summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/vc4/vc4_hvs.c
blob: 604933e20e6a2d4058e3aed02cbedcc07e0d3f29 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2015 Broadcom
 */

/**
 * DOC: VC4 HVS module.
 *
 * The Hardware Video Scaler (HVS) is the piece of hardware that does
 * translation, scaling, colorspace conversion, and compositing of
 * pixels stored in framebuffers into a FIFO of pixels going out to
 * the Pixel Valve (CRTC).  It operates at the system clock rate (the
 * system audio clock gate, specifically), which is much higher than
 * the pixel clock rate.
 *
 * There is a single global HVS, with multiple output FIFOs that can
 * be consumed by the PVs.  This file just manages the resources for
 * the HVS, while the vc4_crtc.c code actually drives HVS setup for
 * each CRTC.
 */

#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/component.h>
#include <linux/platform_device.h>

#include <drm/drm_atomic_helper.h>
#include <drm/drm_vblank.h>

#include "vc4_drv.h"
#include "vc4_regs.h"

static const struct debugfs_reg32 hvs_regs[] = {
	VC4_REG32(SCALER_DISPCTRL),
	VC4_REG32(SCALER_DISPSTAT),
	VC4_REG32(SCALER_DISPID),
	VC4_REG32(SCALER_DISPECTRL),
	VC4_REG32(SCALER_DISPPROF),
	VC4_REG32(SCALER_DISPDITHER),
	VC4_REG32(SCALER_DISPEOLN),
	VC4_REG32(SCALER_DISPLIST0),
	VC4_REG32(SCALER_DISPLIST1),
	VC4_REG32(SCALER_DISPLIST2),
	VC4_REG32(SCALER_DISPLSTAT),
	VC4_REG32(SCALER_DISPLACT0),
	VC4_REG32(SCALER_DISPLACT1),
	VC4_REG32(SCALER_DISPLACT2),
	VC4_REG32(SCALER_DISPCTRL0),
	VC4_REG32(SCALER_DISPBKGND0),
	VC4_REG32(SCALER_DISPSTAT0),
	VC4_REG32(SCALER_DISPBASE0),
	VC4_REG32(SCALER_DISPCTRL1),
	VC4_REG32(SCALER_DISPBKGND1),
	VC4_REG32(SCALER_DISPSTAT1),
	VC4_REG32(SCALER_DISPBASE1),
	VC4_REG32(SCALER_DISPCTRL2),
	VC4_REG32(SCALER_DISPBKGND2),
	VC4_REG32(SCALER_DISPSTAT2),
	VC4_REG32(SCALER_DISPBASE2),
	VC4_REG32(SCALER_DISPALPHA2),
	VC4_REG32(SCALER_OLEDOFFS),
	VC4_REG32(SCALER_OLEDCOEF0),
	VC4_REG32(SCALER_OLEDCOEF1),
	VC4_REG32(SCALER_OLEDCOEF2),
};

void vc4_hvs_dump_state(struct drm_device *dev)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct drm_printer p = drm_info_printer(&vc4->hvs->pdev->dev);
	int i;

	drm_print_regset32(&p, &vc4->hvs->regset);

	DRM_INFO("HVS ctx:\n");
	for (i = 0; i < 64; i += 4) {
		DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n",
			 i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D",
			 readl((u32 __iomem *)vc4->hvs->dlist + i + 0),
			 readl((u32 __iomem *)vc4->hvs->dlist + i + 1),
			 readl((u32 __iomem *)vc4->hvs->dlist + i + 2),
			 readl((u32 __iomem *)vc4->hvs->dlist + i + 3));
	}
}

static int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data)
{
	struct drm_info_node *node = m->private;
	struct drm_device *dev = node->minor->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct drm_printer p = drm_seq_file_printer(m);

	drm_printf(&p, "%d\n", atomic_read(&vc4->underrun));

	return 0;
}

/* The filter kernel is composed of dwords each containing 3 9-bit
 * signed integers packed next to each other.
 */
#define VC4_INT_TO_COEFF(coeff) (coeff & 0x1ff)
#define VC4_PPF_FILTER_WORD(c0, c1, c2)				\
	((((c0) & 0x1ff) << 0) |				\
	 (((c1) & 0x1ff) << 9) |				\
	 (((c2) & 0x1ff) << 18))

