summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/gt/intel_rc6.c
blob: 9e303c29d6e35bd4233c0a1fd69a640bd0579a03 (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
/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright © 2019 Intel Corporation
 */

#include <linux/pm_runtime.h>

#include "i915_drv.h"
#include "intel_gt.h"
#include "intel_gt_pm.h"
#include "intel_rc6.h"
#include "intel_sideband.h"

/**
 * DOC: RC6
 *
 * RC6 is a special power stage which allows the GPU to enter an very
 * low-voltage mode when idle, using down to 0V while at this stage.  This
 * stage is entered automatically when the GPU is idle when RC6 support is
 * enabled, and as soon as new workload arises GPU wakes up automatically as
 * well.
 *
 * There are different RC6 modes available in Intel GPU, which differentiate
 * among each other with the latency required to enter and leave RC6 and
 * voltage consumed by the GPU in different states.
 *
 * The combination of the following flags define which states GPU is allowed
 * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
 * RC6pp is deepest RC6. Their support by hardware varies according to the
 * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
 * which brings the most power savings; deeper states save more power, but
 * require higher latency to switch to and wake up.
 */

static struct intel_gt *rc6_to_gt(struct intel_rc6 *rc6)
{
	return container_of(rc6, struct intel_gt, rc6);
}

static struct intel_uncore *rc6_to_uncore(struct intel_rc6 *rc)
{
	return rc6_to_gt(rc)->uncore;
}

static struct drm_i915_private *rc6_to_i915(struct intel_rc6 *rc)
{
	return rc6_to_gt(rc)->i915;
}

static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
{
	intel_uncore_write_fw(uncore, reg, val);
}

static void gen11_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	/* 2b: Program RC6 thresholds.*/
	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
	set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);

	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);

	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);

	set(uncore, GEN6_RC_SLEEP, 0);

	set(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */

	/*
	 * 2c: Program Coarse Power Gating Policies.
	 *
	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
	 * use instead is a more conservative estimate for the maximum time
	 * it takes us to service a CS interrupt and submit a new ELSP - that
	 * is the time which the GPU is idle waiting for the CPU to select the
	 * next request to execute. If the idle hysteresis is less than that
	 * interrupt service latency, the hardware will automatically gate
	 * the power well and we will then incur the wake up cost on top of
	 * the service latency. A similar guide from plane_state is that we
	 * do not want the enable hysteresis to less than the wakeup latency.
	 *
	 * igt/gem_exec_nop/sequential provides a rough estimate for the
	 * service latency, and puts it under 10us for Icelake, similar to
	 * Broadwell+, To be conservative, we want to factor in a context
	 * switch on top (due to ksoftirqd).
	 */
	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);

	/* 3a: Enable RC6 */
	rc6->ctl_enable =
		GEN6_RC_CTL_HW_ENABLE |
		GEN6_RC_CTL_RC6_ENABLE |
		GEN6_RC_CTL_EI_MODE(1);

	set(uncore, GEN9_PG_ENABLE,
	    GEN9_RENDER_PG_ENABLE |
	    GEN9_MEDIA_PG_ENABLE |
	    GEN11_MEDIA_SAMPLER_PG_ENABLE);
}

static void gen9_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	u32 rc6_mode;

	/* 2b: Program RC6 thresholds.*/
	if (INTEL_GEN(rc6_to_i915(rc6)) >= 10) {
		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
	} else if (IS_SKYLAKE(rc6_to_i915(rc6))) {
		/*
		 * WaRsDoubleRc6WrlWithCoarsePowerGating:skl Doubling WRL only
		 * when CPG is enabled
		 */
		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
	} else {
		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
	}

	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);

	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);

	set(uncore, GEN6_RC_SLEEP, 0);

	/*
	 * 2c: Program Coarse Power Gating Policies.
	 *
	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
	 * use instead is a more conservative estimate for the maximum time
	 * it takes us to service a CS interrupt and submit a new ELSP - that
	 * is the time which the GPU is idle waiting for the CPU to select the
	 * next request to execute. If the idle hysteresis is less than that
	 * interrupt service latency, the hardware will automatically gate
	 * the power well and we will then incur the wake up cost on top of
	 * the service latency. A similar guide from plane_state is that we
	 * do not want the enable hysteresis to less than the wakeup latency.
	 *
	 * igt/gem_exec_nop/sequential provides a rough estimate for the
	 * service latency, and puts it around 10us for Broadwell (and other
	 * big core) and around 40us for Broxton (and other low power cores).
	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
	 * However, the wakeup latency on Broxton is closer to 100us. To be
	 * conservative, we have to factor in a context switch on top (due
	 * to ksoftirqd).
	 */
	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);

