summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/intel_device_info.c
blob: 0fd13df424cf19719958b5de465cebec849895c3 (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
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
/*
 * 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 "intel_device_info.h"
#include "i915_drv.h"

#define PLATFORM_NAME(x) [INTEL_##x] = #x
static const char * const platform_names[] = {
	PLATFORM_NAME(I830),
	PLATFORM_NAME(I845G),
	PLATFORM_NAME(I85X),
	PLATFORM_NAME(I865G),
	PLATFORM_NAME(I915G),
	PLATFORM_NAME(I915GM),
	PLATFORM_NAME(I945G),
	PLATFORM_NAME(I945GM),
	PLATFORM_NAME(G33),
	PLATFORM_NAME(PINEVIEW),
	PLATFORM_NAME(I965G),
	PLATFORM_NAME(I965GM),
	PLATFORM_NAME(G45),
	PLATFORM_NAME(GM45),
	PLATFORM_NAME(IRONLAKE),
	PLATFORM_NAME(SANDYBRIDGE),
	PLATFORM_NAME(IVYBRIDGE),
	PLATFORM_NAME(VALLEYVIEW),
	PLATFORM_NAME(HASWELL),
	PLATFORM_NAME(BROADWELL),
	PLATFORM_NAME(CHERRYVIEW),
	PLATFORM_NAME(SKYLAKE),
	PLATFORM_NAME(BROXTON),
	PLATFORM_NAME(KABYLAKE),
	PLATFORM_NAME(GEMINILAKE),
	PLATFORM_NAME(COFFEELAKE),
	PLATFORM_NAME(CANNONLAKE),
	PLATFORM_NAME(ICELAKE),
};
#undef PLATFORM_NAME

const char *intel_platform_name(enum intel_platform platform)
{
	BUILD_BUG_ON(ARRAY_SIZE(platform_names) != INTEL_MAX_PLATFORMS);

	if (WARN_ON_ONCE(platform >= ARRAY_SIZE(platform_names) ||
			 platform_names[platform] == NULL))
		return "<unknown>";

	return platform_names[platform];
}

void intel_device_info_dump_flags(const struct intel_device_info *info,
				  struct drm_printer *p)
{
#define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->name));
	DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG);
#undef PRINT_FLAG
}

static void 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", sseu_subslice_total(sseu));
	for (s = 0; s < sseu->max_slices; s++) {
		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
			   s, hweight8(sseu->subslice_mask[s]),
			   sseu->subslice_mask[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_device_info_dump_runtime(const struct intel_device_info *info,
				    struct drm_printer *p)
{
	sseu_dump(&info->sseu, p);

	drm_printf(p, "CS timestamp frequency: %u kHz\n",
		   info->cs_timestamp_frequency_khz);
}

void intel_device_info_dump(const struct intel_device_info *info,
			    struct drm_printer *p)
{
	struct drm_i915_private *dev_priv =
		container_of(info, struct drm_i915_private, info);

	drm_printf(p, "pciid=0x%04x rev=0x%02x platform=%s gen=%i\n",
		   INTEL_DEVID(dev_priv),
		   INTEL_REVID(dev_priv),
		   intel_platform_name(info->platform),
		   info->gen);

	intel_device_info_dump_flags(info, p);
}

void intel_device_info_dump_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%hhx):\n",
			   s, hweight8(sseu->subslice_mask[s]),
			   sseu->subslice_mask[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);
		}
	}
}

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_sseu_info_init(struct drm_i915_private *dev_priv)
{
	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
	u8 s_en;
	u32 ss_en, ss_en_mask;
	u8 eu_en;
	int s;

	sseu->max_slices = 1;
	sseu->max_subslices = 8;
	sseu->max_eus_per_subslice = 8;

	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
	ss_en_mask = BIT(sseu->max_subslices) - 1;
	eu_en = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);

	for (s = 0; s < sseu->max_slices; s++) {
		if (s_en & BIT(s)) {
			int ss_idx = sseu->max_subslices * s;
			int ss;

			sseu->slice_mask |= BIT(s);
			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
			for (ss = 0; ss < sseu->max_subslices; ss++) {
				if (sseu->subslice_mask[s] & BIT(ss))
					sseu_set_eus(sseu, s, ss, eu_en);
			}
		}
	}
	sseu->eu_per_subslice = hweight8(eu_en);
	sseu->eu_total = compute_eu_total(sseu);

