summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/msm_gpu.h
blob: 37cffac4cbe3428fbd91c2700d8ea957c328db81 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 */

#ifndef __MSM_GPU_H__
#define __MSM_GPU_H__

#include <linux/clk.h>
#include <linux/interconnect.h>
#include <linux/pm_opp.h>
#include <linux/regulator/consumer.h>

#include "msm_drv.h"
#include "msm_fence.h"
#include "msm_ringbuffer.h"
#include "msm_gem.h"

struct msm_gem_submit;
struct msm_gpu_perfcntr;
struct msm_gpu_state;

struct msm_gpu_config {
	const char *ioname;
	unsigned int nr_rings;
};

/* So far, with hardware that I've seen to date, we can have:
 *  + zero, one, or two z180 2d cores
 *  + a3xx or a2xx 3d core, which share a common CP (the firmware
 *    for the CP seems to implement some different PM4 packet types
 *    but the basics of cmdstream submission are the same)
 *
 * Which means that the eventual complete "class" hierarchy, once
 * support for all past and present hw is in place, becomes:
 *  + msm_gpu
 *    + adreno_gpu
 *      + a3xx_gpu
 *      + a2xx_gpu
 *    + z180_gpu
 */
struct msm_gpu_funcs {
	int (*get_param)(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
	int (*hw_init)(struct msm_gpu *gpu);
	int (*pm_suspend)(struct msm_gpu *gpu);
	int (*pm_resume)(struct msm_gpu *gpu);
	void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit,
			struct msm_file_private *ctx);
	void (*flush)(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
	irqreturn_t (*irq)(struct msm_gpu *irq);
	struct msm_ringbuffer *(*active_ring)(struct msm_gpu *gpu);
	void (*recover)(struct msm_gpu *gpu);
	void (*destroy)(struct msm_gpu *gpu);
#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
	/* show GPU status in debugfs: */
	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
			struct drm_printer *p);
	/* for generation specific debugfs: */
	void (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
#endif
	unsigned long (*gpu_busy)(struct msm_gpu *gpu);
	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
	int (*gpu_state_put)(struct msm_gpu_state *state);
	unsigned long (*gpu_get_freq)(struct msm_gpu *gpu);
	void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp);
	struct msm_gem_address_space *(*create_address_space)
		(struct msm_gpu *gpu, struct platform_device *pdev);
};

struct msm_gpu {
	const char *name;
	struct drm_device *dev;
	struct platform_device *pdev;
	const struct msm_gpu_funcs *funcs;

	/* performance counters (hw & sw): */
	spinlock_t perf_lock;
	bool perfcntr_active;
	struct {
		bool active;
		ktime_t time;
	} last_sample;
	uint32_t totaltime, activetime;    /* sw counters */
	uint32_t last_cntrs[5];            /* hw counters */
	const struct msm_gpu_perfcntr *perfcntrs;
	uint32_t num_perfcntrs;

	struct msm_ringbuffer *rb[MSM_GPU_MAX_RINGS];
	int nr_rings;

	/* list of GEM active objects: */
	struct list_head active_list;

	/* does gpu need hw_init? */
	bool needs_hw_init;

	/* number of GPU hangs (for all contexts) */
	int global_faults;

	/* worker for handling active-list retiring: */
	struct work_struct retire_work;

	void __iomem *mmio;
	int irq;

	struct msm_gem_address_space *aspace;

	/* Power Control: */
	struct regulator *gpu_reg, *gpu_cx;
	struct clk_bulk_data *grp_clks;
	int nr_clocks;
	struct clk *ebi1_clk, *core_clk, *rbbmtimer_clk;
	uint32_t fast_rate;

	/* The gfx-mem interconnect path that's used by all GPU types. */
	struct icc_path *icc_path;

	/*
	 * Second interconnect path for some A3xx and all A4xx GPUs to the
	 * On Chip MEMory (OCMEM).
	 */
	struct icc_path *ocmem_icc_path;

	/* Hang and Inactivity Detection:
	 */
#define DRM_MSM_INACTIVE_PERIOD   66 /* in ms (roughly four frames) */

#define DRM_MSM_HANGCHECK_PERIOD 500 /* in ms */
#define DRM_MSM_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_MSM_HANGCHECK_PERIOD)
	struct timer_list hangcheck_timer;
	struct work_struct recover_work;

	struct drm_gem_object *memptrs_bo;

	struct {
		struct devfreq *devfreq;
		u64 busy_cycles;
		ktime_t time;
	} devfreq;

	struct msm_gpu_state *crashstate;
	/* True if the hardware supports expanded apriv (a650 and newer) */
	bool hw_apriv;
};

