1
0
Fork 0
alistair23-linux/drivers/base/power/wakeup.c

1185 lines
31 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/*
* drivers/base/power/wakeup.c - System wakeup events framework
*
* Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
*/
#define pr_fmt(fmt) "PM: " fmt
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
#include <linux/capability.h>
#include <linux/export.h>
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
#include <linux/suspend.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pm_wakeirq.h>
#include <trace/events/power.h>
#include "power.h"
#ifndef CONFIG_SUSPEND
suspend_state_t pm_suspend_target_state;
#define pm_suspend_target_state (PM_SUSPEND_ON)
#endif
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/*
* If set, the suspend/hibernate code will abort transitions to a sleep state
* if wakeup events are registered during or immediately before the transition.
*/
bool events_check_enabled __read_mostly;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/* First wakeup IRQ seen by the kernel in the last cycle. */
unsigned int pm_wakeup_irq __read_mostly;
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
/* If greater than 0 and the system is suspending, terminate the suspend. */
static atomic_t pm_abort_suspend __read_mostly;
/*
* Combined counters of registered wakeup events and wakeup events in progress.
* They need to be modified together atomically, so it's better to use one
* atomic variable to hold them both.
*/
static atomic_t combined_event_count = ATOMIC_INIT(0);
#define IN_PROGRESS_BITS (sizeof(int) * 4)
#define MAX_IN_PROGRESS ((1 << IN_PROGRESS_BITS) - 1)
static void split_counters(unsigned int *cnt, unsigned int *inpr)
{
unsigned int comb = atomic_read(&combined_event_count);
*cnt = (comb >> IN_PROGRESS_BITS);
*inpr = comb & MAX_IN_PROGRESS;
}
/* A preserved old value of the events counter. */
static unsigned int saved_count;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
static DEFINE_RAW_SPINLOCK(events_lock);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
static void pm_wakeup_timer_fn(struct timer_list *t);
static LIST_HEAD(wakeup_sources);
static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
DEFINE_STATIC_SRCU(wakeup_srcu);
static struct wakeup_source deleted_ws = {
.name = "deleted",
.lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
};
static DEFINE_IDA(wakeup_ida);
/**
* wakeup_source_create - Create a struct wakeup_source object.
* @name: Name of the new wakeup source.
*/
struct wakeup_source *wakeup_source_create(const char *name)
{
struct wakeup_source *ws;
const char *ws_name;
int id;
ws = kzalloc(sizeof(*ws), GFP_KERNEL);
if (!ws)
goto err_ws;
ws_name = kstrdup_const(name, GFP_KERNEL);
if (!ws_name)
goto err_name;
ws->name = ws_name;
id = ida_alloc(&wakeup_ida, GFP_KERNEL);
if (id < 0)
goto err_id;
ws->id = id;
return ws;
err_id:
kfree_const(ws->name);
err_name:
kfree(ws);
err_ws:
return NULL;
}
EXPORT_SYMBOL_GPL(wakeup_source_create);
/*
* Record wakeup_source statistics being deleted into a dummy wakeup_source.
*/
static void wakeup_source_record(struct wakeup_source *ws)
{
unsigned long flags;
spin_lock_irqsave(&deleted_ws.lock, flags);
if (ws->event_count) {
deleted_ws.total_time =
ktime_add(deleted_ws.total_time, ws->total_time);
deleted_ws.prevent_sleep_time =
ktime_add(deleted_ws.prevent_sleep_time,
ws->prevent_sleep_time);
deleted_ws.max_time =
ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ?
deleted_ws.max_time : ws->max_time;
deleted_ws.event_count += ws->event_count;
deleted_ws.active_count += ws->active_count;
deleted_ws.relax_count += ws->relax_count;
deleted_ws.expire_count += ws->expire_count;
deleted_ws.wakeup_count += ws->wakeup_count;
}
spin_unlock_irqrestore(&deleted_ws.lock, flags);
}
PM / wakeup: Fix sysfs registration error path We shouldn't call wakeup_source_destroy() from the error path in wakeup_source_register() because that calls __pm_relax() which takes a lock that isn't initialized until wakeup_source_add() is called. Add a new function, wakeup_source_free(), that just does the bare minimum to free a wakeup source that was created but hasn't been added yet and use it from the two places it's needed. This fixes the following problem seen on various x86 server boxes: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 12 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc4- Hardware name: HP ProLiant XL420 Gen9/ProLiant XL420 Gen9, BIOS U19 12/27/2015 Call Trace:   dump_stack+0x62/0x9a   register_lock_class+0x95a/0x960   ? __platform_driver_probe+0xcd/0x230   ? __platform_create_bundle+0xc0/0xe0   ? i8042_init+0x4ec/0x578   ? do_one_initcall+0xfe/0x45a   ? kernel_init_freeable+0x614/0x6a7   ? kernel_init+0x11/0x138   ? ret_from_fork+0x35/0x40   ? is_dynamic_key+0xf0/0xf0   ? rwlock_bug.part.0+0x60/0x60   ? __debug_check_no_obj_freed+0x8e/0x250   __lock_acquire.isra.13+0x5f/0x830   ? __debug_check_no_obj_freed+0x152/0x250   lock_acquire+0x107/0x220   ? __pm_relax.part.2+0x21/0xa0   _raw_spin_lock_irqsave+0x35/0x50   ? __pm_relax.part.2+0x21/0xa0   __pm_relax.part.2+0x21/0xa0   wakeup_source_destroy.part.3+0x18/0x190   wakeup_source_register+0x43/0x50 Fixes: c8377adfa781 ("PM / wakeup: Show wakeup sources stats in sysfs") Reported-by: Qian Cai <cai@lca.pw> Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-08-13 18:40:53 -06:00
static void wakeup_source_free(struct wakeup_source *ws)
{
ida_free(&wakeup_ida, ws->id);
kfree_const(ws->name);
kfree(ws);
}
/**
* wakeup_source_destroy - Destroy a struct wakeup_source object.
