rcutree_plugin.h 24.8 KB
Newer Older
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
/*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions that provide either classic
 * or preemptable semantics.
 *
 * 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.
 *
 * Copyright Red Hat, 2009
 * Copyright IBM Corporation, 2009
 *
 * Author: Ingo Molnar <mingo@elte.hu>
 *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 */

27
#include <linux/delay.h>
28 29 30 31 32 33

#ifdef CONFIG_TREE_PREEMPT_RCU

struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);

34 35
static int rcu_preempted_readers_exp(struct rcu_node *rnp);

36 37 38
/*
 * Tell them what RCU they are running.
 */
39
static void __init rcu_bootup_announce(void)
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
{
	printk(KERN_INFO
	       "Experimental preemptable hierarchical RCU implementation.\n");
}

/*
 * Return the number of RCU-preempt batches processed thus far
 * for debug and statistics.
 */
long rcu_batches_completed_preempt(void)
{
	return rcu_preempt_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);

/*
 * Return the number of RCU batches processed thus far for debug & stats.
 */
long rcu_batches_completed(void)
{
	return rcu_batches_completed_preempt();
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);

/*
 * Record a preemptable-RCU quiescent state for the specified CPU.  Note
 * that this just means that the task currently running on the CPU is
 * not in a quiescent state.  There might be any number of tasks blocked
 * while in an RCU read-side critical section.
 */
70
static void rcu_preempt_qs(int cpu)
71 72
{
	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
73
	rdp->passed_quiesc_completed = rdp->gpnum - 1;
74 75
	barrier();
	rdp->passed_quiesc = 1;
76 77 78
}

/*
79 80 81 82 83 84 85 86 87 88 89
 * 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 appropriate entry
 * of the blocked_tasks[] array.  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 blocked_tasks[] entry indexed by the low-order bit of
 * rnp->gpnum empties.
 *
 * Caller must disable preemption.
90
 */
91
static void rcu_preempt_note_context_switch(int cpu)
92 93
{
	struct task_struct *t = current;
94
	unsigned long flags;
95 96 97 98 99 100 101 102 103 104
	int phase;
	struct rcu_data *rdp;
	struct rcu_node *rnp;

	if (t->rcu_read_lock_nesting &&
	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {

		/* Possibly blocking in an RCU read-side critical section. */
		rdp = rcu_preempt_state.rda[cpu];
		rnp = rdp->mynode;
105
		spin_lock_irqsave(&rnp->lock, flags);
106
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
107
		t->rcu_blocked_node = rnp;
108 109 110 111 112 113 114 115 116 117

		/*
		 * 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.
118 119 120
		 *
		 * But first, note that the current CPU must still be
		 * on line!
121
		 */
122
		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
123 124
		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
125
		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
126
		spin_unlock_irqrestore(&rnp->lock, flags);
127 128 129 130 131 132 133 134 135 136 137
	}

	/*
	 * 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 we continue to block the current grace period.
	 */
138
	rcu_preempt_qs(cpu);
139
	local_irq_save(flags);
140
	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
141
	local_irq_restore(flags);
142 143 144 145 146 147 148 149 150 151 152 153 154 155
}

/*
 * Tree-preemptable 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)
{
	ACCESS_ONCE(current->rcu_read_lock_nesting)++;
	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);

156 157 158 159 160 161 162
/*
 * Check for preempted RCU readers blocking the current grace period
 * for the specified rcu_node structure.  If the caller needs a reliable
 * answer, it must hold the rcu_node's ->lock.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
163 164 165 166
	int phase = rnp->gpnum & 0x1;

	return !list_empty(&rnp->blocked_tasks[phase]) ||
	       !list_empty(&rnp->blocked_tasks[phase + 2]);
167 168
}

169 170 171 172 173 174 175
/*
 * Record a quiescent state for all tasks that were previously queued
 * on the specified rcu_node structure and that were blocking the current
 * RCU grace period.  The caller must hold the specified rnp->lock with
 * irqs disabled, and this lock is released upon return, but irqs remain
 * disabled.
 */
P
Paul E. McKenney 已提交
176
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193
	__releases(rnp->lock)
{
	unsigned long mask;
	struct rcu_node *rnp_p;

	if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
		spin_unlock_irqrestore(&rnp->lock, flags);
		return;  /* Still need more quiescent states! */
	}

	rnp_p = rnp->parent;
	if (rnp_p == NULL) {
		/*
		 * Either there is only one rcu_node in the tree,
		 * or tasks were kicked up to root rcu_node due to
		 * CPUs going offline.
		 */
P
Paul E. McKenney 已提交
194
		rcu_report_qs_rsp(&rcu_preempt_state, flags);
195 196 197 198 199 200 201
		return;
	}

