Re: [tip:perf/urgent] perf, x86: Fix accidentally ack'ing a secondevent on intel perf counter
From: Yinghai Lu
Date: Fri Sep 03 2010 - 13:16:49 EST
On 09/03/2010 08:00 AM, Don Zickus wrote:
> On Fri, Sep 03, 2010 at 12:39:25AM -0700, Yinghai Lu wrote:
>> Can you put this into perf branch ?
>>
>> Thanks
>>
>> Yinghai
>>
>> [PATCH] x86,nmi: move unknown_nmi_panic to traps.c
>
> This patch duplicates a bunch of stuff we already have in
> unknown_nmi_error. The only thing I think you are interested in is using
> the 'unknown_nmi_panic' flag. I am putting together a smaller patch that
> uses that flag in traps.c (though it would be nice to combine that flag
> with panic_on_unrecovered_nmi).
please make sure
keep using unknown_nmi_panic in boot command line and sysctl
when LOCKUP_DETECTOR is defined.
that does work until hw nmi watchdog is merged with software lock detector.
assume that time hw nmi watchdog is relying on perf nmi and perf nmi would eat all unknown nmi.
good to have Robert/Peter/Don's patches to make per nmi not to eat all unknown nmi.
Thanks
Yinghai
>
> Cheers,
> Don
>
>>
>> So we use it even LOCKUP_DETECTOR is defined.
>> need Robert/Peter/Don's patch...
>>
>> that will keep unknown_nmi_panic to have same behavoir before hw nmi watchdog
>>
>> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
>>
>> ---
>> arch/x86/include/asm/nmi.h | 8 --------
>> arch/x86/kernel/apic/hw_nmi.c | 1 -
>> arch/x86/kernel/apic/nmi.c | 27 ---------------------------
>> arch/x86/kernel/traps.c | 29 ++++++++++++++++++++++++++++-
>> kernel/sysctl.c | 4 +++-
>> 5 files changed, 31 insertions(+), 38 deletions(-)
>>
>> Index: linux-2.6/arch/x86/kernel/apic/nmi.c
>> ===================================================================
>> --- linux-2.6.orig/arch/x86/kernel/apic/nmi.c
>> +++ linux-2.6/arch/x86/kernel/apic/nmi.c
>> @@ -37,7 +37,6 @@
>>
>> #include <asm/mach_traps.h>
>>
>> -int unknown_nmi_panic;
>> int nmi_watchdog_enabled;
>>
>> /* For reliability, we're prepared to waste bits here. */
>> @@ -483,23 +482,6 @@ static void disable_ioapic_nmi_watchdog(
>> on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
>> }
>>
>> -static int __init setup_unknown_nmi_panic(char *str)
>> -{
>> - unknown_nmi_panic = 1;
>> - return 1;
>> -}
>> -__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
>> -
>> -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
>> -{
>> - unsigned char reason = get_nmi_reason();
>> - char buf[64];
>> -
>> - sprintf(buf, "NMI received for unknown reason %02x\n", reason);
>> - die_nmi(buf, regs, 1); /* Always panic here */
>> - return 0;
>> -}
>> -
>> /*
>> * proc handler for /proc/sys/kernel/nmi
>> */
>> @@ -540,15 +522,6 @@ int proc_nmi_enabled(struct ctl_table *t
>>
>> #endif /* CONFIG_SYSCTL */
>>
>> -int do_nmi_callback(struct pt_regs *regs, int cpu)
>> -{
>> -#ifdef CONFIG_SYSCTL
>> - if (unknown_nmi_panic)
>> - return unknown_nmi_panic_callback(regs, cpu);
>> -#endif
>> - return 0;
>> -}
>> -
>> void arch_trigger_all_cpu_backtrace(void)
>> {
>> int i;
>> Index: linux-2.6/arch/x86/kernel/apic/hw_nmi.c
>> ===================================================================
>> --- linux-2.6.orig/arch/x86/kernel/apic/hw_nmi.c
>> +++ linux-2.6/arch/x86/kernel/apic/hw_nmi.c
>> @@ -100,7 +100,6 @@ void acpi_nmi_disable(void) { return; }
>> #endif
>> atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
>> EXPORT_SYMBOL(nmi_active);
>> -int unknown_nmi_panic;
>> void cpu_nmi_set_wd_enabled(void) { return; }
>> void stop_apic_nmi_watchdog(void *unused) { return; }
>> void setup_apic_nmi_watchdog(void *unused) { return; }
>> Index: linux-2.6/arch/x86/kernel/traps.c
>> ===================================================================
>> --- linux-2.6.orig/arch/x86/kernel/traps.c
>> +++ linux-2.6/arch/x86/kernel/traps.c
>> @@ -377,6 +377,33 @@ unknown_nmi_error(unsigned char reason,
>> printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
>> }
>>
>> +#if defined(CONFIG_SYSCTL) && defined(CONFIG_X86_LOCAL_APIC)
>> +int unknown_nmi_panic;
>> +static int __init setup_unknown_nmi_panic(char *str)
>> +{
>> + unknown_nmi_panic = 1;
>> + return 1;
>> +}
>> +__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
>> +
>> +static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
>> +{
>> + unsigned char reason = get_nmi_reason();
>> + char buf[64];
>> +
>> + sprintf(buf, "NMI received for unknown reason %02x\n", reason);
>> + die_nmi(buf, regs, 1); /* Always panic here */
>> + return 0;
>> +}
>> +
>> +static int do_nmi_callback(struct pt_regs *regs, int cpu)
>> +{
>> + if (unknown_nmi_panic)
>> + return unknown_nmi_panic_callback(regs, cpu);
>> + return 0;
>> +}
>> +#endif
>> +
>> static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
>> {
>> unsigned char reason = 0;
>> @@ -405,8 +432,8 @@ static notrace __kprobes void default_do
>> */
>> if (nmi_watchdog_tick(regs, reason))
>> return;
>> - if (!do_nmi_callback(regs, cpu))
>> #endif /* !CONFIG_LOCKUP_DETECTOR */
>> + if (!do_nmi_callback(regs, cpu))
>> unknown_nmi_error(reason, regs);
>> #else
>> unknown_nmi_error(reason, regs);
>> Index: linux-2.6/kernel/sysctl.c
>> ===================================================================
>> --- linux-2.6.orig/kernel/sysctl.c
>> +++ linux-2.6/kernel/sysctl.c
>> @@ -739,7 +739,7 @@ static struct ctl_table kern_table[] = {
>> .extra2 = &one,
>> },
>> #endif
>> -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
>> +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
>> {
>> .procname = "unknown_nmi_panic",
>> .data = &unknown_nmi_panic,
>> @@ -747,6 +747,8 @@ static struct ctl_table kern_table[] = {
>> .mode = 0644,
>> .proc_handler = proc_dointvec,
>> },
>> +#endif
>> +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
>> {
>> .procname = "nmi_watchdog",
>> .data = &nmi_watchdog_enabled,
>> Index: linux-2.6/arch/x86/include/asm/nmi.h
>> ===================================================================
>> --- linux-2.6.orig/arch/x86/include/asm/nmi.h
>> +++ linux-2.6/arch/x86/include/asm/nmi.h
>> @@ -7,14 +7,6 @@
>>
>> #ifdef ARCH_HAS_NMI_WATCHDOG
>>
>> -/**
>> - * do_nmi_callback
>> - *
>> - * Check to see if a callback exists and execute it. Return 1
>> - * if the handler exists and was handled successfully.
>> - */
>> -int do_nmi_callback(struct pt_regs *regs, int cpu);
>> -
>> extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
>> extern int check_nmi_watchdog(void);
>> #if !defined(CONFIG_LOCKUP_DETECTOR)
> --
> To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/