summaryrefslogtreecommitdiffstats
path: root/kernel/rcutiny.c
blob: 4d60fbc9c64cb1421a9d48c0431f555ddcb808eb (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
/*
 * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
 *
 * 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, 2008
 *
 * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *		Documentation/RCU
 */
#include <linux/moduleparam.h>
#include <linux/completion.h>
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/rcupdate.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/cpu.h>

/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */
static struct task_struct *rcu_kthread_task;
static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
static unsigned long have_rcu_kthread_work;
static void invoke_rcu_kthread(void);

/* Forward declarations for rcutiny_plugin.h. */
struct rcu_ctrlblk;
static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
static int rcu_kthread(void *arg);
static void __call_rcu(struct rcu_head *head,
		       void (*func)(struct rcu_head *rcu),
		       struct rcu_ctrlblk *rcp);

#include "rcutiny_plugin.h"

#ifdef CONFIG_NO_HZ

static long rcu_dynticks_nesting = 1;

/*
 * Enter dynticks-idle mode, which is an extended quiescent state
 * if we have fully entered that mode (i.e., if the new value of
 * dynticks_nesting is zero).
 */
void rcu_enter_nohz(void)
{
	if (--rcu_dynticks_nesting == 0)
		rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
}

/*
 * Exit dynticks-idle mode, so that we are no longer in an extended
 * quiescent state.
 */
void rcu_exit_nohz(void)
{
	rcu_dynticks_nesting++;
}

#endif /* #ifdef CONFIG_NO_HZ */

/*
 * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
 * Also disable irqs to avoid confusion due to interrupt handlers
 * invoking call_rcu().
 */
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
	unsigned long flags;

	local_irq_save(flags);
	if (rcp->rcucblist != NULL &&
	    rcp->donetail != rcp->curtail) {
		rcp->donetail = rcp->curtail;
		local_irq_restore(flags);
		return 1;
	}
	local_irq_restore(flags);

	return 0;
}

/*
 * Record an rcu quiescent state.  And an rcu_bh quiescent state while we
 * are at it, given that any rcu quiescent state is also an rcu_bh
 * quiescent state.  Use "+" instead of "||" to defeat short circuiting.
 */
void rcu_sched_qs(int cpu)
{
	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
	    rcu_qsctr_help(&rcu_bh_ctrlblk))
		invoke_rcu_kthread();
}

/*
 * Record an rcu_bh quiescent state.
 */
void rcu_bh_qs(int cpu)
{
	if (rcu_qsctr_help(&rcu_bh_ctrlblk))
		invoke_rcu_kthread();
}

/*
 * Check to see if the scheduling-clock interrupt came from an extended
 * quiescent state, and, if so, tell RCU about it.
 */
void rcu_check_callbacks(int cpu, int user)
{
	if (user ||
	    (idle_cpu(cpu) &&
	     !in_softirq() &&
	     hardirq_count() <= (1 << HARDIRQ_SHIFT)))
		rcu_sched_qs(cpu);
	else if (!in_softirq())
		rcu_bh_qs(cpu);
	rcu_preempt_check_callbacks();
}

/*
 * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
 * whose grace period has elapsed.
 */
static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
	struct rcu_head *next, *list;
	unsigned long flags;
	RCU_TRACE(int cb_count = 0);

	/* If no RCU callbacks ready to invoke, just return. */
	if (&rcp->rcucblist == rcp->donetail)
		return;

	/* Move the ready-to-invoke callbacks to a local list. */
	local_irq_save(flags);
	list = rcp->rcucblist;
	rcp->rcucblist = *rcp->donetail;
	*rcp->donetail = NULL;
	if (rcp->curtail == rcp->donetail)
		rcp->curtail = &rcp->rcucblist;
	rcu_preempt_remove_callbacks(rcp);
	rcp->donetail = &rcp->rcucblist;
	local_irq_restore(flags);

	/* Invoke the callbacks on the local list. */
	while (list) {
		next = list->next;
		prefetch(next);
		debug_rcu_head_unqueue(list);
		local_bh_disable();
		__rcu_reclaim(list);
		local_bh_enable();
		list = next;
		RCU_TRACE(cb_count++);
	}
	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
}

/*
 * This kthread invokes RCU callbacks whose grace periods have
 * elapsed.  It is awakened as needed, and takes the place of the
 * RCU_SOFTIRQ that was used previously for this purpose.
 * This is a kthread, but it is never stopped, at least not until
 * the system goes down.
 */
static int rcu_kthread(void *arg)
{
	unsigned long work;
	unsigned long morework;
	unsigned long flags;

	for (;;) {
		wait_event_interruptible(rcu_kthread_wq,
					 have_rcu_kthread_work != 0);
		morework = rcu_boost();
		local_irq_save(flags);
		work = have_rcu_kthread_work;
		have_rcu_kthread_work = morework;
		local_irq_restore(flags);
		if (work) {
			rcu_process_callbacks(&rcu_sched_ctrlblk);
			rcu_process_callbacks(&rcu_bh_ctrlblk);
			rcu_preempt_process_callbacks();
		}
		schedule_timeout_interruptible(1); /* Leave CPU for others. */
	}

	return 0;  /* Not reached, but needed to shut gcc up. */
}

/*
 * Wake up rcu_kthread() to process callbacks now eligible for invocation
 * or to boost readers.
 */
static void invoke_rcu_kthread(void)
{
	unsigned long flags;

	local_irq_save(flags);
	have_rcu_kthread_work = 1;
	wake_up(&rcu_kthread_wq);
	local_irq_restore(flags);
}

/*
 * Wait for a grace period to elapse.  But it is illegal to invoke
 * synchronize_sched() from within an RCU read-side critical section.
 * Therefore, any legal call to synchronize_sched() is a quiescent
 * state, and so on a UP system, synchronize_sched() need do nothing.
 * Ditto for synchronize_rcu_bh().  (But Lai Jiangshan points out the
 * benefits of doing might_sleep() to reduce latency.)
 *
 * Cool, huh?  (Due to Josh Triplett.)
 *
 * But we want to make this a static inline later.  The cond_resched()
 * currently makes this problematic.
 */
void synchronize_sched(void)
{
	cond_resched();
}
EXPORT_SYMBOL_GPL(synchronize_sched);

/*
 * Helper function for call_rcu() and call_rcu_bh().
 */
static void __call_rcu(struct rcu_head *head,
		       void (*func)(struct rcu_head *rcu),
		       struct rcu_ctrlblk *rcp)
{
	unsigned long flags;

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

	local_irq_save(flags);
	*rcp->curtail = head;
	rcp->curtail = &head->next;
	RCU_TRACE(rcp->qlen++);
	local_irq_restore(flags);
}

/*
 * Post an RCU callback to be invoked after the end of an RCU-sched grace
 * period.  But since we have but one CPU, that would be after any
 * quiescent state.
 */
void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_sched_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);

/*
 * Post an RCU bottom-half callback to be invoked after any subsequent
 * quiescent state.
 */
void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_bh_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);

void rcu_barrier_bh(void)
{
	struct rcu_synchronize rcu;

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

void rcu_barrier_sched(void)
{
	struct rcu_synchronize rcu;

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

/*
 * Spawn the kthread that invokes RCU callbacks.
 */
static int __init rcu_spawn_kthreads(void)
{
	struct sched_param sp;

	rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread");
	sp.sched_priority = RCU_BOOST_PRIO;
	sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp);
	return 0;
}
early_initcall(rcu_spawn_kthreads);