summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/msm_perf.c
blob: 3d3da79fec2aaea362e3a2020822767a78cbefb1 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2013 Red Hat
 * Author: Rob Clark <robdclark@gmail.com>
 */

/* For profiling, userspace can:
 *
 *   tail -f /sys/kernel/debug/dri/<minor>/gpu
 *
 * This will enable performance counters/profiling to track the busy time
 * and any gpu specific performance counters that are supported.
 */

#ifdef CONFIG_DEBUG_FS

#include <linux/debugfs.h>
#include <linux/uaccess.h>

#include <drm/drm_file.h>

#include "msm_drv.h"
#include "msm_gpu.h"

struct msm_perf_state {
	struct drm_device *dev;

	bool open;
	int cnt;
	struct mutex read_lock;

	char buf[256];
	int buftot, bufpos;

	unsigned long next_jiffies;
};

#define SAMPLE_TIME (HZ/4)

/* wait for next sample time: */
static int wait_sample(struct msm_perf_state *perf)
{
	unsigned long start_jiffies = jiffies;

	if (time_after(perf->next_jiffies, start_jiffies)) {
		unsigned long remaining_jiffies =
			perf->next_jiffies - start_jiffies;
		int ret = schedule_timeout_interruptible(remaining_jiffies);
		if (ret > 0) {
			/* interrupted */
			return -ERESTARTSYS;
		}
	}
	perf->next_jiffies += SAMPLE_TIME;
	return 0;
}

static int refill_buf(struct msm_perf_state *perf)
{
	struct msm_drm_private *priv = perf->dev->dev_private;
	struct msm_gpu *gpu = priv->gpu;
	char *ptr = perf->buf;
	int rem = sizeof(perf->buf);
	int i, n;

	if ((perf->cnt++ % 32) == 0) {
		/* Header line: */
		n = snprintf(ptr, rem, "%%BUSY");
		ptr += n;
		rem -= n;

		for (i = 0; i < gpu->num_perfcntrs; i++) {
			const struct msm_gpu_perfcntr *perfcntr = &gpu->perfcntrs[i];
			n = snprintf(ptr, rem, "\t%s", perfcntr->name);
			ptr += n;
			rem -= n;
		}
	} else {
		/* Sample line: */
		uint32_t activetime = 0, totaltime = 0;
		uint32_t cntrs[5];
		uint32_t val;
		int ret;

		/* sleep until next sample time: */
		ret = wait_sample(perf);
		if (ret)
			return ret;

		ret = msm_gpu_perfcntr_sample(gpu, &activetime, &totaltime,
				ARRAY_SIZE(cntrs), cntrs);
		if (ret < 0)
			return ret;

		val = totaltime ? 1000 * activetime / totaltime : 0;
		n = snprintf(ptr, rem, "%3d.%d%%", val / 10, val % 10);
		ptr += n;
		rem -= n;

		for (i = 0; i < ret; i++) {
			/* cycle counters (I think).. convert to MHz.. */
			val = cntrs[i] / 10000;
			n = snprintf(ptr, rem, "\t%5d.%02d",
					val / 100, val % 100);
			ptr += n;
			rem -= n;
		}
	}

	n = snprintf(ptr, rem, "\n");
	ptr += n;
	rem -= n;

	perf->bufpos = 0;
	perf->buftot = ptr - perf->buf;

	return 0;
}

static ssize_t perf_read(struct file *file, char __user *buf,
		size_t sz, loff_t *ppos)
{
	struct msm_perf_state *perf = file->private_data;
	int n = 0, ret = 0;

	mutex_lock(&perf->read_lock);

	if (perf->bufpos >= perf->buftot) {
		ret = refill_buf(perf);
		if (ret)
			goto out;
	}

	n = min((int)sz, perf->buftot - perf->bufpos);
	if (copy_to_user(buf, &perf->buf[perf->bufpos], n)) {
		ret = -EFAULT;
		goto out;
	}

	perf->bufpos += n;
	*ppos += n;

out:
	mutex_unlock(&perf->read_lock);
	if (ret)
		return ret;
	return n;
}

static int perf_open(struct inode *inode, struct file *file)
{
	struct msm_perf_state *perf = inode->i_private;
	struct drm_device *dev = perf->dev;
	struct msm_drm_private *priv = dev->dev_private;
	struct msm_gpu *gpu = priv->gpu;
	int ret = 0;

	if (!gpu)
		return -ENODEV;

	mutex_lock(&gpu->lock);

	if (perf->open) {
		ret = -EBUSY;
		goto out;
	}

	file->private_data = perf;
	perf->open = true;
	perf->cnt = 0;
	perf->buftot = 0;
	perf->bufpos = 0;
	msm_gpu_perfcntr_start(gpu);
	perf->next_jiffies = jiffies + SAMPLE_TIME;

out:
	mutex_unlock(&gpu->lock);
	return ret;
}

static int perf_release(struct inode *inode, struct file *file)
{
	struct msm_perf_state *perf = inode->i_private;
	struct msm_drm_private *priv = perf->dev->dev_private;
	msm_gpu_perfcntr_stop(priv->gpu);
	perf->open = false;
	return 0;
}


static const struct file_operations perf_debugfs_fops = {
	.owner = THIS_MODULE,
	.open = perf_open,
	.read = perf_read,
	.llseek = no_llseek,
	.release = perf_release,
};

int msm_perf_debugfs_init(struct drm_minor *minor)
{
	struct msm_drm_private *priv = minor->dev->dev_private;
	struct msm_perf_state *perf;

	/* only create on first minor: */
	if (priv->perf)
		return 0;

	perf = kzalloc(sizeof(*perf), GFP_KERNEL);
	if (!perf)
		return -ENOMEM;

	perf->dev = minor->dev;

	mutex_init(&perf->read_lock);
	priv->perf = perf;

	debugfs_create_file("perf", S_IFREG | S_IRUGO, minor->debugfs_root,
			    perf, &perf_debugfs_fops);
	return 0;
}

void msm_perf_debugfs_cleanup(struct msm_drm_private *priv)
{
	struct msm_perf_state *perf = priv->perf;

	if (!perf)
		return;

	priv->perf = NULL;

	mutex_destroy(&perf->read_lock);

	kfree(perf);
}

#endif