From 84d56e66b9b4a646f04ec30696ca1aeea5e654d5 Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:43:55 -0700 Subject: watchdog: new definitions and variables, initialization The hardlockup and softockup had always been tied together. Due to the request of KVM folks, they had a need to have one enabled but not the other. Internally rework the code to split things apart more cleanly. There is a bunch of churn here, but the end result should be code that should be easier to maintain and fix without knowing the internals of what is going on. This patch (of 9): Introduce new definitions and variables to separate the user interface in /proc/sys/kernel from the internal run state of the lockup detectors. The internal run state is represented by two bits in a new variable that is named 'watchdog_enabled'. This helps simplify the code, for example: - In order to check if any of the two lockup detectors is enabled, it is sufficient to check if 'watchdog_enabled' is not zero. - In order to enable/disable one or both lockup detectors, it is sufficient to set/clear one or both bits in 'watchdog_enabled'. - Concurrent updates of 'watchdog_enabled' need not be synchronized via a spinlock or a mutex. Updates can either be atomic or concurrency can be detected by using 'cmpxchg'. Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/nmi.h') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 9b2022ab4d85..3885a7d12bd2 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -68,6 +68,8 @@ static inline bool trigger_allbutself_cpu_backtrace(void) #ifdef CONFIG_LOCKUP_DETECTOR int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(int watchdog_thresh); +extern int nmi_watchdog_enabled; +extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern int sysctl_softlockup_all_cpu_backtrace; -- cgit v1.2.3 From 83a80a39075a9ded23df1e26a4b617c289077630 Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:44:08 -0700 Subject: watchdog: introduce separate handlers for parameters in /proc/sys/kernel Separate handlers for each watchdog parameter in /proc/sys/kernel replace the proc_dowatchdog() function. Three of those handlers merely call proc_watchdog_common() with one different argument. Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 8 ++++++++ kernel/watchdog.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include/linux/nmi.h') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 3885a7d12bd2..5b5450585b8a 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -74,6 +74,14 @@ extern int watchdog_user_enabled; extern int watchdog_thresh; extern int sysctl_softlockup_all_cpu_backtrace; struct ctl_table; +extern int proc_watchdog(struct ctl_table *, int , + void __user *, size_t *, loff_t *); +extern int proc_nmi_watchdog(struct ctl_table *, int , + void __user *, size_t *, loff_t *); +extern int proc_soft_watchdog(struct ctl_table *, int , + void __user *, size_t *, loff_t *); +extern int proc_watchdog_thresh(struct ctl_table *, int , + void __user *, size_t *, loff_t *); extern int proc_dowatchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 3600a01c97a9..26002ed4c16e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -768,6 +768,65 @@ out: return err; } +/* + * /proc/sys/kernel/watchdog + */ +int proc_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/nmi_watchdog + */ +int proc_nmi_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/soft_watchdog + */ +int proc_soft_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/watchdog_thresh + */ +int proc_watchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err, old; + + mutex_lock(&watchdog_proc_mutex); + + old = ACCESS_ONCE(watchdog_thresh); + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (err || !write) + goto out; + + /* + * Update the sample period. + * Restore 'watchdog_thresh' on failure. + */ + set_sample_period(); + err = proc_watchdog_update(); + if (err) + watchdog_thresh = old; +out: + mutex_unlock(&watchdog_proc_mutex); + return err; +} + /* * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ -- cgit v1.2.3 From 195daf665a6299de98a4da3843fed2dd9de19d3a Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:44:13 -0700 Subject: watchdog: enable the new user interface of the watchdog mechanism With the current user interface of the watchdog mechanism it is only possible to disable or enable both lockup detectors at the same time. This series introduces new kernel parameters and changes the semantics of some existing kernel parameters, so that the hard lockup detector and the soft lockup detector can be