[PATCH v3 4/4] drm/xe: Handle PUNIT errors by requesting cold-reset recovery

[Mallesh Koujalagi <mallesh.koujalagi@intel.com>]

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 cold reset is required to
restore normal operation.

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

Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
---
 drivers/gpu/drm/xe/xe_ras.c | 21 ++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_ras.h |  1 +
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 437811845c01..e2e1ab3fb4ce 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -5,6 +5,7 @@
 
 #include "xe_assert.h"
 #include "xe_device_types.h"
+#include "xe_device.h"
 #include "xe_printk.h"
 #include "xe_ras.h"
 #include "xe_ras_types.h"
@@ -93,6 +94,24 @@ static enum xe_ras_recovery_action handle_compute_errors(struct xe_device *xe,
 	return XE_RAS_RECOVERY_ACTION_RECOVERED;
 }
 
+/**
+ * xe_punit_error_handler - Handler for Punit errors requiring cold reset
+ * @xe: device instance
+ *
+ * Handles Punit errors that affect the device and cannot be recovered
+ * through driver reload, PCIe reset, etc.
+ *
+ * Marks the device as wedged with DRM_WEDGE_RECOVERY_COLD_RESET method
+ * and notifies userspace that a device cold reset is required.
+ */
+void xe_punit_error_handler(struct xe_device *xe)
+{
+	xe_err(xe, "Recovery: Device cold reset required\n");
+
+	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)
 {
@@ -132,7 +151,7 @@ static enum xe_ras_recovery_action handle_soc_internal_errors(struct xe_device *
 			xe_err(xe, "[RAS]: PUNIT %s error detected: 0x%x\n",
 			       severity_to_str(xe, common.severity),
 			       ieh_error->global_error_status);
-			/** TODO: Add PUNIT error handling */
+			xe_punit_error_handler(xe);
 			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
index e191ab80080c..ab1fde200625 100644
--- a/drivers/gpu/drm/xe/xe_ras.h
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -11,6 +11,7 @@
 struct xe_device;
 
 void xe_ras_init(struct xe_device *xe);
+void xe_punit_error_handler(struct xe_device *xe);
 enum xe_ras_recovery_action  xe_ras_process_errors(struct xe_device *xe);
 
 #endif
-- 
2.34.1