	/* Report up the rest of the hierarchy. */
	mask = rnp->grpmask;
	spin_unlock(&rnp->lock);	/* irqs remain disabled. */
	spin_lock(&rnp_p->lock);	/* irqs already disabled. */
P
Paul E. McKenney 已提交
202
	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
203 204 205 206 207 208 209
}

/*
 * 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.
 */
210 211 212
static void rcu_read_unlock_special(struct task_struct *t)
{
	int empty;
213
	int empty_exp;
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
	unsigned long flags;
	struct rcu_node *rnp;
	int special;

	/* NMI handlers cannot block and cannot safely manipulate state. */
	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) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
231
		rcu_preempt_qs(smp_processor_id());
232 233 234 235 236 237 238 239 240 241 242 243
	}

	/* 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;

244 245 246 247 248 249
		/*
		 * Remove this task from the list it blocked on.  The
		 * task can migrate while we acquire the lock, but at
		 * most one time.  So at most two passes through loop.
		 */
		for (;;) {
250
			rnp = t->rcu_blocked_node;
251
			spin_lock(&rnp->lock);  /* irqs already disabled. */
252
			if (rnp == t->rcu_blocked_node)
253
				break;
254
			spin_unlock(&rnp->lock);  /* irqs remain disabled. */
255
		}
256
		empty = !rcu_preempted_readers(rnp);
257 258
		empty_exp = !rcu_preempted_readers_exp(rnp);
		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
259
		list_del_init(&t->rcu_node_entry);
260
		t->rcu_blocked_node = NULL;
261 262 263 264

		/*
		 * If this was the last task on the current list, and if
		 * we aren't waiting on any CPUs, report the quiescent state.
P
Paul E. McKenney 已提交
265
		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
266
		 */
267
		if (empty)
268
			spin_unlock_irqrestore(&rnp->lock, flags);
269
		else
P
Paul E. McKenney 已提交
270
			rcu_report_unblock_qs_rnp(rnp, flags);
271 272 273 274 275 276 277

		/*
		 * If this was the last task on the expedited lists,
		 * then we need to report up the rcu_node hierarchy.
		 */
		if (!empty_exp && !rcu_preempted_readers_exp(rnp))
			rcu_report_exp_rnp(&rcu_preempt_state, rnp);
278 279
	} else {
		local_irq_restore(flags);
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
	}
}

/*
 * Tree-preemptable 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 rcutree.c */
	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
		rcu_read_unlock_special(t);
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);

#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

/*
 * Scan the current list of tasks blocked within RCU read-side critical
 * sections, printing out the tid of each.
 */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
	unsigned long flags;
	struct list_head *lp;
311
	int phase;
312 313
	struct task_struct *t;

314
	if (rcu_preempted_readers(rnp)) {
315
		spin_lock_irqsave(&rnp->lock, flags);
316
		phase = rnp->gpnum & 0x1;
317 318 319 320 321 322 323 324 325
		lp = &rnp->blocked_tasks[phase];
		list_for_each_entry(t, lp, rcu_node_entry)
			printk(" P%d", t->pid);
		spin_unlock_irqrestore(&rnp->lock, flags);
	}
}

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

326 327 328 329 330 331 332 333 334
/*
 * Check that the list of blocked tasks for the newly completed grace
 * period is in fact empty.  It is a serious bug to complete a grace
 * period that still has RCU readers blocked!  This function must be
 * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
 * must be held by the caller.
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
335
	WARN_ON_ONCE(rcu_preempted_readers(rnp));
336
	WARN_ON_ONCE(rnp->qsmask);
337 338
}

339 340
#ifdef CONFIG_HOTPLUG_CPU

341 342 343 344 345 346
/*
 * Handle tasklist migration for case in which all CPUs covered by the
 * specified rcu_node have gone offline.  Move them up to the root
 * rcu_node.  The reason for not just moving them to the immediate
 * parent is to remove the need for rcu_read_unlock_special() to
 * make more than two attempts to acquire the target rcu_node's lock.
347 348
 * Returns true if there were tasks blocking the current RCU grace
 * period.
349
 *
350 351 352
 * Returns 1 if there was previously a task blocking the current grace
 * period on the specified rcu_node structure.
 *
353 354
 * The caller must hold rnp->lock with irqs disabled.
 */
355 356 357
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
358 359 360 361
{
	int i;
	struct list_head *lp;
	struct list_head *lp_root;
362
	int retval = 0;
363 364 365
	struct rcu_node *rnp_root = rcu_get_root(rsp);
	struct task_struct *tp;