	/* 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 drm_i915_private *dev_priv)
{
	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
	const u32 fuse2 = I915_READ(GEN8_FUSE2);
	int s, ss;
	const int eu_mask = 0xff;
	u32 subslice_mask, eu_en;

	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
			    GEN10_F2_S_ENA_SHIFT;
	sseu->max_slices = 6;
	sseu->max_subslices = 4;
	sseu->max_eus_per_subslice = 8;

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

	/*
	 * Slice0 can have up to 3 subslices, but there are only 2 in
	 * slice1/2.
	 */
	sseu->subslice_mask[0] = subslice_mask;
	for (s = 1; s < sseu->max_slices; s++)
		sseu->subslice_mask[s] = subslice_mask & 0x3;

	/* Slice0 */
	eu_en = ~I915_READ(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 = ~I915_READ(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 = ~I915_READ(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 = ~I915_READ(GEN10_EU_DISABLE3);
	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);

	/* Do a second pass where we mark the subslices disabled if all their
	 * eus are off.
	 */
	for (s = 0; s < sseu->max_slices; s++) {
		for (ss = 0; ss < sseu->max_subslices; ss++) {
			if (sseu_get_eus(sseu, s, ss) == 0)
				sseu->subslice_mask[s] &= ~BIT(ss);
		}
	}

	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 = sseu_subslice_total(sseu) ?
				DIV_ROUND_UP(sseu->eu_total,
					     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 drm_i915_private *dev_priv)
{
	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
	u32 fuse;

	fuse = I915_READ(CHV_FUSE_GT);

	sseu->slice_mask = BIT(0);
	sseu->max_slices = 1;
	sseu->max_subslices = 2;
	sseu->max_eus_per_subslice = 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);

		sseu->subslice_mask[0] |= 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);

		sseu->subslice_mask[0] |= BIT(1);
		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
	}

	sseu->eu_total = compute_eu_total(sseu);

	/*
	 * CHV expected to always have a uniform distribution of EU
	 * across subslices.
	*/
	sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
				sseu->eu_total / 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 = sseu_subslice_total(sseu) > 1;
	sseu->has_eu_pg = (sseu->eu_per_subslice > 2);
}

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

	fuse2 = I915_READ(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. */
	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
	sseu->max_eus_per_subslice = 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;

		sseu->subslice_mask[s] = subslice_mask;

		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
		for (ss = 0; ss < sseu->max_subslices; ss++) {
			int eu_per_ss;
			u8 eu_disabled_mask;

			if (!(sseu->subslice_mask[s] & BIT(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 = sseu_subslice_total(sseu) ?
				DIV_ROUND_UP(sseu->eu_total,
					     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(dev_priv) && hweight8(sseu->slice_mask) > 1;
	sseu->has_subslice_pg =
		IS_GEN9_LP(dev_priv) && sseu_subslice_total(sseu) > 1;
	sseu->has_eu_pg = sseu->eu_per_subslice > 2;

	if (IS_GEN9_LP(dev_priv)) {
#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 broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
{
	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
	int s, ss;
	u32 fuse2, subslice_mask, eu_disable[3]; /* s_max */

	fuse2 = I915_READ(GEN8_FUSE2);
	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
	sseu->max_slices = 3;
	sseu->max_subslices = 3;
	sseu->max_eus_per_subslice = 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_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK;
	eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) |
			((I915_READ(GEN8_EU_DISABLE1) & GEN8_EU_DIS1_S1_MASK) <<
			 (32 - GEN8_EU_DIS0_S1_SHIFT));
	eu_disable[2] = (I915_READ(GEN8_EU_DISABLE1) >> GEN8_EU_DIS1_S2_SHIFT) |
			((I915_READ(GEN8_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;

		sseu->subslice_mask[s] = subslice_mask;

