summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
blob: 6fb8c2f9b9e44e9b8e0d7654e0c0804f5c4eb14d (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
/* Copyright (c) 2016-2017 The Linux Foundation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 and
 * only 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.
 *
 */
#ifndef __A5XX_GPU_H__
#define __A5XX_GPU_H__

#include "adreno_gpu.h"

/* Bringing over the hack from the previous targets */
#undef ROP_COPY
#undef ROP_XOR

#include "a5xx.xml.h"

struct a5xx_gpu {
	struct adreno_gpu base;

	struct drm_gem_object *pm4_bo;
	uint64_t pm4_iova;

	struct drm_gem_object *pfp_bo;
	uint64_t pfp_iova;

	struct drm_gem_object *gpmu_bo;
	uint64_t gpmu_iova;
	uint32_t gpmu_dwords;

	uint32_t lm_leakage;

	struct msm_ringbuffer *cur_ring;
	struct msm_ringbuffer *next_ring;

	struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS];
	struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
	uint64_t preempt_iova[MSM_GPU_MAX_RINGS];

	atomic_t preempt_state;
	struct timer_list preempt_timer;
};

#define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base)

/*
 * In order to do lockless preemption we use a simple state machine to progress
 * through the process.
 *
 * PREEMPT_NONE - no preemption in progress.  Next state START.
 * PREEMPT_START - The trigger is evaulating if preemption is possible. Next
 * states: TRIGGERED, NONE
 * PREEMPT_ABORT - An intermediate state before moving back to NONE. Next
 * state: NONE.
 * PREEMPT_TRIGGERED: A preemption has been executed on the hardware. Next
 * states: FAULTED, PENDING
 * PREEMPT_FAULTED: A preemption timed out (never completed). This will trigger
 * recovery.  Next state: N/A
 * PREEMPT_PENDING: Preemption complete interrupt fired - the callback is
 * checking the success of the operation. Next state: FAULTED, NONE.
 */

enum preempt_state {
	PREEMPT_NONE = 0,
	PREEMPT_START,
	PREEMPT_ABORT,
	PREEMPT_TRIGGERED,
	PREEMPT_FAULTED,
	PREEMPT_PENDING,
};

/*
 * struct a5xx_preempt_record is a shared buffer between the microcode and the
 * CPU to store the state for preemption. The record itself is much larger
 * (64k) but most of that is used by the CP for storage.
 *
 * There is a preemption record assigned per ringbuffer. When the CPU triggers a
 * preemption, it fills out the record with the useful information (wptr, ring
 * base, etc) and the microcode uses that information to set up the CP following
 * the preemption.  When a ring is switched out, the CP will save the ringbuffer
 * state back to the record. In this way, once the records are properly set up
 * the CPU can quickly switch back and forth between ringbuffers by only
 * updating a few registers (often only the wptr).
 *
 * These are the CPU aware registers in the record:
 * @magic: Must always be 0x27C4BAFC
 * @info: Type of the record - written 0 by the CPU, updated by the CP
 * @data: Data field from SET_RENDER_MODE or a checkpoint. Written and used by
 * the CP
 * @cntl: Value of RB_CNTL written by CPU, save/restored by CP
 * @rptr: Value of RB_RPTR written by CPU, save/restored by CP
 * @wptr: Value of RB_WPTR written by CPU, save/restored by CP
 * @rptr_addr: Value of RB_RPTR_ADDR written by CPU, save/restored by CP
 * @rbase: Value of RB_BASE written by CPU, save/restored by CP
 * @counter: GPU address of the storage area for the performance counters
 */
struct a5xx_preempt_record {
	uint32_t magic;
	uint32_t info;
	uint32_t data;
	uint32_t cntl;
	uint32_t rptr;
	uint32_t wptr;
	uint64_t rptr_addr;
	uint64_t rbase;
	uint64_t counter;
};

/* Magic identifier for the preemption record */
#define A5XX_PREEMPT_RECORD_MAGIC 0x27C4BAFCUL

/*
 * Even though the structure above is only a few bytes, we need a full 64k to
 * store the entire preemption record from the CP
 */
#define A5XX_PREEMPT_RECORD_SIZE (64 * 1024)

/*
 * The preemption counter block is a storage area for the value of the
 * preemption counters that are saved immediately before context switch. We
 * append it on to the end of the allocation for the preemption record.
 */
#define A5XX_PREEMPT_COUNTER_SIZE (16 * 4)


int a5xx_power_init(struct msm_gpu *gpu);
void a5xx_gpmu_ucode_init(struct msm_gpu *gpu);

static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs,
		uint32_t reg, uint32_t mask, uint32_t value)
{
	while (usecs--) {
		udelay(1);
		if ((gpu_read(gpu, reg) & mask) == value)
			return 0;
		cpu_relax();
	}

	return -ETIMEDOUT;
}

bool a5xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
void a5xx_set_hwcg(struct msm_gpu *gpu, bool state);

void a5xx_preempt_init(struct msm_gpu *gpu);
void a5xx_preempt_hw_init(struct msm_gpu *gpu);
void a5xx_preempt_trigger(struct msm_gpu *gpu);
void a5xx_preempt_irq(struct msm_gpu *gpu);
void a5xx_preempt_fini(struct msm_gpu *gpu);

/* Return true if we are in a preempt state */
static inline bool a5xx_in_preempt(struct a5xx_gpu *a5xx_gpu)
{
	int preempt_state = atomic_read(&a5xx_gpu->preempt_state);

	return !(preempt_state == PREEMPT_NONE ||
			preempt_state == PREEMPT_ABORT);
}

#endif /* __A5XX_GPU_H__ */