[PATCH v4] drm/xe: Add helper function to inject fault into ct_dead_capture()

[Satyanarayana K V P]

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 at intel.com>
Suggested-by: John Harrison <John.C.Harrison at Intel.com>
---
Cc: Michal Wajdeczko <michal.wajdeczko at intel.com>
Cc: Jani Nikula <jani.nikula at intel.com>

V3 -> V4:
- Updated the name of helper function and moved to xe_device.h file.

V2 -> V3:
- Added inline function to avoid compilation error in the absence of
CONFIG_FUNCTION_ERROR_INJECTION.

V1 -> V2:
- Fixed review comments.
---
 drivers/gpu/drm/xe/xe_device.h | 18 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_ct.c |  6 ++++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 0bc3bc8e6803..b937d585083b 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -195,6 +195,24 @@ 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);
 
+/**
+ * is_injection_active() - Helper function to inject fault.
+ *
+ * This is a helper function to inject fault into ct_dead_capture().
+ * As fault is injected using this function, need to make sure that
+ * the compiler does not optimize and make it as a inline function.
+ * To prevent compile optimization, "noinline" is added.
+ */
+#ifdef CONFIG_FUNCTION_ERROR_INJECTION
+static noinline int xe_is_injection_active(void)
+{
+	        return 0;
+}
+ALLOW_ERROR_INJECTION(xe_is_injection_active, ERRNO);
+#else
+static inline int xe_is_injection_active(void) { return 0; }
+#endif
+
 /*
  * 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 ff6edf1b14f4..a6964d13f3a3 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1963,6 +1963,12 @@ 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)
-- 
2.43.0