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 <lucas.demarchi@intel.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-11-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index bc717519502ddccdb87aa1df6b089d22803a34e8..8d6df6bd885e4363c72449c1e39b1de3848f92a8 100644 (file)
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -35,6 +35,7 @@
 #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)
@@ -361,10 +362,13 @@ void xe_debugfs_register(struct xe_device *xe)
                                 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);

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 4099ed1262e1dc93cb67295747b5a2157ad10c17..8c65291f36fc006d7fbd06781f49149e4c1774e4 100644 (file)
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -3,6 +3,8 @@
  * 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"
@@ -13,6 +15,7 @@
 #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 {
@@ -43,6 +46,11 @@ static const char *hw_error_to_str(const enum hardware_error hw_err)
        }
 }
 
+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)
 {
        struct xe_tile *tile = container_of(work, typeof(*tile), csc_hw_error_work);
@@ -130,6 +138,9 @@ 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))
                        hw_error_source_handler(tile, hw_err);