vfio.c 40.8 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 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 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 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 1177 1178 1179 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 1205 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 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 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 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 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 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660
/*
 * VFIO core
 *
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.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.
 *
 * 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>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pci.h>
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/wait.h>

#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;
	dev_t				group_devt;
	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;
	struct rw_semaphore		group_lock;
	struct vfio_iommu_driver	*iommu_driver;
	void				*iommu_data;
};

struct vfio_unbound_dev {
	struct device			*dev;
	struct list_head		unbound_next;
};

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;
	struct list_head		unbound_list;
	struct mutex			unbound_lock;
	atomic_t			opened;
};

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;
};

/**
 * 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)
{
	return idr_alloc(&vfio.group_idr, group, 0, MINORMASK + 1, GFP_KERNEL);
}

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);
}

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);
}

/**
 * Group objects - create, release, get, put, search
 */
static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
{
	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);
	INIT_LIST_HEAD(&group->unbound_list);
	mutex_init(&group->unbound_lock);
	atomic_set(&group->container_users, 0);
	atomic_set(&group->opened, 0);
	group->iommu_group = iommu_group;

	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);
			vfio_group_unlock_and_free(group);
			return tmp;
		}
	}

	minor = vfio_alloc_group_minor(group);
	if (minor < 0) {
		vfio_group_unlock_and_free(group);
		return ERR_PTR(minor);
	}

	dev = device_create(vfio.class, NULL,
			    MKDEV(MAJOR(vfio.group_devt), minor),
			    group, "%d", iommu_group_id(iommu_group));
	if (IS_ERR(dev)) {
		vfio_free_group_minor(minor);
		vfio_group_unlock_and_free(group);
		return (struct vfio_group *)dev; /* ERR_PTR */
	}

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

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

	mutex_unlock(&vfio.group_lock);

	return group;
}

/* called with vfio.group_lock held */
static void vfio_group_release(struct kref *kref)
{
	struct vfio_group *group = container_of(kref, struct vfio_group, kref);
	struct vfio_unbound_dev *unbound, *tmp;
	struct iommu_group *iommu_group = group->iommu_group;

	WARN_ON(!list_empty(&group->device_list));

	list_for_each_entry_safe(unbound, tmp,
				 &group->unbound_list, unbound_next) {
		list_del(&unbound->unbound_next);
		kfree(unbound);
	}

	device_destroy(vfio.class, MKDEV(MAJOR(vfio.group_devt), group->minor));
	list_del(&group->vfio_next);
	vfio_free_group_minor(group->minor);
	vfio_group_unlock_and_free(group);
	iommu_group_put(iommu_group);
}

static void vfio_group_put(struct vfio_group *group)
{
	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
}

/* 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;
}

/**
 * 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;
	dev_set_drvdata(dev, device);

	/* 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 */
void vfio_device_put(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	kref_put_mutex(&device->kref, vfio_device_release, &group->device_lock);
	vfio_group_put(group);
}
EXPORT_SYMBOL_GPL(vfio_device_put);

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;
}

/*
 * 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.
 */
static const char * const vfio_driver_whitelist[] = { "pci-stub" };

static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
{
	int i;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

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

	for (i = 0; i < ARRAY_SIZE(vfio_driver_whitelist); i++) {
		if (!strcmp(drv->name, vfio_driver_whitelist[i]))
			return true;
	}

	return false;
}

/*
 * 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
 *  - a PCI interconnect device
 *
 * 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.
 */
static int vfio_dev_viable(struct device *dev, void *data)
{
	struct vfio_group *group = data;
	struct vfio_device *device;
	struct device_driver *drv = ACCESS_ONCE(dev->driver);
	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);

	if (!ret || !drv || vfio_dev_whitelisted(dev, drv))
		return 0;

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

	return ret;
}

/**
 * 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 */
	WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
	     iommu_group_id(group->iommu_group));

	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;
	struct vfio_unbound_dev *unbound;

	/*
	 * Need to go through a group_lock lookup to get a reference or we
	 * risk racing a group being removed.  Ignore spurious notifies.
	 */
	group = vfio_group_try_get(group);
	if (!group)
		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:
		/*
		 * 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.
		 */
		break;
	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
		pr_debug("%s: Device %s, group %d binding to driver\n",
			 __func__, dev_name(dev),
			 iommu_group_id(group->iommu_group));
		break;
	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
		pr_debug("%s: Device %s, group %d bound to driver %s\n",
			 __func__, dev_name(dev),
			 iommu_group_id(group->iommu_group), dev->driver->name);
		BUG_ON(vfio_group_nb_verify(group, dev));
		break;
	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
		pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
			 __func__, dev_name(dev),
			 iommu_group_id(group->iommu_group), dev->driver->name);
		break;
	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
		pr_debug("%s: Device %s, group %d unbound from driver\n",
			 __func__, dev_name(dev),
			 iommu_group_id(group->iommu_group));
		/*
		 * 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.
		 */

