#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/times.h>
-#include <linux/acct.h>
+#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
+#include <linux/delayacct.h>
#include <asm/tlb.h>
#include <asm/unistd.h>
/* For active balancing */
int active_balance;
int push_cpu;
+ int cpu; /* cpu of this runqueue */
struct task_struct *migration_thread;
struct list_head migration_queue;
static DEFINE_PER_CPU(struct rq, runqueues);
+static inline int cpu_of(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ return rq->cpu;
+#else
+ return 0;
+#endif
+}
+
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* See detach_destroy_domains: synchronize_sched for details.
.release = single_release,
};
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
+{
+ if (rq) {
+ rq->rq_sched_info.run_delay += delta_jiffies;
+ rq->rq_sched_info.pcnt++;
+ }
+}
+
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
+{
+ if (rq)
+ rq->rq_sched_info.cpu_time += delta_jiffies;
+}
# define schedstat_inc(rq, field) do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0)
#else /* !CONFIG_SCHEDSTATS */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
+{}
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
+{}
# define schedstat_inc(rq, field) do { } while (0)
# define schedstat_add(rq, field, amt) do { } while (0)
#endif
return rq;
}
-#ifdef CONFIG_SCHEDSTATS
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
/*
* Called when a process is dequeued from the active array and given
* the cpu. We should note that with the exception of interactive
*/
static void sched_info_arrive(struct task_struct *t)
{
- unsigned long now = jiffies, diff = 0;
- struct rq *rq = task_rq(t);
+ unsigned long now = jiffies, delta_jiffies = 0;
if (t->sched_info.last_queued)
- diff = now - t->sched_info.last_queued;
+ delta_jiffies = now - t->sched_info.last_queued;
sched_info_dequeued(t);
- t->sched_info.run_delay += diff;
+ t->sched_info.run_delay += delta_jiffies;
t->sched_info.last_arrival = now;
t->sched_info.pcnt++;
- if (!rq)
- return;
-
- rq->rq_sched_info.run_delay += diff;
- rq->rq_sched_info.pcnt++;
+ rq_sched_info_arrive(task_rq(t), delta_jiffies);
}
/*
*/
static inline void sched_info_queued(struct task_struct *t)
{
- if (!t->sched_info.last_queued)
- t->sched_info.last_queued = jiffies;
+ if (unlikely(sched_info_on()))
+ if (!t->sched_info.last_queued)
+ t->sched_info.last_queued = jiffies;
}
/*
*/
static inline void sched_info_depart(struct task_struct *t)
{
- struct rq *rq = task_rq(t);
- unsigned long diff = jiffies - t->sched_info.last_arrival;
-
- t->sched_info.cpu_time += diff;
+ unsigned long delta_jiffies = jiffies - t->sched_info.last_arrival;
- if (rq)
- rq->rq_sched_info.cpu_time += diff;
+ t->sched_info.cpu_time += delta_jiffies;
+ rq_sched_info_depart(task_rq(t), delta_jiffies);
}
/*
* the idle task.) We are only called when prev != next.
*/
static inline void
-sched_info_switch(struct task_struct *prev, struct task_struct *next)
+__sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
struct rq *rq = task_rq(prev);
if (next != rq->idle)
sched_info_arrive(next);
}
+static inline void
+sched_info_switch(struct task_struct *prev, struct task_struct *next)
+{
+ if (unlikely(sched_info_on()))
+ __sched_info_switch(prev, next);
+}
#else
#define sched_info_queued(t) do { } while (0)
#define sched_info_switch(t, next) do { } while (0)
-#endif /* CONFIG_SCHEDSTATS */
+#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
/*
* Adding/removing a task to/from a priority array:
INIT_LIST_HEAD(&p->run_list);
p->array = NULL;
-#ifdef CONFIG_SCHEDSTATS
- memset(&p->sched_info, 0, sizeof(p->sched_info));
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+ if (unlikely(sched_info_on()))
+ memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
p->oncpu = 0;
__releases(rq->lock)
{
struct mm_struct *mm = rq->prev_mm;
- unsigned long prev_task_flags;
+ long prev_state;
rq->prev_mm = NULL;
/*
* A task struct has one reference for the use as "current".
- * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
- * calls schedule one last time. The schedule call will never return,
- * and the scheduled task must drop that reference.
- * The test for EXIT_ZOMBIE must occur while the runqueue locks are
+ * 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>
*/
- prev_task_flags = prev->flags;
+ prev_state = prev->state;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
if (mm)
mmdrop(mm);
- if (unlikely(prev_task_flags & PF_DEAD)) {
+ if (unlikely(prev_state == TASK_DEAD)) {
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
WARN_ON(rq->prev_mm);
rq->prev_mm = oldmm;
}
+ /*
+ * Since the runqueue lock will be released by the next
+ * task (which is an invalid locking op but in the case
+ * of the scheduler it's an obvious special-case), so we
+ * do an early lockdep release here:
+ */
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+#endif
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
*/
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
- unsigned long *imbalance, enum idle_type idle, int *sd_idle)
+ unsigned long *imbalance, enum idle_type idle, int *sd_idle,
+ cpumask_t *cpus)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
sum_weighted_load = sum_nr_running = avg_load = 0;
for_each_cpu_mask(i, group->cpumask) {
- struct rq *rq = cpu_rq(i);
+ struct rq *rq;
+
+ if (!cpu_isset(i, *cpus))
+ continue;
+
+ rq = cpu_rq(i);
if (*sd_idle && !idle_cpu(i))
*sd_idle = 0;
*/
static struct rq *
find_busiest_queue(struct sched_group *group, enum idle_type idle,
- unsigned long imbalance)
+ unsigned long imbalance, cpumask_t *cpus)
{
struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
int i;
for_each_cpu_mask(i, group->cpumask) {
+
+ if (!cpu_isset(i, *cpus))
+ continue;
+
rq = cpu_rq(i);
if (rq->nr_running == 1 && rq->raw_weighted_load > imbalance)
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
+ cpumask_t cpus = CPU_MASK_ALL;
if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
!sched_smt_power_savings)
schedstat_inc(sd, lb_cnt[idle]);
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
+redo:
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ &cpus);
if (!group) {
schedstat_inc(sd, lb_nobusyg[idle]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, idle, imbalance);
+ busiest = find_busiest_queue(group, idle, imbalance, &cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
double_rq_unlock(this_rq, busiest);
/* All tasks on this runqueue were pinned by CPU affinity */
- if (unlikely(all_pinned))
+ if (unlikely(all_pinned)) {
+ cpu_clear(cpu_of(busiest), cpus);
+ if (!cpus_empty(cpus))
+ goto redo;
goto out_balanced;
+ }
}
if (!nr_moved) {
unsigned long imbalance;
int nr_moved = 0;
int sd_idle = 0;
+ cpumask_t cpus = CPU_MASK_ALL;
if (sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings)
sd_idle = 1;
schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
- group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
+redo:
+ group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE,
+ &sd_idle, &cpus);
if (!group) {
schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance);
+ busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance,
+ &cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
goto out_balanced;
minus_1_or_zero(busiest->nr_running),
imbalance, sd, NEWLY_IDLE, NULL);
spin_unlock(&busiest->lock);
+
+ if (!nr_moved) {
+ cpu_clear(cpu_of(busiest), cpus);
+ if (!cpus_empty(cpus))
+ goto redo;
+ }
}
if (!nr_moved) {
spin_lock_irq(&rq->lock);
- if (unlikely(prev->flags & PF_DEAD))
- prev->state = EXIT_DEAD;
-
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
switch_count = &prev->nvcsw;
#ifdef CONFIG_PREEMPT
/*
- * this is is the entry point to schedule() from in-kernel preemption
+ * this is the entry point to schedule() from in-kernel preemption
* off of preempt_enable. Kernel preemptions off return from interrupt
* occur there and call schedule directly.
*/
EXPORT_SYMBOL(preempt_schedule);
/*
- * this is is the entry point to schedule() from kernel preemption
+ * this is the entry point to schedule() from kernel preemption
* off of irq context.
* Note, that this is called and return with irqs disabled. This will
* protect us against recursive calling from irq.
struct task_struct *task = current;
int saved_lock_depth;
#endif
- /* Catch callers which need to be fixed*/
+ /* Catch callers which need to be fixed */
BUG_ON(ti->preempt_count || !irqs_disabled());
need_resched:
* @p: the task in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
+ *
+ * NOTE: the task may be already dead
*/
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
(p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
(!p->mm && param->sched_priority > MAX_RT_PRIO-1))
return -EINVAL;
- if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
- != (param->sched_priority == 0))
+ if (is_rt_policy(policy) != (param->sched_priority != 0))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (!capable(CAP_SYS_NICE)) {
- /*
- * can't change policy, except between SCHED_NORMAL
- * and SCHED_BATCH:
- */
- if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
- (policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
- !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
- return -EPERM;
- /* can't increase priority */
- if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
- param->sched_priority > p->rt_priority &&
- param->sched_priority >
- p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
- return -EPERM;
+ if (is_rt_policy(policy)) {
+ unsigned long rlim_rtprio;
+ unsigned long flags;
+
+ if (!lock_task_sighand(p, &flags))
+ return -ESRCH;
+ rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+ unlock_task_sighand(p, &flags);
+
+ /* can't set/change the rt policy */
+ if (policy != p->policy && !rlim_rtprio)
+ return -EPERM;
+
+ /* can't increase priority */
+ if (param->sched_priority > p->rt_priority &&
+ param->sched_priority > rlim_rtprio)
+ return -EPERM;
+ }
+
/* can't change other user's priorities */
if ((current->euid != p->euid) &&
(current->euid != p->uid))
return -EINVAL;
if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
return -EFAULT;
- read_lock_irq(&tasklist_lock);
+
+ rcu_read_lock();
+ retval = -ESRCH;
p = find_process_by_pid(pid);
- if (!p) {
- read_unlock_irq(&tasklist_lock);
- return -ESRCH;
- }
- get_task_struct(p);
- read_unlock_irq(&tasklist_lock);
- retval = sched_setscheduler(p, policy, &lparam);
- put_task_struct(p);
+ if (p != NULL)
+ retval = sched_setscheduler(p, policy, &lparam);
+ rcu_read_unlock();
return retval;
}
#ifndef CONFIG_SMP
cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_online_map);
+
cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
#endif
long sched_getaffinity(pid_t pid, cpumask_t *mask)
return 0;
}
-static inline int __resched_legal(void)
+static inline int __resched_legal(int expected_preempt_count)
{
- if (unlikely(preempt_count()))
+ if (unlikely(preempt_count() != expected_preempt_count))
return 0;
if (unlikely(system_state != SYSTEM_RUNNING))
return 0;
int __sched cond_resched(void)
{
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(0)) {
__cond_resched();
return 1;
}
ret = 1;
spin_lock(lock);
}
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(1)) {
spin_release(&lock->dep_map, 1, _THIS_IP_);
_raw_spin_unlock(lock);
preempt_enable_no_resched();
{
BUG_ON(!in_softirq());
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(0)) {
raw_local_irq_disable();
_local_bh_enable();
raw_local_irq_enable();
{
struct rq *rq = &__raw_get_cpu_var(runqueues);
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
schedule();
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
}
EXPORT_SYMBOL(io_schedule);
struct rq *rq = &__raw_get_cpu_var(runqueues);
long ret;
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
ret = schedule_timeout(timeout);
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
return ret;
}
return list_entry(p->sibling.next,struct task_struct,sibling);
}
-static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };
+static const char stat_nam[] = "RSDTtZX";
static void show_task(struct task_struct *p)
{
unsigned long free = 0;
unsigned state;
- printk("%-13.13s ", p->comm);
state = p->state ? __ffs(p->state) + 1 : 0;
- if (state < ARRAY_SIZE(stat_nam))
- printk(stat_nam[state]);
- else
- printk("?");
+ printk("%-13.13s %c", p->comm,
+ state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if (BITS_PER_LONG == 32)
if (state == TASK_RUNNING)
printk(" running ");
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
-void __devinit init_idle(struct task_struct *idle, int cpu)
+void __cpuinit init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
p->timestamp = p->timestamp - rq_src->timestamp_last_tick
+ rq_dest->timestamp_last_tick;
deactivate_task(p, rq_src);
- activate_task(p, rq_dest, 0);
+ __activate_task(p, rq_dest);
if (TASK_PREEMPTS_CURR(p, rq_dest))
resched_task(rq_dest->curr);
}
BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
/* Cannot have done final schedule yet: would have vanished. */
- BUG_ON(p->flags & PF_DEAD);
+ BUG_ON(p->state == TASK_DEAD);
get_task_struct(p);
int __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
+ int err;
/* Start one for the boot CPU: */
- migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
}
/* cpus with isolated domains */
-static cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;
+static cpumask_t __cpuinitdata cpu_isolated_map = CPU_MASK_NONE;
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
cache = vmalloc(max_size);
if (!cache) {
printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
- return 1000000; // return 1 msec on very small boxen
+ return 1000000; /* return 1 msec on very small boxen */
}
while (size <= max_size) {
for (i = 0; i < MAX_NUMNODES; i++)
init_numa_sched_groups_power(sched_group_nodes[i]);
- init_numa_sched_groups_power(sched_group_allnodes);
+ if (sched_group_allnodes) {
+ int group = cpu_to_allnodes_group(first_cpu(*cpu_map));
+ struct sched_group *sg = &sched_group_allnodes[group];
+
+ init_numa_sched_groups_power(sg);
+ }
#endif
/* Attach the domains */
void __init sched_init_smp(void)
{
+ cpumask_t non_isolated_cpus;
+
lock_cpu_hotplug();
arch_init_sched_domains(&cpu_online_map);
+ cpus_andnot(non_isolated_cpus, cpu_online_map, cpu_isolated_map);
+ if (cpus_empty(non_isolated_cpus))
+ cpu_set(smp_processor_id(), non_isolated_cpus);
unlock_cpu_hotplug();
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
+
+ /* Move init over to a non-isolated CPU */
+ if (set_cpus_allowed(current, non_isolated_cpus) < 0)
+ BUG();
}
#else
void __init sched_init_smp(void)
rq->cpu_load[j] = 0;
rq->active_balance = 0;
rq->push_cpu = 0;
+ rq->cpu = i;
rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
#endif
}
set_load_weight(&init_task);
+
+#ifdef CONFIG_RT_MUTEXES
+ plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+#endif
+
/*
* The boot idle thread does lazy MMU switching as well:
*/