rcutree_plugin.h 69.3 KB
Newer Older
1 2 3
/*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * 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 20 21 22 23 24 25 26
 *
 * 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 34 35 36
#define RCU_KTHREAD_PRIO 1

#ifdef CONFIG_RCU_BOOST
#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
#else
#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
#endif

37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
/*
 * Check the RCU kernel configuration parameters and print informative
 * messages about anything out of the ordinary.  If you like #ifdef, you
 * will love this function.
 */
static void __init rcu_bootup_announce_oddness(void)
{
#ifdef CONFIG_RCU_TRACE
	printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
#endif
#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
	printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
	       CONFIG_RCU_FANOUT);
#endif
#ifdef CONFIG_RCU_FANOUT_EXACT
	printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
#endif
#ifdef CONFIG_RCU_FAST_NO_HZ
	printk(KERN_INFO
	       "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
#endif
#ifdef CONFIG_PROVE_RCU
	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
#endif
#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
#endif
64
#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
65 66 67 68
	printk(KERN_INFO "\tDump stacks of tasks blocking RCU-preempt GP.\n");
#endif
#if defined(CONFIG_RCU_CPU_STALL_INFO)
	printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n");
69 70
#endif
#if NUM_RCU_LVL_4 != 0
71
	printk(KERN_INFO "\tFour-level hierarchy is enabled.\n");
72
#endif
73 74
	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
		printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
75 76
	if (nr_cpu_ids != NR_CPUS)
		printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
77 78
}

79 80
#ifdef CONFIG_TREE_PREEMPT_RCU

81 82
struct rcu_state rcu_preempt_state =
	RCU_STATE_INITIALIZER(rcu_preempt, call_rcu);
83
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
84
static struct rcu_state *rcu_state = &rcu_preempt_state;
85

86
static void rcu_read_unlock_special(struct task_struct *t);
87 88
static int rcu_preempted_readers_exp(struct rcu_node *rnp);

89 90 91
/*
 * Tell them what RCU they are running.
 */
92
static void __init rcu_bootup_announce(void)
93
{
P
Paul E. McKenney 已提交
94
	printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n");
95
	rcu_bootup_announce_oddness();
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
}

/*
 * 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);

117 118 119 120 121 122 123 124 125
/*
 * Force a quiescent state for preemptible RCU.
 */
void rcu_force_quiescent_state(void)
{
	force_quiescent_state(&rcu_preempt_state, 0);
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);

126
/*
P
Paul E. McKenney 已提交
127
 * Record a preemptible-RCU quiescent state for the specified CPU.  Note
128 129 130
 * 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.
131 132 133 134
 *
 * Unlike the other rcu_*_qs() functions, callers to this function
 * must disable irqs in order to protect the assignment to
 * ->rcu_read_unlock_special.
135
 */
136
static void rcu_preempt_qs(int cpu)
137 138
{
	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
139

140
	rdp->passed_quiesce_gpnum = rdp->gpnum;
141
	barrier();
142
	if (rdp->passed_quiesce == 0)
143
		trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs");
144
	rdp->passed_quiesce = 1;
145
	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
146 147 148
}

/*
149 150 151
 * 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
152 153 154 155 156 157
 * record that fact, so we enqueue the task on the blkd_tasks list.
 * 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 blkd_tasks list entries
 * predating the current grace period drain, in other words, until
 * rnp->gp_tasks becomes NULL.
158 159
 *
 * Caller must disable preemption.
160
 */
161
static void rcu_preempt_note_context_switch(int cpu)
162 163
{
	struct task_struct *t = current;
164
	unsigned long flags;
165 166 167
	struct rcu_data *rdp;
	struct rcu_node *rnp;

168
	if (t->rcu_read_lock_nesting > 0 &&
169 170 171
	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {

		/* Possibly blocking in an RCU read-side critical section. */
172
		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
173
		rnp = rdp->mynode;
P
Paul E. McKenney 已提交
174
		raw_spin_lock_irqsave(&rnp->lock, flags);
175
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
176
		t->rcu_blocked_node = rnp;
177 178 179 180 181 182 183 184 185

		/*
		 * 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
186 187 188 189 190 191
		 * cannot end.  Note that there is some uncertainty as
		 * to exactly when the current grace period started.
		 * We take a conservative approach, which can result
		 * in unnecessarily waiting on tasks that started very
		 * slightly after the current grace period began.  C'est
		 * la vie!!!
192 193 194
		 *
		 * But first, note that the current CPU must still be
		 * on line!
195
		 */
196
		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
197
		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
198 199 200
		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
			rnp->gp_tasks = &t->rcu_node_entry;
201 202 203 204
#ifdef CONFIG_RCU_BOOST
			if (rnp->boost_tasks != NULL)
				rnp->boost_tasks = rnp->gp_tasks;
#endif /* #ifdef CONFIG_RCU_BOOST */
205 206 207 208 209
		} else {
			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
			if (rnp->qsmask & rdp->grpmask)
				rnp->gp_tasks = &t->rcu_node_entry;
		}
210 211 212 213 214
		trace_rcu_preempt_task(rdp->rsp->name,
				       t->pid,
				       (rnp->qsmask & rdp->grpmask)
				       ? rnp->gpnum
				       : rnp->gpnum + 1);
P
Paul E. McKenney 已提交
215
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
216 217 218 219 220 221 222 223
	} else if (t->rcu_read_lock_nesting < 0 &&
		   t->rcu_read_unlock_special) {

		/*
		 * Complete exit from RCU read-side critical section on
		 * behalf of preempted instance of __rcu_read_unlock().
		 */
		rcu_read_unlock_special(t);
224 225 226 227 228 229 230 231 232 233 234
	}

	/*
	 * 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.
	 */
235
	local_irq_save(flags);
236
	rcu_preempt_qs(cpu);
237
	local_irq_restore(flags);
238 239 240
}

/*
P
Paul E. McKenney 已提交
241
 * Tree-preemptible RCU implementation for rcu_read_lock().
242 243 244 245 246
 * Just increment ->rcu_read_lock_nesting, shared state will be updated
 * if we block.
 */
void __rcu_read_lock(void)
{
247
	current->rcu_read_lock_nesting++;
248 249 250 251
	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);

252 253 254 255 256
/*
 * 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.
 */
257
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
258
{
259
	return rnp->gp_tasks != NULL;
260 261
}

262 263 264 265 266 267 268
/*
 * 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
269
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
270 271 272 273 274
	__releases(rnp->lock)
{
	unsigned long mask;
	struct rcu_node *rnp_p;

275
	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
P
Paul E. McKenney 已提交
276
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
277 278 279 280 281 282 283 284 285 286
		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
287
		rcu_report_qs_rsp(&rcu_preempt_state, flags);
288 289 290 291 292
		return;
	}

	/* Report up the rest of the hierarchy. */
	mask = rnp->grpmask;
P
Paul E. McKenney 已提交
293 294
	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
P
Paul E. McKenney 已提交
295
	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
296 297
}

298 299 300 301 302 303 304 305 306 307 308 309 310 311 312
/*
 * 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 rcu_node *rnp)
{
	struct list_head *np;

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

313 314 315 316 317
/*
 * 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.
 */
318
static noinline void rcu_read_unlock_special(struct task_struct *t)
319 320
{
	int empty;
321
	int empty_exp;
322
	int empty_exp_now;
323
	unsigned long flags;
324
	struct list_head *np;
325 326 327
#ifdef CONFIG_RCU_BOOST
	struct rt_mutex *rbmp = NULL;
#endif /* #ifdef CONFIG_RCU_BOOST */
328 329 330 331 332 333 334 335 336 337 338 339 340 341 342
	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) {
343
		rcu_preempt_qs(smp_processor_id());
344 345 346
	}

	/* Hardware IRQ handlers cannot block. */
347
	if (in_irq() || in_serving_softirq()) {
348 349 350 351 352 353 354 355
		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;

356 357 358 359 360 361
		/*
		 * 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 (;;) {
362
			rnp = t->rcu_blocked_node;
P
Paul E. McKenney 已提交
363
			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
364
			if (rnp == t->rcu_blocked_node)
365
				break;
P
Paul E. McKenney 已提交
366
			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
367
		}
368
		empty = !rcu_preempt_blocked_readers_cgp(rnp);
369 370
		empty_exp = !rcu_preempted_readers_exp(rnp);
		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
371
		np = rcu_next_node_entry(t, rnp);
372
		list_del_init(&t->rcu_node_entry);
373
		t->rcu_blocked_node = NULL;
374 375
		trace_rcu_unlock_preempted_task("rcu_preempt",
						rnp->gpnum, t->pid);
376 377 378 379
		if (&t->rcu_node_entry == rnp->gp_tasks)
			rnp->gp_tasks = np;
		if (&t->rcu_node_entry == rnp->exp_tasks)
			rnp->exp_tasks = np;
380 381 382
#ifdef CONFIG_RCU_BOOST
		if (&t->rcu_node_entry == rnp->boost_tasks)
			rnp->boost_tasks = np;
383 384 385 386
		/* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */
		if (t->rcu_boost_mutex) {
			rbmp = t->rcu_boost_mutex;
			t->rcu_boost_mutex = NULL;
387
		}
388
#endif /* #ifdef CONFIG_RCU_BOOST */
389 390 391 392