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

			if (!(sseu->subslice_mask[ss] & BIT(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 = sseu_subslice_total(sseu) ?
				DIV_ROUND_UP(sseu->eu_total,
					     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 haswell_sseu_info_init(struct drm_i915_private *dev_priv)
{
	struct intel_device_info *info = mkwrite_device_info(dev_priv);
	struct sseu_dev_info *sseu = &info->sseu;
	u32 fuse1;
	int s, ss;

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

	sseu->max_slices = hweight8(sseu->slice_mask);
	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);

	fuse1 = I915_READ(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);
		/* fall through */
	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;
	}
	sseu->max_eus_per_subslice = sseu->eu_per_subslice;

	for (s = 0; s < sseu->max_slices; s++) {
		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;
}

static u32 read_reference_ts_freq(struct drm_i915_private *dev_priv)
{
	u32 ts_override = I915_READ(GEN9_TIMESTAMP_OVERRIDE);
	u32 base_freq, frac_freq;

	base_freq = ((ts_override & GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK) >>
		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_SHIFT) + 1;
	base_freq *= 1000;

	frac_freq = ((ts_override &
		      GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK) >>
		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_SHIFT);
	frac_freq = 1000 / (frac_freq + 1);

	return base_freq + frac_freq;
}

static u32 gen10_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
					u32 rpm_config_reg)
{
	u32 f19_2_mhz = 19200;
	u32 f24_mhz = 24000;
	u32 crystal_clock = (rpm_config_reg &
			     GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
			    GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;

	switch (crystal_clock) {
	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
		return f19_2_mhz;
	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
		return f24_mhz;
	default:
		MISSING_CASE(crystal_clock);
		return 0;
	}
}

static u32 gen11_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
					u32 rpm_config_reg)
{
	u32 f19_2_mhz = 19200;
	u32 f24_mhz = 24000;
	u32 f25_mhz = 25000;
	u32 f38_4_mhz = 38400;
	u32 crystal_clock = (rpm_config_reg &
			     GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
			    GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;

	switch (crystal_clock) {
	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
		return f24_mhz;
	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
		return f19_2_mhz;
	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ:
		return f38_4_mhz;
	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ:
		return f25_mhz;
	default:
		MISSING_CASE(crystal_clock);
		return 0;
	}
}

static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
{
	u32 f12_5_mhz = 12500;
	u32 f19_2_mhz = 19200;
	u32 f24_mhz = 24000;

	if (INTEL_GEN(dev_priv) <= 4) {
		/* PRMs say:
		 *
		 *     "The value in this register increments once every 16
		 *      hclks." (through the “Clocking Configuration”
		 *      (“CLKCFG”) MCHBAR register)
		 */
		return dev_priv->rawclk_freq / 16;
	} else if (INTEL_GEN(dev_priv) <= 8) {
		/* PRMs say:
		 *
		 *     "The PCU TSC counts 10ns increments; this timestamp
		 *      reflects bits 38:3 of the TSC (i.e. 80ns granularity,
		 *      rolling over every 1.5 hours).
		 */
		return f12_5_mhz;
	} else if (INTEL_GEN(dev_priv) <= 9) {
		u32 ctc_reg = I915_READ(CTC_MODE);
		u32 freq = 0;

		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
			freq = read_reference_ts_freq(dev_priv);
		} else {
			freq = IS_GEN9_LP(dev_priv) ? f19_2_mhz : f24_mhz;

			/* Now figure out how the command stream's timestamp
			 * register increments from this frequency (it might
			 * increment only every few clock cycle).
			 */
			freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >>
				      CTC_SHIFT_PARAMETER_SHIFT);
		}

		return freq;
	} else if (INTEL_GEN(dev_priv) <= 11) {
		u32 ctc_reg = I915_READ(CTC_MODE);
		u32 freq = 0;

