From 53823639173cc9e9a261f68f4abefe62364b86c6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 23 Jan 2010 22:02:51 +0100 Subject: PM / Runtime: Add sysfs switch for disabling device run-time PM Add new device sysfs attribute, power/control, allowing the user space to block the run-time power management of the devices. If this attribute is set to "on", the driver of the device won't be able to power manage it at run time (without breaking the rules) and the device will always be in the full power state (except when the entire system goes into a sleep state). Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern --- include/linux/pm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index 198b8f9fe05e..25b1eca8049d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -430,6 +430,7 @@ struct dev_pm_info { unsigned int request_pending:1; unsigned int deferred_resume:1; unsigned int run_wake:1; + unsigned int runtime_auto:1; enum rpm_request request; enum rpm_status runtime_status; int runtime_error; -- cgit v1.2.2 From 5af84b82701a96be4b033aaa51d86c72e2ded061 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 23 Jan 2010 22:23:32 +0100 Subject: PM: Asynchronous suspend and resume of devices Theoretically, the total time of system sleep transitions (suspend to RAM, hibernation) can be reduced by running suspend and resume callbacks of device drivers in parallel with each other. However, there are dependencies between devices such that we're not allowed to suspend the parent of a device before suspending the device itself. Analogously, we're not allowed to resume a device before resuming its parent. The most straightforward way to take these dependencies into accout is to start the async threads used for suspending and resuming devices at the core level, so that async_schedule() is called for each suspend and resume callback supposed to be executed asynchronously. For this purpose, introduce a new device flag, power.async_suspend, used to mark the devices whose suspend and resume callbacks are to be executed asynchronously (ie. in parallel with the main suspend/resume thread and possibly in parallel with each other) and helper function device_enable_async_suspend() allowing one to set power.async_suspend for given device (power.async_suspend is unset by default for all devices). For each device with the power.async_suspend flag set the PM core will use async_schedule() to execute its suspend and resume callbacks. The async threads started for different devices as a result of calling async_schedule() are synchronized with each other and with the main suspend/resume thread with the help of completions, in the following way: (1) There is a completion, power.completion, for each device object. (2) Each device's completion is reset before calling async_schedule() for the device or, in the case of devices with the power.async_suspend flags unset, before executing the device's suspend and resume callbacks. (3) During suspend, right before running the bus type, device type and device class suspend callbacks for the device, the PM core waits for the completions of all the device's children to be completed. (4) During resume, right before running the bus type, device type and device class resume callbacks for the device, the PM core waits for the completion of the device's parent to be completed. (5) The PM core completes power.completion for each device right after the bus type, device type and device class suspend (or resume) callbacks executed for the device have returned. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index 25b1eca8049d..9c16cd20fc96 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -26,6 +26,7 @@ #include #include #include +#include /* * Callbacks for platform drivers to implement. @@ -412,9 +413,11 @@ struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; unsigned int should_wakeup:1; + unsigned async_suspend:1; enum dpm_state status; /* Owned by the PM core */ #ifdef CONFIG_PM_SLEEP struct list_head entry; + struct completion completion; #endif #ifdef CONFIG_PM_RUNTIME struct timer_list suspend_timer; -- cgit v1.2.2 From f8824cee405c62ba465b85365201166d9cf86a14 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 27 Jan 2010 23:47:38 +0100 Subject: PM: Allow device drivers to use dpm_wait() There are some dependencies between devices (in particular, between EHCI USB controllers and their OHCI/UHCI siblings) which are not reflected by the structure of the device tree. With synchronous suspend and resume these dependencies are taken into accout automatically, because the devices in question are always registered in the right order, but to meet these constraints with asynchronous suspend and resume the drivers of these devices will need to use dpm_wait() in their suspend/resume routines, so introduce a helper function allowing them to do that. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index 9c16cd20fc96..e80df06ad22a 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -512,6 +512,7 @@ extern void __suspend_report_result(const char *function, void *fn, int ret); __suspend_report_result(__func__, fn, ret); \ } while (0) +extern void device_pm_wait_for_dev(struct device *sub, struct device *dev); #else /* !CONFIG_PM_SLEEP */ #define device_pm_lock() do {} while (0) @@ -524,6 +525,7 @@ static inline int dpm_suspend_start(pm_message_t state) #define suspend_report_result(fn, ret) do {} while (0) +static inline void device_pm_wait_for_dev(struct device *a, struct device *b) {} #endif /* !CONFIG_PM_SLEEP */ /* How to reorder dpm_list after device_move() */ -- cgit v1.2.2 From d690b2cd222afc75320b9b8e9da7df02e9e630ca Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 6 Mar 2010 21:28:37 +0100 Subject: PM: Provide generic subsystem-level callbacks There are subsystems whose power management callbacks only need to invoke the callbacks provided by device drivers. Still, their system sleep PM callbacks should play well with the runtime PM callbacks, so that devices suspended at run time can be left in that state for a system sleep transition. Provide a set of generic PM callbacks for such subsystems and define convenience macros for populating dev_pm_ops structures. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 51 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 6 deletions(-) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index e80df06ad22a..8e258c727971 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -215,20 +215,59 @@ struct dev_pm_ops { int (*runtime_idle)(struct device *dev); }; +#ifdef CONFIG_PM_SLEEP +#define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend = suspend_fn, \ + .resume = resume_fn, \ + .freeze = suspend_fn, \ + .thaw = resume_fn, \ + .poweroff = suspend_fn, \ + .restore = resume_fn, +#else +#define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) +#endif + +#ifdef CONFIG_PM_RUNTIME +#define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + .runtime_suspend = suspend_fn, \ + .runtime_resume = resume_fn, \ + .runtime_idle = idle_fn, +#else +#define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) +#endif + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ const struct dev_pm_ops name = { \ - .suspend = suspend_fn, \ - .resume = resume_fn, \ - .freeze = suspend_fn, \ - .thaw = resume_fn, \ - .poweroff = suspend_fn, \ - .restore = resume_fn, \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +} + +/* + * Use this for defining a set of PM operations to be used in all situations + * (sustem suspend, hibernation or runtime PM). + */ +#define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ +const struct dev_pm_ops name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } +/* + * Use this for subsystems (bus types, device types, device classes) that don't + * need any special suspend/resume handling in addition to invoking the PM + * callbacks provided by device drivers supporting both the system sleep PM and + * runtime PM, make the pm member point to generic_subsys_pm_ops. + */ +#ifdef CONFIG_PM_OPS +extern struct dev_pm_ops generic_subsys_pm_ops; +#define GENERIC_SUBSYS_PM_OPS (&generic_subsys_pm_ops) +#else +#define GENERIC_SUBSYS_PM_OPS NULL +#endif + /** * PM_EVENT_ messages * -- cgit v1.2.2 From c125e96f044427f38d106fab7bc5e4a5e6a18262 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 5 Jul 2010 22:43:53 +0200 Subject: PM: Make it possible to avoid races between wakeup and system sleep One of the arguments during the suspend blockers discussion was that the mainline kernel didn't contain any mechanisms making it possible to avoid races between wakeup and system suspend. Generally, there are two problems in that area. First, if a wakeup event occurs exactly when /sys/power/state is being written to, it may be delivered to user space right before the freezer kicks in, so the user space consumer of the event may not be able to process it before the system is suspended. Second, if a wakeup event occurs after user space has been frozen, it is not generally guaranteed that the ongoing transition of the system into a sleep state will be aborted. To address these issues introduce a new global sysfs attribute, /sys/power/wakeup_count, associated with a running counter of wakeup events and three helper functions, pm_stay_awake(), pm_relax(), and pm_wakeup_event(), that may be used by kernel subsystems to control the behavior of this