* [RFC][PATCH 1/3] Suspend: Testing facility (rev. 2)
2007-11-03 19:54 [RFC][PATCH 0/3] Suspend and hibernation test facility (rev. 2) Rafael J. Wysocki
@ 2007-11-03 19:56 ` Rafael J. Wysocki
2007-11-03 19:57 ` [RFC][PATCH 2/3] Hibernation: New testing " Rafael J. Wysocki
2007-11-03 19:58 ` [RFC][PATCH 3/3] PM: Suspend/hibernation debug documentation update " Rafael J. Wysocki
2 siblings, 0 replies; 5+ messages in thread
From: Rafael J. Wysocki @ 2007-11-03 19:56 UTC (permalink / raw)
To: pm list; +Cc: Johannes Berg, Len Brown, LKML, Pavel Machek
From: Rafael J. Wysocki <rjw@sisk.pl>
Introduce sysfs attribute /sys/power/pm_test allowing one to test the suspend
core code. Namely, writing one of the strings:
freezer
devices
platform
processors
core
to this file causes the suspend code to work in one of the test modes defined as
follows:
freezer - test the freezing of processes
devices - test the freezing of processes and suspending of devices
platform - test the freezing of processes, suspending of devices and platform
global control methods(*)
processors - test the freezing of processes, suspending of devices, platform
global control methods and the disabling of nonboot CPUs
core - test the freezing of processes, suspending of devices, platform global
control methods, the disabling of nonboot CPUs and suspending of
platform/system devices
(*) These are ACPI global control methods on ACPI systems
Then, if a suspend is started by normal means, the suspend core will perform
its normal operations up to the point indicated by given test level. Next, it
will wait for 5 seconds and carry out the resume operations needed to transition
the system back to the fully functional state.
Writing "none" to /sys/power/pm_test turns the testing off.
When open for reading, /sys/power/pm_test contains a space-separated list of all
available tests (including "none" that represents the normal functionality) in
which the current test level is indicated by square brackets.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
kernel/power/main.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++-----
kernel/power/power.h | 18 ++++++++
2 files changed, 118 insertions(+), 9 deletions(-)
Index: linux-2.6/kernel/power/main.c
===================================================================
--- linux-2.6.orig/kernel/power/main.c
+++ linux-2.6/kernel/power/main.c
@@ -31,6 +31,80 @@ DEFINE_MUTEX(pm_mutex);
unsigned int pm_flags;
EXPORT_SYMBOL(pm_flags);
+#ifdef CONFIG_PM_DEBUG
+int pm_test_level = TEST_NONE;
+
+static int suspend_test(int level)
+{
+ if (pm_test_level == level) {
+ printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+ mdelay(5000);
+ return 1;
+ }
+ return 0;
+}
+
+static const char * const pm_tests[__TEST_AFTER_LAST] = {
+ [TEST_NONE] = "none",
+ [TEST_CORE] = "core",
+ [TEST_CPUS] = "processors",
+ [TEST_PLATFORM] = "platform",
+ [TEST_DEVICES] = "devices",
+ [TEST_FREEZER] = "freezer",
+};
+
+static ssize_t pm_test_show(struct kset *kset, char *buf)
+{
+ char *s = buf;
+ int level;
+
+ for (level = TEST_FIRST; level <= TEST_MAX; level++)
+ if (pm_tests[level]) {
+ if (level == pm_test_level)
+ s += sprintf(s, "[%s] ", pm_tests[level]);
+ else
+ s += sprintf(s, "%s ", pm_tests[level]);
+ }
+
+ if (s != buf)
+ /* convert the last space to a newline */
+ *(s-1) = '\n';
+
+ return (s - buf);
+}
+
+static ssize_t pm_test_store(struct kset *kset, const char *buf, size_t n)