* @ws: Wakeup source to destroy.
*
* Use only for wakeup source objects created with wakeup_source_create().
*/
void wakeup_source_destroy(struct wakeup_source *ws)
{
if (!ws)
return;
__pm_relax(ws);
wakeup_source_record(ws);
PM / wakeup: Fix sysfs registration error path We shouldn't call wakeup_source_destroy() from the error path in wakeup_source_register() because that calls __pm_relax() which takes a lock that isn't initialized until wakeup_source_add() is called. Add a new function, wakeup_source_free(), that just does the bare minimum to free a wakeup source that was created but hasn't been added yet and use it from the two places it's needed. This fixes the following problem seen on various x86 server boxes: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 12 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc4- Hardware name: HP ProLiant XL420 Gen9/ProLiant XL420 Gen9, BIOS U19 12/27/2015 Call Trace:   dump_stack+0x62/0x9a   register_lock_class+0x95a/0x960   ? __platform_driver_probe+0xcd/0x230   ? __platform_create_bundle+0xc0/0xe0   ? i8042_init+0x4ec/0x578   ? do_one_initcall+0xfe/0x45a   ? kernel_init_freeable+0x614/0x6a7   ? kernel_init+0x11/0x138   ? ret_from_fork+0x35/0x40   ? is_dynamic_key+0xf0/0xf0   ? rwlock_bug.part.0+0x60/0x60   ? __debug_check_no_obj_freed+0x8e/0x250   __lock_acquire.isra.13+0x5f/0x830   ? __debug_check_no_obj_freed+0x152/0x250   lock_acquire+0x107/0x220   ? __pm_relax.part.2+0x21/0xa0   _raw_spin_lock_irqsave+0x35/0x50   ? __pm_relax.part.2+0x21/0xa0   __pm_relax.part.2+0x21/0xa0   wakeup_source_destroy.part.3+0x18/0x190   wakeup_source_register+0x43/0x50 Fixes: c8377adfa781 ("PM / wakeup: Show wakeup sources stats in sysfs") Reported-by: Qian Cai <cai@lca.pw> Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-08-13 18:40:53 -06:00
wakeup_source_free(ws);
}
EXPORT_SYMBOL_GPL(wakeup_source_destroy);
/**
* wakeup_source_add - Add given object to the list of wakeup sources.
* @ws: Wakeup source object to add to the list.
*/
void wakeup_source_add(struct wakeup_source *ws)
{
unsigned long flags;
if (WARN_ON(!ws))
return;
spin_lock_init(&ws->lock);
timer_setup(&ws->timer, pm_wakeup_timer_fn, 0);
ws->active = false;
raw_spin_lock_irqsave(&events_lock, flags);
list_add_rcu(&ws->entry, &wakeup_sources);
raw_spin_unlock_irqrestore(&events_lock, flags);
}
EXPORT_SYMBOL_GPL(wakeup_source_add);
/**
* wakeup_source_remove - Remove given object from the wakeup sources list.
* @ws: Wakeup source object to remove from the list.
*/
void wakeup_source_remove(struct wakeup_source *ws)
{
unsigned long flags;
if (WARN_ON(!ws))
return;
raw_spin_lock_irqsave(&events_lock, flags);
list_del_rcu(&ws->entry);
raw_spin_unlock_irqrestore(&events_lock, flags);
synchronize_srcu(&wakeup_srcu);
del_timer_sync(&ws->timer);
/*
* Clear timer.function to make wakeup_source_not_registered() treat
* this wakeup source as not registered.
*/
ws->timer.function = NULL;
}
EXPORT_SYMBOL_GPL(wakeup_source_remove);
/**
* wakeup_source_register - Create wakeup source and add it to the list.
* @dev: Device this wakeup source is associated with (or NULL if virtual).
* @name: Name of the wakeup source to register.
