[PATCH] pi-futex: rt mutex core

Core functions for the rt-mutex subsystem.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

11 files changed, 1181 insertions, 0 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 678c1a90380d..3a256957fb56 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -124,6 +124,7 @@ extern struct group_info init_groups;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.fs_excl	= ATOMIC_INIT(0),				\
 	.pi_lock	= SPIN_LOCK_UNLOCKED,				\
+	INIT_RT_MUTEXES(tsk)						\
 }
 
 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
new file mode 100644
index 000000000000..12309c916c68
--- /dev/null
+++ b/include/linux/rtmutex.h
@@ -0,0 +1,104 @@
+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the public data structure and API definitions.
+ */
+
+#ifndef __LINUX_RT_MUTEX_H
+#define __LINUX_RT_MUTEX_H
+
+#include <linux/linkage.h>
+#include <linux/plist.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * The rt_mutex structure
+ *
+ * @wait_lock:	spinlock to protect the structure
+ * @wait_list:	pilist head to enqueue waiters in priority order
+ * @owner:	the mutex owner
+ */
+struct rt_mutex {
+	spinlock_t		wait_lock;
+	struct plist_head	wait_list;
+	struct task_struct	*owner;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	int			save_state;
+	struct list_head	held_list_entry;
+	unsigned long		acquire_ip;
+	const char 		*name, *file;
+	int			line;
+	void			*magic;
+#endif
+};
+
+struct rt_mutex_waiter;
+struct hrtimer_sleeper;
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
+	, .name = #mutexname, .file = __FILE__, .line = __LINE__
+# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, __FUNCTION__)
+ extern void rt_mutex_debug_task_free(struct task_struct *tsk);
+#else
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
+# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, NULL)
+# define rt_mutex_debug_task_free(t)		do { } while (0)
+#endif
+
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+	{ .wait_lock = SPIN_LOCK_UNLOCKED \
+	, .wait_list = PLIST_HEAD_INIT(mutexname.wait_list, mutexname.wait_lock) \
+	, .owner = NULL \
+	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
+
+#define DEFINE_RT_MUTEX(mutexname) \
+	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
+
+/***
+ * rt_mutex_is_locked - is the mutex locked
+ * @lock: the mutex to be queried
+ *
+ * Returns 1 if the mutex is locked, 0 if unlocked.
+ */
+static inline int rt_mutex_is_locked(struct rt_mutex *lock)
+{
+	return lock->owner != NULL;
+}
+
+extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
+extern void rt_mutex_destroy(struct rt_mutex *lock);
+
+extern void rt_mutex_lock(struct rt_mutex *lock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
+						int detect_deadlock);
+extern int rt_mutex_timed_lock(struct rt_mutex *lock,
+					struct hrtimer_sleeper *timeout,
+					int detect_deadlock);
+
+extern int rt_mutex_trylock(struct rt_mutex *lock);
+
+extern void rt_mutex_unlock(struct rt_mutex *lock);
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define INIT_RT_MUTEX_DEBUG(tsk)					\
+	.held_list_head	= LIST_HEAD_INIT(tsk.held_list_head),		\
+	.held_list_lock	= SPIN_LOCK_UNLOCKED
+#else
+# define INIT_RT_MUTEX_DEBUG(tsk)
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk)						\
+	.pi_waiters	= PLIST_HEAD_INIT(tsk.pi_waiters, tsk.pi_lock),	\
+	INIT_RT_MUTEX_DEBUG(tsk)
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6f167645e7e2..6ea23c9af413 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -73,6 +73,7 @@ struct sched_param {
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
 #include <linux/futex.h>
+#include <linux/rtmutex.h>
 
 #include <linux/time.h>
 #include <linux/param.h>
@@ -858,6 +859,17 @@ struct task_struct {
 	/* Protection of the PI data structures: */
 	spinlock_t pi_lock;
 
+#ifdef CONFIG_RT_MUTEXES
+	/* PI waiters blocked on a rt_mutex held by this task */
+	struct plist_head pi_waiters;
+	/* Deadlock detection and priority inheritance handling */
+	struct rt_mutex_waiter *pi_blocked_on;
+# ifdef CONFIG_DEBUG_RT_MUTEXES
+	spinlock_t held_list_lock;
+	struct list_head held_list_head;
+# endif
+#endif
+
 #ifdef CONFIG_DEBUG_MUTEXES
 	/* mutex deadlock detection */
 	struct mutex_waiter *blocked_on;
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index bee12a7a0576..46e4d8f2771f 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -149,6 +149,7 @@ enum
 	KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */
 	KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
+	KERN_MAX_LOCK_DEPTH=74,
 };
 
 
diff --git a/init/Kconfig b/init/Kconfig
index df55b3665601..f70f2fd273c2 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -339,9 +339,14 @@ config BASE_FULL
 	  kernel data structures. This saves memory on small machines,
 	  but may reduce performance.
 
+config RT_MUTEXES
+	boolean
+	select PLIST
+
 config FUTEX
 	bool "Enable futex support" if EMBEDDED
 	default y
+	select RT_MUTEXES
 	help
 	  Disabling this option will cause the kernel to be built without
 	  support for "fast userspace mutexes".  The resulting kernel may not
diff --git a/kernel/Makefile b/kernel/Makefile
index 752bd7d383af..21df9a338ff0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_FUTEX) += futex.o
 ifeq ($(CONFIG_COMPAT),y)
 obj-$(CONFIG_FUTEX) += futex_compat.o
 endif
+obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += cpu.o spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b4e54ef0225..b664a081fffa 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -104,6 +104,7 @@ static kmem_cache_t *mm_cachep;
 void free_task(struct task_struct *tsk)
 {
 	free_thread_info(tsk->thread_info);
+	rt_mutex_debug_task_free(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -913,6 +914,19 @@ asmlinkage long sys_set_tid_address(int __user *tidptr)
 	return current->pid;
 }
 
+static inline void rt_mutex_init_task(struct task_struct *p)
+{
+#ifdef CONFIG_RT_MUTEXES
+	spin_lock_init(&p->pi_lock);
+	plist_head_init(&p->pi_waiters, &p->pi_lock);
+	p->pi_blocked_on = NULL;
+# ifdef CONFIG_DEBUG_RT_MUTEXES
+	spin_lock_init(&p->held_list_lock);
+	INIT_LIST_HEAD(&p->held_list_head);
+# endif
+#endif
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1034,6 +1048,8 @@ static task_t *copy_process(unsigned long clone_flags,
 	mpol_fix_fork_child_flag(p);
 #endif
 
+	rt_mutex_init_task(p);
+
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
new file mode 100644
index 000000000000..937a474fae94
--- /dev/null
+++ b/kernel/rtmutex.c
@@ -0,0 +1,904 @@
+/*
+ * RT-Mutexes: simple blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner.
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
+ *  Copyright (C) 2006 Esben Nielsen
+ */
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+#include "rtmutex_common.h"
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# include "rtmutex-debug.h"
+#else
+# include "rtmutex.h"
+#endif
+
+/*
+ * lock->owner state tracking:
+ *
+ * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
+ * are used to keep track of the "owner is pending" and "lock has
+ * waiters" state.
+ *
+ * owner	bit1	bit0
+ * NULL		0	0	lock is free (fast acquire possible)
+ * NULL		0	1	invalid state
+ * NULL		1	0	Transitional State*
+ * NULL		1	1	invalid state
+ * taskpointer	0	0	lock is held (fast release possible)
+ * taskpointer	0	1	task is pending owner
+ * taskpointer	1	0	lock is held and has waiters
+ * taskpointer	1	1	task is pending owner and lock has more waiters
+ *
+ * Pending ownership is assigned to the top (highest priority)
+ * waiter of the lock, when the lock is released. The thread is woken
+ * up and can now take the lock. Until the lock is taken (bit 0
+ * cleared) a competing higher priority thread can steal the lock
+ * which puts the woken up thread back on the waiters list.
+ *
+ * The fast atomic compare exchange based acquire and release is only
+ * possible when bit 0 and 1 of lock->owner are 0.
+ *
+ * (*) There's a small time where the owner can be NULL and the
+ * "lock has waiters" bit is set.  This can happen when grabbing the lock.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to set this
+ * bit before looking at the lock, hence the reason this is a transitional
+ * state.
+ */
+
+static void
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
+		   unsigned long mask)
+{
+	unsigned long val = (unsigned long)owner | mask;
+
+	if (rt_mutex_has_waiters(lock))
+		val |= RT_MUTEX_HAS_WAITERS;
+
+	lock->owner = (struct task_struct *)val;
+}
+
+static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	lock->owner = (struct task_struct *)
+			((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
+}
+
+static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	if (!rt_mutex_has_waiters(lock))
+		clear_rt_mutex_waiters(lock);
+}
+
+/*
+ * We can speed up the acquire/release, if the architecture
+ * supports cmpxchg and if there's no debugging state to be set up
+ */
+#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+# define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+	do {
+		owner = *p;
+	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
+}
+#else
+# define rt_mutex_cmpxchg(l,c,n)	(0)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	lock->owner = (struct task_struct *)
+			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
+}
+#endif
+
+/*
+ * Calculate task priority from the waiter list priority
+ *
+ * Return task->normal_prio when the waiter list is empty or when
+ * the waiter is not allowed to do priority boosting
+ */
+int rt_mutex_getprio(struct task_struct *task)
+{
+	if (likely(!task_has_pi_waiters(task)))
+		return task->normal_prio;
+
+	return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+		   task->normal_prio);
+}
+
+/*
+ * Adjust the priority of a task, after its pi_waiters got modified.
