Re: [RFC][PATCH] x86, reboot: use NMI instead of REBOOT_VECTOR to stop cpus

[Ingo Molnar <mingo@elte.hu>]

* Don Zickus <dzickus@redhat.com> wrote:

> --- a/arch/x86/kernel/smp.c
> +++ b/arch/x86/kernel/smp.c
> @@ -28,6 +28,7 @@
>  #include <asm/mmu_context.h>
>  #include <asm/proto.h>
>  #include <asm/apic.h>
> +#include <asm/nmi.h>
>  /*
>   *	Some notes on x86 processor bugs affecting SMP operation:
>   *
> @@ -147,6 +148,57 @@ void native_send_call_func_ipi(const struct cpumask *mask)
>  	free_cpumask_var(allbutself);
>  }
>  
> +static int stopping_cpu;

Is access to this variable sufficiently serialized by all callpaths 
of stop_other_cpus()?

> +
> +static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
> +{
> +	/* We are registerd on stopping cpu too, avoid spurious NMI */
> +	if (raw_smp_processor_id() == stopping_cpu)
> +		return NMI_HANDLED;
> +
> +	stop_this_cpu(NULL);
> +
> +	return NMI_HANDLED;
> +}
> +
> +static void native_nmi_stop_other_cpus(int wait)
> +{
> +	unsigned long flags;
> +	unsigned long timeout;
> +
> +	if (reboot_force)
> +		return;
> +
> +	/*
> +	 * Use an own vector here because smp_call_function
> +	 * does lots of things not suitable in a panic situation.
> +	 */
> +	if (num_online_cpus() > 1) {
> +		stopping_cpu = safe_smp_processor_id();
> +
> +		if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
> +					 NMI_FLAG_FIRST, "smp_stop"))
> +			return;		/* return what? */
> +
> +		/* sync above data before sending NMI */
> +		wmb();
> +
> +		apic->send_IPI_allbutself(NMI_VECTOR);
> +
> +		/*
> +		 * Don't wait longer than a second if the caller
> +		 * didn't ask us to wait.
> +		 */
> +		timeout = USEC_PER_SEC;
> +		while (num_online_cpus() > 1 && (wait || timeout--))
> +			udelay(1);
> +	}
> +
> +	local_irq_save(flags);
> +	disable_local_APIC();
> +	local_irq_restore(flags);
> +}
> +
>  /*
>   * this function calls the 'stop' function on all other CPUs in the system.
>   */
> @@ -159,7 +211,7 @@ asmlinkage void smp_reboot_interrupt(void)
>  	irq_exit();
>  }
>  
> -static void native_stop_other_cpus(int wait)
> +static void native_irq_stop_other_cpus(int wait)
>  {
>  	unsigned long flags;
>  	unsigned long timeout;
> @@ -229,7 +281,7 @@ struct smp_ops smp_ops = {
>  	.smp_prepare_cpus	= native_smp_prepare_cpus,
>  	.smp_cpus_done		= native_smp_cpus_done,
>  
> -	.stop_other_cpus	= native_stop_other_cpus,
> +	.stop_other_cpus	= native_nmi_stop_other_cpus,
>  	.smp_send_reschedule	= native_smp_send_reschedule,
>  
>  	.cpu_up			= native_cpu_up,

I'd be fine about this if you also aded some sort of 
CONFIG_KERNEL_DEBUG dependent test facility that did a "send NMI to 
all CPUs and check that they truly arrive" non-destructive test.

That would at least give people an automatic way to test it without 
waiting for the first crash of their kernel.

Thanks,

	Ingo