sched/deadline: Add SCHED_DEADLINE inheritance logic

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@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Added !RT_MUTEXES build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-11-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 134 insertions, 54 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9ea15019a5b6..13c53a99920f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1124,8 +1124,12 @@ 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
@@ -1359,6 +1363,8 @@ 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
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 440434df3627..34e4ebea8fce 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -35,6 +35,7 @@ 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 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)
 {
@@ -45,6 +46,10 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 {
         return p->normal_prio;
 }
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+        return NULL;
+}
 # define rt_mutex_adjust_pi(p)          do { } while (0)
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 7049ae526a54..01b450a61abd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1090,6 +1090,7 @@ 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/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 3bf0aa68dd3f..2e960a2bab81 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -96,13 +96,16 @@ static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
                      struct rt_mutex_waiter *right)
 {
-        if (left->task->prio < right->task->prio)
+        if (left->prio < right->prio)
                 return 1;
 
         /*
-         * If both tasks are dl_task(), we check their deadlines.
+         * 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->task->prio) && dl_prio(right->task->prio))
+        if (dl_prio(left->prio))
                 return (left->task->dl.deadline < right->task->dl.deadline);
 
         return 0;
@@ -197,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task)
         if (likely(!task_has_pi_waiters(task)))
                 return task->normal_prio;
 
-        return min(task_top_pi_waiter(task)->task->prio,
+        return min(task_top_pi_waiter(task)->prio,
                    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.
  *
@@ -210,7 +221,7 @@ 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);
 }
 
@@ -328,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
          * When deadlock detection is off then we check, if further
          * priority adjustment is necessary.
          */
-        if (!detect_deadlock && waiter->task->prio == task->prio)
+        if (!detect_deadlock && waiter->prio == task->prio)
                 goto out_unlock_pi;
 
         lock = waiter->lock;
@@ -350,7 +361,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
         /* Requeue the waiter */
         rt_mutex_dequeue(lock, waiter);
-        waiter->task->prio = task->prio;
+        waiter->prio = task->prio;
         rt_mutex_enqueue(lock, waiter);
 
         /* Release the task */
@@ -448,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
          * 3) it is top waiter
          */
         if (rt_mutex_has_waiters(lock)) {
-                if (task->prio >= rt_mutex_top_waiter(lock)->task->prio) {
+                if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
                         if (!waiter || waiter != rt_mutex_top_waiter(lock))
                                 return 0;
                 }
@@ -508,6 +519,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
         __rt_mutex_adjust_prio(task);
         waiter->task = task;
         waiter->lock = lock;
+        waiter->prio = task->prio;
 
         /* Get the top priority waiter on the lock */
         if (rt_mutex_has_waiters(lock))
@@ -653,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
         raw_spin_lock_irqsave(&task->pi_lock, flags);
 
         waiter = task->pi_blocked_on;