2005-04-17 06:20:36 +08:00
|
|
|
/* rwsem.c: R/W semaphores: contention handling functions
|
|
|
|
*
|
|
|
|
* Written by David Howells (dhowells@redhat.com).
|
|
|
|
* Derived from arch/i386/kernel/semaphore.c
|
2013-02-05 21:11:55 +08:00
|
|
|
*
|
|
|
|
* Writer lock-stealing by Alex Shi <alex.shi@intel.com>
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
#include <linux/rwsem.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/init.h>
|
2011-11-17 10:29:17 +08:00
|
|
|
#include <linux/export.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-07-03 15:24:53 +08:00
|
|
|
/*
|
|
|
|
* Initialize an rwsem:
|
|
|
|
*/
|
|
|
|
void __init_rwsem(struct rw_semaphore *sem, const char *name,
|
|
|
|
struct lock_class_key *key)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
|
|
/*
|
|
|
|
* Make sure we are not reinitializing a held semaphore:
|
|
|
|
*/
|
|
|
|
debug_check_no_locks_freed((void *)sem, sizeof(*sem));
|
2006-10-11 13:45:14 +08:00
|
|
|
lockdep_init_map(&sem->dep_map, name, key, 0);
|
2006-07-03 15:24:53 +08:00
|
|
|
#endif
|
|
|
|
sem->count = RWSEM_UNLOCKED_VALUE;
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_lock_init(&sem->wait_lock);
|
2006-07-03 15:24:53 +08:00
|
|
|
INIT_LIST_HEAD(&sem->wait_list);
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(__init_rwsem);
|
|
|
|
|
2013-05-07 21:45:49 +08:00
|
|
|
enum rwsem_waiter_type {
|
|
|
|
RWSEM_WAITING_FOR_WRITE,
|
|
|
|
RWSEM_WAITING_FOR_READ
|
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
struct rwsem_waiter {
|
|
|
|
struct list_head list;
|
|
|
|
struct task_struct *task;
|
2013-05-07 21:45:49 +08:00
|
|
|
enum rwsem_waiter_type type;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
2010-08-10 08:21:17 +08:00
|
|
|
/* Wake types for __rwsem_do_wake(). Note that RWSEM_WAKE_NO_ACTIVE and
|
|
|
|
* RWSEM_WAKE_READ_OWNED imply that the spinlock must have been kept held
|
|
|
|
* since the rwsem value was observed.
|
|
|
|
*/
|
|
|
|
#define RWSEM_WAKE_ANY 0 /* Wake whatever's at head of wait list */
|
|
|
|
#define RWSEM_WAKE_NO_ACTIVE 1 /* rwsem was observed with no active thread */
|
|
|
|
#define RWSEM_WAKE_READ_OWNED 2 /* rwsem was observed to be read owned */
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* handle the lock release when processes blocked on it that can now run
|
|
|
|
* - if we come here from up_xxxx(), then:
|
|
|
|
* - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
|
|
|
|
* - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
|
2010-08-10 08:21:15 +08:00
|
|
|
* - there must be someone on the queue
|
2005-04-17 06:20:36 +08:00
|
|
|
* - the spinlock must be held by the caller
|
|
|
|
* - woken process blocks are discarded from the list after having task zeroed
|
|
|
|
* - writers are only woken if downgrading is false
|
|
|
|
*/
|
2010-08-10 08:21:17 +08:00
|
|
|
static struct rw_semaphore *
|
|
|
|
__rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct rwsem_waiter *waiter;
|
|
|
|
struct task_struct *tsk;
|
|
|
|
struct list_head *next;
|
2013-02-05 21:11:55 +08:00
|
|
|
signed long woken, loop, adjustment;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-10 08:21:15 +08:00
|
|
|
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
|
2013-05-07 21:45:49 +08:00
|
|
|
if (waiter->type != RWSEM_WAITING_FOR_WRITE)
|
2010-08-10 08:21:15 +08:00
|
|
|
goto readers_only;
|
|
|
|
|
2010-08-10 08:21:17 +08:00
|
|
|
if (wake_type == RWSEM_WAKE_READ_OWNED)
|
2010-08-10 08:21:19 +08:00
|
|
|
/* Another active reader was observed, so wakeup is not
|
|
|
|
* likely to succeed. Save the atomic op.
