Re: [PATCH v3 1/6] drm/xe/cper: Add software CPER emission entry point

["Nilawar, Badal" <badal.nilawar@intel.com>]

On 05-11-2026 14:23, Mallesh Koujalagi wrote:
> Add a software CPER emission handler for CRI SIGIDs.
>
> Keep hardware CPER handling unchanged and return early
> when the Xe device is unavailable.
>
> Cc: Badal Nilawar <badal.nilawar@intel.com>
> Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> ---
> v3:
> - Handle early PCI probe where xe device is null. (Sashiko)
> ---
>   drivers/gpu/drm/xe/xe_cper.c | 22 +++++++++++++++++++++-
>   1 file changed, 21 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_cper.c b/drivers/gpu/drm/xe/xe_cper.c
> index bb90030bcd2d..db3513c59834 100644
> --- a/drivers/gpu/drm/xe/xe_cper.c
> +++ b/drivers/gpu/drm/xe/xe_cper.c
> @@ -32,6 +32,11 @@ static bool is_hw_sigid(enum xe_sigid sigid)
>   	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
>   }
>   
> +static bool is_sw_sigid(enum xe_sigid sigid)
> +{
> +	return in_range(sigid, INTEL_SIGID_GPU_XE_SOFTWARE_START, INTEL_SIGID_BATCH);
> +}
> +
>   /* CPER platform_id GUIDs (RFC 9562 UUIDv5) for each PCI device ID. */
>   static const struct xe_device_guid_entry xe_device_guids[] = {
>   	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
> @@ -240,6 +245,12 @@ static void cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid s
>   	xe_cper_emit_counter(xe, cper_sev, sigid, counter, &response);
>   }
>   
> +static void cper_emit_sw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
> +			     u32 component, u32 location, const void *data,
> +			     struct va_format *vaf)
> +{
> +}
> +
>   /**
>    * xe_cper_emit() - Emit a CPER record for a SIGID log entry
>    * @xe: The &xe_device
> @@ -268,12 +279,21 @@ void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
>   		  u32 component, u32 location, const void *data, size_t len,
>   		  struct va_format *vaf)
>   {
> +	if (!xe)
> +		return;

xe is expected to be valid here. Silently returning on NULL would hide a 
caller bug.

> +
>   	if (is_hw_sigid(sigid) && !IS_ERR_OR_NULL(data)) {
>   		cper_emit_hw_err(xe, cper_sev, sigid, data);
>   		return;
>   	}
>   
> -	/* TODO software CPER */
> +	if (xe->info.platform == XE_CRESCENTISLAND) {

Introduce has_driver_cper flag here.

Thanks,
Badal

> +		if (is_sw_sigid(sigid) &&
> +		    (cper_sev == CPER_SEV_RECOVERABLE ||
> +		     cper_sev == CPER_SEV_FATAL))
> +			cper_emit_sw_err(xe, cper_sev, sigid, component, location, data, vaf);
> +		return;
> +	}
>   }
>   
>   static ssize_t cper_on_query_show(struct device *dev, struct device_attribute *attr, char *buf)