summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/gt/intel_sseu.c
blob: 367fd44b81c8515f118379c3924dec257bb9e0a4 (plain)
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
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2019 Intel Corporation
 */

#include "i915_drv.h"
#include "intel_lrc_reg.h"
#include "intel_sseu.h"

void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
			 u8 max_subslices, u8 max_eus_per_subslice)
{
	sseu->max_slices = max_slices;
	sseu->max_subslices = max_subslices;
	sseu->max_eus_per_subslice = max_eus_per_subslice;

	sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
	GEM_BUG_ON(sseu->ss_stride > GEN_MAX_SUBSLICE_STRIDE);
	sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
	GEM_BUG_ON(sseu->eu_stride > GEN_MAX_EU_STRIDE);
}

unsigned int
intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
{
	unsigned int i, total = 0;

	for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
		total += hweight8(sseu->subslice_mask[i]);

	return total;
}

u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
{
	int i, offset = slice * sseu->ss_stride;
	u32 mask = 0;

	GEM_BUG_ON(slice >= sseu->max_slices);

	for (i = 0; i < sseu->ss_stride; i++)
		mask |= (u32)sseu->subslice_mask[offset + i] <<
			i * BITS_PER_BYTE;

	return mask;
}

void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
			      u32 ss_mask)
{
	int offset = slice * sseu->ss_stride;

	memcpy(&sseu->subslice_mask[offset], &ss_mask, sseu->ss_stride);
}

unsigned int
intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
{
	return hweight32(intel_sseu_get_subslices(sseu, slice));
}

static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
		       int subslice)
{
	int slice_stride = sseu->max_subslices * sseu->eu_stride;

	return slice * slice_stride + subslice * sseu->eu_stride;
}

static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
			int subslice)
{
	int i, offset = sseu_eu_idx(sseu, slice, subslice);
	u16 eu_mask = 0;

	for (i = 0; i < sseu->eu_stride; i++)
		eu_mask |=
			((u16)sseu->eu_mask[offset + i]) << (i * BITS_PER_BYTE);

	return eu_mask;
}

static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
			 u16 eu_mask)
{
	int i, offset = sseu_eu_idx(sseu, slice, subslice);

	for (i = 0; i < sseu->eu_stride; i++)
		sseu->eu_mask[offset + i] =
			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
}

static u16 compute_eu_total(const struct sseu_dev_info *sseu)
{
	u16 i, total = 0;

	for (i = 0; i < ARRAY_SIZE(sseu->eu_mask); i++)
		total += hweight8(sseu->eu_mask[i]);

	return total;
}

static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
				    u8 s_en, u32 ss_en, u16 eu_en)
{
	int s, ss;

	/* ss_en represents entire subslice mask across all slices */
	GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
		   sizeof(ss_en) * BITS_PER_BYTE);

	for (s = 0; s < sseu->max_slices; s++) {
		if ((s_en & BIT(s)) == 0)
			continue;

		sseu->slice_mask |= BIT(s);

		intel_sseu_set_subslices(sseu, s, ss_en);

		for (ss = 0; ss < sseu->max_subslices; ss++)
			if (intel_sseu_has_subslice(sseu, s, ss))
				sseu_set_eus(sseu, s, ss, eu_en);
	}
	sseu->eu_per_subslice = hweight16(eu_en);
	sseu->eu_total = compute_eu_total(sseu);
}

static void gen12_sseu_info_init(struct intel_gt *gt)
{
	struct sseu_dev_info *sseu = &gt->info.sseu;
	struct intel_uncore *uncore = gt->uncore;
	u32 dss_en;
	u16 eu_en = 0;
	u8 eu_en_fuse;
	u8 s_en;
	int eu;

	/*
	 * Gen12 has Dual-Subslices, which behave similarly to 2 gen11 SS.
	 * Instead of splitting these, provide userspace with an array
	 * of DSS to more closely represent the hardware resource.
	 */
	intel_sseu_set_info(sseu, 1, 6, 16);

	s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
		GEN11_GT_S_ENA_MASK;

	dss_en = intel_uncore_read(uncore, GEN12_GT_DSS_ENABLE);