disabled or enabled individually. With this series applied, the user interface is as follows. - parameters in /proc/sys/kernel . soft_watchdog This is a new parameter to control and examine the run state of the soft lockup detector. . nmi_watchdog The semantics of this parameter have changed. It can now be used to control and examine the run state of the hard lockup detector. . watchdog This parameter is still available to control the run state of both lockup detectors at the same time. If this parameter is examined, it shows the logical OR of soft_watchdog and nmi_watchdog. . watchdog_thresh The semantics of this parameter are not affected by the patch. - kernel command line parameters . nosoftlockup The semantics of this parameter have changed. It can now be used to disable the soft lockup detector at boot time. . nmi_watchdog=0 or nmi_watchdog=1 Disable or enable the hard lockup detector at boot time. The patch introduces '=1' as a new option. . nowatchdog The semantics of this parameter are not affected by the patch. It is still available to disable both lockup detectors at boot time. Also, remove the proc_dowatchdog() function which is no longer needed. [dzickus@redhat.com: wrote changelog] [dzickus@redhat.com: update documentation for kernel params and sysctl] Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 6 ++- Documentation/sysctl/kernel.txt | 62 +++++++++++++++++++++++----- include/linux/nmi.h | 2 - kernel/sysctl.c | 35 +++++++++++----- kernel/watchdog.c | 81 ++++++++----------------------------- 5 files changed, 97 insertions(+), 89 deletions(-) (limited to 'include/linux/nmi.h') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 01aa47d3b6ab..71eecb263250 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2236,8 +2236,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels Format: [panic,][nopanic,][num] - Valid num: 0 + Valid num: 0 or 1 0 - turn nmi_watchdog off + 1 - turn nmi_watchdog on When panic is specified, panic when an NMI watchdog timeout occurs (or 'nopanic' to override the opposite default). @@ -2464,7 +2465,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nousb [USB] Disable the USB subsystem - nowatchdog [KNL] Disable the lockup detector (NMI watchdog). + nowatchdog [KNL] Disable both lockup detectors, i.e. + soft-lockup and NMI watchdog (hard-lockup). nowb [ARM] diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 83ab25660fc9..99d7eb3a1416 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -77,12 +77,14 @@ show up in /proc/sys/kernel: - shmmax [ sysv ipc ] - shmmni - softlockup_all_cpu_backtrace +- soft_watchdog - stop-a [ SPARC only ] - sysrq ==> Documentation/sysrq.txt - sysctl_writes_strict - tainted - threads-max - unknown_nmi_panic +- watchdog - watchdog_thresh - version @@ -417,16 +419,23 @@ successful IPC object allocation. nmi_watchdog: -Enables/Disables the NMI watchdog on x86 systems. When the value is -non-zero the NMI watchdog is enabled and will continuously test all -online cpus to determine whether or not they are still functioning -properly. Currently, passing "nmi_watchdog=" parameter at boot time is -required for this function to work. +This parameter can be used to control the NMI watchdog +(i.e. the hard lockup detector) on x86 systems. -If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel -parameter), the NMI watchdog shares registers with oprofile. By -disabling the NMI watchdog, oprofile may have more registers to -utilize. + 0 - disable the hard lockup detector + 1 - enable the hard lockup detector + +The hard lockup detector monitors each CPU for its ability to respond to +timer interrupts. The mechanism utilizes CPU performance counter registers +that are programmed to generate Non-Maskable Interrupts (NMIs) periodically +while a CPU is busy. Hence, the alternative name 'NMI watchdog'. + +The NMI watchdog is disabled by default if the kernel is running as a guest +in a KVM virtual machine. This default can be overridden by adding + + nmi_watchdog=1 + +to the guest kernel command line (see Documentation/kernel-parameters.txt). ============================================================== @@ -816,6 +825,22 @@ NMI. ============================================================== +soft_watchdog + +This parameter can be used to control the soft lockup detector. + + 0 - disable the soft lockup detector + 1 - enable the soft lockup detector + +The soft lockup detector monitors CPUs for threads that are hogging the CPUs +without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads +from running. The mechanism depends on the CPUs ability to respond to timer +interrupts which are needed for the 'watchdog/N' threads to be woken up by +the watchdog timer function, otherwise the NMI watchdog - if enabled - can +detect a hard lockup condition. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which @@ -858,6 +883,25 @@ example. If a system hangs up, try pressing the NMI switch. ============================================================== +watchdog: + +This parameter can be used to disable or enable the soft lockup detector +_and_ the NMI watchdog (i.e. the hard lockup detector) at the same time. + + 0 - disable both lockup detectors + 1 - enable both lockup detectors + +The soft lockup detector and the NMI watchdog can also be disabled or +enabled individually, using the soft_watchdog and nmi_watchdog parameters. +If the watchdog parameter is read, for example by executing + + cat /proc/sys/kernel/watchdog + +the output of this command (0 or 1) shows the logical OR of soft_watchdog +and nmi_watchdog. + +============================================================== + watchdog_thresh: This value can be used to control the frequency of hrtimer and NMI diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 5b5450585b8a..0426357297d5 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -82,8 +82,6 @@ extern int proc_soft_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); -extern int proc_dowatchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); #endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ce410bb9f2e1..245e7dcc3741 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -846,7 +846,7 @@ static struct ctl_table kern_table[] = { .data = &watchdog_user_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, }, @@ -855,10 +855,32 @@ static struct ctl_table kern_table[] = { .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog_thresh, .extra1 = &zero, .extra2 = &sixty, }, + { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_nmi_watchdog, + .extra1 = &zero, +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) + .extra2 = &one, +#else + .extra2 = &zero, +#endif + }, + { + .procname = "soft_watchdog", + .data = &soft_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = &zero, + .extra2 = &one, + }, { .procname = "softlockup_panic", .data = &softlockup_panic, @@ -879,15 +901,6 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif /* CONFIG_SMP */ - { - .procname = "nmi_watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dowatchdog, - .extra1 = &zero, - .extra2 = &one, - }, #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index fd2b6dc14486..63d702885686 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -110,15 +110,9 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_user_enabled = 0; - else if (!strncmp(str, "1", 1) || !strncmp(str, "2", 1)) { - /* - * Setting 'nmi_watchdog=1' or 'nmi_watchdog=2' (legacy option) - * has the same effect. - */ - watchdog_user_enabled = 1; - watchdog_enable_hardlockup_detector(true); - } + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -137,19 +131,18 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_user_enabled = 0; + watchdog_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); -/* deprecated */ static int __init nosoftlockup_setup(char *str) { - watchdog_user_enabled = 0; + watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; return 1; } __setup("nosoftlockup", nosoftlockup_setup); -/* */ + #ifdef CONFIG_SMP static int __init softlockup_all_cpu_backtrace_setup(char *str) { @@ -264,10 +257,11 @@ static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); - /* Warn about unreasonable delays: */ - if (time_after(now, touch_ts + get_softlockup_thresh())) - return now - touch_ts; - + if (watchdog_enabled & SOFT_WATCHDOG_ENABLED) { + /* Warn about unreasonable delays. */ + if (time_after(now, touch_ts + get_softlockup_thresh())) + return now - touch_ts; + } return 0; } @@ -532,6 +526,10 @@ static int watchdog_nmi_enable(unsigned int cpu) struct perf_event_attr *wd_attr; struct perf_event *event = per_cpu(watchdog_ev, cpu); + /* nothing to do if the hard lockup detector is disabled */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + goto out; + /* * Some kernels need to default hard lockup detection to * 'disabled', for example a guest on a hypervisor. @@ -856,59 +854,12 @@ out: mutex_unlock(&watchdog_proc_mutex); return err; } - -/* - * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh - */ - -int proc_dowatchdog(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int