From 554ec063982752e9a569ab9189eeffa3d96731b2 Mon Sep 17 00:00:00 2001 From: Dongdong Deng Date: Tue, 4 Jan 2011 22:38:08 -0500 Subject: x86: Avoid calling arch_trigger_all_cpu_backtrace() at the same time The spin_lock_debug/rcu_cpu_stall detector uses trigger_all_cpu_backtrace() to dump cpu backtrace. Therefore it is possible that trigger_all_cpu_backtrace() could be called at the same time on different CPUs, which triggers and 'unknown reason NMI' warning. The following case illustrates the problem: CPU1 CPU2 ... CPU N trigger_all_cpu_backtrace() set "backtrace_mask" to cpu mask | generate NMI interrupts generate NMI interrupts ... \ | / \ | / The "backtrace_mask" will be cleaned by the first NMI interrupt at nmi_watchdog_tick(), then the following NMI interrupts generated by other cpus's arch_trigger_all_cpu_backtrace() will be taken as unknown reason NMI interrupts. This patch uses a test_and_set to avoid the problem, and stop the arch_trigger_all_cpu_backtrace() from calling to avoid dumping a double cpu backtrace info when there is already a trigger_all_cpu_backtrace() in progress. Signed-off-by: Dongdong Deng Reviewed-by: Bruce Ashfield Cc: fweisbec@gmail.com LKML-Reference: <1294198689-15447-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar Signed-off-by: Don Zickus --- arch/x86/kernel/apic/hw_nmi.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 2b40a6045da..72ec29e1ae0 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -28,10 +28,20 @@ u64 hw_nmi_get_sample_period(void) /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; +/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +static unsigned long backtrace_flag; + void arch_trigger_all_cpu_backtrace(void) { int i; + if (test_and_set_bit(0, &backtrace_flag)) + /* + * If there is already a trigger_all_cpu_backtrace() in progress + * (backtrace_flag == 1), don't output double cpu dump infos. + */ + return; + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); printk(KERN_INFO "sending NMI to all CPUs:\n"); @@ -43,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void) break; mdelay(1); } + + clear_bit(0, &backtrace_flag); + smp_mb__after_clear_bit(); } static int __kprobes -- cgit v1.2.3