*/
struct wakeup_source *wakeup_source_register(struct device *dev,
const char *name)
{
struct wakeup_source *ws;
int ret;
ws = wakeup_source_create(name);
if (ws) {
if (!dev || device_is_registered(dev)) {
ret = wakeup_source_sysfs_add(dev, ws);
if (ret) {
wakeup_source_free(ws);
return NULL;
}
}
wakeup_source_add(ws);
}
return ws;
}
EXPORT_SYMBOL_GPL(wakeup_source_register);
/**
* wakeup_source_unregister - Remove wakeup source from the list and remove it.
* @ws: Wakeup source object to unregister.
*/
void wakeup_source_unregister(struct wakeup_source *ws)
{
if (ws) {
wakeup_source_remove(ws);
if (ws->dev)
wakeup_source_sysfs_remove(ws);
wakeup_source_destroy(ws);
}
}
EXPORT_SYMBOL_GPL(wakeup_source_unregister);
/**
* wakeup_sources_read_lock - Lock wakeup source list for read.
*
* Returns an index of srcu lock for struct wakeup_srcu.
* This index must be passed to the matching wakeup_sources_read_unlock().
*/
int wakeup_sources_read_lock(void)
{
return srcu_read_lock(&wakeup_srcu);
}
EXPORT_SYMBOL_GPL(wakeup_sources_read_lock);
/**
* wakeup_sources_read_unlock - Unlock wakeup source list.
* @idx: return value from corresponding wakeup_sources_read_lock()
*/
void wakeup_sources_read_unlock(int idx)
{
srcu_read_unlock(&wakeup_srcu, idx);
}
EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock);
/**
* wakeup_sources_walk_start - Begin a walk on wakeup source list
*
* Returns first object of the list of wakeup sources.
*
* Note that to be safe, wakeup sources list needs to be locked by calling
* wakeup_source_read_lock() for this.
*/
struct wakeup_source *wakeup_sources_walk_start(void)
{
struct list_head *ws_head = &wakeup_sources;
return list_entry_rcu(ws_head->next, struct wakeup_source, entry);
}
EXPORT_SYMBOL_GPL(wakeup_sources_walk_start);
/**
* wakeup_sources_walk_next - Get next wakeup source from the list
* @ws: Previous wakeup source object
*
* Note that to be safe, wakeup sources list needs to be locked by calling
* wakeup_source_read_lock() for this.
*/
struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws)
{
struct list_head *ws_head = &wakeup_sources;
return list_next_or_null_rcu(ws_head, &ws->entry,
struct wakeup_source, entry);
}
EXPORT_SYMBOL_GPL(wakeup_sources_walk_next);
/**
* device_wakeup_attach - Attach a wakeup source object to a device object.
* @dev: Device to handle.
* @ws: Wakeup source object to attach to @dev.
*
* This causes @dev to be treated as a wakeup device.
*/
static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
{
spin_lock_irq(&dev->power.lock);
if (dev->power.wakeup) {
spin_unlock_irq(&dev->power.lock);
return -EEXIST;
}
dev->power.wakeup = ws;
if (dev->power.wakeirq)
device_wakeup_attach_irq(dev, dev->power.wakeirq);
spin_unlock_irq(&dev->power.lock);
return 0;
}
/**
* device_wakeup_enable - Enable given device to be a wakeup source.
* @dev: Device to handle.
*
* Create a wakeup source object, register it and attach it to @dev.
*/
int device_wakeup_enable(struct device *dev)
{
struct wakeup_source *ws;
int ret;
if (!dev || !dev->power.can_wakeup)
return -EINVAL;
if (pm_suspend_target_state != PM_SUSPEND_ON)
dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__);
ws = wakeup_source_register(dev, dev_name(dev));
if (!ws)
return -ENOMEM;
ret = device_wakeup_attach(dev, ws);
if (ret)
wakeup_source_unregister(ws);
return ret;
}
EXPORT_SYMBOL_GPL(device_wakeup_enable);
/**
* device_wakeup_attach_irq - Attach a wakeirq to a wakeup source
* @dev: Device to handle
* @wakeirq: Device specific wakeirq entry
*
* Attach a device wakeirq to the wakeup source so the device
* wake IRQ can be configured automatically for suspend and
* resume.
*
* Call under the device's power.lock lock.
*/
void device_wakeup_attach_irq(struct device *dev,
struct wake_irq *wakeirq)
{
struct wakeup_source *ws;
ws = dev->power.wakeup;
if (!ws)
return;
if (ws->wakeirq)
dev_err(dev, "Leftover wakeup IRQ found, overriding\n");
ws->wakeirq = wakeirq;
}
/**
* device_wakeup_detach_irq - Detach a wakeirq from a wakeup source
* @dev: Device to handle
*
* Removes a device wakeirq from the wakeup source.
*
* Call under the device's power.lock lock.
*/
void device_wakeup_detach_irq(struct device *dev)
{
struct wakeup_source *ws;
ws = dev->power.wakeup;
if (ws)
ws->wakeirq = NULL;
}
/**
* device_wakeup_arm_wake_irqs(void)
*
* Itereates over the list of device wakeirqs to arm them.