		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);
		break;
	}

	vfio_group_put(group);
	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) {
		group = vfio_create_group(iommu_group);
		if (IS_ERR(group)) {
			iommu_group_put(iommu_group);
			return PTR_ERR(group);
		}
	} 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);
	}

	device = vfio_group_get_device(group, dev);
	if (device) {
		WARN(1, "Device %s already exists on group %d\n",
		     dev_name(dev), iommu_group_id(iommu_group));
		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);
	}

	/*
	 * 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.
	 */
	vfio_group_put(group);

	return 0;
}
EXPORT_SYMBOL_GPL(vfio_add_group_dev);

/**
 * 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.
 */
struct vfio_device *vfio_device_get_from_dev(struct device *dev)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;
	struct vfio_device *device;

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

	group = vfio_group_get_from_iommu(iommu_group);
	iommu_group_put(iommu_group);
	if (!group)
		return NULL;

	device = vfio_group_get_device(group, dev);
	vfio_group_put(group);

	return device;
}
EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);

static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
						     char *buf)
{
	struct vfio_device *it, *device = NULL;

	mutex_lock(&group->device_lock);
	list_for_each_entry(it, &group->device_list, group_next) {
		if (!strcmp(dev_name(it->dev), buf)) {
			device = it;
			vfio_device_get(device);
			break;
		}
	}
	mutex_unlock(&group->device_lock);

	return device;
}

/*
 * 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);

/* Given a referenced group, check if it contains the device */
static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
{
	struct vfio_device *device;

	device = vfio_group_get_device(group, dev);
	if (!device)
		return false;

	vfio_device_put(device);
	return true;
}

/*
 * 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)
{
	struct vfio_device *device = dev_get_drvdata(dev);
	struct vfio_group *group = device->group;
	void *device_data = device->device_data;
	struct vfio_unbound_dev *unbound;
	unsigned int i = 0;
	long ret;
	bool interrupted = false;

	/*
	 * 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);

	/*
	 * 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);

	vfio_device_put(device);

	/*
	 * 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.
	 */
	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);

		if (interrupted) {
			ret = wait_event_timeout(vfio.release_q,
					!vfio_dev_present(group, dev), HZ * 10);
		} else {
			ret = wait_event_interruptible_timeout(vfio.release_q,
					!vfio_dev_present(group, dev), HZ * 10);
			if (ret == -ERESTARTSYS) {
				interrupted = true;
				dev_warn(dev,
					 "Device is currently in use, task"
					 " \"%s\" (%d) "
					 "blocked until device is released",
					 current->comm, task_pid_nr(current));
			}
		}
	} while (ret <= 0);

	vfio_group_put(group);

	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)
{
	struct vfio_iommu_driver *driver;
	long ret = 0;

	down_read(&container->group_lock);

	driver = container->iommu_driver;

	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);
			list_for_each_entry(driver, &vfio.iommu_drivers_list,
					    vfio_next) {
				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);
	}

	up_read(&container->group_lock);

	return ret;
}

/* hold write lock on container->group_lock */
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;

	down_write(&container->group_lock);

	/*
	 * 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) {
		up_write(&container->group_lock);
		return -EINVAL;
	}

	mutex_lock(&vfio.iommu_drivers_lock);
	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
		void *data;

		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;
		}

		/* module reference holds the driver we're working on */
		mutex_unlock(&vfio.iommu_drivers_lock);

		data = driver->ops->open(arg);
		if (IS_ERR(data)) {
			ret = PTR_ERR(data);
			module_put(driver->ops->owner);
			goto skip_drivers_unlock;
		}

		ret = __vfio_container_attach_groups(container, driver, data);
		if (!ret) {
			container->iommu_driver = driver;
			container->iommu_data = data;
		} else {
			driver->ops->release(data);
			module_put(driver->ops->owner);
		}

		goto skip_drivers_unlock;
	}

	mutex_unlock(&vfio.iommu_drivers_lock);
skip_drivers_unlock:
	up_write(&container->group_lock);

	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:
		down_read(&container->group_lock);

		driver = container->iommu_driver;
		data = container->iommu_data;

		if (driver) /* passthrough all unrecognized ioctls */
			ret = driver->ops->ioctl(data, cmd, arg);

		up_read(&container->group_lock);
	}

	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);
	init_rwsem(&container->group_lock);
	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;
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;

	down_read(&container->group_lock);

