summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/adreno/adreno_gpu.h
blob: 99bb468f5f245ef4f0b2473d56628e2daed4b4bc (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 *
 * Copyright (c) 2014,2017, 2019 The Linux Foundation. All rights reserved.
 */

#ifndef __ADRENO_GPU_H__
#define __ADRENO_GPU_H__

#include <linux/firmware.h>
#include <linux/iopoll.h>

#include "msm_gpu.h"

#include "adreno_common.xml.h"
#include "adreno_pm4.xml.h"

#define REG_ADRENO_DEFINE(_offset, _reg) [_offset] = (_reg) + 1
#define REG_SKIP ~0
#define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP

/**
 * adreno_regs: List of registers that are used in across all
 * 3D devices. Each device type has different offset value for the same
 * register, so an array of register offsets are declared for every device
 * and are indexed by the enumeration values defined in this enum
 */
enum adreno_regs {
	REG_ADRENO_CP_RB_BASE,
	REG_ADRENO_CP_RB_BASE_HI,
	REG_ADRENO_CP_RB_RPTR_ADDR,
	REG_ADRENO_CP_RB_RPTR_ADDR_HI,
	REG_ADRENO_CP_RB_RPTR,
	REG_ADRENO_CP_RB_WPTR,
	REG_ADRENO_CP_RB_CNTL,
	REG_ADRENO_REGISTER_MAX,
};

enum {
	ADRENO_FW_PM4 = 0,
	ADRENO_FW_SQE = 0, /* a6xx */
	ADRENO_FW_PFP = 1,
	ADRENO_FW_GMU = 1, /* a6xx */
	ADRENO_FW_GPMU = 2,
	ADRENO_FW_MAX,
};

enum adreno_quirks {
	ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
	ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
	ADRENO_QUIRK_LMLOADKILL_DISABLE = 3,
};

struct adreno_rev {
	uint8_t  core;
	uint8_t  major;
	uint8_t  minor;
	uint8_t  patchid;
};

#define ADRENO_REV(core, major, minor, patchid) \
	((struct adreno_rev){ core, major, minor, patchid })

struct adreno_gpu_funcs {
	struct msm_gpu_funcs base;
	int (*get_timestamp)(struct msm_gpu *gpu, uint64_t *value);
};

struct adreno_reglist {
	u32 offset;
	u32 value;
};

extern const struct adreno_reglist a630_hwcg[], a640_hwcg[], a650_hwcg[];

struct adreno_info {
	struct adreno_rev rev;
	uint32_t revn;
	const char *name;
	const char *fw[ADRENO_FW_MAX];
	uint32_t gmem;
	enum adreno_quirks quirks;
	struct msm_gpu *(*init)(struct drm_device *dev);
	const char *zapfw;
	u32 inactive_period;
	const struct adreno_reglist *hwcg;
};

const struct adreno_info *adreno_info(struct adreno_rev rev);

struct adreno_gpu {
	struct msm_gpu base;
	struct adreno_rev rev;
	const struct adreno_info *info;
	uint32_t gmem;  /* actual gmem size */
	uint32_t revn;  /* numeric revision name */
	const struct adreno_gpu_funcs *funcs;

	/* interesting register offsets to dump: */
	const unsigned int *registers;

	/*
	 * Are we loading fw from legacy path?  Prior to addition
	 * of gpu firmware to linux-firmware, the fw files were
	 * placed in toplevel firmware directory, following qcom's
	 * android kernel.  But linux-firmware preferred they be
	 * placed in a 'qcom' subdirectory.
	 *
	 * For backwards compatibility, we try first to load from
	 * the new path, using request_firmware_direct() to avoid
	 * any potential timeout waiting for usermode helper, then
	 * fall back to the old path (with direct load).  And
	 * finally fall back to request_firmware() with the new
	 * path to allow the usermode helper.
	 */
	enum {
		FW_LOCATION_UNKNOWN = 0,
		FW_LOCATION_NEW,       /* /lib/firmware/qcom/$fwfile */
		FW_LOCATION_LEGACY,    /* /lib/firmware/$fwfile */
		FW_LOCATION_HELPER,
	} fwloc;

	/* firmware: */
	const struct firmware *fw[ADRENO_FW_MAX];

	/*
	 * Register offsets are different between some GPUs.
	 * GPU specific offsets will be exported by GPU specific
	 * code (a3xx_gpu.c) and stored in this common location.
	 */
	const unsigned int *reg_offsets;
};
#define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)

struct adreno_ocmem {
	struct ocmem *ocmem;
	unsigned long base;
	void *hdl;
};

/* platform config data (ie. from DT, or pdata) */
struct adreno_platform_config {
	struct adreno_rev rev;
};

