[PATCH] detect soft lockups
This patch adds a new kernel debug feature: CONFIG_DETECT_SOFTLOCKUP.
When enabled then per-CPU watchdog threads are started, which try to run
once per second. If they get delayed for more than 10 seconds then a
callback from the timer interrupt detects this condition and prints out a
warning message and a stack dump (once per lockup incident). The feature
is otherwise non-intrusive, it doesnt try to unlock the box in any way, it
only gets the debug info out, automatically, and on all CPUs affected by
the lockup.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-Off-By: Matthias Urlichs <smurf@smurf.noris.de>
Signed-off-by: Richard Purdie <rpurdie@rpsys.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/kernel/Makefile b/kernel/Makefile
index cb05cd0..8d57a2f 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -27,6 +27,7 @@
obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_SYSFS) += ksysfs.o
+obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_SECCOMP) += seccomp.o
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index eaacd5c..d967e87 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -1059,6 +1059,7 @@
BUG_ON(!error);
restore_processor_state();
restore_highmem();
+ touch_softlockup_watchdog();
device_power_up();
local_irq_enable();
return error;
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
new file mode 100644
index 0000000..7597620
--- /dev/null
+++ b/kernel/softlockup.c
@@ -0,0 +1,151 @@
+/*
+ * Detect Soft Lockups
+ *
+ * started by Ingo Molnar, (C) 2005, Red Hat
+ *
+ * this code detects soft lockups: incidents in where on a CPU
+ * the kernel does not reschedule for 10 seconds or more.
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+
+static DEFINE_SPINLOCK(print_lock);
+
+static DEFINE_PER_CPU(unsigned long, timestamp) = 0;
+static DEFINE_PER_CPU(unsigned long, print_timestamp) = 0;
+static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
+
+static int did_panic = 0;
+static int softlock_panic(struct notifier_block *this, unsigned long event,
+ void *ptr)
+{
+ did_panic = 1;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+ .notifier_call = softlock_panic,
+};
+
+void touch_softlockup_watchdog(void)
+{
+ per_cpu(timestamp, raw_smp_processor_id()) = jiffies;
+}
+EXPORT_SYMBOL(touch_softlockup_watchdog);
+
+/*
+ * This callback runs from the timer interrupt, and checks
+ * whether the watchdog thread has hung or not:
+ */
+void softlockup_tick(struct pt_regs *regs)
+{
+ int this_cpu = smp_processor_id();
+ unsigned long timestamp = per_cpu(timestamp, this_cpu);
+
+ if (per_cpu(print_timestamp, this_cpu) == timestamp)
+ return;
+
+ /* Do not cause a second panic when there already was one */
+ if (did_panic)
+ return;
+
+ if (time_after(jiffies, timestamp + 10*HZ)) {
+ per_cpu(print_timestamp, this_cpu) = timestamp;
+
+ spin_lock(&print_lock);
+ printk(KERN_ERR "BUG: soft lockup detected on CPU#%d!\n",
+ this_cpu);
+ show_regs(regs);
+ spin_unlock(&print_lock);
+ }
+}
+
+/*
+ * The watchdog thread - runs every second and touches the timestamp.
+ */
+static int watchdog(void * __bind_cpu)
+{
+ struct sched_param param = { .sched_priority = 99 };
+ int this_cpu = (long) __bind_cpu;
+
+ printk("softlockup thread %d started up.\n", this_cpu);
+
+ sched_setscheduler(current, SCHED_FIFO, ¶m);
+ current->flags |= PF_NOFREEZE;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /*
+ * Run briefly once per second - if this gets delayed for
+ * more than 10 seconds then the debug-printout triggers
+ * in softlockup_tick():
+ */
+ while (!kthread_should_stop()) {
+ msleep_interruptible(1000);
+ touch_softlockup_watchdog();
+ }
+ __set_current_state(TASK_RUNNING);
+
+ return 0;
+}
+
+/*
+ * Create/destroy watchdog threads as CPUs come and go:
+ */
+static int __devinit
+cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+ int hotcpu = (unsigned long)hcpu;
+ struct task_struct *p;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ BUG_ON(per_cpu(watchdog_task, hotcpu));
+ p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
+ if (IS_ERR(p)) {
+ printk("watchdog for %i failed\n", hotcpu);
+ return NOTIFY_BAD;
+ }
+ per_cpu(watchdog_task, hotcpu) = p;
+ kthread_bind(p, hotcpu);
+ break;
+ case CPU_ONLINE:
+
+ wake_up_process(per_cpu(watchdog_task, hotcpu));
+ break;
+#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_UP_CANCELED:
+ /* Unbind so it can run. Fall thru. */
+ kthread_bind(per_cpu(watchdog_task, hotcpu), smp_processor_id());
+ case CPU_DEAD:
+ p = per_cpu(watchdog_task, hotcpu);
+ per_cpu(watchdog_task, hotcpu) = NULL;
+ kthread_stop(p);
+ break;
+#endif /* CONFIG_HOTPLUG_CPU */
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block __devinitdata cpu_nfb = {
+ .notifier_call = cpu_callback
+};
+
+__init void spawn_softlockup_task(void)
+{
+ void *cpu = (void *)(long)smp_processor_id();
+
+ cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+ cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
+ register_cpu_notifier(&cpu_nfb);
+
+ notifier_chain_register(&panic_notifier_list, &panic_block);
+}
+
diff --git a/kernel/timer.c b/kernel/timer.c
index 5377f40..1433d87 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -950,6 +950,7 @@
{
jiffies_64++;
update_times();
+ softlockup_tick(regs);
}
#ifdef __ARCH_WANT_SYS_ALARM