forked from thesofproject/linux
/
intel_engine_cs.c
1714 lines (1439 loc) · 45.1 KB
/
intel_engine_cs.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright © 2016 Intel Corporation
*
* 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, sublicense,
* 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 NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS 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.
*
*/
#include <drm/drm_print.h>
#include "i915_drv.h"
#include "intel_ringbuffer.h"
#include "intel_lrc.h"
/* Haswell does have the CXT_SIZE register however it does not appear to be
* valid. Now, docs explain in dwords what is in the context object. The full
* size is 70720 bytes, however, the power context and execlist context will
* never be saved (power context is stored elsewhere, and execlists don't work
* on HSW) - so the final size, including the extra state required for the
* Resource Streamer, is 66944 bytes, which rounds to 17 pages.
*/
#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE)
#define DEFAULT_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
#define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE)
#define GEN10_LR_CONTEXT_RENDER_SIZE (18 * PAGE_SIZE)
#define GEN11_LR_CONTEXT_RENDER_SIZE (14 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_OTHER_SIZE ( 2 * PAGE_SIZE)
struct engine_class_info {
const char *name;
int (*init_legacy)(struct intel_engine_cs *engine);
int (*init_execlists)(struct intel_engine_cs *engine);
u8 uabi_class;
};
static const struct engine_class_info intel_engine_classes[] = {
[RENDER_CLASS] = {
.name = "rcs",
.init_execlists = logical_render_ring_init,
.init_legacy = intel_init_render_ring_buffer,
.uabi_class = I915_ENGINE_CLASS_RENDER,
},
[COPY_ENGINE_CLASS] = {
.name = "bcs",
.init_execlists = logical_xcs_ring_init,
.init_legacy = intel_init_blt_ring_buffer,
.uabi_class = I915_ENGINE_CLASS_COPY,
},
[VIDEO_DECODE_CLASS] = {
.name = "vcs",
.init_execlists = logical_xcs_ring_init,
.init_legacy = intel_init_bsd_ring_buffer,
.uabi_class = I915_ENGINE_CLASS_VIDEO,
},
[VIDEO_ENHANCEMENT_CLASS] = {
.name = "vecs",
.init_execlists = logical_xcs_ring_init,
.init_legacy = intel_init_vebox_ring_buffer,
.uabi_class = I915_ENGINE_CLASS_VIDEO_ENHANCE,
},
};
#define MAX_MMIO_BASES 3
struct engine_info {
unsigned int hw_id;
unsigned int uabi_id;
u8 class;
u8 instance;
/* mmio bases table *must* be sorted in reverse gen order */
struct engine_mmio_base {
u32 gen : 8;
u32 base : 24;
} mmio_bases[MAX_MMIO_BASES];
};
static const struct engine_info intel_engines[] = {
[RCS] = {
.hw_id = RCS_HW,
.uabi_id = I915_EXEC_RENDER,
.class = RENDER_CLASS,
.instance = 0,
.mmio_bases = {
{ .gen = 1, .base = RENDER_RING_BASE }
},
},
[BCS] = {
.hw_id = BCS_HW,
.uabi_id = I915_EXEC_BLT,
.class = COPY_ENGINE_CLASS,
.instance = 0,
.mmio_bases = {
{ .gen = 6, .base = BLT_RING_BASE }
},
},
[VCS] = {
.hw_id = VCS_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 0,
.mmio_bases = {
{ .gen = 11, .base = GEN11_BSD_RING_BASE },
{ .gen = 6, .base = GEN6_BSD_RING_BASE },
{ .gen = 4, .base = BSD_RING_BASE }
},
},
[VCS2] = {
.hw_id = VCS2_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 1,
.mmio_bases = {
{ .gen = 11, .base = GEN11_BSD2_RING_BASE },
{ .gen = 8, .base = GEN8_BSD2_RING_BASE }
},
},
[VCS3] = {
.hw_id = VCS3_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 2,
.mmio_bases = {
{ .gen = 11, .base = GEN11_BSD3_RING_BASE }
},
},
[VCS4] = {
.hw_id = VCS4_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 3,
.mmio_bases = {
{ .gen = 11, .base = GEN11_BSD4_RING_BASE }
},
},
[VECS] = {
.hw_id = VECS_HW,
.uabi_id = I915_EXEC_VEBOX,
.class = VIDEO_ENHANCEMENT_CLASS,
.instance = 0,
.mmio_bases = {
{ .gen = 11, .base = GEN11_VEBOX_RING_BASE },
{ .gen = 7, .base = VEBOX_RING_BASE }
},
},
[VECS2] = {
.hw_id = VECS2_HW,
.uabi_id = I915_EXEC_VEBOX,
.class = VIDEO_ENHANCEMENT_CLASS,
.instance = 1,
.mmio_bases = {
{ .gen = 11, .base = GEN11_VEBOX2_RING_BASE }
},
},
};
/**
* ___intel_engine_context_size() - return the size of the context for an engine
* @dev_priv: i915 device private
* @class: engine class
*
* Each engine class may require a different amount of space for a context
* image.