|
|
|
|
*/
|
2010-08-10 08:21:15 +08:00
|
|
|
goto out;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-02-05 21:11:55 +08:00
|
|
|
/* Wake up the writing waiter and let the task grab the sem: */
|
|
|
|
wake_up_process(waiter->task);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out;
|
|
|
|
|
2010-08-10 08:21:15 +08:00
|
|
|
readers_only:
|
2010-08-10 08:21:17 +08:00
|
|
|
/* If we come here from up_xxxx(), another thread might have reached
|
|
|
|
* rwsem_down_failed_common() before we acquired the spinlock and
|
|
|
|
* woken up a waiter, making it now active. We prefer to check for
|
|
|
|
* this first in order to not spend too much time with the spinlock
|
|
|
|
* held if we're not going to be able to wake up readers in the end.
|
|
|
|
*
|
|
|
|
* Note that we do not need to update the rwsem count: any writer
|
|
|
|
* trying to acquire rwsem will run rwsem_down_write_failed() due
|
|
|
|
* to the waiting threads and block trying to acquire the spinlock.
|
|
|
|
*
|
|
|
|
* We use a dummy atomic update in order to acquire the cache line
|
|
|
|
* exclusively since we expect to succeed and run the final rwsem
|
|
|
|
* count adjustment pretty soon.
|
|
|
|
*/
|
|
|
|
if (wake_type == RWSEM_WAKE_ANY &&
|
2010-08-10 08:21:19 +08:00
|
|
|
rwsem_atomic_update(0, sem) < RWSEM_WAITING_BIAS)
|
|
|
|
/* Someone grabbed the sem for write already */
|
2010-08-10 08:21:17 +08:00
|
|
|
goto out;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-10 08:21:15 +08:00
|
|
|
/* Grant an infinite number of read locks to the readers at the front
|
|
|
|
* of the queue. Note we increment the 'active part' of the count by
|
|
|
|
* the number of readers before waking any processes up.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
woken = 0;
|
|
|
|
do {
|
|
|
|
woken++;
|
|
|
|
|
|
|
|
if (waiter->list.next == &sem->wait_list)
|
|
|
|
break;
|
|
|
|
|
|
|
|
waiter = list_entry(waiter->list.next,
|
|
|
|
struct rwsem_waiter, list);
|
|
|
|
|
2013-05-07 21:45:49 +08:00
|
|
|
} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-10 08:21:18 +08:00
|
|
|
adjustment = woken * RWSEM_ACTIVE_READ_BIAS;
|
2013-05-07 21:45:49 +08:00
|
|
|
if (waiter->type != RWSEM_WAITING_FOR_WRITE)
|
2010-08-10 08:21:18 +08:00
|
|
|
/* hit end of list above */
|
|
|
|
adjustment -= RWSEM_WAITING_BIAS;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-10 08:21:18 +08:00
|
|
|
rwsem_atomic_add(adjustment, sem);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
next = sem->wait_list.next;
|
2010-08-10 08:21:18 +08:00
|
|
|
for (loop = woken; loop > 0; loop--) {
|
2005-04-17 06:20:36 +08:00
|
|
|
waiter = list_entry(next, struct rwsem_waiter, list);
|
|
|
|
next = waiter->list.next;
|
|
|
|
tsk = waiter->task;
|
2005-05-01 23:58:47 +08:00
|
|
|
smp_mb();
|
2005-04-17 06:20:36 +08:00
|
|
|
waiter->task = NULL;
|
|
|
|
wake_up_process(tsk);
|
|
|
|
put_task_struct(tsk);
|
|
|
|
}
|
|
|
|
|
|
|
|
sem->wait_list.next = next;
|
|
|
|
next->prev = &sem->wait_list;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return sem;
|
2013-02-05 21:11:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Try to get write sem, caller holds sem->wait_lock: */
