* See Documentation/rt-mutex-design.txt for details.
*/
#include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/sched.h>
+#include <linux/sched/rt.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.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
+ *
+ * owner bit0
+ * NULL 0 lock is free (fast acquire possible)
+ * NULL 1 lock is free and has waiters and the top waiter
+ * is going to take the lock*
+ * taskpointer 0 lock is held (fast release possible)
+ * taskpointer 1 lock is held and has waiters**
*
* The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 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.
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
+ *
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
*/
-void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
- unsigned long mask)
+static void
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
{
- unsigned long val = (unsigned long)owner | mask;
+ unsigned long val = (unsigned long)owner;
if (rt_mutex_has_waiters(lock))
val |= RT_MUTEX_HAS_WAITERS;
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);
+}
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+ __releases(lock->wait_lock)
+{
+ struct task_struct *owner = rt_mutex_owner(lock);
+
+ clear_rt_mutex_waiters(lock);
+ raw_spin_unlock(&lock->wait_lock);
+ /*
+ * If a new waiter comes in between the unlock and the cmpxchg
+ * we have two situations:
+ *
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * cmpxchg(p, owner, 0) == owner
+ * mark_rt_mutex_waiters(lock);
+ * acquire(lock);
+ * or:
+ *
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * mark_rt_mutex_waiters(lock);
+ *
+ * cmpxchg(p, owner, 0) != owner
+ * enqueue_waiter();
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * wake waiter();
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * acquire(lock);
+ */
+ return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
+#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);
+}
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+ __releases(lock->wait_lock)
+{
+ lock->owner = NULL;
+ raw_spin_unlock(&lock->wait_lock);
+ return true;
+}
+#endif
+
/*
* Calculate task priority from the waiter list priority
*
*
* This can be both boosting and unboosting. task->pi_lock must be held.
*/
-void __rt_mutex_adjust_prio(struct task_struct *task)
+static void __rt_mutex_adjust_prio(struct task_struct *task)
{
int prio = rt_mutex_getprio(task);
{
unsigned long flags;
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
/*
*/
int max_lock_depth = 1024;
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+ return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
/*
* Adjust the priority chain. Also used for deadlock detection.
* Decreases task's usage by one - may thus free the task.
* Returns 0 or -EDEADLK.
*/
-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)
+static int rt_mutex_adjust_prio_chain(struct task_struct *task,
+ int deadlock_detect,
+ struct rt_mutex *orig_lock,
+ struct rt_mutex *next_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;
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);
+ top_task->comm, task_pid_nr(top_task));
}
put_task_struct(task);
- return deadlock_detect ? -EDEADLK : 0;
+ return -EDEADLK;
}
retry:
/*
* Task can not go away as we did a get_task() before !
*/
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
/*
* reached or the state of the chain has changed while we
* dropped the locks.
*/
- if (!waiter || !waiter->task)
+ if (!waiter)
goto out_unlock_pi;
- if (top_waiter && (!task_has_pi_waiters(task) ||
- top_waiter != task_top_pi_waiter(task)))
+ /*
+ * Check the orig_waiter state. After we dropped the locks,
+ * the previous owner of the lock might have released the lock.
+ */
+ if (orig_waiter && !rt_mutex_owner(orig_lock))
goto out_unlock_pi;
+ /*
+ * We dropped all locks after taking a refcount on @task, so
+ * the task might have moved on in the lock chain or even left
+ * the chain completely and blocks now on an unrelated lock or
+ * on @orig_lock.
+ *
+ * We stored the lock on which @task was blocked in @next_lock,
+ * so we can detect the chain change.
+ */
+ if (next_lock != waiter->lock)
+ 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) {
+ if (!task_has_pi_waiters(task))
+ goto out_unlock_pi;
+ /*
+ * If deadlock detection is off, we stop here if we
+ * are not the top pi waiter of the task.
