From 58687acba59266735adb8ccd9b5b9aa2c7cd205b Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 7 May 2010 17:11:44 -0400 Subject: lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Randy Dunlap LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/apic/Makefile | 4 ++-- arch/x86/kernel/apic/hw_nmi.c | 2 +- arch/x86/kernel/traps.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 1a4512e48d24..52f32e0ea194 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -3,10 +3,10 @@ # obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o -ifneq ($(CONFIG_NMI_WATCHDOG),y) +ifneq ($(CONFIG_LOCKUP_DETECTOR),y) obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o endif -obj-$(CONFIG_NMI_WATCHDOG) += hw_nmi.o +obj-$(CONFIG_LOCKUP_DETECTOR) += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index e8b78a0be5de..79425f96fcee 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -89,7 +89,7 @@ int hw_nmi_is_cpu_stuck(struct pt_regs *regs) u64 hw_nmi_get_sample_period(void) { - return cpu_khz * 1000; + return (u64)(cpu_khz) * 1000 * 60; } #ifdef ARCH_HAS_NMI_WATCHDOG diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bdc7fab3ef3e..bd347c2b34dc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -406,7 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) == NOTIFY_STOP) return; -#ifndef CONFIG_NMI_WATCHDOG +#ifndef CONFIG_LOCKUP_DETECTOR /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. @@ -414,7 +414,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, cpu)) -#endif /* !CONFIG_NMI_WATCHDOG */ +#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); -- cgit v1.2.1