litmus-rt.git - The LITMUS^RT kernel.

diff options

author	Artem Bityutskiy <Artem.Bityutskiy@nokia.com>	2008-08-25 11:58:19 -0400
committer	Artem Bityutskiy <Artem.Bityutskiy@nokia.com>	2008-08-31 10:21:51 -0400
commit	7dad181bbe58b8fe9e170da28bcd5f6ec9addd6d (patch)
tree	fd15bc2beeb1162e1c6315f590d82758d65af39c /include/linux/raw.h
parent	9bbb5726efb64e2cfed42f6eec07db80cd87e63b (diff)

UBIFS: improve statfs reporting even more

Since free space we report in statfs is file size which should fit to the FS - change the way we calculate free space and use leb_overhead instead of dark_wm in calculations. Results of "freespace" test (120MiB volume, 16KiB LEB size, 512 bytes page size). Before the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 85204992 bytes 81.3 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 11284480 bytes 10.8 MiB, wrote 13.2% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 12935168 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 12939264 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 7596218 bytes 7.2 MiB each time freespace: was free: 78675968 bytes 75.0 MiB, wrote: 88903680 bytes 84.8 MiB, delta: 10227712 bytes 9.8 MiB, wrote 13.0% more than predicted freespace: was free: 72015872 bytes 68.7 MiB, wrote: 81514496 bytes 77.7 MiB, delta: 9498624 bytes 9.1 MiB, wrote 13.2% more than predicted freespace: was free: 63938560 bytes 61.0 MiB, wrote: 72589312 bytes 69.2 MiB, delta: 8650752 bytes 8.2 MiB, wrote 13.5% more than predicted freespace: was free: 56127488 bytes 53.5 MiB, wrote: 63762432 bytes 60.8 MiB, delta: 7634944 bytes 7.3 MiB, wrote 13.6% more than predicted freespace: was free: 48336896 bytes 46.1 MiB, wrote: 54935552 bytes 52.4 MiB, delta: 6598656 bytes 6.3 MiB, wrote 13.7% more than predicted freespace: was free: 40587264 bytes 38.7 MiB, wrote: 46157824 bytes 44.0 MiB, delta: 5570560 bytes 5.3 MiB, wrote 13.7% more than predicted freespace: was free: 32841728 bytes 31.3 MiB, wrote: 37384192 bytes 35.7 MiB, delta: 4542464 bytes 4.3 MiB, wrote 13.8% more than predicted freespace: was free: 25100288 bytes 23.9 MiB, wrote: 28618752 bytes 27.3 MiB, delta: 3518464 bytes 3.4 MiB, wrote 14.0% more than predicted freespace: was free: 17342464 bytes 16.5 MiB, wrote: 19841024 bytes 18.9 MiB, delta: 2498560 bytes 2.4 MiB, wrote 14.4% more than predicted freespace: was free: 9605120 bytes 9.2 MiB, wrote: 11063296 bytes 10.6 MiB, delta: 1458176 bytes 1.4 MiB, wrote 15.2% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 7606272 bytes 7.3 MiB each time freespace: trashing: was free: 83668992 bytes 79.8 MiB, need free: 7606272 bytes 7.3 MiB, files created: 248297, delete 225724 (90.9% of them) freespace: was free: 70803456 bytes 67.5 MiB, wrote: 82485248 bytes 78.7 MiB, delta: 11681792 bytes 11.1 MiB, wrote 16.5% more than predicted freespace: trashing: was free: 81080320 bytes 77.3 MiB, need free: 15212544 bytes 14.5 MiB, files created: 248711, delete 202047 (81.2% of them) freespace: was free: 59867136 bytes 57.1 MiB, wrote: 71897088 bytes 68.6 MiB, delta: 12029952 bytes 11.5 MiB, wrote 20.1% more than predicted freespace: trashing: was free: 82243584 bytes 78.4 MiB, need free: 22818816 bytes 21.8 MiB, files created: 248866, delete 179817 (72.3% of them) freespace: was free: 50905088 bytes 48.5 MiB, wrote: 63168512 bytes 60.2 MiB, delta: 12263424 bytes 11.7 MiB, wrote 24.1% more than predicted freespace: trashing: was free: 83402752 bytes 79.5 MiB, need free: 30425088 bytes 29.0 MiB, files created: 248920, delete 158114 (63.5% of them) freespace: was free: 42651648 bytes 40.7 MiB, wrote: 55406592 bytes 52.8 MiB, delta: 12754944 bytes 12.2 MiB, wrote 29.9% more than predicted freespace: trashing: was free: 84402176 bytes 80.5 MiB, need free: 38031360 bytes 36.3 MiB, files created: 248709, delete 136641 (54.9% of them) freespace: was free: 35233792 bytes 33.6 MiB, wrote: 48250880 bytes 46.0 MiB, delta: 13017088 bytes 12.4 MiB, wrote 36.9% more than predicted freespace: trashing: was free: 82530304 bytes 78.7 MiB, need free: 45637632 bytes 43.5 MiB, files created: 248778, delete 111208 (44.7% of them) freespace: was free: 27287552 bytes 26.0 MiB, wrote: 40267776 bytes 38.4 MiB, delta: 12980224 bytes 12.4 MiB, wrote 47.6% more than predicted freespace: trashing: was free: 85114880 bytes 81.2 MiB, need free: 53243904 bytes 50.8 MiB, files created: 248508, delete 93052 (37.4% of them) freespace: was free: 22437888 bytes 21.4 MiB, wrote: 35328000 bytes 33.7 MiB, delta: 12890112 bytes 12.3 MiB, wrote 57.4% more than predicted freespace: trashing: was free: 84103168 bytes 80.2 MiB, need free: 60850176 bytes 58.0 MiB, files created: 248637, delete 68743 (27.6% of them) freespace: was free: 15536128 bytes 14.8 MiB, wrote: 28319744 bytes 27.0 MiB, delta: 12783616 bytes 12.2 MiB, wrote 82.3% more than predicted freespace: trashing: was free: 84357120 bytes 80.4 MiB, need free: 68456448 bytes 65.3 MiB, files created: 248567, delete 46852 (18.8% of them) freespace: was free: 9015296 bytes 8.6 MiB, wrote: 22044672 bytes 21.0 MiB, delta: 13029376 bytes 12.4 MiB, wrote 144.5% more than predicted freespace: trashing: was free: 84942848 bytes 81.0 MiB, need free: 76062720 bytes 72.5 MiB, files created: 248636, delete 25993 (10.5% of them) freespace: was free: 6086656 bytes 5.8 MiB, wrote: 8331264 bytes 7.9 MiB, delta: 2244608 bytes 2.1 MiB, wrote 36.9% more than predicted freespace: Test 3 finished freespace: finished successfully After the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 94048256 bytes 89.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 2441216 bytes 2.3 MiB, wrote 2.6% more than predicted freespace: was free: 92246016 bytes 88.0 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 4247552 bytes 4.1 MiB, wrote 4.6% more than predicted freespace: was free: 92254208 bytes 88.0 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 4235264 bytes 4.0 MiB, wrote 4.6% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 8386001 bytes 8.0 MiB each time freespace: was free: 86605824 bytes 82.6 MiB, wrote: 88252416 bytes 84.2 MiB, delta: 1646592 bytes 1.6 MiB, wrote 1.9% more than predicted freespace: was free: 78667776 bytes 75.0 MiB, wrote: 80715776 bytes 77.0 MiB, delta: 2048000 bytes 2.0 MiB, wrote 2.6% more than predicted freespace: was free: 69615616 bytes 66.4 MiB, wrote: 71630848 bytes 68.3 MiB, delta: 2015232 bytes 1.9 MiB, wrote 2.9% more than predicted freespace: was free: 61018112 bytes 58.2 MiB, wrote: 62783488 bytes 59.9 MiB, delta: 1765376 bytes 1.7 MiB, wrote 2.9% more than predicted freespace: was free: 52424704 bytes 50.0 MiB, wrote: 53968896 bytes 51.5 MiB, delta: 1544192 bytes 1.5 MiB, wrote 2.9% more than predicted freespace: was free: 43880448 bytes 41.8 MiB, wrote: 45199360 bytes 43.1 MiB, delta: 1318912 bytes 1.3 MiB, wrote 3.0% more than predicted freespace: was free: 35332096 bytes 33.7 MiB, wrote: 36425728 bytes 34.7 MiB, delta: 1093632 bytes 1.0 MiB, wrote 3.1% more than predicted freespace: was free: 26771456 bytes 25.5 MiB, wrote: 27643904 bytes 26.4 MiB, delta: 872448 bytes 852.0 KiB, wrote 3.3% more than predicted freespace: was free: 18231296 bytes 17.4 MiB, wrote: 18878464 bytes 18.0 MiB, delta: 647168 bytes 632.0 KiB, wrote 3.5% more than predicted freespace: was free: 9674752 bytes 9.2 MiB, wrote: 10088448 bytes 9.6 MiB, delta: 413696 bytes 404.0 KiB, wrote 4.3% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 8397544 bytes 8.0 MiB each time freespace: trashing: was free: 92372992 bytes 88.1 MiB, need free: 8397552 bytes 8.0 MiB, files created: 248296, delete 225723 (90.9% of them) freespace: was free: 71909376 bytes 68.6 MiB, wrote: 82472960 bytes 78.7 MiB, delta: 10563584 bytes 10.1 MiB, wrote 14.7% more than predicted freespace: trashing: was free: 88989696 bytes 84.9 MiB, need free: 16795096 bytes 16.0 MiB, files created: 248794, delete 201838 (81.1% of them) freespace: was free: 60354560 bytes 57.6 MiB, wrote: 71782400 bytes 68.5 MiB, delta: 11427840 bytes 10.9 MiB, wrote 18.9% more than predicted freespace: trashing: was free: 90304512 bytes 86.1 MiB, need free: 25192640 bytes 24.0 MiB, files created: 248733, delete 179342 (72.1% of them) freespace: was free: 51187712 bytes 48.8 MiB, wrote: 62943232 bytes 60.0 MiB, delta: 11755520 bytes 11.2 MiB, wrote 23.0% more than predicted freespace: trashing: was free: 91209728 bytes 87.0 MiB, need free: 33590184 bytes 32.0 MiB, files created: 248779, delete 157160 (63.2% of them) freespace: was free: 42704896 bytes 40.7 MiB, wrote: 55050240 bytes 52.5 MiB, delta: 12345344 bytes 11.8 MiB, wrote 28.9% more than predicted freespace: trashing: was free: 92700672 bytes 88.4 MiB, need free: 41987728 bytes 40.0 MiB, files created: 248848, delete 136135 (54.7% of them) freespace: was free: 35250176 bytes 33.6 MiB, wrote: 48115712 bytes 45.9 MiB, delta: 12865536 bytes 12.3 MiB, wrote 36.5% more than predicted freespace: trashing: was free: 93986816 bytes 89.6 MiB, need free: 50385272 bytes 48.1 MiB, files created: 248723, delete 115385 (46.4% of them) freespace: was free: 29995008 bytes 28.6 MiB, wrote: 41582592 bytes 39.7 MiB, delta: 11587584 bytes 11.1 MiB, wrote 38.6% more than predicted freespace: trashing: was free: 91881472 bytes 87.6 MiB, need free: 58782816 bytes 56.1 MiB, files created: 248645, delete 89569 (36.0% of them) freespace: was free: 22511616 bytes 21.5 MiB, wrote: 34705408 bytes 33.1 MiB, delta: 12193792 bytes 11.6 MiB, wrote 54.2% more than predicted freespace: trashing: was free: 91774976 bytes 87.5 MiB, need free: 67180360 bytes 64.1 MiB, files created: 248580, delete 66616 (26.8% of them) freespace: was free: 16908288 bytes 16.1 MiB, wrote: 26898432 bytes 25.7 MiB, delta: 9990144 bytes 9.5 MiB, wrote 59.1% more than predicted freespace: trashing: was free: 92450816 bytes 88.2 MiB, need free: 75577904 bytes 72.1 MiB, files created: 248654, delete 45381 (18.3% of them) freespace: was free: 10170368 bytes 9.7 MiB, wrote: 19111936 bytes 18.2 MiB, delta: 8941568 bytes 8.5 MiB, wrote 87.9% more than predicted freespace: trashing: was free: 93282304 bytes 89.0 MiB, need free: 83975448 bytes 80.1 MiB, files created: 248513, delete 24794 (10.0% of them) freespace: was free: 3911680 bytes 3.7 MiB, wrote: 7872512 bytes 7.5 MiB, delta: 3960832 bytes 3.8 MiB, wrote 101.3% more than predicted freespace: Test 3 finished freespace: finished successfully Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>

