Merge branch 'stable-3.2' into pandora-3.2

[pandora-kernel.git] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 6ab532c..f4235a7 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1016,8 +1016,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
         * After ->on_cpu is cleared, the task can be moved to a different CPU.
         * We must ensure this doesn't happen until the switch is completely
         * finished.
+        *
+        * Pairs with the control dependency and rmb in try_to_wake_up().
         */
-       smp_wmb();
+       smp_mb();
        prev->on_cpu = 0;
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
@@ -2189,6 +2191,10 @@ static int irqtime_account_si_update(void)
 
 #endif
 
+#ifdef CONFIG_SMP
+static void unthrottle_offline_cfs_rqs(struct rq *rq);
+#endif
+
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
@@ -2926,7 +2932,6 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-       WARN_ON(task_is_stopped_or_traced(p));
        return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
@@ -3187,11 +3192,11 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
         * If a task dies, then it sets TASK_DEAD in tsk->state and calls
         * schedule one last time. The schedule call will never return, and
         * the scheduled task must drop that reference.
-        * The test for TASK_DEAD must occur while the runqueue locks are
-        * still held, otherwise prev could be scheduled on another cpu, die
-        * there before we look at prev->state, and then the reference would
-        * be dropped twice.
-        *              Manfred Spraul <manfred@colorfullife.com>
+        *
+        * We must observe prev->state before clearing prev->on_cpu (in
+        * finish_lock_switch), otherwise a concurrent wakeup can get prev
+        * running on another CPU and we could rave with its RUNNING -> DEAD
+        * transition, resulting in a double drop.
         */
        prev_state = prev->state;
        finish_arch_switch(prev);
@@ -5220,8 +5225,11 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
        if (rt_prio(prio))
                p->sched_class = &rt_sched_class;
-       else
+       else {
+               if (rt_prio(oldprio))
+                       p->rt.timeout = 0;
                p->sched_class = &fair_sched_class;
+       }
 
        p->prio = prio;
 
@@ -6567,8 +6575,6 @@ static void unthrottle_offline_cfs_rqs(struct rq *rq)
                        unthrottle_cfs_rq(cfs_rq);
        }
 }
-#else
-static void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 #endif
 
 /*
@@ -6596,9 +6602,6 @@ static void migrate_tasks(unsigned int dead_cpu)
         */
        rq->stop = NULL;
 
-       /* Ensure any throttled groups are reachable by pick_next_task */
-       unthrottle_offline_cfs_rqs(rq);
-
        for ( ; ; ) {
                /*
                 * There's this thread running, bail when that's the only
@@ -6625,6 +6628,10 @@ static void migrate_tasks(unsigned int dead_cpu)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
+#if !defined(CONFIG_HOTPLUG_CPU) || !defined(CONFIG_CFS_BANDWIDTH)
+static void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+#endif
+
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
 
 static struct ctl_table sd_ctl_dir[] = {
@@ -6673,16 +6680,25 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
        *tablep = NULL;
 }
 
+static int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
 static void
 set_table_entry(struct ctl_table *entry,
                const char *procname, void *data, int maxlen,
-               mode_t mode, proc_handler *proc_handler)
+               mode_t mode, proc_handler *proc_handler,
+               bool load_idx)
 {
        entry->procname = procname;
        entry->data = data;
        entry->maxlen = maxlen;
        entry->mode = mode;
        entry->proc_handler = proc_handler;
+
+       if (load_idx) {
+               entry->extra1 = &min_load_idx;
+               entry->extra2 = &max_load_idx;
+       }
 }
 
 static struct ctl_table *
@@ -6694,30 +6710,30 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
                return NULL;
 
        set_table_entry(&table[0], "min_interval", &sd->min_interval,
-               sizeof(long), 0644, proc_doulongvec_minmax);
+               sizeof(long), 0644, proc_doulongvec_minmax, false);
        set_table_entry(&table[1], "max_interval", &sd->max_interval,
-               sizeof(long), 0644, proc_doulongvec_minmax);
+               sizeof(long), 0644, proc_doulongvec_minmax, false);
        set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, true);
        set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, true);
        set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, true);
        set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, true);
        set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, true);
        set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, false);
        set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, false);
        set_table_entry(&table[9], "cache_nice_tries",
                &sd->cache_nice_tries,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, false);
        set_table_entry(&table[10], "flags", &sd->flags,
-               sizeof(int), 0644, proc_dointvec_minmax);
+               sizeof(int), 0644, proc_dointvec_minmax, false);
        set_table_entry(&table[11], "name", sd->name,
-               CORENAME_MAX_SIZE, 0444, proc_dostring);
+               CORENAME_MAX_SIZE, 0444, proc_dostring, false);
        /* &table[12] is terminator */
 
        return table;
@@ -7155,11 +7171,11 @@ static int init_rootdomain(struct root_domain *rd)
 {
        memset(rd, 0, sizeof(*rd));
 
-       if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+       if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
                goto out;
-       if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+       if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
                goto free_span;
-       if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+       if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
                goto free_online;
 
        if (cpupri_init(&rd->cpupri) != 0)
@@ -9093,6 +9109,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {
        struct task_struct *g, *p;
 
+       /*
+        * Autogroups do not have RT tasks; see autogroup_create().
+        */
+       if (task_group_is_autogroup(tg))
+               return 0;
+
        do_each_thread(g, p) {
                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
                        return 1;