rcupdate.h 37.6 KB
Newer Older
L
Linus Torvalds 已提交
1
/*
2
 * Read-Copy Update mechanism for mutual exclusion
L
Linus Torvalds 已提交
3 4 5 6 7 8 9 10 11 12 13 14
 *
 * 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
15 16
 * along with this program; if not, you can access it online at
 * http://www.gnu.org/licenses/gpl-2.0.html.
L
Linus Torvalds 已提交
17
 *
18
 * Copyright IBM Corporation, 2001
L
Linus Torvalds 已提交
19 20
 *
 * Author: Dipankar Sarma <dipankar@in.ibm.com>
21
 *
22
 * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
L
Linus Torvalds 已提交
23 24 25 26 27 28
 * 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 -
29
 *		http://lse.sourceforge.net/locking/rcupdate.html
L
Linus Torvalds 已提交
30 31 32 33 34 35
 *
 */

#ifndef __LINUX_RCUPDATE_H
#define __LINUX_RCUPDATE_H

36
#include <linux/types.h>
L
Linus Torvalds 已提交
37 38 39 40 41
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
42
#include <linux/lockdep.h>
P
Paul E. McKenney 已提交
43
#include <linux/completion.h>
44
#include <linux/debugobjects.h>
45
#include <linux/bug.h>
46
#include <linux/compiler.h>
47
#include <asm/barrier.h>
L
Linus Torvalds 已提交
48

D
Dave Young 已提交
49 50 51 52
#ifdef CONFIG_RCU_TORTURE_TEST
extern int rcutorture_runnable; /* for sysctl */
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */

53
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
54 55 56 57 58 59 60
void rcutorture_record_test_transition(void);
void rcutorture_record_progress(unsigned long vernum);
void do_trace_rcu_torture_read(const char *rcutorturename,
			       struct rcu_head *rhp,
			       unsigned long secs,
			       unsigned long c_old,
			       unsigned long c);
61 62 63 64 65 66 67
#else
static inline void rcutorture_record_test_transition(void)
{
}
static inline void rcutorture_record_progress(unsigned long vernum)
{
}
68
#ifdef CONFIG_RCU_TRACE
69 70 71 72 73
void do_trace_rcu_torture_read(const char *rcutorturename,
			       struct rcu_head *rhp,
			       unsigned long secs,
			       unsigned long c_old,
			       unsigned long c);
74
#else
75 76
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
	do { } while (0)
77
#endif
78 79
#endif

80 81
#define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
#define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
82 83
#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
84
#define ulong2long(a)		(*(long *)(&(a)))
85

86
/* Exported common interfaces */
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101

#ifdef CONFIG_PREEMPT_RCU

/**
 * call_rcu() - Queue an RCU callback for invocation after a grace period.
 * @head: structure to be used for queueing the RCU updates.
 * @func: actual callback function to be invoked after the grace period
 *
 * The callback function will be invoked some time after a full grace
 * period elapses, in other words after all pre-existing RCU read-side
 * critical sections have completed.  However, the callback function
 * might well execute concurrently with RCU read-side critical sections
 * that started after call_rcu() was invoked.  RCU read-side critical
 * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
 * and may be nested.
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
 *
 * Note that all CPUs must agree that the grace period extended beyond
 * all pre-existing RCU read-side critical section.  On systems with more
 * than one CPU, this means that when "func()" is invoked, each CPU is
 * guaranteed to have executed a full memory barrier since the end of its
 * last RCU read-side critical section whose beginning preceded the call
 * to call_rcu().  It also means that each CPU executing an RCU read-side
 * critical section that continues beyond the start of "func()" must have
 * executed a memory barrier after the call_rcu() but before the beginning
 * of that RCU read-side critical section.  Note that these guarantees
 * include CPUs that are offline, idle, or executing in user mode, as
 * well as CPUs that are executing in the kernel.
 *
 * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
 * resulting RCU callback function "func()", then both CPU A and CPU B are
 * guaranteed to execute a full memory barrier during the time interval
 * between the call to call_rcu() and the invocation of "func()" -- even
 * if CPU A and CPU B are the same CPU (but again only if the system has
 * more than one CPU).
121
 */
122 123
void call_rcu(struct rcu_head *head,
	      void (*func)(struct rcu_head *head));
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

#else /* #ifdef CONFIG_PREEMPT_RCU */

/* In classic RCU, call_rcu() is just call_rcu_sched(). */
#define	call_rcu	call_rcu_sched

