linux-hardened/include/linux/rwsem.h
Jason Low ce069fc920 locking/rwsem: Reduce the size of struct rw_semaphore
Recent optimistic spinning additions to rwsem provide significant performance
benefits on many workloads on large machines. The cost of it was increasing
the size of the rwsem structure by up to 128 bits.

However, now that the previous patches in this series bring the overhead of
struct optimistic_spin_queue to 32 bits, this patch reorders some fields in
struct rw_semaphore such that we can reduce the overhead of the rwsem structure
by 64 bits (on 64 bit systems).

The extra overhead required for rwsem optimistic spinning would now be up
to 8 additional bytes instead of up to 16 bytes. Additionally, the size of
rwsem would now be more in line with mutexes.

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Waiman Long <waiman.long@hp.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Link: http://lkml.kernel.org/r/1405358872-3732-6-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-16 14:57:03 +02:00

178 lines
5.1 KiB
C

/* rwsem.h: R/W semaphores, public interface
*
* Written by David Howells (dhowells@redhat.com).
* Derived from asm-i386/semaphore.h
*/
#ifndef _LINUX_RWSEM_H
#define _LINUX_RWSEM_H
#include <linux/linkage.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/osq_lock.h>
struct rw_semaphore;
#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
#include <linux/rwsem-spinlock.h> /* use a generic implementation */
#else
/* All arch specific implementations share the same struct */
struct rw_semaphore {
long count;
struct list_head wait_list;
raw_spinlock_t wait_lock;
#ifdef CONFIG_SMP
struct optimistic_spin_queue osq; /* spinner MCS lock */
/*
* Write owner. Used as a speculative check to see
* if the owner is running on the cpu.
*/
struct task_struct *owner;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
/* Include the arch specific part */
#include <asm/rwsem.h>
/* In all implementations count != 0 means locked */
static inline int rwsem_is_locked(struct rw_semaphore *sem)
{
return sem->count != 0;
}
#endif
/* Common initializer macros and functions */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
#else
# define __RWSEM_DEP_MAP_INIT(lockname)
#endif
#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
#else
#define __RWSEM_OPT_INIT(lockname)
#endif
#define __RWSEM_INITIALIZER(name) \
{ .count = RWSEM_UNLOCKED_VALUE, \
.wait_list = LIST_HEAD_INIT((name).wait_list), \
.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \
__RWSEM_OPT_INIT(name) \
__RWSEM_DEP_MAP_INIT(name) }
#define DECLARE_RWSEM(name) \
struct rw_semaphore name = __RWSEM_INITIALIZER(name)
extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
struct lock_class_key *key);
#define init_rwsem(sem) \
do { \
static struct lock_class_key __key; \
\
__init_rwsem((sem), #sem, &__key); \
} while (0)
/*
* This is the same regardless of which rwsem implementation that is being used.
* It is just a heuristic meant to be called by somebody alreadying holding the
* rwsem to see if somebody from an incompatible type is wanting access to the
* lock.
*/
static inline int rwsem_is_contended(struct rw_semaphore *sem)
{
return !list_empty(&sem->wait_list);
}
/*
* lock for reading
*/
extern void down_read(struct rw_semaphore *sem);
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
extern int down_read_trylock(struct rw_semaphore *sem);
/*
* lock for writing
*/
extern void down_write(struct rw_semaphore *sem);
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
extern int down_write_trylock(struct rw_semaphore *sem);
/*
* release a read lock
*/
extern void up_read(struct rw_semaphore *sem);
/*
* release a write lock
*/
extern void up_write(struct rw_semaphore *sem);
/*
* downgrade write lock to read lock
*/
extern void downgrade_write(struct rw_semaphore *sem);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* nested locking. NOTE: rwsems are not allowed to recurse
* (which occurs if the same task tries to acquire the same
* lock instance multiple times), but multiple locks of the
* same lock class might be taken, if the order of the locks
* is always the same. This ordering rule can be expressed
* to lockdep via the _nested() APIs, but enumerating the
* subclasses that are used. (If the nesting relationship is
* static then another method for expressing nested locking is
* the explicit definition of lock class keys and the use of
* lockdep_set_class() at lock initialization time.
* See Documentation/lockdep-design.txt for more details.)
*/
extern void down_read_nested(struct rw_semaphore *sem, int subclass);
extern void down_write_nested(struct rw_semaphore *sem, int subclass);
extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
# define down_write_nest_lock(sem, nest_lock) \
do { \
typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
_down_write_nest_lock(sem, &(nest_lock)->dep_map); \
} while (0);
/*
* Take/release a lock when not the owner will release it.
*
* [ This API should be avoided as much as possible - the
* proper abstraction for this case is completions. ]
*/
extern void down_read_non_owner(struct rw_semaphore *sem);
extern void up_read_non_owner(struct rw_semaphore *sem);
#else
# define down_read_nested(sem, subclass) down_read(sem)
# define down_write_nest_lock(sem, nest_lock) down_write(sem)
# define down_write_nested(sem, subclass) down_write(sem)
# define down_read_non_owner(sem) down_read(sem)
# define up_read_non_owner(sem) up_read(sem)
#endif
#endif /* _LINUX_RWSEM_H */