linux_dsm_epyc7002/kernel/power/hibernate.c

1242 lines
29 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support.
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
* Copyright (c) 2004 Pavel Machek <pavel@ucw.cz>
* Copyright (c) 2009 Rafael J. Wysocki, Novell Inc.
* Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com>
*/
#define pr_fmt(fmt) "PM: hibernation: " fmt
#include <linux/export.h>
#include <linux/suspend.h>
#include <linux/reboot.h>
#include <linux/string.h>
#include <linux/device.h>
#include <linux/async.h>
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pm.h>
#include <linux/nmi.h>
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.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/syscore_ops.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
#include <linux/ktime.h>
#include <linux/security.h>
#include <trace/events/power.h>
#include "power.h"
static int nocompress;
static int noresume;
static int nohibernate;
static int resume_wait;
static unsigned int resume_delay;
static char resume_file[256] = CONFIG_PM_STD_PARTITION;
dev_t swsusp_resume_device;
sector_t swsusp_resume_block;
__visible int in_suspend __nosavedata;
enum {
HIBERNATION_INVALID,
HIBERNATION_PLATFORM,
HIBERNATION_SHUTDOWN,
HIBERNATION_REBOOT,
#ifdef CONFIG_SUSPEND
HIBERNATION_SUSPEND,
#endif
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
HIBERNATION_TEST_RESUME,
/* keep last */
__HIBERNATION_AFTER_LAST
};
#define HIBERNATION_MAX (__HIBERNATION_AFTER_LAST-1)
#define HIBERNATION_FIRST (HIBERNATION_INVALID + 1)
static int hibernation_mode = HIBERNATION_SHUTDOWN;
bool freezer_test_done;
static const struct platform_hibernation_ops *hibernation_ops;
bool hibernation_available(void)
{
return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION);
}
/**
* hibernation_set_ops - Set the global hibernate operations.
* @ops: Hibernation operations to use in subsequent hibernation transitions.
*/
void hibernation_set_ops(const struct platform_hibernation_ops *ops)
{
if (ops && !(ops->begin && ops->end && ops->pre_snapshot
&& ops->prepare && ops->finish && ops->enter && ops->pre_restore
&& ops->restore_cleanup && ops->leave)) {
WARN_ON(1);
return;
}
lock_system_sleep();
hibernation_ops = ops;
if (ops)
hibernation_mode = HIBERNATION_PLATFORM;
else if (hibernation_mode == HIBERNATION_PLATFORM)
hibernation_mode = HIBERNATION_SHUTDOWN;
unlock_system_sleep();
}
EXPORT_SYMBOL_GPL(hibernation_set_ops);
static bool entering_platform_hibernation;
bool system_entering_hibernation(void)
{
return entering_platform_hibernation;
}
EXPORT_SYMBOL(system_entering_hibernation);
#ifdef CONFIG_PM_DEBUG
static void hibernation_debug_sleep(void)
{
pr_info("debug: Waiting for 5 seconds.\n");
mdelay(5000);
}
static int hibernation_test(int level)
{
if (pm_test_level == level) {
hibernation_debug_sleep();
return 1;
}
return 0;
}
#else /* !CONFIG_PM_DEBUG */
static int hibernation_test(int level) { return 0; }
#endif /* !CONFIG_PM_DEBUG */
/**
* platform_begin - Call platform to start hibernation.
* @platform_mode: Whether or not to use the platform driver.
*/
static int platform_begin(int platform_mode)
{
return (platform_mode && hibernation_ops) ?
hibernation_ops->begin(PMSG_FREEZE) : 0;
}
/**
* platform_end - Call platform to finish transition to the working state.
* @platform_mode: Whether or not to use the platform driver.
*/
static void platform_end(int platform_mode)
{
if (platform_mode && hibernation_ops)
hibernation_ops->end();
}
/**
* platform_pre_snapshot - Call platform to prepare the machine for hibernation.
* @platform_mode: Whether or not to use the platform driver.
*
* Use the platform driver to prepare the system for creating a hibernate image,
* if so configured, and return an error code if that fails.
*/
static int platform_pre_snapshot(int platform_mode)
{
return (platform_mode && hibernation_ops) ?
hibernation_ops->pre_snapshot() : 0;
}
/**
* platform_leave - Call platform to prepare a transition to the working state.
* @platform_mode: Whether or not to use the platform driver.
*
* Use the platform driver prepare to prepare the machine for switching to the
* normal mode of operation.
*
* This routine is called on one CPU with interrupts disabled.
*/
static void platform_leave(int platform_mode)
{
if (platform_mode && hibernation_ops)
hibernation_ops->leave();
}
/**
* platform_finish - Call platform to switch the system to the working state.
* @platform_mode: Whether or not to use the platform driver.
*
* Use the platform driver to switch the machine to the normal mode of
* operation.
*
* This routine must be called after platform_prepare().
*/
static void platform_finish(int platform_mode)
{
if (platform_mode && hibernation_ops)
hibernation_ops->finish();
}
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
/**
* platform_pre_restore - Prepare for hibernate image restoration.
* @platform_mode: Whether or not to use the platform driver.