+ *
+ * This can be both boosting and unboosting. task->pi_lock must be held.
+ */
+static void __rt_mutex_adjust_prio(struct task_struct *task)
+{
+	int prio = rt_mutex_getprio(task);
+
+	if (task->prio != prio)
+		rt_mutex_setprio(task, prio);
+}
+
+/*
+ * Adjust task priority (undo boosting). Called from the exit path of
+ * rt_mutex_slowunlock() and rt_mutex_slowlock().
+ *
+ * (Note: We do this outside of the protection of lock->wait_lock to
+ * allow the lock to be taken while or before we readjust the priority
+ * of task. We do not use the spin_xx_mutex() variants here as we are
+ * outside of the debug path.)
+ */
+static void rt_mutex_adjust_prio(struct task_struct *task)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&task->pi_lock, flags);
+	__rt_mutex_adjust_prio(task);
+	spin_unlock_irqrestore(&task->pi_lock, flags);
+}
+
+/*
+ * Max number of times we'll walk the boosting chain:
+ */
+int max_lock_depth = 1024;
+
+/*
+ * Adjust the priority chain. Also used for deadlock detection.
+ * Decreases task's usage by one - may thus free the task.
+ * Returns 0 or -EDEADLK.
+ */
+static int rt_mutex_adjust_prio_chain(task_t *task,
+				      int deadlock_detect,
+				      struct rt_mutex *orig_lock,
+				      struct rt_mutex_waiter *orig_waiter
+				      __IP_DECL__)
+{
+	struct rt_mutex *lock;
+	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
+	int detect_deadlock, ret = 0, depth = 0;
+	unsigned long flags;
+
+	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
+							 deadlock_detect);
+
+	/*
+	 * The (de)boosting is a step by step approach with a lot of
+	 * pitfalls. We want this to be preemptible and we want hold a
+	 * maximum of two locks per step. So we have to check
+	 * carefully whether things change under us.
+	 */
+ again:
+	if (++depth > max_lock_depth) {
+		static int prev_max;
+
+		/*
+		 * Print this only once. If the admin changes the limit,
+		 * print a new message when reaching the limit again.
+		 */
+		if (prev_max != max_lock_depth) {
+			prev_max = max_lock_depth;
+			printk(KERN_WARNING "Maximum lock depth %d reached "
+			       "task: %s (%d)\n", max_lock_depth,
+			       current->comm, current->pid);
+		}
+		put_task_struct(task);
+
+		return deadlock_detect ? -EDEADLK : 0;
+	}
+ retry:
+	/*
+	 * Task can not go away as we did a get_task() before !
+	 */
+	spin_lock_irqsave(&task->pi_lock, flags);
+
+	waiter = task->pi_blocked_on;
+	/*
+	 * Check whether the end of the boosting chain has been
+	 * reached or the state of the chain has changed while we
+	 * dropped the locks.
+	 */
+	if (!waiter || !waiter->task)
+		goto out_unlock_pi;
+
+	if (top_waiter && (!task_has_pi_waiters(task) ||
+			   top_waiter != task_top_pi_waiter(task)))
+		goto out_unlock_pi;
+
+	/*
+	 * When deadlock detection is off then we check, if further
+	 * priority adjustment is necessary.
