Message-ID: <20210811121414.857244892@linutronix.de>
Date:   Wed, 11 Aug 2021 14:22:45 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Will Deacon <will@...nel.org>,
        Waiman Long <longman@...hat.com>,
        Boqun Feng <boqun.feng@...il.com>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Davidlohr Bueso <dave@...olabs.net>,
        Mike Galbraith <efault@....de>
Subject: [patch V4 12/68] rtmutex: Split API and implementation

From: Thomas Gleixner <tglx@...utronix.de>

Prepare for reusing the inner functions of rtmutex for RT lock
substitutions.

Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
 kernel/locking/Makefile         |    2 
 kernel/locking/rtmutex.c        |  479 +---------------------------------------
 kernel/locking/rtmutex_api.c    |  453 +++++++++++++++++++++++++++++++++++++
 kernel/locking/rtmutex_common.h |   78 +++---
 4 files changed, 514 insertions(+), 498 deletions(-)
 create mode 100644 kernel/locking/rtmutex_api.c
---
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
-obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
+obj-$(CONFIG_RT_MUTEXES) += rtmutex_api.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -11,14 +11,12 @@
  *
  *  See Documentation/locking/rt-mutex-design.rst for details.
  */
-#include <linux/spinlock.h>
-#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/deadline.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
-#include <linux/sched/deadline.h>
 #include <linux/sched/wake_q.h>
-#include <linux/sched/debug.h>
-#include <linux/timer.h>
 
 #include "rtmutex_common.h"
 
@@ -371,11 +369,6 @@ rt_mutex_cond_detect_deadlock(struct rt_
 	return chwalk == RT_MUTEX_FULL_CHAINWALK;
 }
 
-/*
- * Max number of times we'll walk the boosting chain:
- */
-int max_lock_depth = 1024;
-
 static __always_inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
 {
 	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
@@ -1112,42 +1105,6 @@ static void __sched remove_waiter(struct
 	raw_spin_lock_irq(&lock->wait_lock);
 }
 
-/*
- * Recheck the pi chain, in case we got a priority setting
- *
- * Called from sched_setscheduler
- */
-void __sched rt_mutex_adjust_pi(struct task_struct *task)
-{
-	struct rt_mutex_waiter *waiter;
-	struct rt_mutex *next_lock;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
-
-	waiter = task->pi_blocked_on;
-	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-		return;
-	}
-	next_lock = waiter->lock;
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
-	/* gets dropped in rt_mutex_adjust_prio_chain()! */
-	get_task_struct(task);
-
-	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
-				   next_lock, NULL, task);
-}
-
-void __sched rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
-{
-	debug_rt_mutex_init_waiter(waiter);
-	RB_CLEAR_NODE(&waiter->pi_tree_entry);
-	RB_CLEAR_NODE(&waiter->tree_entry);
-	waiter->task = NULL;
-}
-
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
@@ -1274,6 +1231,15 @@ static int __sched rt_mutex_slowlock(str
 	return ret;
 }
 
+static __always_inline int __rt_mutex_lock(struct rt_mutex *lock,
+					   unsigned int state)
+{
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+		return 0;
+
+	return rt_mutex_slowlock(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+}
+
 static int __sched __rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
 	int ret = try_to_take_rt_mutex(lock, current, NULL);
@@ -1316,21 +1282,16 @@ static int __sched rt_mutex_slowtrylock(
 	return ret;
 }
 
-/*
- * Performs the wakeup of the top-waiter and re-enables preemption.
- */
-void __sched rt_mutex_postunlock(struct wake_q_head *wake_q)
+static __always_inline int __rt_mutex_trylock(struct rt_mutex *lock)
 {
-	wake_up_q(wake_q);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+		return 1;
 
-	/* Pairs with preempt_disable() in mark_wakeup_next_waiter() */
-	preempt_enable();
+	return rt_mutex_slowtrylock(lock);
 }
 
 /*
  * Slow path to release a rt-mutex.
- *
- * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static void __sched rt_mutex_slowunlock(struct rt_mutex *lock)
 {
@@ -1393,416 +1354,10 @@ static void __sched rt_mutex_slowunlock(
 	rt_mutex_postunlock(&wake_q);
 }
 
