Doug / smarc-fsl-linux-kernel | Embedian Git Server

Commit 851a67b825540a8e00c0be3ee25e4627ba8b133b

Authored by Peter Zijlstra 2007-10-12 04:11:12 +0800

lockdep: annotate rcu_read_{,un}lock{,_bh}

lockdep annotate rcu_read_{,un}lock{,_bh} in order to catch imbalanced
usage.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Showing 3 changed files with 29 additions and 0 deletions Inline Diff

include/linux/lockdep.h
include/linux/rcupdate.h
kernel/rcupdate.c

include/linux/lockdep.h

Diff comments View file @ 851a67b

 /*
  * Runtime locking correctness validator
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *
  * see Documentation/lockdep-design.txt for more details.
  */
 #ifndef __LINUX_LOCKDEP_H
 #define __LINUX_LOCKDEP_H
 struct task_struct;
 struct lockdep_map;
 #ifdef CONFIG_LOCKDEP
 #include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/debug_locks.h>
 #include <linux/stacktrace.h>
 /*
  * Lock-class usage-state bits:
  */
 enum lock_usage_bit
 {
 	LOCK_USED = 0,
 	LOCK_USED_IN_HARDIRQ,
 	LOCK_USED_IN_SOFTIRQ,
 	LOCK_ENABLED_SOFTIRQS,
 	LOCK_ENABLED_HARDIRQS,
 	LOCK_USED_IN_HARDIRQ_READ,
 	LOCK_USED_IN_SOFTIRQ_READ,
 	LOCK_ENABLED_SOFTIRQS_READ,
 	LOCK_ENABLED_HARDIRQS_READ,
 	LOCK_USAGE_STATES
 };
 /*
  * Usage-state bitmasks:
  */
 #define LOCKF_USED			(1 << LOCK_USED)
 #define LOCKF_USED_IN_HARDIRQ		(1 << LOCK_USED_IN_HARDIRQ)
 #define LOCKF_USED_IN_SOFTIRQ		(1 << LOCK_USED_IN_SOFTIRQ)
 #define LOCKF_ENABLED_HARDIRQS		(1 << LOCK_ENABLED_HARDIRQS)
 #define LOCKF_ENABLED_SOFTIRQS		(1 << LOCK_ENABLED_SOFTIRQS)
 #define LOCKF_ENABLED_IRQS (LOCKF_ENABLED_HARDIRQS | LOCKF_ENABLED_SOFTIRQS)
 #define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
 #define LOCKF_USED_IN_HARDIRQ_READ	(1 << LOCK_USED_IN_HARDIRQ_READ)
 #define LOCKF_USED_IN_SOFTIRQ_READ	(1 << LOCK_USED_IN_SOFTIRQ_READ)
 #define LOCKF_ENABLED_HARDIRQS_READ	(1 << LOCK_ENABLED_HARDIRQS_READ)
 #define LOCKF_ENABLED_SOFTIRQS_READ	(1 << LOCK_ENABLED_SOFTIRQS_READ)
 #define LOCKF_ENABLED_IRQS_READ \
 		(LOCKF_ENABLED_HARDIRQS_READ | LOCKF_ENABLED_SOFTIRQS_READ)
 #define LOCKF_USED_IN_IRQ_READ \
 		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
 #define MAX_LOCKDEP_SUBCLASSES		8UL
 /*
  * Lock-classes are keyed via unique addresses, by embedding the
  * lockclass-key into the kernel (or module) .data section. (For
  * static locks we use the lock address itself as the key.)
  */
 struct lockdep_subclass_key {
 	char __one_byte;
 } __attribute__ ((__packed__));
 struct lock_class_key {
 	struct lockdep_subclass_key	subkeys[MAX_LOCKDEP_SUBCLASSES];
 };
 /*
  * The lock-class itself:
  */
 struct lock_class {
 	/*
 	 * class-hash:
 	 */
 	struct list_head		hash_entry;
 	/*
 	 * global list of all lock-classes:
 	 */
 	struct list_head		lock_entry;
 	struct lockdep_subclass_key	*key;
 	unsigned int			subclass;
 	/*
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
 	struct stack_trace		usage_traces[LOCK_USAGE_STATES];
 	/*
 	 * These fields represent a directed graph of lock dependencies,
 	 * to every node we attach a list of "forward" and a list of
 	 * "backward" graph nodes.
 	 */
 	struct list_head		locks_after, locks_before;
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
 	 * to ensure that we check one node only once:
 	 */
 	unsigned int			version;
 	/*
 	 * Statistics counter:
 	 */
 	unsigned long			ops;
 	const char			*name;
 	int				name_version;
 #ifdef CONFIG_LOCK_STAT
 	unsigned long			contention_point[4];
 #endif
 };
 #ifdef CONFIG_LOCK_STAT
 struct lock_time {
 	s64				min;
 	s64				max;
 	s64				total;
 	unsigned long			nr;
 };
 enum bounce_type {
 	bounce_acquired_write,
 	bounce_acquired_read,
 	bounce_contended_write,
 	bounce_contended_read,
 	nr_bounce_types,
 	bounce_acquired = bounce_acquired_write,
 	bounce_contended = bounce_contended_write,
 };
 struct lock_class_stats {
 	unsigned long			contention_point[4];
 	struct lock_time		read_waittime;
 	struct lock_time		write_waittime;
 	struct lock_time		read_holdtime;
 	struct lock_time		write_holdtime;
 	unsigned long			bounces[nr_bounce_types];
 };
 struct lock_class_stats lock_stats(struct lock_class *class);
 void clear_lock_stats(struct lock_class *class);
 #endif
 /*
  * Map the lock object (the lock instance) to the lock-class object.
  * This is embedded into specific lock instances:
  */
 struct lockdep_map {
 	struct lock_class_key		*key;
 	struct lock_class		*class_cache;
 	const char			*name;
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
 #endif
 };
 /*
  * Every lock has a list of other locks that were taken after it.
  * We only grow the list, never remove from it:
  */
 struct lock_list {
 	struct list_head		entry;
 	struct lock_class		*class;
 	struct stack_trace		trace;
 	int				distance;
 };
 /*
  * We record lock dependency chains, so that we can cache them:
  */
 struct lock_chain {
 	struct list_head		entry;
 	u64				chain_key;
 };
 struct held_lock {
 	/*
 	 * One-way hash of the dependency chain up to this point. We
 	 * hash the hashes step by step as the dependency chain grows.
 	 *
 	 * We use it for dependency-caching and we skip detection
 	 * passes and dependency-updates if there is a cache-hit, so
 	 * it is absolutely critical for 100% coverage of the validator
 	 * to have a unique key value for every unique dependency path
 	 * that can occur in the system, to make a unique hash value
 	 * as likely as possible - hence the 64-bit width.
 	 *
 	 * The task struct holds the current hash value (initialized
 	 * with zero), here we store the previous hash value:
 	 */
 	u64				prev_chain_key;
 	struct lock_class		*class;
 	unsigned long			acquire_ip;
 	struct lockdep_map		*instance;
 #ifdef CONFIG_LOCK_STAT
 	u64 				waittime_stamp;
 	u64				holdtime_stamp;
 #endif
 	/*
 	 * The lock-stack is unified in that the lock chains of interrupt
 	 * contexts nest ontop of process context chains, but we 'separate'
 	 * the hashes by starting with 0 if we cross into an interrupt
 	 * context, and we also keep do not add cross-context lock
 	 * dependencies - the lock usage graph walking covers that area
 	 * anyway, and we'd just unnecessarily increase the number of
 	 * dependencies otherwise. [Note: hardirq and softirq contexts
 	 * are separated from each other too.]
 	 *
 	 * The following field is used to detect when we cross into an
 	 * interrupt context:
 	 */
 	int				irq_context;
 	int				trylock;
 	int				read;
 	int				check;
 	int				hardirqs_off;
 };
 /*
  * Initialization, self-test and debugging-output methods:
  */
 extern void lockdep_init(void);
 extern void lockdep_info(void);
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);
 extern void lockdep_free_key_range(void *start, unsigned long size);
 extern void lockdep_sys_exit(void);
 extern void lockdep_off(void);
 extern void lockdep_on(void);
 /*
  * These methods are used by specific locking variants (spinlocks,
  * rwlocks, mutexes and rwsems) to pass init/acquire/release events
  * to lockdep:
  */
 extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
 			     struct lock_class_key *key, int subclass);
 /*
+ * To initialize a lockdep_map statically use this macro.
+ * Note that _name must not be NULL.
+ */
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), }
+/*
  * Reinitialize a lock key - for cases where there is special locking or
  * special initialization of locks so that the validator gets the scope
  * of dependencies wrong: they are either too broad (they need a class-split)
  * or they are too narrow (they suffer from a false class-split):
  */
 #define lockdep_set_class(lock, key) \
 		lockdep_init_map(&(lock)->dep_map, #key, key, 0)
 #define lockdep_set_class_and_name(lock, key, name) \
 		lockdep_init_map(&(lock)->dep_map, name, key, 0)
 #define lockdep_set_class_and_subclass(lock, key, sub) \
 		lockdep_init_map(&(lock)->dep_map, #key, key, sub)
 #define lockdep_set_subclass(lock, sub)	\
 		lockdep_init_map(&(lock)->dep_map, #lock, \
 				 (lock)->dep_map.key, sub)
 /*
  * Acquire a lock.
