aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/rcuclassic.c
blob: 6f8696c502f429ebcbaf65e537fdf47e3127d300 (plain)
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
27
28
29
30
31
32
33
34
35
36
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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
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
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
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
/*
 * Read-Copy Update mechanism for mutual exclusion
 *
 * 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 IBM Corporation, 2001
 *
 * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 *	    Manfred Spraul <manfred@colorfullife.com>
 *
 * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 * Papers:
 * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
 * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 * 		Documentation/RCU
 *
 */
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
struct lockdep_map rcu_lock_map =
	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
EXPORT_SYMBOL_GPL(rcu_lock_map);
#endif


/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_ctrlblk = {
	.cur = -300,
	.completed = -300,
	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
	.cpumask = CPU_MASK_NONE,
};
static struct rcu_ctrlblk rcu_bh_ctrlblk = {
	.cur = -300,
	.completed = -300,
	.lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
	.cpumask = CPU_MASK_NONE,
};

DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };

static int blimit = 10;
static int qhimark = 10000;
static int qlowmark = 100;

#ifdef CONFIG_SMP
static void force_quiescent_state(struct rcu_data *rdp,
			struct rcu_ctrlblk *rcp)
{
	int cpu;
	cpumask_t cpumask;
	set_need_resched();
	if (unlikely(!rcp->signaled)) {
		rcp->signaled = 1;
		/*
		 * Don't send IPI to itself. With irqs disabled,
		 * rdp->cpu is the current cpu.
		 *
		 * cpu_online_map is updated by the _cpu_down()
		 * using stop_machine_run(). Since we're in irqs disabled
		 * section, stop_machine_run() is not exectuting, hence
		 * the cpu_online_map is stable.
		 *
		 * However,  a cpu might have been offlined _just_ before
		 * we disabled irqs while entering here.
		 * And rcu subsystem might not yet have handled the CPU_DEAD
		 * notification, leading to the offlined cpu's bit
		 * being set in the rcp->cpumask.
		 *
		 * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent
		 * sending smp_reschedule() to an offlined CPU.
		 */
		cpus_and(cpumask, rcp->cpumask, cpu_online_map);
		cpu_clear(rdp->cpu, cpumask);
		for_each_cpu_mask_nr(cpu, cpumask)
			smp_send_reschedule(cpu);
	}
}
#else
static inline void force_quiescent_state(struct rcu_data *rdp,
			struct rcu_ctrlblk *rcp)
{
	set_need_resched();
}
#endif

/**
 * call_rcu - Queue an RCU callback for invocation after a grace period.
 * @head: structure to be used for queueing the RCU updates.
 * @func: actual update function to be invoked after the grace period
 *
 * The update function will be invoked some time after a full grace
 * period elapses, 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 call_rcu(struct rcu_head *head,
				void (*func)(struct rcu_head *rcu))
{
	unsigned long flags;
	struct rcu_data *rdp;

	head->func = func;
	head->next = NULL;
	local_irq_save(flags);
	rdp = &__get_cpu_var(rcu_data);
	*rdp->nxttail = head;
	rdp->nxttail = &head->next;
	if (unlikely(++rdp->qlen > qhimark)) {
		rdp->blimit = INT_MAX;
		force_quiescent_state(rdp, &rcu_ctrlblk);
	}
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(call_rcu);

/**
 * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
 * @head: structure to be used for queueing the RCU updates.
 * @func: actual update function to be invoked after the grace period
 *
 * The update function will be invoked some time after a full grace
 * period elapses, in other words after all currently executing RCU
 * read-side critical sections have completed. call_rcu_bh() assumes
 * that the read-side critical sections end on completion of a softirq
 * handler. This means that read-side critical sections in process
 * context must not be interrupted by softirqs. This interface is to be
 * used when most of the read-side critical sections are in softirq context.
 * RCU read-side critical sections are delimited by rcu_read_lock() and
 * rcu_read_unlock(), * if in interrupt context or rcu_read_lock_bh()
 * and rcu_read_unlock_bh(), if in process context. These may be nested.
 */
void call_rcu_bh(struct rcu_head *head,
				void (*func)(struct rcu_head *rcu))
{
	unsigned long flags;
	struct rcu_data *rdp;

