sched.h 13.1 KB
Newer Older
1 2 3
#undef TRACE_SYSTEM
#define TRACE_SYSTEM sched

4
#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
5 6 7 8
#define _TRACE_SCHED_H

#include <linux/sched.h>
#include <linux/tracepoint.h>
9
#include <linux/binfmts.h>
10

11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
/*
 * Tracepoint for calling kthread_stop, performed to end a kthread:
 */
TRACE_EVENT(sched_kthread_stop,

	TP_PROTO(struct task_struct *t),

	TP_ARGS(t),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, t->comm, TASK_COMM_LEN);
		__entry->pid	= t->pid;
	),

30
	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
);

/*
 * Tracepoint for the return value of the kthread stopping:
 */
TRACE_EVENT(sched_kthread_stop_ret,

	TP_PROTO(int ret),

	TP_ARGS(ret),

	TP_STRUCT__entry(
		__field(	int,	ret	)
	),

	TP_fast_assign(
		__entry->ret	= ret;
	),

50
	TP_printk("ret=%d", __entry->ret)
51 52 53 54 55
);

/*
 * Tracepoint for waking up a task:
 */
56
DECLARE_EVENT_CLASS(sched_wakeup_template,
57

58
	TP_PROTO(struct task_struct *p, int success),
59

60
	TP_ARGS(__perf_task(p), success),
61 62 63 64 65 66

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
		__field(	int,	success			)
67
		__field(	int,	target_cpu		)
68 69 70 71 72 73 74
	),

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio;
		__entry->success	= success;
75
		__entry->target_cpu	= task_cpu(p);
76 77
	),

78
	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
79
		  __entry->comm, __entry->pid, __entry->prio,
80
		  __entry->success, __entry->target_cpu)
81 82
);

83
DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
84 85
	     TP_PROTO(struct task_struct *p, int success),
	     TP_ARGS(p, success));
86

87 88 89
/*
 * Tracepoint for waking up a new task:
 */
90
DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
91 92
	     TP_PROTO(struct task_struct *p, int success),
	     TP_ARGS(p, success));
93

94 95 96 97 98 99
#ifdef CREATE_TRACE_POINTS
static inline long __trace_sched_switch_state(struct task_struct *p)
{
	long state = p->state;

#ifdef CONFIG_PREEMPT
100 101 102
#ifdef CONFIG_SCHED_DEBUG
	BUG_ON(p != current);
#endif /* CONFIG_SCHED_DEBUG */
103 104 105
	/*
	 * For all intents and purposes a preempted task is a running task.
	 */
106
	if (preempt_count() & PREEMPT_ACTIVE)
107
		state = TASK_RUNNING | TASK_STATE_MAX;
108
#endif /* CONFIG_PREEMPT */
109 110 111

	return state;
}
112
#endif /* CREATE_TRACE_POINTS */
113

114 115 116 117 118
/*
 * Tracepoint for task switches, performed by the scheduler:
 */
TRACE_EVENT(sched_switch,

119
	TP_PROTO(struct task_struct *prev,
120 121
		 struct task_struct *next),

122
	TP_ARGS(prev, next),
123 124 125 126 127

	TP_STRUCT__entry(
		__array(	char,	prev_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	prev_pid			)
		__field(	int,	prev_prio			)
128
		__field(	long,	prev_state			)
129 130 131 132 133 134 135 136 137
		__array(	char,	next_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	next_pid			)
		__field(	int,	next_prio			)
	),

	TP_fast_assign(
		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
		__entry->prev_pid	= prev->pid;
		__entry->prev_prio	= prev->prio;
138
		__entry->prev_state	= __trace_sched_switch_state(prev);
139 140 141 142 143
		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
		__entry->next_pid	= next->pid;
		__entry->next_prio	= next->prio;
	),

144
	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
145
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
146 147
		__entry->prev_state & (TASK_STATE_MAX-1) ?
		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
148 149
				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
150
				{ 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
151
		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
152 153 154 155 156 157 158 159
		__entry->next_comm, __entry->next_pid, __entry->next_prio)
);

/*
 * Tracepoint for a task being migrated:
 */
TRACE_EVENT(sched_migrate_task,

160
	TP_PROTO(struct task_struct *p, int dest_cpu),
161

162
	TP_ARGS(p, dest_cpu),
163 164 165 166 167 168 169 170 171 172 173 174 175

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
		__field(	int,	orig_cpu		)
		__field(	int,	dest_cpu		)
	),

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio;
176
		__entry->orig_cpu	= task_cpu(p);
177 178 179
		__entry->dest_cpu	= dest_cpu;
	),

180
	TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d",
181 182 183 184
		  __entry->comm, __entry->pid, __entry->prio,
		  __entry->orig_cpu, __entry->dest_cpu)
);

