#include <asm/unistd.h>
/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+ return (unsigned long long)jiffies * (1000000000 / HZ);
+}
+
+/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
* and back.
unsigned long nr_uninterruptible;
unsigned long expired_timestamp;
- unsigned long long timestamp_last_tick;
+ /* Cached timestamp set by update_cpu_clock() */
+ unsigned long long most_recent_timestamp;
struct task_struct *curr, *idle;
+ unsigned long next_balance;
struct mm_struct *prev_mm;
struct prio_array *active, *expired, arrays[2];
int best_expired_prio;
* bump this up when changing the output format or the meaning of an existing
* format, so that tools can adapt (or abort)
*/
-#define SCHEDSTAT_VERSION 12
+#define SCHEDSTAT_VERSION 14
static int show_schedstat(struct seq_file *seq, void *v)
{
seq_printf(seq, "domain%d %s", dcnt++, mask_str);
for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
itype++) {
- seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu",
+ seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu "
+ "%lu",
sd->lb_cnt[itype],
sd->lb_balanced[itype],
sd->lb_failed[itype],
sd->lb_nobusyq[itype],
sd->lb_nobusyg[itype]);
}
- seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
+ seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu"
+ " %lu %lu %lu\n",
sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
- sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
+ sd->ttwu_wake_remote, sd->ttwu_move_affine,
+ sd->ttwu_move_balance);
}
preempt_enable();
#endif
{
unsigned long long now;
+ if (rt_task(p))
+ goto out;
+
now = sched_clock();
#ifdef CONFIG_SMP
if (!local) {
/* Compensate for drifting sched_clock */
struct rq *this_rq = this_rq();
- now = (now - this_rq->timestamp_last_tick)
- + rq->timestamp_last_tick;
+ now = (now - this_rq->most_recent_timestamp)
+ + rq->most_recent_timestamp;
}
#endif
(now - p->timestamp) >> 20);
}
- if (!rt_task(p))
- p->prio = recalc_task_prio(p, now);
+ p->prio = recalc_task_prio(p, now);
/*
* This checks to make sure it's not an uninterruptible task
}
}
p->timestamp = now;
-
+out:
__activate_task(p, rq);
}
if (this_sd->flags & SD_WAKE_AFFINE) {
unsigned long tl = this_load;
- unsigned long tl_per_task = cpu_avg_load_per_task(this_cpu);
+ unsigned long tl_per_task;
+
+ tl_per_task = cpu_avg_load_per_task(this_cpu);
/*
* If sync wakeup then subtract the (maximum possible)
return try_to_wake_up(p, state, 0);
}
+static void task_running_tick(struct rq *rq, struct task_struct *p);
/*
* Perform scheduler related setup for a newly forked process p.
* p is forked by current.
* runqueue lock is not a problem.
*/
current->time_slice = 1;
- scheduler_tick();
+ task_running_tick(cpu_rq(cpu), current);
}
local_irq_enable();
put_cpu();
* Not the local CPU - must adjust timestamp. This should
* get optimised away in the !CONFIG_SMP case.
*/
- p->timestamp = (p->timestamp - this_rq->timestamp_last_tick)
- + rq->timestamp_last_tick;
+ p->timestamp = (p->timestamp - this_rq->most_recent_timestamp)
+ + rq->most_recent_timestamp;
__activate_task(p, rq);
if (TASK_PREEMPTS_CURR(p, rq))
resched_task(rq->curr);
struct mm_struct *mm = next->mm;
struct mm_struct *oldmm = prev->active_mm;
+ /*
+ * For paravirt, this is coupled with an exit in switch_to to
+ * combine the page table reload and the switch backend into
+ * one hypercall.
+ */
+ arch_enter_lazy_cpu_mode();
+
if (!mm) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
set_task_cpu(p, this_cpu);
inc_nr_running(p, this_rq);
enqueue_task(p, this_array);
- p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
- + this_rq->timestamp_last_tick;
+ p->timestamp = (p->timestamp - src_rq->most_recent_timestamp)
+ + this_rq->most_recent_timestamp;
/*
* Note that idle threads have a prio of MAX_PRIO, for this test
* to be always true for them.
* 2) too many balance attempts have failed.