+	 */
+	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+		goto out_unlock_pi;
+
+	lock = waiter->lock;
+	if (!spin_trylock(&lock->wait_lock)) {
+		spin_unlock_irqrestore(&task->pi_lock, flags);
+		cpu_relax();
+		goto retry;
+	}
+
+	/* Deadlock detection */
+	if (lock == orig_lock || rt_mutex_owner(lock) == current) {
+		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
+		spin_unlock(&lock->wait_lock);
+		ret = deadlock_detect ? -EDEADLK : 0;
+		goto out_unlock_pi;
+	}
+
+	top_waiter = rt_mutex_top_waiter(lock);
+
+	/* Requeue the waiter */
+	plist_del(&waiter->list_entry, &lock->wait_list);
+	waiter->list_entry.prio = task->prio;
+	plist_add(&waiter->list_entry, &lock->wait_list);
+
+	/* Release the task */
+	spin_unlock_irqrestore(&task->pi_lock, flags);
+	put_task_struct(task);
+
+	/* Grab the next task */
+	task = rt_mutex_owner(lock);
+	spin_lock_irqsave(&task->pi_lock, flags);
+
+	if (waiter == rt_mutex_top_waiter(lock)) {
+		/* Boost the owner */
+		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
+		waiter->pi_list_entry.prio = waiter->list_entry.prio;
+		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		__rt_mutex_adjust_prio(task);
+
+	} else if (top_waiter == waiter) {
+		/* Deboost the owner */
+		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+		waiter = rt_mutex_top_waiter(lock);
+		waiter->pi_list_entry.prio = waiter->list_entry.prio;
+		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		__rt_mutex_adjust_prio(task);
+	}
+
+	get_task_struct(task);
+	spin_unlock_irqrestore(&task->pi_lock, flags);
+
+	top_waiter = rt_mutex_top_waiter(lock);
+	spin_unlock(&lock->wait_lock);
+
+	if (!detect_deadlock && waiter != top_waiter)
+		goto out_put_task;
+
+	goto again;
+
+ out_unlock_pi:
+	spin_unlock_irqrestore(&task->pi_lock, flags);
+ out_put_task:
+	put_task_struct(task);
+	return ret;
+}
+
+/*
+ * Optimization: check if we can steal the lock from the
+ * assigned pending owner [which might not have taken the
+ * lock yet]:
+ */
+static inline int try_to_steal_lock(struct rt_mutex *lock)
+{
+	struct task_struct *pendowner = rt_mutex_owner(lock);
+	struct rt_mutex_waiter *next;
+	unsigned long flags;
+
+	if (!rt_mutex_owner_pending(lock))
+		return 0;
+
+	if (pendowner == current)
+		return 1;
+
+	spin_lock_irqsave(&pendowner->pi_lock, flags);
+	if (current->prio >= pendowner->prio) {
+		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+		return 0;
+	}
+
+	/*
+	 * Check if a waiter is enqueued on the pending owners
+	 * pi_waiters list. Remove it and readjust pending owners
+	 * priority.
+	 */
+	if (likely(!rt_mutex_has_waiters(lock))) {
+		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+		return 1;
+	}
+
+	/* No chain handling, pending owner is not blocked on anything: */
+	next = rt_mutex_top_waiter(lock);
+	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
+	__rt_mutex_adjust_prio(pendowner);
+	spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+
+	/*
+	 * We are going to steal the lock and a waiter was
+	 * enqueued on the pending owners pi_waiters queue. So
+	 * we have to enqueue this waiter into
+	 * current->pi_waiters list. This covers the case,
+	 * where current is boosted because it holds another
+	 * lock and gets unboosted because the booster is
+	 * interrupted, so we would delay a waiter with higher
+	 * priority as current->normal_prio.
+	 *
+	 * Note: in the rare case of a SCHED_OTHER task changing
+	 * its priority and thus stealing the lock, next->task
+	 * might be current:
+	 */
+	if (likely(next->task != current)) {
+		spin_lock_irqsave(&current->pi_lock, flags);
+		plist_add(&next->pi_list_entry, &current->pi_waiters);
+		__rt_mutex_adjust_prio(current);
+		spin_unlock_irqrestore(&current->pi_lock, flags);
+	}
+	return 1;
+}
+
+/*
+ * Try to take an rt-mutex
+ *
+ * This fails
+ * - when the lock has a real owner
+ * - when a different pending owner exists and has higher priority than current
+ *
+ * Must be called with lock->wait_lock held.
+ */
+static int try_to_take_rt_mutex(struct rt_mutex *lock __IP_DECL__)
+{
+	/*
+	 * We have to be careful here if the atomic speedups are
+	 * enabled, such that, when
+	 *  - no other waiter is on the lock
+	 *  - the lock has been released since we did the cmpxchg
+	 * the lock can be released or taken while we are doing the
+	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+	 *
+	 * The atomic acquire/release aware variant of
+	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
+	 * the WAITERS bit, the atomic release / acquire can not
+	 * happen anymore and lock->wait_lock protects us from the
+	 * non-atomic case.
+	 *
+	 * Note, that this might set lock->owner =
+	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
+	 * any more. This is fixed up when we take the ownership.
+	 * This is the transitional state explained at the top of this file.
