From c1dc0b9c0c8979ce4d411caadff5c0d79dee58bc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 2 Aug 2009 11:28:21 +0200 Subject: 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 Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/nmi.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index b3025b43b63..1bb1ac20e9e 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -39,7 +39,7 @@ int unknown_nmi_panic; int nmi_watchdog_enabled; -static cpumask_var_t backtrace_mask; +static cpumask_t backtrace_mask __read_mostly; /* nmi_active: * >0: the lapic NMI watchdog is active, but can be disabled @@ -138,7 +138,6 @@ int __init check_nmi_watchdog(void) if (!prev_nmi_count) goto error; - alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO); printk(KERN_INFO "Testing NMI watchdog ... "); #ifdef CONFIG_SMP @@ -415,14 +414,17 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) } /* We can be called before check_nmi_watchdog, hence NULL check. */ - if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) { + if (cpumask_test_cpu(cpu, &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, backtrace_mask); + cpumask_clear_cpu(cpu, &backtrace_mask); + + rc = 1; } /* Could check oops_in_progress here too, but it's safer not to */ @@ -556,10 +558,14 @@ void __trigger_all_cpu_backtrace(void) { int i; - cpumask_copy(backtrace_mask, cpu_online_mask); + cpumask_copy(&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(backtrace_mask)) + if (cpumask_empty(&backtrace_mask)) break; mdelay(1); } -- cgit v1.2.3 From 47cab6a722d44c71c4f8224017ef548522243cf4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Aug 2009 09:31:54 +0200 Subject: debug lockups: Improve lockup detection, fix generic arch fallback As Andrew noted, my previous patch ("debug lockups: Improve lockup detection") broke/removed SysRq-L support from architecture that do not provide a __trigger_all_cpu_backtrace implementation. Restore a fallback path and clean up the SysRq-L machinery a bit: - Rename the arch method to arch_trigger_all_cpu_backtrace() - Simplify the define - Document the method a bit - in the hope of more architectures adding support for it. [ The patch touches Sparc code for the rename. ] Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Cc: "David S. Miller" LKML-Reference: <20090802140809.7ec4bb6b.akpm@linux-foundation.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/nmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 1bb1ac20e9e..db7220220d0 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -554,7 +554,7 @@ int do_nmi_callback(struct pt_regs *regs, int cpu) return 0; } -void __trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(void) { int i; -- cgit v1.2.3