+{
+ const char * const *s;
+ int level;
+ char *p;
+ int len;
+ int error = -EINVAL;
+
+ p = memchr(buf, '\n', n);
+ len = p ? p - buf : n;
+
+ mutex_lock(&pm_mutex);
+
+ level = TEST_FIRST;
+ for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
+ if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
+ pm_test_level = level;
+ error = 0;
+ break;
+ }
+
+ mutex_unlock(&pm_mutex);
+
+ return error ? error : n;
+}
+
+power_attr(pm_test);
+#else /* !CONFIG_PM_DEBUG */
+static inline int suspend_test(int level) { return 0; }
+#endif /* !CONFIG_PM_DEBUG */
+
+
#ifdef CONFIG_SUSPEND
/* This is just an arbitrary number */
@@ -136,7 +210,10 @@ static int suspend_enter(suspend_state_t
printk(KERN_ERR "Some devices failed to power down\n");
goto Done;
}
- error = suspend_ops->enter(state);
+
+ if (!suspend_test(TEST_CORE))
+ error = suspend_ops->enter(state);
+
device_power_up();
Done:
arch_suspend_enable_irqs();
@@ -167,16 +244,25 @@ int suspend_devices_and_enter(suspend_st
printk(KERN_ERR "Some devices failed to suspend\n");
goto Resume_console;
}
+
+ if (suspend_test(TEST_DEVICES))
+ goto Resume_devices;
+
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
goto Resume_devices;
}
+
+ if (suspend_test(TEST_PLATFORM))
+ goto Finish;
+
error = disable_nonboot_cpus();
- if (!error)
+ if (!error && !suspend_test(TEST_CPUS))
suspend_enter(state);
enable_nonboot_cpus();
+ Finish:
if (suspend_ops->finish)
suspend_ops->finish();
Resume_devices:
@@ -243,12 +329,17 @@ static int enter_state(suspend_state_t s
printk("done.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
- if ((error = suspend_prepare()))
+ error = suspend_prepare();
+ if (error)
goto Unlock;
+ if (suspend_test(TEST_FREEZER))
+ goto Finish;
+
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state);
+ Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
@@ -366,18 +457,18 @@ pm_trace_store(struct kset *kset, const
}
power_attr(pm_trace);
+#endif /* CONFIG_PM_TRACE */
static struct attribute * g[] = {
&state_attr.attr,
+#ifdef CONFIG_PM_TRACE
&pm_trace_attr.attr,
+#endif
+#ifdef CONFIG_PM_DEBUG
+ &pm_test_attr.attr,
+#endif
NULL,
};
-#else
-static struct attribute * g[] = {
- &state_attr.attr,
- NULL,
-};
-#endif /* CONFIG_PM_TRACE */
static struct attribute_group attr_group = {
.attrs = g,
Index: linux-2.6/kernel/power/power.h
===================================================================
--- linux-2.6.orig/kernel/power/power.h
+++ linux-2.6/kernel/power/power.h
@@ -190,3 +190,21 @@ int restore_highmem(void);
static inline unsigned int count_highmem_pages(void) { return 0; }
static inline int restore_highmem(void) { return 0; }
#endif
+
+/*
+ * Suspend test levels
+ */
+enum {
+ /* keep first */
+ TEST_NONE,
+ TEST_CORE,
+ TEST_CPUS,
+ TEST_PLATFORM,
+ TEST_DEVICES,
+ TEST_FREEZER,
+ /* keep last */
+ __TEST_AFTER_LAST
+};
+
+#define TEST_FIRST TEST_NONE
+#define TEST_MAX (__TEST_AFTER_LAST - 1)
^ permalink raw reply [flat|nested] 5+ messages in thread* [RFC][PATCH 3/3] PM: Suspend/hibernation debug documentation update (rev. 2)
2007-11-03 19:54 [RFC][PATCH 0/3] Suspend and hibernation test facility (rev. 2) Rafael J. Wysocki
2007-11-03 19:56 ` [RFC][PATCH 1/3] Suspend: Testing " Rafael J. Wysocki
2007-11-03 19:57 ` [RFC][PATCH 2/3] Hibernation: New testing " Rafael J. Wysocki
@ 2007-11-03 19:58 ` Rafael J. Wysocki
[not found] ` <E1IoPIE-0005qK-9U@faramir.fjphome.nl>
