rcupdate.h 42.4 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

49
extern int rcu_expedited; /* for sysctl */
D
Dave Young 已提交
50 51 52 53
#ifdef CONFIG_RCU_TORTURE_TEST
extern int rcutorture_runnable; /* for sysctl */
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */

54 55 56 57 58 59 60 61
enum rcutorture_type {
	RCU_FLAVOR,
	RCU_BH_FLAVOR,
	RCU_SCHED_FLAVOR,
	SRCU_FLAVOR,
	INVALID_RCU_FLAVOR
};

62
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
63 64
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
			    unsigned long *gpnum, unsigned long *completed);
65 66 67 68 69 70 71
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);
72
#else
73 74 75 76 77 78 79 80 81
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
					  int *flags,
					  unsigned long *gpnum,
					  unsigned long *completed)
{
	*flags = 0;
	*gpnum = 0;
	*completed = 0;
}
82 83 84 85 86 87
static inline void rcutorture_record_test_transition(void)
{
}
static inline void rcutorture_record_progress(unsigned long vernum)
{
}
88
#ifdef CONFIG_RCU_TRACE
89 90 91 92 93
void do_trace_rcu_torture_read(const char *rcutorturename,
			       struct rcu_head *rhp,
			       unsigned long secs,
			       unsigned long c_old,
			       unsigned long c);
94
#else
95 96
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
	do { } while (0)
97
#endif
98 99
#endif

100 101
#define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
#define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
102 103
#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
104
#define ulong2long(a)		(*(long *)(&(a)))
105

106
/* Exported common interfaces */
107 108 109 110 111 112 113 114 115 116 117 118 119 120 121

#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.
122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
 *
 * 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).
141
 */
142 143
void call_rcu(struct rcu_head *head,
	      void (*func)(struct rcu_head *head));
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

#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.
169 170 171
 *
 * See the description of call_rcu() for more detailed information on
 * memory ordering guarantees.
172
 */
173 174
void call_rcu_bh(struct rcu_head *head,
		 void (*func)(struct rcu_head *head));
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190

/**
 * 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.
191 192 193
 *
 * See the description of call_rcu() for more detailed information on
 * memory ordering guarantees.
194
 */
195 196
void call_rcu_sched(struct rcu_head *head,
		    void (*func)(struct rcu_head *rcu));
197

198
void synchronize_sched(void);
199

P
Paul E. McKenney 已提交
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
/**
 * call_rcu_tasks() - Queue an RCU for invocation task-based 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_tasks() assumes
 * that the read-side critical sections end at a voluntary context
 * switch (not a preemption!), entry into idle, or transition to usermode
 * execution.  As such, there are no read-side primitives analogous to
 * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
 * to determine that all tasks have passed through a safe state, not so
 * much for data-strcuture synchronization.
 *
 * See the description of call_rcu() for more detailed information on
 * memory ordering guarantees.
 */
void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head));

220 221
#ifdef CONFIG_PREEMPT_RCU

222 223 224
void __rcu_read_lock(void);
void __rcu_read_unlock(void);
void rcu_read_unlock_special(struct task_struct *t);
225 226
void synchronize_rcu(void);

227 228 229 230 231 232 233 234
/*
 * 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)

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
#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 */
260 261 262 263
void rcu_init(void);
void rcu_sched_qs(int cpu);
void rcu_bh_qs(int cpu);
void rcu_check_callbacks(int cpu, int user);
264
struct notifier_block;
265 266 267 268
void rcu_idle_enter(void);
void rcu_idle_exit(void);
void rcu_irq_enter(void);
void rcu_irq_exit(void);
269

270 271 272 273 274 275 276 277 278 279 280 281
#ifdef CONFIG_RCU_STALL_COMMON
void rcu_sysrq_start(void);
void rcu_sysrq_end(void);
#else /* #ifdef CONFIG_RCU_STALL_COMMON */
static inline void rcu_sysrq_start(void)
{
}
static inline void rcu_sysrq_end(void)
{
}
#endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */

282
#ifdef CONFIG_RCU_USER_QS
283 284
void rcu_user_enter(void);
void rcu_user_exit(void);
285 286 287
#else
static inline void rcu_user_enter(void) { }
static inline void rcu_user_exit(void) { }
F
Frederic Weisbecker 已提交
288 289
static inline void rcu_user_hooks_switch(struct task_struct *prev,
					 struct task_struct *next) { }
290 291
#endif /* CONFIG_RCU_USER_QS */