		/*
		 * If this was the last task on the current list, and if
		 * we aren't waiting on any CPUs, report the quiescent state.
393 394
		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
		 * so we must take a snapshot of the expedited state.
395
		 */
396
		empty_exp_now = !rcu_preempted_readers_exp(rnp);
397 398 399 400 401 402 403 404
		if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) {
			trace_rcu_quiescent_state_report("preempt_rcu",
							 rnp->gpnum,
							 0, rnp->qsmask,
							 rnp->level,
							 rnp->grplo,
							 rnp->grphi,
							 !!rnp->gp_tasks);
P
Paul E. McKenney 已提交
405
			rcu_report_unblock_qs_rnp(rnp, flags);
406 407
		} else
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
408

409 410
#ifdef CONFIG_RCU_BOOST
		/* Unboost if we were boosted. */
411 412
		if (rbmp)
			rt_mutex_unlock(rbmp);
413 414
#endif /* #ifdef CONFIG_RCU_BOOST */

415 416 417 418
		/*
		 * If this was the last task on the expedited lists,
		 * then we need to report up the rcu_node hierarchy.
		 */
419
		if (!empty_exp && empty_exp_now)
420
			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
421 422
	} else {
		local_irq_restore(flags);
423 424 425 426
	}
}

/*
P
Paul E. McKenney 已提交
427
 * Tree-preemptible RCU implementation for rcu_read_unlock().
428 429 430 431 432 433 434 435 436
 * 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;

437 438 439
	if (t->rcu_read_lock_nesting != 1)
		--t->rcu_read_lock_nesting;
	else {
440
		barrier();  /* critical section before exit code. */
441 442
		t->rcu_read_lock_nesting = INT_MIN;
		barrier();  /* assign before ->rcu_read_unlock_special load */
443 444
		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
			rcu_read_unlock_special(t);
445 446
		barrier();  /* ->rcu_read_unlock_special load before assign */
		t->rcu_read_lock_nesting = 0;
447
	}
448
#ifdef CONFIG_PROVE_LOCKING
449 450 451 452 453
	{
		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);

		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
	}
454
#endif /* #ifdef CONFIG_PROVE_LOCKING */
455 456 457
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);

458 459 460 461 462 463 464 465 466 467 468
#ifdef CONFIG_RCU_CPU_STALL_VERBOSE

/*
 * Dump detailed information for all tasks blocking the current RCU
 * grace period on the specified rcu_node structure.
 */
static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
{
	unsigned long flags;
	struct task_struct *t;

469
	if (!rcu_preempt_blocked_readers_cgp(rnp))
470 471 472 473 474 475 476
		return;
	raw_spin_lock_irqsave(&rnp->lock, flags);
	t = list_entry(rnp->gp_tasks,
		       struct task_struct, rcu_node_entry);
	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
		sched_show_task(t);
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
}

/*
 * Dump detailed information for all tasks blocking the current RCU
 * grace period.
 */
static void rcu_print_detail_task_stall(struct rcu_state *rsp)
{
	struct rcu_node *rnp = rcu_get_root(rsp);

	rcu_print_detail_task_stall_rnp(rnp);
	rcu_for_each_leaf_node(rsp, rnp)
		rcu_print_detail_task_stall_rnp(rnp);
}

#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */

static void rcu_print_detail_task_stall(struct rcu_state *rsp)
{
}

#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */

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
#ifdef CONFIG_RCU_CPU_STALL_INFO

static void rcu_print_task_stall_begin(struct rcu_node *rnp)
{
	printk(KERN_ERR "\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
	       rnp->level, rnp->grplo, rnp->grphi);
}

static void rcu_print_task_stall_end(void)
{
	printk(KERN_CONT "\n");
}

#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */

static void rcu_print_task_stall_begin(struct rcu_node *rnp)
{
}

static void rcu_print_task_stall_end(void)
{
}

#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */

525 526 527 528
/*
 * Scan the current list of tasks blocked within RCU read-side critical
 * sections, printing out the tid of each.
 */
529
static int rcu_print_task_stall(struct rcu_node *rnp)
530 531
{
	struct task_struct *t;
532
	int ndetected = 0;
533

534
	if (!rcu_preempt_blocked_readers_cgp(rnp))
535
		return 0;
536
	rcu_print_task_stall_begin(rnp);
537 538
	t = list_entry(rnp->gp_tasks,
		       struct task_struct, rcu_node_entry);
539
	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
540
		printk(KERN_CONT " P%d", t->pid);
541 542
		ndetected++;
	}
543
	rcu_print_task_stall_end();
544
	return ndetected;
545 546
}

547 548 549 550 551 552 553 554 555 556
/*
 * Suppress preemptible RCU's CPU stall warnings by pushing the
 * time of the next stall-warning message comfortably far into the
 * future.
 */
static void rcu_preempt_stall_reset(void)
{
	rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
}

557 558 559 560 561 562
/*
 * 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.
563 564 565
 *
 * Also, if there are blocked tasks on the list, they automatically
 * block the newly created grace period, so set up ->gp_tasks accordingly.
566 567 568
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
569
	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
570 571
	if (!list_empty(&rnp->blkd_tasks))
		rnp->gp_tasks = rnp->blkd_tasks.next;
572
	WARN_ON_ONCE(rnp->qsmask);
573 574
}

575 576
#ifdef CONFIG_HOTPLUG_CPU

577 578 579 580 581 582
/*
 * 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.
583 584
 * Returns true if there were tasks blocking the current RCU grace
 * period.
585
 *
586 587 588
 * Returns 1 if there was previously a task blocking the current grace
 * period on the specified rcu_node structure.
 *
589 590
 * The caller must hold rnp->lock with irqs disabled.
 */
591 592 593
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
594 595 596
{
	struct list_head *lp;
	struct list_head *lp_root;
597
	int retval = 0;
598
	struct rcu_node *rnp_root = rcu_get_root(rsp);
599
	struct task_struct *t;
600

601 602
	if (rnp == rnp_root) {
		WARN_ONCE(1, "Last CPU thought to be offlined?");
603
		return 0;  /* Shouldn't happen: at least one CPU online. */
604
	}
605 606 607

	/* If we are on an internal node, complain bitterly. */
	WARN_ON_ONCE(rnp != rdp->mynode);
608 609

	/*
610 611 612 613 614 615 616
	 * Move tasks up to root rcu_node.  Don't try to get fancy for
	 * this corner-case operation -- just put this node's tasks
	 * at the head of the root node's list, and update the root node's
	 * ->gp_tasks and ->exp_tasks pointers to those of this node's,
	 * if non-NULL.  This might result in waiting for more tasks than
	 * absolutely necessary, but this is a good performance/complexity
	 * tradeoff.
617
	 */
618
	if (rcu_preempt_blocked_readers_cgp(rnp) && rnp->qsmask == 0)
619 620 621
		retval |= RCU_OFL_TASKS_NORM_GP;
	if (rcu_preempted_readers_exp(rnp))
		retval |= RCU_OFL_TASKS_EXP_GP;
622 623 624 625 626 627 628 629 630 631 632 633
	lp = &rnp->blkd_tasks;
	lp_root = &rnp_root->blkd_tasks;
	while (!list_empty(lp)) {
		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
		list_del(&t->rcu_node_entry);
		t->rcu_blocked_node = rnp_root;
		list_add(&t->rcu_node_entry, lp_root);
		if (&t->rcu_node_entry == rnp->gp_tasks)
			rnp_root->gp_tasks = rnp->gp_tasks;
		if (&t->rcu_node_entry == rnp->exp_tasks)
			rnp_root->exp_tasks = rnp->exp_tasks;
634 635 636 637
#ifdef CONFIG_RCU_BOOST
		if (&t->rcu_node_entry == rnp->boost_tasks)
			rnp_root->boost_tasks = rnp->boost_tasks;
#endif /* #ifdef CONFIG_RCU_BOOST */
638
		raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
639
	}
640 641 642 643 644 645 646 647 648 649

