/* Power(C) State timer broadcast control */
static void lapic_timer_state_broadcast(struct acpi_processor *pr,
struct acpi_processor_cx *cx,
int broadcast)
{
int state = cx - pr->power.states;
if (state >= pr->power.timer_broadcast_on_state) {
if (broadcast)
tick_broadcast_enter();
else
tick_broadcast_exit();
}
}
static bool tegra30_cpu_core_power_down(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
tick_broadcast_enter();
smp_wmb();
cpu_suspend(0, tegra30_sleep_cpu_secondary_finish);
tick_broadcast_exit();
return true;
}
static bool tegra30_cpu_cluster_power_down(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
/* All CPUs entering LP2 is not working.
* Don't let CPU0 enter LP2 when any secondary CPU is online.
*/
if (num_online_cpus() > 1 || !tegra_cpu_rail_off_ready()) {
cpu_do_idle();
return false;
}
tick_broadcast_enter();
tegra_idle_lp2_last();
tick_broadcast_exit();
return true;
}
/*
* AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
* pending message MSR. If we detect C1E, then we handle it the same
* way as C3 power states (local apic timer and TSC stop)
*/
static void amd_e400_idle(void)
{
if (!amd_e400_c1e_detected) {
u32 lo, hi;
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (lo & K8_INTP_C1E_ACTIVE_MASK) {
amd_e400_c1e_detected = true;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halt in AMD C1E");
pr_info("System has AMD C1E enabled\n");
}
}
if (amd_e400_c1e_detected) {
int cpu = smp_processor_id();
if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
cpumask_set_cpu(cpu, amd_e400_c1e_mask);
/* Force broadcast so ACPI can not interfere. */
tick_broadcast_force();
pr_info("Switch to broadcast mode on CPU%d\n", cpu);
}
tick_broadcast_enter();
default_idle();
/*
* The switch back from broadcast mode needs to be
* called with interrupts disabled.
*/
local_irq_disable();
tick_broadcast_exit();
local_irq_enable();
} else
default_idle();
}
/*
* AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
* states (local apic timer and TSC stop).
*/
static void amd_e400_idle(void)
{
/*
* We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
* gets set after static_cpu_has() places have been converted via
* alternatives.
*/
if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
default_idle();
return;
}
tick_broadcast_enter();
default_idle();
/*
* The switch back from broadcast mode needs to be called with
* interrupts disabled.
*/
local_irq_disable();
tick_broadcast_exit();
local_irq_enable();
}
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
mutex_unlock(&round_robin_lock);
return;
}
for_each_cpu(cpu, tmp) {
if (cpu_weight[cpu] < min_weight) {
min_weight = cpu_weight[cpu];
preferred_cpu = cpu;
}
}
if (tsk_in_cpu[tsk_index] != -1)
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = preferred_cpu;
cpumask_set_cpu(preferred_cpu, pad_busy_cpus);
cpu_weight[preferred_cpu]++;
mutex_unlock(&round_robin_lock);
set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu));
}
static void exit_round_robin(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = -1;
}
static unsigned int idle_pct = 5; /* percentage */
static unsigned int round_robin_time = 1; /* second */
static int power_saving_thread(void *data)
{
struct sched_param param = {.sched_priority = 1};
int do_sleep;
unsigned int tsk_index = (unsigned long)data;
u64 last_jiffies = 0;
sched_setscheduler(current, SCHED_RR, ¶m);
while (!kthread_should_stop()) {
unsigned long expire_time;
try_to_freeze();
/* round robin to cpus */
expire_time = last_jiffies + round_robin_time * HZ;
if (time_before(expire_time, jiffies)) {
last_jiffies = jiffies;
round_robin_cpu(tsk_index);
}
do_sleep = 0;
expire_time = jiffies + HZ * (100 - idle_pct) / 100;
while (!need_resched()) {
if (tsc_detected_unstable && !tsc_marked_unstable) {
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
local_irq_disable();
tick_broadcast_enable();
tick_broadcast_enter();
stop_critical_timings();
mwait_idle_with_hints(power_saving_mwait_eax, 1);
start_critical_timings();
tick_broadcast_exit();
local_irq_enable();
if (time_before(expire_time, jiffies)) {
do_sleep = 1;
break;
}
}
/*
* current sched_rt has threshold for rt task running time.
* When a rt task uses 95% CPU time, the rt thread will be
* scheduled out for 5% CPU time to not starve other tasks. But
* the mechanism only works when all CPUs have RT task running,
* as if one CPU hasn't RT task, RT task from other CPUs will
* borrow CPU time from this CPU and cause RT task use > 95%
* CPU time. To make 'avoid starvation' work, takes a nap here.
*/
if (unlikely(do_sleep))
schedule_timeout_killable(HZ * idle_pct / 100);
/* If an external event has set the need_resched flag, then
* we need to deal with it, or this loop will continue to
* spin without calling __mwait().
*/
if (unlikely(need_resched()))
schedule();
}
exit_round_robin(tsk_index);
return 0;
}
static struct task_struct *ps_tsks[NR_CPUS];
static unsigned int ps_tsk_num;
static int create_power_saving_task(void)
{
int rc;
ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
(void *)(unsigned long)ps_tsk_num,
"acpi_pad/%d", ps_tsk_num);
if (IS_ERR(ps_tsks[ps_tsk_num])) {
rc = PTR_ERR(ps_tsks[ps_tsk_num]);
ps_tsks[ps_tsk_num] = NULL;
} else {
rc = 0;
ps_tsk_num++;
}
return rc;
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
unsigned int broadcast;
bool reflect;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
if (cpuidle_not_available(drv, dev))
goto use_default;
/*
* Suspend-to-idle ("freeze") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in iterrupts (if any). In that case bypass
* the cpuidle governor and go stratight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
if (idle_should_freeze()) {
entered_state = cpuidle_enter_freeze(drv, dev);
if (entered_state >= 0) {
local_irq_enable();
goto exit_idle;
}
reflect = false;
next_state = cpuidle_find_deepest_state(drv, dev);
} else {
reflect = true;
/*
* Ask the cpuidle framework to choose a convenient idle state.
*/
next_state = cpuidle_select(drv, dev);
}
/* Fall back to the default arch idle method on errors. */
if (next_state < 0)
goto use_default;
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP;
/*
* Tell the time framework to switch to a broadcast timer
* because our local timer will be shutdown. If a local timer
* is used from another cpu as a broadcast timer, this call may
* fail if it is not available
*/
if (broadcast && tick_broadcast_enter())
goto use_default;
/* Take note of the planned idle state. */
idle_set_state(this_rq(), &drv->states[next_state]);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
/* The cpu is no longer idle or about to enter idle. */
idle_set_state(this_rq(), NULL);
if (broadcast)
tick_broadcast_exit();
/*
* Give the governor an opportunity to reflect on the outcome
*/
if (reflect)
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
return;
use_default:
/*
* We can't use the cpuidle framework, let's use the default
* idle routine.
*/
if (current_clr_polling_and_test())
local_irq_enable();
else
arch_cpu_idle();
goto exit_idle;
}