/* The whole filter kernel is arranged as the coefficients 0-16 going
 * up, then a pad, then 17-31 going down and reversed within the
 * dwords.  This means that a linear phase kernel (where it's
 * symmetrical at the boundary between 15 and 16) has the last 5
 * dwords matching the first 5, but reversed.
 */
#define VC4_LINEAR_PHASE_KERNEL(c0, c1, c2, c3, c4, c5, c6, c7, c8,	\
				c9, c10, c11, c12, c13, c14, c15)	\
	{VC4_PPF_FILTER_WORD(c0, c1, c2),				\
	 VC4_PPF_FILTER_WORD(c3, c4, c5),				\
	 VC4_PPF_FILTER_WORD(c6, c7, c8),				\
	 VC4_PPF_FILTER_WORD(c9, c10, c11),				\
	 VC4_PPF_FILTER_WORD(c12, c13, c14),				\
	 VC4_PPF_FILTER_WORD(c15, c15, 0)}

#define VC4_LINEAR_PHASE_KERNEL_DWORDS 6
#define VC4_KERNEL_DWORDS (VC4_LINEAR_PHASE_KERNEL_DWORDS * 2 - 1)

/* Recommended B=1/3, C=1/3 filter choice from Mitchell/Netravali.
 * http://www.cs.utexas.edu/~fussell/courses/cs384g/lectures/mitchell/Mitchell.pdf
 */
static const u32 mitchell_netravali_1_3_1_3_kernel[] =
	VC4_LINEAR_PHASE_KERNEL(0, -2, -6, -8, -10, -8, -3, 2, 18,
				50, 82, 119, 155, 187, 213, 227);

static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs,
					struct drm_mm_node *space,
					const u32 *kernel)
{
	int ret, i;
	u32 __iomem *dst_kernel;

	ret = drm_mm_insert_node(&hvs->dlist_mm, space, VC4_KERNEL_DWORDS);
	if (ret) {
		DRM_ERROR("Failed to allocate space for filter kernel: %d\n",
			  ret);
		return ret;
	}

	dst_kernel = hvs->dlist + space->start;

	for (i = 0; i < VC4_KERNEL_DWORDS; i++) {
		if (i < VC4_LINEAR_PHASE_KERNEL_DWORDS)
			writel(kernel[i], &dst_kernel[i]);
		else {
			writel(kernel[VC4_KERNEL_DWORDS - i - 1],
			       &dst_kernel[i]);
		}
	}

	return 0;
}

static void vc4_hvs_lut_load(struct drm_crtc *crtc)
{
	struct drm_device *dev = crtc->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
	u32 i;

	/* The LUT memory is laid out with each HVS channel in order,
	 * each of which takes 256 writes for R, 256 for G, then 256
	 * for B.
	 */
	HVS_WRITE(SCALER_GAMADDR,
		  SCALER_GAMADDR_AUTOINC |
		  (vc4_state->assigned_channel * 3 * crtc->gamma_size));

	for (i = 0; i < crtc->gamma_size; i++)
		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_r[i]);
	for (i = 0; i < crtc->gamma_size; i++)
		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_g[i]);
	for (i = 0; i < crtc->gamma_size; i++)
		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
}

static void vc4_hvs_update_gamma_lut(struct drm_crtc *crtc)
{
	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
	struct drm_color_lut *lut = crtc->state->gamma_lut->data;
	u32 length = drm_color_lut_size(crtc->state->gamma_lut);
	u32 i;

	for (i = 0; i < length; i++) {
		vc4_crtc->lut_r[i] = drm_color_lut_extract(lut[i].red, 8);
		vc4_crtc->lut_g[i] = drm_color_lut_extract(lut[i].green, 8);
		vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8);
	}

	vc4_hvs_lut_load(crtc);
}

int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	u32 reg;
	int ret;

	if (!vc4->hvs->hvs5)
		return output;

	switch (output) {
	case 0:
		return 0;

	case 1:
		return 1;

	case 2:
		reg = HVS_READ(SCALER_DISPECTRL);
		ret = FIELD_GET(SCALER_DISPECTRL_DSP2_MUX_MASK, reg);
		if (ret == 0)
			return 2;

		return 0;

	case 3:
		reg = HVS_READ(SCALER_DISPCTRL);
		ret = FIELD_GET(SCALER_DISPCTRL_DSP3_MUX_MASK, reg);
		if (ret == 3)
			return -EPIPE;

		return ret;

	case 4:
		reg = HVS_READ(SCALER_DISPEOLN);
		ret = FIELD_GET(SCALER_DISPEOLN_DSP4_MUX_MASK, reg);
		if (ret == 3)
			return -EPIPE;

		return ret;

	case 5:
		reg = HVS_READ(SCALER_DISPDITHER);
		ret = FIELD_GET(SCALER_DISPDITHER_DSP5_MUX_MASK, reg);
		if (ret == 3)
			return -EPIPE;

		return ret;

	default:
		return -EPIPE;
	}
}

static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc,
				struct drm_display_mode *mode, bool oneshot)
{
	struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state);
	unsigned int chan = vc4_crtc_state->assigned_channel;
	bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE;
	u32 dispbkgndx;
	u32 dispctrl;

	HVS_WRITE(SCALER_DISPCTRLX(chan), 0);
	HVS_WRITE(SCALER_DISPCTRLX(chan), SCALER_DISPCTRLX_RESET);
	HVS_WRITE(SCALER_DISPCTRLX(chan), 0);

	/* Turn on the scaler, which will wait for vstart to start
	 * compositing.
	 * When feeding the transposer, we should operate in oneshot
	 * mode.
	 */
	dispctrl = SCALER_DISPCTRLX_ENABLE;

	if (!vc4->hvs->hvs5)
		dispctrl |= VC4_SET_FIELD(mode->hdisplay,
					  SCALER_DISPCTRLX_WIDTH) |
			    VC4_SET_FIELD(mode->vdisplay,
					  SCALER_DISPCTRLX_HEIGHT) |
			    (oneshot ? SCALER_DISPCTRLX_ONESHOT : 0);
	else
		dispctrl |= VC4_SET_FIELD(mode->hdisplay,
					  SCALER5_DISPCTRLX_WIDTH) |
			    VC4_SET_FIELD(mode->vdisplay,
					  SCALER5_DISPCTRLX_HEIGHT) |
			    (oneshot ? SCALER5_DISPCTRLX_ONESHOT : 0);

	HVS_WRITE(SCALER_DISPCTRLX(chan), dispctrl);

	dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(chan));
	dispbkgndx &= ~SCALER_DISPBKGND_GAMMA;
	dispbkgndx &= ~SCALER_DISPBKGND_INTERLACE;

	HVS_WRITE(SCALER_DISPBKGNDX(chan), dispbkgndx |
		  SCALER_DISPBKGND_AUTOHS |
		  ((!vc4->hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) |
		  (interlace ? SCALER_DISPBKGND_INTERLACE : 0));

	/* Reload the LUT, since the SRAMs would have been disabled if
	 * all CRTCs had SCALER_DISPBKGND_GAMMA unset at once.
	 */
	vc4_hvs_lut_load(crtc);

	return 0;
}

void vc4_hvs_stop_channel(struct drm_device *dev, unsigned int chan)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);

	if (HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_ENABLE)
		return;

	HVS_WRITE(SCALER_DISPCTRLX(chan),
		  HVS_READ(SCALER_DISPCTRLX(chan)) | SCALER_DISPCTRLX_RESET);
	HVS_WRITE(SCALER_DISPCTRLX(chan),
		  HVS_READ(SCALER_DISPCTRLX(chan)) & ~SCALER_DISPCTRLX_ENABLE);

	/* Once we leave, the scaler should be disabled and its fifo empty. */
	WARN_ON_ONCE(HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_RESET);

	WARN_ON_ONCE(VC4_GET_FIELD(HVS_READ(SCALER_DISPSTATX(chan)),
				   SCALER_DISPSTATX_MODE) !=
		     SCALER_DISPSTATX_MODE_DISABLED);

	WARN_ON_ONCE((HVS_READ(SCALER_DISPSTATX(chan)) &
		      (SCALER_DISPSTATX_FULL | SCALER_DISPSTATX_EMPTY)) !=
		     SCALER_DISPSTATX_EMPTY);
}

int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state)
{
	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state);
	struct drm_device *dev = crtc->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct drm_plane *plane;
	unsigned long flags;
	const struct drm_plane_state *plane_state;
	u32 dlist_count = 0;
	int ret;

	/* The pixelvalve can only feed one encoder (and encoders are
	 * 1:1 with connectors.)
	 */
	if (hweight32(crtc_state->connector_mask) > 1)
		return -EINVAL;

	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state)
		dlist_count += vc4_plane_dlist_size(plane_state);

	dlist_count++; /* Account for SCALER_CTL0_END. */

	spin_lock_irqsave(&vc4->hvs->mm_lock, flags);
	ret = drm_mm_insert_node(&vc4->hvs->dlist_mm, &vc4_state->mm,
				 dlist_count);
	spin_unlock_irqrestore(&vc4->hvs->mm_lock, flags);
	if (ret)
		return ret;

	return 0;
}

static void vc4_hvs_update_dlist(struct drm_crtc *crtc)
{
	struct drm_device *dev = crtc->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
	unsigned long flags;

	if (crtc->state->event) {
		crtc->state->event->pipe = drm_crtc_index(crtc);

		WARN_ON(drm_crtc_vblank_get(crtc) != 0);

		spin_lock_irqsave(&dev->event_lock, flags);

		if (!vc4_crtc->feeds_txp || vc4_state->txp_armed) {
			vc4_crtc->event = crtc->state->event;
			crtc->state->event = NULL;
		}

		HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
			  vc4_state->mm.start);

		spin_unlock_irqrestore(&dev->event_lock, flags);
	} else {
		HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel),
			  vc4_state->mm.start);
	}

	spin_lock_irqsave(&vc4_crtc->irq_lock, flags);
	vc4_crtc->current_dlist = vc4_state->mm.start;
	spin_unlock_irqrestore(&vc4_crtc->irq_lock, flags);
}

void vc4_hvs_atomic_begin(struct drm_crtc *crtc,
			  struct drm_atomic_state *state)
{
	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
	unsigned long flags;

	spin_lock_irqsave(&vc4_crtc->irq_lock, flags);
	vc4_crtc->current_hvs_channel = vc4_state->assigned_channel;
	spin_unlock_irqrestore(&vc4_crtc->irq_lock, flags);
}

void vc4_hvs_atomic_enable(struct drm_crtc *crtc,
			   struct drm_atomic_state *state)
{
	struct drm_device *dev = crtc->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
	bool oneshot = vc4_crtc->feeds_txp;

	vc4_hvs_update_dlist(crtc);
	vc4_hvs_init_channel(vc4, crtc, mode, oneshot);
}

void vc4_hvs_atomic_disable(struct drm_crtc *crtc,
			    struct drm_atomic_state *state)
{
	struct drm_device *dev = crtc->dev;
	struct drm_crtc_state *old_state = drm_atomic_get_old_crtc_state(state, crtc);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(old_state);
	unsigned int chan = vc4_state->assigned_channel;