#ifdef CONFIG_RCU_BOOST
	/* In case root is being boosted and leaf is not. */
	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
	if (rnp_root->boost_tasks != NULL &&
	    rnp_root->boost_tasks != rnp_root->gp_tasks)
		rnp_root->boost_tasks = rnp_root->gp_tasks;
	raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
#endif /* #ifdef CONFIG_RCU_BOOST */

650 651
	rnp->gp_tasks = NULL;
	rnp->exp_tasks = NULL;
652
	return retval;
653 654
}

655 656
#endif /* #ifdef CONFIG_HOTPLUG_CPU */

657
/*
P
Paul E. McKenney 已提交
658
 * Do CPU-offline processing for preemptible RCU.
659
 */
660
static void rcu_preempt_cleanup_dead_cpu(int cpu)
661
{
662
	rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state);
663 664
}

665 666 667 668 669 670 671 672 673 674 675 676
/*
 * 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) {
677
		rcu_preempt_qs(cpu);
678 679
		return;
	}
680 681
	if (t->rcu_read_lock_nesting > 0 &&
	    per_cpu(rcu_preempt_data, cpu).qs_pending)
682
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
683 684 685
}

/*
P
Paul E. McKenney 已提交
686
 * Process callbacks for preemptible RCU.
687 688 689
 */
static void rcu_preempt_process_callbacks(void)
{
690
	__rcu_process_callbacks(&rcu_preempt_state);
691 692
}

693 694
#ifdef CONFIG_RCU_BOOST

695 696 697 698 699
static void rcu_preempt_do_callbacks(void)
{
	rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
}

700 701
#endif /* #ifdef CONFIG_RCU_BOOST */

702
/*
P
Paul E. McKenney 已提交
703
 * Queue a preemptible-RCU callback for invocation after a grace period.
704 705 706
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
707
	__call_rcu(head, func, &rcu_preempt_state, 0);
708 709 710
}
EXPORT_SYMBOL_GPL(call_rcu);

711 712 713 714 715 716 717 718 719 720 721 722 723 724
/*
 * Queue an RCU callback for lazy invocation after a grace period.
 * This will likely be later named something like "call_rcu_lazy()",
 * but this change will require some way of tagging the lazy RCU
 * callbacks in the list of pending callbacks.  Until then, this
 * function may only be called from __kfree_rcu().
 */
void kfree_call_rcu(struct rcu_head *head,
		    void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_preempt_state, 1);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);

725 726 727 728 729
/**
 * 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
730 731 732 733 734
 * read-side critical sections have completed.  Note, however, that
 * upon return from synchronize_rcu(), the caller might well be executing
 * concurrently with new RCU read-side critical sections that began while
 * synchronize_rcu() was waiting.  RCU read-side critical sections are
 * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
735 736 737
 */
void synchronize_rcu(void)
{
738 739 740 741
	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
			   !lock_is_held(&rcu_lock_map) &&
			   !lock_is_held(&rcu_sched_lock_map),
			   "Illegal synchronize_rcu() in RCU read-side critical section");
742 743
	if (!rcu_scheduler_active)
		return;
744
	wait_rcu_gp(call_rcu);
745 746 747
}
EXPORT_SYMBOL_GPL(synchronize_rcu);

748 749 750 751 752 753 754 755 756 757 758 759
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)
{
760
	return rnp->exp_tasks != NULL;
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
}

/*
 * 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!)
 *
786 787 788
 * Most callers will set the "wake" flag, but the task initiating the
 * expedited grace period need not wake itself.
 *
789 790
 * Caller must hold sync_rcu_preempt_exp_mutex.
 */
791 792
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
			       bool wake)
793 794 795 796
{
	unsigned long flags;
	unsigned long mask;

P
Paul E. McKenney 已提交
797
	raw_spin_lock_irqsave(&rnp->lock, flags);
798
	for (;;) {
799 800
		if (!sync_rcu_preempt_exp_done(rnp)) {
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
801
			break;
802
		}
803
		if (rnp->parent == NULL) {
804
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
805 806
			if (wake)
				wake_up(&sync_rcu_preempt_exp_wq);
807 808 809
			break;
		}
		mask = rnp->grpmask;
P
Paul E. McKenney 已提交
810
		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
811
		rnp = rnp->parent;
P
Paul E. McKenney 已提交
812
		raw_spin_lock(&rnp->lock); /* irqs already disabled */
813 814 815 816 817 818 819 820 821 822 823 824 825 826
		rnp->expmask &= ~mask;
	}
}

/*
 * 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)
{
827
	unsigned long flags;
828
	int must_wait = 0;
829

830 831 832 833
	raw_spin_lock_irqsave(&rnp->lock, flags);
	if (list_empty(&rnp->blkd_tasks))
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	else {
834
		rnp->exp_tasks = rnp->blkd_tasks.next;
835
		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
836 837
		must_wait = 1;
	}
838
	if (!must_wait)
839
		rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */
840 841
}

842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857
/**
 * synchronize_rcu_expedited - Brute-force RCU grace period
 *
 * 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 ->blkd_tasks lists and wait for this list to drain.  This consumes
 * significant time on all CPUs and is unfriendly to real-time workloads,
 * so is thus not recommended for any sort of common-case code.
 * In fact, if you are using synchronize_rcu_expedited() in a loop,
 * please restructure your code to batch your updates, and then Use a
 * single synchronize_rcu() instead.
 *
 * Note that it is illegal to call this function while holding any lock
 * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
 * to call this function from a CPU-hotplug notifier.  Failing to observe
 * these restriction will result in deadlock.
858 859 860
 */
void synchronize_rcu_expedited(void)
{
861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888
	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. */

889
	/* force all RCU readers onto ->blkd_tasks lists. */
890 891
	synchronize_sched_expedited();

P
Paul E. McKenney 已提交
892
	raw_spin_lock_irqsave(&rsp->onofflock, flags);
893 894 895

	/* Initialize ->expmask for all non-leaf rcu_node structures. */
	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
P
Paul E. McKenney 已提交
896
		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
897
		rnp->expmask = rnp->qsmaskinit;
P
Paul E. McKenney 已提交
898
		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
899 900
	}

901
	/* Snapshot current state of ->blkd_tasks lists. */
902 903 904 905 906
	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));

P
Paul E. McKenney 已提交
907
	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
908

909
	/* Wait for snapshotted ->blkd_tasks lists to drain. */
910 911 912 913 914 915 916 917 918 919 920
	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. */
921 922 923
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

924
/*
P
Paul E. McKenney 已提交
925
 * Check to see if there is any immediate preemptible-RCU-related work
926 927 928 929 930 931 932 933 934
 * to be done.
 */
static int rcu_preempt_pending(int cpu)
{
	return __rcu_pending(&rcu_preempt_state,
			     &per_cpu(rcu_preempt_data, cpu));
}

/*
935
 * Does preemptible RCU have callbacks on this CPU?
936
 */
937
static int rcu_preempt_cpu_has_callbacks(int cpu)
938 939 940 941
{
	return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
}

942 943 944 945 946
/**
 * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
 */
void rcu_barrier(void)
{
947
	_rcu_barrier(&rcu_preempt_state);
948 949 950
}
EXPORT_SYMBOL_GPL(rcu_barrier);

951
/*
P
Paul E. McKenney 已提交
952
 * Initialize preemptible RCU's per-CPU data.
953 954 955 956 957 958
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
}

959
/*
960 961
 * Move preemptible RCU's callbacks from dying CPU to other online CPU
 * and record a quiescent state.
962
 */
963
static void rcu_preempt_cleanup_dying_cpu(void)
964
{
965
	rcu_cleanup_dying_cpu(&rcu_preempt_state);
966 967
}

968
/*
P
Paul E. McKenney 已提交
969
 * Initialize preemptible RCU's state structures.
970 971 972
 */
static void __init __rcu_init_preempt(void)
{
973
	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
974 975
}

976 977
#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */

978 979
static struct rcu_state *rcu_state = &rcu_sched_state;

980 981 982
/*
 * Tell them what RCU they are running.
 */
983
static void __init rcu_bootup_announce(void)
984 985
{
	printk(KERN_INFO "Hierarchical RCU implementation.\n");
986
	rcu_bootup_announce_oddness();
987 988 989 990 991 992 993 994 995 996 997
}

/*
 * 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);

998 999 1000 1001 1002 1003 1004 1005 1006 1007
/*
 * Force a quiescent state for RCU, which, because there is no preemptible
 * RCU, becomes the same as rcu-sched.
 */
void rcu_force_quiescent_state(void)
{
	rcu_sched_force_quiescent_state();
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);

1008 1009 1010 1011 1012 1013 1014 1015
/*
 * Because preemptible RCU does not exist, we never have to check for
 * CPUs being in quiescent states.
 */
static void rcu_preempt_note_context_switch(int cpu)
{
}