*/
- if (sd->nr_balance_failed > sd->cache_nice_tries)
+ if (sd->nr_balance_failed > sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+ if (task_hot(p, rq->most_recent_timestamp, sd))
+ schedstat_inc(sd, lb_hot_gained[idle]);
+#endif
return 1;
+ }
- if (task_hot(p, rq->timestamp_last_tick, sd))
+ if (task_hot(p, rq->most_recent_timestamp, sd))
return 0;
return 1;
}
goto skip_bitmap;
}
-#ifdef CONFIG_SCHEDSTATS
- if (task_hot(tmp, busiest->timestamp_last_tick, sd))
- schedstat_inc(sd, lb_hot_gained[idle]);
-#endif
-
pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
pulled++;
rem_load_move -= tmp->load_weight;
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum idle_type idle, int *sd_idle,
- cpumask_t *cpus)
+ cpumask_t *cpus, int *balance)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
unsigned long load, group_capacity;
int local_group;
int i;
+ unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long sum_nr_running, sum_weighted_load;
local_group = cpu_isset(this_cpu, group->cpumask);
+ if (local_group)
+ balance_cpu = first_cpu(group->cpumask);
+
/* Tally up the load of all CPUs in the group */
sum_weighted_load = sum_nr_running = avg_load = 0;
*sd_idle = 0;
/* Bias balancing toward cpus of our domain */
- if (local_group)
+ if (local_group) {
+ if (idle_cpu(i) && !first_idle_cpu) {
+ first_idle_cpu = 1;
+ balance_cpu = i;
+ }
+
load = target_load(i, load_idx);
- else
+ } else
load = source_load(i, load_idx);
avg_load += load;
sum_weighted_load += rq->raw_weighted_load;
}
+ /*
+ * First idle cpu or the first cpu(busiest) in this sched group
+ * is eligible for doing load balancing at this and above
+ * domains.
+ */
+ if (local_group && balance_cpu != this_cpu && balance) {
+ *balance = 0;
+ goto ret;
+ }
+
total_load += avg_load;
total_pwr += group->cpu_power;
pwr_now /= SCHED_LOAD_SCALE;
/* Amount of load we'd subtract */
- tmp = busiest_load_per_task*SCHED_LOAD_SCALE/busiest->cpu_power;
+ tmp = busiest_load_per_task * SCHED_LOAD_SCALE /
+ busiest->cpu_power;
if (max_load > tmp)
pwr_move += busiest->cpu_power *
min(busiest_load_per_task, max_load - tmp);
/* Amount of load we'd add */
- if (max_load*busiest->cpu_power <
- busiest_load_per_task*SCHED_LOAD_SCALE)
- tmp = max_load*busiest->cpu_power/this->cpu_power;
+ if (max_load * busiest->cpu_power <
+ busiest_load_per_task * SCHED_LOAD_SCALE)
+ tmp = max_load * busiest->cpu_power / this->cpu_power;
else
- tmp = busiest_load_per_task*SCHED_LOAD_SCALE/this->cpu_power;
- pwr_move += this->cpu_power*min(this_load_per_task, this_load + tmp);
+ tmp = busiest_load_per_task * SCHED_LOAD_SCALE /
+ this->cpu_power;
+ pwr_move += this->cpu_power *
+ min(this_load_per_task, this_load + tmp);
pwr_move /= SCHED_LOAD_SCALE;
/* Move if we gain throughput */
*imbalance = min_load_per_task;
return group_min;
}
-ret:
#endif
+ret:
*imbalance = 0;
return NULL;
}
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
- *
- * Called with this_rq unlocked.
*/
static int load_balance(int this_cpu, struct rq *this_rq,
- struct sched_domain *sd, enum idle_type idle)
+ struct sched_domain *sd, enum idle_type idle,
+ int *balance)
{
int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
cpumask_t cpus = CPU_MASK_ALL;
+ unsigned long flags;
/*
* When power savings policy is enabled for the parent domain, idle
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
- &cpus);
+ &cpus, balance);
+
+ if (*balance == 0)
+ goto out_balanced;
+
if (!group) {
schedstat_inc(sd, lb_nobusyg[idle]);
goto out_balanced;
* still unbalanced. nr_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
+ local_irq_save(flags);
double_rq_lock(this_rq, busiest);
nr_moved = move_tasks(this_rq, this_cpu, busiest,
minus_1_or_zero(busiest->nr_running),
imbalance, sd, idle, &all_pinned);
double_rq_unlock(this_rq, busiest);
+ local_irq_restore(flags);
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(all_pinned)) {
if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
- spin_lock(&busiest->lock);
+ spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
- spin_unlock(&busiest->lock);
+ spin_unlock_irqrestore(&busiest->lock, flags);
all_pinned = 1;
goto out_one_pinned;
}
busiest->push_cpu = this_cpu;
active_balance = 1;
}
- spin_unlock(&busiest->lock);
+ spin_unlock_irqrestore(&busiest->lock, flags);
if (active_balance)
wake_up_process(busiest->migration_thread);
schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE,
- &sd_idle, &cpus);
+ &sd_idle, &cpus, NULL);
if (!group) {
schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
goto out_balanced;
static void idle_balance(int this_cpu, struct rq *this_rq)
{
struct sched_domain *sd;
+ int pulled_task = 0;
+ unsigned long next_balance = jiffies + 60 * HZ;
for_each_domain(this_cpu, sd) {
if (sd->flags & SD_BALANCE_NEWIDLE) {
/* If we've pulled tasks over stop searching: */
- if (load_balance_newidle(this_cpu, this_rq, sd))
+ pulled_task = load_balance_newidle(this_cpu,
+ this_rq, sd);
+ if (time_after(next_balance,
+ sd->last_balance + sd->balance_interval))
+ next_balance = sd->last_balance
+ + sd->balance_interval;
+ if (pulled_task)
break;
}
}
+ if (!pulled_task)
+ /*
+ * We are going idle. next_balance may be set based on
+ * a busy processor. So reset next_balance.
+ */
+ this_rq->next_balance = next_balance;
}
/*
spin_unlock(&target_rq->lock);
}
-/*
- * rebalance_tick will get called every timer tick, on every CPU.
- *
- * It checks each scheduling domain to see if it is due to be balanced,
- * and initiates a balancing operation if so.
- *
- * Balancing parameters are set up in arch_init_sched_domains.
- */
-
-static void
-rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle)
+static void update_load(struct rq *this_rq)
{
- unsigned long this_load, interval;
- struct sched_domain *sd;
- int i, scale;
+ unsigned long this_load;
+ unsigned int i, scale;
this_load = this_rq->raw_weighted_load;
/* Update our load: */
- for (i = 0, scale = 1; i < 3; i++, scale <<= 1) {
+ for (i = 0, scale = 1; i < 3; i++, scale += scale) {
unsigned long old_load, new_load;
+ /* scale is effectively 1 << i now, and >> i divides by scale */
+
old_load = this_rq->cpu_load[i];
new_load = this_load;
/*
*/
if (new_load > old_load)
new_load += scale-1;
- this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale;
+ this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
}
+}
+
+/*
+ * run_rebalance_domains is triggered when needed from the scheduler tick.
+ *
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
+ */
+static DEFINE_SPINLOCK(balancing);
+
+static void run_rebalance_domains(struct softirq_action *h)
+{
+ int this_cpu = smp_processor_id(), balance = 1;
+ struct rq *this_rq = cpu_rq(this_cpu);
+ unsigned long interval;
+ struct sched_domain *sd;
+ /*
+ * We are idle if there are no processes running. This
+ * is valid even if we are the idle process (SMT).
+ */
+ enum idle_type idle = !this_rq->nr_running ?
+ SCHED_IDLE : NOT_IDLE;
+ /* Earliest time when we have to call run_rebalance_domains again */
+ unsigned long next_balance = jiffies + 60*HZ;
for_each_domain(this_cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
if (unlikely(!interval))
interval = 1;
- if (jiffies - sd->last_balance >= interval) {
- if (load_balance(this_cpu, this_rq, sd, idle)) {
+ if (sd->flags & SD_SERIALIZE) {
+ if (!spin_trylock(&balancing))
+ goto out;
+ }
+
+ if (time_after_eq(jiffies, sd->last_balance + interval)) {
+ if (load_balance(this_cpu, this_rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
* longer idle, or one of our SMT siblings is
*/
idle = NOT_IDLE;
}
- sd->last_balance += interval;
+ sd->last_balance = jiffies;
}
+ if (sd->flags & SD_SERIALIZE)
+ spin_unlock(&balancing);
+out:
+ if (time_after(next_balance, sd->last_balance + interval))
+ next_balance = sd->last_balance + interval;
+
+ /*
+ * Stop the load balance at this level. There is another
+ * CPU in our sched group which is doing load balancing more
+ * actively.
+ */
+ if (!balance)
+ break;
}
+ this_rq->next_balance = next_balance;
}
#else
/*
* on UP we do not need to balance between CPUs:
*/
-static inline void rebalance_tick(int cpu, struct rq *rq, enum idle_type idle)
-{
-}
static inline void idle_balance(int cpu, struct rq *rq)
{
}
#endif
-static inline int wake_priority_sleeper(struct rq *rq)
-{
- int ret = 0;
-
-#ifdef CONFIG_SCHED_SMT
- if (!rq->nr_running)
- return 0;
-
- spin_lock(&rq->lock);
- /*
- * If an SMT sibling task has been put to sleep for priority
- * reasons reschedule the idle task to see if it can now run.
- */
- if (rq->nr_running) {
- resched_task(rq->idle);
- ret = 1;
- }
- spin_unlock(&rq->lock);
-#endif
- return ret;
-}
-
DEFINE_PER_CPU(struct kernel_stat, kstat);
EXPORT_PER_CPU_SYMBOL(kstat);
static inline void
update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now)
{
- p->sched_time += now - max(p->timestamp, rq->timestamp_last_tick);
+ p->sched_time += now - p->last_ran;
+ p->last_ran = rq->most_recent_timestamp = now;
}
/*
unsigned long flags;
local_irq_save(flags);
- ns = max(p->timestamp, task_rq(p)->timestamp_last_tick);
- ns = p->sched_time + sched_clock() - ns;
+ ns = p->sched_time + sched_clock() - p->last_ran;
local_irq_restore(flags);
return ns;
cpustat->steal = cputime64_add(cpustat->steal, tmp);
}
-/*
- * This function gets called by the timer code, with HZ frequency.
- * We call it with interrupts disabled.
- *
- * It also gets called by the fork code, when changing the parent's
- * timeslices.
- */
-void scheduler_tick(void)
+static void task_running_tick(struct rq *rq, struct task_struct *p)
{
- unsigned long long now = sched_clock();
- struct task_struct *p = current;
- int cpu = smp_processor_id();
- struct rq *rq = cpu_rq(cpu);
-
- update_cpu_clock(p, rq, now);
-
- rq->timestamp_last_tick = now;
-
- if (p == rq->idle) {
- if (wake_priority_sleeper(rq))
- goto out;
- rebalance_tick(cpu, rq, SCHED_IDLE);
- return;
- }
-
- /* Task might have expired already, but not scheduled off yet */
if (p->array != rq->active) {
+ /* Task has expired but was not scheduled yet */
set_tsk_need_resched(p);
- goto out;
+ return;
}
spin_lock(&rq->lock);
/*
}
out_unlock:
spin_unlock(&rq->lock);
-out:
- rebalance_tick(cpu, rq, NOT_IDLE);
-}
-
-#ifdef CONFIG_SCHED_SMT
-static inline void wakeup_busy_runqueue(struct rq *rq)
-{
- /* If an SMT runqueue is sleeping due to priority reasons wake it up */
- if (rq->curr == rq->idle && rq->nr_running)
- resched_task(rq->idle);
-}
-
-/*
- * Called with interrupt disabled and this_rq's runqueue locked.
- */
-static void wake_sleeping_dependent(int this_cpu)
-{
- struct sched_domain *tmp, *sd = NULL;
- int i;
-
- for_each_domain(this_cpu, tmp) {
- if (tmp->flags & SD_SHARE_CPUPOWER) {
- sd = tmp;
- break;
- }
- }
-
- if (!sd)
- return;
-
- for_each_cpu_mask(i, sd->span) {
- struct rq *smt_rq = cpu_rq(i);
-
- if (i == this_cpu)
- continue;
- if (unlikely(!spin_trylock(&smt_rq->lock)))
- continue;
-
- wakeup_busy_runqueue(smt_rq);
- spin_unlock(&smt_rq->lock);
- }
-}
-
-/*
- * number of 'lost' timeslices this task wont be able to fully
- * utilize, if another task runs on a sibling. This models the
- * slowdown effect of other tasks running on siblings:
- */
-static inline unsigned long
-smt_slice(struct task_struct *p, struct sched_domain *sd)
-{
- return p->time_slice * (100 - sd->per_cpu_gain) / 100;
}
/*
- * To minimise lock contention and not have to drop this_rq's runlock we only
- * trylock the sibling runqueues and bypass those runqueues if we fail to
- * acquire their lock. As we only trylock the normal locking order does not
- * need to be obeyed.
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled.
+ *
+ * It also gets called by the fork code, when changing the parent's
+ * timeslices.
*/
-static int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
+void scheduler_tick(void)
{
- struct sched_domain *tmp, *sd = NULL;
- int ret = 0, i;
-
- /* kernel/rt threads do not participate in dependent sleeping */
- if (!p->mm || rt_task(p))
- return 0;
-
- for_each_domain(this_cpu, tmp) {
- if (tmp->flags & SD_SHARE_CPUPOWER) {
- sd = tmp;
- break;
- }
- }
-
- if (!sd)
- return 0;
-
- for_each_cpu_mask(i, sd->span) {
- struct task_struct *smt_curr;
- struct rq *smt_rq;
-
- if (i == this_cpu)
- continue;
-
- smt_rq = cpu_rq(i);
- if (unlikely(!spin_trylock(&smt_rq->lock)))
- continue;
-
- smt_curr = smt_rq->curr;
+ unsigned long long now = sched_clock();
+ struct task_struct *p = current;
+ int cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(cpu);
- if (!smt_curr->mm)
- goto unlock;
+ update_cpu_clock(p, rq, now);
- /*
- * If a user task with lower static priority than the
- * running task on the SMT sibling is trying to schedule,
- * delay it till there is proportionately less timeslice
- * left of the sibling task to prevent a lower priority
- * task from using an unfair proportion of the
- * physical cpu's resources. -ck
- */
- if (rt_task(smt_curr)) {
- /*
- * With real time tasks we run non-rt tasks only
- * per_cpu_gain% of the time.
- */
- if ((jiffies % DEF_TIMESLICE) >
- (sd->per_cpu_gain * DEF_TIMESLICE / 100))
- ret = 1;
- } else {
- if (smt_curr->static_prio < p->static_prio &&
- !TASK_PREEMPTS_CURR(p, smt_rq) &&
- smt_slice(smt_curr, sd) > task_timeslice(p))
- ret = 1;
- }
-unlock:
- spin_unlock(&smt_rq->lock);
- }
- return ret;
-}
-#else
-static inline void wake_sleeping_dependent(int this_cpu)
-{
-}
-static inline int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
-{
- return 0;
-}
+ if (p != rq->idle)
+ task_running_tick(rq, p);
+#ifdef CONFIG_SMP
+ update_load(rq);
+ if (time_after_eq(jiffies, rq->next_balance))
+ raise_softirq(SCHED_SOFTIRQ);
#endif
+}
#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
/*
* Spinlock count overflowing soon?
*/
- DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
+ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
+ PREEMPT_MASK - 10);
}
EXPORT_SYMBOL(add_preempt_count);
"%s/0x%08x/%d\n",
current->comm, preempt_count(), current->pid);
debug_show_held_locks(current);
+ if (irqs_disabled())
+ print_irqtrace_events(current);
dump_stack();
}
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
if (!rq->nr_running) {
next = rq->idle;
rq->expired_timestamp = 0;
- wake_sleeping_dependent(cpu);
goto switch_tasks;
}
}
}
}
next->sleep_type = SLEEP_NORMAL;
- if (dependent_sleeper(cpu, rq, next))
- next = rq->idle;
switch_tasks:
if (next == rq->idle)
schedstat_inc(rq, sched_goidle);
sched_info_switch(prev, next);
if (likely(prev != next)) {
- next->timestamp = now;
+ next->timestamp = next->last_ran = now;
rq->nr_switches++;
rq->curr = next;
++*switch_count;
}
/**
- * sched_setscheduler - change the scheduling policy and/or RT priority of
- * a thread.
+ * 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: the task may be already dead
+ * NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
/**
* sys_sched_yield - yield the current processor to other threads.
*
- * this function yields the current CPU by moving the calling thread
+ * This function yields the current CPU by moving the calling thread
* to the expired array. If there are no other threads running on this
* CPU then this function will return.
*/
return 0;
}
-static inline int __resched_legal(int expected_preempt_count)
-{
- if (unlikely(preempt_count() != expected_preempt_count))
- return 0;
- if (unlikely(system_state != SYSTEM_RUNNING))
- return 0;
- return 1;
-}
-
static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
int __sched cond_resched(void)
{
- if (need_resched() && __resched_legal(0)) {
+ if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
+ system_state == SYSTEM_RUNNING) {
__cond_resched();
return 1;
}
ret = 1;
spin_lock(lock);
}
- if (need_resched() && __resched_legal(1)) {
+ if (need_resched() && system_state == SYSTEM_RUNNING) {
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(0)) {
+ if (need_resched() && system_state == SYSTEM_RUNNING) {
raw_local_irq_disable();
_local_bh_enable();
raw_local_irq_enable();
/**
* yield - yield the current processor to other threads.
*
- * this is a shortcut for kernel-space yielding - it marks the
+ * This is a shortcut for kernel-space yielding - it marks the
* thread runnable and calls sys_sched_yield().
*/
void __sched yield(void)
return retval;
}
-static inline struct task_struct *eldest_child(struct task_struct *p)
-{
- if (list_empty(&p->children))
- return NULL;
- return list_entry(p->children.next,struct task_struct,sibling);
-}
-
-static inline struct task_struct *older_sibling(struct task_struct *p)
-{
- if (p->sibling.prev==&p->parent->children)
- return NULL;
- return list_entry(p->sibling.prev,struct task_struct,sibling);
-}
-
-static inline struct task_struct *younger_sibling(struct task_struct *p)
-{
- if (p->sibling.next==&p->parent->children)
- return NULL;
- return list_entry(p->sibling.next,struct task_struct,sibling);
-}
-
static const char stat_nam[] = "RSDTtZX";
static void show_task(struct task_struct *p)
{
- struct task_struct *relative;
unsigned long free = 0;
unsigned state;
free = (unsigned long)n - (unsigned long)end_of_stack(p);
}
#endif
- printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
- if ((relative = eldest_child(p)))
- printk("%5d ", relative->pid);
- else
- printk(" ");
- if ((relative = younger_sibling(p)))
- printk("%7d", relative->pid);
- else
- printk(" ");
- if ((relative = older_sibling(p)))
- printk(" %5d", relative->pid);
- else
- printk(" ");
+ printk("%5lu %5d %6d", free, p->pid, p->parent->pid);
if (!p->mm)
printk(" (L-TLB)\n");
else
* console might take alot of time:
*/
touch_nmi_watchdog();
- if (p->state & state_filter)
+ if (!state_filter || (p->state & state_filter))
show_task(p);
} while_each_thread(g, p);
* afterwards, and pretending it was a local activate.
* This way is cleaner and logically correct.
*/
- p->timestamp = p->timestamp - rq_src->timestamp_last_tick
- + rq_dest->timestamp_last_tick;
+ p->timestamp = p->timestamp - rq_src->most_recent_timestamp
+ + rq_dest->most_recent_timestamp;
deactivate_task(p, rq_src);
__activate_task(p, rq_dest);
if (TASK_PREEMPTS_CURR(p, rq_dest))
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+ " has parent");
break;
}
printk("span %s\n", str);
if (!cpu_isset(cpu, sd->span))
- printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
+ printk(KERN_ERR "ERROR: domain->span does not contain "
+ "CPU%d\n", cpu);
if (!cpu_isset(cpu, group->cpumask))
- printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
+ printk(KERN_ERR "ERROR: domain->groups does not contain"
+ " CPU%d\n", cpu);
printk(KERN_DEBUG);
for (i = 0; i < level + 2; i++)
if (!group->cpu_power) {
printk("\n");
- printk(KERN_ERR "ERROR: domain->cpu_power not set\n");
+ printk(KERN_ERR "ERROR: domain->cpu_power not "
+ "set\n");
}
if (!cpus_weight(group->cpumask)) {
printk("\n");
if (!cpus_equal(sd->span, groupmask))
- printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+ printk(KERN_ERR "ERROR: groups don't span "
+ "domain->span\n");
level++;
sd = sd->parent;
+ if (!sd)
+ continue;
- if (sd) {
- if (!cpus_subset(groupmask, sd->span))
- printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
- }
+ if (!cpus_subset(groupmask, sd->span))
+ printk(KERN_ERR "ERROR: parent span is not a superset "
+ "of domain->span\n");
} while (sd);
}
}
/* cpus with isolated domains */
-static cpumask_t __cpuinitdata cpu_isolated_map = CPU_MASK_NONE;
+static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
*/
static void touch_cache(void *__cache, unsigned long __size)
{
- unsigned long size = __size/sizeof(long), chunk1 = size/3,
- chunk2 = 2*size/3;
+ unsigned long size = __size / sizeof(long);
+ unsigned long chunk1 = size / 3;
+ unsigned long chunk2 = 2 * size / 3;
unsigned long *cache = __cache;
int i;
*/
measure_one(cache, size, cpu1, cpu2);
for (i = 0; i < ITERATIONS; i++)
- cost1 += measure_one(cache, size - i*1024, cpu1, cpu2);
+ cost1 += measure_one(cache, size - i * 1024, cpu1, cpu2);
measure_one(cache, size, cpu2, cpu1);
for (i = 0; i < ITERATIONS; i++)
- cost1 += measure_one(cache, size - i*1024, cpu2, cpu1);
+ cost1 += measure_one(cache, size - i * 1024, cpu2, cpu1);
/*
* (We measure the non-migrating [cached] cost on both
measure_one(cache, size, cpu1, cpu1);
for (i = 0; i < ITERATIONS; i++)
- cost2 += measure_one(cache, size - i*1024, cpu1, cpu1);
+ cost2 += measure_one(cache, size - i * 1024, cpu1, cpu1);
measure_one(cache, size, cpu2, cpu2);
for (i = 0; i < ITERATIONS; i++)
- cost2 += measure_one(cache, size - i*1024, cpu2, cpu2);
+ cost2 += measure_one(cache, size - i * 1024, cpu2, cpu2);
/*
* Get the per-iteration migration cost:
*/
- do_div(cost1, 2*ITERATIONS);
- do_div(cost2, 2*ITERATIONS);
+ do_div(cost1, 2 * ITERATIONS);
+ do_div(cost2, 2 * ITERATIONS);
return cost1 - cost2;
}
*/
cache = vmalloc(max_size);
if (!cache) {
- printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
+ printk("could not vmalloc %d bytes for cache!\n", 2 * max_size);
return 1000000; /* return 1 msec on very small boxen */
}
avg_fluct = (avg_fluct + fluct)/2;
if (migration_debug)
- printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n",
+ printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): "
+ "(%8Ld %8Ld)\n",
cpu1, cpu2, size,
(long)cost / 1000000,
((long)cost / 100000) % 10,
-1
#endif
);
- if (system_state == SYSTEM_BOOTING) {
- if (num_online_cpus() > 1) {
- printk("migration_cost=");
- for (distance = 0; distance <= max_distance; distance++) {
- if (distance)
- printk(",");
- printk("%ld", (long)migration_cost[distance] / 1000);
- }
- printk("\n");
+ if (system_state == SYSTEM_BOOTING && num_online_cpus() > 1) {
+ printk("migration_cost=");
+ for (distance = 0; distance <= max_distance; distance++) {
+ if (distance)
+ printk(",");
+ printk("%ld", (long)migration_cost[distance] / 1000);
}
+ printk("\n");
}
j1 = jiffies;
if (migration_debug)
- printk("migration: %ld seconds\n", (j1-j0)/HZ);
+ printk("migration: %ld seconds\n", (j1-j0) / HZ);
/*
* Move back to the original CPU. NUMA-Q gets confused
lock_cpu_hotplug();
arch_init_sched_domains(&cpu_online_map);
- cpus_andnot(non_isolated_cpus, cpu_online_map, cpu_isolated_map);
+ cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
if (cpus_empty(non_isolated_cpus))
cpu_set(smp_processor_id(), non_isolated_cpus);
unlock_cpu_hotplug();
set_load_weight(&init_task);
+#ifdef CONFIG_SMP
+ open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);
+#endif
+
#ifdef CONFIG_RT_MUTEXES
plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
#endif
printk("in_atomic():%d, irqs_disabled():%d\n",
in_atomic(), irqs_disabled());
debug_show_held_locks(current);
+ if (irqs_disabled())
+ print_irqtrace_events(current);
dump_stack();
}
#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff