path: root/kernel/rtmutex.c

/*
 * 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
 *
 *  See Documentation/rt-mutex-design.txt for details.
 */
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>

#include "rtmutex_common.h"

/*
 * 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(struct task_struct *task,
				      int deadlock_detect,
				      struct rt_mutex *orig_lock,
				      struct rt_mutex_waiter *orig_waiter,
				      struct task_struct *top_task)
{
	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,
			       top_task->comm, top_task->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;

	/*
	 * Check the orig_waiter state. After we dropped the locks,
	 * the previous owner of the lock might have released the lock
	 * and made us the pending owner:
	 */
	if (orig_waiter && !orig_waiter->task)
		goto out_unlock_pi;

	/*
	 * Drop out, when the task has no waiters. Note,
	 * top_waiter can be NULL, when we are in the deboosting
	 * mode!
	 */
	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) == top_task) {
		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);
	get_task_struct(task);
	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);
	}

	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
 *'n1728' href='#n1728'>1728