Part of what makes futex_unlock_pi() intricate is that rt_mutex_futex_unlock() -> rt_mutex_slowunlock() can drop rt_mutex::wait_lock. This means we cannot rely on the atomicy of wait_lock, which we would like to do in order to not rely on hb->lock so much. The reason rt_mutex_slowunlock() needs to drop wait_lock is because it can race with the rt_mutex fastpath, however futexes have their own fast path. Since futexes already have a bunch of separate rt_mutex accessors, complete that set and implement a rt_mutex variant without fastpath for them. Signed-off-by: Peter Zijlstra (Intel) --- kernel/futex.c | 30 ++++++++++----------- kernel/locking/rtmutex.c | 55 +++++++++++++++++++++++++++++----------- kernel/locking/rtmutex_common.h | 9 +++++- 3 files changed, 62 insertions(+), 32 deletions(-) --- a/kernel/futex.c +++ b/kernel/futex.c @@ -916,7 +916,7 @@ void exit_pi_state_list(struct task_stru pi_state->owner = NULL; raw_spin_unlock_irq(&curr->pi_lock); - rt_mutex_unlock(&pi_state->pi_mutex); + rt_mutex_futex_unlock(&pi_state->pi_mutex); spin_unlock(&hb->lock); @@ -1364,20 +1364,18 @@ static int wake_futex_pi(u32 __user *uad pi_state->owner = new_owner; raw_spin_unlock(&new_owner->pi_lock); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - - deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); - /* - * First unlock HB so the waiter does not spin on it once he got woken - * up. Second wake up the waiter before the priority is adjusted. If we - * deboost first (and lose our higher priority), then the task might get - * scheduled away before the wake up can take place. + * We've updated the uservalue, this unlock cannot fail. */ + deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); - wake_up_q(&wake_q); - if (deboost) + + if (deboost) { + wake_up_q(&wake_q); rt_mutex_adjust_prio(current); + } return 0; } @@ -2253,7 +2251,7 @@ static int fixup_owner(u32 __user *uaddr * task acquired the rt_mutex after we removed ourself from the * rt_mutex waiters list. */ - if (rt_mutex_trylock(&q->pi_state->pi_mutex)) { + if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) { locked = 1; goto out; } @@ -2568,7 +2566,7 @@ static int futex_lock_pi(u32 __user *uad if (!trylock) { ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to); } else { - ret = rt_mutex_trylock(&q.pi_state->pi_mutex); + ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); /* Fixup the trylock return value: */ ret = ret ? 0 : -EWOULDBLOCK; } @@ -2591,7 +2589,7 @@ static int futex_lock_pi(u32 __user *uad * it and return the fault to userspace. */ if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) - rt_mutex_unlock(&q.pi_state->pi_mutex); + rt_mutex_futex_unlock(&q.pi_state->pi_mutex); /* Unqueue and drop the lock */ unqueue_me_pi(&q); @@ -2898,7 +2896,7 @@ static int futex_wait_requeue_pi(u32 __u spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) - rt_mutex_unlock(&q.pi_state->pi_mutex); + rt_mutex_futex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -2938,7 +2936,7 @@ static int futex_wait_requeue_pi(u32 __u * userspace. */ if (ret && rt_mutex_owner(pi_mutex) == current) - rt_mutex_unlock(pi_mutex); + rt_mutex_futex_unlock(pi_mutex); /* Unqueue and drop the lock. */ unqueue_me_pi(&q); --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1488,15 +1488,23 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_interrup /* * Futex variant with full deadlock detection. + * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock(). */ -int rt_mutex_timed_futex_lock(struct rt_mutex *lock, +int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) { might_sleep(); - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - RT_MUTEX_FULL_CHAINWALK, - rt_mutex_slowlock); + return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, + timeout, RT_MUTEX_FULL_CHAINWALK); +} + +/* + * Futex variant, must not use fastpath. + */ +int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return rt_mutex_slowtrylock(lock); } /** @@ -1555,19 +1563,38 @@ void __sched rt_mutex_unlock(struct rt_m EXPORT_SYMBOL_GPL(rt_mutex_unlock); /** - * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock - * @lock: the rt_mutex to be unlocked - * - * Returns: true/false indicating whether priority adjustment is - * required or not. + * Futex variant, that since futex variants do not use the fast-path, can be + * simple and will not need to retry. */ -bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh) +bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wake_q) +{ + lockdep_assert_held(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + return false; /* done */ + } + + mark_wakeup_next_waiter(wake_q, lock); + return true; /* deboost and wakeups */ +} + +void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) - return false; + DEFINE_WAKE_Q(wake_q); + bool deboost; - return rt_mutex_slowunlock(lock, wqh); + raw_spin_lock_irq(&lock->wait_lock); + deboost = __rt_mutex_futex_unlock(lock, &wake_q); + raw_spin_unlock_irq(&lock->wait_lock); + + if (deboost) { + wake_up_q(&wake_q); + rt_mutex_adjust_prio(current); + } } /** --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -109,9 +109,14 @@ extern int rt_mutex_start_proxy_lock(str extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter); + extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); -extern bool rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh); +extern int rt_mutex_futex_trylock(struct rt_mutex *l); + +extern void rt_mutex_futex_unlock(struct rt_mutex *lock); +extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wqh); + extern void rt_mutex_adjust_prio(struct task_struct *task); #ifdef CONFIG_DEBUG_RT_MUTEXES