*
* Use the platform driver to prepare the system for resume from a hibernation
* image.
*
* If the restore fails after this function has been called,
* platform_restore_cleanup() must be called.
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
*/
static int platform_pre_restore(int platform_mode)
{
return (platform_mode && hibernation_ops) ?
hibernation_ops->pre_restore() : 0;
}
/**
* platform_restore_cleanup - Switch to the working state after failing restore.
* @platform_mode: Whether or not to use the platform driver.
*
* Use the platform driver to switch the system to the normal mode of operation
* after a failing restore.
*
* If platform_pre_restore() has been called before the failing restore, this
* function must be called too, regardless of the result of
* platform_pre_restore().
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
*/
static void platform_restore_cleanup(int platform_mode)
{
if (platform_mode && hibernation_ops)
hibernation_ops->restore_cleanup();
}
/**
* platform_recover - Recover from a failure to suspend devices.
* @platform_mode: Whether or not to use the platform driver.
*/
static void platform_recover(int platform_mode)
{
if (platform_mode && hibernation_ops && hibernation_ops->recover)
hibernation_ops->recover();
}
/**
* swsusp_show_speed - Print time elapsed between two events during hibernation.
* @start: Starting event.
* @stop: Final event.
* @nr_pages: Number of memory pages processed between @start and @stop.
* @msg: Additional diagnostic message to print.
*/
void swsusp_show_speed(ktime_t start, ktime_t stop,
unsigned nr_pages, char *msg)
{
ktime_t diff;
u64 elapsed_centisecs64;
unsigned int centisecs;
unsigned int k;
unsigned int kps;
diff = ktime_sub(stop, start);
elapsed_centisecs64 = ktime_divns(diff, 10*NSEC_PER_MSEC);
centisecs = elapsed_centisecs64;
if (centisecs == 0)
centisecs = 1; /* avoid div-by-zero */
k = nr_pages * (PAGE_SIZE / 1024);
kps = (k * 100) / centisecs;
pr_info("%s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n",
msg, k, centisecs / 100, centisecs % 100, kps / 1000,
(kps % 1000) / 10);
}
x86/power: Fix 'nosmt' vs hibernation triple fault during resume As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ <stable@vger.kernel.org> # v4.19+ Debugged-by: Thomas Gleixner <tglx@linutronix.de> Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Pavel Machek <pavel@ucw.cz> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-05-30 05:09:39 +07:00
__weak int arch_resume_nosmt(void)
{
return 0;
}
/**
* create_image - Create a hibernation image.
* @platform_mode: Whether or not to use the platform driver.
*
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
* Execute device drivers' "late" and "noirq" freeze callbacks, create a
* hibernation image and run the drivers' "noirq" and "early" thaw callbacks.
*
* Control reappears in this routine after the subsequent restore.
*/
static int create_image(int platform_mode)
{
int error;
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
error = dpm_suspend_end(PMSG_FREEZE);
if (error) {
pr_err("Some devices failed to power down, aborting\n");
return error;
}
error = platform_pre_snapshot(platform_mode);
if (error || hibernation_test(TEST_PLATFORM))
goto Platform_finish;
error = suspend_disable_secondary_cpus();
if (error || hibernation_test(TEST_CPUS))
goto Enable_cpus;
local_irq_disable();
system_state = SYSTEM_SUSPEND;
error = syscore_suspend();
if (error) {
pr_err("Some system devices failed to power down, aborting\n");
goto Enable_irqs;
}
if (hibernation_test(TEST_CORE) || pm_wakeup_pending())
goto Power_up;
in_suspend = 1;
save_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
error = swsusp_arch_suspend();
/* Restore control flow magically appears here */
restore_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
pr_err("Error %d creating image\n", error);
if (!in_suspend) {
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;
clear_free_pages();
}
platform_leave(platform_mode);
Power_up:
syscore_resume();
Enable_irqs:
system_state = SYSTEM_RUNNING;
local_irq_enable();
Enable_cpus:
suspend_enable_secondary_cpus();
x86/power: Fix 'nosmt' vs hibernation triple fault during resume As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ <stable@vger.kernel.org> # v4.19+ Debugged-by: Thomas Gleixner <tglx@linutronix.de> Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Pavel Machek <pavel@ucw.cz> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-05-30 05:09:39 +07:00
/* Allow architectures to do nosmt-specific post-resume dances */
if (!in_suspend)
error = arch_resume_nosmt();
Platform_finish:
platform_finish(platform_mode);
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
dpm_resume_start(in_suspend ?
