sched: add new API sched_setscheduler_nocheck: add a flag to control access checks

[linux-2.6-omap-h63xx.git] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index eaf6751e7612cbc5167865c8c1e4e929ff32ca5a..8d7c246ab864cbc35a0af29aa52da05546d83baa 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1127,6 +1127,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
        return HRTIMER_NORESTART;
 }
 
+#ifdef CONFIG_SMP
 static void hotplug_hrtick_disable(int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
@@ -1182,6 +1183,7 @@ static void init_hrtick(void)
 {
        hotcpu_notifier(hotplug_hrtick, 0);
 }
+#endif /* CONFIG_SMP */
 
 static void init_rq_hrtick(struct rq *rq)
 {
@@ -4744,16 +4746,8 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
        set_load_weight(p);
 }
 
-/**
- * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
- * @p: the task in question.
- * @policy: new policy.
- * @param: structure containing the new RT priority.
- *
- * NOTE that the task may be already dead.
- */
-int sched_setscheduler(struct task_struct *p, int policy,
-                      struct sched_param *param)
+static int __sched_setscheduler(struct task_struct *p, int policy,
+                               struct sched_param *param, bool user)
 {
        int retval, oldprio, oldpolicy = -1, on_rq, running;
        unsigned long flags;
@@ -4785,7 +4779,7 @@ recheck:
        /*
         * Allow unprivileged RT tasks to decrease priority:
         */
-       if (!capable(CAP_SYS_NICE)) {
+       if (user && !capable(CAP_SYS_NICE)) {
                if (rt_policy(policy)) {
                        unsigned long rlim_rtprio;
 
@@ -4821,7 +4815,8 @@ recheck:
         * Do not allow realtime tasks into groups that have no runtime
         * assigned.
         */
-       if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+       if (user
+           && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
                return -EPERM;
 #endif
 
@@ -4870,8 +4865,39 @@ recheck:
 
        return 0;
 }
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+                      struct sched_param *param)
+{
+       return __sched_setscheduler(p, policy, param, true);
+}
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission.  For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+                              struct sched_param *param)
+{
+       return __sched_setscheduler(p, policy, param, false);
+}
+
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
@@ -6877,7 +6903,12 @@ static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
 {
-       default_relax_domain_level = simple_strtoul(str, NULL, 0);
+       unsigned long val;
+
+       val = simple_strtoul(str, NULL, 0);
+       if (val < SD_LV_MAX)
+               default_relax_domain_level = val;
+
        return 1;
 }
 __setup("relax_domain_level=", setup_relax_domain_level);
@@ -7235,6 +7266,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 {
 }
 
+/*
+ * Free current domain masks.
+ * Called after all cpus are attached to NULL domain.
+ */
+static void free_sched_domains(void)
+{
+       ndoms_cur = 0;
+       if (doms_cur != &fallback_doms)
+               kfree(doms_cur);
+       doms_cur = &fallback_doms;
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -7382,6 +7425,7 @@ int arch_reinit_sched_domains(void)
        get_online_cpus();
        mutex_lock(&sched_domains_mutex);
        detach_destroy_domains(&cpu_online_map);
+       free_sched_domains();
        err = arch_init_sched_domains(&cpu_online_map);
        mutex_unlock(&sched_domains_mutex);
        put_online_cpus();
@@ -7467,6 +7511,7 @@ static int update_sched_domains(struct notifier_block *nfb,
        case CPU_DOWN_PREPARE:
        case CPU_DOWN_PREPARE_FROZEN:
                detach_destroy_domains(&cpu_online_map);
+               free_sched_domains();
                return NOTIFY_OK;
 
        case CPU_UP_CANCELED:
@@ -7485,8 +7530,16 @@ static int update_sched_domains(struct notifier_block *nfb,
                return NOTIFY_DONE;
        }
 
+#ifndef CONFIG_CPUSETS
+       /*
+        * Create default domain partitioning if cpusets are disabled.
+        * Otherwise we let cpusets rebuild the domains based on the
+        * current setup.
+        */
+
        /* The hotplug lock is already held by cpu_up/cpu_down */
        arch_init_sched_domains(&cpu_online_map);
+#endif
 
        return NOTIFY_OK;
 }
@@ -7626,7 +7679,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
        else
                rt_se->rt_rq = parent->my_q;
 
-       rt_se->rt_rq = &rq->rt;
        rt_se->my_q = rt_rq;
        rt_se->parent = parent;
        INIT_LIST_HEAD(&rt_se->run_list);
@@ -8348,7 +8400,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_CGROUP_SCHED
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-       struct task_group *tgi, *parent = tg->parent;
+       struct task_group *tgi, *parent = tg ? tg->parent : NULL;
        unsigned long total = 0;
 
        if (!parent) {