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
|
/*
* 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/>.
*/
#ifndef __MSM_GPU_H__
#define __MSM_GPU_H__
#include <linux/clk.h>
#include <linux/regulator/consumer.h>
#include "msm_drv.h"
#include "msm_ringbuffer.h"
struct msm_gem_submit;
struct msm_gpu_perfcntr;
/* 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);
int (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit,
struct msm_file_private *ctx);
void (*flush)(struct msm_gpu *gpu);
void (*idle)(struct msm_gpu *gpu);
irqreturn_t (*irq)(struct msm_gpu *irq);
uint32_t (*last_fence)(struct msm_gpu *gpu);
void (*recover)(struct msm_gpu *gpu);
void (*destroy)(struct msm_gpu *gpu);
#ifdef CONFIG_DEBUG_FS
/* show GPU status in debugfs: */
void (*show)(struct msm_gpu *gpu, struct seq_file *m);
#endif
};
struct msm_gpu {
const char *name;
struct drm_device *dev;
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;
uint32_t rb_iova;
/* list of GEM active objects: */
struct list_head active_list;
uint32_t submitted_fence;
/* is gpu powered/active? */
int active_cnt;
bool inactive;
/* worker for handling active-list retiring: */
struct work_struct retire_work;
void __iomem *mmio;
int irq;
struct msm_mmu *mmu;
int id;
/* Power Control: */
struct regulator *gpu_reg, *gpu_cx;
struct clk *ebi1_clk, *grp_clks[6];
uint32_t fast_rate, slow_rate, bus_freq;
#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
struct msm_bus_scale_pdata *bus_scale_table;
uint32_t bsc;
#endif
/* Hang and Inactivity Detection:
*/
#define DRM_MSM_INACTIVE_PERIOD 66 /* in ms (roughly four frames) */
#define DRM_MSM_INACTIVE_JIFFIES msecs_to_jiffies(DRM_MSM_INACTIVE_PERIOD)
struct timer_list inactive_timer;
struct work_struct inactive_work;
#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;
uint32_t hangcheck_fence;
struct work_struct recover_work;
struct list_head submit_list;
};
static inline bool msm_gpu_active(struct msm_gpu *gpu)
{
return gpu->submitted_fence > gpu->funcs->last_fence(gpu);
}
/* 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;
};
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));
}
int msm_gpu_pm_suspend(struct msm_gpu *gpu);
int msm_gpu_pm_resume(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);
int 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, const char *ioname, const char *irqname, int ringsz);
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);
#endif /* __MSM_GPU_H__ */
|
