VServer 1.9.2 (patch-2.6.8.1-vs1.9.2.diff)

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

diff --git a/kernel/sched.c b/kernel/sched.c
index 022dabf..305f948 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -42,6 +42,7 @@
 #include <linux/kthread.h>
 #include <linux/vserver/sched.h>
 #include <linux/vs_base.h>
+#include <asm/tlb.h>
 
 #include <asm/unistd.h>
 
@@ -553,7 +554,7 @@ static inline void resched_task(task_t *p)
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
  */
-inline int task_curr(task_t *p)
+inline int task_curr(const task_t *p)
 {
        return cpu_curr(task_cpu(p)) == p;
 }
@@ -703,10 +704,9 @@ static int wake_idle(int cpu, task_t *p)
                return cpu;
 
        cpus_and(tmp, sd->span, cpu_online_map);
-       for_each_cpu_mask(i, tmp) {
-               if (!cpu_isset(i, p->cpus_allowed))
-                       continue;
+       cpus_and(tmp, tmp, p->cpus_allowed);
 
+       for_each_cpu_mask(i, tmp) {
                if (idle_cpu(i))
                        return i;
        }
@@ -1102,7 +1102,7 @@ unsigned long nr_uninterruptible(void)
 {
        unsigned long i, sum = 0;
 
-       for_each_online_cpu(i)
+       for_each_cpu(i)
                sum += cpu_rq(i)->nr_uninterruptible;
 
        return sum;
@@ -1112,7 +1112,7 @@ unsigned long long nr_context_switches(void)
 {
        unsigned long long i, sum = 0;
 
-       for_each_online_cpu(i)
+       for_each_cpu(i)
                sum += cpu_rq(i)->nr_switches;
 
        return sum;
@@ -1122,7 +1122,7 @@ unsigned long nr_iowait(void)
 {
        unsigned long i, sum = 0;
 
-       for_each_online_cpu(i)
+       for_each_cpu(i)
                sum += atomic_read(&cpu_rq(i)->nr_iowait);
 
        return sum;
@@ -2720,7 +2720,7 @@ asmlinkage long sys_nice(int increment)
  * RT tasks are offset by -200. Normal tasks are centered
  * around 0, value goes from -16 to +15.
  */
-int task_prio(task_t *p)
+int task_prio(const task_t *p)
 {
        return p->prio - MAX_RT_PRIO;
 }
@@ -2729,7 +2729,7 @@ int task_prio(task_t *p)
  * task_nice - return the nice value of a given task.
  * @p: the task in question.
  */
-int task_nice(task_t *p)
+int task_nice(const task_t *p)
 {
        return TASK_NICE(p);
 }
@@ -3003,6 +3003,21 @@ out_unlock:
        return retval;
 }
 
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+
+cpumask_t cpu_present_map;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+cpumask_t cpu_online_map = CPU_MASK_ALL;
+cpumask_t cpu_possible_map = CPU_MASK_ALL;
+#endif
+
 /**
  * sys_sched_getaffinity - get the cpu affinity of a process
  * @pid: pid of the process
@@ -3382,7 +3397,7 @@ int set_cpus_allowed(task_t *p, cpumask_t new_mask)
        runqueue_t *rq;
 
        rq = task_rq_lock(p, &flags);
-       if (any_online_cpu(new_mask) == NR_CPUS) {
+       if (!cpus_intersects(new_mask, cpu_online_map)) {
                ret = -EINVAL;
                goto out;
        }
@@ -3397,6 +3412,7 @@ int set_cpus_allowed(task_t *p, cpumask_t new_mask)
                task_rq_unlock(rq, &flags);
                wake_up_process(rq->migration_thread);
                wait_for_completion(&req.done);
+               tlb_migrate_finish(p->mm);
                return 0;
        }
 out:
@@ -3557,8 +3573,7 @@ static void migrate_all_tasks(int src_cpu)
                if (dest_cpu == NR_CPUS)
                        dest_cpu = any_online_cpu(tsk->cpus_allowed);
                if (dest_cpu == NR_CPUS) {
-                       cpus_clear(tsk->cpus_allowed);
-                       cpus_complement(tsk->cpus_allowed);
+                       cpus_setall(tsk->cpus_allowed);
                        dest_cpu = any_online_cpu(tsk->cpus_allowed);
 
                        /* Don't tell them about moving exiting tasks
@@ -3620,6 +3635,7 @@ static int migration_call(struct notifier_block *nfb, unsigned long action,
                p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
                if (IS_ERR(p))
                        return NOTIFY_BAD;
+               p->flags |= PF_NOFREEZE;
                kthread_bind(p, cpu);
                /* Must be high prio: stop_machine expects to yield to it. */
                rq = task_rq_lock(p, &flags);
@@ -3874,7 +3890,7 @@ void sched_domain_debug(void)
                        int j;
                        char str[NR_CPUS];
                        struct sched_group *group = sd->groups;
-                       cpumask_t groupmask, tmp;
+                       cpumask_t groupmask;
 
                        cpumask_scnprintf(str, NR_CPUS, sd->span);
                        cpus_clear(groupmask);
@@ -3904,8 +3920,7 @@ void sched_domain_debug(void)
                                if (!cpus_weight(group->cpumask))
                                        printk(" ERROR empty group:");
 
-                               cpus_and(tmp, groupmask, group->cpumask);
-                               if (cpus_weight(tmp) > 0)
+                               if (cpus_intersects(groupmask, group->cpumask))
                                        printk(" ERROR repeated CPUs:");
 
                                cpus_or(groupmask, groupmask, group->cpumask);
@@ -3924,8 +3939,7 @@ void sched_domain_debug(void)
                        sd = sd->parent;
 
                        if (sd) {
-                               cpus_and(tmp, groupmask, sd->span);
-                               if (!cpus_equal(tmp, groupmask))
+                               if (!cpus_subset(groupmask, sd->span))
                                        printk(KERN_DEBUG "ERROR parent span is not a superset of domain->span\n");
                        }
 
@@ -3964,16 +3978,16 @@ void __init sched_init(void)
        /* Set up an initial dummy domain for early boot */
        static struct sched_domain sched_domain_init;
        static struct sched_group sched_group_init;
-       cpumask_t cpu_mask_all = CPU_MASK_ALL;
 
        memset(&sched_domain_init, 0, sizeof(struct sched_domain));
-       sched_domain_init.span = cpu_mask_all;
+       sched_domain_init.span = CPU_MASK_ALL;
        sched_domain_init.groups = &sched_group_init;
        sched_domain_init.last_balance = jiffies;
        sched_domain_init.balance_interval = INT_MAX; /* Don't balance */
+       sched_domain_init.busy_factor = 1;
 
        memset(&sched_group_init, 0, sizeof(struct sched_group));
-       sched_group_init.cpumask = cpu_mask_all;
+       sched_group_init.cpumask = CPU_MASK_ALL;
        sched_group_init.next = &sched_group_init;
        sched_group_init.cpu_power = SCHED_LOAD_SCALE;
 #endif