#endif /* #else #ifdef CONFIG_PREEMPT_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 callback function to be invoked after the grace period
 *
 * The callback 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.
149 150 151
 *
 * See the description of call_rcu() for more detailed information on
 * memory ordering guarantees.
152
 */
153 154
void call_rcu_bh(struct rcu_head *head,
		 void (*func)(struct rcu_head *head));
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170

/**
 * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
 * @head: structure to be used for queueing the RCU updates.
 * @func: actual callback function to be invoked after the grace period
 *
 * The callback 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_sched() assumes
 * that the read-side critical sections end on enabling of preemption
 * or on voluntary preemption.
 * RCU read-side critical sections are delimited by :
 *  - rcu_read_lock_sched() and  rcu_read_unlock_sched(),
 *  OR
 *  anything that disables preemption.
 *  These may be nested.
171 172 173
 *
 * See the description of call_rcu() for more detailed information on
 * memory ordering guarantees.
174
 */
175 176
void call_rcu_sched(struct rcu_head *head,
		    void (*func)(struct rcu_head *rcu));
177

178
void synchronize_sched(void);
179

180 181
#ifdef CONFIG_PREEMPT_RCU

182 183 184
void __rcu_read_lock(void);
void __rcu_read_unlock(void);
void rcu_read_unlock_special(struct task_struct *t);
185 186
void synchronize_rcu(void);

187 188 189 190 191 192 193 194
/*
 * Defined as a macro as it is a very low level header included from
 * areas that don't even know about current.  This gives the rcu_read_lock()
 * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
 * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
 */
#define rcu_preempt_depth() (current->rcu_read_lock_nesting)

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
#else /* #ifdef CONFIG_PREEMPT_RCU */

static inline void __rcu_read_lock(void)
{
	preempt_disable();
}

static inline void __rcu_read_unlock(void)
{
	preempt_enable();
}

static inline void synchronize_rcu(void)
{
	synchronize_sched();
}

static inline int rcu_preempt_depth(void)
{
	return 0;
}

#endif /* #else #ifdef CONFIG_PREEMPT_RCU */

/* Internal to kernel */
220 221 222 223
void rcu_init(void);
void rcu_sched_qs(int cpu);
void rcu_bh_qs(int cpu);
void rcu_check_callbacks(int cpu, int user);
224
struct notifier_block;
225 226 227 228
void rcu_idle_enter(void);
void rcu_idle_exit(void);
void rcu_irq_enter(void);
void rcu_irq_exit(void);
229 230

#ifdef CONFIG_RCU_USER_QS
231 232
void rcu_user_enter(void);
void rcu_user_exit(void);
233 234 235
#else
static inline void rcu_user_enter(void) { }
static inline void rcu_user_exit(void) { }
F
Frederic Weisbecker 已提交
236 237
static inline void rcu_user_hooks_switch(struct task_struct *prev,
					 struct task_struct *next) { }
238 239
#endif /* CONFIG_RCU_USER_QS */

240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
/**
 * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
 * @a: Code that RCU needs to pay attention to.
 *
 * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden
 * in the inner idle loop, that is, between the rcu_idle_enter() and
 * the rcu_idle_exit() -- RCU will happily ignore any such read-side
 * critical sections.  However, things like powertop need tracepoints
 * in the inner idle loop.
 *
 * This macro provides the way out:  RCU_NONIDLE(do_something_with_RCU())
 * will tell RCU that it needs to pay attending, invoke its argument
 * (in this example, a call to the do_something_with_RCU() function),
 * and then tell RCU to go back to ignoring this CPU.  It is permissible
 * to nest RCU_NONIDLE() wrappers, but the nesting level is currently
 * quite limited.  If deeper nesting is required, it will be necessary
 * to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
 */
#define RCU_NONIDLE(a) \
	do { \
260
		rcu_irq_enter(); \
261
		do { a; } while (0); \
262
		rcu_irq_exit(); \
263 264
	} while (0)

265
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
266
bool __rcu_is_watching(void);
267 268
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */

269 270 271 272 273 274 275 276 277
/*
 * Infrastructure to implement the synchronize_() primitives in
 * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
 */

typedef void call_rcu_func_t(struct rcu_head *head,
			     void (*func)(struct rcu_head *head));
void wait_rcu_gp(call_rcu_func_t crf);

278
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
279
#include <linux/rcutree.h>
P
Paul E. McKenney 已提交
280
#elif defined(CONFIG_TINY_RCU)
281
#include <linux/rcutiny.h>
282 283
#else
#error "Unknown RCU implementation specified to kernel configuration"
284
#endif
285

286 287 288 289 290 291 292
/*
 * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
 * initialization and destruction of rcu_head on the stack. rcu_head structures
 * allocated dynamically in the heap or defined statically don't need any
 * initialization.
 */
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
293 294
void init_rcu_head_on_stack(struct rcu_head *head);
void destroy_rcu_head_on_stack(struct rcu_head *head);
295
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
296 297 298 299 300 301 302
static inline void init_rcu_head_on_stack(struct rcu_head *head)
{
}

static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
{
}
303
#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
304

305 306 307 308 309 310 311 312 313
#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
bool rcu_lockdep_current_cpu_online(void);
#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
static inline bool rcu_lockdep_current_cpu_online(void)
{
	return 1;
}
#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */

314
#ifdef CONFIG_DEBUG_LOCK_ALLOC
315

316 317 318 319 320 321 322 323 324 325
static inline void rcu_lock_acquire(struct lockdep_map *map)
{
	lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
}

static inline void rcu_lock_release(struct lockdep_map *map)
{
	lock_release(map, 1, _THIS_IP_);
}

326
extern struct lockdep_map rcu_lock_map;
327 328
extern struct lockdep_map rcu_bh_lock_map;
extern struct lockdep_map rcu_sched_lock_map;
329
extern struct lockdep_map rcu_callback_map;
330
extern int debug_lockdep_rcu_enabled(void);
331

332
/**
333
 * rcu_read_lock_held() - might we be in RCU read-side critical section?
334
 *
335 336
 * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
 * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
337
 * this assumes we are in an RCU read-side critical section unless it can
338 339
 * prove otherwise.  This is useful for debug checks in functions that
 * require that they be called within an RCU read-side critical section.
340
 *
341
 * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
342
 * and while lockdep is disabled.
343 344 345 346 347
 *
 * Note that rcu_read_lock() and the matching rcu_read_unlock() must
 * occur in the same context, for example, it is illegal to invoke
 * rcu_read_unlock() in process context if the matching rcu_read_lock()
 * was invoked from within an irq handler.
348 349 350
 *
 * 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.
351 352 353
 */
static inline int rcu_read_lock_held(void)
{
354 355
	if (!debug_lockdep_rcu_enabled())
		return 1;
356
	if (!rcu_is_watching())
357
		return 0;
358 359
	if (!rcu_lockdep_current_cpu_online())
		return 0;
360
	return lock_is_held(&rcu_lock_map);
361 362
}

363 364 365
/*
 * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
 * hell.
366
 */
367
int rcu_read_lock_bh_held(void);
368 369

/**
370
 * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
371
 *
372 373 374 375 376
 * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
 * RCU-sched read-side critical section.  In absence of
 * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
 * critical section unless it can prove otherwise.  Note that disabling
 * of preemption (including disabling irqs) counts as an RCU-sched
377 378 379
 * read-side critical section.  This is useful for debug checks in functions
 * that required that they be called within an RCU-sched read-side
 * critical section.
380
 *
381 382
 * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
 * and while lockdep is disabled.
383 384 385 386 387 388 389 390 391 392 393 394 395
 *
 * Note that if the CPU is in the idle loop from an RCU point of
 * view (ie: that we are in the section between rcu_idle_enter() and
 * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
 * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
 * that are in such a section, considering these as in extended quiescent
 * state, so such a CPU is effectively never in an RCU read-side critical
 * section regardless of what RCU primitives it invokes.  This state of
 * affairs is required --- we need to keep an RCU-free window in idle
 * where the CPU may possibly enter into low power mode. This way we can
 * notice an extended quiescent state to other CPUs that started a grace
 * period. Otherwise we would delay any grace period as long as we run in
 * the idle task.
396 397 398
 *
 * Similarly, we avoid claiming an SRCU read lock held if the current
 * CPU is offline.
399
 */
400
#ifdef CONFIG_PREEMPT_COUNT
401 402 403 404
static inline int rcu_read_lock_sched_held(void)
{
	int lockdep_opinion = 0;

405 406
	if (!debug_lockdep_rcu_enabled())
		return 1;
407
	if (!rcu_is_watching())
408
		return 0;
409 410
	if (!rcu_lockdep_current_cpu_online())
		return 0;
411 412
	if (debug_locks)
		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
413
	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
414
}
415
#else /* #ifdef CONFIG_PREEMPT_COUNT */
416 417 418
static inline int rcu_read_lock_sched_held(void)
{
	return 1;
419
}
420
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
421 422 423

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

424 425
# define rcu_lock_acquire(a)		do { } while (0)
# define rcu_lock_release(a)		do { } while (0)
426 427 428 429 430 431 432 433 434 435 436

static inline int rcu_read_lock_held(void)
{
	return 1;
}

static inline int rcu_read_lock_bh_held(void)
{
	return 1;
}

437
#ifdef CONFIG_PREEMPT_COUNT
438 439
static inline int rcu_read_lock_sched_held(void)
{
440
	return preempt_count() != 0 || irqs_disabled();
441
}
442
#else /* #ifdef CONFIG_PREEMPT_COUNT */
443 444 445
static inline int rcu_read_lock_sched_held(void)
{
	return 1;
446
}
447
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
448 449 450 451 452

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

#ifdef CONFIG_PROVE_RCU

453 454 455
/**
 * rcu_lockdep_assert - emit lockdep splat if specified condition not met
 * @c: condition to check
456
 * @s: informative message
457
 */
458
#define rcu_lockdep_assert(c, s)					\
459
	do {								\
460
		static bool __section(.data.unlikely) __warned;		\
461 462
		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
			__warned = true;				\
463
			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
464 465 466
		}							\
	} while (0)

467 468 469 470
#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU)
static inline void rcu_preempt_sleep_check(void)
{
	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
471
			   "Illegal context switch in RCU read-side critical section");
472 473 474 475 476 477 478
}
#else /* #ifdef CONFIG_PROVE_RCU */
static inline void rcu_preempt_sleep_check(void)
{
}
#endif /* #else #ifdef CONFIG_PROVE_RCU */

479 480
#define rcu_sleep_check()						\
	do {								\
481
		rcu_preempt_sleep_check();				\
482
		rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),	\
J
Joe Perches 已提交
483
				   "Illegal context switch in RCU-bh read-side critical section"); \
484
		rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),	\
J
Joe Perches 已提交
485
				   "Illegal context switch in RCU-sched read-side critical section"); \
486 487
	} while (0)

488 489
#else /* #ifdef CONFIG_PROVE_RCU */

490 491
#define rcu_lockdep_assert(c, s) do { } while (0)
#define rcu_sleep_check() do { } while (0)
492 493 494 495 496 497 498 499 500 501 502

#endif /* #else #ifdef CONFIG_PROVE_RCU */

/*
 * Helper functions for rcu_dereference_check(), rcu_dereference_protected()
 * and rcu_assign_pointer().  Some of these could be folded into their
 * callers, but they are left separate in order to ease introduction of
 * multiple flavors of pointers to match the multiple flavors of RCU
 * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in
 * the future.
 */
503 504 505 506 507 508 509 510

#ifdef __CHECKER__
#define rcu_dereference_sparse(p, space) \
	((void)(((typeof(*p) space *)p) == p))
#else /* #ifdef __CHECKER__ */
#define rcu_dereference_sparse(p, space)
#endif /* #else #ifdef __CHECKER__ */

511
#define __rcu_access_pointer(p, space) \
512 513 514 515 516
({ \
	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
	rcu_dereference_sparse(p, space); \
	((typeof(*p) __force __kernel *)(_________p1)); \
})
517
#define __rcu_dereference_check(p, c, space) \
518 519 520 521 522 523 524
({ \
	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
	rcu_dereference_sparse(p, space); \
	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
	((typeof(*p) __force __kernel *)(_________p1)); \
})
525
#define __rcu_dereference_protected(p, c, space) \
526 527 528 529 530
({ \
	rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \
	rcu_dereference_sparse(p, space); \
	((typeof(*p) __force __kernel *)(p)); \
})
531

532
#define __rcu_access_index(p, space) \
533 534 535 536 537
({ \
	typeof(p) _________p1 = ACCESS_ONCE(p); \
	rcu_dereference_sparse(p, space); \
	(_________p1); \
})
538
#define __rcu_dereference_index_check(p, c) \
539 540 541 542 543 544 545
({ \
	typeof(p) _________p1 = ACCESS_ONCE(p); \
	rcu_lockdep_assert(c, \
			   "suspicious rcu_dereference_index_check() usage"); \
	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
	(_________p1); \
})
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

/**
 * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
 * @v: The value to statically initialize with.
 */
#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)

/**
 * rcu_assign_pointer() - assign to RCU-protected pointer
 * @p: pointer to assign to
 * @v: value to assign (publish)
 *
 * Assigns the specified value to the specified RCU-protected
 * pointer, ensuring that any concurrent RCU readers will see
 * any prior initialization.
 *
 * Inserts memory barriers on architectures that require them
 * (which is most of them), and also prevents the compiler from
 * reordering the code that initializes the structure after the pointer
 * assignment.  More importantly, this call documents which pointers
 * will be dereferenced by RCU read-side code.
 *
 * In some special cases, you may use RCU_INIT_POINTER() instead
 * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
 * to the fact that it does not constrain either the CPU or the compiler.
 * That said, using RCU_INIT_POINTER() when you should have used
 * rcu_assign_pointer() is a very bad thing that results in
 * impossible-to-diagnose memory corruption.  So please be careful.
 * See the RCU_INIT_POINTER() comment header for details.
 *
 * Note that rcu_assign_pointer() evaluates each of its arguments only
 * once, appearances notwithstanding.  One of the "extra" evaluations
 * is in typeof() and the other visible only to sparse (__CHECKER__),
 * neither of which actually execute the argument.  As with most cpp
 * macros, this execute-arguments-only-once property is important, so
 * please be careful when making changes to rcu_assign_pointer() and the
 * other macros that it invokes.
 */
584
#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v))
585 586 587 588 589 590 591 592 593 594 595 596

/**
 * rcu_access_pointer() - fetch RCU pointer with no dereferencing
 * @p: The pointer to read
 *
 * Return the value of the specified RCU-protected pointer, but omit the
 * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
 * when the value of this pointer is accessed, but the pointer is not
 * dereferenced, for example, when testing an RCU-protected pointer against
 * NULL.  Although rcu_access_pointer() may also be used in cases where
 * update-side locks prevent the value of the pointer from changing, you
 * should instead use rcu_dereference_protected() for this use case.
597 598 599 600 601 602 603
 *
 * It is also permissible to use rcu_access_pointer() when read-side
 * access to the pointer was removed at least one grace period ago, as
 * is the case in the context of the RCU callback that is freeing up
 * the data, or after a synchronize_rcu() returns.  This can be useful
 * when tearing down multi-linked structures after a grace period
 * has elapsed.
604 605 606
 */
#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)

607
/**
608
 * rcu_dereference_check() - rcu_dereference with debug checking
609 610
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
611
 *
612
 * Do an rcu_dereference(), but check that the conditions under which the
613 614 615 616 617
 * dereference will take place are correct.  Typically the conditions
 * indicate the various locking conditions that should be held at that
 * point.  The check should return true if the conditions are satisfied.
 * An implicit check for being in an RCU read-side critical section
 * (rcu_read_lock()) is included.
618 619 620
 *
 * For example:
 *
621
 *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
622 623
 *
 * could be used to indicate to lockdep that foo->bar may only be dereferenced
624
 * if either rcu_read_lock() is held, or that the lock required to replace
625 626 627 628 629 630
 * the bar struct at foo->bar is held.
 *
 * Note that the list of conditions may also include indications of when a lock
 * need not be held, for example during initialisation or destruction of the
 * target struct:
 *
631
 *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
632
 *					      atomic_read(&foo->usage) == 0);
633 634 635 636 637 638
 *
 * Inserts memory barriers on architectures that require them
 * (currently only the Alpha), prevents the compiler from refetching
 * (and from merging fetches), and, more importantly, documents exactly
 * which pointers are protected by RCU and checks that the pointer is
 * annotated as __rcu.
639 640
 */
#define rcu_dereference_check(p, c) \
641 642 643 644 645 646 647 648 649 650 651
	__rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu)

/**
 * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
 *
 * This is the RCU-bh counterpart to rcu_dereference_check().
 */
#define rcu_dereference_bh_check(p, c) \
	__rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
652

653
/**
654 655 656 657 658 659 660 661 662 663 664 665
 * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
 *
 * This is the RCU-sched counterpart to rcu_dereference_check().
 */
#define rcu_dereference_sched_check(p, c) \
	__rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \
				__rcu)

#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/

666 667 668 669 670 671 672 673 674
/*
 * The tracing infrastructure traces RCU (we want that), but unfortunately
 * some of the RCU checks causes tracing to lock up the system.
 *
 * The tracing version of rcu_dereference_raw() must not call
 * rcu_read_lock_held().
 */
#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)

675 676 677 678 679 680 681 682 683 684 685 686 687 688
/**
 * rcu_access_index() - fetch RCU index with no dereferencing
 * @p: The index to read
 *
 * Return the value of the specified RCU-protected index, but omit the
 * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
 * when the value of this index is accessed, but the index is not
 * dereferenced, for example, when testing an RCU-protected index against
 * -1.  Although rcu_access_index() may also be used in cases where
 * update-side locks prevent the value of the index from changing, you
 * should instead use rcu_dereference_index_protected() for this use case.
 */
#define rcu_access_index(p) __rcu_access_index((p), __rcu)

689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
/**
 * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
 *
 * Similar to rcu_dereference_check(), but omits the sparse checking.
 * This allows rcu_dereference_index_check() to be used on integers,
 * which can then be used as array indices.  Attempting to use
 * rcu_dereference_check() on an integer will give compiler warnings
 * because the sparse address-space mechanism relies on dereferencing
 * the RCU-protected pointer.  Dereferencing integers is not something
 * that even gcc will put up with.
 *
 * Note that this function does not implicitly check for RCU read-side
 * critical sections.  If this function gains lots of uses, it might
 * make sense to provide versions for each flavor of RCU, but it does
 * not make sense as of early 2010.
 */
#define rcu_dereference_index_check(p, c) \
	__rcu_dereference_index_check((p), (c))

/**
 * rcu_dereference_protected() - fetch RCU pointer when updates prevented
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
714 715 716 717 718 719 720 721
 *
 * Return the value of the specified RCU-protected pointer, but omit
 * both the smp_read_barrier_depends() and the ACCESS_ONCE().  This
 * is useful in cases where update-side locks prevent the value of the
 * pointer from changing.  Please note that this primitive does -not-
 * prevent the compiler from repeating this reference or combining it
 * with other references, so it should not be used without protection
 * of appropriate locks.
722 723 724 725
 *
 * This function is only for update-side use.  Using this function
 * when protected only by rcu_read_lock() will result in infrequent
 * but very ugly failures.
726 727
 */
#define rcu_dereference_protected(p, c) \
728
	__rcu_dereference_protected((p), (c), __rcu)
729

730

731
/**
732 733
 * rcu_dereference() - fetch RCU-protected pointer for dereferencing
 * @p: The pointer to read, prior to dereferencing
734
 *
735
 * This is a simple wrapper around rcu_dereference_check().
736
 */
737
#define rcu_dereference(p) rcu_dereference_check(p, 0)
738

L
Linus Torvalds 已提交
739
/**
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
 * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing
 * @p: The pointer to read, prior to dereferencing
 *
 * Makes rcu_dereference_check() do the dirty work.
 */
#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0)

/**
 * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing
 * @p: The pointer to read, prior to dereferencing
 *
 * Makes rcu_dereference_check() do the dirty work.
 */
#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0)

/**
 * rcu_read_lock() - mark the beginning of an RCU read-side critical section
L
Linus Torvalds 已提交
757
 *
758
 * When synchronize_rcu() is invoked on one CPU while other CPUs
L
Linus Torvalds 已提交
759
 * are within RCU read-side critical sections, then the
760
 * synchronize_rcu() is guaranteed to block until after all the other
L
Linus Torvalds 已提交
761 762 763 764 765 766
 * CPUs exit their critical sections.  Similarly, if call_rcu() is invoked
 * on one CPU while other CPUs are within RCU read-side critical
 * sections, invocation of the corresponding RCU callback is deferred
 * until after the all the other CPUs exit their critical sections.
 *
 * Note, however, that RCU callbacks are permitted to run concurrently
767
 * with new RCU read-side critical sections.  One way that this can happen
L
Linus Torvalds 已提交
768 769 770 771 772 773 774 775 776 777 778 779 780 781
 * is via the following sequence of events: (1) CPU 0 enters an RCU
 * read-side critical section, (2) CPU 1 invokes call_rcu() to register
 * an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
 * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU
 * callback is invoked.  This is legal, because the RCU read-side critical
 * section that was running concurrently with the call_rcu() (and which
 * therefore might be referencing something that the corresponding RCU
 * callback would free up) has completed before the corresponding
 * RCU callback is invoked.
 *
 * RCU read-side critical sections may be nested.  Any deferred actions
 * will be deferred until the outermost RCU read-side critical section
 * completes.
 *
782 783 784 785 786 787 788 789 790 791
 * You can avoid reading and understanding the next paragraph by
 * following this rule: don't put anything in an rcu_read_lock() RCU
 * read-side critical section that would block in a !PREEMPT kernel.
 * But if you want the full story, read on!
 *
 * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
 * is illegal to block while in an RCU read-side critical section.  In
 * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
 * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
 * be preempted, but explicit blocking is illegal.  Finally, in preemptible
792
 * RCU implementations in real-time (with -rt patchset) kernel builds,
793 794 795
 * RCU read-side critical sections may be preempted and they may also
 * block, but only when acquiring spinlocks that are subject to priority
 * inheritance.
L
Linus Torvalds 已提交
796
 */
797 798 799 800
static inline void rcu_read_lock(void)
{
	__rcu_read_lock();
	__acquire(RCU);
801
	rcu_lock_acquire(&rcu_lock_map);
802
	rcu_lockdep_assert(rcu_is_watching(),
803
			   "rcu_read_lock() used illegally while idle");
804
}
L
Linus Torvalds 已提交
805 806 807 808 809 810 811 812 813 814

/*
 * So where is rcu_write_lock()?  It does not exist, as there is no
 * way for writers to lock out RCU readers.  This is a feature, not
 * a bug -- this property is what provides RCU's performance benefits.
 * Of course, writers must coordinate with each other.  The normal
 * spinlock primitives work well for this, but any other technique may be
 * used as well.  RCU does not care how the writers keep out of each
 * others' way, as long as they do so.
 */
815 816

/**
817
 * rcu_read_unlock() - marks the end of an RCU read-side critical section.
818 819 820
 *
 * See rcu_read_lock() for more information.
 */
821 822
static inline void rcu_read_unlock(void)
{
823
	rcu_lockdep_assert(rcu_is_watching(),
824
			   "rcu_read_unlock() used illegally while idle");
825
	rcu_lock_release(&rcu_lock_map);
826 827 828
	__release(RCU);
	__rcu_read_unlock();
}
L
Linus Torvalds 已提交
829 830

/**
831
 * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
L
Linus Torvalds 已提交
832 833
 *
 * This is equivalent of rcu_read_lock(), but to be used when updates
834 835 836 837 838 839 840
 * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since
 * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a
 * softirq handler to be a quiescent state, a process in RCU read-side
 * critical section must be protected by disabling softirqs. Read-side
 * critical sections in interrupt context can use just rcu_read_lock(),
 * though this should at least be commented to avoid confusing people
 * reading the code.
841 842 843 844 845
 *
 * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh()
 * must occur in the same context, for example, it is illegal to invoke
 * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh()
 * was invoked from some other task.
L
Linus Torvalds 已提交
846
 */
847 848
static inline void rcu_read_lock_bh(void)
{
849
	local_bh_disable();
850
	__acquire(RCU_BH);
851
	rcu_lock_acquire(&rcu_bh_lock_map);
852
	rcu_lockdep_assert(rcu_is_watching(),
853
			   "rcu_read_lock_bh() used illegally while idle");
854
}
L
Linus Torvalds 已提交
855 856 857 858 859 860

/*
 * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
 *
 * See rcu_read_lock_bh() for more information.
 */
861 862
static inline void rcu_read_unlock_bh(void)
{
863
	rcu_lockdep_assert(rcu_is_watching(),
864
			   "rcu_read_unlock_bh() used illegally while idle");
865
	rcu_lock_release(&rcu_bh_lock_map);
866
	__release(RCU_BH);
867
	local_bh_enable();
868
}
L
Linus Torvalds 已提交
869

870
/**
871
 * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
872
 *
873 874 875 876
 * This is equivalent of rcu_read_lock(), but to be used when updates
 * are being done using call_rcu_sched() or synchronize_rcu_sched().
 * Read-side critical sections can also be introduced by anything that
 * disables preemption, including local_irq_disable() and friends.
877 878 879 880 881
 *
 * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched()
 * must occur in the same context, for example, it is illegal to invoke
 * rcu_read_unlock_sched() from process context if the matching
 * rcu_read_lock_sched() was invoked from an NMI handler.
882
 */
883 884 885
static inline void rcu_read_lock_sched(void)
{
	preempt_disable();
886
	__acquire(RCU_SCHED);
887
	rcu_lock_acquire(&rcu_sched_lock_map);
888
	rcu_lockdep_assert(rcu_is_watching(),
889
			   "rcu_read_lock_sched() used illegally while idle");
890
}
891 892

/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
893
static inline notrace void rcu_read_lock_sched_notrace(void)
894 895
{
	preempt_disable_notrace();
896
	__acquire(RCU_SCHED);
897
}
898 899 900 901 902 903

/*
 * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
 *
 * See rcu_read_lock_sched for more information.
 */
904 905
static inline void rcu_read_unlock_sched(void)
{
906
	rcu_lockdep_assert(rcu_is_watching(),
907
			   "rcu_read_unlock_sched() used illegally while idle");
908
	rcu_lock_release(&rcu_sched_lock_map);
909
	__release(RCU_SCHED);
910 911
	preempt_enable();
}
912 913

/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
914
static inline notrace void rcu_read_unlock_sched_notrace(void)
915
{
916
	__release(RCU_SCHED);
917 918
	preempt_enable_notrace();
}
919

920 921 922
/**
 * RCU_INIT_POINTER() - initialize an RCU protected pointer
 *
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
 * Initialize an RCU-protected pointer in special cases where readers
 * do not need ordering constraints on the CPU or the compiler.  These
 * special cases are:
 *
 * 1.	This use of RCU_INIT_POINTER() is NULLing out the pointer -or-
 * 2.	The caller has taken whatever steps are required to prevent
 *	RCU readers from concurrently accessing this pointer -or-
 * 3.	The referenced data structure has already been exposed to
 *	readers either at compile time or via rcu_assign_pointer() -and-
 *	a.	You have not made -any- reader-visible changes to
 *		this structure since then -or-
 *	b.	It is OK for readers accessing this structure from its
 *		new location to see the old state of the structure.  (For
 *		example, the changes were to statistical counters or to
 *		other state where exact synchronization is not required.)
 *
 * Failure to follow these rules governing use of RCU_INIT_POINTER() will
 * result in impossible-to-diagnose memory corruption.  As in the structures
 * will look OK in crash dumps, but any concurrent RCU readers might
 * see pre-initialized values of the referenced data structure.  So
 * please be very careful how you use RCU_INIT_POINTER()!!!
 *
 * If you are creating an RCU-protected linked structure that is accessed
 * by a single external-to-structure RCU-protected pointer, then you may
 * use RCU_INIT_POINTER() to initialize the internal RCU-protected
 * pointers, but you must use rcu_assign_pointer() to initialize the
 * external-to-structure pointer -after- you have completely initialized
 * the reader-accessible portions of the linked structure.
951 952
 */
#define RCU_INIT_POINTER(p, v) \
953
	do { \
954
		p = RCU_INITIALIZER(v); \
955
	} while (0)
L
Lai Jiangshan 已提交
956

957 958 959 960 961 962
/**
 * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
 *
 * GCC-style initialization for an RCU-protected pointer in a structure field.
 */
#define RCU_POINTER_INITIALIZER(p, v) \
963
		.p = RCU_INITIALIZER(v)
L
Lai Jiangshan 已提交
964

965 966 967 968 969 970 971 972 973 974 975 976
/*
 * Does the specified offset indicate that the corresponding rcu_head
 * structure can be handled by kfree_rcu()?
 */
#define __is_kfree_rcu_offset(offset) ((offset) < 4096)

/*
 * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
 */
#define __kfree_rcu(head, offset) \
	do { \
		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
P
Paul E. McKenney 已提交
977
		kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
978 979
	} while (0)

L
Lai Jiangshan 已提交
980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001
/**
 * kfree_rcu() - kfree an object after a grace period.
 * @ptr:	pointer to kfree
 * @rcu_head:	the name of the struct rcu_head within the type of @ptr.
 *
 * Many rcu callbacks functions just call kfree() on the base structure.
 * These functions are trivial, but their size adds up, and furthermore
 * when they are used in a kernel module, that module must invoke the
 * high-latency rcu_barrier() function at module-unload time.
 *
 * The kfree_rcu() function handles this issue.  Rather than encoding a
 * function address in the embedded rcu_head structure, kfree_rcu() instead
 * encodes the offset of the rcu_head structure within the base structure.
 * Because the functions are not allowed in the low-order 4096 bytes of
 * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
 * If the offset is larger than 4095 bytes, a compile-time error will
 * be generated in __kfree_rcu().  If this error is triggered, you can
 * either fall back to use of call_rcu() or rearrange the structure to
 * position the rcu_head structure into the first 4096 bytes.
 *
 * Note that the allowable offset might decrease in the future, for example,
 * to allow something like kmem_cache_free_rcu().
1002 1003 1004
 *
 * The BUILD_BUG_ON check must not involve any function calls, hence the
 * checks are done in macros here.
L
Lai Jiangshan 已提交
1005 1006 1007 1008
 */
#define kfree_rcu(ptr, rcu_head)					\
	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))

1009
#ifdef CONFIG_RCU_NOCB_CPU
1010
bool rcu_is_nocb_cpu(int cpu);
1011 1012 1013 1014 1015
#else
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */


1016 1017
/* Only for use by adaptive-ticks code. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
1018 1019
bool rcu_sys_is_idle(void);
void rcu_sysidle_force_exit(void);
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */

static inline bool rcu_sys_is_idle(void)
{
	return false;
}

static inline void rcu_sysidle_force_exit(void)
{
}

#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */


L
Linus Torvalds 已提交
1034
#endif /* __LINUX_RCUPDATE_H */