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
|
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES
*/
#include <linux/iommufd.h>
#include <linux/slab.h>
#include <linux/iommu.h>
#include "io_pagetable.h"
#include "iommufd_private.h"
static bool allow_unsafe_interrupts;
module_param(allow_unsafe_interrupts, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(
allow_unsafe_interrupts,
"Allow IOMMUFD to bind to devices even if the platform cannot isolate "
"the MSI interrupt window. Enabling this is a security weakness.");
/*
* A iommufd_device object represents the binding relationship between a
* consuming driver and the iommufd. These objects are created/destroyed by
* external drivers, not by userspace.
*/
struct iommufd_device {
struct iommufd_object obj;
struct iommufd_ctx *ictx;
struct iommufd_hw_pagetable *hwpt;
/* Head at iommufd_hw_pagetable::devices */
struct list_head devices_item;
/* always the physical device */
struct device *dev;
struct iommu_group *group;
bool enforce_cache_coherency;
};
void iommufd_device_destroy(struct iommufd_object *obj)
{
struct iommufd_device *idev =
container_of(obj, struct iommufd_device, obj);
iommu_device_release_dma_owner(idev->dev);
iommu_group_put(idev->group);
iommufd_ctx_put(idev->ictx);
}
/**
* iommufd_device_bind - Bind a physical device to an iommu fd
* @ictx: iommufd file descriptor
* @dev: Pointer to a physical device struct
* @id: Output ID number to return to userspace for this device
*
* A successful bind establishes an ownership over the device and returns
* struct iommufd_device pointer, otherwise returns error pointer.
*
* A driver using this API must set driver_managed_dma and must not touch
* the device until this routine succeeds and establishes ownership.
*
* Binding a PCI device places the entire RID under iommufd control.
*
* The caller must undo this with iommufd_device_unbind()
*/
struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
struct device *dev, u32 *id)
{
struct iommufd_device *idev;
struct iommu_group *group;
int rc;
/*
* iommufd always sets IOMMU_CACHE because we offer no way for userspace
* to restore cache coherency.
*/
if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY))
return ERR_PTR(-EINVAL);
group = iommu_group_get(dev);
if (!group)
return ERR_PTR(-ENODEV);
rc = iommu_device_claim_dma_owner(dev, ictx);
if (rc)
goto out_group_put;
idev = iommufd_object_alloc(ictx, idev, IOMMUFD_OBJ_DEVICE);
if (IS_ERR(idev)) {
rc = PTR_ERR(idev);
goto out_release_owner;
}
idev->ictx = ictx;
iommufd_ctx_get(ictx);
idev->dev = dev;
idev->enforce_cache_coherency =
device_iommu_capable(dev, IOMMU_CAP_ENFORCE_CACHE_COHERENCY);
/* The calling driver is a user until iommufd_device_unbind() */
refcount_inc(&idev->obj.users);
/* group refcount moves into iommufd_device */
idev->group = group;
/*
* If the caller fails after this success it must call
* iommufd_unbind_device() which is safe since we hold this refcount.
* This also means the device is a leaf in the graph and no other object
* can take a reference on it.
*/
iommufd_object_finalize(ictx, &idev->obj);
*id = idev->obj.id;
return idev;
out_release_owner:
iommu_device_release_dma_owner(dev);
out_group_put:
iommu_group_put(group);
return ERR_PTR(rc);
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_bind, IOMMUFD);
/**
* iommufd_device_unbind - Undo iommufd_device_bind()
* @idev: Device returned by iommufd_device_bind()
*
* Release the device from iommufd control. The DMA ownership will return back
* to unowned with DMA controlled by the DMA API. This invalidates the
* iommufd_device pointer, other APIs that consume it must not be called
* concurrently.
