/* * lock->owner state tracking: * * 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 of lock->owner is 0. * * (*) 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.
*/
if (rt_mutex_has_waiters(lock))
val |= RT_MUTEX_HAS_WAITERS;
return (struct task_struct *)val;
}
static __always_inline void
rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
{ /* * lock->wait_lock is held but explicit acquire semantics are needed * for a new lock owner so WRITE_ONCE is insufficient.
*/
xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner));
}
static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock)
{ /* lock->wait_lock is held so the unlock provides release semantics. */
WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL));
}
/* * The rbtree has no waiters enqueued, now make sure that the * lock->owner still has the waiters bit set, otherwise the * following can happen: * * CPU 0 CPU 1 CPU2 * l->owner=T1 * rt_mutex_lock(l) * lock(l->lock) * l->owner = T1 | HAS_WAITERS; * enqueue(T2) * boost() * unlock(l->lock) * block() * * rt_mutex_lock(l) * lock(l->lock) * l->owner = T1 | HAS_WAITERS; * enqueue(T3) * boost() * unlock(l->lock) * block() * signal(->T2) signal(->T3) * lock(l->lock) * dequeue(T2) * deboost() * unlock(l->lock) * lock(l->lock) * dequeue(T3) * ==> wait list is empty * deboost() * unlock(l->lock) * lock(l->lock) * fixup_rt_mutex_waiters() * if (wait_list_empty(l) { * l->owner = owner * owner = l->owner & ~HAS_WAITERS; * ==> l->owner = T1 * } * lock(l->lock) * rt_mutex_unlock(l) fixup_rt_mutex_waiters() * if (wait_list_empty(l) { * owner = l->owner & ~HAS_WAITERS; * cmpxchg(l->owner, T1, NULL) * ===> Success (l->owner = NULL) * * l->owner = owner * ==> l->owner = T1 * } * * With the check for the waiter bit in place T3 on CPU2 will not * overwrite. All tasks fiddling with the waiters bit are * serialized by l->lock, so nothing else can modify the waiters * bit. If the bit is set then nothing can change l->owner either * so the simple RMW is safe. The cmpxchg() will simply fail if it * happens in the middle of the RMW because the waiters bit is * still set.
*/
owner = READ_ONCE(*p); if (owner & RT_MUTEX_HAS_WAITERS) { /* * See rt_mutex_set_owner() and rt_mutex_clear_owner() on * why xchg_acquire() is used for updating owner for * locking and WRITE_ONCE() for unlocking. * * WRITE_ONCE() would work for the acquire case too, but * in case that the lock acquisition failed it might * force other lockers into the slow path unnecessarily.
*/ if (acquire_lock)
xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS); else
WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
}
}
/* * We can speed up the acquire/release, if there's no debugging state to be * set up.
*/ #ifndef CONFIG_DEBUG_RT_MUTEXES static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock, struct task_struct *old, struct task_struct *new)
{ return try_cmpxchg_acquire(&lock->owner, &old, new);
}
/* * Callers must hold the ->wait_lock -- which is the whole purpose as we force * all future threads that attempt to [Rmw] the lock to the slowpath. As such * relaxed semantics suffice.
*/ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock)
{ unsignedlong *p = (unsignedlong *) &lock->owner; unsignedlong owner, new;
owner = READ_ONCE(*p); do { new = owner | RT_MUTEX_HAS_WAITERS;
} while (!try_cmpxchg_relaxed(p, &owner, new));
/* * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE * operations in the event of contention. Ensure the successful * cmpxchg is visible.
*/
smp_mb__after_atomic();
}
/* * Safe fastpath aware unlock: * 1) Clear the waiters bit * 2) Drop lock->wait_lock * 3) Try to unlock the lock with cmpxchg
*/ static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex_base *lock, unsignedlong flags)
__releases(lock->wait_lock)
{ struct task_struct *owner = rt_mutex_owner(lock);
clear_rt_mutex_waiters(lock);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* * 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_release(lock, owner, NULL);
}
static __always_inline bool rt_mutex_try_acquire(struct rt_mutex_base *lock)
{ /* * With debug enabled rt_mutex_cmpxchg trylock() will always fail. * * Avoid unconditionally taking the slow path by using * rt_mutex_slow_trylock() which is covered by the debug code and can * acquire a non-contended rtmutex.
