rcutiny_plugin.h 30.2 KB
Newer Older
1
/*
P
Paul E. McKenney 已提交
2
 * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition
3
 * Internal non-public definitions that provide either classic
P
Paul E. McKenney 已提交
4
 * or preemptible semantics.
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * 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, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
P
Paul E. McKenney 已提交
20
 * Copyright (c) 2010 Linaro
21 22 23 24
 *
 * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 */

25
#include <linux/kthread.h>
26 27 28 29 30 31 32 33
#include <linux/debugfs.h>
#include <linux/seq_file.h>

#ifdef CONFIG_RCU_TRACE
#define RCU_TRACE(stmt)	stmt
#else /* #ifdef CONFIG_RCU_TRACE */
#define RCU_TRACE(stmt)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
34

35 36 37 38 39
/* Global control variables for rcupdate callback mechanism. */
struct rcu_ctrlblk {
	struct rcu_head *rcucblist;	/* List of pending callbacks (CBs). */
	struct rcu_head **donetail;	/* ->next pointer of last "done" CB. */
	struct rcu_head **curtail;	/* ->next pointer of last CB. */
40
	RCU_TRACE(long qlen);		/* Number of pending CBs. */
41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
};

/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_sched_ctrlblk = {
	.donetail	= &rcu_sched_ctrlblk.rcucblist,
	.curtail	= &rcu_sched_ctrlblk.rcucblist,
};

static struct rcu_ctrlblk rcu_bh_ctrlblk = {
	.donetail	= &rcu_bh_ctrlblk.rcucblist,
	.curtail	= &rcu_bh_ctrlblk.rcucblist,
};

#ifdef CONFIG_DEBUG_LOCK_ALLOC
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

P
Paul E. McKenney 已提交
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
#ifdef CONFIG_TINY_PREEMPT_RCU

#include <linux/delay.h>

/* Global control variables for preemptible RCU. */
struct rcu_preempt_ctrlblk {
	struct rcu_ctrlblk rcb;	/* curtail: ->next ptr of last CB for GP. */
	struct rcu_head **nexttail;
				/* Tasks blocked in a preemptible RCU */
				/*  read-side critical section while an */
				/*  preemptible-RCU grace period is in */
				/*  progress must wait for a later grace */
				/*  period.  This pointer points to the */
				/*  ->next pointer of the last task that */
				/*  must wait for a later grace period, or */
				/*  to &->rcb.rcucblist if there is no */
				/*  such task. */
	struct list_head blkd_tasks;
				/* Tasks blocked in RCU read-side critical */
				/*  section.  Tasks are placed at the head */
				/*  of this list and age towards the tail. */
	struct list_head *gp_tasks;
				/* Pointer to the first task blocking the */
				/*  current grace period, or NULL if there */
83
				/*  is no such task. */
P
Paul E. McKenney 已提交
84 85 86 87 88 89
	struct list_head *exp_tasks;
				/* Pointer to first task blocking the */
				/*  current expedited grace period, or NULL */
				/*  if there is no such task.  If there */
				/*  is no current expedited grace period, */
				/*  then there cannot be any such task. */
90 91 92 93 94 95 96 97
#ifdef CONFIG_RCU_BOOST
	struct list_head *boost_tasks;
				/* Pointer to first task that needs to be */
				/*  priority-boosted, or NULL if no priority */
				/*  boosting is needed.  If there is no */
				/*  current or expedited grace period, there */
				/*  can be no such task. */
#endif /* #ifdef CONFIG_RCU_BOOST */
P
Paul E. McKenney 已提交
98 99 100 101
	u8 gpnum;		/* Current grace period. */
	u8 gpcpu;		/* Last grace period blocked by the CPU. */
	u8 completed;		/* Last grace period completed. */
				/*  If all three are equal, RCU is idle. */
102
#ifdef CONFIG_RCU_BOOST
103 104
	s8 boosted_this_gp;	/* Has boosting already happened? */
	unsigned long boost_time; /* When to start boosting (jiffies) */
105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
#endif /* #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_TRACE
	unsigned long n_grace_periods;
#ifdef CONFIG_RCU_BOOST
	unsigned long n_tasks_boosted;
	unsigned long n_exp_boosts;
	unsigned long n_normal_boosts;
	unsigned long n_normal_balk_blkd_tasks;
	unsigned long n_normal_balk_gp_tasks;
	unsigned long n_normal_balk_boost_tasks;
	unsigned long n_normal_balk_boosted;
	unsigned long n_normal_balk_notyet;
	unsigned long n_normal_balk_nos;
	unsigned long n_exp_balk_blkd_tasks;
	unsigned long n_exp_balk_nos;
#endif /* #ifdef CONFIG_RCU_BOOST */
#endif /* #ifdef CONFIG_RCU_TRACE */
P
Paul E. McKenney 已提交
122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
};