+	 */
+	mark_rt_mutex_waiters(lock);
+
+	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+		return 0;
+
+	/* We got the lock. */
+	debug_rt_mutex_lock(lock __IP__);
+
+	rt_mutex_set_owner(lock, current, 0);
+
+	rt_mutex_deadlock_account_lock(lock, current);
+
+	return 1;
+}
+
+/*
+ * Task blocks on lock.
+ *
+ * Prepare waiter and propagate pi chain
+ *
+ * This must be called with lock->wait_lock held.
+ */
+static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
+				   struct rt_mutex_waiter *waiter,
+				   int detect_deadlock
+				   __IP_DECL__)
+{
+	struct rt_mutex_waiter *top_waiter = waiter;
+	task_t *owner = rt_mutex_owner(lock);
+	int boost = 0, res;
+	unsigned long flags;
+
+	spin_lock_irqsave(&current->pi_lock, flags);
+	__rt_mutex_adjust_prio(current);
+	waiter->task = current;
+	waiter->lock = lock;
+	plist_node_init(&waiter->list_entry, current->prio);
+	plist_node_init(&waiter->pi_list_entry, current->prio);
+
+	/* Get the top priority waiter on the lock */
+	if (rt_mutex_has_waiters(lock))
+		top_waiter = rt_mutex_top_waiter(lock);
+	plist_add(&waiter->list_entry, &lock->wait_list);
+
+	current->pi_blocked_on = waiter;
+
+	spin_unlock_irqrestore(&current->pi_lock, flags);
+
+	if (waiter == rt_mutex_top_waiter(lock)) {
+		spin_lock_irqsave(&owner->pi_lock, flags);
+		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
+		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+
+		__rt_mutex_adjust_prio(owner);
+		if (owner->pi_blocked_on) {
+			boost = 1;
+			get_task_struct(owner);
+		}
+		spin_unlock_irqrestore(&owner->pi_lock, flags);
+	}
+	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
+		spin_lock_irqsave(&owner->pi_lock, flags);
+		if (owner->pi_blocked_on) {
+			boost = 1;
+			get_task_struct(owner);
+		}
+		spin_unlock_irqrestore(&owner->pi_lock, flags);
+	}
+	if (!boost)
+		return 0;
+
+	spin_unlock(&lock->wait_lock);
+
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 waiter __IP__);
+
+	spin_lock(&lock->wait_lock);
+
+	return res;
+}
+
+/*
+ * Wake up the next waiter on the lock.
+ *
+ * Remove the top waiter from the current tasks waiter list and from
+ * the lock waiter list. Set it as pending owner. Then wake it up.
+ *
+ * Called with lock->wait_lock held.
+ */
+static void wakeup_next_waiter(struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter *waiter;
+	struct task_struct *pendowner;
+	unsigned long flags;
+
+	spin_lock_irqsave(&current->pi_lock, flags);
+
+	waiter = rt_mutex_top_waiter(lock);
+	plist_del(&waiter->list_entry, &lock->wait_list);
+
+	/*
+	 * Remove it from current->pi_waiters. We do not adjust a
+	 * possible priority boost right now. We execute wakeup in the
+	 * boosted mode and go back to normal after releasing
+	 * lock->wait_lock.
+	 */
+	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	pendowner = waiter->task;
+	waiter->task = NULL;
+
+	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+
+	spin_unlock_irqrestore(&current->pi_lock, flags);
+
+	/*
+	 * Clear the pi_blocked_on variable and enqueue a possible
+	 * waiter into the pi_waiters list of the pending owner. This
+	 * prevents that in case the pending owner gets unboosted a
+	 * waiter with higher priority than pending-owner->normal_prio
+	 * is blocked on the unboosted (pending) owner.
