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
|
// SPDX-License-Identifier: MIT
/*
* Copyright © 2021 Intel Corporation
*/
#include <drm/ttm/ttm_bo_driver.h>
#include <drm/ttm/ttm_placement.h>
#include "i915_drv.h"
#include "intel_memory_region.h"
#include "intel_region_ttm.h"
#include "gem/i915_gem_object.h"
#include "gem/i915_gem_region.h"
#include "gem/i915_gem_ttm.h"
#include "gem/i915_gem_mman.h"
#include "gt/intel_migrate.h"
#include "gt/intel_engine_pm.h"
#define I915_PL_LMEM0 TTM_PL_PRIV
#define I915_PL_SYSTEM TTM_PL_SYSTEM
#define I915_PL_STOLEN TTM_PL_VRAM
#define I915_PL_GGTT TTM_PL_TT
#define I915_TTM_PRIO_PURGE 0
#define I915_TTM_PRIO_NO_PAGES 1
#define I915_TTM_PRIO_HAS_PAGES 2
/*
* Size of struct ttm_place vector in on-stack struct ttm_placement allocs
*/
#define I915_TTM_MAX_PLACEMENTS INTEL_REGION_UNKNOWN
/**
* struct i915_ttm_tt - TTM page vector with additional private information
* @ttm: The base TTM page vector.
* @dev: The struct device used for dma mapping and unmapping.
* @cached_st: The cached scatter-gather table.
*
* Note that DMA may be going on right up to the point where the page-
* vector is unpopulated in delayed destroy. Hence keep the
* scatter-gather table mapped and cached up to that point. This is
* different from the cached gem object io scatter-gather table which
* doesn't have an associated dma mapping.
*/
struct i915_ttm_tt {
struct ttm_tt ttm;
struct device *dev;
struct sg_table *cached_st;
};
static const struct ttm_place sys_placement_flags = {
.fpfn = 0,
.lpfn = 0,
.mem_type = I915_PL_SYSTEM,
.flags = 0,
};
static struct ttm_placement i915_sys_placement = {
.num_placement = 1,
.placement = &sys_placement_flags,
.num_busy_placement = 1,
.busy_placement = &sys_placement_flags,
};
static int i915_ttm_err_to_gem(int err)
{
/* Fastpath */
if (likely(!err))
return 0;
switch (err) {
case -EBUSY:
/*
* TTM likes to convert -EDEADLK to -EBUSY, and wants us to
* restart the operation, since we don't record the contending
* lock. We use -EAGAIN to restart.
*/
return -EAGAIN;
case -ENOSPC:
/*
* Memory type / region is full, and we can't evict.
* Except possibly system, that returns -ENOMEM;
*/
return -ENXIO;
default:
break;
}
return err;
}
static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj);
static enum ttm_caching
i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
{
/*
* Objects only allowed in system get cached cpu-mappings.
* Other objects get WC mapping for now. Even if in system.
*/
if (obj->mm.region->type == INTEL_MEMORY_SYSTEM &&
obj->mm.n_placements <= 1)
return ttm_cached;
return ttm_write_combined;
}
static void
i915_ttm_place_from_region(const struct intel_memory_region *mr,
struct ttm_place *place,
unsigned int flags)
{
memset(place, 0, sizeof(*place));
place->mem_type = intel_region_to_ttm_type(mr);
if (flags & I915_BO_ALLOC_CONTIGUOUS)
place->flags = TTM_PL_FLAG_CONTIGUOUS;
}
static void
i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
struct ttm_place *requested,
struct ttm_place *busy,
struct ttm_placement *placement)
{
unsigned int num_allowed = obj->mm.n_placements;
unsigned int flags = obj->flags;
unsigned int i;
placement->num_placement = 1;
i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
obj->mm.region, requested, flags);
/* Cache this on object? */
placement->num_busy_placement = num_allowed;
for (i = 0; i < placement->num_busy_placement; ++i)
i915_ttm_place_from_region(obj->mm.placements[i], busy + i, flags);
if (num_allowed == 0) {
*busy = *requested;
placement->num_busy_placement = 1;
}
placement->placement = requested;
placement->busy_placement = busy;
}
static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
uint32_t page_flags)
{
struct ttm_resource_manager *man =
ttm_manager_type(bo->bdev, bo->resource->mem_type);
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
struct i915_ttm_tt *i915_tt;
int ret;
i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL);
if (!i915_tt)
return NULL;
if (obj->flags & I915_BO_ALLOC_CPU_CLEAR &&
man->use_tt)
page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
i915_ttm_select_tt_caching(obj));
if (ret) {
kfree(i915_tt);
return NULL;
}
i915_tt->dev = obj->base.dev->dev;
return &i915_tt->ttm;
}
static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
