[PATCH 13/16] sched: drafted deadline inheritance logic.
From: Juri Lelli
Date: Fri Apr 06 2012 - 03:15:37 EST
From: Dario Faggioli <raistlin@xxxxxxxx>
Some method to deal with rt-mutexes and make sched_dl interact with
the current PI-coded is needed, raising all but trivial issues, that
needs (according to us) to be solved with some restructuring of
the pi-code (i.e., going toward a proxy execution-ish implementation).
This is under development, in the meanwhile, as a temporary solution,
what this commits does is:
- ensure a pi-lock owner with waiters is never throttled down. Instead,
when it runs out of runtime, it immediately gets replenished and it's
deadline is postponed;
- the scheduling parameters (relative deadline and default runtime)
used for that replenishments --during the whole period it holds the
pi-lock-- are the ones of the waiting task with earliest deadline.
Acting this way, we provide some kind of boosting to the lock-owner,
still by using the existing (actually, slightly modified by the previous
commit) pi-architecture.
We would stress the fact that this is only a surely needed, all but
clean solution to the problem. In the end it's only a way to re-start
discussion within the community. So, as always, comments, ideas, rants,
etc.. are welcome! :-)
Signed-off-by: Dario Faggioli <raistlin@xxxxxxxx>
Signed-off-by: Juri Lelli <juri.lelli@xxxxxxxxx>
---
include/linux/sched.h | 9 +++++-
kernel/fork.c | 1 +
kernel/rtmutex.c | 13 +++++++-
kernel/sched.c | 34 ++++++++++++++++++---
kernel/sched_dl.c | 77 +++++++++++++++++++++++++++++++++---------------
5 files changed, 102 insertions(+), 32 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5ef7bb6..ca45db4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1309,8 +1309,12 @@ struct sched_dl_entity {
* @dl_new tells if a new instance arrived. If so we must
* start executing it with full runtime and reset its absolute
* deadline;
+ *
+ * @dl_boosted tells if we are boosted due to DI. If so we are
+ * outside bandwidth enforcement mechanism (but only until we
+ * exit the critical section).
*/
- int dl_throttled, dl_new;
+ int dl_throttled, dl_new, dl_boosted;
/*
* Bandwidth enforcement timer. Each -deadline task has its
@@ -1556,6 +1560,8 @@ struct task_struct {
struct rb_node *pi_waiters_leftmost;
/* Deadlock detection and priority inheritance handling */
struct rt_mutex_waiter *pi_blocked_on;
+ /* Top pi_waiters task */
+ struct task_struct *pi_top_task;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
@@ -2236,6 +2242,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
#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 struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
diff --git a/kernel/fork.c b/kernel/fork.c
index 344e0b4..b8b0dff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1036,6 +1036,7 @@ static void rt_mutex_init_task(struct task_struct *p)
p->pi_waiters = RB_ROOT;
p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 6234c0e..cf155ba 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -217,6 +217,14 @@ int rt_mutex_getprio(struct task_struct *task)
task->normal_prio);
}
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+ if (likely(!task_has_pi_waiters(task)))
+ return NULL;
+
+ return task_top_pi_waiter(task)->task;
+}
+
/*
* Adjust the priority of a task, after its pi_waiters got modified.
*
@@ -226,7 +234,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
{
int prio = rt_mutex_getprio(task);
- if (task->prio != prio)
+ if (task->prio != prio || dl_prio(prio))
rt_mutex_setprio(task, prio);
}
@@ -712,7 +720,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
waiter = task->pi_blocked_on;
if (!rt_mutex_real_waiter(waiter) ||
- waiter->task->prio == task->prio) {
+ (waiter->task->prio == task->prio &&
+ !dl_prio(task->prio))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
diff --git a/kernel/sched.c b/kernel/sched.c
index 00e69a0..3963e4e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5238,7 +5238,7 @@ EXPORT_SYMBOL(sleep_on_timeout);
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, on_rq, running;
+ int oldprio, on_rq, running, enqueue_flag = 0;
struct rq *rq;
const struct sched_class *prev_class;
@@ -5265,6 +5265,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
}
trace_sched_pi_setprio(p, prio);
+ p->pi_top_task = rt_mutex_get_top_task(p);
oldprio = p->prio;
prev_class = p->sched_class;
on_rq = p->on_rq;
@@ -5274,19 +5275,42 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (running)
p->sched_class->put_prev_task(rq, p);
- if (dl_prio(prio))
+ /*
+ * Boosting condition are:
+ * 1. -rt task is running and holds mutex A
+ * --> -dl task blocks on mutex A
+ *
+ * 2. -dl task is running and holds mutex A
+ * --> -dl task blocks on mutex A and could preempt the
+ * running task
+ */
+ if (dl_prio(prio)) {
+ if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+ dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+ p->dl.dl_boosted = 1;
+ p->dl.dl_throttled = 0;
+ enqueue_flag = ENQUEUE_REPLENISH;
+ } else
+ p->dl.dl_boosted = 0;
p->sched_class = &dl_sched_class;
- else if (rt_prio(prio))
+ } else if (rt_prio(prio)) {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
+ if (oldprio < prio)
+ enqueue_flag = ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
- else
+ } else {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
p->sched_class = &fair_sched_class;
+ }
p->prio = prio;
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq)
- enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+ enqueue_task(rq, p, enqueue_flag);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
diff --git a/kernel/sched_dl.c b/kernel/sched_dl.c
index 05140bb..e393292 100644
--- a/kernel/sched_dl.c
+++ b/kernel/sched_dl.c
@@ -224,15 +224,16 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
* one, and to (try to!) reconcile itself with its own scheduling
* parameters.
*/
-static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
- dl_se->deadline = rq->clock + dl_se->dl_deadline;
- dl_se->runtime = dl_se->dl_runtime;
+ dl_se->deadline = rq->clock + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
dl_se->dl_new = 0;
}
@@ -254,11 +255,23 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
* could happen are, typically, a entity voluntarily trying to overcume its
* runtime, or it just underestimated it during sched_setscheduler_ex().
*/
-static void replenish_dl_entity(struct sched_dl_entity *dl_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
+ BUG_ON(pi_se->dl_runtime <= 0);
+
+ /*
+ * This could be the case for a !-dl task that is boosted.
+ * Just go with full inherited parameters.
+ */
+ if (dl_se->dl_deadline == 0) {
+ dl_se->deadline = rq->clock + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+
/*
* We Keep moving the deadline away until we get some
* available runtime for the entity. This ensures correct
@@ -266,8 +279,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
* arbitrary large.
*/
while (dl_se->runtime <= 0) {
- dl_se->deadline += dl_se->dl_period;
- dl_se->runtime += dl_se->dl_runtime;
+ dl_se->deadline += pi_se->dl_period;
+ dl_se->runtime += pi_se->dl_runtime;
}
/*
@@ -281,8 +294,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
*/
if (dl_time_before(dl_se->deadline, rq->clock)) {
WARN_ON_ONCE(1);
- dl_se->deadline = rq->clock + dl_se->dl_deadline;
- dl_se->runtime = dl_se->dl_runtime;
+ dl_se->deadline = rq->clock + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
}
}
@@ -299,7 +312,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
* task with deadline equal to period this is the same of using
* dl_deadline instead of dl_period in the equation above.
*/
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, u64 t)
{
u64 left, right;
@@ -316,8 +330,8 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
* to the (absolute) deadline. Therefore, overflowing the u64
* type is very unlikely to occur in both cases.
*/
- left = dl_se->dl_period * dl_se->runtime;
- right = (dl_se->deadline - t) * dl_se->dl_runtime;
+ left = pi_se->dl_deadline * dl_se->runtime;
+ right = (dl_se->deadline - t) * pi_se->dl_runtime;
return dl_time_before(right, left);
}
@@ -331,7 +345,8 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
* - using the remaining runtime with the current deadline would make
* the entity exceed its bandwidth.
*/
-static void update_dl_entity(struct sched_dl_entity *dl_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -341,14 +356,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
* the actual scheduling parameters have to be "renewed".
*/
if (dl_se->dl_new) {
- setup_new_dl_entity(dl_se);
+ setup_new_dl_entity(dl_se, pi_se);
return;
}
if (dl_time_before(dl_se->deadline, rq->clock) ||
- dl_entity_overflow(dl_se, rq->clock)) {
- dl_se->deadline = rq->clock + dl_se->dl_deadline;
- dl_se->runtime = dl_se->dl_runtime;
+ dl_entity_overflow(dl_se, pi_se, rq->clock)) {
+ dl_se->deadline = rq->clock + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
}
}
@@ -362,7 +377,7 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
* actually started or not (i.e., the replenishment instant is in
* the future or in the past).
*/
-static int start_dl_timer(struct sched_dl_entity *dl_se)
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -371,6 +386,8 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
unsigned long range;
s64 delta;
+ if (boosted)
+ return 0;
/*
* We want the timer to fire at the deadline, but considering
* that it is actually coming from rq->clock and not from
@@ -540,7 +557,7 @@ static void update_curr_dl(struct rq *rq)
dl_se->runtime -= delta_exec;
if (dl_runtime_exceeded(rq, dl_se)) {
__dequeue_task_dl(rq, curr, 0);
- if (likely(start_dl_timer(dl_se)))
+ if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
dl_se->dl_throttled = 1;
else
enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
@@ -695,7 +712,8 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
}
static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, int flags)
{
BUG_ON(on_dl_rq(dl_se));
@@ -705,9 +723,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
* we want a replenishment of its runtime.
*/
if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
- replenish_dl_entity(dl_se);
+ replenish_dl_entity(dl_se, pi_se);
else
- update_dl_entity(dl_se);
+ update_dl_entity(dl_se, pi_se);
__enqueue_dl_entity(dl_se);
}
@@ -719,6 +737,18 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
+ struct task_struct *pi_task = p->pi_top_task;
+ struct sched_dl_entity *pi_se = &p->dl;
+
+ /*
+ * Use the scheduling parameters of the top pi-waiter
+ * task if we have one and its (relative) deadline is
+ * smaller than our one... OTW we keep our runtime and
+ * deadline.
+ */
+ if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+ pi_se = &pi_task->dl;
+
/*
* If p is throttled, we do nothing. In fact, if it exhausted
* its budget it needs a replenishment and, since it now is on
@@ -728,7 +758,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
if (p->dl.dl_throttled)
return;
- enqueue_dl_entity(&p->dl, flags);
+ enqueue_dl_entity(&p->dl, pi_se, flags);
if (!task_current(rq, p) && p->dl.nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
@@ -962,8 +992,7 @@ static void task_dead_dl(struct task_struct *p)
{
struct hrtimer *timer = &p->dl.dl_timer;
- if (hrtimer_active(timer))
- hrtimer_try_to_cancel(timer);
+ hrtimer_try_to_cancel(timer);
}
static void set_curr_task_dl(struct rq *rq)
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/