+	 */
+	spin_lock_irqsave(&pendowner->pi_lock, flags);
+
+	WARN_ON(!pendowner->pi_blocked_on);
+	WARN_ON(pendowner->pi_blocked_on != waiter);
+	WARN_ON(pendowner->pi_blocked_on->lock != lock);
+
+	pendowner->pi_blocked_on = NULL;
+
+	if (rt_mutex_has_waiters(lock)) {
+		struct rt_mutex_waiter *next;
+
+		next = rt_mutex_top_waiter(lock);
+		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
+	}
+	spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+
+	wake_up_process(pendowner);
+}
+
+/*
+ * Remove a waiter from a lock
+ *
+ * Must be called with lock->wait_lock held
+ */
+static void remove_waiter(struct rt_mutex *lock,
+			  struct rt_mutex_waiter *waiter  __IP_DECL__)
+{
+	int first = (waiter == rt_mutex_top_waiter(lock));
+	int boost = 0;
+	task_t *owner = rt_mutex_owner(lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&current->pi_lock, flags);
+	plist_del(&waiter->list_entry, &lock->wait_list);
+	waiter->task = NULL;
+	current->pi_blocked_on = NULL;
+	spin_unlock_irqrestore(&current->pi_lock, flags);
+
+	if (first && owner != current) {
+
+		spin_lock_irqsave(&owner->pi_lock, flags);
+
+		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+
+		if (rt_mutex_has_waiters(lock)) {
+			struct rt_mutex_waiter *next;
+
+			next = rt_mutex_top_waiter(lock);
+			plist_add(&next->pi_list_entry, &owner->pi_waiters);
+		}
+		__rt_mutex_adjust_prio(owner);
+
+		if (owner->pi_blocked_on) {
+			boost = 1;
+			get_task_struct(owner);
+		}
+		spin_unlock_irqrestore(&owner->pi_lock, flags);
+	}
+
+	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
+
+	if (!boost)
+		return;
+
+	spin_unlock(&lock->wait_lock);
+
+	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL __IP__);
+
+	spin_lock(&lock->wait_lock);
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+		  struct hrtimer_sleeper *timeout,
+		  int detect_deadlock __IP_DECL__)
+{
+	struct rt_mutex_waiter waiter;
+	int ret = 0;
+
+	debug_rt_mutex_init_waiter(&waiter);
+	waiter.task = NULL;
+
+	spin_lock(&lock->wait_lock);
+
+	/* Try to acquire the lock again: */
+	if (try_to_take_rt_mutex(lock __IP__)) {
+		spin_unlock(&lock->wait_lock);
+		return 0;
+	}
+
+	set_current_state(state);
+
+	/* Setup the timer, when timeout != NULL */
+	if (unlikely(timeout))
+		hrtimer_start(&timeout->timer, timeout->timer.expires,
+			      HRTIMER_ABS);
+
+	for (;;) {
+		/* Try to acquire the lock: */
+		if (try_to_take_rt_mutex(lock __IP__))
+			break;
+
+		/*
+		 * TASK_INTERRUPTIBLE checks for signals and
+		 * timeout. Ignored otherwise.
+		 */
+		if (unlikely(state == TASK_INTERRUPTIBLE)) {
+			/* Signal pending? */
+			if (signal_pending(current))
+				ret = -EINTR;
+			if (timeout && !timeout->task)
+				ret = -ETIMEDOUT;
+			if (ret)
+				break;
+		}
+
+		/*
+		 * waiter.task is NULL the first time we come here and
+		 * when we have been woken up by the previous owner
+		 * but the lock got stolen by a higher prio task.
+		 */
+		if (!waiter.task) {
+			ret = task_blocks_on_rt_mutex(lock, &waiter,
+						      detect_deadlock __IP__);
+			/*
+			 * If we got woken up by the owner then start loop
+			 * all over without going into schedule to try
+			 * to get the lock now:
+			 */
+			if (unlikely(!waiter.task))
+				continue;
+
+			if (unlikely(ret))
+				break;
+		}
+		spin_unlock(&lock->wait_lock);
+
+		debug_rt_mutex_print_deadlock(&waiter);
+
+		schedule();
+
+		spin_lock(&lock->wait_lock);
+		set_current_state(state);
+	}
+
+	set_current_state(TASK_RUNNING);
+
+	if (unlikely(waiter.task))
+		remove_waiter(lock, &waiter __IP__);
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit
+	 * unconditionally. We might have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	spin_unlock(&lock->wait_lock);
+
+	/* Remove pending timer: */
+	if (unlikely(timeout))
+		hrtimer_cancel(&timeout->timer);
+
+	/*
+	 * Readjust priority, when we did not get the lock. We might
+	 * have been the pending owner and boosted. Since we did not
+	 * take the lock, the PI boost has to go.
+	 */
+	if (unlikely(ret))
+		rt_mutex_adjust_prio(current);
+
+	debug_rt_mutex_free_waiter(&waiter);
+
+	return ret;
+}
+
+/*
+ * Slow path try-lock function:
+ */
+static inline int
+rt_mutex_slowtrylock(struct rt_mutex *lock __IP_DECL__)
+{
+	int ret = 0;
+
+	spin_lock(&lock->wait_lock);
+
+	if (likely(rt_mutex_owner(lock) != current)) {
+
+		ret = try_to_take_rt_mutex(lock __IP__);
+		/*
+		 * try_to_take_rt_mutex() sets the lock waiters
+		 * bit unconditionally. Clean this up.
+		 */
+		fixup_rt_mutex_waiters(lock);
+	}
+
+	spin_unlock(&lock->wait_lock);
+
+	return ret;
+}
+
+/*
+ * Slow path to release a rt-mutex:
+ */
+static void __sched
+rt_mutex_slowunlock(struct rt_mutex *lock)
+{
+	spin_lock(&lock->wait_lock);
+
+	debug_rt_mutex_unlock(lock);
+
+	rt_mutex_deadlock_account_unlock(current);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		spin_unlock(&lock->wait_lock);
+		return;
+	}
+
+	wakeup_next_waiter(lock);
+
+	spin_unlock(&lock->wait_lock);
+
+	/* Undo pi boosting if necessary: */
+	rt_mutex_adjust_prio(current);
+}
+
+/*
+ * 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 inline int
+rt_mutex_fastlock(struct rt_mutex *lock, int state,
+		  int detect_deadlock,
+		  int (*slowfn)(struct rt_mutex *lock, int state,
+				struct hrtimer_sleeper *timeout,
+				int detect_deadlock __IP_DECL__))
+{
+	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+		rt_mutex_deadlock_account_lock(lock, current);
+		return 0;
+	} else
+		return slowfn(lock, state, NULL, detect_deadlock __RET_IP__);
+}
+
+static inline int
+rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
+			struct hrtimer_sleeper *timeout, int detect_deadlock,
+			int (*slowfn)(struct rt_mutex *lock, int state,
+				      struct hrtimer_sleeper *timeout,
+				      int detect_deadlock __IP_DECL__))
+{
+	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+		rt_mutex_deadlock_account_lock(lock, current);
+		return 0;
+	} else
+		return slowfn(lock, state, timeout, detect_deadlock __RET_IP__);
+}
+
+static inline int
+rt_mutex_fasttrylock(struct rt_mutex *lock,
+		     int (*slowfn)(struct rt_mutex *lock __IP_DECL__))
+{
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+		rt_mutex_deadlock_account_lock(lock, current);
+		return 1;
+	}
+	return slowfn(lock __RET_IP__);
+}
+
+static inline void
+rt_mutex_fastunlock(struct rt_mutex *lock,
+		    void (*slowfn)(struct rt_mutex *lock))
+{
+	if (likely(rt_mutex_cmpxchg(lock, current, NULL)))
+		rt_mutex_deadlock_account_unlock(current);
+	else
+		slowfn(lock);
+}
+
+/**
+ * rt_mutex_lock - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ */
+void __sched rt_mutex_lock(struct rt_mutex *lock)
+{
+	might_sleep();
+
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock);
+
+/**
+ * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
+ *
+ * @lock: 		the rt_mutex to be locked
+ * @detect_deadlock:	deadlock detection on/off
+ *
+ * Returns:
+ *  0 		on success
+ * -EINTR 	when interrupted by a signal
+ * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ */
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
+						 int detect_deadlock)
+{
+	might_sleep();
+
+	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
+				 detect_deadlock, rt_mutex_slowlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
+
+/**
+ * rt_mutex_lock_interruptible_ktime - lock a rt_mutex interruptible
+ *				       the timeout structure is provided
+ *				       by the caller
+ *
+ * @lock: 		the rt_mutex to be locked
+ * @timeout:		timeout structure or NULL (no timeout)
+ * @detect_deadlock:	deadlock detection on/off
+ *
+ * Returns:
+ *  0 		on success
+ * -EINTR 	when interrupted by a signal
+ * -ETIMEOUT	when the timeout expired
+ * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ */
+int
+rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
+		    int detect_deadlock)
+{
+	might_sleep();
+
+	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
+				       detect_deadlock, rt_mutex_slowlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
+
+/**
+ * rt_mutex_trylock - try to lock a rt_mutex
+ *
+ * @lock:	the rt_mutex to be locked
+ *
+ * Returns 1 on success and 0 on contention
+ */
+int __sched rt_mutex_trylock(struct rt_mutex *lock)
+{
+	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
+}
+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)
+{
+	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_unlock);
+
+/***
+ * rt_mutex_destroy - mark a mutex unusable
+ * @lock: the mutex to be destroyed
+ *
+ * This function marks the mutex uninitialized, and any subsequent
+ * use of the mutex is forbidden. The mutex must not be locked when
+ * this function is called.
+ */
+void rt_mutex_destroy(struct rt_mutex *lock)
+{
+	WARN_ON(rt_mutex_is_locked(lock));
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	lock->magic = NULL;
+#endif
+}
+
+EXPORT_SYMBOL_GPL(rt_mutex_destroy);
+
+/**
+ * __rt_mutex_init - initialize the rt lock
+ *
+ * @lock: the rt lock to be initialized
+ *
+ * Initialize the rt lock to unlocked state.
+ *
+ * Initializing of a locked rt lock is not allowed
+ */
+void __rt_mutex_init(struct rt_mutex *lock, const char *name)
+{
+	lock->owner = NULL;
+	spin_lock_init(&lock->wait_lock);
+	plist_head_init(&lock->wait_list, &lock->wait_lock);
+
+	debug_rt_mutex_init(lock, name);
+}
+EXPORT_SYMBOL_GPL(__rt_mutex_init);
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
new file mode 100644
index 000000000000..1e0fca13ff72
--- /dev/null
+++ b/kernel/rtmutex.h
@@ -0,0 +1,29 @@
+/*
+ * RT-Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains macros used solely by rtmutex.c.
+ * Non-debug version.
+ */
+
+#define __IP_DECL__
+#define __IP__
+#define __RET_IP__
+#define rt_mutex_deadlock_check(l)			(0)
+#define rt_mutex_deadlock_account_lock(m, t)		do { } while (0)
+#define rt_mutex_deadlock_account_unlock(l)		do { } while (0)
+#define debug_rt_mutex_init_waiter(w)			do { } while (0)
+#define debug_rt_mutex_free_waiter(w)			do { } while (0)
+#define debug_rt_mutex_lock(l)				do { } while (0)
+#define debug_rt_mutex_proxy_lock(l,p)			do { } while (0)
+#define debug_rt_mutex_proxy_unlock(l)			do { } while (0)
+#define debug_rt_mutex_unlock(l)			do { } while (0)
+#define debug_rt_mutex_init(m, n)			do { } while (0)
+#define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
+#define debug_rt_mutex_print_deadlock(w)		do { } while (0)
+#define debug_rt_mutex_detect_deadlock(w,d)		(d)
+#define debug_rt_mutex_reset_waiter(w)			do { } while (0)
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
new file mode 100644
index 000000000000..50eed60eb085
--- /dev/null
+++ b/kernel/rtmutex_common.h
@@ -0,0 +1,93 @@
+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the private data structure and API definitions.
+ */
+
+#ifndef __KERNEL_RTMUTEX_COMMON_H
+#define __KERNEL_RTMUTEX_COMMON_H
+
+#include <linux/rtmutex.h>
+
+/*
+ * This is the control structure for tasks blocked on a rt_mutex,
+ * which is allocated on the kernel stack on of the blocked task.
+ *
+ * @list_entry:		pi node to enqueue into the mutex waiters list
+ * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @task:		task reference to the blocked task
+ */
+struct rt_mutex_waiter {
+	struct plist_node	list_entry;
+	struct plist_node	pi_list_entry;
+	struct task_struct	*task;
+	struct rt_mutex		*lock;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	unsigned long		ip;
+	pid_t			deadlock_task_pid;
+	struct rt_mutex		*deadlock_lock;
+#endif
+};
+
+/*
+ * Various helpers to access the waiters-plist:
+ */
+static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
+{
+	return !plist_head_empty(&lock->wait_list);
+}
+
+static inline struct rt_mutex_waiter *
+rt_mutex_top_waiter(struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter *w;
+
+	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
+			       list_entry);
+	BUG_ON(w->lock != lock);
+
+	return w;
+}
+
+static inline int task_has_pi_waiters(struct task_struct *p)
+{
+	return !plist_head_empty(&p->pi_waiters);
+}
+
+static inline struct rt_mutex_waiter *
+task_top_pi_waiter(struct task_struct *p)
+{
+	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
+				  pi_list_entry);
+}
+
+/*
+ * lock->owner state tracking:
+ */
+#define RT_MUTEX_OWNER_PENDING	1UL
+#define RT_MUTEX_HAS_WAITERS	2UL
+#define RT_MUTEX_OWNER_MASKALL	3UL
+
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
+{
+	return (struct task_struct *)
+		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
+}
+
+static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
+{
+ 	return (struct task_struct *)
+		((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
+}
+
+static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
+{
+	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
+}
+
+#endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f54afed8426f..93a2c5398648 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -133,6 +133,10 @@ extern int acct_parm[];
 extern int no_unaligned_warning;
 #endif
 
+#ifdef CONFIG_RT_MUTEXES
+extern int max_lock_depth;
+#endif
+
 static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t,
 		       ctl_table *, void **);
 static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
@@ -688,6 +692,17 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_RT_MUTEXES
+	{
+		.ctl_name	= KERN_MAX_LOCK_DEPTH,
+		.procname	= "max_lock_depth",
+		.data		= &max_lock_depth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+
 	{ .ctl_name = 0 }
 };