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
|
// SPDX-License-Identifier: MIT
/*
* Copyright © 2022 Intel Corporation
*/
#include "xe_guc_ads.h"
#include <drm/drm_managed.h>
#include <generated/xe_wa_oob.h>
#include "abi/guc_actions_abi.h"
#include "regs/xe_engine_regs.h"
#include "regs/xe_gt_regs.h"
#include "regs/xe_guc_regs.h"
#include "xe_bo.h"
#include "xe_gt.h"
#include "xe_gt_ccs_mode.h"
#include "xe_gt_printk.h"
#include "xe_guc.h"
#include "xe_guc_ct.h"
#include "xe_hw_engine.h"
#include "xe_lrc.h"
#include "xe_map.h"
#include "xe_mmio.h"
#include "xe_platform_types.h"
#include "xe_uc_fw.h"
#include "xe_wa.h"
/* Slack of a few additional entries per engine */
#define ADS_REGSET_EXTRA_MAX 8
static struct xe_guc *
ads_to_guc(struct xe_guc_ads *ads)
{
return container_of(ads, struct xe_guc, ads);
}
static struct xe_gt *
ads_to_gt(struct xe_guc_ads *ads)
{
return container_of(ads, struct xe_gt, uc.guc.ads);
}
static struct xe_device *
ads_to_xe(struct xe_guc_ads *ads)
{
return gt_to_xe(ads_to_gt(ads));
}
static struct iosys_map *
ads_to_map(struct xe_guc_ads *ads)
{
return &ads->bo->vmap;
}
/* UM Queue parameters: */
#define GUC_UM_QUEUE_SIZE (SZ_64K)
#define GUC_PAGE_RES_TIMEOUT_US (-1)
/*
* The Additional Data Struct (ADS) has pointers for different buffers used by
* the GuC. One single gem object contains the ADS struct itself (guc_ads) and
* all the extra buffers indirectly linked via the ADS struct's entries.
*
* Layout of the ADS blob allocated for the GuC:
*
* +---------------------------------------+ <== base
* | guc_ads |
* +---------------------------------------+
* | guc_policies |
* +---------------------------------------+
* | guc_gt_system_info |
* +---------------------------------------+
* | guc_engine_usage |
* +---------------------------------------+
* | guc_um_init_params |
* +---------------------------------------+ <== static
* | guc_mmio_reg[countA] (engine 0.0) |
* | guc_mmio_reg[countB] (engine 0.1) |
* | guc_mmio_reg[countC] (engine 1.0) |
* | ... |
* +---------------------------------------+ <== dynamic
* | padding |
* +---------------------------------------+ <== 4K aligned
* | golden contexts |
* +---------------------------------------+
* | padding |
* +---------------------------------------+ <== 4K aligned
* | w/a KLVs |
* +---------------------------------------+
* | padding |
* +---------------------------------------+ <== 4K aligned
* | capture lists |
* +---------------------------------------+
* | padding |
* +---------------------------------------+ <== 4K aligned
* | UM queues |
* +---------------------------------------+
* | padding |
* +---------------------------------------+ <== 4K aligned
* | private data |
* +---------------------------------------+
* | padding |
* +---------------------------------------+ <== 4K aligned
*/
struct __guc_ads_blob {
struct guc_ads ads;
struct guc_policies policies;
struct guc_gt_system_info system_info;
struct guc_engine_usage engine_usage;
struct guc_um_init_params um_init_params;
/* From here on, location is dynamic! Refer to above diagram. */
struct guc_mmio_reg regset[];
} __packed;
#define ads_blob_read(ads_, field_) \
xe_map_rd_field(ads_to_xe(ads_), ads_to_map(ads_), 0, \
struct __guc_ads_blob, field_)
#define ads_blob_write(ads_, field_, val_) \
xe_map_wr_field(ads_to_xe(ads_), ads_to_map(ads_), 0, \
struct __guc_ads_blob, field_, val_)
#define info_map_write(xe_, map_, field_, val_) \
