#include <linux/init_task.h>
#include <linux/context_tracking.h>
#include <linux/compiler.h>
+#include <linux/frame.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
/*
* context_switch - switch to the new MM and the new thread's register state.
*/
-static inline struct rq *
+static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
- to_wakeup = wq_worker_sleeping(prev, cpu);
+ to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
balance_callback(rq);
}
+STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */
static inline void sched_submit_work(struct task_struct *tsk)
{
case CPU_UP_PREPARE:
rq->calc_load_update = calc_load_update;
+ account_reset_rq(rq);
break;
case CPU_ONLINE:
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
- static void free_sched_group(struct task_group *tg)
+ static void sched_free_group(struct task_group *tg)
{
free_fair_sched_group(tg);
free_rt_sched_group(tg);
return tg;
err:
- free_sched_group(tg);
+ sched_free_group(tg);
return ERR_PTR(-ENOMEM);
}
}
/* rcu callback to free various structures associated with a task group */
- static void free_sched_group_rcu(struct rcu_head *rhp)
+ static void sched_free_group_rcu(struct rcu_head *rhp)
{
/* now it should be safe to free those cfs_rqs */
- free_sched_group(container_of(rhp, struct task_group, rcu));
+ sched_free_group(container_of(rhp, struct task_group, rcu));
}
- /* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
/* wait for possible concurrent references to cfs_rqs complete */
- call_rcu(&tg->rcu, free_sched_group_rcu);
+ call_rcu(&tg->rcu, sched_free_group_rcu);
}
void sched_offline_group(struct task_group *tg)
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);
+ sched_online_group(tg, parent);
+
return &tg->css;
}
- static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+ static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
- struct task_group *parent = css_tg(css->parent);
- if (parent)
- sched_online_group(tg, parent);
- return 0;
+ sched_offline_group(tg);
}
static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
- sched_destroy_group(tg);
- }
-
- static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
- {
- struct task_group *tg = css_tg(css);
-
- sched_offline_group(tg);
+ /*
+ * Relies on the RCU grace period between css_released() and this.
+ */
+ sched_free_group(tg);
}
static void cpu_cgroup_fork(struct task_struct *task)
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
+ .css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
- .css_online = cpu_cgroup_css_online,
- .css_offline = cpu_cgroup_css_offline,
.fork = cpu_cgroup_fork,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.legacy_cftypes = cpu_files,
- .early_init = 1,
+ .early_init = true,
};
#endif /* CONFIG_CGROUP_SCHED */
}
static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
- u64 reset)
+ u64 val)
{
struct cpuacct *ca = css_ca(css);
int err = 0;
int i;
- if (reset) {
+ /*
+ * Only allow '0' here to do a reset.
+ */
+ if (val) {
err = -EINVAL;
goto out;
}
void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
struct cpuacct *ca;
- int cpu;
-
- cpu = task_cpu(tsk);
rcu_read_lock();
-
- ca = task_ca(tsk);
-
- while (true) {
- u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
- *cpuusage += cputime;
-
- ca = parent_ca(ca);
- if (!ca)
- break;
- }
-
+ for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
+ *this_cpu_ptr(ca->cpuusage) += cputime;
rcu_read_unlock();
}
*
* Note: it's the caller that updates the account of the root cgroup.
*/
- void cpuacct_account_field(struct task_struct *p, int index, u64 val)
+ void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
{
- struct kernel_cpustat *kcpustat;
struct cpuacct *ca;
rcu_read_lock();
- ca = task_ca(p);
- while (ca != &root_cpuacct) {
- kcpustat = this_cpu_ptr(ca->cpustat);
- kcpustat->cpustat[index] += val;
- ca = parent_ca(ca);
- }
+ for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
+ this_cpu_ptr(ca->cpustat)->cpustat[index] += val;
rcu_read_unlock();
}
.css_alloc = cpuacct_css_alloc,
.css_free = cpuacct_css_free,
.legacy_cftypes = files,
- .early_init = 1,
+ .early_init = true,
};
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 now = cfs_rq_clock_task(cfs_rq);
- int cpu = cpu_of(rq_of(cfs_rq));
+ struct rq *rq = rq_of(cfs_rq);
+ int cpu = cpu_of(rq);
/*
* Track task load average for carrying it to new CPU after migrated, and
if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
update_tg_load_avg(cfs_rq, 0);
+
+ if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+ unsigned long max = rq->cpu_capacity_orig;
+
+ /*
+ * There are a few boundary cases this might miss but it should
+ * get called often enough that that should (hopefully) not be
+ * a real problem -- added to that it only calls on the local
+ * CPU, so if we enqueue remotely we'll miss an update, but
+ * the next tick/schedule should update.
+ *
+ * It will not get called when we go idle, because the idle
+ * thread is a different class (!fair), nor will the utilization
+ * number include things like RT tasks.
+ *
+ * As is, the util number is not freq-invariant (we'd have to
+ * implement arch_scale_freq_capacity() for that).
+ *
+ * See cpu_util().
+ */
+ cpufreq_update_util(rq_clock(rq),
+ min(cfs_rq->avg.util_avg, max), max);
+ }
}
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
+ bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING);
+ bool curr = cfs_rq->curr == se;
+
/*
- * Update the normalized vruntime before updating min_vruntime
- * through calling update_curr().
+ * If we're the current task, we must renormalise before calling
+ * update_curr().
*/
- if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
+ if (renorm && curr)
se->vruntime += cfs_rq->min_vruntime;
+ update_curr(cfs_rq);
+
/*
- * Update run-time statistics of the 'current'.
+ * Otherwise, renormalise after, such that we're placed at the current
+ * moment in time, instead of some random moment in the past.
*/
- update_curr(cfs_rq);
+ if (renorm && !curr)
+ se->vruntime += cfs_rq->min_vruntime;
+
enqueue_entity_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
update_cfs_shares(cfs_rq);
update_stats_enqueue(cfs_rq, se);
check_spread(cfs_rq, se);
}
- if (se != cfs_rq->curr)
+ if (!curr)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
return i;
/*
- * Otherwise, iterate the domains and find an elegible idle cpu.
+ * Otherwise, iterate the domains and find an eligible idle cpu.
+ *
+ * A completely idle sched group at higher domains is more
+ * desirable than an idle group at a lower level, because lower
+ * domains have smaller groups and usually share hardware
+ * resources which causes tasks to contend on them, e.g. x86
+ * hyperthread siblings in the lowest domain (SMT) can contend
+ * on the shared cpu pipeline.
+ *
+ * However, while we prefer idle groups at higher domains
+ * finding an idle cpu at the lowest domain is still better than
+ * returning 'target', which we've already established, isn't
+ * idle.
*/
sd = rcu_dereference(per_cpu(sd_llc, target));
for_each_lower_domain(sd) {
tsk_cpus_allowed(p)))
goto next;
+ /* Ensure the entire group is idle */
for_each_cpu(i, sched_group_cpus(sg)) {
if (i == target || !idle_cpu(i))
goto next;
}
+ /*
+ * It doesn't matter which cpu we pick, the
+ * whole group is idle.
+ */
target = cpumask_first_and(sched_group_cpus(sg),
tsk_cpus_allowed(p));
goto done;
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @time: Current time.
+ * @util: Current utilization.
+ * @max: Utilization ceiling.
+ *
+ * This function is called by the scheduler on every invocation of
+ * update_load_avg() on the CPU whose utilization is being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ */
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
+{
+ struct update_util_data *data;
+
+ data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+ if (data)
+ data->func(data, time, util, max);
+}
+
+/**
+ * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
+ * @time: Current time.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid. Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_trigger_update(u64 time)
+{
+ cpufreq_update_util(time, ULONG_MAX, 0);
+}
+#else
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
+static inline void cpufreq_trigger_update(u64 time) {}
+#endif /* CONFIG_CPU_FREQ */
++
+ static inline void account_reset_rq(struct rq *rq)
+ {
+ #ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ rq->prev_irq_time = 0;
+ #endif
+ #ifdef CONFIG_PARAVIRT
+ rq->prev_steal_time = 0;
+ #endif
+ #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+ rq->prev_steal_time_rq = 0;
+ #endif
+ }