-/*
- * debug aware fast / slowpath lock,trylock,unlock
- *
- * The atomic acquire/release ops are compiled away, when either the
- * architecture does not support cmpxchg or when debugging is enabled.
- */
-static __always_inline int __rt_mutex_lock(struct rt_mutex *lock, long state,
-					   unsigned int subclass)
-{
-	int ret;
-
-	might_sleep();
-	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
-		return 0;
-
-	ret = rt_mutex_slowlock(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
-	if (ret)
-		mutex_release(&lock->dep_map, _RET_IP_);
-	return ret;
-}
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-/**
- * rt_mutex_lock_nested - lock a rt_mutex
- *
- * @lock: the rt_mutex to be locked
- * @subclass: the lockdep subclass
- */
-void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
-{
-	__rt_mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass);
-}
-EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
-
-#else /* !CONFIG_DEBUG_LOCK_ALLOC */
-
-/**
- * rt_mutex_lock - lock a rt_mutex
- *
- * @lock: the rt_mutex to be locked
- */
-void __sched rt_mutex_lock(struct rt_mutex *lock)
-{
-	__rt_mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0);
-}
-EXPORT_SYMBOL_GPL(rt_mutex_lock);
-#endif
-
-/**
- * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
- *
- * @lock:		the rt_mutex to be locked
- *
- * Returns:
- *  0		on success
- * -EINTR	when interrupted by a signal
- */
-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
-{
-	return __rt_mutex_lock(lock, TASK_INTERRUPTIBLE, 0);
-}
-EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
-
-/**
- * rt_mutex_trylock - try to lock a rt_mutex
- *
- * @lock:	the rt_mutex to be locked
- *
- * This function can only be called in thread context. It's safe to call it
- * from atomic regions, but not from hard or soft interrupt context.
- *
- * Returns:
- *  1 on success
- *  0 on contention
- */
-int __sched rt_mutex_trylock(struct rt_mutex *lock)
+static __always_inline void __rt_mutex_unlock(struct rt_mutex *lock)
 {
-	int ret;
-
-	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
-		return 0;
-
-	/*
-	 * No lockdep annotation required because lockdep disables the fast
-	 * path.
-	 */
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
-		return 1;
-
-	ret = rt_mutex_slowtrylock(lock);
-	if (ret)
-		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(rt_mutex_trylock);
-
-/**
- * rt_mutex_unlock - unlock a rt_mutex
- *
- * @lock: the rt_mutex to be unlocked
- */
-void __sched rt_mutex_unlock(struct rt_mutex *lock)
-{
-	mutex_release(&lock->dep_map, _RET_IP_);
 	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
 		return;
 
