[PATCH 3/4] drm/xe: Add handler for critical errors which require cold-reset

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

This handler is designed to be called when critical errors are detected
that affect device-level state persisting across warm resets. The cold
reset recovery method signals to userspace that only a complete device
power cycle can restore normal operation.

Signed-off-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
---
 drivers/gpu/drm/xe/xe_hw_error.c | 28 ++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_hw_error.h |  1 +
 2 files changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 8c65291f36fc..d7825d6b9703 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -5,6 +5,8 @@
 
 #include <linux/fault-inject.h>
 
+#include <drm/drm_drv.h>
+
 #include "regs/xe_gsc_regs.h"
 #include "regs/xe_hw_error_regs.h"
 #include "regs/xe_irq_regs.h"
@@ -162,6 +164,32 @@ static void process_hw_errors(struct xe_device *xe)
 	}
 }
 
+/**
+ * xe_critical_error_handler - Handler for critical errors
+ * @xe: device instance
+ *
+ * Handles critical 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 complete device power cycle is required.
+ */
+void xe_critical_error_handler(struct xe_device *xe)
+{
+	drm_err(&xe->drm, "CRITICAL: error detected\n");
+	drm_err(&xe->drm, "Recovery: Device cold reset required\n");
+
+	/* Set cold reset recovery method */
+	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_COLD_RESET);
+
+	if (xe_device_wedged(xe)) {
+		drm_dev_wedged_event(&xe->drm, xe->wedged.method, NULL);
+	} else {
+		/* Declare device wedged - will trigger uevent with cold reset method */
+		xe_device_declare_wedged(xe);
+	}
+}
+
 /**
  * xe_hw_error_init - Initialize hw errors
  * @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_hw_error.h b/drivers/gpu/drm/xe/xe_hw_error.h
index d86e28c5180c..f824e22655a0 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.h
+++ b/drivers/gpu/drm/xe/xe_hw_error.h
@@ -11,5 +11,6 @@ struct xe_tile;
 struct xe_device;
 
 void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl);
+void xe_critical_error_handler(struct xe_device *xe);
 void xe_hw_error_init(struct xe_device *xe);
 #endif
-- 
2.34.1