		/* First figure out the reference frequency. There are 2 ways
		 * we can compute the frequency, either through the
		 * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE
		 * tells us which one we should use.
		 */
		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
			freq = read_reference_ts_freq(dev_priv);
		} else {
			u32 rpm_config_reg = I915_READ(RPM_CONFIG0);

			if (INTEL_GEN(dev_priv) <= 10)
				freq = gen10_get_crystal_clock_freq(dev_priv,
								rpm_config_reg);
			else
				freq = gen11_get_crystal_clock_freq(dev_priv,
								rpm_config_reg);

			/* Now figure out how the command stream's timestamp
			 * register increments from this frequency (it might
			 * increment only every few clock cycle).
			 */
			freq >>= 3 - ((rpm_config_reg &
				       GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
				      GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT);
		}

		return freq;
	}

	MISSING_CASE("Unknown gen, unable to read command streamer timestamp frequency\n");
	return 0;
}

/**
 * intel_device_info_runtime_init - initialize runtime info
 * @info: intel device info struct
 *
 * Determine various intel_device_info fields at runtime.
 *
 * Use it when either:
 *   - it's judged too laborious to fill n static structures with the limit
 *     when a simple if statement does the job,
 *   - run-time checks (eg read fuse/strap registers) are needed.
 *
 * This function needs to be called:
 *   - after the MMIO has been setup as we are reading registers,
 *   - after the PCH has been detected,
 *   - before the first usage of the fields it can tweak.
 */
void intel_device_info_runtime_init(struct intel_device_info *info)
{
	struct drm_i915_private *dev_priv =
		container_of(info, struct drm_i915_private, info);
	enum pipe pipe;

	if (INTEL_GEN(dev_priv) >= 10) {
		for_each_pipe(dev_priv, pipe)
			info->num_scalers[pipe] = 2;
	} else if (INTEL_GEN(dev_priv) == 9) {
		info->num_scalers[PIPE_A] = 2;
		info->num_scalers[PIPE_B] = 2;
		info->num_scalers[PIPE_C] = 1;
	}

	BUILD_BUG_ON(I915_NUM_ENGINES >
		     sizeof(intel_ring_mask_t) * BITS_PER_BYTE);

	/*
	 * Skylake and Broxton currently don't expose the topmost plane as its
	 * use is exclusive with the legacy cursor and we only want to expose
	 * one of those, not both. Until we can safely expose the topmost plane
	 * as a DRM_PLANE_TYPE_CURSOR with all the features exposed/supported,
	 * we don't expose the topmost plane at all to prevent ABI breakage
	 * down the line.
	 */
	if (IS_GEN10(dev_priv) || IS_GEMINILAKE(dev_priv))
		for_each_pipe(dev_priv, pipe)
			info->num_sprites[pipe] = 3;
	else if (IS_BROXTON(dev_priv)) {
		info->num_sprites[PIPE_A] = 2;
		info->num_sprites[PIPE_B] = 2;
		info->num_sprites[PIPE_C] = 1;
	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
		for_each_pipe(dev_priv, pipe)
			info->num_sprites[pipe] = 2;
	} else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) {
		for_each_pipe(dev_priv, pipe)
			info->num_sprites[pipe] = 1;
	}

	if (i915_modparams.disable_display) {
		DRM_INFO("Display disabled (module parameter)\n");
		info->num_pipes = 0;
	} else if (info->num_pipes > 0 &&
		   (IS_GEN7(dev_priv) || IS_GEN8(dev_priv)) &&
		   HAS_PCH_SPLIT(dev_priv)) {
		u32 fuse_strap = I915_READ(FUSE_STRAP);
		u32 sfuse_strap = I915_READ(SFUSE_STRAP);

		/*
		 * SFUSE_STRAP is supposed to have a bit signalling the display
		 * is fused off. Unfortunately it seems that, at least in
		 * certain cases, fused off display means that PCH display
		 * reads don't land anywhere. In that case, we read 0s.
		 *
		 * On CPT/PPT, we can detect this case as SFUSE_STRAP_FUSE_LOCK
		 * should be set when taking over after the firmware.
		 */
		if (fuse_strap & ILK_INTERNAL_DISPLAY_DISABLE ||
		    sfuse_strap & SFUSE_STRAP_DISPLAY_DISABLED ||
		    (HAS_PCH_CPT(dev_priv) &&
		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
			DRM_INFO("Display fused off, disabling\n");
			info->num_pipes = 0;
		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
			DRM_INFO("PipeC fused off\n");
			info->num_pipes -= 1;
		}
	} else if (info->num_pipes > 0 && IS_GEN9(dev_priv)) {
		u32 dfsm = I915_READ(SKL_DFSM);
		u8 disabled_mask = 0;
		bool invalid;
		int num_bits;

