[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>

4 files changed, 9 insertions, 0 deletions

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 8bbdbda07a2d..0178457db721 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -478,6 +478,11 @@ void touch_nmi_watchdog (void)
          */
         for (i = 0; i < NR_CPUS; i++)
                 alert_counter[i] = 0;
+
+        /*
+         * Tickle the softlockup detector too:
+         */
+        touch_softlockup_watchdog();
 }
 
 extern void die_nmi(struct pt_regs *, const char *msg);
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 6f794a78ee1e..b0c5ee2b3446 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -422,6 +422,7 @@ static int timer_resume(struct sys_device *dev)
                 last_timer->resume();
         cur_timer = last_timer;
         last_timer = NULL;
+        touch_softlockup_watchdog();
         return 0;
 }
 
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 64a8e05d5811..84cae81fff8b 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -463,6 +463,8 @@ void touch_nmi_watchdog (void)
          */
         for (i = 0; i < NR_CPUS; i++)
                 per_cpu(nmi_touch, i) = 1;
+
+        touch_softlockup_watchdog();
 }
 
 void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 66bf6ddeb0c3..2b5d9da912a2 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -1041,6 +1041,7 @@ static int timer_resume(struct sys_device *dev)
         write_sequnlock_irqrestore(&xtime_lock,flags);
         jiffies += sleep_length;
         wall_jiffies += sleep_length;
+        touch_softlockup_watchdog();
         return 0;
 }