*/
void iommufd_device_unbind(struct iommufd_device *idev)
{
bool was_destroyed;
was_destroyed = iommufd_object_destroy_user(idev->ictx, &idev->obj);
WARN_ON(!was_destroyed);
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_unbind, IOMMUFD);
static int iommufd_device_setup_msi(struct iommufd_device *idev,
struct iommufd_hw_pagetable *hwpt,
phys_addr_t sw_msi_start)
{
int rc;
/*
* If the IOMMU driver gives a IOMMU_RESV_SW_MSI then it is asking us to
* call iommu_get_msi_cookie() on its behalf. This is necessary to setup
* the MSI window so iommu_dma_prepare_msi() can install pages into our
* domain after request_irq(). If it is not done interrupts will not
* work on this domain.
*
* FIXME: This is conceptually broken for iommufd since we want to allow
* userspace to change the domains, eg switch from an identity IOAS to a
* DMA IOAS. There is currently no way to create a MSI window that
* matches what the IRQ layer actually expects in a newly created
* domain.
*/
if (sw_msi_start != PHYS_ADDR_MAX && !hwpt->msi_cookie) {
rc = iommu_get_msi_cookie(hwpt->domain, sw_msi_start);
if (rc)
return rc;
/*
* iommu_get_msi_cookie() can only be called once per domain,
* it returns -EBUSY on later calls.
*/
hwpt->msi_cookie = true;
}
/*
* For historical compat with VFIO the insecure interrupt path is
* allowed if the module parameter is set. Insecure means that a MemWr
* operation from the device (eg a simple DMA) cannot trigger an
* interrupt outside this iommufd context.
*/
if (!iommu_group_has_isolated_msi(idev->group)) {
if (!allow_unsafe_interrupts)
return -EPERM;
dev_warn(
idev->dev,
"MSI interrupts are not secure, they cannot be isolated by the platform. "
"Check that platform features like interrupt remapping are enabled. "
"Use the \"allow_unsafe_interrupts\" module parameter to override\n");
}
return 0;
}
static bool iommufd_hw_pagetable_has_group(struct iommufd_hw_pagetable *hwpt,
struct iommu_group *group)
{
struct iommufd_device *cur_dev;
list_for_each_entry(cur_dev, &hwpt->devices, devices_item)
if (cur_dev->group == group)
return true;
return false;
}
static int iommufd_device_do_attach(struct iommufd_device *idev,
struct iommufd_hw_pagetable *hwpt)
{
phys_addr_t sw_msi_start = PHYS_ADDR_MAX;
int rc;
mutex_lock(&hwpt->devices_lock);
/*
* Try to upgrade the domain we have, it is an iommu driver bug to
* report IOMMU_CAP_ENFORCE_CACHE_COHERENCY but fail
* enforce_cache_coherency when there are no devices attached to the
* domain.
*/
if (idev->enforce_cache_coherency && !hwpt->enforce_cache_coherency) {
if (hwpt->domain->ops->enforce_cache_coherency)
hwpt->enforce_cache_coherency =
hwpt->domain->ops->enforce_cache_coherency(
hwpt->domain);
if (!hwpt->enforce_cache_coherency) {
WARN_ON(list_empty(&hwpt->devices));
rc = -EINVAL;
goto out_unlock;
}
}
rc = iopt_table_enforce_group_resv_regions(&hwpt->ioas->iopt, idev->dev,
idev->group, &sw_msi_start);
if (rc)
goto out_unlock;
rc = iommufd_device_setup_msi(idev, hwpt, sw_msi_start);
if (rc)
goto out_iova;
/*
* FIXME: Hack around missing a device-centric iommu api, only attach to
* the group once for the first device that is in the group.
*/
if (!iommufd_hw_pagetable_has_group(hwpt, idev->group)) {
rc = iommu_attach_group(hwpt->domain, idev->group);
if (rc)
goto out_iova;
if (list_empty(&hwpt->devices)) {
rc = iopt_table_add_domain(&hwpt->ioas->iopt,
hwpt->domain);
if (rc)
goto out_detach;
}
}
idev->hwpt = hwpt;
refcount_inc(&hwpt->obj.users);
list_add(&idev->devices_item, &hwpt->devices);
mutex_unlock(&hwpt->devices_lock);
return 0;
out_detach:
iommu_detach_group(hwpt->domain, idev->group);
out_iova:
iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
out_unlock:
mutex_unlock(&hwpt->devices_lock);
return rc;
}
/*
* When automatically managing the domains we search for a compatible domain in
* the iopt and if one is found use it, otherwise create a new domain.
* Automatic domain selection will never pick a manually created domain.
*/
static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
struct iommufd_ioas *ioas)
{
struct iommufd_hw_pagetable *hwpt;
int rc;
/*
* There is no differentiation when domains are allocated, so any domain
* that is willing to attach to the device is interchangeable with any
* other.
*/
mutex_lock(&ioas->mutex);
list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) {
if (!hwpt->auto_domain)
continue;
rc = iommufd_device_do_attach(idev, hwpt);
/*
* -EINVAL means the domain is incompatible with the device.
* Other error codes should propagate to userspace as failure.
* Success means the domain is attached.
*/
if (rc == -EINVAL)
continue;
goto out_unlock;
}
hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev->dev);
if (IS_ERR(hwpt)) {
rc = PTR_ERR(hwpt);
goto out_unlock;
}
hwpt->auto_domain = true;
rc = iommufd_device_do_attach(idev, hwpt);
if (rc)
goto out_abort;
list_add_tail(&hwpt->hwpt_item, &ioas->hwpt_list);
mutex_unlock(&ioas->mutex);
iommufd_object_finalize(idev->ictx, &hwpt->obj);
return 0;
out_abort:
iommufd_object_abort_and_destroy(idev->ictx, &hwpt->obj);
out_unlock:
mutex_unlock(&ioas->mutex);
return rc;
}
/**
* iommufd_device_attach - Connect a device from an iommu_domain
* @idev: device to attach
* @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
* Output the IOMMUFD_OBJ_HW_PAGETABLE ID
*
* This connects the device to an iommu_domain, either automatically or manually
* selected. Once this completes the device could do DMA.
*
* The caller should return the resulting pt_id back to userspace.
* This function is undone by calling iommufd_device_detach().
*/
int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
{
struct iommufd_object *pt_obj;
int rc;
pt_obj = iommufd_get_object(idev->ictx, *pt_id, IOMMUFD_OBJ_ANY);
if (IS_ERR(pt_obj))
return PTR_ERR(pt_obj);
switch (pt_obj->type) {
case IOMMUFD_OBJ_HW_PAGETABLE: {
struct iommufd_hw_pagetable *hwpt =
container_of(pt_obj, struct iommufd_hw_pagetable, obj);
rc = iommufd_device_do_attach(idev, hwpt);
if (rc)
goto out_put_pt_obj;
mutex_lock(&hwpt->ioas->mutex);
list_add_tail(&hwpt->hwpt_item, &hwpt->ioas->hwpt_list);
mutex_unlock(&hwpt->ioas->mutex);
break;
}
case IOMMUFD_OBJ_IOAS: {
struct iommufd_ioas *ioas =
container_of(pt_obj, struct iommufd_ioas, obj);
rc = iommufd_device_auto_get_domain(idev, ioas);
if (rc)
goto out_put_pt_obj;
break;
}
default:
rc = -EINVAL;
goto out_put_pt_obj;
}
refcount_inc(&idev->obj.users);
*pt_id = idev->hwpt->obj.id;
rc = 0;
out_put_pt_obj:
iommufd_put_object(pt_obj);
return rc;
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
/**
* iommufd_device_detach - Disconnect a device to an iommu_domain
* @idev: device to detach
*
* Undo iommufd_device_attach(). This disconnects the idev from the previously
* attached pt_id. The device returns back to a blocked DMA translation.
