[PATCH] pi-futex: scheduler support for pi

Add framework to boost/unboost the priority of RT tasks.

This consists of:

 - caching the 'normal' priority in ->normal_prio
 - providing a functions to set/get the priority of the task
 - make sched_setscheduler() aware of boosting

The effective_prio() cleanups also fix a priority-calculation bug pointed out
by Andrey Gelman, in set_user_nice().

has_rt_policy() fix: Peter Williams <pwil3058@bigpond.net.au>

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andrey Gelman <agelman@012.net.il>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 21 insertions, 2 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e127ef7e8da8..678c1a90380d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -87,6 +87,7 @@ extern struct group_info init_groups;
         .lock_depth     = -1,                                           \
         .prio           = MAX_PRIO-20,                                  \
         .static_prio    = MAX_PRIO-20,                                  \
+        .normal_prio    = MAX_PRIO-20,                                  \
         .policy         = SCHED_NORMAL,                                 \
         .cpus_allowed   = CPU_MASK_ALL,                                 \
         .mm             = NULL,                                         \
@@ -122,6 +123,7 @@ extern struct group_info init_groups;
         .journal_info   = NULL,                                         \
         .cpu_timers     = INIT_CPU_TIMERS(tsk.cpu_timers),              \
         .fs_excl        = ATOMIC_INIT(0),                               \
+        .pi_lock        = SPIN_LOCK_UNLOCKED,                           \
 }
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0bc81a151e50..6f167645e7e2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -495,8 +495,11 @@ struct signal_struct {
 
 #define MAX_PRIO                (MAX_RT_PRIO + 40)
 
-#define rt_task(p)              (unlikely((p)->prio < MAX_RT_PRIO))
+#define rt_prio(prio)           unlikely((prio) < MAX_RT_PRIO)
+#define rt_task(p)              rt_prio((p)->prio)
 #define batch_task(p)           (unlikely((p)->policy == SCHED_BATCH))
+#define has_rt_policy(p) \
+        unlikely((p)->policy != SCHED_NORMAL && (p)->policy != SCHED_BATCH)
 
 /*
  * Some day this will be a full-fledged user tracking system..
@@ -725,7 +728,7 @@ struct task_struct {
 #endif
 #endif
         int load_weight;        /* for niceness load balancing purposes */
-        int prio, static_prio;
+        int prio, static_prio, normal_prio;
         struct list_head run_list;
         prio_array_t *array;
 
@@ -852,6 +855,9 @@ struct task_struct {
 /* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
         spinlock_t alloc_lock;
 
+        /* Protection of the PI data structures: */
+        spinlock_t pi_lock;
+
 #ifdef CONFIG_DEBUG_MUTEXES
         /* mutex deadlock detection */
         struct mutex_waiter *blocked_on;
@@ -1018,6 +1024,17 @@ static inline void idle_task_exit(void) {}
 #endif
 
 extern void sched_idle_next(void);
+
+#ifdef CONFIG_RT_MUTEXES
+extern int rt_mutex_getprio(task_t *p);
+extern void rt_mutex_setprio(task_t *p, int prio);
+#else
+static inline int rt_mutex_getprio(task_t *p)
+{
+        return p->normal_prio;
+}
+#endif
+
 extern void set_user_nice(task_t *p, long nice);
 extern int task_prio(const task_t *p);
 extern int task_nice(const task_t *p);