#define ADRENO_IDLE_TIMEOUT msecs_to_jiffies(1000)

#define spin_until(X) ({                                   \
	int __ret = -ETIMEDOUT;                            \
	unsigned long __t = jiffies + ADRENO_IDLE_TIMEOUT; \
	do {                                               \
		if (X) {                                   \
			__ret = 0;                         \
			break;                             \
		}                                          \
	} while (time_before(jiffies, __t));               \
	__ret;                                             \
})

static inline bool adreno_is_a2xx(struct adreno_gpu *gpu)
{
	return (gpu->revn < 300);
}

static inline bool adreno_is_a20x(struct adreno_gpu *gpu)
{
	return (gpu->revn < 210);
}

static inline bool adreno_is_a225(struct adreno_gpu *gpu)
{
	return gpu->revn == 225;
}

static inline bool adreno_is_a3xx(struct adreno_gpu *gpu)
{
	return (gpu->revn >= 300) && (gpu->revn < 400);
}

static inline bool adreno_is_a305(struct adreno_gpu *gpu)
{
	return gpu->revn == 305;
}

static inline bool adreno_is_a306(struct adreno_gpu *gpu)
{
	/* yes, 307, because a305c is 306 */
	return gpu->revn == 307;
}

static inline bool adreno_is_a320(struct adreno_gpu *gpu)
{
	return gpu->revn == 320;
}

static inline bool adreno_is_a330(struct adreno_gpu *gpu)
{
	return gpu->revn == 330;
}

static inline bool adreno_is_a330v2(struct adreno_gpu *gpu)
{
	return adreno_is_a330(gpu) && (gpu->rev.patchid > 0);
}

static inline bool adreno_is_a4xx(struct adreno_gpu *gpu)
{
	return (gpu->revn >= 400) && (gpu->revn < 500);
}

static inline int adreno_is_a405(struct adreno_gpu *gpu)
{
	return gpu->revn == 405;
}

static inline int adreno_is_a420(struct adreno_gpu *gpu)
{
	return gpu->revn == 420;
}

static inline int adreno_is_a430(struct adreno_gpu *gpu)
{
       return gpu->revn == 430;
}

static inline int adreno_is_a510(struct adreno_gpu *gpu)
{
	return gpu->revn == 510;
}

static inline int adreno_is_a530(struct adreno_gpu *gpu)
{
	return gpu->revn == 530;
}

static inline int adreno_is_a540(struct adreno_gpu *gpu)
{
	return gpu->revn == 540;
}

static inline int adreno_is_a618(struct adreno_gpu *gpu)
{
       return gpu->revn == 618;
}

static inline int adreno_is_a630(struct adreno_gpu *gpu)
{
       return gpu->revn == 630;
}

static inline int adreno_is_a640(struct adreno_gpu *gpu)
{
       return gpu->revn == 640;
}

static inline int adreno_is_a650(struct adreno_gpu *gpu)
{
       return gpu->revn == 650;
}

int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu,
		const char *fwname);
struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
		const struct firmware *fw, u64 *iova);
int adreno_hw_init(struct msm_gpu *gpu);
void adreno_recover(struct msm_gpu *gpu);
void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
		struct msm_file_private *ctx);
void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
		struct drm_printer *p);
#endif
void adreno_dump_info(struct msm_gpu *gpu);
void adreno_dump(struct msm_gpu *gpu);
void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords);
struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu);

int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
			  struct adreno_ocmem *ocmem);
void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *ocmem);

int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
		int nr_rings);
void adreno_gpu_cleanup(struct adreno_gpu *gpu);
int adreno_load_fw(struct adreno_gpu *adreno_gpu);

void adreno_gpu_state_destroy(struct msm_gpu_state *state);

int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
int adreno_gpu_state_put(struct msm_gpu_state *state);

/*
 * Common helper function to initialize the default address space for arm-smmu
 * attached targets
 */
struct msm_gem_address_space *
adreno_iommu_create_address_space(struct msm_gpu *gpu,
		struct platform_device *pdev);

/*
 * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
 * out of secure mode
 */
int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid);

/* ringbuffer helpers (the parts that are adreno specific) */

static inline void
OUT_PKT0(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt)
{
	adreno_wait_ring(ring, cnt+1);
	OUT_RING(ring, CP_TYPE0_PKT | ((cnt-1) << 16) | (regindx & 0x7FFF));
}

