[PATCH] x86: all cpu backtrace

When a spinlock lockup occurs, arrange for the NMI code to emit an all-cpu
backtrace, so we get to see which CPU is holding the lock, and where.

Cc: Andi Kleen <ak@muc.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Andi Kleen <ak@suse.de>

1 files changed, 26 insertions, 0 deletions

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index eaafe233a5da..171194ccb7bc 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/dmi.h>
 #include <linux/kprobes.h>
+#include <linux/cpumask.h>
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
@@ -42,6 +43,8 @@ int nmi_watchdog_enabled;
 static DEFINE_PER_CPU(unsigned long, perfctr_nmi_owner);
 static DEFINE_PER_CPU(unsigned long, evntsel_nmi_owner[3]);
 
+static cpumask_t backtrace_mask = CPU_MASK_NONE;
+
 /* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
  * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
  */
@@ -907,6 +910,16 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
                 touched = 1;
         }
 
+        if (cpu_isset(cpu, backtrace_mask)) {
+                static DEFINE_SPINLOCK(lock);   /* Serialise the printks */
+
+                spin_lock(&lock);
+                printk("NMI backtrace for cpu %d\n", cpu);
+                dump_stack();
+                spin_unlock(&lock);
+                cpu_clear(cpu, backtrace_mask);
+        }
+
         sum = per_cpu(irq_stat, cpu).apic_timer_irqs;
 
         /* if the apic timer isn't firing, this cpu isn't doing much */
@@ -1033,6 +1046,19 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 
 #endif
 
+void __trigger_all_cpu_backtrace(void)
+{
+        int i;
+
+        backtrace_mask = cpu_online_map;
+        /* Wait for up to 10 seconds for all CPUs to do the backtrace */
+        for (i = 0; i < 10 * 1000; i++) {
+                if (cpus_empty(backtrace_mask))
+                        break;
+                mdelay(1);
+        }
+}
+
 EXPORT_SYMBOL(nmi_active);
 EXPORT_SYMBOL(nmi_watchdog);
 EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);