185
DECLARE_EVENT_CLASS(sched_process_template,
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202

	TP_PROTO(struct task_struct *p),

	TP_ARGS(p),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
		__entry->pid		= p->pid;
		__entry->prio		= p->prio;
	),

203
	TP_printk("comm=%s pid=%d prio=%d",
204 205 206 207
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
208
 * Tracepoint for freeing a task:
209
 */
210 211 212 213
DEFINE_EVENT(sched_process_template, sched_process_free,
	     TP_PROTO(struct task_struct *p),
	     TP_ARGS(p));
	     
214

215 216 217 218 219 220
/*
 * Tracepoint for a task exiting:
 */
DEFINE_EVENT(sched_process_template, sched_process_exit,
	     TP_PROTO(struct task_struct *p),
	     TP_ARGS(p));
221

222 223 224 225 226 227 228
/*
 * Tracepoint for waiting on task to unschedule:
 */
DEFINE_EVENT(sched_process_template, sched_wait_task,
	TP_PROTO(struct task_struct *p),
	TP_ARGS(p));

229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249
/*
 * Tracepoint for a waiting task:
 */
TRACE_EVENT(sched_process_wait,

	TP_PROTO(struct pid *pid),

	TP_ARGS(pid),

	TP_STRUCT__entry(
		__array(	char,	comm,	TASK_COMM_LEN	)
		__field(	pid_t,	pid			)
		__field(	int,	prio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
		__entry->pid		= pid_nr(pid);
		__entry->prio		= current->prio;
	),

250
	TP_printk("comm=%s pid=%d prio=%d",
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
		  __entry->comm, __entry->pid, __entry->prio)
);

/*
 * Tracepoint for do_fork:
 */
TRACE_EVENT(sched_process_fork,

	TP_PROTO(struct task_struct *parent, struct task_struct *child),

	TP_ARGS(parent, child),

	TP_STRUCT__entry(
		__array(	char,	parent_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	parent_pid			)
		__array(	char,	child_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	child_pid			)
	),

	TP_fast_assign(
		memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN);
		__entry->parent_pid	= parent->pid;
		memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN);
		__entry->child_pid	= child->pid;
	),

277
	TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d",
278 279 280 281
		__entry->parent_comm, __entry->parent_pid,
		__entry->child_comm, __entry->child_pid)
);

282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
/*
 * Tracepoint for exec:
 */
TRACE_EVENT(sched_process_exec,

	TP_PROTO(struct task_struct *p, pid_t old_pid,
		 struct linux_binprm *bprm),

	TP_ARGS(p, old_pid, bprm),

	TP_STRUCT__entry(
		__string(	filename,	bprm->filename	)
		__field(	pid_t,		pid		)
		__field(	pid_t,		old_pid		)
	),

	TP_fast_assign(
		__assign_str(filename, bprm->filename);
		__entry->pid		= p->pid;
301
		__entry->old_pid	= old_pid;
302 303 304 305 306 307
	),

	TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),
		  __entry->pid, __entry->old_pid)
);

308 309 310 311
/*
 * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
 *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
 */
312
DECLARE_EVENT_CLASS(sched_stat_template,
313 314 315

	TP_PROTO(struct task_struct *tsk, u64 delay),

316
	TP_ARGS(__perf_task(tsk), __perf_count(delay)),
317 318 319 320 321 322 323 324 325 326 327 328 329

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( u64,	delay			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid	= tsk->pid;
		__entry->delay	= delay;
	),

330
	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
331 332 333 334
			__entry->comm, __entry->pid,
			(unsigned long long)__entry->delay)
);

335 336 337 338 339 340 341 342 343 344 345 346 347

/*
 * Tracepoint for accounting wait time (time the task is runnable
 * but not actually running due to scheduler contention).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_wait,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

/*
 * Tracepoint for accounting sleep time (time the task is not runnable,
 * including iowait, see below).
 */
348 349 350
DEFINE_EVENT(sched_stat_template, sched_stat_sleep,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));
351 352 353 354 355

/*
 * Tracepoint for accounting iowait time (time the task is not runnable
 * due to waiting on IO to complete).
 */
356 357 358
DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));
359

360 361 362 363 364 365 366
/*
 * Tracepoint for accounting blocked time (time the task is in uninterruptible).
 */
DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
	     TP_PROTO(struct task_struct *tsk, u64 delay),
	     TP_ARGS(tsk, delay));

367 368 369 370
/*
 * Tracepoint for accounting runtime (time the task is executing
 * on a CPU).
 */
371
DECLARE_EVENT_CLASS(sched_stat_runtime,
372 373 374

	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),

375
	TP_ARGS(tsk, __perf_count(runtime), vruntime),
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( u64,	runtime			)
		__field( u64,	vruntime			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid		= tsk->pid;
		__entry->runtime	= runtime;
		__entry->vruntime	= vruntime;
	),