	/* 3a: Enable RC6 */
	set(uncore, GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */

	/* WaRsUseTimeoutMode:cnl (pre-prod) */
	if (IS_CNL_REVID(rc6_to_i915(rc6), CNL_REVID_A0, CNL_REVID_C0))
		rc6_mode = GEN7_RC_CTL_TO_MODE;
	else
		rc6_mode = GEN6_RC_CTL_EI_MODE(1);

	rc6->ctl_enable =
		GEN6_RC_CTL_HW_ENABLE |
		GEN6_RC_CTL_RC6_ENABLE |
		rc6_mode;

	/*
	 * WaRsDisableCoarsePowerGating:skl,cnl
	 *   - Render/Media PG need to be disabled with RC6.
	 */
	if (!NEEDS_WaRsDisableCoarsePowerGating(rc6_to_i915(rc6)))
		set(uncore, GEN9_PG_ENABLE,
		    GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
}

static void gen8_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	/* 2b: Program RC6 thresholds.*/
	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
	set(uncore, GEN6_RC_SLEEP, 0);
	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */

	/* 3: Enable RC6 */
	rc6->ctl_enable =
	    GEN6_RC_CTL_HW_ENABLE |
	    GEN7_RC_CTL_TO_MODE |
	    GEN6_RC_CTL_RC6_ENABLE;
}

static void gen6_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	u32 rc6vids, rc6_mask;
	int ret;

	set(uncore, GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
	set(uncore, GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);

	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);

	set(uncore, GEN6_RC_SLEEP, 0);
	set(uncore, GEN6_RC1e_THRESHOLD, 1000);
	if (IS_IVYBRIDGE(i915))
		set(uncore, GEN6_RC6_THRESHOLD, 125000);
	else
		set(uncore, GEN6_RC6_THRESHOLD, 50000);
	set(uncore, GEN6_RC6p_THRESHOLD, 150000);
	set(uncore, GEN6_RC6pp_THRESHOLD, 64000); /* unused */

	/* We don't use those on Haswell */
	rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
	if (HAS_RC6p(i915))
		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
	if (HAS_RC6pp(i915))
		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
	rc6->ctl_enable =
	    rc6_mask |
	    GEN6_RC_CTL_EI_MODE(1) |
	    GEN6_RC_CTL_HW_ENABLE;

	rc6vids = 0;
	ret = sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
				     &rc6vids, NULL);
	if (IS_GEN(i915, 6) && ret) {
		DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n");
	} else if (IS_GEN(i915, 6) &&
		   (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
		DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n",
				 GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450);
		rc6vids &= 0xffff00;
		rc6vids |= GEN6_ENCODE_RC6_VID(450);
		ret = sandybridge_pcode_write(i915, GEN6_PCODE_WRITE_RC6VIDS, rc6vids);
		if (ret)
			DRM_ERROR("Couldn't fix incorrect rc6 voltage\n");
	}
}

/* Check that the pcbr address is not empty. */
static int chv_rc6_init(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	resource_size_t pctx_paddr, paddr;
	resource_size_t pctx_size = 32 * SZ_1K;
	u32 pcbr;

	pcbr = intel_uncore_read(uncore, VLV_PCBR);
	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
		DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
		paddr = rc6_to_i915(rc6)->dsm.end + 1 - pctx_size;
		GEM_BUG_ON(paddr > U32_MAX);

		pctx_paddr = (paddr & ~4095);
		intel_uncore_write(uncore, VLV_PCBR, pctx_paddr);
	}

	return 0;
}

static int vlv_rc6_init(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct drm_i915_gem_object *pctx;
	resource_size_t pctx_paddr;
	resource_size_t pctx_size = 24 * SZ_1K;
	u32 pcbr;

	pcbr = intel_uncore_read(uncore, VLV_PCBR);
	if (pcbr) {
		/* BIOS set it up already, grab the pre-alloc'd space */
		resource_size_t pcbr_offset;

		pcbr_offset = (pcbr & ~4095) - i915->dsm.start;
		pctx = i915_gem_object_create_stolen_for_preallocated(i915,
								      pcbr_offset,
								      I915_GTT_OFFSET_NONE,
								      pctx_size);
		if (IS_ERR(pctx))
			return PTR_ERR(pctx);

		goto out;
	}

	DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");