		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
			disabled_mask |= BIT(PIPE_A);
		if (dfsm & SKL_DFSM_PIPE_B_DISABLE)
			disabled_mask |= BIT(PIPE_B);
		if (dfsm & SKL_DFSM_PIPE_C_DISABLE)
			disabled_mask |= BIT(PIPE_C);

		num_bits = hweight8(disabled_mask);

		switch (disabled_mask) {
		case BIT(PIPE_A):
		case BIT(PIPE_B):
		case BIT(PIPE_A) | BIT(PIPE_B):
		case BIT(PIPE_A) | BIT(PIPE_C):
			invalid = true;
			break;
		default:
			invalid = false;
		}

		if (num_bits > info->num_pipes || invalid)
			DRM_ERROR("invalid pipe fuse configuration: 0x%x\n",
				  disabled_mask);
		else
			info->num_pipes -= num_bits;
	}

	/* Initialize slice/subslice/EU info */
	if (IS_HASWELL(dev_priv))
		haswell_sseu_info_init(dev_priv);
	else if (IS_CHERRYVIEW(dev_priv))
		cherryview_sseu_info_init(dev_priv);
	else if (IS_BROADWELL(dev_priv))
		broadwell_sseu_info_init(dev_priv);
	else if (INTEL_GEN(dev_priv) == 9)
		gen9_sseu_info_init(dev_priv);
	else if (INTEL_GEN(dev_priv) == 10)
		gen10_sseu_info_init(dev_priv);
	else if (INTEL_GEN(dev_priv) >= 11)
		gen11_sseu_info_init(dev_priv);

	/* Initialize command stream timestamp frequency */
	info->cs_timestamp_frequency_khz = read_timestamp_frequency(dev_priv);
}

void intel_driver_caps_print(const struct intel_driver_caps *caps,
			     struct drm_printer *p)
{
	drm_printf(p, "scheduler: %x\n", caps->scheduler);
}

/*
 * Determine which engines are fused off in our particular hardware. Since the
 * fuse register is in the blitter powerwell, we need forcewake to be ready at
 * this point (but later we need to prune the forcewake domains for engines that
 * are indeed fused off).
 */
void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
{
	struct intel_device_info *info = mkwrite_device_info(dev_priv);
	u8 vdbox_disable, vebox_disable;
	u32 media_fuse;
	int i;

	if (INTEL_GEN(dev_priv) < 11)
		return;

	media_fuse = I915_READ(GEN11_GT_VEBOX_VDBOX_DISABLE);

	vdbox_disable = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK;
	vebox_disable = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >>
			GEN11_GT_VEBOX_DISABLE_SHIFT;

	DRM_DEBUG_DRIVER("vdbox disable: %04x\n", vdbox_disable);
	for (i = 0; i < I915_MAX_VCS; i++) {
		if (!HAS_ENGINE(dev_priv, _VCS(i)))
			continue;

		if (!(BIT(i) & vdbox_disable))
			continue;

		info->ring_mask &= ~ENGINE_MASK(_VCS(i));
		DRM_DEBUG_DRIVER("vcs%u fused off\n", i);
	}

	DRM_DEBUG_DRIVER("vebox disable: %04x\n", vebox_disable);
	for (i = 0; i < I915_MAX_VECS; i++) {
		if (!HAS_ENGINE(dev_priv, _VECS(i)))
			continue;

		if (!(BIT(i) & vebox_disable))
			continue;

		info->ring_mask &= ~ENGINE_MASK(_VECS(i));
		DRM_DEBUG_DRIVER("vecs%u fused off\n", i);
	}
}