rcu.h 24.6 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2 3 4 5 6 7 8 9 10
#undef TRACE_SYSTEM
#define TRACE_SYSTEM rcu

#if !defined(_TRACE_RCU_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_RCU_H

#include <linux/tracepoint.h>

/*
11 12 13 14 15 16
 * Tracepoint for start/end markers used for utilization calculations.
 * By convention, the string is of the following forms:
 *
 * "Start <activity>" -- Mark the start of the specified activity,
 *			 such as "context switch".  Nesting is permitted.
 * "End <activity>" -- Mark the end of the specified activity.
17 18 19
 *
 * An "@" character within "<activity>" is a comment character: Data
 * reduction scripts will ignore the "@" and the remainder of the line.
20 21 22
 */
TRACE_EVENT(rcu_utilization,

23
	TP_PROTO(const char *s),
24 25 26 27

	TP_ARGS(s),

	TP_STRUCT__entry(
28
		__field(const char *, s)
29 30 31 32 33 34 35 36 37
	),

	TP_fast_assign(
		__entry->s = s;
	),

	TP_printk("%s", __entry->s)
);

38 39
#ifdef CONFIG_RCU_TRACE

40
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
41 42

/*
43 44 45 46 47 48
 * Tracepoint for grace-period events.  Takes a string identifying the
 * RCU flavor, the grace-period number, and a string identifying the
 * grace-period-related event as follows:
 *
 *	"AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL.
 *	"AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL.
49
 *	"newreq": Request a new grace period.
50 51 52 53 54 55 56 57 58 59 60 61 62
 *	"start": Start a grace period.
 *	"cpustart": CPU first notices a grace-period start.
 *	"cpuqs": CPU passes through a quiescent state.
 *	"cpuonl": CPU comes online.
 *	"cpuofl": CPU goes offline.
 *	"reqwait": GP kthread sleeps waiting for grace-period request.
 *	"reqwaitsig": GP kthread awakened by signal from reqwait state.
 *	"fqswait": GP kthread waiting until time to force quiescent states.
 *	"fqsstart": GP kthread starts forcing quiescent states.
 *	"fqsend": GP kthread done forcing quiescent states.
 *	"fqswaitsig": GP kthread awakened by signal from fqswait state.
 *	"end": End a grace period.
 *	"cpuend": CPU first notices a grace-period end.
63 64 65
 */
TRACE_EVENT(rcu_grace_period,

66
	TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
67 68 69 70

	TP_ARGS(rcuname, gpnum, gpevent),

	TP_STRUCT__entry(
71
		__field(const char *, rcuname)
72
		__field(unsigned long, gpnum)
73
		__field(const char *, gpevent)
74 75 76 77 78 79 80 81 82 83 84 85
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->gpevent = gpevent;
	),

	TP_printk("%s %lu %s",
		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
);

86
/*
87 88 89 90
 * Tracepoint for future grace-period events, including those for no-callbacks
 * CPUs.  The caller should pull the data from the rcu_node structure,
 * other than rcuname, which comes from the rcu_state structure, and event,
 * which is one of the following:
91 92 93 94 95 96 97 98 99 100 101
 *
 * "Startleaf": Request a nocb grace period based on leaf-node data.
 * "Startedleaf": Leaf-node start proved sufficient.
 * "Startedleafroot": Leaf-node start proved sufficient after checking root.
 * "Startedroot": Requested a nocb grace period based on root-node data.
 * "StartWait": Start waiting for the requested grace period.
 * "ResumeWait": Resume waiting after signal.
 * "EndWait": Complete wait.
 * "Cleanup": Clean up rcu_node structure after previous GP.
 * "CleanupMore": Clean up, and another no-CB GP is needed.
 */
102
TRACE_EVENT(rcu_future_grace_period,
103

104
	TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
105
		 unsigned long c, u8 level, int grplo, int grphi,
106
		 const char *gpevent),
107 108 109 110