|
2013-05-07 21:45:54 +08:00
|
|
|
static int try_get_writer_sem(struct rw_semaphore *sem)
|
2013-02-05 21:11:55 +08:00
|
|
|
{
|
|
|
|
long oldcount, adjustment;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-02-05 21:11:55 +08:00
|
|
|
adjustment = RWSEM_ACTIVE_WRITE_BIAS;
|
2013-05-07 21:45:54 +08:00
|
|
|
if (list_is_singular(&sem->wait_list))
|
2013-02-05 21:11:55 +08:00
|
|
|
adjustment -= RWSEM_WAITING_BIAS;
|
|
|
|
|
|
|
|
try_again_write:
|
|
|
|
oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
|
2013-05-07 21:45:53 +08:00
|
|
|
if (!(oldcount & RWSEM_ACTIVE_MASK))
|
2013-02-05 21:11:55 +08:00
|
|
|
return 1;
|
|
|
|
/* some one grabbed the sem already */
|
2010-08-10 08:21:18 +08:00
|
|
|
if (rwsem_atomic_update(-adjustment, sem) & RWSEM_ACTIVE_MASK)
|
2013-02-05 21:11:55 +08:00
|
|
|
return 0;
|
2010-08-10 08:21:15 +08:00
|
|
|
goto try_again_write;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2013-05-07 21:45:51 +08:00
|
|
|
* wait for the read lock to be granted
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2013-05-07 21:45:51 +08:00
|
|
|
struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2013-05-07 21:45:51 +08:00
|
|
|
signed long adjustment = -RWSEM_ACTIVE_READ_BIAS;
|
2010-08-10 08:21:20 +08:00
|
|
|
struct rwsem_waiter waiter;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct task_struct *tsk = current;
|
|
|
|
signed long count;
|
|
|
|
|
|
|
|
/* set up my own style of waitqueue */
|
2010-08-10 08:21:20 +08:00
|
|
|
waiter.task = tsk;
|
2013-05-07 21:45:52 +08:00
|
|
|
waiter.type = RWSEM_WAITING_FOR_READ;
|
2005-04-17 06:20:36 +08:00
|
|
|
get_task_struct(tsk);
|
|
|
|
|
2013-05-07 21:45:50 +08:00
|
|
|
raw_spin_lock_irq(&sem->wait_lock);
|
2010-08-10 08:21:18 +08:00
|
|
|
if (list_empty(&sem->wait_list))
|
|
|
|
adjustment += RWSEM_WAITING_BIAS;
|
2010-08-10 08:21:20 +08:00
|
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-10 08:21:17 +08:00
|
|
|
/* we're now waiting on the lock, but no longer actively locking */
|
2005-04-17 06:20:36 +08:00
|
|
|
count = rwsem_atomic_update(adjustment, sem);
|
|
|
|
|
2013-05-07 21:45:52 +08:00
|
|
|
/* If there are no active locks, wake the front queued process(es). */
|
2010-08-10 08:21:19 +08:00
|
|
|
if (count == RWSEM_WAITING_BIAS)
|
2010-08-10 08:21:17 +08:00
|
|
|
sem = __rwsem_do_wake(sem, RWSEM_WAKE_NO_ACTIVE);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_unlock_irq(&sem->wait_lock);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* wait to be given the lock */
|
2013-05-07 21:45:50 +08:00
|
|
|
while (true) {
|
|
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
2010-08-10 08:21:20 +08:00
|
|
|
if (!waiter.task)
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
|
|
|
schedule();
|
|
|
|
}
|
|
|
|
|
|
|
|
tsk->state = TASK_RUNNING;
|
|
|
|
|
|
|
|
return sem;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2013-05-07 21:45:53 +08:00
|
|
|
* wait until we successfully acquire the write lock
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2011-01-27 04:32:01 +08:00
|
|
|
struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2013-05-07 21:45:51 +08:00
|
|
|
signed long adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
|
|
|
|
struct rwsem_waiter waiter;
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
signed long count;
|
|
|
|
|
|
|
|
/* set up my own style of waitqueue */
|
|
|
|
waiter.task = tsk;
|
2013-05-07 21:45:53 +08:00
|
|
|
waiter.type = RWSEM_WAITING_FOR_WRITE;
|
2013-05-07 21:45:51 +08:00
|
|
|
|
|
|
|
raw_spin_lock_irq(&sem->wait_lock);
|
|
|
|
if (list_empty(&sem->wait_list))
|
|
|
|
adjustment += RWSEM_WAITING_BIAS;
|
|
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
|
|
|
|
|
|
|
/* we're now waiting on the lock, but no longer actively locking */
|
|
|
|
count = rwsem_atomic_update(adjustment, sem);
|
|
|
|
|
2013-05-07 21:45:54 +08:00
|
|
|
/* If there were already threads queued before us and there are no
|
|
|
|
* active writers, the lock must be read owned; so we try to wake
|
|
|
|
* any read locks that were queued ahead of us. */
|
|
|
|
if (count > RWSEM_WAITING_BIAS &&
|
|
|
|
adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
|
2013-05-07 21:45:51 +08:00
|
|
|
sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
|
|
|
|
|
2013-05-07 21:45:53 +08:00
|
|
|
/* wait until we successfully acquire the lock */
|
2013-05-07 21:45:51 +08:00
|
|
|
while (true) {
|
|
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
2013-05-07 21:45:53 +08:00
|
|
|
|
2013-05-07 21:45:54 +08:00
|
|
|
if (try_get_writer_sem(sem))
|
2013-05-07 21:45:51 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
raw_spin_unlock_irq(&sem->wait_lock);
|
|
|
|
schedule();
|
2013-05-07 21:45:53 +08:00
|
|
|
raw_spin_lock_irq(&sem->wait_lock);
|
2013-05-07 21:45:51 +08:00
|
|
|
}
|
|
|
|
|
2013-05-07 21:45:53 +08:00
|
|
|
list_del(&waiter.list);
|
|
|
|
raw_spin_unlock_irq(&sem->wait_lock);
|
2013-05-07 21:45:51 +08:00
|
|
|
tsk->state = TASK_RUNNING;
|
|
|
|
|
|
|
|
return sem;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* handle waking up a waiter on the semaphore
|
|
|
|
* - up_read/up_write has decremented the active part of count if we come here
|
|
|
|
*/
|
2011-01-27 04:32:01 +08:00
|
|
|
struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* do nothing if list empty */
|
|
|
|
if (!list_empty(&sem->wait_list))
|
2010-08-10 08:21:17 +08:00
|
|
|
sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return sem;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* downgrade a write lock into a read lock
|
|
|
|
* - caller incremented waiting part of count and discovered it still negative
|
|
|
|
* - just wake up any readers at the front of the queue
|
|
|
|
*/
|
2011-01-27 04:32:01 +08:00
|
|
|
struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* do nothing if list empty */
|
|
|
|
if (!list_empty(&sem->wait_list))
|
2010-08-10 08:21:17 +08:00
|
|
|
sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-02-24 16:54:54 +08:00
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return sem;
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(rwsem_down_read_failed);
|
|
|
|
EXPORT_SYMBOL(rwsem_down_write_failed);
|
|
|
|
EXPORT_SYMBOL(rwsem_wake);
|
|
|
|
EXPORT_SYMBOL(rwsem_downgrade_wake);
|