xe_map_wr_field(xe_, map_, 0, struct guc_gt_system_info, field_, val_)
#define info_map_read(xe_, map_, field_) \
xe_map_rd_field(xe_, map_, 0, struct guc_gt_system_info, field_)
static size_t guc_ads_regset_size(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
xe_assert(xe, ads->regset_size);
return ads->regset_size;
}
static size_t guc_ads_golden_lrc_size(struct xe_guc_ads *ads)
{
return PAGE_ALIGN(ads->golden_lrc_size);
}
static u32 guc_ads_waklv_size(struct xe_guc_ads *ads)
{
return PAGE_ALIGN(ads->ads_waklv_size);
}
static size_t guc_ads_capture_size(struct xe_guc_ads *ads)
{
/* FIXME: Allocate a proper capture list */
return PAGE_ALIGN(PAGE_SIZE);
}
static size_t guc_ads_um_queues_size(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
if (!xe->info.has_usm)
return 0;
return GUC_UM_QUEUE_SIZE * GUC_UM_HW_QUEUE_MAX;
}
static size_t guc_ads_private_data_size(struct xe_guc_ads *ads)
{
return PAGE_ALIGN(ads_to_guc(ads)->fw.private_data_size);
}
static size_t guc_ads_regset_offset(struct xe_guc_ads *ads)
{
return offsetof(struct __guc_ads_blob, regset);
}
static size_t guc_ads_golden_lrc_offset(struct xe_guc_ads *ads)
{
size_t offset;
offset = guc_ads_regset_offset(ads) +
guc_ads_regset_size(ads);
return PAGE_ALIGN(offset);
}
static size_t guc_ads_waklv_offset(struct xe_guc_ads *ads)
{
u32 offset;
offset = guc_ads_golden_lrc_offset(ads) +
guc_ads_golden_lrc_size(ads);
return PAGE_ALIGN(offset);
}
static size_t guc_ads_capture_offset(struct xe_guc_ads *ads)
{
size_t offset;
offset = guc_ads_waklv_offset(ads) +
guc_ads_waklv_size(ads);
return PAGE_ALIGN(offset);
}
static size_t guc_ads_um_queues_offset(struct xe_guc_ads *ads)
{
u32 offset;
offset = guc_ads_capture_offset(ads) +
guc_ads_capture_size(ads);
return PAGE_ALIGN(offset);
}
static size_t guc_ads_private_data_offset(struct xe_guc_ads *ads)
{
size_t offset;
offset = guc_ads_um_queues_offset(ads) +
guc_ads_um_queues_size(ads);
return PAGE_ALIGN(offset);
}
static size_t guc_ads_size(struct xe_guc_ads *ads)
{
return guc_ads_private_data_offset(ads) +
guc_ads_private_data_size(ads);
}
static bool needs_wa_1607983814(struct xe_device *xe)
{
return GRAPHICS_VERx100(xe) < 1250;
}
static size_t calculate_regset_size(struct xe_gt *gt)
{
struct xe_reg_sr_entry *sr_entry;
unsigned long sr_idx;
struct xe_hw_engine *hwe;
enum xe_hw_engine_id id;
unsigned int count = 0;
for_each_hw_engine(hwe, gt, id)
xa_for_each(&hwe->reg_sr.xa, sr_idx, sr_entry)
count++;
count += ADS_REGSET_EXTRA_MAX * XE_NUM_HW_ENGINES;
if (needs_wa_1607983814(gt_to_xe(gt)))
count += LNCFCMOCS_REG_COUNT;
return count * sizeof(struct guc_mmio_reg);
}
static u32 engine_enable_mask(struct xe_gt *gt, enum xe_engine_class class)
{
struct xe_hw_engine *hwe;
enum xe_hw_engine_id id;
u32 mask = 0;
for_each_hw_engine(hwe, gt, id)
if (hwe->class == class)
mask |= BIT(hwe->instance);
return mask;
}
static size_t calculate_golden_lrc_size(struct xe_guc_ads *ads)
{
struct xe_gt *gt = ads_to_gt(ads);
size_t total_size = 0, alloc_size, real_size;
int class;
for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
if (!engine_enable_mask(gt, class))
continue;
real_size = xe_gt_lrc_size(gt, class);
alloc_size = PAGE_ALIGN(real_size);
total_size += alloc_size;
}
return total_size;
}
static void guc_waklv_enable_one_word(struct xe_guc_ads *ads,
enum xe_guc_klv_ids klv_id,
u32 value,
u32 *offset, u32 *remain)
{
u32 size;
u32 klv_entry[] = {
/* 16:16 key/length */
FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
FIELD_PREP(GUC_KLV_0_LEN, 1),
value,
/* 1 dword data */
};
size = sizeof(klv_entry);
if (*remain < size) {
drm_warn(&ads_to_xe(ads)->drm,
"w/a klv buffer too small to add klv id %d\n", klv_id);
} else {
xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
klv_entry, size);
*offset += size;
*remain -= size;
}
}
static void guc_waklv_enable_simple(struct xe_guc_ads *ads,
enum xe_guc_klv_ids klv_id, u32 *offset, u32 *remain)
{
u32 klv_entry[] = {
/* 16:16 key/length */
FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
FIELD_PREP(GUC_KLV_0_LEN, 0),
/* 0 dwords data */
};
u32 size;
size = sizeof(klv_entry);
if (xe_gt_WARN(ads_to_gt(ads), *remain < size,
"w/a klv buffer too small to add klv id %d\n", klv_id))
return;
xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
klv_entry, size);
*offset += size;
*remain -= size;
}
static void guc_waklv_init(struct xe_guc_ads *ads)
{
struct xe_gt *gt = ads_to_gt(ads);
u64 addr_ggtt;
u32 offset, remain, size;
offset = guc_ads_waklv_offset(ads);
remain = guc_ads_waklv_size(ads);
if (XE_WA(gt, 14019882105))
guc_waklv_enable_simple(ads,
GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED,
&offset, &remain);
if (XE_WA(gt, 18024947630))
guc_waklv_enable_simple(ads,
GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING,
&offset, &remain);
if (XE_WA(gt, 16022287689))
guc_waklv_enable_simple(ads,
GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE,
&offset, &remain);
/*
* On RC6 exit, GuC will write register 0xB04 with the default value provided. As of now,
* the default value for this register is determined to be 0xC40. This could change in the
* future, so GuC depends on KMD to send it the correct value.
*/
if (XE_WA(gt, 13011645652))
guc_waklv_enable_one_word(ads,
GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE,
0xC40,
&offset, &remain);
if (XE_WA(gt, 14022293748) || XE_WA(gt, 22019794406))
guc_waklv_enable_simple(ads,
GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET,
&offset, &remain);
size = guc_ads_waklv_size(ads) - remain;
if (!size)
return;
offset = guc_ads_waklv_offset(ads);
addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
ads_blob_write(ads, ads.wa_klv_addr_lo, lower_32_bits(addr_ggtt));
ads_blob_write(ads, ads.wa_klv_addr_hi, upper_32_bits(addr_ggtt));
ads_blob_write(ads, ads.wa_klv_size, size);
}
static int calculate_waklv_size(struct xe_guc_ads *ads)
{
/*
* A single page is both the minimum size possible and
* is sufficiently large enough for all current platforms.
*/
return SZ_4K;
}
#define MAX_GOLDEN_LRC_SIZE (SZ_4K * 64)
int xe_guc_ads_init(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct xe_tile *tile = gt_to_tile(gt);
struct xe_bo *bo;
ads->golden_lrc_size = calculate_golden_lrc_size(ads);
ads->regset_size = calculate_regset_size(gt);
ads->ads_waklv_size = calculate_waklv_size(ads);
bo = xe_managed_bo_create_pin_map(xe, tile, guc_ads_size(ads) + MAX_GOLDEN_LRC_SIZE,
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE);
if (IS_ERR(bo))
return PTR_ERR(bo);
ads->bo = bo;
return 0;
}
/**
* xe_guc_ads_init_post_hwconfig - initialize ADS post hwconfig load
* @ads: Additional data structures object
*
* Recalcuate golden_lrc_size & regset_size as the number hardware engines may
* have changed after the hwconfig was loaded. Also verify the new sizes fit in
* the already allocated ADS buffer object.
*
* Return: 0 on success, negative error code on error.
