update.c 10.2 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * 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.
 *
18
 * Copyright IBM Corporation, 2001
L
Linus Torvalds 已提交
19 20 21
 *
 * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 *	    Manfred Spraul <manfred@colorfullife.com>
22
 *
L
Linus Torvalds 已提交
23 24 25 26 27 28 29
 * 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 -
30
 *		http://lse.sourceforge.net/locking/rcupdate.html
L
Linus Torvalds 已提交
31 32 33 34 35 36 37 38 39
 *
 */
#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>
A
Arun Sharma 已提交
40
#include <linux/atomic.h>
L
Linus Torvalds 已提交
41 42 43 44
#include <linux/bitops.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
45
#include <linux/mutex.h>
46
#include <linux/export.h>
47
#include <linux/hardirq.h>
48
#include <linux/delay.h>
49
#include <linux/module.h>
L
Linus Torvalds 已提交
50

51 52 53 54 55
#define CREATE_TRACE_POINTS
#include <trace/events/rcu.h>

#include "rcu.h"

56 57 58 59 60 61
MODULE_ALIAS("rcupdate");
#ifdef MODULE_PARAM_PREFIX
#undef MODULE_PARAM_PREFIX
#endif
#define MODULE_PARAM_PREFIX "rcupdate."

62 63
module_param(rcu_expedited, int, 0);

64 65
#ifdef CONFIG_PREEMPT_RCU

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
/*
 * Preemptible 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)
{
	current->rcu_read_lock_nesting++;
	barrier();  /* critical section after entry code. */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);

/*
 * Preemptible 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;

	if (t->rcu_read_lock_nesting != 1) {
		--t->rcu_read_lock_nesting;
	} else {
		barrier();  /* critical section before exit code. */
		t->rcu_read_lock_nesting = INT_MIN;
94 95 96
#ifdef CONFIG_PROVE_RCU_DELAY
		udelay(10); /* Make preemption more probable. */
#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
		barrier();  /* assign before ->rcu_read_unlock_special load */
		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
			rcu_read_unlock_special(t);
		barrier();  /* ->rcu_read_unlock_special load before assign */
		t->rcu_read_lock_nesting = 0;
	}
#ifdef CONFIG_PROVE_LOCKING
	{
		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);

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

113
#endif /* #ifdef CONFIG_PREEMPT_RCU */
114

115 116 117 118 119
#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);
120 121 122 123 124 125 126 127 128 129

static struct lock_class_key rcu_bh_lock_key;
struct lockdep_map rcu_bh_lock_map =
	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
EXPORT_SYMBOL_GPL(rcu_bh_lock_map);

static struct lock_class_key rcu_sched_lock_key;
struct lockdep_map rcu_sched_lock_map =
	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
130

131
int notrace debug_lockdep_rcu_enabled(void)
132 133 134 135 136 137
{
	return rcu_scheduler_active && debug_locks &&
	       current->lockdep_recursion == 0;
}
EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);

138
/**
139
 * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
140 141 142 143
 *
 * Check for bottom half being disabled, which covers both the
 * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
 * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
144 145 146
 * will show the situation.  This is useful for debug checks in functions
 * that require that they be called within an RCU read-side critical
 * section.
147 148
 *
 * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
149 150 151
 *
 * Note that rcu_read_lock() is disallowed if the CPU is either idle or
 * offline from an RCU perspective, so check for those as well.
152 153 154 155 156
 */
int rcu_read_lock_bh_held(void)
{
	if (!debug_lockdep_rcu_enabled())
		return 1;
157
	if (!rcu_is_watching())
158
		return 0;
159 160
	if (!rcu_lockdep_current_cpu_online())
		return 0;
161
	return in_softirq() || irqs_disabled();
162 163 164 165 166
}
EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);

#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

167 168 169 170 171
struct rcu_synchronize {
	struct rcu_head head;
	struct completion completion;
};

P
Paul E. McKenney 已提交
172 173 174 175
/*
 * Awaken the corresponding synchronize_rcu() instance now that a
 * grace period has elapsed.
 */
176
static void wakeme_after_rcu(struct rcu_head  *head)
D
Dipankar Sarma 已提交
177
{
178 179 180 181
	struct rcu_synchronize *rcu;

	rcu = container_of(head, struct rcu_synchronize, head);
	complete(&rcu->completion);
D
Dipankar Sarma 已提交
182
}
183

184 185 186 187 188 189 190 191 192 193 194 195 196 197
void wait_rcu_gp(call_rcu_func_t crf)
{
	struct rcu_synchronize rcu;

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

198 199 200 201 202 203 204 205 206 207
#ifdef CONFIG_PROVE_RCU
/*
 * wrapper function to avoid #include problems.
 */
int rcu_my_thread_group_empty(void)
{
	return thread_group_empty(current);
}
EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
#endif /* #ifdef CONFIG_PROVE_RCU */
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

#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
static inline void debug_init_rcu_head(struct rcu_head *head)
{
	debug_object_init(head, &rcuhead_debug_descr);
}

static inline void debug_rcu_head_free(struct rcu_head *head)
{
	debug_object_free(head, &rcuhead_debug_descr);
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 * Activation is performed internally by call_rcu().
 */
static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct rcu_head *head = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. We just make sure that it is
		 * tracked in the object tracker.
		 */
		debug_object_init(head, &rcuhead_debug_descr);
		debug_object_activate(head, &rcuhead_debug_descr);
		return 0;
	default:
		return 1;
	}
}

/**
 * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects
 * @head: pointer to rcu_head structure to be initialized
 *
 * This function informs debugobjects of a new rcu_head structure that
 * has been allocated as an auto variable on the stack.  This function
 * is not required for rcu_head structures that are statically defined or
 * that are dynamically allocated on the heap.  This function has no
 * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
 */
void init_rcu_head_on_stack(struct rcu_head *head)
{
	debug_object_init_on_stack(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(init_rcu_head_on_stack);

/**
 * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects
 * @head: pointer to rcu_head structure to be initialized
 *
 * This function informs debugobjects that an on-stack rcu_head structure
 * is about to go out of scope.  As with init_rcu_head_on_stack(), this
 * function is not required for rcu_head structures that are statically
 * defined or that are dynamically allocated on the heap.  Also as with
 * init_rcu_head_on_stack(), this function has no effect for
 * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
 */
void destroy_rcu_head_on_stack(struct rcu_head *head)
{
	debug_object_free(head, &rcuhead_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);

struct debug_obj_descr rcuhead_debug_descr = {
	.name = "rcu_head",
	.fixup_activate = rcuhead_fixup_activate,
};
EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
284 285

#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
286
void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
287 288
			       unsigned long secs,
			       unsigned long c_old, unsigned long c)
289
{
290
	trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c);
291 292 293
}
EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
#else
294 295
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
	do { } while (0)
296
#endif
297 298 299 300 301 302 303 304 305 306

#ifdef CONFIG_RCU_STALL_COMMON

#ifdef CONFIG_PROVE_RCU
#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
#else
#define RCU_STALL_DELAY_DELTA	       0
#endif

int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
307
static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
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

module_param(rcu_cpu_stall_suppress, int, 0644);
module_param(rcu_cpu_stall_timeout, int, 0644);

int rcu_jiffies_till_stall_check(void)
{
	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);

	/*
	 * Limit check must be consistent with the Kconfig limits
	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
	 */
	if (till_stall_check < 3) {
		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
		till_stall_check = 3;
	} else if (till_stall_check > 300) {
		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
		till_stall_check = 300;
	}
	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
}

static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
{
	rcu_cpu_stall_suppress = 1;
	return NOTIFY_DONE;
}

static struct notifier_block rcu_panic_block = {
	.notifier_call = rcu_panic,
};

static int __init check_cpu_stall_init(void)
{
	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
	return 0;
}
early_initcall(check_cpu_stall_init);

#endif /* #ifdef CONFIG_RCU_STALL_COMMON */