summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/msm/msm_gpu.c
blob: ffbff27600e0ff620fe623172e30783f53ce5fe7 (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
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include "msm_gpu.h"
#include "msm_gem.h"
#include "msm_mmu.h"
#include "msm_fence.h"


/*
 * Power Management:
 */

#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
#include <mach/board.h>
static void bs_init(struct msm_gpu *gpu)
{
	if (gpu->bus_scale_table) {
		gpu->bsc = msm_bus_scale_register_client(gpu->bus_scale_table);
		DBG("bus scale client: %08x", gpu->bsc);
	}
}

static void bs_fini(struct msm_gpu *gpu)
{
	if (gpu->bsc) {
		msm_bus_scale_unregister_client(gpu->bsc);
		gpu->bsc = 0;
	}
}

static void bs_set(struct msm_gpu *gpu, int idx)
{
	if (gpu->bsc) {
		DBG("set bus scaling: %d", idx);
		msm_bus_scale_client_update_request(gpu->bsc, idx);
	}
}
#else
static void bs_init(struct msm_gpu *gpu) {}
static void bs_fini(struct msm_gpu *gpu) {}
static void bs_set(struct msm_gpu *gpu, int idx) {}
#endif

static int enable_pwrrail(struct msm_gpu *gpu)
{
	struct drm_device *dev = gpu->dev;
	int ret = 0;

	if (gpu->gpu_reg) {
		ret = regulator_enable(gpu->gpu_reg);
		if (ret) {
			dev_err(dev->dev, "failed to enable 'gpu_reg': %d\n", ret);
			return ret;
		}
	}

	if (gpu->gpu_cx) {
		ret = regulator_enable(gpu->gpu_cx);
		if (ret) {
			dev_err(dev->dev, "failed to enable 'gpu_cx': %d\n", ret);
			return ret;
		}
	}

	return 0;
}

static int disable_pwrrail(struct msm_gpu *gpu)
{
	if (gpu->gpu_cx)
		regulator_disable(gpu->gpu_cx);
	if (gpu->gpu_reg)
		regulator_disable(gpu->gpu_reg);
	return 0;
}

static int enable_clk(struct msm_gpu *gpu)
{
	int i;

	if (gpu->core_clk && gpu->fast_rate)
		clk_set_rate(gpu->core_clk, gpu->fast_rate);

	/* Set the RBBM timer rate to 19.2Mhz */
	if (gpu->rbbmtimer_clk)
		clk_set_rate(gpu->rbbmtimer_clk, 19200000);

	for (i = gpu->nr_clocks - 1; i >= 0; i--)
		if (gpu->grp_clks[i])
			clk_prepare(gpu->grp_clks[i]);

	for (i = gpu->nr_clocks - 1; i >= 0; i--)
		if (gpu->grp_clks[i])
			clk_enable(gpu->grp_clks[i]);

	return 0;
}

static int disable_clk(struct msm_gpu *gpu)
{
	int i;

	for (i = gpu->nr_clocks - 1; i >= 0; i--)
		if (gpu->grp_clks[i])
			clk_disable(gpu->grp_clks[i]);

	for (i = gpu->nr_clocks - 1; i >= 0; i--)
		if (gpu->grp_clks[i])
			clk_unprepare(gpu->grp_clks[i]);

	/*
	 * Set the clock to a deliberately low rate. On older targets the clock
	 * speed had to be non zero to avoid problems. On newer targets this
	 * will be rounded down to zero anyway so it all works out.
	 */
	if (gpu->core_clk)
		clk_set_rate(gpu->core_clk, 27000000);

	if (gpu->rbbmtimer_clk)
		clk_set_rate(gpu->rbbmtimer_clk, 0);

	return 0;
}

static int enable_axi(struct msm_gpu *gpu)
{
	if (gpu->ebi1_clk)
		clk_prepare_enable(gpu->ebi1_clk);
	if (gpu->bus_freq)
		bs_set(gpu, gpu->bus_freq);
	return 0;
}

static int disable_axi(struct msm_gpu *gpu)
{
	if (gpu->ebi1_clk)
		clk_disable_unprepare(gpu->ebi1_clk);
	if (gpu->bus_freq)
		bs_set(gpu, 0);
	return 0;
}

int msm_gpu_pm_resume(struct msm_gpu *gpu)
{
	int ret;

	DBG("%s", gpu->name);

	ret = enable_pwrrail(gpu);
	if (ret)
		return ret;

	ret = enable_clk(gpu);
	if (ret)
		return ret;

	ret = enable_axi(gpu);
	if (ret)
		return ret;

	gpu->needs_hw_init = true;

	return 0;
}

int msm_gpu_pm_suspend(struct msm_gpu *gpu)
{
	int ret;

	DBG("%s", gpu->name);

	ret = disable_axi(gpu);
	if (ret)
		return ret;

	ret = disable_clk(gpu);
	if (ret)
		return ret;

	ret = disable_pwrrail(gpu);
	if (ret)
		return ret;

	return 0;
}

int msm_gpu_hw_init(struct msm_gpu *gpu)
{
	int ret;

	WARN_ON(!mutex_is_locked(&gpu->dev->struct_mutex));

	if (!gpu->needs_hw_init)
		return 0;

	disable_irq(gpu->irq);
	ret = gpu->funcs->hw_init(gpu);
	if (!ret)
		gpu->needs_hw_init = false;
	enable_irq(gpu->irq);

	return ret;
}

/*
 * Hangcheck detection for locked gpu:
 */

static void retire_submits(struct msm_gpu *gpu);

static void recover_worker(struct work_struct *work)
{
	struct msm_gpu *gpu = container_of(work, struct msm_gpu, recover_work);
	struct drm_device *dev = gpu->dev;
	struct msm_gem_submit *submit;
	uint32_t fence = gpu->funcs->last_fence(gpu);

	msm_update_fence(gpu->fctx, fence + 1);

	mutex_lock(&dev->struct_mutex);

	dev_err(dev->dev, "%s: hangcheck recover!\n", gpu->name);
	list_for_each_entry(submit, &gpu->submit_list, node) {
		if (submit->fence->seqno == (fence + 1)) {
			struct task_struct *task;

			rcu_read_lock();
			task = pid_task(submit->pid, PIDTYPE_PID);
			if (task) {
				dev_err(dev->dev, "%s: offending task: %s\n",
						gpu->name, task->comm);
			}
			rcu_read_unlock();
			break;
		}
	}

	if (msm_gpu_active(gpu)) {
		/* retire completed submits, plus the one that hung: */
		retire_submits(gpu);

		pm_runtime_get_sync(&gpu->pdev->dev);
		gpu->funcs->recover(gpu);
		pm_runtime_put_sync(&gpu->pdev->dev);

		/* replay the remaining submits after the one that hung: */
		list_for_each_entry(submit, &gpu->submit_list, node) {
			gpu->funcs->submit(gpu, submit, NULL);
		}
	}

	mutex_unlock(&dev->struct_mutex);

	msm_gpu_retire(gpu);
}

static void hangcheck_timer_reset(struct msm_gpu *gpu)
{
	DBG("%s", gpu->name);
	mod_timer(&gpu->hangcheck_timer,
			round_jiffies_up(jiffies + DRM_MSM_HANGCHECK_JIFFIES));
}

static void hangcheck_handler(unsigned long data)
{
	struct msm_gpu *gpu = (struct msm_gpu *)data;
	struct drm_device *dev = gpu->dev;
	struct msm_drm_private *priv = dev->dev_private;
	uint32_t fence = gpu->funcs->last_fence(gpu);

	if (fence != gpu->hangcheck_fence) {
		/* some progress has been made.. ya! */
		gpu->hangcheck_fence = fence;
	} else if (fence < gpu->fctx->last_fence) {
		/* no progress and not done.. hung! */
		gpu->hangcheck_fence = fence;
		dev_err(dev->dev, "%s: hangcheck detected gpu lockup!\n",
				gpu->name);
		dev_err(dev->dev, "%s:     completed fence: %u\n",
				gpu->name, fence);
		dev_err(dev->dev, "%s:     submitted fence: %u\n",
				gpu->name, gpu->fctx->last_fence);
		queue_work(priv->wq, &gpu->recover_work);
	}

	/* if still more pending work, reset the hangcheck timer: */
	if (gpu->fctx->last_fence > gpu->hangcheck_fence)
		hangcheck_timer_reset(gpu);

