[PATCH v13 3/4] drm/xe: Handle PUNIT errors by requesting cold-reset recovery

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 <[email protected]>
Reviewed-by: Raag Jadav <[email protected]>
---
v3:
- Use PUNIT instead of PMU. (Riana)
- Use consistent wording.
- Remove log. (Raag)

v4:
- Make function static. (Raag)

v5:
- Remove kdoc for static function. (Raag)
- Remove xe_ prefix for static function.

v9:
- Remove unwanted header. (Sashiko)
---
 drivers/gpu/drm/xe/xe_ras.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 352f056fd9ef..3033a377bace 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -254,6 +254,12 @@ 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;
@@ -285,7 +291,7 @@ 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;
 		}
 	}
-- 
2.48.1