linux_dsm_epyc7002/kernel/power/suspend.c

311 lines
6.7 KiB
C
Raw Normal View History

/*
* kernel/power/suspend.c - Suspend to RAM and standby functionality.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
* Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
*
* This file is released under the GPLv2.
*/
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/suspend.h>
#include "power.h"
const char *const pm_states[PM_SUSPEND_MAX] = {
[PM_SUSPEND_STANDBY] = "standby",
[PM_SUSPEND_MEM] = "mem",
};
static struct platform_suspend_ops *suspend_ops;
/**
* suspend_set_ops - Set the global suspend method table.
* @ops: Pointer to ops structure.
*/
void suspend_set_ops(struct platform_suspend_ops *ops)
{
mutex_lock(&pm_mutex);
suspend_ops = ops;
mutex_unlock(&pm_mutex);
}
bool valid_state(suspend_state_t state)
{
/*
* All states need lowlevel support and need to be valid to the lowlevel
* implementation, no valid callback implies that none are valid.
*/
return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
}
/**
* suspend_valid_only_mem - generic memory-only valid callback
*
* Platform drivers that implement mem suspend only and only need
* to check for that in their .valid callback can use this instead
* of rolling their own .valid callback.
*/
int suspend_valid_only_mem(suspend_state_t state)
{
return state == PM_SUSPEND_MEM;
}
static int suspend_test(int level)
{
#ifdef CONFIG_PM_DEBUG
if (pm_test_level == level) {
printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
mdelay(5000);
return 1;
}
#endif /* !CONFIG_PM_DEBUG */
return 0;
}
/**
* suspend_prepare - Do prep work before entering low-power state.
*
* This is common code that is called for each state that we're entering.
* Run suspend notifiers, allocate a console and stop all processes.
*/
static int suspend_prepare(void)
{
int error;
if (!suspend_ops || !suspend_ops->enter)
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
if (error)
goto Finish;
error = usermodehelper_disable();
if (error)
goto Finish;
error = suspend_freeze_processes();
if (!error)
return 0;
suspend_thaw_processes();
usermodehelper_enable();
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
return error;
}
/* default implementation */
void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
{
local_irq_disable();
}
/* default implementation */
void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
{
local_irq_enable();
}
/**
* suspend_enter - enter the desired system sleep state.
* @state: state to enter
*
* This function should be called after devices have been suspended.
*/
static int suspend_enter(suspend_state_t state)
{
int error;
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
goto Platform_finish;
}
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
goto Platform_finish;
}
if (suspend_ops->prepare_late) {
error = suspend_ops->prepare_late();
if (error)
goto Platform_wake;
}
if (suspend_test(TEST_PLATFORM))
goto Platform_wake;
error = disable_nonboot_cpus();
if (error || suspend_test(TEST_CPUS))
goto Enable_cpus;
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
error = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
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>
2010-07-06 03:43:53 +07:00
if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) {
error = suspend_ops->enter(state);
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>
2010-07-06 03:43:53 +07:00
events_check_enabled = false;
}
sysdev_resume();
}
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
Enable_cpus:
enable_nonboot_cpus();
Platform_wake:
if (suspend_ops->wake)
suspend_ops->wake();
dpm_resume_noirq(PMSG_RESUME);
Platform_finish:
if (suspend_ops->finish)
suspend_ops->finish();
return error;
}
/**
* suspend_devices_and_enter - suspend devices and enter the desired system
* sleep state.
* @state: state to enter
*/
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
if (!suspend_ops)
return -ENOSYS;
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
pm_restrict_gfp_mask();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
suspend_enter(state);
Resume_devices:
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
pm_restore_gfp_mask();
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
return error;
Recover_platform:
if (suspend_ops->recover)
suspend_ops->recover();
goto Resume_devices;
}
/**
* suspend_finish - Do final work before exiting suspend sequence.
*
* Call platform code to clean up, restart processes, and free the
* console that we've allocated. This is not called for suspend-to-disk.
*/
static void suspend_finish(void)
{
suspend_thaw_processes();
usermodehelper_enable();
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
}
/**
* enter_state - Do common work of entering low-power state.
* @state: pm_state structure for state we're entering.
*
* Make sure we're the only ones trying to enter a sleep state. Fail
* if someone has beat us to it, since we don't want anything weird to
* happen when we wake up.
* Then, do the setup for suspend, enter the state, and cleaup (after
* we've woken up).
*/
int enter_state(suspend_state_t state)
{
int error;
if (!valid_state(state))
return -ENODEV;
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare();
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state);
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
/**
* pm_suspend - Externally visible function for suspending system.
* @state: Enumerated value of state to enter.
*
* Determine whether or not value is within range, get state
* structure, and enter (above).
*/
int pm_suspend(suspend_state_t state)
{
if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
return enter_state(state);
return -EINVAL;
}
EXPORT_SYMBOL(pm_suspend);