	/*
	 * From the Gunit register HAS:
	 * The Gfx driver is expected to program this register and ensure
	 * proper allocation within Gfx stolen memory.  For example, this
	 * register should be programmed such than the PCBR range does not
	 * overlap with other ranges, such as the frame buffer, protected
	 * memory, or any other relevant ranges.
	 */
	pctx = i915_gem_object_create_stolen(i915, pctx_size);
	if (IS_ERR(pctx)) {
		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
		return PTR_ERR(pctx);
	}

	GEM_BUG_ON(range_overflows_t(u64,
				     i915->dsm.start,
				     pctx->stolen->start,
				     U32_MAX));
	pctx_paddr = i915->dsm.start + pctx->stolen->start;
	intel_uncore_write(uncore, VLV_PCBR, pctx_paddr);

out:
	rc6->pctx = pctx;
	return 0;
}

static void chv_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	/* 2a: Program RC6 thresholds.*/
	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */

	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
	set(uncore, GEN6_RC_SLEEP, 0);

	/* TO threshold set to 500 us (0x186 * 1.28 us) */
	set(uncore, GEN6_RC6_THRESHOLD, 0x186);

	/* Allows RC6 residency counter to work */
	set(uncore, VLV_COUNTER_CONTROL,
	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
			       VLV_MEDIA_RC6_COUNT_EN |
			       VLV_RENDER_RC6_COUNT_EN));

	/* 3: Enable RC6 */
	rc6->ctl_enable = GEN7_RC_CTL_TO_MODE;
}

static void vlv_rc6_enable(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);

	for_each_engine(engine, rc6_to_gt(rc6), id)
		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);

	set(uncore, GEN6_RC6_THRESHOLD, 0x557);

	/* Allows RC6 residency counter to work */
	set(uncore, VLV_COUNTER_CONTROL,
	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
			       VLV_MEDIA_RC0_COUNT_EN |
			       VLV_RENDER_RC0_COUNT_EN |
			       VLV_MEDIA_RC6_COUNT_EN |
			       VLV_RENDER_RC6_COUNT_EN));

	rc6->ctl_enable =
	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
}

static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	u32 rc6_ctx_base, rc_ctl, rc_sw_target;
	bool enable_rc6 = true;

	rc_ctl = intel_uncore_read(uncore, GEN6_RC_CONTROL);
	rc_sw_target = intel_uncore_read(uncore, GEN6_RC_STATE);
	rc_sw_target &= RC_SW_TARGET_STATE_MASK;
	rc_sw_target >>= RC_SW_TARGET_STATE_SHIFT;
	DRM_DEBUG_DRIVER("BIOS enabled RC states: "
			 "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n",
			 onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE),
			 onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE),
			 rc_sw_target);

	if (!(intel_uncore_read(uncore, RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
		DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n");
		enable_rc6 = false;
	}

	/*
	 * The exact context size is not known for BXT, so assume a page size
	 * for this check.
	 */
	rc6_ctx_base =
		intel_uncore_read(uncore, RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
	if (!(rc6_ctx_base >= i915->dsm_reserved.start &&
	      rc6_ctx_base + PAGE_SIZE < i915->dsm_reserved.end)) {
		DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n");
		enable_rc6 = false;
	}

	if (!((intel_uncore_read(uncore, PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1 &&
	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1 &&
	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1 &&
	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1)) {
		DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n");
		enable_rc6 = false;
	}

	if (!intel_uncore_read(uncore, GEN8_PUSHBUS_CONTROL) ||
	    !intel_uncore_read(uncore, GEN8_PUSHBUS_ENABLE) ||
	    !intel_uncore_read(uncore, GEN8_PUSHBUS_SHIFT)) {
		DRM_DEBUG_DRIVER("Pushbus not setup properly.\n");
		enable_rc6 = false;
	}

	if (!intel_uncore_read(uncore, GEN6_GFXPAUSE)) {
		DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
		enable_rc6 = false;
	}

	if (!intel_uncore_read(uncore, GEN8_MISC_CTRL0)) {
		DRM_DEBUG_DRIVER("GPM control not setup properly.\n");
		enable_rc6 = false;
	}

	return enable_rc6;
}

static bool rc6_supported(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);

	if (!HAS_RC6(i915))
		return false;

	if (intel_vgpu_active(i915))
		return false;

	if (is_mock_gt(rc6_to_gt(rc6)))
		return false;

	if (IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(rc6)) {
		dev_notice(i915->drm.dev,
			   "RC6 and powersaving disabled by BIOS\n");
		return false;
	}

	return true;
}

static void rpm_get(struct intel_rc6 *rc6)
{
	GEM_BUG_ON(rc6->wakeref);
	pm_runtime_get_sync(&rc6_to_i915(rc6)->drm.pdev->dev);
	rc6->wakeref = true;
}

static void rpm_put(struct intel_rc6 *rc6)
{
	GEM_BUG_ON(!rc6->wakeref);
	pm_runtime_put(&rc6_to_i915(rc6)->drm.pdev->dev);
	rc6->wakeref = false;
}

static bool pctx_corrupted(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);

	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
		return false;

	if (intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO))
		return false;

	dev_notice(i915->drm.dev,
		   "RC6 context corruption, disabling runtime power management\n");
	return true;
}

static void __intel_rc6_disable(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	struct intel_uncore *uncore = rc6_to_uncore(rc6);

	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
	if (INTEL_GEN(i915) >= 9)
		set(uncore, GEN9_PG_ENABLE, 0);
	set(uncore, GEN6_RC_CONTROL, 0);
	set(uncore, GEN6_RC_STATE, 0);
	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
}

void intel_rc6_init(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	int err;

	/* Disable runtime-pm until we can save the GPU state with rc6 pctx */
	rpm_get(rc6);

	if (!rc6_supported(rc6))
		return;

	if (IS_CHERRYVIEW(i915))
		err = chv_rc6_init(rc6);
	else if (IS_VALLEYVIEW(i915))
		err = vlv_rc6_init(rc6);
	else
		err = 0;

	/* Sanitize rc6, ensure it is disabled before we are ready. */
	__intel_rc6_disable(rc6);

	rc6->supported = err == 0;
}

void intel_rc6_sanitize(struct intel_rc6 *rc6)
{
	if (rc6->enabled) { /* unbalanced suspend/resume */
		rpm_get(rc6);
		rc6->enabled = false;
	}

	if (rc6->supported)
		__intel_rc6_disable(rc6);
}

void intel_rc6_enable(struct intel_rc6 *rc6)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	struct intel_uncore *uncore = rc6_to_uncore(rc6);

	if (!rc6->supported)
		return;

	GEM_BUG_ON(rc6->enabled);

	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);

	if (IS_CHERRYVIEW(i915))
		chv_rc6_enable(rc6);
	else if (IS_VALLEYVIEW(i915))
		vlv_rc6_enable(rc6);
	else if (INTEL_GEN(i915) >= 11)
		gen11_rc6_enable(rc6);
	else if (INTEL_GEN(i915) >= 9)
		gen9_rc6_enable(rc6);
	else if (IS_BROADWELL(i915))
		gen8_rc6_enable(rc6);
	else if (INTEL_GEN(i915) >= 6)
		gen6_rc6_enable(rc6);

	rc6->manual = rc6->ctl_enable & GEN6_RC_CTL_RC6_ENABLE;
	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
		rc6->ctl_enable = 0;

	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);

	if (unlikely(pctx_corrupted(rc6)))
		return;

	/* rc6 is ready, runtime-pm is go! */
	rpm_put(rc6);
	rc6->enabled = true;
}

void intel_rc6_unpark(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);

	if (!rc6->enabled)
		return;

	/* Restore HW timers for automatic RC6 entry while busy */
	set(uncore, GEN6_RC_CONTROL, rc6->ctl_enable);
}

void intel_rc6_park(struct intel_rc6 *rc6)
{
	struct intel_uncore *uncore = rc6_to_uncore(rc6);

	if (!rc6->enabled)
		return;

	if (unlikely(pctx_corrupted(rc6))) {
		intel_rc6_disable(rc6);
		return;
	}

	if (!rc6->manual)
		return;

	/* Turn off the HW timers and go directly to rc6 */
	set(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE);
	set(uncore, GEN6_RC_STATE, 0x4 << RC_SW_TARGET_STATE_SHIFT);
}

void intel_rc6_disable(struct intel_rc6 *rc6)
{
	if (!rc6->enabled)
		return;

	rpm_get(rc6);
	rc6->enabled = false;

	__intel_rc6_disable(rc6);
}

void intel_rc6_fini(struct intel_rc6 *rc6)
{
	struct drm_i915_gem_object *pctx;

	intel_rc6_disable(rc6);

	pctx = fetch_and_zero(&rc6->pctx);
	if (pctx)
		i915_gem_object_put(pctx);

	if (rc6->wakeref)
		rpm_put(rc6);
}

static u64 vlv_residency_raw(struct intel_uncore *uncore, const i915_reg_t reg)
{
	u32 lower, upper, tmp;
	int loop = 2;

	/*
	 * The register accessed do not need forcewake. We borrow
	 * uncore lock to prevent concurrent access to range reg.
	 */
	lockdep_assert_held(&uncore->lock);

	/*
	 * vlv and chv residency counters are 40 bits in width.
	 * With a control bit, we can choose between upper or lower
	 * 32bit window into this counter.
	 *
	 * Although we always use the counter in high-range mode elsewhere,
	 * userspace may attempt to read the value before rc6 is initialised,
	 * before we have set the default VLV_COUNTER_CONTROL value. So always
	 * set the high bit to be safe.
	 */
	set(uncore, VLV_COUNTER_CONTROL,
	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
	upper = intel_uncore_read_fw(uncore, reg);
	do {
		tmp = upper;

		set(uncore, VLV_COUNTER_CONTROL,
		    _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
		lower = intel_uncore_read_fw(uncore, reg);

		set(uncore, VLV_COUNTER_CONTROL,
		    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
		upper = intel_uncore_read_fw(uncore, reg);
	} while (upper != tmp && --loop);

	/*
	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
	 * now.
	 */

	return lower | (u64)upper << 8;
}

u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg)
{
	struct drm_i915_private *i915 = rc6_to_i915(rc6);
	struct intel_uncore *uncore = rc6_to_uncore(rc6);
	u64 time_hw, prev_hw, overflow_hw;
	unsigned int fw_domains;
	unsigned long flags;
	unsigned int i;
	u32 mul, div;

	if (!rc6->supported)
		return 0;

	/*
	 * Store previous hw counter values for counter wrap-around handling.
	 *
	 * There are only four interesting registers and they live next to each
	 * other so we can use the relative address, compared to the smallest
	 * one as the index into driver storage.
	 */
	i = (i915_mmio_reg_offset(reg) -
	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
	if (WARN_ON_ONCE(i >= ARRAY_SIZE(rc6->cur_residency)))
		return 0;

	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ);

	spin_lock_irqsave(&uncore->lock, flags);
	intel_uncore_forcewake_get__locked(uncore, fw_domains);

	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
		mul = 1000000;
		div = i915->czclk_freq;
		overflow_hw = BIT_ULL(40);
		time_hw = vlv_residency_raw(uncore, reg);
	} else {
		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
		if (IS_GEN9_LP(i915)) {
			mul = 10000;
			div = 12;
		} else {
			mul = 1280;
			div = 1;
		}

		overflow_hw = BIT_ULL(32);
		time_hw = intel_uncore_read_fw(uncore, reg);
	}

	/*
	 * Counter wrap handling.
	 *
	 * But relying on a sufficient frequency of queries otherwise counters
	 * can still wrap.
	 */
	prev_hw = rc6->prev_hw_residency[i];
	rc6->prev_hw_residency[i] = time_hw;

	/* RC6 delta from last sample. */
	if (time_hw >= prev_hw)
		time_hw -= prev_hw;
	else
		time_hw += overflow_hw - prev_hw;

	/* Add delta to RC6 extended raw driver copy. */
	time_hw += rc6->cur_residency[i];
	rc6->cur_residency[i] = time_hw;

	intel_uncore_forcewake_put__locked(uncore, fw_domains);
	spin_unlock_irqrestore(&uncore->lock, flags);

	return mul_u64_u32_div(time_hw, mul, div);
}

u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
{
	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
}

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_rc6.c"
#endif