drm/xe/xe_drm_ras: Wire get and clear counter callbacks

Hook CRI get-error-counter and clear-error-counter support to
xe_drm_ras to allow userspace to query and clear counters if supported.

Integrate this with xe_drm_ras.

Usage:

Query all error counter value using ynl

$ sudo ynl --family drm_ras --dump get-error-counter --json \
'{"node-id":0}'
[{'error-id': 1, 'error-name': 'core-compute', 'error-value': 0},
 {'error-id': 2, 'error-name': 'soc-internal', 'error-value': 0},
 {'error-id': 3, 'error-name': 'device-memory', 'error-value': 0},
 {'error-id': 4, 'error-name': 'pcie', 'error-value': 0},
 {'error-id': 5, 'error-name': 'fabric', 'error-value': 0}]

Query single error counter value using ynl

$ sudo ynl --family drm_ras  --do get-error-counter --json \
'{"node-id":1, "error-id":1}'
{'error-id': 1, 'error-name': 'core-compute', 'error-value': 2}

Clear counter using ynl

$ sudo ynl --family drm_ras  --do clear-error-counter --json '\
{"node-id":1, "error-id":1}'
None

Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://patch.msgid.link/20260618060633.2790109-12-riana.tauro@intel.com
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
This commit is contained in:
Riana Tauro 2026-06-18 11:36:38 +05:30
parent 2801adbd34
commit 2f02918ab2

View File

@ -11,27 +11,46 @@
#include "xe_device_types.h"
#include "xe_drm_ras.h"
#include "xe_ras.h"
static const char * const error_components[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES;
static const char * const error_severity[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES;
static int hw_query_error_counter(struct xe_drm_ras_counter *info,
u32 error_id, const char **name, u32 *val)
static int query_error_counter(struct xe_device *xe,
enum drm_xe_ras_error_severity severity,
u32 error_id, const char **name, u32 *val)
{
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[severity];
if (!info || !info[error_id].name)
return -ENOENT;
*name = info[error_id].name;
/* Fetch counter from system controller if supported */
if (xe->info.has_sysctrl)
return xe_ras_get_counter(xe, severity, error_id, val);
*val = atomic_read(&info[error_id].counter);
return 0;
}
static int hw_clear_error_counter(struct xe_drm_ras_counter *info, u32 error_id)
static int clear_error_counter(struct xe_device *xe,
enum drm_xe_ras_error_severity severity,
u32 error_id)
{
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[severity];
if (!info || !info[error_id].name)
return -ENOENT;
/* Clear counter from system controller if supported */
if (xe->info.has_sysctrl)
return xe_ras_clear_counter(xe, severity, error_id);
atomic_set(&info[error_id].counter, 0);
return 0;
@ -41,38 +60,30 @@ static int query_uncorrectable_error_counter(struct drm_ras_node *ep, u32 error_
const char **name, u32 *val)
{
struct xe_device *xe = ep->priv;
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_UNCORRECTABLE];
return hw_query_error_counter(info, error_id, name, val);
return query_error_counter(xe, DRM_XE_RAS_ERR_SEV_UNCORRECTABLE, error_id, name, val);
}
static int clear_uncorrectable_error_counter(struct drm_ras_node *node, u32 error_id)
{
struct xe_device *xe = node->priv;
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_UNCORRECTABLE];
return hw_clear_error_counter(info, error_id);
return clear_error_counter(xe, DRM_XE_RAS_ERR_SEV_UNCORRECTABLE, error_id);
}
static int query_correctable_error_counter(struct drm_ras_node *ep, u32 error_id,
const char **name, u32 *val)
{
struct xe_device *xe = ep->priv;
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_CORRECTABLE];
return hw_query_error_counter(info, error_id, name, val);
return query_error_counter(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id, name, val);
}
static int clear_correctable_error_counter(struct drm_ras_node *node, u32 error_id)
{
struct xe_device *xe = node->priv;
struct xe_drm_ras *ras = &xe->ras;
struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_CORRECTABLE];
return hw_clear_error_counter(info, error_id);
return clear_error_counter(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id);
}
static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *xe)