Re: [PATCH] locking: Revert switching guards to _irq_{disable,enable}()

[Peter Zijlstra <peterz@infradead.org>]

On Sat, Aug 29, 2026 at 01:11:56AM +0200, Thomas Gleixner wrote:

> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
> index 346c438ac880..b0be24a386f3 100644
> --- a/arch/x86/kernel/process.c
> +++ b/arch/x86/kernel/process.c
> @@ -824,7 +824,7 @@ void __noreturn stop_this_cpu(void *dummy)
>  	struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info);
>  	unsigned int cpu = smp_processor_id();
>  
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  
>  	/*
>  	 * Remove this CPU from the online mask and disable it
> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
> index 0fed6d0d7e32..40104170be24 100644
> --- a/arch/x86/kernel/reboot.c
> +++ b/arch/x86/kernel/reboot.c
> @@ -98,7 +98,7 @@ static int __init set_efi_reboot(const struct dmi_system_id *d)
>  
>  void __noreturn machine_real_restart(unsigned int type)
>  {
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  
>  	/*
>  	 * Write zero to CMOS register number 0x0f, which the BIOS POST
> @@ -535,7 +535,7 @@ static inline void nmi_shootdown_cpus_on_restart(void);
>  #if IS_ENABLED(CONFIG_KVM_X86)
>  static void emergency_reboot_disable_virtualization(void)
>  {
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  
>  	/*
>  	 * Disable virtualization on all CPUs before rebooting to avoid hanging
> @@ -699,7 +699,7 @@ void native_machine_shutdown(void)
>  	 * not receive the per-cpu timer interrupt which may trigger
>  	 * scheduler's load balance.
>  	 */
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  	stop_other_cpus();
>  #endif
>  
> @@ -823,7 +823,8 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
>  	 */
>  	if (cpu == crashing_cpu)
>  		return NMI_HANDLED;
> -	local_irq_disable();
> +
> +	raw_force_local_irq_disable();
>  
>  	if (shootdown_callback)
>  		shootdown_callback(cpu, regs);
> @@ -865,7 +866,7 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
>  {
>  	unsigned long msecs;
>  
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  
>  	/*
>  	 * Avoid certain doom if a shootdown already occurred; re-registering

> diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
> index 132a9df98471..f13e88fb7a78 100644
> --- a/drivers/acpi/sleep.c
> +++ b/drivers/acpi/sleep.c
> @@ -1095,7 +1095,7 @@ static int acpi_power_off(struct sys_off_data *data)
>  {
>  	/* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */
>  	pr_debug("%s called\n", __func__);
> -	local_irq_disable();
> +	raw_force_local_irq_disable();
>  	acpi_enter_sleep_state(ACPI_STATE_S5);
>  	return NOTIFY_DONE;
>  }

> diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
> index 57b074e0cfbb..dd55786768d1 100644
> --- a/include/linux/irqflags.h
> +++ b/include/linux/irqflags.h

> +static __always_inline void raw_force_local_irq_disable(void)
> +{
> +	arch_local_irq_disable();
> +	__preempt_count_add(HARDIRQ_DISABLE_OFFSET);
> +}

So this thing is on all sorts of don't care, we're going down paths. It
needs to ensure IRQs really are off, and preempt_count has at least one
DISABLE_OFFSET on.

*However* if something like acpi_power_off() were to 'fail' to enter S5
and continue on with the notifier, things are now unbalanced. Probably
not a problem, since the next handler will likely do
raw_force_load_irq_disable() again.

At the least this wants a comment I suppose.


> diff --git a/init/main.c b/init/main.c
> index 2613d3f9b3ce..fa84ce260b04 100644
> --- a/init/main.c
> +++ b/init/main.c
> @@ -991,7 +991,6 @@ void start_kernel(void)
>  
>  	cgroup_init_early();
>  
> -	local_irq_disable();
>  	early_boot_irqs_disabled = true;

If we want to preserve the paranoia of having that statement in the
first place, it could be replaced with something like:

	WARN_ON_ONCE(!irqs_disabled());

I suppose (lockdep isn't available yet).