Re: [PATCH v6 04/10] drm/xe/cper: Construct CPER record for hardware errors

[Raag Jadav <raag.jadav@intel.com>]

On Wed, Oct 28, 2026 at 03:27:28PM +0530, Badal Nilawar wrote:
> Assemble the CPER record header, section descriptor and the Intel
> error section for Intel GPU hardware errors.

...

> +static void cper_init_record_hdr(struct xe_device *xe, u8 severity,
> +				 const guid_t *notification_type,
> +				 struct cper_record_header *rhdr,
> +				 u32 total_len)
> +{
> +	const guid_t *device_guid;
> +	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);

Reverse xmas order please!

> +	/* Assemble the CPER record header (UEFI Appendix N.2.1) */
> +	memcpy(rhdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
> +	rhdr->revision          = CPER_RECORD_REV;
> +	rhdr->signature_end     = CPER_SIG_END;
> +	rhdr->section_count     = 1;
> +	rhdr->error_severity    = severity;
> +	rhdr->validation_bits   = CPER_VALID_TIMESTAMP;
> +	rhdr->record_length     = total_len;
> +	rhdr->timestamp         = cper_timestamp_now();
> +	rhdr->creator_id        = INTEL_CPER_CREATOR_XEKMD;
> +	rhdr->notification_type = *notification_type;
> +	rhdr->record_id         = cper_next_record_id();

Blank line here.

> +	device_guid = lookup_device_guid(pdev);
> +	if (device_guid) {
> +		rhdr->platform_id      = *device_guid;
> +		rhdr->validation_bits |= CPER_VALID_PLATFORM_ID;
> +	} else {
> +		xe_printk(xe, warn_once, "CPER: no platform GUID for device %04x\n",
> +			  pdev->device);

Move this to lookup_device_guid() before returning NULL.

> +	}
> +}
> +
> +static void cper_init_section_desc(struct xe_device *xe, u8 severity,
> +				   struct cper_section_descriptor *sdesc,
> +				   u32 einfo_len)
> +{
> +	sdesc->section_offset   = sizeof(struct cper_record_header) +
> +				  sizeof(struct cper_section_descriptor);
> +	sdesc->section_length   = sizeof(struct xe_cper_intel_hdr) + einfo_len;
> +	sdesc->revision         = CPER_SEC_REV;
> +	sdesc->validation_bits  = 0;
> +	sdesc->section_type     = INTEL_CPER_SECTION_ACCEL_GENERIC;
> +	sdesc->section_severity = severity;

Blank line here.

> +	if (xe->info.has_device_uid) {
> +		memcpy(&sdesc->fru_id, &xe->device_uid, sizeof(xe->device_uid));
> +		sdesc->validation_bits |= CPER_SEC_VALID_FRU_ID;
> +	}
> +}
> +
> +static void cper_record_emit(struct xe_device *xe, u8 severity,
> +			     const guid_t *notification_type,
> +			     const struct xe_cper_intel_hdr *ihdr,
> +			     const void *einfo, u32 einfo_len)
> +{
> +	struct cper_section_descriptor *sdesc;
> +	struct cper_record_header *rhdr;
> +	struct xe_cper_nonstd_record *rec;
> +	u32 total_len;

Reverse xmas order please!

And with that

Reviewed-by: Raag Jadav <raag.jadav@intel.com>

> +	total_len = sizeof(struct xe_cper_nonstd_record) + einfo_len;
> +	rec = kzalloc(total_len, GFP_KERNEL);
> +	if (!rec)
> +		return;
> +
> +	rhdr = &rec->record_hdr;
> +	sdesc = &rec->section_desc;
> +
> +	/* Assemble the CPER record header (UEFI Appendix N.2.1) */
> +	cper_init_record_hdr(xe, severity, notification_type, rhdr, total_len);
> +
> +	/* Assemble the section descriptor (UEFI Appendix N.2.2) */
> +	cper_init_section_desc(xe, severity, sdesc, einfo_len);
> +
> +	/* Copy the Intel-specific section header */
> +	rec->intel_hdr = *ihdr;
> +
> +	/* Append optional variable-length error info */
> +	if (einfo && einfo_len)
> +		memcpy((u8 *)rec + sizeof(*rec), einfo, einfo_len);
> +
> +	/* TODO: Emit trace event */
> +
> +	kfree(rec);
> +}