summaryrefslogtreecommitdiff
path: root/kernel/rcutree_plugin.h
blob: b8e4b0384f0068582b2e9fd68e440c717b0b64b3 (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
/*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions that provide either classic
 * or preemptable semantics.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright Red Hat, 2009
 * Copyright IBM Corporation, 2009
 *
 * Author: Ingo Molnar <mingo@elte.hu>
 *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 */


#ifdef CONFIG_TREE_PREEMPT_RCU

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

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

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

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

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

/*
 * We have entered the scheduler or are between softirqs in ksoftirqd.
 * If we are in an RCU read-side critical section, we need to reflect
 * that in the state of the rcu_node structure corresponding to this CPU.
 * Caller must disable hardirqs.
 */
static void rcu_preempt_qs(int cpu)
{
	struct task_struct *t = current;
	int phase;
	struct rcu_data *rdp;
	struct rcu_node *rnp;

	if (t->rcu_read_lock_nesting &&
	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
		WARN_ON_ONCE(cpu != smp_processor_id());

		/* Possibly blocking in an RCU read-side critical section. */
		rdp = rcu_preempt_state.rda[cpu];
		rnp = rdp->mynode;
		spin_lock(&rnp->lock);
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
		t->rcu_blocked_node = rnp;

		/*
		 * If this CPU has already checked in, then this task
		 * will hold up the next grace period rather than the
		 * current grace period.  Queue the task accordingly.
		 * If the task is queued for the current grace period
		 * (i.e., this CPU has not yet passed through a quiescent
		 * state for the current grace period), then as long
		 * as that task remains queued, the current grace period
		 * cannot end.
		 *
		 * But first, note that the current CPU must still be
		 * on line!
		 */
		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
		phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1);
		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
		smp_mb();  /* Ensure later ctxt swtch seen after above. */
		spin_unlock(&rnp->lock);
	}

	/*
	 * 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.
	 */
	rcu_preempt_qs_record(cpu);
	t->rcu_read_unlock_special &= ~(RCU_READ_UNLOCK_NEED_QS |
					RCU_READ_UNLOCK_GOT_QS);
}

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

static void rcu_read_unlock_special(struct task_struct *t)
{
	int empty;
	unsigned long flags;
	unsigned long mask;
	struct rcu_node *rnp;
	int special;

	/* NMI handlers cannot block and cannot safely manipulate state. */
	if (in_nmi())
		return;

	local_irq_save(flags);

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

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

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

		/*
		 * Remove this task from the 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 (;;) {
			rnp = t->rcu_blocked_node;
			spin_lock(&rnp->lock);
			if (rnp == t->rcu_blocked_node)
				break;
			spin_unlock(&rnp->lock);
		}
		empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
		list_del_init(&t->rcu_node_entry);
		t->rcu_blocked_node = NULL;

		/*
		 * If this was the last task on the current list, and if
		 * we aren't waiting on any CPUs, report the quiescent state.
		 * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk()
		 * drop rnp->lock and restore irq.
		 */
		if (!empty && rnp->qsmask == 0 &&
		    list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) {
			t->rcu_read_unlock_special &=
				~(RCU_READ_UNLOCK_NEED_QS |
				  RCU_READ_UNLOCK_GOT_QS);
			if (rnp->parent == NULL) {
				/* Only one rcu_node in the tree. */
				cpu_quiet_msk_finish(&rcu_preempt_state, flags);
				return;
			}
			/* Report up the rest of the hierarchy. */
			mask = rnp->grpmask;
			spin_unlock_irqrestore(&rnp->lock, flags);
			rnp = rnp->parent;
			spin_lock_irqsave(&rnp->lock, flags);
			cpu_quiet_msk(mask, &rcu_preempt_state, rnp, flags);
			return;
		}
		spin_unlock(&rnp->lock);
	}
	local_irq_restore(flags);
}

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

	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
		rcu_read_unlock_special(t);
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);

#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

/*
 * Scan the current list of tasks blocked within RCU read-side critical
 * sections, printing out the tid of each.
 */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
	unsigned long flags;
	struct list_head *lp;
	int phase = rnp->gpnum & 0x1;
	struct task_struct *t;

	if (!list_empty(&rnp->blocked_tasks[phase])) {
		spin_lock_irqsave(&rnp->lock, flags);
		phase = rnp->gpnum & 0x1; /* re-read under lock. */
		lp = &rnp->blocked_tasks[phase];
		list_for_each_entry(t, lp, rcu_node_entry)
			printk(" P%d", t->pid);
		spin_unlock_irqrestore(&rnp->lock, flags);
	}
}

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

/*
 * Check that the list of blocked tasks for the newly completed grace
 * period is in fact empty.  It is a serious bug to complete a grace
 * period that still has RCU readers blocked!  This function must be
 * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
 * must be held by the caller.
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
	WARN_ON_ONCE(!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]));
}

/*
 * Check for preempted RCU readers for the specified rcu_node structure.
 * If the caller needs a reliable answer, it must hold the rcu_node's
 * >lock.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
	return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
}

#ifdef CONFIG_HOTPLUG_CPU

/*
 * 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.
 *
 * The caller must hold rnp->lock with irqs disabled.
 */
static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
				      struct rcu_node *rnp)
{
	int i;
	struct list_head *lp;
	struct list_head *lp_root;
	struct rcu_node *rnp_root = rcu_get_root(rsp);
	struct task_struct *tp;

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

	/*
	 * Move tasks up to root rcu_node.  Rely on the fact that the
	 * root rcu_node can be at most one ahead of the rest of the
	 * rcu_nodes in terms of gp_num value.  This fact allows us to
	 * move the blocked_tasks[] array directly, element by element.
	 */
	for (i = 0; i < 2; i++) {
		lp = &rnp->blocked_tasks[i];
		lp_root = &rnp_root->blocked_tasks[i];
		while (!list_empty(lp)) {
			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
			spin_lock(&rnp_root->lock); /* irqs already disabled */
			list_del(&tp->rcu_node_entry);
			tp->rcu_blocked_node = rnp_root;
			list_add(&tp->rcu_node_entry, lp_root);
			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
		}
	}
}

/*
 * Do CPU-offline processing for preemptable RCU.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
	__rcu_offline_cpu(cpu, &rcu_preempt_state);
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

/*
 * 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) {
		t->rcu_read_unlock_special &=
			~(RCU_READ_UNLOCK_NEED_QS | RCU_READ_UNLOCK_GOT_QS);
		rcu_preempt_qs_record(cpu);
		return;
	}
	if (per_cpu(rcu_preempt_data, cpu).qs_pending) {
		if (t->rcu_read_unlock_special & RCU_READ_UNLOCK_GOT_QS) {
			rcu_preempt_qs_record(cpu);
			t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_GOT_QS;
		} else if (!(t->rcu_read_unlock_special &
			     RCU_READ_UNLOCK_NEED_QS)) {
			t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
		}
	}
}

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

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

/*
 * Check to see if there is any immediate preemptable-RCU-related work
 * to be done.
 */
static int rcu_preempt_pending(int cpu)
{
	return __rcu_pending(&rcu_preempt_state,
			     &per_cpu(rcu_preempt_data, cpu));
}

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

/*
 * Initialize preemptable RCU's per-CPU data.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
}

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

	if (t->rcu_read_lock_nesting == 0)
		return;
	t->rcu_read_lock_nesting = 1;
	rcu_read_unlock();
}

#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */

/*
 * Tell them what RCU they are running.
 */
static inline void rcu_bootup_announce(void)
{
	printk(KERN_INFO "Hierarchical RCU implementation.\n");
}

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

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

#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

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

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

/*
 * Because there is no preemptable RCU, there can be no readers blocked,
 * so there is no need to check for blocked tasks.
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
}

/*
 * Because preemptable RCU does not exist, there are never any preempted
 * RCU readers.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Because preemptable RCU does not exist, it never needs to migrate
 * tasks that were blocked within RCU read-side critical sections.
 */
static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
				      struct rcu_node *rnp)
{
}

/*
 * Because preemptable RCU does not exist, it never needs CPU-offline
 * processing.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

/*
 * Because preemptable RCU does not exist, it never has any callbacks
 * to check.
 */
void rcu_preempt_check_callbacks(int cpu)
{
}

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

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

/*
 * Because preemptable RCU does not exist, it never has any work to do.
 */
static int rcu_preempt_pending(int cpu)
{
	return 0;
}

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

/*
 * Because preemptable RCU does not exist, there is no per-CPU
 * data to initialize.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
}

#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */