* - 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)
* - there must be someone on the queue
- * - the spinlock must be held by the caller
+ * - the wait_lock must be held by the caller
+ * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
+ * to actually wakeup the blocked task(s) and drop the reference count,
+ * preferably when the wait_lock is released
* - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if downgrading is false
+ * - writers are only marked woken if downgrading is false
*/
static struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+__rwsem_mark_wake(struct rw_semaphore *sem,
+ enum rwsem_wake_type wake_type, struct wake_q_head *wake_q)
{
struct rwsem_waiter *waiter;
struct task_struct *tsk;
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
- if (wake_type == RWSEM_WAKE_ANY)
- /* Wake writer at the front of the queue, but do not
- * grant it the lock yet as we want other writers
- * to be able to steal it. Readers, on the other hand,
- * will block as they will notice the queued writer.
+ if (wake_type == RWSEM_WAKE_ANY) {
+ /*
+ * Mark writer at the front of the queue for wakeup.
+ * Until the task is actually later awoken later by
+ * the caller, other writers are able to steal it.
+ * Readers, on the other hand, will block as they
+ * will notice the queued writer.
*/
- wake_up_process(waiter->task);
+ wake_q_add(wake_q, waiter->task);
+ }
goto out;
}
waiter = list_entry(next, struct rwsem_waiter, list);
next = waiter->list.next;
tsk = waiter->task;
+
+ wake_q_add(wake_q, tsk);
/*
- * 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().
+ * Ensure that the last operation is setting the reader
+ * waiter to nil such that rwsem_down_read_failed() cannot
+ * race with do_exit() by always holding a reference count
+ * to the task to wakeup.
*/
- smp_mb();
- waiter->task = NULL;
- wake_up_process(tsk);
- put_task_struct(tsk);
+ smp_store_release(&waiter->task, NULL);
} while (--loop);
sem->wait_list.next = next;
long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
struct rwsem_waiter waiter;
struct task_struct *tsk = current;
+ WAKE_Q(wake_q);
/* set up my own style of waitqueue */
waiter.task = tsk;
waiter.type = RWSEM_WAITING_FOR_READ;
- get_task_struct(tsk);
raw_spin_lock_irq(&sem->wait_lock);
if (list_empty(&sem->wait_list))
if (count == RWSEM_WAITING_BIAS ||
(count > RWSEM_WAITING_BIAS &&
adjustment != -RWSEM_ACTIVE_READ_BIAS))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
/* wait to be given the lock */
while (true) {
}
EXPORT_SYMBOL(rwsem_down_read_failed);
+/*
+ * This function must be called with the sem->wait_lock held to prevent
+ * race conditions between checking the rwsem wait list and setting the
+ * sem->count accordingly.
+ */
static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
{
/*
- * Try acquiring the write lock. Check count first in order
- * to reduce unnecessary expensive cmpxchg() operations.
+ * Avoid trying to acquire write lock if count isn't RWSEM_WAITING_BIAS.
*/
- if (count == RWSEM_WAITING_BIAS &&
- cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS,
- RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
- if (!list_is_singular(&sem->wait_list))
- rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+ if (count != RWSEM_WAITING_BIAS)
+ return false;
+
+ /*
+ * Acquire the lock by trying to set it to ACTIVE_WRITE_BIAS. If there
+ * are other tasks on the wait list, we need to add on WAITING_BIAS.
+ */
+ count = list_is_singular(&sem->wait_list) ?
+ RWSEM_ACTIVE_WRITE_BIAS :
+ RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
+
+ if (cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) {
rwsem_set_owner(sem);
return true;
}
bool waiting = true; /* any queued threads before us */
struct rwsem_waiter waiter;
struct rw_semaphore *ret = sem;
+ WAKE_Q(wake_q);
/* undo write bias from down_write operation, stop active locking */
count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
* 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)
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+ if (count > RWSEM_WAITING_BIAS) {
+ WAKE_Q(wake_q);
+
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
+ /*
+ * The wakeup is normally called _after_ the wait_lock
+ * is released, but given that we are proactively waking
+ * readers we can deal with the wake_q overhead as it is
+ * similar to releasing and taking the wait_lock again
+ * for attempting rwsem_try_write_lock().
+ */
+ wake_up_q(&wake_q);
+ }
} else
count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
if (list_empty(&sem->wait_list))
rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
else
- __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
return ERR_PTR(-EINTR);
}
struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
unsigned long flags;
+ WAKE_Q(wake_q);
/*
* If a spinner is present, it is not necessary to do the wakeup.
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ wake_up_q(&wake_q);
return sem;
}
struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
unsigned long flags;
+ WAKE_Q(wake_q);
raw_spin_lock_irqsave(&sem->wait_lock, flags);
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ wake_up_q(&wake_q);
return sem;
}