#include <linux/ftrace.h>
#include <linux/slab.h>
#include <linux/init_task.h>
+#include <linux/binfmts.h>
+#include <asm/switch_to.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
#include <asm/mutex.h>
#ifdef HAVE_JUMP_LABEL
-#define jump_label_key__true jump_label_key_enabled
-#define jump_label_key__false jump_label_key_disabled
+#define jump_label_key__true STATIC_KEY_INIT_TRUE
+#define jump_label_key__false STATIC_KEY_INIT_FALSE
#define SCHED_FEAT(name, enabled) \
jump_label_key__##enabled ,
-struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
+struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
#include "features.h"
};
static void sched_feat_disable(int i)
{
- if (jump_label_enabled(&sched_feat_keys[i]))
- jump_label_dec(&sched_feat_keys[i]);
+ if (static_key_enabled(&sched_feat_keys[i]))
+ static_key_slow_dec(&sched_feat_keys[i]);
}
static void sched_feat_enable(int i)
{
- if (!jump_label_enabled(&sched_feat_keys[i]))
- jump_label_inc(&sched_feat_keys[i]);
+ if (!static_key_enabled(&sched_feat_keys[i]))
+ static_key_slow_inc(&sched_feat_keys[i]);
}
#else
static void sched_feat_disable(int i) { };
delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
- if (static_branch((¶virt_steal_rq_enabled))) {
+ if (static_key_false((¶virt_steal_rq_enabled))) {
u64 st;
steal = paravirt_steal_clock(cpu_of(rq));
*/
static int select_fallback_rq(int cpu, struct task_struct *p)
{
- int dest_cpu;
const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+ enum { cpuset, possible, fail } state = cpuset;
+ int dest_cpu;
/* Look for allowed, online CPU in same node. */
- for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+ for_each_cpu(dest_cpu, nodemask) {
+ if (!cpu_online(dest_cpu))
+ continue;
+ if (!cpu_active(dest_cpu))
+ continue;
if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
return dest_cpu;
+ }
- /* Any allowed, online CPU? */
- dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask);
- if (dest_cpu < nr_cpu_ids)
- return dest_cpu;
+ for (;;) {
+ /* Any allowed, online CPU? */
+ for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
+ if (!cpu_online(dest_cpu))
+ continue;
+ if (!cpu_active(dest_cpu))
+ continue;
+ goto out;
+ }
- /* No more Mr. Nice Guy. */
- dest_cpu = cpuset_cpus_allowed_fallback(p);
- /*
- * Don't tell them about moving exiting tasks or
- * kernel threads (both mm NULL), since they never
- * leave kernel.
- */
- if (p->mm && printk_ratelimit()) {
- printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
- task_pid_nr(p), p->comm, cpu);
+ switch (state) {
+ case cpuset:
+ /* No more Mr. Nice Guy. */
+ cpuset_cpus_allowed_fallback(p);
+ state = possible;
+ break;
+
+ case possible:
+ do_set_cpus_allowed(p, cpu_possible_mask);
+ state = fail;
+ break;
+
+ case fail:
+ BUG();
+ break;
+ }
+ }
+
+out:
+ if (state != cpuset) {
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit()) {
+ printk_sched("process %d (%s) no longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, cpu);
+ }
}
return dest_cpu;
local_irq_enable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
finish_lock_switch(rq, prev);
+ finish_arch_post_lock_switch();
fire_sched_in_preempt_notifiers(current);
if (mm)
* Once we've updated the global active value, we need to apply the exponential
* weights adjusted to the number of cycles missed.
*/
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
{
long delta, active, n;
- if (time_before(jiffies, calc_load_update))
- return;
-
/*
* If we crossed a calc_load_update boundary, make sure to fold
* any pending idle changes, the respective CPUs might have
atomic_long_add(delta, &calc_load_tasks);
/*
- * If we were idle for multiple load cycles, apply them.
+ * It could be the one fold was all it took, we done!