	/* workaround for missing irq: */
	queue_work(priv->wq, &gpu->retire_work);
}

/*
 * Performance Counters:
 */

/* called under perf_lock */
static int update_hw_cntrs(struct msm_gpu *gpu, uint32_t ncntrs, uint32_t *cntrs)
{
	uint32_t current_cntrs[ARRAY_SIZE(gpu->last_cntrs)];
	int i, n = min(ncntrs, gpu->num_perfcntrs);

	/* read current values: */
	for (i = 0; i < gpu->num_perfcntrs; i++)
		current_cntrs[i] = gpu_read(gpu, gpu->perfcntrs[i].sample_reg);

	/* update cntrs: */
	for (i = 0; i < n; i++)
		cntrs[i] = current_cntrs[i] - gpu->last_cntrs[i];

	/* save current values: */
	for (i = 0; i < gpu->num_perfcntrs; i++)
		gpu->last_cntrs[i] = current_cntrs[i];

	return n;
}

static void update_sw_cntrs(struct msm_gpu *gpu)
{
	ktime_t time;
	uint32_t elapsed;
	unsigned long flags;

	spin_lock_irqsave(&gpu->perf_lock, flags);
	if (!gpu->perfcntr_active)
		goto out;

	time = ktime_get();
	elapsed = ktime_to_us(ktime_sub(time, gpu->last_sample.time));

	gpu->totaltime += elapsed;
	if (gpu->last_sample.active)
		gpu->activetime += elapsed;

	gpu->last_sample.active = msm_gpu_active(gpu);
	gpu->last_sample.time = time;

out:
	spin_unlock_irqrestore(&gpu->perf_lock, flags);
}

void msm_gpu_perfcntr_start(struct msm_gpu *gpu)
{
	unsigned long flags;

	pm_runtime_get_sync(&gpu->pdev->dev);

	spin_lock_irqsave(&gpu->perf_lock, flags);
	/* we could dynamically enable/disable perfcntr registers too.. */
	gpu->last_sample.active = msm_gpu_active(gpu);
	gpu->last_sample.time = ktime_get();
	gpu->activetime = gpu->totaltime = 0;
	gpu->perfcntr_active = true;
	update_hw_cntrs(gpu, 0, NULL);
	spin_unlock_irqrestore(&gpu->perf_lock, flags);
}

void msm_gpu_perfcntr_stop(struct msm_gpu *gpu)
{
	gpu->perfcntr_active = false;
	pm_runtime_put_sync(&gpu->pdev->dev);
}

/* returns -errno or # of cntrs sampled */
int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime,
		uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&gpu->perf_lock, flags);

	if (!gpu->perfcntr_active) {
		ret = -EINVAL;
		goto out;
	}

	*activetime = gpu->activetime;
	*totaltime = gpu->totaltime;

	gpu->activetime = gpu->totaltime = 0;

	ret = update_hw_cntrs(gpu, ncntrs, cntrs);

out:
	spin_unlock_irqrestore(&gpu->perf_lock, flags);

	return ret;
}

/*
 * Cmdstream submission/retirement:
 */

static void retire_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
	int i;

	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;
		/* move to inactive: */
		msm_gem_move_to_inactive(&msm_obj->base);
		msm_gem_put_iova(&msm_obj->base, gpu->aspace);
		drm_gem_object_unreference(&msm_obj->base);
	}

	pm_runtime_mark_last_busy(&gpu->pdev->dev);
	pm_runtime_put_autosuspend(&gpu->pdev->dev);
	msm_gem_submit_free(submit);
}

static void retire_submits(struct msm_gpu *gpu)
{
	struct drm_device *dev = gpu->dev;

	WARN_ON(!mutex_is_locked(&dev->struct_mutex));

	while (!list_empty(&gpu->submit_list)) {
		struct msm_gem_submit *submit;

		submit = list_first_entry(&gpu->submit_list,
				struct msm_gem_submit, node);

		if (dma_fence_is_signaled(submit->fence)) {
			retire_submit(gpu, submit);
		} else {
			break;
		}
	}
}

static void retire_worker(struct work_struct *work)
{
	struct msm_gpu *gpu = container_of(work, struct msm_gpu, retire_work);
	struct drm_device *dev = gpu->dev;
	uint32_t fence = gpu->funcs->last_fence(gpu);

	msm_update_fence(gpu->fctx, fence);

	mutex_lock(&dev->struct_mutex);
	retire_submits(gpu);
	mutex_unlock(&dev->struct_mutex);
}