+ */
+ if (!detect_deadlock && 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.
goto out_unlock_pi;
lock = waiter->lock;
- if (!spin_trylock(&lock->wait_lock)) {
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!raw_spin_trylock(&lock->wait_lock)) {
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
cpu_relax();
goto retry;
}
- /* Deadlock detection */
+ /*
+ * Deadlock detection. If the lock is the same as the original
+ * lock which caused us to walk the lock chain or if the
+ * current lock is owned by the task which initiated the chain
+ * walk, we detected a deadlock.
+ */
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;
+ raw_spin_unlock(&lock->wait_lock);
+ ret = -EDEADLK;
goto out_unlock_pi;
}
plist_add(&waiter->list_entry, &lock->wait_list);
/* Release the task */
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!rt_mutex_owner(lock)) {
+ /*
+ * If the requeue above changed the top waiter, then we need
+ * to wake the new top waiter up to try to get the lock.
+ */
+
+ if (top_waiter != rt_mutex_top_waiter(lock))
+ wake_up_process(rt_mutex_top_waiter(lock)->task);
+ raw_spin_unlock(&lock->wait_lock);
+ goto out_put_task;
+ }
put_task_struct(task);
/* Grab the next task */
task = rt_mutex_owner(lock);
get_task_struct(task);
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
__rt_mutex_adjust_prio(task);
}
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ /*
+ * Check whether the task which owns the current lock is pi
+ * blocked itself. If yes we store a pointer to the lock for
+ * the lock chain change detection above. After we dropped
+ * task->pi_lock next_lock cannot be dereferenced anymore.
+ */
+ next_lock = task_blocked_on_lock(task);
+
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
top_waiter = rt_mutex_top_waiter(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
+
+ /*
+ * We reached the end of the lock chain. Stop right here. No
+ * point to go back just to figure that out.
+ */
+ if (!next_lock)
+ goto out_put_task;
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
goto again;
out_unlock_pi:
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_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(¤t->pi_lock, flags);
- plist_add(&next->pi_list_entry, ¤t->pi_waiters);
- __rt_mutex_adjust_prio(current);
- spin_unlock_irqrestore(¤t->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.
+ *
+ * @lock: the lock to be acquired.
+ * @task: the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
*/
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+ struct rt_mutex_waiter *waiter)
{
/*
* We have to be careful here if the atomic speedups are
*/
mark_rt_mutex_waiters(lock);
- if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+ if (rt_mutex_owner(lock))
return 0;
+ /*
+ * It will get the lock because of one of these conditions:
+ * 1) there is no waiter
+ * 2) higher priority than waiters
+ * 3) it is top waiter
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (!waiter || waiter != rt_mutex_top_waiter(lock))
+ return 0;
+ }
+ }
+
+ if (waiter || rt_mutex_has_waiters(lock)) {
+ unsigned long flags;
+ struct rt_mutex_waiter *top;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+ /* remove the queued waiter. */
+ if (waiter) {
+ plist_del(&waiter->list_entry, &lock->wait_list);
+ task->pi_blocked_on = NULL;
+ }
+
+ /*
+ * We have to enqueue the top waiter(if it exists) into
+ * task->pi_waiters list.
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ top = rt_mutex_top_waiter(lock);
+ top->pi_list_entry.prio = top->list_entry.prio;
+ plist_add(&top->pi_list_entry, &task->pi_waiters);
+ }
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ }
+
/* We got the lock. */
debug_rt_mutex_lock(lock);
- rt_mutex_set_owner(lock, current, 0);
+ rt_mutex_set_owner(lock, task);
- rt_mutex_deadlock_account_lock(lock, current);
+ rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
*/
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
+ struct task_struct *task,
int detect_deadlock)
{
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex_waiter *top_waiter = waiter;
- unsigned long flags;
+ struct rt_mutex *next_lock;
int chain_walk = 0, res;
+ unsigned long flags;
+
+ /*
+ * Early deadlock detection. We really don't want the task to
+ * enqueue on itself just to untangle the mess later. It's not
+ * only an optimization. We drop the locks, so another waiter
+ * can come in before the chain walk detects the deadlock. So
+ * the other will detect the deadlock and return -EDEADLOCK,
+ * which is wrong, as the other waiter is not in a deadlock
+ * situation.
