aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched_debug.c
blob: 75ccf7aa98f3571ca257764d01abb3e9656427f1 (plain) (blame)
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
/*
 * kernel/time/sched_debug.c
 *
 * Print the CFS rbtree
 *
 * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
 *
 * 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.
 */

#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
#include <linux/utsname.h>

/*
 * This allows printing both to /proc/sched_debug and
 * to the console
 */
#define SEQ_printf(m, x...)			\
 do {						\
	if (m)					\
		seq_printf(m, x);		\
	else					\
		printk(x);			\
 } while (0)

static void
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
	if (rq->curr == p)
		SEQ_printf(m, "R");
	else
		SEQ_printf(m, " ");

	SEQ_printf(m, "%15s %5d %15Ld %13Ld %13Ld %9Ld %5d ",
		p->comm, p->pid,
		(long long)p->se.fair_key,
		(long long)(p->se.fair_key - rq->cfs.fair_clock),
		(long long)p->se.wait_runtime,
		(long long)(p->nvcsw + p->nivcsw),
		p->prio);
#ifdef CONFIG_SCHEDSTATS
	SEQ_printf(m, "%15Ld %15Ld %15Ld %15Ld %15Ld %15Ld\n",
		(long long)p->se.vruntime,
		(long long)p->se.sum_exec_runtime,
		(long long)p->se.sum_wait_runtime,
		(long long)p->se.sum_sleep_runtime,
		(long long)p->se.wait_runtime_overruns,
		(long long)p->se.wait_runtime_underruns);
#else
	SEQ_printf(m, "%15Ld %15Ld %15Ld %15Ld %15Ld\n",
		0LL, 0LL, 0LL, 0LL, 0LL);
#endif
}

static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
{
	struct task_struct *g, *p;

	SEQ_printf(m,
	"\nrunnable tasks:\n"
	"            task   PID        tree-key         delta       waiting"
	"  switches  prio"
	"    exec-runtime        sum-exec        sum-wait       sum-sleep"
	"    wait-overrun   wait-underrun\n"
	"------------------------------------------------------------------"
	"--------------------------------"
	"------------------------------------------------"
	"--------------------------------\n");

	read_lock_irq(&tasklist_lock);

	do_each_thread(g, p) {
		if (!p->se.on_rq || task_cpu(p) != rq_cpu)
			continue;

		print_task(m, rq, p);
	} while_each_thread(g, p);

	read_unlock_irq(&tasklist_lock);
}

static void
print_cfs_rq_runtime_sum(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
	s64 wait_runtime_rq_sum = 0;
	struct task_struct *p;
	struct rb_node *curr;
	unsigned long flags;
	struct rq *rq = &per_cpu(runqueues, cpu);

	spin_lock_irqsave(&rq->lock, flags);
	curr = first_fair(cfs_rq);
	while (curr) {
		p = rb_entry(curr, struct task_struct, se.run_node);
		wait_runtime_rq_sum += p->se.wait_runtime;

		curr = rb_next(curr);
	}
	spin_unlock_irqrestore(&rq->lock, flags);

	SEQ_printf(m, "  .%-30s: %Ld\n", "wait_runtime_rq_sum",
		(long long)wait_runtime_rq_sum);
}

void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
	s64 MIN_vruntime = -1, max_vruntime = -1, spread;
	struct rq *rq = &per_cpu(runqueues, cpu);
	struct sched_entity *last;
	unsigned long flags;

	SEQ_printf(m, "\ncfs_rq\n");

#define P(x) \
	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(cfs_rq->x))

	P(fair_clock);
	P(exec_clock);
	P(min_vruntime);

	spin_lock_irqsave(&rq->lock, flags);
	if (cfs_rq->rb_leftmost)
		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
	last = __pick_last_entity(cfs_rq);
	if (last)
		max_vruntime = last->vruntime;
	spin_unlock_irqrestore(&rq->lock, flags);
	SEQ_printf(m, "  .%-30s: %Ld\n", "MIN_vruntime",
			(long long)MIN_vruntime);
	SEQ_printf(m, "  .%-30s: %Ld\n", "max_vruntime",
			(long long)max_vruntime);
	spread = max_vruntime - MIN_vruntime;
	SEQ_printf(m, "  .%-30s: %Ld\n", "spread",
			(long long)spread);

	P(wait_runtime);
	P(wait_runtime_overruns);
	P(wait_runtime_underruns);
	P(sleeper_bonus);
#undef P

	print_cfs_rq_runtime_sum(m, cpu, cfs_rq);
}

static void print_cpu(struct seq_file *m, int cpu)
{
	struct rq *rq = &per_cpu(runqueues, cpu);

