Received-SPF: pass (google.com: domain of linux-kernel+bounces-165148-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Message-ID: <0febde44-99f1-48ba-a233-78b9a32468da@redhat.com>
Date: Wed, 1 May 2024 20:33:27 +1000
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v9 06/19] ACPI: processor: Move checks and availability of
 acpi_processor earlier
Content-Language: en-US
To: Jonathan Cameron <Jonathan.Cameron@huawei.com>,
 Thomas Gleixner <tglx@linutronix.de>, Peter Zijlstra <peterz@infradead.org>,
 linux-pm@vger.kernel.org, loongarch@lists.linux.dev,
 linux-acpi@vger.kernel.org, linux-arch@vger.kernel.org,
 linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
 kvmarm@lists.linux.dev, x86@kernel.org, Russell King
 <linux@armlinux.org.uk>, "Rafael J . Wysocki" <rafael@kernel.org>,
 Miguel Luis <miguel.luis@oracle.com>, James Morse <james.morse@arm.com>,
 Salil Mehta <salil.mehta@huawei.com>,
 Jean-Philippe Brucker <jean-philippe@linaro.org>,
 Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will@kernel.org>,
 Marc Zyngier <maz@kernel.org>, Hanjun Guo <guohanjun@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
 Dave Hansen <dave.hansen@linux.intel.com>, linuxarm@huawei.com,
 justin.he@arm.com, jianyong.wu@arm.com
References: <20240430142434.10471-1-Jonathan.Cameron@huawei.com>
 <20240430142434.10471-7-Jonathan.Cameron@huawei.com>
From: Gavin Shan <gshan@redhat.com>
In-Reply-To: <20240430142434.10471-7-Jonathan.Cameron@huawei.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

On 5/1/24 00:24, 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@huawei.com>
> 
> ---
> v9: Add back a blank line accidentally removed in code move.
>      Fix up error returns so that the new cleanup in processor_add()
>      is triggered on detection of the bios bug.
>      Combined with the previous 2 patches, should solve the leak
>      that Gavin identified.
> ---
>   drivers/acpi/acpi_processor.c | 80 +++++++++++++++++++++--------------
>   1 file changed, 49 insertions(+), 31 deletions(-)
> 

It would be nice for acpi_processor_set_per_cpu() to return errno,
explained as below. The patch looks good to me in either me.

Reviewed-by: Gavin Shan <gshan@redhat.com>

> diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
> index 16e36e55a560..4a79b42d649e 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);
> +
> +	/*
> +	 * 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);
> +		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;
> +}
> +

I think it'd better for acpi_processor_set_per_cpu() to return errno. -EINVAL
is returned if a mismatched ACPI device is found, and 0 is returned on success.

With the improvement, the callers needn't to translate boolen to errno.

>   #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 +228,16 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
>   	if (ret)
>   		goto out;
>   
> +	if (!acpi_processor_set_per_cpu(pr, device)) {
> +		ret = -EINVAL;
> +		acpi_unmap_cpu(pr->id);
> +		goto out;
> +	}
> +

If errno is returned from acpi_processor_set_per_cpu(), this chunk of code becomes:

	ret = acpi_processor_set_per_cpu(pr, device);
	if (ret) {
		acpi_unmap_cpu(pr->id);
		goto out;
	}

>   	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 +255,8 @@ 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 +355,13 @@ 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 -EINVAL;
>   	}
>   

		ret = acpi_processor_set_per_cpu(pr, device);
		if (ret)
			return ret;

>   	/*
> @@ -365,8 +407,6 @@ 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 +435,6 @@ static int acpi_processor_add(struct acpi_device *device,
>   	if (result) /* Processor is not physically present or unavailable */
>   		goto err_clear_driver_data;
>   
> -	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_clear_driver_data;
> -	}
> -	/*
> -	 * 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;
> @@ -470,10 +488,6 @@ 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();
>   
> @@ -481,6 +495,10 @@ 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