+ */
+ if (owner == task)
+ return -EDEADLK;
- spin_lock_irqsave(¤t->pi_lock, flags);
- __rt_mutex_adjust_prio(current);
- waiter->task = current;
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+ __rt_mutex_adjust_prio(task);
+ waiter->task = task;
waiter->lock = lock;
- plist_node_init(&waiter->list_entry, current->prio);
- plist_node_init(&waiter->pi_list_entry, current->prio);
+ plist_node_init(&waiter->list_entry, task->prio);
+ plist_node_init(&waiter->pi_list_entry, task->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;
+ task->pi_blocked_on = waiter;
- spin_unlock_irqrestore(¤t->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!owner)
+ return 0;
+
+ raw_spin_lock_irqsave(&owner->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)
chain_walk = 1;
- spin_unlock_irqrestore(&owner->pi_lock, flags);
- }
- else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+ } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
chain_walk = 1;
+ }
+
+ /* Store the lock on which owner is blocked or NULL */
+ next_lock = task_blocked_on_lock(owner);
- if (!chain_walk)
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ /*
+ * Even if full deadlock detection is on, if the owner is not
+ * blocked itself, we can avoid finding this out in the chain
+ * walk.
+ */
+ if (!chain_walk || !next_lock)
return 0;
/*
*/
get_task_struct(owner);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
- res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
- current);
+ res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+ next_lock, waiter, task);
- spin_lock(&lock->wait_lock);
+ raw_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.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * 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(¤t->pi_lock, flags);
+ raw_spin_lock_irqsave(¤t->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
* lock->wait_lock.
*/
plist_del(&waiter->pi_list_entry, ¤t->pi_waiters);
- pendowner = waiter->task;
- waiter->task = NULL;
-
- rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
-
- spin_unlock_irqrestore(¤t->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.
+ * As we are waking up the top waiter, and the waiter stays
+ * queued on the lock until it gets the lock, this lock
+ * obviously has waiters. Just set the bit here and this has
+ * the added benefit of forcing all new tasks into the
+ * slow path making sure no task of lower priority than
+ * the top waiter can steal this lock.
*/
- 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;
+ lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
- next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
- }
- spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- wake_up_process(pendowner);
+ /*
+ * It's safe to dereference waiter as it cannot go away as
+ * long as we hold lock->wait_lock. The waiter task needs to
+ * acquire it in order to dequeue the waiter.
+ */
+ wake_up_process(waiter->task);
}
/*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
*
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
*/
-void remove_waiter(struct rt_mutex *lock,
- struct rt_mutex_waiter *waiter)
+static void remove_waiter(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter)
{
int first = (waiter == rt_mutex_top_waiter(lock));
struct task_struct *owner = rt_mutex_owner(lock);
+ struct rt_mutex *next_lock = NULL;
unsigned long flags;
- int chain_walk = 0;
- spin_lock_irqsave(¤t->pi_lock, flags);
+ raw_spin_lock_irqsave(¤t->pi_lock, flags);
plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->task = NULL;
current->pi_blocked_on = NULL;
- spin_unlock_irqrestore(¤t->pi_lock, flags);
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- if (first && owner != current) {
+ if (!owner)
+ return;
+
+ if (first) {
- spin_lock_irqsave(&owner->pi_lock, flags);
+ raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
}
__rt_mutex_adjust_prio(owner);
- if (owner->pi_blocked_on)
- chain_walk = 1;
+ /* Store the lock on which owner is blocked or NULL */
+ next_lock = task_blocked_on_lock(owner);
- spin_unlock_irqrestore(&owner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
- if (!chain_walk)
+ if (!next_lock)
return;
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(owner);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
- rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+ rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
}
/*
void rt_mutex_adjust_pi(struct task_struct *task)
{
struct rt_mutex_waiter *waiter;
+ struct rt_mutex *next_lock;
unsigned long flags;
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
if (!waiter || waiter->list_entry.prio == task->prio) {
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
-
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ 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, 0, NULL, NULL, task);
+
+ rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
}
-/*
- * Slow path lock function:
+/**
+ * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * @lock: the rt_mutex to take
+ * @state: the state the task should block in (TASK_INTERRUPTIBLE
+ * or TASK_UNINTERRUPTIBLE)
+ * @timeout: the pre-initialized and started timer, or NULL for none
+ * @waiter: the pre-initialized rt_mutex_waiter
+ *
+ * lock->wait_lock must be held by the caller.
