github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-13 05:04:29 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/xe: Handle PUNIT errors by requesting cold-reset recovery

Browse Source 
When PUNIT (power management unit) errors are detected that persist across
warm resets, mark the device as wedged with DRM_WEDGE_RECOVERY_COLD_RESET
and notify userspace that a complete device power cycle is required to
restore normal operation.

Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://patch.msgid.link/20260805071152.1225416-9-mallesh.koujalagi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
This commit is contained in:
Mallesh Koujalagi 2026-08-05 12:41:56 +05:30 committed by Rodrigo Vivi
parent 048364a21a
commit 9b00f61536
No known key found for this signature in database
GPG Key ID: FA625F640EEB13CA
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
drivers/gpu/drm/xe/xe_ras.c
View File

@ -306,6 +306,12 @@ static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
return XE_RAS_RECOVERY_ACTION_RECOVERED;
}
static void punit_error_handler(struct xe_device *xe)
{
xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_COLD_RESET);
xe_device_declare_wedged(xe);
}
static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
{
struct xe_ras_soc_error *info = (void *)arr->details;
@ -337,7 +343,7 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",
sev_to_str(counter->common.severity),
ieh_error->global_error_status);
/* TODO: Add PUNIT error handling */
punit_error_handler(xe);
return XE_RAS_RECOVERY_ACTION_DISCONNECT;
}
}