Introduce new top level suspend and hibernation callbacks Introduce 'struct pm_ops' and 'struct pm_ext_ops' ('ext' meaning 'extended') representing suspend and hibernation operations for bus types, device classes, device types and device drivers. Modify the PM core to use 'struct pm_ops' and 'struct pm_ext_ops' objects, if defined, instead of the ->suspend(), ->resume(), ->suspend_late(), and ->resume_early() callbacks (the old callbacks will be considered as legacy and gradually phased out). The main purpose of doing this is to separate suspend (aka S2RAM and standby) callbacks from hibernation callbacks in such a way that the new callbacks won't take arguments and the semantics of each of them will be clearly specified. This has been requested for multiple times by many people, including Linus himself, and the reason is that within the current scheme if ->resume() is called, for example, it's difficult to say why it's been called (ie. is it a resume from RAM or from hibernation or a suspend/hibernation failure etc.?). The second purpose is to make the suspend/hibernation callbacks more flexible so that device drivers can handle more than they can within the current scheme. For example, some drivers may need to prevent new children of the device from being registered before their ->suspend() callbacks are executed or they may want to carry out some operations requiring the availability of some other devices, not directly bound via the parent-child relationship, in order to prepare for the execution of ->suspend(), etc. Ultimately, we'd like to stop using the freezing of tasks for suspend and therefore the drivers' suspend/hibernation code will have to take care of the handling of the user space during suspend/hibernation. That, in turn, would be difficult within the current scheme, without the new ->prepare() and ->complete() callbacks. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-05-21 04:00:01 +07:00
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
return error;
}
/**
* hibernation_snapshot - Quiesce devices and create a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
* This routine must be called with system_transition_mutex held.
*/
int hibernation_snapshot(int platform_mode)
{
pm_message_t msg;
int error;
pm_suspend_clear_flags();
error = platform_begin(platform_mode);
if (error)
goto Close;
/* Preallocate image memory before shutting down devices. */
error = hibernate_preallocate_memory();
if (error)
goto Close;
error = freeze_kernel_threads();
if (error)
goto Cleanup;
if (hibernation_test(TEST_FREEZER)) {
/*
* Indicate to the caller that we are returning due to a
* successful freezer test.
*/
freezer_test_done = true;
goto Thaw;
}
error = dpm_prepare(PMSG_FREEZE);
if (error) {
dpm_complete(PMSG_RECOVER);
goto Thaw;
}
suspend_console();
pm_restrict_gfp_mask();
error = dpm_suspend(PMSG_FREEZE);
if (error || hibernation_test(TEST_DEVICES))
platform_recover(platform_mode);
else
error = create_image(platform_mode);
/*
* In the case that we call create_image() above, the control
* returns here (1) after the image has been created or the
* image creation has failed and (2) after a successful restore.
*/
/* We may need to release the preallocated image pages here. */
if (error || !in_suspend)
swsusp_free();
msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE;
dpm_resume(msg);
if (error || !in_suspend)
pm_restore_gfp_mask();
resume_console();
dpm_complete(msg);
Close:
platform_end(platform_mode);
return error;
Thaw:
thaw_kernel_threads();
Cleanup:
swsusp_free();
goto Close;
}
x86 / hibernate: Use hlt_play_dead() when resuming from hibernation On Intel hardware, native_play_dead() uses mwait_play_dead() by default and only falls back to the other methods if that fails. That also happens during resume from hibernation, when the restore (boot) kernel runs disable_nonboot_cpus() to take all of the CPUs except for the boot one offline. However, that is problematic, because the address passed to __monitor() in mwait_play_dead() is likely to be written to in the last phase of hibernate image restoration and that causes the "dead" CPU to start executing instructions again. Unfortunately, the page containing the address in that CPU's instruction pointer may not be valid any more at that point. First, that page may have been overwritten with image kernel memory contents already, so the instructions the CPU attempts to execute may simply be invalid. Second, the page tables previously used by that CPU may have been overwritten by image kernel memory contents, so the address in its instruction pointer is impossible to resolve then. A report from Varun Koyyalagunta and investigation carried out by Chen Yu show that the latter sometimes happens in practice. To prevent it from happening, temporarily change the smp_ops.play_dead pointer during resume from hibernation so that it points to a special "play dead" routine which uses hlt_play_dead() and avoids the inadvertent "revivals" of "dead" CPUs this way. A slightly unpleasant consequence of this change is that if the system is hibernated with one or more CPUs offline, it will generally draw more power after resume than it did before hibernation, because the physical state entered by CPUs via hlt_play_dead() is higher-power than the mwait_play_dead() one in the majority of cases. It is possible to work around this, but it is unclear how much of a problem that's going to be in practice, so the workaround will be implemented later if it turns out to be necessary. Link: https://bugzilla.kernel.org/show_bug.cgi?id=106371 Reported-by: Varun Koyyalagunta <cpudebug@centtech.com> Original-by: Chen Yu <yu.c.chen@intel.com> Tested-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org>
2016-07-14 08:55:23 +07:00
int __weak hibernate_resume_nonboot_cpu_disable(void)
{
return suspend_disable_secondary_cpus();
x86 / hibernate: Use hlt_play_dead() when resuming from hibernation On Intel hardware, native_play_dead() uses mwait_play_dead() by default and only falls back to the other methods if that fails. That also happens during resume from hibernation, when the restore (boot) kernel runs disable_nonboot_cpus() to take all of the CPUs except for the boot one offline. However, that is problematic, because the address passed to __monitor() in mwait_play_dead() is likely to be written to in the last phase of hibernate image restoration and that causes the "dead" CPU to start executing instructions again. Unfortunately, the page containing the address in that CPU's instruction pointer may not be valid any more at that point. First, that page may have been overwritten with image kernel memory contents already, so the instructions the CPU attempts to execute may simply be invalid. Second, the page tables previously used by that CPU may have been overwritten by image kernel memory contents, so the address in its instruction pointer is impossible to resolve then. A report from Varun Koyyalagunta and investigation carried out by Chen Yu show that the latter sometimes happens in practice. To prevent it from happening, temporarily change the smp_ops.play_dead pointer during resume from hibernation so that it points to a special "play dead" routine which uses hlt_play_dead() and avoids the inadvertent "revivals" of "dead" CPUs this way. A slightly unpleasant consequence of this change is that if the system is hibernated with one or more CPUs offline, it will generally draw more power after resume than it did before hibernation, because the physical state entered by CPUs via hlt_play_dead() is higher-power than the mwait_play_dead() one in the majority of cases. It is possible to work around this, but it is unclear how much of a problem that's going to be in practice, so the workaround will be implemented later if it turns out to be necessary. Link: https://bugzilla.kernel.org/show_bug.cgi?id=106371 Reported-by: Varun Koyyalagunta <cpudebug@centtech.com> Original-by: Chen Yu <yu.c.chen@intel.com> Tested-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org>
2016-07-14 08:55:23 +07:00
}
/**
* resume_target_kernel - Restore system state from a hibernation image.
* @platform_mode: Whether or not to use the platform driver.
*
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
* Execute device drivers' "noirq" and "late" freeze callbacks, restore the
* contents of highmem that have not been restored yet from the image and run
* the low-level code that will restore the remaining contents of memory and
* switch to the just restored target kernel.
*/
static int resume_target_kernel(bool platform_mode)
{
int error;
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
error = dpm_suspend_end(PMSG_QUIESCE);
if (error) {
pr_err("Some devices failed to power down, aborting resume\n");
return error;
}
error = platform_pre_restore(platform_mode);
if (error)
goto Cleanup;
x86 / hibernate: Use hlt_play_dead() when resuming from hibernation On Intel hardware, native_play_dead() uses mwait_play_dead() by default and only falls back to the other methods if that fails. That also happens during resume from hibernation, when the restore (boot) kernel runs disable_nonboot_cpus() to take all of the CPUs except for the boot one offline. However, that is problematic, because the address passed to __monitor() in mwait_play_dead() is likely to be written to in the last phase of hibernate image restoration and that causes the "dead" CPU to start executing instructions again. Unfortunately, the page containing the address in that CPU's instruction pointer may not be valid any more at that point. First, that page may have been overwritten with image kernel memory contents already, so the instructions the CPU attempts to execute may simply be invalid. Second, the page tables previously used by that CPU may have been overwritten by image kernel memory contents, so the address in its instruction pointer is impossible to resolve then. A report from Varun Koyyalagunta and investigation carried out by Chen Yu show that the latter sometimes happens in practice. To prevent it from happening, temporarily change the smp_ops.play_dead pointer during resume from hibernation so that it points to a special "play dead" routine which uses hlt_play_dead() and avoids the inadvertent "revivals" of "dead" CPUs this way. A slightly unpleasant consequence of this change is that if the system is hibernated with one or more CPUs offline, it will generally draw more power after resume than it did before hibernation, because the physical state entered by CPUs via hlt_play_dead() is higher-power than the mwait_play_dead() one in the majority of cases. It is possible to work around this, but it is unclear how much of a problem that's going to be in practice, so the workaround will be implemented later if it turns out to be necessary. Link: https://bugzilla.kernel.org/show_bug.cgi?id=106371 Reported-by: Varun Koyyalagunta <cpudebug@centtech.com> Original-by: Chen Yu <yu.c.chen@intel.com> Tested-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org>
2016-07-14 08:55:23 +07:00
error = hibernate_resume_nonboot_cpu_disable();
if (error)
goto Enable_cpus;
local_irq_disable();
system_state = SYSTEM_SUSPEND;
error = syscore_suspend();
if (error)
goto Enable_irqs;
save_processor_state();
error = restore_highmem();
if (!error) {
error = swsusp_arch_resume();
/*
* The code below is only ever reached in case of a failure.
* Otherwise, execution continues at the place where
* swsusp_arch_suspend() was called.
*/
BUG_ON(!error);
/*
* This call to restore_highmem() reverts the changes made by
* the previous one.
*/
restore_highmem();
}
/*
* The only reason why swsusp_arch_resume() can fail is memory being
* very tight, so we have to free it as soon as we can to avoid
* subsequent failures.
*/
swsusp_free();
restore_processor_state();
touch_softlockup_watchdog();
syscore_resume();
Enable_irqs:
system_state = SYSTEM_RUNNING;
local_irq_enable();
Enable_cpus:
suspend_enable_secondary_cpus();
Cleanup:
platform_restore_cleanup(platform_mode);
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
dpm_resume_start(PMSG_RECOVER);
return error;
}
/**
* hibernation_restore - Quiesce devices and restore from a hibernation image.
* @platform_mode: If set, use platform driver to prepare for the transition.
*
* This routine must be called with system_transition_mutex held. If it is
* successful, control reappears in the restored target kernel in
* hibernation_snapshot().