err, old_thresh, old_enabled; - bool old_hardlockup; - - mutex_lock(&watchdog_proc_mutex); - old_thresh = ACCESS_ONCE(watchdog_thresh); - old_enabled = ACCESS_ONCE(watchdog_user_enabled); - old_hardlockup = watchdog_hardlockup_detector_is_enabled(); - - err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - set_sample_period(); - /* - * Watchdog threads shouldn't be enabled if they are - * disabled. The 'watchdog_running' variable check in - * watchdog_*_all_cpus() function takes care of this. - */ - if (watchdog_user_enabled && watchdog_thresh) { - /* - * Prevent a change in watchdog_thresh accidentally overriding - * the enablement of the hardlockup detector. - */ - if (watchdog_user_enabled != old_enabled) - watchdog_enable_hardlockup_detector(true); - err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh); - } else - watchdog_disable_all_cpus(); - - /* Restore old values on failure */ - if (err) { - watchdog_thresh = old_thresh; - watchdog_user_enabled = old_enabled; - watchdog_enable_hardlockup_detector(old_hardlockup); - } -out: - mutex_unlock(&watchdog_proc_mutex); - return err; -} #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { set_sample_period(); - if (watchdog_user_enabled) + if (watchdog_enabled) watchdog_enable_all_cpus(false); } -- cgit v1.2.3 From 692297d8f96887f836d9049a653ed05a71cf48fb Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:44:19 -0700 Subject: watchdog: introduce the hardlockup_detector_disable() function Have kvm_guest_init() use hardlockup_detector_disable() instead of watchdog_enable_hardlockup_detector(false). Remove the watchdog_hardlockup_detector_is_enabled() and the watchdog_enable_hardlockup_detector() function which are no longer needed. Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/kvm.c | 2 +- include/linux/nmi.h | 9 ++------- kernel/watchdog.c | 21 ++------------------- 3 files changed, 5 insertions(+), 27 deletions(-) (limited to 'include/linux/nmi.h') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e354cc6446ab..9435620062df 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -513,7 +513,7 @@ void __init kvm_guest_init(void) * can get false positives too easily, for example if the host is * overcommitted. */ - watchdog_enable_hardlockup_detector(false); + hardlockup_detector_disable(); } static noinline uint32_t __kvm_cpuid_base(void) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0426357297d5..3d46fb4708e0 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -25,16 +25,11 @@ static inline void touch_nmi_watchdog(void) #endif #if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void watchdog_enable_hardlockup_detector(bool val); -extern bool watchdog_hardlockup_detector_is_enabled(void); +extern void hardlockup_detector_disable(void); #else -static inline void watchdog_enable_hardlockup_detector(bool val) +static inline void hardlockup_detector_disable(void) { } -static inline bool watchdog_hardlockup_detector_is_enabled(void) -{ - return true; -} #endif /* diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 49d02250aaac..f2be11ab7e08 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -83,8 +83,6 @@ static unsigned long soft_lockup_nmi_warn; #ifdef CONFIG_HARDLOCKUP_DETECTOR static int hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; - -static bool hardlockup_detector_enabled = true; /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these @@ -93,14 +91,9 @@ static bool hardlockup_detector_enabled = true; * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void watchdog_enable_hardlockup_detector(bool val) -{ - hardlockup_detector_enabled = val; -} - -bool watchdog_hardlockup_detector_is_enabled(void) +void hardlockup_detector_disable(void) { - return hardlockup_detector_enabled; + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; } static int __init hardlockup_panic_setup(char *str) @@ -530,15 +523,6 @@ static int watchdog_nmi_enable(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) goto out; - /* - * Some kernels need to default hard lockup detection to - * 'disabled', for example a guest on a hypervisor. - */ - if (!watchdog_hardlockup_detector_is_enabled()) { - event = ERR_PTR(-ENOENT); - goto handle_err; - } - /* is it already setup and enabled? */ if (event && event->state > PERF_EVENT_STATE_OFF) goto out; @@ -553,7 +537,6 @@ static int watchdog_nmi_enable(unsigned int cpu) /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); -handle_err: /* save cpu0 error for future comparision */ if (cpu == 0 && IS_ERR(event)) cpu0_err = PTR_ERR(event); -- cgit v1.2.3