d47996082f
Introduce a generic implementation necessary for down_write_killable(). This is a trivial extension of the already existing down_write() call which can be interrupted by SIGKILL. This patch doesn't provide down_write_killable() yet because arches have to provide the necessary pieces before. rwsem_down_write_failed() which is a generic slow path for the write lock is extended to take a task state and renamed to __rwsem_down_write_failed_common(). The return value is either a valid semaphore pointer or ERR_PTR(-EINTR). rwsem_down_write_failed_killable() is exported as a new way to wait for the lock and be killable. For rwsem-spinlock implementation the current __down_write() it updated in a similar way as __rwsem_down_write_failed_common() except it doesn't need new exports just visible __down_write_killable(). Architectures which are not using the generic rwsem implementation are supposed to provide their __down_write_killable() implementation and use rwsem_down_write_failed_killable() for the slow path. Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Zankel <chris@zankel.net> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Signed-off-by: Jason Low <jason.low2@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-alpha@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1460041951-22347-7-git-send-email-mhocko@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
316 lines
6.9 KiB
C
316 lines
6.9 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/export.h>
|
|
|
|
enum rwsem_waiter_type {
|
|
RWSEM_WAITING_FOR_WRITE,
|
|
RWSEM_WAITING_FOR_READ
|
|
};
|
|
|
|
struct rwsem_waiter {
|
|
struct list_head list;
|
|
struct task_struct *task;
|
|
enum rwsem_waiter_type type;
|
|
};
|
|
|
|
int rwsem_is_locked(struct rw_semaphore *sem)
|
|
{
|
|
int ret = 1;
|
|
unsigned long flags;
|
|
|
|
if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
|
|
ret = (sem->count != 0);
|
|
raw_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->count = 0;
|
|
raw_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 (waiter->type == RWSEM_WAITING_FOR_WRITE) {
|
|
if (wakewrite)
|
|
/* Wake up a writer. Note that we do not grant it the
|
|
* lock - it will have to acquire it when it runs. */
|
|
wake_up_process(waiter->task);
|
|
goto out;
|
|
}
|
|
|
|
/* grant an infinite number of read locks to the front of the queue */
|
|
woken = 0;
|
|
do {
|
|
struct list_head *next = waiter->list.next;
|
|
|
|
list_del(&waiter->list);
|
|
tsk = waiter->task;
|
|
/*
|
|
* Make sure we do not wakeup the next reader before
|
|
* setting the nil condition to grant the next reader;
|
|
* otherwise we could miss the wakeup on the other
|
|
* side and end up sleeping again. See the pairing
|
|
* in rwsem_down_read_failed().
|
|
*/
|
|
smp_mb();
|
|
waiter->task = NULL;
|
|
wake_up_process(tsk);
|
|
put_task_struct(tsk);
|
|
woken++;
|
|
if (next == &sem->wait_list)
|
|
break;
|
|
waiter = list_entry(next, struct rwsem_waiter, list);
|
|
} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
|
|
|
|
sem->count += 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;
|
|
|
|
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
|
|
wake_up_process(waiter->task);
|
|
|
|
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;
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (sem->count >= 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->count++;
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
goto out;
|
|
}
|
|
|
|
tsk = current;
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
|
|
/* set up my own style of waitqueue */
|
|
waiter.task = tsk;
|
|
waiter.type = 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 */
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
/* wait to be given the lock */
|
|
for (;;) {
|
|
if (!waiter.task)
|
|
break;
|
|
schedule();
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
|
|
__set_task_state(tsk, 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;
|
|
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (sem->count >= 0 && list_empty(&sem->wait_list)) {
|
|
/* granted */
|
|
sem->count++;
|
|
ret = 1;
|
|
}
|
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* get a write lock on the semaphore
|
|
*/
|
|
int __sched __down_write_common(struct rw_semaphore *sem, int state)
|
|
{
|
|
struct rwsem_waiter waiter;
|
|
struct task_struct *tsk;
|
|
unsigned long flags;
|
|
int ret = 0;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
/* set up my own style of waitqueue */
|
|
tsk = current;
|
|
waiter.task = tsk;
|
|
waiter.type = RWSEM_WAITING_FOR_WRITE;
|
|
list_add_tail(&waiter.list, &sem->wait_list);
|
|
|
|
/* wait for someone to release the lock */
|
|
for (;;) {
|
|
/*
|
|
* That is the key to support write lock stealing: allows the
|
|
* task already on CPU to get the lock soon rather than put
|
|
* itself into sleep and waiting for system woke it or someone
|
|
* else in the head of the wait list up.
|
|
*/
|
|
if (sem->count == 0)
|
|
break;
|
|
if (signal_pending_state(state, current)) {
|
|
ret = -EINTR;
|
|
goto out;
|
|
}
|
|
set_task_state(tsk, state);
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
schedule();
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
}
|
|
/* got the lock */
|
|
sem->count = -1;
|
|
out:
|
|
list_del(&waiter.list);
|
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
|
|
void __sched __down_write(struct rw_semaphore *sem)
|
|
{
|
|
__down_write_common(sem, TASK_UNINTERRUPTIBLE);
|
|
}
|
|
|
|
int __sched __down_write_killable(struct rw_semaphore *sem)
|
|
{
|
|
return __down_write_common(sem, TASK_KILLABLE);
|
|
}
|
|
|
|
/*
|
|
* trylock for writing -- returns 1 if successful, 0 if contention
|
|
*/
|
|
int __down_write_trylock(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
int ret = 0;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (sem->count == 0) {
|
|
/* got the lock */
|
|
sem->count = -1;
|
|
ret = 1;
|
|
}
|
|
|
|
raw_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;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
if (--sem->count == 0 && !list_empty(&sem->wait_list))
|
|
sem = __rwsem_wake_one_writer(sem);
|
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* release a write lock on the semaphore
|
|
*/
|
|
void __up_write(struct rw_semaphore *sem)
|
|
{
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
sem->count = 0;
|
|
if (!list_empty(&sem->wait_list))
|
|
sem = __rwsem_do_wake(sem, 1);
|
|
|
|
raw_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;
|
|
|
|
raw_spin_lock_irqsave(&sem->wait_lock, flags);
|
|
|
|
sem->count = 1;
|
|
if (!list_empty(&sem->wait_list))
|
|
sem = __rwsem_do_wake(sem, 0);
|
|
|
|
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
|
|
}
|
|
|