#include <linux/freezer.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
+#include <linux/refcount.h>
#include <asm/futex.h>
struct rt_mutex pi_mutex;
struct task_struct *owner;
- atomic_t refcount;
+ refcount_t refcount;
union futex_key key;
} __randomize_layout;
if (IS_ERR(dir))
return PTR_ERR(dir);
- if (!debugfs_create_bool("ignore-private", mode, dir,
- &fail_futex.ignore_private)) {
- debugfs_remove_recursive(dir);
- return -ENOMEM;
- }
-
+ debugfs_create_bool("ignore-private", mode, dir,
+ &fail_futex.ignore_private);
return 0;
}
INIT_LIST_HEAD(&pi_state->list);
/* pi_mutex gets initialized later */
pi_state->owner = NULL;
- atomic_set(&pi_state->refcount, 1);
+ refcount_set(&pi_state->refcount, 1);
pi_state->key = FUTEX_KEY_INIT;
current->pi_state_cache = pi_state;
static void get_pi_state(struct futex_pi_state *pi_state)
{
- WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+ WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount));
}
/*
if (!pi_state)
return;
- if (!atomic_dec_and_test(&pi_state->refcount))
+ if (!refcount_dec_and_test(&pi_state->refcount))
return;
/*
* refcount is at 0 - put it back to 1.
*/
pi_state->owner = NULL;
- atomic_set(&pi_state->refcount, 1);
+ refcount_set(&pi_state->refcount, 1);
current->pi_state_cache = pi_state;
}
}
* In that case; drop the locks to let put_pi_state() make
* progress and retry the loop.
*/
- if (!atomic_inc_not_zero(&pi_state->refcount)) {
+ if (!refcount_inc_not_zero(&pi_state->refcount)) {
raw_spin_unlock_irq(&curr->pi_lock);
cpu_relax();
raw_spin_lock_irq(&curr->pi_lock);
* and futex_wait_requeue_pi() as it cannot go to 0 and consequently
* free pi_state before we can take a reference ourselves.
*/
- WARN_ON(!atomic_read(&pi_state->refcount));
+ WARN_ON(!refcount_read(&pi_state->refcount));
/*
* Now that we have a pi_state, we can acquire wait_lock
* Queue the task for later wakeup for after we've released
* the hb->lock. wake_q_add() grabs reference to p.
*/
- wake_q_add(wake_q, p);
- put_task_struct(p);
+ wake_q_add_safe(wake_q, p);
}
/*
* decrement the counter at queue_unlock() when some error has
* occurred and we don't end up adding the task to the list.
*/
- hb_waiters_inc(hb);
+ hb_waiters_inc(hb); /* implies smp_mb(); (A) */
q->lock_ptr = &hb->lock;
- spin_lock(&hb->lock); /* implies smp_mb(); (A) */
+ spin_lock(&hb->lock);
return hb;
}
* and BUG when futex_unlock_pi() interleaves with this.
*
* Therefore acquire wait_lock while holding hb->lock, but drop the
- * latter before calling rt_mutex_start_proxy_lock(). This still fully
- * serializes against futex_unlock_pi() as that does the exact same
- * lock handoff sequence.
+ * latter before calling __rt_mutex_start_proxy_lock(). This
+ * interleaves with futex_unlock_pi() -- which does a similar lock
+ * handoff -- such that the latter can observe the futex_q::pi_state
+ * before __rt_mutex_start_proxy_lock() is done.
*/
raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
spin_unlock(q.lock_ptr);
+ /*
+ * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+ * such that futex_unlock_pi() is guaranteed to observe the waiter when
+ * it sees the futex_q::pi_state.
+ */
ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
if (ret) {
if (ret == 1)
ret = 0;
-
- spin_lock(q.lock_ptr);
- goto no_block;
+ goto cleanup;
}
-
if (unlikely(to))
hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+cleanup:
spin_lock(q.lock_ptr);
/*
- * If we failed to acquire the lock (signal/timeout), we must
+ * If we failed to acquire the lock (deadlock/signal/timeout), we must
* first acquire the hb->lock before removing the lock from the
- * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
- * wait lists consistent.
+ * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
+ * lists consistent.
*
* In particular; it is important that futex_unlock_pi() can not
* observe this inconsistency.
* there is no point where we hold neither; and therefore
* wake_futex_pi() must observe a state consistent with what we
* observed.
+ *
+ * In particular; this forces __rt_mutex_start_proxy() to
+ * complete such that we're guaranteed to observe the
+ * rt_waiter. Also see the WARN in wake_futex_pi().
*/
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
{
u32 uval, uninitialized_var(nval), mval;
+ /* Futex address must be 32bit aligned */
+ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
+ return -1;
+
retry:
if (get_user(uval, uaddr))
return -1;
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
u32, val3)
{