*/
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
int hibernation_restore(int platform_mode)
{
int error;
pm_prepare_console();
suspend_console();
pm_restrict_gfp_mask();
error = dpm_suspend_start(PMSG_QUIESCE);
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
if (!error) {
error = resume_target_kernel(platform_mode);
/*
* The above should either succeed and jump to the new kernel,
* or return with an error. Otherwise things are just
* undefined, so let's be paranoid.
*/
BUG_ON(!error);
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
}
dpm_resume_end(PMSG_RECOVER);
pm_restore_gfp_mask();
resume_console();
pm_restore_console();
return error;
}
/**
* hibernation_platform_enter - Power off the system using the platform driver.
*/
int hibernation_platform_enter(void)
{
int error;
if (!hibernation_ops)
return -ENOSYS;
/*
* We have cancelled the power transition by running
* hibernation_ops->finish() before saving the image, so we should let
* the firmware know that we're going to enter the sleep state after all
*/
error = hibernation_ops->begin(PMSG_HIBERNATE);
if (error)
goto Close;
entering_platform_hibernation = true;
suspend_console();
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
hibernation_ops->recover();
goto Resume_devices;
}
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
error = dpm_suspend_end(PMSG_HIBERNATE);
if (error)
goto Resume_devices;
error = hibernation_ops->prepare();
if (error)
goto Platform_finish;
error = suspend_disable_secondary_cpus();
if (error)
goto Enable_cpus;
local_irq_disable();
system_state = SYSTEM_SUSPEND;
syscore_suspend();
if (pm_wakeup_pending()) {
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
error = -EAGAIN;
goto Power_up;
}
hibernation_ops->enter();
/* We should never get here */
while (1);
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
Power_up:
syscore_resume();
system_state = SYSTEM_RUNNING;
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
local_irq_enable();
Enable_cpus:
suspend_enable_secondary_cpus();
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
Platform_finish:
hibernation_ops->finish();
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 02:38:29 +07:00
dpm_resume_start(PMSG_RESTORE);
Resume_devices:
entering_platform_hibernation = false;
dpm_resume_end(PMSG_RESTORE);
resume_console();
Close:
hibernation_ops->end();
return error;
}
/**
* power_down - Shut the machine down for hibernation.
*
* Use the platform driver, if configured, to put the system into the sleep
* state corresponding to hibernation, or try to power it off or reboot,
* depending on the value of hibernation_mode.
*/
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 05:09:51 +07:00
static void power_down(void)
{
#ifdef CONFIG_SUSPEND
int error;
if (hibernation_mode == HIBERNATION_SUSPEND) {
error = suspend_devices_and_enter(PM_SUSPEND_MEM);
if (error) {
hibernation_mode = hibernation_ops ?
HIBERNATION_PLATFORM :
HIBERNATION_SHUTDOWN;
} else {
/* Restore swap signature. */
error = swsusp_unmark();
if (error)
pr_err("Swap will be unusable! Try swapon -a.\n");
return;
}
}
#endif
switch (hibernation_mode) {
case HIBERNATION_REBOOT:
kernel_restart(NULL);
break;
case HIBERNATION_PLATFORM:
hibernation_platform_enter();
/* Fall through */
case HIBERNATION_SHUTDOWN:
if (pm_power_off)
kernel_power_off();
break;
}
kernel_halt();
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 05:09:51 +07:00
/*
* Valid image is on the disk, if we continue we risk serious data
* corruption after resume.
*/
pr_crit("Power down manually\n");
while (1)
cpu_relax();
}
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
static int load_image_and_restore(void)
{
int error;
unsigned int flags;
pm_pr_dbg("Loading hibernation image.\n");
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
lock_device_hotplug();
error = create_basic_memory_bitmaps();
if (error)
goto Unlock;
error = swsusp_read(&flags);
swsusp_close(FMODE_READ);
if (!error)
error = hibernation_restore(flags & SF_PLATFORM_MODE);
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
pr_err("Failed to load image, recovering.\n");
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
swsusp_free();
free_basic_memory_bitmaps();
Unlock:
unlock_device_hotplug();
return error;
}
/**
* hibernate - Carry out system hibernation, including saving the image.