*/
void device_wakeup_arm_wake_irqs(void)
{
struct wakeup_source *ws;
int srcuidx;
srcuidx = srcu_read_lock(&wakeup_srcu);
list_for_each_entry_rcu(ws, &wakeup_sources, entry)
dev_pm_arm_wake_irq(ws->wakeirq);
srcu_read_unlock(&wakeup_srcu, srcuidx);
}
/**
* device_wakeup_disarm_wake_irqs(void)
*
* Itereates over the list of device wakeirqs to disarm them.
*/
void device_wakeup_disarm_wake_irqs(void)
{
struct wakeup_source *ws;
int srcuidx;
srcuidx = srcu_read_lock(&wakeup_srcu);
list_for_each_entry_rcu(ws, &wakeup_sources, entry)
dev_pm_disarm_wake_irq(ws->wakeirq);
srcu_read_unlock(&wakeup_srcu, srcuidx);
}
/**
* device_wakeup_detach - Detach a device's wakeup source object from it.
* @dev: Device to detach the wakeup source object from.
*
* After it returns, @dev will not be treated as a wakeup device any more.
*/
static struct wakeup_source *device_wakeup_detach(struct device *dev)
{
struct wakeup_source *ws;
spin_lock_irq(&dev->power.lock);
ws = dev->power.wakeup;
dev->power.wakeup = NULL;
spin_unlock_irq(&dev->power.lock);
return ws;
}
/**
* device_wakeup_disable - Do not regard a device as a wakeup source any more.
* @dev: Device to handle.
*
* Detach the @dev's wakeup source object from it, unregister this wakeup source
* object and destroy it.
*/
int device_wakeup_disable(struct device *dev)
{
struct wakeup_source *ws;
if (!dev || !dev->power.can_wakeup)
return -EINVAL;
ws = device_wakeup_detach(dev);
wakeup_source_unregister(ws);
return 0;
}
EXPORT_SYMBOL_GPL(device_wakeup_disable);
/**
* device_set_wakeup_capable - Set/reset device wakeup capability flag.
* @dev: Device to handle.
* @capable: Whether or not @dev is capable of waking up the system from sleep.
*
* If @capable is set, set the @dev's power.can_wakeup flag and add its
* wakeup-related attributes to sysfs. Otherwise, unset the @dev's
* power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
*
* This function may sleep and it can't be called from any context where
* sleeping is not allowed.
*/
void device_set_wakeup_capable(struct device *dev, bool capable)
{
if (!!dev->power.can_wakeup == !!capable)
return;
dev->power.can_wakeup = capable;
if (device_is_registered(dev) && !list_empty(&dev->power.entry)) {
if (capable) {
int ret = wakeup_sysfs_add(dev);
if (ret)
dev_info(dev, "Wakeup sysfs attributes not added\n");
} else {
wakeup_sysfs_remove(dev);
}
}
}
EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
/**
* device_init_wakeup - Device wakeup initialization.
* @dev: Device to handle.
* @enable: Whether or not to enable @dev as a wakeup device.
*
* By default, most devices should leave wakeup disabled. The exceptions are
* devices that everyone expects to be wakeup sources: keyboards, power buttons,
* possibly network interfaces, etc. Also, devices that don't generate their
* own wakeup requests but merely forward requests from one bus to another
* (like PCI bridges) should have wakeup enabled by default.
*/
int device_init_wakeup(struct device *dev, bool enable)
{
int ret = 0;
if (!dev)
return -EINVAL;
if (enable) {
device_set_wakeup_capable(dev, true);
ret = device_wakeup_enable(dev);
} else {
device_wakeup_disable(dev);
device_set_wakeup_capable(dev, false);
}
return ret;
}
EXPORT_SYMBOL_GPL(device_init_wakeup);
/**
* device_set_wakeup_enable - Enable or disable a device to wake up the system.
* @dev: Device to handle.
*/
int device_set_wakeup_enable(struct device *dev, bool enable)
{
return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
}
EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
/**
* wakeup_source_not_registered - validate the given wakeup source.
* @ws: Wakeup source to be validated.
*/
static bool wakeup_source_not_registered(struct wakeup_source *ws)
{
/*
* Use timer struct to check if the given source is initialized
* by wakeup_source_add.
*/
return ws->timer.function != pm_wakeup_timer_fn;
}
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/*
* The functions below use the observation that each wakeup event starts a
* period in which the system should not be suspended. The moment this period
* will end depends on how the wakeup event is going to be processed after being
* detected and all of the possible cases can be divided into two distinct
* groups.
*
* First, a wakeup event may be detected by the same functional unit that will
* carry out the entire processing of it and possibly will pass it to user space
* for further processing. In that case the functional unit that has detected
* the event may later "close" the "no suspend" period associated with it
* directly as soon as it has been dealt with. The pair of pm_stay_awake() and
* pm_relax(), balanced with each other, is supposed to be used in such
* situations.
*
* Second, a wakeup event may be detected by one functional unit and processed
* by another one. In that case the unit that has detected it cannot really
* "close" the "no suspend" period associated with it, unless it knows in
* advance what's going to happen to the event during processing. This
* knowledge, however, may not be available to it, so it can simply specify time
* to wait before the system can be suspended and pass it as the second
* argument of pm_wakeup_event().