366 367
	if (rnp == rnp_root) {
		WARN_ONCE(1, "Last CPU thought to be offlined?");
368
		return 0;  /* Shouldn't happen: at least one CPU online. */
369
	}
370 371
	WARN_ON_ONCE(rnp != rdp->mynode &&
		     (!list_empty(&rnp->blocked_tasks[0]) ||
372 373 374
		      !list_empty(&rnp->blocked_tasks[1]) ||
		      !list_empty(&rnp->blocked_tasks[2]) ||
		      !list_empty(&rnp->blocked_tasks[3])));
375 376 377 378 379 380 381

	/*
	 * Move tasks up to root rcu_node.  Rely on the fact that the
	 * root rcu_node can be at most one ahead of the rest of the
	 * rcu_nodes in terms of gp_num value.  This fact allows us to
	 * move the blocked_tasks[] array directly, element by element.
	 */
382 383 384 385 386
	if (rcu_preempted_readers(rnp))
		retval |= RCU_OFL_TASKS_NORM_GP;
	if (rcu_preempted_readers_exp(rnp))
		retval |= RCU_OFL_TASKS_EXP_GP;
	for (i = 0; i < 4; i++) {
387 388 389 390 391 392 393 394 395 396 397
		lp = &rnp->blocked_tasks[i];
		lp_root = &rnp_root->blocked_tasks[i];
		while (!list_empty(lp)) {
			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
			spin_lock(&rnp_root->lock); /* irqs already disabled */
			list_del(&tp->rcu_node_entry);
			tp->rcu_blocked_node = rnp_root;
			list_add(&tp->rcu_node_entry, lp_root);
			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
		}
	}
398
	return retval;
399 400
}

401 402 403 404 405 406 407 408 409 410
/*
 * Do CPU-offline processing for preemptable RCU.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
	__rcu_offline_cpu(cpu, &rcu_preempt_state);
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

411 412 413 414 415 416 417 418 419 420 421 422
/*
 * Check for a quiescent state from the current CPU.  When a task blocks,
 * the task is recorded in the corresponding CPU's rcu_node structure,
 * which is checked elsewhere.
 *
 * Caller must disable hard irqs.
 */
static void rcu_preempt_check_callbacks(int cpu)
{
	struct task_struct *t = current;

	if (t->rcu_read_lock_nesting == 0) {
423 424
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
		rcu_preempt_qs(cpu);
425 426
		return;
	}
427
	if (per_cpu(rcu_preempt_data, cpu).qs_pending)
428
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
}

/*
 * Process callbacks for preemptable RCU.
 */
static void rcu_preempt_process_callbacks(void)
{
	__rcu_process_callbacks(&rcu_preempt_state,
				&__get_cpu_var(rcu_preempt_data));
}

/*
 * Queue a preemptable-RCU callback for invocation after a grace period.
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_preempt_state);
}
EXPORT_SYMBOL_GPL(call_rcu);

449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
/**
 * 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)
{
	struct rcu_synchronize rcu;

	if (!rcu_scheduler_active)
		return;

	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);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);

473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556
static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
static 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(struct rcu_node *rnp)
{
	return !list_empty(&rnp->blocked_tasks[2]) ||
	       !list_empty(&rnp->blocked_tasks[3]);
}

/*
 * return non-zero if there is no RCU expedited grace period in progress
 * for the specified rcu_node structure, in other words, if all CPUs and
 * tasks covered by the specified rcu_node structure have done their bit
 * for the current expedited grace period.  Works only for preemptible
 * RCU -- other RCU implementation use other means.
 *
 * Caller must hold sync_rcu_preempt_exp_mutex.
 */
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
	return !rcu_preempted_readers_exp(rnp) &&
	       ACCESS_ONCE(rnp->expmask) == 0;
}

/*
 * 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.  This event is reported either to the rcu_node structure on
 * which the task was queued or to one of that rcu_node structure's ancestors,
 * recursively up the tree.  (Calm down, calm down, we do the recursion
 * iteratively!)
 *
 * Caller must hold sync_rcu_preempt_exp_mutex.
 */
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
{
	unsigned long flags;
	unsigned long mask;

	spin_lock_irqsave(&rnp->lock, flags);
	for (;;) {
		if (!sync_rcu_preempt_exp_done(rnp))
			break;
		if (rnp->parent == NULL) {
			wake_up(&sync_rcu_preempt_exp_wq);
			break;
		}
		mask = rnp->grpmask;
		spin_unlock(&rnp->lock); /* irqs remain disabled */
		rnp = rnp->parent;
		spin_lock(&rnp->lock); /* irqs already disabled */
		rnp->expmask &= ~mask;
	}
	spin_unlock_irqrestore(&rnp->lock, flags);
}

/*
 * Snapshot the tasks blocking the newly started preemptible-RCU expedited
 * grace period for the specified rcu_node structure.  If there are no such
 * tasks, report it up the rcu_node hierarchy.
 *
 * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock.
 */
static void
sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
{
	int must_wait;

	spin_lock(&rnp->lock); /* irqs already disabled */
	list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
	list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
	must_wait = rcu_preempted_readers_exp(rnp);
	spin_unlock(&rnp->lock); /* irqs remain disabled */
	if (!must_wait)
		rcu_report_exp_rnp(rsp, rnp);
}

557
/*
558 559 560 561 562
 * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
 * is to invoke synchronize_sched_expedited() to push all the tasks to
 * the ->blocked_tasks[] lists, move all entries from the first set of
 * ->blocked_tasks[] lists to the second set, and finally wait for this
 * second set to drain.
563 564 565
 */
void synchronize_rcu_expedited(void)
{
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625
	unsigned long flags;
	struct rcu_node *rnp;
	struct rcu_state *rsp = &rcu_preempt_state;
	long snap;
	int trycount = 0;

	smp_mb(); /* Caller's modifications seen first by other CPUs. */
	snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
	smp_mb(); /* Above access cannot bleed into critical section. */

	/*
	 * Acquire lock, falling back to synchronize_rcu() if too many
	 * lock-acquisition failures.  Of course, if someone does the
	 * expedited grace period for us, just leave.
	 */
	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
		if (trycount++ < 10)
			udelay(trycount * num_online_cpus());
		else {
			synchronize_rcu();
			return;
		}
		if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
			goto mb_ret; /* Others did our work for us. */
	}
	if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
		goto unlock_mb_ret; /* Others did our work for us. */

	/* force all RCU readers onto blocked_tasks[]. */
	synchronize_sched_expedited();

	spin_lock_irqsave(&rsp->onofflock, flags);

	/* Initialize ->expmask for all non-leaf rcu_node structures. */
	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
		spin_lock(&rnp->lock); /* irqs already disabled. */
		rnp->expmask = rnp->qsmaskinit;
		spin_unlock(&rnp->lock); /* irqs remain disabled. */
	}

	/* Snapshot current state of ->blocked_tasks[] lists. */
	rcu_for_each_leaf_node(rsp, rnp)
		sync_rcu_preempt_exp_init(rsp, rnp);
	if (NUM_RCU_NODES > 1)
		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));

	spin_unlock_irqrestore(&rsp->onofflock, flags);

	/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
	rnp = rcu_get_root(rsp);
	wait_event(sync_rcu_preempt_exp_wq,
		   sync_rcu_preempt_exp_done(rnp));

	/* Clean up and exit. */
	smp_mb(); /* ensure expedited GP seen before counter increment. */
	ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
unlock_mb_ret:
	mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
	smp_mb(); /* ensure subsequent action seen after grace period. */
626 627 628
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646
/*
 * Check to see if there is any immediate preemptable-RCU-related work
 * to be done.
 */
static int rcu_preempt_pending(int cpu)
{
	return __rcu_pending(&rcu_preempt_state,
			     &per_cpu(rcu_preempt_data, cpu));
}

/*
 * Does preemptable RCU need the CPU to stay out of dynticks mode?
 */
static int rcu_preempt_needs_cpu(int cpu)
{
	return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
}

647 648 649 650 651 652 653 654 655
/**
 * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
 */
void rcu_barrier(void)
{
	_rcu_barrier(&rcu_preempt_state, call_rcu);
}
EXPORT_SYMBOL_GPL(rcu_barrier);

656 657 658 659 660 661 662 663
/*
 * Initialize preemptable RCU's per-CPU data.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
}

664 665 666 667 668 669 670 671
/*
 * Move preemptable RCU's callbacks to ->orphan_cbs_list.
 */
static void rcu_preempt_send_cbs_to_orphanage(void)
{
	rcu_send_cbs_to_orphanage(&rcu_preempt_state);
}

672 673 674 675 676 677 678 679
/*
 * Initialize preemptable RCU's state structures.
 */
static void __init __rcu_init_preempt(void)
{
	RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
}

680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700
/*
 * Check for a task exiting while in a preemptable-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;
	rcu_read_unlock();
}

#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */

/*
 * Tell them what RCU they are running.
 */
701
static void __init rcu_bootup_announce(void)
702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
{
	printk(KERN_INFO "Hierarchical RCU implementation.\n");
}

/*
 * Return the number of RCU batches processed thus far for debug & stats.
 */
long rcu_batches_completed(void)
{
	return rcu_batches_completed_sched();
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);

/*
 * Because preemptable RCU does not exist, we never have to check for
 * CPUs being in quiescent states.
 */
719
static void rcu_preempt_note_context_switch(int cpu)
720 721 722
{
}

723 724 725 726 727 728 729 730 731
/*
 * Because preemptable RCU does not exist, there are never any preempted
 * RCU readers.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
	return 0;
}

732 733 734
#ifdef CONFIG_HOTPLUG_CPU

/* Because preemptible RCU does not exist, no quieting of tasks. */
P
Paul E. McKenney 已提交
735
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
736 737 738 739 740 741
{
	spin_unlock_irqrestore(&rnp->lock, flags);
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

742 743 744 745 746 747 748 749 750 751 752 753
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

/*
 * Because preemptable RCU does not exist, we never have to check for
 * tasks blocked within RCU read-side critical sections.
 */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
}

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

754 755
/*
 * Because there is no preemptable RCU, there can be no readers blocked,
756 757
 * so there is no need to check for blocked tasks.  So check only for
 * bogus qsmask values.
758 759 760
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
761
	WARN_ON_ONCE(rnp->qsmask);
762 763
}

764 765
#ifdef CONFIG_HOTPLUG_CPU

766 767
/*
 * Because preemptable RCU does not exist, it never needs to migrate
768 769 770
 * tasks that were blocked within RCU read-side critical sections, and
 * such non-existent tasks cannot possibly have been blocking the current
 * grace period.
771
 */
772 773 774
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
775
{
776
	return 0;
777 778
}

779 780 781 782 783 784 785 786 787 788
/*
 * Because preemptable RCU does not exist, it never needs CPU-offline
 * processing.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

789 790 791 792
/*
 * Because preemptable RCU does not exist, it never has any callbacks
 * to check.
 */
793
static void rcu_preempt_check_callbacks(int cpu)
794 795 796 797 798 799 800
{
}

/*
 * Because preemptable RCU does not exist, it never has any callbacks
 * to process.
 */
801
static void rcu_preempt_process_callbacks(void)
802 803 804 805 806 807 808 809 810 811 812 813
{
}

/*
 * In classic RCU, call_rcu() is just call_rcu_sched().
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	call_rcu_sched(head, func);
}
EXPORT_SYMBOL_GPL(call_rcu);

814 815 816 817 818 819 820 821 822 823
/*
 * Wait for an rcu-preempt grace period, but make it happen quickly.
 * But because preemptable RCU does not exist, map to rcu-sched.
 */
void synchronize_rcu_expedited(void)
{
	synchronize_sched_expedited();
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

824 825 826 827 828 829 830 831 832 833 834 835 836 837
#ifdef CONFIG_HOTPLUG_CPU

/*
 * Because preemptable RCU does not exist, there is never any need to
 * report on tasks preempted in RCU read-side critical sections during
 * expedited RCU grace periods.
 */
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
{
	return;
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853
/*
 * Because preemptable RCU does not exist, it never has any work to do.
 */
static int rcu_preempt_pending(int cpu)
{
	return 0;
}

/*
 * Because preemptable RCU does not exist, it never needs any CPU.
 */
static int rcu_preempt_needs_cpu(int cpu)
{
	return 0;
}

854 855 856 857 858 859 860 861 862 863
/*
 * Because preemptable RCU does not exist, rcu_barrier() is just
 * another name for rcu_barrier_sched().
 */
void rcu_barrier(void)
{
	rcu_barrier_sched();
}
EXPORT_SYMBOL_GPL(rcu_barrier);

864 865 866 867 868 869 870 871
/*
 * Because preemptable RCU does not exist, there is no per-CPU
 * data to initialize.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
}

872 873 874 875 876 877 878
/*
 * Because there is no preemptable RCU, there are no callbacks to move.
 */
static void rcu_preempt_send_cbs_to_orphanage(void)
{
}

879 880 881 882 883 884 885
/*
 * Because preemptable RCU does not exist, it need not be initialized.
 */
static void __init __rcu_init_preempt(void)
{
}

886
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */