mirror of
https://github.com/torvalds/linux.git
synced 2024-11-13 23:51:39 +00:00
29671f22a8
rwsem_is_locked() tests ->activity without locks, so we should always keep ->activity consistent. However, the code in __rwsem_do_wake() breaks this rule, it updates ->activity after _all_ readers waken up, this may give some reader a wrong ->activity value, thus cause rwsem_is_locked() behaves wrong. Quote from Andrew: " - we have one or more processes sleeping in down_read(), waiting for access. - we wake one or more processes up without altering ->activity - they start to run and they do rwsem_is_locked(). This incorrectly returns "false", because the waker process is still crunching away in __rwsem_do_wake(). - the waker now alters ->activity, but it was too late. " So we need get a spinlock to protect this. And rwsem_is_locked() should not block, thus we use spin_trylock_irqsave(). [akpm@linux-foundation.org: simplify code] Reported-by: Brian Behlendorf <behlendorf1@llnl.gov> Cc: Ben Woodard <bwoodard@llnl.gov> Cc: David Howells <dhowells@redhat.com> Signed-off-by: WANG Cong <amwang@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
322 lines
6.8 KiB
C
322 lines
6.8 KiB
C
/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
|
|
* generic spinlock implementation
|
|
*
|
|
* Copyright (c) 2001 David Howells (dhowells@redhat.com).
|
|
* - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
|
|
* - Derived also from comments by Linus
|
|
*/
|
|
#include <linux/rwsem.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
|
|
struct rwsem_waiter {
|
|
struct list_head list;
|
|
struct task_struct *task;
|
|
unsigned int flags;
|
|
#define RWSEM_WAITING_FOR_READ 0x00000001
|
|
#define RWSEM_WAITING_FOR_WRITE 0x00000002
|
|
};
|
|
|
|
int rwsem_is_locked(struct rw_semaphore *sem)
|
|
{
|
|
int ret = 1;
|
|
unsigned long flags;
|
|
|
|
if (spin_trylock_irqsave(&sem->wait_lock, flags)) {
|
|
ret = (sem->activity != 0);
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(rwsem_is_locked);
|
|
|
|
/*
|
|
* initialise the semaphore
|
|
*/
|
|
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));
|
|
lockdep_init_map(&sem->dep_map, name, key, 0);
|
|
#endif
|
|
sem->activity = 0;
|
|
spin_lock_init(&sem->wait_lock);
|
|
INIT_LIST_HEAD(&sem->wait_list);
|
|
}
|
|
EXPORT_SYMBOL(__init_rwsem);
|
|
|
|
/*
|
|
* handle the lock release when processes blocked on it that can now run
|
|
* - if we come here, then:
|
|
* - the 'active count' _reached_ zero
|
|
* - the 'waiting count' is non-zero
|
|
* - 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 wakewrite is non-zero
|
|
*/
|
|
static inline struct rw_semaphore *
|
|
__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
|
|
{
|
|
struct rwsem_waiter *waiter;
|
|
struct task_struct *tsk;
|
|
int woken;
|
|
|
|
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
|
|
|
|
if (!wakewrite) {
|
|
if (waiter->flags & RWSEM_WAITING_FOR_WRITE)
|
|
goto out;
|
|
goto dont_wake_writers;
|
|
}
|
|
|
|
/* if we are allowed to wake writers try to grant a single write lock
|
|
* if there's a writer at the front of the queue
|
|
* - we leave the 'waiting count' incremented to signify potential
|
|
* contention
|
|
*/
|
|
if (waiter->flags & RWSEM_WAITING_FOR_WRITE) {
|
|
sem->activity = -1;
|
|
list_del(&waiter->list);
|
|
tsk = waiter->task;
|
|
/* Don't touch waiter after ->task has been NULLed */
|
|
smp_mb();
|
|
waiter->task = NULL;
|
|
wake_up_process(tsk);
|
|
put_task_struct(tsk);
|
|
goto out;
|
|
}
|
|
|
|
/* grant an infinite number of read locks to the front of the queue */
|
|
dont_wake_writers:
|
|
woken = 0;
|
|
while (waiter->flags & RWSEM_WAITING_FOR_READ) {
|
|
struct list_head *next = waiter->list.next;
|
|
|
|
list_del(&waiter->list);
|
|
tsk = waiter->task;
|
|
smp_mb();
|
|
waiter->task = NULL;
|
|
wake_up_process(tsk);
|
|
put_task_struct(tsk);
|
|
woken++;
|
|
if (list_empty(&sem->wait_list))
|
|
break;
|
|
waiter = list_entry(next, struct rwsem_waiter, list);
|
|
}
|
|
|
|
sem->activity += woken;
|
|
|
|
out:
|
|
return sem;
|
|
}
|
|
|
|
/*
|
|
* wake a single writer
|
|
*/
|
|
static inline struct rw_semaphore *
|
|
__rwsem_wake_one_writer(struct rw_semaphore *sem)
|
|
{
|
|
struct rwsem_waiter *waiter;
|
|
struct task_struct *tsk;
|
|
|
|
sem->activity = -1;
|
|
|
|
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
|
|
list_del(&waiter->list);
|
|
|
|
tsk = waiter->task;
|
|
smp_mb();
|
|
waiter->task = NULL;
|
|
wake_up_process(tsk);
|
|
put_task_struct(tsk);
|
|
return sem;
|
|
}
|
|
|
|
/*
|
|
* get a read lock on the semaphore
|
|
*/
|
|
void __sched __down_read(struct rw_semaphore *sem)
|
|
{
|
|
struct rwsem_waiter waiter;
|
|
struct task_struct *tsk;
|
|
|
|
spin_lock_irq(&sem->wait_lock);
|
|
|
|
if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->activity++;
|
|
spin_unlock_irq(&sem->wait_lock);
|
|
goto out;
|
|
}
|
|
|
|
tsk = current;
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
|
|
/* set up my own style of waitqueue */
|
|
waiter.task = tsk;
|
|
waiter.flags = RWSEM_WAITING_FOR_READ;
|
|
get_task_struct(tsk);
|
|
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
|
|
|
/* we don't need to touch the semaphore struct anymore */
|
|
spin_unlock_irq(&sem->wait_lock);
|
|
|
|
/* wait to be given the lock */
|
|
for (;;) {
|
|
if (!waiter.task)
|
|
break;
|
|
schedule();
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
|
|
tsk->state = TASK_RUNNING;
|
|
out:
|
|
;
|
|
}
|
|
|
|
/*
|
|
* trylock for reading -- returns 1 if successful, 0 if contention
|
|
*/
|
|
int __down_read_trylock(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
int ret = 0;
|
|
|
|
|
|
spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->activity++;
|
|
ret = 1;
|
|
}
|
|
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* get a write lock on the semaphore
|
|
* - we increment the waiting count anyway to indicate an exclusive lock
|
|
*/
|
|
void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
|
|
{
|
|
struct rwsem_waiter waiter;
|
|
struct task_struct *tsk;
|
|
|
|
spin_lock_irq(&sem->wait_lock);
|
|
|
|
if (sem->activity == 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->activity = -1;
|
|
spin_unlock_irq(&sem->wait_lock);
|
|
goto out;
|
|
}
|
|
|
|
tsk = current;
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
|
|
/* set up my own style of waitqueue */
|
|
waiter.task = tsk;
|
|
waiter.flags = RWSEM_WAITING_FOR_WRITE;
|
|
get_task_struct(tsk);
|
|
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
|
|
|
/* we don't need to touch the semaphore struct anymore */
|
|
spin_unlock_irq(&sem->wait_lock);
|
|
|
|
/* wait to be given the lock */
|
|
for (;;) {
|
|
if (!waiter.task)
|
|
break;
|
|
schedule();
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
|
|
tsk->state = TASK_RUNNING;
|
|
out:
|
|
;
|
|
}
|
|
|
|
void __sched __down_write(struct rw_semaphore *sem)
|
|
{
|
|
__down_write_nested(sem, 0);
|
|
}
|
|
|
|
/*
|
|
* trylock for writing -- returns 1 if successful, 0 if contention
|
|
*/
|
|
int __down_write_trylock(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
int ret = 0;
|
|
|
|
spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (sem->activity == 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->activity = -1;
|
|
ret = 1;
|
|
}
|
|
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* release a read lock on the semaphore
|
|
*/
|
|
void __up_read(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (--sem->activity == 0 && !list_empty(&sem->wait_list))
|
|
sem = __rwsem_wake_one_writer(sem);
|
|
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* release a write lock on the semaphore
|
|
*/
|
|
void __up_write(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
sem->activity = 0;
|
|
if (!list_empty(&sem->wait_list))
|
|
sem = __rwsem_do_wake(sem, 1);
|
|
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* downgrade a write lock into a read lock
|
|
* - just wake up any readers at the front of the queue
|
|
*/
|
|
void __downgrade_write(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
sem->activity = 1;
|
|
if (!list_empty(&sem->wait_list))
|
|
sem = __rwsem_do_wake(sem, 0);
|
|
|
|
spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
|