*
* It is valid to call pm_relax() after pm_wakeup_event(), in which case the
* "no suspend" period will be ended either by the pm_relax(), or by the timer
* function executed when the timer expires, whichever comes first.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
/**
* wakup_source_activate - Mark given wakeup source as active.
* @ws: Wakeup source to handle.
*
* Update the @ws' statistics and, if @ws has just been activated, notify the PM
* core of the event by incrementing the counter of of wakeup events being
* processed.
*/
static void wakeup_source_activate(struct wakeup_source *ws)
{
unsigned int cec;
if (WARN_ONCE(wakeup_source_not_registered(ws),
"unregistered wakeup source\n"))
return;
ws->active = true;
ws->active_count++;
ws->last_time = ktime_get();
if (ws->autosleep_enabled)
ws->start_prevent_time = ws->last_time;
/* Increment the counter of events in progress. */
cec = atomic_inc_return(&combined_event_count);
trace_wakeup_source_activate(ws->name, cec);
}
/**
* wakeup_source_report_event - Report wakeup event using the given source.
* @ws: Wakeup source to report the event for.
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
* @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*/
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
static void wakeup_source_report_event(struct wakeup_source *ws, bool hard)
{
ws->event_count++;
/* This is racy, but the counter is approximate anyway. */
if (events_check_enabled)
ws->wakeup_count++;
if (!ws->active)
wakeup_source_activate(ws);
if (hard)
pm_system_wakeup();
}
/**
* __pm_stay_awake - Notify the PM core of a wakeup event.
* @ws: Wakeup source object associated with the source of the event.
*
* It is safe to call this function from interrupt context.
*/
void __pm_stay_awake(struct wakeup_source *ws)
{
unsigned long flags;
if (!ws)
return;
spin_lock_irqsave(&ws->lock, flags);
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
wakeup_source_report_event(ws, false);
del_timer(&ws->timer);
ws->timer_expires = 0;
spin_unlock_irqrestore(&ws->lock, flags);
}
EXPORT_SYMBOL_GPL(__pm_stay_awake);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/**
* pm_stay_awake - Notify the PM core that a wakeup event is being processed.
* @dev: Device the wakeup event is related to.
*
* Notify the PM core of a wakeup event (signaled by @dev) by calling
* __pm_stay_awake for the @dev's wakeup source object.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Call this function after detecting of a wakeup event if pm_relax() is going
* to be called directly after processing the event (and possibly passing it to
* user space for further processing).
*/
void pm_stay_awake(struct device *dev)
{
unsigned long flags;
if (!dev)
return;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
spin_lock_irqsave(&dev->power.lock, flags);
__pm_stay_awake(dev->power.wakeup);
spin_unlock_irqrestore(&dev->power.lock, flags);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
EXPORT_SYMBOL_GPL(pm_stay_awake);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
#ifdef CONFIG_PM_AUTOSLEEP
static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now)
{
ktime_t delta = ktime_sub(now, ws->start_prevent_time);
ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta);
}
#else
static inline void update_prevent_sleep_time(struct wakeup_source *ws,
ktime_t now) {}
#endif
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/**
* wakup_source_deactivate - Mark given wakeup source as inactive.
* @ws: Wakeup source to handle.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Update the @ws' statistics and notify the PM core that the wakeup source has
* become inactive by decrementing the counter of wakeup events being processed
* and incrementing the counter of registered wakeup events.
*/
static void wakeup_source_deactivate(struct wakeup_source *ws)
{
unsigned int cnt, inpr, cec;
ktime_t duration;
ktime_t now;
ws->relax_count++;
/*
* __pm_relax() may be called directly or from a timer function.
* If it is called directly right after the timer function has been
* started, but before the timer function calls __pm_relax(), it is
* possible that __pm_stay_awake() will be called in the meantime and
* will set ws->active. Then, ws->active may be cleared immediately
* by the __pm_relax() called from the timer function, but in such a
* case ws->relax_count will be different from ws->active_count.
*/
if (ws->relax_count != ws->active_count) {
ws->relax_count--;
return;
}
ws->active = false;
now = ktime_get();
duration = ktime_sub(now, ws->last_time);
ws->total_time = ktime_add(ws->total_time, duration);
if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
ws->max_time = duration;
ws->last_time = now;
del_timer(&ws->timer);
ws->timer_expires = 0;
if (ws->autosleep_enabled)
update_prevent_sleep_time(ws, now);
/*
* Increment the counter of registered wakeup events and decrement the
* couter of wakeup events in progress simultaneously.
*/
cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
trace_wakeup_source_deactivate(ws->name, cec);
split_counters(&cnt, &inpr);
if (!inpr && waitqueue_active(&wakeup_count_wait_queue))
wake_up(&wakeup_count_wait_queue);
}
/**
* __pm_relax - Notify the PM core that processing of a wakeup event has ended.
* @ws: Wakeup source object associated with the source of the event.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Call this function for wakeup events whose processing started with calling
* __pm_stay_awake().
