Merge branch 'x86/core' into core/ipi

[safe/jmp/linux-2.6] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 1a0fdfa..983c3ac 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
        ktime_t now;
 
-       if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+       if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
                return;
 
        if (hrtimer_active(&rt_b->rt_period_timer))
@@ -1093,7 +1093,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
        if (rq == this_rq()) {
                hrtimer_restart(timer);
        } else if (!rq->hrtick_csd_pending) {
-               __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+               __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
                rq->hrtick_csd_pending = 1;
        }
 }
@@ -1323,8 +1323,8 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
  * slice expiry etc.
  */
 
-#define WEIGHT_IDLEPRIO                2
-#define WMULT_IDLEPRIO         (1 << 31)
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
 
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
@@ -3880,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick)
        int cpu = smp_processor_id();
 
        if (stop_tick) {
-               cpumask_set_cpu(cpu, nohz.cpu_mask);
                cpu_rq(cpu)->in_nohz_recently = 1;
 
-               /*
-                * If we are going offline and still the leader, give up!
-                */
-               if (!cpu_active(cpu) &&
-                   atomic_read(&nohz.load_balancer) == cpu) {
+               if (!cpu_active(cpu)) {
+                       if (atomic_read(&nohz.load_balancer) != cpu)
+                               return 0;
+
+                       /*
+                        * If we are going offline and still the leader,
+                        * give up!
+                        */
                        if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
                                BUG();
+
                        return 0;
                }
 
+               cpumask_set_cpu(cpu, nohz.cpu_mask);
+
                /* time for ilb owner also to sleep */
                if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
                        if (atomic_read(&nohz.load_balancer) == cpu)
@@ -4440,7 +4445,7 @@ void __kprobes sub_preempt_count(int val)
        /*
         * Underflow?
         */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
                return;
        /*
         * Is the spinlock portion underflowing?
@@ -4687,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-                            int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+                       int nr_exclusive, int sync, void *key)
 {
        wait_queue_t *curr, *next;
 
@@ -5869,8 +5874,8 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
  */
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+               struct timespec __user *, interval)
 {
        struct task_struct *p;
        unsigned int time_slice;
@@ -5939,12 +5944,7 @@ void sched_show_task(struct task_struct *p)
                printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-       {
-               unsigned long *n = end_of_stack(p);
-               while (!*n)
-                       n++;
-               free = (unsigned long)n - (unsigned long)end_of_stack(p);
-       }
+       free = stack_not_used(p);
 #endif
        printk(KERN_CONT "%5lu %5d %6d\n", free,
                task_pid_nr(p), task_pid_nr(p->real_parent));
@@ -6939,20 +6939,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+       struct root_domain *old_rd = NULL;
        unsigned long flags;
 
        spin_lock_irqsave(&rq->lock, flags);
 
        if (rq->rd) {
-               struct root_domain *old_rd = rq->rd;
+               old_rd = rq->rd;
 
                if (cpumask_test_cpu(rq->cpu, old_rd->online))
                        set_rq_offline(rq);
 
                cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-               if (atomic_dec_and_test(&old_rd->refcount))
-                       free_rootdomain(old_rd);
+               /*
+                * If we dont want to free the old_rt yet then
+                * set old_rd to NULL to skip the freeing later
+                * in this function:
+                */
+               if (!atomic_dec_and_test(&old_rd->refcount))
+                       old_rd = NULL;
        }
 
        atomic_inc(&rd->refcount);
@@ -6963,6 +6969,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
                set_rq_online(rq);
 
        spin_unlock_irqrestore(&rq->lock, flags);
+
+       if (old_rd)
+               free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -9050,6 +9059,13 @@ static int tg_schedulable(struct task_group *tg, void *data)
                runtime = d->rt_runtime;
        }
 
+#ifdef CONFIG_USER_SCHED
+       if (tg == &root_task_group) {
+               period = global_rt_period();
+               runtime = global_rt_runtime();
+       }
+#endif
+
        /*
         * Cannot have more runtime than the period.
         */
@@ -9203,6 +9219,16 @@ static int sched_rt_global_constraints(void)
 
        return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+       /* Don't accept realtime tasks when there is no way for them to run */
+       if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+               return 0;
+
+       return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9296,8 +9322,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
                      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-       /* Don't accept realtime tasks when there is no way for them to run */
-       if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+       if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
                return -EINVAL;
 #else
        /* We don't support RT-tasks being in separate groups */
@@ -9460,7 +9485,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
 static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 {
-       u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+       u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
        u64 data;
 
 #ifndef CONFIG_64BIT
@@ -9479,7 +9504,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 
 static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
 {
-       u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+       u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 
 #ifndef CONFIG_64BIT
        /*
@@ -9575,7 +9600,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
        ca = task_ca(tsk);
 
        for (; ca; ca = ca->parent) {
-               u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+               u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
                *cpuusage += cputime;
        }
 }