RE: [PATCH v6 04/16] ACPI: processor: Move checks and availability of acpi_processor earlier

[Salil Mehta <salil.mehta@huawei.com>]

>  From: Jonathan Cameron <jonathan.cameron@huawei.com>
>  Sent: Wednesday, April 17, 2024 2:19 PM
>  
>  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@huawei.com>
>  ---
>  v6: As per discussion in v5 thread, don't use the cpu->dev and
>      make this data available earlier by moving the assignment checks
>      int acpi_processor_get_info().
>  ---
>   drivers/acpi/acpi_processor.c | 79 +++++++++++++++++++++--------------
>   1 file changed, 47 insertions(+), 32 deletions(-)
>  
>  diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
>  index ba0a6f0ac841..2c164451ab53 100644
>  --- a/drivers/acpi/acpi_processor.c
>  +++ b/drivers/acpi/acpi_processor.c
>  @@ -184,7 +184,35 @@ static void __init acpi_pcc_cpufreq_init(void) {}
>  
>   /* Initialization */
>   #ifdef CONFIG_ACPI_HOTPLUG_CPU
>  -static int acpi_processor_hotadd_init(struct acpi_processor *pr)
>  +static DEFINE_PER_CPU(void *, processor_device_array);
>  +
>  +static void acpi_processor_set_per_cpu(struct acpi_processor *pr,
>  +				       struct acpi_device *device)
>  +{
>  +	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. */
>  +		return;
>  +	}
>  +	/*
>  +	 * 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;
>  +}
>  +
>  +static int acpi_processor_hotadd_init(struct acpi_processor *pr,
>  +				      struct acpi_device *device)
>   {
>   	int ret;
>  
>  @@ -198,6 +226,8 @@ static int acpi_processor_hotadd_init(struct
>  acpi_processor *pr)
>   	if (ret)
>   		goto out;
>  
>  +	acpi_processor_set_per_cpu(pr, device);
>  +
>   	ret = arch_register_cpu(pr->id);
>   	if (ret) {
>   		acpi_unmap_cpu(pr->id);
>  @@ -217,7 +247,8 @@ 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;
>   }
>  @@ -232,6 +263,7 @@ static int acpi_processor_get_info(struct acpi_device
>  *device)
>   	acpi_status status = AE_OK;
>   	static int cpu0_initialized;
>   	unsigned long long value;
>  +	int ret;
>  
>   	acpi_processor_errata();
>  
>  @@ -316,10 +348,12 @@ 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);
>  +		ret = acpi_processor_hotadd_init(pr, device);
>  
>   		if (ret)
>  -			return ret;
>  +			goto err;
>  +	} else {
>  +		acpi_processor_set_per_cpu(pr, device);
>   	}
>  
>   	/*
>  @@ -357,6 +391,10 @@ static int acpi_processor_get_info(struct
>  acpi_device *device)
>   		arch_fix_phys_package_id(pr->id, value);
>  
>   	return 0;
>  +
>  +err:
>  +	per_cpu(processors, pr->id) = NULL;
>  +	return ret;
>   }
>  
>   /*
>  @@ -365,8 +403,6 @@ 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 +431,6 @@ 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;
>  @@ -469,15 +483,16 @@ 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();
>  
>   	/* Remove the CPU. */
>   	arch_unregister_cpu(pr->id);
>  +
>  +	/* Clean up. */
>  +	per_cpu(processor_device_array, pr->id) = NULL;
>  +	per_cpu(processors, pr->id) = NULL;
>  +


Shouldn't above change come after acpi_unmap_cpu() i.e. after next line?


>   	acpi_unmap_cpu(pr->id);
>  
>   	cpus_write_unlock();
>  --
>  2.39.2