	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),

	TP_STRUCT__entry(
111
		__field(const char *, rcuname)
112 113 114 115 116 117
		__field(unsigned long, gpnum)
		__field(unsigned long, completed)
		__field(unsigned long, c)
		__field(u8, level)
		__field(int, grplo)
		__field(int, grphi)
118
		__field(const char *, gpevent)
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->completed = completed;
		__entry->c = c;
		__entry->level = level;
		__entry->grplo = grplo;
		__entry->grphi = grphi;
		__entry->gpevent = gpevent;
	),

	TP_printk("%s %lu %lu %lu %u %d %d %s",
		  __entry->rcuname, __entry->gpnum, __entry->completed,
		  __entry->c, __entry->level, __entry->grplo, __entry->grphi,
		  __entry->gpevent)
);

138 139 140 141 142 143 144 145 146
/*
 * Tracepoint for grace-period-initialization events.  These are
 * distinguished by the type of RCU, the new grace-period number, the
 * rcu_node structure level, the starting and ending CPU covered by the
 * rcu_node structure, and the mask of CPUs that will be waited for.
 * All but the type of RCU are extracted from the rcu_node structure.
 */
TRACE_EVENT(rcu_grace_period_init,

147
	TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
148 149 150 151 152
		 int grplo, int grphi, unsigned long qsmask),

	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),

	TP_STRUCT__entry(
153
		__field(const char *, rcuname)
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174
		__field(unsigned long, gpnum)
		__field(u8, level)
		__field(int, grplo)
		__field(int, grphi)
		__field(unsigned long, qsmask)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->level = level;
		__entry->grplo = grplo;
		__entry->grphi = grphi;
		__entry->qsmask = qsmask;
	),

	TP_printk("%s %lu %u %d %d %lx",
		  __entry->rcuname, __entry->gpnum, __entry->level,
		  __entry->grplo, __entry->grphi, __entry->qsmask)
);

175 176 177 178 179 180 181 182
/*
 * Tracepoint for expedited grace-period events.  Takes a string identifying
 * the RCU flavor, the expedited grace-period sequence number, and a string
 * identifying the grace-period-related event as follows:
 *
 *	"snap": Captured snapshot of expedited grace period sequence number.
 *	"start": Started a real expedited grace period.
 *	"end": Ended a real expedited grace period.
183
 *	"endwake": Woke piggybackers up.
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
 *	"done": Someone else did the expedited grace period for us.
 */
TRACE_EVENT(rcu_exp_grace_period,

	TP_PROTO(const char *rcuname, unsigned long gpseq, const char *gpevent),

	TP_ARGS(rcuname, gpseq, gpevent),

	TP_STRUCT__entry(
		__field(const char *, rcuname)
		__field(unsigned long, gpseq)
		__field(const char *, gpevent)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpseq = gpseq;
		__entry->gpevent = gpevent;
	),

	TP_printk("%s %lu %s",
		  __entry->rcuname, __entry->gpseq, __entry->gpevent)
);

/*
 * Tracepoint for expedited grace-period funnel-locking events.  Takes a
 * string identifying the RCU flavor, an integer identifying the rcu_node
 * combining-tree level, another pair of integers identifying the lowest-
 * and highest-numbered CPU associated with the current rcu_node structure,
 * and a string.  identifying the grace-period-related event as follows:
 *
215 216
 *	"nxtlvl": Advance to next level of rcu_node funnel
 *	"wait": Wait for someone else to do expedited GP
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
 */
TRACE_EVENT(rcu_exp_funnel_lock,

	TP_PROTO(const char *rcuname, u8 level, int grplo, int grphi,
		 const char *gpevent),

	TP_ARGS(rcuname, level, grplo, grphi, gpevent),

	TP_STRUCT__entry(
		__field(const char *, rcuname)
		__field(u8, level)
		__field(int, grplo)
		__field(int, grphi)
		__field(const char *, gpevent)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->level = level;
		__entry->grplo = grplo;
		__entry->grphi = grphi;
		__entry->gpevent = gpevent;
	),

	TP_printk("%s %d %d %d %s",
		  __entry->rcuname, __entry->level, __entry->grplo,
		  __entry->grphi, __entry->gpevent)
);

