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
|
// SPDX-License-Identifier: MIT
/*
* Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst)
*
* Based on bo.c which bears the following copyright notice,
* but is dual licensed:
*
* Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
* All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the
* "Software"), to deal in the Software without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sub license, and/or sell copies of the Software, and to
* permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*
**************************************************************************/
/*
* Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
*/
#include <linux/dma-resv.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
/**
* DOC: Reservation Object Overview
*
* The reservation object provides a mechanism to manage shared and
* exclusive fences associated with a buffer. A reservation object
* can have attached one exclusive fence (normally associated with
* write operations) or N shared fences (read operations). The RCU
* mechanism is used to protect read access to fences from locked
* write-side updates.
*/
DEFINE_WD_CLASS(reservation_ww_class);
EXPORT_SYMBOL(reservation_ww_class);
/**
* dma_resv_list_alloc - allocate fence list
* @shared_max: number of fences we need space for
*
* Allocate a new dma_resv_list and make sure to correctly initialize
* shared_max.
*/
static struct dma_resv_list *dma_resv_list_alloc(unsigned int shared_max)
{
struct dma_resv_list *list;
list = kmalloc(struct_size(list, shared, shared_max), GFP_KERNEL);
if (!list)
return NULL;
list->shared_max = (ksize(list) - offsetof(typeof(*list), shared)) /
sizeof(*list->shared);
return list;
}
/**
* dma_resv_list_free - free fence list
* @list: list to free
*
* Free a dma_resv_list and make sure to drop all references.
*/
static void dma_resv_list_free(struct dma_resv_list *list)
{
unsigned int i;
if (!list)
return;
for (i = 0; i < list->shared_count; ++i)
dma_fence_put(rcu_dereference_protected(list->shared[i], true));
kfree_rcu(list, rcu);
}
/**
* dma_resv_init - initialize a reservation object
* @obj: the reservation object
*/
void dma_resv_init(struct dma_resv *obj)
{
ww_mutex_init(&obj->lock, &reservation_ww_class);
seqcount_ww_mutex_init(&obj->seq, &obj->lock);
RCU_INIT_POINTER(obj->fence, NULL);
RCU_INIT_POINTER(obj->fence_excl, NULL);
}
EXPORT_SYMBOL(dma_resv_init);
/**
* dma_resv_fini - destroys a reservation object
* @obj: the reservation object
*/
void dma_resv_fini(struct dma_resv *obj)
{
struct dma_resv_list *fobj;
struct dma_fence *excl;
/*
* This object should be dead and all references must have
* been released to it, so no need to be protected with rcu.
*/
excl = rcu_dereference_protected(obj->fence_excl, 1);
if (excl)
dma_fence_put(excl);
fobj = rcu_dereference_protected(obj->fence, 1);
dma_resv_list_free(fobj);
ww_mutex_destroy(&obj->lock);
}
EXPORT_SYMBOL(dma_resv_fini);
/**
* dma_resv_reserve_shared - Reserve space to add shared fences to
* a dma_resv.
* @obj: reservation object
* @num_fences: number of fences we want to add
*
* Should be called before dma_resv_add_shared_fence(). Must
* be called with obj->lock held.
*
* RETURNS
* Zero for success, or -errno
*/
int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences)
{
struct dma_resv_list *old, *new;
unsigned int i, j, k, max;
dma_resv_assert_held(obj);
old = dma_resv_get_list(obj);
if (old && old->shared_max) {
if ((old->shared_count + num_fences) <= old->shared_max)
return 0;
max = max(old->shared_count + num_fences, old->shared_max * 2);
} else {
max = max(4ul, roundup_pow_of_two(num_fences));
}
new = dma_resv_list_alloc(max);
if (!new)
return -ENOMEM;
/*
* no need to bump fence refcounts, rcu_read access
* requires the use of kref_get_unless_zero, and the
* references from the old struct are carried over to
* the new.
*/
for (i = 0, j = 0, k = max; i < (old ? old->shared_count : 0); ++i) {
struct dma_fence *fence;
fence = rcu_dereference_protected(old->shared[i],
dma_resv_held(obj));
if (dma_fence_is_signaled(fence))
RCU_INIT_POINTER(new->shared[--k], fence);
else
RCU_INIT_POINTER(new->shared[j++], fence);
}
new->shared_count = j;
/*
* We are not changing the effective set of fences here so can
* merely update the pointer to the new array; both existing
* readers and new readers will see exactly the same set of
* active (unsignaled) shared fences. Individual fences and the
* old array are protected by RCU and so will not vanish under
* the gaze of the rcu_read_lock() readers.
