Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: Fix kthread_bind() by moving the body of kthread_bind() to sched.c sched: Disable SD_PREFER_LOCAL at node level sched: Fix boot crash by zalloc()ing most of the cpu masks sched: Strengthen buddies and mitigate buddy induced latencies
This commit is contained in:
commit
608221fdf9
|
@ -143,7 +143,7 @@ extern unsigned long node_remap_size[];
|
|||
| 1*SD_BALANCE_FORK \
|
||||
| 0*SD_BALANCE_WAKE \
|
||||
| 1*SD_WAKE_AFFINE \
|
||||
| 1*SD_PREFER_LOCAL \
|
||||
| 0*SD_PREFER_LOCAL \
|
||||
| 0*SD_SHARE_CPUPOWER \
|
||||
| 0*SD_POWERSAVINGS_BALANCE \
|
||||
| 0*SD_SHARE_PKG_RESOURCES \
|
||||
|
|
|
@ -149,29 +149,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
|
|||
}
|
||||
EXPORT_SYMBOL(kthread_create);
|
||||
|
||||
/**
|
||||
* kthread_bind - bind a just-created kthread to a cpu.
|
||||
* @k: thread created by kthread_create().
|
||||
* @cpu: cpu (might not be online, must be possible) for @k to run on.
|
||||
*
|
||||
* Description: This function is equivalent to set_cpus_allowed(),
|
||||
* except that @cpu doesn't need to be online, and the thread must be
|
||||
* stopped (i.e., just returned from kthread_create()).
|
||||
*/
|
||||
void kthread_bind(struct task_struct *k, unsigned int cpu)
|
||||
{
|
||||
/* Must have done schedule() in kthread() before we set_task_cpu */
|
||||
if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
|
||||
WARN_ON(1);
|
||||
return;
|
||||
}
|
||||
set_task_cpu(k, cpu);
|
||||
k->cpus_allowed = cpumask_of_cpu(cpu);
|
||||
k->rt.nr_cpus_allowed = 1;
|
||||
k->flags |= PF_THREAD_BOUND;
|
||||
}
|
||||
EXPORT_SYMBOL(kthread_bind);
|
||||
|
||||
/**
|
||||
* kthread_stop - stop a thread created by kthread_create().
|
||||
* @k: thread created by kthread_create().
|
||||
|
|
|
@ -1992,6 +1992,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
|
|||
p->sched_class->prio_changed(rq, p, oldprio, running);
|
||||
}
|
||||
|
||||
/**
|
||||
* kthread_bind - bind a just-created kthread to a cpu.
|
||||
* @k: thread created by kthread_create().
|
||||
* @cpu: cpu (might not be online, must be possible) for @k to run on.
|
||||
*
|
||||
* Description: This function is equivalent to set_cpus_allowed(),
|
||||
* except that @cpu doesn't need to be online, and the thread must be
|
||||
* stopped (i.e., just returned from kthread_create()).
|
||||
*
|
||||
* Function lives here instead of kthread.c because it messes with
|
||||
* scheduler internals which require locking.
|
||||
*/
|
||||
void kthread_bind(struct task_struct *p, unsigned int cpu)
|
||||
{
|
||||
struct rq *rq = cpu_rq(cpu);
|
||||
unsigned long flags;
|
||||
|
||||
/* Must have done schedule() in kthread() before we set_task_cpu */
|
||||
if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
|
||||
WARN_ON(1);
|
||||
return;
|
||||
}
|
||||
|
||||
spin_lock_irqsave(&rq->lock, flags);
|
||||
set_task_cpu(p, cpu);
|
||||
p->cpus_allowed = cpumask_of_cpu(cpu);
|
||||
p->rt.nr_cpus_allowed = 1;
|
||||
p->flags |= PF_THREAD_BOUND;
|
||||
spin_unlock_irqrestore(&rq->lock, flags);
|
||||
}
|
||||
EXPORT_SYMBOL(kthread_bind);
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* Is this task likely cache-hot:
|
||||
|
@ -2004,7 +2036,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
|
|||
/*
|
||||
* Buddy candidates are cache hot:
|
||||
*/
|
||||
if (sched_feat(CACHE_HOT_BUDDY) &&
|
||||
if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
|
||||
(&p->se == cfs_rq_of(&p->se)->next ||
|
||||
&p->se == cfs_rq_of(&p->se)->last))
|
||||
return 1;
|
||||
|
@ -9532,13 +9564,13 @@ void __init sched_init(void)
|
|||
current->sched_class = &fair_sched_class;
|
||||
|
||||
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
|
||||
alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
|
||||
zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
|
||||
#ifdef CONFIG_SMP
|
||||
#ifdef CONFIG_NO_HZ
|
||||
alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
|
||||
zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
|
||||
alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
|
||||
#endif
|
||||
alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
|
||||
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
|
||||
#endif /* SMP */
|
||||
|
||||
perf_event_init();
|
||||
|
|
|
@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
|
|||
* re-elected due to buddy favours.
|
||||
*/
|
||||
clear_buddies(cfs_rq, curr);
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
* Ensure that a task that missed wakeup preemption by a
|
||||
* narrow margin doesn't have to wait for a full slice.
|
||||
* This also mitigates buddy induced latencies under load.
|
||||
*/
|
||||
if (!sched_feat(WAKEUP_PREEMPT))
|
||||
return;
|
||||
|
||||
if (delta_exec < sysctl_sched_min_granularity)
|
||||
return;
|
||||
|
||||
if (cfs_rq->nr_running > 1) {
|
||||
struct sched_entity *se = __pick_next_entity(cfs_rq);
|
||||
s64 delta = curr->vruntime - se->vruntime;
|
||||
|
||||
if (delta > ideal_runtime)
|
||||
resched_task(rq_of(cfs_rq)->curr);
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
|
|||
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
struct sched_entity *se = __pick_next_entity(cfs_rq);
|
||||
struct sched_entity *buddy;
|
||||
struct sched_entity *left = se;
|
||||
|
||||
if (cfs_rq->next) {
|
||||
buddy = cfs_rq->next;
|
||||
cfs_rq->next = NULL;
|
||||
if (wakeup_preempt_entity(buddy, se) < 1)
|
||||
return buddy;
|
||||
}
|
||||
if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
|
||||
se = cfs_rq->next;
|
||||
|
||||
if (cfs_rq->last) {
|
||||
buddy = cfs_rq->last;
|
||||
cfs_rq->last = NULL;
|
||||
if (wakeup_preempt_entity(buddy, se) < 1)
|
||||
return buddy;
|
||||
}
|
||||
/*
|
||||
* Prefer last buddy, try to return the CPU to a preempted task.
|
||||
*/
|
||||
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
|
||||
se = cfs_rq->last;
|
||||
|
||||
clear_buddies(cfs_rq, se);
|
||||
|
||||
return se;
|
||||
}
|
||||
|
@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
|
|||
struct sched_entity *se = &curr->se, *pse = &p->se;
|
||||
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
|
||||
int sync = wake_flags & WF_SYNC;
|
||||
int scale = cfs_rq->nr_running >= sched_nr_latency;
|
||||
|
||||
update_curr(cfs_rq);
|
||||
|
||||
|
@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
|
|||
if (unlikely(se == pse))
|
||||
return;
|
||||
|
||||
/*
|
||||
* Only set the backward buddy when the current task is still on the
|
||||
* rq. This can happen when a wakeup gets interleaved with schedule on
|
||||
* the ->pre_schedule() or idle_balance() point, either of which can
|
||||
* drop the rq lock.
|
||||
*
|
||||
* Also, during early boot the idle thread is in the fair class, for
|
||||
* obvious reasons its a bad idea to schedule back to the idle thread.
|
||||
*/
|
||||
if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
|
||||
set_last_buddy(se);
|
||||
if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
|
||||
if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
|
||||
set_next_buddy(pse);
|
||||
|
||||
/*
|
||||
|
@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
|
|||
|
||||
BUG_ON(!pse);
|
||||
|
||||
if (wakeup_preempt_entity(se, pse) == 1)
|
||||
if (wakeup_preempt_entity(se, pse) == 1) {
|
||||
resched_task(curr);
|
||||
/*
|
||||
* Only set the backward buddy when the current task is still
|
||||
* on the rq. This can happen when a wakeup gets interleaved
|
||||
* with schedule on the ->pre_schedule() or idle_balance()
|
||||
* point, either of which can * drop the rq lock.
|
||||
*
|
||||
* Also, during early boot the idle thread is in the fair class,
|
||||
* for obvious reasons its a bad idea to schedule back to it.
|
||||
*/
|
||||
if (unlikely(!se->on_rq || curr == rq->idle))
|
||||
return;
|
||||
if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
|
||||
set_last_buddy(se);
|
||||
}
|
||||
}
|
||||
|
||||
static struct task_struct *pick_next_task_fair(struct rq *rq)
|
||||
|
|
Loading…
Reference in New Issue