/*
- * Read-Copy Update mechanism for mutual exclusion
+ * 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
* 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
+ * Copyright 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://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
+ * 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>
+#include <linux/completion.h>
/**
* struct rcu_head - callback structure for use with RCU
void (*func)(struct rcu_head *head);
};
-#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
+/* Exported common interfaces */
+extern void synchronize_rcu_bh(void);
+extern void synchronize_sched(void);
+extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
+extern void synchronize_sched_expedited(void);
+extern int sched_expedited_torture_stats(char *page);
+
+/* Internal to kernel */
+extern void rcu_init(void);
+extern int rcu_scheduler_active;
+extern void rcu_scheduler_starting(void);
+
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#include <linux/rcutree.h>
+#elif defined(CONFIG_TINY_RCU)
+#include <linux/rcutiny.h>
+#else
+#error "Unknown RCU implementation specified to kernel configuration"
+#endif
+
+#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)
+#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, NULL, _THIS_IP_)
+# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
-/* 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;
+extern struct lockdep_map rcu_bh_lock_map;
+# define rcu_read_acquire_bh() \
+ lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_)
- 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;
+extern struct lockdep_map rcu_sched_lock_map;
+# define rcu_read_acquire_sched() \
+ lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_release_sched() \
+ lock_release(&rcu_sched_lock_map, 1, _THIS_IP_)
-/* Is batch a before batch b ? */
-static inline int rcu_batch_before(long a, long b)
+/**
+ * rcu_read_lock_held - might we be in RCU read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
+ * an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an RCU read-side critical section unless it can
+ * prove otherwise.
+ */
+static inline int rcu_read_lock_held(void)
{
- return (a - b) < 0;
+ if (debug_locks)
+ return lock_is_held(&rcu_lock_map);
+ return 1;
}
-/* Is batch a after batch b ? */
-static inline int rcu_batch_after(long a, long b)
+/**
+ * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
+ * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an RCU-bh read-side critical section unless it can
+ * prove otherwise.
+ */
+static inline int rcu_read_lock_bh_held(void)
{
- return (a - b) > 0;
+ if (debug_locks)
+ return lock_is_held(&rcu_bh_lock_map);
+ return 1;
}
-/*
- * Per-CPU data for Read-Copy UPdate.
- * nxtlist - new callbacks are added here
- * curlist - current batch for which quiescent cycle started if any
+/**
+ * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
+ * RCU-sched read-side critical section. In absence of CONFIG_PROVE_LOCKING,
+ * 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 read-side critical section.
*/
-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;
-};
+static inline int rcu_read_lock_sched_held(void)
+{
+ int lockdep_opinion = 0;
-DECLARE_PER_CPU(struct rcu_data, rcu_data);
-DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
+ if (debug_locks)
+ lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
+ return lockdep_opinion || preempt_count() != 0 || !rcu_scheduler_active;
+}
-/*
- * 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)
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+# define rcu_read_acquire() do { } while (0)
+# define rcu_read_release() do { } while (0)
+# define rcu_read_acquire_bh() do { } while (0)
+# define rcu_read_release_bh() do { } while (0)
+# define rcu_read_acquire_sched() do { } while (0)
+# define rcu_read_release_sched() do { } while (0)
+
+static inline int rcu_read_lock_held(void)
{
- struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
- rdp->passed_quiesc = 1;
+ return 1;
}
-static inline void rcu_bh_qsctr_inc(int cpu)
+
+static inline int rcu_read_lock_bh_held(void)
{
- struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
- rdp->passed_quiesc = 1;
+ return 1;
}
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
+static inline int rcu_read_lock_sched_held(void)
+{
+ return preempt_count() != 0 || !rcu_scheduler_active;
+}
-#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
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_PROVE_RCU
+
+/**
+ * rcu_dereference_check - rcu_dereference with debug checking
+ *
+ * Do an rcu_dereference(), but check that the context is correct.
+ * For example, rcu_dereference_check(gp, rcu_read_lock_held()) to
+ * ensure that the rcu_dereference_check() executes within an RCU
+ * read-side critical section. It is also possible to check for
+ * locks being held, for example, by using lockdep_is_held().
+ */
+#define rcu_dereference_check(p, c) \
+ ({ \
+ if (debug_locks && !(c)) \
+ lockdep_rcu_dereference(__FILE__, __LINE__); \
+ rcu_dereference_raw(p); \
+ })
+
+#else /* #ifdef CONFIG_PROVE_RCU */
+
+#define rcu_dereference_check(p, c) rcu_dereference_raw(p)
+
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
/**
* rcu_read_lock - mark the beginning of an RCU read-side critical section.
