nmi_watchdog: Add new, generic implementation, using perf events

This is a new generic nmi_watchdog implementation using the perf
events infrastructure as suggested by Ingo.

The implementation is simple, just create an in-kernel perf
event and register an overflow handler to check for cpu lockups.

I created a generic implementation that lives in kernel/ and
the hardware specific part that for now lives in arch/x86.

This approach has a number of advantages:

 - It simplifies the x86 PMU implementation in the long run,
   in that it removes the hardcoded low-level PMU implementation
   that was the NMI watchdog before.

 - It allows new NMI watchdog features to be added in a central
   place.

 - It allows other architectures to enable the NMI watchdog,
   as long as they have perf events (that provide NMIs)
   implemented.

 - It also allows for more graceful co-existence of existing
   perf events apps and the NMI watchdog - before these changes
   the relationship was exclusive. (The NMI watchdog will 'spend'
   a perf event when enabled. In later iterations we might be
   able to piggyback from an existing NMI event without having
   to allocate a hardware event for the NMI watchdog - turning
   this into a no-hardware-cost feature.)

As for compatibility, we'll keep the old NMI watchdog code as
well until the new one can 100% replace it on all CPUs, old and
new alike.  That might take some time as the NMI watchdog has
been ported to many CPU models.

I have done light testing to make sure the framework works
correctly and it does.

 v2: Set the correct timeout values based on the old nmi
     watchdog

Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: gorcunov@gmail.com
Cc: aris@redhat.com
Cc: peterz@infradead.org
LKML-Reference: <1265424425-31562-3-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 114 insertions, 0 deletions

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
new file mode 100644
index 000000000000..8c0e6a410d05
--- /dev/null
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -0,0 +1,114 @@
+/*
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ *
+ */
+
+#include <asm/apic.h>
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/kernel_stat.h>
+#include <asm/mce.h>
+
+#include <linux/nmi.h>
+#include <linux/module.h>
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+static DEFINE_PER_CPU(unsigned, last_irq_sum);
+
+/*
+ * Take the local apic timer and PIT/HPET into account. We don't
+ * know which one is active, when we have highres/dyntick on
+ */
+static inline unsigned int get_timer_irqs(int cpu)
+{
+        return per_cpu(irq_stat, cpu).apic_timer_irqs +
+                per_cpu(irq_stat, cpu).irq0_irqs;
+}
+
+static inline int mce_in_progress(void)
+{
+#if defined(CONFIG_X86_MCE)
+        return atomic_read(&mce_entry) > 0;
+#endif
+        return 0;
+}
+
+int hw_nmi_is_cpu_stuck(struct pt_regs *regs)
+{
+	unsigned int sum;
+	int cpu = smp_processor_id();
+
+	/* FIXME: cheap hack for this check, probably should get its own
+	 * die_notifier handler
+	 */
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
+
+		spin_lock(&lock);
+		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		dump_stack();
+		spin_unlock(&lock);
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+	}
+
+	/* if we are doing an mce, just assume the cpu is not stuck */
+        /* Could check oops_in_progress here too, but it's safer not to */
+        if (mce_in_progress())
+                return 0;
+
+	/* We determine if the cpu is stuck by checking whether any
+	 * interrupts have happened since we last checked.  Of course
+	 * an nmi storm could create false positives, but the higher
+	 * level logic should account for that
+	 */
+	sum = get_timer_irqs(cpu);
+	if (__get_cpu_var(last_irq_sum) == sum) {
+		return 1;
+	} else {
+		__get_cpu_var(last_irq_sum) = sum;
+		return 0;
+	}
+}
+
+void arch_trigger_all_cpu_backtrace(void)
+{
+	int i;
+
+	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+
+	printk(KERN_INFO "sending NMI to all CPUs:\n");
+	apic->send_IPI_all(NMI_VECTOR);
+
+	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+	}
+}
+
+/* STUB calls to mimic old nmi_watchdog behaviour */
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
+atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
+int nmi_watchdog_enabled;
+int unknown_nmi_panic;
+void cpu_nmi_set_wd_enabled(void) { return; }
+void acpi_nmi_enable(void) { return; }
+void acpi_nmi_disable(void) { return; }
+void stop_apic_nmi_watchdog(void *unused) { return; }
+void setup_apic_nmi_watchdog(void *unused) { return; }
+int __init check_nmi_watchdog(void) { return 0; }