/* no-op packet: */
static inline void
OUT_PKT2(struct msm_ringbuffer *ring)
{
	adreno_wait_ring(ring, 1);
	OUT_RING(ring, CP_TYPE2_PKT);
}

static inline void
OUT_PKT3(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
{
	adreno_wait_ring(ring, cnt+1);
	OUT_RING(ring, CP_TYPE3_PKT | ((cnt-1) << 16) | ((opcode & 0xFF) << 8));
}

static inline u32 PM4_PARITY(u32 val)
{
	return (0x9669 >> (0xF & (val ^
		(val >> 4) ^ (val >> 8) ^ (val >> 12) ^
		(val >> 16) ^ ((val) >> 20) ^ (val >> 24) ^
		(val >> 28)))) & 1;
}

/* Maximum number of values that can be executed for one opcode */
#define TYPE4_MAX_PAYLOAD 127

#define PKT4(_reg, _cnt) \
	(CP_TYPE4_PKT | ((_cnt) << 0) | (PM4_PARITY((_cnt)) << 7) | \
	 (((_reg) & 0x3FFFF) << 8) | (PM4_PARITY((_reg)) << 27))

static inline void
OUT_PKT4(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt)
{
	adreno_wait_ring(ring, cnt + 1);
	OUT_RING(ring, PKT4(regindx, cnt));
}

static inline void
OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
{
	adreno_wait_ring(ring, cnt + 1);
	OUT_RING(ring, CP_TYPE7_PKT | (cnt << 0) | (PM4_PARITY(cnt) << 15) |
		((opcode & 0x7F) << 16) | (PM4_PARITY(opcode) << 23));
}

/*
 * adreno_reg_check() - Checks the validity of a register enum
 * @gpu:		Pointer to struct adreno_gpu
 * @offset_name:	The register enum that is checked
 */
static inline bool adreno_reg_check(struct adreno_gpu *gpu,
		enum adreno_regs offset_name)
{
	BUG_ON(offset_name >= REG_ADRENO_REGISTER_MAX || !gpu->reg_offsets[offset_name]);

	/*
	 * REG_SKIP is a special value that tell us that the register in
	 * question isn't implemented on target but don't trigger a BUG(). This
	 * is used to cleanly implement adreno_gpu_write64() and
	 * adreno_gpu_read64() in a generic fashion
	 */
	if (gpu->reg_offsets[offset_name] == REG_SKIP)
		return false;

	return true;
}

static inline u32 adreno_gpu_read(struct adreno_gpu *gpu,
		enum adreno_regs offset_name)
{
	u32 reg = gpu->reg_offsets[offset_name];
	u32 val = 0;
	if(adreno_reg_check(gpu,offset_name))
		val = gpu_read(&gpu->base, reg - 1);
	return val;
}

static inline void adreno_gpu_write(struct adreno_gpu *gpu,
		enum adreno_regs offset_name, u32 data)
{
	u32 reg = gpu->reg_offsets[offset_name];
	if(adreno_reg_check(gpu, offset_name))
		gpu_write(&gpu->base, reg - 1, data);
}

struct msm_gpu *a2xx_gpu_init(struct drm_device *dev);
struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
struct msm_gpu *a4xx_gpu_init(struct drm_device *dev);
struct msm_gpu *a5xx_gpu_init(struct drm_device *dev);
struct msm_gpu *a6xx_gpu_init(struct drm_device *dev);

static inline void adreno_gpu_write64(struct adreno_gpu *gpu,
		enum adreno_regs lo, enum adreno_regs hi, u64 data)
{
	adreno_gpu_write(gpu, lo, lower_32_bits(data));
	adreno_gpu_write(gpu, hi, upper_32_bits(data));
}

static inline uint32_t get_wptr(struct msm_ringbuffer *ring)
{
	return (ring->cur - ring->start) % (MSM_GPU_RINGBUFFER_SZ >> 2);
}

/*
 * Given a register and a count, return a value to program into
 * REG_CP_PROTECT_REG(n) - this will block both reads and writes for _len
 * registers starting at _reg.
 *
 * The register base needs to be a multiple of the length. If it is not, the
 * hardware will quietly mask off the bits for you and shift the size. For
 * example, if you intend the protection to start at 0x07 for a length of 4
 * (0x07-0x0A) the hardware will actually protect (0x04-0x07) which might
 * expose registers you intended to protect!
 */
#define ADRENO_PROTECT_RW(_reg, _len) \
	((1 << 30) | (1 << 29) | \
	((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF))

/*
 * Same as above, but allow reads over the range. For areas of mixed use (such
 * as performance counters) this allows us to protect a much larger range with a
 * single register
 */
#define ADRENO_PROTECT_RDONLY(_reg, _len) \
	((1 << 29) \
	((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF))


#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
		interval, timeout)

#endif /* __ADRENO_GPU_H__ */