*/
int hibernate(void)
{
int error, nr_calls = 0;
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
bool snapshot_test = false;
if (!hibernation_available()) {
pm_pr_dbg("Hibernation not available.\n");
return -EPERM;
}
lock_system_sleep();
/* The snapshot device should not be opened while we're running */
if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
error = -EBUSY;
goto Unlock;
}
pr_info("hibernation entry\n");
pm_prepare_console();
error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
if (error) {
nr_calls--;
goto Exit;
}
ksys_sync_helper();
error = freeze_processes();
if (error)
goto Exit;
lock_device_hotplug();
/* Allocate memory management structures */
error = create_basic_memory_bitmaps();
if (error)
goto Thaw;
error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
if (error || freezer_test_done)
goto Free_bitmaps;
if (in_suspend) {
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
unsigned int flags = 0;
if (hibernation_mode == HIBERNATION_PLATFORM)
flags |= SF_PLATFORM_MODE;
if (nocompress)
flags |= SF_NOCOMPRESS_MODE;
else
flags |= SF_CRC32_MODE;
pm_pr_dbg("Writing hibernation image.\n");
swsusp: introduce restore platform operations At least on some machines it is necessary to prepare the ACPI firmware for the restoration of the system memory state from the hibernation image if the "platform" mode of hibernation has been used. Namely, in that cases we need to disable the GPEs before replacing the "boot" kernel with the "frozen" kernel (cf. http://bugzilla.kernel.org/show_bug.cgi?id=7887). After the restore they will be re-enabled by hibernation_ops->finish(), but if the restore fails, they have to be re-enabled by the restore code explicitly. For this purpose we can introduce two additional hibernation operations, called pre_restore() and restore_cleanup() and call them from the restore code path. Still, they should be called if the "platform" mode of hibernation has been used, so we need to pass the information about the hibernation mode from the "frozen" kernel to the "boot" kernel in the image header. Apparently, we can't drop the disabling of GPEs before the restore because of Bug #7887 .  We also can't do it unconditionally, because the GPEs wouldn't have been enabled after a successful restore if the suspend had been done in the 'shutdown' or 'reboot' mode. In principle we could (and probably should) unconditionally disable the GPEs before each snapshot creation *and* before the restore, but then we'd have to unconditionally enable them after the snapshot creation as well as after the restore (or restore failure)   Still, for this purpose we'd need to modify acpi_enter_sleep_state_prep() and acpi_leave_sleep_state() and we'd have to introduce some mechanism synchronizing the disablind/enabling of the GPEs with the device drivers' .suspend()/.resume() routines and with disable_/enable_nonboot_cpus().  However, this would have affected the suspend (ie. s2ram) code as well as the hibernation, which I'd like to avoid in this patch series. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:30 +07:00
error = swsusp_write(flags);
swsusp_free();
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
if (!error) {
if (hibernation_mode == HIBERNATION_TEST_RESUME)
snapshot_test = true;
else
power_down();
}
in_suspend = 0;
pm_restore_gfp_mask();
} else {
pm_pr_dbg("Hibernation image restored successfully.\n");
}
Free_bitmaps:
free_basic_memory_bitmaps();
Thaw:
unlock_device_hotplug();
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
if (snapshot_test) {
pm_pr_dbg("Checking hibernation image\n");
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
error = swsusp_check();
if (!error)
error = load_image_and_restore();
}
thaw_processes();
/* Don't bother checking whether freezer_test_done is true */
freezer_test_done = false;
Exit:
__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
pm_restore_console();
atomic_inc(&snapshot_device_available);
Unlock:
unlock_system_sleep();
pr_info("hibernation exit\n");
return error;
}
/**
* software_resume - Resume from a saved hibernation image.
*
* This routine is called as a late initcall, when all devices have been
* discovered and initialized already.
*
* The image reading code is called to see if there is a hibernation image
* available for reading. If that is the case, devices are quiesced and the
* contents of memory is restored from the saved image.
*
* If this is successful, control reappears in the restored target kernel in
* hibernation_snapshot() which returns to hibernate(). Otherwise, the routine
* attempts to recover gracefully and make the kernel return to the normal mode
* of operation.
*/
static int software_resume(void)
{
int error, nr_calls = 0;
/*
* If the user said "noresume".. bail out early.
*/
if (noresume || !hibernation_available())
return 0;
/*
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
* calling hibernate functions (which take system_transition_mutex)
* this can cause lockdep to complain about a possible ABBA deadlock
* which cannot happen since we're in the boot code here and
* sysfs can't be invoked yet. Therefore, we use a subclass
* here to avoid lockdep complaining.
*/
mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
if (swsusp_resume_device)
goto Check_image;
if (!strlen(resume_file)) {
error = -ENOENT;
goto Unlock;
}
pm_pr_dbg("Checking hibernation image partition %s\n", resume_file);
if (resume_delay) {
pr_info("Waiting %dsec before reading resume device ...\n",
resume_delay);
ssleep(resume_delay);
}
/* Check if the device is there */
swsusp_resume_device = name_to_dev_t(resume_file);
/*
* name_to_dev_t is ineffective to verify parition if resume_file is in
* integer format. (e.g. major:minor)
*/
if (isdigit(resume_file[0]) && resume_wait) {
int partno;
while (!get_gendisk(swsusp_resume_device, &partno))
msleep(10);
}
if (!swsusp_resume_device) {
/*
* Some device discovery might still be in progress; we need
* to wait for this to finish.
*/
wait_for_device_probe();
if (resume_wait) {
while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0)
msleep(10);
async_synchronize_full();
}
swsusp_resume_device = name_to_dev_t(resume_file);
if (!swsusp_resume_device) {
error = -ENODEV;
goto Unlock;
}
}
Check_image:
pm_pr_dbg("Hibernation image partition %d:%d present\n",
MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
pm_pr_dbg("Looking for hibernation image.\n");
error = swsusp_check();
if (error)
goto Unlock;
/* The snapshot device should not be opened while we're running */
if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
error = -EBUSY;
swsusp_close(FMODE_READ);
goto Unlock;
}
pr_info("resume from hibernation\n");
pm_prepare_console();
error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
if (error) {
nr_calls--;
goto Close_Finish;
}
pm_pr_dbg("Preparing processes for hibernation restore.\n");
error = freeze_processes();
if (error)
goto Close_Finish;
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
error = load_image_and_restore();
thaw_processes();
Finish:
__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
pm_restore_console();
pr_info("resume failed (%d)\n", error);
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
Unlock:
mutex_unlock(&system_transition_mutex);
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
swsusp_close(FMODE_READ);
goto Finish;
}
late_initcall_sync(software_resume);
static const char * const hibernation_modes[] = {
[HIBERNATION_PLATFORM] = "platform",
[HIBERNATION_SHUTDOWN] = "shutdown",
[HIBERNATION_REBOOT] = "reboot",
#ifdef CONFIG_SUSPEND
[HIBERNATION_SUSPEND] = "suspend",
#endif
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
[HIBERNATION_TEST_RESUME] = "test_resume",
};
/*
* /sys/power/disk - Control hibernation mode.
*
* Hibernation can be handled in several ways. There are a few different ways
* to put the system into the sleep state: using the platform driver (e.g. ACPI
* or other hibernation_ops), powering it off or rebooting it (for testing
* mostly).
*
* The sysfs file /sys/power/disk provides an interface for selecting the
* hibernation mode to use. Reading from this file causes the available modes
* to be printed. There are 3 modes that can be supported:
*
* 'platform'
* 'shutdown'
* 'reboot'
*
* If a platform hibernation driver is in use, 'platform' will be supported
* and will be used by default. Otherwise, 'shutdown' will be used by default.
* The selected option (i.e. the one corresponding to the current value of
* hibernation_mode) is enclosed by a square bracket.
*
* To select a given hibernation mode it is necessary to write the mode's
* string representation (as returned by reading from /sys/power/disk) back
* into /sys/power/disk.
*/
static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
int i;
char *start = buf;
if (!hibernation_available())
return sprintf(buf, "[disabled]\n");
for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
if (!hibernation_modes[i])
continue;
switch (i) {
case HIBERNATION_SHUTDOWN:
case HIBERNATION_REBOOT:
#ifdef CONFIG_SUSPEND
case HIBERNATION_SUSPEND:
#endif
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
case HIBERNATION_TEST_RESUME:
break;
case HIBERNATION_PLATFORM:
if (hibernation_ops)
break;
/* not a valid mode, continue with loop */
continue;
}
if (i == hibernation_mode)
buf += sprintf(buf, "[%s] ", hibernation_modes[i]);
else
buf += sprintf(buf, "%s ", hibernation_modes[i]);
}
buf += sprintf(buf, "\n");
return buf-start;
}
static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
int error = 0;
int i;
int len;
char *p;
int mode = HIBERNATION_INVALID;
if (!hibernation_available())
return -EPERM;
p = memchr(buf, '\n', n);
len = p ? p - buf : n;
lock_system_sleep();
for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
if (len == strlen(hibernation_modes[i])
&& !strncmp(buf, hibernation_modes[i], len)) {
mode = i;
break;
}
}
if (mode != HIBERNATION_INVALID) {
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 05:09:51 +07:00
switch (mode) {
case HIBERNATION_SHUTDOWN:
case HIBERNATION_REBOOT:
#ifdef CONFIG_SUSPEND
case HIBERNATION_SUSPEND:
#endif
PM / hibernate: Introduce test_resume mode for hibernation test_resume mode is to verify if the snapshot data written to swap device can be successfully restored to memory. It is useful to ease the debugging process on hibernation, since this mode can not only bypass the BIOSes/bootloader, but also the system re-initialization. To avoid the risk to break the filesystm on persistent storage, this patch resumes the image with tasks frozen. For example: echo test_resume > /sys/power/disk echo disk > /sys/power/state [ 187.306470] PM: Image saving progress: 70% [ 187.395298] PM: Image saving progress: 80% [ 187.476697] PM: Image saving progress: 90% [ 187.554641] PM: Image saving done. [ 187.558896] PM: Wrote 594600 kbytes in 0.90 seconds (660.66 MB/s) [ 187.566000] PM: S| [ 187.589742] PM: Basic memory bitmaps freed [ 187.594694] PM: Checking hibernation image [ 187.599865] PM: Image signature found, resuming [ 187.605209] PM: Loading hibernation image. [ 187.665753] PM: Basic memory bitmaps created [ 187.691397] PM: Using 3 thread(s) for decompression. [ 187.691397] PM: Loading and decompressing image data (148650 pages)... [ 187.889719] PM: Image loading progress: 0% [ 188.100452] PM: Image loading progress: 10% [ 188.244781] PM: Image loading progress: 20% [ 189.057305] PM: Image loading done. [ 189.068793] PM: Image successfully loaded Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-07-22 09:30:47 +07:00
case HIBERNATION_TEST_RESUME:
