[RFC PATCH 3/4] watchdog: Move hardlockup detector to separate file
Move hardlockup detector code to watchdog_hld.c. Also update the makefile accordigly. Signed-off-by: Babu Moger--- kernel/Makefile |1 + kernel/watchdog_hld.c | 238 + 2 files changed, 239 insertions(+), 0 deletions(-) create mode 100644 kernel/watchdog_hld.c diff --git a/kernel/Makefile b/kernel/Makefile index eb26e12..314e7d6 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c new file mode 100644 index 000..cd690fb --- /dev/null +++ b/kernel/watchdog_hld.c @@ -0,0 +1,238 @@ +/* + * Detect hard and soft lockups on a system + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Note: Most of this code is borrowed heavily from the original softlockup + * detector, so thanks to Ingo for the initial implementation. + * Some chunks also taken from the old x86-specific nmi watchdog code, thanks + * to those contributors as well. + */ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(bool, hard_watchdog_warn); +static DEFINE_PER_CPU(bool, watchdog_nmi_touch); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); + +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +unsigned int __read_mostly hardlockup_panic = + CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +static unsigned long hardlockup_allcpu_dumped; +/* + * 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 + * cases this function can be called to disable hard lockup detection. This + * function should only be executed once by the boot processor before the + * kernel command line parameters are parsed, because otherwise it is not + * possible to override this in hardlockup_panic_setup(). + */ +void hardlockup_detector_disable(void) +{ + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; +} + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + else if (!strncmp(str, "nopanic", 7)) + hardlockup_panic = 0; + else if (!strncmp(str, "0", 1)) + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); + +void touch_nmi_watchdog(void) +{ + /* +* Using __raw here because some code paths have +* preemption enabled. If preemption is enabled +* then interrupts should be enabled too, in which +* case we shouldn't have to worry about the watchdog +* going off. +*/ + raw_cpu_write(watchdog_nmi_touch, true); + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); + +/* watchdog detector functions */ +static bool is_hardlockup(void) +{ + unsigned long hrint = __this_cpu_read(hrtimer_interrupts); + + if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) + return true; + + __this_cpu_write(hrtimer_interrupts_saved, hrint); + return false; +} + +static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + +/* Callback function for perf event subsystem */ +static void watchdog_overflow_callback(struct perf_event *event, +struct perf_sample_data *data, +struct pt_regs *regs) +{ + /* Ensure the watchdog never gets throttled */ + event->hw.interrupts = 0; + + if (__this_cpu_read(watchdog_nmi_touch) == true) { + __this_cpu_write(watchdog_nmi_touch, false); + return; + } + + /* check for a hardlockup +* This is done by making sure our timer interrupt +* is incrementing. The timer interrupt should have +* fired multiple times before we overflow'd. If it hasn't +* then this is a good indication the cpu is stuck +*/ + if (is_hardlockup()) { + int this_cpu = smp_processor_id(); + struct pt_regs *regs = get_irq_regs(); + + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; + +
[RFC PATCH 3/4] watchdog: Move hardlockup detector to separate file
Move hardlockup detector code to watchdog_hld.c. Also update the makefile accordigly. Signed-off-by: Babu Moger --- kernel/Makefile |1 + kernel/watchdog_hld.c | 238 + 2 files changed, 239 insertions(+), 0 deletions(-) create mode 100644 kernel/watchdog_hld.c diff --git a/kernel/Makefile b/kernel/Makefile index eb26e12..314e7d6 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c new file mode 100644 index 000..cd690fb --- /dev/null +++ b/kernel/watchdog_hld.c @@ -0,0 +1,238 @@ +/* + * Detect hard and soft lockups on a system + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Note: Most of this code is borrowed heavily from the original softlockup + * detector, so thanks to Ingo for the initial implementation. + * Some chunks also taken from the old x86-specific nmi watchdog code, thanks + * to those contributors as well. + */ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(bool, hard_watchdog_warn); +static DEFINE_PER_CPU(bool, watchdog_nmi_touch); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); + +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +unsigned int __read_mostly hardlockup_panic = + CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +static unsigned long hardlockup_allcpu_dumped; +/* + * 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 + * cases this function can be called to disable hard lockup detection. This + * function should only be executed once by the boot processor before the + * kernel command line parameters are parsed, because otherwise it is not + * possible to override this in hardlockup_panic_setup(). + */ +void hardlockup_detector_disable(void) +{ + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; +} + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + else if (!strncmp(str, "nopanic", 7)) + hardlockup_panic = 0; + else if (!strncmp(str, "0", 1)) + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); + +void touch_nmi_watchdog(void) +{ + /* +* Using __raw here because some code paths have +* preemption enabled. If preemption is enabled +* then interrupts should be enabled too, in which +* case we shouldn't have to worry about the watchdog +* going off. +*/ + raw_cpu_write(watchdog_nmi_touch, true); + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); + +/* watchdog detector functions */ +static bool is_hardlockup(void) +{ + unsigned long hrint = __this_cpu_read(hrtimer_interrupts); + + if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) + return true; + + __this_cpu_write(hrtimer_interrupts_saved, hrint); + return false; +} + +static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + +/* Callback function for perf event subsystem */ +static void watchdog_overflow_callback(struct perf_event *event, +struct perf_sample_data *data, +struct pt_regs *regs) +{ + /* Ensure the watchdog never gets throttled */ + event->hw.interrupts = 0; + + if (__this_cpu_read(watchdog_nmi_touch) == true) { + __this_cpu_write(watchdog_nmi_touch, false); + return; + } + + /* check for a hardlockup +* This is done by making sure our timer interrupt +* is incrementing. The timer interrupt should have +* fired multiple times before we overflow'd. If it hasn't +* then this is a good indication the cpu is stuck +*/ + if (is_hardlockup()) { + int this_cpu = smp_processor_id(); + struct pt_regs *regs = get_irq_regs(); + + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; + + pr_emerg("Watchdog detected hard