| Message ID | 20181016165513.7133-1-vkuznets@redhat.com (mailing list archive) |
|---|---|
| State | Superseded, archived |
| Headers | show |
| Series | [v3] kernel/hung_task.c: disable on suspend | expand |
On Tue, Oct 16, 2018 at 6:55 PM Vitaly Kuznetsov <vkuznets@redhat.com> wrote: > > It is possible to observe hung_task complaints when system goes to > suspend-to-idle state: > > # echo freeze > /sys/power/state > > PM: Syncing filesystems ... done. > Freezing user space processes ... (elapsed 0.001 seconds) done. > OOM killer disabled. > Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. > sd 0:0:0:0: [sda] Synchronizing SCSI cache > INFO: task bash:1569 blocked for more than 120 seconds. > Not tainted 4.19.0-rc3_+ #687 > "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. > bash D 0 1569 604 0x00000000 > Call Trace: > ? __schedule+0x1fe/0x7e0 > schedule+0x28/0x80 > suspend_devices_and_enter+0x4ac/0x750 > pm_suspend+0x2c0/0x310 > > Register a PM notifier to disable the detector on suspend and re-enable > back on wakeup. > > Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> > --- > Changes since v2: > - Resurrect 'v1' as zeroing timeouts can be racy [Rafael J. Wysocki] > --- > kernel/hung_task.c | 28 +++++++++++++++++++++++++++- > 1 file changed, 27 insertions(+), 1 deletion(-) > > diff --git a/kernel/hung_task.c b/kernel/hung_task.c > index b9132d1269ef..41955c5d8427 100644 > --- a/kernel/hung_task.c > +++ b/kernel/hung_task.c > @@ -15,6 +15,7 @@ > #include <linux/lockdep.h> > #include <linux/export.h> > #include <linux/sysctl.h> > +#include <linux/suspend.h> > #include <linux/utsname.h> > #include <linux/sched/signal.h> > #include <linux/sched/debug.h> > @@ -242,6 +243,26 @@ void reset_hung_task_detector(void) > } > EXPORT_SYMBOL_GPL(reset_hung_task_detector); > > +static bool hung_detector_suspended; > + > +static int hungtask_pm_notify(struct notifier_block *self, > + unsigned long action, void *hcpu) > +{ > + switch (action) { > + case PM_SUSPEND_PREPARE: > + case PM_HIBERNATION_PREPARE: Please add PM_RESTORE_PREPARE here -> > + hung_detector_suspended = true; > + break; > + case PM_POST_SUSPEND: > + case PM_POST_HIBERNATION: -> and PM_POST_RESTORE here for completeness. > + hung_detector_suspended = false; > + break; > + default: > + break; > + } > + return NOTIFY_OK; > +} > + > /* > * kthread which checks for tasks stuck in D state > */ > @@ -261,7 +282,8 @@ static int watchdog(void *dummy) > interval = min_t(unsigned long, interval, timeout); > t = hung_timeout_jiffies(hung_last_checked, interval); > if (t <= 0) { > - if (!atomic_xchg(&reset_hung_task, 0)) > + if (!atomic_xchg(&reset_hung_task, 0) && > + !hung_detector_suspended) > check_hung_uninterruptible_tasks(timeout); > hung_last_checked = jiffies; > continue; > @@ -275,6 +297,10 @@ static int watchdog(void *dummy) > static int __init hung_task_init(void) > { > atomic_notifier_chain_register(&panic_notifier_list, &panic_block); > + > + /* Disable hung task detector on suspend */ > + pm_notifier(hungtask_pm_notify, 0); > + > watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); > > return 0; > -- Apart from the above it is fine by me. This is the minimum fix for the issue at hand AFAICS. Thanks, Rafael
diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b9132d1269ef..41955c5d8427 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -15,6 +15,7 @@ #include <linux/lockdep.h> #include <linux/export.h> #include <linux/sysctl.h> +#include <linux/suspend.h> #include <linux/utsname.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> @@ -242,6 +243,26 @@ void reset_hung_task_detector(void) } EXPORT_SYMBOL_GPL(reset_hung_task_detector); +static bool hung_detector_suspended; + +static int hungtask_pm_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + hung_detector_suspended = true; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + hung_detector_suspended = false; + break; + default: + break; + } + return NOTIFY_OK; +} + /* * kthread which checks for tasks stuck in D state */ @@ -261,7 +282,8 @@ static int watchdog(void *dummy) interval = min_t(unsigned long, interval, timeout); t = hung_timeout_jiffies(hung_last_checked, interval); if (t <= 0) { - if (!atomic_xchg(&reset_hung_task, 0)) + if (!atomic_xchg(&reset_hung_task, 0) && + !hung_detector_suspended) check_hung_uninterruptible_tasks(timeout); hung_last_checked = jiffies; continue; @@ -275,6 +297,10 @@ static int watchdog(void *dummy) static int __init hung_task_init(void) { atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + /* Disable hung task detector on suspend */ + pm_notifier(hungtask_pm_notify, 0); + watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); return 0;
It is possible to observe hung_task complaints when system goes to suspend-to-idle state: # echo freeze > /sys/power/state PM: Syncing filesystems ... done. Freezing user space processes ... (elapsed 0.001 seconds) done. OOM killer disabled. Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. sd 0:0:0:0: [sda] Synchronizing SCSI cache INFO: task bash:1569 blocked for more than 120 seconds. Not tainted 4.19.0-rc3_+ #687 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. bash D 0 1569 604 0x00000000 Call Trace: ? __schedule+0x1fe/0x7e0 schedule+0x28/0x80 suspend_devices_and_enter+0x4ac/0x750 pm_suspend+0x2c0/0x310 Register a PM notifier to disable the detector on suspend and re-enable back on wakeup. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> --- Changes since v2: - Resurrect 'v1' as zeroing timeouts can be racy [Rafael J. Wysocki] --- kernel/hung_task.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-)