aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/rcupdate.c
blob: a967c9feb90a045f4f7f3631dbc93ad5aebf67f9 (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
/*
 * 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 -
 * 		http://lse.sourceforge.net/locking/rcupdate.html
 *
 */
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
#include <linux/kernel_stat.h>

enum rcu_barrier {
	RCU_BARRIER_STD,
	RCU_BARRIER_BH,
	RCU_BARRIER_SCHED,
};

static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
static atomic_t rcu_barrier_cpu_count;
static DEFINE_MUTEX(rcu_barrier_mutex);
static struct completion rcu_barrier_completion;
int rcu_scheduler_active __read_mostly;

static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
static struct rcu_head rcu_migrate_head[3];
static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);

/*
 * Awaken the corresponding synchronize_rcu() instance now that a
 * grace period has elapsed.
 */
void wakeme_after_rcu(struct rcu_head  *head)
{
	struct rcu_synchronize *rcu;

	rcu = container_of(head, struct rcu_synchronize, head);
	complete(&rcu->completion);
}

/**
 * synchronize_rcu - wait until a grace period has elapsed.
 *
 * Control will return to the caller some time after a full grace
 * period has elapsed, in other words after all currently executing RCU
 * read-side critical sections have completed.  RCU read-side critical
 * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
 * and may be nested.
 */
void synchronize_rcu(void)
{
	struct rcu_synchronize rcu;

	if (rcu_blocking_is_gp())
		return;

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

static void rcu_barrier_callback(struct rcu_head *notused)
{
	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
		complete(&rcu_barrier_completion);
}

/*
 * Called with preemption disabled, and from cross-cpu IRQ context.
 */
static void rcu_barrier_func(void *type)
{
	int cpu = smp_processor_id();
	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);

	atomic_inc(&rcu_barrier_cpu_count);
	switch ((enum rcu_barrier)type) {
	case RCU_BARRIER_STD:
		call_rcu(head, rcu_barrier_callback);
		break;
	case RCU_BARRIER_BH:
		call_rcu_bh(head, rcu_barrier_callback);
		break;
	case RCU_BARRIER_SCHED:
		call_rcu_sched(head, rcu_barrier_callback);
		break;
	}
}

static inline void wait_migrated_callbacks(void)
{
	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
}

/*
 * Orchestrate the specified type of RCU barrier, waiting for all
 * RCU callbacks of the specified type to complete.
 */
static void _rcu_barrier(enum rcu_barrier type)
{
	BUG_ON(in_interrupt());
	/* Take cpucontrol mutex to protect against CPU hotplug */
	mutex_lock(&rcu_barrier_mutex);
	init_completion(&rcu_barrier_completion);
	/*
	 * Initialize rcu_barrier_cpu_count to 1, then invoke
	 * rcu_barrier_func() on each CPU, so that each CPU also has
	 * incremented rcu_barrier_cpu_count.  Only then is it safe to
	 * decrement rcu_barrier_cpu_count -- otherwise the first CPU
	 * might complete its grace period before all of the other CPUs
	 * did their increment, causing this function to return too
	 * early.
	 */
	atomic_set(&rcu_barrier_cpu_count, 1);
	on_each_cpu(rcu_barrier_func, (void *)type, 1);
	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
		complete(&rcu_barrier_completion);
	wait_for_completion(&rcu_barrier_completion);
	mutex_unlock(&rcu_barrier_mutex);
	wait_migrated_callbacks();
}

/**
 * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
 */
void rcu_barrier(void)
{
	_rcu_barrier(RCU_BARRIER_STD);
}
EXPORT_SYMBOL_GPL(rcu_barrier);

/**
 * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
 */
void rcu_barrier_bh(void)
{
	_rcu_barrier(RCU_BARRIER_BH);
}
EXPORT_SYMBOL_GPL(rcu_barrier_bh);

/**
 * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
 */
void rcu_barrier_sched(void)
{
	_rcu_barrier(RCU_BARRIER_SCHED);
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);

static void rcu_migrate_callback(struct rcu_head *notused)
{
	if (atomic_dec_and_test(&rcu_migrate_type_count))
		wake_up(&rcu_migrate_wq);
}

static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
		unsigned long action, void *hcpu)
{
	if (action == CPU_DYING) {
		/*
		 * preempt_disable() in on_each_cpu() prevents stop_machine(),
		 * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
		 * returns, all online cpus have queued rcu_barrier_func(),
		 * and the dead cpu(if it exist) queues rcu_migrate_callback()s.
		 *
		 * These callbacks ensure _rcu_barrier() waits for all
		 * RCU callbacks of the specified type to complete.
		 */
		atomic_set(&rcu_migrate_type_count, 3);
		call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
		call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
		call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
	} else if (action == CPU_POST_DEAD) {
		/* rcu_migrate_head is protected by cpu_add_remove_lock */
		wait_migrated_callbacks();
	}

	return NOTIFY_OK;
}

void __init rcu_init(void)
{
	__rcu_init();
	hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
}

void rcu_scheduler_starting(void)
{
	WARN_ON(num_online_cpus() != 1);
	WARN_ON(nr_context_switches() > 0);
	rcu_scheduler_active = 1;
}