292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
/**
 * 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 { \
312
		rcu_irq_enter(); \
313
		do { a; } while (0); \
314
		rcu_irq_exit(); \
315 316
	} while (0)

P
Paul E. McKenney 已提交
317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332
/*
 * Note a voluntary context switch for RCU-tasks benefit.  This is a
 * macro rather than an inline function to avoid #include hell.
 */
#ifdef CONFIG_TASKS_RCU
#define rcu_note_voluntary_context_switch(t) \
	do { \
		preempt_disable(); /* Exclude synchronize_sched(); */ \
		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
		preempt_enable(); \
	} while (0)
#else /* #ifdef CONFIG_TASKS_RCU */
#define rcu_note_voluntary_context_switch(t)	do { } while (0)
#endif /* #else #ifdef CONFIG_TASKS_RCU */

333 334 335 336 337 338 339 340 341 342 343 344 345
/**
 * cond_resched_rcu_qs - Report potential quiescent states to RCU
 *
 * This macro resembles cond_resched(), except that it is defined to
 * report potential quiescent states to RCU-tasks even if the cond_resched()
 * machinery were to be shut off, as some advocate for PREEMPT kernels.
 */
#define cond_resched_rcu_qs() \
do { \
	rcu_note_voluntary_context_switch(current); \
	cond_resched(); \
} while (0)

346
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
347
bool __rcu_is_watching(void);
348 349
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */

350 351 352 353 354 355 356 357 358
/*
 * 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);

359
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
360
#include <linux/rcutree.h>
P
Paul E. McKenney 已提交
361
#elif defined(CONFIG_TINY_RCU)
362
#include <linux/rcutiny.h>
363 364
#else
#error "Unknown RCU implementation specified to kernel configuration"
365
#endif
366

367 368 369 370 371 372 373
/*
 * 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
374 375
void init_rcu_head(struct rcu_head *head);
void destroy_rcu_head(struct rcu_head *head);
376 377
void init_rcu_head_on_stack(struct rcu_head *head);
void destroy_rcu_head_on_stack(struct rcu_head *head);
378
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
379 380 381 382 383 384 385 386
static inline void init_rcu_head(struct rcu_head *head)
{
}

static inline void destroy_rcu_head(struct rcu_head *head)
{
}

387 388 389 390 391 392 393
static inline void init_rcu_head_on_stack(struct rcu_head *head)
{
}

static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
{
}
394
#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
395

396 397 398 399 400 401 402 403 404
#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) */

405
#ifdef CONFIG_DEBUG_LOCK_ALLOC
406

407 408
static inline void rcu_lock_acquire(struct lockdep_map *map)
{
409
	lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
410 411 412 413 414 415 416
}

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

417
extern struct lockdep_map rcu_lock_map;
418 419
extern struct lockdep_map rcu_bh_lock_map;
extern struct lockdep_map rcu_sched_lock_map;
420
extern struct lockdep_map rcu_callback_map;
421
int debug_lockdep_rcu_enabled(void);
422

423
/**
424
 * rcu_read_lock_held() - might we be in RCU read-side critical section?
425
 *
426 427
 * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
 * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
428
 * this assumes we are in an RCU read-side critical section unless it can
429 430
 * prove otherwise.  This is useful for debug checks in functions that
 * require that they be called within an RCU read-side critical section.
431
 *
432
 * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
433
 * and while lockdep is disabled.
434 435 436 437 438
 *
 * 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.
439 440 441
 *
 * 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.
442 443 444
 */
static inline int rcu_read_lock_held(void)
{
445 446
	if (!debug_lockdep_rcu_enabled())
		return 1;
447
	if (!rcu_is_watching())
448
		return 0;
449 450
	if (!rcu_lockdep_current_cpu_online())
		return 0;
451
	return lock_is_held(&rcu_lock_map);
452 453
}

454 455 456
/*
 * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
 * hell.
457
 */
458
int rcu_read_lock_bh_held(void);
459 460

/**
461
 * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
462
 *
463 464 465 466 467
 * 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
468 469 470
 * 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.
471
 *
472 473
 * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
 * and while lockdep is disabled.
474 475 476 477 478 479 480 481 482 483 484 485 486
 *
 * 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.
487 488 489
 *
 * Similarly, we avoid claiming an SRCU read lock held if the current
 * CPU is offline.
490
 */
491
#ifdef CONFIG_PREEMPT_COUNT
492 493 494 495
static inline int rcu_read_lock_sched_held(void)
{
	int lockdep_opinion = 0;

496 497
	if (!debug_lockdep_rcu_enabled())
		return 1;
498
	if (!rcu_is_watching())
499
		return 0;
500 501
	if (!rcu_lockdep_current_cpu_online())
		return 0;
502 503
	if (debug_locks)
		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
504
	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
505
}
506
#else /* #ifdef CONFIG_PREEMPT_COUNT */
507 508 509
static inline int rcu_read_lock_sched_held(void)
{
	return 1;
510
}
511
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
512 513 514

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

515 516
# define rcu_lock_acquire(a)		do { } while (0)
# define rcu_lock_release(a)		do { } while (0)
517 518 519 520 521 522 523 524 525 526 527

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

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

528
#ifdef CONFIG_PREEMPT_COUNT
529 530
static inline int rcu_read_lock_sched_held(void)
{
531
	return preempt_count() != 0 || irqs_disabled();
532
}
533
#else /* #ifdef CONFIG_PREEMPT_COUNT */
534 535 536
static inline int rcu_read_lock_sched_held(void)
{
	return 1;
537
}
538
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
539 540 541 542 543

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

#ifdef CONFIG_PROVE_RCU

544 545 546
/**
 * rcu_lockdep_assert - emit lockdep splat if specified condition not met
 * @c: condition to check
547
 * @s: informative message
548
 */
549
#define rcu_lockdep_assert(c, s)					\
550
	do {								\
551
		static bool __section(.data.unlikely) __warned;		\
552 553
		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
			__warned = true;				\
554
			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
555 556 557
		}							\
	} while (0)

558 559 560 561
#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),
562
			   "Illegal context switch in RCU read-side critical section");
563 564 565 566 567 568 569
}
#else /* #ifdef CONFIG_PROVE_RCU */
static inline void rcu_preempt_sleep_check(void)
{
}
#endif /* #else #ifdef CONFIG_PROVE_RCU */

570 571
#define rcu_sleep_check()						\
	do {								\
572
		rcu_preempt_sleep_check();				\
573
		rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),	\
J
Joe Perches 已提交
574
				   "Illegal context switch in RCU-bh read-side critical section"); \
575
		rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),	\
J
Joe Perches 已提交
576
				   "Illegal context switch in RCU-sched read-side critical section"); \
577 578
	} while (0)

579 580
#else /* #ifdef CONFIG_PROVE_RCU */

581 582
#define rcu_lockdep_assert(c, s) do { } while (0)
#define rcu_sleep_check() do { } while (0)
583 584 585 586 587 588 589 590 591 592 593

#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.
 */
594 595 596 597 598 599 600 601

#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__ */

602
#define __rcu_access_pointer(p, space) \
603 604 605 606 607
({ \
	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
	rcu_dereference_sparse(p, space); \
	((typeof(*p) __force __kernel *)(_________p1)); \
})
608
#define __rcu_dereference_check(p, c, space) \
609 610 611 612 613 614 615
({ \
	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)); \
})
616
#define __rcu_dereference_protected(p, c, space) \
617 618 619 620 621
({ \
	rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \
	rcu_dereference_sparse(p, space); \
	((typeof(*p) __force __kernel *)(p)); \
})
622

623
#define __rcu_access_index(p, space) \
624 625 626 627 628
({ \
	typeof(p) _________p1 = ACCESS_ONCE(p); \
	rcu_dereference_sparse(p, space); \
	(_________p1); \
})
629
#define __rcu_dereference_index_check(p, c) \
630 631 632 633 634 635 636
({ \
	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); \
})
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674

/**
 * 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.
 */
675
#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v))
676 677 678 679 680 681 682 683 684 685 686 687

/**
 * 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.
688 689 690 691 692 693 694
 *
 * 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.
695 696 697
 */
#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)

698
/**
699
 * rcu_dereference_check() - rcu_dereference with debug checking
700 701
 * @p: The pointer to read, prior to dereferencing
 * @c: The conditions under which the dereference will take place
702
 *
703
 * Do an rcu_dereference(), but check that the conditions under which the
704 705 706 707 708
 * 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.
709 710 711
 *
 * For example:
 *
712
 *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
713 714
 *
 * could be used to indicate to lockdep that foo->bar may only be dereferenced
715
 * if either rcu_read_lock() is held, or that the lock required to replace
716 717 718 719 720 721
 * 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:
 *
722
 *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
723
 *					      atomic_read(&foo->usage) == 0);
724 725 726 727 728 729
 *
 * 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.
730 731
 */
#define rcu_dereference_check(p, c) \
732 733 734 735 736 737 738 739 740 741 742
	__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)
743

744
/**
745 746 747 748 749 750 751 752 753 754 755 756
 * 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? @@@*/

757 758 759 760 761 762 763 764 765
/*
 * 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)

766 767 768 769 770 771 772 773 774 775 776 777 778 779
/**
 * 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)

780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804
/**
 * 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
805 806 807 808 809 810 811 812
 *
 * 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.
813 814 815 816
 *
 * 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.
817 818
 */
#define rcu_dereference_protected(p, c) \
819
	__rcu_dereference_protected((p), (c), __rcu)
820

821

822
/**
823 824
 * rcu_dereference() - fetch RCU-protected pointer for dereferencing
 * @p: The pointer to read, prior to dereferencing
825
 *
826
 * This is a simple wrapper around rcu_dereference_check().
827
 */
828
#define rcu_dereference(p) rcu_dereference_check(p, 0)
829

L
Linus Torvalds 已提交
830
/**
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847
 * 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
848
 *
849
 * When synchronize_rcu() is invoked on one CPU while other CPUs
L
Linus Torvalds 已提交
850
 * are within RCU read-side critical sections, then the
851
 * synchronize_rcu() is guaranteed to block until after all the other
L
Linus Torvalds 已提交
852 853 854 855 856 857
 * 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
858
 * with new RCU read-side critical sections.  One way that this can happen
L
Linus Torvalds 已提交
859 860 861 862 863 864 865 866 867 868 869 870 871 872
 * 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.
 *
873 874 875 876 877
 * 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!
 *
878 879 880 881 882 883 884 885
 * 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) in CONFIG_PREEMPT
 * kernel builds, RCU read-side critical sections may be preempted,
 * but explicit blocking is illegal.  Finally, in preemptible RCU
 * implementations in real-time (with -rt patchset) kernel builds, 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
886
 */
887 888 889 890
static inline void rcu_read_lock(void)
{
	__rcu_read_lock();
	__acquire(RCU);
891
	rcu_lock_acquire(&rcu_lock_map);
892
	rcu_lockdep_assert(rcu_is_watching(),
893
			   "rcu_read_lock() used illegally while idle");
894
}
L
Linus Torvalds 已提交
895 896 897 898 899 900 901 902 903 904

/*
 * 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.
 */
905 906

/**
907
 * rcu_read_unlock() - marks the end of an RCU read-side critical section.
908
 *
909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
 * In most situations, rcu_read_unlock() is immune from deadlock.
 * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock()
 * is responsible for deboosting, which it does via rt_mutex_unlock().
 * Unfortunately, this function acquires the scheduler's runqueue and
 * priority-inheritance spinlocks.  This means that deadlock could result
 * if the caller of rcu_read_unlock() already holds one of these locks or
 * any lock that is ever acquired while holding them.
 *
 * That said, RCU readers are never priority boosted unless they were
 * preempted.  Therefore, one way to avoid deadlock is to make sure
 * that preemption never happens within any RCU read-side critical
 * section whose outermost rcu_read_unlock() is called with one of
 * rt_mutex_unlock()'s locks held.  Such preemption can be avoided in
 * a number of ways, for example, by invoking preempt_disable() before
 * critical section's outermost rcu_read_lock().
 *
 * Given that the set of locks acquired by rt_mutex_unlock() might change
 * at any time, a somewhat more future-proofed approach is to make sure
 * that that preemption never happens within any RCU read-side critical
 * section whose outermost rcu_read_unlock() is called with irqs disabled.
 * This approach relies on the fact that rt_mutex_unlock() currently only
 * acquires irq-disabled locks.
 *
 * The second of these two approaches is best in most situations,
 * however, the first approach can also be useful, at least to those
 * developers willing to keep abreast of the set of locks acquired by
 * rt_mutex_unlock().
 *
937 938
 * See rcu_read_lock() for more information.
 */
939 940
static inline void rcu_read_unlock(void)
{
941
	rcu_lockdep_assert(rcu_is_watching(),
942
			   "rcu_read_unlock() used illegally while idle");
943
	rcu_lock_release(&rcu_lock_map);
944 945 946
	__release(RCU);
	__rcu_read_unlock();
}
L
Linus Torvalds 已提交
947 948

/**
949
 * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
L
Linus Torvalds 已提交
950 951
 *
 * This is equivalent of rcu_read_lock(), but to be used when updates
952 953 954 955 956 957 958
 * 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.
959 960 961 962 963
 *
 * 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
964
 */
965 966
static inline void rcu_read_lock_bh(void)
{
967
	local_bh_disable();
968
	__acquire(RCU_BH);
969
	rcu_lock_acquire(&rcu_bh_lock_map);
970
	rcu_lockdep_assert(rcu_is_watching(),
971
			   "rcu_read_lock_bh() used illegally while idle");
972
}
L
Linus Torvalds 已提交
973 974 975 976 977 978

/*
 * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
 *
 * See rcu_read_lock_bh() for more information.
 */
979 980
static inline void rcu_read_unlock_bh(void)
{
981
	rcu_lockdep_assert(rcu_is_watching(),
982
			   "rcu_read_unlock_bh() used illegally while idle");
983
	rcu_lock_release(&rcu_bh_lock_map);
984
	__release(RCU_BH);
985
	local_bh_enable();
986
}
L
Linus Torvalds 已提交
987

988
/**
989
 * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
990
 *
991 992 993 994
 * 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.
995 996 997 998 999
 *
 * 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.
1000
 */
1001 1002 1003
static inline void rcu_read_lock_sched(void)
{
	preempt_disable();
1004
	__acquire(RCU_SCHED);
1005
	rcu_lock_acquire(&rcu_sched_lock_map);
1006
	rcu_lockdep_assert(rcu_is_watching(),
1007
			   "rcu_read_lock_sched() used illegally while idle");
1008
}
1009 1010

/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
1011
static inline notrace void rcu_read_lock_sched_notrace(void)
1012 1013
{
	preempt_disable_notrace();
1014
	__acquire(RCU_SCHED);
1015
}
1016 1017 1018 1019 1020 1021

/*
 * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
 *
 * See rcu_read_lock_sched for more information.
 */
1022 1023
static inline void rcu_read_unlock_sched(void)
{
1024
	rcu_lockdep_assert(rcu_is_watching(),
1025
			   "rcu_read_unlock_sched() used illegally while idle");
1026
	rcu_lock_release(&rcu_sched_lock_map);
1027
	__release(RCU_SCHED);
1028 1029
	preempt_enable();
}
1030 1031

/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
1032
static inline notrace void rcu_read_unlock_sched_notrace(void)
1033
{
1034
	__release(RCU_SCHED);
1035 1036
	preempt_enable_notrace();
}
1037

1038 1039 1040
/**
 * RCU_INIT_POINTER() - initialize an RCU protected pointer
 *
1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068
 * 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.
1069 1070 1071
 *
 * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no
 * ordering guarantees for either the CPU or the compiler.
1072 1073
 */
#define RCU_INIT_POINTER(p, v) \
1074
	do { \
1075
		p = RCU_INITIALIZER(v); \
1076
	} while (0)
L
Lai Jiangshan 已提交
1077

1078 1079 1080 1081 1082 1083
/**
 * 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) \
1084
		.p = RCU_INITIALIZER(v)
L
Lai Jiangshan 已提交
1085

1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
/*
 * 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
1098
		kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
1099 1100
	} while (0)

L
Lai Jiangshan 已提交
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122
/**
 * 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().
1123 1124 1125
 *
 * 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
1126 1127 1128 1129
 */
#define kfree_rcu(ptr, rcu_head)					\
	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))

1130 1131 1132 1133 1134 1135 1136 1137
#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
	*delta_jiffies = ULONG_MAX;
	return 0;
}
#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */

1138 1139 1140
#if defined(CONFIG_RCU_NOCB_CPU_ALL)
static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
#elif defined(CONFIG_RCU_NOCB_CPU)
1141
bool rcu_is_nocb_cpu(int cpu);
1142 1143
#else
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
1144
#endif
1145 1146


1147 1148
/* Only for use by adaptive-ticks code. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
1149 1150
bool rcu_sys_is_idle(void);
void rcu_sysidle_force_exit(void);
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
#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
1165
#endif /* __LINUX_RCUPDATE_H */