| Message ID | 20201012223400.23609-2-ilina@codeaurora.org |
|---|---|
| State | New |
| Headers | show |
| Series | Better domain idle from device wakeup patterns | expand |
Hi Lina, [...] > >> 5. Runtime PM Initialization, Device Probing and Removal > >> ======================================================== > >> @@ -639,6 +648,18 @@ suspend routine). It may be necessary to resume the device and suspend it again > >> in order to do so. The same is true if the driver uses different power levels > >> or other settings for runtime suspend and system sleep. > >> > >> +When a device enters idle at runtime, it may trigger the runtime PM up the > >> +hierarchy. Devices that have an predictable interrupt pattern, may help > >> +influence a better idle state determination of its parent. For example, a > >> +display device could get a VSYNC interrupt every 16ms. A PM domain containing > >> +the device, could also be entering and exiting idle due to runtime PM > > > >/containing the device/that has the device attached to it > > > >> +coordination. If the domain were also entering runtime idle, we would know when > >> +the domain would be waken up as a result of the display device waking up. Using > >> +the device's next_event, the PM domain governor can make a better choice of the > >> +idle state for the domain, knowing it would be be woken up by the device in the > >> +near future. This is specially useful when the device is sensitive to its PM > >> +domain's idle state enter and exit latencies. > > > >The above sounds a little hand wavy, can you try to be a little more exact? > > > I can try and rephrase this. But what I think I should be saying is that > if the domain has multiple devices and if some devices are sensitive to > the exit latency of the domain idle, then knowing the next wakeup would > help the governor make better domain idle state decision. > > >Perhaps, rather than just saying "sensitive to it's PM domain's idle > >state..", how about explaining that by using the "next event" the > >governor is able to select a more optimal domain idle state, thus we > >should avoid wasting energy and better conform to QoS latency > >constraints. > > > QoS is not what we are trying to conform to. We are trying to provide > residency information to the domain to help it make better choice. Just > like we use the CPU's next wakeup in the cluster domain governor. Yep, that makes perfect sense to me as well. Then, please try to clarify this in the above text. > >> + > >> During system resume, the simplest approach is to bring all devices back to full > >> power, even if they had been suspended before the system suspend began. There > >> are several reasons for this, including: > >> diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c > >> index 8143210a5c54..53c2b3d962bc 100644 > >> --- a/drivers/base/power/runtime.c > >> +++ b/drivers/base/power/runtime.c > >> @@ -122,6 +122,33 @@ u64 pm_runtime_suspended_time(struct device *dev) > >> } > >> EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); > >> > >> +/** > >> + * pm_runtime_set_next_wakeup_event - Notify PM framework of an impending event. > >> + * @dev: Device to handle > >> + * @next: impending interrupt/wakeup for the device > > > >At what typical points do you expect this function to be called? > > > Most likely from at the start of the usecase and periodically when the > interrupt/work is being handled. I would think this change to a > different periodicity when the usecase parameters changes. Alright, thanks for explaining. > > >> + */ > >> +int pm_runtime_set_next_event(struct device *dev, ktime_t next) > >> +{ > >> + unsigned long flags; > >> + int ret = -EINVAL; > >> + > >> + /* > >> + * Note the next pending wakeup of a device, > >> + * if the device does not have runtime PM enabled. > >> + */ > > > >/s/Note/Store > > > >Do you really need to check if runtime PM is enabled? Does it matter? > > > Hmm.. This has no meaning without runtime PM. Any reason why we don't > need the check? I am okay to removing the check. In principle, I want to avoid unnecessary code, thus I am in favor of dropping the check. Not a big deal though. > > >> + spin_lock_irqsave(&dev->power.lock, flags); > >> + if (!dev->power.disable_depth) { > >> + if (ktime_before(ktime_get(), next)) { > >> + dev->power.next_event = next; > >> + ret = 0; > >> + } > >> + } > >> + spin_unlock_irqrestore(&dev->power.lock, flags); > >> + > >> + return ret; > >> +} > >> +EXPORT_SYMBOL_GPL(pm_runtime_set_next_event); [...] Kind regards Uffe
diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 0553008b6279..90a5ac481ad4 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -515,6 +515,14 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: power.use_autosuspend isn't set, otherwise returns the expiration time in jiffies + `int pm_runtime_set_next_event(struct device *dev, ktime_t next);` + - notify runtime PM of the next event on the device. Devices that are + sensitive to their domain idle enter/exit latencies may provide this + information for use by the PM domain governor. The governor may determine + if it worthwhile to enter a domain idle state. If the residency of the + domain idle state is not met, the domain would waste more power entering + and exiting the said idle state. + It is safe to execute the following helper functions from interrupt context: - pm_request_idle() @@ -545,6 +553,7 @@ functions may also be used in interrupt context: - pm_runtime_put_sync() - pm_runtime_put_sync_suspend() - pm_runtime_put_sync_autosuspend() +- pm_runtime_set_next_event() 5. Runtime PM Initialization, Device Probing and Removal ======================================================== @@ -639,6 +648,18 @@ suspend routine). It may be necessary to resume the device and suspend it again in order to do so. The same is true if the driver uses different power levels or other settings for runtime suspend and system sleep. +When a device enters idle at runtime, it may trigger the runtime PM up the +hierarchy. Devices that have an predictable interrupt pattern, may help +influence a better idle state determination of its parent. For example, a +display device could get a VSYNC interrupt every 16ms. A PM domain containing +the device, could also be entering and exiting idle due to runtime PM +coordination. If the domain were also entering runtime idle, we would know when +the domain would be waken up as a result of the display device waking up. Using +the device's next_event, the PM domain governor can make a better choice of the +idle state for the domain, knowing it would be be woken up by the device in the +near future. This is specially useful when the device is sensitive to its PM +domain's idle state enter and exit latencies. + During system resume, the simplest approach is to bring all devices back to full power, even if they had been suspended before the system suspend began. There are several reasons for this, including: diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 8143210a5c54..53c2b3d962bc 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -122,6 +122,33 @@ u64 pm_runtime_suspended_time(struct device *dev) } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); +/** + * pm_runtime_set_next_wakeup_event - Notify PM framework of an impending event. + * @dev: Device to handle + * @next: impending interrupt/wakeup for the device + */ +int pm_runtime_set_next_event(struct device *dev, ktime_t next) +{ + unsigned long flags; + int ret = -EINVAL; + + /* + * Note the next pending wakeup of a device, + * if the device does not have runtime PM enabled. + */ + spin_lock_irqsave(&dev->power.lock, flags); + if (!dev->power.disable_depth) { + if (ktime_before(ktime_get(), next)) { + dev->power.next_event = next; + ret = 0; + } + } + spin_unlock_irqrestore(&dev->power.lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(pm_runtime_set_next_event); + /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. @@ -1380,6 +1407,9 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); + /* Reset the next wakeup for the device */ + dev->power.next_event = KTIME_MAX; + if (!dev->power.disable_depth++) __pm_runtime_barrier(dev); @@ -1609,6 +1639,7 @@ void pm_runtime_init(struct device *dev) dev->power.deferred_resume = false; INIT_WORK(&dev->power.work, pm_runtime_work); + dev->power.next_event = KTIME_MAX; dev->power.timer_expires = 0; hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); dev->power.suspend_timer.function = pm_suspend_timer_fn; diff --git a/include/linux/pm.h b/include/linux/pm.h index a30a4b54df52..9051658674a4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -8,6 +8,7 @@ #ifndef _LINUX_PM_H #define _LINUX_PM_H +#include <linux/ktime.h> #include <linux/list.h> #include <linux/workqueue.h> #include <linux/spinlock.h> @@ -616,6 +617,7 @@ struct dev_pm_info { u64 active_time; u64 suspended_time; u64 accounting_timestamp; + ktime_t next_event; #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ void (*set_latency_tolerance)(struct device *, s32); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 6245caa18034..af6d35178335 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -59,6 +59,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device *dev); +extern int pm_runtime_set_next_event(struct device *dev, ktime_t next); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
Some devices have a predictable interrupt pattern while executing a particular usecase. An example would be the VSYNC interrupt on devices associated with displays. A 60 Hz display could cause a periodic interrupt every 16 ms. A PM domain that holds such a device could power off and on at similar intervals. Entering a domain idle state saves power, only if the domain remains in the idle state for the amount of time greater than or equal to the residency of the idle state. Knowing the next wakeup event of the device will help the PM domain governor make better idle state decisions. Let's add the pm_runtime_set_next_wake() API for the device and document the usage of the API. Signed-off-by: Lina Iyer <ilina@codeaurora.org> --- Documentation/power/runtime_pm.rst | 21 ++++++++++++++++++++ drivers/base/power/runtime.c | 31 ++++++++++++++++++++++++++++++ include/linux/pm.h | 2 ++ include/linux/pm_runtime.h | 1 + 4 files changed, 55 insertions(+)