	vc4_hvs_stop_channel(dev, chan);
}

void vc4_hvs_atomic_flush(struct drm_crtc *crtc,
			  struct drm_atomic_state *state)
{
	struct drm_crtc_state *old_state = drm_atomic_get_old_crtc_state(state,
									 crtc);
	struct drm_device *dev = crtc->dev;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
	struct drm_plane *plane;
	struct vc4_plane_state *vc4_plane_state;
	bool debug_dump_regs = false;
	bool enable_bg_fill = false;
	u32 __iomem *dlist_start = vc4->hvs->dlist + vc4_state->mm.start;
	u32 __iomem *dlist_next = dlist_start;

	if (debug_dump_regs) {
		DRM_INFO("CRTC %d HVS before:\n", drm_crtc_index(crtc));
		vc4_hvs_dump_state(dev);
	}

	/* Copy all the active planes' dlist contents to the hardware dlist. */
	drm_atomic_crtc_for_each_plane(plane, crtc) {
		/* Is this the first active plane? */
		if (dlist_next == dlist_start) {
			/* We need to enable background fill when a plane
			 * could be alpha blending from the background, i.e.
			 * where no other plane is underneath. It suffices to
			 * consider the first active plane here since we set
			 * needs_bg_fill such that either the first plane
			 * already needs it or all planes on top blend from
			 * the first or a lower plane.
			 */
			vc4_plane_state = to_vc4_plane_state(plane->state);
			enable_bg_fill = vc4_plane_state->needs_bg_fill;
		}

		dlist_next += vc4_plane_write_dlist(plane, dlist_next);
	}

	writel(SCALER_CTL0_END, dlist_next);
	dlist_next++;

	WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size);

	if (enable_bg_fill)
		/* This sets a black background color fill, as is the case
		 * with other DRM drivers.
		 */
		HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel),
			  HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel)) |
			  SCALER_DISPBKGND_FILL);

	/* Only update DISPLIST if the CRTC was already running and is not
	 * being disabled.
	 * vc4_crtc_enable() takes care of updating the dlist just after
	 * re-enabling VBLANK interrupts and before enabling the engine.
	 * If the CRTC is being disabled, there's no point in updating this
	 * information.
	 */
	if (crtc->state->active && old_state->active)
		vc4_hvs_update_dlist(crtc);

	if (crtc->state->color_mgmt_changed) {
		u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel));

		if (crtc->state->gamma_lut) {
			vc4_hvs_update_gamma_lut(crtc);
			dispbkgndx |= SCALER_DISPBKGND_GAMMA;
		} else {
			/* Unsetting DISPBKGND_GAMMA skips the gamma lut step
			 * in hardware, which is the same as a linear lut that
			 * DRM expects us to use in absence of a user lut.
			 */
			dispbkgndx &= ~SCALER_DISPBKGND_GAMMA;
		}
		HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel), dispbkgndx);
	}

	if (debug_dump_regs) {
		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
		vc4_hvs_dump_state(dev);
	}
}

void vc4_hvs_mask_underrun(struct drm_device *dev, int channel)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);

	dispctrl &= ~SCALER_DISPCTRL_DSPEISLUR(channel);

	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
}

void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	u32 dispctrl = HVS_READ(SCALER_DISPCTRL);

	dispctrl |= SCALER_DISPCTRL_DSPEISLUR(channel);

	HVS_WRITE(SCALER_DISPSTAT,
		  SCALER_DISPSTAT_EUFLOW(channel));
	HVS_WRITE(SCALER_DISPCTRL, dispctrl);
}

static void vc4_hvs_report_underrun(struct drm_device *dev)
{
	struct vc4_dev *vc4 = to_vc4_dev(dev);

	atomic_inc(&vc4->underrun);
	DRM_DEV_ERROR(dev->dev, "HVS underrun\n");
}

static irqreturn_t vc4_hvs_irq_handler(int irq, void *data)
{
	struct drm_device *dev = data;
	struct vc4_dev *vc4 = to_vc4_dev(dev);
	irqreturn_t irqret = IRQ_NONE;
	int channel;
	u32 control;
	u32 status;

	status = HVS_READ(SCALER_DISPSTAT);
	control = HVS_READ(SCALER_DISPCTRL);

	for (channel = 0; channel < SCALER_CHANNELS_COUNT; channel++) {
		/* Interrupt masking is not always honored, so check it here. */
		if (status & SCALER_DISPSTAT_EUFLOW(channel) &&
		    control & SCALER_DISPCTRL_DSPEISLUR(channel)) {
			vc4_hvs_mask_underrun(dev, channel);
			vc4_hvs_report_underrun(dev);

			irqret = IRQ_HANDLED;
		}
	}

	/* Clear every per-channel interrupt flag. */
	HVS_WRITE(SCALER_DISPSTAT, SCALER_DISPSTAT_IRQMASK(0) |
				   SCALER_DISPSTAT_IRQMASK(1) |
				   SCALER_DISPSTAT_IRQMASK(2));

	return irqret;
}

static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
{
	struct platform_device *pdev = to_platform_device(dev);
	struct drm_device *drm = dev_get_drvdata(master);
	struct vc4_dev *vc4 = to_vc4_dev(drm);
	struct vc4_hvs *hvs = NULL;
	int ret;
	u32 dispctrl;

	hvs = devm_kzalloc(&pdev->dev, sizeof(*hvs), GFP_KERNEL);
	if (!hvs)
		return -ENOMEM;

	hvs->pdev = pdev;

	if (of_device_is_compatible(pdev->dev.of_node, "brcm,bcm2711-hvs"))
		hvs->hvs5 = true;

	hvs->regs = vc4_ioremap_regs(pdev, 0);
	if (IS_ERR(hvs->regs))
		return PTR_ERR(hvs->regs);

	hvs->regset.base = hvs->regs;
	hvs->regset.regs = hvs_regs;
	hvs->regset.nregs = ARRAY_SIZE(hvs_regs);

	if (hvs->hvs5) {
		hvs->core_clk = devm_clk_get(&pdev->dev, NULL);
		if (IS_ERR(hvs->core_clk)) {
			dev_err(&pdev->dev, "Couldn't get core clock\n");
			return PTR_ERR(hvs->core_clk);
		}

		ret = clk_prepare_enable(hvs->core_clk);
		if (ret) {
			dev_err(&pdev->dev, "Couldn't enable the core clock\n");
			return ret;
		}
	}

	if (!hvs->hvs5)
		hvs->dlist = hvs->regs + SCALER_DLIST_START;
	else
		hvs->dlist = hvs->regs + SCALER5_DLIST_START;

	spin_lock_init(&hvs->mm_lock);

	/* Set up the HVS display list memory manager.  We never
	 * overwrite the setup from the bootloader (just 128b out of
	 * our 16K), since we don't want to scramble the screen when
	 * transitioning from the firmware's boot setup to runtime.
	 */
	drm_mm_init(&hvs->dlist_mm,
		    HVS_BOOTLOADER_DLIST_END,
		    (SCALER_DLIST_SIZE >> 2) - HVS_BOOTLOADER_DLIST_END);

	/* Set up the HVS LBM memory manager.  We could have some more
	 * complicated data structure that allowed reuse of LBM areas
	 * between planes when they don't overlap on the screen, but
	 * for now we just allocate globally.
	 */
	if (!hvs->hvs5)
		/* 48k words of 2x12-bit pixels */
		drm_mm_init(&hvs->lbm_mm, 0, 48 * 1024);
	else
		/* 60k words of 4x12-bit pixels */
		drm_mm_init(&hvs->lbm_mm, 0, 60 * 1024);

	/* Upload filter kernels.  We only have the one for now, so we
	 * keep it around for the lifetime of the driver.
	 */
	ret = vc4_hvs_upload_linear_kernel(hvs,
					   &hvs->mitchell_netravali_filter,
					   mitchell_netravali_1_3_1_3_kernel);
	if (ret)
		return ret;

	vc4->hvs = hvs;

	dispctrl = HVS_READ(SCALER_DISPCTRL);

	dispctrl |= SCALER_DISPCTRL_ENABLE;
	dispctrl |= SCALER_DISPCTRL_DISPEIRQ(0) |
		    SCALER_DISPCTRL_DISPEIRQ(1) |
		    SCALER_DISPCTRL_DISPEIRQ(2);

	/* Set DSP3 (PV1) to use HVS channel 2, which would otherwise
	 * be unused.
	 */
	dispctrl &= ~SCALER_DISPCTRL_DSP3_MUX_MASK;
	dispctrl &= ~(SCALER_DISPCTRL_DMAEIRQ |
		      SCALER_DISPCTRL_SLVWREIRQ |
		      SCALER_DISPCTRL_SLVRDEIRQ |
		      SCALER_DISPCTRL_DSPEIEOF(0) |
		      SCALER_DISPCTRL_DSPEIEOF(1) |
		      SCALER_DISPCTRL_DSPEIEOF(2) |
		      SCALER_DISPCTRL_DSPEIEOLN(0) |
		      SCALER_DISPCTRL_DSPEIEOLN(1) |
		      SCALER_DISPCTRL_DSPEIEOLN(2) |
		      SCALER_DISPCTRL_DSPEISLUR(0) |
		      SCALER_DISPCTRL_DSPEISLUR(1) |
		      SCALER_DISPCTRL_DSPEISLUR(2) |
		      SCALER_DISPCTRL_SCLEIRQ);
	dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);

	HVS_WRITE(SCALER_DISPCTRL, dispctrl);

	ret = devm_request_irq(dev, platform_get_irq(pdev, 0),
			       vc4_hvs_irq_handler, 0, "vc4 hvs", drm);
	if (ret)
		return ret;

	vc4_debugfs_add_regset32(drm, "hvs_regs", &hvs->regset);
	vc4_debugfs_add_file(drm, "hvs_underrun", vc4_hvs_debugfs_underrun,
			     NULL);

	return 0;
}

static void vc4_hvs_unbind(struct device *dev, struct device *master,
			   void *data)
{
	struct drm_device *drm = dev_get_drvdata(master);
	struct vc4_dev *vc4 = to_vc4_dev(drm);
	struct vc4_hvs *hvs = vc4->hvs;

	if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter))
		drm_mm_remove_node(&vc4->hvs->mitchell_netravali_filter);

	drm_mm_takedown(&vc4->hvs->dlist_mm);
	drm_mm_takedown(&vc4->hvs->lbm_mm);

	clk_disable_unprepare(hvs->core_clk);

	vc4->hvs = NULL;
}

static const struct component_ops vc4_hvs_ops = {
	.bind   = vc4_hvs_bind,
	.unbind = vc4_hvs_unbind,
};

static int vc4_hvs_dev_probe(struct platform_device *pdev)
{
	return component_add(&pdev->dev, &vc4_hvs_ops);
}

static int vc4_hvs_dev_remove(struct platform_device *pdev)
{
	component_del(&pdev->dev, &vc4_hvs_ops);
	return 0;
}

static const struct of_device_id vc4_hvs_dt_match[] = {
	{ .compatible = "brcm,bcm2711-hvs" },
	{ .compatible = "brcm,bcm2835-hvs" },
	{}
};

struct platform_driver vc4_hvs_driver = {
	.probe = vc4_hvs_dev_probe,
	.remove = vc4_hvs_dev_remove,
	.driver = {
		.name = "vc4_hvs",
		.of_match_table = vc4_hvs_dt_match,
	},
};