/* It turns out that all targets use the same ringbuffer size */
#define MSM_GPU_RINGBUFFER_SZ SZ_32K
#define MSM_GPU_RINGBUFFER_BLKSIZE 32

#define MSM_GPU_RB_CNTL_DEFAULT \
		(AXXX_CP_RB_CNTL_BUFSZ(ilog2(MSM_GPU_RINGBUFFER_SZ / 8)) | \
		AXXX_CP_RB_CNTL_BLKSZ(ilog2(MSM_GPU_RINGBUFFER_BLKSIZE / 8)))

static inline bool msm_gpu_active(struct msm_gpu *gpu)
{
	int i;

	for (i = 0; i < gpu->nr_rings; i++) {
		struct msm_ringbuffer *ring = gpu->rb[i];

		if (ring->seqno > ring->memptrs->fence)
			return true;
	}

	return false;
}

/* Perf-Counters:
 * The select_reg and select_val are just there for the benefit of the child
 * class that actually enables the perf counter..  but msm_gpu base class
 * will handle sampling/displaying the counters.
 */

struct msm_gpu_perfcntr {
	uint32_t select_reg;
	uint32_t sample_reg;
	uint32_t select_val;
	const char *name;
};

struct msm_gpu_submitqueue {
	int id;
	u32 flags;
	u32 prio;
	int faults;
	struct list_head node;
	struct kref ref;
};

struct msm_gpu_state_bo {
	u64 iova;
	size_t size;
	void *data;
	bool encoded;
};

struct msm_gpu_state {
	struct kref ref;
	struct timespec64 time;

	struct {
		u64 iova;
		u32 fence;
		u32 seqno;
		u32 rptr;
		u32 wptr;
		void *data;
		int data_size;
		bool encoded;
	} ring[MSM_GPU_MAX_RINGS];

	int nr_registers;
	u32 *registers;

	u32 rbbm_status;

	char *comm;
	char *cmd;

	int nr_bos;
	struct msm_gpu_state_bo *bos;
};

static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
{
	msm_writel(data, gpu->mmio + (reg << 2));
}

static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg)
{
	return msm_readl(gpu->mmio + (reg << 2));
}

static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or)
{
	uint32_t val = gpu_read(gpu, reg);

	val &= ~mask;
	gpu_write(gpu, reg, val | or);
}

static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
{
	u64 val;

	/*
	 * Why not a readq here? Two reasons: 1) many of the LO registers are
	 * not quad word aligned and 2) the GPU hardware designers have a bit
	 * of a history of putting registers where they fit, especially in
	 * spins. The longer a GPU family goes the higher the chance that
	 * we'll get burned.  We could do a series of validity checks if we
	 * wanted to, but really is a readq() that much better? Nah.
	 */

	/*
	 * For some lo/hi registers (like perfcounters), the hi value is latched
	 * when the lo is read, so make sure to read the lo first to trigger
	 * that
	 */
	val = (u64) msm_readl(gpu->mmio + (lo << 2));
	val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32);

	return val;
}

static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
{
	/* Why not a writeq here? Read the screed above */
	msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2));
	msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2));
}

int msm_gpu_pm_suspend(struct msm_gpu *gpu);
int msm_gpu_pm_resume(struct msm_gpu *gpu);
void msm_gpu_resume_devfreq(struct msm_gpu *gpu);

int msm_gpu_hw_init(struct msm_gpu *gpu);

void msm_gpu_perfcntr_start(struct msm_gpu *gpu);
void msm_gpu_perfcntr_stop(struct msm_gpu *gpu);
int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime,
		uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs);

void msm_gpu_retire(struct msm_gpu *gpu);
void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
		struct msm_file_private *ctx);

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);

void msm_gpu_cleanup(struct msm_gpu *gpu);

struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
void __init adreno_register(void);
void __exit adreno_unregister(void);

static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue)
{
	if (queue)
		kref_put(&queue->ref, msm_submitqueue_destroy);
}

static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu)
{
	struct msm_gpu_state *state = NULL;

	mutex_lock(&gpu->dev->struct_mutex);

	if (gpu->crashstate) {
		kref_get(&gpu->crashstate->ref);
		state = gpu->crashstate;
	}

	mutex_unlock(&gpu->dev->struct_mutex);

	return state;
}

static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
{
	mutex_lock(&gpu->dev->struct_mutex);

	if (gpu->crashstate) {
		if (gpu->funcs->gpu_state_put(gpu->crashstate))
			gpu->crashstate = NULL;
	}

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

/*
 * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
 * support expanded privileges
 */
#define check_apriv(gpu, flags) \
	(((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags))


#endif /* __MSM_GPU_H__ */