Re: [RFC PATCH v2 22/35] ACPI: Check _STA present bit before making CPUs not present

[Gavin Shan]

On 9/14/23 02:38, James Morse wrote:
> When called acpi_processor_post_eject() unconditionally make a CPU
> not-present and unregisters it.
>
> To add support for AML events where the CPU has become disabled, but
> remains present, the _STA method should be checked before calling
> acpi_processor_remove().
>
> Rename acpi_processor_post_eject() acpi_processor_remove_possible(), and
> check the _STA before calling.
>
> Adding the function prototype for arch_unregister_cpu() allows the
> preprocessor guards to be removed.
>
> After this change CPUs will remain registered and visible to
> user-space as offline if buggy firmware triggers an eject-request,
> but doesn't clear the corresponding _STA bits after _EJ0 has been
> called.
>
> Signed-off-by: James Morse <james.morse@xxxxxxx>
> ---
>   drivers/acpi/acpi_processor.c | 31 +++++++++++++++++++++++++------
>   include/linux/cpu.h           |  1 +
>   2 files changed, 26 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
> index 00dcc23d49a8..2cafea1edc24 100644
> --- a/drivers/acpi/acpi_processor.c
> +++ b/drivers/acpi/acpi_processor.c
> @@ -457,13 +457,12 @@ static int acpi_processor_add(struct acpi_device *device,
>   	return result;
>   }
>   
> -#ifdef CONFIG_ACPI_HOTPLUG_PRESENT_CPU
>   /* Removal */
> -static void acpi_processor_post_eject(struct acpi_device *device)
> +static void acpi_processor_make_not_present(struct acpi_device *device)
>   {
>   	struct acpi_processor *pr;
>   
> -	if (!device || !acpi_driver_data(device))
> +	if (!IS_ENABLED(CONFIG_ACPI_HOTPLUG_PRESENT_CPU))
>   		return;
>   

In order to use IS_ENABLED(),

>   	pr = acpi_driver_data(device);
> @@ -501,7 +500,29 @@ static void acpi_processor_post_eject(struct acpi_device *device)
>   	free_cpumask_var(pr->throttling.shared_cpu_map);
>   	kfree(pr);
>   }
> -#endif /* CONFIG_ACPI_HOTPLUG_PRESENT_CPU */
> +
> +static void acpi_processor_post_eject(struct acpi_device *device)
> +{
> +	struct acpi_processor *pr;
> +	unsigned long long sta;
> +	acpi_status status;
> +
> +	if (!device)
> +		return;
> +
> +	pr = acpi_driver_data(device);
> +	if (!pr || pr->id >= nr_cpu_ids || invalid_phys_cpuid(pr->phys_id))
> +		return;
> +

Do we really need to validate the logic and hardware CPU IDs here? I think
the ACPI processor device can't be added successfully if one of them is
invalid.

> +	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
> +	if (ACPI_FAILURE(status))
> +		return;
> +
> +	if (cpu_present(pr->id) && !(sta & ACPI_STA_DEVICE_PRESENT)) {
> +		acpi_processor_make_not_present(device);
> +		return;
> +	}
> +}
>   
>   #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC
>   bool __init processor_physically_present(acpi_handle handle)
> @@ -626,9 +647,7 @@ static const struct acpi_device_id processor_device_ids[] = {
>   static struct acpi_scan_handler processor_handler = {
>   	.ids = processor_device_ids,
>   	.attach = acpi_processor_add,
> -#ifdef CONFIG_ACPI_HOTPLUG_PRESENT_CPU
>   	.post_eject = acpi_processor_post_eject,
> -#endif
>   	.hotplug = {
>   		.enabled = true,
>   	},
> diff --git a/include/linux/cpu.h b/include/linux/cpu.h
> index a71691d7c2ca..e117c06e0c6b 100644
> --- a/include/linux/cpu.h
> +++ b/include/linux/cpu.h
> @@ -81,6 +81,7 @@ struct device *cpu_device_create(struct device *parent, void *drvdata,
>   				 const struct attribute_group **groups,
>   				 const char *fmt, ...);
>   extern int arch_register_cpu(int cpu);
> +extern void arch_unregister_cpu(int cpu);

arch_unregister_cpu() is protected by CONFIG_HOTPLUG_CPU in the individual architectures,
for example arch/ia64/kernel/topology.c

>   #ifdef CONFIG_HOTPLUG_CPU
>   extern void unregister_cpu(struct cpu *cpu);
>   extern ssize_t arch_cpu_probe(const char *, size_t);

Thanks,
Gavin