Re: [PATCH v2 5/5] drm/xe/debugfs: Add interface to trigger power management unit error handler

["Tauro, Riana" <riana.tauro@intel.com>]

On 3/18/2026 12:10 PM, Mallesh Koujalagi wrote:
> Add a debugfs interface to manually trigger power management unit error
> handler for testing cold reset recovery paths. This is useful for
> validating the error recovery mechanism.
>
> The new debugfs entry 'trigger_punit_error' is located at:
>    /sys/kernel/debug/dri/N/trigger_punit_error
>
> Reading the file displays usage instructions. Writing '1' invokes
> xe_punit_error_handler(), which marks the device as wedged with
> DRM_WEDGE_RECOVERY_COLD_RESET method and sends a uevent to userspace
> indicating that a complete device power cycle is required for recovery.
>
> Writing '0' or any other false value has no effect.
>
> This interface is intended for development, testing, and validation
> of power management unit error recovery code.

Would fault injection be more appropriate here?

Thanks
Riana

> Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_debugfs.c | 38 +++++++++++++++++++++++++++++++++
>   1 file changed, 38 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
> index 844cfafe1ec7..390bbed9c1af 100644
> --- a/drivers/gpu/drm/xe/xe_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_debugfs.c
> @@ -18,6 +18,7 @@
>   #include "xe_gt_debugfs.h"
>   #include "xe_gt_printk.h"
>   #include "xe_guc_ads.h"
> +#include "xe_hw_error.h"
>   #include "xe_mmio.h"
>   #include "xe_pm.h"
>   #include "xe_psmi.h"
> @@ -509,6 +510,40 @@ static const struct file_operations disable_late_binding_fops = {
>   	.write = disable_late_binding_set,
>   };
>   
> +static ssize_t trigger_punit_error_show(struct file *f, char __user *ubuf,
> +					size_t size, loff_t *pos)
> +{
> +	const char *msg = "Write 1 to trigger power management unit error handler\n";
> +
> +	return simple_read_from_buffer(ubuf, size, pos, msg, strlen(msg));
> +}
> +
> +static ssize_t trigger_punit_error_set(struct file *f,
> +				       const char __user *ubuf,
> +				       size_t size, loff_t *pos)
> +{
> +	struct xe_device *xe = file_inode(f)->i_private;
> +	bool trigger;
> +	ssize_t ret;
> +
> +	ret = kstrtobool_from_user(ubuf, size, &trigger);
> +	if (ret)
> +		return ret;
> +
> +	if (trigger) {
> +		xe_punit_error_handler(xe);
> +		drm_info(&xe->drm, "PMU error handler triggered via debugfs\n");
> +	}
> +
> +	return size;
> +}
> +
> +static const struct file_operations trigger_punit_error_fops = {
> +	.owner = THIS_MODULE,
> +	.read = trigger_punit_error_show,
> +	.write = trigger_punit_error_set,
> +};
> +
>   void xe_debugfs_register(struct xe_device *xe)
>   {
>   	struct ttm_device *bdev = &xe->ttm;
> @@ -550,6 +585,9 @@ void xe_debugfs_register(struct xe_device *xe)
>   	debugfs_create_file("disable_late_binding", 0600, root, xe,
>   			    &disable_late_binding_fops);
>   
> +	debugfs_create_file("trigger_punit_error", 0600, root, xe,
> +			    &trigger_punit_error_fops);
> +
>   	/*
>   	 * Don't expose page reclaim configuration file if not supported by the
>   	 * hardware initially.