static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
	.rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist,
	.rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist,
	.nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist,
	.blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks),
};

static int rcu_preempted_readers_exp(void);
static void rcu_report_exp_done(void);

/*
 * Return true if the CPU has not yet responded to the current grace period.
 */
137
static int rcu_cpu_blocking_cur_gp(void)
P
Paul E. McKenney 已提交
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
{
	return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum;
}

/*
 * Check for a running RCU reader.  Because there is only one CPU,
 * there can be but one running RCU reader at a time.  ;-)
 */
static int rcu_preempt_running_reader(void)
{
	return current->rcu_read_lock_nesting;
}

/*
 * Check for preempted RCU readers blocking any grace period.
 * If the caller needs a reliable answer, it must disable hard irqs.
 */
static int rcu_preempt_blocked_readers_any(void)
{
	return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks);
}

/*
 * Check for preempted RCU readers blocking the current grace period.
 * If the caller needs a reliable answer, it must disable hard irqs.
 */
static int rcu_preempt_blocked_readers_cgp(void)
{
	return rcu_preempt_ctrlblk.gp_tasks != NULL;
}

/*
 * Return true if another preemptible-RCU grace period is needed.
 */
static int rcu_preempt_needs_another_gp(void)
{
	return *rcu_preempt_ctrlblk.rcb.curtail != NULL;
}

/*
 * Return true if a preemptible-RCU grace period is in progress.
 * The caller must disable hardirqs.
 */
static int rcu_preempt_gp_in_progress(void)
{
	return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum;
}

186 187 188 189 190 191 192 193 194 195 196 197 198 199
/*
 * Advance a ->blkd_tasks-list pointer to the next entry, instead
 * returning NULL if at the end of the list.
 */
static struct list_head *rcu_next_node_entry(struct task_struct *t)
{
	struct list_head *np;

	np = t->rcu_node_entry.next;
	if (np == &rcu_preempt_ctrlblk.blkd_tasks)
		np = NULL;
	return np;
}

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
#ifdef CONFIG_RCU_TRACE

#ifdef CONFIG_RCU_BOOST
static void rcu_initiate_boost_trace(void);
static void rcu_initiate_exp_boost_trace(void);
#endif /* #ifdef CONFIG_RCU_BOOST */

/*
 * Dump additional statistice for TINY_PREEMPT_RCU.
 */
static void show_tiny_preempt_stats(struct seq_file *m)
{
	seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n",
		   rcu_preempt_ctrlblk.rcb.qlen,
		   rcu_preempt_ctrlblk.n_grace_periods,
		   rcu_preempt_ctrlblk.gpnum,
		   rcu_preempt_ctrlblk.gpcpu,
		   rcu_preempt_ctrlblk.completed,
		   "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)],
		   "N."[!rcu_preempt_ctrlblk.gp_tasks],
		   "E."[!rcu_preempt_ctrlblk.exp_tasks]);
#ifdef CONFIG_RCU_BOOST
	seq_printf(m, "             ttb=%c btg=",
		   "B."[!rcu_preempt_ctrlblk.boost_tasks]);
	switch (rcu_preempt_ctrlblk.boosted_this_gp) {
	case -1:
		seq_puts(m, "exp");
		break;
	case 0:
		seq_puts(m, "no");
		break;
	case 1:
232 233 234
		seq_puts(m, "begun");
		break;
	case 2:
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
		seq_puts(m, "done");
		break;
	default:
		seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp);
	}
	seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
		   rcu_preempt_ctrlblk.n_tasks_boosted,
		   rcu_preempt_ctrlblk.n_exp_boosts,
		   rcu_preempt_ctrlblk.n_normal_boosts,
		   (int)(jiffies & 0xffff),
		   (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
	seq_printf(m, "             %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n",
		   "normal balk",
		   rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks,
		   rcu_preempt_ctrlblk.n_normal_balk_gp_tasks,
		   rcu_preempt_ctrlblk.n_normal_balk_boost_tasks,
		   rcu_preempt_ctrlblk.n_normal_balk_boosted,
		   rcu_preempt_ctrlblk.n_normal_balk_notyet,
		   rcu_preempt_ctrlblk.n_normal_balk_nos);
	seq_printf(m, "             exp balk: bt=%lu nos=%lu\n",
		   rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks,
		   rcu_preempt_ctrlblk.n_exp_balk_nos);
#endif /* #ifdef CONFIG_RCU_BOOST */
}