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* It is safe to call it from interrupt context.
*/
void __pm_relax(struct wakeup_source *ws)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned long flags;
if (!ws)
return;
spin_lock_irqsave(&ws->lock, flags);
if (ws->active)
wakeup_source_deactivate(ws);
spin_unlock_irqrestore(&ws->lock, flags);
}
EXPORT_SYMBOL_GPL(__pm_relax);
/**
* pm_relax - Notify the PM core that processing of a wakeup event has ended.
* @dev: Device that signaled the event.
*
* Execute __pm_relax() for the @dev's wakeup source object.
*/
void pm_relax(struct device *dev)
{
unsigned long flags;
if (!dev)
return;
spin_lock_irqsave(&dev->power.lock, flags);
__pm_relax(dev->power.wakeup);
spin_unlock_irqrestore(&dev->power.lock, flags);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
EXPORT_SYMBOL_GPL(pm_relax);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/**
* pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
* @data: Address of the wakeup source object associated with the event source.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Call wakeup_source_deactivate() for the wakeup source whose address is stored
* in @data if it is currently active and its timer has not been canceled and
* the expiration time of the timer is not in future.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
static void pm_wakeup_timer_fn(struct timer_list *t)
{
struct wakeup_source *ws = from_timer(ws, t, timer);
unsigned long flags;
spin_lock_irqsave(&ws->lock, flags);
if (ws->active && ws->timer_expires
&& time_after_eq(jiffies, ws->timer_expires)) {
wakeup_source_deactivate(ws);
ws->expire_count++;
}
spin_unlock_irqrestore(&ws->lock, flags);
}
/**
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
* pm_wakeup_ws_event - Notify the PM core of a wakeup event.
* @ws: Wakeup source object associated with the event source.
* @msec: Anticipated event processing time (in milliseconds).
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
* @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*
* Notify the PM core of a wakeup event whose source is @ws that will take
* approximately @msec milliseconds to be processed by the kernel. If @ws is
* not active, activate it. If @msec is nonzero, set up the @ws' timer to
* execute pm_wakeup_timer_fn() in future.
*
* It is safe to call this function from interrupt context.
*/
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned long flags;
unsigned long expires;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
if (!ws)
return;
spin_lock_irqsave(&ws->lock, flags);
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
wakeup_source_report_event(ws, hard);
if (!msec) {
wakeup_source_deactivate(ws);
goto unlock;
}
expires = jiffies + msecs_to_jiffies(msec);
if (!expires)
expires = 1;
if (!ws->timer_expires || time_after(expires, ws->timer_expires)) {
mod_timer(&ws->timer, expires);
ws->timer_expires = expires;
}
unlock:
spin_unlock_irqrestore(&ws->lock, flags);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
EXPORT_SYMBOL_GPL(pm_wakeup_ws_event);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/**
* pm_wakeup_dev_event - Notify the PM core of a wakeup event.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
* @dev: Device the wakeup event is related to.
* @msec: Anticipated event processing time (in milliseconds).
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
* @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
* Call pm_wakeup_ws_event() for the @dev's wakeup source object.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned long flags;
if (!dev)
return;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
spin_lock_irqsave(&dev->power.lock, flags);
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
pm_wakeup_ws_event(dev->power.wakeup, msec, hard);
spin_unlock_irqrestore(&dev->power.lock, flags);
}
PM / wakeup: Integrate mechanism to abort transitions in progress The system wakeup framework is not very consistent with respect to the way it handles suspend-to-idle and generally wakeup events occurring during transitions to system low-power states. First off, system transitions in progress are aborted by the event reporting helpers like pm_wakeup_event() only if the wakeup_count sysfs attribute is in use (as documented), but there are cases in which system-wide transitions should be aborted even if that is not the case. For example, a wakeup signal from a designated wakeup device during system-wide PM transition, it should cause the transition to be aborted right away. Moreover, there is a freeze_wake() call in wakeup_source_activate(), but that really is only effective after suspend_freeze_state has been set to FREEZE_STATE_ENTER by freeze_enter(). However, it is very unlikely that wakeup_source_activate() will ever be called at that time, as it could only be triggered by a IRQF_NO_SUSPEND interrupt handler, so wakeups from suspend-to-idle don't really occur in wakeup_source_activate(). At the same time there is a way to abort a system suspend in progress (or wake up the system from suspend-to-idle), which is by calling pm_system_wakeup(), but in turn that doesn't cause any wakeup source objects to be activated, so it will not be covered by wakeup source statistics and will not prevent the system from suspending again immediately (in case autosleep is used, for example). Consequently, if anyone wants to abort system transitions in progress and allow the wakeup_count mechanism to work, they need to use both pm_system_wakeup() and pm_wakeup_event(), say, at the same time which is awkward. For the above reasons, make it possible to trigger pm_system_wakeup() from within wakeup_source_activate() and provide a new pm_wakeup_hard_event() helper to do so within the wakeup framework. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-04-26 15:22:09 -06:00
