linux_old1/include/linux/nmi.h

204 lines
6.1 KiB
C
Raw Normal View History

/*
* linux/include/linux/nmi.h
*/
#ifndef LINUX_NMI_H
#define LINUX_NMI_H
#include <linux/sched.h>
#include <asm/irq.h>
#if defined(CONFIG_HAVE_NMI_WATCHDOG)
#include <asm/nmi.h>
#endif
#ifdef CONFIG_LOCKUP_DETECTOR
void lockup_detector_init(void);
void lockup_detector_soft_poweroff(void);
watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Don Zickus <dzickus@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-13 03:37:04 +08:00
void lockup_detector_cleanup(void);
bool is_hardlockup(void);
extern int watchdog_user_enabled;
extern int nmi_watchdog_user_enabled;
extern int soft_watchdog_user_enabled;
extern int watchdog_thresh;
extern unsigned long watchdog_enabled;
extern struct cpumask watchdog_cpumask;
extern unsigned long *watchdog_cpumask_bits;
#ifdef CONFIG_SMP
extern int sysctl_softlockup_all_cpu_backtrace;
extern int sysctl_hardlockup_all_cpu_backtrace;
#else
#define sysctl_softlockup_all_cpu_backtrace 0
#define sysctl_hardlockup_all_cpu_backtrace 0
#endif /* !CONFIG_SMP */
#else /* CONFIG_LOCKUP_DETECTOR */
static inline void lockup_detector_init(void) { }
static inline void lockup_detector_soft_poweroff(void) { }
watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Don Zickus <dzickus@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-13 03:37:04 +08:00
static inline void lockup_detector_cleanup(void) { }
#endif /* !CONFIG_LOCKUP_DETECTOR */
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
extern void touch_softlockup_watchdog_sched(void);
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned int softlockup_panic;
#else
static inline void touch_softlockup_watchdog_sched(void) { }
static inline void touch_softlockup_watchdog(void) { }
static inline void touch_softlockup_watchdog_sync(void) { }
static inline void touch_all_softlockup_watchdogs(void) { }
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
void reset_hung_task_detector(void);
#else
static inline void reset_hung_task_detector(void) { }
#endif
kernel/watchdog.c: move shared definitions to nmi.h Patch series "Clean up watchdog handlers", v2. This is an attempt to cleanup watchdog handlers. Right now, kernel/watchdog.c implements both softlockup and hardlockup detectors. Softlockup code is generic. Hardlockup code is arch specific. Some architectures don't use hardlockup detectors. They use their own watchdog detectors. To make both these combination work, we have numerous #ifdefs in kernel/watchdog.c. We are trying here to make these handlers independent of each other. Also provide an interface for architectures to implement their own handlers. watchdog_nmi_enable and watchdog_nmi_disable will be defined as weak such that architectures can override its definitions. Thanks to Don Zickus for his suggestions. Here are our previous discussions http://www.spinics.net/lists/sparclinux/msg16543.html http://www.spinics.net/lists/sparclinux/msg16441.html This patch (of 3): Move shared macros and definitions to nmi.h so that watchdog.c, new file watchdog_hld.c or any other architecture specific handler can use those definitions. Link: http://lkml.kernel.org/r/1478034826-43888-2-git-send-email-babu.moger@oracle.com Signed-off-by: Babu Moger <babu.moger@oracle.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Andi Kleen <andi@firstfloor.org> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: Josh Hunt <johunt@akamai.com> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-12-15 07:06:21 +08:00
/*
* The run state of the lockup detectors is controlled by the content of the
* 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
* bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
*
* 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and
* 'soft_watchdog_user_enabled' are variables that are only used as an
* 'interface' between the parameters in /proc/sys/kernel and the internal
* state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is
* handled differently because its value is not boolean, and the lockup
* detectors are 'suspended' while 'watchdog_thresh' is equal zero.
kernel/watchdog.c: move shared definitions to nmi.h Patch series "Clean up watchdog handlers", v2. This is an attempt to cleanup watchdog handlers. Right now, kernel/watchdog.c implements both softlockup and hardlockup detectors. Softlockup code is generic. Hardlockup code is arch specific. Some architectures don't use hardlockup detectors. They use their own watchdog detectors. To make both these combination work, we have numerous #ifdefs in kernel/watchdog.c. We are trying here to make these handlers independent of each other. Also provide an interface for architectures to implement their own handlers. watchdog_nmi_enable and watchdog_nmi_disable will be defined as weak such that architectures can override its definitions. Thanks to Don Zickus for his suggestions. Here are our previous discussions http://www.spinics.net/lists/sparclinux/msg16543.html http://www.spinics.net/lists/sparclinux/msg16441.html This patch (of 3): Move shared macros and definitions to nmi.h so that watchdog.c, new file watchdog_hld.c or any other architecture specific handler can use those definitions. Link: http://lkml.kernel.org/r/1478034826-43888-2-git-send-email-babu.moger@oracle.com Signed-off-by: Babu Moger <babu.moger@oracle.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Andi Kleen <andi@firstfloor.org> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: Josh Hunt <johunt@akamai.com> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-12-15 07:06:21 +08:00
*/
#define NMI_WATCHDOG_ENABLED_BIT 0
#define SOFT_WATCHDOG_ENABLED_BIT 1
#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
#if defined(CONFIG_HARDLOCKUP_DETECTOR)
extern void hardlockup_detector_disable(void);
extern unsigned int hardlockup_panic;
#else
static inline void hardlockup_detector_disable(void) {}
#endif
#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
# define NMI_WATCHDOG_SYSCTL_PERM 0644
#else
# define NMI_WATCHDOG_SYSCTL_PERM 0444
#endif
#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
extern void arch_touch_nmi_watchdog(void);
extern void hardlockup_detector_perf_stop(void);
extern void hardlockup_detector_perf_restart(void);
watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Don Zickus <dzickus@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-13 03:37:04 +08:00
extern void hardlockup_detector_perf_disable(void);
extern void hardlockup_detector_perf_cleanup(void);
#else
static inline void hardlockup_detector_perf_stop(void) { }
static inline void hardlockup_detector_perf_restart(void) { }
watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Don Zickus <dzickus@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-13 03:37:04 +08:00
static inline void hardlockup_detector_perf_disable(void) { }
static inline void hardlockup_detector_perf_cleanup(void) { }
#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
static inline void arch_touch_nmi_watchdog(void) {}
#endif
#endif
void watchdog_nmi_reconfigure(bool run);
/**
* touch_nmi_watchdog - restart NMI watchdog timeout.
*
* If the architecture supports the NMI watchdog, touch_nmi_watchdog()
* may be used to reset the timeout - for code which intentionally
* disables interrupts for a long time. This call is stateless.
*/
[PATCH] x86: fix laptop bootup hang in init_acpi() During kernel bootup, a new T60 laptop (CoreDuo, 32-bit) hangs about 10%-20% of the time in acpi_init(): Calling initcall 0xc055ce1a: topology_init+0x0/0x2f() Calling initcall 0xc055d75e: mtrr_init_finialize+0x0/0x2c() Calling initcall 0xc05664f3: param_sysfs_init+0x0/0x175() Calling initcall 0xc014cb65: pm_sysrq_init+0x0/0x17() Calling initcall 0xc0569f99: init_bio+0x0/0xf4() Calling initcall 0xc056b865: genhd_device_init+0x0/0x50() Calling initcall 0xc056c4bd: fbmem_init+0x0/0x87() Calling initcall 0xc056dd74: acpi_init+0x0/0x1ee() It's a hard hang that not even an NMI could punch through! Frustratingly, adding printks or function tracing to the ACPI code made the hangs go away ... After some time an additional detail emerged: disabling the NMI watchdog made these occasional hangs go away. So i spent the better part of today trying to debug this and trying out various theories when i finally found the likely reason for the hang: if acpi_ns_initialize_devices() executes an _INI AML method and an NMI happens to hit that AML execution in the wrong moment, the machine would hang. (my theory is that this must be some sort of chipset setup method doing stores to chipset mmio registers?) Unfortunately given the characteristics of the hang it was sheer impossible to figure out which of the numerous AML methods is impacted by this problem. As a workaround i wrote an interface to disable chipset-based NMIs while executing _INI sections - and indeed this fixed the hang. I did a boot-loop of 100 separate reboots and none hung - while without the patch it would hang every 5-10 attempts. Out of caution i did not touch the nmi_watchdog=2 case (it's not related to the chipset anyway and didnt hang). I implemented this for both x86_64 and i686, tested the i686 laptop both with nmi_watchdog=1 [which triggered the hangs] and nmi_watchdog=2, and tested an Athlon64 box with the 64-bit kernel as well. Everything builds and works with the patch applied. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andi Kleen <ak@suse.de> Cc: Len Brown <lenb@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2007-02-13 20:26:24 +08:00
static inline void touch_nmi_watchdog(void)
{
arch_touch_nmi_watchdog();
[PATCH] x86: fix laptop bootup hang in init_acpi() During kernel bootup, a new T60 laptop (CoreDuo, 32-bit) hangs about 10%-20% of the time in acpi_init(): Calling initcall 0xc055ce1a: topology_init+0x0/0x2f() Calling initcall 0xc055d75e: mtrr_init_finialize+0x0/0x2c() Calling initcall 0xc05664f3: param_sysfs_init+0x0/0x175() Calling initcall 0xc014cb65: pm_sysrq_init+0x0/0x17() Calling initcall 0xc0569f99: init_bio+0x0/0xf4() Calling initcall 0xc056b865: genhd_device_init+0x0/0x50() Calling initcall 0xc056c4bd: fbmem_init+0x0/0x87() Calling initcall 0xc056dd74: acpi_init+0x0/0x1ee() It's a hard hang that not even an NMI could punch through! Frustratingly, adding printks or function tracing to the ACPI code made the hangs go away ... After some time an additional detail emerged: disabling the NMI watchdog made these occasional hangs go away. So i spent the better part of today trying to debug this and trying out various theories when i finally found the likely reason for the hang: if acpi_ns_initialize_devices() executes an _INI AML method and an NMI happens to hit that AML execution in the wrong moment, the machine would hang. (my theory is that this must be some sort of chipset setup method doing stores to chipset mmio registers?) Unfortunately given the characteristics of the hang it was sheer impossible to figure out which of the numerous AML methods is impacted by this problem. As a workaround i wrote an interface to disable chipset-based NMIs while executing _INI sections - and indeed this fixed the hang. I did a boot-loop of 100 separate reboots and none hung - while without the patch it would hang every 5-10 attempts. Out of caution i did not touch the nmi_watchdog=2 case (it's not related to the chipset anyway and didnt hang). I implemented this for both x86_64 and i686, tested the i686 laptop both with nmi_watchdog=1 [which triggered the hangs] and nmi_watchdog=2, and tested an Athlon64 box with the 64-bit kernel as well. Everything builds and works with the patch applied. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andi Kleen <ak@suse.de> Cc: Len Brown <lenb@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2007-02-13 20:26:24 +08:00
touch_softlockup_watchdog();
}
kernel/watchdog.c: control hard lockup detection default In some cases we don't want hard lockup detection enabled by default. An example is when running as a guest. Introduce watchdog_enable_hardlockup_detector(bool) allowing those cases to disable hard lockup detection. This must be executed early by the boot processor from e.g. smp_prepare_boot_cpu, in order to allow kernel command line arguments to override it, as well as to avoid hard lockup detection being enabled before we've had a chance to indicate that it's unwanted. In summary, initial boot: default=enabled smp_prepare_boot_cpu watchdog_enable_hardlockup_detector(false): default=disabled cmdline has 'nmi_watchdog=1': default=enabled The running kernel still has the ability to enable/disable at any time with /proc/sys/kernel/nmi_watchdog us usual. However even when the default has been overridden /proc/sys/kernel/nmi_watchdog will initially show '1'. To truly turn it on one must disable/enable it, i.e. echo 0 > /proc/sys/kernel/nmi_watchdog echo 1 > /proc/sys/kernel/nmi_watchdog This patch will be immediately useful for KVM with the next patch of this series. Other hypervisor guest types may find it useful as well. [akpm@linux-foundation.org: fix build] [dzickus@redhat.com: fix compile issues on sparc] Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:55:35 +08:00
/*
* Create trigger_all_cpu_backtrace() out of the arch-provided
* base function. Return whether such support was available,
