summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2009-08-02 11:28:21 +0200
committerIngo Molnar <mingo@elte.hu>2009-08-02 13:27:17 +0200
commitc1dc0b9c0c8979ce4d411caadff5c0d79dee58bc (patch)
tree6822205799a6cf8928623d60aa226c95534a20f9 /kernel
parented680c4ad478d0fee9740f7d029087f181346564 (diff)
downloadlinux-c1dc0b9c0c8979ce4d411caadff5c0d79dee58bc.tar.gz
linux-c1dc0b9c0c8979ce4d411caadff5c0d79dee58bc.tar.bz2
linux-c1dc0b9c0c8979ce4d411caadff5c0d79dee58bc.zip
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 'kernel')
-rw-r--r--kernel/rcutree.c7
1 files changed, 6 insertions, 1 deletions
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7717b95c2027..9c5fa9fc57ec 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -35,6 +35,7 @@
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
+#include <linux/nmi.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
@@ -469,6 +470,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
}
printk(" (detected by %d, t=%ld jiffies)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start));
+ trigger_all_cpu_backtrace();
+
force_quiescent_state(rsp, 0); /* Kick them all. */
}
@@ -479,12 +482,14 @@ static void print_cpu_stall(struct rcu_state *rsp)
printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
smp_processor_id(), jiffies - rsp->gp_start);
- dump_stack();
+ trigger_all_cpu_backtrace();
+
spin_lock_irqsave(&rnp->lock, flags);
if ((long)(jiffies - rsp->jiffies_stall) >= 0)
rsp->jiffies_stall =
jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
spin_unlock_irqrestore(&rnp->lock, flags);
+
set_need_resched(); /* kick ourselves to get things going. */
}