	head->func = func;
	head->next = NULL;
	local_irq_save(flags);
	rdp = &__get_cpu_var(rcu_bh_data);
	*rdp->nxttail = head;
	rdp->nxttail = &head->next;

	if (unlikely(++rdp->qlen > qhimark)) {
		rdp->blimit = INT_MAX;
		force_quiescent_state(rdp, &rcu_bh_ctrlblk);
	}

	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);

/*
 * Return the number of RCU batches processed thus far.  Useful
 * for debug and statistics.
 */
long rcu_batches_completed(void)
{
	return rcu_ctrlblk.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);

/*
 * Return the number of RCU batches processed thus far.  Useful
 * for debug and statistics.
 */
long rcu_batches_completed_bh(void)
{
	return rcu_bh_ctrlblk.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);

/* Raises the softirq for processing rcu_callbacks. */
static inline void raise_rcu_softirq(void)
{
	raise_softirq(RCU_SOFTIRQ);
	/*
	 * The smp_mb() here is required to ensure that this cpu's
	 * __rcu_process_callbacks() reads the most recently updated
	 * value of rcu->cur.
	 */
	smp_mb();
}

/*
 * Invoke the completed RCU callbacks. They are expected to be in
 * a per-cpu list.
 */
static void rcu_do_batch(struct rcu_data *rdp)
{
	struct rcu_head *next, *list;
	int count = 0;

	list = rdp->donelist;
	while (list) {
		next = list->next;
		prefetch(next);
		list->func(list);
		list = next;
		if (++count >= rdp->blimit)
			break;
	}
	rdp->donelist = list;

	local_irq_disable();
	rdp->qlen -= count;
	local_irq_enable();
	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
		rdp->blimit = blimit;

	if (!rdp->donelist)
		rdp->donetail = &rdp->donelist;
	else
		raise_rcu_softirq();
}

/*
 * Grace period handling:
 * The grace period handling consists out of two steps:
 * - A new grace period is started.
 *   This is done by rcu_start_batch. The start is not broadcasted to
 *   all cpus, they must pick this up by comparing rcp->cur with
 *   rdp->quiescbatch. All cpus are recorded  in the
 *   rcu_ctrlblk.cpumask bitmap.
 * - All cpus must go through a quiescent state.
 *   Since the start of the grace period is not broadcasted, at least two
 *   calls to rcu_check_quiescent_state are required:
 *   The first call just notices that a new grace period is running. The
 *   following calls check if there was a quiescent state since the beginning
 *   of the grace period. If so, it updates rcu_ctrlblk.cpumask. If
 *   the bitmap is empty, then the grace period is completed.
 *   rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace
 *   period (if necessary).
 */
/*
 * Register a new batch of callbacks, and start it up if there is currently no
 * active batch and the batch to be registered has not already occurred.
 * Caller must hold rcu_ctrlblk.lock.
 */
static void rcu_start_batch(struct rcu_ctrlblk *rcp)
{
	if (rcp->next_pending &&
			rcp->completed == rcp->cur) {
		rcp->next_pending = 0;
		/*
		 * next_pending == 0 must be visible in
		 * __rcu_process_callbacks() before it can see new value of cur.
		 */
		smp_wmb();
		rcp->cur++;

