu_group_put(iommu_group);
Alex Williamson's avatar
Alex Williamson committed
420 421 422 423
}

static void vfio_group_put(struct vfio_group *group)
{
424
	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
Alex Williamson's avatar
Alex Williamson committed
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
struct vfio_group_put_work {
	struct work_struct work;
	struct vfio_group *group;
};

static void vfio_group_put_bg(struct work_struct *work)
{
	struct vfio_group_put_work *do_work;

	do_work = container_of(work, struct vfio_group_put_work, work);

	vfio_group_put(do_work->group);
	kfree(do_work);
}

static void vfio_group_schedule_put(struct vfio_group *group)
{
	struct vfio_group_put_work *do_work;

	do_work = kmalloc(sizeof(*do_work), GFP_KERNEL);
	if (WARN_ON(!do_work))
		return;

	INIT_WORK(&do_work->work, vfio_group_put_bg);
	do_work->group = group;
	schedule_work(&do_work->work);
}

Alex Williamson's avatar
Alex Williamson committed
455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
/* Assume group_lock or group reference is held */
static void vfio_group_get(struct vfio_group *group)
{
	kref_get(&group->kref);
}

/*
 * Not really a try as we will sleep for mutex, but we need to make
 * sure the group pointer is valid under lock and get a reference.
 */
static struct vfio_group *vfio_group_try_get(struct vfio_group *group)
{
	struct vfio_group *target = group;

	mutex_lock(&vfio.group_lock);
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group == target) {
			vfio_group_get(group);
			mutex_unlock(&vfio.group_lock);
			return group;
		}
	}
	mutex_unlock(&vfio.group_lock);

	return NULL;
}

static
struct vfio_group *vfio_group_get_from_iommu(struct iommu_group *iommu_group)
{
	struct vfio_group *group;

	mutex_lock(&vfio.group_lock);
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group->iommu_group == iommu_group) {
			vfio_group_get(group);
			mutex_unlock(&vfio.group_lock);
			return group;
		}
	}
	mutex_unlock(&vfio.group_lock);

	return NULL;
}

static struct vfio_group *vfio_group_get_from_minor(int minor)
{
	struct vfio_group *group;

	mutex_lock(&vfio.group_lock);
	group = idr_find(&vfio.group_idr, minor);
	if (!group) {
		mutex_unlock(&vfio.group_lock);
		return NULL;
	}
	vfio_group_get(group);
	mutex_unlock(&vfio.group_lock);

	return group;
}

516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
static struct vfio_group *vfio_group_get_from_dev(struct device *dev)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;

	iommu_group = iommu_group_get(dev);
	if (!iommu_group)
		return NULL;

	group = vfio_group_get_from_iommu(iommu_group);
	iommu_group_put(iommu_group);

	return group;
}

Alex Williamson's avatar
Alex Williamson committed
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
/**
 * Device objects - create, release, get, put, search
 */
static
struct vfio_device *vfio_group_create_device(struct vfio_group *group,
					     struct device *dev,
					     const struct vfio_device_ops *ops,
					     void *device_data)
{
	struct vfio_device *device;

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

	kref_init(&device->kref);
	device->dev = dev;
	device->group = group;
	device->ops = ops;
	device->device_data = device_data;
551
	dev_set_drvdata(dev, device);
Alex Williamson's avatar
Alex Williamson committed
552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580

	/* No need to get group_lock, caller has group reference */
	vfio_group_get(group);

	mutex_lock(&group->device_lock);
	list_add(&device->group_next, &group->device_list);
	mutex_unlock(&group->device_lock);

	return device;
}

static void vfio_device_release(struct kref *kref)
{
	struct vfio_device *device = container_of(kref,
						  struct vfio_device, kref);
	struct vfio_group *group = device->group;

	list_del(&device->group_next);
	mutex_unlock(&group->device_lock);

	dev_set_drvdata(device->dev, NULL);

	kfree(device);

	/* vfio_del_group_dev may be waiting for this device */
	wake_up(&vfio.release_q);
}

/* Device reference always implies a group reference */
581
void vfio_device_put(struct vfio_device *device)
Alex Williamson's avatar
Alex Williamson committed
582
{
583
	struct vfio_group *group = device->group;
584
	kref_put_mutex(&device->kref, vfio_device_release, &group->device_lock);
585
	vfio_group_put(group);
Alex Williamson's avatar
Alex Williamson committed
586
}
587
EXPORT_SYMBOL_GPL(vfio_device_put);
Alex Williamson's avatar
Alex Williamson committed
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

static void vfio_device_get(struct vfio_device *device)
{
	vfio_group_get(device->group);
	kref_get(&device->kref);
}

static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
						 struct device *dev)
{
	struct vfio_device *device;

	mutex_lock(&group->device_lock);
	list_for_each_entry(device, &group->device_list, group_next) {
		if (device->dev == dev) {
			vfio_device_get(device);
			mutex_unlock(&group->device_lock);
			return device;
		}
	}
	mutex_unlock(&group->device_lock);
	return NULL;
}

/*
613 614 615 616 617 618 619 620 621 622 623 624 625
 * Some drivers, like pci-stub, are only used to prevent other drivers from
 * claiming a device and are therefore perfectly legitimate for a user owned
 * group.  The pci-stub driver has no dependencies on DMA or the IOVA mapping
 * of the device, but it does prevent the user from having direct access to
 * the device, which is useful in some circumstances.
 *
 * We also assume that we can include PCI interconnect devices, ie. bridges.
 * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge
 * then all of the downstream devices will be part of the same IOMMU group as
 * the bridge.  Thus, if placing the bridge into the user owned IOVA space
 * breaks anything, it only does so for user owned devices downstream.  Note
 * that error notification via MSI can be affected for platforms that handle
 * MSI within the same IOVA space as DMA.
Alex Williamson's avatar
Alex Williamson committed
626
 */
627
static const char * const vfio_driver_whitelist[] = { "pci-stub" };
Alex Williamson's avatar
Alex Williamson committed
628

629
static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
Alex Williamson's avatar
Alex Williamson committed
630
{
631 632 633 634 635 636 637
	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
			return true;
	}