* to allow calling code to fall back to some other mechanism:
*/
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
#ifdef arch_trigger_cpumask_backtrace
static inline bool trigger_all_cpu_backtrace(void)
{
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
arch_trigger_cpumask_backtrace(cpu_online_mask, false);
return true;
}
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
static inline bool trigger_allbutself_cpu_backtrace(void)
{
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
arch_trigger_cpumask_backtrace(cpu_online_mask, true);
return true;
}
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
arch_trigger_cpumask_backtrace(mask, false);
return true;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
arch_trigger_cpumask_backtrace(cpumask_of(cpu), false);
return true;
}
/* generic implementation */
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self,
void (*raise)(cpumask_t *mask));
bool nmi_cpu_backtrace(struct pt_regs *regs);
#else
static inline bool trigger_all_cpu_backtrace(void)
{
return false;
}
static inline bool trigger_allbutself_cpu_backtrace(void)
{
return false;
}
nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm] Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
return false;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
return false;
}
#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh);
#endif
kernel/watchdog: Prevent false positives with turbo modes The hardlockup detector on x86 uses a performance counter based on unhalted CPU cycles and a periodic hrtimer. The hrtimer period is about 2/5 of the performance counter period, so the hrtimer should fire 2-3 times before the performance counter NMI fires. The NMI code checks whether the hrtimer fired since the last invocation. If not, it assumess a hard lockup. The calculation of those periods is based on the nominal CPU frequency. Turbo modes increase the CPU clock frequency and therefore shorten the period of the perf/NMI watchdog. With extreme Turbo-modes (3x nominal frequency) the perf/NMI period is shorter than the hrtimer period which leads to false positives. A simple fix would be to shorten the hrtimer period, but that comes with the side effect of more frequent hrtimer and softlockup thread wakeups, which is not desired. Implement a low pass filter, which checks the perf/NMI period against kernel time. If the perf/NMI fires before 4/5 of the watchdog period has elapsed then the event is ignored and postponed to the next perf/NMI. That solves the problem and avoids the overhead of shorter hrtimer periods and more frequent softlockup thread wakeups. Fixes: 58687acba592 ("lockup_detector: Combine nmi_watchdog and softlockup detector") Reported-and-tested-by: Kan Liang <Kan.liang@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: dzickus@redhat.com Cc: prarit@redhat.com Cc: ak@linux.intel.com Cc: babu.moger@oracle.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: acme@redhat.com Cc: stable@vger.kernel.org Cc: atomlin@redhat.com Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1708150931310.1886@nanos
2017-08-15 15:50:13 +08:00
#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
defined(CONFIG_HARDLOCKUP_DETECTOR)
void watchdog_update_hrtimer_threshold(u64 period);
#else
static inline void watchdog_update_hrtimer_threshold(u64 period) { }
#endif
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 *);
watchdog: add watchdog_cpumask sysctl to assist nohz Change the default behavior of watchdog so it only runs on the housekeeping cores when nohz_full is enabled at build and boot time. Allow modifying the set of cores the watchdog is currently running on with a new kernel.watchdog_cpumask sysctl. In the current system, the watchdog subsystem runs a periodic timer that schedules the watchdog kthread to run. However, nohz_full cores are designed to allow userspace application code running on those cores to have 100% access to the CPU. So the watchdog system prevents the nohz_full application code from being able to run the way it wants to, thus the motivation to suppress the watchdog on nohz_full cores, which this patchset provides by default. However, if we disable the watchdog globally, then the housekeeping cores can't benefit from the watchdog functionality. So we allow disabling it only on some cores. See Documentation/lockup-watchdogs.txt for more information. [jhubbard@nvidia.com: fix a watchdog crash in some configurations] Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:45 +08:00
extern int proc_watchdog_cpumask(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
#include <asm/nmi.h>
#endif
#endif