*/
void iommufd_device_detach(struct iommufd_device *idev)
{
struct iommufd_hw_pagetable *hwpt = idev->hwpt;
mutex_lock(&hwpt->ioas->mutex);
mutex_lock(&hwpt->devices_lock);
list_del(&idev->devices_item);
if (!iommufd_hw_pagetable_has_group(hwpt, idev->group)) {
if (list_empty(&hwpt->devices)) {
iopt_table_remove_domain(&hwpt->ioas->iopt,
hwpt->domain);
list_del(&hwpt->hwpt_item);
}
iommu_detach_group(hwpt->domain, idev->group);
}
iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
mutex_unlock(&hwpt->devices_lock);
mutex_unlock(&hwpt->ioas->mutex);
if (hwpt->auto_domain)
iommufd_object_destroy_user(idev->ictx, &hwpt->obj);
else
refcount_dec(&hwpt->obj.users);
idev->hwpt = NULL;
refcount_dec(&idev->obj.users);
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_detach, IOMMUFD);
void iommufd_access_destroy_object(struct iommufd_object *obj)
{
struct iommufd_access *access =
container_of(obj, struct iommufd_access, obj);
iopt_remove_access(&access->ioas->iopt, access);
iommufd_ctx_put(access->ictx);
refcount_dec(&access->ioas->obj.users);
}
/**
* iommufd_access_create - Create an iommufd_access
* @ictx: iommufd file descriptor
* @ioas_id: ID for a IOMMUFD_OBJ_IOAS
* @ops: Driver's ops to associate with the access
* @data: Opaque data to pass into ops functions
*
* An iommufd_access allows a driver to read/write to the IOAS without using
* DMA. The underlying CPU memory can be accessed using the
* iommufd_access_pin_pages() or iommufd_access_rw() functions.
*
* The provided ops are required to use iommufd_access_pin_pages().
*/
struct iommufd_access *
iommufd_access_create(struct iommufd_ctx *ictx, u32 ioas_id,
const struct iommufd_access_ops *ops, void *data)
{
struct iommufd_access *access;
struct iommufd_object *obj;
int rc;
/*
* There is no uAPI for the access object, but to keep things symmetric
* use the object infrastructure anyhow.
*/
access = iommufd_object_alloc(ictx, access, IOMMUFD_OBJ_ACCESS);
if (IS_ERR(access))
return access;
access->data = data;
access->ops = ops;
obj = iommufd_get_object(ictx, ioas_id, IOMMUFD_OBJ_IOAS);
if (IS_ERR(obj)) {
rc = PTR_ERR(obj);
goto out_abort;
}
access->ioas = container_of(obj, struct iommufd_ioas, obj);
iommufd_ref_to_users(obj);
if (ops->needs_pin_pages)
access->iova_alignment = PAGE_SIZE;
else
access->iova_alignment = 1;
rc = iopt_add_access(&access->ioas->iopt, access);
if (rc)
goto out_put_ioas;
/* The calling driver is a user until iommufd_access_destroy() */
refcount_inc(&access->obj.users);
access->ictx = ictx;
iommufd_ctx_get(ictx);
iommufd_object_finalize(ictx, &access->obj);
return access;
out_put_ioas:
refcount_dec(&access->ioas->obj.users);
out_abort:
iommufd_object_abort(ictx, &access->obj);
return ERR_PTR(rc);
}
EXPORT_SYMBOL_NS_GPL(iommufd_access_create, IOMMUFD);
/**
* iommufd_access_destroy - Destroy an iommufd_access
* @access: The access to destroy
*
* The caller must stop using the access before destroying it.
*/
void iommufd_access_destroy(struct iommufd_access *access)
{
bool was_destroyed;
was_destroyed = iommufd_object_destroy_user(access->ictx, &access->obj);
WARN_ON(!was_destroyed);
}
EXPORT_SYMBOL_NS_GPL(iommufd_access_destroy, IOMMUFD);
/**
* iommufd_access_notify_unmap - Notify users of an iopt to stop using it
* @iopt: iopt to work on
* @iova: Starting iova in the iopt
* @length: Number of bytes
*
* After this function returns there should be no users attached to the pages
* linked to this iopt that intersect with iova,length. Anyone that has attached
* a user through iopt_access_pages() needs to detach it through
* iommufd_access_unpin_pages() before this function returns.
*
* iommufd_access_destroy() will wait for any outstanding unmap callback to
* complete. Once iommufd_access_destroy() no unmap ops are running or will
* run in the future. Due to this a driver must not create locking that prevents
* unmap to complete while iommufd_access_destroy() is running.