*/ return rt_mutex_slowtrylock(lock);
}
/* * Only use with rt_waiter_node_{less,equal}()
*/ #define task_to_waiter_node(p) \
&(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline } #define task_to_waiter(p) \
&(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left, struct rt_waiter_node *right)
{ if (left->prio < right->prio) return 1;
/* * If both waiters have dl_prio(), we check the deadlines of the * associated tasks. * If left waiter has a dl_prio(), and we didn't return 1 above, * then right waiter has a dl_prio() too.
*/ if (dl_prio(left->prio)) return dl_time_before(left->deadline, right->deadline);
return 0;
}
static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left, struct rt_waiter_node *right)
{ if (left->prio != right->prio) return 0;
/* * If both waiters have dl_prio(), we check the deadlines of the * associated tasks. * If left waiter has a dl_prio(), and we didn't return 0 above, * then right waiter has a dl_prio() too.
*/ if (dl_prio(left->prio)) return left->deadline == right->deadline;
#ifdef RT_MUTEX_BUILD_SPINLOCKS /* * Note that RT tasks are excluded from same priority (lateral) * steals to prevent the introduction of an unbounded latency.
*/ if (rt_or_dl_prio(waiter->tree.prio)) returnfalse;
if (!wake_q_empty(&wqh->head))
wake_up_q(&wqh->head);
/* Pairs with preempt_disable() in mark_wakeup_next_waiter() */
preempt_enable();
}
/* * Deadlock detection is conditional: * * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted * if the detect argument is == RT_MUTEX_FULL_CHAINWALK. * * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always * conducted independent of the detect argument. * * If the waiter argument is NULL this indicates the deboost path and * deadlock detection is disabled independent of the detect argument * and the config settings.
*/ static __always_inline bool
rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk chwalk)
{ if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) return waiter != NULL; return chwalk == RT_MUTEX_FULL_CHAINWALK;
}
/* * Adjust the priority chain. Also used for deadlock detection. * Decreases task's usage by one - may thus free the task. * * @task: the task owning the mutex (owner) for which a chain walk is * probably needed * @chwalk: do we have to carry out deadlock detection? * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck * things for a task that has just got its priority adjusted, and * is waiting on a mutex) * @next_lock: the mutex on which the owner of @orig_lock was blocked before * we dropped its pi_lock. Is never dereferenced, only used for * comparison to detect lock chain changes. * @orig_waiter: rt_mutex_waiter struct for the task that has just donated * its priority to the mutex owner (can be NULL in the case * depicted above or if the top waiter is gone away and we are * actually deboosting the owner) * @top_task: the current top waiter * * Returns 0 or -EDEADLK. * * Chain walk basics and protection scope * * [R] refcount on task * [Pn] task->pi_lock held * [L] rtmutex->wait_lock held * * Normal locking order: * * rtmutex->wait_lock * task->pi_lock * * Step Description Protected by * function arguments: * @task [R] * @orig_lock if != NULL @top_task is blocked on it * @next_lock Unprotected. Cannot be * dereferenced. Only used for * comparison. * @orig_waiter if != NULL @top_task is blocked on it * @top_task current, or in case of proxy * locking protected by calling * code * again: * loop_sanity_check(); * retry: * [1] lock(task->pi_lock); [R] acquire [P1] * [2] waiter = task->pi_blocked_on; [P1] * [3] check_exit_conditions_1(); [P1] * [4] lock = waiter->lock; [P1] * [5] if (!try_lock(lock->wait_lock)) { [P1] try to acquire [L] * unlock(task->pi_lock); release [P1] * goto retry; * } * [6] check_exit_conditions_2(); [P1] + [L] * [7] requeue_lock_waiter(lock, waiter); [P1] + [L] * [8] unlock(task->pi_lock); release [P1] * put_task_struct(task); release [R] * [9] check_exit_conditions_3(); [L] * [10] task = owner(lock); [L] * get_task_struct(task); [L] acquire [R] * lock(task->pi_lock); [L] acquire [P2] * [11] requeue_pi_waiter(tsk, waiters(lock));[P2] + [L] * [12] check_exit_conditions_4(); [P2] + [L] * [13] unlock(task->pi_lock); release [P2] * unlock(lock->wait_lock); release [L] * goto again; * * Where P1 is the blocking task and P2 is the lock owner; going up one step * the owner becomes the next blocked task etc.. * *
*/ staticint __sched rt_mutex_adjust_prio_chain(struct task_struct *task, enum rtmutex_chainwalk chwalk, struct rt_mutex_base *orig_lock, struct rt_mutex_base *next_lock, struct rt_mutex_waiter *orig_waiter, struct task_struct *top_task)
{ struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; struct rt_mutex_waiter *prerequeue_top_waiter; int ret = 0, depth = 0; struct rt_mutex_base *lock; bool detect_deadlock; bool requeue = true;
/* * 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: /* * We limit the lock chain length for each invocation.