	/* one bit per pair of EUs */
	eu_en_fuse = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
		       GEN11_EU_DIS_MASK);
	for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
		if (eu_en_fuse & BIT(eu))
			eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);

	gen11_compute_sseu_info(sseu, s_en, dss_en, eu_en);

	/* TGL only supports slice-level power gating */
	sseu->has_slice_pg = 1;
}

static void gen11_sseu_info_init(struct intel_gt *gt)
{
	struct sseu_dev_info *sseu = &gt->info.sseu;
	struct intel_uncore *uncore = gt->uncore;
	u32 ss_en;
	u8 eu_en;
	u8 s_en;

	if (IS_JSL_EHL(gt->i915))
		intel_sseu_set_info(sseu, 1, 4, 8);
	else
		intel_sseu_set_info(sseu, 1, 8, 8);

	s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
		GEN11_GT_S_ENA_MASK;
	ss_en = ~intel_uncore_read(uncore, GEN11_GT_SUBSLICE_DISABLE);

	eu_en = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
		  GEN11_EU_DIS_MASK);

	gen11_compute_sseu_info(sseu, s_en, ss_en, eu_en);

	/* ICL has no power gating restrictions. */
	sseu->has_slice_pg = 1;
	sseu->has_subslice_pg = 1;
	sseu->has_eu_pg = 1;
}

static void gen10_sseu_info_init(struct intel_gt *gt)
{
	struct intel_uncore *uncore = gt->uncore;
	struct sseu_dev_info *sseu = &gt->info.sseu;
	const u32 fuse2 = intel_uncore_read(uncore, GEN8_FUSE2);
	const int eu_mask = 0xff;
	u32 subslice_mask, eu_en;
	int s, ss;

	intel_sseu_set_info(sseu, 6, 4, 8);

	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
		GEN10_F2_S_ENA_SHIFT;

	/* Slice0 */
	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE0);
	for (ss = 0; ss < sseu->max_subslices; ss++)
		sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) & eu_mask);
	/* Slice1 */
	sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE1);
	sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
	/* Slice2 */
	sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
	sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
	/* Slice3 */
	sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
	eu_en = ~intel_uncore_read(uncore, GEN8_EU_DISABLE2);
	sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
	/* Slice4 */
	sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
	sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
	/* Slice5 */
	sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
	eu_en = ~intel_uncore_read(uncore, GEN10_EU_DISABLE3);
	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);

	subslice_mask = (1 << 4) - 1;
	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
			   GEN10_F2_SS_DIS_SHIFT);

	for (s = 0; s < sseu->max_slices; s++) {
		u32 subslice_mask_with_eus = subslice_mask;

		for (ss = 0; ss < sseu->max_subslices; ss++) {
			if (sseu_get_eus(sseu, s, ss) == 0)
				subslice_mask_with_eus &= ~BIT(ss);
		}

		/*
		 * Slice0 can have up to 3 subslices, but there are only 2 in
		 * slice1/2.
		 */
		intel_sseu_set_subslices(sseu, s, s == 0 ?
					 subslice_mask_with_eus :
					 subslice_mask_with_eus & 0x3);
	}

	sseu->eu_total = compute_eu_total(sseu);

	/*
	 * CNL is expected to always have a uniform distribution
	 * of EU across subslices with the exception that any one
	 * EU in any one subslice may be fused off for die
	 * recovery.
	 */
	sseu->eu_per_subslice =
		intel_sseu_subslice_total(sseu) ?
		DIV_ROUND_UP(sseu->eu_total, intel_sseu_subslice_total(sseu)) :
		0;

	/* No restrictions on Power Gating */
	sseu->has_slice_pg = 1;
	sseu->has_subslice_pg = 1;
	sseu->has_eu_pg = 1;
}

static void cherryview_sseu_info_init(struct intel_gt *gt)
{
	struct sseu_dev_info *sseu = &gt->info.sseu;
	u32 fuse;
	u8 subslice_mask = 0;

	fuse = intel_uncore_read(gt->uncore, CHV_FUSE_GT);

	sseu->slice_mask = BIT(0);
	intel_sseu_set_info(sseu, 1, 2, 8);

