Re: [PATCH 2/2] x86, NMI: add back unknown_nmi_panic and nmi_watchdog sysctls

[Yinghai Lu <yinghai@kernel.org>]

On 11/29/2010 02:07 PM, Don Zickus wrote:
> Originally adapted from Huang Ying's patch which moved the unknown_nmi_panic
> to the traps.c file.  Because the old nmi watchdog was deleted before this
> change happened, the unknown_nmi_panic sysctl was lost.  This re-adds it.
> 
> Also, the nmi_watchdog sysctl was re-implemented and its documentation
> updated accordingly.
> 
> Patch-inspired-by: Huang Ying <ying.huang@intel.com>
> Signed-off-by: Don Zickus <dzickus@redhat.com>
> ---
>  Documentation/kernel-parameters.txt |   10 +---------
>  arch/x86/kernel/apic/hw_nmi.c       |    3 ---
>  arch/x86/kernel/traps.c             |   16 +++++++++++-----
>  kernel/sysctl.c                     |   16 ++++++++++++++++
>  kernel/sysctl_binary.c              |    1 -
>  kernel/watchdog.c                   |    2 ++
>  6 files changed, 30 insertions(+), 18 deletions(-)
> 
> diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
> index cdd2a6e..5e55e46 100644
> --- a/Documentation/kernel-parameters.txt
> +++ b/Documentation/kernel-parameters.txt
> @@ -1579,20 +1579,12 @@ and is between 256 and 4096 characters. It is defined in the file
>  
>  	nmi_watchdog=	[KNL,BUGS=X86] Debugging features for SMP kernels
>  			Format: [panic,][num]
> -			Valid num: 0,1,2
> +			Valid num: 0
>  			0 - turn nmi_watchdog off
> -			1 - use the IO-APIC timer for the NMI watchdog
> -			2 - use the local APIC for the NMI watchdog using
> -			a performance counter. Note: This will use one
> -			performance counter and the local APIC's performance
> -			vector.
>  			When panic is specified, panic when an NMI watchdog
>  			timeout occurs.
>  			This is useful when you use a panic=... timeout and
>  			need the box quickly up again.
> -			Instead of 1 and 2 it is possible to use the following
> -			symbolic names: lapic and ioapic
> -			Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
>  
>  	netpoll.carrier_timeout=
>  			[NET] Specifies amount of time (in seconds) that
> diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
> index d13081e..a86840c 100644
> --- a/arch/x86/kernel/apic/hw_nmi.c
> +++ b/arch/x86/kernel/apic/hw_nmi.c
> @@ -100,6 +100,3 @@ static int __init register_trigger_all_cpu_backtrace(void)
>  }
>  early_initcall(register_trigger_all_cpu_backtrace);
>  #endif
> -
> -/* STUB calls to mimic old nmi_watchdog behaviour */
> -int unknown_nmi_panic;
> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index f02c179..bb6f041 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -83,6 +83,8 @@ EXPORT_SYMBOL_GPL(used_vectors);
>  
>  static int ignore_nmis;
>  
> +int unknown_nmi_panic;
> +
>  static inline void conditional_sti(struct pt_regs *regs)
>  {
>  	if (regs->flags & X86_EFLAGS_IF)
> @@ -300,6 +302,13 @@ gp_in_kernel:
>  	die("general protection fault", regs, error_code);
>  }
>  
> +static int __init setup_unknown_nmi_panic(char *str)
> +{
> +	unknown_nmi_panic = 1;
> +	return 1;
> +}
> +__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
> +
>  static notrace __kprobes void
>  mem_parity_error(unsigned char reason, struct pt_regs *regs)
>  {
> @@ -371,7 +380,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
>  			reason, smp_processor_id());
>  
>  	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
> -	if (panic_on_unrecovered_nmi)
> +	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
>  		panic("NMI: Not continuing");
>  
>  	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
> @@ -397,11 +406,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
>  		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
>  							== NOTIFY_STOP)
>  			return;
> -
> -			unknown_nmi_error(reason, regs);
> -#else
> -		unknown_nmi_error(reason, regs);
>  #endif
> +		unknown_nmi_error(reason, regs);
>  
>  		return;
>  	}
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index d91b07d..140344d 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -733,6 +733,22 @@ static struct ctl_table kern_table[] = {
>  		.extra1		= &zero,
>  		.extra2		= &one,
>  	},
> +	{
> +		.procname       = "nmi_watchdog",
> +		.data           = &watchdog_enabled,
> +		.maxlen         = sizeof (int),
> +		.mode           = 0644,
> +		.proc_handler   = proc_dowatchdog_enabled,
> +	},
> +#endif
> +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
> +	{
> +		.procname       = "unknown_nmi_panic",
> +		.data           = &unknown_nmi_panic,
> +		.maxlen         = sizeof (int),
> +		.mode           = 0644,
> +		.proc_handler   = proc_dointvec,
> +	},
>  #endif
>  #if defined(CONFIG_X86)
>  	{
> diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
> index 1357c57..4b2545a 100644
> --- a/kernel/sysctl_binary.c
> +++ b/kernel/sysctl_binary.c
> @@ -136,7 +136,6 @@ static const struct bin_table bin_kern_table[] = {
>  	{ CTL_INT,	KERN_IA64_UNALIGNED,		"ignore-unaligned-usertrap" },
>  	{ CTL_INT,	KERN_COMPAT_LOG,		"compat-log" },
>  	{ CTL_INT,	KERN_MAX_LOCK_DEPTH,		"max_lock_depth" },
> -	{ CTL_INT,	KERN_NMI_WATCHDOG,		"nmi_watchdog" },
>  	{ CTL_INT,	KERN_PANIC_ON_NMI,		"panic_on_unrecovered_nmi" },
>  	{}
>  };
> diff --git a/kernel/watchdog.c b/kernel/watchdog.c
> index fd77b69..e0f44dc 100644
> --- a/kernel/watchdog.c
> +++ b/kernel/watchdog.c
> @@ -57,6 +57,8 @@ static int __init hardlockup_panic_setup(char *str)
>  {
>  	if (!strncmp(str, "panic", 5))
>  		hardlockup_panic = 1;
> +	else if (!strncmp(str, "0", 1))
> +		no_watchdog = 1;
>  	return 1;
>  }
>  __setup("nmi_watchdog=", hardlockup_panic_setup);

Thanks, unknown_nmi_panic works again.

Acked-by: Yinghai Lu <yinghai@kernel.org>