Re: [PATCH v8 04/16] ACPI: processor: Move checks and availability of acpi_processor earlier

[Gavin Shan]

On 4/26/24 23:51, Jonathan Cameron wrote:
> Make the per_cpu(processors, cpu) entries available earlier so that
> they are available in arch_register_cpu() as ARM64 will need access
> to the acpi_handle to distinguish between acpi_processor_add()
> and earlier registration attempts (which will fail as _STA cannot
> be checked).
>
> Reorder the remove flow to clear this per_cpu() after
> arch_unregister_cpu() has completed, allowing it to be used in
> there as well.
>
> Note that on x86 for the CPU hotplug case, the pr->id prior to
> acpi_map_cpu() may be invalid. Thus the per_cpu() structures
> must be initialized after that call or after checking the ID
> is valid (not hotplug path).
>
> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
>
> ---
> v8: On buggy bios detection when setting per_cpu structures
>      do not carry on.
>      Fix up the clearing of per cpu structures to remove unwanted
>      side effects and ensure an error code isn't use to reference them.
> ---
>   drivers/acpi/acpi_processor.c | 79 +++++++++++++++++++++--------------
>   1 file changed, 48 insertions(+), 31 deletions(-)
>
> diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
> index ba0a6f0ac841..3b180e21f325 100644
> --- a/drivers/acpi/acpi_processor.c
> +++ b/drivers/acpi/acpi_processor.c
> @@ -183,8 +183,38 @@ static void __init acpi_pcc_cpufreq_init(void) {}
>   #endif /* CONFIG_X86 */
>   
>   /* Initialization */
> +static DEFINE_PER_CPU(void *, processor_device_array);
> +
> +static bool acpi_processor_set_per_cpu(struct acpi_processor *pr,
> +				       struct acpi_device *device)
> +{
> +	BUG_ON(pr->id >= nr_cpu_ids);

One blank line after BUG_ON() if we need to follow original implementation.

> +	/*
> +	 * Buggy BIOS check.
> +	 * ACPI id of processors can be reported wrongly by the BIOS.
> +	 * Don't trust it blindly
> +	 */
> +	if (per_cpu(processor_device_array, pr->id) != NULL &&
> +	    per_cpu(processor_device_array, pr->id) != device) {
> +		dev_warn(&device->dev,
> +			 "BIOS reported wrong ACPI id %d for the processor\n",
> +			 pr->id);
> +		/* Give up, but do not abort the namespace scan. */

It depends on how the return value is handled by the caller if the namespace
is continued to be scanned. The caller can be acpi_processor_hotadd_init()
and acpi_processor_get_info() after this patch is applied. So I think this
specific comment need to be moved to the caller.

Besides, it seems acpi_processor_set_per_cpu() isn't properly called and
memory leakage can happen. More details are given below.

> +		return false;
> +	}
> +	/*
> +	 * processor_device_array is not cleared on errors to allow buggy BIOS
> +	 * checks.
> +	 */
> +	per_cpu(processor_device_array, pr->id) = device;
> +	per_cpu(processors, pr->id) = pr;
> +
> +	return true;
> +}
> +
>   #ifdef CONFIG_ACPI_HOTPLUG_CPU
> -static int acpi_processor_hotadd_init(struct acpi_processor *pr)
> +static int acpi_processor_hotadd_init(struct acpi_processor *pr,
> +				      struct acpi_device *device)
>   {
>   	int ret;
>   
> @@ -198,8 +228,15 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
>   	if (ret)
>   		goto out;
>   
> +	if (!acpi_processor_set_per_cpu(pr, device)) {
> +		acpi_unmap_cpu(pr->id);
> +		goto out;
> +	}
> +

With the 'goto out', zero is returned from acpi_processor_hotadd_init() to acpi_processor_get_info().
The zero return value is carried from acpi_map_cpu() in acpi_processor_hotadd_init(). If I'm correct,
we need return errno from acpi_processor_get_info() to acpi_processor_add() so that cleanup can be
done. For example, the cleanup corresponding to the 'err' tag can be done in acpi_processor_add().
Otherwise, we will have memory leakage.

>   	ret = arch_register_cpu(pr->id);
>   	if (ret) {
> +		/* Leave the processor device array in place to detect buggy bios */
> +		per_cpu(processors, pr->id) = NULL;
>   		acpi_unmap_cpu(pr->id);
>   		goto out;
>   	}
> @@ -217,7 +254,8 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
>   	return ret;
>   }
>   #else
> -static inline int acpi_processor_hotadd_init(struct acpi_processor *pr)
> +static inline int acpi_processor_hotadd_init(struct acpi_processor *pr,
> +					     struct acpi_device *device)
>   {
>   	return -ENODEV;
>   }
> @@ -316,10 +354,13 @@ static int acpi_processor_get_info(struct acpi_device *device)
>   	 *  because cpuid <-> apicid mapping is persistent now.
>   	 */
>   	if (invalid_logical_cpuid(pr->id) || !cpu_present(pr->id)) {
> -		int ret = acpi_processor_hotadd_init(pr);
> +		int ret = acpi_processor_hotadd_init(pr, device);
>   
>   		if (ret)
>   			return ret;
> +	} else {
> +		if (!acpi_processor_set_per_cpu(pr, device))
> +			return 0;
>   	}
>   

For non-hotplug case, we still need pass the error to acpi_processor_add() so that
cleanup corresponding 'err' tag can be done. Otherwise, we will have memory leakage.

>   	/*
> @@ -365,8 +406,6 @@ static int acpi_processor_get_info(struct acpi_device *device)
>    * (cpu_data(cpu)) values, like CPU feature flags, family, model, etc.
>    * Such things have to be put in and set up by the processor driver's .probe().
>    */
> -static DEFINE_PER_CPU(void *, processor_device_array);
> -
>   static int acpi_processor_add(struct acpi_device *device,
>   					const struct acpi_device_id *id)
>   {
> @@ -395,28 +434,6 @@ static int acpi_processor_add(struct acpi_device *device,
>   	if (result) /* Processor is not physically present or unavailable */
>   		return 0;
>   
> -	BUG_ON(pr->id >= nr_cpu_ids);
> -
> -	/*
> -	 * Buggy BIOS check.
> -	 * ACPI id of processors can be reported wrongly by the BIOS.
> -	 * Don't trust it blindly
> -	 */
> -	if (per_cpu(processor_device_array, pr->id) != NULL &&
> -	    per_cpu(processor_device_array, pr->id) != device) {
> -		dev_warn(&device->dev,
> -			"BIOS reported wrong ACPI id %d for the processor\n",
> -			pr->id);
> -		/* Give up, but do not abort the namespace scan. */
> -		goto err;
> -	}
> -	/*
> -	 * processor_device_array is not cleared on errors to allow buggy BIOS
> -	 * checks.
> -	 */
> -	per_cpu(processor_device_array, pr->id) = device;
> -	per_cpu(processors, pr->id) = pr;
> -
>   	dev = get_cpu_device(pr->id);
>   	if (!dev) {
>   		result = -ENODEV;
> @@ -469,10 +486,6 @@ static void acpi_processor_remove(struct acpi_device *device)
>   	device_release_driver(pr->dev);
>   	acpi_unbind_one(pr->dev);
>   
> -	/* Clean up. */
> -	per_cpu(processor_device_array, pr->id) = NULL;
> -	per_cpu(processors, pr->id) = NULL;
> -
>   	cpu_maps_update_begin();
>   	cpus_write_lock();
>   
> @@ -480,6 +493,10 @@ static void acpi_processor_remove(struct acpi_device *device)
>   	arch_unregister_cpu(pr->id);
>   	acpi_unmap_cpu(pr->id);
>   
> +	/* Clean up. */
> +	per_cpu(processor_device_array, pr->id) = NULL;
> +	per_cpu(processors, pr->id) = NULL;
> +
>   	cpus_write_unlock();
>   	cpu_maps_update_done();
>   

Thanks,
Gavin