aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/char
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2009-08-02 05:28:21 -0400
committerIngo Molnar <mingo@elte.hu>2009-08-02 07:27:17 -0400
commitc1dc0b9c0c8979ce4d411caadff5c0d79dee58bc (patch)
tree6822205799a6cf8928623d60aa226c95534a20f9 /drivers/char
parented680c4ad478d0fee9740f7d029087f181346564 (diff)
debug lockups: Improve lockup detection
When debugging a recent lockup bug i found various deficiencies in how our current lockup detection helpers work: - SysRq-L is not very efficient as it uses a workqueue, hence it cannot punch through hard lockups and cannot see through most soft lockups either. - The SysRq-L code depends on the NMI watchdog - which is off by default. - We dont print backtraces from the RCU code's built-in 'RCU state machine is stuck' debug code. This debug code tends to be one of the first (and only) mechanisms that show that a lockup has occured. This patch changes the code so taht we: - Trigger the NMI backtrace code from SysRq-L instead of using a workqueue (which cannot punch through hard lockups) - Trigger print-all-CPU-backtraces from the RCU lockup detection code Also decouple the backtrace printing code from the NMI watchdog: - Dont use variable size cpumasks (it might not be initialized and they are a bit more fragile anyway) - Trigger an NMI immediately via an IPI, instead of waiting for the NMI tick to occur. This is a lot faster and can produce more relevant backtraces. It will also work if the NMI watchdog is disabled. - Dont print the 'dazed and confused' message when we print a backtrace from the NMI - Do a show_regs() plus a dump_stack() to get maximum info out of the dump. Worst-case we get two stacktraces - which is not a big deal. Sometimes, if register content is corrupted, the precise stack walker in show_regs() wont give us a full backtrace - in this case dump_stack() will do it. Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'drivers/char')
-rw-r--r--drivers/char/sysrq.c8
1 files changed, 2 insertions, 6 deletions
diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index 5d7a02f63e1c..165f307f30e8 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -24,6 +24,7 @@
24#include <linux/sysrq.h> 24#include <linux/sysrq.h>
25#include <linux/kbd_kern.h> 25#include <linux/kbd_kern.h>
26#include <linux/proc_fs.h> 26#include <linux/proc_fs.h>
27#include <linux/nmi.h>
27#include <linux/quotaops.h> 28#include <linux/quotaops.h>
28#include <linux/perf_counter.h> 29#include <linux/perf_counter.h>
29#include <linux/kernel.h> 30#include <linux/kernel.h>
@@ -222,12 +223,7 @@ static DECLARE_WORK(sysrq_showallcpus, sysrq_showregs_othercpus);
222 223
223static void sysrq_handle_showallcpus(int key, struct tty_struct *tty) 224static void sysrq_handle_showallcpus(int key, struct tty_struct *tty)
224{ 225{
225 struct pt_regs *regs = get_irq_regs(); 226 trigger_all_cpu_backtrace();
226 if (regs) {
227 printk(KERN_INFO "CPU%d:\n", smp_processor_id());
228 show_regs(regs);
229 }
230 schedule_work(&sysrq_showallcpus);
231} 227}
232 228
233static struct sysrq_key_op sysrq_showallcpus_op = { 229static struct sysrq_key_op sysrq_showallcpus_op = {