246 247 248 249 250 251 252 253 254
/*
 * Tracepoint for RCU no-CBs CPU callback handoffs.  This event is intended
 * to assist debugging of these handoffs.
 *
 * The first argument is the name of the RCU flavor, and the second is
 * the number of the offloaded CPU are extracted.  The third and final
 * argument is a string as follows:
 *
 *	"WakeEmpty": Wake rcuo kthread, first CB to empty list.
255
 *	"WakeEmptyIsDeferred": Wake rcuo kthread later, first CB to empty list.
256
 *	"WakeOvf": Wake rcuo kthread, CB list is huge.
257
 *	"WakeOvfIsDeferred": Wake rcuo kthread later, CB list is huge.
258 259
 *	"WakeNot": Don't wake rcuo kthread.
 *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
260
 *	"DeferredWake": Carried out the "IsDeferred" wakeup.
261 262
 *	"Poll": Start of new polling cycle for rcu_nocb_poll.
 *	"Sleep": Sleep waiting for CBs for !rcu_nocb_poll.
263 264
 *	"WokeEmpty": rcuo kthread woke to find empty list.
 *	"WokeNonEmpty": rcuo kthread woke to find non-empty list.
265 266
 *	"WaitQueue": Enqueue partially done, timed wait for it to complete.
 *	"WokeQueue": Partial enqueue now complete.
267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
 */
TRACE_EVENT(rcu_nocb_wake,

	TP_PROTO(const char *rcuname, int cpu, const char *reason),

	TP_ARGS(rcuname, cpu, reason),

	TP_STRUCT__entry(
		__field(const char *, rcuname)
		__field(int, cpu)
		__field(const char *, reason)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->cpu = cpu;
		__entry->reason = reason;
	),

	TP_printk("%s %d %s", __entry->rcuname, __entry->cpu, __entry->reason)
);

289 290 291 292 293 294 295 296
/*
 * Tracepoint for tasks blocking within preemptible-RCU read-side
 * critical sections.  Track the type of RCU (which one day might
 * include SRCU), the grace-period number that the task is blocking
 * (the current or the next), and the task's PID.
 */
TRACE_EVENT(rcu_preempt_task,

297
	TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
298 299 300 301

	TP_ARGS(rcuname, pid, gpnum),

	TP_STRUCT__entry(
302
		__field(const char *, rcuname)
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
		__field(unsigned long, gpnum)
		__field(int, pid)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->pid = pid;
	),

	TP_printk("%s %lu %d",
		  __entry->rcuname, __entry->gpnum, __entry->pid)
);

/*
 * Tracepoint for tasks that blocked within a given preemptible-RCU
 * read-side critical section exiting that critical section.  Track the
 * type of RCU (which one day might include SRCU) and the task's PID.
 */
TRACE_EVENT(rcu_unlock_preempted_task,

324
	TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
325 326 327 328

	TP_ARGS(rcuname, gpnum, pid),

	TP_STRUCT__entry(
329
		__field(const char *, rcuname)
330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352
		__field(unsigned long, gpnum)
		__field(int, pid)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->pid = pid;
	),

	TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
);

/*
 * Tracepoint for quiescent-state-reporting events.  These are
 * distinguished by the type of RCU, the grace-period number, the
 * mask of quiescent lower-level entities, the rcu_node structure level,
 * the starting and ending CPU covered by the rcu_node structure, and
 * whether there are any blocked tasks blocking the current grace period.
 * All but the type of RCU are extracted from the rcu_node structure.
 */
TRACE_EVENT(rcu_quiescent_state_report,

353
	TP_PROTO(const char *rcuname, unsigned long gpnum,
354 355 356 357 358 359
		 unsigned long mask, unsigned long qsmask,
		 u8 level, int grplo, int grphi, int gp_tasks),

	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),

	TP_STRUCT__entry(
360
		__field(const char *, rcuname)
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
		__field(unsigned long, gpnum)
		__field(unsigned long, mask)
		__field(unsigned long, qsmask)
		__field(u8, level)
		__field(int, grplo)
		__field(int, grphi)
		__field(u8, gp_tasks)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->mask = mask;
		__entry->qsmask = qsmask;
		__entry->level = level;
		__entry->grplo = grplo;
		__entry->grphi = grphi;
		__entry->gp_tasks = gp_tasks;
	),

	TP_printk("%s %lu %lx>%lx %u %d %d %u",
		  __entry->rcuname, __entry->gpnum,
		  __entry->mask, __entry->qsmask, __entry->level,
		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
);

/*
 * Tracepoint for quiescent states detected by force_quiescent_state().
389 390 391 392 393
 * These trace events include the type of RCU, the grace-period number that
 * was blocked by the CPU, the CPU itself, and the type of quiescent state,
 * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
 * when kicking a CPU that has been in dyntick-idle mode for too long, or
 * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
394 395 396
 */
TRACE_EVENT(rcu_fqs,

397
	TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
398 399 400 401

	TP_ARGS(rcuname, gpnum, cpu, qsevent),

	TP_STRUCT__entry(
402
		__field(const char *, rcuname)
403 404
		__field(unsigned long, gpnum)
		__field(int, cpu)
405
		__field(const char *, qsevent)
406 407 408 409 410 411 412 413 414 415 416 417 418 419
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->gpnum = gpnum;
		__entry->cpu = cpu;
		__entry->qsevent = qsevent;
	),

	TP_printk("%s %lu %d %s",
		  __entry->rcuname, __entry->gpnum,
		  __entry->cpu, __entry->qsevent)
);

420
#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) */
421 422 423

/*
 * Tracepoint for dyntick-idle entry/exit events.  These take a string
424 425 426 427 428 429 430 431 432 433
 * as argument: "Start" for entering dyntick-idle mode, "End" for
 * leaving it, "--=" for events moving towards idle, and "++=" for events
 * moving away from idle.  "Error on entry: not idle task" and "Error on
 * exit: not idle task" indicate that a non-idle task is erroneously
 * toying with the idle loop.
 *
 * These events also take a pair of numbers, which indicate the nesting
 * depth before and after the event of interest.  Note that task-related
 * events use the upper bits of each number, while interrupt-related
 * events use the lower bits.
434 435 436
 */
TRACE_EVENT(rcu_dyntick,

437
	TP_PROTO(const char *polarity, long long oldnesting, long long newnesting),
438

439
	TP_ARGS(polarity, oldnesting, newnesting),
440 441

	TP_STRUCT__entry(
442
		__field(const char *, polarity)
443 444
		__field(long long, oldnesting)
		__field(long long, newnesting)
445 446 447 448
	),

	TP_fast_assign(
		__entry->polarity = polarity;
449 450
		__entry->oldnesting = oldnesting;
		__entry->newnesting = newnesting;
451 452
	),

453 454
	TP_printk("%s %llx %llx", __entry->polarity,
		  __entry->oldnesting, __entry->newnesting)
455 456
);

457 458 459 460 461 462 463 464 465 466 467 468 469 470
/*
 * Tracepoint for RCU preparation for idle, the goal being to get RCU
 * processing done so that the current CPU can shut off its scheduling
 * clock and enter dyntick-idle mode.  One way to accomplish this is
 * to drain all RCU callbacks from this CPU, and the other is to have
 * done everything RCU requires for the current grace period.  In this
 * latter case, the CPU will be awakened at the end of the current grace
 * period in order to process the remainder of its callbacks.
 *
 * These tracepoints take a string as argument:
 *
 *	"No callbacks": Nothing to do, no callbacks on this CPU.
 *	"In holdoff": Nothing to do, holding off after unsuccessful attempt.
 *	"Begin holdoff": Attempt failed, don't retry until next jiffy.
471
 *	"Dyntick with callbacks": Entering dyntick-idle despite callbacks.
472
 *	"Dyntick with lazy callbacks": Entering dyntick-idle w/lazy callbacks.
473 474
 *	"More callbacks": Still more callbacks, try again to clear them out.
 *	"Callbacks drained": All callbacks processed, off to dyntick idle!
475
 *	"Timer": Timer fired to cause CPU to continue processing callbacks.
476
 *	"Demigrate": Timer fired on wrong CPU, woke up correct CPU.
477
 *	"Cleanup after idle": Idle exited, timer canceled.
478 479 480
 */
TRACE_EVENT(rcu_prep_idle,

481
	TP_PROTO(const char *reason),
482 483 484 485

	TP_ARGS(reason),

	TP_STRUCT__entry(
486
		__field(const char *, reason)
487 488 489 490 491 492 493 494 495
	),

	TP_fast_assign(
		__entry->reason = reason;
	),

	TP_printk("%s", __entry->reason)
);

496 497 498
/*
 * Tracepoint for the registration of a single RCU callback function.
 * The first argument is the type of RCU, the second argument is
499 500 501
 * a pointer to the RCU callback itself, the third element is the
 * number of lazy callbacks queued, and the fourth element is the
 * total number of callbacks queued.
502 503 504
 */
TRACE_EVENT(rcu_callback,

505
	TP_PROTO(const char *rcuname, struct rcu_head *rhp, long qlen_lazy,
506
		 long qlen),
507

508
	TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
509 510

	TP_STRUCT__entry(
511
		__field(const char *, rcuname)
512 513
		__field(void *, rhp)
		__field(void *, func)
514
		__field(long, qlen_lazy)
515 516 517 518 519 520 521
		__field(long, qlen)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->rhp = rhp;
		__entry->func = rhp->func;
522
		__entry->qlen_lazy = qlen_lazy;
523 524 525
		__entry->qlen = qlen;
	),

526 527 528
	TP_printk("%s rhp=%p func=%pf %ld/%ld",
		  __entry->rcuname, __entry->rhp, __entry->func,
		  __entry->qlen_lazy, __entry->qlen)
529 530 531 532 533 534 535
);

/*
 * Tracepoint for the registration of a single RCU callback of the special
 * kfree() form.  The first argument is the RCU type, the second argument
 * is a pointer to the RCU callback, the third argument is the offset
 * of the callback within the enclosing RCU-protected data structure,
536 537
 * the fourth argument is the number of lazy callbacks queued, and the
 * fifth argument is the total number of callbacks queued.
538 539 540
 */
TRACE_EVENT(rcu_kfree_callback,

541
	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset,
542
		 long qlen_lazy, long qlen),
543

544
	TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
545 546

	TP_STRUCT__entry(
547
		__field(const char *, rcuname)
548 549
		__field(void *, rhp)
		__field(unsigned long, offset)
550
		__field(long, qlen_lazy)
551 552 553 554 555 556 557
		__field(long, qlen)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->rhp = rhp;
		__entry->offset = offset;
558
		__entry->qlen_lazy = qlen_lazy;
559 560 561
		__entry->qlen = qlen;
	),

562
	TP_printk("%s rhp=%p func=%ld %ld/%ld",
563
		  __entry->rcuname, __entry->rhp, __entry->offset,
564
		  __entry->qlen_lazy, __entry->qlen)
565 566
);

567 568
/*
 * Tracepoint for marking the beginning rcu_do_batch, performed to start
569
 * RCU callback invocation.  The first argument is the RCU flavor,
570 571 572
 * the second is the number of lazy callbacks queued, the third is
 * the total number of callbacks queued, and the fourth argument is
 * the current RCU-callback batch limit.
573 574 575
 */
TRACE_EVENT(rcu_batch_start,

576
	TP_PROTO(const char *rcuname, long qlen_lazy, long qlen, long blimit),
577

578
	TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
579 580

	TP_STRUCT__entry(
581
		__field(const char *, rcuname)
582
		__field(long, qlen_lazy)
583
		__field(long, qlen)
584
		__field(long, blimit)
585 586 587
	),

	TP_fast_assign(
588
		__entry->rcuname = rcuname;
589
		__entry->qlen_lazy = qlen_lazy;
590 591
		__entry->qlen = qlen;
		__entry->blimit = blimit;
592 593
	),

594
	TP_printk("%s CBs=%ld/%ld bl=%ld",
595 596
		  __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
		  __entry->blimit)
597 598 599
);

/*
600
 * Tracepoint for the invocation of a single RCU callback function.
601 602
 * The first argument is the type of RCU, and the second argument is
 * a pointer to the RCU callback itself.
603 604 605
 */
TRACE_EVENT(rcu_invoke_callback,

606
	TP_PROTO(const char *rcuname, struct rcu_head *rhp),
607

608
	TP_ARGS(rcuname, rhp),
609 610

	TP_STRUCT__entry(
611
		__field(const char *, rcuname)
612 613
		__field(void *, rhp)
		__field(void *, func)
614 615 616
	),

	TP_fast_assign(
617
		__entry->rcuname = rcuname;
618 619
		__entry->rhp = rhp;
		__entry->func = rhp->func;
620 621
	),

622 623
	TP_printk("%s rhp=%p func=%pf",
		  __entry->rcuname, __entry->rhp, __entry->func)
624 625 626
);

/*
627
 * Tracepoint for the invocation of a single RCU callback of the special
628 629 630 631
 * kfree() form.  The first argument is the RCU flavor, the second
 * argument is a pointer to the RCU callback, and the third argument
 * is the offset of the callback within the enclosing RCU-protected
 * data structure.
632 633 634
 */
TRACE_EVENT(rcu_invoke_kfree_callback,

635
	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset),
636

637
	TP_ARGS(rcuname, rhp, offset),
638 639

	TP_STRUCT__entry(
640
		__field(const char *, rcuname)
641
		__field(void *, rhp)
642
		__field(unsigned long, offset)
643 644 645
	),

	TP_fast_assign(
646
		__entry->rcuname = rcuname;
647
		__entry->rhp = rhp;
648 649 650
		__entry->offset	= offset;
	),

651 652
	TP_printk("%s rhp=%p func=%ld",
		  __entry->rcuname, __entry->rhp, __entry->offset)
653 654 655
);

/*
656
 * Tracepoint for exiting rcu_do_batch after RCU callbacks have been
657 658 659 660 661 662 663 664
 * invoked.  The first argument is the name of the RCU flavor,
 * the second argument is number of callbacks actually invoked,
 * the third argument (cb) is whether or not any of the callbacks that
 * were ready to invoke at the beginning of this batch are still
 * queued, the fourth argument (nr) is the return value of need_resched(),
 * the fifth argument (iit) is 1 if the current task is the idle task,
 * and the sixth argument (risk) is the return value from
 * rcu_is_callbacks_kthread().
665 666 667
 */
TRACE_EVENT(rcu_batch_end,

668
	TP_PROTO(const char *rcuname, int callbacks_invoked,
669
		 char cb, char nr, char iit, char risk),
670

671
	TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk),
672 673

	TP_STRUCT__entry(
674
		__field(const char *, rcuname)
675
		__field(int, callbacks_invoked)
676 677 678 679
		__field(char, cb)
		__field(char, nr)
		__field(char, iit)
		__field(char, risk)
680 681 682
	),

	TP_fast_assign(
683
		__entry->rcuname = rcuname;
684
		__entry->callbacks_invoked = callbacks_invoked;
685 686 687 688 689 690 691 692 693 694 695 696
		__entry->cb = cb;
		__entry->nr = nr;
		__entry->iit = iit;
		__entry->risk = risk;
	),

	TP_printk("%s CBs-invoked=%d idle=%c%c%c%c",
		  __entry->rcuname, __entry->callbacks_invoked,
		  __entry->cb ? 'C' : '.',
		  __entry->nr ? 'S' : '.',
		  __entry->iit ? 'I' : '.',
		  __entry->risk ? 'R' : '.')
697 698
);

699 700 701
/*
 * Tracepoint for rcutorture readers.  The first argument is the name
 * of the RCU flavor from rcutorture's viewpoint and the second argument
702 703 704 705
 * is the callback address.  The third argument is the start time in
 * seconds, and the last two arguments are the grace period numbers
 * at the beginning and end of the read, respectively.  Note that the
 * callback address can be NULL.
706
 */
707
#define RCUTORTURENAME_LEN 8
708 709
TRACE_EVENT(rcu_torture_read,

710
	TP_PROTO(const char *rcutorturename, struct rcu_head *rhp,
711
		 unsigned long secs, unsigned long c_old, unsigned long c),
712

713
	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
714 715

	TP_STRUCT__entry(
716
		__field(char, rcutorturename[RCUTORTURENAME_LEN])
717
		__field(struct rcu_head *, rhp)
718 719 720
		__field(unsigned long, secs)
		__field(unsigned long, c_old)
		__field(unsigned long, c)
721 722 723
	),

	TP_fast_assign(
724 725 726
		strncpy(__entry->rcutorturename, rcutorturename,
			RCUTORTURENAME_LEN);
		__entry->rcutorturename[RCUTORTURENAME_LEN - 1] = 0;
727
		__entry->rhp = rhp;
728 729 730
		__entry->secs = secs;
		__entry->c_old = c_old;
		__entry->c = c;
731 732
	),

733 734 735
	TP_printk("%s torture read %p %luus c: %lu %lu",
		  __entry->rcutorturename, __entry->rhp,
		  __entry->secs, __entry->c_old, __entry->c)
736 737
);

738 739 740
/*
 * Tracepoint for _rcu_barrier() execution.  The string "s" describes
 * the _rcu_barrier phase:
741 742 743 744 745 746 747
 *	"Begin": _rcu_barrier() started.
 *	"EarlyExit": _rcu_barrier() piggybacked, thus early exit.
 *	"Inc1": _rcu_barrier() piggyback check counter incremented.
 *	"OfflineNoCB": _rcu_barrier() found callback on never-online CPU
 *	"OnlineNoCB": _rcu_barrier() found online no-CBs CPU.
 *	"OnlineQ": _rcu_barrier() found online CPU with callbacks.
 *	"OnlineNQ": _rcu_barrier() found online CPU, no callbacks.
748
 *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
749
 *	"IRQNQ": An rcu_barrier_callback() callback found no callbacks.
750 751
 *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
 *	"LastCB": An rcu_barrier_callback() invoked the last callback.
752
 *	"Inc2": _rcu_barrier() piggyback check counter incremented.
753 754 755 756 757
 * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
 * is the count of remaining callbacks, and "done" is the piggybacking count.
 */
TRACE_EVENT(rcu_barrier,

758
	TP_PROTO(const char *rcuname, const char *s, int cpu, int cnt, unsigned long done),
759 760 761 762

	TP_ARGS(rcuname, s, cpu, cnt, done),

	TP_STRUCT__entry(
763 764
		__field(const char *, rcuname)
		__field(const char *, s)
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
		__field(int, cpu)
		__field(int, cnt)
		__field(unsigned long, done)
	),

	TP_fast_assign(
		__entry->rcuname = rcuname;
		__entry->s = s;
		__entry->cpu = cpu;
		__entry->cnt = cnt;
		__entry->done = done;
	),

	TP_printk("%s %s cpu %d remaining %d # %lu",
		  __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt,
		  __entry->done)
);

783 784 785
#else /* #ifdef CONFIG_RCU_TRACE */

#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
786 787 788
#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
				      level, grplo, grphi, event) \
				      do { } while (0)
789 790 791 792 793 794
#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
				    qsmask) do { } while (0)
#define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
	do { } while (0)
#define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
	do { } while (0)
795
#define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
796 797
#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
798 799 800
#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
					 grplo, grphi, gp_tasks) do { } \
	while (0)
801
#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
802
#define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0)
803
#define trace_rcu_prep_idle(reason) do { } while (0)
804 805 806 807 808
#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
	do { } while (0)
#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \
	do { } while (0)
809 810
#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
811 812
#define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
	do { } while (0)
813 814
#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
	do { } while (0)
815
#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0)
816 817 818

#endif /* #else #ifdef CONFIG_RCU_TRACE */

819 820 821 822
#endif /* _TRACE_RCU_H */

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