*
* 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)
+static inline void rcu_read_lock(void)
+{
+ __rcu_read_lock();
+ __acquire(RCU);
+ rcu_read_acquire();
+}
/*
* So where is rcu_write_lock()? It does not exist, as there is no
*/
/**
+ * rcu_read_unlock - marks the end of an RCU read-side critical section.
+ *
+ * See rcu_read_lock() for more information.
+ */
+static inline void rcu_read_unlock(void)
+{
+ rcu_read_release();
+ __release(RCU);
+ __rcu_read_unlock();
+}
+
+/**
* 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
* can use just rcu_read_lock().
*
*/
-#define rcu_read_lock_bh() \
- do { \
- local_bh_disable(); \
- __acquire(RCU_BH); \
- rcu_read_acquire(); \
- } while(0)
+static inline void rcu_read_lock_bh(void)
+{
+ __rcu_read_lock_bh();
+ __acquire(RCU_BH);
+ rcu_read_acquire_bh();
+}
/*
* 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)
+static inline void rcu_read_unlock_bh(void)
+{
+ rcu_read_release_bh();
+ __release(RCU_BH);
+ __rcu_read_unlock_bh();
+}
+
+/**
+ * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
+ *
+ * Should be used with either
+ * - synchronize_sched()
+ * or
+ * - call_rcu_sched() and rcu_barrier_sched()
+ * on the write-side to insure proper synchronization.
+ */
+static inline void rcu_read_lock_sched(void)
+{
+ preempt_disable();
+ __acquire(RCU_SCHED);
+ rcu_read_acquire_sched();
+}
+
+/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
+static inline notrace void rcu_read_lock_sched_notrace(void)
+{
+ preempt_disable_notrace();
+ __acquire(RCU_SCHED);
+}
/*
- * Prevent the compiler from merging or refetching accesses. The compiler
- * is also forbidden from reordering successive instances of ACCESS_ONCE(),
- * but only when the compiler is aware of some particular ordering. One way
- * to make the compiler aware of ordering is to put the two invocations of
- * ACCESS_ONCE() in different C statements.
+ * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
*
- * This macro does absolutely -nothing- to prevent the CPU from reordering,
- * merging, or refetching absolutely anything at any time.
+ * See rcu_read_lock_sched for more information.
*/
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+static inline void rcu_read_unlock_sched(void)
+{
+ rcu_read_release_sched();
+ __release(RCU_SCHED);
+ preempt_enable();
+}
+
+/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
+static inline notrace void rcu_read_unlock_sched_notrace(void)
+{
+ __release(RCU_SCHED);
+ preempt_enable_notrace();
+}
+
/**
- * rcu_dereference - fetch an RCU-protected pointer in an
- * RCU read-side critical section. This pointer may later
- * be safely dereferenced.
+ * rcu_dereference_raw - fetch an RCU-protected pointer
+ *
+ * The caller must be within some flavor of RCU read-side critical
+ * section, or must be otherwise preventing the pointer from changing,
+ * for example, by holding an appropriate lock. This pointer may later
+ * be safely dereferenced. It is the caller's responsibility to have
+ * done the right thing, as this primitive does no checking of any kind.
*
* 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) ({ \
+#define rcu_dereference_raw(p) ({ \
typeof(p) _________p1 = ACCESS_ONCE(p); \
smp_read_barrier_depends(); \
(_________p1); \
})
/**
+ * rcu_dereference - fetch an RCU-protected pointer, checking for RCU
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference(p) \
+ rcu_dereference_check(p, rcu_read_lock_held())
+
+/**
+ * rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_bh(p) \
+ rcu_dereference_check(p, rcu_read_lock_bh_held())
+
+/**
+ * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_sched(p) \
+ rcu_dereference_check(p, rcu_read_lock_sched_held())
+
+/**
* 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.
* code.
*/
-#define rcu_assign_pointer(p, v) ({ \
- smp_wmb(); \
- (p) = (v); \
- })
+#define rcu_assign_pointer(p, v) \
+ ({ \
+ if (!__builtin_constant_p(v) || \
+ ((v) != NULL)) \
+ smp_wmb(); \
+ (p) = (v); \
+ })
+
+/* Infrastructure to implement the synchronize_() primitives. */
+
+struct rcu_synchronize {
+ struct rcu_head head;
+ struct completion completion;
+};
+
+extern void wakeme_after_rcu(struct rcu_head *head);
/**
- * synchronize_sched - block until all CPUs have exited any non-preemptive
- * kernel code sequences.
+ * 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
*
- * 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.
+ * 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.
*/
-#define synchronize_sched() synchronize_rcu()
+extern void call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *head));
-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);
+/**
+ * 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.
+ */
+extern void call_rcu_bh(struct rcu_head *head,
+ void (*func)(struct rcu_head *head));
-#endif /* __KERNEL__ */
#endif /* __LINUX_RCUPDATE_H */