*/
- if (ticks >= LOAD_FREQ) {
- n = ticks / LOAD_FREQ;
+ if (time_before(jiffies, calc_load_update + 10))
+ return;
- active = atomic_long_read(&calc_load_tasks);
- active = active > 0 ? active * FIXED_1 : 0;
+ /*
+ * Catch-up, fold however many we are behind still
+ */
+ delta = jiffies - calc_load_update - 10;
+ n = 1 + (delta / LOAD_FREQ);
- avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
- avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
- avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
- calc_load_update += n * LOAD_FREQ;
- }
+ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
- /*
- * Its possible the remainder of the above division also crosses
- * a LOAD_FREQ period, the regular check in calc_global_load()
- * which comes after this will take care of that.
- *
- * Consider us being 11 ticks before a cycle completion, and us
- * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
- * age us 4 cycles, and the test in calc_global_load() will
- * pick up the final one.
- */
+ calc_load_update += n * LOAD_FREQ;
}
#else
void calc_load_account_idle(struct rq *this_rq)
return 0;
}
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
{
}
#endif
{
long active;
- calc_global_nohz(ticks);
-
if (time_before(jiffies, calc_load_update + 10))
return;
avenrun[2] = calc_load(avenrun[2], EXP_15, active);
calc_load_update += LOAD_FREQ;
+
+ /*
+ * Account one period with whatever state we found before
+ * folding in the nohz state and ageing the entire idle period.
+ *
+ * This avoids loosing a sample when we go idle between
+ * calc_load_account_active() (10 ticks ago) and now and thus
+ * under-accounting.
+ */
+ calc_global_nohz();
}
/*
}
+#if !defined(CONFIG_XEN) || defined(CONFIG_VIRT_CPU_ACCOUNTING)
+# define cputime_to_u64(t) ((__force u64)(t))
+#else
+# include <linux/syscore_ops.h>
+# define NS_PER_TICK (1000000000 / HZ)
+
+static DEFINE_PER_CPU(u64, steal_snapshot);
+static DEFINE_PER_CPU(unsigned int, steal_residual);
+
+static u64 cputime_to_u64(cputime_t t)
+{
+ u64 s = this_vcpu_read(runstate.time[RUNSTATE_runnable]);
+ unsigned long adj = div_u64_rem(s - __this_cpu_read(steal_snapshot)
+ + __this_cpu_read(steal_residual),
+ NS_PER_TICK,
+ &__get_cpu_var(steal_residual));
+
+ __this_cpu_write(steal_snapshot, s);
+ if (t < jiffies_to_cputime(adj))
+ return 0;
+
+ return (__force u64)(t - jiffies_to_cputime(adj));
+}
+
+static void steal_resume(void)
+{
+ cputime_to_u64(((cputime_t)1 << (BITS_PER_LONG * sizeof(cputime_t)
+ / sizeof(long) - 1)) - 1);
+}
+
+static struct syscore_ops steal_syscore_ops = {
+ .resume = steal_resume,
+};
+
+static int __init steal_register(void)
+{
+ register_syscore_ops(&steal_syscore_ops);
+ return 0;
+}
+core_initcall(steal_register);
+#endif
+
/*
* Account user cpu time to a process.
* @p: the process that the cpu time gets accounted to
index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
/* Add user time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime_to_u64(cputime));
/* Account for user time used */
acct_update_integrals(p);
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime_to_u64(cputime));
/* Account for system time used */
acct_update_integrals(p);
struct rq *rq = this_rq();
if (atomic_read(&rq->nr_iowait) > 0)
- cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+ cpustat[CPUTIME_IOWAIT] += cputime_to_u64(cputime);
else
- cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+ cpustat[CPUTIME_IDLE] += cputime_to_u64(cputime);
}
static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
- if (static_branch(¶virt_steal_enabled)) {
+ if (static_key_false(¶virt_steal_enabled)) {
u64 steal, st = 0;
steal = paravirt_steal_clock(smp_processor_id());
return;
if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_IRQ] += cputime_to_u64(cputime_one_jiffy);
} else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_SOFTIRQ] += cputime_to_u64(cputime_one_jiffy);
} else if (this_cpu_ksoftirqd() == p) {
/*
* ksoftirqd time do not get accounted in cpu_softirq_time.