#ifdef CONFIG_X86
	{
		unsigned int freq = cpu_khz ? : 1;

		SEQ_printf(m, "\ncpu#%d, %u.%03u MHz\n",
			   cpu, freq / 1000, (freq % 1000));
	}
#else
	SEQ_printf(m, "\ncpu#%d\n", cpu);
#endif

#define P(x) \
	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))

	P(nr_running);
	SEQ_printf(m, "  .%-30s: %lu\n", "load",
		   rq->ls.load.weight);
	P(nr_switches);
	P(nr_load_updates);
	P(nr_uninterruptible);
	SEQ_printf(m, "  .%-30s: %lu\n", "jiffies", jiffies);
	P(next_balance);
	P(curr->pid);
	P(clock);
	P(idle_clock);
	P(prev_clock_raw);
	P(clock_warps);
	P(clock_overflows);
	P(clock_deep_idle_events);
	P(clock_max_delta);
	P(cpu_load[0]);
	P(cpu_load[1]);
	P(cpu_load[2]);
	P(cpu_load[3]);
	P(cpu_load[4]);
#undef P

	print_cfs_stats(m, cpu);

	print_rq(m, rq, cpu);
}

static int sched_debug_show(struct seq_file *m, void *v)
{
	u64 now = ktime_to_ns(ktime_get());
	int cpu;

	SEQ_printf(m, "Sched Debug Version: v0.05-v20, %s %.*s\n",
		init_utsname()->release,
		(int)strcspn(init_utsname()->version, " "),
		init_utsname()->version);

	SEQ_printf(m, "now at %Lu nsecs\n", (unsigned long long)now);

	for_each_online_cpu(cpu)
		print_cpu(m, cpu);

	SEQ_printf(m, "\n");

	return 0;
}

static void sysrq_sched_debug_show(void)
{
	sched_debug_show(NULL, NULL);
}

static int sched_debug_open(struct inode *inode, struct file *filp)
{
	return single_open(filp, sched_debug_show, NULL);
}

static struct file_operations sched_debug_fops = {
	.open		= sched_debug_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static int __init init_sched_debug_procfs(void)
{
	struct proc_dir_entry *pe;

	pe = create_proc_entry("sched_debug", 0644, NULL);
	if (!pe)
		return -ENOMEM;

	pe->proc_fops = &sched_debug_fops;

	return 0;
}

__initcall(init_sched_debug_procfs);

void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
	unsigned long flags;
	int num_threads = 1;

	rcu_read_lock();
	if (lock_task_sighand(p, &flags)) {
		num_threads = atomic_read(&p->signal->count);
		unlock_task_sighand(p, &flags);
	}
	rcu_read_unlock();

	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, num_threads);
	SEQ_printf(m, "----------------------------------------------\n");
#define P(F) \
	SEQ_printf(m, "%-25s:%20Ld\n", #F, (long long)p->F)

	P(se.wait_runtime);
	P(se.wait_start_fair);
	P(se.exec_start);
	P(se.sleep_start_fair);
	P(se.vruntime);
	P(se.sum_exec_runtime);

#ifdef CONFIG_SCHEDSTATS
	P(se.wait_start);
	P(se.sleep_start);
	P(se.block_start);
	P(se.sleep_max);
	P(se.block_max);
	P(se.exec_max);
	P(se.slice_max);
	P(se.wait_max);
	P(se.wait_runtime_overruns);
	P(se.wait_runtime_underruns);
	P(se.sum_wait_runtime);
#endif
	SEQ_printf(m, "%-25s:%20Ld\n",
		   "nr_switches", (long long)(p->nvcsw + p->nivcsw));
	P(se.load.weight);
	P(policy);
	P(prio);
#undef P

	{
		u64 t0, t1;

		t0 = sched_clock();
		t1 = sched_clock();
		SEQ_printf(m, "%-25s:%20Ld\n",
			   "clock-delta", (long long)(t1-t0));
	}
}

void proc_sched_set_task(struct task_struct *p)
{
#ifdef CONFIG_SCHEDSTATS
	p->se.sleep_max			= 0;
	p->se.block_max			= 0;
	p->se.exec_max			= 0;
	p->se.slice_max			= 0;
	p->se.wait_max			= 0;
	p->se.wait_runtime_overruns	= 0;
	p->se.wait_runtime_underruns	= 0;
#endif
	p->se.sum_exec_runtime		= 0;
	p->se.prev_sum_exec_runtime	= 0;
}