hibernation_mode = mode;
rework pm_ops pm_disk_mode, kill misuse This patch series cleans up some misconceptions about pm_ops. Some users of the pm_ops structure attempt to use it to stop the user from entering suspend to disk, this, however, is not possible since the user can always use "shutdown" in /sys/power/disk and then the pm_ops are never invoked. Also, platforms that don't support suspend to disk simply should not allow configuring SOFTWARE_SUSPEND (read the help text on it, it only selects suspend to disk and nothing else, all the other stuff depends on PM). The pm_ops structure is actually intended to provide a way to enter platform-defined sleep states (currently supported states are "standby" and "mem" (suspend to ram)) and additionally (if SOFTWARE_SUSPEND is configured) allows a platform to support a platform specific way to enter low-power mode once everything has been saved to disk. This is currently only used by ACPI (S4). This patch: The pm_ops.pm_disk_mode is used in totally bogus ways since nobody really seems to understand what it actually does. This patch clarifies the pm_disk_mode description. It also removes all the arm and sh users that think they can veto suspend to disk via pm_ops; not so since the user can always do echo shutdown > /sys/power/disk, they need to find a better way involving Kconfig or such. ACPI is the only user left with a non-zero pm_disk_mode. The patch also sets the default mode to shutdown again, but when a new pm_ops is registered its pm_disk_mode is selected as default, that way the default stays for ACPI where it is apparently required. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: David Brownell <david-b@pacbell.net> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: <linux-pm@lists.linux-foundation.org> Cc: Len Brown <lenb@kernel.org> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Greg KH <greg@kroah.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-01 05:09:51 +07:00
break;
case HIBERNATION_PLATFORM:
if (hibernation_ops)
hibernation_mode = mode;
else
error = -EINVAL;
}
} else
error = -EINVAL;
if (!error)
pm_pr_dbg("Hibernation mode set to '%s'\n",
hibernation_modes[mode]);
unlock_system_sleep();
return error ? error : n;
}
power_attr(disk);
static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device),
MINOR(swsusp_resume_device));
}
static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
dev_t res;
int len = n;
char *name;
if (len && buf[len-1] == '\n')
len--;
name = kstrndup(buf, len, GFP_KERNEL);
if (!name)
return -ENOMEM;
res = name_to_dev_t(name);
kfree(name);
if (!res)
return -EINVAL;
lock_system_sleep();
swsusp_resume_device = res;
unlock_system_sleep();
pm_pr_dbg("Configured hibernation resume from disk to %u\n",
swsusp_resume_device);
noresume = 0;
software_resume();
return n;
}
power_attr(resume);
static ssize_t resume_offset_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%llu\n", (unsigned long long)swsusp_resume_block);
}
static ssize_t resume_offset_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf,
size_t n)
{
unsigned long long offset;
int rc;
rc = kstrtoull(buf, 0, &offset);
if (rc)
return rc;
swsusp_resume_block = offset;
return n;
}
power_attr(resume_offset);
static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%lu\n", image_size);
}
static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
unsigned long size;
if (sscanf(buf, "%lu", &size) == 1) {
image_size = size;
return n;
}
return -EINVAL;
}
power_attr(image_size);
2011-05-15 16:38:48 +07:00
static ssize_t reserved_size_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%lu\n", reserved_size);
}
static ssize_t reserved_size_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t n)
{
unsigned long size;
if (sscanf(buf, "%lu", &size) == 1) {
reserved_size = size;
return n;
}
return -EINVAL;
}
power_attr(reserved_size);
static struct attribute * g[] = {
&disk_attr.attr,
&resume_offset_attr.attr,
&resume_attr.attr,
&image_size_attr.attr,
2011-05-15 16:38:48 +07:00
&reserved_size_attr.attr,
NULL,
};
static const struct attribute_group attr_group = {
.attrs = g,
};
static int __init pm_disk_init(void)
{
return sysfs_create_group(power_kobj, &attr_group);
}
core_initcall(pm_disk_init);
static int __init resume_setup(char *str)
{
if (noresume)
return 1;
strncpy( resume_file, str, 255 );
return 1;
}
static int __init resume_offset_setup(char *str)
{
unsigned long long offset;
if (noresume)
return 1;
if (sscanf(str, "%llu", &offset) == 1)
swsusp_resume_block = offset;
return 1;
}
static int __init hibernate_setup(char *str)
{
if (!strncmp(str, "noresume", 8)) {
noresume = 1;
} else if (!strncmp(str, "nocompress", 10)) {
nocompress = 1;
} else if (!strncmp(str, "no", 2)) {
noresume = 1;
nohibernate = 1;
} else if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)
&& !strncmp(str, "protect_image", 13)) {
enable_restore_image_protection();
}
return 1;
}
static int __init noresume_setup(char *str)
{
noresume = 1;
return 1;
}
static int __init resumewait_setup(char *str)
{
resume_wait = 1;
return 1;
}
static int __init resumedelay_setup(char *str)
{
int rc = kstrtouint(str, 0, &resume_delay);
if (rc)
return rc;
return 1;
}
static int __init nohibernate_setup(char *str)
{
noresume = 1;
nohibernate = 1;
return 1;
}
__setup("noresume", noresume_setup);
__setup("resume_offset=", resume_offset_setup);
__setup("resume=", resume_setup);
__setup("hibernate=", hibernate_setup);
__setup("resumewait", resumewait_setup);
__setup("resumedelay=", resumedelay_setup);
__setup("nohibernate", nohibernate_setup);