391
	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
392 393 394 395 396
			__entry->comm, __entry->pid,
			(unsigned long long)__entry->runtime,
			(unsigned long long)__entry->vruntime)
);

397 398 399 400
DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
	     TP_ARGS(tsk, runtime, vruntime));

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
/*
 * Tracepoint for showing priority inheritance modifying a tasks
 * priority.
 */
TRACE_EVENT(sched_pi_setprio,

	TP_PROTO(struct task_struct *tsk, int newprio),

	TP_ARGS(tsk, newprio),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
		__field( int,	oldprio			)
		__field( int,	newprio			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid		= tsk->pid;
		__entry->oldprio	= tsk->prio;
		__entry->newprio	= newprio;
	),

	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
			__entry->comm, __entry->pid,
			__entry->oldprio, __entry->newprio)
);

430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
#ifdef CONFIG_DETECT_HUNG_TASK
TRACE_EVENT(sched_process_hang,
	TP_PROTO(struct task_struct *tsk),
	TP_ARGS(tsk),

	TP_STRUCT__entry(
		__array( char,	comm,	TASK_COMM_LEN	)
		__field( pid_t,	pid			)
	),

	TP_fast_assign(
		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
		__entry->pid = tsk->pid;
	),

	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
);
#endif /* CONFIG_DETECT_HUNG_TASK */

449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
DECLARE_EVENT_CLASS(sched_move_task_template,

	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),

	TP_ARGS(tsk, src_cpu, dst_cpu),

	TP_STRUCT__entry(
		__field( pid_t,	pid			)
		__field( pid_t,	tgid			)
		__field( pid_t,	ngid			)
		__field( int,	src_cpu			)
		__field( int,	src_nid			)
		__field( int,	dst_cpu			)
		__field( int,	dst_nid			)
	),

	TP_fast_assign(
		__entry->pid		= task_pid_nr(tsk);
		__entry->tgid		= task_tgid_nr(tsk);
		__entry->ngid		= task_numa_group_id(tsk);
		__entry->src_cpu	= src_cpu;
		__entry->src_nid	= cpu_to_node(src_cpu);
		__entry->dst_cpu	= dst_cpu;
		__entry->dst_nid	= cpu_to_node(dst_cpu);
	),

	TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d",
			__entry->pid, __entry->tgid, __entry->ngid,
			__entry->src_cpu, __entry->src_nid,
			__entry->dst_cpu, __entry->dst_nid)
);

/*
 * Tracks migration of tasks from one runqueue to another. Can be used to
 * detect if automatic NUMA balancing is bouncing between nodes
 */
DEFINE_EVENT(sched_move_task_template, sched_move_numa,
	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),

	TP_ARGS(tsk, src_cpu, dst_cpu)
);

DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),

	TP_ARGS(tsk, src_cpu, dst_cpu)
);

TRACE_EVENT(sched_swap_numa,

	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
		 struct task_struct *dst_tsk, int dst_cpu),

	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu),

	TP_STRUCT__entry(
		__field( pid_t,	src_pid			)
		__field( pid_t,	src_tgid		)
		__field( pid_t,	src_ngid		)
		__field( int,	src_cpu			)
		__field( int,	src_nid			)
		__field( pid_t,	dst_pid			)
		__field( pid_t,	dst_tgid		)
		__field( pid_t,	dst_ngid		)
		__field( int,	dst_cpu			)
		__field( int,	dst_nid			)
	),

	TP_fast_assign(
		__entry->src_pid	= task_pid_nr(src_tsk);
		__entry->src_tgid	= task_tgid_nr(src_tsk);
		__entry->src_ngid	= task_numa_group_id(src_tsk);
		__entry->src_cpu	= src_cpu;
		__entry->src_nid	= cpu_to_node(src_cpu);
		__entry->dst_pid	= task_pid_nr(dst_tsk);
		__entry->dst_tgid	= task_tgid_nr(dst_tsk);
		__entry->dst_ngid	= task_numa_group_id(dst_tsk);
		__entry->dst_cpu	= dst_cpu;
		__entry->dst_nid	= cpu_to_node(dst_cpu);
	),

	TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
			__entry->src_pid, __entry->src_tgid, __entry->src_ngid,
			__entry->src_cpu, __entry->src_nid,
			__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
			__entry->dst_cpu, __entry->dst_nid)
);
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555

/*
 * Tracepoint for waking a polling cpu without an IPI.
 */
TRACE_EVENT(sched_wake_idle_without_ipi,

	TP_PROTO(int cpu),

	TP_ARGS(cpu),

	TP_STRUCT__entry(
		__field(	int,	cpu	)
	),

	TP_fast_assign(
		__entry->cpu	= cpu;
	),

	TP_printk("cpu=%d", __entry->cpu)
);
556
#endif /* _TRACE_SCHED_H */
557 558 559

/* This part must be outside protection */
#include <trace/define_trace.h>