	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
		u8 disabled_mask =
			((fuse & CHV_FGT_EU_DIS_SS0_R0_MASK) >>
			 CHV_FGT_EU_DIS_SS0_R0_SHIFT) |
			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);

		subslice_mask |= BIT(0);
		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
	}

	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
		u8 disabled_mask =
			((fuse & CHV_FGT_EU_DIS_SS1_R0_MASK) >>
			 CHV_FGT_EU_DIS_SS1_R0_SHIFT) |
			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);

		subslice_mask |= BIT(1);
		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
	}

	intel_sseu_set_subslices(sseu, 0, subslice_mask);

	sseu->eu_total = compute_eu_total(sseu);

	/*
	 * CHV expected to always have a uniform distribution of EU
	 * across subslices.
	 */
	sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
		sseu->eu_total /
		intel_sseu_subslice_total(sseu) :
		0;
	/*
	 * CHV supports subslice power gating on devices with more than
	 * one subslice, and supports EU power gating on devices with
	 * more than one EU pair per subslice.
	 */
	sseu->has_slice_pg = 0;
	sseu->has_subslice_pg = intel_sseu_subslice_total(sseu) > 1;
	sseu->has_eu_pg = (sseu->eu_per_subslice > 2);
}

static void gen9_sseu_info_init(struct intel_gt *gt)
{
	struct drm_i915_private *i915 = gt->i915;
	struct intel_device_info *info = mkwrite_device_info(i915);
	struct sseu_dev_info *sseu = &gt->info.sseu;
	struct intel_uncore *uncore = gt->uncore;
	u32 fuse2, eu_disable, subslice_mask;
	const u8 eu_mask = 0xff;
	int s, ss;

	fuse2 = intel_uncore_read(uncore, GEN8_FUSE2);
	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;

	/* BXT has a single slice and at most 3 subslices. */
	intel_sseu_set_info(sseu, IS_GEN9_LP(i915) ? 1 : 3,
			    IS_GEN9_LP(i915) ? 3 : 4, 8);

	/*
	 * The subslice disable field is global, i.e. it applies
	 * to each of the enabled slices.
	 */
	subslice_mask = (1 << sseu->max_subslices) - 1;
	subslice_mask &= ~((fuse2 & GEN9_F2_SS_DIS_MASK) >>
			   GEN9_F2_SS_DIS_SHIFT);

	/*
	 * Iterate through enabled slices and subslices to
	 * count the total enabled EU.
	 */
	for (s = 0; s < sseu->max_slices; s++) {
		if (!(sseu->slice_mask & BIT(s)))
			/* skip disabled slice */
			continue;

		intel_sseu_set_subslices(sseu, s, subslice_mask);

		eu_disable = intel_uncore_read(uncore, GEN9_EU_DISABLE(s));
		for (ss = 0; ss < sseu->max_subslices; ss++) {
			int eu_per_ss;
			u8 eu_disabled_mask;

			if (!intel_sseu_has_subslice(sseu, s, ss))
				/* skip disabled subslice */
				continue;

			eu_disabled_mask = (eu_disable >> (ss * 8)) & eu_mask;

			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);

			eu_per_ss = sseu->max_eus_per_subslice -
				hweight8(eu_disabled_mask);

			/*
			 * Record which subslice(s) has(have) 7 EUs. we
			 * can tune the hash used to spread work among
			 * subslices if they are unbalanced.
			 */
			if (eu_per_ss == 7)
				sseu->subslice_7eu[s] |= BIT(ss);
		}
	}

	sseu->eu_total = compute_eu_total(sseu);

	/*
	 * SKL is expected to always have a uniform distribution
	 * of EU across subslices with the exception that any one
	 * EU in any one subslice may be fused off for die
	 * recovery. BXT is expected to be perfectly uniform in EU
	 * distribution.
	 */
	sseu->eu_per_subslice =
		intel_sseu_subslice_total(sseu) ?
		DIV_ROUND_UP(sseu->eu_total, intel_sseu_subslice_total(sseu)) :
		0;