1016
/*
P
Paul E. McKenney 已提交
1017
 * Because preemptible RCU does not exist, there are never any preempted
1018 1019
 * RCU readers.
 */
1020
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
1021 1022 1023 1024
{
	return 0;
}

1025 1026 1027
#ifdef CONFIG_HOTPLUG_CPU

/* Because preemptible RCU does not exist, no quieting of tasks. */
P
Paul E. McKenney 已提交
1028
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
1029
{
P
Paul E. McKenney 已提交
1030
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
1031 1032 1033 1034
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

1035
/*
P
Paul E. McKenney 已提交
1036
 * Because preemptible RCU does not exist, we never have to check for
1037 1038 1039 1040 1041 1042
 * tasks blocked within RCU read-side critical sections.
 */
static void rcu_print_detail_task_stall(struct rcu_state *rsp)
{
}

1043
/*
P
Paul E. McKenney 已提交
1044
 * Because preemptible RCU does not exist, we never have to check for
1045 1046
 * tasks blocked within RCU read-side critical sections.
 */
1047
static int rcu_print_task_stall(struct rcu_node *rnp)
1048
{
1049
	return 0;
1050 1051
}

1052 1053 1054 1055 1056 1057 1058 1059
/*
 * Because preemptible RCU does not exist, there is no need to suppress
 * its CPU stall warnings.
 */
static void rcu_preempt_stall_reset(void)
{
}

1060
/*
P
Paul E. McKenney 已提交
1061
 * Because there is no preemptible RCU, there can be no readers blocked,
1062 1063
 * so there is no need to check for blocked tasks.  So check only for
 * bogus qsmask values.
1064 1065 1066
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
1067
	WARN_ON_ONCE(rnp->qsmask);
1068 1069
}

1070 1071
#ifdef CONFIG_HOTPLUG_CPU

1072
/*
P
Paul E. McKenney 已提交
1073
 * Because preemptible RCU does not exist, it never needs to migrate
1074 1075 1076
 * tasks that were blocked within RCU read-side critical sections, and
 * such non-existent tasks cannot possibly have been blocking the current
 * grace period.
1077
 */
1078 1079 1080
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
1081
{
1082
	return 0;
1083 1084
}

1085 1086
#endif /* #ifdef CONFIG_HOTPLUG_CPU */

1087
/*
P
Paul E. McKenney 已提交
1088
 * Because preemptible RCU does not exist, it never needs CPU-offline
1089 1090
 * processing.
 */
1091
static void rcu_preempt_cleanup_dead_cpu(int cpu)
1092 1093 1094
{
}

1095
/*
P
Paul E. McKenney 已提交
1096
 * Because preemptible RCU does not exist, it never has any callbacks
1097 1098
 * to check.
 */
1099
static void rcu_preempt_check_callbacks(int cpu)
1100 1101 1102 1103
{
}

/*
P
Paul E. McKenney 已提交
1104
 * Because preemptible RCU does not exist, it never has any callbacks
1105 1106
 * to process.
 */
1107
static void rcu_preempt_process_callbacks(void)
1108 1109 1110
{
}

1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126
/*
 * Queue an RCU callback for lazy invocation after a grace period.
 * This will likely be later named something like "call_rcu_lazy()",
 * but this change will require some way of tagging the lazy RCU
 * callbacks in the list of pending callbacks.  Until then, this
 * function may only be called from __kfree_rcu().
 *
 * Because there is no preemptible RCU, we use RCU-sched instead.
 */
void kfree_call_rcu(struct rcu_head *head,
		    void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_sched_state, 1);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);

1127 1128
/*
 * Wait for an rcu-preempt grace period, but make it happen quickly.
P
Paul E. McKenney 已提交
1129
 * But because preemptible RCU does not exist, map to rcu-sched.
1130 1131 1132 1133 1134 1135 1136
 */
void synchronize_rcu_expedited(void)
{
	synchronize_sched_expedited();
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

1137 1138 1139
#ifdef CONFIG_HOTPLUG_CPU

/*
P
Paul E. McKenney 已提交
1140
 * Because preemptible RCU does not exist, there is never any need to
1141 1142 1143
 * report on tasks preempted in RCU read-side critical sections during
 * expedited RCU grace periods.
 */
1144 1145
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
			       bool wake)
1146 1147 1148 1149 1150
{
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

1151
/*
P
Paul E. McKenney 已提交
1152
 * Because preemptible RCU does not exist, it never has any work to do.
1153 1154 1155 1156 1157 1158 1159
 */
static int rcu_preempt_pending(int cpu)
{
	return 0;
}

/*
1160
 * Because preemptible RCU does not exist, it never has callbacks
1161
 */
1162
static int rcu_preempt_cpu_has_callbacks(int cpu)
1163 1164 1165 1166
{
	return 0;
}

1167
/*
P
Paul E. McKenney 已提交
1168
 * Because preemptible RCU does not exist, rcu_barrier() is just
1169 1170 1171 1172 1173 1174 1175 1176
 * another name for rcu_barrier_sched().
 */
void rcu_barrier(void)
{
	rcu_barrier_sched();
}
EXPORT_SYMBOL_GPL(rcu_barrier);

1177
/*
P
Paul E. McKenney 已提交
1178
 * Because preemptible RCU does not exist, there is no per-CPU
1179 1180 1181 1182 1183 1184
 * data to initialize.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
}

1185
/*
1186
 * Because there is no preemptible RCU, there is no cleanup to do.
1187
 */
1188
static void rcu_preempt_cleanup_dying_cpu(void)
1189 1190 1191
{
}

1192
/*
P
Paul E. McKenney 已提交
1193
 * Because preemptible RCU does not exist, it need not be initialized.
1194 1195 1196 1197 1198
 */
static void __init __rcu_init_preempt(void)
{
}

1199
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
1200

1201 1202 1203 1204
#ifdef CONFIG_RCU_BOOST

#include "rtmutex_common.h"

1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
#ifdef CONFIG_RCU_TRACE

static void rcu_initiate_boost_trace(struct rcu_node *rnp)
{
	if (list_empty(&rnp->blkd_tasks))
		rnp->n_balk_blkd_tasks++;
	else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL)
		rnp->n_balk_exp_gp_tasks++;
	else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL)
		rnp->n_balk_boost_tasks++;
	else if (rnp->gp_tasks != NULL && rnp->qsmask != 0)
		rnp->n_balk_notblocked++;
	else if (rnp->gp_tasks != NULL &&
1218
		 ULONG_CMP_LT(jiffies, rnp->boost_time))
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231
		rnp->n_balk_notyet++;
	else
		rnp->n_balk_nos++;
}

#else /* #ifdef CONFIG_RCU_TRACE */

static void rcu_initiate_boost_trace(struct rcu_node *rnp)
{
}

#endif /* #else #ifdef CONFIG_RCU_TRACE */

1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
/*
 * Carry out RCU priority boosting on the task indicated by ->exp_tasks
 * or ->boost_tasks, advancing the pointer to the next task in the
 * ->blkd_tasks list.
 *
 * Note that irqs must be enabled: boosting the task can block.
 * Returns 1 if there are more tasks needing to be boosted.
 */
static int rcu_boost(struct rcu_node *rnp)
{
	unsigned long flags;
	struct rt_mutex mtx;
	struct task_struct *t;
	struct list_head *tb;

	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL)
		return 0;  /* Nothing left to boost. */

	raw_spin_lock_irqsave(&rnp->lock, flags);

	/*
	 * Recheck under the lock: all tasks in need of boosting
	 * might exit their RCU read-side critical sections on their own.
	 */
	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) {
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		return 0;
	}

	/*
	 * Preferentially boost tasks blocking expedited grace periods.
	 * This cannot starve the normal grace periods because a second
	 * expedited grace period must boost all blocked tasks, including
	 * those blocking the pre-existing normal grace period.
	 */
1267
	if (rnp->exp_tasks != NULL) {
1268
		tb = rnp->exp_tasks;
1269 1270
		rnp->n_exp_boosts++;
	} else {
1271
		tb = rnp->boost_tasks;
1272 1273 1274
		rnp->n_normal_boosts++;
	}
	rnp->n_tasks_boosted++;
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298

	/*
	 * We boost task t by manufacturing an rt_mutex that appears to
	 * be held by task t.  We leave a pointer to that rt_mutex where
	 * task t can find it, and task t will release the mutex when it
	 * exits its outermost RCU read-side critical section.  Then
	 * simply acquiring this artificial rt_mutex will boost task
	 * t's priority.  (Thanks to tglx for suggesting this approach!)
	 *
	 * Note that task t must acquire rnp->lock to remove itself from
	 * the ->blkd_tasks list, which it will do from exit() if from
	 * nowhere else.  We therefore are guaranteed that task t will
	 * stay around at least until we drop rnp->lock.  Note that
	 * rnp->lock also resolves races between our priority boosting
	 * and task t's exiting its outermost RCU read-side critical
	 * section.
	 */
	t = container_of(tb, struct task_struct, rcu_node_entry);
	rt_mutex_init_proxy_locked(&mtx, t);
	t->rcu_boost_mutex = &mtx;
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */

1299 1300
	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
}

/*
 * Timer handler to initiate waking up of boost kthreads that
 * have yielded the CPU due to excessive numbers of tasks to
 * boost.  We wake up the per-rcu_node kthread, which in turn
 * will wake up the booster kthread.
 */
static void rcu_boost_kthread_timer(unsigned long arg)
{
1311
	invoke_rcu_node_kthread((struct rcu_node *)arg);
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323
}

/*
 * Priority-boosting kthread.  One per leaf rcu_node and one for the
 * root rcu_node.
 */
static int rcu_boost_kthread(void *arg)
{
	struct rcu_node *rnp = (struct rcu_node *)arg;
	int spincnt = 0;
	int more2boost;

1324
	trace_rcu_utilization("Start boost kthread@init");
1325
	for (;;) {
1326
		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
1327
		trace_rcu_utilization("End boost kthread@rcu_wait");
1328
		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
1329
		trace_rcu_utilization("Start boost kthread@rcu_wait");
1330
		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
1331 1332 1333 1334 1335 1336
		more2boost = rcu_boost(rnp);
		if (more2boost)
			spincnt++;
		else
			spincnt = 0;
		if (spincnt > 10) {
1337
			trace_rcu_utilization("End boost kthread@rcu_yield");
1338
			rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
1339
			trace_rcu_utilization("Start boost kthread@rcu_yield");
1340 1341 1342
			spincnt = 0;
		}
	}
1343
	/* NOTREACHED */
1344
	trace_rcu_utilization("End boost kthread@notreached");
1345 1346 1347 1348 1349 1350 1351 1352 1353
	return 0;
}

/*
 * Check to see if it is time to start boosting RCU readers that are
 * blocking the current grace period, and, if so, tell the per-rcu_node
 * kthread to start boosting them.  If there is an expedited grace
 * period in progress, it is always time to boost.
 *
1354 1355 1356
 * The caller must hold rnp->lock, which this function releases,
 * but irqs remain disabled.  The ->boost_kthread_task is immortal,
 * so we don't need to worry about it going away.
1357
 */
1358
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
1359 1360 1361
{
	struct task_struct *t;

1362 1363
	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
		rnp->n_balk_exp_gp_tasks++;
1364
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
1365
		return;
1366
	}
1367 1368 1369 1370 1371 1372 1373
	if (rnp->exp_tasks != NULL ||
	    (rnp->gp_tasks != NULL &&
	     rnp->boost_tasks == NULL &&
	     rnp->qsmask == 0 &&
	     ULONG_CMP_GE(jiffies, rnp->boost_time))) {
		if (rnp->exp_tasks == NULL)
			rnp->boost_tasks = rnp->gp_tasks;
1374
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
1375 1376 1377
		t = rnp->boost_kthread_task;
		if (t != NULL)
			wake_up_process(t);
1378
	} else {
1379
		rcu_initiate_boost_trace(rnp);
1380 1381
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	}
1382 1383
}

1384 1385 1386 1387 1388 1389 1390 1391 1392
/*
 * Wake up the per-CPU kthread to invoke RCU callbacks.
 */
static void invoke_rcu_callbacks_kthread(void)
{
	unsigned long flags;

	local_irq_save(flags);
	__this_cpu_write(rcu_cpu_has_work, 1);
1393 1394 1395
	if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
	    current != __this_cpu_read(rcu_cpu_kthread_task))
		wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
1396 1397 1398
	local_irq_restore(flags);
}

1399 1400 1401 1402 1403 1404 1405 1406 1407
/*
 * Is the current CPU running the RCU-callbacks kthread?
 * Caller must have preemption disabled.
 */
static bool rcu_is_callbacks_kthread(void)
{
	return __get_cpu_var(rcu_cpu_kthread_task) == current;
}

1408 1409 1410 1411 1412
/*
 * Set the affinity of the boost kthread.  The CPU-hotplug locks are
 * held, so no one should be messing with the existence of the boost
 * kthread.
 */
1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
					  cpumask_var_t cm)
{
	struct task_struct *t;

	t = rnp->boost_kthread_task;
	if (t != NULL)
		set_cpus_allowed_ptr(rnp->boost_kthread_task, cm);
}

#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(struct rcu_node *rnp)
{
	rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
}

/*
 * Create an RCU-boost kthread for the specified node if one does not
 * already exist.  We only create this kthread for preemptible RCU.
 * Returns zero if all is well, a negated errno otherwise.
 */
static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
						 struct rcu_node *rnp,
						 int rnp_index)
{
	unsigned long flags;
	struct sched_param sp;
	struct task_struct *t;

	if (&rcu_preempt_state != rsp)
		return 0;
1448
	rsp->boost = 1;
1449 1450 1451
	if (rnp->boost_kthread_task != NULL)
		return 0;
	t = kthread_create(rcu_boost_kthread, (void *)rnp,
1452
			   "rcub/%d", rnp_index);
1453 1454 1455 1456 1457
	if (IS_ERR(t))
		return PTR_ERR(t);
	raw_spin_lock_irqsave(&rnp->lock, flags);
	rnp->boost_kthread_task = t;
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
1458
	sp.sched_priority = RCU_BOOST_PRIO;
1459
	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
1460
	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
1461 1462 1463
	return 0;
}

1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552
#ifdef CONFIG_HOTPLUG_CPU

/*
 * Stop the RCU's per-CPU kthread when its CPU goes offline,.
 */
static void rcu_stop_cpu_kthread(int cpu)
{
	struct task_struct *t;

	/* Stop the CPU's kthread. */
	t = per_cpu(rcu_cpu_kthread_task, cpu);
	if (t != NULL) {
		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
		kthread_stop(t);
	}
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

static void rcu_kthread_do_work(void)
{
	rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
	rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
	rcu_preempt_do_callbacks();
}

/*
 * Wake up the specified per-rcu_node-structure kthread.
 * Because the per-rcu_node kthreads are immortal, we don't need
 * to do anything to keep them alive.
 */
static void invoke_rcu_node_kthread(struct rcu_node *rnp)
{
	struct task_struct *t;

	t = rnp->node_kthread_task;
	if (t != NULL)
		wake_up_process(t);
}

/*
 * Set the specified CPU's kthread to run RT or not, as specified by
 * the to_rt argument.  The CPU-hotplug locks are held, so the task
 * is not going away.
 */
static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
{
	int policy;
	struct sched_param sp;
	struct task_struct *t;

	t = per_cpu(rcu_cpu_kthread_task, cpu);
	if (t == NULL)
		return;
	if (to_rt) {
		policy = SCHED_FIFO;
		sp.sched_priority = RCU_KTHREAD_PRIO;
	} else {
		policy = SCHED_NORMAL;
		sp.sched_priority = 0;
	}
	sched_setscheduler_nocheck(t, policy, &sp);
}

/*
 * Timer handler to initiate the waking up of per-CPU kthreads that
 * have yielded the CPU due to excess numbers of RCU callbacks.
 * We wake up the per-rcu_node kthread, which in turn will wake up
 * the booster kthread.
 */
static void rcu_cpu_kthread_timer(unsigned long arg)
{
	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
	struct rcu_node *rnp = rdp->mynode;

	atomic_or(rdp->grpmask, &rnp->wakemask);
	invoke_rcu_node_kthread(rnp);
}

/*
 * Drop to non-real-time priority and yield, but only after posting a
 * timer that will cause us to regain our real-time priority if we
 * remain preempted.  Either way, we restore our real-time priority
 * before returning.
 */
static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
{
	struct sched_param sp;
	struct timer_list yield_timer;
1553
	int prio = current->rt_priority;
1554 1555 1556 1557 1558 1559 1560

	setup_timer_on_stack(&yield_timer, f, arg);
	mod_timer(&yield_timer, jiffies + 2);
	sp.sched_priority = 0;
	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
	set_user_nice(current, 19);
	schedule();
1561 1562
	set_user_nice(current, 0);
	sp.sched_priority = prio;
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599
	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
	del_timer(&yield_timer);
}

/*
 * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
 * This can happen while the corresponding CPU is either coming online
 * or going offline.  We cannot wait until the CPU is fully online
 * before starting the kthread, because the various notifier functions
 * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
 * the corresponding CPU is online.
 *
 * Return 1 if the kthread needs to stop, 0 otherwise.
 *
 * Caller must disable bh.  This function can momentarily enable it.
 */
static int rcu_cpu_kthread_should_stop(int cpu)
{
	while (cpu_is_offline(cpu) ||
	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
	       smp_processor_id() != cpu) {
		if (kthread_should_stop())
			return 1;
		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
		local_bh_enable();
		schedule_timeout_uninterruptible(1);
		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
			set_cpus_allowed_ptr(current, cpumask_of(cpu));
		local_bh_disable();
	}
	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
	return 0;
}

/*
 * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
1600 1601
 * RCU softirq used in flavors and configurations of RCU that do not
 * support RCU priority boosting.
1602 1603 1604 1605 1606 1607 1608 1609 1610 1611
 */
static int rcu_cpu_kthread(void *arg)
{
	int cpu = (int)(long)arg;
	unsigned long flags;
	int spincnt = 0;
	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
	char work;
	char *workp = &per_cpu(rcu_cpu_has_work, cpu);

1612
	trace_rcu_utilization("Start CPU kthread@init");
1613 1614
	for (;;) {
		*statusp = RCU_KTHREAD_WAITING;
1615
		trace_rcu_utilization("End CPU kthread@rcu_wait");
1616
		rcu_wait(*workp != 0 || kthread_should_stop());
1617
		trace_rcu_utilization("Start CPU kthread@rcu_wait");
1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637
		local_bh_disable();
		if (rcu_cpu_kthread_should_stop(cpu)) {
			local_bh_enable();
			break;
		}
		*statusp = RCU_KTHREAD_RUNNING;
		per_cpu(rcu_cpu_kthread_loops, cpu)++;
		local_irq_save(flags);
		work = *workp;
		*workp = 0;
		local_irq_restore(flags);
		if (work)
			rcu_kthread_do_work();
		local_bh_enable();
		if (*workp != 0)
			spincnt++;
		else
			spincnt = 0;
		if (spincnt > 10) {
			*statusp = RCU_KTHREAD_YIELDING;
1638
			trace_rcu_utilization("End CPU kthread@rcu_yield");
1639
			rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
1640
			trace_rcu_utilization("Start CPU kthread@rcu_yield");
1641 1642 1643 1644
			spincnt = 0;
		}
	}
	*statusp = RCU_KTHREAD_STOPPED;
1645
	trace_rcu_utilization("End CPU kthread@term");
1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674
	return 0;
}

/*
 * Spawn a per-CPU kthread, setting up affinity and priority.
 * Because the CPU hotplug lock is held, no other CPU will be attempting
 * to manipulate rcu_cpu_kthread_task.  There might be another CPU
 * attempting to access it during boot, but the locking in kthread_bind()
 * will enforce sufficient ordering.
 *
 * Please note that we cannot simply refuse to wake up the per-CPU
 * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
 * which can result in softlockup complaints if the task ends up being
 * idle for more than a couple of minutes.
 *
 * However, please note also that we cannot bind the per-CPU kthread to its
 * CPU until that CPU is fully online.  We also cannot wait until the
 * CPU is fully online before we create its per-CPU kthread, as this would
 * deadlock the system when CPU notifiers tried waiting for grace
 * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
 * is online.  If its CPU is not yet fully online, then the code in
 * rcu_cpu_kthread() will wait until it is fully online, and then do
 * the binding.
 */
static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
{
	struct sched_param sp;
	struct task_struct *t;

1675
	if (!rcu_scheduler_fully_active ||
1676 1677
	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
		return 0;
E
Eric Dumazet 已提交
1678 1679 1680
	t = kthread_create_on_node(rcu_cpu_kthread,
				   (void *)(long)cpu,
				   cpu_to_node(cpu),
1681
				   "rcuc/%d", cpu);
1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
	if (IS_ERR(t))
		return PTR_ERR(t);
	if (cpu_online(cpu))
		kthread_bind(t, cpu);
	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
	sp.sched_priority = RCU_KTHREAD_PRIO;
	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
	per_cpu(rcu_cpu_kthread_task, cpu) = t;
	wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
	return 0;
}

/*
 * Per-rcu_node kthread, which is in charge of waking up the per-CPU
 * kthreads when needed.  We ignore requests to wake up kthreads
 * for offline CPUs, which is OK because force_quiescent_state()
 * takes care of this case.
 */
static int rcu_node_kthread(void *arg)
{
	int cpu;
	unsigned long flags;
	unsigned long mask;
	struct rcu_node *rnp = (struct rcu_node *)arg;
	struct sched_param sp;
	struct task_struct *t;

	for (;;) {
		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
		rcu_wait(atomic_read(&rnp->wakemask) != 0);
		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
		raw_spin_lock_irqsave(&rnp->lock, flags);
		mask = atomic_xchg(&rnp->wakemask, 0);
		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
			if ((mask & 0x1) == 0)
				continue;
			preempt_disable();
			t = per_cpu(rcu_cpu_kthread_task, cpu);
			if (!cpu_online(cpu) || t == NULL) {
				preempt_enable();
				continue;
			}
			per_cpu(rcu_cpu_has_work, cpu) = 1;
			sp.sched_priority = RCU_KTHREAD_PRIO;
			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
			preempt_enable();
		}
	}
	/* NOTREACHED */
	rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
	return 0;
}

/*
 * Set the per-rcu_node kthread's affinity to cover all CPUs that are
 * served by the rcu_node in question.  The CPU hotplug lock is still
 * held, so the value of rnp->qsmaskinit will be stable.
 *
 * We don't include outgoingcpu in the affinity set, use -1 if there is
 * no outgoing CPU.  If there are no CPUs left in the affinity set,
 * this function allows the kthread to execute on any CPU.
 */
static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
{
	cpumask_var_t cm;
	int cpu;
	unsigned long mask = rnp->qsmaskinit;

	if (rnp->node_kthread_task == NULL)
		return;
	if (!alloc_cpumask_var(&cm, GFP_KERNEL))
		return;
	cpumask_clear(cm);
	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
		if ((mask & 0x1) && cpu != outgoingcpu)
			cpumask_set_cpu(cpu, cm);
	if (cpumask_weight(cm) == 0) {
		cpumask_setall(cm);
		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
			cpumask_clear_cpu(cpu, cm);
		WARN_ON_ONCE(cpumask_weight(cm) == 0);
	}
	set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
	rcu_boost_kthread_setaffinity(rnp, cm);
	free_cpumask_var(cm);
}

/*
 * Spawn a per-rcu_node kthread, setting priority and affinity.
 * Called during boot before online/offline can happen, or, if
 * during runtime, with the main CPU-hotplug locks held.  So only
 * one of these can be executing at a time.
 */
static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
						struct rcu_node *rnp)
{
	unsigned long flags;
	int rnp_index = rnp - &rsp->node[0];
	struct sched_param sp;
	struct task_struct *t;

1785
	if (!rcu_scheduler_fully_active ||
1786 1787 1788 1789
	    rnp->qsmaskinit == 0)
		return 0;
	if (rnp->node_kthread_task == NULL) {
		t = kthread_create(rcu_node_kthread, (void *)rnp,
1790
				   "rcun/%d", rnp_index);
1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810
		if (IS_ERR(t))
			return PTR_ERR(t);
		raw_spin_lock_irqsave(&rnp->lock, flags);
		rnp->node_kthread_task = t;
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		sp.sched_priority = 99;
		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
		wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
	}
	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
}

/*
 * Spawn all kthreads -- called as soon as the scheduler is running.
 */
static int __init rcu_spawn_kthreads(void)
{
	int cpu;
	struct rcu_node *rnp;

1811
	rcu_scheduler_fully_active = 1;
1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832
	for_each_possible_cpu(cpu) {
		per_cpu(rcu_cpu_has_work, cpu) = 0;
		if (cpu_online(cpu))
			(void)rcu_spawn_one_cpu_kthread(cpu);
	}
	rnp = rcu_get_root(rcu_state);
	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
	if (NUM_RCU_NODES > 1) {
		rcu_for_each_leaf_node(rcu_state, rnp)
			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
	}
	return 0;
}
early_initcall(rcu_spawn_kthreads);

static void __cpuinit rcu_prepare_kthreads(int cpu)
{
	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
	struct rcu_node *rnp = rdp->mynode;

	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
1833
	if (rcu_scheduler_fully_active) {
1834 1835 1836 1837 1838 1839
		(void)rcu_spawn_one_cpu_kthread(cpu);
		if (rnp->node_kthread_task == NULL)
			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
	}
}

1840 1841
#else /* #ifdef CONFIG_RCU_BOOST */

1842
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
1843
{
1844
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
1845 1846
}

1847
static void invoke_rcu_callbacks_kthread(void)
1848
{
1849
	WARN_ON_ONCE(1);
1850 1851
}

