aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/msm/msm_gpu.c
blob: e1e1ec9321ffe5d8db74e53a5d52b8a4122a51d9 (plain) (blame)
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
/*
 * 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"


/*
 * Power Management:
 */

#ifdef CONFIG_MSM_BUS_SCALING
#include <mach/board.h>
#include <mach/kgsl.h>
static void bs_init(struct msm_gpu *gpu, struct platform_device *pdev)
{
	struct drm_device *dev = gpu->dev;
	struct kgsl_device_platform_data *pdata = pdev->dev.platform_data;

	if (!pdev) {
		dev_err(dev->dev, "could not find dtv pdata\n");
		return;
	}

	if (pdata->bus_scale_table) {
		gpu->bsc = msm_bus_scale_register_client(pdata->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, struct platform_device *pdev) {}
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)
{
	struct clk *rate_clk = NULL;
	int i;

	/* NOTE: kgsl_pwrctrl_clk() ignores grp_clks[0].. */
	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--) {
		if (gpu->grp_clks[i]) {
			clk_prepare(gpu->grp_clks[i]);
			rate_clk = gpu->grp_clks[i];
		}
	}

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

	for (i = ARRAY_SIZE(gpu->grp_clks) - 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)
{
	struct clk *rate_clk = NULL;
	int i;

	/* NOTE: kgsl_pwrctrl_clk() ignores grp_clks[0].. */
	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--) {
		if (gpu->grp_clks[i]) {
			clk_disable(gpu->grp_clks[i]);
			rate_clk = gpu->grp_clks[i];
		}
	}

	if (rate_clk && gpu->slow_rate)
		clk_set_rate(rate_clk, gpu->slow_rate);

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

	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;

	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;
}

/*
 * Hangcheck detection for locked 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;

	dev_err(dev->dev, "%s: hangcheck recover!\n", gpu->name);

	mutex_lock(&dev->struct_mutex);
	gpu->funcs->recover(gpu);
	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;
	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->submitted_fence) {
		/* no progress and not done.. hung! */
		struct msm_drm_private *priv = gpu->dev->dev_private;
		gpu->hangcheck_fence = fence;
		queue_work(priv->wq, &gpu->recover_work);
	}

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

/*
 * Cmdstream submission/retirement:
 */

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);

	mutex_lock(&dev->struct_mutex);

	while (!list_empty(&gpu->active_list)) {
		struct msm_gem_object *obj;

		obj = list_first_entry(&gpu->active_list,
				struct msm_gem_object, mm_list);

		if (obj->fence <= fence) {
			/* move to inactive: */
			msm_gem_move_to_inactive(&obj->base);
			msm_gem_put_iova(&obj->base, gpu->id);
			drm_gem_object_unreference(&obj->base);
		} else {
			break;
		}
	}

	msm_update_fence(gpu->dev, fence);

	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);
}

/* add bo's to gpu's ring, and kick gpu: */
int 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, ret;

	mutex_lock(&dev->struct_mutex);

	submit->fence = ++priv->next_fence;

	gpu->submitted_fence = submit->fence;

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

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

		/* 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));

		if (!is_active(msm_obj)) {
			uint32_t iova;

			/* ring takes a reference to the bo and iova: */
			drm_gem_object_reference(&msm_obj->base);
			msm_gem_get_iova_locked(&msm_obj->base,
					submit->gpu->id, &iova);
		}

		msm_gem_move_to_active(&msm_obj->base, gpu, submit->fence);
	}
	hangcheck_timer_reset(gpu);
	mutex_unlock(&dev->struct_mutex);

	return ret;
}

/*
 * Init/Cleanup:
 */

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

static const char *clk_names[] = {
		"src_clk", "core_clk", "iface_clk", "mem_clk", "mem_iface_clk",
};

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, const char *ioname, const char *irqname, int ringsz)
{
	int i, ret;

	gpu->dev = drm;
	gpu->funcs = funcs;
	gpu->name = name;

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

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

	BUG_ON(ARRAY_SIZE(clk_names) != ARRAY_SIZE(gpu->grp_clks));

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

	/* Get Interrupt: */
	gpu->irq = platform_get_irq_byname(pdev, 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;
	}

	/* Acquire clocks: */
	for (i = 0; i < ARRAY_SIZE(clk_names); i++) {
		gpu->grp_clks[i] = devm_clk_get(&pdev->dev, clk_names[i]);
		DBG("grp_clks[%s]: %p", clk_names[i], gpu->grp_clks[i]);
		if (IS_ERR(gpu->grp_clks[i]))
			gpu->grp_clks[i] = NULL;
	}

	gpu->ebi1_clk = devm_clk_get(&pdev->dev, "bus_clk");
	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;

	/* 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:
	 */
	gpu->iommu = iommu_domain_alloc(&platform_bus_type);
	if (!gpu->iommu) {
		dev_err(drm->dev, "failed to allocate IOMMU\n");
		ret = -ENOMEM;
		goto fail;
	}
	gpu->id = msm_register_iommu(drm, gpu->iommu);

	/* Create ringbuffer: */
	gpu->rb = msm_ringbuffer_new(gpu, 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;
	}

	ret = msm_gem_get_iova_locked(gpu->rb->bo, gpu->id, &gpu->rb_iova);
	if (ret) {
		gpu->rb_iova = 0;
		dev_err(drm->dev, "could not map ringbuffer: %d\n", ret);
		goto fail;
	}

	bs_init(gpu, pdev);

	return 0;

fail:
	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->id);
		msm_ringbuffer_destroy(gpu->rb);
	}

	if (gpu->iommu)
		iommu_domain_free(gpu->iommu);
}