On Wednesday, June 20, 2018 7:22:07 PM CEST Ulf Hansson wrote:
> As it's now perfectly possible that a PM domain managed by genpd contains
> devices belonging to CPUs, we should start to take into account the
> residency values for the idle states during the state selection process.
> The residency value specifies the minimum duration of time, the CPU or a
> group of CPUs, needs to spend in an idle state to not waste energy entering
> it.
>
> To deal with this, let's add a new genpd governor, pm_domain_cpu_gov, that
> may be used for a PM domain that have CPU devices attached or if the CPUs
> are attached through subdomains.
>
> The new governor computes the minimum expected idle duration time for the
> online CPUs being attached to the PM domain and its subdomains. Then in the
> state selection process, trying the deepest state first, it verifies that
> the idle duration time satisfies the state's residency value.
>
> It should be noted that, when computing the minimum expected idle duration
> time, we use the information from tick_nohz_get_next_wakeup(), to find the
> next wakeup for the related CPUs. Future wise, this may deserve to be
> improved, as there are more reasons to why a CPU may be woken up from idle.
>
> Cc: Thomas Gleixner <[email protected]>
> Cc: Daniel Lezcano <[email protected]>
> Cc: Lina Iyer <[email protected]>
> Cc: Frederic Weisbecker <[email protected]>
> Cc: Ingo Molnar <[email protected]>
> Co-developed-by: Lina Iyer <[email protected]>
> Signed-off-by: Ulf Hansson <[email protected]>
> ---
> drivers/base/power/domain_governor.c | 58 ++++++++++++++++++++++++++++
> include/linux/pm_domain.h | 2 +
> 2 files changed, 60 insertions(+)
>
> diff --git a/drivers/base/power/domain_governor.c
> b/drivers/base/power/domain_governor.c
> index 99896fbf18e4..1aad55719537 100644
> --- a/drivers/base/power/domain_governor.c
> +++ b/drivers/base/power/domain_governor.c
> @@ -10,6 +10,9 @@
> #include <linux/pm_domain.h>
> #include <linux/pm_qos.h>
> #include <linux/hrtimer.h>
> +#include <linux/cpumask.h>
> +#include <linux/ktime.h>
> +#include <linux/tick.h>
>
> static int dev_update_qos_constraint(struct device *dev, void *data)
> {
> @@ -245,6 +248,56 @@ static bool always_on_power_down_ok(struct dev_pm_domain
> *domain)
> return false;
> }
>
> +static bool cpu_power_down_ok(struct dev_pm_domain *pd)
> +{
> + struct generic_pm_domain *genpd = pd_to_genpd(pd);
> + ktime_t domain_wakeup, cpu_wakeup;
> + s64 idle_duration_ns;
> + int cpu, i;
> +
> + if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
> + return true;
> +
> + /*
> + * Find the next wakeup for any of the online CPUs within the PM domain
> + * and its subdomains. Note, we only need the genpd->cpus, as it already
> + * contains a mask of all CPUs from subdomains.
> + */
> + domain_wakeup = ktime_set(KTIME_SEC_MAX, 0);
> + for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) {
> + cpu_wakeup = tick_nohz_get_next_wakeup(cpu);
> + if (ktime_before(cpu_wakeup, domain_wakeup))
> + domain_wakeup = cpu_wakeup;
> + }
> +
> + /* The minimum idle duration is from now - until the next wakeup. */
> + idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get()));
> +
If idle_duration_ns is negative at this point, you can return false right
away and then you won't need to bother with this case below.
> + /*
> + * Find the deepest idle state that has its residency value satisfied
> + * and by also taking into account the power off latency for the state.
> + * Start at the deepest supported state.
> + */
> + i = genpd->state_count - 1;
> + do {
> + if (!genpd->states[i].residency_ns)
> + break;
> +
> + /* Check idle_duration_ns >= 0 to compare signed/unsigned. */
> + if (idle_duration_ns >= 0 && idle_duration_ns >=
> + (genpd->states[i].residency_ns +
> + genpd->states[i].power_off_latency_ns))
Why don't you set state_idx and return true right here?
Then you'll only need to return false if you haven't found a matching state.
> + break;
> + i--;
> + } while (i >= 0);
> +
> + if (i < 0)
> + return false;
> +
> + genpd->state_idx = i;
> + return true;
> +}
> +
> struct dev_power_governor simple_qos_governor = {
> .suspend_ok = default_suspend_ok,
> .power_down_ok = default_power_down_ok,
> @@ -257,3 +310,8 @@ struct dev_power_governor pm_domain_always_on_gov = {
> .power_down_ok = always_on_power_down_ok,
> .suspend_ok = default_suspend_ok,
> };
> +
> +struct dev_power_governor pm_domain_cpu_gov = {
> + .suspend_ok = NULL,
> + .power_down_ok = cpu_power_down_ok,
I see that I haven't got your code flow right after all. :-)
And which means that this should work AFAICS.
> +};
> diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
> index 2c09cf80b285..97901c833108 100644
> --- a/include/linux/pm_domain.h
> +++ b/include/linux/pm_domain.h
> @@ -160,6 +160,7 @@ int dev_pm_genpd_set_performance_state(struct device
> *dev, unsigned int state);
>
> extern struct dev_power_governor simple_qos_governor;
> extern struct dev_power_governor pm_domain_always_on_gov;
> +extern struct dev_power_governor pm_domain_cpu_gov;
> #else
>
> static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
> @@ -203,6 +204,7 @@ static inline int
> dev_pm_genpd_set_performance_state(struct device *dev,
>
> #define simple_qos_governor (*(struct dev_power_governor *)(NULL))
> #define pm_domain_always_on_gov (*(struct dev_power_governor
> *)(NULL))
> +#define pm_domain_cpu_gov (*(struct dev_power_governor *)(NULL))
> #endif
>
> #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
>