EXPORT_SYMBOL_GPL(pm_wakeup_dev_event);
void pm_print_active_wakeup_sources(void)
{
struct wakeup_source *ws;
int srcuidx, active = 0;
struct wakeup_source *last_activity_ws = NULL;
srcuidx = srcu_read_lock(&wakeup_srcu);
list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
if (ws->active) {
pm_pr_dbg("active wakeup source: %s\n", ws->name);
active = 1;
} else if (!active &&
(!last_activity_ws ||
ktime_to_ns(ws->last_time) >
ktime_to_ns(last_activity_ws->last_time))) {
last_activity_ws = ws;
}
}
if (!active && last_activity_ws)
pm_pr_dbg("last active wakeup source: %s\n",
last_activity_ws->name);
srcu_read_unlock(&wakeup_srcu, srcuidx);
}
EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
/**
* pm_wakeup_pending - Check if power transition in progress should be aborted.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Compare the current number of registered wakeup events with its preserved
* value from the past and return true if new wakeup events have been registered
* since the old value was stored. Also return true if the current number of
* wakeup events being processed is different from zero.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
bool pm_wakeup_pending(void)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned long flags;
bool ret = false;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
raw_spin_lock_irqsave(&events_lock, flags);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
if (events_check_enabled) {
unsigned int cnt, inpr;
split_counters(&cnt, &inpr);
ret = (cnt != saved_count || inpr > 0);
events_check_enabled = !ret;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
raw_spin_unlock_irqrestore(&events_lock, flags);
if (ret) {
pm_pr_dbg("Wakeup pending, aborting suspend\n");
pm_print_active_wakeup_sources();
}
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
return ret || atomic_read(&pm_abort_suspend) > 0;
}
void pm_system_wakeup(void)
{
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
atomic_inc(&pm_abort_suspend);
s2idle_wake();
}
EXPORT_SYMBOL_GPL(pm_system_wakeup);
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
void pm_system_cancel_wakeup(void)
{
atomic_dec_if_positive(&pm_abort_suspend);
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
}
void pm_wakeup_clear(bool reset)
{
pm_wakeup_irq = 0;
ACPI / PM: Ignore spurious SCI wakeups from suspend-to-idle The ACPI SCI (System Control Interrupt) is set up as a wakeup IRQ during suspend-to-idle transitions and, consequently, any events signaled through it wake up the system from that state. However, on some systems some of the events signaled via the ACPI SCI while suspended to idle should not cause the system to wake up. In fact, quite often they should just be discarded. Arguably, systems should not resume entirely on such events, but in order to decide which events really should cause the system to resume and which are spurious, it is necessary to resume up to the point when ACPI SCIs are actually handled and processed, which is after executing dpm_resume_noirq() in the system resume path. For this reasons, add a loop around freeze_enter() in which the platforms can process events signaled via multiplexed IRQ lines like the ACPI SCI and add suspend-to-idle hooks that can be used for this purpose to struct platform_freeze_ops. In the ACPI case, the ->wake hook is used for checking if the SCI has triggered while suspended and deferring the interrupt-induced system wakeup until the events signaled through it are actually processed sufficiently to decide whether or not the system should resume. In turn, the ->sync hook allows all of the relevant event queues to be flushed so as to prevent events from being missed due to race conditions. In addition to that, some ACPI code processing wakeup events needs to be modified to use the "hard" version of wakeup triggers, so that it will cause a system resume to happen on device-induced wakeup events even if the "soft" mechanism to prevent the system from suspending is not enabled. However, to preserve the existing behavior with respect to suspend-to-RAM, this only is done in the suspend-to-idle case and only if an SCI has occurred while suspended. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2017-06-12 14:56:34 -06:00
if (reset)
atomic_set(&pm_abort_suspend, 0);
}
void pm_system_irq_wakeup(unsigned int irq_number)
{
if (pm_wakeup_irq == 0) {
pm_wakeup_irq = irq_number;
pm_system_wakeup();
}
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
/**
* pm_get_wakeup_count - Read the number of registered wakeup events.
* @count: Address to store the value at.
* @block: Whether or not to block.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Store the number of registered wakeup events at the address in @count. If
* @block is set, block until the current number of wakeup events being
* processed is zero.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*
* Return 'false' if the current number of wakeup events being processed is
* nonzero. Otherwise return 'true'.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
bool pm_get_wakeup_count(unsigned int *count, bool block)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned int cnt, inpr;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
if (block) {
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait(&wakeup_count_wait_queue, &wait,
TASK_INTERRUPTIBLE);
split_counters(&cnt, &inpr);
if (inpr == 0 || signal_pending(current))
break;
pm_print_active_wakeup_sources();
schedule();
}
finish_wait(&wakeup_count_wait_queue, &wait);
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
split_counters(&cnt, &inpr);
*count = cnt;
return !inpr;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
/**
* pm_save_wakeup_count - Save the current number of registered wakeup events.
* @count: Value to compare with the current number of registered wakeup events.
