[PATCH v1] Input: atlas - Check ACPI_COMPANION() against NULL

[PATCH v1] Input: atlas - Check ACPI_COMPANION() against NULL

[Rafael J. Wysocki]

From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>

Every platform driver can be forced to match a device that doesn't match
its list of device IDs because of device_match_driver_override(), so
platform drivers that rely on the existence of a device's ACPI companion
object need to verify its presence.

Accordingly, add a requisite ACPI_COMPANION() check against NULL to the
atlas_btns driver.

Fixes: b8303880b641 ("Input: atlas - convert ACPI driver to a platform one")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/input/misc/atlas_btns.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/input/misc/atlas_btns.c
+++ b/drivers/input/misc/atlas_btns.c
@@ -60,11 +60,15 @@ static acpi_status acpi_atlas_button_han
 
 static int atlas_acpi_button_probe(struct platform_device *pdev)
 {
-	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+	struct acpi_device *device;
 	acpi_status status;
 	int i;
 	int err;
 
+	device = ACPI_COMPANION(&pdev->dev);
+	if (!device)
+		return -ENODEV;
+
 	input_dev = input_allocate_device();
 	if (!input_dev) {
 		pr_err("unable to allocate input device\n");

Re: [PATCH v1] Input: atlas - Check ACPI_COMPANION() against NULL

[Dmitry Torokhov]

On Tue, May 12, 2026 at 06:26:54PM +0200, Rafael J. Wysocki wrote:
> From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
> 
> Every platform driver can be forced to match a device that doesn't match
> its list of device IDs because of device_match_driver_override(), so
> platform drivers that rely on the existence of a device's ACPI companion
> object need to verify its presence.
> 
> Accordingly, add a requisite ACPI_COMPANION() check against NULL to the
> atlas_btns driver.
> 
> Fixes: b8303880b641 ("Input: atlas - convert ACPI driver to a platform one")
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Applied, thank you.

-- 
Dmitry

Re: [PATCH v1] Input: atlas - Check ACPI_COMPANION() against NULL

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Incomplete Fix for driver_override Abuse (Global State Corruption)
--

commit ef51cbfbb2dd379fb06abd9c22db66e86bb70eb3
Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Input: atlas - Check ACPI_COMPANION() against NULL

This commit adds a check to ensure the ACPI companion device is present in
the atlas_btns driver to prevent issues when a device is forced to match
via device_match_driver_override().

> diff --git a/drivers/input/misc/atlas_btns.c b/drivers/input/misc/atlas_btns.c
> index 47b31725e8507..835ad45a9d65c 100644
> --- a/drivers/input/misc/atlas_btns.c
> +++ b/drivers/input/misc/atlas_btns.c
> @@ -60,11 +60,15 @@ static acpi_status acpi_atlas_button_handler(u32 function,
>  
>  static int atlas_acpi_button_probe(struct platform_device *pdev)
>  {
> -	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
> +	struct acpi_device *device;
>  	acpi_status status;
>  	int i;
>  	int err;
>  
> +	device = ACPI_COMPANION(&pdev->dev);
> +	if (!device)
> +		return -ENODEV;
> +
>  	input_dev = input_allocate_device();

The commit message mentions this check is to protect against
device_match_driver_override() forcing a match with unexpected devices.

If driver_override is used to force-bind this driver to multiple platform
devices that do have ACPI companions, could this cause issues with the global
input_dev variable?

Since input_dev is overwritten on each successful probe, it looks like earlier
allocated input devices would be leaked if multiple bindings succeed.

Additionally, if these devices are later unbound, or if a subsequent probe
fails after modifying input_dev, could this lead to a double-free or null
pointer dereference when the shared input_dev pointer is cleaned up?

Would it make sense to either reject multiple bindings or store the input
device in the platform device's private data using platform_set_drvdata()?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/8696590.T7Z3S40VBb@rafael.j.wysocki?part=1