*/
rcu_assign_pointer(obj->fence, new);
if (!old)
return 0;
/* Drop the references to the signaled fences */
for (i = k; i < max; ++i) {
struct dma_fence *fence;
fence = rcu_dereference_protected(new->shared[i],
dma_resv_held(obj));
dma_fence_put(fence);
}
kfree_rcu(old, rcu);
return 0;
}
EXPORT_SYMBOL(dma_resv_reserve_shared);
/**
* dma_resv_add_shared_fence - Add a fence to a shared slot
* @obj: the reservation object
* @fence: the shared fence to add
*
* Add a fence to a shared slot, obj->lock must be held, and
* dma_resv_reserve_shared() has been called.
*/
void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
{
struct dma_resv_list *fobj;
struct dma_fence *old;
unsigned int i, count;
dma_fence_get(fence);
dma_resv_assert_held(obj);
fobj = dma_resv_get_list(obj);
count = fobj->shared_count;
write_seqcount_begin(&obj->seq);
for (i = 0; i < count; ++i) {
old = rcu_dereference_protected(fobj->shared[i],
dma_resv_held(obj));
if (old->context == fence->context ||
dma_fence_is_signaled(old))
goto replace;
}
BUG_ON(fobj->shared_count >= fobj->shared_max);
old = NULL;
count++;
replace:
RCU_INIT_POINTER(fobj->shared[i], fence);
/* pointer update must be visible before we extend the shared_count */
smp_store_mb(fobj->shared_count, count);
write_seqcount_end(&obj->seq);
dma_fence_put(old);
}
EXPORT_SYMBOL(dma_resv_add_shared_fence);
/**
* dma_resv_add_excl_fence - Add an exclusive fence.
* @obj: the reservation object
* @fence: the shared fence to add
*
* Add a fence to the exclusive slot. The obj->lock must be held.
*/
void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
{
struct dma_fence *old_fence = dma_resv_get_excl(obj);
struct dma_resv_list *old;
u32 i = 0;
dma_resv_assert_held(obj);
old = dma_resv_get_list(obj);
if (old)
i = old->shared_count;
if (fence)
dma_fence_get(fence);
write_seqcount_begin(&obj->seq);
/* write_seqcount_begin provides the necessary memory barrier */
RCU_INIT_POINTER(obj->fence_excl, fence);
if (old)
old->shared_count = 0;
write_seqcount_end(&obj->seq);
/* inplace update, no shared fences */
while (i--)
dma_fence_put(rcu_dereference_protected(old->shared[i],
dma_resv_held(obj)));
dma_fence_put(old_fence);
}
EXPORT_SYMBOL(dma_resv_add_excl_fence);
/**
* dma_resv_copy_fences - Copy all fences from src to dst.
* @dst: the destination reservation object
* @src: the source reservation object
*
* Copy all fences from src to dst. dst-lock must be held.