	/*
	 * SKL+ supports slice power gating on devices with more than
	 * one slice, and supports EU power gating on devices with
	 * more than one EU pair per subslice. BXT+ supports subslice
	 * power gating on devices with more than one subslice, and
	 * supports EU power gating on devices with more than one EU
	 * pair per subslice.
	 */
	sseu->has_slice_pg =
		!IS_GEN9_LP(i915) && hweight8(sseu->slice_mask) > 1;
	sseu->has_subslice_pg =
		IS_GEN9_LP(i915) && intel_sseu_subslice_total(sseu) > 1;
	sseu->has_eu_pg = sseu->eu_per_subslice > 2;

	if (IS_GEN9_LP(i915)) {
#define IS_SS_DISABLED(ss)	(!(sseu->subslice_mask[0] & BIT(ss)))
		info->has_pooled_eu = hweight8(sseu->subslice_mask[0]) == 3;

		sseu->min_eu_in_pool = 0;
		if (info->has_pooled_eu) {
			if (IS_SS_DISABLED(2) || IS_SS_DISABLED(0))
				sseu->min_eu_in_pool = 3;
			else if (IS_SS_DISABLED(1))
				sseu->min_eu_in_pool = 6;
			else
				sseu->min_eu_in_pool = 9;
		}
#undef IS_SS_DISABLED
	}
}

static void bdw_sseu_info_init(struct intel_gt *gt)
{
	struct sseu_dev_info *sseu = &gt->info.sseu;
	struct intel_uncore *uncore = gt->uncore;
	int s, ss;
	u32 fuse2, subslice_mask, eu_disable[3]; /* s_max */
	u32 eu_disable0, eu_disable1, eu_disable2;

	fuse2 = intel_uncore_read(uncore, GEN8_FUSE2);
	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
	intel_sseu_set_info(sseu, 3, 3, 8);

	/*
	 * The subslice disable field is global, i.e. it applies
	 * to each of the enabled slices.
	 */
	subslice_mask = GENMASK(sseu->max_subslices - 1, 0);
	subslice_mask &= ~((fuse2 & GEN8_F2_SS_DIS_MASK) >>
			   GEN8_F2_SS_DIS_SHIFT);
	eu_disable0 = intel_uncore_read(uncore, GEN8_EU_DISABLE0);
	eu_disable1 = intel_uncore_read(uncore, GEN8_EU_DISABLE1);
	eu_disable2 = intel_uncore_read(uncore, GEN8_EU_DISABLE2);
	eu_disable[0] = eu_disable0 & GEN8_EU_DIS0_S0_MASK;
	eu_disable[1] = (eu_disable0 >> GEN8_EU_DIS0_S1_SHIFT) |
		((eu_disable1 & GEN8_EU_DIS1_S1_MASK) <<
		 (32 - GEN8_EU_DIS0_S1_SHIFT));
	eu_disable[2] = (eu_disable1 >> GEN8_EU_DIS1_S2_SHIFT) |
		((eu_disable2 & GEN8_EU_DIS2_S2_MASK) <<
		 (32 - GEN8_EU_DIS1_S2_SHIFT));

	/*
	 * Iterate through enabled slices and subslices to
	 * count the total enabled EU.
	 */
	for (s = 0; s < sseu->max_slices; s++) {
		if (!(sseu->slice_mask & BIT(s)))
			/* skip disabled slice */
			continue;

		intel_sseu_set_subslices(sseu, s, subslice_mask);

		for (ss = 0; ss < sseu->max_subslices; ss++) {
			u8 eu_disabled_mask;
			u32 n_disabled;

			if (!intel_sseu_has_subslice(sseu, s, ss))
				/* skip disabled subslice */
				continue;

			eu_disabled_mask =
				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);

			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);

			n_disabled = hweight8(eu_disabled_mask);

			/*
			 * Record which subslices have 7 EUs.
			 */
			if (sseu->max_eus_per_subslice - n_disabled == 7)
				sseu->subslice_7eu[s] |= 1 << ss;
		}
	}

	sseu->eu_total = compute_eu_total(sseu);

	/*
	 * BDW is expected to always have a uniform distribution of EU across
	 * subslices with the exception that any one EU in any one subslice may
	 * be fused off for die recovery.
	 */
	sseu->eu_per_subslice =
		intel_sseu_subslice_total(sseu) ?
		DIV_ROUND_UP(sseu->eu_total, intel_sseu_subslice_total(sseu)) :
		0;