/* call from irq handler to schedule work to retire bo's */
void msm_gpu_retire(struct msm_gpu *gpu)
{
	struct msm_drm_private *priv = gpu->dev->dev_private;
	queue_work(priv->wq, &gpu->retire_work);
	update_sw_cntrs(gpu);
}

/* add bo's to gpu's ring, and kick gpu: */
void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
		struct msm_file_private *ctx)
{
	struct drm_device *dev = gpu->dev;
	struct msm_drm_private *priv = dev->dev_private;
	int i;

	WARN_ON(!mutex_is_locked(&dev->struct_mutex));

	pm_runtime_get_sync(&gpu->pdev->dev);

	msm_gpu_hw_init(gpu);

	list_add_tail(&submit->node, &gpu->submit_list);

	msm_rd_dump_submit(submit);

	update_sw_cntrs(gpu);

	for (i = 0; i < submit->nr_bos; i++) {
		struct msm_gem_object *msm_obj = submit->bos[i].obj;
		uint64_t iova;

		/* can't happen yet.. but when we add 2d support we'll have
		 * to deal w/ cross-ring synchronization:
		 */
		WARN_ON(is_active(msm_obj) && (msm_obj->gpu != gpu));

		/* submit takes a reference to the bo and iova until retired: */
		drm_gem_object_reference(&msm_obj->base);
		msm_gem_get_iova(&msm_obj->base,
				submit->gpu->aspace, &iova);

		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
			msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
			msm_gem_move_to_active(&msm_obj->base, gpu, false, submit->fence);
	}

	gpu->funcs->submit(gpu, submit, ctx);
	priv->lastctx = ctx;

	hangcheck_timer_reset(gpu);
}

/*
 * Init/Cleanup:
 */

static irqreturn_t irq_handler(int irq, void *data)
{
	struct msm_gpu *gpu = data;
	return gpu->funcs->irq(gpu);
}

static struct clk *get_clock(struct device *dev, const char *name)
{
	struct clk *clk = devm_clk_get(dev, name);

	return IS_ERR(clk) ? NULL : clk;
}

static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu)
{
	struct device *dev = &pdev->dev;
	struct property *prop;
	const char *name;
	int i = 0;

	gpu->nr_clocks = of_property_count_strings(dev->of_node, "clock-names");
	if (gpu->nr_clocks < 1) {
		gpu->nr_clocks = 0;
		return 0;
	}

	gpu->grp_clks = devm_kcalloc(dev, sizeof(struct clk *), gpu->nr_clocks,
		GFP_KERNEL);
	if (!gpu->grp_clks)
		return -ENOMEM;

	of_property_for_each_string(dev->of_node, "clock-names", prop, name) {
		gpu->grp_clks[i] = get_clock(dev, name);

		/* Remember the key clocks that we need to control later */
		if (!strcmp(name, "core") || !strcmp(name, "core_clk"))
			gpu->core_clk = gpu->grp_clks[i];
		else if (!strcmp(name, "rbbmtimer") || !strcmp(name, "rbbmtimer_clk"))
			gpu->rbbmtimer_clk = gpu->grp_clks[i];

		++i;
	}

	return 0;
}

static struct msm_gem_address_space *
msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
		uint64_t va_start, uint64_t va_end)
{
	struct iommu_domain *iommu;
	struct msm_gem_address_space *aspace;
	int ret;

	/*
	 * Setup IOMMU.. eventually we will (I think) do this once per context
	 * and have separate page tables per context.  For now, to keep things
	 * simple and to get something working, just use a single address space:
	 */
	iommu = iommu_domain_alloc(&platform_bus_type);
	if (!iommu)
		return NULL;

	iommu->geometry.aperture_start = va_start;
	iommu->geometry.aperture_end = va_end;

	dev_info(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);

	aspace = msm_gem_address_space_create(&pdev->dev, iommu, "gpu");
	if (IS_ERR(aspace)) {
		dev_err(gpu->dev->dev, "failed to init iommu: %ld\n",
			PTR_ERR(aspace));
		iommu_domain_free(iommu);
		return ERR_CAST(aspace);
	}

	ret = aspace->mmu->funcs->attach(aspace->mmu, NULL, 0);
	if (ret) {
		msm_gem_address_space_put(aspace);
		return ERR_PTR(ret);
	}

	return aspace;
}

int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
		const char *name, struct msm_gpu_config *config)
{
	int ret;

	if (WARN_ON(gpu->num_perfcntrs > ARRAY_SIZE(gpu->last_cntrs)))
		gpu->num_perfcntrs = ARRAY_SIZE(gpu->last_cntrs);

	gpu->dev = drm;
	gpu->funcs = funcs;
	gpu->name = name;
	gpu->fctx = msm_fence_context_alloc(drm, name);
	if (IS_ERR(gpu->fctx)) {
		ret = PTR_ERR(gpu->fctx);
		gpu->fctx = NULL;
		goto fail;
	}

	INIT_LIST_HEAD(&gpu->active_list);
	INIT_WORK(&gpu->retire_work, retire_worker);
	INIT_WORK(&gpu->recover_work, recover_worker);

	INIT_LIST_HEAD(&gpu->submit_list);

	setup_timer(&gpu->hangcheck_timer, hangcheck_handler,
			(unsigned long)gpu);

	spin_lock_init(&gpu->perf_lock);


	/* Map registers: */
	gpu->mmio = msm_ioremap(pdev, config->ioname, name);
	if (IS_ERR(gpu->mmio)) {
		ret = PTR_ERR(gpu->mmio);
		goto fail;
	}

	/* Get Interrupt: */
	gpu->irq = platform_get_irq_byname(pdev, config->irqname);
	if (gpu->irq < 0) {
		ret = gpu->irq;
		dev_err(drm->dev, "failed to get irq: %d\n", ret);
		goto fail;
	}

	ret = devm_request_irq(&pdev->dev, gpu->irq, irq_handler,
			IRQF_TRIGGER_HIGH, gpu->name, gpu);
	if (ret) {
		dev_err(drm->dev, "failed to request IRQ%u: %d\n", gpu->irq, ret);
		goto fail;
	}

	ret = get_clocks(pdev, gpu);
	if (ret)
		goto fail;

	gpu->ebi1_clk = msm_clk_get(pdev, "bus");
	DBG("ebi1_clk: %p", gpu->ebi1_clk);
	if (IS_ERR(gpu->ebi1_clk))
		gpu->ebi1_clk = NULL;

	/* Acquire regulators: */
	gpu->gpu_reg = devm_regulator_get(&pdev->dev, "vdd");
	DBG("gpu_reg: %p", gpu->gpu_reg);
	if (IS_ERR(gpu->gpu_reg))
		gpu->gpu_reg = NULL;

	gpu->gpu_cx = devm_regulator_get(&pdev->dev, "vddcx");
	DBG("gpu_cx: %p", gpu->gpu_cx);
	if (IS_ERR(gpu->gpu_cx))
		gpu->gpu_cx = NULL;

	gpu->pdev = pdev;
	platform_set_drvdata(pdev, gpu);

	bs_init(gpu);

	gpu->aspace = msm_gpu_create_address_space(gpu, pdev,
		config->va_start, config->va_end);

	if (gpu->aspace == NULL)
		dev_info(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);
	else if (IS_ERR(gpu->aspace)) {
		ret = PTR_ERR(gpu->aspace);
		goto fail;
	}

	/* Create ringbuffer: */
	gpu->rb = msm_ringbuffer_new(gpu, config->ringsz);
	if (IS_ERR(gpu->rb)) {
		ret = PTR_ERR(gpu->rb);
		gpu->rb = NULL;
		dev_err(drm->dev, "could not create ringbuffer: %d\n", ret);
		goto fail;
	}

	return 0;

fail:
	platform_set_drvdata(pdev, NULL);
	return ret;
}

void msm_gpu_cleanup(struct msm_gpu *gpu)
{
	DBG("%s", gpu->name);

	WARN_ON(!list_empty(&gpu->active_list));

	bs_fini(gpu);

	if (gpu->rb) {
		if (gpu->rb_iova)
			msm_gem_put_iova(gpu->rb->bo, gpu->aspace);
		msm_ringbuffer_destroy(gpu->rb);
	}
	if (gpu->aspace) {
		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
			NULL, 0);
		msm_gem_address_space_put(gpu->aspace);
	}
}