  *
  * Values for "read":
  *
  *   0: exclusive (write) acquire
  *   1: read-acquire (no recursion allowed)
  *   2: read-acquire with same-instance recursion allowed
  *
  * Values for check:
  *
  *   0: disabled
  *   1: simple checks (freeing, held-at-exit-time, etc.)
  *   2: full validation
  */
 extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			 int trylock, int read, int check, unsigned long ip);
 extern void lock_release(struct lockdep_map *lock, int nested,
 			 unsigned long ip);
 # define INIT_LOCKDEP				.lockdep_recursion = 0,
 #define lockdep_depth(tsk)	(debug_locks ? (tsk)->lockdep_depth : 0)
 #else /* !LOCKDEP */
 static inline void lockdep_off(void)
 {
 }
 static inline void lockdep_on(void)
 {
 }
 # define lock_acquire(l, s, t, r, c, i)		do { } while (0)
 # define lock_release(l, n, i)			do { } while (0)
 # define lockdep_init()				do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub)	do { (void)(key); } while (0)
 # define lockdep_set_class(lock, key)		do { (void)(key); } while (0)
 # define lockdep_set_class_and_name(lock, key, name) \
 		do { (void)(key); } while (0)
 #define lockdep_set_class_and_subclass(lock, key, sub) \
 		do { (void)(key); } while (0)
 #define lockdep_set_subclass(lock, sub)		do { } while (0)
 # define INIT_LOCKDEP
 # define lockdep_reset()		do { debug_locks = 1; } while (0)
 # define lockdep_free_key_range(start, size)	do { } while (0)
 # define lockdep_sys_exit() 			do { } while (0)
 /*
  * The class key takes no space if lockdep is disabled:
  */
 struct lock_class_key { };
 #define lockdep_depth(tsk)	(0)
 #endif /* !LOCKDEP */
 #ifdef CONFIG_LOCK_STAT
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
 extern void lock_acquired(struct lockdep_map *lock);
 #define LOCK_CONTENDED(_lock, try, lock)			\
 do {								\
 	if (!try(_lock)) {					\
 		lock_contended(&(_lock)->dep_map, _RET_IP_);	\
 		lock(_lock);					\
 	}							\
 	lock_acquired(&(_lock)->dep_map);			\
 } while (0)
 #else /* CONFIG_LOCK_STAT */
 #define lock_contended(lockdep_map, ip) do {} while (0)
 #define lock_acquired(lockdep_map) do {} while (0)
 #define LOCK_CONTENDED(_lock, try, lock) \
 	lock(_lock)
 #endif /* CONFIG_LOCK_STAT */
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_GENERIC_HARDIRQS)
 extern void early_init_irq_lock_class(void);
 #else
 static inline void early_init_irq_lock_class(void)
 {
 }
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void early_boot_irqs_off(void);
 extern void early_boot_irqs_on(void);
 extern void print_irqtrace_events(struct task_struct *curr);
 #else
 static inline void early_boot_irqs_off(void)
 {
 }
 static inline void early_boot_irqs_on(void)
 {
 }
 static inline void print_irqtrace_events(struct task_struct *curr)
 {
 }
 #endif
 /*
  * For trivial one-depth nesting of a lock-class, the following
  * global define can be used. (Subsystems with multiple levels
  * of nesting should define their own lock-nesting subclasses.)
  */
 #define SINGLE_DEPTH_NESTING			1
 /*
  * Map the dependency ops to NOP or to real lockdep ops, depending
  * on the per lock-class debug mode:
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define spin_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, i)
 # else
 #  define spin_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, i)
 # endif
 # define spin_release(l, n, i)			lock_release(l, n, i)
 #else
 # define spin_acquire(l, s, t, i)		do { } while (0)
 # define spin_release(l, n, i)			do { } while (0)
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define rwlock_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, i)
 #  define rwlock_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 2, 2, i)
 # else
 #  define rwlock_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, i)
 #  define rwlock_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 2, 1, i)
 # endif
 # define rwlock_release(l, n, i)		lock_release(l, n, i)
 #else
 # define rwlock_acquire(l, s, t, i)		do { } while (0)
 # define rwlock_acquire_read(l, s, t, i)	do { } while (0)
 # define rwlock_release(l, n, i)		do { } while (0)
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define mutex_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, i)
 # else
 #  define mutex_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, i)
 # endif
 # define mutex_release(l, n, i)			lock_release(l, n, i)
 #else
 # define mutex_acquire(l, s, t, i)		do { } while (0)
 # define mutex_release(l, n, i)			do { } while (0)
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 2, i)
 # else
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 1, i)
 # endif
 # define rwsem_release(l, n, i)			lock_release(l, n, i)
 #else
 # define rwsem_acquire(l, s, t, i)		do { } while (0)
 # define rwsem_acquire_read(l, s, t, i)		do { } while (0)
 # define rwsem_release(l, n, i)			do { } while (0)
 #endif
 #endif /* __LINUX_LOCKDEP_H */

include/linux/rcupdate.h

Diff comments View file @ 851a67b

 /*
  * Read-Copy Update mechanism for mutual exclusion
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2001
  *
  * Author: Dipankar Sarma <dipankar@in.ibm.com>
  *
  * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
  * Papers:
  * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
  * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		http://lse.sourceforge.net/locking/rcupdate.html
  *
  */
 #ifndef __LINUX_RCUPDATE_H
 #define __LINUX_RCUPDATE_H
 #ifdef __KERNEL__
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
+#include <linux/lockdep.h>
 /**
  * struct rcu_head - callback structure for use with RCU
  * @next: next update requests in a list
  * @func: actual update function to call after the grace period.