*
* Return: size (in bytes) of an engine class specific context image
*
* Note: this size includes the HWSP, which is part of the context image
* in LRC mode, but does not include the "shared data page" used with
* GuC submission. The caller should account for this if using the GuC.
*/
static u32
__intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
{
u32 cxt_size;
BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE);
switch (class) {
case RENDER_CLASS:
switch (INTEL_GEN(dev_priv)) {
default:
MISSING_CASE(INTEL_GEN(dev_priv));
return DEFAULT_LR_CONTEXT_RENDER_SIZE;
case 11:
return GEN11_LR_CONTEXT_RENDER_SIZE;
case 10:
return GEN10_LR_CONTEXT_RENDER_SIZE;
case 9:
return GEN9_LR_CONTEXT_RENDER_SIZE;
case 8:
return GEN8_LR_CONTEXT_RENDER_SIZE;
case 7:
if (IS_HASWELL(dev_priv))
return HSW_CXT_TOTAL_SIZE;
cxt_size = I915_READ(GEN7_CXT_SIZE);
return round_up(GEN7_CXT_TOTAL_SIZE(cxt_size) * 64,
PAGE_SIZE);
case 6:
cxt_size = I915_READ(CXT_SIZE);
return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64,
PAGE_SIZE);
case 5:
case 4:
case 3:
case 2:
/* For the special day when i810 gets merged. */
case 1:
return 0;
}
break;
default:
MISSING_CASE(class);
/* fall through */
case VIDEO_DECODE_CLASS:
case VIDEO_ENHANCEMENT_CLASS:
case COPY_ENGINE_CLASS:
if (INTEL_GEN(dev_priv) < 8)
return 0;
return GEN8_LR_CONTEXT_OTHER_SIZE;
}
}
static u32 __engine_mmio_base(struct drm_i915_private *i915,
const struct engine_mmio_base *bases)
{
int i;
for (i = 0; i < MAX_MMIO_BASES; i++)
if (INTEL_GEN(i915) >= bases[i].gen)
break;
GEM_BUG_ON(i == MAX_MMIO_BASES);
GEM_BUG_ON(!bases[i].base);
return bases[i].base;
}
static void __sprint_engine_name(char *name, const struct engine_info *info)
{
WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",
intel_engine_classes[info->class].name,
info->instance) >= INTEL_ENGINE_CS_MAX_NAME);
}
static int
intel_engine_setup(struct drm_i915_private *dev_priv,
enum intel_engine_id id)
{
const struct engine_info *info = &intel_engines[id];
struct intel_engine_cs *engine;
GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
if (GEM_DEBUG_WARN_ON(info->class > MAX_ENGINE_CLASS))
return -EINVAL;
if (GEM_DEBUG_WARN_ON(info->instance > MAX_ENGINE_INSTANCE))
return -EINVAL;
if (GEM_DEBUG_WARN_ON(dev_priv->engine_class[info->class][info->instance]))
return -EINVAL;
GEM_BUG_ON(dev_priv->engine[id]);
engine = kzalloc(sizeof(*engine), GFP_KERNEL);
if (!engine)
return -ENOMEM;
engine->id = id;
engine->i915 = dev_priv;
__sprint_engine_name(engine->name, info);
engine->hw_id = engine->guc_id = info->hw_id;
engine->mmio_base = __engine_mmio_base(dev_priv, info->mmio_bases);
engine->class = info->class;
engine->instance = info->instance;
engine->uabi_id = info->uabi_id;
engine->uabi_class = intel_engine_classes[info->class].uabi_class;
engine->context_size = __intel_engine_context_size(dev_priv,
engine->class);
if (WARN_ON(engine->context_size > BIT(20)))
engine->context_size = 0;
if (engine->context_size)
DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
/* Nothing to do here, execute in order of dependencies */
engine->schedule = NULL;
seqlock_init(&engine->stats.lock);
ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
dev_priv->engine_class[info->class][info->instance] = engine;
dev_priv->engine[id] = engine;
return 0;
}
/**
* intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
* @dev_priv: i915 device private
*
* Return: non-zero if the initialization failed.