 	rt_mutex_slowunlock(lock);
 }
-EXPORT_SYMBOL_GPL(rt_mutex_unlock);
-
-/*
- * Futex variants, must not use fastpath.
- */
-int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
-{
-	return rt_mutex_slowtrylock(lock);
-}
-
-int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
-{
-	return __rt_mutex_slowtrylock(lock);
-}
-
-/**
- * __rt_mutex_futex_unlock - Futex variant, that since futex variants
- * do not use the fast-path, can be simple and will not need to retry.
- *
- * @lock:	The rt_mutex to be unlocked
- * @wake_q:	The wake queue head from which to get the next lock waiter
- */
-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 */
-	}
-
-	/*
-	 * We've already deboosted, mark_wakeup_next_waiter() will
-	 * retain preempt_disabled when we drop the wait_lock, to
-	 * avoid inversion prior to the wakeup.  preempt_disable()
-	 * therein pairs with rt_mutex_postunlock().
-	 */
-	mark_wakeup_next_waiter(wake_q, lock);
-
-	return true; /* call postunlock() */
-}
-
-void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
-{
-	DEFINE_WAKE_Q(wake_q);
-	unsigned long flags;
-	bool postunlock;
-
-	raw_spin_lock_irqsave(&lock->wait_lock, flags);
-	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
-	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-
-	if (postunlock)
-		rt_mutex_postunlock(&wake_q);
-}
-
-/**
- * __rt_mutex_init - initialize the rt_mutex
- *
- * @lock:	The rt_mutex to be initialized
- * @name:	The lock name used for debugging
- * @key:	The lock class key used for debugging
- *
- * Initialize the rt_mutex to unlocked state.
- *
- * Initializing of a locked rt_mutex is not allowed
- */
-void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name,
-		     struct lock_class_key *key)
-{
-	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map(&lock->dep_map, name, key, 0);
-
-	__rt_mutex_basic_init(lock);
-}
-EXPORT_SYMBOL_GPL(__rt_mutex_init);
-
-/**
- * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
- *				proxy owner
- *
- * @lock:	the rt_mutex to be locked
- * @proxy_owner:the task to set as owner
- *
- * No locking. Caller has to do serializing itself
- *
- * Special API call for PI-futex support. This initializes the rtmutex and
- * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
- * possible at this point because the pi_state which contains the rtmutex
- * is not yet visible to other tasks.
- */
-void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock,
-					struct task_struct *proxy_owner)
-{
-	__rt_mutex_basic_init(lock);
-	rt_mutex_set_owner(lock, proxy_owner);
-}
-
-/**
- * rt_mutex_proxy_unlock - release a lock on behalf of owner
- *
- * @lock:	the rt_mutex to be locked
- *
- * No locking. Caller has to do serializing itself
- *
- * Special API call for PI-futex support. This merrily cleans up the rtmutex
- * (debugging) state. Concurrent operations on this rt_mutex are not
- * possible because it belongs to the pi_state which is about to be freed
- * and it is not longer visible to other tasks.
- */
-void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock)
-{
-	debug_rt_mutex_proxy_unlock(lock);
-	rt_mutex_set_owner(lock, NULL);
-}
-
-/**
- * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock:		the rt_mutex to take
- * @waiter:		the pre-initialized rt_mutex_waiter
- * @task:		the task to prepare
- *
- * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
- * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
- *
- * NOTE: does _NOT_ remove the @waiter on failure; must either call
- * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
- *
- * Returns:
- *  0 - task blocked on lock
- *  1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for PI-futex support.
- */
-int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
-					struct rt_mutex_waiter *waiter,
-					struct task_struct *task)
-{
-	int ret;
-
-	lockdep_assert_held(&lock->wait_lock);
-
-	if (try_to_take_rt_mutex(lock, task, NULL))
-		return 1;
-
-	/* We enforce deadlock detection for futexes */
-	ret = task_blocks_on_rt_mutex(lock, waiter, task,
-				      RT_MUTEX_FULL_CHAINWALK);
-
-	if (ret && !rt_mutex_owner(lock)) {
-		/*
-		 * Reset the return value. We might have
-		 * returned with -EDEADLK and the owner
-		 * released the lock while we were walking the
-		 * pi chain.  Let the waiter sort it out.
-		 */
-		ret = 0;
-	}
-
-	return ret;
-}
-
-/**
- * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock:		the rt_mutex to take
- * @waiter:		the pre-initialized rt_mutex_waiter
- * @task:		the task to prepare
- *
- * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
- * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
- *
- * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
- * on failure.
- *
- * Returns:
- *  0 - task blocked on lock
- *  1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for PI-futex support.
- */
-int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock,
-				      struct rt_mutex_waiter *waiter,
-				      struct task_struct *task)
-{
-	int ret;
-
-	raw_spin_lock_irq(&lock->wait_lock);
-	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-	raw_spin_unlock_irq(&lock->wait_lock);
-
-	return ret;
-}
-
-/**
- * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
- * @lock:		the rt_mutex we were woken on
- * @to:			the timeout, null if none. hrtimer should already have
- *			been started.
- * @waiter:		the pre-initialized rt_mutex_waiter
- *
- * Wait for the lock acquisition started on our behalf by
- * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
- * rt_mutex_cleanup_proxy_lock().
- *
- * Returns:
- *  0 - success
- * <0 - error, one of -EINTR, -ETIMEDOUT
- *
- * Special API call for PI-futex support
- */
-int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