attribute and to request the PM core to abort system transitions into a sleep state already in progress. The /sys/power/wakeup_count file may be read from or written to by user space. Reads will always succeed (unless interrupted by a signal) and return the current value of the wakeup events counter. Writes, however, will only succeed if the written number is equal to the current value of the wakeup events counter. If a write is successful, it will cause the kernel to save the current value of the wakeup events counter and to abort the subsequent system transition into a sleep state if any wakeup events are reported after the write has returned. [The assumption is that before writing to /sys/power/state user space will first read from /sys/power/wakeup_count. Next, user space consumers of wakeup events will have a chance to acknowledge or veto the upcoming system transition to a sleep state. Finally, if the transition is allowed to proceed, /sys/power/wakeup_count will be written to and if that succeeds, /sys/power/state will be written to as well. Still, if any wakeup events are reported to the PM core by kernel subsystems after that point, the transition will be aborted.] Additionally, put a wakeup events counter into struct dev_pm_info and make these per-device wakeup event counters available via sysfs, so that it's possible to check the activity of various wakeup event sources within the kernel. To illustrate how subsystems can use pm_wakeup_event(), make the low-level PCI runtime PM wakeup-handling code use it. Signed-off-by: Rafael J. Wysocki Acked-by: Jesse Barnes Acked-by: Greg Kroah-Hartman Acked-by: markgross Reviewed-by: Alan Stern --- include/linux/pm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8e258c727971..b417fc46f3fc 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -457,6 +457,7 @@ struct dev_pm_info { #ifdef CONFIG_PM_SLEEP struct list_head entry; struct completion completion; + unsigned long wakeup_count; #endif #ifdef CONFIG_PM_RUNTIME struct timer_list suspend_timer; @@ -552,6 +553,11 @@ extern void __suspend_report_result(const char *function, void *fn, int ret); } while (0) extern void device_pm_wait_for_dev(struct device *sub, struct device *dev); + +/* drivers/base/power/wakeup.c */ +extern void pm_wakeup_event(struct device *dev, unsigned int msec); +extern void pm_stay_awake(struct device *dev); +extern void pm_relax(void); #else /* !CONFIG_PM_SLEEP */ #define device_pm_lock() do {} while (0) @@ -565,6 +571,10 @@ static inline int dpm_suspend_start(pm_message_t state) #define suspend_report_result(fn, ret) do {} while (0) static inline void device_pm_wait_for_dev(struct device *a, struct device *b) {} + +static inline void pm_wakeup_event(struct device *dev, unsigned int msec) {} +static inline void pm_stay_awake(struct device *dev) {} +static inline void pm_relax(void) {} #endif /* !CONFIG_PM_SLEEP */ /* How to reorder dpm_list after device_move() */ -- cgit v1.2.2 From 8d4b9d1bfef117862a2889dec4dac227068544c9 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 19 Jul 2010 02:01:06 +0200 Subject: PM / Runtime: Add runtime PM statistics (v3) In order for PowerTOP to be able to report how well the new runtime PM is working for the various drivers, the kernel needs to export some basic statistics in sysfs. This patch adds two sysfs files in the runtime PM domain that expose the total time a device has been active, and the time a device has been suspended. With this PowerTOP can compute the activity percentage Active %age = 100 * (delta active) / (delta active + delta suspended) and present the information to the user. I've written the PowerTOP code (slated for version 1.12) already, and the output looks like this: Runtime Device Power Management statistics Active Device name 10.0% 06:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8101E/RTL8102E PCI Express Fast Ethernet controller [version 2: fix stat update bugs noticed by Alan Stern] [version 3: rebase to -next and move the sysfs declaration] Signed-off-by: Arjan van de Ven Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/pm.h') diff --git a/include/linux/pm.h b/include/linux/pm.h index b417fc46f3fc..52e8c55ff314 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -477,9 +477,15 @@ struct dev_pm_info { enum rpm_request request; enum rpm_status runtime_status; int runtime_error; + unsigned long active_jiffies; + unsigned long suspended_jiffies; + unsigned long accounting_timestamp; #endif }; +extern void update_pm_runtime_accounting(struct device *dev); + + /* * The PM_EVENT_ messages are also used by drivers implementing the legacy * suspend framework, based on the ->suspend() and ->resume() callbacks common -- cgit v1.2.2