#endif /* #ifdef CONFIG_RCU_TRACE */

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
#ifdef CONFIG_RCU_BOOST

#include "rtmutex_common.h"

/*
 * Carry out RCU priority boosting on the task indicated by ->boost_tasks,
 * and advance ->boost_tasks to the next task in the ->blkd_tasks list.
 */
static int rcu_boost(void)
{
	unsigned long flags;
	struct rt_mutex mtx;
	struct list_head *np;
	struct task_struct *t;

	if (rcu_preempt_ctrlblk.boost_tasks == NULL)
		return 0;  /* Nothing to boost. */
	raw_local_irq_save(flags);
	rcu_preempt_ctrlblk.boosted_this_gp++;
	t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct,
			 rcu_node_entry);
	np = rcu_next_node_entry(t);
	rt_mutex_init_proxy_locked(&mtx, t);
	t->rcu_boost_mutex = &mtx;
	t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
	raw_local_irq_restore(flags);
	rt_mutex_lock(&mtx);
289
	RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
290
	rcu_preempt_ctrlblk.boosted_this_gp++;
291 292 293 294 295 296 297 298 299
	rt_mutex_unlock(&mtx);
	return rcu_preempt_ctrlblk.boost_tasks != NULL;
}

/*
 * Check to see if it is now time to start boosting RCU readers blocking
 * the current grace period, and, if so, tell the rcu_kthread_task to
 * start boosting them.  If there is an expedited boost in progress,
 * we wait for it to complete.
300 301 302 303
 *
 * If there are no blocked readers blocking the current grace period,
 * return 0 to let the caller know, otherwise return 1.  Note that this
 * return value is independent of whether or not boosting was done.
304
 */
305
static int rcu_initiate_boost(void)
306
{
307 308 309 310
	if (!rcu_preempt_blocked_readers_cgp()) {
		RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++);
		return 0;
	}
311 312 313 314 315 316
	if (rcu_preempt_ctrlblk.gp_tasks != NULL &&
	    rcu_preempt_ctrlblk.boost_tasks == NULL &&
	    rcu_preempt_ctrlblk.boosted_this_gp == 0 &&
	    ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) {
		rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks;
		invoke_rcu_kthread();
317 318 319 320
		RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
	} else
		RCU_TRACE(rcu_initiate_boost_trace());
	return 1;
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
}

/*
 * Initiate boosting for an expedited grace period.
 */
static void rcu_initiate_expedited_boost(void)
{
	unsigned long flags;

	raw_local_irq_save(flags);
	if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) {
		rcu_preempt_ctrlblk.boost_tasks =
			rcu_preempt_ctrlblk.blkd_tasks.next;
		rcu_preempt_ctrlblk.boosted_this_gp = -1;
		invoke_rcu_kthread();
336 337 338
		RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
	} else
		RCU_TRACE(rcu_initiate_exp_boost_trace());
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
	raw_local_irq_restore(flags);
}

#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000);

/*
 * Do priority-boost accounting for the start of a new grace period.
 */
static void rcu_preempt_boost_start_gp(void)
{
	rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
	if (rcu_preempt_ctrlblk.boosted_this_gp > 0)
		rcu_preempt_ctrlblk.boosted_this_gp = 0;
}