*/ if (++depth > max_lock_depth) { staticint 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, task_pid_nr(top_task));
}
put_task_struct(task);
return -EDEADLK;
}
/* * We are fully preemptible here and only hold the refcount on * @task. So everything can have changed under us since the * caller or our own code below (goto retry/again) dropped all * locks.
*/
retry: /* * [1] Task cannot go away as we did a get_task() before !
*/
raw_spin_lock_irq(&task->pi_lock);
/* * [2] Get the waiter on which @task is blocked on.
*/
waiter = task->pi_blocked_on;
/* * [3] check_exit_conditions_1() protected by task->pi_lock.
*/
/* * 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) 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.
*/ 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;
/* * There could be 'spurious' loops in the lock graph due to ww_mutex, * consider: * * P1: A, ww_A, ww_B * P2: ww_B, ww_A * P3: A * * P3 should not return -EDEADLK because it gets trapped in the cycle * created by P1 and P2 (which will resolve -- and runs into * max_lock_depth above). Therefore disable detect_deadlock such that * the below termination condition can trigger once all relevant tasks * are boosted. * * Even when we start with ww_mutex we can disable deadlock detection, * since we would supress a ww_mutex induced deadlock at [6] anyway. * Supressing it here however is not sufficient since we might still * hit [6] due to adjustment driven iteration. * * NOTE: if someone were to create a deadlock between 2 ww_classes we'd * utterly fail to report it; lockdep should.
*/ if (IS_ENABLED(CONFIG_PREEMPT_RT) && waiter->ww_ctx && detect_deadlock)
detect_deadlock = false;
/* * 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 deadlock * detection is enabled we continue, but stop the * requeueing in the chain walk.
*/ if (top_waiter != task_top_pi_waiter(task)) { if (!detect_deadlock) goto out_unlock_pi; else
requeue = false;
}
}
/* * If the waiter priority is the same as the task priority * then there is no further priority adjustment necessary. If * deadlock detection is off, we stop the chain walk. If its * enabled we continue, but stop the requeueing in the chain * walk.
*/ if (rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) { if (!detect_deadlock) goto out_unlock_pi; else
requeue = false;
}
/* * [4] Get the next lock; per holding task->pi_lock we can't unblock * and guarantee @lock's existence.
*/
lock = waiter->lock; /* * [5] We need to trylock here as we are holding task->pi_lock, * which is the reverse lock order versus the other rtmutex * operations. * * Per the above, holding task->pi_lock guarantees lock exists, so * inverting this lock order is infeasible from a life-time * perspective.
*/ if (!raw_spin_trylock(&lock->wait_lock)) {
raw_spin_unlock_irq(&task->pi_lock);
cpu_relax(); goto retry;
}
/* * [6] check_exit_conditions_2() protected by task->pi_lock and * lock->wait_lock. * * 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) {
ret = -EDEADLK;
/* * When the deadlock is due to ww_mutex; also see above. Don't * report the deadlock and instead let the ww_mutex wound/die * logic pick which of the contending threads gets -EDEADLK. * * NOTE: assumes the cycle only contains a single ww_class; any * other configuration and we fail to report; also, see * lockdep.
*/ if (IS_ENABLED(CONFIG_PREEMPT_RT) && orig_waiter && orig_waiter->ww_ctx)
ret = 0;
/* * If we just follow the lock chain for deadlock detection, no * need to do all the requeue operations. To avoid a truckload * of conditionals around the various places below, just do the * minimum chain walk checks.
*/ if (!requeue) { /* * No requeue[7] here. Just release @task [8]
*/
raw_spin_unlock(&task->pi_lock);
put_task_struct(task);
/* * [9] check_exit_conditions_3 protected by lock->wait_lock. * If there is no owner of the lock, end of chain.
*/ if (!rt_mutex_owner(lock)) {
raw_spin_unlock_irq(&lock->wait_lock); return 0;
}
/* [10] Grab the next task, i.e. owner of @lock */
task = get_task_struct(rt_mutex_owner(lock));
raw_spin_lock(&task->pi_lock);
/* * No requeue [11] here. We just do deadlock detection. * * [12] Store whether owner is blocked * itself. Decision is made after dropping the locks
*/
next_lock = task_blocked_on_lock(task); /* * Get the top waiter for the next iteration
*/
top_waiter = rt_mutex_top_waiter(lock);
/* [13] Drop locks */
raw_spin_unlock(&task->pi_lock);
raw_spin_unlock_irq(&lock->wait_lock);
/* If owner is not blocked, end of chain. */ if (!next_lock) goto out_put_task; goto again;
}
/* * Store the current top waiter before doing the requeue * operation on @lock. We need it for the boost/deboost * decision below.
*/
prerequeue_top_waiter = rt_mutex_top_waiter(lock);
/* [7] Requeue the waiter in the lock waiter tree. */
rt_mutex_dequeue(lock, waiter);
/* * Update the waiter prio fields now that we're dequeued. * * These values can have changed through either: * * sys_sched_set_scheduler() / sys_sched_setattr() * * or * * DL CBS enforcement advancing the effective deadline.
*/
waiter_update_prio(waiter, task);
rt_mutex_enqueue(lock, waiter);
/* * [8] Release the (blocking) task in preparation for * taking the owner task in [10]. * * Since we hold lock->waiter_lock, task cannot unblock, even if we * release task->pi_lock.
*/
raw_spin_unlock(&task->pi_lock);
put_task_struct(task);
/* * [9] check_exit_conditions_3 protected by lock->wait_lock. * * We must abort the chain walk if there is no lock owner even * in the dead lock detection case, as we have nothing to * follow here. This is the end of the chain we are walking.
*/ if (!rt_mutex_owner(lock)) { /* * If the requeue [7] above changed the top waiter, * then we need to wake the new top waiter up to try * to get the lock.
*/
top_waiter = rt_mutex_top_waiter(lock); if (prerequeue_top_waiter != top_waiter)
wake_up_state(top_waiter->task, top_waiter->wake_state);
raw_spin_unlock_irq(&lock->wait_lock); return 0;
}
/* * [10] Grab the next task, i.e. the owner of @lock * * Per holding lock->wait_lock and checking for !owner above, there * must be an owner and it cannot go away.
*/
task = get_task_struct(rt_mutex_owner(lock));
raw_spin_lock(&task->pi_lock);
/* [11] requeue the pi waiters if necessary */ if (waiter == rt_mutex_top_waiter(lock)) { /* * The waiter became the new top (highest priority) * waiter on the lock. Replace the previous top waiter * in the owner tasks pi waiters tree with this waiter * and adjust the priority of the owner.
*/
rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
waiter_clone_prio(waiter, task);
rt_mutex_enqueue_pi(task, waiter);
rt_mutex_adjust_prio(lock, task);
} elseif (prerequeue_top_waiter == waiter) { /* * The waiter was the top waiter on the lock, but is * no longer the top priority waiter. Replace waiter in * the owner tasks pi waiters tree with the new top * (highest priority) waiter and adjust the priority * of the owner. * The new top waiter is stored in @waiter so that * @waiter == @top_waiter evaluates to true below and * we continue to deboost the rest of the chain.
*/
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
waiter_clone_prio(waiter, task);
rt_mutex_enqueue_pi(task, waiter);
rt_mutex_adjust_prio(lock, task);
} else { /* * Nothing changed. No need to do any priority * adjustment.
*/
}
/* * [12] check_exit_conditions_4() protected by task->pi_lock * and lock->wait_lock. The actual decisions are made after we * dropped the locks. * * 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); /* * Store the top waiter of @lock for the end of chain walk * decision below.
*/
top_waiter = rt_mutex_top_waiter(lock);
/* [13] Drop the locks */
raw_spin_unlock(&task->pi_lock);
raw_spin_unlock_irq(&lock->wait_lock);
/* * Make the actual exit decisions [12], based on the stored * values. * * 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 the current waiter is not the top waiter on the lock, * then we can stop the chain walk here if we are not in full * deadlock detection mode.
*/ if (!detect_deadlock && waiter != top_waiter) goto out_put_task;
/* * Try to take an rt-mutex * * Must be called with lock->wait_lock held and interrupts disabled * * @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 tree if the * callsite called task_blocked_on_lock(), otherwise NULL
*/ staticint __sched
try_to_take_rt_mutex(struct rt_mutex_base *lock, struct task_struct *task, struct rt_mutex_waiter *waiter)
{
lockdep_assert_held(&lock->wait_lock);
/* * Before testing whether we can acquire @lock, we set the * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all * other tasks which try to modify @lock into the slow path * and they serialize on @lock->wait_lock. * * The RT_MUTEX_HAS_WAITERS bit can have a transitional state * as explained at the top of this file if and only if: * * - There is a lock owner. The caller must fixup the * transient state if it does a trylock or leaves the lock * function due to a signal or timeout. * * - @task acquires the lock and there are no other * waiters. This is undone in rt_mutex_set_owner(@task) at * the end of this function.
*/
mark_rt_mutex_waiters(lock);
/* * If @lock has an owner, give up.
*/ if (rt_mutex_owner(lock)) return 0;
/* * If @waiter != NULL, @task has already enqueued the waiter * into @lock waiter tree. If @waiter == NULL then this is a * trylock attempt.
*/ if (waiter) { struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock);
/* * If waiter is the highest priority waiter of @lock, * or allowed to steal it, take it over.
*/ if (waiter == top_waiter || rt_mutex_steal(waiter, top_waiter)) { /* * We can acquire the lock. Remove the waiter from the * lock waiters tree.
*/
rt_mutex_dequeue(lock, waiter);
} else { return 0;
}
} else { /* * If the lock has waiters already we check whether @task is * eligible to take over the lock. * * If there are no other waiters, @task can acquire * the lock. @task->pi_blocked_on is NULL, so it does * not need to be dequeued.
*/ if (rt_mutex_has_waiters(lock)) { /* Check whether the trylock can steal it. */ if (!rt_mutex_steal(task_to_waiter(task),
rt_mutex_top_waiter(lock))) return 0;
/* * The current top waiter stays enqueued. We * don't have to change anything in the lock * waiters order.
*/
} else { /* * No waiters. Take the lock without the * pi_lock dance.@task->pi_blocked_on is NULL * and we have no waiters to enqueue in @task * pi waiters tree.
*/ goto takeit;
}
}
/* * Clear @task->pi_blocked_on. Requires protection by * @task->pi_lock. Redundant operation for the @waiter == NULL * case, but conditionals are more expensive than a redundant * store.
*/
raw_spin_lock(&task->pi_lock);
task->pi_blocked_on = NULL; /* * Finish the lock acquisition. @task is the new owner. If * other waiters exist we have to insert the highest priority * waiter into @task->pi_waiters tree.
*/ if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
raw_spin_unlock(&task->pi_lock);
takeit: /* * This either preserves the RT_MUTEX_HAS_WAITERS bit if there * are still waiters or clears it.
*/
rt_mutex_set_owner(lock, task);
return 1;
}
/* * Task blocks on lock. * * Prepare waiter and propagate pi chain * * This must be called with lock->wait_lock held and interrupts disabled
*/ staticint __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task, struct ww_acquire_ctx *ww_ctx, enum rtmutex_chainwalk chwalk, struct wake_q_head *wake_q)
{ struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; struct rt_mutex_base *next_lock; int chain_walk = 0, res;
lockdep_assert_held(&lock->wait_lock);
/* * 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. * * Except for ww_mutex, in that case the chain walk must already deal * with spurious cycles, see the comments at [3] and [6].
*/ if (owner == task && !(build_ww_mutex() && ww_ctx)) return -EDEADLK;
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
raw_spin_unlock(&owner->pi_lock); /* * 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;
/* * The owner can't disappear while holding a lock, * so the owner struct is protected by wait_lock. * Gets dropped in rt_mutex_adjust_prio_chain()!
*/
get_task_struct(owner);
res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
next_lock, waiter, task);
raw_spin_lock_irq(&lock->wait_lock);
return res;
}
/* * Remove the top waiter from the current tasks pi waiter tree and * queue it up. * * Called with lock->wait_lock held and interrupts disabled.
*/ staticvoid __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh, struct rt_mutex_base *lock)
{ struct rt_mutex_waiter *waiter;
lockdep_assert_held(&lock->wait_lock);
raw_spin_lock(¤t->pi_lock);
waiter = rt_mutex_top_waiter(lock);
/* * Remove it from current->pi_waiters and deboost. * * We must in fact deboost here in order to ensure we call * rt_mutex_setprio() to update p->pi_top_task before the * task unblocks.
*/
rt_mutex_dequeue_pi(current, waiter);
rt_mutex_adjust_prio(lock, current);
/* * 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.
*/
lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
/* * We deboosted before waking the top waiter task such that we don't * run two tasks with the 'same' priority (and ensure the * p->pi_top_task pointer points to a blocked task). This however can * lead to priority inversion if we would get preempted after the * deboost but before waking our donor task, hence the preempt_disable() * before unlock. * * Pairs with preempt_enable() in rt_mutex_wake_up_q();
*/
preempt_disable();
rt_mutex_wake_q_add(wqh, waiter);
raw_spin_unlock(¤t->pi_lock);
}
staticint __sched __rt_mutex_slowtrylock(struct rt_mutex_base *lock)
{ int 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, true);
/* * If the lock already has an owner we fail to get the lock. * This can be done without taking the @lock->wait_lock as * it is only being read, and this is a trylock anyway.
*/ if (rt_mutex_owner(lock)) return 0;
/* * The mutex has currently no owner. Lock the wait lock and try to * acquire the lock. We use irqsave here to support early boot calls.
*/
raw_spin_lock_irqsave(&lock->wait_lock, flags);
static __always_inline int __rt_mutex_trylock(struct rt_mutex_base *lock)
{ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 1;
return rt_mutex_slowtrylock(lock);
}
/* * Slow path to release a rt-mutex.
*/ staticvoid __sched rt_mutex_slowunlock(struct rt_mutex_base *lock)
{
DEFINE_RT_WAKE_Q(wqh); unsignedlong flags;
/* irqsave required to support early boot calls */
raw_spin_lock_irqsave(&lock->wait_lock, flags);
debug_rt_mutex_unlock(lock);
/* * 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, flags) == true) return; /* Relock the rtmutex and try again */
raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
/* * The wakeup next waiter path does not suffer from the above * race. See the comments there. * * Queue the next waiter for wakeup once we release the wait_lock.
*/
mark_wakeup_next_waiter(&wqh, lock);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
rcu_read_lock(); for (;;) { /* If owner changed, trylock again. */ if (owner != rt_mutex_owner(lock)) break; /* * Ensure that @owner is dereferenced after checking that * the lock owner still matches @owner. If that fails, * @owner might point to freed memory. If it still matches, * the rcu_read_lock() ensures the memory stays valid.
*/
barrier(); /* * Stop spinning when: * - the lock owner has been scheduled out * - current is not longer the top waiter * - current is requested to reschedule (redundant * for CONFIG_PREEMPT_RCU=y) * - the VCPU on which owner runs is preempted
*/ if (!owner_on_cpu(owner) || need_resched() ||
!rt_mutex_waiter_is_top_waiter(lock, waiter)) {
res = false; break;
}
cpu_relax();
}
rcu_read_unlock(); return res;
} #else staticbool rtmutex_spin_on_owner(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *owner)
{ returnfalse;
} #endif
#ifdef RT_MUTEX_BUILD_MUTEX /* * Functions required for: * - rtmutex, futex on all kernels * - mutex and rwsem substitutions on RT kernels
*/
/* * Remove a waiter from a lock and give up * * Must be called with lock->wait_lock held and interrupts disabled. It must * have just failed to try_to_take_rt_mutex().
*/ staticvoid __sched remove_waiter(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter)
{ bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_base *next_lock;
/* * Only update priority if the waiter was the highest priority * waiter of the lock and there is an owner to update.
*/ if (!owner || !is_top_waiter) return;
raw_spin_lock(&owner->pi_lock);
rt_mutex_dequeue_pi(owner, waiter);
if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
rt_mutex_adjust_prio(lock, owner);
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
raw_spin_unlock(&owner->pi_lock);
/* * Don't walk the chain, if the owner task is not blocked * itself.
*/ if (!next_lock) return;
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(owner);
/** * rt_mutex_slowlock_block() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @ww_ctx: WW mutex context pointer * @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 * @wake_q: wake_q of tasks to wake when we drop the lock->wait_lock * * Must be called with lock->wait_lock held and interrupts disabled
*/ staticint __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, struct ww_acquire_ctx *ww_ctx, unsignedint state, struct hrtimer_sleeper *timeout, struct rt_mutex_waiter *waiter, struct wake_q_head *wake_q)
__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
{ struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex); struct task_struct *owner; int ret = 0;
lockevent_inc(rtmutex_slow_block); for (;;) { /* Try to acquire the lock: */ if (try_to_take_rt_mutex(lock, current, waiter)) {
lockevent_inc(rtmutex_slow_acq3); break;
}
if (timeout && !timeout->task) {
ret = -ETIMEDOUT; break;
} if (signal_pending_state(state, current)) {
ret = -EINTR; break;
}
if (build_ww_mutex() && ww_ctx) {
ret = __ww_mutex_check_kill(rtm, waiter, ww_ctx); if (ret) break;
}
staticvoid __sched rt_mutex_handle_deadlock(int res, int detect_deadlock, struct rt_mutex_base *lock, 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;
if (build_ww_mutex() && w->ww_ctx) return;
raw_spin_unlock_irq(&lock->wait_lock);
WARN(1, "rtmutex deadlock detected\n");
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
rt_mutex_schedule();
}
}
/** * __rt_mutex_slowlock - Locking slowpath invoked with lock::wait_lock held * @lock: The rtmutex to block lock * @ww_ctx: WW mutex context pointer * @state: The task state for sleeping * @chwalk: Indicator whether full or partial chainwalk is requested * @waiter: Initializer waiter for blocking * @wake_q: The wake_q to wake tasks after we release the wait_lock
*/ staticint __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, struct ww_acquire_ctx *ww_ctx, unsignedint state, enum rtmutex_chainwalk chwalk, struct rt_mutex_waiter *waiter, struct wake_q_head *wake_q)
{ struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex); struct ww_mutex *ww = ww_container_of(rtm); int ret;
/* * rt_mutex_slowlock - Locking slowpath invoked when fast path fails * @lock: The rtmutex to block lock * @ww_ctx: WW mutex context pointer * @state: The task state for sleeping
*/ staticint __sched rt_mutex_slowlock(struct rt_mutex_base *lock, struct ww_acquire_ctx *ww_ctx, unsignedint state)
{
DEFINE_WAKE_Q(wake_q); unsignedlong flags; int ret;
/* * Do all pre-schedule work here, before we queue a waiter and invoke * PI -- any such work that trips on rtlock (PREEMPT_RT spinlock) would * otherwise recurse back into task_blocks_on_rt_mutex() through * rtlock_slowlock() and will then enqueue a second waiter for this * same task and things get really confusing real fast.
*/
rt_mutex_pre_schedule();
/* * Technically we could use raw_spin_[un]lock_irq() here, but this can * be called in early boot if the cmpxchg() fast path is disabled * (debug, no architecture support). In this case we will acquire the * rtmutex with lock->wait_lock held. But we cannot unconditionally * enable interrupts in that early boot case. So we need to use the * irqsave/restore variants.
*/
raw_spin_lock_irqsave(&lock->wait_lock, flags);
ret = __rt_mutex_slowlock_locked(lock, ww_ctx, state, &wake_q);
raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
rt_mutex_post_schedule();
return ret;
}
static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock, unsignedint state)
{
lockdep_assert(!current->pi_blocked_on);
/* Restore the task state */
current_restore_rtlock_saved_state();
/* * try_to_take_rt_mutex() sets the waiter bit unconditionally. * We might have to fix that up:
*/
fixup_rt_mutex_waiters(lock, true);
debug_rt_mutex_free_waiter(&waiter);
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.