2 siblings, 1 reply; 5+ messages in thread
From: Rafael J. Wysocki @ 2007-11-03 19:58 UTC (permalink / raw)
To: pm list; +Cc: Johannes Berg, Len Brown, LKML, Pavel Machek
From: Rafael J. Wysocki <rjw@sisk.pl>
Update the suspend/hibernation debugging and testing documentation to describe
the newly introduced testing facilities.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
Documentation/power/basic-pm-debugging.txt | 203 ++++++++++++++++++++---------
Documentation/power/drivers-testing.txt | 30 ++--
2 files changed, 163 insertions(+), 70 deletions(-)
Index: linux-2.6/Documentation/power/drivers-testing.txt
===================================================================
--- linux-2.6.orig/Documentation/power/drivers-testing.txt
+++ linux-2.6/Documentation/power/drivers-testing.txt
@@ -6,9 +6,9 @@ Testing suspend and resume support in de
Unfortunately, to effectively test the support for the system-wide suspend and
resume transitions in a driver, it is necessary to suspend and resume a fully
functional system with this driver loaded. Moreover, that should be done
-several times, preferably several times in a row, and separately for the suspend
-to disk (STD) and the suspend to RAM (STR) transitions, because each of these
-cases involves different ordering of operations and different interactions with
+several times, preferably several times in a row, and separately for hibernation
+(aka suspend to disk or STD) and suspend to RAM (STR), because each of these
+cases involves slightly different operations and different interactions with
the machine's BIOS.
Of course, for this purpose the test system has to be known to suspend and
@@ -22,20 +22,24 @@ for more information about the debugging
Once you have resolved the suspend/resume-related problems with your test system
without the new driver, you are ready to test it:
-a) Build the driver as a module, load it and try the STD in the test mode (see:
-Documents/power/basic-pm-debugging.txt, 1a)).
+a) Build the driver as a module, load it and try the test modes of hibernation
+ (see: Documents/power/basic-pm-debugging.txt, 1).
-b) Load the driver and attempt to suspend to disk in the "reboot", "shutdown"
-and "platform" modes (see: Documents/power/basic-pm-debugging.txt, 1).
+b) Load the driver and attempt to hibernate in the "reboot", "shutdown" and
+ "platform" modes (see: Documents/power/basic-pm-debugging.txt, 1).
-c) Compile the driver directly into the kernel and try the STD in the test mode.
+c) Compile the driver directly into the kernel and try the test modes of
+ hibernation.
-d) Attempt to suspend to disk with the driver compiled directly into the kernel
-in the "reboot", "shutdown" and "platform" modes.
+d) Attempt to hibernate with the driver compiled directly into the kernel
+ in the "reboot", "shutdown" and "platform" modes.
-e) Attempt to suspend to RAM using the s2ram tool with the driver loaded (see:
-Documents/power/basic-pm-debugging.txt, 2). As far as the STR tests are
-concerned, it should not matter whether or not the driver is built as a module.
+e) Try the test modes of suspend (see: Documents/power/basic-pm-debugging.txt,
+ 2). [As far as the STR tests are concerned, it should not matter whether or
+ not the driver is built as a module.]
+
+f) Attempt to suspend to RAM using the s2ram tool with the driver loaded
+ (see: Documents/power/basic-pm-debugging.txt, 2).