#else /* #ifdef CONFIG_RCU_BOOST */

/*
 * If there is no RCU priority boosting, we don't boost.
 */
static int rcu_boost(void)
{
	return 0;
}

/*
365 366 367
 * If there is no RCU priority boosting, we don't initiate boosting,
 * but we do indicate whether there are blocked readers blocking the
 * current grace period.
368
 */
369
static int rcu_initiate_boost(void)
370
{
371
	return rcu_preempt_blocked_readers_cgp();
372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
}

/*
 * If there is no RCU priority boosting, we don't initiate expedited boosting.
 */
static void rcu_initiate_expedited_boost(void)
{
}

/*
 * If there is no RCU priority boosting, nothing to do at grace-period start.
 */
static void rcu_preempt_boost_start_gp(void)
{
}

#endif /* else #ifdef CONFIG_RCU_BOOST */

P
Paul E. McKenney 已提交
390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416
/*
 * Record a preemptible-RCU quiescent state for the specified CPU.  Note
 * that this just means that the task currently running on the CPU is
 * in a quiescent state.  There might be any number of tasks blocked
 * while in an RCU read-side critical section.
 *
 * Unlike the other rcu_*_qs() functions, callers to this function
 * must disable irqs in order to protect the assignment to
 * ->rcu_read_unlock_special.
 *
 * Because this is a single-CPU implementation, the only way a grace
 * period can end is if the CPU is in a quiescent state.  The reason is
 * that a blocked preemptible-RCU reader can exit its critical section
 * only if the CPU is running it at the time.  Therefore, when the
 * last task blocking the current grace period exits its RCU read-side
 * critical section, neither the CPU nor blocked tasks will be stopping
 * the current grace period.  (In contrast, SMP implementations
 * might have CPUs running in RCU read-side critical sections that
 * block later grace periods -- but this is not possible given only
 * one CPU.)
 */
static void rcu_preempt_cpu_qs(void)
{
	/* Record both CPU and task as having responded to current GP. */
	rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;

417
	/* If there is no GP then there is nothing more to do.  */
418
	if (!rcu_preempt_gp_in_progress())
P
Paul E. McKenney 已提交
419
		return;
420 421 422 423 424
	/*
	 * Check up on boosting.  If there are no readers blocking the
	 * current grace period, leave.
	 */
	if (rcu_initiate_boost())
425
		return;
P
Paul E. McKenney 已提交
426 427 428 429 430 431 432 433 434 435

	/* Advance callbacks. */
	rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum;
	rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail;
	rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail;

	/* If there are no blocked readers, next GP is done instantly. */
	if (!rcu_preempt_blocked_readers_any())
		rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;

436
	/* If there are done callbacks, cause them to be invoked. */
P
Paul E. McKenney 已提交
437
	if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
438
		invoke_rcu_kthread();
P
Paul E. McKenney 已提交
439 440 441 442 443 444 445 446 447 448 449
}

/*
 * Start a new RCU grace period if warranted.  Hard irqs must be disabled.
 */
static void rcu_preempt_start_gp(void)
{
	if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) {

		/* Official start of GP. */
		rcu_preempt_ctrlblk.gpnum++;
450
		RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
P
Paul E. McKenney 已提交
451 452 453 454 455 456

		/* Any blocked RCU readers block new GP. */
		if (rcu_preempt_blocked_readers_any())
			rcu_preempt_ctrlblk.gp_tasks =
				rcu_preempt_ctrlblk.blkd_tasks.next;

457 458 459
		/* Set up for RCU priority boosting. */
		rcu_preempt_boost_start_gp();

P
Paul E. McKenney 已提交
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
		/* If there is no running reader, CPU is done with GP. */
		if (!rcu_preempt_running_reader())
			rcu_preempt_cpu_qs();
	}
}

/*
 * We have entered the scheduler, and the current task might soon be
 * context-switched away from.  If this task is in an RCU read-side
 * critical section, we will no longer be able to rely on the CPU to
 * record that fact, so we enqueue the task on the blkd_tasks list.
 * If the task started after the current grace period began, as recorded
 * by ->gpcpu, we enqueue at the beginning of the list.  Otherwise
 * before the element referenced by ->gp_tasks (or at the tail if
 * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element.
 * The task will dequeue itself when it exits the outermost enclosing
 * RCU read-side critical section.  Therefore, the current grace period
 * cannot be permitted to complete until the ->gp_tasks pointer becomes
 * NULL.
 *
 * Caller must disable preemption.
 */
void rcu_preempt_note_context_switch(void)
{
	struct task_struct *t = current;
	unsigned long flags;

	local_irq_save(flags); /* must exclude scheduler_tick(). */
	if (rcu_preempt_running_reader() &&
	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {

		/* Possibly blocking in an RCU read-side critical section. */
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;

		/*
		 * If this CPU has already checked in, then this task
		 * will hold up the next grace period rather than the
		 * current grace period.  Queue the task accordingly.
		 * If the task is queued for the current grace period
		 * (i.e., this CPU has not yet passed through a quiescent
		 * state for the current grace period), then as long
		 * as that task remains queued, the current grace period
		 * cannot end.
		 */
		list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks);
505
		if (rcu_cpu_blocking_cur_gp())
P
Paul E. McKenney 已提交
506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579
			rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry;
	}

	/*
	 * Either we were not in an RCU read-side critical section to
	 * begin with, or we have now recorded that critical section
	 * globally.  Either way, we can now note a quiescent state
	 * for this CPU.  Again, if we were in an RCU read-side critical
	 * section, and if that critical section was blocking the current
	 * grace period, then the fact that the task has been enqueued
	 * means that current grace period continues to be blocked.
	 */
	rcu_preempt_cpu_qs();
	local_irq_restore(flags);
}

/*
 * Tiny-preemptible RCU implementation for rcu_read_lock().
 * Just increment ->rcu_read_lock_nesting, shared state will be updated
 * if we block.
 */
void __rcu_read_lock(void)
{
	current->rcu_read_lock_nesting++;
	barrier();  /* needed if we ever invoke rcu_read_lock in rcutiny.c */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);

/*
 * Handle special cases during rcu_read_unlock(), such as needing to
 * notify RCU core processing or task having blocked during the RCU
 * read-side critical section.
 */
static void rcu_read_unlock_special(struct task_struct *t)
{
	int empty;
	int empty_exp;
	unsigned long flags;
	struct list_head *np;
	int special;

	/*
	 * NMI handlers cannot block and cannot safely manipulate state.
	 * They therefore cannot possibly be special, so just leave.
	 */
	if (in_nmi())
		return;

	local_irq_save(flags);

	/*
	 * If RCU core is waiting for this CPU to exit critical section,
	 * let it know that we have done so.
	 */
	special = t->rcu_read_unlock_special;
	if (special & RCU_READ_UNLOCK_NEED_QS)
		rcu_preempt_cpu_qs();

	/* Hardware IRQ handlers cannot block. */
	if (in_irq()) {
		local_irq_restore(flags);
		return;
	}

	/* Clean up if blocked during RCU read-side critical section. */
	if (special & RCU_READ_UNLOCK_BLOCKED) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;

		/*
		 * Remove this task from the ->blkd_tasks list and adjust
		 * any pointers that might have been referencing it.
		 */
		empty = !rcu_preempt_blocked_readers_cgp();
		empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
580
		np = rcu_next_node_entry(t);
P
Paul E. McKenney 已提交
581 582 583 584 585
		list_del(&t->rcu_node_entry);
		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
			rcu_preempt_ctrlblk.gp_tasks = np;
		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
			rcu_preempt_ctrlblk.exp_tasks = np;
586 587 588 589
#ifdef CONFIG_RCU_BOOST
		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
			rcu_preempt_ctrlblk.boost_tasks = np;
#endif /* #ifdef CONFIG_RCU_BOOST */
P
Paul E. McKenney 已提交
590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
		INIT_LIST_HEAD(&t->rcu_node_entry);

		/*
		 * If this was the last task on the current list, and if
		 * we aren't waiting on the CPU, report the quiescent state
		 * and start a new grace period if needed.
		 */
		if (!empty && !rcu_preempt_blocked_readers_cgp()) {
			rcu_preempt_cpu_qs();
			rcu_preempt_start_gp();
		}

		/*
		 * If this was the last task on the expedited lists,
		 * then we need wake up the waiting task.
		 */
		if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
			rcu_report_exp_done();
	}
609 610 611 612 613 614 615 616
#ifdef CONFIG_RCU_BOOST
	/* Unboost self if was boosted. */
	if (special & RCU_READ_UNLOCK_BOOSTED) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
		rt_mutex_unlock(t->rcu_boost_mutex);
		t->rcu_boost_mutex = NULL;
	}
#endif /* #ifdef CONFIG_RCU_BOOST */
P
Paul E. McKenney 已提交
617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653
	local_irq_restore(flags);
}

/*
 * Tiny-preemptible RCU implementation for rcu_read_unlock().
 * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
 * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
 * invoke rcu_read_unlock_special() to clean up after a context switch
 * in an RCU read-side critical section and other special cases.
 */
void __rcu_read_unlock(void)
{
	struct task_struct *t = current;

	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutiny.c */
	--t->rcu_read_lock_nesting;
	barrier();  /* decrement before load of ->rcu_read_unlock_special */
	if (t->rcu_read_lock_nesting == 0 &&
	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
		rcu_read_unlock_special(t);
#ifdef CONFIG_PROVE_LOCKING
	WARN_ON_ONCE(t->rcu_read_lock_nesting < 0);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);

/*
 * Check for a quiescent state from the current CPU.  When a task blocks,
 * the task is recorded in the rcu_preempt_ctrlblk structure, which is
 * checked elsewhere.  This is called from the scheduling-clock interrupt.
 *
 * Caller must disable hard irqs.
 */
static void rcu_preempt_check_callbacks(void)
{
	struct task_struct *t = current;

654 655 656
	if (rcu_preempt_gp_in_progress() &&
	    (!rcu_preempt_running_reader() ||
	     !rcu_cpu_blocking_cur_gp()))
P
Paul E. McKenney 已提交
657 658 659
		rcu_preempt_cpu_qs();
	if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
	    rcu_preempt_ctrlblk.rcb.donetail)
660
		invoke_rcu_kthread();
661 662 663
	if (rcu_preempt_gp_in_progress() &&
	    rcu_cpu_blocking_cur_gp() &&
	    rcu_preempt_running_reader())
P
Paul E. McKenney 已提交
664 665 666 667 668
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
}

/*
 * TINY_PREEMPT_RCU has an extra callback-list tail pointer to
669
 * update, so this is invoked from rcu_process_callbacks() to
P
Paul E. McKenney 已提交
670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685
 * handle that case.  Of course, it is invoked for all flavors of
 * RCU, but RCU callbacks can appear only on one of the lists, and
 * neither ->nexttail nor ->donetail can possibly be NULL, so there
 * is no need for an explicit check.
 */
static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
{
	if (rcu_preempt_ctrlblk.nexttail == rcp->donetail)
		rcu_preempt_ctrlblk.nexttail = &rcp->rcucblist;
}

/*
 * Process callbacks for preemptible RCU.
 */
static void rcu_preempt_process_callbacks(void)
{
686
	rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
P
Paul E. McKenney 已提交
687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
}

/*
 * Queue a preemptible -RCU callback for invocation after a grace period.
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	unsigned long flags;

	debug_rcu_head_queue(head);
	head->func = func;
	head->next = NULL;

	local_irq_save(flags);
	*rcu_preempt_ctrlblk.nexttail = head;
	rcu_preempt_ctrlblk.nexttail = &head->next;
703
	RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++);
P
Paul E. McKenney 已提交
704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818
	rcu_preempt_start_gp();  /* checks to see if GP needed. */
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(call_rcu);

void rcu_barrier(void)
{
	struct rcu_synchronize rcu;

	init_rcu_head_on_stack(&rcu.head);
	init_completion(&rcu.completion);
	/* Will wake me after RCU finished. */
	call_rcu(&rcu.head, wakeme_after_rcu);
	/* Wait for it. */
	wait_for_completion(&rcu.completion);
	destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(rcu_barrier);

/*
 * synchronize_rcu - wait until a grace period has elapsed.
 *
 * Control will return to the caller some time after a full grace
 * period has elapsed, in other words after all currently executing RCU
 * read-side critical sections have completed.  RCU read-side critical
 * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
 * and may be nested.
 */
void synchronize_rcu(void)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	if (!rcu_scheduler_active)
		return;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

	WARN_ON_ONCE(rcu_preempt_running_reader());
	if (!rcu_preempt_blocked_readers_any())
		return;

	/* Once we get past the fastpath checks, same code as rcu_barrier(). */
	rcu_barrier();
}
EXPORT_SYMBOL_GPL(synchronize_rcu);

static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
static unsigned long sync_rcu_preempt_exp_count;
static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);

/*
 * Return non-zero if there are any tasks in RCU read-side critical
 * sections blocking the current preemptible-RCU expedited grace period.
 * If there is no preemptible-RCU expedited grace period currently in
 * progress, returns zero unconditionally.
 */
static int rcu_preempted_readers_exp(void)
{
	return rcu_preempt_ctrlblk.exp_tasks != NULL;
}

/*
 * Report the exit from RCU read-side critical section for the last task
 * that queued itself during or before the current expedited preemptible-RCU
 * grace period.
 */
static void rcu_report_exp_done(void)
{
	wake_up(&sync_rcu_preempt_exp_wq);
}

/*
 * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
 * is to rely in the fact that there is but one CPU, and that it is
 * illegal for a task to invoke synchronize_rcu_expedited() while in a
 * preemptible-RCU read-side critical section.  Therefore, any such
 * critical sections must correspond to blocked tasks, which must therefore
 * be on the ->blkd_tasks list.  So just record the current head of the
 * list in the ->exp_tasks pointer, and wait for all tasks including and
 * after the task pointed to by ->exp_tasks to drain.
 */
void synchronize_rcu_expedited(void)
{
	unsigned long flags;
	struct rcu_preempt_ctrlblk *rpcp = &rcu_preempt_ctrlblk;
	unsigned long snap;

	barrier(); /* ensure prior action seen before grace period. */

	WARN_ON_ONCE(rcu_preempt_running_reader());

	/*
	 * Acquire lock so that there is only one preemptible RCU grace
	 * period in flight.  Of course, if someone does the expedited
	 * grace period for us while we are acquiring the lock, just leave.
	 */
	snap = sync_rcu_preempt_exp_count + 1;
	mutex_lock(&sync_rcu_preempt_exp_mutex);
	if (ULONG_CMP_LT(snap, sync_rcu_preempt_exp_count))
		goto unlock_mb_ret; /* Others did our work for us. */

	local_irq_save(flags);

	/*
	 * All RCU readers have to already be on blkd_tasks because
	 * we cannot legally be executing in an RCU read-side critical
	 * section.
	 */

	/* Snapshot current head of ->blkd_tasks list. */
	rpcp->exp_tasks = rpcp->blkd_tasks.next;
	if (rpcp->exp_tasks == &rpcp->blkd_tasks)
		rpcp->exp_tasks = NULL;
	local_irq_restore(flags);

	/* Wait for tail of ->blkd_tasks list to drain. */
	if (rcu_preempted_readers_exp())
819
		rcu_initiate_expedited_boost();
P
Paul E. McKenney 已提交
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854
		wait_event(sync_rcu_preempt_exp_wq,
			   !rcu_preempted_readers_exp());

	/* Clean up and exit. */
	barrier(); /* ensure expedited GP seen before counter increment. */
	sync_rcu_preempt_exp_count++;
unlock_mb_ret:
	mutex_unlock(&sync_rcu_preempt_exp_mutex);
	barrier(); /* ensure subsequent action seen after grace period. */
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

/*
 * Does preemptible RCU need the CPU to stay out of dynticks mode?
 */
int rcu_preempt_needs_cpu(void)
{
	if (!rcu_preempt_running_reader())
		rcu_preempt_cpu_qs();
	return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
}

/*
 * Check for a task exiting while in a preemptible -RCU read-side
 * critical section, clean up if so.  No need to issue warnings,
 * as debug_check_no_locks_held() already does this if lockdep
 * is enabled.
 */
void exit_rcu(void)
{
	struct task_struct *t = current;

	if (t->rcu_read_lock_nesting == 0)
		return;
	t->rcu_read_lock_nesting = 1;
855
	__rcu_read_unlock();
P
Paul E. McKenney 已提交
856 857 858 859
}

#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */

860 861 862 863 864 865 866 867 868 869 870 871
#ifdef CONFIG_RCU_TRACE

/*
 * Because preemptible RCU does not exist, it is not necessary to
 * dump out its statistics.
 */
static void show_tiny_preempt_stats(struct seq_file *m)
{
}

#endif /* #ifdef CONFIG_RCU_TRACE */

872 873 874 875 876 877 878 879 880
/*
 * Because preemptible RCU does not exist, it is never necessary to
 * boost preempted RCU readers.
 */
static int rcu_boost(void)
{
	return 0;
}

P
Paul E. McKenney 已提交
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906
/*
 * Because preemptible RCU does not exist, it never has any callbacks
 * to check.
 */
static void rcu_preempt_check_callbacks(void)
{
}

/*
 * Because preemptible RCU does not exist, it never has any callbacks
 * to remove.
 */
static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
{
}

/*
 * Because preemptible RCU does not exist, it never has any callbacks
 * to process.
 */
static void rcu_preempt_process_callbacks(void)
{
}

#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */

907 908 909 910 911 912 913
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#include <linux/kernel_stat.h>

/*
 * During boot, we forgive RCU lockdep issues.  After this function is
 * invoked, we start taking RCU lockdep issues seriously.
 */
914
void __init rcu_scheduler_starting(void)
915 916 917 918 919 920
{
	WARN_ON(nr_context_switches() > 0);
	rcu_scheduler_active = 1;
}

#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
921 922 923 924 925 926

#ifdef CONFIG_RCU_BOOST
#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
#else /* #ifdef CONFIG_RCU_BOOST */
#define RCU_BOOST_PRIO 1
#endif /* #else #ifdef CONFIG_RCU_BOOST */
927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020

#ifdef CONFIG_RCU_TRACE

#ifdef CONFIG_RCU_BOOST

static void rcu_initiate_boost_trace(void)
{
	if (rcu_preempt_ctrlblk.gp_tasks == NULL)
		rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++;
	else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
		rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++;
	else if (rcu_preempt_ctrlblk.boosted_this_gp != 0)
		rcu_preempt_ctrlblk.n_normal_balk_boosted++;
	else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
		rcu_preempt_ctrlblk.n_normal_balk_notyet++;
	else
		rcu_preempt_ctrlblk.n_normal_balk_nos++;
}

static void rcu_initiate_exp_boost_trace(void)
{
	if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
		rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++;
	else
		rcu_preempt_ctrlblk.n_exp_balk_nos++;
}

#endif /* #ifdef CONFIG_RCU_BOOST */

static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
{
	unsigned long flags;

	raw_local_irq_save(flags);
	rcp->qlen -= n;
	raw_local_irq_restore(flags);
}

/*
 * Dump statistics for TINY_RCU, such as they are.
 */
static int show_tiny_stats(struct seq_file *m, void *unused)
{
	show_tiny_preempt_stats(m);
	seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
	seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
	return 0;
}

static int show_tiny_stats_open(struct inode *inode, struct file *file)
{
	return single_open(file, show_tiny_stats, NULL);
}

static const struct file_operations show_tiny_stats_fops = {
	.owner = THIS_MODULE,
	.open = show_tiny_stats_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

static struct dentry *rcudir;

static int __init rcutiny_trace_init(void)
{
	struct dentry *retval;

	rcudir = debugfs_create_dir("rcu", NULL);
	if (!rcudir)
		goto free_out;
	retval = debugfs_create_file("rcudata", 0444, rcudir,
				     NULL, &show_tiny_stats_fops);
	if (!retval)
		goto free_out;
	return 0;
free_out:
	debugfs_remove_recursive(rcudir);
	return 1;
}

static void __exit rcutiny_trace_cleanup(void)
{
	debugfs_remove_recursive(rcudir);
}

module_init(rcutiny_trace_init);
module_exit(rcutiny_trace_cleanup);

MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
MODULE_LICENSE("GPL");

#endif /* #ifdef CONFIG_RCU_TRACE */