Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

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

diff --git a/kernel/sched.c b/kernel/sched.c
index f53e2b8ef52153f8c8f95d48e28cf1afc0589d9e..f2095660efec72966823de6b66c6147367b8327b 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -118,6 +118,12 @@
  */
 #define RUNTIME_INF    ((u64)~0ULL)
 
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
 #ifdef CONFIG_SMP
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
@@ -203,7 +209,6 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
        hrtimer_init(&rt_b->rt_period_timer,
                        CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        rt_b->rt_period_timer.function = sched_rt_period_timer;
-       rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 }
 
 static inline int rt_bandwidth_enabled(void)
@@ -355,7 +360,9 @@ static inline struct task_group *task_group(struct task_struct *p)
        struct task_group *tg;
 
 #ifdef CONFIG_USER_SCHED
-       tg = p->user->tg;
+       rcu_read_lock();
+       tg = __task_cred(p)->user->tg;
+       rcu_read_unlock();
 #elif defined(CONFIG_CGROUP_SCHED)
        tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
                                struct task_group, css);
@@ -596,6 +603,8 @@ struct rq {
 #ifdef CONFIG_SCHEDSTATS
        /* latency stats */
        struct sched_info rq_sched_info;
+       unsigned long long rq_cpu_time;
+       /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
        /* sys_sched_yield() stats */
        unsigned int yld_exp_empty;
@@ -1129,7 +1138,6 @@ static void init_rq_hrtick(struct rq *rq)
 
        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        rq->hrtick_timer.function = hrtick;
-       rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
 #else  /* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
@@ -1857,6 +1865,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
        clock_offset = old_rq->clock - new_rq->clock;
 
+       trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
 #ifdef CONFIG_SCHEDSTATS
        if (p->se.wait_start)
                p->se.wait_start -= clock_offset;
@@ -2328,7 +2338,7 @@ out_activate:
        success = 1;
 
 out_running:
-       trace_sched_wakeup(rq, p);
+       trace_sched_wakeup(rq, p, success);
        check_preempt_curr(rq, p, sync);
 
        p->state = TASK_RUNNING;
@@ -2461,7 +2471,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                p->sched_class->task_new(rq, p);
                inc_nr_running(rq);
        }
-       trace_sched_wakeup_new(rq, p);
+       trace_sched_wakeup_new(rq, p, 1);
        check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
        if (p->sched_class->task_wake_up)
@@ -2840,7 +2850,6 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
            || unlikely(!cpu_active(dest_cpu)))
                goto out;
 
-       trace_sched_migrate_task(rq, p, dest_cpu);
        /* force the process onto the specified CPU */
        if (migrate_task(p, dest_cpu, &req)) {
                /* Need to wait for migration thread (might exit: take ref). */
@@ -4181,7 +4190,6 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
        if (p == rq->idle) {
                p->stime = cputime_add(p->stime, steal);
-               account_group_system_time(p, steal);
                if (atomic_read(&rq->nr_iowait) > 0)
                        cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
                else
@@ -4317,7 +4325,7 @@ void __kprobes sub_preempt_count(int val)
        /*
         * Underflow?
         */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
                return;
        /*
         * Is the spinlock portion underflowing?
@@ -5112,6 +5120,22 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
        set_load_weight(p);
 }
 
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+       const struct cred *cred = current_cred(), *pcred;
+       bool match;
+
+       rcu_read_lock();
+       pcred = __task_cred(p);
+       match = (cred->euid == pcred->euid ||
+                cred->euid == pcred->uid);
+       rcu_read_unlock();
+       return match;
+}
+
 static int __sched_setscheduler(struct task_struct *p, int policy,
                                struct sched_param *param, bool user)
 {
@@ -5171,8 +5195,7 @@ recheck:
                        return -EPERM;
 
                /* can't change other user's priorities */
-               if ((current->euid != p->euid) &&
-                   (current->euid != p->uid))
+               if (!check_same_owner(p))
                        return -EPERM;
        }
 
@@ -5404,8 +5427,7 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
        read_unlock(&tasklist_lock);
 
        retval = -EPERM;
-       if ((current->euid != p->euid) && (current->euid != p->uid) &&
-                       !capable(CAP_SYS_NICE))
+       if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                goto out_unlock;
 
        retval = security_task_setscheduler(p, 0, NULL);
@@ -5874,6 +5896,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         * The idle tasks have their own, simple scheduling class:
         */
        idle->sched_class = &idle_sched_class;
+       ftrace_graph_init_task(idle);
 }
 
 /*
@@ -6621,7 +6644,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
        struct sched_group *group = sd->groups;
        char str[256];
 
-       cpulist_scnprintf(str, sizeof(str), sd->span);
+       cpulist_scnprintf(str, sizeof(str), &sd->span);
        cpus_clear(*groupmask);
 
        printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@@ -6674,7 +6697,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
                cpus_or(*groupmask, *groupmask, group->cpumask);
 
-               cpulist_scnprintf(str, sizeof(str), group->cpumask);
+               cpulist_scnprintf(str, sizeof(str), &group->cpumask);
                printk(KERN_CONT " %s", str);
 
                group = group->next;
@@ -7075,7 +7098,7 @@ cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
 {
        int group;
 #ifdef CONFIG_SCHED_MC
-       *mask = cpu_coregroup_map(cpu);
+       *mask = *cpu_coregroup_mask(cpu);
        cpus_and(*mask, *mask, *cpu_map);
        group = first_cpu(*mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -7448,7 +7471,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                sd = &per_cpu(core_domains, i);
                SD_INIT(sd, MC);
                set_domain_attribute(sd, attr);
-               sd->span = cpu_coregroup_map(i);
+               sd->span = *cpu_coregroup_mask(i);
                cpus_and(sd->span, sd->span, *cpu_map);
                sd->parent = p;
                p->child = sd;
@@ -7491,7 +7514,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                SCHED_CPUMASK_VAR(this_core_map, allmasks);
                SCHED_CPUMASK_VAR(send_covered, allmasks);
 
-               *this_core_map = cpu_coregroup_map(i);
+               *this_core_map = *cpu_coregroup_mask(i);
                cpus_and(*this_core_map, *this_core_map, *cpu_map);
                if (i != first_cpu(*this_core_map))
                        continue;