Each of the above tests should be repeated several times and the STD tests
should be mixed with the STR tests. If any of them fails, the driver cannot be
Index: linux-2.6/Documentation/power/basic-pm-debugging.txt
===================================================================
--- linux-2.6.orig/Documentation/power/basic-pm-debugging.txt
+++ linux-2.6/Documentation/power/basic-pm-debugging.txt
@@ -1,45 +1,102 @@
-Debugging suspend and resume
+Debugging hibernation and suspend
(C) 2007 Rafael J. Wysocki <rjw@sisk.pl>, GPL
-1. Testing suspend to disk (STD)
+1. Testing hibernation (aka suspend to disk or STD)
-To verify that the STD works, you can try to suspend in the "reboot" mode:
+To check if hibernation works, you can try to hibernate in the "reboot" mode:
# echo reboot > /sys/power/disk
# echo disk > /sys/power/state
-and the system should suspend, reboot, resume and get back to the command prompt
-where you have started the transition. If that happens, the STD is most likely
-to work correctly, but you need to repeat the test at least a couple of times in
-a row for confidence. This is necessary, because some problems only show up on
-a second attempt at suspending and resuming the system. You should also test
-the "platform" and "shutdown" modes of suspend:
+and the system should create a hibernation image, reboot, resume and get back to
+the command prompt where you have started the transition. If that happens,
+hibernation is most likely to work correctly. Still, you need to repeat the
+test at least a couple of times in a row for confidence. [This is necessary,
+because some problems only show up on a second attempt at suspending and
+resuming the system.] Moreover, hibernating in the "reboot" and "shutdown"
+modes causes the PM core to skip some platform-related callbacks which on ACPI
+systems might be necessary to make hibernation work. Thus, if you machine fails
+to hibernate or resume in the "reboot" mode, you should try the "platform" mode:
# echo platform > /sys/power/disk
# echo disk > /sys/power/state
-or
+which is the default and recommended mode of hibernation.
+
+Unfortunately, the "platform" mode of hibernation does not work on some systems
+with broken BIOSes. In such cases the "shutdown" mode of hibernation might
+work:
# echo shutdown > /sys/power/disk
# echo disk > /sys/power/state
-in which cases you will have to press the power button to make the system
-resume. If that does not work, you will need to identify what goes wrong.
+(it is similar to the "reboot" mode, but it requires you to press the power
+button to make the system resume).
+
+If neither "platform" nor "shutdown" hibernation mode works, you will need to
+identify what goes wrong.
-a) Test mode of STD
+a) Test modes of hibernation
-To verify if there are any drivers that cause problems you can run the STD
-in the test mode:
+To find out why hibernation fails on your system, you can use a special testing
+facility available if the kernel is compiled with CONFIG_PM_DEBUG set. Then,
+there is the file /sys/power/pm_test that can be used to make the hibernation
+core run in a test mode. There are 5 test modes available:
+
+freezer - test the freezing of processes
+devices - test the freezing of processes and suspending of devices
+platform - test the freezing of processes, suspending of devices and platform
+ global control methods(*)
+processors - test the freezing of processes, suspending of devices, platform
+ global control methods(*) and the disabling of nonboot CPUs
+core - test the freezing of processes, suspending of devices, platform global
+ control methods(*), the disabling of nonboot CPUs and suspending of
+ platform/system devices
+
+(*) - the platform global control methods are only available on ACPI systems
+ and are only tested if the hibernation mode is set to "platform"
+
+To use one of them it is necessary to write the corresponding string to
+/sys/power/pm_test (eg. "devices" to test the freezing of processes and
+suspending devices) and issue the standard hibernation commands. For example,
+to use the "devices" test mode along with the "platform" mode of hibernation,
+you should do the following:
-# echo test > /sys/power/disk
+# echo devices > /sys/power/pm_test
+# echo platform > /sys/power/disk
# echo disk > /sys/power/state
-in which case the system should freeze tasks, suspend devices, disable nonboot
-CPUs (if any), wait for 5 seconds, enable nonboot CPUs, resume devices, thaw
-tasks and return to your command prompt. If that fails, most likely there is
-a driver that fails to either suspend or resume (in the latter case the system
-may hang or be unstable after the test, so please take that into consideration).
-To find this driver, you can carry out a binary search according to the rules:
+Then, the kernel will try to freeze processes, suspend devices, wait 5 seconds,
+resume devices and thaw processes. If "platform" is written to
+/sys/power/pm_test , then after suspending devices the kernel will additionally
+invoke the global control methods (eg. ACPI global control methods) used to
+prepare the platform firmware for hibernation. Next, it will wait 5 seconds and
+invoke the platform (eg. ACPI) global methods used to cancel hibernation etc.
