sched/rtmutex: Refactor rt_mutex_setprio()

With the introduction of SCHED_DEADLINE the whole notion that priority
is a single number is gone, therefore the @prio argument to
rt_mutex_setprio() doesn't make sense anymore.

So rework the code to pass a pi_task instead.

Note this also fixes a problem with pi_top_task caching; previously we
would not set the pointer (call rt_mutex_update_top_task) if the
priority didn't change, this could lead to a stale pointer.

As for the XXX, I think its fine to use pi_task->prio, because if it
differs from waiter->prio, a PI chain update is immenent.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170323150216.303827095@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This commit is contained in:
Peter Zijlstra 2017-03-23 15:56:11 +01:00 committed by Thomas Gleixner
parent aa2bfe5536
commit acd58620e4
3 changed files with 91 additions and 111 deletions

View File

@ -18,28 +18,20 @@ static inline int rt_task(struct task_struct *p)
}
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
extern void rt_mutex_update_top_task(struct task_struct *p);
extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
/*
* Must hold either p->pi_lock or task_rq(p)->lock.
*/
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
{
return p->pi_top_task;
}
extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
return tsk->pi_blocked_on != NULL;
}
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
return p->normal_prio;
}
static inline int rt_mutex_get_effective_prio(struct task_struct *task,
int newprio)
{
return newprio;
}
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
{
return NULL;

View File

@ -322,67 +322,16 @@ rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
RB_CLEAR_NODE(&waiter->pi_tree_entry);
}
/*
* Must hold both p->pi_lock and task_rq(p)->lock.
*/
void rt_mutex_update_top_task(struct task_struct *p)
static void rt_mutex_adjust_prio(struct task_struct *p)
{
if (!task_has_pi_waiters(p)) {
p->pi_top_task = NULL;
return;
}
struct task_struct *pi_task = NULL;
p->pi_top_task = task_top_pi_waiter(p)->task;
}
lockdep_assert_held(&p->pi_lock);
/*
* Calculate task priority from the waiter tree priority
*
* Return task->normal_prio when the waiter tree 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;
if (task_has_pi_waiters(p))
pi_task = task_top_pi_waiter(p)->task;
return min(task_top_pi_waiter(task)->prio,
task->normal_prio);
}
/*
* Must hold either p->pi_lock or task_rq(p)->lock.
*/
struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
{
return task->pi_top_task;
}
/*
* Called by sched_setscheduler() to get the priority which will be
* effective after the change.
*/
int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
{
struct task_struct *top_task = rt_mutex_get_top_task(task);
if (!top_task)
return newprio;
return min(top_task->prio, newprio);
}
/*
* 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 || dl_prio(prio))
rt_mutex_setprio(task, prio);
rt_mutex_setprio(p, pi_task);
}
/*
@ -742,7 +691,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
*/
rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
rt_mutex_adjust_prio(task);
} else if (prerequeue_top_waiter == waiter) {
/*
@ -758,7 +707,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
rt_mutex_adjust_prio(task);
} else {
/*
* Nothing changed. No need to do any priority
@ -966,7 +915,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
return -EDEADLK;
raw_spin_lock(&task->pi_lock);
__rt_mutex_adjust_prio(task);
rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
waiter->prio = task->prio;
@ -988,7 +937,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
rt_mutex_dequeue_pi(owner, top_waiter);
rt_mutex_enqueue_pi(owner, waiter);
__rt_mutex_adjust_prio(owner);
rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
@ -1040,13 +989,14 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
waiter = rt_mutex_top_waiter(lock);
/*
* 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.
* 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(current);
rt_mutex_adjust_prio(current);
/*
* As we are waking up the top waiter, and the waiter stays
@ -1058,9 +1008,19 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
*/
lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
raw_spin_unlock(&current->pi_lock);
/*
* 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_postunlock();
*/
preempt_disable();
wake_q_add(wake_q, waiter->task);
raw_spin_unlock(&current->pi_lock);
}
/*
@ -1095,7 +1055,7 @@ static void remove_waiter(struct rt_mutex *lock,
if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
__rt_mutex_adjust_prio(owner);
rt_mutex_adjust_prio(owner);
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
@ -1134,8 +1094,7 @@ void rt_mutex_adjust_pi(struct task_struct *task)
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
if (!waiter || (waiter->prio == task->prio &&
!dl_prio(task->prio))) {
if (!waiter || (waiter->prio == task->prio && !dl_prio(task->prio))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
@ -1389,17 +1348,6 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
* Queue the next waiter for wakeup once we release the wait_lock.
*/
mark_wakeup_next_waiter(wake_q, lock);
/*
* We should deboost before waking the top waiter task such that
* we don't run two tasks with the 'same' priority. This however
* can lead to prio-inversion if we would get preempted after
* the deboost but before waking our high-prio task, hence the
* preempt_disable before unlock. Pairs with preempt_enable() in
* rt_mutex_postunlock();
*/
preempt_disable();
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
return true; /* call rt_mutex_postunlock() */

View File

@ -3671,10 +3671,25 @@ EXPORT_SYMBOL(default_wake_function);
#ifdef CONFIG_RT_MUTEXES
static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
{
if (pi_task)
prio = min(prio, pi_task->prio);
return prio;
}
static inline int rt_effective_prio(struct task_struct *p, int prio)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
return __rt_effective_prio(pi_task, prio);
}
/*
* rt_mutex_setprio - set the current priority of a task
* @p: task
* @prio: prio value (kernel-internal form)
* @p: task to boost
* @pi_task: donor task
*
* This function changes the 'effective' priority of a task. It does
* not touch ->normal_prio like __setscheduler().
@ -3682,18 +3697,42 @@ EXPORT_SYMBOL(default_wake_function);
* Used by the rt_mutex code to implement priority inheritance
* logic. Call site only calls if the priority of the task changed.
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
int oldprio, queued, running, queue_flag =
int prio, oldprio, queued, running, queue_flag =
DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
const struct sched_class *prev_class;
struct rq_flags rf;
struct rq *rq;
BUG_ON(prio > MAX_PRIO);
/* XXX used to be waiter->prio, not waiter->task->prio */
prio = __rt_effective_prio(pi_task, p->normal_prio);
/*
* If nothing changed; bail early.
*/
if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
return;
rq = __task_rq_lock(p, &rf);
update_rq_clock(rq);
/*
* Set under pi_lock && rq->lock, such that the value can be used under
* either lock.
*
* Note that there is loads of tricky to make this pointer cache work
* right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
* ensure a task is de-boosted (pi_task is set to NULL) before the
* task is allowed to run again (and can exit). This ensures the pointer
* points to a blocked task -- which guaratees the task is present.
*/
p->pi_top_task = pi_task;
/*
* For FIFO/RR we only need to set prio, if that matches we're done.
*/
if (prio == p->prio && !dl_prio(prio))
goto out_unlock;
/*
* Idle task boosting is a nono in general. There is one
@ -3713,9 +3752,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
goto out_unlock;
}
rt_mutex_update_top_task(p);
trace_sched_pi_setprio(p, prio);
trace_sched_pi_setprio(p, prio); /* broken */
oldprio = p->prio;
if (oldprio == prio)
@ -3739,7 +3776,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
* running task
*/
if (dl_prio(prio)) {
struct task_struct *pi_task = rt_mutex_get_top_task(p);
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
@ -3777,6 +3813,11 @@ out_unlock:
balance_callback(rq);
preempt_enable();
}
#else
static inline int rt_effective_prio(struct task_struct *p, int prio)
{
return prio;
}
#endif
void set_user_nice(struct task_struct *p, long nice)
@ -4023,10 +4064,9 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
* Keep a potential priority boosting if called from
* sched_setscheduler().
*/
p->prio = normal_prio(p);
if (keep_boost)
p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
else
p->prio = normal_prio(p);
p->prio = rt_effective_prio(p, p->prio);
if (dl_prio(p->prio))
p->sched_class = &dl_sched_class;
@ -4313,7 +4353,7 @@ change:
* the runqueue. This will be done when the task deboost
* itself.
*/
new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
new_effective_prio = rt_effective_prio(p, newprio);
if (new_effective_prio == oldprio)
queue_flags &= ~DEQUEUE_MOVE;
}