*/
void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
unsigned long length)
{
struct iommufd_ioas *ioas =
container_of(iopt, struct iommufd_ioas, iopt);
struct iommufd_access *access;
unsigned long index;
xa_lock(&ioas->iopt.access_list);
xa_for_each(&ioas->iopt.access_list, index, access) {
if (!iommufd_lock_obj(&access->obj))
continue;
xa_unlock(&ioas->iopt.access_list);
access->ops->unmap(access->data, iova, length);
iommufd_put_object(&access->obj);
xa_lock(&ioas->iopt.access_list);
}
xa_unlock(&ioas->iopt.access_list);
}
/**
* iommufd_access_unpin_pages() - Undo iommufd_access_pin_pages
* @access: IOAS access to act on
* @iova: Starting IOVA
* @length: Number of bytes to access
*
* Return the struct page's. The caller must stop accessing them before calling
* this. The iova/length must exactly match the one provided to access_pages.
*/
void iommufd_access_unpin_pages(struct iommufd_access *access,
unsigned long iova, unsigned long length)
{
struct io_pagetable *iopt = &access->ioas->iopt;
struct iopt_area_contig_iter iter;
unsigned long last_iova;
struct iopt_area *area;
if (WARN_ON(!length) ||
WARN_ON(check_add_overflow(iova, length - 1, &last_iova)))
return;
down_read(&iopt->iova_rwsem);
iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova)
iopt_area_remove_access(
area, iopt_area_iova_to_index(area, iter.cur_iova),
iopt_area_iova_to_index(
area,
min(last_iova, iopt_area_last_iova(area))));
up_read(&iopt->iova_rwsem);
WARN_ON(!iopt_area_contig_done(&iter));
}
EXPORT_SYMBOL_NS_GPL(iommufd_access_unpin_pages, IOMMUFD);
static bool iopt_area_contig_is_aligned(struct iopt_area_contig_iter *iter)
{
if (iopt_area_start_byte(iter->area, iter->cur_iova) % PAGE_SIZE)
return false;
if (!iopt_area_contig_done(iter) &&
(iopt_area_start_byte(iter->area, iopt_area_last_iova(iter->area)) %
PAGE_SIZE) != (PAGE_SIZE - 1))
return false;
return true;
}
static bool check_area_prot(struct iopt_area *area, unsigned int flags)
{
if (flags & IOMMUFD_ACCESS_RW_WRITE)
return area->iommu_prot & IOMMU_WRITE;
return area->iommu_prot & IOMMU_READ;
}
/**
* iommufd_access_pin_pages() - Return a list of pages under the iova
* @access: IOAS access to act on
* @iova: Starting IOVA
* @length: Number of bytes to access
* @out_pages: Output page list
* @flags: IOPMMUFD_ACCESS_RW_* flags
*
* Reads @length bytes starting at iova and returns the struct page * pointers.
* These can be kmap'd by the caller for CPU access.
*
* The caller must perform iommufd_access_unpin_pages() when done to balance
* this.
*
* This API always requires a page aligned iova. This happens naturally if the
* ioas alignment is >= PAGE_SIZE and the iova is PAGE_SIZE aligned. However
* smaller alignments have corner cases where this API can fail on otherwise
* aligned iova.