+
+Writing "none" to /sys/power/pm_test causes the kernel to switch to the normal
+hibernation/suspend operations. Also, when open for reading, /sys/power/pm_test
+contains a space-separated list of all available tests (including "none" that
+represents the normal functionality) in which the current test level is
+indicated by square brackets.
+
+Generally, as you can see, each test level is more "invasive" than the previous
+one and the "core" level tests the hardware and drivers as deeply as possible
+without creating a hibernation image. Obviously, if the "devices" test fails,
+the "platform" test will fail as well and so on. Thus, as a rule of thumb, you
+should try the test modes starting from "freezer", through "devices", "platform"
+and "processors" up to "core" (repeat the test on each level a couple of times
+to make sure that any random factors are avoided).
+
+If the "freezer" test fails, there is a task that cannot be frozen (in that case
+it usually is possible to identify the offending task by analysing the output of
+dmesg obtained after the failing test). Failure at this level usually means
+that there is a problem with the tasks freezer subsystem that should be
+reported.
+
+If the "devices" test fails, most likely there is a driver that cannot suspend
+or resume its device (in the latter case the system may hang or become unstable
+after the test, so please take that into consideration). To find this driver,
+you can carry out a binary search according to the rules:
- if the test fails, unload a half of the drivers currently loaded and repeat
(that would probably involve rebooting the system, so always note what drivers
have been loaded before the test),
@@ -47,23 +104,46 @@ have been loaded before the test),
recently and repeat.
Once you have found the failing driver (there can be more than just one of
-them), you have to unload it every time before the STD transition. In that case
-please make sure to report the problem with the driver.
+them), you have to unload it every time before hibernation. In that case please
+make sure to report the problem with the driver.
-It is also possible that a cycle can still fail after you have unloaded
-all modules. In that case, you would want to look in your kernel configuration
-for the drivers that can be compiled as modules (testing again with them as
-modules), and possibly also try boot time options such as "noapic" or "noacpi".
+It is also possible that the "devices" test will still fail after you have
+unloaded all modules. In that case, you may want to look in your kernel
+configuration for the drivers that can be compiled as modules (and test again
+with these drivers compiled as modules). You may also try to use some special
+kernel command line options such as "noapic", "noacpi" or even "acpi=off".
+
+If the "platform" test fails, there is a problem with the handling of the
+platform (eg. ACPI) firmware on your system. In that case the "platform" mode
+of hibernation is not likely to work. You can try the "shutdown" mode, but that
+is rather a poor man's workaround.
+
+If the "processors" test fails, the disabling/enabling of nonboot CPUs does not
+work (of course, this only may be an issue on SMP systems) and the problem
+should be reported. In that case you can also try to switch the nonboot CPUs
+off and on using the /sys/devices/system/cpu/cpu*/online sysfs attributes and
+see if that works.
+
+If the "core" test fails, which means that suspending of the system/platform
+devices has failed (these devices are suspended on one CPU with interrupts off),
+the problem is most probably hardware-related and serious, so it should be
+reported.
+
+A failure of any of the "platform", "processors" or "core" tests may cause your
+system to hang or become unstable, so please beware. Such a failure usually
+indicates a serious problem that very well may be related to the hardware, but
+please report it anyway.
b) Testing minimal configuration
-If the test mode of STD works, you can boot the system with "init=/bin/bash"
-and attempt to suspend in the "reboot", "shutdown" and "platform" modes. If
-that does not work, there probably is a problem with a driver statically
-compiled into the kernel and you can try to compile more drivers as modules,
-so that they can be tested individually. Otherwise, there is a problem with a
-modular driver and you can find it by loading a half of the modules you normally
-use and binary searching in accordance with the algorithm:
+If all of the hibernation test modes work, you can boot the system with the
+"init=/bin/bash" command line parameter and attempt to hibernate in the
+"reboot", "shutdown" and "platform" modes. If that does not work, there
+probably is a problem with a driver statically compiled into the kernel and you
+can try to compile more drivers as modules, so that they can be tested
+individually. Otherwise, there is a problem with a modular driver and you can
+find it by loading a half of the modules you normally use and binary searching
+in accordance with the algorithm:
- if there are n modules loaded and the attempt to suspend and resume fails,
unload n/2 of the modules and try again (that would probably involve rebooting
the system),
@@ -71,19 +151,19 @@ the system),
load n/2 modules more and try again.