1852 1853 1854 1855 1856
static bool rcu_is_callbacks_kthread(void)
{
	return false;
}

1857 1858 1859 1860
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
{
}

1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876
#ifdef CONFIG_HOTPLUG_CPU

static void rcu_stop_cpu_kthread(int cpu)
{
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
{
}

static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
{
}

1877 1878 1879 1880 1881 1882 1883
static int __init rcu_scheduler_really_started(void)
{
	rcu_scheduler_fully_active = 1;
	return 0;
}
early_initcall(rcu_scheduler_really_started);

1884 1885 1886 1887
static void __cpuinit rcu_prepare_kthreads(int cpu)
{
}

1888 1889
#endif /* #else #ifdef CONFIG_RCU_BOOST */

1890 1891 1892 1893 1894 1895 1896 1897
#if !defined(CONFIG_RCU_FAST_NO_HZ)

/*
 * Check to see if any future RCU-related work will need to be done
 * by the current CPU, even if none need be done immediately, returning
 * 1 if so.  This function is part of the RCU implementation; it is -not-
 * an exported member of the RCU API.
 *
1898 1899
 * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
 * any flavor of RCU.
1900
 */
1901
int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
1902
{
1903
	*delta_jiffies = ULONG_MAX;
1904 1905 1906
	return rcu_cpu_has_callbacks(cpu);
}

1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921
/*
 * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it.
 */
static void rcu_prepare_for_idle_init(int cpu)
{
}

/*
 * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
 * after it.
 */
static void rcu_cleanup_after_idle(int cpu)
{
}

1922
/*
1923
 * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n,
1924 1925 1926 1927 1928 1929
 * is nothing.
 */
static void rcu_prepare_for_idle(int cpu)
{
}

1930 1931 1932 1933 1934 1935 1936 1937
/*
 * Don't bother keeping a running count of the number of RCU callbacks
 * posted because CONFIG_RCU_FAST_NO_HZ=n.
 */
static void rcu_idle_count_callbacks_posted(void)
{
}

1938 1939
#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */

1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964
/*
 * This code is invoked when a CPU goes idle, at which point we want
 * to have the CPU do everything required for RCU so that it can enter
 * the energy-efficient dyntick-idle mode.  This is handled by a
 * state machine implemented by rcu_prepare_for_idle() below.
 *
 * The following three proprocessor symbols control this state machine:
 *
 * RCU_IDLE_FLUSHES gives the maximum number of times that we will attempt
 *	to satisfy RCU.  Beyond this point, it is better to incur a periodic
 *	scheduling-clock interrupt than to loop through the state machine
 *	at full power.
 * RCU_IDLE_OPT_FLUSHES gives the number of RCU_IDLE_FLUSHES that are
 *	optional if RCU does not need anything immediately from this
 *	CPU, even if this CPU still has RCU callbacks queued.  The first
 *	times through the state machine are mandatory: we need to give
 *	the state machine a chance to communicate a quiescent state
 *	to the RCU core.
 * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
 *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
 *	is sized to be roughly one RCU grace period.  Those energy-efficiency
 *	benchmarkers who might otherwise be tempted to set this to a large
 *	number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
 *	system.  And if you are -that- concerned about energy efficiency,
 *	just power the system down and be done with it!
1965 1966 1967
 * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is
 *	permitted to sleep in dyntick-idle mode with only lazy RCU
 *	callbacks pending.  Setting this too high can OOM your system.
1968 1969 1970 1971 1972 1973 1974
 *
 * The values below work well in practice.  If future workloads require
 * adjustment, they can be converted into kernel config parameters, though
 * making the state machine smarter might be a better option.
 */
#define RCU_IDLE_FLUSHES 5		/* Number of dyntick-idle tries. */
#define RCU_IDLE_OPT_FLUSHES 3		/* Optional dyntick-idle tries. */
1975
#define RCU_IDLE_GP_DELAY 6		/* Roughly one grace period. */
1976
#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
1977

1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019
/*
 * Does the specified flavor of RCU have non-lazy callbacks pending on
 * the specified CPU?  Both RCU flavor and CPU are specified by the
 * rcu_data structure.
 */
static bool __rcu_cpu_has_nonlazy_callbacks(struct rcu_data *rdp)
{
	return rdp->qlen != rdp->qlen_lazy;
}

#ifdef CONFIG_TREE_PREEMPT_RCU

/*
 * Are there non-lazy RCU-preempt callbacks?  (There cannot be if there
 * is no RCU-preempt in the kernel.)
 */
static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);

	return __rcu_cpu_has_nonlazy_callbacks(rdp);
}

#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */

static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu)
{
	return 0;
}

#endif /* else #ifdef CONFIG_TREE_PREEMPT_RCU */

/*
 * Does any flavor of RCU have non-lazy callbacks on the specified CPU?
 */
static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
{
	return __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_sched_data, cpu)) ||
	       __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_bh_data, cpu)) ||
	       rcu_preempt_cpu_has_nonlazy_callbacks(cpu);
}

2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060
/*
 * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
 * callbacks on this CPU, (2) this CPU has not yet attempted to enter
 * dyntick-idle mode, or (3) this CPU is in the process of attempting to
 * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
 * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
 * it is better to incur scheduling-clock interrupts than to spin
 * continuously for the same time duration!
 *
 * The delta_jiffies argument is used to store the time when RCU is
 * going to need the CPU again if it still has callbacks.  The reason
 * for this is that rcu_prepare_for_idle() might need to post a timer,
 * but if so, it will do so after tick_nohz_stop_sched_tick() has set
 * the wakeup time for this CPU.  This means that RCU's timer can be
 * delayed until the wakeup time, which defeats the purpose of posting
 * a timer.
 */
int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);

	/* Flag a new idle sojourn to the idle-entry state machine. */
	rdtp->idle_first_pass = 1;
	/* If no callbacks, RCU doesn't need the CPU. */
	if (!rcu_cpu_has_callbacks(cpu)) {
		*delta_jiffies = ULONG_MAX;
		return 0;
	}
	if (rdtp->dyntick_holdoff == jiffies) {
		/* RCU recently tried and failed, so don't try again. */
		*delta_jiffies = 1;
		return 1;
	}
	/* Set up for the possibility that RCU will post a timer. */
	if (rcu_cpu_has_nonlazy_callbacks(cpu))
		*delta_jiffies = RCU_IDLE_GP_DELAY;
	else
		*delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
	return 0;
}

2061 2062 2063 2064 2065 2066 2067 2068 2069
/*
 * Handler for smp_call_function_single().  The only point of this
 * handler is to wake the CPU up, so the handler does only tracing.
 */
void rcu_idle_demigrate(void *unused)
{
	trace_rcu_prep_idle("Demigrate");
}

2070 2071 2072 2073 2074 2075
/*
 * Timer handler used to force CPU to start pushing its remaining RCU
 * callbacks in the case where it entered dyntick-idle mode with callbacks
 * pending.  The hander doesn't really need to do anything because the
 * real work is done upon re-entry to idle, or by the next scheduling-clock
 * interrupt should idle not be re-entered.
2076 2077 2078 2079
 *
 * One special case: the timer gets migrated without awakening the CPU
 * on which the timer was scheduled on.  In this case, we must wake up
 * that CPU.  We do so with smp_call_function_single().
2080
 */
2081
static void rcu_idle_gp_timer_func(unsigned long cpu_in)
2082
{
2083 2084
	int cpu = (int)cpu_in;

2085
	trace_rcu_prep_idle("Timer");
2086 2087 2088 2089
	if (cpu != smp_processor_id())
		smp_call_function_single(cpu, rcu_idle_demigrate, NULL, 0);
	else
		WARN_ON_ONCE(1); /* Getting here can hang the system... */
2090 2091 2092 2093 2094 2095 2096
}

/*
 * Initialize the timer used to pull CPUs out of dyntick-idle mode.
 */
static void rcu_prepare_for_idle_init(int cpu)
{
2097 2098 2099 2100 2101 2102
	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);

	rdtp->dyntick_holdoff = jiffies - 1;
	setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
	rdtp->idle_gp_timer_expires = jiffies - 1;
	rdtp->idle_first_pass = 1;
2103 2104 2105 2106
}

/*
 * Clean up for exit from idle.  Because we are exiting from idle, there
2107
 * is no longer any point to ->idle_gp_timer, so cancel it.  This will
2108 2109 2110 2111
 * do nothing if this timer is not active, so just cancel it unconditionally.
 */
static void rcu_cleanup_after_idle(int cpu)
{
2112 2113 2114
	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);

	del_timer(&rdtp->idle_gp_timer);
2115
	trace_rcu_prep_idle("Cleanup after idle");
2116 2117
}