  */
 struct rcu_head {
 	struct rcu_head *next;
 	void (*func)(struct rcu_head *head);
 };
 #define RCU_HEAD_INIT 	{ .next = NULL, .func = NULL }
 #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
 #define INIT_RCU_HEAD(ptr) do { \
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 /* Global control variables for rcupdate callback mechanism. */
 struct rcu_ctrlblk {
 	long	cur;		/* Current batch number.                      */
 	long	completed;	/* Number of the last completed batch         */
 	int	next_pending;	/* Is the next batch already waiting?         */
 	int	signaled;
 	spinlock_t	lock	____cacheline_internodealigned_in_smp;
 	cpumask_t	cpumask; /* CPUs that need to switch in order    */
 	                         /* for current batch to proceed.        */
 } ____cacheline_internodealigned_in_smp;
 /* Is batch a before batch b ? */
 static inline int rcu_batch_before(long a, long b)
 {
         return (a - b) < 0;
 }
 /* Is batch a after batch b ? */
 static inline int rcu_batch_after(long a, long b)
 {
         return (a - b) > 0;
 }
 /*
  * Per-CPU data for Read-Copy UPdate.
  * nxtlist - new callbacks are added here
  * curlist - current batch for which quiescent cycle started if any
  */
 struct rcu_data {
 	/* 1) quiescent state handling : */
 	long		quiescbatch;     /* Batch # for grace period */
 	int		passed_quiesc;	 /* User-mode/idle loop etc. */
 	int		qs_pending;	 /* core waits for quiesc state */
 	/* 2) batch handling */
 	long  	       	batch;           /* Batch # for current RCU batch */
 	struct rcu_head *nxtlist;
 	struct rcu_head **nxttail;
 	long            qlen; 	 	 /* # of queued callbacks */
 	struct rcu_head *curlist;
 	struct rcu_head **curtail;
 	struct rcu_head *donelist;
 	struct rcu_head **donetail;
 	long		blimit;		 /* Upper limit on a processed batch */
 	int cpu;
 	struct rcu_head barrier;
 };
 DECLARE_PER_CPU(struct rcu_data, rcu_data);
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 /*
  * Increment the quiescent state counter.
  * The counter is a bit degenerated: We do not need to know
  * how many quiescent states passed, just if there was at least
  * one since the start of the grace period. Thus just a flag.
  */
 static inline void rcu_qsctr_inc(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 	rdp->passed_quiesc = 1;
 }
 static inline void rcu_bh_qsctr_inc(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 	rdp->passed_quiesc = 1;
 }
 extern int rcu_pending(int cpu);
 extern int rcu_needs_cpu(int cpu);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern struct lockdep_map rcu_lock_map;
+# define rcu_read_acquire()	lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_)
+# define rcu_read_release()	lock_release(&rcu_lock_map, 1, _THIS_IP_)
+#else
+# define rcu_read_acquire()	do { } while (0)
+# define rcu_read_release()	do { } while (0)
+#endif
 /**
  * rcu_read_lock - mark the beginning of an RCU read-side critical section.
  *
  * When synchronize_rcu() is invoked on one CPU while other CPUs
  * are within RCU read-side critical sections, then the
  * synchronize_rcu() is guaranteed to block until after all the other
  * 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
  * with RCU read-side critical sections.  One way that this can happen
  * 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.
  *
  * It is illegal to block while in an RCU read-side critical section.
  */
 #define rcu_read_lock() \
 	do { \
 		preempt_disable(); \
 		__acquire(RCU); \
+		rcu_read_acquire(); \
 	} while(0)
 /**
  * rcu_read_unlock - marks the end of an RCU read-side critical section.
  *
  * See rcu_read_lock() for more information.
  */
 #define rcu_read_unlock() \
 	do { \
+		rcu_read_release(); \
 		__release(RCU); \
 		preempt_enable(); \
 	} while(0)
 /*
  * 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.
  */
 /**
  * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
  *
  * This is equivalent of rcu_read_lock(), but to be used when updates
  * are being done using call_rcu_bh(). Since call_rcu_bh() callbacks
  * 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().
  *
  */
 #define rcu_read_lock_bh() \
 	do { \
 		local_bh_disable(); \
 		__acquire(RCU_BH); \
+		rcu_read_acquire(); \
 	} while(0)
 /*
  * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
  *
  * See rcu_read_lock_bh() for more information.
  */
 #define rcu_read_unlock_bh() \
 	do { \
+		rcu_read_release(); \
 		__release(RCU_BH); \
 		local_bh_enable(); \
 	} while(0)
 /**
  * rcu_dereference - fetch an RCU-protected pointer in an
  * RCU read-side critical section.  This pointer may later
  * be safely dereferenced.
  *
  * Inserts memory barriers on architectures that require them
  * (currently only the Alpha), and, more importantly, documents
  * exactly which pointers are protected by RCU.
  */
 #define rcu_dereference(p)     ({ \
 				typeof(p) _________p1 = p; \
 				smp_read_barrier_depends(); \
 				(_________p1); \
 				})
 /**
  * rcu_assign_pointer - assign (publicize) a pointer to a newly
  * initialized structure that will be dereferenced by RCU read-side
  * critical sections.  Returns the value assigned.
  *
  * Inserts memory barriers on architectures that require them
  * (pretty much all of them other than x86), 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.
  */
 #define rcu_assign_pointer(p, v)	({ \
 						smp_wmb(); \
 						(p) = (v); \
 					})
 /**
  * synchronize_sched - block until all CPUs have exited any non-preemptive
  * kernel code sequences.
  *
  * This means that all preempt_disable code sequences, including NMI and
  * hardware-interrupt handlers, in progress on entry will have completed
  * before this primitive returns.  However, this does not guarantee that
  * softirq handlers will have completed, since in some kernels, these
  * handlers can run in process context, and can block.
  *
  * This primitive provides the guarantees made by the (now removed)
  * synchronize_kernel() API.  In contrast, synchronize_rcu() only
  * guarantees that rcu_read_lock() sections will have completed.
  * In "classic RCU", these two guarantees happen to be one and
  * the same, but can differ in realtime RCU implementations.
  */
 #define synchronize_sched() synchronize_rcu()
 extern void rcu_init(void);
 extern void rcu_check_callbacks(int cpu, int user);
 extern void rcu_restart_cpu(int cpu);
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
 /* Exported interfaces */
 extern void FASTCALL(call_rcu(struct rcu_head *head,
 				void (*func)(struct rcu_head *head)));
 extern void FASTCALL(call_rcu_bh(struct rcu_head *head,
 				void (*func)(struct rcu_head *head)));
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
 #endif /* __KERNEL__ */
 #endif /* __LINUX_RCUPDATE_H */

kernel/rcupdate.c

Diff comments View file @ 851a67b

 /*
  * Read-Copy Update mechanism for mutual exclusion
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2001
  *
  * Authors: Dipankar Sarma <dipankar@in.ibm.com>
  *	    Manfred Spraul <manfred@colorfullife.com>
  *
  * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
  * Papers:
  * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
  * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		http://lse.sourceforge.net/locking/rcupdate.html
  *
  */
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/rcupdate.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
+#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);
+#endif
 /* Definition for rcupdate control block. */
 static struct rcu_ctrlblk rcu_ctrlblk = {
 	.cur = -300,
 	.completed = -300,
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
 	.cpumask = CPU_MASK_NONE,
 };
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cur = -300,
 	.completed = -300,
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
 	.cpumask = CPU_MASK_NONE,
 };
 DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 /* Fake initialization required by compiler */
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
 static int blimit = 10;
 static int qhimark = 10000;
 static int qlowmark = 100;
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
 #ifdef CONFIG_SMP
 static void force_quiescent_state(struct rcu_data *rdp,
 			struct rcu_ctrlblk *rcp)
 {
 	int cpu;
 	cpumask_t cpumask;
 	set_need_resched();
 	if (unlikely(!rcp->signaled)) {
 		rcp->signaled = 1;
 		/*
 		 * Don't send IPI to itself. With irqs disabled,
 		 * rdp->cpu is the current cpu.
 		 */
 		cpumask = rcp->cpumask;
 		cpu_clear(rdp->cpu, cpumask);
 		for_each_cpu_mask(cpu, cpumask)
 			smp_send_reschedule(cpu);
 	}
 }
 #else
 static inline void force_quiescent_state(struct rcu_data *rdp,
 			struct rcu_ctrlblk *rcp)
 {
 	set_need_resched();
 }
 #endif
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
  * @func: actual update function to be invoked after the grace period
  *
  * The update 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.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
 void fastcall call_rcu(struct rcu_head *head,
 				void (*func)(struct rcu_head *rcu))
 {
 	unsigned long flags;
 	struct rcu_data *rdp;
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
 	rdp = &__get_cpu_var(rcu_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
 	if (unlikely(++rdp->qlen > qhimark)) {
 		rdp->blimit = INT_MAX;
 		force_quiescent_state(rdp, &rcu_ctrlblk);
 	}
 	local_irq_restore(flags);
 }
 /**
  * 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 update function to be invoked after the grace period
  *
  * The update 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.
  */
 void fastcall call_rcu_bh(struct rcu_head *head,
 				void (*func)(struct rcu_head *rcu))
 {
 	unsigned long flags;
 	struct rcu_data *rdp;
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
 	rdp = &__get_cpu_var(rcu_bh_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
 	if (unlikely(++rdp->qlen > qhimark)) {
 		rdp->blimit = INT_MAX;
 		force_quiescent_state(rdp, &rcu_bh_ctrlblk);
 	}
 	local_irq_restore(flags);
 }
 /*
  * Return the number of RCU batches processed thus far.  Useful
  * for debug and statistics.
  */
 long rcu_batches_completed(void)
 {
 	return rcu_ctrlblk.completed;
 }
 /*
  * Return the number of RCU batches processed thus far.  Useful
  * for debug and statistics.
  */
 long rcu_batches_completed_bh(void)
 {
 	return rcu_bh_ctrlblk.completed;
 }
 static void rcu_barrier_callback(struct rcu_head *notused)
 {
 	if (atomic_dec_and_test(&rcu_barrier_cpu_count))
 		complete(&rcu_barrier_completion);
 }
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
 static void rcu_barrier_func(void *notused)
 {
 	int cpu = smp_processor_id();
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 	struct rcu_head *head;
 	head = &rdp->barrier;
 	atomic_inc(&rcu_barrier_cpu_count);
 	call_rcu(head, rcu_barrier_callback);
 }
 /**
  * rcu_barrier - Wait until all the in-flight RCUs are complete.
  */
 void rcu_barrier(void)
 {
 	BUG_ON(in_interrupt());
 	/* Take cpucontrol mutex to protect against CPU hotplug */
 	mutex_lock(&rcu_barrier_mutex);
 	init_completion(&rcu_barrier_completion);
 	atomic_set(&rcu_barrier_cpu_count, 0);
 	on_each_cpu(rcu_barrier_func, NULL, 0, 1);
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 /*
  * Invoke the completed RCU callbacks. They are expected to be in
  * a per-cpu list.
  */
 static void rcu_do_batch(struct rcu_data *rdp)
 {
 	struct rcu_head *next, *list;
 	int count = 0;
 	list = rdp->donelist;
 	while (list) {
 		next = list->next;
 		prefetch(next);
 		list->func(list);
 		list = next;
 		if (++count >= rdp->blimit)
 			break;
 	}
 	rdp->donelist = list;
 	local_irq_disable();
 	rdp->qlen -= count;
 	local_irq_enable();
 	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
 		rdp->blimit = blimit;
 	if (!rdp->donelist)
 		rdp->donetail = &rdp->donelist;
 	else
 		tasklet_schedule(&per_cpu(rcu_tasklet, rdp->cpu));
 }
 /*
  * Grace period handling:
  * The grace period handling consists out of two steps:
  * - A new grace period is started.
  *   This is done by rcu_start_batch. The start is not broadcasted to
  *   all cpus, they must pick this up by comparing rcp->cur with
  *   rdp->quiescbatch. All cpus are recorded  in the
  *   rcu_ctrlblk.cpumask bitmap.
  * - All cpus must go through a quiescent state.
  *   Since the start of the grace period is not broadcasted, at least two
  *   calls to rcu_check_quiescent_state are required:
  *   The first call just notices that a new grace period is running. The
  *   following calls check if there was a quiescent state since the beginning
  *   of the grace period. If so, it updates rcu_ctrlblk.cpumask. If
  *   the bitmap is empty, then the grace period is completed.
  *   rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace
  *   period (if necessary).
  */
 /*
  * Register a new batch of callbacks, and start it up if there is currently no
  * active batch and the batch to be registered has not already occurred.
  * Caller must hold rcu_ctrlblk.lock.