638 639 640
	return match_string(vfio_driver_whitelist,
			    ARRAY_SIZE(vfio_driver_whitelist),
			    drv->name) >= 0;
Alex Williamson's avatar
Alex Williamson committed
641 642 643
}

/*
644 645 646 647 648
 * A vfio group is viable for use by userspace if all devices are in
 * one of the following states:
 *  - driver-less
 *  - bound to a vfio driver
 *  - bound to a whitelisted driver
649
 *  - a PCI interconnect device
650 651 652 653 654 655
 *
 * We use two methods to determine whether a device is bound to a vfio
 * driver.  The first is to test whether the device exists in the vfio
 * group.  The second is to test if the device exists on the group
 * unbound_list, indicating it's in the middle of transitioning from
 * a vfio driver to driver-less.
Alex Williamson's avatar
Alex Williamson committed
656 657 658 659 660
 */
static int vfio_dev_viable(struct device *dev, void *data)
{
	struct vfio_group *group = data;
	struct vfio_device *device;
661
	struct device_driver *drv = READ_ONCE(dev->driver);
662 663 664 665 666 667 668 669 670 671 672
	struct vfio_unbound_dev *unbound;
	int ret = -EINVAL;

	mutex_lock(&group->unbound_lock);
	list_for_each_entry(unbound, &group->unbound_list, unbound_next) {
		if (dev == unbound->dev) {
			ret = 0;
			break;
		}
	}
	mutex_unlock(&group->unbound_lock);
Alex Williamson's avatar
Alex Williamson committed
673

674
	if (!ret || !drv || vfio_dev_whitelisted(dev, drv))
Alex Williamson's avatar
Alex Williamson committed
675 676 677 678 679 680 681 682
		return 0;

	device = vfio_group_get_device(group, dev);
	if (device) {
		vfio_device_put(device);
		return 0;
	}

683
	return ret;
Alex Williamson's avatar
Alex Williamson committed
684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
}

/**
 * Async device support
 */
static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
{
	struct vfio_device *device;

	/* Do we already know about it?  We shouldn't */
	device = vfio_group_get_device(group, dev);
	if (WARN_ON_ONCE(device)) {
		vfio_device_put(device);
		return 0;
	}

	/* Nothing to do for idle groups */
	if (!atomic_read(&group->container_users))
		return 0;

	/* TODO Prevent device auto probing */
705 706
	dev_WARN(dev, "Device added to live group %d!\n",
		 iommu_group_id(group->iommu_group));
Alex Williamson's avatar
Alex Williamson committed
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724

	return 0;
}

static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
{
	/* We don't care what happens when the group isn't in use */
	if (!atomic_read(&group->container_users))
		return 0;

	return vfio_dev_viable(dev, group);
}

static int vfio_iommu_group_notifier(struct notifier_block *nb,
				     unsigned long action, void *data)
{
	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
	struct device *dev = data;
725
	struct vfio_unbound_dev *unbound;
Alex Williamson's avatar
Alex Williamson committed
726 727

	/*
728 729
	 * Need to go through a group_lock lookup to get a reference or we
	 * risk racing a group being removed.  Ignore spurious notifies.
Alex Williamson's avatar
Alex Williamson committed
730 731
	 */
	group = vfio_group_try_get(group);
732
	if (!group)
Alex Williamson's avatar
Alex Williamson committed
733 734 735 736 737 738 739
		return NOTIFY_OK;

	switch (action) {
	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
		vfio_group_nb_add_dev(group, dev);
		break;
	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
740 741 742 743 744 745 746
		/*
		 * Nothing to do here.  If the device is in use, then the
		 * vfio sub-driver should block the remove callback until
		 * it is unused.  If the device is unused or attached to a
		 * stub driver, then it should be released and we don't
		 * care that it will be going away.
		 */
Alex Williamson's avatar
Alex Williamson committed
747 748
		break;
	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
749 750
		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
			iommu_group_id(group->iommu_group));
Alex Williamson's avatar
Alex Williamson committed
751 752
		break;
	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
753 754
		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
			iommu_group_id(group->iommu_group), dev->driver->name);
Alex Williamson's avatar
Alex Williamson committed
755 756 757
		BUG_ON(vfio_group_nb_verify(group, dev));
		break;
	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
758 759 760
		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
			__func__, iommu_group_id(group->iommu_group),
			dev->driver->name);
Alex Williamson's avatar
Alex Williamson committed
761 762
		break;
	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
763 764
		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
			iommu_group_id(group->iommu_group));
Alex Williamson's avatar
Alex Williamson committed
765 766 767 768 769 770 771
		/*
		 * XXX An unbound device in a live group is ok, but we'd
		 * really like to avoid the above BUG_ON by preventing other
		 * drivers from binding to it.  Once that occurs, we have to
		 * stop the system to maintain isolation.  At a minimum, we'd
		 * want a toggle to disable driver auto probe for this device.
		 */
772 773 774 775 776 777 778 779 780 781 782

		mutex_lock(&group->unbound_lock);
		list_for_each_entry(unbound,
				    &group->unbound_list, unbound_next) {
			if (dev == unbound->dev) {
				list_del(&unbound->unbound_next);
				kfree(unbound);
				break;
			}
		}
		mutex_unlock(&group->unbound_lock);
Alex Williamson's avatar
Alex Williamson committed
783 784 785
		break;
	}

786 787 788 789 790 791 792 793
	/*
	 * If we're the last reference to the group, the group will be
	 * released, which includes unregistering the iommu group notifier.
	 * We hold a read-lock on that notifier list, unregistering needs
	 * a write-lock... deadlock.  Release our reference asynchronously
	 * to avoid that situation.
	 */
	vfio_group_schedule_put(group);
Alex Williamson's avatar
Alex Williamson committed
794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
	return NOTIFY_OK;
}

/**
 * VFIO driver API
 */
int vfio_add_group_dev(struct device *dev,
		       const struct vfio_device_ops *ops, void *device_data)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;
	struct vfio_device *device;

	iommu_group = iommu_group_get(dev);
	if (!iommu_group)
		return -EINVAL;

	group = vfio_group_get_from_iommu(iommu_group);
	if (!group) {
813
		group = vfio_create_group(iommu_group);
Alex Williamson's avatar
Alex Williamson committed
814 815 816 817
		if (IS_ERR(group)) {
			iommu_group_put(iommu_group);
			return PTR_ERR(group);
		}
818 819 820 821 822 823
	} else {
		/*
		 * A found vfio_group already holds a reference to the
		 * iommu_group.  A created vfio_group keeps the reference.
		 */
		iommu_group_put(iommu_group);
Alex Williamson's avatar
Alex Williamson committed
824 825 826 827
	}

	device = vfio_group_get_device(group, dev);
	if (device) {
828 829
		dev_WARN(dev, "Device already exists on group %d\n",
			 iommu_group_id(iommu_group));
Alex Williamson's avatar
Alex Williamson committed
830 831 832 833 834 835 836 837 838 839 840 841
		vfio_device_put(device);
		vfio_group_put(group);
		return -EBUSY;
	}

	device = vfio_group_create_device(group, dev, ops, device_data);
	if (IS_ERR(device)) {
		vfio_group_put(group);
		return PTR_ERR(device);
	}

	/*
842 843 844
	 * Drop all but the vfio_device reference.  The vfio_device holds
	 * a reference to the vfio_group, which holds a reference to the
	 * iommu_group.
Alex Williamson's avatar
Alex Williamson committed
845 846 847 848 849 850 851
	 */
	vfio_group_put(group);

	return 0;
}
EXPORT_SYMBOL_GPL(vfio_add_group_dev);

852
/**
853 854 855 856 857
 * Get a reference to the vfio_device for a device.  Even if the
 * caller thinks they own the device, they could be racing with a
 * release call path, so we can't trust drvdata for the shortcut.
 * Go the long way around, from the iommu_group to the vfio_group
 * to the vfio_device.
858 859 860
 */
struct vfio_device *vfio_device_get_from_dev(struct device *dev)
{
861 862 863
	struct vfio_group *group;
	struct vfio_device *device;

864
	group = vfio_group_get_from_dev(dev);
865 866 867 868 869
	if (!group)
		return NULL;

	device = vfio_group_get_device(group, dev);
	vfio_group_put(group);
870 871 872 873 874

	return device;
}
EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);

875 876 877
static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
						     char *buf)
{
878
	struct vfio_device *it, *device = NULL;
879 880

	mutex_lock(&group->device_lock);
881 882 883
	list_for_each_entry(it, &group->device_list, group_next) {
		if (!strcmp(dev_name(it->dev), buf)) {
			device = it;
884 885 886 887 888 889 890 891 892
			vfio_device_get(device);
			break;
		}
	}
	mutex_unlock(&group->device_lock);

	return device;
}

893 894 895 896 897 898 899 900 901
/*
 * Caller must hold a reference to the vfio_device
 */
void *vfio_device_data(struct vfio_device *device)
{
	return device->device_data;
}
EXPORT_SYMBOL_GPL(vfio_device_data);

Alex Williamson's avatar
Alex Williamson committed
902 903 904 905 906
/*
 * Decrement the device reference count and wait for the device to be
 * removed.  Open file descriptors for the device... */
void *vfio_del_group_dev(struct device *dev)
{
907
	DEFINE_WAIT_FUNC(wait, woken_wake_function);
Alex Williamson's avatar
Alex Williamson committed
908 909 910
	struct vfio_device *device = dev_get_drvdata(dev);
	struct vfio_group *group = device->group;
	void *device_data = device->device_data;
911
	struct vfio_unbound_dev *unbound;
912
	unsigned int i = 0;
913
	bool interrupted = false;
Alex Williamson's avatar
Alex Williamson committed
914

915 916 917 918 919 920
	/*
	 * The group exists so long as we have a device reference.  Get
	 * a group reference and use it to scan for the device going away.
	 */
	vfio_group_get(group);

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938
	/*
	 * When the device is removed from the group, the group suddenly
	 * becomes non-viable; the device has a driver (until the unbind
	 * completes), but it's not present in the group.  This is bad news
	 * for any external users that need to re-acquire a group reference
	 * in order to match and release their existing reference.  To
	 * solve this, we track such devices on the unbound_list to bridge
	 * the gap until they're fully unbound.
	 */
	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
	if (unbound) {
		unbound->dev = dev;
		mutex_lock(&group->unbound_lock);
		list_add(&unbound->unbound_next, &group->unbound_list);
		mutex_unlock(&group->unbound_lock);
	}
	WARN_ON(!unbound);

Alex Williamson's avatar
Alex Williamson committed
939 940
	vfio_device_put(device);

941 942 943 944 945 946 947 948
	/*
	 * If the device is still present in the group after the above
	 * 'put', then it is in use and we need to request it from the
	 * bus driver.  The driver may in turn need to request the
	 * device from the user.  We send the request on an arbitrary
	 * interval with counter to allow the driver to take escalating
	 * measures to release the device if it has the ability to do so.
	 */
949 950
	add_wait_queue(&vfio.release_q, &wait);

951 952 953 954 955 956 957 958 959 960
	do {
		device = vfio_group_get_device(group, dev);
		if (!device)
			break;

		if (device->ops->request)
			device->ops->request(device_data, i++);

		vfio_device_put(device);

961
		if (interrupted) {
962
			wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
963
		} else {
964 965
			wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
			if (signal_pending(current)) {
966 967 968 969 970 971 972 973
				interrupted = true;
				dev_warn(dev,
					 "Device is currently in use, task"
					 " \"%s\" (%d) "
					 "blocked until device is released",
					 current->comm, task_pid_nr(current));
			}
		}
974

975 976 977
	} while (1);

	remove_wait_queue(&vfio.release_q, &wait);
978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994
	/*
	 * In order to support multiple devices per group, devices can be
	 * plucked from the group while other devices in the group are still
	 * in use.  The container persists with this group and those remaining
	 * devices still attached.  If the user creates an isolation violation
	 * by binding this device to another driver while the group is still in
	 * use, that's their fault.  However, in the case of removing the last,
	 * or potentially the only, device in the group there can be no other
	 * in-use devices in the group.  The user has done their due diligence
	 * and we should lay no claims to those devices.  In order to do that,
	 * we need to make sure the group is detached from the container.
	 * Without this stall, we're potentially racing with a user process
	 * that may attempt to immediately bind this device to another driver.
	 */
	if (list_empty(&group->device_list))
		wait_event(group->container_q, !group->container);