-				     struct hrtimer_sleeper *to,
-				     struct rt_mutex_waiter *waiter)
-{
-	int ret;
-
-	raw_spin_lock_irq(&lock->wait_lock);
-	/* sleep on the mutex */
-	set_current_state(TASK_INTERRUPTIBLE);
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
-	/*
-	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
-	 * have to fix that up.
-	 */
-	fixup_rt_mutex_waiters(lock);
-	raw_spin_unlock_irq(&lock->wait_lock);
-
-	return ret;
-}
-
-/**
- * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
- * @lock:		the rt_mutex we were woken on
- * @waiter:		the pre-initialized rt_mutex_waiter
- *
- * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
- * rt_mutex_wait_proxy_lock().
- *
- * Unless we acquired the lock; we're still enqueued on the wait-list and can
- * in fact still be granted ownership until we're removed. Therefore we can
- * find we are in fact the owner and must disregard the
- * rt_mutex_wait_proxy_lock() failure.
- *
- * Returns:
- *  true  - did the cleanup, we done.
- *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
- *          caller should disregards its return value.
- *
- * Special API call for PI-futex support
- */
-bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
-					 struct rt_mutex_waiter *waiter)
-{
-	bool cleanup = false;
-
-	raw_spin_lock_irq(&lock->wait_lock);
-	/*
-	 * Do an unconditional try-lock, this deals with the lock stealing
-	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
-	 * sets a NULL owner.
-	 *
-	 * We're not interested in the return value, because the subsequent
-	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
-	 * we will own the lock and it will have removed the waiter. If we
-	 * failed the trylock, we're still not owner and we need to remove
-	 * ourselves.
-	 */
-	try_to_take_rt_mutex(lock, current, waiter);
-	/*
-	 * Unless we're the owner; we're still enqueued on the wait_list.
-	 * So check if we became owner, if not, take us off the wait_list.
-	 */
-	if (rt_mutex_owner(lock) != current) {
-		remove_waiter(lock, waiter);
-		cleanup = true;
-	}
-	/*
-	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
-	 * have to fix that up.
-	 */
-	fixup_rt_mutex_waiters(lock);
-
-	raw_spin_unlock_irq(&lock->wait_lock);
-
-	return cleanup;
-}
-
-#ifdef CONFIG_DEBUG_RT_MUTEXES
-void rt_mutex_debug_task_free(struct task_struct *task)
-{
-	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters.rb_root));
-	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
-}
-#endif
--- /dev/null
+++ b/kernel/locking/rtmutex_api.c
@@ -0,0 +1,453 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rtmutex API
+ */
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#include "rtmutex.c"
+
+/*
+ * Max number of times we'll walk the boosting chain:
+ */
+int max_lock_depth = 1024;
+
+/*
+ * Debug aware fast / slowpath lock,trylock,unlock
+ *
+ * The atomic acquire/release ops are compiled away, when either the
+ * architecture does not support cmpxchg or when debugging is enabled.
+ */
+static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock,
+						  unsigned int state,
+						  unsigned int subclass)
+{
+	int ret;
+
+	might_sleep();
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	ret = __rt_mutex_lock(lock, state);
+	if (ret)
+		mutex_release(&lock->dep_map, _RET_IP_);
+	return ret;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+	__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+
+#else /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+/**
+ * rt_mutex_lock - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ */
+void __sched rt_mutex_lock(struct rt_mutex *lock)
+{
+	__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
+
+/**
+ * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
+ *
+ * @lock:		the rt_mutex to be locked
+ *
+ * Returns:
+ *  0		on success
+ * -EINTR	when interrupted by a signal
+ */
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
+{
+	return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
+
+/**
+ * rt_mutex_trylock - try to lock a rt_mutex
+ *
+ * @lock:	the rt_mutex to be locked
+ *
+ * This function can only be called in thread context. It's safe to call it
+ * from atomic regions, but not from hard or soft interrupt context.
+ *
+ * Returns:
+ *  1 on success
+ *  0 on contention
+ */
+int __sched rt_mutex_trylock(struct rt_mutex *lock)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
+		return 0;
+
+	ret = __rt_mutex_trylock(lock);
+	if (ret)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rt_mutex_trylock);
+
+/**
+ * rt_mutex_unlock - unlock a rt_mutex
+ *
+ * @lock: the rt_mutex to be unlocked
+ */
+void __sched rt_mutex_unlock(struct rt_mutex *lock)
+{
+	mutex_release(&lock->dep_map, _RET_IP_);
+	__rt_mutex_unlock(lock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_unlock);
+
+/*
+ * Futex variants, must not use fastpath.
+ */
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+	return rt_mutex_slowtrylock(lock);
+}
+
+int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+	return __rt_mutex_slowtrylock(lock);
+}
+
+/**
+ * __rt_mutex_futex_unlock - Futex variant, that since futex variants
+ * do not use the fast-path, can be simple and will not need to retry.
+ *
+ * @lock:	The rt_mutex to be unlocked
+ * @wake_q:	The wake queue head from which to get the next lock waiter
+ */
+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 */
+	}
+
+	/*
+	 * We've already deboosted, mark_wakeup_next_waiter() will
+	 * retain preempt_disabled when we drop the wait_lock, to
+	 * avoid inversion prior to the wakeup.  preempt_disable()
+	 * therein pairs with rt_mutex_postunlock().
+	 */
+	mark_wakeup_next_waiter(wake_q, lock);
+
+	return true; /* call postunlock() */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	DEFINE_WAKE_Q(wake_q);
+	unsigned long flags;
+	bool postunlock;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q);
+}
+
+/**
+ * __rt_mutex_init - initialize the rt_mutex
+ *
+ * @lock:	The rt_mutex to be initialized
+ * @name:	The lock name used for debugging
+ * @key:	The lock class key used for debugging
+ *
+ * Initialize the rt_mutex to unlocked state.
+ *
+ * Initializing of a locked rt_mutex is not allowed
+ */
+void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name,
+		     struct lock_class_key *key)
+{
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+
+	__rt_mutex_basic_init(lock);
+}
+EXPORT_SYMBOL_GPL(__rt_mutex_init);
+
+/**
+ * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
+ *				proxy owner
+ *
+ * @lock:	the rt_mutex to be locked
+ * @proxy_owner:the task to set as owner
+ *
+ * No locking. Caller has to do serializing itself
+ *
+ * Special API call for PI-futex support. This initializes the rtmutex and
+ * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
+ * possible at this point because the pi_state which contains the rtmutex
+ * is not yet visible to other tasks.
+ */
+void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock,
+					struct task_struct *proxy_owner)
+{
+	__rt_mutex_basic_init(lock);
+	rt_mutex_set_owner(lock, proxy_owner);
+}
+
+/**
+ * rt_mutex_proxy_unlock - release a lock on behalf of owner
+ *
+ * @lock:	the rt_mutex to be locked
+ *
+ * No locking. Caller has to do serializing itself
+ *
+ * Special API call for PI-futex support. This just cleans up the rtmutex
+ * (debugging) state. Concurrent operations on this rt_mutex are not
+ * possible because it belongs to the pi_state which is about to be freed
+ * and it is not longer visible to other tasks.
+ */
+void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock)
+{
+	debug_rt_mutex_proxy_unlock(lock);
+	rt_mutex_set_owner(lock, NULL);
+}
+
+/**
+ * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: does _NOT_ remove the @waiter on failure; must either call
+ * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
+int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+					struct rt_mutex_waiter *waiter,
+					struct task_struct *task)
+{
+	int ret;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	if (try_to_take_rt_mutex(lock, task, NULL))
+		return 1;
+
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task,
+				      RT_MUTEX_FULL_CHAINWALK);
+
+	if (ret && !rt_mutex_owner(lock)) {
+		/*
+		 * Reset the return value. We might have
+		 * returned with -EDEADLK and the owner
+		 * released the lock while we were walking the
+		 * pi chain.  Let the waiter sort it out.
+		 */
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
+ * on failure.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
+int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				      struct rt_mutex_waiter *waiter,
+				      struct task_struct *task)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @to:			the timeout, null if none. hrtimer should already have
+ *			been started.
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Wait for the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
+ *
+ * Returns:
+ *  0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT
+ *
+ * Special API call for PI-futex support
+ */
+int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+				     struct hrtimer_sleeper *to,
+				     struct rt_mutex_waiter *waiter)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	/* sleep on the mutex */
+	set_current_state(TASK_INTERRUPTIBLE);
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
+ * rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+					 struct rt_mutex_waiter *waiter)
+{
+	bool cleanup = false;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * Do an unconditional try-lock, this deals with the lock stealing
+	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+	 * sets a NULL owner.
+	 *
+	 * We're not interested in the return value, because the subsequent
+	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+	 * we will own the lock and it will have removed the waiter. If we
+	 * failed the trylock, we're still not owner and we need to remove
+	 * ourselves.
+	 */
+	try_to_take_rt_mutex(lock, current, waiter);
+	/*
+	 * Unless we're the owner; we're still enqueued on the wait_list.
+	 * So check if we became owner, if not, take us off the wait_list.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		cleanup = true;
+	}
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return cleanup;
+}
+
+/*
+ * Recheck the pi chain, in case we got a priority setting
+ *
+ * Called from sched_setscheduler
+ */
+void __sched rt_mutex_adjust_pi(struct task_struct *task)
+{
+	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+	waiter = task->pi_blocked_on;
+	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		return;
+	}
+	next_lock = waiter->lock;
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+	/* gets dropped in rt_mutex_adjust_prio_chain()! */
+	get_task_struct(task);
+
+	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+				   next_lock, NULL, task);
+}
+
+/*
+ * Performs the wakeup of the top-waiter and re-enables preemption.
+ */
+void __sched rt_mutex_postunlock(struct wake_q_head *wake_q)
+{
+	wake_up_q(wake_q);
+
+	/* Pairs with preempt_disable() in mark_wakeup_next_waiter() */
+	preempt_enable();
+}
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+void rt_mutex_debug_task_free(struct task_struct *task)
+{
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters.rb_root));
+	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
+}
+#endif
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -38,6 +38,33 @@ struct rt_mutex_waiter {
 };
 
 /*
+ * PI-futex support (proxy locking functions, etc.):
+ */
+extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
+				       struct task_struct *proxy_owner);
+extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
+extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter);
+
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+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 *wake_q);
+
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
+
+/*
  * Must be guarded because this header is included from rcu/tree_plugin.h
  * unconditionally.
  */
@@ -78,13 +105,6 @@ static inline struct task_struct *rt_mut
 
 	return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS);
 }
-#else /* CONFIG_RT_MUTEXES */
-/* Used in rcu/tree_plugin.h */
-static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
-{
-	return NULL;
-}
-#endif  /* !CONFIG_RT_MUTEXES */
 
 /*
  * Constants for rt mutex functions which have a selectable deadlock
@@ -108,34 +128,6 @@ static inline void __rt_mutex_basic_init
 	lock->waiters = RB_ROOT_CACHED;
 }
 
-/*
- * PI-futex support (proxy locking functions, etc.):
- */
-extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
-				       struct task_struct *proxy_owner);
-extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
-extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
-				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task);
-extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
-				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task);
-extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
-			       struct hrtimer_sleeper *to,
-			       struct rt_mutex_waiter *waiter);
-extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
-				 struct rt_mutex_waiter *waiter);
-
-extern int rt_mutex_futex_trylock(struct rt_mutex *l);
-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_postunlock(struct wake_q_head *wake_q);
-
 /* Debug functions */
 static inline void debug_rt_mutex_unlock(struct rt_mutex *lock)
 {
@@ -161,4 +153,20 @@ static inline void debug_rt_mutex_free_w
 		memset(waiter, 0x22, sizeof(*waiter));
 }
 
+static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->task = NULL;
+}
+
+#else /* CONFIG_RT_MUTEXES */
+/* Used in rcu/tree_plugin.h */
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
+{
+	return NULL;
+}
+#endif  /* !CONFIG_RT_MUTEXES */
+
 #endif

Powered by blists - more mailing lists