*/
int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
{
struct dma_resv_list *src_list, *dst_list;
struct dma_fence *old, *new;
unsigned int i;
dma_resv_assert_held(dst);
rcu_read_lock();
src_list = rcu_dereference(src->fence);
retry:
if (src_list) {
unsigned int shared_count = src_list->shared_count;
rcu_read_unlock();
dst_list = dma_resv_list_alloc(shared_count);
if (!dst_list)
return -ENOMEM;
rcu_read_lock();
src_list = rcu_dereference(src->fence);
if (!src_list || src_list->shared_count > shared_count) {
kfree(dst_list);
goto retry;
}
dst_list->shared_count = 0;
for (i = 0; i < src_list->shared_count; ++i) {
struct dma_fence __rcu **dst;
struct dma_fence *fence;
fence = rcu_dereference(src_list->shared[i]);
if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
&fence->flags))
continue;
if (!dma_fence_get_rcu(fence)) {
dma_resv_list_free(dst_list);
src_list = rcu_dereference(src->fence);
goto retry;
}
if (dma_fence_is_signaled(fence)) {
dma_fence_put(fence);
continue;
}
dst = &dst_list->shared[dst_list->shared_count++];
rcu_assign_pointer(*dst, fence);
}
} else {
dst_list = NULL;
}
new = dma_fence_get_rcu_safe(&src->fence_excl);
rcu_read_unlock();
src_list = dma_resv_get_list(dst);
old = dma_resv_get_excl(dst);
write_seqcount_begin(&dst->seq);
/* write_seqcount_begin provides the necessary memory barrier */
RCU_INIT_POINTER(dst->fence_excl, new);
RCU_INIT_POINTER(dst->fence, dst_list);
write_seqcount_end(&dst->seq);
dma_resv_list_free(src_list);
dma_fence_put(old);
return 0;
}
EXPORT_SYMBOL(dma_resv_copy_fences);
/**
* dma_resv_get_fences_rcu - Get an object's shared and exclusive
* fences without update side lock held
* @obj: the reservation object
* @pfence_excl: the returned exclusive fence (or NULL)
* @pshared_count: the number of shared fences returned
* @pshared: the array of shared fence ptrs returned (array is krealloc'd to
* the required size, and must be freed by caller)
*
* Retrieve all fences from the reservation object. If the pointer for the
* exclusive fence is not specified the fence is put into the array of the
* shared fences as well. Returns either zero or -ENOMEM.
*/
int dma_resv_get_fences_rcu(struct dma_resv *obj,
struct dma_fence **pfence_excl,
unsigned int *pshared_count,
struct dma_fence ***pshared)
{
struct dma_fence **shared = NULL;
struct dma_fence *fence_excl;
unsigned int shared_count;
int ret = 1;
do {
struct dma_resv_list *fobj;
unsigned int i, seq;
size_t sz = 0;
shared_count = i = 0;
rcu_read_lock();
seq = read_seqcount_begin(&obj->seq);
fence_excl = rcu_dereference(obj->fence_excl);
if (fence_excl && !dma_fence_get_rcu(fence_excl))
goto unlock;
fobj = rcu_dereference(obj->fence);
if (fobj)
sz += sizeof(*shared) * fobj->shared_max;
if (!pfence_excl && fence_excl)
sz += sizeof(*shared);
if (sz) {
struct dma_fence **nshared;
nshared = krealloc(shared, sz,
GFP_NOWAIT | __GFP_NOWARN);
if (!nshared) {
rcu_read_unlock();
dma_fence_put(fence_excl);
fence_excl = NULL;
nshared = krealloc(shared, sz, GFP_KERNEL);
if (nshared) {
shared = nshared;
continue;
}
ret = -ENOMEM;
break;
}
shared = nshared;
shared_count = fobj ? fobj->shared_count : 0;
for (i = 0; i < shared_count; ++i) {
shared[i] = rcu_dereference(fobj->shared[i]);
if (!dma_fence_get_rcu(shared[i]))
break;
}
}
if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) {
while (i--)
dma_fence_put(shared[i]);
dma_fence_put(fence_excl);
goto unlock;
}
ret = 0;
unlock:
rcu_read_unlock();
} while (ret);
if (pfence_excl)
*pfence_excl = fence_excl;
else if (fence_excl)
shared[shared_count++] = fence_excl;
if (!shared_count) {
kfree(shared);
shared = NULL;
}
*pshared_count = shared_count;
*pshared = shared;
return ret;
}
EXPORT_SYMBOL_GPL(dma_resv_get_fences_rcu);
/**
* dma_resv_wait_timeout_rcu - Wait on reservation's objects
* shared and/or exclusive fences.
* @obj: the reservation object
* @wait_all: if true, wait on all fences, else wait on just exclusive fence
* @intr: if true, do interruptible wait
* @timeout: timeout value in jiffies or zero to return immediately
*
* RETURNS
* Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or
* greater than zer on success.
*/
long dma_resv_wait_timeout_rcu(struct dma_resv *obj,
bool wait_all, bool intr,
unsigned long timeout)
{
long ret = timeout ? timeout : 1;
unsigned int seq, shared_count;
struct dma_fence *fence;
int i;
retry:
shared_count = 0;
seq = read_seqcount_begin(&obj->seq);
rcu_read_lock();
i = -1;
fence = rcu_dereference(obj->fence_excl);
if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
if (!dma_fence_get_rcu(fence))
goto unlock_retry;
if (dma_fence_is_signaled(fence)) {
dma_fence_put(fence);
fence = NULL;
}
} else {
fence = NULL;
}
if (wait_all) {
struct dma_resv_list *fobj = rcu_dereference(obj->fence);
if (fobj)
shared_count = fobj->shared_count;
for (i = 0; !fence && i < shared_count; ++i) {
struct dma_fence *lfence;
lfence = rcu_dereference(fobj->shared[i]);
if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
&lfence->flags))
continue;
if (!dma_fence_get_rcu(lfence))
goto unlock_retry;
if (dma_fence_is_signaled(lfence)) {
dma_fence_put(lfence);
continue;
}
fence = lfence;
break;
}
}
rcu_read_unlock();
if (fence) {
if (read_seqcount_retry(&obj->seq, seq)) {
dma_fence_put(fence);
goto retry;
}
ret = dma_fence_wait_timeout(fence, intr, ret);
dma_fence_put(fence);
if (ret > 0 && wait_all && (i + 1 < shared_count))
goto retry;
}
return ret;
unlock_retry:
rcu_read_unlock();
goto retry;
}
EXPORT_SYMBOL_GPL(dma_resv_wait_timeout_rcu);
static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence)
{
struct dma_fence *fence, *lfence = passed_fence;
int ret = 1;
if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) {
fence = dma_fence_get_rcu(lfence);
if (!fence)
return -1;
ret = !!dma_fence_is_signaled(fence);
dma_fence_put(fence);
}
return ret;
}
/**
* dma_resv_test_signaled_rcu - Test if a reservation object's
* fences have been signaled.
* @obj: the reservation object
* @test_all: if true, test all fences, otherwise only test the exclusive
* fence
*
* RETURNS
* true if all fences signaled, else false
*/
bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all)
{
unsigned int seq, shared_count;
int ret;
rcu_read_lock();
retry:
ret = true;
shared_count = 0;
seq = read_seqcount_begin(&obj->seq);
if (test_all) {
struct dma_resv_list *fobj = rcu_dereference(obj->fence);
unsigned int i;
if (fobj)
shared_count = fobj->shared_count;
for (i = 0; i < shared_count; ++i) {
struct dma_fence *fence;
fence = rcu_dereference(fobj->shared[i]);
ret = dma_resv_test_signaled_single(fence);
if (ret < 0)
goto retry;
else if (!ret)
break;
}
if (read_seqcount_retry(&obj->seq, seq))
goto retry;
}
if (!shared_count) {
struct dma_fence *fence_excl = rcu_dereference(obj->fence_excl);
if (fence_excl) {
ret = dma_resv_test_signaled_single(fence_excl);
if (ret < 0)
goto retry;
if (read_seqcount_retry(&obj->seq, seq))
goto retry;
}
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(dma_resv_test_signaled_rcu);
#if IS_ENABLED(CONFIG_LOCKDEP)
static int __init dma_resv_lockdep(void)
{
struct mm_struct *mm = mm_alloc();
struct ww_acquire_ctx ctx;
struct dma_resv obj;
struct address_space mapping;
int ret;
if (!mm)
return -ENOMEM;
dma_resv_init(&obj);
address_space_init_once(&mapping);
mmap_read_lock(mm);
ww_acquire_init(&ctx, &reservation_ww_class);
ret = dma_resv_lock(&obj, &ctx);
if (ret == -EDEADLK)
dma_resv_lock_slow(&obj, &ctx);
fs_reclaim_acquire(GFP_KERNEL);
/* for unmap_mapping_range on trylocked buffer objects in shrinkers */
i_mmap_lock_write(&mapping);
i_mmap_unlock_write(&mapping);
#ifdef CONFIG_MMU_NOTIFIER
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
__dma_fence_might_wait();
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
#else
__dma_fence_might_wait();
#endif
fs_reclaim_release(GFP_KERNEL);
ww_mutex_unlock(&obj.lock);
ww_acquire_fini(&ctx);
mmap_read_unlock(mm);
mmput(mm);
return 0;
}
subsys_initcall(dma_resv_lockdep);
#endif
|