*/
int intel_engines_init_mmio(struct drm_i915_private *dev_priv)
{
struct intel_device_info *device_info = mkwrite_device_info(dev_priv);
const unsigned int ring_mask = INTEL_INFO(dev_priv)->ring_mask;
struct intel_engine_cs *engine;
enum intel_engine_id id;
unsigned int mask = 0;
unsigned int i;
int err;
WARN_ON(ring_mask == 0);
WARN_ON(ring_mask &
GENMASK(BITS_PER_TYPE(mask) - 1, I915_NUM_ENGINES));
if (i915_inject_load_failure())
return -ENODEV;
for (i = 0; i < ARRAY_SIZE(intel_engines); i++) {
if (!HAS_ENGINE(dev_priv, i))
continue;
err = intel_engine_setup(dev_priv, i);
if (err)
goto cleanup;
mask |= ENGINE_MASK(i);
}
/*
* Catch failures to update intel_engines table when the new engines
* are added to the driver by a warning and disabling the forgotten
* engines.
*/
if (WARN_ON(mask != ring_mask))
device_info->ring_mask = mask;
/* We always presume we have at least RCS available for later probing */
if (WARN_ON(!HAS_ENGINE(dev_priv, RCS))) {
err = -ENODEV;
goto cleanup;
}
device_info->num_rings = hweight32(mask);
i915_check_and_clear_faults(dev_priv);
return 0;
cleanup:
for_each_engine(engine, dev_priv, id)
kfree(engine);
return err;
}
/**
* intel_engines_init() - init the Engine Command Streamers
* @dev_priv: i915 device private
*
* Return: non-zero if the initialization failed.
*/
int intel_engines_init(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
enum intel_engine_id id, err_id;
int err;
for_each_engine(engine, dev_priv, id) {
const struct engine_class_info *class_info =
&intel_engine_classes[engine->class];
int (*init)(struct intel_engine_cs *engine);
if (HAS_EXECLISTS(dev_priv))
init = class_info->init_execlists;
else
init = class_info->init_legacy;
err = -EINVAL;
err_id = id;
if (GEM_DEBUG_WARN_ON(!init))
goto cleanup;
err = init(engine);
if (err)
goto cleanup;
GEM_BUG_ON(!engine->submit_request);
}
return 0;
cleanup:
for_each_engine(engine, dev_priv, id) {
if (id >= err_id) {
kfree(engine);
dev_priv->engine[id] = NULL;
} else {
dev_priv->gt.cleanup_engine(engine);
}
}
return err;
}
void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
{
struct drm_i915_private *dev_priv = engine->i915;
/* Our semaphore implementation is strictly monotonic (i.e. we proceed
* so long as the semaphore value in the register/page is greater
* than the sync value), so whenever we reset the seqno,
* so long as we reset the tracking semaphore value to 0, it will
* always be before the next request's seqno. If we don't reset
* the semaphore value, then when the seqno moves backwards all
* future waits will complete instantly (causing rendering corruption).
*/
if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
if (HAS_VEBOX(dev_priv))
I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
}
intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
/* After manually advancing the seqno, fake the interrupt in case
* there are any waiters for that seqno.
*/
intel_engine_wakeup(engine);
GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
}
static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
{
i915_gem_batch_pool_init(&engine->batch_pool, engine);
}
static void intel_engine_init_execlist(struct intel_engine_cs *engine)
{
struct intel_engine_execlists * const execlists = &engine->execlists;
execlists->port_mask = 1;
GEM_BUG_ON(!is_power_of_2(execlists_num_ports(execlists)));
GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
execlists->queue_priority = INT_MIN;
execlists->queue = RB_ROOT_CACHED;
}
/**
* intel_engines_setup_common - setup engine state not requiring hw access
* @engine: Engine to setup.
*
* Initializes @engine@ structure members shared between legacy and execlists
* submission modes which do not require hardware access.
*
* Typically done early in the submission mode specific engine setup stage.
*/
void intel_engine_setup_common(struct intel_engine_cs *engine)
{
i915_timeline_init(engine->i915, &engine->timeline, engine->name);
i915_timeline_set_subclass(&engine->timeline, TIMELINE_ENGINE);
intel_engine_init_execlist(engine);
intel_engine_init_hangcheck(engine);
intel_engine_init_batch_pool(engine);
intel_engine_init_cmd_parser(engine);
}
int intel_engine_create_scratch(struct intel_engine_cs *engine,
unsigned int size)
{
struct drm_i915_gem_object *obj;
struct i915_vma *vma;
int ret;
WARN_ON(engine->scratch);
obj = i915_gem_object_create_stolen(engine->i915, size);
if (!obj)
obj = i915_gem_object_create_internal(engine->i915, size);
if (IS_ERR(obj)) {
DRM_ERROR("Failed to allocate scratch page\n");
return PTR_ERR(obj);
}
vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto err_unref;
}
ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
if (ret)
goto err_unref;
engine->scratch = vma;
return 0;
err_unref:
i915_gem_object_put(obj);
return ret;
}
void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
{
i915_vma_unpin_and_release(&engine->scratch, 0);
}
static void cleanup_status_page(struct intel_engine_cs *engine)
{
if (HWS_NEEDS_PHYSICAL(engine->i915)) {
void *addr = fetch_and_zero(&engine->status_page.page_addr);
__free_page(virt_to_page(addr));
}
i915_vma_unpin_and_release(&engine->status_page.vma,
I915_VMA_RELEASE_MAP);
}
static int init_status_page(struct intel_engine_cs *engine)
{
struct drm_i915_gem_object *obj;
struct i915_vma *vma;
unsigned int flags;
void *vaddr;
int ret;
obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
if (IS_ERR(obj)) {
DRM_ERROR("Failed to allocate status page\n");
return PTR_ERR(obj);
}
ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
if (ret)
goto err;
vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto err;
}
flags = PIN_GLOBAL;
if (!HAS_LLC(engine->i915))
/* On g33, we cannot place HWS above 256MiB, so
* restrict its pinning to the low mappable arena.
* Though this restriction is not documented for
* gen4, gen5, or byt, they also behave similarly
* and hang if the HWS is placed at the top of the
* GTT. To generalise, it appears that all !llc
* platforms have issues with us placing the HWS
* above the mappable region (even though we never
* actually map it).
*/
flags |= PIN_MAPPABLE;
else
flags |= PIN_HIGH;
ret = i915_vma_pin(vma, 0, 0, flags);
if (ret)
goto err;
vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
if (IS_ERR(vaddr)) {
ret = PTR_ERR(vaddr);
goto err_unpin;
}
engine->status_page.vma = vma;
engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE);
return 0;
err_unpin:
i915_vma_unpin(vma);
err:
i915_gem_object_put(obj);
return ret;
}
static int init_phys_status_page(struct intel_engine_cs *engine)
{
struct page *page;
/*
* Though the HWS register does support 36bit addresses, historically
* we have had hangs and corruption reported due to wild writes if
* the HWS is placed above 4G.
*/
page = alloc_page(GFP_KERNEL | __GFP_DMA32 | __GFP_ZERO);
if (!page)
return -ENOMEM;
engine->status_page.page_addr = page_address(page);
return 0;
}
static void __intel_context_unpin(struct i915_gem_context *ctx,
struct intel_engine_cs *engine)
{
intel_context_unpin(to_intel_context(ctx, engine));
}
/**
* intel_engines_init_common - initialize cengine state which might require hw access
* @engine: Engine to initialize.
*
* Initializes @engine@ structure members shared between legacy and execlists
* submission modes which do require hardware access.
*
* Typcally done at later stages of submission mode specific engine setup.
*
* Returns zero on success or an error code on failure.
*/
int intel_engine_init_common(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct intel_context *ce;
int ret;
engine->set_default_submission(engine);
/* We may need to do things with the shrinker which
* require us to immediately switch back to the default
* context. This can cause a problem as pinning the
* default context also requires GTT space which may not
* be available. To avoid this we always pin the default
* context.
*/
ce = intel_context_pin(i915->kernel_context, engine);
if (IS_ERR(ce))
return PTR_ERR(ce);
/*
* Similarly the preempt context must always be available so that
* we can interrupt the engine at any time.
*/
if (i915->preempt_context) {
ce = intel_context_pin(i915->preempt_context, engine);
if (IS_ERR(ce)) {
ret = PTR_ERR(ce);
goto err_unpin_kernel;
}
}
ret = intel_engine_init_breadcrumbs(engine);
if (ret)
goto err_unpin_preempt;
if (HWS_NEEDS_PHYSICAL(i915))
ret = init_phys_status_page(engine);
else
ret = init_status_page(engine);
if (ret)
goto err_breadcrumbs;
return 0;
err_breadcrumbs:
intel_engine_fini_breadcrumbs(engine);
err_unpin_preempt:
if (i915->preempt_context)
__intel_context_unpin(i915->preempt_context, engine);
err_unpin_kernel:
__intel_context_unpin(i915->kernel_context, engine);
return ret;
}
/**
* intel_engines_cleanup_common - cleans up the engine state created by
* the common initiailizers.
* @engine: Engine to cleanup.
*
* This cleans up everything created by the common helpers.
*/
void intel_engine_cleanup_common(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
intel_engine_cleanup_scratch(engine);
cleanup_status_page(engine);
intel_engine_fini_breadcrumbs(engine);
intel_engine_cleanup_cmd_parser(engine);
i915_gem_batch_pool_fini(&engine->batch_pool);
if (engine->default_state)
i915_gem_object_put(engine->default_state);
if (i915->preempt_context)
__intel_context_unpin(i915->preempt_context, engine);
__intel_context_unpin(i915->kernel_context, engine);
i915_timeline_fini(&engine->timeline);
}
u64 intel_engine_get_active_head(const struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
u64 acthd;
if (INTEL_GEN(dev_priv) >= 8)
acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base),
RING_ACTHD_UDW(engine->mmio_base));
else if (INTEL_GEN(dev_priv) >= 4)
acthd = I915_READ(RING_ACTHD(engine->mmio_base));
else
acthd = I915_READ(ACTHD);
return acthd;
}
u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
u64 bbaddr;
if (INTEL_GEN(dev_priv) >= 8)
bbaddr = I915_READ64_2x32(RING_BBADDR(engine->mmio_base),
RING_BBADDR_UDW(engine->mmio_base));
else
bbaddr = I915_READ(RING_BBADDR(engine->mmio_base));
return bbaddr;
}
int intel_engine_stop_cs(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
const u32 base = engine->mmio_base;
const i915_reg_t mode = RING_MI_MODE(base);
int err;
if (INTEL_GEN(dev_priv) < 3)
return -ENODEV;
GEM_TRACE("%s\n", engine->name);
I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
err = 0;
if (__intel_wait_for_register_fw(dev_priv,
mode, MODE_IDLE, MODE_IDLE,
1000, 0,
NULL)) {
GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
err = -ETIMEDOUT;
}
/* A final mmio read to let GPU writes be hopefully flushed to memory */
POSTING_READ_FW(mode);
return err;
}
void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
GEM_TRACE("%s\n", engine->name);
I915_WRITE_FW(RING_MI_MODE(engine->mmio_base),
_MASKED_BIT_DISABLE(STOP_RING));
}
const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
{
switch (type) {
case I915_CACHE_NONE: return " uncached";
case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
case I915_CACHE_L3_LLC: return " L3+LLC";
case I915_CACHE_WT: return " WT";
default: return "";
}
}
u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
{
const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
u32 mcr_s_ss_select;
u32 slice = fls(sseu->slice_mask);
u32 subslice = fls(sseu->subslice_mask[slice]);
if (IS_GEN10(dev_priv))
mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
GEN8_MCR_SUBSLICE(subslice);
else if (INTEL_GEN(dev_priv) >= 11)
mcr_s_ss_select = GEN11_MCR_SLICE(slice) |
GEN11_MCR_SUBSLICE(subslice);
else
mcr_s_ss_select = 0;
return mcr_s_ss_select;
}
static inline uint32_t
read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
int subslice, i915_reg_t reg)
{
uint32_t mcr_slice_subslice_mask;
uint32_t mcr_slice_subslice_select;
uint32_t default_mcr_s_ss_select;
uint32_t mcr;
uint32_t ret;
enum forcewake_domains fw_domains;
if (INTEL_GEN(dev_priv) >= 11) {
mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
GEN11_MCR_SUBSLICE_MASK;
mcr_slice_subslice_select = GEN11_MCR_SLICE(slice) |
GEN11_MCR_SUBSLICE(subslice);
} else {
mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
GEN8_MCR_SUBSLICE_MASK;
mcr_slice_subslice_select = GEN8_MCR_SLICE(slice) |
GEN8_MCR_SUBSLICE(subslice);
}
default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
FW_REG_READ);
fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
GEN8_MCR_SELECTOR,
FW_REG_READ | FW_REG_WRITE);
spin_lock_irq(&dev_priv->uncore.lock);
intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) !=
default_mcr_s_ss_select);
mcr &= ~mcr_slice_subslice_mask;
mcr |= mcr_slice_subslice_select;
I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
ret = I915_READ_FW(reg);
mcr &= ~mcr_slice_subslice_mask;
mcr |= default_mcr_s_ss_select;
I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
spin_unlock_irq(&dev_priv->uncore.lock);
return ret;
}
/* NB: please notice the memset */
void intel_engine_get_instdone(struct intel_engine_cs *engine,
struct intel_instdone *instdone)
{
struct drm_i915_private *dev_priv = engine->i915;
u32 mmio_base = engine->mmio_base;
int slice;
int subslice;
memset(instdone, 0, sizeof(*instdone));
switch (INTEL_GEN(dev_priv)) {
default:
instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
if (engine->id != RCS)
break;
instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
instdone->sampler[slice][subslice] =
read_subslice_reg(dev_priv, slice, subslice,
GEN7_SAMPLER_INSTDONE);
instdone->row[slice][subslice] =
read_subslice_reg(dev_priv, slice, subslice,
GEN7_ROW_INSTDONE);
}
break;
case 7:
instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
if (engine->id != RCS)
break;
instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
instdone->sampler[0][0] = I915_READ(GEN7_SAMPLER_INSTDONE);
instdone->row[0][0] = I915_READ(GEN7_ROW_INSTDONE);
break;
case 6:
case 5:
case 4:
instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
if (engine->id == RCS)
/* HACK: Using the wrong struct member */
instdone->slice_common = I915_READ(GEN4_INSTDONE1);
break;
case 3:
case 2:
instdone->instdone = I915_READ(GEN2_INSTDONE);
break;
}
}
static bool ring_is_idle(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
bool idle = true;
/* If the whole device is asleep, the engine must be idle */
if (!intel_runtime_pm_get_if_in_use(dev_priv))
return true;
/* First check that no commands are left in the ring */
if ((I915_READ_HEAD(engine) & HEAD_ADDR) !=
(I915_READ_TAIL(engine) & TAIL_ADDR))
idle = false;
/* No bit for gen2, so assume the CS parser is idle */
if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
idle = false;
intel_runtime_pm_put(dev_priv);
return idle;
}
/**
* intel_engine_is_idle() - Report if the engine has finished process all work
* @engine: the intel_engine_cs
*
* Return true if there are no requests pending, nothing left to be submitted
* to hardware, and that the engine is idle.
*/
bool intel_engine_is_idle(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
/* More white lies, if wedged, hw state is inconsistent */
if (i915_terminally_wedged(&dev_priv->gpu_error))
return true;
/* Any inflight/incomplete requests? */
if (!intel_engine_signaled(engine, intel_engine_last_submit(engine)))
return false;
if (I915_SELFTEST_ONLY(engine->breadcrumbs.mock))
return true;
/* Waiting to drain ELSP? */
if (READ_ONCE(engine->execlists.active)) {
struct tasklet_struct *t = &engine->execlists.tasklet;
local_bh_disable();
if (tasklet_trylock(t)) {
/* Must wait for any GPU reset in progress. */
if (__tasklet_is_enabled(t))
t->func(t->data);
tasklet_unlock(t);
}
local_bh_enable();
/* Otherwise flush the tasklet if it was on another cpu */
tasklet_unlock_wait(t);
if (READ_ONCE(engine->execlists.active))
return false;