*/
int xe_guc_ads_init_post_hwconfig(struct xe_guc_ads *ads)
{
struct xe_gt *gt = ads_to_gt(ads);
u32 prev_regset_size = ads->regset_size;
xe_gt_assert(gt, ads->bo);
ads->golden_lrc_size = calculate_golden_lrc_size(ads);
ads->regset_size = calculate_regset_size(gt);
xe_gt_assert(gt, ads->golden_lrc_size +
(ads->regset_size - prev_regset_size) <=
MAX_GOLDEN_LRC_SIZE);
return 0;
}
static void guc_policies_init(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
u32 global_flags = 0;
ads_blob_write(ads, policies.dpc_promote_time,
GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US);
ads_blob_write(ads, policies.max_num_work_items,
GLOBAL_POLICY_MAX_NUM_WI);
if (xe->wedged.mode == 2)
global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET;
ads_blob_write(ads, policies.global_flags, global_flags);
ads_blob_write(ads, policies.is_valid, 1);
}
static void fill_engine_enable_masks(struct xe_gt *gt,
struct iosys_map *info_map)
{
struct xe_device *xe = gt_to_xe(gt);
info_map_write(xe, info_map, engine_enabled_masks[GUC_RENDER_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_RENDER));
info_map_write(xe, info_map, engine_enabled_masks[GUC_BLITTER_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_COPY));
info_map_write(xe, info_map, engine_enabled_masks[GUC_VIDEO_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_VIDEO_DECODE));
info_map_write(xe, info_map,
engine_enabled_masks[GUC_VIDEOENHANCE_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_VIDEO_ENHANCE));
info_map_write(xe, info_map, engine_enabled_masks[GUC_COMPUTE_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_COMPUTE));
info_map_write(xe, info_map, engine_enabled_masks[GUC_GSC_OTHER_CLASS],
engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER));
}
static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
u8 guc_class;
for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) {
if (!info_map_read(xe, &info_map,
engine_enabled_masks[guc_class]))
continue;
ads_blob_write(ads, ads.eng_state_size[guc_class],
guc_ads_golden_lrc_size(ads) -
xe_lrc_skip_size(xe));
ads_blob_write(ads, ads.golden_context_lrca[guc_class],
xe_bo_ggtt_addr(ads->bo) +
guc_ads_golden_lrc_offset(ads));
}
}
static void guc_mapping_table_init_invalid(struct xe_gt *gt,
struct iosys_map *info_map)
{
struct xe_device *xe = gt_to_xe(gt);
unsigned int i, j;
/* Table must be set to invalid values for entries not used */
for (i = 0; i < GUC_MAX_ENGINE_CLASSES; ++i)
for (j = 0; j < GUC_MAX_INSTANCES_PER_CLASS; ++j)
info_map_write(xe, info_map, mapping_table[i][j],
GUC_MAX_INSTANCES_PER_CLASS);
}
static void guc_mapping_table_init(struct xe_gt *gt,
struct iosys_map *info_map)
{
struct xe_device *xe = gt_to_xe(gt);
struct xe_hw_engine *hwe;
enum xe_hw_engine_id id;
guc_mapping_table_init_invalid(gt, info_map);
for_each_hw_engine(hwe, gt, id) {
u8 guc_class;
guc_class = xe_engine_class_to_guc_class(hwe->class);
info_map_write(xe, info_map,
mapping_table[guc_class][hwe->logical_instance],
hwe->instance);
}
}
static void guc_capture_list_init(struct xe_guc_ads *ads)
{
int i, j;
u32 addr = xe_bo_ggtt_addr(ads->bo) + guc_ads_capture_offset(ads);
/* FIXME: Populate a proper capture list */
for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) {
for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) {
ads_blob_write(ads, ads.capture_instance[i][j], addr);
ads_blob_write(ads, ads.capture_class[i][j], addr);
}
ads_blob_write(ads, ads.capture_global[i], addr);
}
}
static void guc_mmio_regset_write_one(struct xe_guc_ads *ads,
struct iosys_map *regset_map,
struct xe_reg reg,
unsigned int n_entry)
{
struct guc_mmio_reg entry = {
.offset = reg.addr,
.flags = reg.masked ? GUC_REGSET_MASKED : 0,
};
xe_map_memcpy_to(ads_to_xe(ads), regset_map, n_entry * sizeof(entry),
&entry, sizeof(entry));
}
static unsigned int guc_mmio_regset_write(struct xe_guc_ads *ads,
struct iosys_map *regset_map,
struct xe_hw_engine *hwe)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_hw_engine *hwe_rcs_reset_domain =
xe_gt_any_hw_engine_by_reset_domain(hwe->gt, XE_ENGINE_CLASS_RENDER);
struct xe_reg_sr_entry *entry;
unsigned long idx;
unsigned int count = 0;
const struct {
struct xe_reg reg;
bool skip;
} *e, extra_regs[] = {
{ .reg = RING_MODE(hwe->mmio_base), },
{ .reg = RING_HWS_PGA(hwe->mmio_base), },
{ .reg = RING_IMR(hwe->mmio_base), },
{ .reg = RCU_MODE, .skip = hwe != hwe_rcs_reset_domain },
{ .reg = CCS_MODE,
.skip = hwe != hwe_rcs_reset_domain || !xe_gt_ccs_mode_enabled(hwe->gt) },
};
u32 i;
BUILD_BUG_ON(ARRAY_SIZE(extra_regs) > ADS_REGSET_EXTRA_MAX);
xa_for_each(&hwe->reg_sr.xa, idx, entry)
guc_mmio_regset_write_one(ads, regset_map, entry->reg, count++);
for (e = extra_regs; e < extra_regs + ARRAY_SIZE(extra_regs); e++) {
if (e->skip)
continue;
guc_mmio_regset_write_one(ads, regset_map, e->reg, count++);
}
/* Wa_1607983814 */
if (needs_wa_1607983814(xe) && hwe->class == XE_ENGINE_CLASS_RENDER) {
for (i = 0; i < LNCFCMOCS_REG_COUNT; i++) {
guc_mmio_regset_write_one(ads, regset_map,
XELP_LNCFCMOCS(i), count++);
}
}
return count;
}
static void guc_mmio_reg_state_init(struct xe_guc_ads *ads)
{
size_t regset_offset = guc_ads_regset_offset(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct xe_hw_engine *hwe;
enum xe_hw_engine_id id;
u32 addr = xe_bo_ggtt_addr(ads->bo) + regset_offset;
struct iosys_map regset_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
regset_offset);
unsigned int regset_used = 0;
for_each_hw_engine(hwe, gt, id) {
unsigned int count;
u8 gc;
/*
* 1. Write all MMIO entries for this exec queue to the table. No
* need to worry about fused-off engines and when there are
* entries in the regset: the reg_state_list has been zero'ed
* by xe_guc_ads_populate()
*/
count = guc_mmio_regset_write(ads, ®set_map, hwe);
if (!count)
continue;
/*
* 2. Record in the header (ads.reg_state_list) the address
* location and number of entries
*/
gc = xe_engine_class_to_guc_class(hwe->class);
ads_blob_write(ads, ads.reg_state_list[gc][hwe->instance].address, addr);
ads_blob_write(ads, ads.reg_state_list[gc][hwe->instance].count, count);
addr += count * sizeof(struct guc_mmio_reg);
iosys_map_incr(®set_map, count * sizeof(struct guc_mmio_reg));
regset_used += count * sizeof(struct guc_mmio_reg);
}
xe_gt_assert(gt, regset_used <= ads->regset_size);
}
static void guc_um_init_params(struct xe_guc_ads *ads)
{
u32 um_queue_offset = guc_ads_um_queues_offset(ads);
u64 base_dpa;
u32 base_ggtt;
int i;
base_ggtt = xe_bo_ggtt_addr(ads->bo) + um_queue_offset;
base_dpa = xe_bo_main_addr(ads->bo, PAGE_SIZE) + um_queue_offset;
for (i = 0; i < GUC_UM_HW_QUEUE_MAX; ++i) {
ads_blob_write(ads, um_init_params.queue_params[i].base_dpa,
base_dpa + (i * GUC_UM_QUEUE_SIZE));
ads_blob_write(ads, um_init_params.queue_params[i].base_ggtt_address,
base_ggtt + (i * GUC_UM_QUEUE_SIZE));
ads_blob_write(ads, um_init_params.queue_params[i].size_in_bytes,
GUC_UM_QUEUE_SIZE);
}
ads_blob_write(ads, um_init_params.page_response_timeout_in_us,
GUC_PAGE_RES_TIMEOUT_US);
}
static void guc_doorbell_init(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
if (GRAPHICS_VER(xe) >= 12 && !IS_DGFX(xe)) {
u32 distdbreg =
xe_mmio_read32(gt, DIST_DBS_POPULATED);
ads_blob_write(ads,
system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_DOORBELL_COUNT_PER_SQIDI],
REG_FIELD_GET(DOORBELLS_PER_SQIDI_MASK, distdbreg) + 1);
}
}
/**
* xe_guc_ads_populate_minimal - populate minimal ADS
* @ads: Additional data structures object
*
* This function populates a minimal ADS that does not support submissions but
* enough so the GuC can load and the hwconfig table can be read.
*/
void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads)
{
struct xe_gt *gt = ads_to_gt(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
u32 base = xe_bo_ggtt_addr(ads->bo);
xe_gt_assert(gt, ads->bo);
xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
guc_policies_init(ads);
guc_prep_golden_lrc_null(ads);
guc_mapping_table_init_invalid(gt, &info_map);
guc_doorbell_init(ads);
ads_blob_write(ads, ads.scheduler_policies, base +
offsetof(struct __guc_ads_blob, policies));
ads_blob_write(ads, ads.gt_system_info, base +
offsetof(struct __guc_ads_blob, system_info));
ads_blob_write(ads, ads.private_data, base +
guc_ads_private_data_offset(ads));
}
void xe_guc_ads_populate(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
u32 base = xe_bo_ggtt_addr(ads->bo);
xe_gt_assert(gt, ads->bo);
xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
guc_policies_init(ads);
fill_engine_enable_masks(gt, &info_map);
guc_mmio_reg_state_init(ads);
guc_prep_golden_lrc_null(ads);
guc_mapping_table_init(gt, &info_map);
guc_capture_list_init(ads);
guc_doorbell_init(ads);
guc_waklv_init(ads);
if (xe->info.has_usm) {
guc_um_init_params(ads);
ads_blob_write(ads, ads.um_init_data, base +
offsetof(struct __guc_ads_blob, um_init_params));
}
ads_blob_write(ads, ads.scheduler_policies, base +
offsetof(struct __guc_ads_blob, policies));
ads_blob_write(ads, ads.gt_system_info, base +
offsetof(struct __guc_ads_blob, system_info));
ads_blob_write(ads, ads.private_data, base +
guc_ads_private_data_offset(ads));
}
static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
offsetof(struct __guc_ads_blob, system_info));
size_t total_size = 0, alloc_size, real_size;
u32 addr_ggtt, offset;
int class;
offset = guc_ads_golden_lrc_offset(ads);
addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
u8 guc_class;
guc_class = xe_engine_class_to_guc_class(class);
if (!info_map_read(xe, &info_map,
engine_enabled_masks[guc_class]))
continue;
xe_gt_assert(gt, gt->default_lrc[class]);
real_size = xe_gt_lrc_size(gt, class);
alloc_size = PAGE_ALIGN(real_size);
total_size += alloc_size;
/*
* This interface is slightly confusing. We need to pass the
* base address of the full golden context and the size of just
* the engine state, which is the section of the context image
* that starts after the execlists LRC registers. This is
* required to allow the GuC to restore just the engine state
* when a watchdog reset occurs.
* We calculate the engine state size by removing the size of
* what comes before it in the context image (which is identical
* on all engines).
*/
ads_blob_write(ads, ads.eng_state_size[guc_class],
real_size - xe_lrc_skip_size(xe));
ads_blob_write(ads, ads.golden_context_lrca[guc_class],
addr_ggtt);
xe_map_memcpy_to(xe, ads_to_map(ads), offset,
gt->default_lrc[class], real_size);
addr_ggtt += alloc_size;
offset += alloc_size;
}
xe_gt_assert(gt, total_size == ads->golden_lrc_size);
}
void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads)
{
guc_populate_golden_lrc(ads);
}
static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset)
{
struct xe_guc_ct *ct = &ads_to_guc(ads)->ct;
u32 action[] = {
XE_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE,
policy_offset
};
return xe_guc_ct_send(ct, action, ARRAY_SIZE(action), 0, 0);
}
/**
* xe_guc_ads_scheduler_policy_toggle_reset - Toggle reset policy
* @ads: Additional data structures object
*
* This function update the GuC's engine reset policy based on wedged.mode.
*
* Return: 0 on success, and negative error code otherwise.
*/
int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads)
{
struct xe_device *xe = ads_to_xe(ads);
struct xe_gt *gt = ads_to_gt(ads);
struct xe_tile *tile = gt_to_tile(gt);
struct guc_policies *policies;
struct xe_bo *bo;
int ret = 0;
policies = kmalloc(sizeof(*policies), GFP_KERNEL);
if (!policies)
return -ENOMEM;
policies->dpc_promote_time = ads_blob_read(ads, policies.dpc_promote_time);
policies->max_num_work_items = ads_blob_read(ads, policies.max_num_work_items);
policies->is_valid = 1;
if (xe->wedged.mode == 2)
policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET;
else
policies->global_flags &= ~GLOBAL_POLICY_DISABLE_ENGINE_RESET;
bo = xe_managed_bo_create_from_data(xe, tile, policies, sizeof(struct guc_policies),
XE_BO_FLAG_VRAM_IF_DGFX(tile) |
XE_BO_FLAG_GGTT);
if (IS_ERR(bo)) {
ret = PTR_ERR(bo);
goto out;
}
ret = guc_ads_action_update_policies(ads, xe_bo_ggtt_addr(bo));
out:
kfree(policies);
return ret;
}
|