*/
static int __sched
-rt_mutex_slowlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- int detect_deadlock)
+__rt_mutex_slowlock(struct rt_mutex *lock, int state,
+ struct hrtimer_sleeper *timeout,
+ struct rt_mutex_waiter *waiter)
{
- 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)) {
- 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_MODE_ABS);
-
for (;;) {
/* Try to acquire the lock: */
- if (try_to_take_rt_mutex(lock))
+ if (try_to_take_rt_mutex(lock, current, waiter))
break;
/*
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);
- /*
- * 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)) {
- /*
- * Reset the return value. We might
- * have returned with -EDEADLK and the
- * owner released the lock while we
- * were walking the pi chain.
- */
- ret = 0;
- continue;
- }
- if (unlikely(ret))
- break;
- }
-
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
- debug_rt_mutex_print_deadlock(&waiter);
+ debug_rt_mutex_print_deadlock(waiter);
- if (waiter.task)
- schedule_rt_mutex(lock);
+ schedule_rt_mutex(lock);
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
set_current_state(state);
}
+ return ret;
+}
+
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+ struct rt_mutex_waiter *w)
+{
+ /*
+ * If the result is not -EDEADLOCK or the caller requested
+ * deadlock detection, nothing to do here.
+ */
+ if (res != -EDEADLOCK || detect_deadlock)
+ return;
+
+ /*
+ * Yell lowdly and stop the task right here.
+ */
+ rt_mutex_print_deadlock(w);
+ while (1) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+ }
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+ struct hrtimer_sleeper *timeout,
+ int detect_deadlock)
+{
+ struct rt_mutex_waiter waiter;
+ int ret = 0;
+
+ debug_rt_mutex_init_waiter(&waiter);
+
+ raw_spin_lock(&lock->wait_lock);
+
+ /* Try to acquire the lock again: */
+ if (try_to_take_rt_mutex(lock, current, NULL)) {
+ raw_spin_unlock(&lock->wait_lock);
+ return 0;
+ }
+
+ set_current_state(state);
+
+ /* Setup the timer, when timeout != NULL */
+ if (unlikely(timeout)) {
+ hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&timeout->timer))
+ timeout->task = NULL;
+ }
+
+ ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+ if (likely(!ret))
+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
+
set_current_state(TASK_RUNNING);
- if (unlikely(waiter.task))
+ if (unlikely(ret)) {
remove_waiter(lock, &waiter);
+ rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+ }
/*
* try_to_take_rt_mutex() sets the waiter bit
*/
fixup_rt_mutex_waiters(lock);
- spin_unlock(&lock->wait_lock);
+ raw_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;
{
int ret = 0;
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
if (likely(rt_mutex_owner(lock) != current)) {
- ret = try_to_take_rt_mutex(lock);
+ ret = try_to_take_rt_mutex(lock, current, NULL);
/*
* try_to_take_rt_mutex() sets the lock waiters
* bit unconditionally. Clean this up.
fixup_rt_mutex_waiters(lock);
}
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
return ret;
}
static void __sched
rt_mutex_slowunlock(struct rt_mutex *lock)
{
- spin_lock(&lock->wait_lock);
+ raw_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;
+ /*
+ * We must be careful here if the fast path is enabled. If we
+ * have no waiters queued we cannot set owner to NULL here
+ * because of:
+ *
+ * foo->lock->owner = NULL;
+ * rtmutex_lock(foo->lock); <- fast path
+ * free = atomic_dec_and_test(foo->refcnt);
+ * rtmutex_unlock(foo->lock); <- fast path
+ * if (free)
+ * kfree(foo);
+ * raw_spin_unlock(foo->lock->wait_lock);
+ *
+ * So for the fastpath enabled kernel:
+ *
+ * Nothing can set the waiters bit as long as we hold
+ * lock->wait_lock. So we do the following sequence:
+ *
+ * owner = rt_mutex_owner(lock);
+ * clear_rt_mutex_waiters(lock);
+ * raw_spin_unlock(&lock->wait_lock);
+ * if (cmpxchg(&lock->owner, owner, 0) == owner)
+ * return;
+ * goto retry;
+ *
+ * The fastpath disabled variant is simple as all access to
+ * lock->owner is serialized by lock->wait_lock:
+ *
+ * lock->owner = NULL;
+ * raw_spin_unlock(&lock->wait_lock);
+ */
+ while (!rt_mutex_has_waiters(lock)) {
+ /* Drops lock->wait_lock ! */
+ if (unlock_rt_mutex_safe(lock) == true)
+ return;
+ /* Relock the rtmutex and try again */
+ raw_spin_lock(&lock->wait_lock);
}
+ /*
+ * The wakeup next waiter path does not suffer from the above
+ * race. See the comments there.
+ */
wakeup_next_waiter(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
/* Undo pi boosting if necessary: */
rt_mutex_adjust_prio(current);
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
+ * rt_mutex_timed_lock - 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)
* Returns:
* 0 on success
* -EINTR when interrupted by a signal
- * -ETIMEOUT when the timeout expired
+ * -ETIMEDOUT when the timeout expired
* -EDEADLK when the lock would deadlock (when deadlock detection is on)
*/
int
}
EXPORT_SYMBOL_GPL(rt_mutex_unlock);
-/***
+/**
* rt_mutex_destroy - mark a mutex unusable
* @lock: the mutex to be destroyed
*
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);
+ raw_spin_lock_init(&lock->wait_lock);
+ plist_head_init(&lock->wait_list);
debug_rt_mutex_init(lock, name);
}
{
__rt_mutex_init(lock, NULL);
debug_rt_mutex_proxy_lock(lock, proxy_owner);
- rt_mutex_set_owner(lock, proxy_owner, 0);
+ rt_mutex_set_owner(lock, proxy_owner);
rt_mutex_deadlock_account_lock(lock, proxy_owner);
}
struct task_struct *proxy_owner)
{
debug_rt_mutex_proxy_unlock(lock);
- rt_mutex_set_owner(lock, NULL, 0);
+ rt_mutex_set_owner(lock, NULL);
rt_mutex_deadlock_account_unlock(proxy_owner);
}
+/**
+ * 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
+ * @detect_deadlock: perform deadlock detection (1) or not (0)
+ *
+ * Returns:
+ * 0 - task blocked on lock
+ * 1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter,
+ struct task_struct *task, int detect_deadlock)
+{
+ int ret;
+
+ raw_spin_lock(&lock->wait_lock);
+
+ if (try_to_take_rt_mutex(lock, task, NULL)) {
+ raw_spin_unlock(&lock->wait_lock);
+ return 1;
+ }
+
+ /* We enforce deadlock detection for futexes */
+ ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
+
+ 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;
+ }
+
+ if (unlikely(ret))
+ remove_waiter(lock, waiter);
+
+ raw_spin_unlock(&lock->wait_lock);
+
+ debug_rt_mutex_print_deadlock(waiter);
+
+ return ret;
+}
+
/**
* rt_mutex_next_owner - return the next owner of the lock
*
return rt_mutex_top_waiter(lock)->task;
}
+
+/**
+ * rt_mutex_finish_proxy_lock() - Complete 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
+ * @detect_deadlock: perform deadlock detection (1) or not (0)
+ *
+ * Complete the lock acquisition started our behalf by another thread.
+ *
+ * Returns:
+ * 0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ *
+ * Special API call for PI-futex requeue support
+ */
+int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *to,
+ struct rt_mutex_waiter *waiter,
+ int detect_deadlock)
+{
+ int ret;
+
+ raw_spin_lock(&lock->wait_lock);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+
+ set_current_state(TASK_RUNNING);
+
+ if (unlikely(ret))
+ remove_waiter(lock, 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(&lock->wait_lock);
+
+ return ret;
+}