*/
static noinline void __schedule_bug(struct task_struct *prev)
{
- struct pt_regs *regs = get_irq_regs();
-
if (oops_in_progress)
return;
print_modules();
if (irqs_disabled())
print_irqtrace_events(prev);
-
- if (regs)
- show_regs(regs);
- else
- dump_stack();
+ dump_stack();
}
/*
}
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+#include <asm/mutex.h>
+
+#ifndef arch_cpu_is_running
+#define arch_cpu_is_running(cpu) true
+#endif
static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
{
*/
barrier();
- return owner->on_cpu;
+ return owner->on_cpu
+ && arch_cpu_is_running(task_thread_info(owner)->cpu);
}
/*
/**
* yield - yield the current processor to other threads.
*
- * This is a shortcut for kernel-space yielding - it marks the
- * thread runnable and calls sys_sched_yield().
+ * Do not ever use this function, there's a 99% chance you're doing it wrong.
+ *
+ * The scheduler is at all times free to pick the calling task as the most
+ * eligible task to run, if removing the yield() call from your code breaks
+ * it, its already broken.
+ *
+ * Typical broken usage is:
+ *
+ * while (!event)
+ * yield();
+ *
+ * where one assumes that yield() will let 'the other' process run that will
+ * make event true. If the current task is a SCHED_FIFO task that will never
+ * happen. Never use yield() as a progress guarantee!!
+ *
+ * If you want to use yield() to wait for something, use wait_event().
+ * If you want to use yield() to be 'nice' for others, use cond_resched().
+ * If you still want to use yield(), do not!
*/
void __sched yield(void)
{
unsigned long action, void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
+ case CPU_STARTING:
case CPU_DOWN_FAILED:
set_cpu_active((long)hcpu, true);
return NOTIFY_OK;
if (!sg)
return -ENOMEM;
+ sg->next = sg;
+
*per_cpu_ptr(sdd->sg, j) = sg;
sgp = kzalloc_node(sizeof(struct sched_group_power),
struct sd_data *sdd = &tl->data;
for_each_cpu(j, cpu_map) {
- struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
- if (sd && (sd->flags & SD_OVERLAP))
- free_sched_groups(sd->groups, 0);
- kfree(*per_cpu_ptr(sdd->sd, j));
- kfree(*per_cpu_ptr(sdd->sg, j));
- kfree(*per_cpu_ptr(sdd->sgp, j));
+ struct sched_domain *sd;
+
+ if (sdd->sd) {
+ sd = *per_cpu_ptr(sdd->sd, j);
+ if (sd && (sd->flags & SD_OVERLAP))
+ free_sched_groups(sd->groups, 0);
+ kfree(*per_cpu_ptr(sdd->sd, j));
+ }
+
+ if (sdd->sg)
+ kfree(*per_cpu_ptr(sdd->sg, j));
+ if (sdd->sgp)
+ kfree(*per_cpu_ptr(sdd->sgp, j));
}
free_percpu(sdd->sd);
+ sdd->sd = NULL;
free_percpu(sdd->sg);
+ sdd->sg = NULL;
free_percpu(sdd->sgp);
+ sdd->sgp = NULL;
}
}
struct task_group, css);
}
-static struct cgroup_subsys_state *
-cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
{
struct task_group *tg, *parent;
return &tg->css;
}
-static void
-cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+static void cpu_cgroup_destroy(struct cgroup *cgrp)
{
struct task_group *tg = cgroup_tg(cgrp);
sched_destroy_group(tg);
}
-static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+static int cpu_cgroup_can_attach(struct cgroup *cgrp,
struct cgroup_taskset *tset)
{
struct task_struct *task;
return 0;
}
-static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+static void cpu_cgroup_attach(struct cgroup *cgrp,
struct cgroup_taskset *tset)
{
struct task_struct *task;
}
static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup *old_cgrp, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp,
+ struct task_struct *task)
{
/*
* cgroup_exit() is called in the copy_process() failure path.
*/
/* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_create(
- struct cgroup_subsys *ss, struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
{
struct cpuacct *ca;
}
/* destroy an existing cpu accounting group */
-static void
-cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+static void cpuacct_destroy(struct cgroup *cgrp)
{
struct cpuacct *ca = cgroup_ca(cgrp);