if (i915_tt->cached_st) {
dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st,
DMA_BIDIRECTIONAL, 0);
sg_free_table(i915_tt->cached_st);
kfree(i915_tt->cached_st);
i915_tt->cached_st = NULL;
}
ttm_pool_free(&bdev->pool, ttm);
}
static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
ttm_tt_destroy_common(bdev, ttm);
ttm_tt_fini(ttm);
kfree(i915_tt);
}
static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
const struct ttm_place *place)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
/* Will do for now. Our pinned objects are still on TTM's LRU lists */
return i915_gem_object_evictable(obj);
}
static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
struct ttm_placement *placement)
{
*placement = i915_sys_placement;
}
static int i915_ttm_move_notify(struct ttm_buffer_object *bo)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
int ret;
ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE);
if (ret)
return ret;
ret = __i915_gem_object_put_pages(obj);
if (ret)
return ret;
return 0;
}
static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
{
struct radix_tree_iter iter;
void __rcu **slot;
if (!obj->ttm.cached_io_st)
return;
rcu_read_lock();
radix_tree_for_each_slot(slot, &obj->ttm.get_io_page.radix, &iter, 0)
radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index);
rcu_read_unlock();
sg_free_table(obj->ttm.cached_io_st);
kfree(obj->ttm.cached_io_st);
obj->ttm.cached_io_st = NULL;
}
static void i915_ttm_purge(struct drm_i915_gem_object *obj)
{
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
struct ttm_operation_ctx ctx = {
.interruptible = true,
.no_wait_gpu = false,
};
struct ttm_placement place = {};
int ret;
if (obj->mm.madv == __I915_MADV_PURGED)
return;
/* TTM's purge interface. Note that we might be reentering. */
ret = ttm_bo_validate(bo, &place, &ctx);
if (!ret) {
i915_ttm_free_cached_io_st(obj);
obj->mm.madv = __I915_MADV_PURGED;
}
}
static void i915_ttm_swap_notify(struct ttm_buffer_object *bo)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
int ret = i915_ttm_move_notify(bo);
GEM_WARN_ON(ret);
GEM_WARN_ON(obj->ttm.cached_io_st);
if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
i915_ttm_purge(obj);
}
static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
if (likely(obj)) {
/* This releases all gem object bindings to the backend. */
i915_ttm_free_cached_io_st(obj);
__i915_gem_free_object(obj);
}
}
static struct intel_memory_region *
i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type)
{
struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev);
/* There's some room for optimization here... */
GEM_BUG_ON(ttm_mem_type != I915_PL_SYSTEM &&
ttm_mem_type < I915_PL_LMEM0);
if (ttm_mem_type == I915_PL_SYSTEM)
return intel_memory_region_lookup(i915, INTEL_MEMORY_SYSTEM,
0);
return intel_memory_region_lookup(i915, INTEL_MEMORY_LOCAL,
ttm_mem_type - I915_PL_LMEM0);
}
static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
struct scatterlist *sg;
struct sg_table *st;
int ret;
if (i915_tt->cached_st)
return i915_tt->cached_st;
st = kzalloc(sizeof(*st), GFP_KERNEL);
if (!st)
return ERR_PTR(-ENOMEM);
sg = __sg_alloc_table_from_pages
(st, ttm->pages, ttm->num_pages, 0,
(unsigned long)ttm->num_pages << PAGE_SHIFT,
i915_sg_segment_size(), NULL, 0, GFP_KERNEL);
if (IS_ERR(sg)) {
kfree(st);
return ERR_CAST(sg);
}
ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
if (ret) {
sg_free_table(st);
kfree(st);
return ERR_PTR(ret);
}
i915_tt->cached_st = st;
return st;
}
static struct sg_table *
i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
struct ttm_resource *res)
{
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
struct ttm_resource_manager *man =
ttm_manager_type(bo->bdev, res->mem_type);
if (man->use_tt)
return i915_ttm_tt_get_st(bo->ttm);
return intel_region_ttm_resource_to_st(obj->mm.region, res);
}
static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
struct ttm_resource *dst_mem,
struct sg_table *dst_st)
{
struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
bdev);
struct ttm_resource_manager *src_man =
ttm_manager_type(bo->bdev, bo->resource->mem_type);
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
struct sg_table *src_st;
struct i915_request *rq;
int ret;
if (!i915->gt.migrate.context)
return -EINVAL;
if (!bo->ttm || !ttm_tt_is_populated(bo->ttm)) {
if (bo->type == ttm_bo_type_kernel)
return -EINVAL;
if (bo->ttm &&
!(bo->ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))
return 0;
intel_engine_pm_get(i915->gt.migrate.context->engine);
ret = intel_context_migrate_clear(i915->gt.migrate.context, NULL,
dst_st->sgl, I915_CACHE_NONE,
dst_mem->mem_type >= I915_PL_LMEM0,
0, &rq);
if (!ret && rq) {
i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
i915_request_put(rq);
}
intel_engine_pm_put(i915->gt.migrate.context->engine);
} else {
src_st = src_man->use_tt ? i915_ttm_tt_get_st(bo->ttm) :
obj->ttm.cached_io_st;
intel_engine_pm_get(i915->gt.migrate.context->engine);
ret = intel_context_migrate_copy(i915->gt.migrate.context,
NULL, src_st->sgl, I915_CACHE_NONE,
bo->resource->mem_type >= I915_PL_LMEM0,
dst_st->sgl, I915_CACHE_NONE,
dst_mem->mem_type >= I915_PL_LMEM0,
&rq);
if (!ret && rq) {
i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
i915_request_put(rq);
}
intel_engine_pm_put(i915->gt.migrate.context->engine);
}
return ret;
}
static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
struct ttm_operation_ctx *ctx,
struct ttm_resource *dst_mem,
struct ttm_place *hop)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
struct ttm_resource_manager *dst_man =
ttm_manager_type(bo->bdev, dst_mem->mem_type);
struct ttm_resource_manager *src_man =
ttm_manager_type(bo->bdev, bo->resource->mem_type);
struct intel_memory_region *dst_reg, *src_reg;
union {
struct ttm_kmap_iter_tt tt;
struct ttm_kmap_iter_iomap io;
} _dst_iter, _src_iter;
struct ttm_kmap_iter *dst_iter, *src_iter;
struct sg_table *dst_st;
int ret;
dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type);
src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type);
GEM_BUG_ON(!dst_reg || !src_reg);
/* Sync for now. We could do the actual copy async. */
ret = ttm_bo_wait_ctx(bo, ctx);
if (ret)
return ret;
ret = i915_ttm_move_notify(bo);
if (ret)
return ret;
if (obj->mm.madv != I915_MADV_WILLNEED) {
i915_ttm_purge(obj);
ttm_resource_free(bo, &dst_mem);
return 0;
}
/* Populate ttm with pages if needed. Typically system memory. */
if (bo->ttm && (dst_man->use_tt ||
(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) {
ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
if (ret)
return ret;
}
dst_st = i915_ttm_resource_get_st(obj, dst_mem);
if (IS_ERR(dst_st))
return PTR_ERR(dst_st);
ret = i915_ttm_accel_move(bo, dst_mem, dst_st);
if (ret) {
/* If we start mapping GGTT, we can no longer use man::use_tt here. */
dst_iter = dst_man->use_tt ?
ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) :
ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
dst_st, dst_reg->region.start);
src_iter = src_man->use_tt ?
ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
obj->ttm.cached_io_st,
src_reg->region.start);
ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter);
}
ttm_bo_move_sync_cleanup(bo, dst_mem);
i915_ttm_free_cached_io_st(obj);
if (!dst_man->use_tt) {
obj->ttm.cached_io_st = dst_st;
obj->ttm.get_io_page.sg_pos = dst_st->sgl;
obj->ttm.get_io_page.sg_idx = 0;
}
return 0;
}
static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem)
{
if (mem->mem_type < I915_PL_LMEM0)
return 0;
mem->bus.caching = ttm_write_combined;
mem->bus.is_iomem = true;
return 0;
}
static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
unsigned long page_offset)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
unsigned long base = obj->mm.region->iomap.base - obj->mm.region->region.start;
struct scatterlist *sg;
unsigned int ofs;
GEM_WARN_ON(bo->ttm);
sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true, true);
return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs;
}
static struct ttm_device_funcs i915_ttm_bo_driver = {
.ttm_tt_create = i915_ttm_tt_create,
.ttm_tt_unpopulate = i915_ttm_tt_unpopulate,
.ttm_tt_destroy = i915_ttm_tt_destroy,
.eviction_valuable = i915_ttm_eviction_valuable,
.evict_flags = i915_ttm_evict_flags,
.move = i915_ttm_move,
.swap_notify = i915_ttm_swap_notify,
.delete_mem_notify = i915_ttm_delete_mem_notify,
.io_mem_reserve = i915_ttm_io_mem_reserve,
.io_mem_pfn = i915_ttm_io_mem_pfn,
};
/**
* i915_ttm_driver - Return a pointer to the TTM device funcs
*
* Return: Pointer to statically allocated TTM device funcs.
*/
struct ttm_device_funcs *i915_ttm_driver(void)
{
return &i915_ttm_bo_driver;
}
static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
{
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
struct ttm_operation_ctx ctx = {
.interruptible = true,
.no_wait_gpu = false,
};
struct sg_table *st;
struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
struct ttm_placement placement;
int real_num_busy;
int ret;
GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS);
/* Move to the requested placement. */
i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
/*
* For now we support LMEM only with TTM.
* TODO: Remove with system support
*/
GEM_BUG_ON(requested.mem_type < I915_PL_LMEM0 ||
busy[0].mem_type < I915_PL_LMEM0);
/* First try only the requested placement. No eviction. */
real_num_busy = fetch_and_zero(&placement.num_busy_placement);
ret = ttm_bo_validate(bo, &placement, &ctx);
if (ret) {
ret = i915_ttm_err_to_gem(ret);
/*
* Anything that wants to restart the operation gets to
* do that.
*/
if (ret == -EDEADLK || ret == -EINTR || ret == -ERESTARTSYS ||
ret == -EAGAIN)
return ret;
/* TODO: Remove this when we support system as TTM. */
real_num_busy = 1;
/*
* If the initial attempt fails, allow all accepted placements,
* evicting if necessary.
*/
placement.num_busy_placement = real_num_busy;
ret = ttm_bo_validate(bo, &placement, &ctx);
if (ret)
return i915_ttm_err_to_gem(ret);
}
/* Object either has a page vector or is an iomem object */
st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st;
if (IS_ERR(st))
return PTR_ERR(st);
__i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl));
i915_ttm_adjust_lru(obj);
return ret;
}
static void i915_ttm_put_pages(struct drm_i915_gem_object *obj,
struct sg_table *st)
{
/*
* We're currently not called from a shrinker, so put_pages()
* typically means the object is about to destroyed, or called
* from move_notify(). So just avoid doing much for now.
* If the object is not destroyed next, The TTM eviction logic
* and shrinkers will move it out if needed.
*/
i915_ttm_adjust_lru(obj);
}
static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
{
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
/*
* Don't manipulate the TTM LRUs while in TTM bo destruction.
* We're called through i915_ttm_delete_mem_notify().
*/
if (!kref_read(&bo->kref))
return;
/*
* Put on the correct LRU list depending on the MADV status
*/
spin_lock(&bo->bdev->lru_lock);
if (obj->mm.madv != I915_MADV_WILLNEED) {
bo->priority = I915_TTM_PRIO_PURGE;
} else if (!i915_gem_object_has_pages(obj)) {
if (bo->priority < I915_TTM_PRIO_HAS_PAGES)
bo->priority = I915_TTM_PRIO_HAS_PAGES;
} else {
if (bo->priority > I915_TTM_PRIO_NO_PAGES)
bo->priority = I915_TTM_PRIO_NO_PAGES;
}
ttm_bo_move_to_lru_tail(bo, bo->resource, NULL);
spin_unlock(&bo->bdev->lru_lock);
}
/*
* TTM-backed gem object destruction requires some clarification.
* Basically we have two possibilities here. We can either rely on the
* i915 delayed destruction and put the TTM object when the object
* is idle. This would be detected by TTM which would bypass the
* TTM delayed destroy handling. The other approach is to put the TTM
* object early and rely on the TTM destroyed handling, and then free
* the leftover parts of the GEM object once TTM's destroyed list handling is
* complete. For now, we rely on the latter for two reasons:
* a) TTM can evict an object even when it's on the delayed destroy list,
* which in theory allows for complete eviction.
* b) There is work going on in TTM to allow freeing an object even when
* it's not idle, and using the TTM destroyed list handling could help us
* benefit from that.
*/
static void i915_ttm_delayed_free(struct drm_i915_gem_object *obj)
{
if (obj->ttm.created) {
ttm_bo_put(i915_gem_to_ttm(obj));
} else {
__i915_gem_free_object(obj);
call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
}
}
static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
{
struct vm_area_struct *area = vmf->vma;
struct drm_i915_gem_object *obj =
i915_ttm_to_gem(area->vm_private_data);
/* Sanity check that we allow writing into this object */
if (unlikely(i915_gem_object_is_readonly(obj) &&
area->vm_flags & VM_WRITE))
return VM_FAULT_SIGBUS;
return ttm_bo_vm_fault(vmf);
}
static int
vm_access_ttm(struct vm_area_struct *area, unsigned long addr,
void *buf, int len, int write)
{
struct drm_i915_gem_object *obj =
i915_ttm_to_gem(area->vm_private_data);
if (i915_gem_object_is_readonly(obj) && write)
return -EACCES;
return ttm_bo_vm_access(area, addr, buf, len, write);
}
static void ttm_vm_open(struct vm_area_struct *vma)
{
struct drm_i915_gem_object *obj =
i915_ttm_to_gem(vma->vm_private_data);
GEM_BUG_ON(!obj);
i915_gem_object_get(obj);
}
static void ttm_vm_close(struct vm_area_struct *vma)
{
struct drm_i915_gem_object *obj =
i915_ttm_to_gem(vma->vm_private_data);
GEM_BUG_ON(!obj);
i915_gem_object_put(obj);
}
static const struct vm_operations_struct vm_ops_ttm = {
.fault = vm_fault_ttm,
.access = vm_access_ttm,
.open = ttm_vm_open,
.close = ttm_vm_close,
};
static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj)
{
/* The ttm_bo must be allocated with I915_BO_ALLOC_USER */
GEM_BUG_ON(!drm_mm_node_allocated(&obj->base.vma_node.vm_node));
return drm_vma_node_offset_addr(&obj->base.vma_node);
}
const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = {
.name = "i915_gem_object_ttm",
.flags = I915_GEM_OBJECT_HAS_IOMEM,
.get_pages = i915_ttm_get_pages,
.put_pages = i915_ttm_put_pages,
.truncate = i915_ttm_purge,
.adjust_lru = i915_ttm_adjust_lru,
.delayed_free = i915_ttm_delayed_free,
.mmap_offset = i915_ttm_mmap_offset,
.mmap_ops = &vm_ops_ttm,
};
void i915_ttm_bo_destroy(struct ttm_buffer_object *bo)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
i915_gem_object_release_memory_region(obj);
mutex_destroy(&obj->ttm.get_io_page.lock);
if (obj->ttm.created)
call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
}
/**
* __i915_gem_ttm_object_init - Initialize a ttm-backed i915 gem object
* @mem: The initial memory region for the object.
* @obj: The gem object.
* @size: Object size in bytes.
* @flags: gem object flags.
*
* Return: 0 on success, negative error code on failure.
*/
int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
resource_size_t size,
unsigned int flags)
{
static struct lock_class_key lock_class;
struct drm_i915_private *i915 = mem->i915;
enum ttm_bo_type bo_type;
int ret;
drm_gem_private_object_init(&i915->drm, &obj->base, size);
i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags);
i915_gem_object_init_memory_region(obj, mem);
i915_gem_object_make_unshrinkable(obj);
obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;
i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN);
mutex_init(&obj->ttm.get_io_page.lock);
bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device :
ttm_bo_type_kernel;
/*
* If this function fails, it will call the destructor, but
* our caller still owns the object. So no freeing in the
* destructor until obj->ttm.created is true.
* Similarly, in delayed_destroy, we can't call ttm_bo_put()
* until successful initialization.
*/
obj->base.vma_node.driver_private = i915_gem_to_ttm(obj);
ret = ttm_bo_init(&i915->bdev, i915_gem_to_ttm(obj), size,
bo_type, &i915_sys_placement,
mem->min_page_size >> PAGE_SHIFT,
true, NULL, NULL, i915_ttm_bo_destroy);
if (!ret)
obj->ttm.created = true;
/* i915 wants -ENXIO when out of memory region space. */
return i915_ttm_err_to_gem(ret);
}
|