Again, if you find the offending module(s), it(they) must be unloaded every time
-before the STD transition, and please report the problem with it(them).
+before hibernation, and please report the problem with it(them).
c) Advanced debugging
-In case the STD does not work on your system even in the minimal configuration
-and compiling more drivers as modules is not practical or some modules cannot
-be unloaded, you can use one of the more advanced debugging techniques to find
-the problem. First, if there is a serial port in your box, you can boot the
-kernel with the 'no_console_suspend' parameter and try to log kernel
-messages using the serial console. This may provide you with some information
-about the reasons of the suspend (resume) failure. Alternatively, it may be
-possible to use a FireWire port for debugging with firescope
-(ftp://ftp.firstfloor.org/pub/ak/firescope/). On i386 it is also possible to
+In case that hibernation does not work on your system even in the minimal
+configuration and compiling more drivers as modules is not practical or some
+modules cannot be unloaded, you can use one of the more advanced debugging
+techniques to find the problem. First, if there is a serial port in your box,
+you can boot the kernel with the 'no_console_suspend' parameter and try to log
+kernel messages using the serial console. This may provide you with some
+information about the reasons of the suspend (resume) failure. Alternatively,
+it may be possible to use a FireWire port for debugging with firescope
+(ftp://ftp.firstfloor.org/pub/ak/firescope/). On x86 it is also possible to
use the PM_TRACE mechanism documented in Documentation/s2ram.txt .
2. Testing suspend to RAM (STR)
@@ -91,16 +171,25 @@ use the PM_TRACE mechanism documented in
To verify that the STR works, it is generally more convenient to use the s2ram
tool available from http://suspend.sf.net and documented at
http://en.opensuse.org/s2ram . However, before doing that it is recommended to
-carry out the procedure described in section 1.
+carry out STR testing using the facility described in section 1.
-Assume you have resolved the problems with the STD and you have found some
-failing drivers. These drivers are also likely to fail during the STR or
-during the resume, so it is better to unload them every time before the STR
-transition. Now, you can follow the instructions at
-http://en.opensuse.org/s2ram to test the system, but if it does not work
-"out of the box", you may need to boot it with "init=/bin/bash" and test
-s2ram in the minimal configuration. In that case, you may be able to search
-for failing drivers by following the procedure analogous to the one described in
-1b). If you find some failing drivers, you will have to unload them every time
-before the STR transition (ie. before you run s2ram), and please report the
-problems with them.
+Namely, after writing "freezer", "devices", "platform", "processors", or "core"
+into /sys/power/pm_test (available if the kernel is compiled with
+CONFIG_PM_DEBUG set) the suspend code will work in the test mode corresponding
+to given string. The STR test modes are defined in the same way as for
+hibernation, so please refer to Section 1 for more information about them. In
+particular, the "core" test allows you to test everything except for the actual
+invocation of the platform firmware in order to put the system into the sleep
+state.
+
+Among other things, the testing with the help of /sys/power/pm_test may allow
+you to identify drivers that fail to suspend or resume their devices. They
+should be unloaded every time before an STR transition.
+
+Next, you can follow the instructions at http://en.opensuse.org/s2ram to test
+the system, but if it does not work "out of the box", you may need to boot it
+with "init=/bin/bash" and test s2ram in the minimal configuration. In that
+case, you may be able to search for failing drivers by following the procedure
+analogous to the one described in section 1. If you find some failing drivers,
+you will have to unload them every time before an STR transition (ie. before
+you run s2ram), and please report the problems with them.
^ permalink raw reply [flat|nested] 5+ messages in thread