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->read))
		ret = driver->ops->read(container->iommu_data,
					buf, count, ppos);

	up_read(&container->group_lock);

	return ret;
}

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;
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;

	down_read(&container->group_lock);

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->write))
		ret = driver->ops->write(container->iommu_data,
					 buf, count, ppos);

	up_read(&container->group_lock);

	return ret;
}

static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	int ret = -EINVAL;

	down_read(&container->group_lock);

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->mmap))
		ret = driver->ops->mmap(container->iommu_data, vma);

	up_read(&container->group_lock);

	return ret;
}

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;

	down_write(&container->group_lock);

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

	group->container = NULL;
	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;
	}

	up_write(&container->group_lock);

	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)
{
	struct fd f;
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret = 0;

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

	f = fdget(container_fd);
	if (!f.file)
		return -EBADF;

	/* Sanity check, is this really our fd? */
	if (f.file->f_op != &vfio_fops) {
		fdput(f);
		return -EINVAL;
	}

	container = f.file->private_data;
	WARN_ON(!container); /* fget ensures we don't race vfio_release */

	down_write(&container->group_lock);

	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;
	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:
	up_write(&container->group_lock);
	fdput(f);
	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);
}

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;
	int ret;

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

	device = vfio_device_get_from_name(group, buf);
	if (!device)
		return -ENODEV;

	ret = device->ops->open(device->device_data);
	if (ret) {
		vfio_device_put(device);
		return ret;
	}

	/*
	 * 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;
	}

	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);

	atomic_inc(&group->container_users);

	fd_install(ret, filep);

	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;
	int opened;

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

	/* 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? */
	if (group->container) {
		atomic_dec(&group->opened);
		vfio_group_put(group);
		return -EBUSY;
	}

	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);

	atomic_dec(&group->opened);

	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,
};

/**
 * 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;

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

	if (!atomic_inc_not_zero(&group->container_users))
		return ERR_PTR(-EINVAL);

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

	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_put(group);
	vfio_group_try_dissolve_container(group);
}
EXPORT_SYMBOL_GPL(vfio_group_put_external_user);

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);

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);

/**
 * Module/class support
 */
static char *vfio_devnode(struct device *dev, umode_t *mode)
{
	return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
}

static struct miscdevice vfio_dev = {
	.minor = VFIO_MINOR,
	.name = "vfio",
	.fops = &vfio_fops,
	.nodename = "vfio/vfio",
	.mode = S_IRUGO | S_IWUGO,
};

static int __init vfio_init(void)
{
	int ret;

	idr_init(&vfio.group_idr);
	mutex_init(&vfio.group_lock);
	mutex_init(&vfio.iommu_drivers_lock);
	INIT_LIST_HEAD(&vfio.group_list);
	INIT_LIST_HEAD(&vfio.iommu_drivers_list);
	init_waitqueue_head(&vfio.release_q);

	ret = misc_register(&vfio_dev);
	if (ret) {
		pr_err("vfio: misc device register failed\n");
		return ret;
	}

	/* /dev/vfio/$GROUP */
	vfio.class = class_create(THIS_MODULE, "vfio");
	if (IS_ERR(vfio.class)) {
		ret = PTR_ERR(vfio.class);
		goto err_class;
	}

	vfio.class->devnode = vfio_devnode;

	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK, "vfio");
	if (ret)
		goto err_alloc_chrdev;

	cdev_init(&vfio.group_cdev, &vfio_group_fops);
	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK);
	if (ret)
		goto err_cdev_add;

	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");

	/*
	 * Attempt to load known iommu-drivers.  This gives us a working
	 * environment without the user needing to explicitly load iommu
	 * drivers.
	 */
	request_module_nowait("vfio_iommu_type1");
	request_module_nowait("vfio_iommu_spapr_tce");

	return 0;

err_cdev_add:
	unregister_chrdev_region(vfio.group_devt, MINORMASK);
err_alloc_chrdev:
	class_destroy(vfio.class);
	vfio.class = NULL;
err_class:
	misc_deregister(&vfio_dev);
	return ret;
}

static void __exit vfio_cleanup(void)
{
	WARN_ON(!list_empty(&vfio.group_list));

	idr_destroy(&vfio.group_idr);
	cdev_del(&vfio.group_cdev);
	unregister_chrdev_region(vfio.group_devt, MINORMASK);
	class_destroy(vfio.class);
	vfio.class = NULL;
	misc_deregister(&vfio_dev);
}

module_init(vfio_init);
module_exit(vfio_cleanup);

MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_ALIAS_MISCDEV(VFIO_MINOR);
MODULE_ALIAS("devname:vfio/vfio");