995
	vfio_group_put(group);
Alex Williamson's avatar
Alex Williamson committed
996 997 998 999 1000 1001 1002 1003 1004 1005 1006

	return device_data;
}
EXPORT_SYMBOL_GPL(vfio_del_group_dev);

/**
 * VFIO base fd, /dev/vfio/vfio
 */
static long vfio_ioctl_check_extension(struct vfio_container *container,
				       unsigned long arg)
{
1007
	struct vfio_iommu_driver *driver;
Alex Williamson's avatar
Alex Williamson committed
1008 1009
	long ret = 0;

1010 1011 1012 1013
	down_read(&container->group_lock);

	driver = container->iommu_driver;

Alex Williamson's avatar
Alex Williamson committed
1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024
	switch (arg) {
		/* No base extensions yet */
	default:
		/*
		 * If no driver is set, poll all registered drivers for
		 * extensions and return the first positive result.  If
		 * a driver is already set, further queries will be passed
		 * only to that driver.
		 */
		if (!driver) {
			mutex_lock(&vfio.iommu_drivers_lock);
1025 1026
			list_for_each_entry(driver, &vfio.iommu_drivers_list,
					    vfio_next) {
1027 1028 1029 1030 1031 1032 1033 1034

#ifdef CONFIG_VFIO_NOIOMMU
				if (!list_empty(&container->group_list) &&
				    (container->noiommu !=
				     (driver->ops == &vfio_noiommu_ops)))
					continue;
#endif

Alex Williamson's avatar
Alex Williamson committed
1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
				if (!try_module_get(driver->ops->owner))
					continue;

				ret = driver->ops->ioctl(NULL,
							 VFIO_CHECK_EXTENSION,
							 arg);
				module_put(driver->ops->owner);
				if (ret > 0)
					break;
			}
			mutex_unlock(&vfio.iommu_drivers_lock);
		} else
			ret = driver->ops->ioctl(container->iommu_data,
						 VFIO_CHECK_EXTENSION, arg);
	}

1051 1052
	up_read(&container->group_lock);

Alex Williamson's avatar
Alex Williamson committed
1053 1054 1055
	return ret;
}

1056
/* hold write lock on container->group_lock */
Alex Williamson's avatar
Alex Williamson committed
1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086
static int __vfio_container_attach_groups(struct vfio_container *container,
					  struct vfio_iommu_driver *driver,
					  void *data)
{
	struct vfio_group *group;
	int ret = -ENODEV;

	list_for_each_entry(group, &container->group_list, container_next) {
		ret = driver->ops->attach_group(data, group->iommu_group);
		if (ret)
			goto unwind;
	}

	return ret;

unwind:
	list_for_each_entry_continue_reverse(group, &container->group_list,
					     container_next) {
		driver->ops->detach_group(data, group->iommu_group);
	}

	return ret;
}

static long vfio_ioctl_set_iommu(struct vfio_container *container,
				 unsigned long arg)
{
	struct vfio_iommu_driver *driver;
	long ret = -ENODEV;

1087
	down_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1088 1089 1090 1091 1092 1093 1094 1095 1096 1097

	/*
	 * The container is designed to be an unprivileged interface while
	 * the group can be assigned to specific users.  Therefore, only by
	 * adding a group to a container does the user get the privilege of
	 * enabling the iommu, which may allocate finite resources.  There
	 * is no unset_iommu, but by removing all the groups from a container,
	 * the container is deprivileged and returns to an unset state.
	 */
	if (list_empty(&container->group_list) || container->iommu_driver) {
1098
		up_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1099 1100 1101 1102
		return -EINVAL;
	}

	mutex_lock(&vfio.iommu_drivers_lock);
1103
	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
Alex Williamson's avatar
Alex Williamson committed
1104 1105
		void *data;

1106 1107 1108 1109 1110 1111 1112 1113 1114
#ifdef CONFIG_VFIO_NOIOMMU
		/*
		 * Only noiommu containers can use vfio-noiommu and noiommu
		 * containers can only use vfio-noiommu.
		 */
		if (container->noiommu != (driver->ops == &vfio_noiommu_ops))
			continue;
#endif

Alex Williamson's avatar
Alex Williamson committed
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
		if (!try_module_get(driver->ops->owner))
			continue;

		/*
		 * The arg magic for SET_IOMMU is the same as CHECK_EXTENSION,
		 * so test which iommu driver reported support for this
		 * extension and call open on them.  We also pass them the
		 * magic, allowing a single driver to support multiple
		 * interfaces if they'd like.
		 */
		if (driver->ops->ioctl(NULL, VFIO_CHECK_EXTENSION, arg) <= 0) {
			module_put(driver->ops->owner);
			continue;
		}

		data = driver->ops->open(arg);
		if (IS_ERR(data)) {
			ret = PTR_ERR(data);
			module_put(driver->ops->owner);
1134
			continue;
Alex Williamson's avatar
Alex Williamson committed
1135 1136 1137
		}

		ret = __vfio_container_attach_groups(container, driver, data);
1138
		if (ret) {
Alex Williamson's avatar
Alex Williamson committed
1139 1140
			driver->ops->release(data);
			module_put(driver->ops->owner);
1141
			continue;
Alex Williamson's avatar
Alex Williamson committed
1142 1143
		}

1144 1145 1146
		container->iommu_driver = driver;
		container->iommu_data = data;
		break;
Alex Williamson's avatar
Alex Williamson committed
1147 1148 1149
	}

	mutex_unlock(&vfio.iommu_drivers_lock);
1150
	up_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176

	return ret;
}

static long vfio_fops_unl_ioctl(struct file *filep,
				unsigned int cmd, unsigned long arg)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	void *data;
	long ret = -EINVAL;

	if (!container)
		return ret;

	switch (cmd) {
	case VFIO_GET_API_VERSION:
		ret = VFIO_API_VERSION;
		break;
	case VFIO_CHECK_EXTENSION:
		ret = vfio_ioctl_check_extension(container, arg);
		break;
	case VFIO_SET_IOMMU:
		ret = vfio_ioctl_set_iommu(container, arg);
		break;
	default:
1177 1178 1179
		driver = container->iommu_driver;
		data = container->iommu_data;

Alex Williamson's avatar
Alex Williamson committed
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
		if (driver) /* passthrough all unrecognized ioctls */
			ret = driver->ops->ioctl(data, cmd, arg);
	}

	return ret;
}

#ifdef CONFIG_COMPAT
static long vfio_fops_compat_ioctl(struct file *filep,
				   unsigned int cmd, unsigned long arg)
{
	arg = (unsigned long)compat_ptr(arg);
	return vfio_fops_unl_ioctl(filep, cmd, arg);
}
#endif	/* CONFIG_COMPAT */

static int vfio_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_container *container;

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

	INIT_LIST_HEAD(&container->group_list);
1205
	init_rwsem(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231
	kref_init(&container->kref);

	filep->private_data = container;

	return 0;
}

static int vfio_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_container *container = filep->private_data;

	filep->private_data = NULL;

	vfio_container_put(container);

	return 0;
}

/*
 * Once an iommu driver is set, we optionally pass read/write/mmap
 * on to the driver, allowing management interfaces beyond ioctl.
 */
static ssize_t vfio_fops_read(struct file *filep, char __user *buf,
			      size_t count, loff_t *ppos)
{
	struct vfio_container *container = filep->private_data;
1232 1233
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;
Alex Williamson's avatar
Alex Williamson committed
1234

1235 1236 1237 1238
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->read))
		ret = driver->ops->read(container->iommu_data,
					buf, count, ppos);
Alex Williamson's avatar
Alex Williamson committed
1239

1240
	return ret;
Alex Williamson's avatar
Alex Williamson committed
1241 1242 1243 1244 1245 1246
}

static ssize_t vfio_fops_write(struct file *filep, const char __user *buf,
			       size_t count, loff_t *ppos)
{
	struct vfio_container *container = filep->private_data;
1247 1248
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;
Alex Williamson's avatar
Alex Williamson committed
1249

1250 1251 1252 1253 1254 1255
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->write))
		ret = driver->ops->write(container->iommu_data,
					 buf, count, ppos);

	return ret;
Alex Williamson's avatar
Alex Williamson committed
1256 1257 1258 1259 1260
}

static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma)
{
	struct vfio_container *container = filep->private_data;
1261 1262
	struct vfio_iommu_driver *driver;
	int ret = -EINVAL;
Alex Williamson's avatar
Alex Williamson committed
1263

1264 1265 1266 1267 1268
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->mmap))
		ret = driver->ops->mmap(container->iommu_data, vma);

	return ret;
Alex Williamson's avatar
Alex Williamson committed
1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291
}

static const struct file_operations vfio_fops = {
	.owner		= THIS_MODULE,
	.open		= vfio_fops_open,
	.release	= vfio_fops_release,
	.read		= vfio_fops_read,
	.write		= vfio_fops_write,
	.unlocked_ioctl	= vfio_fops_unl_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vfio_fops_compat_ioctl,
#endif
	.mmap		= vfio_fops_mmap,
};

/**
 * VFIO Group fd, /dev/vfio/$GROUP
 */
static void __vfio_group_unset_container(struct vfio_group *group)
{
	struct vfio_container *container = group->container;
	struct vfio_iommu_driver *driver;

1292
	down_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1293 1294 1295 1296 1297 1298 1299

	driver = container->iommu_driver;
	if (driver)
		driver->ops->detach_group(container->iommu_data,
					  group->iommu_group);

	group->container = NULL;
1300
	wake_up(&group->container_q);
Alex Williamson's avatar
Alex Williamson committed
1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
	list_del(&group->container_next);

	/* Detaching the last group deprivileges a container, remove iommu */
	if (driver && list_empty(&container->group_list)) {
		driver->ops->release(container->iommu_data);
		module_put(driver->ops->owner);
		container->iommu_driver = NULL;
		container->iommu_data = NULL;
	}

1311
	up_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349

	vfio_container_put(container);
}

/*
 * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
 * if there was no container to unset.  Since the ioctl is called on
 * the group, we know that still exists, therefore the only valid
 * transition here is 1->0.
 */
static int vfio_group_unset_container(struct vfio_group *group)
{
	int users = atomic_cmpxchg(&group->container_users, 1, 0);

	if (!users)
		return -EINVAL;
	if (users != 1)
		return -EBUSY;

	__vfio_group_unset_container(group);

	return 0;
}

/*
 * When removing container users, anything that removes the last user
 * implicitly removes the group from the container.  That is, if the
 * group file descriptor is closed, as well as any device file descriptors,
 * the group is free.
 */
static void vfio_group_try_dissolve_container(struct vfio_group *group)
{
	if (0 == atomic_dec_if_positive(&group->container_users))
		__vfio_group_unset_container(group);
}

static int vfio_group_set_container(struct vfio_group *group, int container_fd)
{
1350
	struct fd f;
Alex Williamson's avatar
Alex Williamson committed
1351 1352
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
1353
	int ret = 0;
Alex Williamson's avatar
Alex Williamson committed
1354 1355 1356 1357

	if (atomic_read(&group->container_users))
		return -EINVAL;

1358 1359 1360
	if (group->noiommu && !capable(CAP_SYS_RAWIO))
		return -EPERM;

1361 1362
	f = fdget(container_fd);
	if (!f.file)
Alex Williamson's avatar
Alex Williamson committed
1363 1364 1365
		return -EBADF;

	/* Sanity check, is this really our fd? */
1366 1367
	if (f.file->f_op != &vfio_fops) {
		fdput(f);
Alex Williamson's avatar
Alex Williamson committed
1368 1369 1370
		return -EINVAL;
	}

1371
	container = f.file->private_data;
Alex Williamson's avatar
Alex Williamson committed
1372 1373
	WARN_ON(!container); /* fget ensures we don't race vfio_release */

1374
	down_write(&container->group_lock);
Alex Williamson's avatar
Alex Williamson committed
1375

1376 1377 1378 1379 1380 1381 1382
	/* Real groups and fake groups cannot mix */
	if (!list_empty(&container->group_list) &&
	    container->noiommu != group->noiommu) {
		ret = -EPERM;
		goto unlock_out;
	}

Alex Williamson's avatar
Alex Williamson committed
1383 1384 1385 1386 1387 1388 1389 1390 1391
	driver = container->iommu_driver;
	if (driver) {
		ret = driver->ops->attach_group(container->iommu_data,
						group->iommu_group);
		if (ret)
			goto unlock_out;
	}

	group->container = container;
1392
	container->noiommu = group->noiommu;
Alex Williamson's avatar
Alex Williamson committed
1393 1394 1395 1396 1397 1398 1399
	list_add(&group->container_next, &container->group_list);

	/* Get a reference on the container and mark a user within the group */
	vfio_container_get(container);
	atomic_inc(&group->container_users);

unlock_out:
1400
	up_write(&container->group_lock);
1401
	fdput(f);
Alex Williamson's avatar
Alex Williamson committed
1402 1403 1404 1405 1406 1407 1408 1409 1410
	return ret;
}

static bool vfio_group_viable(struct vfio_group *group)
{
	return (iommu_group_for_each_dev(group->iommu_group,
					 group, vfio_dev_viable) == 0);
}

1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427
static int vfio_group_add_container_user(struct vfio_group *group)
{
	if (!atomic_inc_not_zero(&group->container_users))
		return -EINVAL;

	if (group->noiommu) {
		atomic_dec(&group->container_users);
		return -EPERM;
	}
	if (!group->container->iommu_driver || !vfio_group_viable(group)) {
		atomic_dec(&group->container_users);
		return -EINVAL;
	}

	return 0;
}

Alex Williamson's avatar
Alex Williamson committed
1428 1429 1430 1431 1432 1433
static const struct file_operations vfio_device_fops;

static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
{
	struct vfio_device *device;
	struct file *filep;
1434
	int ret;
Alex Williamson's avatar
Alex Williamson committed
1435 1436 1437 1438 1439

	if (0 == atomic_read(&group->container_users) ||
	    !group->container->iommu_driver || !vfio_group_viable(group))
		return -EINVAL;

1440 1441 1442
	if (group->noiommu && !capable(CAP_SYS_RAWIO))
		return -EPERM;

1443 1444 1445
	device = vfio_device_get_from_name(group, buf);
	if (!device)
		return -ENODEV;
Alex Williamson's avatar
Alex Williamson committed
1446

1447 1448 1449 1450 1451
	ret = device->ops->open(device->device_data);
	if (ret) {
		vfio_device_put(device);
		return ret;
	}
Alex Williamson's avatar
Alex Williamson committed
1452

1453 1454 1455 1456 1457 1458 1459 1460 1461 1462
	/*
	 * We can't use anon_inode_getfd() because we need to modify
	 * the f_mode flags directly to allow more than just ioctls
	 */
	ret = get_unused_fd_flags(O_CLOEXEC);
	if (ret < 0) {
		device->ops->release(device->device_data);
		vfio_device_put(device);
		return ret;
	}
Alex Williamson's avatar
Alex Williamson committed
1463

1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
				   device, O_RDWR);
	if (IS_ERR(filep)) {
		put_unused_fd(ret);
		ret = PTR_ERR(filep);
		device->ops->release(device->device_data);
		vfio_device_put(device);
		return ret;
	}

	/*
	 * TODO: add an anon_inode interface to do this.
	 * Appears to be missing by lack of need rather than
	 * explicitly prevented.  Now there's need.
	 */
	filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
Alex Williamson's avatar
Alex Williamson committed
1480

1481
	atomic_inc(&group->container_users);
1482

1483
	fd_install(ret, filep);
Alex Williamson's avatar
Alex Williamson committed
1484

1485 1486 1487 1488
	if (group->noiommu)
		dev_warn(device->dev, "vfio-noiommu device opened by user "
			 "(%s:%d)\n", current->comm, task_pid_nr(current));

Alex Williamson's avatar
Alex Williamson committed
1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570
	return ret;
}

static long vfio_group_fops_unl_ioctl(struct file *filep,
				      unsigned int cmd, unsigned long arg)
{
	struct vfio_group *group = filep->private_data;
	long ret = -ENOTTY;

	switch (cmd) {
	case VFIO_GROUP_GET_STATUS:
	{
		struct vfio_group_status status;
		unsigned long minsz;

		minsz = offsetofend(struct vfio_group_status, flags);

		if (copy_from_user(&status, (void __user *)arg, minsz))
			return -EFAULT;

		if (status.argsz < minsz)
			return -EINVAL;

		status.flags = 0;

		if (vfio_group_viable(group))
			status.flags |= VFIO_GROUP_FLAGS_VIABLE;

		if (group->container)
			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET;

		if (copy_to_user((void __user *)arg, &status, minsz))
			return -EFAULT;

		ret = 0;
		break;
	}
	case VFIO_GROUP_SET_CONTAINER:
	{
		int fd;

		if (get_user(fd, (int __user *)arg))
			return -EFAULT;

		if (fd < 0)
			return -EINVAL;

		ret = vfio_group_set_container(group, fd);
		break;
	}
	case VFIO_GROUP_UNSET_CONTAINER:
		ret = vfio_group_unset_container(group);
		break;
	case VFIO_GROUP_GET_DEVICE_FD:
	{
		char *buf;

		buf = strndup_user((const char __user *)arg, PAGE_SIZE);
		if (IS_ERR(buf))
			return PTR_ERR(buf);

		ret = vfio_group_get_device_fd(group, buf);
		kfree(buf);
		break;
	}
	}

	return ret;
}

#ifdef CONFIG_COMPAT
static long vfio_group_fops_compat_ioctl(struct file *filep,
					 unsigned int cmd, unsigned long arg)
{
	arg = (unsigned long)compat_ptr(arg);
	return vfio_group_fops_unl_ioctl(filep, cmd, arg);
}
#endif	/* CONFIG_COMPAT */

static int vfio_group_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_group *group;
1571
	int opened;
Alex Williamson's avatar
Alex Williamson committed
1572 1573 1574 1575 1576

	group = vfio_group_get_from_minor(iminor(inode));
	if (!group)
		return -ENODEV;

1577 1578 1579 1580 1581
	if (group->noiommu && !capable(CAP_SYS_RAWIO)) {
		vfio_group_put(group);
		return -EPERM;
	}

1582 1583 1584 1585 1586 1587 1588 1589
	/* Do we need multiple instances of the group open?  Seems not. */
	opened = atomic_cmpxchg(&group->opened, 0, 1);
	if (opened) {
		vfio_group_put(group);
		return -EBUSY;
	}

	/* Is something still in use from a previous open? */
Alex Williamson's avatar
Alex Williamson committed
1590
	if (group->container) {
1591
		atomic_dec(&group->opened);
Alex Williamson's avatar
Alex Williamson committed
1592 1593 1594 1595
		vfio_group_put(group);
		return -EBUSY;
	}

1596 1597 1598 1599
	/* Warn if previous user didn't cleanup and re-init to drop them */
	if (WARN_ON(group->notifier.head))
		BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

Alex Williamson's avatar
Alex Williamson committed
1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612
	filep->private_data = group;

	return 0;
}

static int vfio_group_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_group *group = filep->private_data;

	filep->private_data = NULL;

	vfio_group_try_dissolve_container(group);

1613 1614
	atomic_dec(&group->opened);

Alex Williamson's avatar
Alex Williamson committed
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 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710
	vfio_group_put(group);

	return 0;
}

static const struct file_operations vfio_group_fops = {
	.owner		= THIS_MODULE,
	.unlocked_ioctl	= vfio_group_fops_unl_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vfio_group_fops_compat_ioctl,
#endif
	.open		= vfio_group_fops_open,
	.release	= vfio_group_fops_release,
};

/**
 * VFIO Device fd
 */
static int vfio_device_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_device *device = filep->private_data;

	device->ops->release(device->device_data);

	vfio_group_try_dissolve_container(device->group);

	vfio_device_put(device);

	return 0;
}

static long vfio_device_fops_unl_ioctl(struct file *filep,
				       unsigned int cmd, unsigned long arg)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->ioctl))
		return -EINVAL;

	return device->ops->ioctl(device->device_data, cmd, arg);
}

static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf,
				     size_t count, loff_t *ppos)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->read))
		return -EINVAL;

	return device->ops->read(device->device_data, buf, count, ppos);
}

static ssize_t vfio_device_fops_write(struct file *filep,
				      const char __user *buf,
				      size_t count, loff_t *ppos)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->write))
		return -EINVAL;

	return device->ops->write(device->device_data, buf, count, ppos);
}

static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->mmap))
		return -EINVAL;

	return device->ops->mmap(device->device_data, vma);
}

#ifdef CONFIG_COMPAT
static long vfio_device_fops_compat_ioctl(struct file *filep,
					  unsigned int cmd, unsigned long arg)
{
	arg = (unsigned long)compat_ptr(arg);
	return vfio_device_fops_unl_ioctl(filep, cmd, arg);
}
#endif	/* CONFIG_COMPAT */

static const struct file_operations vfio_device_fops = {
	.owner		= THIS_MODULE,
	.release	= vfio_device_fops_release,
	.read		= vfio_device_fops_read,
	.write		= vfio_device_fops_write,
	.unlocked_ioctl	= vfio_device_fops_unl_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vfio_device_fops_compat_ioctl,
#endif
	.mmap		= vfio_device_fops_mmap,
};

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
/**
 * External user API, exported by symbols to be linked dynamically.
 *
 * The protocol includes:
 *  1. do normal VFIO init operation:
 *	- opening a new container;
 *	- attaching group(s) to it;
 *	- setting an IOMMU driver for a container.
 * When IOMMU is set for a container, all groups in it are
 * considered ready to use by an external user.
 *
 * 2. User space passes a group fd to an external user.
 * The external user calls vfio_group_get_external_user()
 * to verify that:
 *	- the group is initialized;
 *	- IOMMU is set for it.
 * If both checks passed, vfio_group_get_external_user()
 * increments the container user counter to prevent
 * the VFIO group from disposal before KVM exits.
 *
 * 3. The external user calls vfio_external_user_iommu_id()
 * to know an IOMMU ID.
 *
 * 4. When the external KVM finishes, it calls
 * vfio_group_put_external_user() to release the VFIO group.
 * This call decrements the container user counter.
 */
struct vfio_group *vfio_group_get_external_user(struct file *filep)
{
	struct vfio_group *group = filep->private_data;
1741
	int ret;
1742 1743 1744 1745

	if (filep->f_op != &vfio_group_fops)
		return ERR_PTR(-EINVAL);

1746 1747 1748
	ret = vfio_group_add_container_user(group);
	if (ret)
		return ERR_PTR(ret);
1749 1750 1751 1752 1753 1754 1755 1756 1757 1758

	vfio_group_get(group);

	return group;
}
EXPORT_SYMBOL_GPL(vfio_group_get_external_user);

void vfio_group_put_external_user(struct vfio_group *group)
{
	vfio_group_try_dissolve_container(group);
1759
	vfio_group_put(group);
1760 1761 1762
}
EXPORT_SYMBOL_GPL(vfio_group_put_external_user);

1763 1764 1765 1766 1767 1768 1769 1770 1771
bool vfio_external_group_match_file(struct vfio_group *test_group,
				    struct file *filep)
{
	struct vfio_group *group = filep->private_data;

	return (filep->f_op == &vfio_group_fops) && (group == test_group);
}
EXPORT_SYMBOL_GPL(vfio_external_group_match_file);

1772 1773 1774 1775 1776 1777
int vfio_external_user_iommu_id(struct vfio_group *group)
{
	return iommu_group_id(group->iommu_group);
}
EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);

1778 1779 1780 1781 1782 1783
long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
{
	return vfio_ioctl_check_extension(group->container, arg);
}
EXPORT_SYMBOL_GPL(vfio_external_check_extension);

1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818
/**
 * Sub-module support
 */
/*
 * Helper for managing a buffer of info chain capabilities, allocate or
 * reallocate a buffer with additional @size, filling in @id and @version
 * of the capability.  A pointer to the new capability is returned.
 *
 * NB. The chain is based at the head of the buffer, so new entries are
 * added to the tail, vfio_info_cap_shift() should be called to fixup the
 * next offsets prior to copying to the user buffer.
 */
struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
					       size_t size, u16 id, u16 version)
{
	void *buf;
	struct vfio_info_cap_header *header, *tmp;

	buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
	if (!buf) {
		kfree(caps->buf);
		caps->size = 0;
		return ERR_PTR(-ENOMEM);
	}

	caps->buf = buf;
	header = buf + caps->size;

	/* Eventually copied to user buffer, zero */
	memset(header, 0, size);

	header->id = id;
	header->version = version;

	/* Add to the end of the capability chain */
1819
	for (tmp = buf; tmp->next; tmp = buf + tmp->next)
1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831
		; /* nothing */

	tmp->next = caps->size;
	caps->size += size;

	return header;
}
EXPORT_SYMBOL_GPL(vfio_info_cap_add);

void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
{
	struct vfio_info_cap_header *tmp;
1832
	void *buf = (void *)caps->buf;
1833

1834
	for (tmp = buf; tmp->next; tmp = buf + tmp->next - offset)
1835 1836
		tmp->next += offset;
}
1837
EXPORT_SYMBOL(vfio_info_cap_shift);
1838

1839 1840
int vfio_info_add_capability(struct vfio_info_cap *caps,
			     struct vfio_info_cap_header *cap, size_t size)
1841 1842 1843
{
	struct vfio_info_cap_header *header;

1844
	header = vfio_info_cap_add(caps, size, cap->id, cap->version);
1845 1846 1847
	if (IS_ERR(header))
		return PTR_ERR(header);

1848
	memcpy(header + 1, cap + 1, size - sizeof(*header));
1849 1850 1851 1852

	return 0;
}
EXPORT_SYMBOL(vfio_info_add_capability);
1853

1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901
int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
				       int max_irq_type, size_t *data_size)
{
	unsigned long minsz;
	size_t size;

	minsz = offsetofend(struct vfio_irq_set, count);

	if ((hdr->argsz < minsz) || (hdr->index >= max_irq_type) ||
	    (hdr->count >= (U32_MAX - hdr->start)) ||
	    (hdr->flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
				VFIO_IRQ_SET_ACTION_TYPE_MASK)))
		return -EINVAL;

	if (data_size)
		*data_size = 0;

	if (hdr->start >= num_irqs || hdr->start + hdr->count > num_irqs)
		return -EINVAL;

	switch (hdr->flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
	case VFIO_IRQ_SET_DATA_NONE:
		size = 0;
		break;
	case VFIO_IRQ_SET_DATA_BOOL:
		size = sizeof(uint8_t);
		break;
	case VFIO_IRQ_SET_DATA_EVENTFD:
		size = sizeof(int32_t);
		break;
	default:
		return -EINVAL;
	}

	if (size) {
		if (hdr->argsz - minsz < hdr->count * size)
			return -EINVAL;

		if (!data_size)
			return -EINVAL;

		*data_size = hdr->count * size;
	}

	return 0;
}
EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);

1902 1903 1904 1905
/*
 * Pin a set of guest PFNs and return their associated host PFNs for local
 * domain only.
 * @dev [in]     : device
1906
 * @user_pfn [in]: array of user/guest PFNs to be pinned.
1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927
 * @npage [in]   : count of elements in user_pfn array.  This count should not
 *		   be greater VFIO_PIN_PAGES_MAX_ENTRIES.
 * @prot [in]    : protection flags
 * @phys_pfn[out]: array of host PFNs
 * Return error or number of pages pinned.
 */
int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
		   int prot, unsigned long *phys_pfn)
{
	struct vfio_container *container;
	struct vfio_group *group;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!dev || !user_pfn || !phys_pfn || !npage)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	group = vfio_group_get_from_dev(dev);
1928 1929
	if (!group)
		return -ENODEV;
1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973

	ret = vfio_group_add_container_user(group);
	if (ret)
		goto err_pin_pages;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->pin_pages))
		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
					     npage, prot, phys_pfn);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

err_pin_pages:
	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_pin_pages);

/*
 * Unpin set of host PFNs for local domain only.
 * @dev [in]     : device
 * @user_pfn [in]: array of user/guest PFNs to be unpinned. Number of user/guest
 *		   PFNs should not be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 * @npage [in]   : count of elements in user_pfn array.  This count should not
 *                 be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 * Return error or number of pages unpinned.
 */
int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
{
	struct vfio_container *container;
	struct vfio_group *group;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!dev || !user_pfn || !npage)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	group = vfio_group_get_from_dev(dev);
1974 1975
	if (!group)
		return -ENODEV;
1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996

	ret = vfio_group_add_container_user(group);
	if (ret)
		goto err_unpin_pages;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->unpin_pages))
		ret = driver->ops->unpin_pages(container->iommu_data, user_pfn,
					       npage);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

err_unpin_pages:
	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_unpin_pages);

1997 1998 1999
static int vfio_register_iommu_notifier(struct vfio_group *group,
					unsigned long *events,
					struct notifier_block *nb)
2000 2001 2002 2003 2004 2005 2006
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	ret = vfio_group_add_container_user(group);
	if (ret)
2007
		return -EINVAL;
2008 2009 2010 2011

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->register_notifier))
2012 2013
		ret = driver->ops->register_notifier(container->iommu_data,
						     events, nb);
2014 2015 2016 2017 2018 2019 2020 2021
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

	return ret;
}

2022 2023
static int vfio_unregister_iommu_notifier(struct vfio_group *group,
					  struct notifier_block *nb)
2024 2025 2026 2027 2028 2029 2030
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	ret = vfio_group_add_container_user(group);
	if (ret)
2031
		return -EINVAL;
2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->unregister_notifier))
		ret = driver->ops->unregister_notifier(container->iommu_data,
						       nb);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

2043 2044 2045
	return ret;
}

2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105
void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
{
	group->kvm = kvm;
	blocking_notifier_call_chain(&group->notifier,
				VFIO_GROUP_NOTIFY_SET_KVM, kvm);
}
EXPORT_SYMBOL_GPL(vfio_group_set_kvm);

static int vfio_register_group_notifier(struct vfio_group *group,
					unsigned long *events,
					struct notifier_block *nb)
{
	int ret;
	bool set_kvm = false;

	if (*events & VFIO_GROUP_NOTIFY_SET_KVM)
		set_kvm = true;

	/* clear known events */
	*events &= ~VFIO_GROUP_NOTIFY_SET_KVM;

	/* refuse to continue if still events remaining */
	if (*events)