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]>
---
v3:
- Use PUNIT instead of PMU. (Riana)
- Use consistent wordingi.
- Remove log. (Raag)

v4:
- Make function static. (Raag)

v5:
- Remove kdoc for static function. (Raag)
- Remove xe_ prefix for static function.
---
 drivers/gpu/drm/xe/xe_ras.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index d79f8a6589ac..604470565bf3 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -4,6 +4,8 @@
  */
 
 #include "xe_bo.h"
+#include "xe_assert.h"
+#include "xe_device_types.h"
 #include "xe_device.h"
 #include "xe_printk.h"
 #include "xe_ras.h"
@@ -222,6 +224,12 @@ static enum xe_ras_recovery_action 
handle_core_compute_errors(struct xe_device *
        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 enum xe_ras_recovery_action handle_soc_internal_errors(struct xe_device 
*xe,
                                                              struct 
xe_ras_error_array *arr)
 {
@@ -265,7 +273,7 @@ static enum xe_ras_recovery_action 
handle_soc_internal_errors(struct xe_device *
                        xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",
                               sev_to_str(error_class->common.severity),
                               ieh_error->global_error_status);
-                       /* TODO: Add PUNIT error handling */
+                       punit_error_handler(xe);
                        return XE_RAS_RECOVERY_ACTION_DISCONNECT;
                }
        }
-- 
2.34.1

Reply via email to