*/
int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
unsigned long length, struct page **out_pages,
unsigned int flags)
{
struct io_pagetable *iopt = &access->ioas->iopt;
struct iopt_area_contig_iter iter;
unsigned long last_iova;
struct iopt_area *area;
int rc;
/* Driver's ops don't support pin_pages */
if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
WARN_ON(access->iova_alignment != PAGE_SIZE || !access->ops->unmap))
return -EINVAL;
if (!length)
return -EINVAL;
if (check_add_overflow(iova, length - 1, &last_iova))
return -EOVERFLOW;
down_read(&iopt->iova_rwsem);
iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) {
unsigned long last = min(last_iova, iopt_area_last_iova(area));
unsigned long last_index = iopt_area_iova_to_index(area, last);
unsigned long index =
iopt_area_iova_to_index(area, iter.cur_iova);
if (area->prevent_access ||
!iopt_area_contig_is_aligned(&iter)) {
rc = -EINVAL;
goto err_remove;
}
if (!check_area_prot(area, flags)) {
rc = -EPERM;
goto err_remove;
}
rc = iopt_area_add_access(area, index, last_index, out_pages,
flags);
if (rc)
goto err_remove;
out_pages += last_index - index + 1;
}
if (!iopt_area_contig_done(&iter)) {
rc = -ENOENT;
goto err_remove;
}
up_read(&iopt->iova_rwsem);
return 0;
err_remove:
if (iova < iter.cur_iova) {
last_iova = iter.cur_iova - 1;
iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova)
iopt_area_remove_access(
area,
iopt_area_iova_to_index(area, iter.cur_iova),
iopt_area_iova_to_index(
area, min(last_iova,
iopt_area_last_iova(area))));
}
up_read(&iopt->iova_rwsem);
return rc;
}
EXPORT_SYMBOL_NS_GPL(iommufd_access_pin_pages, IOMMUFD);
/**
* iommufd_access_rw - Read or write data under the iova
* @access: IOAS access to act on
* @iova: Starting IOVA
* @data: Kernel buffer to copy to/from
* @length: Number of bytes to access
* @flags: IOMMUFD_ACCESS_RW_* flags
*
* Copy kernel to/from data into the range given by IOVA/length. If flags
* indicates IOMMUFD_ACCESS_RW_KTHREAD then a large copy can be optimized
* by changing it into copy_to/from_user().
*/
int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
void *data, size_t length, unsigned int flags)
{
struct io_pagetable *iopt = &access->ioas->iopt;
struct iopt_area_contig_iter iter;
struct iopt_area *area;
unsigned long last_iova;
int rc;
if (!length)
return -EINVAL;
if (check_add_overflow(iova, length - 1, &last_iova))
return -EOVERFLOW;
down_read(&iopt->iova_rwsem);
iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) {
unsigned long last = min(last_iova, iopt_area_last_iova(area));
unsigned long bytes = (last - iter.cur_iova) + 1;
if (area->prevent_access) {
rc = -EINVAL;
goto err_out;
}
if (!check_area_prot(area, flags)) {
rc = -EPERM;
goto err_out;
}
rc = iopt_pages_rw_access(
area->pages, iopt_area_start_byte(area, iter.cur_iova),
data, bytes, flags);
if (rc)
goto err_out;
data += bytes;
}
if (!iopt_area_contig_done(&iter))
rc = -ENOENT;
err_out:
up_read(&iopt->iova_rwsem);
return rc;
}
EXPORT_SYMBOL_NS_GPL(iommufd_access_rw, IOMMUFD);
#ifdef CONFIG_IOMMUFD_TEST
/*
* Creating a real iommufd_device is too hard, bypass creating a iommufd_device
* and go directly to attaching a domain.
*/
struct iommufd_hw_pagetable *
iommufd_device_selftest_attach(struct iommufd_ctx *ictx,
struct iommufd_ioas *ioas,
struct device *mock_dev)
{
struct iommufd_hw_pagetable *hwpt;
int rc;
hwpt = iommufd_hw_pagetable_alloc(ictx, ioas, mock_dev);
if (IS_ERR(hwpt))
return hwpt;
rc = iopt_table_add_domain(&hwpt->ioas->iopt, hwpt->domain);
if (rc)
goto out_hwpt;
refcount_inc(&hwpt->obj.users);
iommufd_object_finalize(ictx, &hwpt->obj);
return hwpt;
out_hwpt:
iommufd_object_abort_and_destroy(ictx, &hwpt->obj);
return ERR_PTR(rc);
}
void iommufd_device_selftest_detach(struct iommufd_ctx *ictx,
struct iommufd_hw_pagetable *hwpt)
{
iopt_table_remove_domain(&hwpt->ioas->iopt, hwpt->domain);
refcount_dec(&hwpt->obj.users);
}
#endif
|