		/*
		 * Accessing nohz_cpu_mask before incrementing rcp->cur needs a
		 * Barrier  Otherwise it can cause tickless idle CPUs to be
		 * included in rcp->cpumask, which will extend graceperiods
		 * unnecessarily.
		 */
		smp_mb();
		cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask);

		rcp->signaled = 0;
	}
}

/*
 * cpu went through a quiescent state since the beginning of the grace period.
 * Clear it from the cpu mask and complete the grace period if it was the last
 * cpu. Start another grace period if someone has further entries pending
 */
static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
{
	cpu_clear(cpu, rcp->cpumask);
	if (cpus_empty(rcp->cpumask)) {
		/* batch completed ! */
		rcp->completed = rcp->cur;
		rcu_start_batch(rcp);
	}
}

/*
 * Check if the cpu has gone through a quiescent state (say context
 * switch). If so and if it already hasn't done so in this RCU
 * quiescent cycle, then indicate that it has done so.
 */
static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
					struct rcu_data *rdp)
{
	if (rdp->quiescbatch != rcp->cur) {
		/* start new grace period: */
		rdp->qs_pending = 1;
		rdp->passed_quiesc = 0;
		rdp->quiescbatch = rcp->cur;
		return;
	}

	/* Grace period already completed for this cpu?
	 * qs_pending is checked instead of the actual bitmap to avoid
	 * cacheline trashing.
	 */
	if (!rdp->qs_pending)
		return;

	/*
	 * Was there a quiescent state since the beginning of the grace
	 * period? If no, then exit and wait for the next call.
	 */
	if (!rdp->passed_quiesc)
		return;
	rdp->qs_pending = 0;

	spin_lock(&rcp->lock);
	/*
	 * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
	 * during cpu startup. Ignore the quiescent state.
	 */
	if (likely(rdp->quiescbatch == rcp->cur))
		cpu_quiet(rdp->cpu, rcp);

	spin_unlock(&rcp->lock);
}


#ifdef CONFIG_HOTPLUG_CPU

/* warning! helper for rcu_offline_cpu. do not use elsewhere without reviewing
 * locking requirements, the list it's pulling from has to belong to a cpu
 * which is dead and hence not processing interrupts.
 */
static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
				struct rcu_head **tail)
{
	local_irq_disable();
	*this_rdp->nxttail = list;
	if (list)
		this_rdp->nxttail = tail;
	local_irq_enable();
}

static void __rcu_offline_cpu(struct rcu_data *this_rdp,
				struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
{
	/* if the cpu going offline owns the grace period
	 * we can block indefinitely waiting for it, so flush
	 * it here
	 */
	spin_lock_bh(&rcp->lock);
	if (rcp->cur != rcp->completed)
		cpu_quiet(rdp->cpu, rcp);
	spin_unlock_bh(&rcp->lock);
	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
	rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);

	local_irq_disable();
	this_rdp->qlen += rdp->qlen;
	local_irq_enable();
}

static void rcu_offline_cpu(int cpu)
{
	struct rcu_data *this_rdp = &get_cpu_var(rcu_data);
	struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data);

	__rcu_offline_cpu(this_rdp, &rcu_ctrlblk,
					&per_cpu(rcu_data, cpu));
	__rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk,
					&per_cpu(rcu_bh_data, cpu));
	put_cpu_var(rcu_data);
	put_cpu_var(rcu_bh_data);
}

#else

static void rcu_offline_cpu(int cpu)
{
}

#endif

/*
 * This does the RCU processing work from softirq context.
 */
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
					struct rcu_data *rdp)
{
	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) {
		*rdp->donetail = rdp->curlist;
		rdp->donetail = rdp->curtail;
		rdp->curlist = NULL;
		rdp->curtail = &rdp->curlist;
	}

	if (rdp->nxtlist && !rdp->curlist) {
		local_irq_disable();
		rdp->curlist = rdp->nxtlist;
		rdp->curtail = rdp->nxttail;
		rdp->nxtlist = NULL;
		rdp->nxttail = &rdp->nxtlist;
		local_irq_enable();

		/*
		 * start the next batch of callbacks
		 */

		/* determine batch number */
		rdp->batch = rcp->cur + 1;
		/* see the comment and corresponding wmb() in
		 * the rcu_start_batch()
		 */
		smp_rmb();

		if (!rcp->next_pending) {
			/* and start it/schedule start if it's a new batch */
			spin_lock(&rcp->lock);
			rcp->next_pending = 1;
			rcu_start_batch(rcp);
			spin_unlock(&rcp->lock);
		}
	}

	rcu_check_quiescent_state(rcp, rdp);
	if (rdp->donelist)
		rcu_do_batch(rdp);
}

static void rcu_process_callbacks(struct softirq_action *unused)
{
	__rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
	__rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
}

static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
{
	/* This cpu has pending rcu entries and the grace period
	 * for them has completed.
	 */
	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
		return 1;

	/* This cpu has no pending entries, but there are new entries */
	if (!rdp->curlist && rdp->nxtlist)
		return 1;

	/* This cpu has finished callbacks to invoke */
	if (rdp->donelist)
		return 1;

	/* The rcu core waits for a quiescent state from the cpu */
	if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
		return 1;

	/* nothing to do */
	return 0;
}

/*
 * Check to see if there is any immediate RCU-related work to be done
 * by the current CPU, returning 1 if so.  This function is part of the
 * RCU implementation; it is -not- an exported member of the RCU API.
 */
int rcu_pending(int cpu)
{
	return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
		__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
}

/*
 * 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.
 */
int rcu_needs_cpu(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
	struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);

	return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
}

void rcu_check_callbacks(int cpu, int user)
{
	if (user ||
	    (idle_cpu(cpu) && !in_softirq() &&
				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {

		/*
		 * Get here if this CPU took its interrupt from user
		 * mode or from the idle loop, and if this is not a
		 * nested interrupt.  In this case, the CPU is in
		 * a quiescent state, so count it.
		 *
		 * Also do a memory barrier.  This is needed to handle
		 * the case where writes from a preempt-disable section
		 * of code get reordered into schedule() by this CPU's
		 * write buffer.  The memory barrier makes sure that
		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
		 * by other CPUs to happen after any such write.
		 */

		smp_mb();  /* See above block comment. */
		rcu_qsctr_inc(cpu);
		rcu_bh_qsctr_inc(cpu);

	} else if (!in_softirq()) {

		/*
		 * Get here if this CPU did not take its interrupt from
		 * softirq, in other words, if it is not interrupting
		 * a rcu_bh read-side critical section.  This is an _bh
		 * critical section, so count it.  The memory barrier
		 * is needed for the same reason as is the above one.
		 */

		smp_mb();  /* See above block comment. */
		rcu_bh_qsctr_inc(cpu);
	}
	raise_rcu_softirq();
}

static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
						struct rcu_data *rdp)
{
	memset(rdp, 0, sizeof(*rdp));
	rdp->curtail = &rdp->curlist;
	rdp->nxttail = &rdp->nxtlist;
	rdp->donetail = &rdp->donelist;
	rdp->quiescbatch = rcp->completed;
	rdp->qs_pending = 0;
	rdp->cpu = cpu;
	rdp->blimit = blimit;
}

static void __cpuinit rcu_online_cpu(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
	struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu);

	rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
	rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
}

static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		rcu_online_cpu(cpu);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		rcu_offline_cpu(cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata rcu_nb = {
	.notifier_call	= rcu_cpu_notify,
};

/*
 * Initializes rcu mechanism.  Assumed to be called early.
 * That is before local timer(SMP) or jiffie timer (uniproc) is setup.
 * Note that rcu_qsctr and friends are implicitly
 * initialized due to the choice of ``0'' for RCU_CTR_INVALID.
 */
void __init __rcu_init(void)
{
	rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
			(void *)(long)smp_processor_id());
	/* Register notifier for non-boot CPUs */
	register_cpu_notifier(&rcu_nb);
}

module_param(blimit, int, 0);
module_param(qhimark, int, 0);
module_param(qlowmark, int, 0);