	/*
	 * BDW supports slice power gating on devices with more than
	 * one slice.
	 */
	sseu->has_slice_pg = hweight8(sseu->slice_mask) > 1;
	sseu->has_subslice_pg = 0;
	sseu->has_eu_pg = 0;
}

static void hsw_sseu_info_init(struct intel_gt *gt)
{
	struct drm_i915_private *i915 = gt->i915;
	struct sseu_dev_info *sseu = &gt->info.sseu;
	u32 fuse1;
	u8 subslice_mask = 0;
	int s, ss;

	/*
	 * There isn't a register to tell us how many slices/subslices. We
	 * work off the PCI-ids here.
	 */
	switch (INTEL_INFO(i915)->gt) {
	default:
		MISSING_CASE(INTEL_INFO(i915)->gt);
		fallthrough;
	case 1:
		sseu->slice_mask = BIT(0);
		subslice_mask = BIT(0);
		break;
	case 2:
		sseu->slice_mask = BIT(0);
		subslice_mask = BIT(0) | BIT(1);
		break;
	case 3:
		sseu->slice_mask = BIT(0) | BIT(1);
		subslice_mask = BIT(0) | BIT(1);
		break;
	}

	fuse1 = intel_uncore_read(gt->uncore, HSW_PAVP_FUSE1);
	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
	default:
		MISSING_CASE((fuse1 & HSW_F1_EU_DIS_MASK) >>
			     HSW_F1_EU_DIS_SHIFT);
		fallthrough;
	case HSW_F1_EU_DIS_10EUS:
		sseu->eu_per_subslice = 10;
		break;
	case HSW_F1_EU_DIS_8EUS:
		sseu->eu_per_subslice = 8;
		break;
	case HSW_F1_EU_DIS_6EUS:
		sseu->eu_per_subslice = 6;
		break;
	}

	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
			    hweight8(subslice_mask),
			    sseu->eu_per_subslice);

	for (s = 0; s < sseu->max_slices; s++) {
		intel_sseu_set_subslices(sseu, s, subslice_mask);

		for (ss = 0; ss < sseu->max_subslices; ss++) {
			sseu_set_eus(sseu, s, ss,
				     (1UL << sseu->eu_per_subslice) - 1);
		}
	}

	sseu->eu_total = compute_eu_total(sseu);

	/* No powergating for you. */
	sseu->has_slice_pg = 0;
	sseu->has_subslice_pg = 0;
	sseu->has_eu_pg = 0;
}

void intel_sseu_info_init(struct intel_gt *gt)
{
	struct drm_i915_private *i915 = gt->i915;

	if (IS_HASWELL(i915))
		hsw_sseu_info_init(gt);
	else if (IS_CHERRYVIEW(i915))
		cherryview_sseu_info_init(gt);
	else if (IS_BROADWELL(i915))
		bdw_sseu_info_init(gt);
	else if (GRAPHICS_VER(i915) == 9)
		gen9_sseu_info_init(gt);
	else if (GRAPHICS_VER(i915) == 10)
		gen10_sseu_info_init(gt);
	else if (GRAPHICS_VER(i915) == 11)
		gen11_sseu_info_init(gt);
	else if (GRAPHICS_VER(i915) >= 12)
		gen12_sseu_info_init(gt);
}

u32 intel_sseu_make_rpcs(struct intel_gt *gt,
			 const struct intel_sseu *req_sseu)
{
	struct drm_i915_private *i915 = gt->i915;
	const struct sseu_dev_info *sseu = &gt->info.sseu;
	bool subslice_pg = sseu->has_subslice_pg;
	u8 slices, subslices;
	u32 rpcs = 0;

	/*
	 * No explicit RPCS request is needed to ensure full
	 * slice/subslice/EU enablement prior to Gen9.
	 */
	if (GRAPHICS_VER(i915) < 9)
		return 0;

	/*
	 * If i915/perf is active, we want a stable powergating configuration
	 * on the system. Use the configuration pinned by i915/perf.
	 */
	if (i915->perf.exclusive_stream)
		req_sseu = &i915->perf.sseu;

	slices = hweight8(req_sseu->slice_mask);
	subslices = hweight8(req_sseu->subslice_mask);

	/*
	 * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
	 * wide and Icelake has up to eight subslices, specfial programming is
	 * needed in order to correctly enable all subslices.
	 *
	 * According to documentation software must consider the configuration
	 * as 2x4x8 and hardware will translate this to 1x8x8.
	 *
	 * Furthemore, even though SScount is three bits, maximum documented
	 * value for it is four. From this some rules/restrictions follow:
	 *
	 * 1.
	 * If enabled subslice count is greater than four, two whole slices must
	 * be enabled instead.
	 *
	 * 2.
	 * When more than one slice is enabled, hardware ignores the subslice
	 * count altogether.
	 *
	 * From these restrictions it follows that it is not possible to enable
	 * a count of subslices between the SScount maximum of four restriction,
	 * and the maximum available number on a particular SKU. Either all
	 * subslices are enabled, or a count between one and four on the first
	 * slice.
	 */
	if (GRAPHICS_VER(i915) == 11 &&
	    slices == 1 &&
	    subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
		GEM_BUG_ON(subslices & 1);

		subslice_pg = false;
		slices *= 2;
	}

	/*
	 * Starting in Gen9, render power gating can leave
	 * slice/subslice/EU in a partially enabled state. We
	 * must make an explicit request through RPCS for full
	 * enablement.
	 */
	if (sseu->has_slice_pg) {
		u32 mask, val = slices;

		if (GRAPHICS_VER(i915) >= 11) {
			mask = GEN11_RPCS_S_CNT_MASK;
			val <<= GEN11_RPCS_S_CNT_SHIFT;
		} else {
			mask = GEN8_RPCS_S_CNT_MASK;
			val <<= GEN8_RPCS_S_CNT_SHIFT;
		}

		GEM_BUG_ON(val & ~mask);
		val &= mask;

		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_S_CNT_ENABLE | val;
	}

	if (subslice_pg) {
		u32 val = subslices;

		val <<= GEN8_RPCS_SS_CNT_SHIFT;

		GEM_BUG_ON(val & ~GEN8_RPCS_SS_CNT_MASK);
		val &= GEN8_RPCS_SS_CNT_MASK;

		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
	}

	if (sseu->has_eu_pg) {
		u32 val;

		val = req_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
		val &= GEN8_RPCS_EU_MIN_MASK;

		rpcs |= val;

		val = req_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
		val &= GEN8_RPCS_EU_MAX_MASK;

		rpcs |= val;

		rpcs |= GEN8_RPCS_ENABLE;
	}

	return rpcs;
}

void intel_sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
{
	int s;

	drm_printf(p, "slice total: %u, mask=%04x\n",
		   hweight8(sseu->slice_mask), sseu->slice_mask);
	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
	for (s = 0; s < sseu->max_slices; s++) {
		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
			   s, intel_sseu_subslices_per_slice(sseu, s),
			   intel_sseu_get_subslices(sseu, s));
	}
	drm_printf(p, "EU total: %u\n", sseu->eu_total);
	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
	drm_printf(p, "has slice power gating: %s\n",
		   yesno(sseu->has_slice_pg));
	drm_printf(p, "has subslice power gating: %s\n",
		   yesno(sseu->has_subslice_pg));
	drm_printf(p, "has EU power gating: %s\n", yesno(sseu->has_eu_pg));
}

void intel_sseu_print_topology(const struct sseu_dev_info *sseu,
			       struct drm_printer *p)
{
	int s, ss;

	if (sseu->max_slices == 0) {
		drm_printf(p, "Unavailable\n");
		return;
	}

	for (s = 0; s < sseu->max_slices; s++) {
		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
			   s, intel_sseu_subslices_per_slice(sseu, s),
			   intel_sseu_get_subslices(sseu, s));

		for (ss = 0; ss < sseu->max_subslices; ss++) {
			u16 enabled_eus = sseu_get_eus(sseu, s, ss);

			drm_printf(p, "\tsubslice%d: %u EUs (0x%hx)\n",
				   ss, hweight16(enabled_eus), enabled_eus);
		}
	}
}