Diffstat (limited to 'include/linux/raw.h')

0 files changed, 0 insertions, 0 deletions

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

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

/* * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. * Author: Joerg Roedel <jroedel@suse.de> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published * by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/device.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/types.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/iommu.h> #include <linux/idr.h> #include <linux/notifier.h> #include <linux/err.h> #include <linux/pci.h> #include <linux/bitops.h> #include <trace/events/iommu.h> static struct kset *iommu_group_kset; static struct ida iommu_group_ida; static struct mutex iommu_group_mutex; struct iommu_callback_data { const struct iommu_ops *ops; }; struct iommu_group { struct kobject kobj; struct kobject *devices_kobj; struct list_head devices; struct mutex mutex; struct blocking_notifier_head notifier; void *iommu_data; void (*iommu_data_release)(void *iommu_data); char *name; int id; }; struct iommu_device { struct list_head list; struct device *dev; char *name; }; struct iommu_group_attribute { struct attribute attr; ssize_t (*show)(struct iommu_group *group, char *buf); ssize_t (*store)(struct iommu_group *group, const char *buf, size_t count); }; #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ struct iommu_group_attribute iommu_group_attr_##_name = \ __ATTR(_name, _mode, _show, _store) #define to_iommu_group_attr(_attr) \ container_of(_attr, struct iommu_group_attribute, attr) #define to_iommu_group(_kobj) \ container_of(_kobj, struct iommu_group, kobj) static ssize_t iommu_group_attr_show(struct kobject *kobj, struct attribute *__attr, char *buf) { struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); struct iommu_group *group = to_iommu_group(kobj); ssize_t ret = -EIO; if (attr->show) ret = attr->show(group, buf); return ret; } static ssize_t iommu_group_attr_store(struct kobject *kobj, struct attribute *__attr, const char *buf, size_t count) { struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); struct iommu_group *group = to_iommu_group(kobj); ssize_t ret = -EIO; if (attr->store) ret = attr->store(group, buf, count); return ret; } static const struct sysfs_ops iommu_group_sysfs_ops = { .show = iommu_group_attr_show, .store = iommu_group_attr_store, }; static int iommu_group_create_file(struct iommu_group *group, struct iommu_group_attribute *attr) { return sysfs_create_file(&group->kobj, &attr->attr); } static void iommu_group_remove_file(struct iommu_group *group, struct iommu_group_attribute *attr) { sysfs_remove_file(&group->kobj, &attr->attr); } static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) { return sprintf(buf, "%s\n", group->name); } static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); static void iommu_group_release(struct kobject *kobj) { struct iommu_group *group = to_iommu_group(kobj); if (group->iommu_data_release) group->iommu_data_release(group->iommu_data); mutex_lock(&iommu_group_mutex); ida_remove(&iommu_group_ida, group->id); mutex_unlock(&iommu_group_mutex); kfree(group->name); kfree(group); } static struct kobj_type iommu_group_ktype = { .sysfs_ops = &iommu_group_sysfs_ops, .release = iommu_group_release, }; /** * iommu_group_alloc - Allocate a new group * @name: Optional name to associate with group, visible in sysfs * * This function is called by an iommu driver to allocate a new iommu * group. The iommu group represents the minimum granularity of the iommu. * Upon successful return, the caller holds a reference to the supplied * group in order to hold the group until devices are added. Use * iommu_group_put() to release this extra reference count, allowing the * group to be automatically reclaimed once it has no devices or external * references. */ struct iommu_group *iommu_group_alloc(void) { struct iommu_group *group; int ret; group = kzalloc(sizeof(*group), GFP_KERNEL); if (!group) return ERR_PTR(-ENOMEM); group->kobj.kset = iommu_group_kset; mutex_init(&group->mutex); INIT_LIST_HEAD(&group->devices); BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); mutex_lock(&iommu_group_mutex); again: if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) { kfree(group); mutex_unlock(&iommu_group_mutex); return ERR_PTR(-ENOMEM); } if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id)) goto again; mutex_unlock(&iommu_group_mutex); ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype, NULL, "%d", group->id); if (ret) { mutex_lock(&iommu_group_mutex); ida_remove(&iommu_group_ida, group->id); mutex_unlock(&iommu_group_mutex); kfree(group); return ERR_PTR(ret); } group->devices_kobj = kobject_create_and_add("devices", &group->kobj); if (!group->devices_kobj) { kobject_put(&group->kobj); /* triggers .release & free */ return ERR_PTR(-ENOMEM); } /* * The devices_kobj holds a reference on the group kobject, so * as long as that exists so will the group. We can therefore * use the devices_kobj for reference counting. */ kobject_put(&group->kobj); return group; } EXPORT_SYMBOL_GPL(iommu_group_alloc); struct iommu_group *iommu_group_get_by_id(int id) { struct kobject *group_kobj; struct iommu_group *group; const char *name; if (!iommu_group_kset) return NULL; name = kasprintf(GFP_KERNEL, "%d", id); if (!name) return NULL; group_kobj = kset_find_obj(iommu_group_kset, name); kfree(name); if (!group_kobj) return NULL; group = container_of(group_kobj, struct iommu_group, kobj); BUG_ON(group->id != id); kobject_get(group->devices_kobj); kobject_put(&group->kobj); return group; } EXPORT_SYMBOL_GPL(iommu_group_get_by_id); /** * iommu_group_get_iommudata - retrieve iommu_data registered for a group * @group: the group * * iommu drivers can store data in the group for use when doing iommu * operations. This function provides a way to retrieve it. Caller * should hold a group reference. */ void *iommu_group_get_iommudata(struct iommu_group *group) { return group->iommu_data; } EXPORT_SYMBOL_GPL(iommu_group_get_iommudata); /** * iommu_group_set_iommudata - set iommu_data for a group * @group: the group * @iommu_data: new data * @release: release function for iommu_data * * iommu drivers can store data in the group for use when doing iommu * operations. This function provides a way to set the data after * the group has been allocated. Caller should hold a group reference. */ void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, void (*release)(void *iommu_data)) { group->iommu_data = iommu_data; group->iommu_data_release = release; } EXPORT_SYMBOL_GPL(iommu_group_set_iommudata); /** * iommu_group_set_name - set name for a group * @group: the group * @name: name * * Allow iommu driver to set a name for a group. When set it will * appear in a name attribute file under the group in sysfs. */ int iommu_group_set_name(struct iommu_group *group, const char *name) { int ret; if (group->name) { iommu_group_remove_file(group, &iommu_group_attr_name); kfree(group->name); group->name = NULL; if (!name) return 0; } group->name = kstrdup(name, GFP_KERNEL); if (!group->name) return -ENOMEM; ret = iommu_group_create_file(group, &iommu_group_attr_name); if (ret) { kfree(group->name); group->name = NULL; return ret; } return 0; } EXPORT_SYMBOL_GPL(iommu_group_set_name); /** * iommu_group_add_device - add a device to an iommu group * @group: the group into which to add the device (reference should be held) * @dev: the device * * This function is called by an iommu driver to add a device into a * group. Adding a device increments the group reference count. */ int iommu_group_add_device(struct iommu_group *group, struct device *dev) { int ret, i = 0; struct iommu_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) return -ENOMEM; device->dev = dev; ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); if (ret) { kfree(device); return ret; } device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj)); rename: if (!device->name) { sysfs_remove_link(&dev->kobj, "iommu_group"); kfree(device); return -ENOMEM; } ret = sysfs_create_link_nowarn(group->devices_kobj, &dev->kobj, device->name); if (ret) { kfree(device->name); if (ret == -EEXIST && i >= 0) { /* * Account for the slim chance of collision * and append an instance to the name. */ device->name = kasprintf(GFP_KERNEL, "%s.%d", kobject_name(&dev->kobj), i++); goto rename; } sysfs_remove_link(&dev->kobj, "iommu_group"); kfree(device); return ret; } kobject_get(group->devices_kobj); dev->iommu_group = group; mutex_lock(&group->mutex); list_add_tail(&device->list, &group->devices); mutex_unlock(&group->mutex); /* Notify any listeners about change to group. */ blocking_notifier_call_chain(&group->notifier, IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); trace_add_device_to_group(group->id, dev); return 0; } EXPORT_SYMBOL_GPL(iommu_group_add_device); /** * iommu_group_remove_device - remove a device from it's current group * @dev: device to be removed * * This function is called by an iommu driver to remove the device from * it's current group. This decrements the iommu group reference count. */ void iommu_group_remove_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; struct iommu_device *tmp_device, *device = NULL; /* Pre-notify listeners that a device is being removed. */ blocking_notifier_call_chain(&group->notifier, IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); mutex_lock(&group->mutex); list_for_each_entry(tmp_device, &group->devices, list) { if (tmp_device->dev == dev) { device = tmp_device; list_del(&device->list); break; } } mutex_unlock(&group->mutex); if (!device) return; sysfs_remove_link(group->devices_kobj, device->name); sysfs_remove_link(&dev->kobj, "iommu_group"); trace_remove_device_from_group(group->id, dev); kfree(device->name); kfree(device); dev->iommu_group = NULL; kobject_put(group->devices_kobj); } EXPORT_SYMBOL_GPL(iommu_group_remove_device); /** * iommu_group_for_each_dev - iterate over each device in the group * @group: the group * @data: caller opaque data to be passed to callback function * @fn: caller supplied callback function * * This function is called by group users to iterate over group devices. * Callers should hold a reference count to the group during callback. * The group->mutex is held across callbacks, which will block calls to * iommu_group_add/remove_device. */ int iommu_group_for_each_dev(struct iommu_group *group, void *data, int (*fn)(struct device *, void *)) { struct iommu_device *device; int ret = 0; mutex_lock(&group->mutex); list_for_each_entry(device, &group->devices, list) { ret = fn(device->dev, data); if (ret) break; } mutex_unlock(&group->mutex); return ret; } EXPORT_SYMBOL_GPL(iommu_group_for_each_dev); /** * iommu_group_get - Return the group for a device and increment reference * @dev: get the group that this device belongs to * * This function is called by iommu drivers and users to get the group * for the specified device. If found, the group is returned and the group * reference in incremented, else NULL. */ struct iommu_group *iommu_group_get(struct device *dev) { struct iommu_group *group = dev->iommu_group; if (group) kobject_get(group->devices_kobj); return group; } EXPORT_SYMBOL_GPL(iommu_group_get); /** * iommu_group_put - Decrement group reference * @group: the group to use * * This function is called by iommu drivers and users to release the * iommu group. Once the reference count is zero, the group is released. */ void iommu_group_put(struct iommu_group *group) { if (group) kobject_put(group->devices_kobj); } EXPORT_SYMBOL_GPL(iommu_group_put); /** * iommu_group_register_notifier - Register a notifier for group changes * @group: the group to watch * @nb: notifier block to signal * * This function allows iommu group users to track changes in a group. * See include/linux/iommu.h for actions sent via this notifier. Caller * should hold a reference to the group throughout notifier registration. */ int iommu_group_register_notifier(struct iommu_group *group, struct notifier_block *nb) { return blocking_notifier_chain_register(&group->notifier, nb); } EXPORT_SYMBOL_GPL(iommu_group_register_notifier); /** * iommu_group_unregister_notifier - Unregister a notifier * @group: the group to watch * @nb: notifier block to signal * * Unregister a previously registered group notifier block. */ int iommu_group_unregister_notifier(struct iommu_group *group, struct notifier_block *nb) { return blocking_notifier_chain_unregister(&group->notifier, nb); } EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); /** * iommu_group_id - Return ID for a group * @group: the group to ID * * Return the unique ID for the group matching the sysfs group number. */ int iommu_group_id(struct iommu_group *group) { return group->id; } EXPORT_SYMBOL_GPL(iommu_group_id); static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev, unsigned long *devfns); /* * To consider a PCI device isolated, we require ACS to support Source * Validation, Request Redirection, Completer Redirection, and Upstream * Forwarding. This effectively means that devices cannot spoof their * requester ID, requests and completions cannot be redirected, and all * transactions are forwarded upstream, even as it passes through a * bridge where the target device is downstream. */ #define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) /* * For multifunction devices which are not isolated from each other, find * all the other non-isolated functions and look for existing groups. For * each function, we also need to look for aliases to or from other devices * that may already have a group. */ static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev, unsigned long *devfns) { struct pci_dev *tmp = NULL; struct iommu_group *group; if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS)) return NULL; for_each_pci_dev(tmp) { if (tmp == pdev || tmp->bus != pdev->bus || PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) || pci_acs_enabled(tmp, REQ_ACS_FLAGS)) continue; group = get_pci_alias_group(tmp, devfns); if (group) { pci_dev_put(tmp); return group; } } return NULL; } /* * Look for aliases to or from the given device for exisiting groups. The * dma_alias_devfn only supports aliases on the same bus, therefore the search * space is quite small (especially since we're really only looking at pcie * device, and therefore only expect multiple slots on the root complex or * downstream switch ports). It's conceivable though that a pair of * multifunction devices could have aliases between them that would cause a * loop. To prevent this, we use a bitmap to track where we've been. */ static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev, unsigned long *devfns) { struct pci_dev *tmp = NULL; struct iommu_group *group; if (test_and_set_bit(pdev->devfn & 0xff, devfns)) return NULL; group = iommu_group_get(&pdev->dev); if (group) return group; for_each_pci_dev(tmp) { if (tmp == pdev || tmp->bus != pdev->bus) continue; /* We alias them or they alias us */ if (((pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) && pdev->dma_alias_devfn == tmp->devfn) || ((tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) && tmp->dma_alias_devfn == pdev->devfn)) { group = get_pci_alias_group(tmp, devfns); if (group) { pci_dev_put(tmp); return group; } group = get_pci_function_alias_group(tmp, devfns); if (group) { pci_dev_put(tmp); return group; } } } return NULL; } struct group_for_pci_data { struct pci_dev *pdev; struct iommu_group *group; }; /* * DMA alias iterator callback, return the last seen device. Stop and return * the IOMMU group if we find one along the way. */ static int get_pci_alias_or_group(struct pci_dev *pdev, u16 alias, void *opaque) { struct group_for_pci_data *data = opaque; data->pdev = pdev; data->group = iommu_group_get(&pdev->dev); return data->group != NULL; } /* * Use standard PCI bus topology, isolation features, and DMA alias quirks * to find or create an IOMMU group for a device. */ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev) { struct group_for_pci_data data; struct pci_bus *bus; struct iommu_group *group = NULL; u64 devfns[4] = { 0 }; /* * Find the upstream DMA alias for the device. A device must not * be aliased due to topology in order to have its own IOMMU group. * If we find an alias along the way that already belongs to a * group, use it. */ if (pci_for_each_dma_alias(pdev, get_pci_alias_or_group, &data)) return data.group; pdev = data.pdev; /* * Continue upstream from the point of minimum IOMMU granularity * due to aliases to the point where devices are protected from * peer-to-peer DMA by PCI ACS. Again, if we find an existing * group, use it. */ for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) { if (!bus->self) continue; if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS)) break; pdev = bus->self; group = iommu_group_get(&pdev->dev); if (group) return group; } /* * Look for existing groups on device aliases. If we alias another * device or another device aliases us, use the same group. */ group = get_pci_alias_group(pdev, (unsigned long *)devfns); if (group) return group; /* * Look for existing groups on non-isolated functions on the same * slot and aliases of those funcions, if any. No need to clear * the search bitmap, the tested devfns are still valid. */ group = get_pci_function_alias_group(pdev, (unsigned long *)devfns); if (group) return group; /* No shared group found, allocate new */ return iommu_group_alloc(); } /** * iommu_group_get_for_dev - Find or create the IOMMU group for a device * @dev: target device * * This function is intended to be called by IOMMU drivers and extended to * support common, bus-defined algorithms when determining or creating the * IOMMU group for a device. On success, the caller will hold a reference * to the returned IOMMU group, which will already include the provided * device. The reference should be released with iommu_group_put(). */ struct iommu_group *iommu_group_get_for_dev(struct device *dev) { struct iommu_group *group; int ret; group = iommu_group_get(dev); if (group) return group; if (!dev_is_pci(dev)) return ERR_PTR(-EINVAL); group = iommu_group_get_for_pci_dev(to_pci_dev(dev)); if (IS_ERR(group)) return group; ret = iommu_group_add_device(group, dev); if (ret) { iommu_group_put(group); return ERR_PTR(ret); } return group; } static int add_iommu_group(struct device *dev, void *data) { struct iommu_callback_data *cb = data; const struct iommu_ops *ops = cb->ops; if (!ops->add_device) return 0; WARN_ON(dev->iommu_group); ops->add_device(dev); return 0; } static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct device *dev = data; const struct iommu_ops *ops = dev->bus->iommu_ops; struct iommu_group *group; unsigned long group_action = 0; /* * ADD/DEL call into iommu driver ops if provided, which may * result in ADD/DEL notifiers to group->notifier */ if (action == BUS_NOTIFY_ADD_DEVICE) { if (ops->add_device) return ops->add_device(dev); } else if (action == BUS_NOTIFY_DEL_DEVICE) { if (ops->remove_device && dev->iommu_group) { ops->remove_device(dev); return 0; } } /* * Remaining BUS_NOTIFYs get filtered and republished to the * group, if anyone is listening */ group = iommu_group_get(dev); if (!group) return 0; switch (action) { case BUS_NOTIFY_BIND_DRIVER: group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; break; case BUS_NOTIFY_BOUND_DRIVER: group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; break; case BUS_NOTIFY_UNBIND_DRIVER: group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; break; case BUS_NOTIFY_UNBOUND_DRIVER: group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; break; } if (group_action) blocking_notifier_call_chain(&group->notifier, group_action, dev); iommu_group_put(group); return 0; } static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) { int err; struct notifier_block *nb; struct iommu_callback_data cb = { .ops = ops, }; nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL); if (!nb) return -ENOMEM; nb->notifier_call = iommu_bus_notifier; err = bus_register_notifier(bus, nb); if (err) { kfree(nb); return err; } err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group); if (err) { bus_unregister_notifier(bus, nb); kfree(nb); return err; } return 0; } /** * bus_set_iommu - set iommu-callbacks for the bus * @bus: bus. * @ops: the callbacks provided by the iommu-driver * * This function is called by an iommu driver to set the iommu methods * used for a particular bus. Drivers for devices on that bus can use * the iommu-api after these ops are registered. * This special function is needed because IOMMUs are usually devices on * the bus itself, so the iommu drivers are not initialized when the bus * is set up. With this function the iommu-driver can set the iommu-ops * afterwards. */ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops) { int err; if (bus->iommu_ops != NULL) return -EBUSY; bus->iommu_ops = ops; /* Do IOMMU specific setup for this bus-type */ err = iommu_bus_init(bus, ops); if (err) bus->iommu_ops = NULL; return err; } EXPORT_SYMBOL_GPL(bus_set_iommu); bool iommu_present(struct bus_type *bus) { return bus->iommu_ops != NULL; } EXPORT_SYMBOL_GPL(iommu_present); bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) { if (!bus->iommu_ops || !bus->iommu_ops->capable) return false; return bus->iommu_ops->capable(cap); } EXPORT_SYMBOL_GPL(iommu_capable); /** * iommu_set_fault_handler() - set a fault handler for an iommu domain * @domain: iommu domain * @handler: fault handler * @token: user data, will be passed back to the fault handler * * This function should be used by IOMMU users which want to be notified * whenever an IOMMU fault happens. * * The fault handler itself should return 0 on success, and an appropriate * error code otherwise. */ void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token) { BUG_ON(!domain); domain->handler = handler; domain->handler_token = token; } EXPORT_SYMBOL_GPL(iommu_set_fault_handler); struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) { struct iommu_domain *domain; if (bus == NULL || bus->iommu_ops == NULL) return NULL; domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED); if (!domain) return NULL; domain->ops = bus->iommu_ops; domain->type = IOMMU_DOMAIN_UNMANAGED; return domain; } EXPORT_SYMBOL_GPL(iommu_domain_alloc); void iommu_domain_free(struct iommu_domain *domain) { domain->ops->domain_free(domain); } EXPORT_SYMBOL_GPL(iommu_domain_free); int iommu_attach_device(struct iommu_domain *domain, struct device *dev) { int ret; if (unlikely(domain->ops->attach_dev == NULL)) return -ENODEV; ret = domain->ops->attach_dev(domain, dev); if (!ret) trace_attach_device_to_domain(dev); return ret; } EXPORT_SYMBOL_GPL(iommu_attach_device); void iommu_detach_device(struct iommu_domain *domain, struct device *dev) { if (unlikely(domain->ops->detach_dev == NULL)) return; domain->ops->detach_dev(domain, dev); trace_detach_device_from_domain(dev); } EXPORT_SYMBOL_GPL(iommu_detach_device); /* * IOMMU groups are really the natrual working unit of the IOMMU, but * the IOMMU API works on domains and devices. Bridge that gap by * iterating over the devices in a group. Ideally we'd have a single * device which represents the requestor ID of the group, but we also * allow IOMMU drivers to create policy defined minimum sets, where * the physical hardware may be able to distiguish members, but we * wish to group them at a higher level (ex. untrusted multi-function * PCI devices). Thus we attach each device. */ static int iommu_group_do_attach_device(struct device *dev, void *data) { struct iommu_domain *domain = data; return iommu_attach_device(domain, dev); } int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { return iommu_group_for_each_dev(group, domain, iommu_group_do_attach_device); } EXPORT_SYMBOL_GPL(iommu_attach_group); static int iommu_group_do_detach_device(struct device *dev, void *data) { struct iommu_domain *domain = data; iommu_detach_device(domain, dev); return 0; } void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) { iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device); } EXPORT_SYMBOL_GPL(iommu_detach_group); phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { if (unlikely(domain->ops->iova_to_phys == NULL)) return 0; return domain->ops->iova_to_phys(domain, iova); } EXPORT_SYMBOL_GPL(iommu_iova_to_phys); static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long addr_merge, size_t size) { unsigned int pgsize_idx; size_t pgsize; /* Max page size that still fits into 'size' */ pgsize_idx = __fls(size); /* need to consider alignment requirements ? */ if (likely(addr_merge)) { /* Max page size allowed by address */ unsigned int align_pgsize_idx = __ffs(addr_merge); pgsize_idx = min(pgsize_idx, align_pgsize_idx); } /* build a mask of acceptable page sizes */ pgsize = (1UL << (pgsize_idx + 1)) - 1; /* throw away page sizes not supported by the hardware */ pgsize &= domain->ops->pgsize_bitmap; /* make sure we're still sane */ BUG_ON(!pgsize); /* pick the biggest page */ pgsize_idx = __fls(pgsize); pgsize = 1UL << pgsize_idx; return pgsize; } int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { unsigned long orig_iova = iova; unsigned int min_pagesz; size_t orig_size = size; int ret = 0; if (unlikely(domain->ops->map == NULL || domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) return -EINVAL; /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); /* * both the virtual address and the physical one, as well as * the size of the mapping, must be aligned (at least) to the * size of the smallest page supported by the hardware */ if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) { pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n", iova, &paddr, size, min_pagesz); return -EINVAL; } pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size); while (size) { size_t pgsize = iommu_pgsize(domain, iova | paddr, size); pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", iova, &paddr, pgsize); ret = domain->ops->map(domain, iova, paddr, pgsize, prot); if (ret) break; iova += pgsize; paddr += pgsize; size -= pgsize; } /* unroll mapping in case something went wrong */ if (ret) iommu_unmap(domain, orig_iova, orig_size - size); else trace_map(orig_iova, paddr, orig_size); return ret; } EXPORT_SYMBOL_GPL(iommu_map); size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { size_t unmapped_page, unmapped = 0; unsigned int min_pagesz; unsigned long orig_iova = iova; if (unlikely(domain->ops->unmap == NULL || domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) return -EINVAL; /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); /* * The virtual address, as well as the size of the mapping, must be * aligned (at least) to the size of the smallest page supported * by the hardware */ if (!IS_ALIGNED(iova | size, min_pagesz)) { pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n", iova, size, min_pagesz); return -EINVAL; } pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size); /* * Keep iterating until we either unmap 'size' bytes (or more) * or we hit an area that isn't mapped. */ while (unmapped < size) { size_t pgsize = iommu_pgsize(domain, iova, size - unmapped); unmapped_page = domain->ops->unmap(domain, iova, pgsize); if (!unmapped_page) break; pr_debug("unmapped: iova 0x%lx size 0x%zx\n", iova, unmapped_page); iova += unmapped_page; unmapped += unmapped_page; } trace_unmap(orig_iova, size, unmapped); return unmapped; } EXPORT_SYMBOL_GPL(iommu_unmap); size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { struct scatterlist *s; size_t mapped = 0; unsigned int i, min_pagesz; int ret; if (unlikely(domain->ops->pgsize_bitmap == 0UL)) return 0; min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); for_each_sg(sg, s, nents, i) { phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset; /* * We are mapping on IOMMU page boundaries, so offset within * the page must be 0. However, the IOMMU may support pages * smaller than PAGE_SIZE, so s->offset may still represent * an offset of that boundary within the CPU page. */ if (!IS_ALIGNED(s->offset, min_pagesz)) goto out_err; ret = iommu_map(domain, iova + mapped, phys, s->length, prot); if (ret) goto out_err; mapped += s->length; } return mapped; out_err: /* undo mappings already done */ iommu_unmap(domain, iova, mapped); return 0; } EXPORT_SYMBOL_GPL(default_iommu_map_sg); int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) { if (unlikely(domain->ops->domain_window_enable == NULL)) return -ENODEV; return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size, prot); } EXPORT_SYMBOL_GPL(iommu_domain_window_enable); void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) { if (unlikely(domain->ops->domain_window_disable == NULL)) return; return domain->ops->domain_window_disable(domain, wnd_nr); } EXPORT_SYMBOL_GPL(iommu_domain_window_disable); static int __init iommu_init(void) { iommu_group_kset = kset_create_and_add("iommu_groups", NULL, kernel_kobj); ida_init(&iommu_group_ida); mutex_init(&iommu_group_mutex); BUG_ON(!iommu_group_kset); return 0; } arch_initcall(iommu_init); int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { struct iommu_domain_geometry *geometry; bool *paging; int ret = 0; u32 *count; switch (attr) { case DOMAIN_ATTR_GEOMETRY: geometry = data;


context:
space:
mode: