unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
- resched_curr(rq);
+ if (cpu_online(cpu) || cpu == smp_processor_id())
+ resched_curr(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#ifdef CONFIG_SMP
if (cpu == rq->cpu) {
- schedstat_inc(rq->ttwu_local);
- schedstat_inc(p->se.statistics.nr_wakeups_local);
+ __schedstat_inc(rq->ttwu_local);
+ __schedstat_inc(p->se.statistics.nr_wakeups_local);
} else {
struct sched_domain *sd;
- schedstat_inc(p->se.statistics.nr_wakeups_remote);
+ __schedstat_inc(p->se.statistics.nr_wakeups_remote);
rcu_read_lock();
for_each_domain(rq->cpu, sd) {
if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
- schedstat_inc(sd->ttwu_wake_remote);
+ __schedstat_inc(sd->ttwu_wake_remote);
break;
}
}
}
if (wake_flags & WF_MIGRATED)
- schedstat_inc(p->se.statistics.nr_wakeups_migrate);
+ __schedstat_inc(p->se.statistics.nr_wakeups_migrate);
#endif /* CONFIG_SMP */
- schedstat_inc(rq->ttwu_count);
- schedstat_inc(p->se.statistics.nr_wakeups);
+ __schedstat_inc(rq->ttwu_count);
+ __schedstat_inc(p->se.statistics.nr_wakeups);
if (wake_flags & WF_SYNC)
- schedstat_inc(p->se.statistics.nr_wakeups_sync);
+ __schedstat_inc(p->se.statistics.nr_wakeups_sync);
}
static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
* If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, wait until its done referencing the task.
*
- * Pairs with the smp_store_release() in finish_lock_switch().
+ * Pairs with the smp_store_release() in finish_task().
*
* This ensures that tasks getting woken will be fully ordered against
* their previous state and preserve Program Order.
p->state = TASK_WAKING;
if (p->in_iowait) {
- delayacct_blkio_end();
+ delayacct_blkio_end(p);
atomic_dec(&task_rq(p)->nr_iowait);
}
#else /* CONFIG_SMP */
if (p->in_iowait) {
- delayacct_blkio_end();
+ delayacct_blkio_end(p);
atomic_dec(&task_rq(p)->nr_iowait);
}
if (!task_on_rq_queued(p)) {
if (p->in_iowait) {
- delayacct_blkio_end();
+ delayacct_blkio_end(p);
atomic_dec(&rq->nr_iowait);
}
ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
* Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
* as we're not fully set-up yet.
*/
+ p->recent_used_cpu = task_cpu(p);
__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
rq = __task_rq_lock(p, &rf);
#endif /* CONFIG_PREEMPT_NOTIFIERS */
+static inline void prepare_task(struct task_struct *next)
+{
+#ifdef CONFIG_SMP
+ /*
+ * Claim the task as running, we do this before switching to it
+ * such that any running task will have this set.
+ */
+ next->on_cpu = 1;
+#endif
+}
+
+static inline void finish_task(struct task_struct *prev)
+{
+#ifdef CONFIG_SMP
+ /*
+ * After ->on_cpu is cleared, the task can be moved to a different CPU.
+ * We must ensure this doesn't happen until the switch is completely
+ * finished.
+ *
+ * In particular, the load of prev->state in finish_task_switch() must
+ * happen before this.
+ *
+ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
+ */
+ smp_store_release(&prev->on_cpu, 0);
+#endif
+}
+
+static inline void
+prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+ /*
+ * 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:
+ */
+ rq_unpin_lock(rq, rf);
+ spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+#ifdef CONFIG_DEBUG_SPINLOCK
+ /* this is a valid case when another task releases the spinlock */
+ rq->lock.owner = next;
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq)
+{
+ /*
+ * If we are tracking spinlock dependencies then we have to
+ * fix up the runqueue lock - which gets 'carried over' from
+ * prev into current:
+ */
+ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
/**
* prepare_task_switch - prepare to switch tasks
* @rq: the runqueue preparing to switch
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
- prepare_lock_switch(rq, next);
+ prepare_task(next);
prepare_arch_switch(next);
}
* the scheduled task must drop that reference.
*
* We must observe prev->state before clearing prev->on_cpu (in
- * finish_lock_switch), otherwise a concurrent wakeup can get prev
+ * finish_task), otherwise a concurrent wakeup can get prev
* running on another CPU and we could rave with its RUNNING -> DEAD
* transition, resulting in a double drop.
*/
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
- /*
- * The membarrier system call requires a full memory barrier
- * after storing to rq->curr, before going back to user-space.
- *
- * TODO: This smp_mb__after_unlock_lock can go away if PPC end
- * up adding a full barrier to switch_mm(), or we should figure
- * out if a smp_mb__after_unlock_lock is really the proper API
- * to use.
- */
- smp_mb__after_unlock_lock();
- finish_lock_switch(rq, prev);
+ finish_task(prev);
+ finish_lock_switch(rq);
finish_arch_post_lock_switch();
fire_sched_in_preempt_notifiers(current);
- if (mm)
+ /*
+ * When switching through a kernel thread, the loop in
+ * membarrier_{private,global}_expedited() may have observed that
+ * kernel thread and not issued an IPI. It is therefore possible to
+ * schedule between user->kernel->user threads without passing though
+ * switch_mm(). Membarrier requires a barrier after storing to
+ * rq->curr, before returning to userspace, so provide them here:
+ *
+ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
+ * provided by mmdrop(),
+ * - a sync_core for SYNC_CORE.
+ */
+ if (mm) {
+ membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
+ }
if (unlikely(prev_state == TASK_DEAD)) {
if (prev->sched_class->task_dead)
prev->sched_class->task_dead(prev);
*/
arch_start_context_switch(prev);
+ /*
+ * If mm is non-NULL, we pass through switch_mm(). If mm is
+ * NULL, we will pass through mmdrop() in finish_task_switch().
+ * Both of these contain the full memory barrier required by
+ * membarrier after storing to rq->curr, before returning to
+ * user-space.
+ */
if (!mm) {
next->active_mm = oldmm;
mmgrab(oldmm);
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
- /*
- * 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:
- */
- rq_unpin_lock(rq, rf);
- spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+ prepare_lock_switch(rq, next, rf);
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
+ *
+ * The membarrier system call requires a full memory barrier
+ * after coming from user-space, before storing to rq->curr.
*/
rq_lock(rq, &rf);
smp_mb__after_spinlock();
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
- * rq->curr, before returning to user-space. For TSO
- * (e.g. x86), the architecture must provide its own
- * barrier in switch_mm(). For weakly ordered machines
- * for which spin_unlock() acts as a full memory
- * barrier, finish_lock_switch() in common code takes
- * care of this barrier. For weakly ordered machines for
- * which spin_unlock() acts as a RELEASE barrier (only
- * arm64 and PowerPC), arm64 has a full barrier in
- * switch_to(), and PowerPC has
- * smp_mb__after_unlock_lock() before
- * finish_lock_switch().
+ * rq->curr, before returning to user-space.
+ *
+ * Here are the schemes providing that barrier on the
+ * various architectures:
+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
+ * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+ * - finish_lock_switch() for weakly-ordered
+ * architectures where spin_unlock is a full barrier,
+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
+ * is a RELEASE barrier),
*/
++*switch_count;
return -EINVAL;
}
- if (attr->sched_flags &
- ~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
+ if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV))
return -EINVAL;
/*
}
if (user) {
+ if (attr->sched_flags & SCHED_FLAG_SUGOV)
+ return -EINVAL;
+
retval = security_task_setscheduler(p);
if (retval)
return retval;
}
#endif
#ifdef CONFIG_SMP
- if (dl_bandwidth_enabled() && dl_policy(policy)) {
+ if (dl_bandwidth_enabled() && dl_policy(policy) &&
+ !(attr->sched_flags & SCHED_FLAG_SUGOV)) {
cpumask_t *span = rq->rd->span;
/*
}
EXPORT_SYMBOL_GPL(sched_setattr);
+int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, false, true);
+}
+
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
* @p: the task in question.
ret = sched_getaffinity(pid, mask);
if (ret == 0) {
- size_t retlen = min_t(size_t, len, cpumask_size());
+ unsigned int retlen = min(len, cpumask_size());
if (copy_to_user(user_mask_ptr, mask, retlen))
ret = -EFAULT;
git.samba.org / sfrench / cifs-2.6.git / blobdiff