Re: [PATCH v2 07/11] drm/xe/cper: Allow hardware error CPER reporting from xe_log

[Michal Wajdeczko <michal.wajdeczko@intel.com>]

On 8/25/2026 7:59 PM, Badal Nilawar wrote:
> Add xe_emit_hardware_error_cper() as a public wrapper around the
> internal hardware CPER emission helper, enabling xe_log.c to emit
> hardware error CPER records.
> 
> Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_log.c | 17 +++++++++++------
>  drivers/gpu/drm/xe/xe_ras.c | 23 +++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_ras.h |  4 ++++
>  3 files changed, 38 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_log.c b/drivers/gpu/drm/xe/xe_log.c
> index 5549ef6966fd..c78fc195c55b 100644
> --- a/drivers/gpu/drm/xe/xe_log.c
> +++ b/drivers/gpu/drm/xe/xe_log.c
> @@ -10,15 +10,25 @@
>  
>  #include "xe_device.h"
>  #include "xe_log.h"
> +#include "xe_ras.h"
>  #include "xe_printk.h"
>  
> +static bool is_hw_sigid(enum xe_sigid sigid)
> +{
> +	return (int)sigid >= INTEL_SIGID_GPU_XE_HARDWARE_START;
> +}
> +
>  static void log_emit_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigid,
>  			  u32 component, u32 location, const void *data, size_t len,
>  			  struct va_format *vaf)
>  {
>  	KUNIT_STATIC_STUB_REDIRECT(log_emit_cper, pdev, cper_sev, sigid,
>  				   component, location, data, len, vaf);
> -	/* TODO */
> +	/* TODO software CPER */
> +
> +	if (is_hw_sigid(sigid))
> +		xe_emit_hardware_error_cper(pdev, cper_sev, sigid,
> +					    (struct xe_ras_error_class *)data);

make sure to check data len before doing a cast
also, maybe do all that in xe_emit_hardware_error_cper()
in case we would want to pass other blobs to xe_log

>  }
>  
>  static const char *log_unknown_component_prefix(u32 component)
> @@ -100,11 +110,6 @@ static const char *log_location_prefix(struct pci_dev *pdev, u32 location, char
>  	return buf;
>  }
>  
> -static bool is_hw_sigid(enum xe_sigid sigid)
> -{
> -	return (int)sigid >= INTEL_SIGID_GPU_XE_HARDWARE_START;
> -}
> -
>  static bool is_sev_error(int cper_sev)
>  {
>  	return cper_sev != CPER_SEV_INFORMATIONAL;
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index ff9d917b8e29..b4cdb5ec6491 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -837,6 +837,29 @@ static void emit_hw_error_cper(struct xe_device *xe,
>  	}
>  }
>  
> +/**
> + * xe_emit_hardware_error_cper() - Emit a hardware error CPER record

shouldn't this be named as:

	xe_ras_emit_hardware_cper

as we should use xe_ras prefix for functions in this file
and error is redundant as we already have cper in the name
> + * @pdev: PCI device associated with the Xe device
> + * @cper_sev: CPER severity
> + * @sigid: Error signature identifier
> + * @error_class: Hardware error classification details
> + *
> + * Emit a CPER record for a hardware error
> + */
> +void xe_emit_hardware_error_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigid,
> +				 struct xe_ras_error_class *counter)
> +{
> +	struct xe_device *xe = pdev_to_xe_device(pdev);

I guess we can pass xe to xe_emit_hardware_error_cper()
pdev was only needed in xe_log to cover early probe errors

> +
> +	if (!xe)
> +		return;
> +
> +	if (counter && !ras_counter_is_valid(xe, counter))
> +		return;
> +
> +	emit_hw_error_cper(xe, counter, NULL, sigid, cper_sev);
> +}
> +
>  /**
>   * xe_ras_process_errors() - Process and contain hardware errors
>   * @xe: xe device instance
> diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
> index 618364734043..e5c4b2e2e1fd 100644
> --- a/drivers/gpu/drm/xe/xe_ras.h
> +++ b/drivers/gpu/drm/xe/xe_ras.h
> @@ -7,6 +7,8 @@
>  #define _XE_RAS_H_
>  
>  #include <linux/types.h>
> +#include "abi/xe_sigid_abi.h"
> +#include "xe_device.h"

do we need this?

>  #include "xe_ras_types.h"
>  
>  struct xe_device;
> @@ -18,5 +20,7 @@ int xe_ras_get_counter(struct xe_device *xe, u8 severity, u8 component, u32 *val
>  int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component);
>  void xe_ras_init(struct xe_device *xe);
>  enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
> +void xe_emit_hardware_error_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigid,
> +				 struct xe_ras_error_class *error_class);
>  
>  #endif