drm/xe/xe_hw_error: Add fault injection to trigger csc error handler

Add a debugfs fault handler to trigger csc error handler that
wedges the device and enables runtime survivability mode.

v2: add debugfs only for bmg (Umesh)
v3: do not use csc_fault attribute if debugfs is not enabled
v4: rebase

Cc: Lucas De Marchi <[e-mail]>
Signed-off-by: Riana Tauro <[e-mail]>
Reviewed-by: Raag Jadav <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Rodrigo Vivi <[e-mail]>

drivers/gpu/drm/xe/xe_debugfs.c

···
 #endif
 
 DECLARE_FAULT_ATTR(gt_reset_failure);
+DECLARE_FAULT_ATTR(inject_csc_hw_error);
 
 static void read_residency_counter(struct xe_device *xe, struct xe_mmio *mmio,
 				   u32 offset, char *name, struct drm_printer *p)
···
 				 ARRAY_SIZE(debugfs_list),
 				 root, minor);
 
-	if (xe->info.platform == XE_BATTLEMAGE)
+	if (xe->info.platform == XE_BATTLEMAGE) {
 		drm_debugfs_create_files(debugfs_residencies,
 					 ARRAY_SIZE(debugfs_residencies),
 					 root, minor);
+		fault_create_debugfs_attr("inject_csc_hw_error", root,
+					  &inject_csc_hw_error);
+	}
 
 	debugfs_create_file("forcewake_all", 0400, root, xe,
 			    &forcewake_all_fops);

drivers/gpu/drm/xe/xe_hw_error.c

···
  * Copyright © 2025 Intel Corporation
  */
 
+#include <linux/fault-inject.h>
+
 #include "regs/xe_gsc_regs.h"
 #include "regs/xe_hw_error_regs.h"
 #include "regs/xe_irq_regs.h"
···
 #include "xe_survivability_mode.h"
 
 #define  HEC_UNCORR_FW_ERR_BITS 4
+extern struct fault_attr inject_csc_hw_error;
 
 /* Error categories reported by hardware */
 enum hardware_error {
···
 	default:
 		return "UNKNOWN";
 	}
+}
+
+static bool fault_inject_csc_hw_error(void)
+{
+	return IS_ENABLED(CONFIG_DEBUG_FS) && should_fail(&inject_csc_hw_error, 1);
 }
 
 static void csc_hw_error_work(struct work_struct *work)
···
 void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl)
 {
 	enum hardware_error hw_err;
+
+	if (fault_inject_csc_hw_error())
+		schedule_work(&tile->csc_hw_error_work);
 
 	for (hw_err = 0; hw_err < HARDWARE_ERROR_MAX; hw_err++)
 		if (master_ctl & ERROR_IRQ(hw_err))