  */
 static void rcu_start_batch(struct rcu_ctrlblk *rcp)
 {
 	if (rcp->next_pending &&
 			rcp->completed == rcp->cur) {
 		rcp->next_pending = 0;
 		/*
 		 * next_pending == 0 must be visible in
 		 * __rcu_process_callbacks() before it can see new value of cur.
 		 */
 		smp_wmb();
 		rcp->cur++;
 		/*
 		 * Accessing nohz_cpu_mask before incrementing rcp->cur needs a
 		 * Barrier  Otherwise it can cause tickless idle CPUs to be
 		 * included in rcp->cpumask, which will extend graceperiods
 		 * unnecessarily.
 		 */
 		smp_mb();
 		cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask);
 		rcp->signaled = 0;
 	}
 }
 /*
  * cpu went through a quiescent state since the beginning of the grace period.
  * Clear it from the cpu mask and complete the grace period if it was the last
  * cpu. Start another grace period if someone has further entries pending
  */
 static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
 {
 	cpu_clear(cpu, rcp->cpumask);
 	if (cpus_empty(rcp->cpumask)) {
 		/* batch completed ! */
 		rcp->completed = rcp->cur;
 		rcu_start_batch(rcp);
 	}
 }
 /*
  * Check if the cpu has gone through a quiescent state (say context
  * switch). If so and if it already hasn't done so in this RCU
  * quiescent cycle, then indicate that it has done so.
  */
 static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
 					struct rcu_data *rdp)
 {
 	if (rdp->quiescbatch != rcp->cur) {
 		/* start new grace period: */
 		rdp->qs_pending = 1;
 		rdp->passed_quiesc = 0;
 		rdp->quiescbatch = rcp->cur;
 		return;
 	}
 	/* Grace period already completed for this cpu?
 	 * qs_pending is checked instead of the actual bitmap to avoid
 	 * cacheline trashing.
 	 */
 	if (!rdp->qs_pending)
 		return;
 	/*
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
 	if (!rdp->passed_quiesc)
 		return;
 	rdp->qs_pending = 0;
 	spin_lock(&rcp->lock);
 	/*
 	 * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
 	 * during cpu startup. Ignore the quiescent state.
 	 */
 	if (likely(rdp->quiescbatch == rcp->cur))
 		cpu_quiet(rdp->cpu, rcp);
 	spin_unlock(&rcp->lock);
 }
 #ifdef CONFIG_HOTPLUG_CPU
 /* warning! helper for rcu_offline_cpu. do not use elsewhere without reviewing
  * locking requirements, the list it's pulling from has to belong to a cpu
  * which is dead and hence not processing interrupts.
  */
 static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
 				struct rcu_head **tail)
 {
 	local_irq_disable();
 	*this_rdp->nxttail = list;
 	if (list)
 		this_rdp->nxttail = tail;
 	local_irq_enable();
 }
 static void __rcu_offline_cpu(struct rcu_data *this_rdp,
 				struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
 {
 	/* if the cpu going offline owns the grace period
 	 * we can block indefinitely waiting for it, so flush
 	 * it here
 	 */
 	spin_lock_bh(&rcp->lock);
 	if (rcp->cur != rcp->completed)
 		cpu_quiet(rdp->cpu, rcp);
 	spin_unlock_bh(&rcp->lock);
 	rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
 	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);
 	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
 }
 static void rcu_offline_cpu(int cpu)
 {
 	struct rcu_data *this_rdp = &get_cpu_var(rcu_data);
 	struct rcu_data *this_bh_rdp = &get_cpu_var(rcu_bh_data);
 	__rcu_offline_cpu(this_rdp, &rcu_ctrlblk,
 					&per_cpu(rcu_data, cpu));
 	__rcu_offline_cpu(this_bh_rdp, &rcu_bh_ctrlblk,
 					&per_cpu(rcu_bh_data, cpu));
 	put_cpu_var(rcu_data);
 	put_cpu_var(rcu_bh_data);
 	tasklet_kill_immediate(&per_cpu(rcu_tasklet, cpu), cpu);
 }
 #else
 static void rcu_offline_cpu(int cpu)
 {
 }
 #endif
 /*
  * This does the RCU processing work from tasklet context.
  */
 static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
 					struct rcu_data *rdp)
 {
 	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) {
 		*rdp->donetail = rdp->curlist;
 		rdp->donetail = rdp->curtail;
 		rdp->curlist = NULL;
 		rdp->curtail = &rdp->curlist;
 	}
 	if (rdp->nxtlist && !rdp->curlist) {
 		local_irq_disable();
 		rdp->curlist = rdp->nxtlist;
 		rdp->curtail = rdp->nxttail;
 		rdp->nxtlist = NULL;
 		rdp->nxttail = &rdp->nxtlist;
 		local_irq_enable();
 		/*
 		 * start the next batch of callbacks
 		 */
 		/* determine batch number */
 		rdp->batch = rcp->cur + 1;
 		/* see the comment and corresponding wmb() in
 		 * the rcu_start_batch()
 		 */
 		smp_rmb();
 		if (!rcp->next_pending) {
 			/* and start it/schedule start if it's a new batch */
 			spin_lock(&rcp->lock);
 			rcp->next_pending = 1;
 			rcu_start_batch(rcp);
 			spin_unlock(&rcp->lock);
 		}
 	}
 	rcu_check_quiescent_state(rcp, rdp);
 	if (rdp->donelist)
 		rcu_do_batch(rdp);
 }
 static void rcu_process_callbacks(unsigned long unused)
 {
 	__rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
 	__rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
 }
 static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
 {
 	/* This cpu has pending rcu entries and the grace period
 	 * for them has completed.
 	 */
 	if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
 		return 1;
 	/* This cpu has no pending entries, but there are new entries */
 	if (!rdp->curlist && rdp->nxtlist)
 		return 1;
 	/* This cpu has finished callbacks to invoke */
 	if (rdp->donelist)
 		return 1;
 	/* The rcu core waits for a quiescent state from the cpu */
 	if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
 		return 1;
 	/* nothing to do */
 	return 0;
 }
 /*
  * Check to see if there is any immediate RCU-related work to be done
  * by the current CPU, returning 1 if so.  This function is part of the
  * RCU implementation; it is -not- an exported member of the RCU API.
  */
 int rcu_pending(int cpu)
 {
 	return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
 		__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
 }
 /*
  * Check to see if any future RCU-related work will need to be done
  * by the current CPU, even if none need be done immediately, returning
  * 1 if so.  This function is part of the RCU implementation; it is -not-
  * an exported member of the RCU API.
  */
 int rcu_needs_cpu(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 	struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
 	return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
 }
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
 	    (idle_cpu(cpu) && !in_softirq() &&
 				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 		rcu_qsctr_inc(cpu);
 		rcu_bh_qsctr_inc(cpu);
 	} else if (!in_softirq())
 		rcu_bh_qsctr_inc(cpu);
 	tasklet_schedule(&per_cpu(rcu_tasklet, cpu));
 }
 static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 						struct rcu_data *rdp)
 {
 	memset(rdp, 0, sizeof(*rdp));
 	rdp->curtail = &rdp->curlist;
 	rdp->nxttail = &rdp->nxtlist;
 	rdp->donetail = &rdp->donelist;
 	rdp->quiescbatch = rcp->completed;
 	rdp->qs_pending = 0;
 	rdp->cpu = cpu;
 	rdp->blimit = blimit;
 }
 static void __devinit rcu_online_cpu(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 	struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu);
 	rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
 	rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
 	tasklet_init(&per_cpu(rcu_tasklet, cpu), rcu_process_callbacks, 0UL);
 }
 static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		rcu_online_cpu(cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		rcu_offline_cpu(cpu);
 		break;
 	default:
 		break;
 	}
 	return NOTIFY_OK;
 }
 static struct notifier_block __cpuinitdata rcu_nb = {
 	.notifier_call	= rcu_cpu_notify,
 };
 /*
  * Initializes rcu mechanism.  Assumed to be called early.
  * That is before local timer(SMP) or jiffie timer (uniproc) is setup.
  * Note that rcu_qsctr and friends are implicitly
  * initialized due to the choice of ``0'' for RCU_CTR_INVALID.
  */
 void __init rcu_init(void)
 {
 	rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
 			(void *)(long)smp_processor_id());
 	/* Register notifier for non-boot CPUs */
 	register_cpu_notifier(&rcu_nb);
 }
 struct rcu_synchronize {
 	struct rcu_head head;
 	struct completion completion;
 };
 /* Because of FASTCALL declaration of complete, we use this wrapper */
 static void wakeme_after_rcu(struct rcu_head  *head)
 {
 	struct rcu_synchronize *rcu;
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
 /**
  * synchronize_rcu - wait until a grace period has elapsed.
  *
  * Control will return to the caller some time after a full grace
  * period has elapsed, in other words after all currently executing RCU
  * read-side critical sections have completed.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  *
  * If your read-side code is not protected by rcu_read_lock(), do -not-
  * use synchronize_rcu().
  */
 void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished */
 	call_rcu(&rcu.head, wakeme_after_rcu);
 	/* Wait for it */
 	wait_for_completion(&rcu.completion);
 }
 module_param(blimit, int, 0);
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
 EXPORT_SYMBOL_GPL(call_rcu);
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 EXPORT_SYMBOL_GPL(synchronize_rcu);