2118 2119 2120 2121
/*
 * Check to see if any RCU-related work can be done by the current CPU,
 * and if so, schedule a softirq to get it done.  This function is part
 * of the RCU implementation; it is -not- an exported member of the RCU API.
2122
 *
2123 2124 2125 2126 2127 2128
 * The idea is for the current CPU to clear out all work required by the
 * RCU core for the current grace period, so that this CPU can be permitted
 * to enter dyntick-idle mode.  In some cases, it will need to be awakened
 * at the end of the grace period by whatever CPU ends the grace period.
 * This allows CPUs to go dyntick-idle more quickly, and to reduce the
 * number of wakeups by a modest integer factor.
2129 2130 2131
 *
 * Because it is not legal to invoke rcu_process_callbacks() with irqs
 * disabled, we do one pass of force_quiescent_state(), then do a
2132
 * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
2133
 * later.  The ->dyntick_drain field controls the sequencing.
2134 2135
 *
 * The caller must have disabled interrupts.
2136
 */
2137
static void rcu_prepare_for_idle(int cpu)
2138
{
2139
	struct timer_list *tp;
2140
	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
2141

2142 2143 2144 2145 2146
	/*
	 * If this is an idle re-entry, for example, due to use of
	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
	 * loop, then don't take any state-machine actions, unless the
	 * momentary exit from idle queued additional non-lazy callbacks.
2147
	 * Instead, repost the ->idle_gp_timer if this CPU has callbacks
2148 2149
	 * pending.
	 */
2150 2151
	if (!rdtp->idle_first_pass &&
	    (rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
2152
		if (rcu_cpu_has_callbacks(cpu)) {
2153 2154
			tp = &rdtp->idle_gp_timer;
			mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
2155
		}
2156 2157
		return;
	}
2158 2159
	rdtp->idle_first_pass = 0;
	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
2160

2161
	/*
2162 2163
	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
	 * Also reset state to avoid prejudicing later attempts.
2164
	 */
2165
	if (!rcu_cpu_has_callbacks(cpu)) {
2166 2167
		rdtp->dyntick_holdoff = jiffies - 1;
		rdtp->dyntick_drain = 0;
2168
		trace_rcu_prep_idle("No callbacks");
2169
		return;
2170
	}
2171 2172 2173 2174 2175

	/*
	 * If in holdoff mode, just return.  We will presumably have
	 * refrained from disabling the scheduling-clock tick.
	 */
2176
	if (rdtp->dyntick_holdoff == jiffies) {
2177
		trace_rcu_prep_idle("In holdoff");
2178
		return;
2179
	}
2180

2181 2182
	/* Check and update the ->dyntick_drain sequencing. */
	if (rdtp->dyntick_drain <= 0) {
2183
		/* First time through, initialize the counter. */
2184 2185
		rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
	} else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
2186 2187
		   !rcu_pending(cpu) &&
		   !local_softirq_pending()) {
2188
		/* Can we go dyntick-idle despite still having callbacks? */
2189 2190
		rdtp->dyntick_drain = 0;
		rdtp->dyntick_holdoff = jiffies;
2191 2192
		if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
			trace_rcu_prep_idle("Dyntick with callbacks");
2193
			rdtp->idle_gp_timer_expires =
2194
					   jiffies + RCU_IDLE_GP_DELAY;
2195
		} else {
2196
			rdtp->idle_gp_timer_expires =
2197
					   jiffies + RCU_IDLE_LAZY_GP_DELAY;
2198 2199
			trace_rcu_prep_idle("Dyntick with lazy callbacks");
		}
2200 2201 2202
		tp = &rdtp->idle_gp_timer;
		mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
		rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
2203
		return; /* Nothing more to do immediately. */
2204
	} else if (--(rdtp->dyntick_drain) <= 0) {
2205
		/* We have hit the limit, so time to give up. */
2206
		rdtp->dyntick_holdoff = jiffies;
2207
		trace_rcu_prep_idle("Begin holdoff");
2208 2209
		invoke_rcu_core();  /* Force the CPU out of dyntick-idle. */
		return;
2210 2211
	}

2212 2213 2214 2215 2216 2217 2218 2219 2220 2221
	/*
	 * Do one step of pushing the remaining RCU callbacks through
	 * the RCU core state machine.
	 */
#ifdef CONFIG_TREE_PREEMPT_RCU
	if (per_cpu(rcu_preempt_data, cpu).nxtlist) {
		rcu_preempt_qs(cpu);
		force_quiescent_state(&rcu_preempt_state, 0);
	}
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
2222 2223 2224 2225 2226 2227 2228
	if (per_cpu(rcu_sched_data, cpu).nxtlist) {
		rcu_sched_qs(cpu);
		force_quiescent_state(&rcu_sched_state, 0);
	}
	if (per_cpu(rcu_bh_data, cpu).nxtlist) {
		rcu_bh_qs(cpu);
		force_quiescent_state(&rcu_bh_state, 0);
2229 2230
	}

2231 2232 2233 2234
	/*
	 * If RCU callbacks are still pending, RCU still needs this CPU.
	 * So try forcing the callbacks through the grace period.
	 */
2235
	if (rcu_cpu_has_callbacks(cpu)) {
2236
		trace_rcu_prep_idle("More callbacks");
2237
		invoke_rcu_core();
2238
	} else
2239
		trace_rcu_prep_idle("Callbacks drained");
2240 2241
}

2242
/*
2243 2244 2245 2246 2247 2248
 * Keep a running count of the number of non-lazy callbacks posted
 * on this CPU.  This running counter (which is never decremented) allows
 * rcu_prepare_for_idle() to detect when something out of the idle loop
 * posts a callback, even if an equal number of callbacks are invoked.
 * Of course, callbacks should only be posted from within a trace event
 * designed to be called from idle or from within RCU_NONIDLE().
2249 2250 2251
 */
static void rcu_idle_count_callbacks_posted(void)
{
2252
	__this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
2253 2254
}

2255
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
2256 2257 2258 2259 2260 2261 2262

#ifdef CONFIG_RCU_CPU_STALL_INFO

#ifdef CONFIG_RCU_FAST_NO_HZ

static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
2263 2264
	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
	struct timer_list *tltp = &rdtp->idle_gp_timer;
2265

2266
	sprintf(cp, "drain=%d %c timer=%lu",
2267 2268
		rdtp->dyntick_drain,
		rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
2269
		timer_pending(tltp) ? tltp->expires - jiffies : -1);
2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368
}

#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */

static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
}

#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */

/* Initiate the stall-info list. */
static void print_cpu_stall_info_begin(void)
{
	printk(KERN_CONT "\n");
}

/*
 * Print out diagnostic information for the specified stalled CPU.
 *
 * If the specified CPU is aware of the current RCU grace period
 * (flavor specified by rsp), then print the number of scheduling
 * clock interrupts the CPU has taken during the time that it has
 * been aware.  Otherwise, print the number of RCU grace periods
 * that this CPU is ignorant of, for example, "1" if the CPU was
 * aware of the previous grace period.
 *
 * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
 */
static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
{
	char fast_no_hz[72];
	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
	struct rcu_dynticks *rdtp = rdp->dynticks;
	char *ticks_title;
	unsigned long ticks_value;

	if (rsp->gpnum == rdp->gpnum) {
		ticks_title = "ticks this GP";
		ticks_value = rdp->ticks_this_gp;
	} else {
		ticks_title = "GPs behind";
		ticks_value = rsp->gpnum - rdp->gpnum;
	}
	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
	printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d %s\n",
	       cpu, ticks_value, ticks_title,
	       atomic_read(&rdtp->dynticks) & 0xfff,
	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
	       fast_no_hz);
}

/* Terminate the stall-info list. */
static void print_cpu_stall_info_end(void)
{
	printk(KERN_ERR "\t");
}

/* Zero ->ticks_this_gp for all flavors of RCU. */
static void zero_cpu_stall_ticks(struct rcu_data *rdp)
{
	rdp->ticks_this_gp = 0;
}

/* Increment ->ticks_this_gp for all flavors of RCU. */
static void increment_cpu_stall_ticks(void)
{
	__get_cpu_var(rcu_sched_data).ticks_this_gp++;
	__get_cpu_var(rcu_bh_data).ticks_this_gp++;
#ifdef CONFIG_TREE_PREEMPT_RCU
	__get_cpu_var(rcu_preempt_data).ticks_this_gp++;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
}

#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */

static void print_cpu_stall_info_begin(void)
{
	printk(KERN_CONT " {");
}

static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
{
	printk(KERN_CONT " %d", cpu);
}

static void print_cpu_stall_info_end(void)
{
	printk(KERN_CONT "} ");
}

static void zero_cpu_stall_ticks(struct rcu_data *rdp)
{
}

static void increment_cpu_stall_ticks(void)
{
}

#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */