drm/xe: Add helper function to inject fault into ct_dead_capture()

When injecting fault to xe_guc_ct_send_recv() & xe_guc_mmio_send_recv()
functions, the CI test systems are going out of space and crashing. To
avoid this issue, a new helper function is created and when fault is
injected into this xe_is_injection_active() helper function, ct dead
capture is avoided which suppresses ct dumps in the log.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Suggested-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://lore.kernel.org/r/20250612080402.22011-1-satyanarayana.k.v.p@intel.com

diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 0bc3bc8e680309319261140122c02974547066d7..e4da797a984b59b41f4d0441538ac7edb9f1a64c 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -195,6 +195,8 @@ void xe_device_declare_wedged(struct xe_device *xe);
 struct xe_file *xe_file_get(struct xe_file *xef);
 void xe_file_put(struct xe_file *xef);
 
+int xe_is_injection_active(void);
+
 /*
  * Occasionally it is seen that the G2H worker starts running after a delay of more than
  * a second even after being queued and activated by the Linux workqueue subsystem. This

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index e303fec1817475a72645162192eacd7ed3737034..37509f619503553ec9bb2dd1d3e0027a6ded4a6b 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -2033,6 +2033,24 @@ void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb)
 }
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+
+#ifdef CONFIG_FUNCTION_ERROR_INJECTION
+/*
+ * This is a helper function which assists the driver in identifying if a fault
+ * injection test is currently active, allowing it to reduce unnecessary debug
+ * output. Typically, the function returns zero, but the fault injection
+ * framework can alter this to return an error. Since faults are injected
+ * through this function, it's important to ensure the compiler doesn't optimize
+ * it into an inline function. To avoid such optimization, the 'noinline'
+ * attribute is applied. Compiler optimizes the static function defined in the
+ * header file as an inline function.
+ */
+noinline int xe_is_injection_active(void) { return 0; }
+ALLOW_ERROR_INJECTION(xe_is_injection_active, ERRNO);
+#else
+int xe_is_injection_active(void) { return 0; }
+#endif
+
 static void ct_dead_capture(struct xe_guc_ct *ct, struct guc_ctb *ctb, u32 reason_code)
 {
        struct xe_guc_log_snapshot *snapshot_log;
@@ -2043,6 +2061,12 @@ static void ct_dead_capture(struct xe_guc_ct *ct, struct guc_ctb *ctb, u32 reaso
 
        if (ctb)
                ctb->info.broken = true;
+       /*
+        * Huge dump is getting generated when injecting error for guc CT/MMIO
+        * functions. So, let us suppress the dump when fault is injected.
+        */
+       if (xe_is_injection_active())
+               return;
 
        /* Ignore further errors after the first dump until a reset */
        if (ct->dead.reported)