*
* If @count is equal to the current number of registered wakeup events and the
* current number of wakeup events being processed is zero, store @count as the
* old number of registered wakeup events for pm_check_wakeup_events(), enable
* wakeup events detection and return 'true'. Otherwise disable wakeup events
* detection and return 'false'.
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
*/
bool pm_save_wakeup_count(unsigned int count)
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
{
unsigned int cnt, inpr;
unsigned long flags;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
events_check_enabled = false;
raw_spin_lock_irqsave(&events_lock, flags);
split_counters(&cnt, &inpr);
if (cnt == count && inpr == 0) {
saved_count = count;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
events_check_enabled = true;
}
raw_spin_unlock_irqrestore(&events_lock, flags);
return events_check_enabled;
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 <rjw@sisk.pl> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: markgross <markgross@thegnar.org> Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
2010-07-05 14:43:53 -06:00
}
#ifdef CONFIG_PM_AUTOSLEEP
/**
* pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
* @enabled: Whether to set or to clear the autosleep_enabled flags.
*/
void pm_wakep_autosleep_enabled(bool set)
{
struct wakeup_source *ws;
ktime_t now = ktime_get();
int srcuidx;
srcuidx = srcu_read_lock(&wakeup_srcu);
list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
spin_lock_irq(&ws->lock);
if (ws->autosleep_enabled != set) {
ws->autosleep_enabled = set;
if (ws->active) {
if (set)
ws->start_prevent_time = now;
else
update_prevent_sleep_time(ws, now);
}
}
spin_unlock_irq(&ws->lock);
}
srcu_read_unlock(&wakeup_srcu, srcuidx);
}
#endif /* CONFIG_PM_AUTOSLEEP */
/**
* print_wakeup_source_stats - Print wakeup source statistics information.
* @m: seq_file to print the statistics into.
* @ws: Wakeup source object to print the statistics for.
*/
static int print_wakeup_source_stats(struct seq_file *m,
struct wakeup_source *ws)
{
unsigned long flags;
ktime_t total_time;
ktime_t max_time;
unsigned long active_count;
ktime_t active_time;
ktime_t prevent_sleep_time;
spin_lock_irqsave(&ws->lock, flags);
total_time = ws->total_time;
max_time = ws->max_time;
prevent_sleep_time = ws->prevent_sleep_time;
active_count = ws->active_count;
if (ws->active) {
ktime_t now = ktime_get();
active_time = ktime_sub(now, ws->last_time);
total_time = ktime_add(total_time, active_time);
if (active_time > max_time)
max_time = active_time;
if (ws->autosleep_enabled)
prevent_sleep_time = ktime_add(prevent_sleep_time,
ktime_sub(now, ws->start_prevent_time));
} else {
active_time = 0;
}
seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
ws->name, active_count, ws->event_count,
ws->wakeup_count, ws->expire_count,
ktime_to_ms(active_time), ktime_to_ms(total_time),
ktime_to_ms(max_time), ktime_to_ms(ws->last_time),
ktime_to_ms(prevent_sleep_time));
spin_unlock_irqrestore(&ws->lock, flags);
return 0;
}
static void *wakeup_sources_stats_seq_start(struct seq_file *m,
loff_t *pos)
{
struct wakeup_source *ws;
loff_t n = *pos;
int *srcuidx = m->private;
if (n == 0) {
seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
"expire_count\tactive_since\ttotal_time\tmax_time\t"
"last_change\tprevent_suspend_time\n");
}
*srcuidx = srcu_read_lock(&wakeup_srcu);
list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
if (n-- <= 0)
return ws;
}
return NULL;
}
static void *wakeup_sources_stats_seq_next(struct seq_file *m,
void *v, loff_t *pos)
{
struct wakeup_source *ws = v;
struct wakeup_source *next_ws = NULL;
++(*pos);
list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) {
next_ws = ws;
break;
}
if (!next_ws)
print_wakeup_source_stats(m, &deleted_ws);
return next_ws;
}
static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v)
{
int *srcuidx = m->private;
srcu_read_unlock(&wakeup_srcu, *srcuidx);
}
/**
* wakeup_sources_stats_seq_show - Print wakeup sources statistics information.
* @m: seq_file to print the statistics into.
* @v: wakeup_source of each iteration
*/
static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v)
{
struct wakeup_source *ws = v;
print_wakeup_source_stats(m, ws);
return 0;
}
static const struct seq_operations wakeup_sources_stats_seq_ops = {
.start = wakeup_sources_stats_seq_start,
.next = wakeup_sources_stats_seq_next,
.stop = wakeup_sources_stats_seq_stop,
.show = wakeup_sources_stats_seq_show,
};
static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
{
return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int));
}
static const struct file_operations wakeup_sources_stats_fops = {
.owner = THIS_MODULE,
.open = wakeup_sources_stats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
static int __init wakeup_sources_debugfs_init(void)
{
debugfs_create_file("wakeup_sources", S_IRUGO, NULL, NULL,
&wakeup_sources_stats_fops);
return 0;
}
postcore_initcall(wakeup_sources_debugfs_init);